diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index 78c26280c473..1468609052c7 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -514,6 +514,7 @@ Description: information about CPUs heterogeneity. What: /sys/devices/system/cpu/vulnerabilities /sys/devices/system/cpu/vulnerabilities/gather_data_sampling + /sys/devices/system/cpu/vulnerabilities/indirect_target_selection /sys/devices/system/cpu/vulnerabilities/itlb_multihit /sys/devices/system/cpu/vulnerabilities/l1tf /sys/devices/system/cpu/vulnerabilities/mds diff --git a/Documentation/admin-guide/hw-vuln/index.rst b/Documentation/admin-guide/hw-vuln/index.rst index 3e4a14e38b49..dc69ba0b05e4 100644 --- a/Documentation/admin-guide/hw-vuln/index.rst +++ b/Documentation/admin-guide/hw-vuln/index.rst @@ -22,3 +22,4 @@ are configurable at compile, boot or run time. gather_data_sampling.rst srso reg-file-data-sampling + indirect-target-selection diff --git a/Documentation/admin-guide/hw-vuln/indirect-target-selection.rst b/Documentation/admin-guide/hw-vuln/indirect-target-selection.rst new file mode 100644 index 000000000000..4788e14ebce0 --- /dev/null +++ b/Documentation/admin-guide/hw-vuln/indirect-target-selection.rst @@ -0,0 +1,156 @@ +.. SPDX-License-Identifier: GPL-2.0 + +Indirect Target Selection (ITS) +=============================== + +ITS is a vulnerability in some Intel CPUs that support Enhanced IBRS and were +released before Alder Lake. ITS may allow an attacker to control the prediction +of indirect branches and RETs located in the lower half of a cacheline. + +ITS is assigned CVE-2024-28956 with a CVSS score of 4.7 (Medium). + +Scope of Impact +--------------- +- **eIBRS Guest/Host Isolation**: Indirect branches in KVM/kernel may still be + predicted with unintended target corresponding to a branch in the guest. + +- **Intra-Mode BTI**: In-kernel training such as through cBPF or other native + gadgets. + +- **Indirect Branch Prediction Barrier (IBPB)**: After an IBPB, indirect + branches may still be predicted with targets corresponding to direct branches + executed prior to the IBPB. This is fixed by the IPU 2025.1 microcode, which + should be available via distro updates. Alternatively microcode can be + obtained from Intel's github repository [#f1]_. + +Affected CPUs +------------- +Below is the list of ITS affected CPUs [#f2]_ [#f3]_: + + ======================== ============ ==================== =============== + Common name Family_Model eIBRS Intra-mode BTI + Guest/Host Isolation + ======================== ============ ==================== =============== + SKYLAKE_X (step >= 6) 06_55H Affected Affected + ICELAKE_X 06_6AH Not affected Affected + ICELAKE_D 06_6CH Not affected Affected + ICELAKE_L 06_7EH Not affected Affected + TIGERLAKE_L 06_8CH Not affected Affected + TIGERLAKE 06_8DH Not affected Affected + KABYLAKE_L (step >= 12) 06_8EH Affected Affected + KABYLAKE (step >= 13) 06_9EH Affected Affected + COMETLAKE 06_A5H Affected Affected + COMETLAKE_L 06_A6H Affected Affected + ROCKETLAKE 06_A7H Not affected Affected + ======================== ============ ==================== =============== + +- All affected CPUs enumerate Enhanced IBRS feature. +- IBPB isolation is affected on all ITS affected CPUs, and need a microcode + update for mitigation. +- None of the affected CPUs enumerate BHI_CTRL which was introduced in Golden + Cove (Alder Lake and Sapphire Rapids). This can help guests to determine the + host's affected status. +- Intel Atom CPUs are not affected by ITS. + +Mitigation +---------- +As only the indirect branches and RETs that have their last byte of instruction +in the lower half of the cacheline are vulnerable to ITS, the basic idea behind +the mitigation is to not allow indirect branches in the lower half. + +This is achieved by relying on existing retpoline support in the kernel, and in +compilers. ITS-vulnerable retpoline sites are runtime patched to point to newly +added ITS-safe thunks. These safe thunks consists of indirect branch in the +second half of the cacheline. Not all retpoline sites are patched to thunks, if +a retpoline site is evaluated to be ITS-safe, it is replaced with an inline +indirect branch. + +Dynamic thunks +~~~~~~~~~~~~~~ +From a dynamically allocated pool of safe-thunks, each vulnerable site is +replaced with a new thunk, such that they get a unique address. This could +improve the branch prediction accuracy. Also, it is a defense-in-depth measure +against aliasing. + +Note, for simplicity, indirect branches in eBPF programs are always replaced +with a jump to a static thunk in __x86_indirect_its_thunk_array. If required, +in future this can be changed to use dynamic thunks. + +All vulnerable RETs are replaced with a static thunk, they do not use dynamic +thunks. This is because RETs get their prediction from RSB mostly that does not +depend on source address. RETs that underflow RSB may benefit from dynamic +thunks. But, RETs significantly outnumber indirect branches, and any benefit +from a unique source address could be outweighed by the increased icache +footprint and iTLB pressure. + +Retpoline +~~~~~~~~~ +Retpoline sequence also mitigates ITS-unsafe indirect branches. For this +reason, when retpoline is enabled, ITS mitigation only relocates the RETs to +safe thunks. Unless user requested the RSB-stuffing mitigation. + +Mitigation in guests +^^^^^^^^^^^^^^^^^^^^ +All guests deploy ITS mitigation by default, irrespective of eIBRS enumeration +and Family/Model of the guest. This is because eIBRS feature could be hidden +from a guest. One exception to this is when a guest enumerates BHI_DIS_S, which +indicates that the guest is running on an unaffected host. + +To prevent guests from unnecessarily deploying the mitigation on unaffected +platforms, Intel has defined ITS_NO bit(62) in MSR IA32_ARCH_CAPABILITIES. When +a guest sees this bit set, it should not enumerate the ITS bug. Note, this bit +is not set by any hardware, but is **intended for VMMs to synthesize** it for +guests as per the host's affected status. + +Mitigation options +^^^^^^^^^^^^^^^^^^ +The ITS mitigation can be controlled using the "indirect_target_selection" +kernel parameter. The available options are: + + ======== =================================================================== + on (default) Deploy the "Aligned branch/return thunks" mitigation. + If spectre_v2 mitigation enables retpoline, aligned-thunks are only + deployed for the affected RET instructions. Retpoline mitigates + indirect branches. + + off Disable ITS mitigation. + + vmexit Equivalent to "=on" if the CPU is affected by guest/host isolation + part of ITS. Otherwise, mitigation is not deployed. This option is + useful when host userspace is not in the threat model, and only + attacks from guest to host are considered. + + force Force the ITS bug and deploy the default mitigation. + ======== =================================================================== + +Sysfs reporting +--------------- + +The sysfs file showing ITS mitigation status is: + + /sys/devices/system/cpu/vulnerabilities/indirect_target_selection + +Note, microcode mitigation status is not reported in this file. + +The possible values in this file are: + +.. list-table:: + + * - Not affected + - The processor is not vulnerable. + * - Vulnerable + - System is vulnerable and no mitigation has been applied. + * - Vulnerable, KVM: Not affected + - System is vulnerable to intra-mode BTI, but not affected by eIBRS + guest/host isolation. + * - Mitigation: Aligned branch/return thunks + - The mitigation is enabled, affected indirect branches and RETs are + relocated to safe thunks. + +References +---------- +.. [#f1] Microcode repository - https://github.com/intel/Intel-Linux-Processor-Microcode-Data-Files + +.. [#f2] Affected Processors list - https://www.intel.com/content/www/us/en/developer/topic-technology/software-security-guidance/processors-affected-consolidated-product-cpu-model.html + +.. [#f3] Affected Processors list (machine readable) - https://github.com/intel/Intel-affected-processor-list diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 6593773a512d..2a0ef23bf227 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2048,6 +2048,20 @@ different crypto accelerators. This option can be used to achieve best performance for particular HW. + indirect_target_selection= [X86,Intel] Mitigation control for Indirect + Target Selection(ITS) bug in Intel CPUs. Updated + microcode is also required for a fix in IBPB. + + on: Enable mitigation (default). + off: Disable mitigation. + force: Force the ITS bug and deploy default + mitigation. + vmexit: Only deploy mitigation if CPU is affected by + guest/host isolation part of ITS. + + For details see: + Documentation/admin-guide/hw-vuln/indirect-target-selection.rst + init= [KNL] Format: Run specified binary instead of /sbin/init as init @@ -3311,6 +3325,7 @@ expose users to several CPU vulnerabilities. Equivalent to: if nokaslr then kpti=0 [ARM64] gather_data_sampling=off [X86] + indirect_target_selection=off [X86] kvm.nx_huge_pages=off [X86] l1tf=off [X86] mds=off [X86] @@ -5833,6 +5848,8 @@ Selecting 'on' will also enable the mitigation against user space to user space task attacks. + Selecting specific mitigation does not force enable + user mitigations. Selecting 'off' will disable both the kernel and the user space protections. diff --git a/Documentation/hwmon/dell-smm-hwmon.rst b/Documentation/hwmon/dell-smm-hwmon.rst index d8f1d6859b96..1c12fbba440b 100644 --- a/Documentation/hwmon/dell-smm-hwmon.rst +++ b/Documentation/hwmon/dell-smm-hwmon.rst @@ -32,12 +32,12 @@ Temperature sensors and fans can be queried and set via the standard =============================== ======= ======================================= Name Perm Description =============================== ======= ======================================= -fan[1-3]_input RO Fan speed in RPM. -fan[1-3]_label RO Fan label. -fan[1-3]_min RO Minimal Fan speed in RPM -fan[1-3]_max RO Maximal Fan speed in RPM -fan[1-3]_target RO Expected Fan speed in RPM -pwm[1-3] RW Control the fan PWM duty-cycle. +fan[1-4]_input RO Fan speed in RPM. +fan[1-4]_label RO Fan label. +fan[1-4]_min RO Minimal Fan speed in RPM +fan[1-4]_max RO Maximal Fan speed in RPM +fan[1-4]_target RO Expected Fan speed in RPM +pwm[1-4] RW Control the fan PWM duty-cycle. pwm1_enable WO Enable or disable automatic BIOS fan control (not supported on all laptops, see below for details). @@ -93,7 +93,7 @@ Again, when you find new codes, we'd be happy to have your patches! --------------------------- The driver also exports the fans as thermal cooling devices with -``type`` set to ``dell-smm-fan[1-3]``. This allows for easy fan control +``type`` set to ``dell-smm-fan[1-4]``. This allows for easy fan control using one of the thermal governors. Module parameters diff --git a/Makefile b/Makefile index 93a14eaf4a5f..f4bd6a179b21 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 1 -SUBLEVEL = 138 +SUBLEVEL = 141 EXTRAVERSION = NAME = Curry Ramen @@ -895,6 +895,18 @@ ifdef CONFIG_CC_IS_CLANG KBUILD_CPPFLAGS += -Qunused-arguments # The kernel builds with '-std=gnu11' so use of GNU extensions is acceptable. KBUILD_CFLAGS += -Wno-gnu + +# Clang may emit a warning when a const variable, such as the dummy variables +# in typecheck(), or const member of an aggregate type are not initialized, +# which can result in unexpected behavior. However, in many audited cases of +# the "field" variant of the warning, this is intentional because the field is +# never used within a particular call path, the field is within a union with +# other non-const members, or the containing object is not const so the field +# can be modified via memcpy() / memset(). While the variable warning also gets +# disabled with this same switch, there should not be too much coverage lost +# because -Wuninitialized will still flag when an uninitialized const variable +# is used. +KBUILD_CFLAGS += $(call cc-disable-warning, default-const-init-unsafe) else # gcc inanely warns about local variables called 'main' diff --git a/arch/arm/boot/dts/tegra114.dtsi b/arch/arm/boot/dts/tegra114.dtsi index 09996acad639..bb23bb39dd5b 100644 --- a/arch/arm/boot/dts/tegra114.dtsi +++ b/arch/arm/boot/dts/tegra114.dtsi @@ -139,7 +139,7 @@ reg = <0x54400000 0x00040000>; clocks = <&tegra_car TEGRA114_CLK_DSIB>, <&tegra_car TEGRA114_CLK_DSIBLP>, - <&tegra_car TEGRA114_CLK_PLL_D2_OUT0>; + <&tegra_car TEGRA114_CLK_PLL_D_OUT0>; clock-names = "dsi", "lp", "parent"; resets = <&tegra_car 82>; reset-names = "dsi"; diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c index 4d0d0d49a744..77aec670f635 100644 --- a/arch/arm/mach-at91/pm.c +++ b/arch/arm/mach-at91/pm.c @@ -537,11 +537,12 @@ extern u32 at91_pm_suspend_in_sram_sz; static int at91_suspend_finish(unsigned long val) { - unsigned char modified_gray_code[] = { - 0x00, 0x01, 0x02, 0x03, 0x06, 0x07, 0x04, 0x05, 0x0c, 0x0d, - 0x0e, 0x0f, 0x0a, 0x0b, 0x08, 0x09, 0x18, 0x19, 0x1a, 0x1b, - 0x1e, 0x1f, 0x1c, 0x1d, 0x14, 0x15, 0x16, 0x17, 0x12, 0x13, - 0x10, 0x11, + /* SYNOPSYS workaround to fix a bug in the calibration logic */ + unsigned char modified_fix_code[] = { + 0x00, 0x01, 0x01, 0x06, 0x07, 0x0c, 0x06, 0x07, 0x0b, 0x18, + 0x0a, 0x0b, 0x0c, 0x0d, 0x0d, 0x0a, 0x13, 0x13, 0x12, 0x13, + 0x14, 0x15, 0x15, 0x12, 0x18, 0x19, 0x19, 0x1e, 0x1f, 0x14, + 0x1e, 0x1f, }; unsigned int tmp, index; int i; @@ -552,25 +553,25 @@ static int at91_suspend_finish(unsigned long val) * restore the ZQ0SR0 with the value saved here. But the * calibration is buggy and restoring some values from ZQ0SR0 * is forbidden and risky thus we need to provide processed - * values for these (modified gray code values). + * values for these. */ tmp = readl(soc_pm.data.ramc_phy + DDR3PHY_ZQ0SR0); /* Store pull-down output impedance select. */ index = (tmp >> DDR3PHY_ZQ0SR0_PDO_OFF) & 0x1f; - soc_pm.bu->ddr_phy_calibration[0] = modified_gray_code[index]; + soc_pm.bu->ddr_phy_calibration[0] = modified_fix_code[index] << DDR3PHY_ZQ0SR0_PDO_OFF; /* Store pull-up output impedance select. */ index = (tmp >> DDR3PHY_ZQ0SR0_PUO_OFF) & 0x1f; - soc_pm.bu->ddr_phy_calibration[0] |= modified_gray_code[index]; + soc_pm.bu->ddr_phy_calibration[0] |= modified_fix_code[index] << DDR3PHY_ZQ0SR0_PUO_OFF; /* Store pull-down on-die termination impedance select. */ index = (tmp >> DDR3PHY_ZQ0SR0_PDODT_OFF) & 0x1f; - soc_pm.bu->ddr_phy_calibration[0] |= modified_gray_code[index]; + soc_pm.bu->ddr_phy_calibration[0] |= modified_fix_code[index] << DDR3PHY_ZQ0SR0_PDODT_OFF; /* Store pull-up on-die termination impedance select. */ index = (tmp >> DDR3PHY_ZQ0SRO_PUODT_OFF) & 0x1f; - soc_pm.bu->ddr_phy_calibration[0] |= modified_gray_code[index]; + soc_pm.bu->ddr_phy_calibration[0] |= modified_fix_code[index] << DDR3PHY_ZQ0SRO_PUODT_OFF; /* * The 1st 8 words of memory might get corrupted in the process diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts b/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts index 381d58cea092..c854c7e31051 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts @@ -151,28 +151,12 @@ vcc-pg-supply = <®_aldo1>; }; -&r_ir { - linux,rc-map-name = "rc-beelink-gs1"; - status = "okay"; -}; - -&r_pio { - /* - * FIXME: We can't add that supply for now since it would - * create a circular dependency between pinctrl, the regulator - * and the RSB Bus. - * - * vcc-pl-supply = <®_aldo1>; - */ - vcc-pm-supply = <®_aldo1>; -}; - -&r_rsb { +&r_i2c { status = "okay"; - axp805: pmic@745 { + axp805: pmic@36 { compatible = "x-powers,axp805", "x-powers,axp806"; - reg = <0x745>; + reg = <0x36>; interrupt-parent = <&r_intc>; interrupts = ; interrupt-controller; @@ -290,6 +274,22 @@ }; }; +&r_ir { + linux,rc-map-name = "rc-beelink-gs1"; + status = "okay"; +}; + +&r_pio { + /* + * PL0 and PL1 are used for PMIC I2C + * don't enable the pl-supply else + * it will fail at boot + * + * vcc-pl-supply = <®_aldo1>; + */ + vcc-pm-supply = <®_aldo1>; +}; + &spdif { pinctrl-names = "default"; pinctrl-0 = <&spdif_tx_pin>; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi-3.dts b/arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi-3.dts index 6fc65e8db220..8c476e089185 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi-3.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi-3.dts @@ -175,16 +175,12 @@ vcc-pg-supply = <®_vcc_wifi_io>; }; -&r_ir { - status = "okay"; -}; - -&r_rsb { +&r_i2c { status = "okay"; - axp805: pmic@745 { + axp805: pmic@36 { compatible = "x-powers,axp805", "x-powers,axp806"; - reg = <0x745>; + reg = <0x36>; interrupt-parent = <&r_intc>; interrupts = ; interrupt-controller; @@ -295,6 +291,10 @@ }; }; +&r_ir { + status = "okay"; +}; + &rtc { clocks = <&ext_osc32k>; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi.dtsi index 92745128fcfe..4ec4996592be 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi.dtsi @@ -112,20 +112,12 @@ vcc-pg-supply = <®_aldo1>; }; -&r_ir { - status = "okay"; -}; - -&r_pio { - vcc-pm-supply = <®_bldo3>; -}; - -&r_rsb { +&r_i2c { status = "okay"; - axp805: pmic@745 { + axp805: pmic@36 { compatible = "x-powers,axp805", "x-powers,axp806"; - reg = <0x745>; + reg = <0x36>; interrupt-parent = <&r_intc>; interrupts = ; interrupt-controller; @@ -240,6 +232,14 @@ }; }; +&r_ir { + status = "okay"; +}; + +&r_pio { + vcc-pm-supply = <®_bldo3>; +}; + &rtc { clocks = <&ext_osc32k>; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi index a9bfcdf378ce..fb75800e8999 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi @@ -144,6 +144,19 @@ startup-delay-us = <20000>; }; + reg_usdhc2_vqmmc: regulator-usdhc2-vqmmc { + compatible = "regulator-gpio"; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_usdhc2_vsel>; + gpios = <&gpio1 4 GPIO_ACTIVE_HIGH>; + regulator-max-microvolt = <3300000>; + regulator-min-microvolt = <1800000>; + states = <1800000 0x1>, + <3300000 0x0>; + regulator-name = "PMIC_USDHC_VSELECT"; + vin-supply = <®_nvcc_sd>; + }; + reserved-memory { #address-cells = <2>; #size-cells = <2>; @@ -262,7 +275,7 @@ "SODIMM_19", "", "", - "", + "PMIC_USDHC_VSELECT", "", "", "", @@ -788,6 +801,7 @@ pinctrl-2 = <&pinctrl_usdhc2_200mhz>, <&pinctrl_usdhc2_cd>; pinctrl-3 = <&pinctrl_usdhc2_sleep>, <&pinctrl_usdhc2_cd_sleep>; vmmc-supply = <®_usdhc2_vmmc>; + vqmmc-supply = <®_usdhc2_vqmmc>; }; &wdog1 { @@ -1210,13 +1224,17 @@ ; /* SODIMM 76 */ }; + pinctrl_usdhc2_vsel: usdhc2vselgrp { + fsl,pins = + ; /* PMIC_USDHC_VSELECT */ + }; + /* * Note: Due to ERR050080 we use discrete external on-module resistors pulling-up to the * on-module +V3.3_1.8_SD (LDO5) rail and explicitly disable the internal pull-ups here. */ pinctrl_usdhc2: usdhc2grp { fsl,pins = - , , /* SODIMM 78 */ , /* SODIMM 74 */ , /* SODIMM 80 */ @@ -1227,7 +1245,6 @@ pinctrl_usdhc2_100mhz: usdhc2-100mhzgrp { fsl,pins = - , , , , @@ -1238,7 +1255,6 @@ pinctrl_usdhc2_200mhz: usdhc2-200mhzgrp { fsl,pins = - , , , , @@ -1250,7 +1266,6 @@ /* Avoid backfeeding with removed card power */ pinctrl_usdhc2_sleep: usdhc2slpgrp { fsl,pins = - , , , , diff --git a/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi b/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi index 634373a423ef..481a88d83a65 100644 --- a/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi @@ -1631,7 +1631,7 @@ regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; regulator-always-on; - gpio = <&exp1 14 GPIO_ACTIVE_HIGH>; + gpio = <&exp1 9 GPIO_ACTIVE_HIGH>; enable-active-high; vin-supply = <&vdd_1v8>; }; diff --git a/arch/arm64/boot/dts/qcom/sm8350.dtsi b/arch/arm64/boot/dts/qcom/sm8350.dtsi index 5a4972afc977..75292ec3ee77 100644 --- a/arch/arm64/boot/dts/qcom/sm8350.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8350.dtsi @@ -421,7 +421,7 @@ no-map; }; - pil_camera_mem: mmeory@85200000 { + pil_camera_mem: memory@85200000 { reg = <0x0 0x85200000 0x0 0x500000>; no-map; }; diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index cdb024dd33f5..41612b03af63 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -81,6 +81,7 @@ #define ARM_CPU_PART_CORTEX_A78AE 0xD42 #define ARM_CPU_PART_CORTEX_X1 0xD44 #define ARM_CPU_PART_CORTEX_A510 0xD46 +#define ARM_CPU_PART_CORTEX_X1C 0xD4C #define ARM_CPU_PART_CORTEX_A520 0xD80 #define ARM_CPU_PART_CORTEX_A710 0xD47 #define ARM_CPU_PART_CORTEX_A715 0xD4D @@ -131,6 +132,7 @@ #define FUJITSU_CPU_PART_A64FX 0x001 #define HISI_CPU_PART_TSV110 0xD01 +#define HISI_CPU_PART_HIP09 0xD02 #define APPLE_CPU_PART_M1_ICESTORM 0x022 #define APPLE_CPU_PART_M1_FIRESTORM 0x023 @@ -159,6 +161,7 @@ #define MIDR_CORTEX_A78AE MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE) #define MIDR_CORTEX_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1) #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510) +#define MIDR_CORTEX_X1C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1C) #define MIDR_CORTEX_A520 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A520) #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710) #define MIDR_CORTEX_A715 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A715) @@ -199,6 +202,7 @@ #define MIDR_NVIDIA_CARMEL MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_CARMEL) #define MIDR_FUJITSU_A64FX MIDR_CPU_MODEL(ARM_CPU_IMP_FUJITSU, FUJITSU_CPU_PART_A64FX) #define MIDR_HISI_TSV110 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_TSV110) +#define MIDR_HISI_HIP09 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_HIP09) #define MIDR_APPLE_M1_ICESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM) #define MIDR_APPLE_M1_FIRESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM) #define MIDR_APPLE_M1_ICESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_PRO) diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index 834bff720582..0075dc5d8238 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -619,6 +619,7 @@ u32 aarch64_insn_gen_cas(enum aarch64_insn_register result, } #endif u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type); +u32 aarch64_insn_gen_dsb(enum aarch64_insn_mb_type type); s32 aarch64_get_branch_offset(u32 insn); u32 aarch64_set_branch_offset(u32 insn, s32 offset); diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 01ce10d56b8a..444a1a2e80e5 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -681,7 +681,8 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd) pr_err("%s:%d: bad pmd %016llx.\n", __FILE__, __LINE__, pmd_val(e)) #define pud_none(pud) (!pud_val(pud)) -#define pud_bad(pud) (!pud_table(pud)) +#define pud_bad(pud) ((pud_val(pud) & PUD_TYPE_MASK) != \ + PUD_TYPE_TABLE) #define pud_present(pud) pte_present(pud_pte(pud)) #define pud_leaf(pud) (pud_present(pud) && !pud_table(pud)) #define pud_valid(pud) pte_valid(pud_pte(pud)) diff --git a/arch/arm64/include/asm/spectre.h b/arch/arm64/include/asm/spectre.h index 6f9f4f68b9e2..9de17d4bb036 100644 --- a/arch/arm64/include/asm/spectre.h +++ b/arch/arm64/include/asm/spectre.h @@ -96,6 +96,9 @@ enum mitigation_state arm64_get_meltdown_state(void); enum mitigation_state arm64_get_spectre_bhb_state(void); bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry, int scope); +extern bool __nospectre_bhb; +u8 get_spectre_bhb_loop_value(void); +bool is_spectre_bhb_fw_mitigated(void); void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *__unused); #endif /* __ASSEMBLY__ */ #endif /* __ASM_SPECTRE_H */ diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 43afe07c74fd..3a08c7609d1e 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1234,8 +1234,10 @@ void fpsimd_release_task(struct task_struct *dead_task) */ void sme_alloc(struct task_struct *task, bool flush) { - if (task->thread.za_state && flush) { - memset(task->thread.za_state, 0, za_state_size(task)); + if (task->thread.za_state) { + if (flush) + memset(task->thread.za_state, 0, + za_state_size(task)); return; } diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index 3d12fc5af87b..4978c466e325 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -903,6 +903,7 @@ static u8 spectre_bhb_loop_affected(void) MIDR_ALL_VERSIONS(MIDR_CORTEX_A78AE), MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C), MIDR_ALL_VERSIONS(MIDR_CORTEX_X1), + MIDR_ALL_VERSIONS(MIDR_CORTEX_X1C), MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), MIDR_ALL_VERSIONS(MIDR_CORTEX_X2), MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), @@ -915,6 +916,7 @@ static u8 spectre_bhb_loop_affected(void) MIDR_ALL_VERSIONS(MIDR_CORTEX_A77), MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1), MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_GOLD), + MIDR_ALL_VERSIONS(MIDR_HISI_HIP09), {}, }; static const struct midr_range spectre_bhb_k11_list[] = { @@ -1010,6 +1012,11 @@ bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry, return true; } +u8 get_spectre_bhb_loop_value(void) +{ + return max_bhb_k; +} + static void this_cpu_set_vectors(enum arm64_bp_harden_el1_vectors slot) { const char *v = arm64_get_bp_hardening_vector(slot); @@ -1030,7 +1037,7 @@ static void this_cpu_set_vectors(enum arm64_bp_harden_el1_vectors slot) isb(); } -static bool __read_mostly __nospectre_bhb; +bool __read_mostly __nospectre_bhb; static int __init parse_spectre_bhb_param(char *str) { __nospectre_bhb = true; @@ -1108,6 +1115,11 @@ void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *entry) update_mitigation_state(&spectre_bhb_state, state); } +bool is_spectre_bhb_fw_mitigated(void) +{ + return test_bit(BHB_FW, &system_bhb_mitigations); +} + /* Patched to NOP when enabled */ void noinstr spectre_bhb_patch_loop_mitigation_enable(struct alt_instr *alt, __le32 *origptr, diff --git a/arch/arm64/lib/insn.c b/arch/arm64/lib/insn.c index 49e972beeac7..44bb90ee2f41 100644 --- a/arch/arm64/lib/insn.c +++ b/arch/arm64/lib/insn.c @@ -5,6 +5,7 @@ * * Copyright (C) 2014-2016 Zi Shen Lim */ +#include #include #include #include @@ -1630,43 +1631,41 @@ u32 aarch64_insn_gen_extr(enum aarch64_insn_variant variant, return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RM, insn, Rm); } +static u32 __get_barrier_crm_val(enum aarch64_insn_mb_type type) +{ + switch (type) { + case AARCH64_INSN_MB_SY: + return 0xf; + case AARCH64_INSN_MB_ST: + return 0xe; + case AARCH64_INSN_MB_LD: + return 0xd; + case AARCH64_INSN_MB_ISH: + return 0xb; + case AARCH64_INSN_MB_ISHST: + return 0xa; + case AARCH64_INSN_MB_ISHLD: + return 0x9; + case AARCH64_INSN_MB_NSH: + return 0x7; + case AARCH64_INSN_MB_NSHST: + return 0x6; + case AARCH64_INSN_MB_NSHLD: + return 0x5; + default: + pr_err("%s: unknown barrier type %d\n", __func__, type); + return AARCH64_BREAK_FAULT; + } +} + u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type) { u32 opt; u32 insn; - switch (type) { - case AARCH64_INSN_MB_SY: - opt = 0xf; - break; - case AARCH64_INSN_MB_ST: - opt = 0xe; - break; - case AARCH64_INSN_MB_LD: - opt = 0xd; - break; - case AARCH64_INSN_MB_ISH: - opt = 0xb; - break; - case AARCH64_INSN_MB_ISHST: - opt = 0xa; - break; - case AARCH64_INSN_MB_ISHLD: - opt = 0x9; - break; - case AARCH64_INSN_MB_NSH: - opt = 0x7; - break; - case AARCH64_INSN_MB_NSHST: - opt = 0x6; - break; - case AARCH64_INSN_MB_NSHLD: - opt = 0x5; - break; - default: - pr_err("%s: unknown dmb type %d\n", __func__, type); + opt = __get_barrier_crm_val(type); + if (opt == AARCH64_BREAK_FAULT) return AARCH64_BREAK_FAULT; - } insn = aarch64_insn_get_dmb_value(); insn &= ~GENMASK(11, 8); @@ -1674,3 +1673,18 @@ u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type) return insn; } + +u32 aarch64_insn_gen_dsb(enum aarch64_insn_mb_type type) +{ + u32 opt, insn; + + opt = __get_barrier_crm_val(type); + if (opt == AARCH64_BREAK_FAULT) + return AARCH64_BREAK_FAULT; + + insn = aarch64_insn_get_dsb_base_value(); + insn &= ~GENMASK(11, 8); + insn |= (opt << 8); + + return insn; +} diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index c04ace8f4843..3dd23050a6c8 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -7,6 +7,7 @@ #define pr_fmt(fmt) "bpf_jit: " fmt +#include #include #include #include @@ -17,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -653,7 +655,51 @@ static void build_plt(struct jit_ctx *ctx) plt->target = (u64)&dummy_tramp; } -static void build_epilogue(struct jit_ctx *ctx) +/* Clobbers BPF registers 1-4, aka x0-x3 */ +static void __maybe_unused build_bhb_mitigation(struct jit_ctx *ctx) +{ + const u8 r1 = bpf2a64[BPF_REG_1]; /* aka x0 */ + u8 k = get_spectre_bhb_loop_value(); + + if (!IS_ENABLED(CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY) || + cpu_mitigations_off() || __nospectre_bhb || + arm64_get_spectre_v2_state() == SPECTRE_VULNERABLE) + return; + + if (capable(CAP_SYS_ADMIN)) + return; + + if (supports_clearbhb(SCOPE_SYSTEM)) { + emit(aarch64_insn_gen_hint(AARCH64_INSN_HINT_CLEARBHB), ctx); + return; + } + + if (k) { + emit_a64_mov_i64(r1, k, ctx); + emit(A64_B(1), ctx); + emit(A64_SUBS_I(true, r1, r1, 1), ctx); + emit(A64_B_(A64_COND_NE, -2), ctx); + emit(aarch64_insn_gen_dsb(AARCH64_INSN_MB_ISH), ctx); + emit(aarch64_insn_get_isb_value(), ctx); + } + + if (is_spectre_bhb_fw_mitigated()) { + emit(A64_ORR_I(false, r1, AARCH64_INSN_REG_ZR, + ARM_SMCCC_ARCH_WORKAROUND_3), ctx); + switch (arm_smccc_1_1_get_conduit()) { + case SMCCC_CONDUIT_HVC: + emit(aarch64_insn_get_hvc_value(), ctx); + break; + case SMCCC_CONDUIT_SMC: + emit(aarch64_insn_get_smc_value(), ctx); + break; + default: + pr_err_once("Firmware mitigation enabled with unknown conduit\n"); + } + } +} + +static void build_epilogue(struct jit_ctx *ctx, bool was_classic) { const u8 r0 = bpf2a64[BPF_REG_0]; const u8 r6 = bpf2a64[BPF_REG_6]; @@ -675,10 +721,13 @@ static void build_epilogue(struct jit_ctx *ctx) emit(A64_POP(r8, r9, A64_SP), ctx); emit(A64_POP(r6, r7, A64_SP), ctx); + if (was_classic) + build_bhb_mitigation(ctx); + /* Restore FP/LR registers */ emit(A64_POP(A64_FP, A64_LR, A64_SP), ctx); - /* Set return value */ + /* Move the return value from bpf:r0 (aka x7) to x0 */ emit(A64_MOV(1, A64_R(0), r0), ctx); /* Authenticate lr */ @@ -1527,7 +1576,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) } ctx.epilogue_offset = ctx.idx; - build_epilogue(&ctx); + build_epilogue(&ctx, was_classic); build_plt(&ctx); extable_align = __alignof__(struct exception_table_entry); @@ -1563,7 +1612,7 @@ skip_init_ctx: goto out_off; } - build_epilogue(&ctx); + build_epilogue(&ctx, was_classic); build_plt(&ctx); /* 3. Extra pass to validate JITed code. */ @@ -1893,7 +1942,11 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, emit(A64_STR64I(A64_R(20), A64_SP, regs_off + 8), ctx); if (flags & BPF_TRAMP_F_CALL_ORIG) { - emit_addr_mov_i64(A64_R(0), (const u64)im, ctx); + /* for the first pass, assume the worst case */ + if (!ctx->image) + ctx->idx += 4; + else + emit_a64_mov_i64(A64_R(0), (const u64)im, ctx); emit_call((const u64)__bpf_tramp_enter, ctx); } @@ -1937,7 +1990,11 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, if (flags & BPF_TRAMP_F_CALL_ORIG) { im->ip_epilogue = ctx->image + ctx->idx; - emit_addr_mov_i64(A64_R(0), (const u64)im, ctx); + /* for the first pass, assume the worst case */ + if (!ctx->image) + ctx->idx += 4; + else + emit_a64_mov_i64(A64_R(0), (const u64)im, ctx); emit_call((const u64)__bpf_tramp_exit, ctx); } diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile index 275d4d5260c7..9d4a6ab7bad9 100644 --- a/arch/loongarch/Makefile +++ b/arch/loongarch/Makefile @@ -38,7 +38,7 @@ endif ifdef CONFIG_64BIT ld-emul = $(64bit-emul) -cflags-y += -mabi=lp64s +cflags-y += -mabi=lp64s -mcmodel=normal endif cflags-y += -pipe -msoft-float diff --git a/arch/loongarch/include/asm/ptrace.h b/arch/loongarch/include/asm/ptrace.h index f5d9096d18aa..af86241ae08f 100644 --- a/arch/loongarch/include/asm/ptrace.h +++ b/arch/loongarch/include/asm/ptrace.h @@ -54,7 +54,7 @@ static inline void instruction_pointer_set(struct pt_regs *regs, unsigned long v /* Query offset/name of register from its name/offset */ extern int regs_query_register_offset(const char *name); -#define MAX_REG_OFFSET (offsetof(struct pt_regs, __last)) +#define MAX_REG_OFFSET (offsetof(struct pt_regs, __last) - sizeof(unsigned long)) /** * regs_get_register() - get register value from its offset diff --git a/arch/mips/include/asm/ftrace.h b/arch/mips/include/asm/ftrace.h index db497a8167da..e3212f44446f 100644 --- a/arch/mips/include/asm/ftrace.h +++ b/arch/mips/include/asm/ftrace.h @@ -87,4 +87,20 @@ struct dyn_arch_ftrace { #endif /* CONFIG_DYNAMIC_FTRACE */ #endif /* __ASSEMBLY__ */ #endif /* CONFIG_FUNCTION_TRACER */ + +#ifdef CONFIG_FTRACE_SYSCALLS +#ifndef __ASSEMBLY__ +/* + * Some syscall entry functions on mips start with "__sys_" (fork and clone, + * for instance). We should also match the sys_ variant with those. + */ +#define ARCH_HAS_SYSCALL_MATCH_SYM_NAME +static inline bool arch_syscall_match_sym_name(const char *sym, + const char *name) +{ + return !strcmp(sym, name) || + (!strncmp(sym, "__sys_", 6) && !strcmp(sym + 6, name + 4)); +} +#endif /* __ASSEMBLY__ */ +#endif /* CONFIG_FTRACE_SYSCALLS */ #endif /* _ASM_MIPS_FTRACE_H */ diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h index 4a2b40ce39e0..841612913f0d 100644 --- a/arch/mips/include/asm/ptrace.h +++ b/arch/mips/include/asm/ptrace.h @@ -65,7 +65,8 @@ static inline void instruction_pointer_set(struct pt_regs *regs, /* Query offset/name of register from its name/offset */ extern int regs_query_register_offset(const char *name); -#define MAX_REG_OFFSET (offsetof(struct pt_regs, __last)) +#define MAX_REG_OFFSET \ + (offsetof(struct pt_regs, __last) - sizeof(unsigned long)) /** * regs_get_register() - get register value from its offset diff --git a/arch/mips/kernel/pm-cps.c b/arch/mips/kernel/pm-cps.c index 9bf60d7d44d3..a7bcf2b814c8 100644 --- a/arch/mips/kernel/pm-cps.c +++ b/arch/mips/kernel/pm-cps.c @@ -56,10 +56,7 @@ static DEFINE_PER_CPU_ALIGNED(u32*, ready_count); /* Indicates online CPUs coupled with the current CPU */ static DEFINE_PER_CPU_ALIGNED(cpumask_t, online_coupled); -/* - * Used to synchronize entry to deep idle states. Actually per-core rather - * than per-CPU. - */ +/* Used to synchronize entry to deep idle states */ static DEFINE_PER_CPU_ALIGNED(atomic_t, pm_barrier); /* Saved CPU state across the CPS_PM_POWER_GATED state */ @@ -118,9 +115,10 @@ int cps_pm_enter_state(enum cps_pm_state state) cps_nc_entry_fn entry; struct core_boot_config *core_cfg; struct vpe_boot_config *vpe_cfg; + atomic_t *barrier; /* Check that there is an entry function for this state */ - entry = per_cpu(nc_asm_enter, core)[state]; + entry = per_cpu(nc_asm_enter, cpu)[state]; if (!entry) return -EINVAL; @@ -156,7 +154,7 @@ int cps_pm_enter_state(enum cps_pm_state state) smp_mb__after_atomic(); /* Create a non-coherent mapping of the core ready_count */ - core_ready_count = per_cpu(ready_count, core); + core_ready_count = per_cpu(ready_count, cpu); nc_addr = kmap_noncoherent(virt_to_page(core_ready_count), (unsigned long)core_ready_count); nc_addr += ((unsigned long)core_ready_count & ~PAGE_MASK); @@ -164,7 +162,8 @@ int cps_pm_enter_state(enum cps_pm_state state) /* Ensure ready_count is zero-initialised before the assembly runs */ WRITE_ONCE(*nc_core_ready_count, 0); - coupled_barrier(&per_cpu(pm_barrier, core), online); + barrier = &per_cpu(pm_barrier, cpumask_first(&cpu_sibling_map[cpu])); + coupled_barrier(barrier, online); /* Run the generated entry code */ left = entry(online, nc_core_ready_count); @@ -635,12 +634,14 @@ out_err: static int cps_pm_online_cpu(unsigned int cpu) { - enum cps_pm_state state; - unsigned core = cpu_core(&cpu_data[cpu]); + unsigned int sibling, core; void *entry_fn, *core_rc; + enum cps_pm_state state; + + core = cpu_core(&cpu_data[cpu]); for (state = CPS_PM_NC_WAIT; state < CPS_PM_STATE_COUNT; state++) { - if (per_cpu(nc_asm_enter, core)[state]) + if (per_cpu(nc_asm_enter, cpu)[state]) continue; if (!test_bit(state, state_support)) continue; @@ -652,16 +653,19 @@ static int cps_pm_online_cpu(unsigned int cpu) clear_bit(state, state_support); } - per_cpu(nc_asm_enter, core)[state] = entry_fn; + for_each_cpu(sibling, &cpu_sibling_map[cpu]) + per_cpu(nc_asm_enter, sibling)[state] = entry_fn; } - if (!per_cpu(ready_count, core)) { + if (!per_cpu(ready_count, cpu)) { core_rc = kmalloc(sizeof(u32), GFP_KERNEL); if (!core_rc) { pr_err("Failed allocate core %u ready_count\n", core); return -ENOMEM; } - per_cpu(ready_count, core) = core_rc; + + for_each_cpu(sibling, &cpu_sibling_map[cpu]) + per_cpu(ready_count, sibling) = core_rc; } return 0; diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index a6090896f749..ac669e58e202 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -2974,11 +2974,11 @@ static void __init fixup_device_tree_pmac(void) char type[8]; phandle node; - // Some pmacs are missing #size-cells on escc nodes + // Some pmacs are missing #size-cells on escc or i2s nodes for (node = 0; prom_next_node(&node); ) { type[0] = '\0'; prom_getprop(node, "device_type", type, sizeof(type)); - if (prom_strcmp(type, "escc")) + if (prom_strcmp(type, "escc") && prom_strcmp(type, "i2s")) continue; if (prom_getproplen(node, "#size-cells") != PROM_ERROR) diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index e3c31c771ce9..470d7715ecf4 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -2229,6 +2229,10 @@ static struct pmu power_pmu = { #define PERF_SAMPLE_ADDR_TYPE (PERF_SAMPLE_ADDR | \ PERF_SAMPLE_PHYS_ADDR | \ PERF_SAMPLE_DATA_PAGE_SIZE) + +#define SIER_TYPE_SHIFT 15 +#define SIER_TYPE_MASK (0x7ull << SIER_TYPE_SHIFT) + /* * A counter has overflowed; update its count and record * things if requested. Note that interrupts are hard-disabled @@ -2297,6 +2301,22 @@ static void record_and_restart(struct perf_event *event, unsigned long val, is_kernel_addr(mfspr(SPRN_SIAR))) record = 0; + /* + * SIER[46-48] presents instruction type of the sampled instruction. + * In ISA v3.0 and before values "0" and "7" are considered reserved. + * In ISA v3.1, value "7" has been used to indicate "larx/stcx". + * Drop the sample if "type" has reserved values for this field with a + * ISA version check. + */ + if (event->attr.sample_type & PERF_SAMPLE_DATA_SRC && + ppmu->get_mem_data_src) { + val = (regs->dar & SIER_TYPE_MASK) >> SIER_TYPE_SHIFT; + if (val == 0 || (val == 7 && !cpu_has_feature(CPU_FTR_ARCH_31))) { + record = 0; + atomic64_inc(&event->lost_samples); + } + } + /* * Finally record data if requested. */ diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c index 56301b2bc8ae..031a2b63c171 100644 --- a/arch/powerpc/perf/isa207-common.c +++ b/arch/powerpc/perf/isa207-common.c @@ -321,8 +321,10 @@ void isa207_get_mem_data_src(union perf_mem_data_src *dsrc, u32 flags, sier = mfspr(SPRN_SIER); val = (sier & ISA207_SIER_TYPE_MASK) >> ISA207_SIER_TYPE_SHIFT; - if (val != 1 && val != 2 && !(val == 7 && cpu_has_feature(CPU_FTR_ARCH_31))) + if (val != 1 && val != 2 && !(val == 7 && cpu_has_feature(CPU_FTR_ARCH_31))) { + dsrc->val = 0; return; + } idx = (sier & ISA207_SIER_LDST_MASK) >> ISA207_SIER_LDST_SHIFT; sub_idx = (sier & ISA207_SIER_DATA_SRC_MASK) >> ISA207_SIER_DATA_SRC_SHIFT; diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 86048c60f700..fd861ac47a89 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -115,6 +115,7 @@ struct kernel_mapping { extern struct kernel_mapping kernel_map; extern phys_addr_t phys_ram_base; +extern unsigned long vmemmap_start_pfn; #define is_kernel_mapping(x) \ ((x) >= kernel_map.virt_addr && (x) < (kernel_map.virt_addr + kernel_map.size)) diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 7d1688f850c3..bb19a643c5c2 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -79,7 +79,7 @@ * Define vmemmap for pfn_to_page & page_to_pfn calls. Needed if kernel * is configured with CONFIG_SPARSEMEM_VMEMMAP enabled. */ -#define vmemmap ((struct page *)VMEMMAP_START - (phys_ram_base >> PAGE_SHIFT)) +#define vmemmap ((struct page *)VMEMMAP_START - vmemmap_start_pfn) #define PCI_IO_SIZE SZ_16M #define PCI_IO_END VMEMMAP_START diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index ba2210b553f9..72b3462babbf 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -22,6 +22,7 @@ #include #include +#include #include #include #include @@ -52,6 +53,13 @@ EXPORT_SYMBOL(pgtable_l5_enabled); phys_addr_t phys_ram_base __ro_after_init; EXPORT_SYMBOL(phys_ram_base); +#ifdef CONFIG_SPARSEMEM_VMEMMAP +#define VMEMMAP_ADDR_ALIGN (1ULL << SECTION_SIZE_BITS) + +unsigned long vmemmap_start_pfn __ro_after_init; +EXPORT_SYMBOL(vmemmap_start_pfn); +#endif + unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss; EXPORT_SYMBOL(empty_zero_page); @@ -210,8 +218,12 @@ static void __init setup_bootmem(void) memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start); phys_ram_end = memblock_end_of_DRAM(); - if (!IS_ENABLED(CONFIG_XIP_KERNEL)) + if (!IS_ENABLED(CONFIG_XIP_KERNEL)) { phys_ram_base = memblock_start_of_DRAM(); +#ifdef CONFIG_SPARSEMEM_VMEMMAP + vmemmap_start_pfn = round_down(phys_ram_base, VMEMMAP_ADDR_ALIGN) >> PAGE_SHIFT; +#endif +} /* * Reserve physical address space that would be mapped to virtual * addresses greater than (void *)(-PAGE_SIZE) because: @@ -946,6 +958,9 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) kernel_map.xiprom_sz = (uintptr_t)(&_exiprom) - (uintptr_t)(&_xiprom); phys_ram_base = CONFIG_PHYS_RAM_BASE; +#ifdef CONFIG_SPARSEMEM_VMEMMAP + vmemmap_start_pfn = round_down(phys_ram_base, VMEMMAP_ADDR_ALIGN) >> PAGE_SHIFT; +#endif kernel_map.phys_addr = (uintptr_t)CONFIG_PHYS_RAM_BASE; kernel_map.size = (uintptr_t)(&_end) - (uintptr_t)(&_start); diff --git a/arch/um/Makefile b/arch/um/Makefile index 778c50f27399..25d0501549f5 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -155,5 +155,6 @@ MRPROPER_FILES += $(HOST_DIR)/include/generated archclean: @find . \( -name '*.bb' -o -name '*.bbg' -o -name '*.da' \ -o -name '*.gcov' \) -type f -print | xargs rm -f + $(Q)$(MAKE) -f $(srctree)/Makefile ARCH=$(HEADER_ARCH) clean export HEADER_ARCH SUBARCH USER_CFLAGS CFLAGS_NO_HARDENING OS DEV_NULL_PATH diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index 38d5a71a579b..f6c766b2bdf5 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -68,6 +68,7 @@ void __init mem_init(void) map_memory(brk_end, __pa(brk_end), uml_reserved - brk_end, 1, 1, 0); memblock_free((void *)brk_end, uml_reserved - brk_end); uml_reserved = brk_end; + min_low_pfn = PFN_UP(__pa(uml_reserved)); /* this will put all low memory onto the freelists */ memblock_free_all(); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index c0344aea8491..4ce54c7103c9 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2576,6 +2576,17 @@ config MITIGATION_SPECTRE_BHI indirect branches. See +config MITIGATION_ITS + bool "Enable Indirect Target Selection mitigation" + depends on CPU_SUP_INTEL && X86_64 + depends on RETPOLINE && RETHUNK + default y + help + Enable Indirect Target Selection (ITS) mitigation. ITS is a bug in + BPU on some Intel CPUs that may allow Spectre V2 style attacks. If + disabled, mitigation cannot be enabled via cmdline. + See + endif config ARCH_HAS_ADD_PAGES diff --git a/arch/x86/boot/genimage.sh b/arch/x86/boot/genimage.sh index c9299aeb7333..3882ead513f7 100644 --- a/arch/x86/boot/genimage.sh +++ b/arch/x86/boot/genimage.sh @@ -22,6 +22,7 @@ # This script requires: # bash # syslinux +# genisoimage # mtools (for fdimage* and hdimage) # edk2/OVMF (for hdimage) # @@ -251,7 +252,9 @@ geniso() { cp "$isolinux" "$ldlinux" "$tmp_dir" cp "$FBZIMAGE" "$tmp_dir"/linux echo default linux "$KCMDLINE" > "$tmp_dir"/isolinux.cfg - cp "${FDINITRDS[@]}" "$tmp_dir"/ + if [ ${#FDINITRDS[@]} -gt 0 ]; then + cp "${FDINITRDS[@]}" "$tmp_dir"/ + fi genisoimage -J -r -appid 'LINUX_BOOT' -input-charset=utf-8 \ -quiet -o "$FIMAGE" -b isolinux.bin \ -c boot.cat -no-emul-boot -boot-load-size 4 \ diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index a114338380a6..4f5968810450 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -1559,7 +1559,9 @@ SYM_CODE_END(rewind_stack_and_make_dead) * ORC to unwind properly. * * The alignment is for performance and not for safety, and may be safely - * refactored in the future if needed. + * refactored in the future if needed. The .skips are for safety, to ensure + * that all RETs are in the second half of a cacheline to mitigate Indirect + * Target Selection, rather than taking the slowpath via its_return_thunk. */ SYM_FUNC_START(clear_bhb_loop) push %rbp @@ -1569,10 +1571,22 @@ SYM_FUNC_START(clear_bhb_loop) call 1f jmp 5f .align 64, 0xcc + /* + * Shift instructions so that the RET is in the upper half of the + * cacheline and don't take the slowpath to its_return_thunk. + */ + .skip 32 - (.Lret1 - 1f), 0xcc ANNOTATE_INTRA_FUNCTION_CALL 1: call 2f - RET +.Lret1: RET .align 64, 0xcc + /* + * As above shift instructions for RET at .Lret2 as well. + * + * This should be ideally be: .skip 32 - (.Lret2 - 2f), 0xcc + * but some Clang versions (e.g. 18) don't like this. + */ + .skip 32 - 18, 0xcc 2: movl $5, %eax 3: jmp 4f nop @@ -1580,7 +1594,7 @@ SYM_FUNC_START(clear_bhb_loop) jnz 3b sub $1, %ecx jnz 1b - RET +.Lret2: RET 5: lfence pop %rbp RET diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 37cbbc5c659a..8c385e231e07 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -1216,7 +1216,8 @@ static __init int perf_ibs_op_init(void) if (ibs_caps & IBS_CAPS_OPCNTEXT) { perf_ibs_op.max_period |= IBS_OP_MAX_CNT_EXT_MASK; perf_ibs_op.config_mask |= IBS_OP_MAX_CNT_EXT_MASK; - perf_ibs_op.cnt_mask |= IBS_OP_MAX_CNT_EXT_MASK; + perf_ibs_op.cnt_mask |= (IBS_OP_MAX_CNT_EXT_MASK | + IBS_OP_CUR_CNT_EXT_MASK); } if (ibs_caps & IBS_CAPS_ZEN4) diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 9542c582d546..fd3b73017738 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -5,6 +5,7 @@ #include #include #include +#include #define ALTINSTR_FLAG_INV (1 << 15) #define ALT_NOT(feat) ((feat) | ALTINSTR_FLAG_INV) @@ -81,6 +82,37 @@ extern void apply_ibt_endbr(s32 *start, s32 *end); struct module; +#ifdef CONFIG_MITIGATION_ITS +extern void its_init_mod(struct module *mod); +extern void its_fini_mod(struct module *mod); +extern void its_free_mod(struct module *mod); +extern u8 *its_static_thunk(int reg); +#else /* CONFIG_MITIGATION_ITS */ +static inline void its_init_mod(struct module *mod) { } +static inline void its_fini_mod(struct module *mod) { } +static inline void its_free_mod(struct module *mod) { } +static inline u8 *its_static_thunk(int reg) +{ + WARN_ONCE(1, "ITS not compiled in"); + + return NULL; +} +#endif + +#if defined(CONFIG_RETHUNK) && defined(CONFIG_OBJTOOL) +extern bool cpu_wants_rethunk(void); +extern bool cpu_wants_rethunk_at(void *addr); +#else +static __always_inline bool cpu_wants_rethunk(void) +{ + return false; +} +static __always_inline bool cpu_wants_rethunk_at(void *addr) +{ + return false; +} +#endif + #ifdef CONFIG_SMP extern void alternatives_smp_module_add(struct module *mod, char *name, void *locks, void *locks_end, diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 5709cbba28e7..28edef597282 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -445,6 +445,7 @@ #define X86_FEATURE_BHI_CTRL (21*32+ 2) /* "" BHI_DIS_S HW control available */ #define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* "" BHI_DIS_S HW control enabled */ #define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* "" Clear branch history at vmexit using SW loop */ +#define X86_FEATURE_INDIRECT_THUNK_ITS (21*32 + 5) /* "" Use thunk for indirect branches in lower half of cacheline */ /* * BUG word(s) @@ -495,4 +496,6 @@ #define X86_BUG_RFDS X86_BUG(1*32 + 2) /* CPU is vulnerable to Register File Data Sampling */ #define X86_BUG_BHI X86_BUG(1*32 + 3) /* CPU is affected by Branch History Injection */ #define X86_BUG_IBPB_NO_RET X86_BUG(1*32 + 4) /* "ibpb_no_ret" IBPB omits return target predictions */ +#define X86_BUG_ITS X86_BUG(1*32 + 5) /* CPU is affected by Indirect Target Selection */ +#define X86_BUG_ITS_NATIVE_ONLY X86_BUG(1*32 + 6) /* CPU is affected by ITS, VMX is not affected */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 5ffcfcc41282..727947ed5e5e 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -185,6 +185,14 @@ * VERW clears CPU Register * File. */ +#define ARCH_CAP_ITS_NO BIT_ULL(62) /* + * Not susceptible to + * Indirect Target Selection. + * This bit is not set by + * HW, but is synthesized by + * VMMs for guests to know + * their affected status. + */ #define ARCH_CAP_XAPIC_DISABLE BIT(21) /* * IA32_XAPIC_DISABLE_STATUS MSR diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index 5c5f1e56c404..6f3d145670a9 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -59,6 +59,8 @@ int __register_nmi_handler(unsigned int, struct nmiaction *); void unregister_nmi_handler(unsigned int, const char *); +void set_emergency_nmi_handler(unsigned int type, nmi_handler_t handler); + void stop_nmi(void); void restart_nmi(void); void local_touch_nmi(void); diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index daf58a96e0a7..cccd5072e09f 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -119,9 +119,8 @@ .endm /* - * Equivalent to -mindirect-branch-cs-prefix; emit the 5 byte jmp/call - * to the retpoline thunk with a CS prefix when the register requires - * a RAX prefix byte to encode. Also see apply_retpolines(). + * Emits a conditional CS prefix that is compatible with + * -mindirect-branch-cs-prefix. */ .macro __CS_PREFIX reg:req .irp rs,r8,r9,r10,r11,r12,r13,r14,r15 @@ -245,8 +244,12 @@ _ASM_PTR " 999b\n\t" \ ".popsection\n\t" +#define ITS_THUNK_SIZE 64 + typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE]; +typedef u8 its_thunk_t[ITS_THUNK_SIZE]; extern retpoline_thunk_t __x86_indirect_thunk_array[]; +extern its_thunk_t __x86_indirect_its_thunk_array[]; #ifdef CONFIG_RETHUNK extern void __x86_return_thunk(void); @@ -254,6 +257,12 @@ extern void __x86_return_thunk(void); static inline void __x86_return_thunk(void) {} #endif +#ifdef CONFIG_MITIGATION_ITS +extern void its_return_thunk(void); +#else +static inline void its_return_thunk(void) {} +#endif + extern void retbleed_return_thunk(void); extern void srso_return_thunk(void); extern void srso_alias_return_thunk(void); @@ -280,20 +289,23 @@ extern void (*x86_return_thunk)(void); #ifdef CONFIG_X86_64 +/* + * Emits a conditional CS prefix that is compatible with + * -mindirect-branch-cs-prefix. + */ +#define __CS_PREFIX(reg) \ + ".irp rs,r8,r9,r10,r11,r12,r13,r14,r15\n" \ + ".ifc \\rs," reg "\n" \ + ".byte 0x2e\n" \ + ".endif\n" \ + ".endr\n" + /* * Inline asm uses the %V modifier which is only in newer GCC * which is ensured when CONFIG_RETPOLINE is defined. */ -# define CALL_NOSPEC \ - ALTERNATIVE_2( \ - ANNOTATE_RETPOLINE_SAFE \ - "call *%[thunk_target]\n", \ - "call __x86_indirect_thunk_%V[thunk_target]\n", \ - X86_FEATURE_RETPOLINE, \ - "lfence;\n" \ - ANNOTATE_RETPOLINE_SAFE \ - "call *%[thunk_target]\n", \ - X86_FEATURE_RETPOLINE_LFENCE) +#define CALL_NOSPEC __CS_PREFIX("%V[thunk_target]") \ + "call __x86_indirect_thunk_%V[thunk_target]\n" # define THUNK_TARGET(addr) [thunk_target] "r" (addr) diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 4d810b9478a4..fa3576ef19da 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -456,6 +456,7 @@ struct pebs_xmm { */ #define IBS_OP_CUR_CNT (0xFFF80ULL<<32) #define IBS_OP_CUR_CNT_RAND (0x0007FULL<<32) +#define IBS_OP_CUR_CNT_EXT_MASK (0x7FULL<<52) #define IBS_OP_CNT_CTL (1ULL<<19) #define IBS_OP_VAL (1ULL<<18) #define IBS_OP_ENABLE (1ULL<<17) diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 69f85e274611..3bc6be6404d2 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -18,6 +18,8 @@ #include #include #include +#include +#include #include #include #include @@ -30,6 +32,8 @@ #include #include #include +#include +#include int __read_mostly alternatives_patched; @@ -396,6 +400,212 @@ static int emit_indirect(int op, int reg, u8 *bytes) return i; } +#ifdef CONFIG_MITIGATION_ITS + +#ifdef CONFIG_MODULES +static struct module *its_mod; +static void *its_page; +static unsigned int its_offset; + +/* Initialize a thunk with the "jmp *reg; int3" instructions. */ +static void *its_init_thunk(void *thunk, int reg) +{ + u8 *bytes = thunk; + int i = 0; + + if (reg >= 8) { + bytes[i++] = 0x41; /* REX.B prefix */ + reg -= 8; + } + bytes[i++] = 0xff; + bytes[i++] = 0xe0 + reg; /* jmp *reg */ + bytes[i++] = 0xcc; + + return thunk; +} + +void its_init_mod(struct module *mod) +{ + if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) + return; + + mutex_lock(&text_mutex); + its_mod = mod; + its_page = NULL; +} + +void its_fini_mod(struct module *mod) +{ + if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) + return; + + WARN_ON_ONCE(its_mod != mod); + + its_mod = NULL; + its_page = NULL; + mutex_unlock(&text_mutex); + + for (int i = 0; i < mod->its_num_pages; i++) { + void *page = mod->its_page_array[i]; + set_memory_ro((unsigned long)page, 1); + set_memory_x((unsigned long)page, 1); + } +} + +void its_free_mod(struct module *mod) +{ + if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) + return; + + for (int i = 0; i < mod->its_num_pages; i++) { + void *page = mod->its_page_array[i]; + module_memfree(page); + } + kfree(mod->its_page_array); +} + +DEFINE_FREE(its_execmem, void *, if (_T) module_memfree(_T)); + +static void *its_alloc(void) +{ + void *page __free(its_execmem) = module_alloc(PAGE_SIZE); + + if (!page) + return NULL; + + if (its_mod) { + void *tmp = krealloc(its_mod->its_page_array, + (its_mod->its_num_pages+1) * sizeof(void *), + GFP_KERNEL); + if (!tmp) + return NULL; + + its_mod->its_page_array = tmp; + its_mod->its_page_array[its_mod->its_num_pages++] = page; + } + + return no_free_ptr(page); +} + +static void *its_allocate_thunk(int reg) +{ + int size = 3 + (reg / 8); + void *thunk; + + if (!its_page || (its_offset + size - 1) >= PAGE_SIZE) { + its_page = its_alloc(); + if (!its_page) { + pr_err("ITS page allocation failed\n"); + return NULL; + } + memset(its_page, INT3_INSN_OPCODE, PAGE_SIZE); + its_offset = 32; + } + + /* + * If the indirect branch instruction will be in the lower half + * of a cacheline, then update the offset to reach the upper half. + */ + if ((its_offset + size - 1) % 64 < 32) + its_offset = ((its_offset - 1) | 0x3F) + 33; + + thunk = its_page + its_offset; + its_offset += size; + + set_memory_rw((unsigned long)its_page, 1); + thunk = its_init_thunk(thunk, reg); + set_memory_ro((unsigned long)its_page, 1); + set_memory_x((unsigned long)its_page, 1); + + return thunk; +} +#else /* CONFIG_MODULES */ + +static void *its_allocate_thunk(int reg) +{ + return NULL; +} + +#endif /* CONFIG_MODULES */ + +static int __emit_trampoline(void *addr, struct insn *insn, u8 *bytes, + void *call_dest, void *jmp_dest) +{ + u8 op = insn->opcode.bytes[0]; + int i = 0; + + /* + * Clang does 'weird' Jcc __x86_indirect_thunk_r11 conditional + * tail-calls. Deal with them. + */ + if (is_jcc32(insn)) { + bytes[i++] = op; + op = insn->opcode.bytes[1]; + goto clang_jcc; + } + + if (insn->length == 6) + bytes[i++] = 0x2e; /* CS-prefix */ + + switch (op) { + case CALL_INSN_OPCODE: + __text_gen_insn(bytes+i, op, addr+i, + call_dest, + CALL_INSN_SIZE); + i += CALL_INSN_SIZE; + break; + + case JMP32_INSN_OPCODE: +clang_jcc: + __text_gen_insn(bytes+i, op, addr+i, + jmp_dest, + JMP32_INSN_SIZE); + i += JMP32_INSN_SIZE; + break; + + default: + WARN(1, "%pS %px %*ph\n", addr, addr, 6, addr); + return -1; + } + + WARN_ON_ONCE(i != insn->length); + + return i; +} + +static int emit_its_trampoline(void *addr, struct insn *insn, int reg, u8 *bytes) +{ + u8 *thunk = __x86_indirect_its_thunk_array[reg]; + u8 *tmp = its_allocate_thunk(reg); + + if (tmp) + thunk = tmp; + + return __emit_trampoline(addr, insn, bytes, thunk, thunk); +} + +/* Check if an indirect branch is at ITS-unsafe address */ +static bool cpu_wants_indirect_its_thunk_at(unsigned long addr, int reg) +{ + if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) + return false; + + /* Indirect branch opcode is 2 or 3 bytes depending on reg */ + addr += 1 + reg / 8; + + /* Lower-half of the cacheline? */ + return !(addr & 0x20); +} + +u8 *its_static_thunk(int reg) +{ + u8 *thunk = __x86_indirect_its_thunk_array[reg]; + + return thunk; +} + +#endif + /* * Rewrite the compiler generated retpoline thunk calls. * @@ -466,6 +676,15 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes) bytes[i++] = 0xe8; /* LFENCE */ } +#ifdef CONFIG_MITIGATION_ITS + /* + * Check if the address of last byte of emitted-indirect is in + * lower-half of the cacheline. Such branches need ITS mitigation. + */ + if (cpu_wants_indirect_its_thunk_at((unsigned long)addr + i, reg)) + return emit_its_trampoline(addr, insn, reg, bytes); +#endif + ret = emit_indirect(op, reg, bytes + i); if (ret < 0) return ret; @@ -537,6 +756,21 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) #ifdef CONFIG_RETHUNK +bool cpu_wants_rethunk(void) +{ + return cpu_feature_enabled(X86_FEATURE_RETHUNK); +} + +bool cpu_wants_rethunk_at(void *addr) +{ + if (!cpu_feature_enabled(X86_FEATURE_RETHUNK)) + return false; + if (x86_return_thunk != its_return_thunk) + return true; + + return !((unsigned long)addr & 0x20); +} + /* * Rewrite the compiler generated return thunk tail-calls. * @@ -552,13 +786,12 @@ static int patch_return(void *addr, struct insn *insn, u8 *bytes) { int i = 0; - if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) { - if (x86_return_thunk == __x86_return_thunk) - return -1; - + /* Patch the custom return thunks... */ + if (cpu_wants_rethunk_at(addr)) { i = JMP32_INSN_SIZE; __text_gen_insn(bytes, JMP32_INSN_OPCODE, addr, x86_return_thunk, i); } else { + /* ... or patch them out if not needed. */ bytes[i++] = RET_INSN_OPCODE; } @@ -914,6 +1147,8 @@ static noinline void __init int3_selftest(void) void __init alternative_instructions(void) { + u64 ibt; + int3_selftest(); /* @@ -951,6 +1186,9 @@ void __init alternative_instructions(void) */ paravirt_set_cap(); + /* Keep CET-IBT disabled until caller/callee are patched */ + ibt = ibt_save(); + /* * First patch paravirt functions, such that we overwrite the indirect * call with the direct call. @@ -972,6 +1210,8 @@ void __init alternative_instructions(void) apply_ibt_endbr(__ibt_endbr_seal, __ibt_endbr_seal_end); + ibt_restore(ibt); + #ifdef CONFIG_SMP /* Patch to UP if other cpus not imminent. */ if (!noreplace_smp && (num_present_cpus() == 1 || setup_max_cpus <= 1)) { diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 0be0edb07a2a..7233474c798f 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -48,6 +48,7 @@ static void __init srbds_select_mitigation(void); static void __init l1d_flush_select_mitigation(void); static void __init gds_select_mitigation(void); static void __init srso_select_mitigation(void); +static void __init its_select_mitigation(void); /* The base value of the SPEC_CTRL MSR without task-specific bits set */ u64 x86_spec_ctrl_base; @@ -66,6 +67,14 @@ static DEFINE_MUTEX(spec_ctrl_mutex); void (*x86_return_thunk)(void) __ro_after_init = &__x86_return_thunk; +static void __init set_return_thunk(void *thunk) +{ + if (x86_return_thunk != __x86_return_thunk) + pr_warn("x86/bugs: return thunk changed\n"); + + x86_return_thunk = thunk; +} + /* Update SPEC_CTRL MSR and its cached copy unconditionally */ static void update_spec_ctrl(u64 val) { @@ -174,6 +183,7 @@ void __init cpu_select_mitigations(void) */ srso_select_mitigation(); gds_select_mitigation(); + its_select_mitigation(); } /* @@ -1081,7 +1091,7 @@ do_cmd_auto: setup_force_cpu_cap(X86_FEATURE_UNRET); if (IS_ENABLED(CONFIG_RETHUNK)) - x86_return_thunk = retbleed_return_thunk; + set_return_thunk(retbleed_return_thunk); if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) @@ -1142,6 +1152,116 @@ do_cmd_auto: pr_info("%s\n", retbleed_strings[retbleed_mitigation]); } +#undef pr_fmt +#define pr_fmt(fmt) "ITS: " fmt + +enum its_mitigation_cmd { + ITS_CMD_OFF, + ITS_CMD_ON, + ITS_CMD_VMEXIT, +}; + +enum its_mitigation { + ITS_MITIGATION_OFF, + ITS_MITIGATION_VMEXIT_ONLY, + ITS_MITIGATION_ALIGNED_THUNKS, +}; + +static const char * const its_strings[] = { + [ITS_MITIGATION_OFF] = "Vulnerable", + [ITS_MITIGATION_VMEXIT_ONLY] = "Mitigation: Vulnerable, KVM: Not affected", + [ITS_MITIGATION_ALIGNED_THUNKS] = "Mitigation: Aligned branch/return thunks", +}; + +static enum its_mitigation its_mitigation __ro_after_init = ITS_MITIGATION_ALIGNED_THUNKS; + +static enum its_mitigation_cmd its_cmd __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_ITS) ? ITS_CMD_ON : ITS_CMD_OFF; + +static int __init its_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!IS_ENABLED(CONFIG_MITIGATION_ITS)) { + pr_err("Mitigation disabled at compile time, ignoring option (%s)", str); + return 0; + } + + if (!strcmp(str, "off")) { + its_cmd = ITS_CMD_OFF; + } else if (!strcmp(str, "on")) { + its_cmd = ITS_CMD_ON; + } else if (!strcmp(str, "force")) { + its_cmd = ITS_CMD_ON; + setup_force_cpu_bug(X86_BUG_ITS); + } else if (!strcmp(str, "vmexit")) { + its_cmd = ITS_CMD_VMEXIT; + } else { + pr_err("Ignoring unknown indirect_target_selection option (%s).", str); + } + + return 0; +} +early_param("indirect_target_selection", its_parse_cmdline); + +static void __init its_select_mitigation(void) +{ + enum its_mitigation_cmd cmd = its_cmd; + + if (!boot_cpu_has_bug(X86_BUG_ITS) || cpu_mitigations_off()) { + its_mitigation = ITS_MITIGATION_OFF; + return; + } + + /* Exit early to avoid irrelevant warnings */ + if (cmd == ITS_CMD_OFF) { + its_mitigation = ITS_MITIGATION_OFF; + goto out; + } + if (spectre_v2_enabled == SPECTRE_V2_NONE) { + pr_err("WARNING: Spectre-v2 mitigation is off, disabling ITS\n"); + its_mitigation = ITS_MITIGATION_OFF; + goto out; + } + if (!IS_ENABLED(CONFIG_RETPOLINE) || !IS_ENABLED(CONFIG_RETHUNK)) { + pr_err("WARNING: ITS mitigation depends on retpoline and rethunk support\n"); + its_mitigation = ITS_MITIGATION_OFF; + goto out; + } + if (IS_ENABLED(CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B)) { + pr_err("WARNING: ITS mitigation is not compatible with CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B\n"); + its_mitigation = ITS_MITIGATION_OFF; + goto out; + } + if (boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE)) { + pr_err("WARNING: ITS mitigation is not compatible with lfence mitigation\n"); + its_mitigation = ITS_MITIGATION_OFF; + goto out; + } + + switch (cmd) { + case ITS_CMD_OFF: + its_mitigation = ITS_MITIGATION_OFF; + break; + case ITS_CMD_VMEXIT: + if (boot_cpu_has_bug(X86_BUG_ITS_NATIVE_ONLY)) { + its_mitigation = ITS_MITIGATION_VMEXIT_ONLY; + goto out; + } + fallthrough; + case ITS_CMD_ON: + its_mitigation = ITS_MITIGATION_ALIGNED_THUNKS; + if (!boot_cpu_has(X86_FEATURE_RETPOLINE)) + setup_force_cpu_cap(X86_FEATURE_INDIRECT_THUNK_ITS); + setup_force_cpu_cap(X86_FEATURE_RETHUNK); + set_return_thunk(its_return_thunk); + break; + } +out: + pr_info("%s\n", its_strings[its_mitigation]); +} + #undef pr_fmt #define pr_fmt(fmt) "Spectre V2 : " fmt @@ -1262,9 +1382,13 @@ static __ro_after_init enum spectre_v2_mitigation_cmd spectre_v2_cmd; static enum spectre_v2_user_cmd __init spectre_v2_parse_user_cmdline(void) { + enum spectre_v2_user_cmd mode; char arg[20]; int ret, i; + mode = IS_ENABLED(CONFIG_MITIGATION_SPECTRE_V2) ? + SPECTRE_V2_USER_CMD_AUTO : SPECTRE_V2_USER_CMD_NONE; + switch (spectre_v2_cmd) { case SPECTRE_V2_CMD_NONE: return SPECTRE_V2_USER_CMD_NONE; @@ -1277,7 +1401,7 @@ spectre_v2_parse_user_cmdline(void) ret = cmdline_find_option(boot_command_line, "spectre_v2_user", arg, sizeof(arg)); if (ret < 0) - return SPECTRE_V2_USER_CMD_AUTO; + return mode; for (i = 0; i < ARRAY_SIZE(v2_user_options); i++) { if (match_option(arg, ret, v2_user_options[i].option)) { @@ -1287,8 +1411,8 @@ spectre_v2_parse_user_cmdline(void) } } - pr_err("Unknown user space protection option (%s). Switching to AUTO select\n", arg); - return SPECTRE_V2_USER_CMD_AUTO; + pr_err("Unknown user space protection option (%s). Switching to default\n", arg); + return mode; } static inline bool spectre_v2_in_eibrs_mode(enum spectre_v2_mitigation mode) @@ -1656,10 +1780,11 @@ static void __init bhi_select_mitigation(void) return; } - if (spec_ctrl_bhi_dis()) + if (!IS_ENABLED(CONFIG_X86_64)) return; - if (!IS_ENABLED(CONFIG_X86_64)) + /* Mitigate in hardware if supported */ + if (spec_ctrl_bhi_dis()) return; /* Mitigate KVM by default */ @@ -2591,10 +2716,10 @@ static void __init srso_select_mitigation(void) if (boot_cpu_data.x86 == 0x19) { setup_force_cpu_cap(X86_FEATURE_SRSO_ALIAS); - x86_return_thunk = srso_alias_return_thunk; + set_return_thunk(srso_alias_return_thunk); } else { setup_force_cpu_cap(X86_FEATURE_SRSO); - x86_return_thunk = srso_return_thunk; + set_return_thunk(srso_return_thunk); } srso_mitigation = SRSO_MITIGATION_SAFE_RET; } else { @@ -2774,6 +2899,11 @@ static ssize_t rfds_show_state(char *buf) return sysfs_emit(buf, "%s\n", rfds_strings[rfds_mitigation]); } +static ssize_t its_show_state(char *buf) +{ + return sysfs_emit(buf, "%s\n", its_strings[its_mitigation]); +} + static char *stibp_state(void) { if (spectre_v2_in_eibrs_mode(spectre_v2_enabled) && @@ -2958,6 +3088,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_RFDS: return rfds_show_state(buf); + case X86_BUG_ITS: + return its_show_state(buf); + default: break; } @@ -3037,4 +3170,9 @@ ssize_t cpu_show_reg_file_data_sampling(struct device *dev, struct device_attrib { return cpu_show_common(dev, attr, buf, X86_BUG_RFDS); } + +ssize_t cpu_show_indirect_target_selection(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_ITS); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 62aaabea7e33..48cc1612df49 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1251,6 +1251,10 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define GDS BIT(6) /* CPU is affected by Register File Data Sampling */ #define RFDS BIT(7) +/* CPU is affected by Indirect Target Selection */ +#define ITS BIT(8) +/* CPU is affected by Indirect Target Selection, but guest-host isolation is not affected */ +#define ITS_NATIVE_ONLY BIT(9) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS), @@ -1262,22 +1266,25 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(BROADWELL_G, X86_STEPPING_ANY, SRBDS), VULNBL_INTEL_STEPPINGS(BROADWELL_X, X86_STEPPING_ANY, MMIO), VULNBL_INTEL_STEPPINGS(BROADWELL, X86_STEPPING_ANY, SRBDS), - VULNBL_INTEL_STEPPINGS(SKYLAKE_X, X86_STEPPING_ANY, MMIO | RETBLEED | GDS), + VULNBL_INTEL_STEPPINGS(SKYLAKE_X, X86_STEPPINGS(0x0, 0x5), MMIO | RETBLEED | GDS), + VULNBL_INTEL_STEPPINGS(SKYLAKE_X, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | ITS), VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS), VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS), - VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS), - VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS), + VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPINGS(0x0, 0xb), MMIO | RETBLEED | GDS | SRBDS), + VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS | ITS), + VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPINGS(0x0, 0xc), MMIO | RETBLEED | GDS | SRBDS), + VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS | ITS), VULNBL_INTEL_STEPPINGS(CANNONLAKE_L, X86_STEPPING_ANY, RETBLEED), - VULNBL_INTEL_STEPPINGS(ICELAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS), - VULNBL_INTEL_STEPPINGS(ICELAKE_D, X86_STEPPING_ANY, MMIO | GDS), - VULNBL_INTEL_STEPPINGS(ICELAKE_X, X86_STEPPING_ANY, MMIO | GDS), - VULNBL_INTEL_STEPPINGS(COMETLAKE, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS), - VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPINGS(0x0, 0x0), MMIO | RETBLEED), - VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS), - VULNBL_INTEL_STEPPINGS(TIGERLAKE_L, X86_STEPPING_ANY, GDS), - VULNBL_INTEL_STEPPINGS(TIGERLAKE, X86_STEPPING_ANY, GDS), + VULNBL_INTEL_STEPPINGS(ICELAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS | ITS_NATIVE_ONLY), + VULNBL_INTEL_STEPPINGS(ICELAKE_D, X86_STEPPING_ANY, MMIO | GDS | ITS | ITS_NATIVE_ONLY), + VULNBL_INTEL_STEPPINGS(ICELAKE_X, X86_STEPPING_ANY, MMIO | GDS | ITS | ITS_NATIVE_ONLY), + VULNBL_INTEL_STEPPINGS(COMETLAKE, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS), + VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPINGS(0x0, 0x0), MMIO | RETBLEED | ITS), + VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS), + VULNBL_INTEL_STEPPINGS(TIGERLAKE_L, X86_STEPPING_ANY, GDS | ITS | ITS_NATIVE_ONLY), + VULNBL_INTEL_STEPPINGS(TIGERLAKE, X86_STEPPING_ANY, GDS | ITS | ITS_NATIVE_ONLY), VULNBL_INTEL_STEPPINGS(LAKEFIELD, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), - VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS), + VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | ITS | ITS_NATIVE_ONLY), VULNBL_INTEL_STEPPINGS(ALDERLAKE, X86_STEPPING_ANY, RFDS), VULNBL_INTEL_STEPPINGS(ALDERLAKE_L, X86_STEPPING_ANY, RFDS), VULNBL_INTEL_STEPPINGS(RAPTORLAKE, X86_STEPPING_ANY, RFDS), @@ -1341,6 +1348,32 @@ static bool __init vulnerable_to_rfds(u64 x86_arch_cap_msr) return cpu_matches(cpu_vuln_blacklist, RFDS); } +static bool __init vulnerable_to_its(u64 x86_arch_cap_msr) +{ + /* The "immunity" bit trumps everything else: */ + if (x86_arch_cap_msr & ARCH_CAP_ITS_NO) + return false; + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return false; + + /* None of the affected CPUs have BHI_CTRL */ + if (boot_cpu_has(X86_FEATURE_BHI_CTRL)) + return false; + + /* + * If a VMM did not expose ITS_NO, assume that a guest could + * be running on a vulnerable hardware or may migrate to such + * hardware. + */ + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) + return true; + + if (cpu_matches(cpu_vuln_blacklist, ITS)) + return true; + + return false; +} + static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) { u64 x86_arch_cap_msr = x86_read_arch_cap_msr(); @@ -1455,9 +1488,12 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) if (vulnerable_to_rfds(x86_arch_cap_msr)) setup_force_cpu_bug(X86_BUG_RFDS); - /* When virtualized, eIBRS could be hidden, assume vulnerable */ - if (!(x86_arch_cap_msr & ARCH_CAP_BHI_NO) && - !cpu_matches(cpu_vuln_whitelist, NO_BHI) && + /* + * Intel parts with eIBRS are vulnerable to BHI attacks. Parts with + * BHI_NO still need to use the BHI mitigation to prevent Intra-mode + * attacks. When virtualized, eIBRS could be hidden, assume vulnerable. + */ + if (!cpu_matches(cpu_vuln_whitelist, NO_BHI) && (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED) || boot_cpu_has(X86_FEATURE_HYPERVISOR))) setup_force_cpu_bug(X86_BUG_BHI); @@ -1465,6 +1501,12 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) if (cpu_has(c, X86_FEATURE_AMD_IBPB) && !cpu_has(c, X86_FEATURE_AMD_IBPB_RET)) setup_force_cpu_bug(X86_BUG_IBPB_NO_RET); + if (vulnerable_to_its(x86_arch_cap_msr)) { + setup_force_cpu_bug(X86_BUG_ITS); + if (cpu_matches(cpu_vuln_blacklist, ITS_NATIVE_ONLY)) + setup_force_cpu_bug(X86_BUG_ITS_NATIVE_ONLY); + } + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index ec51ce713dea..48cf91625a16 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -360,7 +360,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) goto fail; ip = trampoline + size; - if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) + if (cpu_wants_rethunk_at(ip)) __text_gen_insn(ip, JMP32_INSN_OPCODE, ip, x86_return_thunk, JMP32_INSN_SIZE); else memcpy(ip, retq, sizeof(retq)); @@ -415,8 +415,6 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) /* ALLOC_TRAMP flags lets us know we created it */ ops->flags |= FTRACE_OPS_FL_ALLOC_TRAMP; - set_vm_flush_reset_perms(trampoline); - if (likely(system_state != SYSTEM_BOOTING)) set_memory_ro((unsigned long)trampoline, npages); set_memory_x((unsigned long)trampoline, npages); diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 991f00c817e6..180c708879d2 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -427,7 +427,6 @@ void *alloc_insn_page(void) if (!page) return NULL; - set_vm_flush_reset_perms(page); /* * First make the page read-only, and only then make it executable to * prevent it from being W+X in between. diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index c032edcd3d95..c34ea5e028c4 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -74,10 +74,11 @@ void *module_alloc(unsigned long size) return NULL; p = __vmalloc_node_range(size, MODULE_ALIGN, - MODULES_VADDR + get_module_load_offset(), - MODULES_END, gfp_mask, - PAGE_KERNEL, VM_DEFER_KMEMLEAK, NUMA_NO_NODE, - __builtin_return_address(0)); + MODULES_VADDR + get_module_load_offset(), + MODULES_END, gfp_mask, PAGE_KERNEL, + VM_FLUSH_RESET_PERMS | VM_DEFER_KMEMLEAK, + NUMA_NO_NODE, __builtin_return_address(0)); + if (p && (kasan_alloc_module_shadow(p, size, gfp_mask) < 0)) { vfree(p); return NULL; @@ -285,10 +286,16 @@ int module_finalize(const Elf_Ehdr *hdr, void *pseg = (void *)para->sh_addr; apply_paravirt(pseg, pseg + para->sh_size); } + + its_init_mod(me); + if (retpolines) { void *rseg = (void *)retpolines->sh_addr; apply_retpolines(rseg, rseg + retpolines->sh_size); } + + its_fini_mod(me); + if (returns) { void *rseg = (void *)returns->sh_addr; apply_returns(rseg, rseg + returns->sh_size); @@ -320,4 +327,5 @@ int module_finalize(const Elf_Ehdr *hdr, void module_arch_cleanup(struct module *mod) { alternatives_smp_module_del(mod); + its_free_mod(mod); } diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index ed6cce6c3950..b9a128546970 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -38,8 +38,12 @@ #define CREATE_TRACE_POINTS #include +/* + * An emergency handler can be set in any context including NMI + */ struct nmi_desc { raw_spinlock_t lock; + nmi_handler_t emerg_handler; struct list_head head; }; @@ -121,9 +125,22 @@ static void nmi_check_duration(struct nmiaction *action, u64 duration) static int nmi_handle(unsigned int type, struct pt_regs *regs) { struct nmi_desc *desc = nmi_to_desc(type); + nmi_handler_t ehandler; struct nmiaction *a; int handled=0; + /* + * Call the emergency handler, if set + * + * In the case of crash_nmi_callback() emergency handler, it will + * return in the case of the crashing CPU to enable it to complete + * other necessary crashing actions ASAP. Other handlers in the + * linked list won't need to be run. + */ + ehandler = desc->emerg_handler; + if (ehandler) + return ehandler(type, regs); + rcu_read_lock(); /* @@ -213,6 +230,31 @@ void unregister_nmi_handler(unsigned int type, const char *name) } EXPORT_SYMBOL_GPL(unregister_nmi_handler); +/** + * set_emergency_nmi_handler - Set emergency handler + * @type: NMI type + * @handler: the emergency handler to be stored + * + * Set an emergency NMI handler which, if set, will preempt all the other + * handlers in the linked list. If a NULL handler is passed in, it will clear + * it. It is expected that concurrent calls to this function will not happen + * or the system is screwed beyond repair. + */ +void set_emergency_nmi_handler(unsigned int type, nmi_handler_t handler) +{ + struct nmi_desc *desc = nmi_to_desc(type); + + if (WARN_ON_ONCE(desc->emerg_handler == handler)) + return; + desc->emerg_handler = handler; + + /* + * Ensure the emergency handler is visible to other CPUs before + * function return + */ + smp_wmb(); +} + static void pci_serr_error(unsigned char reason, struct pt_regs *regs) { diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 299b970e5f82..d9dbcd1cf75f 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -896,15 +896,11 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback) shootdown_callback = callback; atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1); - /* Would it be better to replace the trap vector here? */ - if (register_nmi_handler(NMI_LOCAL, crash_nmi_callback, - NMI_FLAG_FIRST, "crash")) - return; /* Return what? */ + /* - * Ensure the new callback function is set before sending - * out the NMI + * Set emergency handler to preempt other handlers. */ - wmb(); + set_emergency_nmi_handler(NMI_LOCAL, crash_nmi_callback); apic_send_IPI_allbutself(NMI_VECTOR); diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index ca8dfc0c9edb..93809a4dc793 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -79,7 +79,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, break; case RET: - if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) + if (cpu_wants_rethunk_at(insn)) code = text_gen_insn(JMP32_INSN_OPCODE, insn, x86_return_thunk); else code = &retinsn; diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 78ccb5ec3c0e..35aeec9d2267 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -528,6 +528,16 @@ INIT_PER_CPU(irq_stack_backing_store); "SRSO function pair won't alias"); #endif +#if defined(CONFIG_MITIGATION_ITS) && !defined(CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B) +. = ASSERT(__x86_indirect_its_thunk_rax & 0x20, "__x86_indirect_thunk_rax not in second half of cacheline"); +. = ASSERT(((__x86_indirect_its_thunk_rcx - __x86_indirect_its_thunk_rax) % 64) == 0, "Indirect thunks are not cacheline apart"); +. = ASSERT(__x86_indirect_its_thunk_array == __x86_indirect_its_thunk_rax, "Gap in ITS thunk array"); +#endif + +#if defined(CONFIG_MITIGATION_ITS) && !defined(CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B) +. = ASSERT(its_return_thunk & 0x20, "its_return_thunk not in second half of cacheline"); +#endif + #endif /* CONFIG_X86_64 */ #ifdef CONFIG_KEXEC_CORE diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 752fa116a261..a6dc8f662fa4 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1614,7 +1614,7 @@ static unsigned int num_msr_based_features; ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \ ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \ ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO | \ - ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO) + ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO | ARCH_CAP_ITS_NO) static u64 kvm_get_arch_capabilities(void) { @@ -1653,6 +1653,8 @@ static u64 kvm_get_arch_capabilities(void) data |= ARCH_CAP_MDS_NO; if (!boot_cpu_has_bug(X86_BUG_RFDS)) data |= ARCH_CAP_RFDS_NO; + if (!boot_cpu_has_bug(X86_BUG_ITS)) + data |= ARCH_CAP_ITS_NO; if (!boot_cpu_has(X86_FEATURE_RTM)) { /* diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 7880e2a7ec6a..e42661500094 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -258,6 +258,45 @@ SYM_FUNC_START(entry_untrain_ret) SYM_FUNC_END(entry_untrain_ret) __EXPORT_THUNK(entry_untrain_ret) +#ifdef CONFIG_MITIGATION_ITS + +.macro ITS_THUNK reg + +SYM_INNER_LABEL(__x86_indirect_its_thunk_\reg, SYM_L_GLOBAL) + UNWIND_HINT_EMPTY + ANNOTATE_NOENDBR + ANNOTATE_RETPOLINE_SAFE + jmp *%\reg + int3 + .align 32, 0xcc /* fill to the end of the line */ + .skip 32, 0xcc /* skip to the next upper half */ +.endm + +/* ITS mitigation requires thunks be aligned to upper half of cacheline */ +.align 64, 0xcc +.skip 32, 0xcc +SYM_CODE_START(__x86_indirect_its_thunk_array) + +#define GEN(reg) ITS_THUNK reg +#include +#undef GEN + + .align 64, 0xcc +SYM_CODE_END(__x86_indirect_its_thunk_array) + +.align 64, 0xcc +.skip 32, 0xcc +SYM_CODE_START(its_return_thunk) + UNWIND_HINT_FUNC + ANNOTATE_NOENDBR + ANNOTATE_UNRET_SAFE + ret + int3 +SYM_CODE_END(its_return_thunk) +EXPORT_SYMBOL(its_return_thunk) + +#endif /* CONFIG_MITIGATION_ITS */ + SYM_CODE_START(__x86_return_thunk) UNWIND_HINT_FUNC ANNOTATE_NOENDBR diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 0bb6bb8737e1..5a43ad684594 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -660,8 +660,13 @@ static void __init memory_map_top_down(unsigned long map_start, */ addr = memblock_phys_alloc_range(PMD_SIZE, PMD_SIZE, map_start, map_end); - memblock_phys_free(addr, PMD_SIZE); - real_end = addr + PMD_SIZE; + if (!addr) { + pr_warn("Failed to release memory for alloc_low_pages()"); + real_end = max(map_start, ALIGN_DOWN(map_end, PMD_SIZE)); + } else { + memblock_phys_free(addr, PMD_SIZE); + real_end = addr + PMD_SIZE; + } /* step_size need to be small so pgt_buf from BRK could cover it */ step_size = PMD_SIZE; diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 851711509d38..9d75b89fa257 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -959,9 +959,18 @@ int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages, ret = __add_pages(nid, start_pfn, nr_pages, params); WARN_ON_ONCE(ret); - /* update max_pfn, max_low_pfn and high_memory */ - update_end_of_memory_vars(start_pfn << PAGE_SHIFT, - nr_pages << PAGE_SHIFT); + /* + * Special case: add_pages() is called by memremap_pages() for adding device + * private pages. Do not bump up max_pfn in the device private path, + * because max_pfn changes affect dma_addressing_limited(). + * + * dma_addressing_limited() returning true when max_pfn is the device's + * addressable memory can force device drivers to use bounce buffers + * and impact their performance negatively: + */ + if (!params->pgmap) + /* update max_pfn, max_low_pfn and high_memory */ + update_end_of_memory_vars(start_pfn << PAGE_SHIFT, nr_pages << PAGE_SHIFT); return ret; } diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index 230f1dee4f09..e0b0ec0f8245 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -109,8 +109,14 @@ void __init kernel_randomize_memory(void) memory_tb = DIV_ROUND_UP(max_pfn << PAGE_SHIFT, 1UL << TB_SHIFT) + CONFIG_RANDOMIZE_MEMORY_PHYSICAL_PADDING; - /* Adapt physical memory region size based on available memory */ - if (memory_tb < kaslr_regions[0].size_tb) + /* + * Adapt physical memory region size based on available memory, + * except when CONFIG_PCI_P2PDMA is enabled. P2PDMA exposes the + * device BAR space assuming the direct map space is large enough + * for creating a ZONE_DEVICE mapping in the direct map corresponding + * to the physical BAR address. + */ + if (!IS_ENABLED(CONFIG_PCI_P2PDMA) && (memory_tb < kaslr_regions[0].size_tb)) kaslr_regions[0].size_tb = memory_tb; /* diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 8d46b9c0e920..4918268d2007 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -617,7 +617,11 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush); - /* Let nmi_uaccess_okay() know that we're changing CR3. */ + /* + * Indicate that CR3 is about to change. nmi_uaccess_okay() + * and others are sensitive to the window where mm_cpumask(), + * CR3 and cpu_tlbstate.loaded_mm are not all in sync. + */ this_cpu_write(cpu_tlbstate.loaded_mm, LOADED_MM_SWITCHING); barrier(); } @@ -880,8 +884,16 @@ done: static bool should_flush_tlb(int cpu, void *data) { + struct mm_struct *loaded_mm = per_cpu(cpu_tlbstate.loaded_mm, cpu); struct flush_tlb_info *info = data; + /* + * Order the 'loaded_mm' and 'is_lazy' against their + * write ordering in switch_mm_irqs_off(). Ensure + * 'is_lazy' is at least as new as 'loaded_mm'. + */ + smp_rmb(); + /* Lazy TLB will get flushed at the next context switch. */ if (per_cpu(cpu_tlbstate_shared.is_lazy, cpu)) return false; @@ -890,8 +902,15 @@ static bool should_flush_tlb(int cpu, void *data) if (!info->mm) return true; + /* + * While switching, the remote CPU could have state from + * either the prev or next mm. Assume the worst and flush. + */ + if (loaded_mm == LOADED_MM_SWITCHING) + return true; + /* The target mm is loaded, and the CPU is not lazy. */ - if (per_cpu(cpu_tlbstate.loaded_mm, cpu) == info->mm) + if (loaded_mm == info->mm) return true; /* In cpumask, but not the loaded mm? Periodically remove by flushing. */ diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 23a00ead97c0..f8e5aa7f022d 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -36,6 +36,8 @@ static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len) #define EMIT2(b1, b2) EMIT((b1) + ((b2) << 8), 2) #define EMIT3(b1, b2, b3) EMIT((b1) + ((b2) << 8) + ((b3) << 16), 3) #define EMIT4(b1, b2, b3, b4) EMIT((b1) + ((b2) << 8) + ((b3) << 16) + ((b4) << 24), 4) +#define EMIT5(b1, b2, b3, b4, b5) \ + do { EMIT1(b1); EMIT4(b2, b3, b4, b5); } while (0) #define EMIT1_off32(b1, off) \ do { EMIT1(b1); EMIT(off, 4); } while (0) @@ -462,7 +464,11 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip) { u8 *prog = *pprog; - if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) { + if (IS_ENABLED(CONFIG_MITIGATION_ITS) && + cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) { + OPTIMIZER_HIDE_VAR(reg); + emit_jump(&prog, its_static_thunk(reg), ip); + } else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) { EMIT_LFENCE(); EMIT2(0xFF, 0xE0 + reg); } else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) { @@ -481,7 +487,7 @@ static void emit_return(u8 **pprog, u8 *ip) { u8 *prog = *pprog; - if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) { + if (cpu_wants_rethunk()) { emit_jump(&prog, x86_return_thunk, ip); } else { EMIT1(0xC3); /* ret */ @@ -947,6 +953,47 @@ static void emit_nops(u8 **pprog, int len) #define RESTORE_TAIL_CALL_CNT(stack) \ EMIT3_off32(0x48, 0x8B, 0x85, -round_up(stack, 8) - 8) +static int emit_spectre_bhb_barrier(u8 **pprog, u8 *ip, + struct bpf_prog *bpf_prog) +{ + u8 *prog = *pprog; + u8 *func; + + if (cpu_feature_enabled(X86_FEATURE_CLEAR_BHB_LOOP)) { + /* The clearing sequence clobbers eax and ecx. */ + EMIT1(0x50); /* push rax */ + EMIT1(0x51); /* push rcx */ + ip += 2; + + func = (u8 *)clear_bhb_loop; + + if (emit_call(&prog, func, ip)) + return -EINVAL; + EMIT1(0x59); /* pop rcx */ + EMIT1(0x58); /* pop rax */ + } + /* Insert IBHF instruction */ + if ((cpu_feature_enabled(X86_FEATURE_CLEAR_BHB_LOOP) && + cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) || + cpu_feature_enabled(X86_FEATURE_CLEAR_BHB_HW)) { + /* + * Add an Indirect Branch History Fence (IBHF). IBHF acts as a + * fence preventing branch history from before the fence from + * affecting indirect branches after the fence. This is + * specifically used in cBPF jitted code to prevent Intra-mode + * BHI attacks. The IBHF instruction is designed to be a NOP on + * hardware that doesn't need or support it. The REP and REX.W + * prefixes are required by the microcode, and they also ensure + * that the NOP is unlikely to be used in existing code. + * + * IBHF is not a valid instruction in 32-bit mode. + */ + EMIT5(0xF3, 0x48, 0x0F, 0x1E, 0xF8); /* ibhf */ + } + *pprog = prog; + return 0; +} + static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image, int oldproglen, struct jit_context *ctx, bool jmp_padding) { @@ -1752,6 +1799,15 @@ emit_jmp: seen_exit = true; /* Update cleanup_addr */ ctx->cleanup_addr = proglen; + + if (bpf_prog_was_classic(bpf_prog) && + !capable(CAP_SYS_ADMIN)) { + u8 *ip = image + addrs[i - 1]; + + if (emit_spectre_bhb_barrier(&prog, ip, bpf_prog)) + return -EINVAL; + } + pop_callee_regs(&prog, callee_regs_used); EMIT1(0xC9); /* leave */ emit_return(&prog, image + addrs[i - 1] + (prog - temp)); diff --git a/arch/x86/um/os-Linux/mcontext.c b/arch/x86/um/os-Linux/mcontext.c index 49c3744cac37..81b9d1f9f4e6 100644 --- a/arch/x86/um/os-Linux/mcontext.c +++ b/arch/x86/um/os-Linux/mcontext.c @@ -26,7 +26,6 @@ void get_regs_from_mc(struct uml_pt_regs *regs, mcontext_t *mc) COPY(RIP); COPY2(EFLAGS, EFL); COPY2(CS, CSGSFS); - regs->gp[CS / sizeof(unsigned long)] &= 0xffff; - regs->gp[CS / sizeof(unsigned long)] |= 3; + regs->gp[SS / sizeof(unsigned long)] = mc->gregs[REG_CSGSFS] >> 48; #endif } diff --git a/block/bio.c b/block/bio.c index b5cd4b4c041c..edad6243cf93 100644 --- a/block/bio.c +++ b/block/bio.c @@ -579,7 +579,7 @@ struct bio *bio_kmalloc(unsigned short nr_vecs, gfp_t gfp_mask) { struct bio *bio; - if (nr_vecs > UIO_MAXIOV) + if (nr_vecs > BIO_MAX_INLINE_VECS) return NULL; return kmalloc(struct_size(bio, bi_inline_vecs, nr_vecs), gfp_mask); } diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c index 1d017ec5c63c..84f4e9c2b5d9 100644 --- a/crypto/algif_hash.c +++ b/crypto/algif_hash.c @@ -263,10 +263,6 @@ static int hash_accept(struct socket *sock, struct socket *newsock, int flags, return err; err = crypto_ahash_import(&ctx2->req, state); - if (err) { - sock_orphan(sk2); - sock_put(sk2); - } return err; } diff --git a/crypto/lzo-rle.c b/crypto/lzo-rle.c index 0631d975bfac..0abc2d87f042 100644 --- a/crypto/lzo-rle.c +++ b/crypto/lzo-rle.c @@ -55,7 +55,7 @@ static int __lzorle_compress(const u8 *src, unsigned int slen, size_t tmp_len = *dlen; /* size_t(ulong) <-> uint on 64 bit */ int err; - err = lzorle1x_1_compress(src, slen, dst, &tmp_len, ctx); + err = lzorle1x_1_compress_safe(src, slen, dst, &tmp_len, ctx); if (err != LZO_E_OK) return -EINVAL; diff --git a/crypto/lzo.c b/crypto/lzo.c index ebda132dd22b..8338851c7406 100644 --- a/crypto/lzo.c +++ b/crypto/lzo.c @@ -55,7 +55,7 @@ static int __lzo_compress(const u8 *src, unsigned int slen, size_t tmp_len = *dlen; /* size_t(ulong) <-> uint on 64 bit */ int err; - err = lzo1x_1_compress(src, slen, dst, &tmp_len, ctx); + err = lzo1x_1_compress_safe(src, slen, dst, &tmp_len, ctx); if (err != LZO_E_OK) return -EINVAL; diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index 473241b5193f..596e96d3b3bd 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -438,7 +438,7 @@ config ACPI_SBS the modules will be called sbs and sbshc. config ACPI_HED - tristate "Hardware Error Device" + bool "Hardware Error Device" help This driver supports the Hardware Error Device (PNP0C33), which is used to report some hardware errors notified via diff --git a/drivers/acpi/hed.c b/drivers/acpi/hed.c index 60a2939cde6c..e8e9b1ac06b8 100644 --- a/drivers/acpi/hed.c +++ b/drivers/acpi/hed.c @@ -72,7 +72,12 @@ static struct acpi_driver acpi_hed_driver = { .notify = acpi_hed_notify, }, }; -module_acpi_driver(acpi_hed_driver); + +static int __init acpi_hed_driver_init(void) +{ + return acpi_bus_register_driver(&acpi_hed_driver); +} +subsys_initcall(acpi_hed_driver_init); MODULE_AUTHOR("Huang Ying"); MODULE_DESCRIPTION("ACPI Hardware Error Device Driver"); diff --git a/drivers/acpi/pptt.c b/drivers/acpi/pptt.c index 79a83d8236cb..1938e4778725 100644 --- a/drivers/acpi/pptt.c +++ b/drivers/acpi/pptt.c @@ -219,16 +219,18 @@ static int acpi_pptt_leaf_node(struct acpi_table_header *table_hdr, sizeof(struct acpi_table_pptt)); proc_sz = sizeof(struct acpi_pptt_processor); - while ((unsigned long)entry + proc_sz < table_end) { + /* ignore subtable types that are smaller than a processor node */ + while ((unsigned long)entry + proc_sz <= table_end) { cpu_node = (struct acpi_pptt_processor *)entry; + if (entry->type == ACPI_PPTT_TYPE_PROCESSOR && cpu_node->parent == node_entry) return 0; if (entry->length == 0) return 0; + entry = ACPI_ADD_PTR(struct acpi_subtable_header, entry, entry->length); - } return 1; } @@ -261,15 +263,18 @@ static struct acpi_pptt_processor *acpi_find_processor_node(struct acpi_table_he proc_sz = sizeof(struct acpi_pptt_processor); /* find the processor structure associated with this cpuid */ - while ((unsigned long)entry + proc_sz < table_end) { + while ((unsigned long)entry + proc_sz <= table_end) { cpu_node = (struct acpi_pptt_processor *)entry; if (entry->length == 0) { pr_warn("Invalid zero length subtable\n"); break; } + /* entry->length may not equal proc_sz, revalidate the processor structure length */ if (entry->type == ACPI_PPTT_TYPE_PROCESSOR && acpi_cpu_id == cpu_node->acpi_processor_id && + (unsigned long)entry + entry->length <= table_end && + entry->length == proc_sz + cpu_node->number_of_priv_resources * sizeof(u32) && acpi_pptt_leaf_node(table_hdr, cpu_node)) { return (struct acpi_pptt_processor *)entry; } diff --git a/drivers/auxdisplay/charlcd.c b/drivers/auxdisplay/charlcd.c index 6d309e4971b6..e243291a7e77 100644 --- a/drivers/auxdisplay/charlcd.c +++ b/drivers/auxdisplay/charlcd.c @@ -594,18 +594,19 @@ static int charlcd_init(struct charlcd *lcd) return 0; } -struct charlcd *charlcd_alloc(void) +struct charlcd *charlcd_alloc(unsigned int drvdata_size) { struct charlcd_priv *priv; struct charlcd *lcd; - priv = kzalloc(sizeof(*priv), GFP_KERNEL); + priv = kzalloc(sizeof(*priv) + drvdata_size, GFP_KERNEL); if (!priv) return NULL; priv->esc_seq.len = -1; lcd = &priv->lcd; + lcd->drvdata = priv->drvdata; return lcd; } diff --git a/drivers/auxdisplay/charlcd.h b/drivers/auxdisplay/charlcd.h index eed80063a6d2..4bbf106b2dd8 100644 --- a/drivers/auxdisplay/charlcd.h +++ b/drivers/auxdisplay/charlcd.h @@ -49,7 +49,7 @@ struct charlcd { unsigned long y; } addr; - void *drvdata; + void *drvdata; /* Set by charlcd_alloc() */ }; /** @@ -93,7 +93,8 @@ struct charlcd_ops { }; void charlcd_backlight(struct charlcd *lcd, enum charlcd_onoff on); -struct charlcd *charlcd_alloc(void); + +struct charlcd *charlcd_alloc(unsigned int drvdata_size); void charlcd_free(struct charlcd *lcd); int charlcd_register(struct charlcd *lcd); diff --git a/drivers/auxdisplay/hd44780.c b/drivers/auxdisplay/hd44780.c index 8b690f59df27..ebaf0ff518f4 100644 --- a/drivers/auxdisplay/hd44780.c +++ b/drivers/auxdisplay/hd44780.c @@ -226,7 +226,7 @@ static int hd44780_probe(struct platform_device *pdev) if (!hdc) return -ENOMEM; - lcd = charlcd_alloc(); + lcd = charlcd_alloc(0); if (!lcd) goto fail1; diff --git a/drivers/auxdisplay/lcd2s.c b/drivers/auxdisplay/lcd2s.c index 135831a16514..2b597f226c0c 100644 --- a/drivers/auxdisplay/lcd2s.c +++ b/drivers/auxdisplay/lcd2s.c @@ -307,7 +307,7 @@ static int lcd2s_i2c_probe(struct i2c_client *i2c) if (err < 0) return err; - lcd = charlcd_alloc(); + lcd = charlcd_alloc(0); if (!lcd) return -ENOMEM; diff --git a/drivers/auxdisplay/panel.c b/drivers/auxdisplay/panel.c index eba04c0de7eb..0f3999b665e7 100644 --- a/drivers/auxdisplay/panel.c +++ b/drivers/auxdisplay/panel.c @@ -835,7 +835,7 @@ static void lcd_init(void) if (!hdc) return; - charlcd = charlcd_alloc(); + charlcd = charlcd_alloc(0); if (!charlcd) { kfree(hdc); return; diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 31da94afe4f3..27aff2503765 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -595,6 +595,12 @@ ssize_t __weak cpu_show_reg_file_data_sampling(struct device *dev, return sysfs_emit(buf, "Not affected\n"); } +ssize_t __weak cpu_show_indirect_target_selection(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "Not affected\n"); +} + static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL); @@ -609,6 +615,7 @@ static DEVICE_ATTR(retbleed, 0444, cpu_show_retbleed, NULL); static DEVICE_ATTR(gather_data_sampling, 0444, cpu_show_gds, NULL); static DEVICE_ATTR(spec_rstack_overflow, 0444, cpu_show_spec_rstack_overflow, NULL); static DEVICE_ATTR(reg_file_data_sampling, 0444, cpu_show_reg_file_data_sampling, NULL); +static DEVICE_ATTR(indirect_target_selection, 0444, cpu_show_indirect_target_selection, NULL); static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, @@ -625,6 +632,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_gather_data_sampling.attr, &dev_attr_spec_rstack_overflow.attr, &dev_attr_reg_file_data_sampling.attr, + &dev_attr_indirect_target_selection.attr, NULL }; diff --git a/drivers/char/tpm/tpm_tis_core.h b/drivers/char/tpm/tpm_tis_core.h index be72681ab8ea..5f29eebef52b 100644 --- a/drivers/char/tpm/tpm_tis_core.h +++ b/drivers/char/tpm/tpm_tis_core.h @@ -53,7 +53,7 @@ enum tis_int_flags { enum tis_defaults { TIS_MEM_LEN = 0x5000, TIS_SHORT_TIMEOUT = 750, /* ms */ - TIS_LONG_TIMEOUT = 2000, /* 2 sec */ + TIS_LONG_TIMEOUT = 4000, /* 4 secs */ TIS_TIMEOUT_MIN_ATML = 14700, /* usecs */ TIS_TIMEOUT_MAX_ATML = 15000, /* usecs */ }; diff --git a/drivers/clk/imx/clk-imx8mp.c b/drivers/clk/imx/clk-imx8mp.c index 444dfd6adfe6..a74b73cd243e 100644 --- a/drivers/clk/imx/clk-imx8mp.c +++ b/drivers/clk/imx/clk-imx8mp.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include #include @@ -405,11 +406,151 @@ static const char * const imx8mp_clkout_sels[] = {"audio_pll1_out", "audio_pll2_ static struct clk_hw **hws; static struct clk_hw_onecell_data *clk_hw_data; +struct imx8mp_clock_constraints { + unsigned int clkid; + u32 maxrate; +}; + +/* + * Below tables are taken from IMX8MPCEC Rev. 2.1, 07/2023 + * Table 13. Maximum frequency of modules. + * Probable typos fixed are marked with a comment. + */ +static const struct imx8mp_clock_constraints imx8mp_clock_common_constraints[] = { + { IMX8MP_CLK_A53_DIV, 1000 * HZ_PER_MHZ }, + { IMX8MP_CLK_ENET_AXI, 266666667 }, /* Datasheet claims 266MHz */ + { IMX8MP_CLK_NAND_USDHC_BUS, 266666667 }, /* Datasheet claims 266MHz */ + { IMX8MP_CLK_MEDIA_APB, 200 * HZ_PER_MHZ }, + { IMX8MP_CLK_HDMI_APB, 133333333 }, /* Datasheet claims 133MHz */ + { IMX8MP_CLK_ML_AXI, 800 * HZ_PER_MHZ }, + { IMX8MP_CLK_AHB, 133333333 }, + { IMX8MP_CLK_IPG_ROOT, 66666667 }, + { IMX8MP_CLK_AUDIO_AHB, 400 * HZ_PER_MHZ }, + { IMX8MP_CLK_MEDIA_DISP2_PIX, 170 * HZ_PER_MHZ }, + { IMX8MP_CLK_DRAM_ALT, 666666667 }, + { IMX8MP_CLK_DRAM_APB, 200 * HZ_PER_MHZ }, + { IMX8MP_CLK_CAN1, 80 * HZ_PER_MHZ }, + { IMX8MP_CLK_CAN2, 80 * HZ_PER_MHZ }, + { IMX8MP_CLK_PCIE_AUX, 10 * HZ_PER_MHZ }, + { IMX8MP_CLK_I2C5, 66666667 }, /* Datasheet claims 66MHz */ + { IMX8MP_CLK_I2C6, 66666667 }, /* Datasheet claims 66MHz */ + { IMX8MP_CLK_SAI1, 66666667 }, /* Datasheet claims 66MHz */ + { IMX8MP_CLK_SAI2, 66666667 }, /* Datasheet claims 66MHz */ + { IMX8MP_CLK_SAI3, 66666667 }, /* Datasheet claims 66MHz */ + { IMX8MP_CLK_SAI5, 66666667 }, /* Datasheet claims 66MHz */ + { IMX8MP_CLK_SAI6, 66666667 }, /* Datasheet claims 66MHz */ + { IMX8MP_CLK_ENET_QOS, 125 * HZ_PER_MHZ }, + { IMX8MP_CLK_ENET_QOS_TIMER, 200 * HZ_PER_MHZ }, + { IMX8MP_CLK_ENET_REF, 125 * HZ_PER_MHZ }, + { IMX8MP_CLK_ENET_TIMER, 125 * HZ_PER_MHZ }, + { IMX8MP_CLK_ENET_PHY_REF, 125 * HZ_PER_MHZ }, + { IMX8MP_CLK_NAND, 500 * HZ_PER_MHZ }, + { IMX8MP_CLK_QSPI, 400 * HZ_PER_MHZ }, + { IMX8MP_CLK_USDHC1, 400 * HZ_PER_MHZ }, + { IMX8MP_CLK_USDHC2, 400 * HZ_PER_MHZ }, + { IMX8MP_CLK_I2C1, 66666667 }, /* Datasheet claims 66MHz */ + { IMX8MP_CLK_I2C2, 66666667 }, /* Datasheet claims 66MHz */ + { IMX8MP_CLK_I2C3, 66666667 }, /* Datasheet claims 66MHz */ + { IMX8MP_CLK_I2C4, 66666667 }, /* Datasheet claims 66MHz */ + { IMX8MP_CLK_UART1, 80 * HZ_PER_MHZ }, + { IMX8MP_CLK_UART2, 80 * HZ_PER_MHZ }, + { IMX8MP_CLK_UART3, 80 * HZ_PER_MHZ }, + { IMX8MP_CLK_UART4, 80 * HZ_PER_MHZ }, + { IMX8MP_CLK_ECSPI1, 80 * HZ_PER_MHZ }, + { IMX8MP_CLK_ECSPI2, 80 * HZ_PER_MHZ }, + { IMX8MP_CLK_PWM1, 66666667 }, /* Datasheet claims 66MHz */ + { IMX8MP_CLK_PWM2, 66666667 }, /* Datasheet claims 66MHz */ + { IMX8MP_CLK_PWM3, 66666667 }, /* Datasheet claims 66MHz */ + { IMX8MP_CLK_PWM4, 66666667 }, /* Datasheet claims 66MHz */ + { IMX8MP_CLK_GPT1, 100 * HZ_PER_MHZ }, + { IMX8MP_CLK_GPT2, 100 * HZ_PER_MHZ }, + { IMX8MP_CLK_GPT3, 100 * HZ_PER_MHZ }, + { IMX8MP_CLK_GPT4, 100 * HZ_PER_MHZ }, + { IMX8MP_CLK_GPT5, 100 * HZ_PER_MHZ }, + { IMX8MP_CLK_GPT6, 100 * HZ_PER_MHZ }, + { IMX8MP_CLK_WDOG, 66666667 }, /* Datasheet claims 66MHz */ + { IMX8MP_CLK_IPP_DO_CLKO1, 200 * HZ_PER_MHZ }, + { IMX8MP_CLK_IPP_DO_CLKO2, 200 * HZ_PER_MHZ }, + { IMX8MP_CLK_HDMI_REF_266M, 266 * HZ_PER_MHZ }, + { IMX8MP_CLK_USDHC3, 400 * HZ_PER_MHZ }, + { IMX8MP_CLK_MEDIA_MIPI_PHY1_REF, 300 * HZ_PER_MHZ }, + { IMX8MP_CLK_MEDIA_DISP1_PIX, 250 * HZ_PER_MHZ }, + { IMX8MP_CLK_MEDIA_CAM2_PIX, 277 * HZ_PER_MHZ }, + { IMX8MP_CLK_MEDIA_LDB, 595 * HZ_PER_MHZ }, + { IMX8MP_CLK_MEDIA_MIPI_TEST_BYTE, 200 * HZ_PER_MHZ }, + { IMX8MP_CLK_ECSPI3, 80 * HZ_PER_MHZ }, + { IMX8MP_CLK_PDM, 200 * HZ_PER_MHZ }, + { IMX8MP_CLK_SAI7, 66666667 }, /* Datasheet claims 66MHz */ + { IMX8MP_CLK_MAIN_AXI, 400 * HZ_PER_MHZ }, + { /* Sentinel */ } +}; + +static const struct imx8mp_clock_constraints imx8mp_clock_nominal_constraints[] = { + { IMX8MP_CLK_M7_CORE, 600 * HZ_PER_MHZ }, + { IMX8MP_CLK_ML_CORE, 800 * HZ_PER_MHZ }, + { IMX8MP_CLK_GPU3D_CORE, 800 * HZ_PER_MHZ }, + { IMX8MP_CLK_GPU3D_SHADER_CORE, 800 * HZ_PER_MHZ }, + { IMX8MP_CLK_GPU2D_CORE, 800 * HZ_PER_MHZ }, + { IMX8MP_CLK_AUDIO_AXI_SRC, 600 * HZ_PER_MHZ }, + { IMX8MP_CLK_HSIO_AXI, 400 * HZ_PER_MHZ }, + { IMX8MP_CLK_MEDIA_ISP, 400 * HZ_PER_MHZ }, + { IMX8MP_CLK_VPU_BUS, 600 * HZ_PER_MHZ }, + { IMX8MP_CLK_MEDIA_AXI, 400 * HZ_PER_MHZ }, + { IMX8MP_CLK_HDMI_AXI, 400 * HZ_PER_MHZ }, + { IMX8MP_CLK_GPU_AXI, 600 * HZ_PER_MHZ }, + { IMX8MP_CLK_GPU_AHB, 300 * HZ_PER_MHZ }, + { IMX8MP_CLK_NOC, 800 * HZ_PER_MHZ }, + { IMX8MP_CLK_NOC_IO, 600 * HZ_PER_MHZ }, + { IMX8MP_CLK_ML_AHB, 300 * HZ_PER_MHZ }, + { IMX8MP_CLK_VPU_G1, 600 * HZ_PER_MHZ }, + { IMX8MP_CLK_VPU_G2, 500 * HZ_PER_MHZ }, + { IMX8MP_CLK_MEDIA_CAM1_PIX, 400 * HZ_PER_MHZ }, + { IMX8MP_CLK_VPU_VC8000E, 400 * HZ_PER_MHZ }, /* Datasheet claims 500MHz */ + { IMX8MP_CLK_DRAM_CORE, 800 * HZ_PER_MHZ }, + { IMX8MP_CLK_GIC, 400 * HZ_PER_MHZ }, + { /* Sentinel */ } +}; + +static const struct imx8mp_clock_constraints imx8mp_clock_overdrive_constraints[] = { + { IMX8MP_CLK_M7_CORE, 800 * HZ_PER_MHZ}, + { IMX8MP_CLK_ML_CORE, 1000 * HZ_PER_MHZ }, + { IMX8MP_CLK_GPU3D_CORE, 1000 * HZ_PER_MHZ }, + { IMX8MP_CLK_GPU3D_SHADER_CORE, 1000 * HZ_PER_MHZ }, + { IMX8MP_CLK_GPU2D_CORE, 1000 * HZ_PER_MHZ }, + { IMX8MP_CLK_AUDIO_AXI_SRC, 800 * HZ_PER_MHZ }, + { IMX8MP_CLK_HSIO_AXI, 500 * HZ_PER_MHZ }, + { IMX8MP_CLK_MEDIA_ISP, 500 * HZ_PER_MHZ }, + { IMX8MP_CLK_VPU_BUS, 800 * HZ_PER_MHZ }, + { IMX8MP_CLK_MEDIA_AXI, 500 * HZ_PER_MHZ }, + { IMX8MP_CLK_HDMI_AXI, 500 * HZ_PER_MHZ }, + { IMX8MP_CLK_GPU_AXI, 800 * HZ_PER_MHZ }, + { IMX8MP_CLK_GPU_AHB, 400 * HZ_PER_MHZ }, + { IMX8MP_CLK_NOC, 1000 * HZ_PER_MHZ }, + { IMX8MP_CLK_NOC_IO, 800 * HZ_PER_MHZ }, + { IMX8MP_CLK_ML_AHB, 400 * HZ_PER_MHZ }, + { IMX8MP_CLK_VPU_G1, 800 * HZ_PER_MHZ }, + { IMX8MP_CLK_VPU_G2, 700 * HZ_PER_MHZ }, + { IMX8MP_CLK_MEDIA_CAM1_PIX, 500 * HZ_PER_MHZ }, + { IMX8MP_CLK_VPU_VC8000E, 500 * HZ_PER_MHZ }, /* Datasheet claims 400MHz */ + { IMX8MP_CLK_DRAM_CORE, 1000 * HZ_PER_MHZ }, + { IMX8MP_CLK_GIC, 500 * HZ_PER_MHZ }, + { /* Sentinel */ } +}; + +static void imx8mp_clocks_apply_constraints(const struct imx8mp_clock_constraints constraints[]) +{ + const struct imx8mp_clock_constraints *constr; + + for (constr = constraints; constr->clkid; constr++) + clk_hw_set_rate_range(hws[constr->clkid], 0, constr->maxrate); +} + static int imx8mp_clocks_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct device_node *np; void __iomem *anatop_base, *ccm_base; + const char *opmode; int err; np = of_find_compatible_node(NULL, NULL, "fsl,imx8mp-anatop"); @@ -704,6 +845,16 @@ static int imx8mp_clocks_probe(struct platform_device *pdev) imx_check_clk_hws(hws, IMX8MP_CLK_END); + imx8mp_clocks_apply_constraints(imx8mp_clock_common_constraints); + + err = of_property_read_string(np, "fsl,operating-mode", &opmode); + if (!err) { + if (!strcmp(opmode, "nominal")) + imx8mp_clocks_apply_constraints(imx8mp_clock_nominal_constraints); + else if (!strcmp(opmode, "overdrive")) + imx8mp_clocks_apply_constraints(imx8mp_clock_overdrive_constraints); + } + err = of_clk_add_hw_provider(np, of_clk_hw_onecell_get, clk_hw_data); if (err < 0) { dev_err(dev, "failed to register hws for i.MX8MP\n"); diff --git a/drivers/clk/qcom/camcc-sm8250.c b/drivers/clk/qcom/camcc-sm8250.c index 9b32c56a5bc5..e29706d78287 100644 --- a/drivers/clk/qcom/camcc-sm8250.c +++ b/drivers/clk/qcom/camcc-sm8250.c @@ -411,7 +411,7 @@ static struct clk_rcg2 cam_cc_bps_clk_src = { .parent_data = cam_cc_parent_data_0, .num_parents = ARRAY_SIZE(cam_cc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -433,7 +433,7 @@ static struct clk_rcg2 cam_cc_camnoc_axi_clk_src = { .parent_data = cam_cc_parent_data_0, .num_parents = ARRAY_SIZE(cam_cc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -454,7 +454,7 @@ static struct clk_rcg2 cam_cc_cci_0_clk_src = { .parent_data = cam_cc_parent_data_0, .num_parents = ARRAY_SIZE(cam_cc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -469,7 +469,7 @@ static struct clk_rcg2 cam_cc_cci_1_clk_src = { .parent_data = cam_cc_parent_data_0, .num_parents = ARRAY_SIZE(cam_cc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -490,7 +490,7 @@ static struct clk_rcg2 cam_cc_cphy_rx_clk_src = { .parent_data = cam_cc_parent_data_0, .num_parents = ARRAY_SIZE(cam_cc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -511,7 +511,7 @@ static struct clk_rcg2 cam_cc_csi0phytimer_clk_src = { .parent_data = cam_cc_parent_data_0, .num_parents = ARRAY_SIZE(cam_cc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -526,7 +526,7 @@ static struct clk_rcg2 cam_cc_csi1phytimer_clk_src = { .parent_data = cam_cc_parent_data_0, .num_parents = ARRAY_SIZE(cam_cc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -556,7 +556,7 @@ static struct clk_rcg2 cam_cc_csi3phytimer_clk_src = { .parent_data = cam_cc_parent_data_0, .num_parents = ARRAY_SIZE(cam_cc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -571,7 +571,7 @@ static struct clk_rcg2 cam_cc_csi4phytimer_clk_src = { .parent_data = cam_cc_parent_data_0, .num_parents = ARRAY_SIZE(cam_cc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -586,7 +586,7 @@ static struct clk_rcg2 cam_cc_csi5phytimer_clk_src = { .parent_data = cam_cc_parent_data_0, .num_parents = ARRAY_SIZE(cam_cc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -611,7 +611,7 @@ static struct clk_rcg2 cam_cc_fast_ahb_clk_src = { .parent_data = cam_cc_parent_data_0, .num_parents = ARRAY_SIZE(cam_cc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -634,7 +634,7 @@ static struct clk_rcg2 cam_cc_fd_core_clk_src = { .parent_data = cam_cc_parent_data_0, .num_parents = ARRAY_SIZE(cam_cc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -649,7 +649,7 @@ static struct clk_rcg2 cam_cc_icp_clk_src = { .parent_data = cam_cc_parent_data_0, .num_parents = ARRAY_SIZE(cam_cc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -673,7 +673,7 @@ static struct clk_rcg2 cam_cc_ife_0_clk_src = { .parent_data = cam_cc_parent_data_2, .num_parents = ARRAY_SIZE(cam_cc_parent_data_2), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -710,7 +710,7 @@ static struct clk_rcg2 cam_cc_ife_0_csid_clk_src = { .parent_data = cam_cc_parent_data_0, .num_parents = ARRAY_SIZE(cam_cc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -734,7 +734,7 @@ static struct clk_rcg2 cam_cc_ife_1_clk_src = { .parent_data = cam_cc_parent_data_3, .num_parents = ARRAY_SIZE(cam_cc_parent_data_3), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -749,7 +749,7 @@ static struct clk_rcg2 cam_cc_ife_1_csid_clk_src = { .parent_data = cam_cc_parent_data_0, .num_parents = ARRAY_SIZE(cam_cc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -771,7 +771,7 @@ static struct clk_rcg2 cam_cc_ife_lite_clk_src = { .parent_data = cam_cc_parent_data_0, .num_parents = ARRAY_SIZE(cam_cc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -786,7 +786,7 @@ static struct clk_rcg2 cam_cc_ife_lite_csid_clk_src = { .parent_data = cam_cc_parent_data_0, .num_parents = ARRAY_SIZE(cam_cc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -810,7 +810,7 @@ static struct clk_rcg2 cam_cc_ipe_0_clk_src = { .parent_data = cam_cc_parent_data_4, .num_parents = ARRAY_SIZE(cam_cc_parent_data_4), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -825,7 +825,7 @@ static struct clk_rcg2 cam_cc_jpeg_clk_src = { .parent_data = cam_cc_parent_data_0, .num_parents = ARRAY_SIZE(cam_cc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -847,7 +847,7 @@ static struct clk_rcg2 cam_cc_mclk0_clk_src = { .parent_data = cam_cc_parent_data_1, .num_parents = ARRAY_SIZE(cam_cc_parent_data_1), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -862,7 +862,7 @@ static struct clk_rcg2 cam_cc_mclk1_clk_src = { .parent_data = cam_cc_parent_data_1, .num_parents = ARRAY_SIZE(cam_cc_parent_data_1), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -877,7 +877,7 @@ static struct clk_rcg2 cam_cc_mclk2_clk_src = { .parent_data = cam_cc_parent_data_1, .num_parents = ARRAY_SIZE(cam_cc_parent_data_1), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -892,7 +892,7 @@ static struct clk_rcg2 cam_cc_mclk3_clk_src = { .parent_data = cam_cc_parent_data_1, .num_parents = ARRAY_SIZE(cam_cc_parent_data_1), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -907,7 +907,7 @@ static struct clk_rcg2 cam_cc_mclk4_clk_src = { .parent_data = cam_cc_parent_data_1, .num_parents = ARRAY_SIZE(cam_cc_parent_data_1), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -922,7 +922,7 @@ static struct clk_rcg2 cam_cc_mclk5_clk_src = { .parent_data = cam_cc_parent_data_1, .num_parents = ARRAY_SIZE(cam_cc_parent_data_1), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -993,7 +993,7 @@ static struct clk_rcg2 cam_cc_slow_ahb_clk_src = { .parent_data = cam_cc_parent_data_0, .num_parents = ARRAY_SIZE(cam_cc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; diff --git a/drivers/clk/qcom/clk-alpha-pll.c b/drivers/clk/qcom/clk-alpha-pll.c index e63a90db1505..c591fa1ad802 100644 --- a/drivers/clk/qcom/clk-alpha-pll.c +++ b/drivers/clk/qcom/clk-alpha-pll.c @@ -561,14 +561,19 @@ clk_alpha_pll_recalc_rate(struct clk_hw *hw, unsigned long parent_rate) struct clk_alpha_pll *pll = to_clk_alpha_pll(hw); u32 alpha_width = pll_alpha_width(pll); - regmap_read(pll->clkr.regmap, PLL_L_VAL(pll), &l); + if (regmap_read(pll->clkr.regmap, PLL_L_VAL(pll), &l)) + return 0; + + if (regmap_read(pll->clkr.regmap, PLL_USER_CTL(pll), &ctl)) + return 0; - regmap_read(pll->clkr.regmap, PLL_USER_CTL(pll), &ctl); if (ctl & PLL_ALPHA_EN) { - regmap_read(pll->clkr.regmap, PLL_ALPHA_VAL(pll), &low); + if (regmap_read(pll->clkr.regmap, PLL_ALPHA_VAL(pll), &low)) + return 0; if (alpha_width > 32) { - regmap_read(pll->clkr.regmap, PLL_ALPHA_VAL_U(pll), - &high); + if (regmap_read(pll->clkr.regmap, PLL_ALPHA_VAL_U(pll), + &high)) + return 0; a = (u64)high << 32 | low; } else { a = low & GENMASK(alpha_width - 1, 0); @@ -760,8 +765,11 @@ alpha_pll_huayra_recalc_rate(struct clk_hw *hw, unsigned long parent_rate) struct clk_alpha_pll *pll = to_clk_alpha_pll(hw); u32 l, alpha = 0, ctl, alpha_m, alpha_n; - regmap_read(pll->clkr.regmap, PLL_L_VAL(pll), &l); - regmap_read(pll->clkr.regmap, PLL_USER_CTL(pll), &ctl); + if (regmap_read(pll->clkr.regmap, PLL_L_VAL(pll), &l)) + return 0; + + if (regmap_read(pll->clkr.regmap, PLL_USER_CTL(pll), &ctl)) + return 0; if (ctl & PLL_ALPHA_EN) { regmap_read(pll->clkr.regmap, PLL_ALPHA_VAL(pll), &alpha); @@ -955,8 +963,11 @@ clk_trion_pll_recalc_rate(struct clk_hw *hw, unsigned long parent_rate) struct clk_alpha_pll *pll = to_clk_alpha_pll(hw); u32 l, frac, alpha_width = pll_alpha_width(pll); - regmap_read(pll->clkr.regmap, PLL_L_VAL(pll), &l); - regmap_read(pll->clkr.regmap, PLL_ALPHA_VAL(pll), &frac); + if (regmap_read(pll->clkr.regmap, PLL_L_VAL(pll), &l)) + return 0; + + if (regmap_read(pll->clkr.regmap, PLL_ALPHA_VAL(pll), &frac)) + return 0; return alpha_pll_calc_rate(parent_rate, l, frac, alpha_width); } @@ -1014,7 +1025,8 @@ clk_alpha_pll_postdiv_recalc_rate(struct clk_hw *hw, unsigned long parent_rate) struct clk_alpha_pll_postdiv *pll = to_clk_alpha_pll_postdiv(hw); u32 ctl; - regmap_read(pll->clkr.regmap, PLL_USER_CTL(pll), &ctl); + if (regmap_read(pll->clkr.regmap, PLL_USER_CTL(pll), &ctl)) + return 0; ctl >>= PLL_POST_DIV_SHIFT; ctl &= PLL_POST_DIV_MASK(pll); @@ -1230,8 +1242,11 @@ static unsigned long alpha_pll_fabia_recalc_rate(struct clk_hw *hw, struct clk_alpha_pll *pll = to_clk_alpha_pll(hw); u32 l, frac, alpha_width = pll_alpha_width(pll); - regmap_read(pll->clkr.regmap, PLL_L_VAL(pll), &l); - regmap_read(pll->clkr.regmap, PLL_FRAC(pll), &frac); + if (regmap_read(pll->clkr.regmap, PLL_L_VAL(pll), &l)) + return 0; + + if (regmap_read(pll->clkr.regmap, PLL_FRAC(pll), &frac)) + return 0; return alpha_pll_calc_rate(parent_rate, l, frac, alpha_width); } @@ -1381,7 +1396,8 @@ clk_trion_pll_postdiv_recalc_rate(struct clk_hw *hw, unsigned long parent_rate) struct regmap *regmap = pll->clkr.regmap; u32 i, div = 1, val; - regmap_read(regmap, PLL_USER_CTL(pll), &val); + if (regmap_read(regmap, PLL_USER_CTL(pll), &val)) + return 0; val >>= pll->post_div_shift; val &= PLL_POST_DIV_MASK(pll); @@ -2254,9 +2270,12 @@ static unsigned long alpha_pll_lucid_evo_recalc_rate(struct clk_hw *hw, struct regmap *regmap = pll->clkr.regmap; u32 l, frac; - regmap_read(regmap, PLL_L_VAL(pll), &l); + if (regmap_read(regmap, PLL_L_VAL(pll), &l)) + return 0; l &= LUCID_EVO_PLL_L_VAL_MASK; - regmap_read(regmap, PLL_ALPHA_VAL(pll), &frac); + + if (regmap_read(regmap, PLL_ALPHA_VAL(pll), &frac)) + return 0; return alpha_pll_calc_rate(parent_rate, l, frac, pll_alpha_width(pll)); } @@ -2331,7 +2350,8 @@ static unsigned long clk_rivian_evo_pll_recalc_rate(struct clk_hw *hw, struct clk_alpha_pll *pll = to_clk_alpha_pll(hw); u32 l; - regmap_read(pll->clkr.regmap, PLL_L_VAL(pll), &l); + if (regmap_read(pll->clkr.regmap, PLL_L_VAL(pll), &l)) + return 0; return parent_rate * l; } diff --git a/drivers/clk/sunxi-ng/ccu-sun20i-d1.c b/drivers/clk/sunxi-ng/ccu-sun20i-d1.c index cb4bf038e17f..89d8bf4a30a2 100644 --- a/drivers/clk/sunxi-ng/ccu-sun20i-d1.c +++ b/drivers/clk/sunxi-ng/ccu-sun20i-d1.c @@ -412,19 +412,23 @@ static const struct clk_parent_data mmc0_mmc1_parents[] = { { .hw = &pll_periph0_2x_clk.common.hw }, { .hw = &pll_audio1_div2_clk.common.hw }, }; -static SUNXI_CCU_MP_DATA_WITH_MUX_GATE(mmc0_clk, "mmc0", mmc0_mmc1_parents, 0x830, - 0, 4, /* M */ - 8, 2, /* P */ - 24, 3, /* mux */ - BIT(31), /* gate */ - 0); +static SUNXI_CCU_MP_DATA_WITH_MUX_GATE_POSTDIV(mmc0_clk, "mmc0", + mmc0_mmc1_parents, 0x830, + 0, 4, /* M */ + 8, 2, /* P */ + 24, 3, /* mux */ + BIT(31), /* gate */ + 2, /* post-div */ + 0); -static SUNXI_CCU_MP_DATA_WITH_MUX_GATE(mmc1_clk, "mmc1", mmc0_mmc1_parents, 0x834, - 0, 4, /* M */ - 8, 2, /* P */ - 24, 3, /* mux */ - BIT(31), /* gate */ - 0); +static SUNXI_CCU_MP_DATA_WITH_MUX_GATE_POSTDIV(mmc1_clk, "mmc1", + mmc0_mmc1_parents, 0x834, + 0, 4, /* M */ + 8, 2, /* P */ + 24, 3, /* mux */ + BIT(31), /* gate */ + 2, /* post-div */ + 0); static const struct clk_parent_data mmc2_parents[] = { { .fw_name = "hosc" }, @@ -433,12 +437,14 @@ static const struct clk_parent_data mmc2_parents[] = { { .hw = &pll_periph0_800M_clk.common.hw }, { .hw = &pll_audio1_div2_clk.common.hw }, }; -static SUNXI_CCU_MP_DATA_WITH_MUX_GATE(mmc2_clk, "mmc2", mmc2_parents, 0x838, - 0, 4, /* M */ - 8, 2, /* P */ - 24, 3, /* mux */ - BIT(31), /* gate */ - 0); +static SUNXI_CCU_MP_DATA_WITH_MUX_GATE_POSTDIV(mmc2_clk, "mmc2", mmc2_parents, + 0x838, + 0, 4, /* M */ + 8, 2, /* P */ + 24, 3, /* mux */ + BIT(31), /* gate */ + 2, /* post-div */ + 0); static SUNXI_CCU_GATE_HWS(bus_mmc0_clk, "bus-mmc0", psi_ahb_hws, 0x84c, BIT(0), 0); diff --git a/drivers/clk/sunxi-ng/ccu_mp.h b/drivers/clk/sunxi-ng/ccu_mp.h index 6e50f3728fb5..7d836a9fb3db 100644 --- a/drivers/clk/sunxi-ng/ccu_mp.h +++ b/drivers/clk/sunxi-ng/ccu_mp.h @@ -52,6 +52,28 @@ struct ccu_mp { } \ } +#define SUNXI_CCU_MP_DATA_WITH_MUX_GATE_POSTDIV(_struct, _name, _parents, \ + _reg, \ + _mshift, _mwidth, \ + _pshift, _pwidth, \ + _muxshift, _muxwidth, \ + _gate, _postdiv, _flags)\ + struct ccu_mp _struct = { \ + .enable = _gate, \ + .m = _SUNXI_CCU_DIV(_mshift, _mwidth), \ + .p = _SUNXI_CCU_DIV(_pshift, _pwidth), \ + .mux = _SUNXI_CCU_MUX(_muxshift, _muxwidth), \ + .fixed_post_div = _postdiv, \ + .common = { \ + .reg = _reg, \ + .features = CCU_FEATURE_FIXED_POSTDIV, \ + .hw.init = CLK_HW_INIT_PARENTS_DATA(_name, \ + _parents, \ + &ccu_mp_ops, \ + _flags), \ + } \ + } + #define SUNXI_CCU_MP_WITH_MUX_GATE(_struct, _name, _parents, _reg, \ _mshift, _mwidth, \ _pshift, _pwidth, \ diff --git a/drivers/clocksource/i8253.c b/drivers/clocksource/i8253.c index 39f7c2d736d1..b603c25f3dfa 100644 --- a/drivers/clocksource/i8253.c +++ b/drivers/clocksource/i8253.c @@ -103,7 +103,7 @@ int __init clocksource_i8253_init(void) #ifdef CONFIG_CLKEVT_I8253 void clockevent_i8253_disable(void) { - raw_spin_lock(&i8253_lock); + guard(raw_spinlock_irqsave)(&i8253_lock); /* * Writing the MODE register should stop the counter, according to @@ -132,8 +132,6 @@ void clockevent_i8253_disable(void) outb_p(0, PIT_CH0); outb_p(0x30, PIT_MODE); - - raw_spin_unlock(&i8253_lock); } static int pit_shutdown(struct clock_event_device *evt) diff --git a/drivers/clocksource/mips-gic-timer.c b/drivers/clocksource/mips-gic-timer.c index b3ae38f36720..39c70b5ac44c 100644 --- a/drivers/clocksource/mips-gic-timer.c +++ b/drivers/clocksource/mips-gic-timer.c @@ -114,6 +114,9 @@ static void gic_update_frequency(void *data) static int gic_starting_cpu(unsigned int cpu) { + /* Ensure the GIC counter is running */ + clear_gic_config(GIC_CONFIG_COUNTSTOP); + gic_clockevent_cpu_init(cpu, this_cpu_ptr(&gic_clockevent_device)); return 0; } @@ -248,9 +251,6 @@ static int __init gic_clocksource_of_init(struct device_node *node) pr_warn("Unable to register clock notifier\n"); } - /* And finally start the counter */ - clear_gic_config(GIC_CONFIG_COUNTSTOP); - /* * It's safe to use the MIPS GIC timer as a sched clock source only if * its ticks are stable, which is true on either the platforms with diff --git a/drivers/cpufreq/tegra186-cpufreq.c b/drivers/cpufreq/tegra186-cpufreq.c index 6c88827f4e62..1d6b54303723 100644 --- a/drivers/cpufreq/tegra186-cpufreq.c +++ b/drivers/cpufreq/tegra186-cpufreq.c @@ -73,11 +73,18 @@ static int tegra186_cpufreq_init(struct cpufreq_policy *policy) { struct tegra186_cpufreq_data *data = cpufreq_get_driver_data(); unsigned int cluster = data->cpus[policy->cpu].bpmp_cluster_id; + u32 cpu; policy->freq_table = data->clusters[cluster].table; policy->cpuinfo.transition_latency = 300 * 1000; policy->driver_data = NULL; + /* set same policy for all cpus in a cluster */ + for (cpu = 0; cpu < ARRAY_SIZE(tegra186_cpus); cpu++) { + if (data->cpus[cpu].bpmp_cluster_id == cluster) + cpumask_set_cpu(cpu, policy->cpus); + } + return 0; } diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c index c4922684f305..4edac724983a 100644 --- a/drivers/cpuidle/governors/menu.c +++ b/drivers/cpuidle/governors/menu.c @@ -249,8 +249,19 @@ again: * This can deal with workloads that have long pauses interspersed * with sporadic activity with a bunch of short pauses. */ - if ((divisor * 4) <= INTERVALS * 3) + if (divisor * 4 <= INTERVALS * 3) { + /* + * If there are sufficiently many data points still under + * consideration after the outliers have been eliminated, + * returning without a prediction would be a mistake because it + * is likely that the next interval will not exceed the current + * maximum, so return the latter in that case. + */ + if (divisor >= INTERVALS / 2) + return max; + return UINT_MAX; + } thresh = max - 1; goto again; diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptvf_reqmgr.c b/drivers/crypto/marvell/octeontx2/otx2_cptvf_reqmgr.c index 811ded72ce5f..798bb40fed68 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptvf_reqmgr.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cptvf_reqmgr.c @@ -410,9 +410,10 @@ static int cpt_process_ccode(struct otx2_cptlfs_info *lfs, break; } - dev_err(&pdev->dev, - "Request failed with software error code 0x%x\n", - cpt_status->s.uc_compcode); + pr_debug("Request failed with software error code 0x%x: algo = %s driver = %s\n", + cpt_status->s.uc_compcode, + info->req->areq->tfm->__crt_alg->cra_name, + info->req->areq->tfm->__crt_alg->cra_driver_name); otx2_cpt_dump_sg_list(pdev, info->req); break; } diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c index e78ff9333c7a..759b4f80baee 100644 --- a/drivers/dma-buf/dma-resv.c +++ b/drivers/dma-buf/dma-resv.c @@ -308,8 +308,9 @@ void dma_resv_add_fence(struct dma_resv *obj, struct dma_fence *fence, count++; dma_resv_list_set(fobj, i, fence, usage); - /* pointer update must be visible before we extend the num_fences */ - smp_store_mb(fobj->num_fences, count); + /* fence update must be visible before we extend the num_fences */ + smp_wmb(); + fobj->num_fences = count; } EXPORT_SYMBOL(dma_resv_add_fence); diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c index 78b8a97b2363..ffe621695e47 100644 --- a/drivers/dma/dmatest.c +++ b/drivers/dma/dmatest.c @@ -827,9 +827,9 @@ static int dmatest_func(void *data) } else { dma_async_issue_pending(chan); - wait_event_timeout(thread->done_wait, - done->done, - msecs_to_jiffies(params->timeout)); + wait_event_freezable_timeout(thread->done_wait, + done->done, + msecs_to_jiffies(params->timeout)); status = dma_async_is_tx_complete(chan, cookie, NULL, NULL); diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c index 906a3d57644b..fad129c80e0d 100644 --- a/drivers/dma/idxd/cdev.c +++ b/drivers/dma/idxd/cdev.c @@ -11,7 +11,9 @@ #include #include #include +#include #include +#include #include "registers.h" #include "idxd.h" @@ -34,6 +36,7 @@ struct idxd_user_context { struct idxd_wq *wq; struct task_struct *task; unsigned int pasid; + struct mm_struct *mm; unsigned int flags; struct iommu_sva *sva; }; @@ -68,6 +71,19 @@ static inline struct idxd_wq *inode_wq(struct inode *inode) return idxd_cdev->wq; } +static void idxd_xa_pasid_remove(struct idxd_user_context *ctx) +{ + struct idxd_wq *wq = ctx->wq; + void *ptr; + + mutex_lock(&wq->uc_lock); + ptr = xa_cmpxchg(&wq->upasid_xa, ctx->pasid, ctx, NULL, GFP_KERNEL); + if (ptr != (void *)ctx) + dev_warn(&wq->idxd->pdev->dev, "xarray cmpxchg failed for pasid %u\n", + ctx->pasid); + mutex_unlock(&wq->uc_lock); +} + static int idxd_cdev_open(struct inode *inode, struct file *filp) { struct idxd_user_context *ctx; @@ -108,20 +124,25 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp) pasid = iommu_sva_get_pasid(sva); if (pasid == IOMMU_PASID_INVALID) { - iommu_sva_unbind_device(sva); rc = -EINVAL; - goto failed; + goto failed_get_pasid; } ctx->sva = sva; ctx->pasid = pasid; + ctx->mm = current->mm; + + mutex_lock(&wq->uc_lock); + rc = xa_insert(&wq->upasid_xa, pasid, ctx, GFP_KERNEL); + mutex_unlock(&wq->uc_lock); + if (rc < 0) + dev_warn(dev, "PASID entry already exist in xarray.\n"); if (wq_dedicated(wq)) { rc = idxd_wq_set_pasid(wq, pasid); if (rc < 0) { - iommu_sva_unbind_device(sva); dev_err(dev, "wq set pasid failed: %d\n", rc); - goto failed; + goto failed_set_pasid; } } } @@ -130,7 +151,13 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp) mutex_unlock(&wq->wq_lock); return 0; - failed: +failed_set_pasid: + if (device_user_pasid_enabled(idxd)) + idxd_xa_pasid_remove(ctx); +failed_get_pasid: + if (device_user_pasid_enabled(idxd)) + iommu_sva_unbind_device(sva); +failed: mutex_unlock(&wq->wq_lock); kfree(ctx); return rc; @@ -161,8 +188,10 @@ static int idxd_cdev_release(struct inode *node, struct file *filep) } } - if (ctx->sva) + if (ctx->sva) { iommu_sva_unbind_device(ctx->sva); + idxd_xa_pasid_remove(ctx); + } kfree(ctx); mutex_lock(&wq->wq_lock); idxd_wq_put(wq); @@ -209,6 +238,9 @@ static int idxd_cdev_mmap(struct file *filp, struct vm_area_struct *vma) if (!idxd->user_submission_safe && !capable(CAP_SYS_RAWIO)) return -EPERM; + if (current->mm != ctx->mm) + return -EPERM; + rc = check_vma(wq, vma, __func__); if (rc < 0) return rc; @@ -275,6 +307,9 @@ static ssize_t idxd_cdev_write(struct file *filp, const char __user *buf, size_t ssize_t written = 0; int i; + if (current->mm != ctx->mm) + return -EPERM; + for (i = 0; i < len/sizeof(struct dsa_hw_desc); i++) { int rc = idxd_submit_user_descriptor(ctx, udesc + i); @@ -295,6 +330,9 @@ static __poll_t idxd_cdev_poll(struct file *filp, struct idxd_device *idxd = wq->idxd; __poll_t out = 0; + if (current->mm != ctx->mm) + return POLLNVAL; + poll_wait(filp, &wq->err_queue, wait); spin_lock(&idxd->dev_lock); if (idxd->sw_err.valid) @@ -407,6 +445,13 @@ static int idxd_user_drv_probe(struct idxd_dev *idxd_dev) } mutex_lock(&wq->wq_lock); + + wq->wq = create_workqueue(dev_name(wq_confdev(wq))); + if (!wq->wq) { + rc = -ENOMEM; + goto wq_err; + } + wq->type = IDXD_WQT_USER; rc = drv_enable_wq(wq); if (rc < 0) @@ -425,7 +470,9 @@ static int idxd_user_drv_probe(struct idxd_dev *idxd_dev) err_cdev: drv_disable_wq(wq); err: + destroy_workqueue(wq->wq); wq->type = IDXD_WQT_NONE; +wq_err: mutex_unlock(&wq->wq_lock); return rc; } @@ -438,6 +485,8 @@ static void idxd_user_drv_remove(struct idxd_dev *idxd_dev) idxd_wq_del_cdev(wq); drv_disable_wq(wq); wq->type = IDXD_WQT_NONE; + destroy_workqueue(wq->wq); + wq->wq = NULL; mutex_unlock(&wq->wq_lock); } @@ -484,3 +533,70 @@ void idxd_cdev_remove(void) ida_destroy(&ictx[i].minor_ida); } } + +/** + * idxd_copy_cr - copy completion record to user address space found by wq and + * PASID + * @wq: work queue + * @pasid: PASID + * @addr: user fault address to write + * @cr: completion record + * @len: number of bytes to copy + * + * This is called by a work that handles completion record fault. + * + * Return: number of bytes copied. + */ +int idxd_copy_cr(struct idxd_wq *wq, ioasid_t pasid, unsigned long addr, + void *cr, int len) +{ + struct device *dev = &wq->idxd->pdev->dev; + int left = len, status_size = 1; + struct idxd_user_context *ctx; + struct mm_struct *mm; + + mutex_lock(&wq->uc_lock); + + ctx = xa_load(&wq->upasid_xa, pasid); + if (!ctx) { + dev_warn(dev, "No user context\n"); + goto out; + } + + mm = ctx->mm; + /* + * The completion record fault handling work is running in kernel + * thread context. It temporarily switches to the mm to copy cr + * to addr in the mm. + */ + kthread_use_mm(mm); + left = copy_to_user((void __user *)addr + status_size, cr + status_size, + len - status_size); + /* + * Copy status only after the rest of completion record is copied + * successfully so that the user gets the complete completion record + * when a non-zero status is polled. + */ + if (!left) { + u8 status; + + /* + * Ensure that the completion record's status field is written + * after the rest of the completion record has been written. + * This ensures that the user receives the correct completion + * record information once polling for a non-zero status. + */ + wmb(); + status = *(u8 *)cr; + if (put_user(status, (u8 __user *)addr)) + left += status_size; + } else { + left += status_size; + } + kthread_unuse_mm(mm); + +out: + mutex_unlock(&wq->uc_lock); + + return len - left; +} diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index 14c6ef987fed..c3ace4aed0fc 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -185,6 +185,7 @@ struct idxd_wq { struct idxd_dev idxd_dev; struct idxd_cdev *idxd_cdev; struct wait_queue_head err_queue; + struct workqueue_struct *wq; struct idxd_device *idxd; int id; struct idxd_irq_entry ie; @@ -214,6 +215,10 @@ struct idxd_wq { char name[WQ_NAME_SIZE + 1]; u64 max_xfer_bytes; u32 max_batch_size; + + /* Lock to protect upasid_xa access. */ + struct mutex uc_lock; + struct xarray upasid_xa; }; struct idxd_engine { @@ -665,6 +670,8 @@ void idxd_cdev_remove(void); int idxd_cdev_get_major(struct idxd_device *idxd); int idxd_wq_add_cdev(struct idxd_wq *wq); void idxd_wq_del_cdev(struct idxd_wq *wq); +int idxd_copy_cr(struct idxd_wq *wq, ioasid_t pasid, unsigned long addr, + void *buf, int len); /* perfmon */ #if IS_ENABLED(CONFIG_INTEL_IDXD_PERFMON) diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 906d9168fce2..b699813d3a9d 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -140,6 +140,25 @@ static void idxd_cleanup_interrupts(struct idxd_device *idxd) pci_free_irq_vectors(pdev); } +static void idxd_clean_wqs(struct idxd_device *idxd) +{ + struct idxd_wq *wq; + struct device *conf_dev; + int i; + + for (i = 0; i < idxd->max_wqs; i++) { + wq = idxd->wqs[i]; + if (idxd->hw.wq_cap.op_config) + bitmap_free(wq->opcap_bmap); + kfree(wq->wqcfg); + conf_dev = wq_confdev(wq); + put_device(conf_dev); + kfree(wq); + } + bitmap_free(idxd->wq_enable_map); + kfree(idxd->wqs); +} + static int idxd_setup_wqs(struct idxd_device *idxd) { struct device *dev = &idxd->pdev->dev; @@ -154,8 +173,8 @@ static int idxd_setup_wqs(struct idxd_device *idxd) idxd->wq_enable_map = bitmap_zalloc_node(idxd->max_wqs, GFP_KERNEL, dev_to_node(dev)); if (!idxd->wq_enable_map) { - kfree(idxd->wqs); - return -ENOMEM; + rc = -ENOMEM; + goto err_bitmap; } for (i = 0; i < idxd->max_wqs; i++) { @@ -174,10 +193,8 @@ static int idxd_setup_wqs(struct idxd_device *idxd) conf_dev->bus = &dsa_bus_type; conf_dev->type = &idxd_wq_device_type; rc = dev_set_name(conf_dev, "wq%d.%d", idxd->id, wq->id); - if (rc < 0) { - put_device(conf_dev); + if (rc < 0) goto err; - } mutex_init(&wq->wq_lock); init_waitqueue_head(&wq->err_queue); @@ -188,7 +205,6 @@ static int idxd_setup_wqs(struct idxd_device *idxd) wq->enqcmds_retries = IDXD_ENQCMDS_RETRIES; wq->wqcfg = kzalloc_node(idxd->wqcfg_size, GFP_KERNEL, dev_to_node(dev)); if (!wq->wqcfg) { - put_device(conf_dev); rc = -ENOMEM; goto err; } @@ -196,26 +212,58 @@ static int idxd_setup_wqs(struct idxd_device *idxd) if (idxd->hw.wq_cap.op_config) { wq->opcap_bmap = bitmap_zalloc(IDXD_MAX_OPCAP_BITS, GFP_KERNEL); if (!wq->opcap_bmap) { - put_device(conf_dev); rc = -ENOMEM; - goto err; + goto err_opcap_bmap; } bitmap_copy(wq->opcap_bmap, idxd->opcap_bmap, IDXD_MAX_OPCAP_BITS); } + mutex_init(&wq->uc_lock); + xa_init(&wq->upasid_xa); idxd->wqs[i] = wq; } return 0; - err: +err_opcap_bmap: + kfree(wq->wqcfg); + +err: + put_device(conf_dev); + kfree(wq); + while (--i >= 0) { wq = idxd->wqs[i]; + if (idxd->hw.wq_cap.op_config) + bitmap_free(wq->opcap_bmap); + kfree(wq->wqcfg); conf_dev = wq_confdev(wq); put_device(conf_dev); + kfree(wq); + } + bitmap_free(idxd->wq_enable_map); + +err_bitmap: + kfree(idxd->wqs); + return rc; } +static void idxd_clean_engines(struct idxd_device *idxd) +{ + struct idxd_engine *engine; + struct device *conf_dev; + int i; + + for (i = 0; i < idxd->max_engines; i++) { + engine = idxd->engines[i]; + conf_dev = engine_confdev(engine); + put_device(conf_dev); + kfree(engine); + } + kfree(idxd->engines); +} + static int idxd_setup_engines(struct idxd_device *idxd) { struct idxd_engine *engine; @@ -246,6 +294,7 @@ static int idxd_setup_engines(struct idxd_device *idxd) rc = dev_set_name(conf_dev, "engine%d.%d", idxd->id, engine->id); if (rc < 0) { put_device(conf_dev); + kfree(engine); goto err; } @@ -259,10 +308,26 @@ static int idxd_setup_engines(struct idxd_device *idxd) engine = idxd->engines[i]; conf_dev = engine_confdev(engine); put_device(conf_dev); + kfree(engine); } + kfree(idxd->engines); + return rc; } +static void idxd_clean_groups(struct idxd_device *idxd) +{ + struct idxd_group *group; + int i; + + for (i = 0; i < idxd->max_groups; i++) { + group = idxd->groups[i]; + put_device(group_confdev(group)); + kfree(group); + } + kfree(idxd->groups); +} + static int idxd_setup_groups(struct idxd_device *idxd) { struct device *dev = &idxd->pdev->dev; @@ -293,6 +358,7 @@ static int idxd_setup_groups(struct idxd_device *idxd) rc = dev_set_name(conf_dev, "group%d.%d", idxd->id, group->id); if (rc < 0) { put_device(conf_dev); + kfree(group); goto err; } @@ -312,27 +378,25 @@ static int idxd_setup_groups(struct idxd_device *idxd) while (--i >= 0) { group = idxd->groups[i]; put_device(group_confdev(group)); + kfree(group); } + kfree(idxd->groups); + return rc; } static void idxd_cleanup_internals(struct idxd_device *idxd) { - int i; - - for (i = 0; i < idxd->max_groups; i++) - put_device(group_confdev(idxd->groups[i])); - for (i = 0; i < idxd->max_engines; i++) - put_device(engine_confdev(idxd->engines[i])); - for (i = 0; i < idxd->max_wqs; i++) - put_device(wq_confdev(idxd->wqs[i])); + idxd_clean_groups(idxd); + idxd_clean_engines(idxd); + idxd_clean_wqs(idxd); destroy_workqueue(idxd->wq); } static int idxd_setup_internals(struct idxd_device *idxd) { struct device *dev = &idxd->pdev->dev; - int rc, i; + int rc; init_waitqueue_head(&idxd->cmd_waitq); @@ -357,14 +421,11 @@ static int idxd_setup_internals(struct idxd_device *idxd) return 0; err_wkq_create: - for (i = 0; i < idxd->max_groups; i++) - put_device(group_confdev(idxd->groups[i])); + idxd_clean_groups(idxd); err_group: - for (i = 0; i < idxd->max_engines; i++) - put_device(engine_confdev(idxd->engines[i])); + idxd_clean_engines(idxd); err_engine: - for (i = 0; i < idxd->max_wqs; i++) - put_device(wq_confdev(idxd->wqs[i])); + idxd_clean_wqs(idxd); err_wqs: return rc; } @@ -460,6 +521,17 @@ static void idxd_read_caps(struct idxd_device *idxd) multi_u64_to_bmap(idxd->opcap_bmap, &idxd->hw.opcap.bits[0], 4); } +static void idxd_free(struct idxd_device *idxd) +{ + if (!idxd) + return; + + put_device(idxd_confdev(idxd)); + bitmap_free(idxd->opcap_bmap); + ida_free(&idxd_ida, idxd->id); + kfree(idxd); +} + static struct idxd_device *idxd_alloc(struct pci_dev *pdev, struct idxd_driver_data *data) { struct device *dev = &pdev->dev; @@ -477,28 +549,34 @@ static struct idxd_device *idxd_alloc(struct pci_dev *pdev, struct idxd_driver_d idxd_dev_set_type(&idxd->idxd_dev, idxd->data->type); idxd->id = ida_alloc(&idxd_ida, GFP_KERNEL); if (idxd->id < 0) - return NULL; + goto err_ida; idxd->opcap_bmap = bitmap_zalloc_node(IDXD_MAX_OPCAP_BITS, GFP_KERNEL, dev_to_node(dev)); - if (!idxd->opcap_bmap) { - ida_free(&idxd_ida, idxd->id); - return NULL; - } + if (!idxd->opcap_bmap) + goto err_opcap; device_initialize(conf_dev); conf_dev->parent = dev; conf_dev->bus = &dsa_bus_type; conf_dev->type = idxd->data->dev_type; rc = dev_set_name(conf_dev, "%s%d", idxd->data->name_prefix, idxd->id); - if (rc < 0) { - put_device(conf_dev); - return NULL; - } + if (rc < 0) + goto err_name; spin_lock_init(&idxd->dev_lock); spin_lock_init(&idxd->cmd_lock); return idxd; + +err_name: + put_device(conf_dev); + bitmap_free(idxd->opcap_bmap); +err_opcap: + ida_free(&idxd_ida, idxd->id); +err_ida: + kfree(idxd); + + return NULL; } static int idxd_enable_system_pasid(struct idxd_device *idxd) @@ -651,7 +729,7 @@ static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) err: pci_iounmap(pdev, idxd->reg_base); err_iomap: - put_device(idxd_confdev(idxd)); + idxd_free(idxd); err_idxd_alloc: pci_disable_device(pdev); return rc; @@ -714,6 +792,7 @@ static void idxd_remove(struct pci_dev *pdev) destroy_workqueue(idxd->wq); perfmon_pmu_remove(idxd); put_device(idxd_confdev(idxd)); + idxd_free(idxd); } static struct pci_driver idxd_pci_driver = { diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c index c811757d0f97..0689464c4816 100644 --- a/drivers/dma/idxd/sysfs.c +++ b/drivers/dma/idxd/sysfs.c @@ -1315,6 +1315,7 @@ static void idxd_conf_wq_release(struct device *dev) bitmap_free(wq->opcap_bmap); kfree(wq->wqcfg); + xa_destroy(&wq->upasid_xa); kfree(wq); } diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c index e323e1a5f20f..edad538928dd 100644 --- a/drivers/dma/ti/k3-udma.c +++ b/drivers/dma/ti/k3-udma.c @@ -1088,8 +1088,11 @@ static void udma_check_tx_completion(struct work_struct *work) u32 residue_diff; ktime_t time_diff; unsigned long delay; + unsigned long flags; while (1) { + spin_lock_irqsave(&uc->vc.lock, flags); + if (uc->desc) { /* Get previous residue and time stamp */ residue_diff = uc->tx_drain.residue; @@ -1124,6 +1127,8 @@ static void udma_check_tx_completion(struct work_struct *work) break; } + spin_unlock_irqrestore(&uc->vc.lock, flags); + usleep_range(ktime_to_us(delay), ktime_to_us(delay) + 10); continue; @@ -1140,6 +1145,8 @@ static void udma_check_tx_completion(struct work_struct *work) break; } + + spin_unlock_irqrestore(&uc->vc.lock, flags); } static irqreturn_t udma_ring_irq_handler(int irq, void *data) @@ -4209,7 +4216,6 @@ static struct dma_chan *udma_of_xlate(struct of_phandle_args *dma_spec, struct of_dma *ofdma) { struct udma_dev *ud = ofdma->of_dma_data; - dma_cap_mask_t mask = ud->ddev.cap_mask; struct udma_filter_param filter_param; struct dma_chan *chan; @@ -4241,7 +4247,7 @@ static struct dma_chan *udma_of_xlate(struct of_phandle_args *dma_spec, } } - chan = __dma_request_channel(&mask, udma_dma_filter_fn, &filter_param, + chan = __dma_request_channel(&ud->ddev.cap_mask, udma_dma_filter_fn, &filter_param, ofdma->of_node); if (!chan) { dev_err(ud->dev, "get channel fail in %s.\n", __func__); diff --git a/drivers/edac/ie31200_edac.c b/drivers/edac/ie31200_edac.c index 56be8ef40f37..e3635fba63b4 100644 --- a/drivers/edac/ie31200_edac.c +++ b/drivers/edac/ie31200_edac.c @@ -405,10 +405,9 @@ static int ie31200_probe1(struct pci_dev *pdev, int dev_idx) int i, j, ret; struct mem_ctl_info *mci = NULL; struct edac_mc_layer layers[2]; - struct dimm_data dimm_info[IE31200_CHANNELS][IE31200_DIMMS_PER_CHANNEL]; void __iomem *window; struct ie31200_priv *priv; - u32 addr_decode, mad_offset; + u32 addr_decode[IE31200_CHANNELS], mad_offset; /* * Kaby Lake, Coffee Lake seem to work like Skylake. Please re-visit @@ -466,19 +465,10 @@ static int ie31200_probe1(struct pci_dev *pdev, int dev_idx) mad_offset = IE31200_MAD_DIMM_0_OFFSET; } - /* populate DIMM info */ for (i = 0; i < IE31200_CHANNELS; i++) { - addr_decode = readl(window + mad_offset + + addr_decode[i] = readl(window + mad_offset + (i * 4)); - edac_dbg(0, "addr_decode: 0x%x\n", addr_decode); - for (j = 0; j < IE31200_DIMMS_PER_CHANNEL; j++) { - populate_dimm_info(&dimm_info[i][j], addr_decode, j, - skl); - edac_dbg(0, "size: 0x%x, rank: %d, width: %d\n", - dimm_info[i][j].size, - dimm_info[i][j].dual_rank, - dimm_info[i][j].x16_width); - } + edac_dbg(0, "addr_decode: 0x%x\n", addr_decode[i]); } /* @@ -489,14 +479,22 @@ static int ie31200_probe1(struct pci_dev *pdev, int dev_idx) */ for (i = 0; i < IE31200_DIMMS_PER_CHANNEL; i++) { for (j = 0; j < IE31200_CHANNELS; j++) { + struct dimm_data dimm_info; struct dimm_info *dimm; unsigned long nr_pages; - nr_pages = IE31200_PAGES(dimm_info[j][i].size, skl); + populate_dimm_info(&dimm_info, addr_decode[j], i, + skl); + edac_dbg(0, "size: 0x%x, rank: %d, width: %d\n", + dimm_info.size, + dimm_info.dual_rank, + dimm_info.x16_width); + + nr_pages = IE31200_PAGES(dimm_info.size, skl); if (nr_pages == 0) continue; - if (dimm_info[j][i].dual_rank) { + if (dimm_info.dual_rank) { nr_pages = nr_pages / 2; dimm = edac_get_dimm(mci, (i * 2) + 1, j, 0); dimm->nr_pages = nr_pages; diff --git a/drivers/firmware/arm_ffa/bus.c b/drivers/firmware/arm_ffa/bus.c index 248594b59c64..5bda5d7ade42 100644 --- a/drivers/firmware/arm_ffa/bus.c +++ b/drivers/firmware/arm_ffa/bus.c @@ -191,6 +191,7 @@ struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id, dev = &ffa_dev->dev; dev->bus = &ffa_bus_type; dev->release = ffa_release_device; + dev->dma_mask = &dev->coherent_dma_mask; dev_set_name(&ffa_dev->dev, "arm-ffa-%d", id); ffa_dev->id = id; diff --git a/drivers/fpga/altera-cvp.c b/drivers/fpga/altera-cvp.c index 4ffb9da537d8..5295ff90482b 100644 --- a/drivers/fpga/altera-cvp.c +++ b/drivers/fpga/altera-cvp.c @@ -52,7 +52,7 @@ /* V2 Defines */ #define VSE_CVP_TX_CREDITS 0x49 /* 8bit */ -#define V2_CREDIT_TIMEOUT_US 20000 +#define V2_CREDIT_TIMEOUT_US 40000 #define V2_CHECK_CREDIT_US 10 #define V2_POLL_TIMEOUT_US 1000000 #define V2_USER_TIMEOUT_US 500000 diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c index 262b3d276df7..f81d79a297a5 100644 --- a/drivers/gpio/gpio-pca953x.c +++ b/drivers/gpio/gpio-pca953x.c @@ -10,8 +10,9 @@ #include #include -#include +#include #include +#include #include #include #include @@ -20,6 +21,7 @@ #include #include #include +#include #include #include @@ -522,12 +524,10 @@ static int pca953x_gpio_direction_input(struct gpio_chip *gc, unsigned off) struct pca953x_chip *chip = gpiochip_get_data(gc); u8 dirreg = chip->recalc_addr(chip, chip->regs->direction, off); u8 bit = BIT(off % BANK_SZ); - int ret; - mutex_lock(&chip->i2c_lock); - ret = regmap_write_bits(chip->regmap, dirreg, bit, bit); - mutex_unlock(&chip->i2c_lock); - return ret; + guard(mutex)(&chip->i2c_lock); + + return regmap_write_bits(chip->regmap, dirreg, bit, bit); } static int pca953x_gpio_direction_output(struct gpio_chip *gc, @@ -539,17 +539,15 @@ static int pca953x_gpio_direction_output(struct gpio_chip *gc, u8 bit = BIT(off % BANK_SZ); int ret; - mutex_lock(&chip->i2c_lock); + guard(mutex)(&chip->i2c_lock); + /* set output level */ ret = regmap_write_bits(chip->regmap, outreg, bit, val ? bit : 0); if (ret) - goto exit; + return ret; /* then direction */ - ret = regmap_write_bits(chip->regmap, dirreg, bit, 0); -exit: - mutex_unlock(&chip->i2c_lock); - return ret; + return regmap_write_bits(chip->regmap, dirreg, bit, 0); } static int pca953x_gpio_get_value(struct gpio_chip *gc, unsigned off) @@ -560,9 +558,8 @@ static int pca953x_gpio_get_value(struct gpio_chip *gc, unsigned off) u32 reg_val; int ret; - mutex_lock(&chip->i2c_lock); - ret = regmap_read(chip->regmap, inreg, ®_val); - mutex_unlock(&chip->i2c_lock); + scoped_guard(mutex, &chip->i2c_lock) + ret = regmap_read(chip->regmap, inreg, ®_val); if (ret < 0) return ret; @@ -575,9 +572,9 @@ static void pca953x_gpio_set_value(struct gpio_chip *gc, unsigned off, int val) u8 outreg = chip->recalc_addr(chip, chip->regs->output, off); u8 bit = BIT(off % BANK_SZ); - mutex_lock(&chip->i2c_lock); + guard(mutex)(&chip->i2c_lock); + regmap_write_bits(chip->regmap, outreg, bit, val ? bit : 0); - mutex_unlock(&chip->i2c_lock); } static int pca953x_gpio_get_direction(struct gpio_chip *gc, unsigned off) @@ -588,9 +585,8 @@ static int pca953x_gpio_get_direction(struct gpio_chip *gc, unsigned off) u32 reg_val; int ret; - mutex_lock(&chip->i2c_lock); - ret = regmap_read(chip->regmap, dirreg, ®_val); - mutex_unlock(&chip->i2c_lock); + scoped_guard(mutex, &chip->i2c_lock) + ret = regmap_read(chip->regmap, dirreg, ®_val); if (ret < 0) return ret; @@ -607,9 +603,8 @@ static int pca953x_gpio_get_multiple(struct gpio_chip *gc, DECLARE_BITMAP(reg_val, MAX_LINE); int ret; - mutex_lock(&chip->i2c_lock); - ret = pca953x_read_regs(chip, chip->regs->input, reg_val); - mutex_unlock(&chip->i2c_lock); + scoped_guard(mutex, &chip->i2c_lock) + ret = pca953x_read_regs(chip, chip->regs->input, reg_val); if (ret) return ret; @@ -624,16 +619,15 @@ static void pca953x_gpio_set_multiple(struct gpio_chip *gc, DECLARE_BITMAP(reg_val, MAX_LINE); int ret; - mutex_lock(&chip->i2c_lock); + guard(mutex)(&chip->i2c_lock); + ret = pca953x_read_regs(chip, chip->regs->output, reg_val); if (ret) - goto exit; + return; bitmap_replace(reg_val, reg_val, bits, mask, gc->ngpio); pca953x_write_regs(chip, chip->regs->output, reg_val); -exit: - mutex_unlock(&chip->i2c_lock); } static int pca953x_gpio_set_pull_up_down(struct pca953x_chip *chip, @@ -641,7 +635,6 @@ static int pca953x_gpio_set_pull_up_down(struct pca953x_chip *chip, unsigned long config) { enum pin_config_param param = pinconf_to_config_param(config); - u8 pull_en_reg = chip->recalc_addr(chip, PCAL953X_PULL_EN, offset); u8 pull_sel_reg = chip->recalc_addr(chip, PCAL953X_PULL_SEL, offset); u8 bit = BIT(offset % BANK_SZ); @@ -654,7 +647,7 @@ static int pca953x_gpio_set_pull_up_down(struct pca953x_chip *chip, if (!(chip->driver_data & PCA_PCAL)) return -ENOTSUPP; - mutex_lock(&chip->i2c_lock); + guard(mutex)(&chip->i2c_lock); /* Configure pull-up/pull-down */ if (param == PIN_CONFIG_BIAS_PULL_UP) @@ -664,17 +657,13 @@ static int pca953x_gpio_set_pull_up_down(struct pca953x_chip *chip, else ret = 0; if (ret) - goto exit; + return ret; /* Disable/Enable pull-up/pull-down */ if (param == PIN_CONFIG_BIAS_DISABLE) - ret = regmap_write_bits(chip->regmap, pull_en_reg, bit, 0); + return regmap_write_bits(chip->regmap, pull_en_reg, bit, 0); else - ret = regmap_write_bits(chip->regmap, pull_en_reg, bit, bit); - -exit: - mutex_unlock(&chip->i2c_lock); - return ret; + return regmap_write_bits(chip->regmap, pull_en_reg, bit, bit); } static int pca953x_gpio_set_config(struct gpio_chip *gc, unsigned int offset, @@ -887,10 +876,8 @@ static irqreturn_t pca953x_irq_handler(int irq, void *devid) bitmap_zero(pending, MAX_LINE); - mutex_lock(&chip->i2c_lock); - ret = pca953x_irq_pending(chip, pending); - mutex_unlock(&chip->i2c_lock); - + scoped_guard(mutex, &chip->i2c_lock) + ret = pca953x_irq_pending(chip, pending); if (ret) { ret = 0; @@ -1199,9 +1186,9 @@ static void pca953x_remove(struct i2c_client *client) } #ifdef CONFIG_PM_SLEEP -static int pca953x_regcache_sync(struct device *dev) +static int pca953x_regcache_sync(struct pca953x_chip *chip) { - struct pca953x_chip *chip = dev_get_drvdata(dev); + struct device *dev = &chip->client->dev; int ret; u8 regaddr; @@ -1248,13 +1235,38 @@ static int pca953x_regcache_sync(struct device *dev) return 0; } +static int pca953x_restore_context(struct pca953x_chip *chip) +{ + int ret; + + guard(mutex)(&chip->i2c_lock); + + if (chip->client->irq > 0) + enable_irq(chip->client->irq); + regcache_cache_only(chip->regmap, false); + regcache_mark_dirty(chip->regmap); + ret = pca953x_regcache_sync(chip); + if (ret) + return ret; + + return regcache_sync(chip->regmap); +} + +static void pca953x_save_context(struct pca953x_chip *chip) +{ + guard(mutex)(&chip->i2c_lock); + + /* Disable IRQ to prevent early triggering while regmap "cache only" is on */ + if (chip->client->irq > 0) + disable_irq(chip->client->irq); + regcache_cache_only(chip->regmap, true); +} + static int pca953x_suspend(struct device *dev) { struct pca953x_chip *chip = dev_get_drvdata(dev); - mutex_lock(&chip->i2c_lock); - regcache_cache_only(chip->regmap, true); - mutex_unlock(&chip->i2c_lock); + pca953x_save_context(chip); if (atomic_read(&chip->wakeup_path)) device_set_wakeup_path(dev); @@ -1277,17 +1289,7 @@ static int pca953x_resume(struct device *dev) } } - mutex_lock(&chip->i2c_lock); - regcache_cache_only(chip->regmap, false); - regcache_mark_dirty(chip->regmap); - ret = pca953x_regcache_sync(dev); - if (ret) { - mutex_unlock(&chip->i2c_lock); - return ret; - } - - ret = regcache_sync(chip->regmap); - mutex_unlock(&chip->i2c_lock); + ret = pca953x_restore_context(chip); if (ret) { dev_err(dev, "Failed to restore register map: %d\n", ret); return ret; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index dd22d2559720..af86402c70a9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -781,6 +781,7 @@ struct amdgpu_device { bool need_swiotlb; bool accel_working; struct notifier_block acpi_nb; + struct notifier_block pm_nb; struct amdgpu_i2c_chan *i2c_bus[AMDGPU_MAX_I2C_BUS]; struct debugfs_blob_wrapper debugfs_vbios_blob; struct debugfs_blob_wrapper debugfs_discovery_blob; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index fcd0c61499f8..079cf3292f63 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -139,6 +139,10 @@ const char *amdgpu_asic_name[] = { "LAST", }; +static inline void amdgpu_device_stop_pending_resets(struct amdgpu_device *adev); +static int amdgpu_device_pm_notifier(struct notifier_block *nb, unsigned long mode, + void *data); + /** * DOC: pcie_replay_count * @@ -3990,6 +3994,11 @@ fence_driver_init: amdgpu_device_check_iommu_direct_map(adev); + adev->pm_nb.notifier_call = amdgpu_device_pm_notifier; + r = register_pm_notifier(&adev->pm_nb); + if (r) + goto failed; + return 0; release_ras_con: @@ -4051,6 +4060,8 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev) flush_delayed_work(&adev->delayed_init_work); adev->shutdown = true; + unregister_pm_notifier(&adev->pm_nb); + /* make sure IB test finished before entering exclusive mode * to avoid preemption on IB test * */ @@ -4181,6 +4192,33 @@ static int amdgpu_device_evict_resources(struct amdgpu_device *adev) /* * Suspend & resume. */ +/** + * amdgpu_device_pm_notifier - Notification block for Suspend/Hibernate events + * @nb: notifier block + * @mode: suspend mode + * @data: data + * + * This function is called when the system is about to suspend or hibernate. + * It is used to set the appropriate flags so that eviction can be optimized + * in the pm prepare callback. + */ +static int amdgpu_device_pm_notifier(struct notifier_block *nb, unsigned long mode, + void *data) +{ + struct amdgpu_device *adev = container_of(nb, struct amdgpu_device, pm_nb); + + switch (mode) { + case PM_HIBERNATION_PREPARE: + adev->in_s4 = true; + break; + case PM_POST_HIBERNATION: + adev->in_s4 = false; + break; + } + + return NOTIFY_DONE; +} + /** * amdgpu_device_prepare - prepare for device suspend * @@ -4631,6 +4669,8 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev, retry: amdgpu_amdkfd_pre_reset(adev); + amdgpu_device_stop_pending_resets(adev); + if (from_hypervisor) r = amdgpu_virt_request_full_gpu(adev, true); else @@ -5502,11 +5542,12 @@ retry: /* Rest of adevs pre asic reset from XGMI hive. */ tmp_adev->asic_reset_res = r; } - /* - * Drop all pending non scheduler resets. Scheduler resets - * were already dropped during drm_sched_stop - */ - amdgpu_device_stop_pending_resets(tmp_adev); + if (!amdgpu_sriov_vf(tmp_adev)) + /* + * Drop all pending non scheduler resets. Scheduler resets + * were already dropped during drm_sched_stop + */ + amdgpu_device_stop_pending_resets(tmp_adev); } tmp_vram_lost_counter = atomic_read(&((adev)->vram_lost_counter)); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index ab06cb4d7b35..4dcc7de961d0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -42,6 +42,29 @@ #include #include +static const struct dma_buf_attach_ops amdgpu_dma_buf_attach_ops; + +/** + * dma_buf_attach_adev - Helper to get adev of an attachment + * + * @attach: attachment + * + * Returns: + * A struct amdgpu_device * if the attaching device is an amdgpu device or + * partition, NULL otherwise. + */ +static struct amdgpu_device *dma_buf_attach_adev(struct dma_buf_attachment *attach) +{ + if (attach->importer_ops == &amdgpu_dma_buf_attach_ops) { + struct drm_gem_object *obj = attach->importer_priv; + struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj); + + return amdgpu_ttm_adev(bo->tbo.bdev); + } + + return NULL; +} + /** * amdgpu_dma_buf_attach - &dma_buf_ops.attach implementation * @@ -53,12 +76,14 @@ static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf, struct dma_buf_attachment *attach) { + struct amdgpu_device *attach_adev = dma_buf_attach_adev(attach); struct drm_gem_object *obj = dmabuf->priv; struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj); struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); int r; - if (pci_p2pdma_distance(adev->pdev, attach->dev, false) < 0) + if (!amdgpu_dmabuf_is_xgmi_accessible(attach_adev, bo) && + pci_p2pdma_distance(adev->pdev, attach->dev, false) < 0) attach->peer2peer = false; r = pm_runtime_get_sync(adev_to_drm(adev)->dev); @@ -479,6 +504,9 @@ bool amdgpu_dmabuf_is_xgmi_accessible(struct amdgpu_device *adev, struct drm_gem_object *obj = &bo->tbo.base; struct drm_gem_object *gobj; + if (!adev) + return false; + if (obj->import_attach) { struct dma_buf *dma_buf = obj->import_attach->dmabuf; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 0a85a59519ca..1fbb73b2691d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2468,7 +2468,6 @@ static int amdgpu_pmops_freeze(struct device *dev) struct amdgpu_device *adev = drm_to_adev(drm_dev); int r; - adev->in_s4 = true; r = amdgpu_device_suspend(drm_dev, true); if (r) return r; @@ -2481,13 +2480,8 @@ static int amdgpu_pmops_freeze(struct device *dev) static int amdgpu_pmops_thaw(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); - struct amdgpu_device *adev = drm_to_adev(drm_dev); - int r; - r = amdgpu_device_resume(drm_dev, true); - adev->in_s4 = false; - - return r; + return amdgpu_device_resume(drm_dev, true); } static int amdgpu_pmops_poweroff(struct device *dev) @@ -2500,9 +2494,6 @@ static int amdgpu_pmops_poweroff(struct device *dev) static int amdgpu_pmops_restore(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); - struct amdgpu_device *adev = drm_to_adev(drm_dev); - - adev->in_s4 = false; return amdgpu_device_resume(drm_dev, true); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index f8740ad08af4..ae6643c8ade6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -43,7 +43,7 @@ #include "amdgpu_securedisplay.h" #include "amdgpu_atomfirmware.h" -#define AMD_VBIOS_FILE_MAX_SIZE_B (1024*1024*3) +#define AMD_VBIOS_FILE_MAX_SIZE_B (1024*1024*16) static int psp_sysfs_init(struct amdgpu_device *adev); static void psp_sysfs_fini(struct amdgpu_device *adev); @@ -484,7 +484,6 @@ static int psp_sw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; struct psp_context *psp = &adev->psp; - struct psp_gfx_cmd_resp *cmd = psp->cmd; psp_memory_training_fini(psp); if (psp->sos_fw) { @@ -511,8 +510,8 @@ static int psp_sw_fini(void *handle) adev->ip_versions[MP0_HWIP][0] == IP_VERSION(11, 0, 7)) psp_sysfs_fini(adev); - kfree(cmd); - cmd = NULL; + kfree(psp->cmd); + psp->cmd = NULL; psp_free_shared_bufs(psp); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c index d7b76a3d2d55..6174bef0ecb8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c @@ -32,6 +32,7 @@ #include "amdgpu.h" #include "amdgpu_ras.h" +#include "amdgpu_reset.h" #include "vi.h" #include "soc15.h" #include "nv.h" @@ -456,7 +457,7 @@ static int amdgpu_virt_read_pf2vf_data(struct amdgpu_device *adev) return -EINVAL; if (pf2vf_info->size > 1024) { - DRM_ERROR("invalid pf2vf message size\n"); + dev_err(adev->dev, "invalid pf2vf message size: 0x%x\n", pf2vf_info->size); return -EINVAL; } @@ -467,7 +468,9 @@ static int amdgpu_virt_read_pf2vf_data(struct amdgpu_device *adev) adev->virt.fw_reserve.p_pf2vf, pf2vf_info->size, adev->virt.fw_reserve.checksum_key, checksum); if (checksum != checkval) { - DRM_ERROR("invalid pf2vf message\n"); + dev_err(adev->dev, + "invalid pf2vf message: header checksum=0x%x calculated checksum=0x%x\n", + checksum, checkval); return -EINVAL; } @@ -481,7 +484,9 @@ static int amdgpu_virt_read_pf2vf_data(struct amdgpu_device *adev) adev->virt.fw_reserve.p_pf2vf, pf2vf_info->size, 0, checksum); if (checksum != checkval) { - DRM_ERROR("invalid pf2vf message\n"); + dev_err(adev->dev, + "invalid pf2vf message: header checksum=0x%x calculated checksum=0x%x\n", + checksum, checkval); return -EINVAL; } @@ -517,7 +522,7 @@ static int amdgpu_virt_read_pf2vf_data(struct amdgpu_device *adev) ((struct amd_sriov_msg_pf2vf_info *)pf2vf_info)->uuid; break; default: - DRM_ERROR("invalid pf2vf version\n"); + dev_err(adev->dev, "invalid pf2vf version: 0x%x\n", pf2vf_info->version); return -EINVAL; } @@ -617,8 +622,21 @@ static void amdgpu_virt_update_vf2pf_work_item(struct work_struct *work) int ret; ret = amdgpu_virt_read_pf2vf_data(adev); - if (ret) + if (ret) { + adev->virt.vf2pf_update_retry_cnt++; + if ((adev->virt.vf2pf_update_retry_cnt >= AMDGPU_VF2PF_UPDATE_MAX_RETRY_LIMIT) && + amdgpu_sriov_runtime(adev) && !amdgpu_in_reset(adev)) { + if (amdgpu_reset_domain_schedule(adev->reset_domain, + &adev->virt.flr_work)) + return; + else + dev_err(adev->dev, "Failed to queue work! at %s", __func__); + } + goto out; + } + + adev->virt.vf2pf_update_retry_cnt = 0; amdgpu_virt_write_vf2pf_data(adev); out: @@ -639,6 +657,7 @@ void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev) adev->virt.fw_reserve.p_pf2vf = NULL; adev->virt.fw_reserve.p_vf2pf = NULL; adev->virt.vf2pf_update_interval_ms = 0; + adev->virt.vf2pf_update_retry_cnt = 0; if (adev->mman.fw_vram_usage_va != NULL) { /* go through this logic in ip_init and reset to init workqueue*/ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h index dc6aaa4d67be..fc2859726f0a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h @@ -51,6 +51,8 @@ /* tonga/fiji use this offset */ #define mmBIF_IOV_FUNC_IDENTIFIER 0x1503 +#define AMDGPU_VF2PF_UPDATE_MAX_RETRY_LIMIT 30 + enum amdgpu_sriov_vf_mode { SRIOV_VF_MODE_BARE_METAL = 0, SRIOV_VF_MODE_ONE_VF, @@ -250,6 +252,7 @@ struct amdgpu_virt { /* vf2pf message */ struct delayed_work vf2pf_work; uint32_t vf2pf_update_interval_ms; + int vf2pf_update_retry_cnt; /* multimedia bandwidth config */ bool is_mm_bw_enabled; diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c index ec4d5e15b766..de74686cb1db 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c @@ -92,12 +92,12 @@ static void gfxhub_v1_0_init_system_aperture_regs(struct amdgpu_device *adev) { uint64_t value; - /* Program the AGP BAR */ - WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_BASE, 0); - WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_BOT, adev->gmc.agp_start >> 24); - WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_TOP, adev->gmc.agp_end >> 24); - if (!amdgpu_sriov_vf(adev) || adev->asic_type <= CHIP_VEGA10) { + /* Program the AGP BAR */ + WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_BASE, 0); + WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_BOT, adev->gmc.agp_start >> 24); + WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_TOP, adev->gmc.agp_end >> 24); + /* Program the system aperture low logical page number. */ WREG32_SOC15_RLC(GC, 0, mmMC_VM_SYSTEM_APERTURE_LOW_ADDR, min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18); diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c b/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c index f52552c5fa27..6b9f2e1d9d69 100644 --- a/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c +++ b/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c @@ -34,7 +34,17 @@ static void hdp_v5_2_flush_hdp(struct amdgpu_device *adev, if (!ring || !ring->funcs->emit_wreg) { WREG32_NO_KIQ((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0); - RREG32_NO_KIQ((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2); + if (amdgpu_sriov_vf(adev)) { + /* this is fine because SR_IOV doesn't remap the register */ + RREG32_NO_KIQ((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2); + } else { + /* We just need to read back a register to post the write. + * Reading back the remapped register causes problems on + * some platforms so just read back the memory size register. + */ + if (adev->nbio.funcs->get_memsize) + adev->nbio.funcs->get_memsize(adev); + } } else { amdgpu_ring_emit_wreg(ring, (adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c index 12906ba74462..d39c6baae007 100644 --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c @@ -276,6 +276,8 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work) timeout -= 10; } while (timeout > 1); + dev_warn(adev->dev, "waiting IDH_FLR_NOTIFICATION_CMPL timeout\n"); + flr_done: atomic_set(&adev->reset_domain->in_gpu_reset, 0); up_write(&adev->reset_domain->sem); diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c index e07757eea7ad..a311a2425ec0 100644 --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c @@ -300,6 +300,8 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work) timeout -= 10; } while (timeout > 1); + dev_warn(adev->dev, "waiting IDH_FLR_NOTIFICATION_CMPL timeout\n"); + flr_done: atomic_set(&adev->reset_domain->in_gpu_reset, 0); up_write(&adev->reset_domain->sem); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index 8c6bd36296c4..d2a2d2c53ee3 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -813,6 +813,14 @@ struct kfd_process *kfd_create_process(struct file *filep) if (thread->group_leader->mm != thread->mm) return ERR_PTR(-EINVAL); + /* If the process just called exec(3), it is possible that the + * cleanup of the kfd_process (following the release of the mm + * of the old process image) is still in the cleanup work queue. + * Make sure to drain any job before trying to recreate any + * resource for this process. + */ + flush_workqueue(kfd_process_wq); + /* * take kfd processes mutex before starting of process creation * so there won't be a case where two threads of the same process @@ -825,14 +833,6 @@ struct kfd_process *kfd_create_process(struct file *filep) if (process) { pr_debug("Process already found\n"); } else { - /* If the process just called exec(3), it is possible that the - * cleanup of the kfd_process (following the release of the mm - * of the old process image) is still in the cleanup work queue. - * Make sure to drain any job before trying to recreate any - * resource for this process. - */ - flush_workqueue(kfd_process_wq); - process = create_process(thread); if (IS_ERR(process)) goto out; 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 7dee02e8ba6f..64f626cc7913 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2897,11 +2897,6 @@ static int dm_resume(void *handle) return 0; } - - /* leave display off for S4 sequence */ - if (adev->in_s4) - return 0; - /* Recreate dc_state - DC invalidates it when setting power state to S3. */ dc_release_state(dm_state->context); dm_state->context = dc_create_state(dm->dc); @@ -7281,7 +7276,7 @@ static int amdgpu_dm_i2c_xfer(struct i2c_adapter *i2c_adap, int i; int result = -EIO; - if (!ddc_service->ddc_pin || !ddc_service->ddc_pin->hw_info.hw_supported) + if (!ddc_service->ddc_pin) return result; cmd.payloads = kcalloc(num, sizeof(struct i2c_payload), GFP_KERNEL); @@ -10693,7 +10688,7 @@ int amdgpu_dm_process_dmub_aux_transfer_sync( * Transient states before tunneling is enabled could * lead to this error. We can ignore this for now. */ - if (p_notify->result != AUX_RET_ERROR_PROTOCOL_ERROR) { + if (p_notify->result == AUX_RET_ERROR_PROTOCOL_ERROR) { DRM_WARN("DPIA AUX failed on 0x%x(%d), error %d\n", payload->address, payload->length, p_notify->result); @@ -10702,22 +10697,15 @@ int amdgpu_dm_process_dmub_aux_transfer_sync( goto out; } + payload->reply[0] = adev->dm.dmub_notify->aux_reply.command & 0xF; + if (adev->dm.dmub_notify->aux_reply.command & 0xF0) + /* The reply is stored in the top nibble of the command. */ + payload->reply[0] = (adev->dm.dmub_notify->aux_reply.command >> 4) & 0xF; - payload->reply[0] = adev->dm.dmub_notify->aux_reply.command; - if (!payload->write && p_notify->aux_reply.length && - (payload->reply[0] == AUX_TRANSACTION_REPLY_AUX_ACK)) { - - if (payload->length != p_notify->aux_reply.length) { - DRM_WARN("invalid read length %d from DPIA AUX 0x%x(%d)!\n", - p_notify->aux_reply.length, - payload->address, payload->length); - *operation_result = AUX_RET_ERROR_INVALID_REPLY; - goto out; - } - + /*write req may receive a byte indicating partially written number as well*/ + if (p_notify->aux_reply.length) memcpy(payload->data, p_notify->aux_reply.data, p_notify->aux_reply.length); - } /* success */ ret = p_notify->aux_reply.length; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 5eb994ed5471..495491decec1 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -55,6 +55,9 @@ bool is_timing_changed(struct dc_stream_state *cur_stream, struct dc_stream_state *new_stream); +/* + * This function handles both native AUX and I2C-Over-AUX transactions. + */ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg) { @@ -63,6 +66,7 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux, enum aux_return_code_type operation_result; struct amdgpu_device *adev; struct ddc_service *ddc; + uint8_t copy[16]; if (WARN_ON(msg->size > 16)) return -E2BIG; @@ -78,6 +82,11 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux, (msg->request & DP_AUX_I2C_WRITE_STATUS_UPDATE) != 0; payload.defer_delay = 0; + if (payload.write) { + memcpy(copy, msg->buffer, msg->size); + payload.data = copy; + } + result = dc_link_aux_transfer_raw(TO_DM_AUX(aux)->ddc_service, &payload, &operation_result); @@ -91,15 +100,25 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux, if (adev->dm.aux_hpd_discon_quirk) { if (msg->address == DP_SIDEBAND_MSG_DOWN_REQ_BASE && operation_result == AUX_RET_ERROR_HPD_DISCON) { - result = 0; + result = msg->size; operation_result = AUX_RET_SUCCESS; } } - if (payload.write && result >= 0) - result = msg->size; + /* + * result equals to 0 includes the cases of AUX_DEFER/I2C_DEFER + */ + if (payload.write && result >= 0) { + if (result) { + /*one byte indicating partially written bytes*/ + drm_dbg_dp(adev_to_drm(adev), "amdgpu: AUX partially written\n"); + result = payload.data[0]; + } else if (!payload.reply[0]) + /*I2C_ACK|AUX_ACK*/ + result = msg->size; + } - if (result < 0) + if (result < 0) { switch (operation_result) { case AUX_RET_SUCCESS: break; @@ -118,6 +137,13 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux, break; } + drm_dbg_dp(adev_to_drm(adev), "amdgpu: DP AUX transfer fail:%d\n", operation_result); + } + + if (payload.reply[0]) + drm_dbg_dp(adev_to_drm(adev), "amdgpu: AUX reply command not ACK: 0x%02x.", + payload.reply[0]); + return result; } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c index 09eb1bc9aa03..9549f9c15229 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c @@ -116,7 +116,7 @@ static void dcn315_update_clocks(struct clk_mgr *clk_mgr_base, struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base); struct dc_clocks *new_clocks = &context->bw_ctx.bw.dcn.clk; struct dc *dc = clk_mgr_base->ctx->dc; - int display_count; + int display_count = 0; bool update_dppclk = false; bool update_dispclk = false; bool dpp_clock_lowered = false; @@ -192,15 +192,19 @@ static void dcn315_update_clocks(struct clk_mgr *clk_mgr_base, update_dppclk = true; } - if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) { - /* No need to apply the w/a if we haven't taken over from bios yet */ - if (clk_mgr_base->clks.dispclk_khz) - dcn315_disable_otg_wa(clk_mgr_base, context, true); + if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz) && + (new_clocks->dispclk_khz > 0 || (safe_to_lower && display_count == 0))) { + int requested_dispclk_khz = new_clocks->dispclk_khz; + dcn315_disable_otg_wa(clk_mgr_base, context, true); + + /* Clamp the requested clock to PMFW based on their limit. */ + if (dc->debug.min_disp_clk_khz > 0 && requested_dispclk_khz < dc->debug.min_disp_clk_khz) + requested_dispclk_khz = dc->debug.min_disp_clk_khz; + + dcn315_smu_set_dispclk(clk_mgr, requested_dispclk_khz); clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz; - dcn315_smu_set_dispclk(clk_mgr, clk_mgr_base->clks.dispclk_khz); - if (clk_mgr_base->clks.dispclk_khz) - dcn315_disable_otg_wa(clk_mgr_base, context, false); + dcn315_disable_otg_wa(clk_mgr_base, context, false); update_dispclk = true; } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c index 29d2003fb712..afce15aa2ff1 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c @@ -153,7 +153,7 @@ static void dcn316_update_clocks(struct clk_mgr *clk_mgr_base, struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base); struct dc_clocks *new_clocks = &context->bw_ctx.bw.dcn.clk; struct dc *dc = clk_mgr_base->ctx->dc; - int display_count; + int display_count = 0; bool update_dppclk = false; bool update_dispclk = false; bool dpp_clock_lowered = false; @@ -226,11 +226,18 @@ static void dcn316_update_clocks(struct clk_mgr *clk_mgr_base, update_dppclk = true; } - if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) { + if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz) && + (new_clocks->dispclk_khz > 0 || (safe_to_lower && display_count == 0))) { + int requested_dispclk_khz = new_clocks->dispclk_khz; + dcn316_disable_otg_wa(clk_mgr_base, context, safe_to_lower, true); + /* Clamp the requested clock to PMFW based on their limit. */ + if (dc->debug.min_disp_clk_khz > 0 && requested_dispclk_khz < dc->debug.min_disp_clk_khz) + requested_dispclk_khz = dc->debug.min_disp_clk_khz; + + dcn316_smu_set_dispclk(clk_mgr, requested_dispclk_khz); clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz; - dcn316_smu_set_dispclk(clk_mgr, clk_mgr_base->clks.dispclk_khz); dcn316_disable_otg_wa(clk_mgr_base, context, safe_to_lower, false); update_dispclk = true; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 2721842af806..10672bb90a02 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -267,6 +267,7 @@ static bool create_links( link->link_id.type = OBJECT_TYPE_CONNECTOR; link->link_id.id = CONNECTOR_ID_VIRTUAL; link->link_id.enum_id = ENUM_ID_1; + link->psr_settings.psr_version = DC_PSR_VERSION_UNSUPPORTED; link->link_enc = kzalloc(sizeof(*link->link_enc), GFP_KERNEL); if (!link->link_enc) { diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c index 50dc83404644..4ce45f1bdac0 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c @@ -392,11 +392,6 @@ bool dpp3_get_optimal_number_of_taps( int min_taps_y, min_taps_c; enum lb_memory_config lb_config; - if (scl_data->viewport.width > scl_data->h_active && - dpp->ctx->dc->debug.max_downscale_src_width != 0 && - scl_data->viewport.width > dpp->ctx->dc->debug.max_downscale_src_width) - return false; - /* * Set default taps if none are provided * From programming guide: taps = min{ ceil(2*H_RATIO,1), 8} for downscaling @@ -434,6 +429,12 @@ bool dpp3_get_optimal_number_of_taps( else scl_data->taps.h_taps_c = in_taps->h_taps_c; + // Avoid null data in the scl data with this early return, proceed non-adaptive calcualtion first + if (scl_data->viewport.width > scl_data->h_active && + dpp->ctx->dc->debug.max_downscale_src_width != 0 && + scl_data->viewport.width > dpp->ctx->dc->debug.max_downscale_src_width) + return false; + /*Ensure we can support the requested number of vtaps*/ min_taps_y = dc_fixpt_ceil(scl_data->ratios.vert); min_taps_c = dc_fixpt_ceil(scl_data->ratios.vert_c); diff --git a/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c b/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c index 958170fbfece..9d643c79afea 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c @@ -1717,7 +1717,7 @@ static int dcn315_populate_dml_pipes_from_context( pipes[pipe_cnt].dout.dsc_input_bpc = 0; DC_FP_START(); dcn31_zero_pipe_dcc_fraction(pipes, pipe_cnt); - if (pixel_rate_crb && !pipe->top_pipe && !pipe->prev_odm_pipe) { + if (pixel_rate_crb) { int bpp = source_format_to_bpp(pipes[pipe_cnt].pipe.src.source_format); /* Ceil to crb segment size */ int approx_det_segs_required_for_pstate = dcn_get_approx_det_segs_required_for_pstate( @@ -1768,28 +1768,26 @@ static int dcn315_populate_dml_pipes_from_context( continue; } - if (!pipe->top_pipe && !pipe->prev_odm_pipe) { - bool split_required = pipe->stream->timing.pix_clk_100hz >= dcn_get_max_non_odm_pix_rate_100hz(&dc->dml.soc) - || (pipe->plane_state && pipe->plane_state->src_rect.width > 5120); + bool split_required = pipe->stream->timing.pix_clk_100hz >= dcn_get_max_non_odm_pix_rate_100hz(&dc->dml.soc) + || (pipe->plane_state && pipe->plane_state->src_rect.width > 5120); - if (remaining_det_segs > MIN_RESERVED_DET_SEGS && crb_pipes != 0) - pipes[pipe_cnt].pipe.src.det_size_override += (remaining_det_segs - MIN_RESERVED_DET_SEGS) / crb_pipes + - (crb_idx < (remaining_det_segs - MIN_RESERVED_DET_SEGS) % crb_pipes ? 1 : 0); - if (pipes[pipe_cnt].pipe.src.det_size_override > 2 * DCN3_15_MAX_DET_SEGS) { - /* Clamp to 2 pipe split max det segments */ - remaining_det_segs += pipes[pipe_cnt].pipe.src.det_size_override - 2 * (DCN3_15_MAX_DET_SEGS); - pipes[pipe_cnt].pipe.src.det_size_override = 2 * DCN3_15_MAX_DET_SEGS; - } - if (pipes[pipe_cnt].pipe.src.det_size_override > DCN3_15_MAX_DET_SEGS || split_required) { - /* If we are splitting we must have an even number of segments */ - remaining_det_segs += pipes[pipe_cnt].pipe.src.det_size_override % 2; - pipes[pipe_cnt].pipe.src.det_size_override -= pipes[pipe_cnt].pipe.src.det_size_override % 2; - } - /* Convert segments into size for DML use */ - pipes[pipe_cnt].pipe.src.det_size_override *= DCN3_15_CRB_SEGMENT_SIZE_KB; - - crb_idx++; + if (remaining_det_segs > MIN_RESERVED_DET_SEGS && crb_pipes != 0) + pipes[pipe_cnt].pipe.src.det_size_override += (remaining_det_segs - MIN_RESERVED_DET_SEGS) / crb_pipes + + (crb_idx < (remaining_det_segs - MIN_RESERVED_DET_SEGS) % crb_pipes ? 1 : 0); + if (pipes[pipe_cnt].pipe.src.det_size_override > 2 * DCN3_15_MAX_DET_SEGS) { + /* Clamp to 2 pipe split max det segments */ + remaining_det_segs += pipes[pipe_cnt].pipe.src.det_size_override - 2 * (DCN3_15_MAX_DET_SEGS); + pipes[pipe_cnt].pipe.src.det_size_override = 2 * DCN3_15_MAX_DET_SEGS; } + if (pipes[pipe_cnt].pipe.src.det_size_override > DCN3_15_MAX_DET_SEGS || split_required) { + /* If we are splitting we must have an even number of segments */ + remaining_det_segs += pipes[pipe_cnt].pipe.src.det_size_override % 2; + pipes[pipe_cnt].pipe.src.det_size_override -= pipes[pipe_cnt].pipe.src.det_size_override % 2; + } + /* Convert segments into size for DML use */ + pipes[pipe_cnt].pipe.src.det_size_override *= DCN3_15_CRB_SEGMENT_SIZE_KB; + + crb_idx++; pipe_cnt++; } } diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c index 1bc0220e6783..9fe856fd8a84 100644 --- a/drivers/gpu/drm/ast/ast_mode.c +++ b/drivers/gpu/drm/ast/ast_mode.c @@ -103,7 +103,7 @@ static bool ast_get_vbios_mode_info(const struct drm_format_info *format, return false; } - switch (mode->crtc_hdisplay) { + switch (mode->hdisplay) { case 640: vbios_mode->enh_table = &res_640x480[refresh_rate_index]; break; @@ -117,7 +117,7 @@ static bool ast_get_vbios_mode_info(const struct drm_format_info *format, vbios_mode->enh_table = &res_1152x864[refresh_rate_index]; break; case 1280: - if (mode->crtc_vdisplay == 800) + if (mode->vdisplay == 800) vbios_mode->enh_table = &res_1280x800[refresh_rate_index]; else vbios_mode->enh_table = &res_1280x1024[refresh_rate_index]; @@ -129,7 +129,7 @@ static bool ast_get_vbios_mode_info(const struct drm_format_info *format, vbios_mode->enh_table = &res_1440x900[refresh_rate_index]; break; case 1600: - if (mode->crtc_vdisplay == 900) + if (mode->vdisplay == 900) vbios_mode->enh_table = &res_1600x900[refresh_rate_index]; else vbios_mode->enh_table = &res_1600x1200[refresh_rate_index]; @@ -138,7 +138,7 @@ static bool ast_get_vbios_mode_info(const struct drm_format_info *format, vbios_mode->enh_table = &res_1680x1050[refresh_rate_index]; break; case 1920: - if (mode->crtc_vdisplay == 1080) + if (mode->vdisplay == 1080) vbios_mode->enh_table = &res_1920x1080[refresh_rate_index]; else vbios_mode->enh_table = &res_1920x1200[refresh_rate_index]; @@ -182,6 +182,7 @@ static bool ast_get_vbios_mode_info(const struct drm_format_info *format, hborder = (vbios_mode->enh_table->flags & HBorder) ? 8 : 0; vborder = (vbios_mode->enh_table->flags & VBorder) ? 8 : 0; + adjusted_mode->crtc_hdisplay = vbios_mode->enh_table->hde; adjusted_mode->crtc_htotal = vbios_mode->enh_table->ht; adjusted_mode->crtc_hblank_start = vbios_mode->enh_table->hde + hborder; adjusted_mode->crtc_hblank_end = vbios_mode->enh_table->ht - hborder; @@ -191,6 +192,7 @@ static bool ast_get_vbios_mode_info(const struct drm_format_info *format, vbios_mode->enh_table->hfp + vbios_mode->enh_table->hsync); + adjusted_mode->crtc_vdisplay = vbios_mode->enh_table->vde; adjusted_mode->crtc_vtotal = vbios_mode->enh_table->vt; adjusted_mode->crtc_vblank_start = vbios_mode->enh_table->vde + vborder; adjusted_mode->crtc_vblank_end = vbios_mode->enh_table->vt - vborder; diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 66d223c2d9ab..e737e45a3a70 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -573,6 +573,30 @@ mode_valid(struct drm_atomic_state *state) return 0; } +static int drm_atomic_check_valid_clones(struct drm_atomic_state *state, + struct drm_crtc *crtc) +{ + struct drm_encoder *drm_enc; + struct drm_crtc_state *crtc_state = drm_atomic_get_new_crtc_state(state, + crtc); + + drm_for_each_encoder_mask(drm_enc, crtc->dev, crtc_state->encoder_mask) { + if (!drm_enc->possible_clones) { + DRM_DEBUG("enc%d possible_clones is 0\n", drm_enc->base.id); + continue; + } + + if ((crtc_state->encoder_mask & drm_enc->possible_clones) != + crtc_state->encoder_mask) { + DRM_DEBUG("crtc%d failed valid clone check for mask 0x%x\n", + crtc->base.id, crtc_state->encoder_mask); + return -EINVAL; + } + } + + return 0; +} + /** * drm_atomic_helper_check_modeset - validate state object for modeset changes * @dev: DRM device @@ -744,6 +768,10 @@ drm_atomic_helper_check_modeset(struct drm_device *dev, ret = drm_atomic_add_affected_planes(state, crtc); if (ret != 0) return ret; + + ret = drm_atomic_check_valid_clones(state, crtc); + if (ret != 0) + return ret; } /* diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 5ed77e3361fd..fc6028aae9bd 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -6164,6 +6164,7 @@ static void drm_reset_display_info(struct drm_connector *connector) info->has_hdmi_infoframe = false; info->rgb_quant_range_selectable = false; memset(&info->hdmi, 0, sizeof(info->hdmi)); + memset(&connector->hdr_sink_metadata, 0, sizeof(connector->hdr_sink_metadata)); info->edid_hdmi_rgb444_dc_modes = 0; info->edid_hdmi_ycbcr444_dc_modes = 0; diff --git a/drivers/gpu/drm/mediatek/mtk_dpi.c b/drivers/gpu/drm/mediatek/mtk_dpi.c index 1fa958e8c40a..5ad9c384046c 100644 --- a/drivers/gpu/drm/mediatek/mtk_dpi.c +++ b/drivers/gpu/drm/mediatek/mtk_dpi.c @@ -406,12 +406,13 @@ static void mtk_dpi_config_swap_input(struct mtk_dpi *dpi, bool enable) static void mtk_dpi_config_2n_h_fre(struct mtk_dpi *dpi) { - mtk_dpi_mask(dpi, dpi->conf->reg_h_fre_con, H_FRE_2N, H_FRE_2N); + if (dpi->conf->reg_h_fre_con) + mtk_dpi_mask(dpi, dpi->conf->reg_h_fre_con, H_FRE_2N, H_FRE_2N); } static void mtk_dpi_config_disable_edge(struct mtk_dpi *dpi) { - if (dpi->conf->edge_sel_en) + if (dpi->conf->edge_sel_en && dpi->conf->reg_h_fre_con) mtk_dpi_mask(dpi, dpi->conf->reg_h_fre_con, 0, EDGE_SEL_EN); } diff --git a/drivers/gpu/drm/panel/panel-edp.c b/drivers/gpu/drm/panel/panel-edp.c index 2c14779a39e8..1ef1b4c966d2 100644 --- a/drivers/gpu/drm/panel/panel-edp.c +++ b/drivers/gpu/drm/panel/panel-edp.c @@ -1944,6 +1944,7 @@ static const struct edp_panel_entry edp_panels[] = { EDP_PANEL_ENTRY('S', 'H', 'P', 0x1523, &sharp_lq140m1jw46.delay, "LQ140M1JW46"), EDP_PANEL_ENTRY('S', 'H', 'P', 0x154c, &delay_200_500_p2e100, "LQ116M1JW10"), + EDP_PANEL_ENTRY('S', 'T', 'A', 0x0004, &delay_200_500_e200, "116KHD024006"), EDP_PANEL_ENTRY('S', 'T', 'A', 0x0100, &delay_100_500_e200, "2081116HHD028001-51D"), { /* sentinal */ } diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index a35e94e2ffd0..8a86f5d5c708 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -921,27 +921,28 @@ static const struct panel_desc auo_g070vvn01 = { }, }; -static const struct drm_display_mode auo_g101evn010_mode = { - .clock = 68930, - .hdisplay = 1280, - .hsync_start = 1280 + 82, - .hsync_end = 1280 + 82 + 2, - .htotal = 1280 + 82 + 2 + 84, - .vdisplay = 800, - .vsync_start = 800 + 8, - .vsync_end = 800 + 8 + 2, - .vtotal = 800 + 8 + 2 + 6, +static const struct display_timing auo_g101evn010_timing = { + .pixelclock = { 64000000, 68930000, 85000000 }, + .hactive = { 1280, 1280, 1280 }, + .hfront_porch = { 8, 64, 256 }, + .hback_porch = { 8, 64, 256 }, + .hsync_len = { 40, 168, 767 }, + .vactive = { 800, 800, 800 }, + .vfront_porch = { 4, 8, 100 }, + .vback_porch = { 4, 8, 100 }, + .vsync_len = { 8, 16, 223 }, }; static const struct panel_desc auo_g101evn010 = { - .modes = &auo_g101evn010_mode, - .num_modes = 1, + .timings = &auo_g101evn010_timing, + .num_timings = 1, .bpc = 6, .size = { .width = 216, .height = 135, }, .bus_format = MEDIA_BUS_FMT_RGB666_1X7X3_SPWG, + .bus_flags = DRM_BUS_FLAG_DE_HIGH, .connector_type = DRM_MODE_CONNECTOR_LVDS, }; diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c index 955ef2caac89..6efa0a51b7d6 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c @@ -1289,10 +1289,8 @@ static void vop2_plane_atomic_update(struct drm_plane *plane, rb_swap = vop2_win_rb_swap(fb->format->format); vop2_win_write(win, VOP2_WIN_RB_SWAP, rb_swap); - if (!vop2_cluster_window(win)) { - uv_swap = vop2_win_uv_swap(fb->format->format); - vop2_win_write(win, VOP2_WIN_UV_SWAP, uv_swap); - } + uv_swap = vop2_win_uv_swap(fb->format->format); + vop2_win_write(win, VOP2_WIN_UV_SWAP, uv_swap); if (fb->format->is_yuv) { vop2_win_write(win, VOP2_WIN_UV_VIR, DIV_ROUND_UP(fb->pitches[1], 4)); diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c index 5b729013fd26..41493cf3d03b 100644 --- a/drivers/gpu/drm/v3d/v3d_sched.c +++ b/drivers/gpu/drm/v3d/v3d_sched.c @@ -289,11 +289,16 @@ v3d_gpu_reset_for_timeout(struct v3d_dev *v3d, struct drm_sched_job *sched_job) return DRM_GPU_SCHED_STAT_NOMINAL; } -/* If the current address or return address have changed, then the GPU - * has probably made progress and we should delay the reset. This - * could fail if the GPU got in an infinite loop in the CL, but that - * is pretty unlikely outside of an i-g-t testcase. - */ +static void +v3d_sched_skip_reset(struct drm_sched_job *sched_job) +{ + struct drm_gpu_scheduler *sched = sched_job->sched; + + spin_lock(&sched->job_list_lock); + list_add(&sched_job->list, &sched->pending_list); + spin_unlock(&sched->job_list_lock); +} + static enum drm_gpu_sched_stat v3d_cl_job_timedout(struct drm_sched_job *sched_job, enum v3d_queue q, u32 *timedout_ctca, u32 *timedout_ctra) @@ -303,9 +308,16 @@ v3d_cl_job_timedout(struct drm_sched_job *sched_job, enum v3d_queue q, u32 ctca = V3D_CORE_READ(0, V3D_CLE_CTNCA(q)); u32 ctra = V3D_CORE_READ(0, V3D_CLE_CTNRA(q)); + /* If the current address or return address have changed, then the GPU + * has probably made progress and we should delay the reset. This + * could fail if the GPU got in an infinite loop in the CL, but that + * is pretty unlikely outside of an i-g-t testcase. + */ if (*timedout_ctca != ctca || *timedout_ctra != ctra) { *timedout_ctca = ctca; *timedout_ctra = ctra; + + v3d_sched_skip_reset(sched_job); return DRM_GPU_SCHED_STAT_NOMINAL; } @@ -345,11 +357,13 @@ v3d_csd_job_timedout(struct drm_sched_job *sched_job) struct v3d_dev *v3d = job->base.v3d; u32 batches = V3D_CORE_READ(0, V3D_CSD_CURRENT_CFG4); - /* If we've made progress, skip reset and let the timer get - * rearmed. + /* If we've made progress, skip reset, add the job to the pending + * list, and let the timer get rearmed. */ if (job->timedout_batches != batches) { job->timedout_batches = batches; + + v3d_sched_skip_reset(sched_job); return DRM_GPU_SCHED_STAT_NOMINAL; } diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 4187d890bcc1..e078d2ac92c8 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -41,6 +41,10 @@ #define USB_VENDOR_ID_ACTIONSTAR 0x2101 #define USB_DEVICE_ID_ACTIONSTAR_1011 0x1011 +#define USB_VENDOR_ID_ADATA_XPG 0x125f +#define USB_VENDOR_ID_ADATA_XPG_WL_GAMING_MOUSE 0x7505 +#define USB_VENDOR_ID_ADATA_XPG_WL_GAMING_MOUSE_DONGLE 0x7506 + #define USB_VENDOR_ID_ADS_TECH 0x06e1 #define USB_DEVICE_ID_ADS_TECH_RADIO_SI470X 0xa155 diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index 875c44e5cf6c..d8c5c7d451ef 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -27,6 +27,8 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_AASHIMA, USB_DEVICE_ID_AASHIMA_GAMEPAD), HID_QUIRK_BADPAD }, { HID_USB_DEVICE(USB_VENDOR_ID_AASHIMA, USB_DEVICE_ID_AASHIMA_PREDATOR), HID_QUIRK_BADPAD }, + { HID_USB_DEVICE(USB_VENDOR_ID_ADATA_XPG, USB_VENDOR_ID_ADATA_XPG_WL_GAMING_MOUSE), HID_QUIRK_ALWAYS_POLL }, + { HID_USB_DEVICE(USB_VENDOR_ID_ADATA_XPG, USB_VENDOR_ID_ADATA_XPG_WL_GAMING_MOUSE_DONGLE), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_AFATECH, USB_DEVICE_ID_AFATECH_AF9016), HID_QUIRK_FULLSPEED_INTERVAL }, { HID_USB_DEVICE(USB_VENDOR_ID_AIREN, USB_DEVICE_ID_AIREN_SLIMPLUS), HID_QUIRK_NOGET }, { HID_USB_DEVICE(USB_VENDOR_ID_AKAI_09E8, USB_DEVICE_ID_AKAI_09E8_MIDIMIX), HID_QUIRK_NO_INIT_REPORTS }, diff --git a/drivers/hid/hid-thrustmaster.c b/drivers/hid/hid-thrustmaster.c index 3b81468a1df2..0bf70664c35e 100644 --- a/drivers/hid/hid-thrustmaster.c +++ b/drivers/hid/hid-thrustmaster.c @@ -174,6 +174,7 @@ static void thrustmaster_interrupts(struct hid_device *hdev) u8 ep_addr[2] = {b_ep, 0}; if (!usb_check_int_endpoints(usbif, ep_addr)) { + kfree(send_buf); hid_err(hdev, "Unexpected non-int endpoint\n"); return; } diff --git a/drivers/hid/hid-uclogic-core.c b/drivers/hid/hid-uclogic-core.c index 39114d5c55a0..5b35f9f321d4 100644 --- a/drivers/hid/hid-uclogic-core.c +++ b/drivers/hid/hid-uclogic-core.c @@ -142,11 +142,12 @@ static int uclogic_input_configured(struct hid_device *hdev, suffix = "System Control"; break; } - } - - if (suffix) + } else { hi->input->name = devm_kasprintf(&hdev->dev, GFP_KERNEL, "%s %s", hdev->name, suffix); + if (!hi->input->name) + return -ENOMEM; + } return 0; } diff --git a/drivers/hid/usbhid/usbkbd.c b/drivers/hid/usbhid/usbkbd.c index c439ed2f16db..af6bc76dbf64 100644 --- a/drivers/hid/usbhid/usbkbd.c +++ b/drivers/hid/usbhid/usbkbd.c @@ -160,7 +160,7 @@ static int usb_kbd_event(struct input_dev *dev, unsigned int type, return -1; spin_lock_irqsave(&kbd->leds_lock, flags); - kbd->newleds = (!!test_bit(LED_KANA, dev->led) << 3) | (!!test_bit(LED_COMPOSE, dev->led) << 3) | + kbd->newleds = (!!test_bit(LED_KANA, dev->led) << 4) | (!!test_bit(LED_COMPOSE, dev->led) << 3) | (!!test_bit(LED_SCROLLL, dev->led) << 2) | (!!test_bit(LED_CAPSL, dev->led) << 1) | (!!test_bit(LED_NUML, dev->led)); diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index fdb72345c850..f3139d7f3f97 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -1114,68 +1114,10 @@ int vmbus_sendpacket(struct vmbus_channel *channel, void *buffer, EXPORT_SYMBOL(vmbus_sendpacket); /* - * vmbus_sendpacket_pagebuffer - Send a range of single-page buffer - * packets using a GPADL Direct packet type. This interface allows you - * to control notifying the host. This will be useful for sending - * batched data. Also the sender can control the send flags - * explicitly. - */ -int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel, - struct hv_page_buffer pagebuffers[], - u32 pagecount, void *buffer, u32 bufferlen, - u64 requestid) -{ - int i; - struct vmbus_channel_packet_page_buffer desc; - u32 descsize; - u32 packetlen; - u32 packetlen_aligned; - struct kvec bufferlist[3]; - u64 aligned_data = 0; - - if (pagecount > MAX_PAGE_BUFFER_COUNT) - return -EINVAL; - - /* - * Adjust the size down since vmbus_channel_packet_page_buffer is the - * largest size we support - */ - descsize = sizeof(struct vmbus_channel_packet_page_buffer) - - ((MAX_PAGE_BUFFER_COUNT - pagecount) * - sizeof(struct hv_page_buffer)); - packetlen = descsize + bufferlen; - packetlen_aligned = ALIGN(packetlen, sizeof(u64)); - - /* Setup the descriptor */ - desc.type = VM_PKT_DATA_USING_GPA_DIRECT; - desc.flags = VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED; - desc.dataoffset8 = descsize >> 3; /* in 8-bytes granularity */ - desc.length8 = (u16)(packetlen_aligned >> 3); - desc.transactionid = VMBUS_RQST_ERROR; /* will be updated in hv_ringbuffer_write() */ - desc.reserved = 0; - desc.rangecount = pagecount; - - for (i = 0; i < pagecount; i++) { - desc.range[i].len = pagebuffers[i].len; - desc.range[i].offset = pagebuffers[i].offset; - desc.range[i].pfn = pagebuffers[i].pfn; - } - - bufferlist[0].iov_base = &desc; - bufferlist[0].iov_len = descsize; - bufferlist[1].iov_base = buffer; - bufferlist[1].iov_len = bufferlen; - bufferlist[2].iov_base = &aligned_data; - bufferlist[2].iov_len = (packetlen_aligned - packetlen); - - return hv_ringbuffer_write(channel, bufferlist, 3, requestid, NULL); -} -EXPORT_SYMBOL_GPL(vmbus_sendpacket_pagebuffer); - -/* - * vmbus_sendpacket_multipagebuffer - Send a multi-page buffer packet + * vmbus_sendpacket_mpb_desc - Send one or more multi-page buffer packets * using a GPADL Direct packet type. - * The buffer includes the vmbus descriptor. + * The desc argument must include space for the VMBus descriptor. The + * rangecount field must already be set. */ int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel, struct vmbus_packet_mpb_array *desc, @@ -1197,7 +1139,6 @@ int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel, desc->length8 = (u16)(packetlen_aligned >> 3); desc->transactionid = VMBUS_RQST_ERROR; /* will be updated in hv_ringbuffer_write() */ desc->reserved = 0; - desc->rangecount = 1; bufferlist[0].iov_base = desc; bufferlist[0].iov_len = desc_size; diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon.c index 1572b5416015..dbcb8f362061 100644 --- a/drivers/hwmon/dell-smm-hwmon.c +++ b/drivers/hwmon/dell-smm-hwmon.c @@ -67,7 +67,7 @@ #define I8K_POWER_BATTERY 0x01 #define DELL_SMM_NO_TEMP 10 -#define DELL_SMM_NO_FANS 3 +#define DELL_SMM_NO_FANS 4 struct dell_smm_data { struct mutex i8k_mutex; /* lock for sensors writes */ @@ -940,11 +940,14 @@ static const struct hwmon_channel_info *dell_smm_info[] = { HWMON_F_INPUT | HWMON_F_LABEL | HWMON_F_MIN | HWMON_F_MAX | HWMON_F_TARGET, HWMON_F_INPUT | HWMON_F_LABEL | HWMON_F_MIN | HWMON_F_MAX | + HWMON_F_TARGET, + HWMON_F_INPUT | HWMON_F_LABEL | HWMON_F_MIN | HWMON_F_MAX | HWMON_F_TARGET ), HWMON_CHANNEL_INFO(pwm, HWMON_PWM_INPUT | HWMON_PWM_ENABLE, HWMON_PWM_INPUT, + HWMON_PWM_INPUT, HWMON_PWM_INPUT ), NULL diff --git a/drivers/hwmon/gpio-fan.c b/drivers/hwmon/gpio-fan.c index ba408942dbe7..f1926b9171e0 100644 --- a/drivers/hwmon/gpio-fan.c +++ b/drivers/hwmon/gpio-fan.c @@ -392,7 +392,12 @@ static int gpio_fan_set_cur_state(struct thermal_cooling_device *cdev, if (state >= fan_data->num_speed) return -EINVAL; + mutex_lock(&fan_data->lock); + set_fan_speed(fan_data, state); + + mutex_unlock(&fan_data->lock); + return 0; } @@ -488,7 +493,11 @@ MODULE_DEVICE_TABLE(of, of_gpio_fan_match); static void gpio_fan_stop(void *data) { + struct gpio_fan_data *fan_data = data; + + mutex_lock(&fan_data->lock); set_fan_speed(data, 0); + mutex_unlock(&fan_data->lock); } static int gpio_fan_probe(struct platform_device *pdev) @@ -561,7 +570,9 @@ static int gpio_fan_suspend(struct device *dev) if (fan_data->gpios) { fan_data->resume_speed = fan_data->speed_index; + mutex_lock(&fan_data->lock); set_fan_speed(fan_data, 0); + mutex_unlock(&fan_data->lock); } return 0; @@ -571,8 +582,11 @@ static int gpio_fan_resume(struct device *dev) { struct gpio_fan_data *fan_data = dev_get_drvdata(dev); - if (fan_data->gpios) + if (fan_data->gpios) { + mutex_lock(&fan_data->lock); set_fan_speed(fan_data, fan_data->resume_speed); + mutex_unlock(&fan_data->lock); + } return 0; } diff --git a/drivers/hwmon/xgene-hwmon.c b/drivers/hwmon/xgene-hwmon.c index 207084d55044..6768dbf39039 100644 --- a/drivers/hwmon/xgene-hwmon.c +++ b/drivers/hwmon/xgene-hwmon.c @@ -111,7 +111,7 @@ struct xgene_hwmon_dev { phys_addr_t comm_base_addr; void *pcc_comm_addr; - u64 usecs_lat; + unsigned int usecs_lat; }; /* diff --git a/drivers/i2c/busses/i2c-pxa.c b/drivers/i2c/busses/i2c-pxa.c index ade3f0ea5955..8263e017577d 100644 --- a/drivers/i2c/busses/i2c-pxa.c +++ b/drivers/i2c/busses/i2c-pxa.c @@ -1508,7 +1508,10 @@ static int i2c_pxa_probe(struct platform_device *dev) i2c->adap.name); } - clk_prepare_enable(i2c->clk); + ret = clk_prepare_enable(i2c->clk); + if (ret) + return dev_err_probe(&dev->dev, ret, + "failed to enable clock\n"); if (i2c->use_pio) { i2c->adap.algo = &i2c_pxa_pio_algorithm; diff --git a/drivers/i2c/busses/i2c-qup.c b/drivers/i2c/busses/i2c-qup.c index 78682388e02e..82de4651d18f 100644 --- a/drivers/i2c/busses/i2c-qup.c +++ b/drivers/i2c/busses/i2c-qup.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -150,6 +151,8 @@ /* TAG length for DATA READ in RX FIFO */ #define READ_RX_TAGS_LEN 2 +#define QUP_BUS_WIDTH 8 + static unsigned int scl_freq; module_param_named(scl_freq, scl_freq, uint, 0444); MODULE_PARM_DESC(scl_freq, "SCL frequency override"); @@ -227,6 +230,7 @@ struct qup_i2c_dev { int irq; struct clk *clk; struct clk *pclk; + struct icc_path *icc_path; struct i2c_adapter adap; int clk_ctl; @@ -255,6 +259,10 @@ struct qup_i2c_dev { /* To configure when bus is in run state */ u32 config_run; + /* bandwidth votes */ + u32 src_clk_freq; + u32 cur_bw_clk_freq; + /* dma parameters */ bool is_dma; /* To check if the current transfer is using DMA */ @@ -453,6 +461,23 @@ static int qup_i2c_bus_active(struct qup_i2c_dev *qup, int len) return ret; } +static int qup_i2c_vote_bw(struct qup_i2c_dev *qup, u32 clk_freq) +{ + u32 needed_peak_bw; + int ret; + + if (qup->cur_bw_clk_freq == clk_freq) + return 0; + + needed_peak_bw = Bps_to_icc(clk_freq * QUP_BUS_WIDTH); + ret = icc_set_bw(qup->icc_path, 0, needed_peak_bw); + if (ret) + return ret; + + qup->cur_bw_clk_freq = clk_freq; + return 0; +} + static void qup_i2c_write_tx_fifo_v1(struct qup_i2c_dev *qup) { struct qup_i2c_block *blk = &qup->blk; @@ -840,6 +865,10 @@ static int qup_i2c_bam_xfer(struct i2c_adapter *adap, struct i2c_msg *msg, int ret = 0; int idx = 0; + ret = qup_i2c_vote_bw(qup, qup->src_clk_freq); + if (ret) + return ret; + enable_irq(qup->irq); ret = qup_i2c_req_dma(qup); @@ -1645,6 +1674,7 @@ static void qup_i2c_disable_clocks(struct qup_i2c_dev *qup) config = readl(qup->base + QUP_CONFIG); config |= QUP_CLOCK_AUTO_GATE; writel(config, qup->base + QUP_CONFIG); + qup_i2c_vote_bw(qup, 0); clk_disable_unprepare(qup->pclk); } @@ -1745,6 +1775,11 @@ static int qup_i2c_probe(struct platform_device *pdev) goto fail_dma; } qup->is_dma = true; + + qup->icc_path = devm_of_icc_get(&pdev->dev, NULL); + if (IS_ERR(qup->icc_path)) + return dev_err_probe(&pdev->dev, PTR_ERR(qup->icc_path), + "failed to get interconnect path\n"); } nodma: @@ -1793,6 +1828,7 @@ nodma: qup_i2c_enable_clocks(qup); src_clk_freq = clk_get_rate(qup->clk); } + qup->src_clk_freq = src_clk_freq; /* * Bootloaders might leave a pending interrupt on certain QUP's, diff --git a/drivers/i3c/master/svc-i3c-master.c b/drivers/i3c/master/svc-i3c-master.c index f1d8aa56ef8c..bfe86a8ca09a 100644 --- a/drivers/i3c/master/svc-i3c-master.c +++ b/drivers/i3c/master/svc-i3c-master.c @@ -478,6 +478,8 @@ static void svc_i3c_master_ibi_work(struct work_struct *work) queue_work(master->base.wq, &master->hj_work); break; case SVC_I3C_MSTATUS_IBITYPE_MASTER_REQUEST: + svc_i3c_master_emit_stop(master); + break; default: break; } @@ -766,6 +768,8 @@ static int svc_i3c_master_do_daa_locked(struct svc_i3c_master *master, u32 reg; int ret, i; + svc_i3c_master_flush_fifo(master); + while (true) { /* Enter/proceed with DAA */ writel(SVC_I3C_MCTRL_REQUEST_PROC_DAA | diff --git a/drivers/iio/accel/adis16201.c b/drivers/iio/accel/adis16201.c index dfb8e2e5bdf5..f063226a42f3 100644 --- a/drivers/iio/accel/adis16201.c +++ b/drivers/iio/accel/adis16201.c @@ -211,9 +211,9 @@ static const struct iio_chan_spec adis16201_channels[] = { BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 14), ADIS_AUX_ADC_CHAN(ADIS16201_AUX_ADC_REG, ADIS16201_SCAN_AUX_ADC, 0, 12), ADIS_INCLI_CHAN(X, ADIS16201_XINCL_OUT_REG, ADIS16201_SCAN_INCLI_X, - BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 14), + BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 12), ADIS_INCLI_CHAN(Y, ADIS16201_YINCL_OUT_REG, ADIS16201_SCAN_INCLI_Y, - BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 14), + BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 12), IIO_CHAN_SOFT_TIMESTAMP(7) }; diff --git a/drivers/iio/accel/adxl355_core.c b/drivers/iio/accel/adxl355_core.c index 4bc648eac8b2..e73573cd773a 100644 --- a/drivers/iio/accel/adxl355_core.c +++ b/drivers/iio/accel/adxl355_core.c @@ -175,7 +175,7 @@ struct adxl355_data { u8 transf_buf[3]; struct { u8 buf[14]; - s64 ts; + aligned_s64 ts; } buffer; } __aligned(IIO_DMA_MINALIGN); }; diff --git a/drivers/iio/accel/adxl367.c b/drivers/iio/accel/adxl367.c index f1a41b92543a..af0ad4e5e4a5 100644 --- a/drivers/iio/accel/adxl367.c +++ b/drivers/iio/accel/adxl367.c @@ -622,18 +622,14 @@ static int _adxl367_set_odr(struct adxl367_state *st, enum adxl367_odr odr) if (ret) return ret; + st->odr = odr; + /* Activity timers depend on ODR */ ret = _adxl367_set_act_time_ms(st, st->act_time_ms); if (ret) return ret; - ret = _adxl367_set_inact_time_ms(st, st->inact_time_ms); - if (ret) - return ret; - - st->odr = odr; - - return 0; + return _adxl367_set_inact_time_ms(st, st->inact_time_ms); } static int adxl367_set_odr(struct iio_dev *indio_dev, enum adxl367_odr odr) diff --git a/drivers/iio/adc/ad7266.c b/drivers/iio/adc/ad7266.c index 98648c679a55..2ace3aafe497 100644 --- a/drivers/iio/adc/ad7266.c +++ b/drivers/iio/adc/ad7266.c @@ -44,7 +44,7 @@ struct ad7266_state { */ struct { __be16 sample[2]; - s64 timestamp; + aligned_s64 timestamp; } data __aligned(IIO_DMA_MINALIGN); }; diff --git a/drivers/iio/adc/ad7606_spi.c b/drivers/iio/adc/ad7606_spi.c index 287a0591533b..67c96572cecc 100644 --- a/drivers/iio/adc/ad7606_spi.c +++ b/drivers/iio/adc/ad7606_spi.c @@ -127,7 +127,7 @@ static int ad7606_spi_reg_read(struct ad7606_state *st, unsigned int addr) { .tx_buf = &st->d16[0], .len = 2, - .cs_change = 0, + .cs_change = 1, }, { .rx_buf = &st->d16[1], .len = 2, diff --git a/drivers/iio/adc/ad7768-1.c b/drivers/iio/adc/ad7768-1.c index 74b0c85944bd..967f06cd3f94 100644 --- a/drivers/iio/adc/ad7768-1.c +++ b/drivers/iio/adc/ad7768-1.c @@ -169,7 +169,7 @@ struct ad7768_state { union { struct { __be32 chan; - s64 timestamp; + aligned_s64 timestamp; } scan; __be32 d32; u8 d8[2]; diff --git a/drivers/iio/adc/dln2-adc.c b/drivers/iio/adc/dln2-adc.c index 97d162a3cba4..49a2588e7431 100644 --- a/drivers/iio/adc/dln2-adc.c +++ b/drivers/iio/adc/dln2-adc.c @@ -483,7 +483,7 @@ static irqreturn_t dln2_adc_trigger_h(int irq, void *p) struct iio_dev *indio_dev = pf->indio_dev; struct { __le16 values[DLN2_ADC_MAX_CHANNELS]; - int64_t timestamp_space; + aligned_s64 timestamp_space; } data; struct dln2_adc_get_all_vals dev_data; struct dln2_adc *dln2 = iio_priv(indio_dev); diff --git a/drivers/iio/chemical/sps30.c b/drivers/iio/chemical/sps30.c index 814ce0aad1cc..4085a36cd1db 100644 --- a/drivers/iio/chemical/sps30.c +++ b/drivers/iio/chemical/sps30.c @@ -108,7 +108,7 @@ static irqreturn_t sps30_trigger_handler(int irq, void *p) int ret; struct { s32 data[4]; /* PM1, PM2P5, PM4, PM10 */ - s64 ts; + aligned_s64 ts; } scan; mutex_lock(&state->lock); diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c index e49f2d120ed3..f5a68059f0a6 100644 --- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c +++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c @@ -370,6 +370,9 @@ int st_lsm6dsx_read_fifo(struct st_lsm6dsx_hw *hw) if (fifo_status & cpu_to_le16(ST_LSM6DSX_FIFO_EMPTY_MASK)) return 0; + if (!pattern_len) + pattern_len = ST_LSM6DSX_SAMPLE_SIZE; + fifo_len = (le16_to_cpu(fifo_status) & fifo_diff_mask) * ST_LSM6DSX_CHAN_SIZE; fifo_len = (fifo_len / pattern_len) * pattern_len; @@ -587,6 +590,9 @@ int st_lsm6dsx_read_tagged_fifo(struct st_lsm6dsx_hw *hw) if (!fifo_len) return 0; + if (!pattern_len) + pattern_len = ST_LSM6DSX_TAGGED_SAMPLE_SIZE; + for (read_len = 0; read_len < fifo_len; read_len += pattern_len) { err = st_lsm6dsx_read_block(hw, ST_LSM6DSX_REG_FIFO_OUT_TAG_ADDR, diff --git a/drivers/iio/temperature/maxim_thermocouple.c b/drivers/iio/temperature/maxim_thermocouple.c index c28a7a6dea5f..555a61e2f3fd 100644 --- a/drivers/iio/temperature/maxim_thermocouple.c +++ b/drivers/iio/temperature/maxim_thermocouple.c @@ -121,9 +121,9 @@ static const struct maxim_thermocouple_chip maxim_thermocouple_chips[] = { struct maxim_thermocouple_data { struct spi_device *spi; const struct maxim_thermocouple_chip *chip; + char tc_type; u8 buffer[16] __aligned(IIO_DMA_MINALIGN); - char tc_type; }; static int maxim_thermocouple_read(struct maxim_thermocouple_data *data, diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index 8ce569bf7525..1d154055a335 100644 --- a/drivers/infiniband/core/umem.c +++ b/drivers/infiniband/core/umem.c @@ -80,9 +80,12 @@ unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem, unsigned long pgsz_bitmap, unsigned long virt) { - struct scatterlist *sg; + unsigned long curr_len = 0; + dma_addr_t curr_base = ~0; unsigned long va, pgoff; + struct scatterlist *sg; dma_addr_t mask; + dma_addr_t end; int i; umem->iova = va = virt; @@ -107,17 +110,30 @@ unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem, pgoff = umem->address & ~PAGE_MASK; for_each_sgtable_dma_sg(&umem->sgt_append.sgt, sg, i) { - /* Walk SGL and reduce max page size if VA/PA bits differ - * for any address. + /* If the current entry is physically contiguous with the previous + * one, no need to take its start addresses into consideration. */ - mask |= (sg_dma_address(sg) + pgoff) ^ va; + if (check_add_overflow(curr_base, curr_len, &end) || + end != sg_dma_address(sg)) { + + curr_base = sg_dma_address(sg); + curr_len = 0; + + /* Reduce max page size if VA/PA bits differ */ + mask |= (curr_base + pgoff) ^ va; + + /* The alignment of any VA matching a discontinuity point + * in the physical memory sets the maximum possible page + * size as this must be a starting point of a new page that + * needs to be aligned. + */ + if (i != 0) + mask |= va; + } + + curr_len += sg_dma_len(sg); va += sg_dma_len(sg) - pgoff; - /* Except for the last entry, the ending iova alignment sets - * the maximum possible page size as the low bits of the iova - * must be zero when starting the next chunk. - */ - if (i != (umem->sgt_append.sgt.nents - 1)) - mask |= va; + pgoff = 0; } diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index c6053e82ecf6..33e2fe0facd5 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -718,8 +718,8 @@ static int ib_uverbs_reg_mr(struct uverbs_attr_bundle *attrs) goto err_free; pd = uobj_get_obj_read(pd, UVERBS_OBJECT_PD, cmd.pd_handle, attrs); - if (!pd) { - ret = -EINVAL; + if (IS_ERR(pd)) { + ret = PTR_ERR(pd); goto err_free; } @@ -809,8 +809,8 @@ static int ib_uverbs_rereg_mr(struct uverbs_attr_bundle *attrs) if (cmd.flags & IB_MR_REREG_PD) { new_pd = uobj_get_obj_read(pd, UVERBS_OBJECT_PD, cmd.pd_handle, attrs); - if (!new_pd) { - ret = -EINVAL; + if (IS_ERR(new_pd)) { + ret = PTR_ERR(new_pd); goto put_uobjs; } } else { @@ -919,8 +919,8 @@ static int ib_uverbs_alloc_mw(struct uverbs_attr_bundle *attrs) return PTR_ERR(uobj); pd = uobj_get_obj_read(pd, UVERBS_OBJECT_PD, cmd.pd_handle, attrs); - if (!pd) { - ret = -EINVAL; + if (IS_ERR(pd)) { + ret = PTR_ERR(pd); goto err_free; } @@ -1127,8 +1127,8 @@ static int ib_uverbs_resize_cq(struct uverbs_attr_bundle *attrs) return ret; cq = uobj_get_obj_read(cq, UVERBS_OBJECT_CQ, cmd.cq_handle, attrs); - if (!cq) - return -EINVAL; + if (IS_ERR(cq)) + return PTR_ERR(cq); ret = cq->device->ops.resize_cq(cq, cmd.cqe, &attrs->driver_udata); if (ret) @@ -1189,8 +1189,8 @@ static int ib_uverbs_poll_cq(struct uverbs_attr_bundle *attrs) return ret; cq = uobj_get_obj_read(cq, UVERBS_OBJECT_CQ, cmd.cq_handle, attrs); - if (!cq) - return -EINVAL; + if (IS_ERR(cq)) + return PTR_ERR(cq); /* we copy a struct ib_uverbs_poll_cq_resp to user space */ header_ptr = attrs->ucore.outbuf; @@ -1238,8 +1238,8 @@ static int ib_uverbs_req_notify_cq(struct uverbs_attr_bundle *attrs) return ret; cq = uobj_get_obj_read(cq, UVERBS_OBJECT_CQ, cmd.cq_handle, attrs); - if (!cq) - return -EINVAL; + if (IS_ERR(cq)) + return PTR_ERR(cq); ib_req_notify_cq(cq, cmd.solicited_only ? IB_CQ_SOLICITED : IB_CQ_NEXT_COMP); @@ -1321,8 +1321,8 @@ static int create_qp(struct uverbs_attr_bundle *attrs, ind_tbl = uobj_get_obj_read(rwq_ind_table, UVERBS_OBJECT_RWQ_IND_TBL, cmd->rwq_ind_tbl_handle, attrs); - if (!ind_tbl) { - ret = -EINVAL; + if (IS_ERR(ind_tbl)) { + ret = PTR_ERR(ind_tbl); goto err_put; } @@ -1360,8 +1360,10 @@ static int create_qp(struct uverbs_attr_bundle *attrs, if (cmd->is_srq) { srq = uobj_get_obj_read(srq, UVERBS_OBJECT_SRQ, cmd->srq_handle, attrs); - if (!srq || srq->srq_type == IB_SRQT_XRC) { - ret = -EINVAL; + if (IS_ERR(srq) || + srq->srq_type == IB_SRQT_XRC) { + ret = IS_ERR(srq) ? PTR_ERR(srq) : + -EINVAL; goto err_put; } } @@ -1371,23 +1373,29 @@ static int create_qp(struct uverbs_attr_bundle *attrs, rcq = uobj_get_obj_read( cq, UVERBS_OBJECT_CQ, cmd->recv_cq_handle, attrs); - if (!rcq) { - ret = -EINVAL; + if (IS_ERR(rcq)) { + ret = PTR_ERR(rcq); goto err_put; } } } } - if (has_sq) + if (has_sq) { scq = uobj_get_obj_read(cq, UVERBS_OBJECT_CQ, cmd->send_cq_handle, attrs); + if (IS_ERR(scq)) { + ret = PTR_ERR(scq); + goto err_put; + } + } + if (!ind_tbl && cmd->qp_type != IB_QPT_XRC_INI) rcq = rcq ?: scq; pd = uobj_get_obj_read(pd, UVERBS_OBJECT_PD, cmd->pd_handle, attrs); - if (!pd || (!scq && has_sq)) { - ret = -EINVAL; + if (IS_ERR(pd)) { + ret = PTR_ERR(pd); goto err_put; } @@ -1482,18 +1490,18 @@ static int create_qp(struct uverbs_attr_bundle *attrs, err_put: if (!IS_ERR(xrcd_uobj)) uobj_put_read(xrcd_uobj); - if (pd) + if (!IS_ERR_OR_NULL(pd)) uobj_put_obj_read(pd); - if (scq) + if (!IS_ERR_OR_NULL(scq)) rdma_lookup_put_uobject(&scq->uobject->uevent.uobject, UVERBS_LOOKUP_READ); - if (rcq && rcq != scq) + if (!IS_ERR_OR_NULL(rcq) && rcq != scq) rdma_lookup_put_uobject(&rcq->uobject->uevent.uobject, UVERBS_LOOKUP_READ); - if (srq) + if (!IS_ERR_OR_NULL(srq)) rdma_lookup_put_uobject(&srq->uobject->uevent.uobject, UVERBS_LOOKUP_READ); - if (ind_tbl) + if (!IS_ERR_OR_NULL(ind_tbl)) uobj_put_obj_read(ind_tbl); uobj_alloc_abort(&obj->uevent.uobject, attrs); @@ -1655,8 +1663,8 @@ static int ib_uverbs_query_qp(struct uverbs_attr_bundle *attrs) } qp = uobj_get_obj_read(qp, UVERBS_OBJECT_QP, cmd.qp_handle, attrs); - if (!qp) { - ret = -EINVAL; + if (IS_ERR(qp)) { + ret = PTR_ERR(qp); goto out; } @@ -1761,8 +1769,8 @@ static int modify_qp(struct uverbs_attr_bundle *attrs, qp = uobj_get_obj_read(qp, UVERBS_OBJECT_QP, cmd->base.qp_handle, attrs); - if (!qp) { - ret = -EINVAL; + if (IS_ERR(qp)) { + ret = PTR_ERR(qp); goto out; } @@ -2027,8 +2035,8 @@ static int ib_uverbs_post_send(struct uverbs_attr_bundle *attrs) return -ENOMEM; qp = uobj_get_obj_read(qp, UVERBS_OBJECT_QP, cmd.qp_handle, attrs); - if (!qp) { - ret = -EINVAL; + if (IS_ERR(qp)) { + ret = PTR_ERR(qp); goto out; } @@ -2065,9 +2073,9 @@ static int ib_uverbs_post_send(struct uverbs_attr_bundle *attrs) ud->ah = uobj_get_obj_read(ah, UVERBS_OBJECT_AH, user_wr->wr.ud.ah, attrs); - if (!ud->ah) { + if (IS_ERR(ud->ah)) { + ret = PTR_ERR(ud->ah); kfree(ud); - ret = -EINVAL; goto out_put; } ud->remote_qpn = user_wr->wr.ud.remote_qpn; @@ -2304,8 +2312,8 @@ static int ib_uverbs_post_recv(struct uverbs_attr_bundle *attrs) return PTR_ERR(wr); qp = uobj_get_obj_read(qp, UVERBS_OBJECT_QP, cmd.qp_handle, attrs); - if (!qp) { - ret = -EINVAL; + if (IS_ERR(qp)) { + ret = PTR_ERR(qp); goto out; } @@ -2355,8 +2363,8 @@ static int ib_uverbs_post_srq_recv(struct uverbs_attr_bundle *attrs) return PTR_ERR(wr); srq = uobj_get_obj_read(srq, UVERBS_OBJECT_SRQ, cmd.srq_handle, attrs); - if (!srq) { - ret = -EINVAL; + if (IS_ERR(srq)) { + ret = PTR_ERR(srq); goto out; } @@ -2412,8 +2420,8 @@ static int ib_uverbs_create_ah(struct uverbs_attr_bundle *attrs) } pd = uobj_get_obj_read(pd, UVERBS_OBJECT_PD, cmd.pd_handle, attrs); - if (!pd) { - ret = -EINVAL; + if (IS_ERR(pd)) { + ret = PTR_ERR(pd); goto err; } @@ -2482,8 +2490,8 @@ static int ib_uverbs_attach_mcast(struct uverbs_attr_bundle *attrs) return ret; qp = uobj_get_obj_read(qp, UVERBS_OBJECT_QP, cmd.qp_handle, attrs); - if (!qp) - return -EINVAL; + if (IS_ERR(qp)) + return PTR_ERR(qp); obj = qp->uobject; @@ -2532,8 +2540,8 @@ static int ib_uverbs_detach_mcast(struct uverbs_attr_bundle *attrs) return ret; qp = uobj_get_obj_read(qp, UVERBS_OBJECT_QP, cmd.qp_handle, attrs); - if (!qp) - return -EINVAL; + if (IS_ERR(qp)) + return PTR_ERR(qp); obj = qp->uobject; mutex_lock(&obj->mcast_lock); @@ -2667,8 +2675,8 @@ static int kern_spec_to_ib_spec_action(struct uverbs_attr_bundle *attrs, UVERBS_OBJECT_FLOW_ACTION, kern_spec->action.handle, attrs); - if (!ib_spec->action.act) - return -EINVAL; + if (IS_ERR(ib_spec->action.act)) + return PTR_ERR(ib_spec->action.act); ib_spec->action.size = sizeof(struct ib_flow_spec_action_handle); flow_resources_add(uflow_res, @@ -2685,8 +2693,8 @@ static int kern_spec_to_ib_spec_action(struct uverbs_attr_bundle *attrs, UVERBS_OBJECT_COUNTERS, kern_spec->flow_count.handle, attrs); - if (!ib_spec->flow_count.counters) - return -EINVAL; + if (IS_ERR(ib_spec->flow_count.counters)) + return PTR_ERR(ib_spec->flow_count.counters); ib_spec->flow_count.size = sizeof(struct ib_flow_spec_action_count); flow_resources_add(uflow_res, @@ -2904,14 +2912,14 @@ static int ib_uverbs_ex_create_wq(struct uverbs_attr_bundle *attrs) return PTR_ERR(obj); pd = uobj_get_obj_read(pd, UVERBS_OBJECT_PD, cmd.pd_handle, attrs); - if (!pd) { - err = -EINVAL; + if (IS_ERR(pd)) { + err = PTR_ERR(pd); goto err_uobj; } cq = uobj_get_obj_read(cq, UVERBS_OBJECT_CQ, cmd.cq_handle, attrs); - if (!cq) { - err = -EINVAL; + if (IS_ERR(cq)) { + err = PTR_ERR(cq); goto err_put_pd; } @@ -3012,8 +3020,8 @@ static int ib_uverbs_ex_modify_wq(struct uverbs_attr_bundle *attrs) return -EINVAL; wq = uobj_get_obj_read(wq, UVERBS_OBJECT_WQ, cmd.wq_handle, attrs); - if (!wq) - return -EINVAL; + if (IS_ERR(wq)) + return PTR_ERR(wq); if (cmd.attr_mask & IB_WQ_FLAGS) { wq_attr.flags = cmd.flags; @@ -3096,8 +3104,8 @@ static int ib_uverbs_ex_create_rwq_ind_table(struct uverbs_attr_bundle *attrs) num_read_wqs++) { wq = uobj_get_obj_read(wq, UVERBS_OBJECT_WQ, wqs_handles[num_read_wqs], attrs); - if (!wq) { - err = -EINVAL; + if (IS_ERR(wq)) { + err = PTR_ERR(wq); goto put_wqs; } @@ -3252,8 +3260,8 @@ static int ib_uverbs_ex_create_flow(struct uverbs_attr_bundle *attrs) } qp = uobj_get_obj_read(qp, UVERBS_OBJECT_QP, cmd.qp_handle, attrs); - if (!qp) { - err = -EINVAL; + if (IS_ERR(qp)) { + err = PTR_ERR(qp); goto err_uobj; } @@ -3399,15 +3407,15 @@ static int __uverbs_create_xsrq(struct uverbs_attr_bundle *attrs, if (ib_srq_has_cq(cmd->srq_type)) { attr.ext.cq = uobj_get_obj_read(cq, UVERBS_OBJECT_CQ, cmd->cq_handle, attrs); - if (!attr.ext.cq) { - ret = -EINVAL; + if (IS_ERR(attr.ext.cq)) { + ret = PTR_ERR(attr.ext.cq); goto err_put_xrcd; } } pd = uobj_get_obj_read(pd, UVERBS_OBJECT_PD, cmd->pd_handle, attrs); - if (!pd) { - ret = -EINVAL; + if (IS_ERR(pd)) { + ret = PTR_ERR(pd); goto err_put_cq; } @@ -3514,8 +3522,8 @@ static int ib_uverbs_modify_srq(struct uverbs_attr_bundle *attrs) return ret; srq = uobj_get_obj_read(srq, UVERBS_OBJECT_SRQ, cmd.srq_handle, attrs); - if (!srq) - return -EINVAL; + if (IS_ERR(srq)) + return PTR_ERR(srq); attr.max_wr = cmd.max_wr; attr.srq_limit = cmd.srq_limit; @@ -3542,8 +3550,8 @@ static int ib_uverbs_query_srq(struct uverbs_attr_bundle *attrs) return ret; srq = uobj_get_obj_read(srq, UVERBS_OBJECT_SRQ, cmd.srq_handle, attrs); - if (!srq) - return -EINVAL; + if (IS_ERR(srq)) + return PTR_ERR(srq); ret = ib_query_srq(srq, &attr); @@ -3668,8 +3676,8 @@ static int ib_uverbs_ex_modify_cq(struct uverbs_attr_bundle *attrs) return -EOPNOTSUPP; cq = uobj_get_obj_read(cq, UVERBS_OBJECT_CQ, cmd.cq_handle, attrs); - if (!cq) - return -EINVAL; + if (IS_ERR(cq)) + return PTR_ERR(cq); ret = rdma_set_cq_moderation(cq, cmd.attr.cq_count, cmd.attr.cq_period); diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index b99b3cc283b6..97a116960f31 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -2959,22 +2959,23 @@ EXPORT_SYMBOL(__rdma_block_iter_start); bool __rdma_block_iter_next(struct ib_block_iter *biter) { unsigned int block_offset; - unsigned int sg_delta; + unsigned int delta; if (!biter->__sg_nents || !biter->__sg) return false; biter->__dma_addr = sg_dma_address(biter->__sg) + biter->__sg_advance; block_offset = biter->__dma_addr & (BIT_ULL(biter->__pg_bit) - 1); - sg_delta = BIT_ULL(biter->__pg_bit) - block_offset; + delta = BIT_ULL(biter->__pg_bit) - block_offset; - if (sg_dma_len(biter->__sg) - biter->__sg_advance > sg_delta) { - biter->__sg_advance += sg_delta; - } else { + while (biter->__sg_nents && biter->__sg && + sg_dma_len(biter->__sg) - biter->__sg_advance <= delta) { + delta -= sg_dma_len(biter->__sg) - biter->__sg_advance; biter->__sg_advance = 0; biter->__sg = sg_next(biter->__sg); biter->__sg_nents--; } + biter->__sg_advance += delta; return true; } diff --git a/drivers/infiniband/sw/rxe/rxe_cq.c b/drivers/infiniband/sw/rxe/rxe_cq.c index b1a0ab3cd4bd..43dfc6fd8a3e 100644 --- a/drivers/infiniband/sw/rxe/rxe_cq.c +++ b/drivers/infiniband/sw/rxe/rxe_cq.c @@ -71,11 +71,8 @@ int rxe_cq_from_init(struct rxe_dev *rxe, struct rxe_cq *cq, int cqe, err = do_mmap_info(rxe, uresp ? &uresp->mi : NULL, udata, cq->queue->buf, cq->queue->buf_size, &cq->queue->ip); - if (err) { - vfree(cq->queue->buf); - kfree(cq->queue); + if (err) return err; - } cq->is_user = uresp; diff --git a/drivers/input/keyboard/mtk-pmic-keys.c b/drivers/input/keyboard/mtk-pmic-keys.c index 9b34da0ec260..2d8999023468 100644 --- a/drivers/input/keyboard/mtk-pmic-keys.c +++ b/drivers/input/keyboard/mtk-pmic-keys.c @@ -133,8 +133,8 @@ static void mtk_pmic_keys_lp_reset_setup(struct mtk_pmic_keys *keys, u32 value, mask; int error; - kregs_home = keys->keys[MTK_PMIC_HOMEKEY_INDEX].regs; - kregs_pwr = keys->keys[MTK_PMIC_PWRKEY_INDEX].regs; + kregs_home = ®s->keys_regs[MTK_PMIC_HOMEKEY_INDEX]; + kregs_pwr = ®s->keys_regs[MTK_PMIC_PWRKEY_INDEX]; error = of_property_read_u32(keys->dev->of_node, "power-off-time-sec", &long_press_debounce); diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index d8c90a23a101..6cc66774c107 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -163,6 +163,7 @@ static const char * const topbuttonpad_pnp_ids[] = { static const char * const smbus_pnp_ids[] = { /* all of the topbuttonpad_pnp_ids are valid, we just add some extras */ + "DLL060d", /* Dell Precision M3800 */ "LEN0048", /* X1 Carbon 3 */ "LEN0046", /* X250 */ "LEN0049", /* Yoga 11e */ @@ -189,11 +190,15 @@ static const char * const smbus_pnp_ids[] = { "LEN2054", /* E480 */ "LEN2055", /* E580 */ "LEN2068", /* T14 Gen 1 */ + "SYN1221", /* TUXEDO InfinityBook Pro 14 v5 */ + "SYN3003", /* HP EliteBook 850 G1 */ "SYN3015", /* HP EliteBook 840 G2 */ "SYN3052", /* HP EliteBook 840 G4 */ "SYN3221", /* HP 15-ay000 */ "SYN323d", /* HP Spectre X360 13-w013dx */ "SYN3257", /* HP Envy 13-ad105ng */ + "TOS01f6", /* Dynabook Portege X30L-G */ + "TOS0213", /* Dynabook Portege X30-D */ NULL }; diff --git a/drivers/iommu/amd/io_pgtable_v2.c b/drivers/iommu/amd/io_pgtable_v2.c index 232d17bd941f..c86cbbc21e88 100644 --- a/drivers/iommu/amd/io_pgtable_v2.c +++ b/drivers/iommu/amd/io_pgtable_v2.c @@ -264,7 +264,7 @@ static int iommu_v2_map_pages(struct io_pgtable_ops *ops, unsigned long iova, map_size = get_alloc_page_size(pgsize); pte = v2_alloc_pte(pdom->iop.pgd, iova, map_size, &updated); if (!pte) { - ret = -EINVAL; + ret = -ENOMEM; goto out; } diff --git a/drivers/leds/rgb/leds-pwm-multicolor.c b/drivers/leds/rgb/leds-pwm-multicolor.c index da9d2218ae18..97aa06e2ff60 100644 --- a/drivers/leds/rgb/leds-pwm-multicolor.c +++ b/drivers/leds/rgb/leds-pwm-multicolor.c @@ -135,8 +135,11 @@ static int led_pwm_mc_probe(struct platform_device *pdev) /* init the multicolor's LED class device */ cdev = &priv->mc_cdev.led_cdev; - fwnode_property_read_u32(mcnode, "max-brightness", + ret = fwnode_property_read_u32(mcnode, "max-brightness", &cdev->max_brightness); + if (ret) + goto release_mcnode; + cdev->flags = LED_CORE_SUSPENDRESUME; cdev->brightness_set_blocking = led_pwm_mc_set; diff --git a/drivers/mailbox/mailbox.c b/drivers/mailbox/mailbox.c index adf36c05fa43..ef1149e1494f 100644 --- a/drivers/mailbox/mailbox.c +++ b/drivers/mailbox/mailbox.c @@ -414,11 +414,12 @@ struct mbox_chan *mbox_request_channel(struct mbox_client *cl, int index) mutex_lock(&con_mutex); - if (of_parse_phandle_with_args(dev->of_node, "mboxes", - "#mbox-cells", index, &spec)) { + ret = of_parse_phandle_with_args(dev->of_node, "mboxes", "#mbox-cells", + index, &spec); + if (ret) { dev_dbg(dev, "%s: can't parse \"mboxes\" property\n", __func__); mutex_unlock(&con_mutex); - return ERR_PTR(-ENODEV); + return ERR_PTR(ret); } chan = ERR_PTR(-EPROBE_DEFER); diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index e714114d495a..66608b42ee1a 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -2875,6 +2875,27 @@ static dm_cblock_t get_cache_dev_size(struct cache *cache) return to_cblock(size); } +static bool can_resume(struct cache *cache) +{ + /* + * Disallow retrying the resume operation for devices that failed the + * first resume attempt, as the failure leaves the policy object partially + * initialized. Retrying could trigger BUG_ON when loading cache mappings + * into the incomplete policy object. + */ + if (cache->sized && !cache->loaded_mappings) { + if (get_cache_mode(cache) != CM_WRITE) + DMERR("%s: unable to resume a failed-loaded cache, please check metadata.", + cache_device_name(cache)); + else + DMERR("%s: unable to resume cache due to missing proper cache table reload", + cache_device_name(cache)); + return false; + } + + return true; +} + static bool can_resize(struct cache *cache, dm_cblock_t new_size) { if (from_cblock(new_size) > from_cblock(cache->cache_size)) { @@ -2923,6 +2944,9 @@ static int cache_preresume(struct dm_target *ti) struct cache *cache = ti->private; dm_cblock_t csize = get_cache_dev_size(cache); + if (!can_resume(cache)) + return -EINVAL; + /* * Check to see if the cache has resized. */ diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 66bd8c80c83c..171e101e9eec 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -655,6 +655,10 @@ int dm_table_add_target(struct dm_table *t, const char *type, DMERR("%s: zero-length target", dm_device_name(t->md)); return -EINVAL; } + if (start + len < start || start + len > LLONG_MAX >> SECTOR_SHIFT) { + DMERR("%s: too large device", dm_device_name(t->md)); + return -EINVAL; + } ti->type = dm_get_target_type(type); if (!ti->type) { @@ -1227,7 +1231,7 @@ static int dm_keyslot_evict(struct blk_crypto_profile *profile, t = dm_get_live_table(md, &srcu_idx); if (!t) - return 0; + goto put_live_table; for (unsigned int i = 0; i < t->num_targets; i++) { struct dm_target *ti = dm_table_get_target(t, i); @@ -1238,6 +1242,7 @@ static int dm_keyslot_evict(struct blk_crypto_profile *profile, (void *)key); } +put_live_table: dm_put_live_table(md, srcu_idx); return 0; } diff --git a/drivers/md/dm.c b/drivers/md/dm.c index f70129bc703b..4767265793de 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1523,14 +1523,18 @@ static void __send_empty_flush(struct clone_info *ci) { struct dm_table *t = ci->map; struct bio flush_bio; + blk_opf_t opf = REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC; + + if ((ci->io->orig_bio->bi_opf & (REQ_IDLE | REQ_SYNC)) == + (REQ_IDLE | REQ_SYNC)) + opf |= REQ_IDLE; /* * Use an on-stack bio for this, it's safe since we don't * need to reference it after submit. It's just used as * the basis for the clone(s). */ - bio_init(&flush_bio, ci->io->md->disk->part0, NULL, 0, - REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC); + bio_init(&flush_bio, ci->io->md->disk->part0, NULL, 0, opf); ci->bio = &flush_bio; ci->sector_count = 0; diff --git a/drivers/media/i2c/adv7180.c b/drivers/media/i2c/adv7180.c index 216fe396973f..46912a7b671a 100644 --- a/drivers/media/i2c/adv7180.c +++ b/drivers/media/i2c/adv7180.c @@ -194,6 +194,7 @@ struct adv7180_state; #define ADV7180_FLAG_V2 BIT(1) #define ADV7180_FLAG_MIPI_CSI2 BIT(2) #define ADV7180_FLAG_I2P BIT(3) +#define ADV7180_FLAG_TEST_PATTERN BIT(4) struct adv7180_chip_info { unsigned int flags; @@ -673,11 +674,15 @@ static int adv7180_init_controls(struct adv7180_state *state) ADV7180_HUE_MAX, 1, ADV7180_HUE_DEF); v4l2_ctrl_new_custom(&state->ctrl_hdl, &adv7180_ctrl_fast_switch, NULL); - v4l2_ctrl_new_std_menu_items(&state->ctrl_hdl, &adv7180_ctrl_ops, - V4L2_CID_TEST_PATTERN, - ARRAY_SIZE(test_pattern_menu) - 1, - 0, ARRAY_SIZE(test_pattern_menu) - 1, - test_pattern_menu); + if (state->chip_info->flags & ADV7180_FLAG_TEST_PATTERN) { + v4l2_ctrl_new_std_menu_items(&state->ctrl_hdl, + &adv7180_ctrl_ops, + V4L2_CID_TEST_PATTERN, + ARRAY_SIZE(test_pattern_menu) - 1, + 0, + ARRAY_SIZE(test_pattern_menu) - 1, + test_pattern_menu); + } state->sd.ctrl_handler = &state->ctrl_hdl; if (state->ctrl_hdl.error) { @@ -1209,7 +1214,7 @@ static const struct adv7180_chip_info adv7182_info = { }; static const struct adv7180_chip_info adv7280_info = { - .flags = ADV7180_FLAG_V2 | ADV7180_FLAG_I2P, + .flags = ADV7180_FLAG_V2 | ADV7180_FLAG_I2P | ADV7180_FLAG_TEST_PATTERN, .valid_input_mask = BIT(ADV7182_INPUT_CVBS_AIN1) | BIT(ADV7182_INPUT_CVBS_AIN2) | BIT(ADV7182_INPUT_CVBS_AIN3) | @@ -1223,7 +1228,8 @@ static const struct adv7180_chip_info adv7280_info = { }; static const struct adv7180_chip_info adv7280_m_info = { - .flags = ADV7180_FLAG_V2 | ADV7180_FLAG_MIPI_CSI2 | ADV7180_FLAG_I2P, + .flags = ADV7180_FLAG_V2 | ADV7180_FLAG_MIPI_CSI2 | ADV7180_FLAG_I2P | + ADV7180_FLAG_TEST_PATTERN, .valid_input_mask = BIT(ADV7182_INPUT_CVBS_AIN1) | BIT(ADV7182_INPUT_CVBS_AIN2) | BIT(ADV7182_INPUT_CVBS_AIN3) | @@ -1244,7 +1250,8 @@ static const struct adv7180_chip_info adv7280_m_info = { }; static const struct adv7180_chip_info adv7281_info = { - .flags = ADV7180_FLAG_V2 | ADV7180_FLAG_MIPI_CSI2, + .flags = ADV7180_FLAG_V2 | ADV7180_FLAG_MIPI_CSI2 | + ADV7180_FLAG_TEST_PATTERN, .valid_input_mask = BIT(ADV7182_INPUT_CVBS_AIN1) | BIT(ADV7182_INPUT_CVBS_AIN2) | BIT(ADV7182_INPUT_CVBS_AIN7) | @@ -1259,7 +1266,8 @@ static const struct adv7180_chip_info adv7281_info = { }; static const struct adv7180_chip_info adv7281_m_info = { - .flags = ADV7180_FLAG_V2 | ADV7180_FLAG_MIPI_CSI2, + .flags = ADV7180_FLAG_V2 | ADV7180_FLAG_MIPI_CSI2 | + ADV7180_FLAG_TEST_PATTERN, .valid_input_mask = BIT(ADV7182_INPUT_CVBS_AIN1) | BIT(ADV7182_INPUT_CVBS_AIN2) | BIT(ADV7182_INPUT_CVBS_AIN3) | @@ -1279,7 +1287,8 @@ static const struct adv7180_chip_info adv7281_m_info = { }; static const struct adv7180_chip_info adv7281_ma_info = { - .flags = ADV7180_FLAG_V2 | ADV7180_FLAG_MIPI_CSI2, + .flags = ADV7180_FLAG_V2 | ADV7180_FLAG_MIPI_CSI2 | + ADV7180_FLAG_TEST_PATTERN, .valid_input_mask = BIT(ADV7182_INPUT_CVBS_AIN1) | BIT(ADV7182_INPUT_CVBS_AIN2) | BIT(ADV7182_INPUT_CVBS_AIN3) | @@ -1304,7 +1313,7 @@ static const struct adv7180_chip_info adv7281_ma_info = { }; static const struct adv7180_chip_info adv7282_info = { - .flags = ADV7180_FLAG_V2 | ADV7180_FLAG_I2P, + .flags = ADV7180_FLAG_V2 | ADV7180_FLAG_I2P | ADV7180_FLAG_TEST_PATTERN, .valid_input_mask = BIT(ADV7182_INPUT_CVBS_AIN1) | BIT(ADV7182_INPUT_CVBS_AIN2) | BIT(ADV7182_INPUT_CVBS_AIN7) | @@ -1319,7 +1328,8 @@ static const struct adv7180_chip_info adv7282_info = { }; static const struct adv7180_chip_info adv7282_m_info = { - .flags = ADV7180_FLAG_V2 | ADV7180_FLAG_MIPI_CSI2 | ADV7180_FLAG_I2P, + .flags = ADV7180_FLAG_V2 | ADV7180_FLAG_MIPI_CSI2 | ADV7180_FLAG_I2P | + ADV7180_FLAG_TEST_PATTERN, .valid_input_mask = BIT(ADV7182_INPUT_CVBS_AIN1) | BIT(ADV7182_INPUT_CVBS_AIN2) | BIT(ADV7182_INPUT_CVBS_AIN3) | diff --git a/drivers/media/platform/qcom/camss/camss-csid.c b/drivers/media/platform/qcom/camss/camss-csid.c index 6360314f04a6..b90e2e690f3a 100644 --- a/drivers/media/platform/qcom/camss/camss-csid.c +++ b/drivers/media/platform/qcom/camss/camss-csid.c @@ -239,11 +239,13 @@ static int csid_set_stream(struct v4l2_subdev *sd, int enable) int ret; if (enable) { - ret = v4l2_ctrl_handler_setup(&csid->ctrls); - if (ret < 0) { - dev_err(csid->camss->dev, - "could not sync v4l2 controls: %d\n", ret); - return ret; + if (csid->testgen.nmodes != CSID_PAYLOAD_MODE_DISABLED) { + ret = v4l2_ctrl_handler_setup(&csid->ctrls); + if (ret < 0) { + dev_err(csid->camss->dev, + "could not sync v4l2 controls: %d\n", ret); + return ret; + } } if (!csid->testgen.enabled && @@ -318,7 +320,8 @@ static void csid_try_format(struct csid_device *csid, break; case MSM_CSID_PAD_SRC: - if (csid->testgen_mode->cur.val == 0) { + if (csid->testgen.nmodes == CSID_PAYLOAD_MODE_DISABLED || + csid->testgen_mode->cur.val == 0) { /* Test generator is disabled, */ /* keep pad formats in sync */ u32 code = fmt->code; @@ -368,7 +371,8 @@ static int csid_enum_mbus_code(struct v4l2_subdev *sd, code->code = csid->formats[code->index].code; } else { - if (csid->testgen_mode->cur.val == 0) { + if (csid->testgen.nmodes == CSID_PAYLOAD_MODE_DISABLED || + csid->testgen_mode->cur.val == 0) { struct v4l2_mbus_framefmt *sink_fmt; sink_fmt = __csid_get_format(csid, sd_state, @@ -750,7 +754,8 @@ static int csid_link_setup(struct media_entity *entity, /* If test generator is enabled */ /* do not allow a link from CSIPHY to CSID */ - if (csid->testgen_mode->cur.val != 0) + if (csid->testgen.nmodes != CSID_PAYLOAD_MODE_DISABLED && + csid->testgen_mode->cur.val != 0) return -EBUSY; sd = media_entity_to_v4l2_subdev(remote->entity); @@ -843,25 +848,28 @@ int msm_csid_register_entity(struct csid_device *csid, MSM_CSID_NAME, csid->id); v4l2_set_subdevdata(sd, csid); - ret = v4l2_ctrl_handler_init(&csid->ctrls, 1); - if (ret < 0) { - dev_err(dev, "Failed to init ctrl handler: %d\n", ret); - return ret; + if (csid->testgen.nmodes != CSID_PAYLOAD_MODE_DISABLED) { + ret = v4l2_ctrl_handler_init(&csid->ctrls, 1); + if (ret < 0) { + dev_err(dev, "Failed to init ctrl handler: %d\n", ret); + return ret; + } + + csid->testgen_mode = + v4l2_ctrl_new_std_menu_items(&csid->ctrls, + &csid_ctrl_ops, V4L2_CID_TEST_PATTERN, + csid->testgen.nmodes, 0, 0, + csid->testgen.modes); + + if (csid->ctrls.error) { + dev_err(dev, "Failed to init ctrl: %d\n", csid->ctrls.error); + ret = csid->ctrls.error; + goto free_ctrl; + } + + csid->subdev.ctrl_handler = &csid->ctrls; } - csid->testgen_mode = v4l2_ctrl_new_std_menu_items(&csid->ctrls, - &csid_ctrl_ops, V4L2_CID_TEST_PATTERN, - csid->testgen.nmodes, 0, 0, - csid->testgen.modes); - - if (csid->ctrls.error) { - dev_err(dev, "Failed to init ctrl: %d\n", csid->ctrls.error); - ret = csid->ctrls.error; - goto free_ctrl; - } - - csid->subdev.ctrl_handler = &csid->ctrls; - ret = csid_init_formats(sd, NULL); if (ret < 0) { dev_err(dev, "Failed to init format: %d\n", ret); @@ -891,7 +899,8 @@ int msm_csid_register_entity(struct csid_device *csid, media_cleanup: media_entity_cleanup(&sd->entity); free_ctrl: - v4l2_ctrl_handler_free(&csid->ctrls); + if (csid->testgen.nmodes != CSID_PAYLOAD_MODE_DISABLED) + v4l2_ctrl_handler_free(&csid->ctrls); return ret; } @@ -904,5 +913,6 @@ void msm_csid_unregister_entity(struct csid_device *csid) { v4l2_device_unregister_subdev(&csid->subdev); media_entity_cleanup(&csid->subdev.entity); - v4l2_ctrl_handler_free(&csid->ctrls); + if (csid->testgen.nmodes != CSID_PAYLOAD_MODE_DISABLED) + v4l2_ctrl_handler_free(&csid->ctrls); } diff --git a/drivers/media/platform/st/sti/c8sectpfe/c8sectpfe-core.c b/drivers/media/platform/st/sti/c8sectpfe/c8sectpfe-core.c index 1dbb89f0ddb8..b2a977f1ec18 100644 --- a/drivers/media/platform/st/sti/c8sectpfe/c8sectpfe-core.c +++ b/drivers/media/platform/st/sti/c8sectpfe/c8sectpfe-core.c @@ -802,13 +802,12 @@ static int c8sectpfe_probe(struct platform_device *pdev) } tsin->i2c_adapter = of_find_i2c_adapter_by_node(i2c_bus); + of_node_put(i2c_bus); if (!tsin->i2c_adapter) { dev_err(&pdev->dev, "No i2c adapter found\n"); - of_node_put(i2c_bus); ret = -ENODEV; goto err_node_put; } - of_node_put(i2c_bus); tsin->rst_gpio = of_get_named_gpio(child, "reset-gpios", 0); diff --git a/drivers/media/test-drivers/vivid/vivid-kthread-cap.c b/drivers/media/test-drivers/vivid/vivid-kthread-cap.c index 690daada7db4..54e6a6772035 100644 --- a/drivers/media/test-drivers/vivid/vivid-kthread-cap.c +++ b/drivers/media/test-drivers/vivid/vivid-kthread-cap.c @@ -894,9 +894,14 @@ static int vivid_thread_vid_cap(void *data) next_jiffies_since_start = jiffies_since_start; wait_jiffies = next_jiffies_since_start - jiffies_since_start; - while (time_is_after_jiffies(cur_jiffies + wait_jiffies) && - !kthread_should_stop()) - schedule(); + if (!time_is_after_jiffies(cur_jiffies + wait_jiffies)) + continue; + + wait_queue_head_t wait; + + init_waitqueue_head(&wait); + wait_event_interruptible_timeout(wait, kthread_should_stop(), + cur_jiffies + wait_jiffies - jiffies); } dprintk(dev, 1, "Video Capture Thread End\n"); return 0; diff --git a/drivers/media/test-drivers/vivid/vivid-kthread-out.c b/drivers/media/test-drivers/vivid/vivid-kthread-out.c index 0833e021bb11..8a17a01e6e42 100644 --- a/drivers/media/test-drivers/vivid/vivid-kthread-out.c +++ b/drivers/media/test-drivers/vivid/vivid-kthread-out.c @@ -235,9 +235,14 @@ static int vivid_thread_vid_out(void *data) next_jiffies_since_start = jiffies_since_start; wait_jiffies = next_jiffies_since_start - jiffies_since_start; - while (time_is_after_jiffies(cur_jiffies + wait_jiffies) && - !kthread_should_stop()) - schedule(); + if (!time_is_after_jiffies(cur_jiffies + wait_jiffies)) + continue; + + wait_queue_head_t wait; + + init_waitqueue_head(&wait); + wait_event_interruptible_timeout(wait, kthread_should_stop(), + cur_jiffies + wait_jiffies - jiffies); } dprintk(dev, 1, "Video Output Thread End\n"); return 0; diff --git a/drivers/media/test-drivers/vivid/vivid-kthread-touch.c b/drivers/media/test-drivers/vivid/vivid-kthread-touch.c index fa711ee36a3f..c862689786b6 100644 --- a/drivers/media/test-drivers/vivid/vivid-kthread-touch.c +++ b/drivers/media/test-drivers/vivid/vivid-kthread-touch.c @@ -135,9 +135,14 @@ static int vivid_thread_touch_cap(void *data) next_jiffies_since_start = jiffies_since_start; wait_jiffies = next_jiffies_since_start - jiffies_since_start; - while (time_is_after_jiffies(cur_jiffies + wait_jiffies) && - !kthread_should_stop()) - schedule(); + if (!time_is_after_jiffies(cur_jiffies + wait_jiffies)) + continue; + + wait_queue_head_t wait; + + init_waitqueue_head(&wait); + wait_event_interruptible_timeout(wait, kthread_should_stop(), + cur_jiffies + wait_jiffies - jiffies); } dprintk(dev, 1, "Touch Capture Thread End\n"); return 0; diff --git a/drivers/media/test-drivers/vivid/vivid-sdr-cap.c b/drivers/media/test-drivers/vivid/vivid-sdr-cap.c index 0ae5628b86c9..abccd1d0109e 100644 --- a/drivers/media/test-drivers/vivid/vivid-sdr-cap.c +++ b/drivers/media/test-drivers/vivid/vivid-sdr-cap.c @@ -206,9 +206,14 @@ static int vivid_thread_sdr_cap(void *data) next_jiffies_since_start = jiffies_since_start; wait_jiffies = next_jiffies_since_start - jiffies_since_start; - while (time_is_after_jiffies(cur_jiffies + wait_jiffies) && - !kthread_should_stop()) - schedule(); + if (!time_is_after_jiffies(cur_jiffies + wait_jiffies)) + continue; + + wait_queue_head_t wait; + + init_waitqueue_head(&wait); + wait_event_interruptible_timeout(wait, kthread_should_stop(), + cur_jiffies + wait_jiffies - jiffies); } dprintk(dev, 1, "SDR Capture Thread End\n"); return 0; diff --git a/drivers/media/usb/cx231xx/cx231xx-417.c b/drivers/media/usb/cx231xx/cx231xx-417.c index c5e21785fafe..02343e88cc61 100644 --- a/drivers/media/usb/cx231xx/cx231xx-417.c +++ b/drivers/media/usb/cx231xx/cx231xx-417.c @@ -1722,6 +1722,8 @@ static void cx231xx_video_dev_init( vfd->lock = &dev->lock; vfd->release = video_device_release_empty; vfd->ctrl_handler = &dev->mpeg_ctrl_handler.hdl; + vfd->device_caps = V4L2_CAP_READWRITE | V4L2_CAP_STREAMING | + V4L2_CAP_VIDEO_CAPTURE; video_set_drvdata(vfd, dev); if (dev->tuner_type == TUNER_ABSENT) { v4l2_disable_ioctl(vfd, VIDIOC_G_FREQUENCY); diff --git a/drivers/media/usb/uvc/uvc_v4l2.c b/drivers/media/usb/uvc/uvc_v4l2.c index bd4677a6e653..0aaa4fce61da 100644 --- a/drivers/media/usb/uvc/uvc_v4l2.c +++ b/drivers/media/usb/uvc/uvc_v4l2.c @@ -36,6 +36,12 @@ static int uvc_ioctl_ctrl_map(struct uvc_video_chain *chain, unsigned int size; int ret; + if (xmap->data_type > UVC_CTRL_DATA_TYPE_BITMASK) { + uvc_dbg(chain->dev, CONTROL, + "Unsupported UVC data type %u\n", xmap->data_type); + return -EINVAL; + } + map = kzalloc(sizeof(*map), GFP_KERNEL); if (map == NULL) return -ENOMEM; diff --git a/drivers/mmc/host/dw_mmc-exynos.c b/drivers/mmc/host/dw_mmc-exynos.c index 9f20ac524c8b..2a5c3c822f6a 100644 --- a/drivers/mmc/host/dw_mmc-exynos.c +++ b/drivers/mmc/host/dw_mmc-exynos.c @@ -28,6 +28,8 @@ enum dw_mci_exynos_type { DW_MCI_TYPE_EXYNOS5420_SMU, DW_MCI_TYPE_EXYNOS7, DW_MCI_TYPE_EXYNOS7_SMU, + DW_MCI_TYPE_EXYNOS7870, + DW_MCI_TYPE_EXYNOS7870_SMU, DW_MCI_TYPE_ARTPEC8, }; @@ -70,6 +72,12 @@ static struct dw_mci_exynos_compatible { }, { .compatible = "samsung,exynos7-dw-mshc-smu", .ctrl_type = DW_MCI_TYPE_EXYNOS7_SMU, + }, { + .compatible = "samsung,exynos7870-dw-mshc", + .ctrl_type = DW_MCI_TYPE_EXYNOS7870, + }, { + .compatible = "samsung,exynos7870-dw-mshc-smu", + .ctrl_type = DW_MCI_TYPE_EXYNOS7870_SMU, }, { .compatible = "axis,artpec8-dw-mshc", .ctrl_type = DW_MCI_TYPE_ARTPEC8, @@ -86,6 +94,8 @@ static inline u8 dw_mci_exynos_get_ciu_div(struct dw_mci *host) return EXYNOS4210_FIXED_CIU_CLK_DIV; else if (priv->ctrl_type == DW_MCI_TYPE_EXYNOS7 || priv->ctrl_type == DW_MCI_TYPE_EXYNOS7_SMU || + priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870 || + priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870_SMU || priv->ctrl_type == DW_MCI_TYPE_ARTPEC8) return SDMMC_CLKSEL_GET_DIV(mci_readl(host, CLKSEL64)) + 1; else @@ -101,7 +111,8 @@ static void dw_mci_exynos_config_smu(struct dw_mci *host) * set for non-ecryption mode at this time. */ if (priv->ctrl_type == DW_MCI_TYPE_EXYNOS5420_SMU || - priv->ctrl_type == DW_MCI_TYPE_EXYNOS7_SMU) { + priv->ctrl_type == DW_MCI_TYPE_EXYNOS7_SMU || + priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870_SMU) { mci_writel(host, MPSBEGIN0, 0); mci_writel(host, MPSEND0, SDMMC_ENDING_SEC_NR_MAX); mci_writel(host, MPSCTRL0, SDMMC_MPSCTRL_SECURE_WRITE_BIT | @@ -127,6 +138,12 @@ static int dw_mci_exynos_priv_init(struct dw_mci *host) DQS_CTRL_GET_RD_DELAY(priv->saved_strobe_ctrl); } + if (priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870 || + priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870_SMU) { + /* Quirk needed for certain Exynos SoCs */ + host->quirks |= DW_MMC_QUIRK_FIFO64_32; + } + if (priv->ctrl_type == DW_MCI_TYPE_ARTPEC8) { /* Quirk needed for the ARTPEC-8 SoC */ host->quirks |= DW_MMC_QUIRK_EXTENDED_TMOUT; @@ -144,6 +161,8 @@ static void dw_mci_exynos_set_clksel_timing(struct dw_mci *host, u32 timing) if (priv->ctrl_type == DW_MCI_TYPE_EXYNOS7 || priv->ctrl_type == DW_MCI_TYPE_EXYNOS7_SMU || + priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870 || + priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870_SMU || priv->ctrl_type == DW_MCI_TYPE_ARTPEC8) clksel = mci_readl(host, CLKSEL64); else @@ -153,6 +172,8 @@ static void dw_mci_exynos_set_clksel_timing(struct dw_mci *host, u32 timing) if (priv->ctrl_type == DW_MCI_TYPE_EXYNOS7 || priv->ctrl_type == DW_MCI_TYPE_EXYNOS7_SMU || + priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870 || + priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870_SMU || priv->ctrl_type == DW_MCI_TYPE_ARTPEC8) mci_writel(host, CLKSEL64, clksel); else @@ -223,6 +244,8 @@ static int dw_mci_exynos_resume_noirq(struct device *dev) if (priv->ctrl_type == DW_MCI_TYPE_EXYNOS7 || priv->ctrl_type == DW_MCI_TYPE_EXYNOS7_SMU || + priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870 || + priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870_SMU || priv->ctrl_type == DW_MCI_TYPE_ARTPEC8) clksel = mci_readl(host, CLKSEL64); else @@ -231,6 +254,8 @@ static int dw_mci_exynos_resume_noirq(struct device *dev) if (clksel & SDMMC_CLKSEL_WAKEUP_INT) { if (priv->ctrl_type == DW_MCI_TYPE_EXYNOS7 || priv->ctrl_type == DW_MCI_TYPE_EXYNOS7_SMU || + priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870 || + priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870_SMU || priv->ctrl_type == DW_MCI_TYPE_ARTPEC8) mci_writel(host, CLKSEL64, clksel); else @@ -410,6 +435,8 @@ static inline u8 dw_mci_exynos_get_clksmpl(struct dw_mci *host) if (priv->ctrl_type == DW_MCI_TYPE_EXYNOS7 || priv->ctrl_type == DW_MCI_TYPE_EXYNOS7_SMU || + priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870 || + priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870_SMU || priv->ctrl_type == DW_MCI_TYPE_ARTPEC8) return SDMMC_CLKSEL_CCLK_SAMPLE(mci_readl(host, CLKSEL64)); else @@ -423,6 +450,8 @@ static inline void dw_mci_exynos_set_clksmpl(struct dw_mci *host, u8 sample) if (priv->ctrl_type == DW_MCI_TYPE_EXYNOS7 || priv->ctrl_type == DW_MCI_TYPE_EXYNOS7_SMU || + priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870 || + priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870_SMU || priv->ctrl_type == DW_MCI_TYPE_ARTPEC8) clksel = mci_readl(host, CLKSEL64); else @@ -430,6 +459,8 @@ static inline void dw_mci_exynos_set_clksmpl(struct dw_mci *host, u8 sample) clksel = SDMMC_CLKSEL_UP_SAMPLE(clksel, sample); if (priv->ctrl_type == DW_MCI_TYPE_EXYNOS7 || priv->ctrl_type == DW_MCI_TYPE_EXYNOS7_SMU || + priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870 || + priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870_SMU || priv->ctrl_type == DW_MCI_TYPE_ARTPEC8) mci_writel(host, CLKSEL64, clksel); else @@ -444,6 +475,8 @@ static inline u8 dw_mci_exynos_move_next_clksmpl(struct dw_mci *host) if (priv->ctrl_type == DW_MCI_TYPE_EXYNOS7 || priv->ctrl_type == DW_MCI_TYPE_EXYNOS7_SMU || + priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870 || + priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870_SMU || priv->ctrl_type == DW_MCI_TYPE_ARTPEC8) clksel = mci_readl(host, CLKSEL64); else @@ -454,6 +487,8 @@ static inline u8 dw_mci_exynos_move_next_clksmpl(struct dw_mci *host) if (priv->ctrl_type == DW_MCI_TYPE_EXYNOS7 || priv->ctrl_type == DW_MCI_TYPE_EXYNOS7_SMU || + priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870 || + priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870_SMU || priv->ctrl_type == DW_MCI_TYPE_ARTPEC8) mci_writel(host, CLKSEL64, clksel); else @@ -633,6 +668,10 @@ static const struct of_device_id dw_mci_exynos_match[] = { .data = &exynos_drv_data, }, { .compatible = "samsung,exynos7-dw-mshc-smu", .data = &exynos_drv_data, }, + { .compatible = "samsung,exynos7870-dw-mshc", + .data = &exynos_drv_data, }, + { .compatible = "samsung,exynos7870-dw-mshc-smu", + .data = &exynos_drv_data, }, { .compatible = "axis,artpec8-dw-mshc", .data = &artpec_drv_data, }, {}, diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c index 5a5cc40d4bc3..c71d9956b398 100644 --- a/drivers/mmc/host/sdhci-pci-core.c +++ b/drivers/mmc/host/sdhci-pci-core.c @@ -613,8 +613,12 @@ static void sdhci_intel_set_power(struct sdhci_host *host, unsigned char mode, sdhci_set_power(host, mode, vdd); - if (mode == MMC_POWER_OFF) + if (mode == MMC_POWER_OFF) { + if (slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_APL_SD || + slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_BYT_SD) + usleep_range(15000, 17500); return; + } /* * Bus power might not enable after D3 -> D0 transition due to the diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index 071aa16baa98..4b993ba864f2 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -2050,10 +2050,15 @@ void sdhci_set_clock(struct sdhci_host *host, unsigned int clock) host->mmc->actual_clock = 0; - sdhci_writew(host, 0, SDHCI_CLOCK_CONTROL); + clk = sdhci_readw(host, SDHCI_CLOCK_CONTROL); + if (clk & SDHCI_CLOCK_CARD_EN) + sdhci_writew(host, clk & ~SDHCI_CLOCK_CARD_EN, + SDHCI_CLOCK_CONTROL); - if (clock == 0) + if (clock == 0) { + sdhci_writew(host, 0, SDHCI_CLOCK_CONTROL); return; + } clk = sdhci_calc_clk(host, clock, &host->mmc->actual_clock); sdhci_enable_clk(host, clk); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index ded9e369e403..3cedadef9c8a 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2431,7 +2431,7 @@ static int __bond_release_one(struct net_device *bond_dev, RCU_INIT_POINTER(bond->current_arp_slave, NULL); - if (!all && (!bond->params.fail_over_mac || + if (!all && (bond->params.fail_over_mac != BOND_FOM_ACTIVE || BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP)) { if (ether_addr_equal_64bits(bond_dev->dev_addr, slave->perm_hwaddr) && bond_has_slaves(bond)) diff --git a/drivers/net/can/c_can/c_can_platform.c b/drivers/net/can/c_can/c_can_platform.c index c5d7093d5413..c29862b3bb1f 100644 --- a/drivers/net/can/c_can/c_can_platform.c +++ b/drivers/net/can/c_can/c_can_platform.c @@ -334,7 +334,7 @@ static int c_can_plat_probe(struct platform_device *pdev) /* Check if we need custom RAMINIT via syscon. Mostly for TI * platforms. Only supported with DT boot. */ - if (np && of_property_read_bool(np, "syscon-raminit")) { + if (np && of_property_present(np, "syscon-raminit")) { u32 id; struct c_can_raminit *raminit = &priv->raminit_sys; diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index f28bdb5badd0..56b0f49c8116 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -2047,9 +2047,9 @@ EXPORT_SYMBOL_GPL(m_can_class_register); void m_can_class_unregister(struct m_can_classdev *cdev) { + unregister_candev(cdev->net); if (cdev->is_peripheral) can_rx_offload_del(&cdev->offload); - unregister_candev(cdev->net); } EXPORT_SYMBOL_GPL(m_can_class_unregister); diff --git a/drivers/net/can/slcan/slcan-core.c b/drivers/net/can/slcan/slcan-core.c index f4db77007c13..982637f8ea2f 100644 --- a/drivers/net/can/slcan/slcan-core.c +++ b/drivers/net/can/slcan/slcan-core.c @@ -71,12 +71,21 @@ MODULE_AUTHOR("Dario Binacchi "); #define SLCAN_CMD_LEN 1 #define SLCAN_SFF_ID_LEN 3 #define SLCAN_EFF_ID_LEN 8 +#define SLCAN_DATA_LENGTH_LEN 1 +#define SLCAN_ERROR_LEN 1 #define SLCAN_STATE_LEN 1 #define SLCAN_STATE_BE_RXCNT_LEN 3 #define SLCAN_STATE_BE_TXCNT_LEN 3 -#define SLCAN_STATE_FRAME_LEN (1 + SLCAN_CMD_LEN + \ - SLCAN_STATE_BE_RXCNT_LEN + \ - SLCAN_STATE_BE_TXCNT_LEN) +#define SLCAN_STATE_MSG_LEN (SLCAN_CMD_LEN + \ + SLCAN_STATE_LEN + \ + SLCAN_STATE_BE_RXCNT_LEN + \ + SLCAN_STATE_BE_TXCNT_LEN) +#define SLCAN_ERROR_MSG_LEN_MIN (SLCAN_CMD_LEN + \ + SLCAN_ERROR_LEN + \ + SLCAN_DATA_LENGTH_LEN) +#define SLCAN_FRAME_MSG_LEN_MIN (SLCAN_CMD_LEN + \ + SLCAN_SFF_ID_LEN + \ + SLCAN_DATA_LENGTH_LEN) struct slcan { struct can_priv can; @@ -176,6 +185,9 @@ static void slcan_bump_frame(struct slcan *sl) u32 tmpid; char *cmd = sl->rbuff; + if (sl->rcount < SLCAN_FRAME_MSG_LEN_MIN) + return; + skb = alloc_can_skb(sl->dev, &cf); if (unlikely(!skb)) { sl->dev->stats.rx_dropped++; @@ -281,7 +293,7 @@ static void slcan_bump_state(struct slcan *sl) return; } - if (state == sl->can.state || sl->rcount < SLCAN_STATE_FRAME_LEN) + if (state == sl->can.state || sl->rcount != SLCAN_STATE_MSG_LEN) return; cmd += SLCAN_STATE_BE_RXCNT_LEN + SLCAN_CMD_LEN + 1; @@ -328,6 +340,9 @@ static void slcan_bump_err(struct slcan *sl) bool rx_errors = false, tx_errors = false, rx_over_errors = false; int i, len; + if (sl->rcount < SLCAN_ERROR_MSG_LEN_MIN) + return; + /* get len from sanitized ASCII value */ len = cmd[1]; if (len >= '0' && len < '9') @@ -456,8 +471,7 @@ static void slcan_bump(struct slcan *sl) static void slcan_unesc(struct slcan *sl, unsigned char s) { if ((s == '\r') || (s == '\a')) { /* CR or BEL ends the pdu */ - if (!test_and_clear_bit(SLF_ERROR, &sl->flags) && - sl->rcount > 4) + if (!test_and_clear_bit(SLF_ERROR, &sl->flags)) slcan_bump(sl); sl->rcount = 0; diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c index 6fecfe4cd080..21ae3a89924e 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c @@ -75,6 +75,24 @@ static const struct can_bittiming_const mcp251xfd_data_bittiming_const = { .brp_inc = 1, }; +/* The datasheet of the mcp2518fd (DS20006027B) specifies a range of + * [-64,63] for TDCO, indicating a relative TDCO. + * + * Manual tests have shown, that using a relative TDCO configuration + * results in bus off, while an absolute configuration works. + * + * For TDCO use the max value (63) from the data sheet, but 0 as the + * minimum. + */ +static const struct can_tdc_const mcp251xfd_tdc_const = { + .tdcv_min = 0, + .tdcv_max = 63, + .tdco_min = 0, + .tdco_max = 63, + .tdcf_min = 0, + .tdcf_max = 0, +}; + static const char *__mcp251xfd_get_model_str(enum mcp251xfd_model model) { switch (model) { @@ -510,8 +528,7 @@ static int mcp251xfd_set_bittiming(const struct mcp251xfd_priv *priv) { const struct can_bittiming *bt = &priv->can.bittiming; const struct can_bittiming *dbt = &priv->can.data_bittiming; - u32 val = 0; - s8 tdco; + u32 tdcmod, val = 0; int err; /* CAN Control Register @@ -575,11 +592,16 @@ static int mcp251xfd_set_bittiming(const struct mcp251xfd_priv *priv) return err; /* Transmitter Delay Compensation */ - tdco = clamp_t(int, dbt->brp * (dbt->prop_seg + dbt->phase_seg1), - -64, 63); - val = FIELD_PREP(MCP251XFD_REG_TDC_TDCMOD_MASK, - MCP251XFD_REG_TDC_TDCMOD_AUTO) | - FIELD_PREP(MCP251XFD_REG_TDC_TDCO_MASK, tdco); + if (priv->can.ctrlmode & CAN_CTRLMODE_TDC_AUTO) + tdcmod = MCP251XFD_REG_TDC_TDCMOD_AUTO; + else if (priv->can.ctrlmode & CAN_CTRLMODE_TDC_MANUAL) + tdcmod = MCP251XFD_REG_TDC_TDCMOD_MANUAL; + else + tdcmod = MCP251XFD_REG_TDC_TDCMOD_DISABLED; + + val = FIELD_PREP(MCP251XFD_REG_TDC_TDCMOD_MASK, tdcmod) | + FIELD_PREP(MCP251XFD_REG_TDC_TDCV_MASK, priv->can.tdc.tdcv) | + FIELD_PREP(MCP251XFD_REG_TDC_TDCO_MASK, priv->can.tdc.tdco); return regmap_write(priv->map_reg, MCP251XFD_REG_TDC, val); } @@ -2083,10 +2105,12 @@ static int mcp251xfd_probe(struct spi_device *spi) priv->can.do_get_berr_counter = mcp251xfd_get_berr_counter; priv->can.bittiming_const = &mcp251xfd_bittiming_const; priv->can.data_bittiming_const = &mcp251xfd_data_bittiming_const; + priv->can.tdc_const = &mcp251xfd_tdc_const; priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK | CAN_CTRLMODE_LISTENONLY | CAN_CTRLMODE_BERR_REPORTING | CAN_CTRLMODE_FD | CAN_CTRLMODE_FD_NON_ISO | - CAN_CTRLMODE_CC_LEN8_DLC; + CAN_CTRLMODE_CC_LEN8_DLC | CAN_CTRLMODE_TDC_AUTO | + CAN_CTRLMODE_TDC_MANUAL; set_bit(MCP251XFD_FLAGS_DOWN, priv->flags); priv->ndev = ndev; priv->spi = spi; @@ -2179,8 +2203,8 @@ static void mcp251xfd_remove(struct spi_device *spi) struct mcp251xfd_priv *priv = spi_get_drvdata(spi); struct net_device *ndev = priv->ndev; - can_rx_offload_del(&priv->offload); mcp251xfd_unregister(priv); + can_rx_offload_del(&priv->offload); spi->max_speed_hz = priv->spi_max_speed_hz_orig; free_candev(ndev); } diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index ea7d2c01e672..1a23fcc0445c 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -373,15 +373,17 @@ static void b53_enable_vlan(struct b53_device *dev, int port, bool enable, b53_read8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL5, &vc5); } + vc1 &= ~VC1_RX_MCST_FWD_EN; + if (enable) { vc0 |= VC0_VLAN_EN | VC0_VID_CHK_EN | VC0_VID_HASH_VID; - vc1 |= VC1_RX_MCST_UNTAG_EN | VC1_RX_MCST_FWD_EN; + vc1 |= VC1_RX_MCST_UNTAG_EN; vc4 &= ~VC4_ING_VID_CHECK_MASK; if (enable_filtering) { vc4 |= VC4_ING_VID_VIO_DROP << VC4_ING_VID_CHECK_S; vc5 |= VC5_DROP_VTABLE_MISS; } else { - vc4 |= VC4_ING_VID_VIO_FWD << VC4_ING_VID_CHECK_S; + vc4 |= VC4_NO_ING_VID_CHK << VC4_ING_VID_CHECK_S; vc5 &= ~VC5_DROP_VTABLE_MISS; } @@ -393,7 +395,7 @@ static void b53_enable_vlan(struct b53_device *dev, int port, bool enable, } else { vc0 &= ~(VC0_VLAN_EN | VC0_VID_CHK_EN | VC0_VID_HASH_VID); - vc1 &= ~(VC1_RX_MCST_UNTAG_EN | VC1_RX_MCST_FWD_EN); + vc1 &= ~VC1_RX_MCST_UNTAG_EN; vc4 &= ~VC4_ING_VID_CHECK_MASK; vc5 &= ~VC5_DROP_VTABLE_MISS; @@ -1475,12 +1477,21 @@ int b53_vlan_add(struct dsa_switch *ds, int port, bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED; bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID; struct b53_vlan *vl; + u16 old_pvid, new_pvid; int err; err = b53_vlan_prepare(ds, port, vlan); if (err) return err; + b53_read16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port), &old_pvid); + if (pvid) + new_pvid = vlan->vid; + else if (!pvid && vlan->vid == old_pvid) + new_pvid = b53_default_pvid(dev); + else + new_pvid = old_pvid; + vl = &dev->vlans[vlan->vid]; b53_get_vlan_entry(dev, vlan->vid, vl); @@ -1497,10 +1508,10 @@ int b53_vlan_add(struct dsa_switch *ds, int port, b53_set_vlan_entry(dev, vlan->vid, vl); b53_fast_age_vlan(dev, vlan->vid); - if (pvid && !dsa_is_cpu_port(ds, port)) { + if (!dsa_is_cpu_port(ds, port) && new_pvid != old_pvid) { b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port), - vlan->vid); - b53_fast_age_vlan(dev, vlan->vid); + new_pvid); + b53_fast_age_vlan(dev, old_pvid); } return 0; @@ -1912,7 +1923,7 @@ EXPORT_SYMBOL(b53_br_join); void b53_br_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge) { struct b53_device *dev = ds->priv; - struct b53_vlan *vl = &dev->vlans[0]; + struct b53_vlan *vl; s8 cpu_port = dsa_to_port(ds, port)->cpu_dp->index; unsigned int i; u16 pvlan, reg, pvid; @@ -1938,6 +1949,7 @@ void b53_br_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge) dev->ports[port].vlan_ctl_mask = pvlan; pvid = b53_default_pvid(dev); + vl = &dev->vlans[pvid]; /* Make this port join all VLANs without VLAN entries */ if (is58xx(dev)) { @@ -1946,12 +1958,12 @@ void b53_br_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge) if (!(reg & BIT(cpu_port))) reg |= BIT(cpu_port); b53_write16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, reg); - } else { - b53_get_vlan_entry(dev, pvid, vl); - vl->members |= BIT(port) | BIT(cpu_port); - vl->untag |= BIT(port) | BIT(cpu_port); - b53_set_vlan_entry(dev, pvid, vl); } + + b53_get_vlan_entry(dev, pvid, vl); + vl->members |= BIT(port) | BIT(cpu_port); + vl->untag |= BIT(port) | BIT(cpu_port); + b53_set_vlan_entry(dev, pvid, vl); } EXPORT_SYMBOL(b53_br_leave); diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index f1f1368e8146..d51d982c4bc0 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -2083,6 +2083,7 @@ static void sja1105_bridge_stp_state_set(struct dsa_switch *ds, int port, switch (state) { case BR_STATE_DISABLED: case BR_STATE_BLOCKING: + case BR_STATE_LISTENING: /* From UM10944 description of DRPDTAG (why put this there?): * "Management traffic flows to the port regardless of the state * of the INGRESS flag". So BPDUs are still be allowed to pass. @@ -2092,11 +2093,6 @@ static void sja1105_bridge_stp_state_set(struct dsa_switch *ds, int port, mac[port].egress = false; mac[port].dyn_learn = false; break; - case BR_STATE_LISTENING: - mac[port].ingress = true; - mac[port].egress = false; - mac[port].dyn_learn = false; - break; case BR_STATE_LEARNING: mac[port].ingress = true; mac[port].egress = false; diff --git a/drivers/net/ethernet/apm/xgene-v2/main.c b/drivers/net/ethernet/apm/xgene-v2/main.c index 379d19d18dbe..5808e3c73a8f 100644 --- a/drivers/net/ethernet/apm/xgene-v2/main.c +++ b/drivers/net/ethernet/apm/xgene-v2/main.c @@ -9,8 +9,6 @@ #include "main.h" -static const struct acpi_device_id xge_acpi_match[]; - static int xge_get_resources(struct xge_pdata *pdata) { struct platform_device *pdev; @@ -733,7 +731,7 @@ MODULE_DEVICE_TABLE(acpi, xge_acpi_match); static struct platform_driver xge_driver = { .driver = { .name = "xgene-enet-v2", - .acpi_match_table = ACPI_PTR(xge_acpi_match), + .acpi_match_table = xge_acpi_match, }, .probe = xge_probe, .remove = xge_remove, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 393a983f6d69..6b1245a3ab4b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -4041,7 +4041,7 @@ int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode) struct net_device *dev = bp->dev; if (page_mode) { - bp->flags &= ~BNXT_FLAG_AGG_RINGS; + bp->flags &= ~(BNXT_FLAG_AGG_RINGS | BNXT_FLAG_NO_AGG_RINGS); bp->flags |= BNXT_FLAG_RX_PAGE_MODE; if (bp->xdp_prog->aux->xdp_has_frags) @@ -12799,6 +12799,14 @@ static int bnxt_change_mtu(struct net_device *dev, int new_mtu) bnxt_close_nic(bp, true, false); dev->mtu = new_mtu; + + /* MTU change may change the AGG ring settings if an XDP multi-buffer + * program is attached. We need to set the AGG rings settings and + * rx_skb_func accordingly. + */ + if (READ_ONCE(bp->xdp_prog)) + bnxt_set_rx_skb_mode(bp, true); + bnxt_set_ring_params(bp); if (netif_running(dev)) diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index fc3342944dbc..d2f4709dee0d 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -962,22 +962,15 @@ static void macb_update_stats(struct macb *bp) static int macb_halt_tx(struct macb *bp) { - unsigned long halt_time, timeout; - u32 status; + u32 status; macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(THALT)); - timeout = jiffies + usecs_to_jiffies(MACB_HALT_TIMEOUT); - do { - halt_time = jiffies; - status = macb_readl(bp, TSR); - if (!(status & MACB_BIT(TGO))) - return 0; - - udelay(250); - } while (time_before(halt_time, timeout)); - - return -ETIMEDOUT; + /* Poll TSR until TGO is cleared or timeout. */ + return read_poll_timeout_atomic(macb_readl, status, + !(status & MACB_BIT(TGO)), + 250, MACB_HALT_TIMEOUT, false, + bp, TSR); } static void macb_tx_unmap(struct macb *bp, struct macb_tx_skb *tx_skb, int budget) diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 230b317d93da..bf49c07c8b51 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -1536,6 +1536,16 @@ static void enetc_xdp_drop(struct enetc_bdr *rx_ring, int rx_ring_first, } } +static void enetc_bulk_flip_buff(struct enetc_bdr *rx_ring, int rx_ring_first, + int rx_ring_last) +{ + while (rx_ring_first != rx_ring_last) { + enetc_flip_rx_buff(rx_ring, + &rx_ring->rx_swbd[rx_ring_first]); + enetc_bdr_idx_inc(rx_ring, &rx_ring_first); + } +} + static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring, struct napi_struct *napi, int work_limit, struct bpf_prog *prog) @@ -1659,11 +1669,7 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring, enetc_xdp_drop(rx_ring, orig_i, i); rx_ring->stats.xdp_redirect_failures++; } else { - while (orig_i != i) { - enetc_flip_rx_buff(rx_ring, - &rx_ring->rx_swbd[orig_i]); - enetc_bdr_idx_inc(rx_ring, &orig_i); - } + enetc_bulk_flip_buff(rx_ring, orig_i, i); xdp_redirect_frm_cnt++; rx_ring->stats.xdp_redirect++; } diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index a163e7717a53..1f62d1183156 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -3373,8 +3373,7 @@ static u32 ice_get_combined_cnt(struct ice_vsi *vsi) ice_for_each_q_vector(vsi, q_idx) { struct ice_q_vector *q_vector = vsi->q_vectors[q_idx]; - if (q_vector->rx.rx_ring && q_vector->tx.tx_ring) - combined++; + combined += min(q_vector->num_ring_tx, q_vector->num_ring_rx); } return combined; diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index 42d8e5e771b7..fa9d928081d6 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -3551,7 +3551,6 @@ static int ice_vc_repr_add_mac(struct ice_vf *vf, u8 *msg) } ice_vfhw_mac_add(vf, &al->list[i]); - vf->num_mac++; break; } diff --git a/drivers/net/ethernet/marvell/octeontx2/Kconfig b/drivers/net/ethernet/marvell/octeontx2/Kconfig index 993ac180a5db..a32d85d6f599 100644 --- a/drivers/net/ethernet/marvell/octeontx2/Kconfig +++ b/drivers/net/ethernet/marvell/octeontx2/Kconfig @@ -32,6 +32,7 @@ config OCTEONTX2_PF tristate "Marvell OcteonTX2 NIC Physical Function driver" select OCTEONTX2_MBOX select NET_DEVLINK + select PAGE_POOL depends on (64BIT && COMPILE_TEST) || ARM64 select DIMLIB depends on PCI diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c index f9faa5b23bb9..5cd45846237e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c @@ -13,19 +13,26 @@ /* RVU LMTST */ #define LMT_TBL_OP_READ 0 #define LMT_TBL_OP_WRITE 1 -#define LMT_MAP_TABLE_SIZE (128 * 1024) #define LMT_MAPTBL_ENTRY_SIZE 16 +#define LMT_MAX_VFS 256 + +#define LMT_MAP_ENTRY_ENA BIT_ULL(20) +#define LMT_MAP_ENTRY_LINES GENMASK_ULL(18, 16) /* Function to perform operations (read/write) on lmtst map table */ static int lmtst_map_table_ops(struct rvu *rvu, u32 index, u64 *val, int lmt_tbl_op) { void __iomem *lmt_map_base; - u64 tbl_base; + u64 tbl_base, cfg; + int pfs, vfs; tbl_base = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_MAP_BASE); + cfg = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_CFG); + vfs = 1 << (cfg & 0xF); + pfs = 1 << ((cfg >> 4) & 0x7); - lmt_map_base = ioremap_wc(tbl_base, LMT_MAP_TABLE_SIZE); + lmt_map_base = ioremap_wc(tbl_base, pfs * vfs * LMT_MAPTBL_ENTRY_SIZE); if (!lmt_map_base) { dev_err(rvu->dev, "Failed to setup lmt map table mapping!!\n"); return -ENOMEM; @@ -35,6 +42,13 @@ static int lmtst_map_table_ops(struct rvu *rvu, u32 index, u64 *val, *val = readq(lmt_map_base + index); } else { writeq((*val), (lmt_map_base + index)); + + cfg = FIELD_PREP(LMT_MAP_ENTRY_ENA, 0x1); + /* 2048 LMTLINES */ + cfg |= FIELD_PREP(LMT_MAP_ENTRY_LINES, 0x6); + + writeq(cfg, (lmt_map_base + (index + 8))); + /* Flushing the AP interceptor cache to make APR_LMT_MAP_ENTRY_S * changes effective. Write 1 for flush and read is being used as a * barrier and sets up a data dependency. Write to 0 after a write @@ -52,7 +66,7 @@ static int lmtst_map_table_ops(struct rvu *rvu, u32 index, u64 *val, #define LMT_MAP_TBL_W1_OFF 8 static u32 rvu_get_lmtst_tbl_index(struct rvu *rvu, u16 pcifunc) { - return ((rvu_get_pf(pcifunc) * rvu->hw->total_vfs) + + return ((rvu_get_pf(pcifunc) * LMT_MAX_VFS) + (pcifunc & RVU_PFVF_FUNC_MASK)) * LMT_MAPTBL_ENTRY_SIZE; } @@ -69,7 +83,7 @@ static int rvu_get_lmtaddr(struct rvu *rvu, u16 pcifunc, mutex_lock(&rvu->rsrc_lock); rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_ADDR_REQ, iova); - pf = rvu_get_pf(pcifunc) & 0x1F; + pf = rvu_get_pf(pcifunc) & RVU_PFVF_PF_MASK; val = BIT_ULL(63) | BIT_ULL(14) | BIT_ULL(13) | pf << 8 | ((pcifunc & RVU_PFVF_FUNC_MASK) & 0xFF); rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_TXN_REQ, val); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index a3c1d82032f5..aa2ab987eb75 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -580,6 +580,7 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp, u64 lmt_addr, val, tbl_base; int pf, vf, num_vfs, hw_vfs; void __iomem *lmt_map_base; + int apr_pfs, apr_vfs; int buf_size = 10240; size_t off = 0; int index = 0; @@ -595,8 +596,12 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp, return -ENOMEM; tbl_base = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_MAP_BASE); + val = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_CFG); + apr_vfs = 1 << (val & 0xF); + apr_pfs = 1 << ((val >> 4) & 0x7); - lmt_map_base = ioremap_wc(tbl_base, 128 * 1024); + lmt_map_base = ioremap_wc(tbl_base, apr_pfs * apr_vfs * + LMT_MAPTBL_ENTRY_SIZE); if (!lmt_map_base) { dev_err(rvu->dev, "Failed to setup lmt map table mapping!!\n"); kfree(buf); @@ -618,7 +623,7 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp, off += scnprintf(&buf[off], buf_size - 1 - off, "PF%d \t\t\t", pf); - index = pf * rvu->hw->total_vfs * LMT_MAPTBL_ENTRY_SIZE; + index = pf * apr_vfs * LMT_MAPTBL_ENTRY_SIZE; off += scnprintf(&buf[off], buf_size - 1 - off, " 0x%llx\t\t", (tbl_base + index)); lmt_addr = readq(lmt_map_base + index); @@ -631,7 +636,7 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp, /* Reading num of VFs per PF */ rvu_get_pf_numvfs(rvu, pf, &num_vfs, &hw_vfs); for (vf = 0; vf < num_vfs; vf++) { - index = (pf * rvu->hw->total_vfs * 16) + + index = (pf * apr_vfs * LMT_MAPTBL_ENTRY_SIZE) + ((vf + 1) * LMT_MAPTBL_ENTRY_SIZE); off += scnprintf(&buf[off], buf_size - 1 - off, "PF%d:VF%d \t\t", pf, vf); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c index 8663bdf014d8..7417087b6db5 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c @@ -107,12 +107,13 @@ int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura) } #define NPA_MAX_BURST 16 -void cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq) +int cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq) { struct otx2_nic *pfvf = dev; + int cnt = cq->pool_ptrs; u64 ptrs[NPA_MAX_BURST]; - int num_ptrs = 1; dma_addr_t bufptr; + int num_ptrs = 1; /* Refill pool with new buffers */ while (cq->pool_ptrs) { @@ -131,6 +132,7 @@ void cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq) num_ptrs = 1; } } + return cnt - cq->pool_ptrs; } void cn10k_sqe_flush(void *dev, struct otx2_snd_queue *sq, int size, int qidx) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h index 8ae96815865e..c1861f7de254 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h @@ -24,7 +24,7 @@ static inline int mtu_to_dwrr_weight(struct otx2_nic *pfvf, int mtu) return weight; } -void cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq); +int cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq); void cn10k_sqe_flush(void *dev, struct otx2_snd_queue *sq, int size, int qidx); int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura); int cn10k_lmtst_init(struct otx2_nic *pfvf); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c index a487a98eac88..6da8d8f2a870 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c @@ -428,7 +428,8 @@ static int cn10k_mcs_write_tx_secy(struct otx2_nic *pfvf, if (sw_tx_sc->encrypt) sectag_tci |= (MCS_TCI_E | MCS_TCI_C); - policy = FIELD_PREP(MCS_TX_SECY_PLCY_MTU, secy->netdev->mtu); + policy = FIELD_PREP(MCS_TX_SECY_PLCY_MTU, + pfvf->netdev->mtu + OTX2_ETH_HLEN); /* Write SecTag excluding AN bits(1..0) */ policy |= FIELD_PREP(MCS_TX_SECY_PLCY_ST_TCI, sectag_tci >> 2); policy |= FIELD_PREP(MCS_TX_SECY_PLCY_ST_OFFSET, tag_offset); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index d05f91f97a9a..4fc73ac721b0 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -513,11 +513,32 @@ void otx2_config_irq_coalescing(struct otx2_nic *pfvf, int qidx) (pfvf->hw.cq_ecount_wait - 1)); } +static int otx2_alloc_pool_buf(struct otx2_nic *pfvf, struct otx2_pool *pool, + dma_addr_t *dma) +{ + unsigned int offset = 0; + struct page *page; + size_t sz; + + sz = SKB_DATA_ALIGN(pool->rbsize); + sz = ALIGN(sz, OTX2_ALIGN); + + page = page_pool_alloc_frag(pool->page_pool, &offset, sz, GFP_ATOMIC); + if (unlikely(!page)) + return -ENOMEM; + + *dma = page_pool_get_dma_addr(page) + offset; + return 0; +} + static int __otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool, dma_addr_t *dma) { u8 *buf; + if (pool->page_pool) + return otx2_alloc_pool_buf(pfvf, pool, dma); + buf = napi_alloc_frag_align(pool->rbsize, OTX2_ALIGN); if (unlikely(!buf)) return -ENOMEM; @@ -546,20 +567,8 @@ int otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool, int otx2_alloc_buffer(struct otx2_nic *pfvf, struct otx2_cq_queue *cq, dma_addr_t *dma) { - if (unlikely(__otx2_alloc_rbuf(pfvf, cq->rbpool, dma))) { - struct refill_work *work; - struct delayed_work *dwork; - - work = &pfvf->refill_wrk[cq->cq_idx]; - dwork = &work->pool_refill_work; - /* Schedule a task if no other task is running */ - if (!cq->refill_task_sched) { - cq->refill_task_sched = true; - schedule_delayed_work(dwork, - msecs_to_jiffies(100)); - } + if (unlikely(__otx2_alloc_rbuf(pfvf, cq->rbpool, dma))) return -ENOMEM; - } return 0; } @@ -967,6 +976,7 @@ static int otx2_cq_init(struct otx2_nic *pfvf, u16 qidx) int err, pool_id, non_xdp_queues; struct nix_aq_enq_req *aq; struct otx2_cq_queue *cq; + struct otx2_pool *pool; cq = &qset->cq[qidx]; cq->cq_idx = qidx; @@ -975,8 +985,13 @@ static int otx2_cq_init(struct otx2_nic *pfvf, u16 qidx) cq->cq_type = CQ_RX; cq->cint_idx = qidx; cq->cqe_cnt = qset->rqe_cnt; - if (pfvf->xdp_prog) + if (pfvf->xdp_prog) { + pool = &qset->pool[qidx]; xdp_rxq_info_reg(&cq->xdp_rxq, pfvf->netdev, qidx, 0); + xdp_rxq_info_reg_mem_model(&cq->xdp_rxq, + MEM_TYPE_PAGE_POOL, + pool->page_pool); + } } else if (qidx < non_xdp_queues) { cq->cq_type = CQ_TX; cq->cint_idx = qidx - pfvf->hw.rx_queues; @@ -1054,39 +1069,20 @@ static int otx2_cq_init(struct otx2_nic *pfvf, u16 qidx) static void otx2_pool_refill_task(struct work_struct *work) { struct otx2_cq_queue *cq; - struct otx2_pool *rbpool; struct refill_work *wrk; - int qidx, free_ptrs = 0; struct otx2_nic *pfvf; - dma_addr_t bufptr; + int qidx; wrk = container_of(work, struct refill_work, pool_refill_work.work); pfvf = wrk->pf; qidx = wrk - pfvf->refill_wrk; cq = &pfvf->qset.cq[qidx]; - rbpool = cq->rbpool; - free_ptrs = cq->pool_ptrs; - while (cq->pool_ptrs) { - if (otx2_alloc_rbuf(pfvf, rbpool, &bufptr)) { - /* Schedule a WQ if we fails to free atleast half of the - * pointers else enable napi for this RQ. - */ - if (!((free_ptrs - cq->pool_ptrs) > free_ptrs / 2)) { - struct delayed_work *dwork; - - dwork = &wrk->pool_refill_work; - schedule_delayed_work(dwork, - msecs_to_jiffies(100)); - } else { - cq->refill_task_sched = false; - } - return; - } - pfvf->hw_ops->aura_freeptr(pfvf, qidx, bufptr + OTX2_HEAD_ROOM); - cq->pool_ptrs--; - } cq->refill_task_sched = false; + + local_bh_disable(); + napi_schedule(wrk->napi); + local_bh_enable(); } int otx2_config_nix_queues(struct otx2_nic *pfvf) @@ -1206,10 +1202,31 @@ void otx2_sq_free_sqbs(struct otx2_nic *pfvf) } } +void otx2_free_bufs(struct otx2_nic *pfvf, struct otx2_pool *pool, + u64 iova, int size) +{ + struct page *page; + u64 pa; + + pa = otx2_iova_to_phys(pfvf->iommu_domain, iova); + page = virt_to_head_page(phys_to_virt(pa)); + + if (pool->page_pool) { + page_pool_put_full_page(pool->page_pool, page, true); + } else { + dma_unmap_page_attrs(pfvf->dev, iova, size, + DMA_FROM_DEVICE, + DMA_ATTR_SKIP_CPU_SYNC); + + put_page(page); + } +} + void otx2_free_aura_ptr(struct otx2_nic *pfvf, int type) { int pool_id, pool_start = 0, pool_end = 0, size = 0; - u64 iova, pa; + struct otx2_pool *pool; + u64 iova; if (type == AURA_NIX_SQ) { pool_start = otx2_get_pool_idx(pfvf, type, 0); @@ -1225,15 +1242,13 @@ void otx2_free_aura_ptr(struct otx2_nic *pfvf, int type) /* Free SQB and RQB pointers from the aura pool */ for (pool_id = pool_start; pool_id < pool_end; pool_id++) { iova = otx2_aura_allocptr(pfvf, pool_id); + pool = &pfvf->qset.pool[pool_id]; while (iova) { if (type == AURA_NIX_RQ) iova -= OTX2_HEAD_ROOM; - pa = otx2_iova_to_phys(pfvf->iommu_domain, iova); - dma_unmap_page_attrs(pfvf->dev, iova, size, - DMA_FROM_DEVICE, - DMA_ATTR_SKIP_CPU_SYNC); - put_page(virt_to_page(phys_to_virt(pa))); + otx2_free_bufs(pfvf, pool, iova, size); + iova = otx2_aura_allocptr(pfvf, pool_id); } } @@ -1251,6 +1266,8 @@ void otx2_aura_pool_free(struct otx2_nic *pfvf) pool = &pfvf->qset.pool[pool_id]; qmem_free(pfvf->dev, pool->stack); qmem_free(pfvf->dev, pool->fc_addr); + page_pool_destroy(pool->page_pool); + pool->page_pool = NULL; } devm_kfree(pfvf->dev, pfvf->qset.pool); pfvf->qset.pool = NULL; @@ -1334,8 +1351,9 @@ int otx2_aura_init(struct otx2_nic *pfvf, int aura_id, } int otx2_pool_init(struct otx2_nic *pfvf, u16 pool_id, - int stack_pages, int numptrs, int buf_size) + int stack_pages, int numptrs, int buf_size, int type) { + struct page_pool_params pp_params = { 0 }; struct npa_aq_enq_req *aq; struct otx2_pool *pool; int err; @@ -1379,6 +1397,23 @@ int otx2_pool_init(struct otx2_nic *pfvf, u16 pool_id, aq->ctype = NPA_AQ_CTYPE_POOL; aq->op = NPA_AQ_INSTOP_INIT; + if (type != AURA_NIX_RQ) { + pool->page_pool = NULL; + return 0; + } + + pp_params.order = get_order(buf_size); + pp_params.flags = PP_FLAG_PAGE_FRAG | PP_FLAG_DMA_MAP; + pp_params.pool_size = min(OTX2_PAGE_POOL_SZ, numptrs); + pp_params.nid = NUMA_NO_NODE; + pp_params.dev = pfvf->dev; + pp_params.dma_dir = DMA_FROM_DEVICE; + pool->page_pool = page_pool_create(&pp_params); + if (IS_ERR(pool->page_pool)) { + netdev_err(pfvf->netdev, "Creation of page pool failed\n"); + return PTR_ERR(pool->page_pool); + } + return 0; } @@ -1413,7 +1448,7 @@ int otx2_sq_aura_pool_init(struct otx2_nic *pfvf) /* Initialize pool context */ err = otx2_pool_init(pfvf, pool_id, stack_pages, - num_sqbs, hw->sqb_size); + num_sqbs, hw->sqb_size, AURA_NIX_SQ); if (err) goto fail; } @@ -1476,7 +1511,7 @@ int otx2_rq_aura_pool_init(struct otx2_nic *pfvf) } for (pool_id = 0; pool_id < hw->rqpool_cnt; pool_id++) { err = otx2_pool_init(pfvf, pool_id, stack_pages, - num_ptrs, pfvf->rbsize); + num_ptrs, pfvf->rbsize, AURA_NIX_RQ); if (err) goto fail; } @@ -1660,7 +1695,6 @@ int otx2_nix_config_bp(struct otx2_nic *pfvf, bool enable) req->bpid_per_chan = 0; #endif - return otx2_sync_mbox_msg(&pfvf->mbox); } EXPORT_SYMBOL(otx2_nix_config_bp); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index c15d1864a637..1d3c4180d341 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -280,6 +280,7 @@ struct flr_work { struct refill_work { struct delayed_work pool_refill_work; struct otx2_nic *pf; + struct napi_struct *napi; }; /* PTPv2 originTimestamp structure */ @@ -347,7 +348,7 @@ struct dev_hw_ops { int (*sq_aq_init)(void *dev, u16 qidx, u16 sqb_aura); void (*sqe_flush)(void *dev, struct otx2_snd_queue *sq, int size, int qidx); - void (*refill_pool_ptrs)(void *dev, struct otx2_cq_queue *cq); + int (*refill_pool_ptrs)(void *dev, struct otx2_cq_queue *cq); void (*aura_freeptr)(void *dev, int aura, u64 buf); }; @@ -934,7 +935,7 @@ int otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool, int otx2_rxtx_enable(struct otx2_nic *pfvf, bool enable); void otx2_ctx_disable(struct mbox *mbox, int type, bool npa); int otx2_nix_config_bp(struct otx2_nic *pfvf, bool enable); -void otx2_cleanup_rx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq); +void otx2_cleanup_rx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq, int qidx); void otx2_cleanup_tx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq); int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura); int otx2_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura); @@ -942,7 +943,7 @@ int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura); int otx2_alloc_buffer(struct otx2_nic *pfvf, struct otx2_cq_queue *cq, dma_addr_t *dma); int otx2_pool_init(struct otx2_nic *pfvf, u16 pool_id, - int stack_pages, int numptrs, int buf_size); + int stack_pages, int numptrs, int buf_size, int type); int otx2_aura_init(struct otx2_nic *pfvf, int aura_id, int pool_id, int numptrs); @@ -1012,6 +1013,8 @@ u16 otx2_get_max_mtu(struct otx2_nic *pfvf); int otx2_handle_ntuple_tc_features(struct net_device *netdev, netdev_features_t features); int otx2_smq_flush(struct otx2_nic *pfvf, int smq); +void otx2_free_bufs(struct otx2_nic *pfvf, struct otx2_pool *pool, + u64 iova, int size); /* tc support */ int otx2_init_tc(struct otx2_nic *nic); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 6b7fb324e756..c29cb56caf08 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1591,7 +1591,9 @@ static void otx2_free_hw_resources(struct otx2_nic *pf) struct nix_lf_free_req *free_req; struct mbox *mbox = &pf->mbox; struct otx2_cq_queue *cq; + struct otx2_pool *pool; struct msg_req *req; + int pool_id; int qidx; /* Ensure all SQE are processed */ @@ -1618,7 +1620,7 @@ static void otx2_free_hw_resources(struct otx2_nic *pf) for (qidx = 0; qidx < qset->cq_cnt; qidx++) { cq = &qset->cq[qidx]; if (cq->cq_type == CQ_RX) - otx2_cleanup_rx_cqes(pf, cq); + otx2_cleanup_rx_cqes(pf, cq, qidx); else otx2_cleanup_tx_cqes(pf, cq); } @@ -1629,6 +1631,13 @@ static void otx2_free_hw_resources(struct otx2_nic *pf) /* Free RQ buffer pointers*/ otx2_free_aura_ptr(pf, AURA_NIX_RQ); + for (qidx = 0; qidx < pf->hw.rx_queues; qidx++) { + pool_id = otx2_get_pool_idx(pf, AURA_NIX_RQ, qidx); + pool = &pf->qset.pool[pool_id]; + page_pool_destroy(pool->page_pool); + pool->page_pool = NULL; + } + otx2_free_cq_res(pf); /* Free all ingress bandwidth profiles allocated */ @@ -1996,6 +2005,10 @@ int otx2_stop(struct net_device *netdev) netif_tx_disable(netdev); + for (wrk = 0; wrk < pf->qset.cq_cnt; wrk++) + cancel_delayed_work_sync(&pf->refill_wrk[wrk].pool_refill_work); + devm_kfree(pf->dev, pf->refill_wrk); + otx2_free_hw_resources(pf); otx2_free_cints(pf, pf->hw.cint_cnt); otx2_disable_napi(pf); @@ -2003,9 +2016,6 @@ int otx2_stop(struct net_device *netdev) for (qidx = 0; qidx < netdev->num_tx_queues; qidx++) netdev_tx_reset_queue(netdev_get_tx_queue(netdev, qidx)); - for (wrk = 0; wrk < pf->qset.cq_cnt; wrk++) - cancel_delayed_work_sync(&pf->refill_wrk[wrk].pool_refill_work); - devm_kfree(pf->dev, pf->refill_wrk); kfree(qset->sq); kfree(qset->cq); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c index e579183e5239..31caf7a7a3ad 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c @@ -218,9 +218,6 @@ static bool otx2_skb_add_frag(struct otx2_nic *pfvf, struct sk_buff *skb, skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, va - page_address(page) + off, len - off, pfvf->rbsize); - - otx2_dma_unmap_page(pfvf, iova - OTX2_HEAD_ROOM, - pfvf->rbsize, DMA_FROM_DEVICE); return true; } @@ -383,6 +380,8 @@ static void otx2_rcv_pkt_handler(struct otx2_nic *pfvf, if (pfvf->netdev->features & NETIF_F_RXCSUM) skb->ip_summed = CHECKSUM_UNNECESSARY; + skb_mark_for_recycle(skb); + napi_gro_frags(napi); } @@ -429,9 +428,10 @@ process_cqe: return processed_cqe; } -void otx2_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq) +int otx2_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq) { struct otx2_nic *pfvf = dev; + int cnt = cq->pool_ptrs; dma_addr_t bufptr; while (cq->pool_ptrs) { @@ -440,6 +440,8 @@ void otx2_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq) otx2_aura_freeptr(pfvf, cq->cq_idx, bufptr + OTX2_HEAD_ROOM); cq->pool_ptrs--; } + + return cnt - cq->pool_ptrs; } static int otx2_tx_napi_handler(struct otx2_nic *pfvf, @@ -533,6 +535,7 @@ int otx2_napi_handler(struct napi_struct *napi, int budget) struct otx2_cq_queue *cq; struct otx2_qset *qset; struct otx2_nic *pfvf; + int filled_cnt = -1; cq_poll = container_of(napi, struct otx2_cq_poll, napi); pfvf = (struct otx2_nic *)cq_poll->dev; @@ -553,7 +556,7 @@ int otx2_napi_handler(struct napi_struct *napi, int budget) } if (rx_cq && rx_cq->pool_ptrs) - pfvf->hw_ops->refill_pool_ptrs(pfvf, rx_cq); + filled_cnt = pfvf->hw_ops->refill_pool_ptrs(pfvf, rx_cq); /* Clear the IRQ */ otx2_write64(pfvf, NIX_LF_CINTX_INT(cq_poll->cint_idx), BIT_ULL(0)); @@ -566,9 +569,25 @@ int otx2_napi_handler(struct napi_struct *napi, int budget) if (pfvf->flags & OTX2_FLAG_ADPTV_INT_COAL_ENABLED) otx2_adjust_adaptive_coalese(pfvf, cq_poll); - /* Re-enable interrupts */ - otx2_write64(pfvf, NIX_LF_CINTX_ENA_W1S(cq_poll->cint_idx), - BIT_ULL(0)); + if (unlikely(!filled_cnt)) { + struct refill_work *work; + struct delayed_work *dwork; + + work = &pfvf->refill_wrk[cq->cq_idx]; + dwork = &work->pool_refill_work; + /* Schedule a task if no other task is running */ + if (!cq->refill_task_sched) { + work->napi = napi; + cq->refill_task_sched = true; + schedule_delayed_work(dwork, + msecs_to_jiffies(100)); + } + } else { + /* Re-enable interrupts */ + otx2_write64(pfvf, + NIX_LF_CINTX_ENA_W1S(cq_poll->cint_idx), + BIT_ULL(0)); + } } return workdone; } @@ -1191,11 +1210,13 @@ bool otx2_sq_append_skb(struct net_device *netdev, struct otx2_snd_queue *sq, } EXPORT_SYMBOL(otx2_sq_append_skb); -void otx2_cleanup_rx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq) +void otx2_cleanup_rx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq, int qidx) { struct nix_cqe_rx_s *cqe; + struct otx2_pool *pool; int processed_cqe = 0; - u64 iova, pa; + u16 pool_id; + u64 iova; if (pfvf->xdp_prog) xdp_rxq_info_unreg(&cq->xdp_rxq); @@ -1203,6 +1224,9 @@ void otx2_cleanup_rx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq) if (otx2_nix_cq_op_status(pfvf, cq) || !cq->pend_cqe) return; + pool_id = otx2_get_pool_idx(pfvf, AURA_NIX_RQ, qidx); + pool = &pfvf->qset.pool[pool_id]; + while (cq->pend_cqe) { cqe = (struct nix_cqe_rx_s *)otx2_get_next_cqe(cq); processed_cqe++; @@ -1215,9 +1239,8 @@ void otx2_cleanup_rx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq) continue; } iova = cqe->sg.seg_addr - OTX2_HEAD_ROOM; - pa = otx2_iova_to_phys(pfvf->iommu_domain, iova); - otx2_dma_unmap_page(pfvf, iova, pfvf->rbsize, DMA_FROM_DEVICE); - put_page(virt_to_page(phys_to_virt(pa))); + + otx2_free_bufs(pfvf, pool, iova, pfvf->rbsize); } /* Free CQEs to HW */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h index 7ab6db9a986f..a82ffca8ce1b 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h @@ -23,6 +23,8 @@ #define OTX2_ETH_HLEN (VLAN_ETH_HLEN + VLAN_HLEN) #define OTX2_MIN_MTU 60 +#define OTX2_PAGE_POOL_SZ 2048 + #define OTX2_MAX_GSO_SEGS 255 #define OTX2_MAX_FRAGS_IN_SQE 9 @@ -118,6 +120,7 @@ struct otx2_cq_poll { struct otx2_pool { struct qmem *stack; struct qmem *fc_addr; + struct page_pool *page_pool; u16 rbsize; }; @@ -167,6 +170,6 @@ void cn10k_sqe_flush(void *dev, struct otx2_snd_queue *sq, int size, int qidx); void otx2_sqe_flush(void *dev, struct otx2_snd_queue *sq, int size, int qidx); -void otx2_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq); -void cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq); +int otx2_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq); +int cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq); #endif /* OTX2_TXRX_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/qos_sq.c b/drivers/net/ethernet/marvell/octeontx2/nic/qos_sq.c index e142d43f5a62..95a2c8e616bd 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/qos_sq.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/qos_sq.c @@ -63,7 +63,7 @@ static int otx2_qos_sq_aura_pool_init(struct otx2_nic *pfvf, int qidx) /* Initialize pool context */ err = otx2_pool_init(pfvf, pool_id, stack_pages, - num_sqbs, hw->sqb_size); + num_sqbs, hw->sqb_size, AURA_NIX_SQ); if (err) goto aura_free; diff --git a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c index 6a72687d5b83..8cb8d47227f5 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c @@ -34,8 +34,10 @@ struct mtk_flow_data { u16 vlan_in; struct { - u16 id; - __be16 proto; + struct { + u16 id; + __be16 proto; + } vlans[2]; u8 num; } vlan; struct { @@ -321,18 +323,19 @@ mtk_flow_offload_replace(struct mtk_eth *eth, struct flow_cls_offload *f) case FLOW_ACTION_CSUM: break; case FLOW_ACTION_VLAN_PUSH: - if (data.vlan.num == 1 || + if (data.vlan.num + data.pppoe.num == 2 || act->vlan.proto != htons(ETH_P_8021Q)) return -EOPNOTSUPP; - data.vlan.id = act->vlan.vid; - data.vlan.proto = act->vlan.proto; + data.vlan.vlans[data.vlan.num].id = act->vlan.vid; + data.vlan.vlans[data.vlan.num].proto = act->vlan.proto; data.vlan.num++; break; case FLOW_ACTION_VLAN_POP: break; case FLOW_ACTION_PPPOE_PUSH: - if (data.pppoe.num == 1) + if (data.pppoe.num == 1 || + data.vlan.num == 2) return -EOPNOTSUPP; data.pppoe.sid = act->pppoe.sid; @@ -422,12 +425,9 @@ mtk_flow_offload_replace(struct mtk_eth *eth, struct flow_cls_offload *f) if (offload_type == MTK_PPE_PKT_TYPE_BRIDGE) foe.bridge.vlan = data.vlan_in; - if (data.vlan.num == 1) { - if (data.vlan.proto != htons(ETH_P_8021Q)) - return -EOPNOTSUPP; + for (i = 0; i < data.vlan.num; i++) + mtk_foe_entry_set_vlan(eth, &foe, data.vlan.vlans[i].id); - mtk_foe_entry_set_vlan(eth, &foe, data.vlan.id); - } if (data.pppoe.num == 1) mtk_foe_entry_set_pppoe(eth, &foe, data.pppoe.sid); diff --git a/drivers/net/ethernet/mellanox/mlx4/alloc.c b/drivers/net/ethernet/mellanox/mlx4/alloc.c index b330020dc0d6..f2bded847e61 100644 --- a/drivers/net/ethernet/mellanox/mlx4/alloc.c +++ b/drivers/net/ethernet/mellanox/mlx4/alloc.c @@ -682,9 +682,9 @@ static struct mlx4_db_pgdir *mlx4_alloc_db_pgdir(struct device *dma_device) } static int mlx4_alloc_db_from_pgdir(struct mlx4_db_pgdir *pgdir, - struct mlx4_db *db, int order) + struct mlx4_db *db, unsigned int order) { - int o; + unsigned int o; int i; for (o = order; o <= 1; ++o) { @@ -712,7 +712,7 @@ found: return 0; } -int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order) +int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, unsigned int order) { struct mlx4_priv *priv = mlx4_priv(dev); struct mlx4_db_pgdir *pgdir; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 7fccf1a79f09..95eae224bbb4 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -446,6 +446,8 @@ int mlx4_en_process_tx_cq(struct net_device *dev, if (unlikely(!priv->port_up)) return 0; + if (unlikely(!napi_budget) && cq->type == TX_XDP) + return 0; netdev_txq_bql_complete_prefetchw(ring->tx_queue); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index f520949b2024..887d44635400 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -4023,6 +4023,10 @@ static netdev_features_t mlx5e_fix_uplink_rep_features(struct net_device *netdev if (netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER) netdev_warn(netdev, "Disabling HW_VLAN CTAG FILTERING, not supported in switchdev mode\n"); + features &= ~NETIF_F_HW_MACSEC; + if (netdev->features & NETIF_F_HW_MACSEC) + netdev_warn(netdev, "Disabling HW MACsec offload, not supported in switchdev mode\n"); + return features; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 5aeca9534f15..b4980245b50b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -61,6 +61,7 @@ #define MLX5E_REP_PARAMS_DEF_LOG_SQ_SIZE \ max(0x7, MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE) #define MLX5E_REP_PARAMS_DEF_NUM_CHANNELS 1 +#define MLX5E_REP_PARAMS_DEF_LOG_RQ_SIZE 0x8 static const char mlx5e_rep_driver_name[] = "mlx5e_rep"; @@ -705,6 +706,8 @@ static void mlx5e_build_rep_params(struct net_device *netdev) /* RQ */ mlx5e_build_rq_params(mdev, params); + if (!mlx5e_is_uplink_rep(priv) && mlx5_core_is_ecpf(mdev)) + params->log_rq_mtu_frames = MLX5E_REP_PARAMS_DEF_LOG_RQ_SIZE; /* CQ moderation params */ params->rx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation); @@ -726,6 +729,8 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev, netdev->ethtool_ops = &mlx5e_rep_ethtool_ops; netdev->watchdog_timeo = 15 * HZ; + if (mlx5_core_is_ecpf(mdev)) + netdev->tx_queue_len = 1 << MLX5E_REP_PARAMS_DEF_LOG_SQ_SIZE; #if IS_ENABLED(CONFIG_MLX5_CLS_ACT) netdev->hw_features |= NETIF_F_HW_TC; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c index 08a75654f5f1..c170503b3aac 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c @@ -165,6 +165,9 @@ mlx5e_test_loopback_validate(struct sk_buff *skb, struct udphdr *udph; struct iphdr *iph; + if (skb_linearize(skb)) + goto out; + /* We are only going to peek, no need to clone the SKB */ if (MLX5E_TEST_PKT_SIZE - ETH_HLEN > skb_headlen(skb)) goto out; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c index 9459e56ee90a..6aa96d33c210 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/events.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c @@ -163,11 +163,16 @@ static int temp_warn(struct notifier_block *nb, unsigned long type, void *data) u64 value_msb; value_lsb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_lsb); + /* bit 1-63 are not supported for NICs, + * hence read only bit 0 (asic) from lsb. + */ + value_lsb &= 0x1; value_msb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_msb); - mlx5_core_warn(events->dev, - "High temperature on sensors with bit set %llx %llx", - value_msb, value_lsb); + if (net_ratelimit()) + mlx5_core_warn(events->dev, + "High temperature on sensors with bit set %llx %llx", + value_msb, value_lsb); return NOTIFY_OK; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 65483dab9057..b4faac12789d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -850,6 +850,7 @@ static void poll_health(struct timer_list *t) health->prev = count; if (health->miss_counter == MAX_MISSES) { mlx5_core_err(dev, "device's health compromised - reached miss count\n"); + health->synd = ioread8(&h->synd); print_health_info(dev); queue_work(health->wq, &health->report_work); } diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index 2e69ba0143b1..fd3555419179 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -3253,6 +3253,7 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter, struct pci_dev *pdev) { struct lan743x_tx *tx; + u32 sgmii_ctl; int index; int ret; @@ -3265,6 +3266,15 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter, spin_lock_init(&adapter->eth_syslock_spinlock); mutex_init(&adapter->sgmii_rw_lock); pci11x1x_set_rfe_rd_fifo_threshold(adapter); + sgmii_ctl = lan743x_csr_read(adapter, SGMII_CTL); + if (adapter->is_sgmii_en) { + sgmii_ctl |= SGMII_CTL_SGMII_ENABLE_; + sgmii_ctl &= ~SGMII_CTL_SGMII_POWER_DN_; + } else { + sgmii_ctl &= ~SGMII_CTL_SGMII_ENABLE_; + sgmii_ctl |= SGMII_CTL_SGMII_POWER_DN_; + } + lan743x_csr_write(adapter, SGMII_CTL, sgmii_ctl); } else { adapter->max_tx_channels = LAN743X_MAX_TX_CHANNELS; adapter->used_tx_channels = LAN743X_USED_TX_CHANNELS; @@ -3313,7 +3323,6 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter, static int lan743x_mdiobus_init(struct lan743x_adapter *adapter) { - u32 sgmii_ctl; int ret; adapter->mdiobus = devm_mdiobus_alloc(&adapter->pdev->dev); @@ -3325,10 +3334,6 @@ static int lan743x_mdiobus_init(struct lan743x_adapter *adapter) adapter->mdiobus->priv = (void *)adapter; if (adapter->is_pci11x1x) { if (adapter->is_sgmii_en) { - sgmii_ctl = lan743x_csr_read(adapter, SGMII_CTL); - sgmii_ctl |= SGMII_CTL_SGMII_ENABLE_; - sgmii_ctl &= ~SGMII_CTL_SGMII_POWER_DN_; - lan743x_csr_write(adapter, SGMII_CTL, sgmii_ctl); netif_dbg(adapter, drv, adapter->netdev, "SGMII operation\n"); adapter->mdiobus->probe_capabilities = MDIOBUS_C22_C45; @@ -3338,10 +3343,6 @@ static int lan743x_mdiobus_init(struct lan743x_adapter *adapter) netif_dbg(adapter, drv, adapter->netdev, "lan743x-mdiobus-c45\n"); } else { - sgmii_ctl = lan743x_csr_read(adapter, SGMII_CTL); - sgmii_ctl &= ~SGMII_CTL_SGMII_ENABLE_; - sgmii_ctl |= SGMII_CTL_SGMII_POWER_DN_; - lan743x_csr_write(adapter, SGMII_CTL, sgmii_ctl); netif_dbg(adapter, drv, adapter->netdev, "RGMII operation\n"); // Only C22 support when RGMII I/F diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index d674ebda2053..9e55679796d9 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -995,7 +995,7 @@ static u32 mana_gd_write_client_oob(const struct gdma_wqe_request *wqe_req, header->inline_oob_size_div4 = client_oob_size / sizeof(u32); if (oob_in_sgl) { - WARN_ON_ONCE(!pad_data || wqe_req->num_sge < 2); + WARN_ON_ONCE(wqe_req->num_sge < 2); header->client_oob_in_sgl = 1; diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index dc43e74147fb..4bc950d36607 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -204,7 +204,7 @@ static struct pci_driver qede_pci_driver = { }; static struct qed_eth_cb_ops qede_ll_ops = { - { + .common = { #ifdef CONFIG_RFS_ACCEL .arfs_filter_op = qede_arfs_filter_op, #endif diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c index 28d24d59efb8..d57b976b9040 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c @@ -1484,8 +1484,11 @@ static int qlcnic_sriov_channel_cfg_cmd(struct qlcnic_adapter *adapter, u8 cmd_o } cmd_op = (cmd.rsp.arg[0] & 0xff); - if (cmd.rsp.arg[0] >> 25 == 2) - return 2; + if (cmd.rsp.arg[0] >> 25 == 2) { + ret = 2; + goto out; + } + if (cmd_op == QLCNIC_BC_CMD_CHANNEL_INIT) set_bit(QLC_BC_VF_STATE, &vf->state); else diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 4b461e93ffe9..6346821d480b 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -5156,6 +5156,7 @@ static int r8169_mdio_register(struct rtl8169_private *tp) new_bus->priv = tp; new_bus->parent = &pdev->dev; new_bus->irq[0] = PHY_MAC_INTERRUPT; + new_bus->phy_mask = GENMASK(31, 1); snprintf(new_bus->id, MII_BUS_ID_SIZE, "r8169-%x-%x", pci_domain_nr(pdev->bus), pci_dev_id(pdev)); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index f834472599f7..0921b78c6244 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -948,7 +948,7 @@ static int sun8i_dwmac_set_syscon(struct device *dev, /* of_mdio_parse_addr returns a valid (0 ~ 31) PHY * address. No need to mask it again. */ - reg |= 1 << H3_EPHY_ADDR_SHIFT; + reg |= ret << H3_EPHY_ADDR_SHIFT; } else { /* For SoCs without internal PHY the PHY selection bit should be * set to 0 (external PHY). diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 32828d4ac64c..a0a9e4e13e77 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -1918,7 +1918,7 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common) port->slave.mac_addr); if (!is_valid_ether_addr(port->slave.mac_addr)) { eth_random_addr(port->slave.mac_addr); - dev_err(dev, "Use random MAC address\n"); + dev_info(dev, "Use random MAC address\n"); } } } diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index 6e70aa1cc7bf..42684cb83606 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -1411,6 +1411,7 @@ static int cpsw_create_ports(struct cpsw_common *cpsw) ndev->netdev_ops = &cpsw_netdev_ops; ndev->ethtool_ops = &cpsw_ethtool_ops; SET_NETDEV_DEV(ndev, dev); + ndev->dev.of_node = slave_data->slave_node; if (!napi_ndev) { /* CPSW Host port CPDMA interface is shared between diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index dd5919ec408b..e7fd72f57e36 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -156,7 +156,6 @@ struct hv_netvsc_packet { u8 cp_partial; /* partial copy into send buffer */ u8 rmsg_size; /* RNDIS header and PPI size */ - u8 rmsg_pgcnt; /* page count of RNDIS header and PPI */ u8 page_buf_cnt; u16 q_idx; @@ -891,6 +890,18 @@ struct nvsp_message { sizeof(struct nvsp_message)) #define NETVSC_MIN_IN_MSG_SIZE sizeof(struct vmpacket_descriptor) +/* Maximum # of contiguous data ranges that can make up a trasmitted packet. + * Typically it's the max SKB fragments plus 2 for the rndis packet and the + * linear portion of the SKB. But if MAX_SKB_FRAGS is large, the value may + * need to be limited to MAX_PAGE_BUFFER_COUNT, which is the max # of entries + * in a GPA direct packet sent to netvsp over VMBus. + */ +#if MAX_SKB_FRAGS + 2 < MAX_PAGE_BUFFER_COUNT +#define MAX_DATA_RANGES (MAX_SKB_FRAGS + 2) +#else +#define MAX_DATA_RANGES MAX_PAGE_BUFFER_COUNT +#endif + /* Estimated requestor size: * out_ring_size/min_out_msg_size + in_ring_size/min_in_msg_size */ diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 3a834d4e1c84..ac2d706ef2d0 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -980,8 +980,7 @@ static void netvsc_copy_to_send_buf(struct netvsc_device *net_device, + pend_size; int i; u32 padding = 0; - u32 page_count = packet->cp_partial ? packet->rmsg_pgcnt : - packet->page_buf_cnt; + u32 page_count = packet->cp_partial ? 1 : packet->page_buf_cnt; u32 remain; /* Add padding */ @@ -1082,6 +1081,42 @@ static int netvsc_dma_map(struct hv_device *hv_dev, return 0; } +/* Build an "array" of mpb entries describing the data to be transferred + * over VMBus. After the desc header fields, each "array" entry is variable + * size, and each entry starts after the end of the previous entry. The + * "offset" and "len" fields for each entry imply the size of the entry. + * + * The pfns are in HV_HYP_PAGE_SIZE, because all communication with Hyper-V + * uses that granularity, even if the system page size of the guest is larger. + * Each entry in the input "pb" array must describe a contiguous range of + * guest physical memory so that the pfns are sequential if the range crosses + * a page boundary. The offset field must be < HV_HYP_PAGE_SIZE. + */ +static inline void netvsc_build_mpb_array(struct hv_page_buffer *pb, + u32 page_buffer_count, + struct vmbus_packet_mpb_array *desc, + u32 *desc_size) +{ + struct hv_mpb_array *mpb_entry = &desc->range; + int i, j; + + for (i = 0; i < page_buffer_count; i++) { + u32 offset = pb[i].offset; + u32 len = pb[i].len; + + mpb_entry->offset = offset; + mpb_entry->len = len; + + for (j = 0; j < HVPFN_UP(offset + len); j++) + mpb_entry->pfn_array[j] = pb[i].pfn + j; + + mpb_entry = (struct hv_mpb_array *)&mpb_entry->pfn_array[j]; + } + + desc->rangecount = page_buffer_count; + *desc_size = (char *)mpb_entry - (char *)desc; +} + static inline int netvsc_send_pkt( struct hv_device *device, struct hv_netvsc_packet *packet, @@ -1124,8 +1159,11 @@ static inline int netvsc_send_pkt( packet->dma_range = NULL; if (packet->page_buf_cnt) { + struct vmbus_channel_packet_page_buffer desc; + u32 desc_size; + if (packet->cp_partial) - pb += packet->rmsg_pgcnt; + pb++; ret = netvsc_dma_map(ndev_ctx->device_ctx, packet, pb); if (ret) { @@ -1133,11 +1171,12 @@ static inline int netvsc_send_pkt( goto exit; } - ret = vmbus_sendpacket_pagebuffer(out_channel, - pb, packet->page_buf_cnt, - &nvmsg, sizeof(nvmsg), - req_id); - + netvsc_build_mpb_array(pb, packet->page_buf_cnt, + (struct vmbus_packet_mpb_array *)&desc, + &desc_size); + ret = vmbus_sendpacket_mpb_desc(out_channel, + (struct vmbus_packet_mpb_array *)&desc, + desc_size, &nvmsg, sizeof(nvmsg), req_id); if (ret) netvsc_dma_unmap(ndev_ctx->device_ctx, packet); } else { @@ -1286,7 +1325,7 @@ int netvsc_send(struct net_device *ndev, packet->send_buf_index = section_index; if (packet->cp_partial) { - packet->page_buf_cnt -= packet->rmsg_pgcnt; + packet->page_buf_cnt--; packet->total_data_buflen = msd_len + packet->rmsg_size; } else { packet->page_buf_cnt = 0; diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 2fba5dfd9cd0..96a1767281f7 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -325,43 +325,10 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb, return txq; } -static u32 fill_pg_buf(unsigned long hvpfn, u32 offset, u32 len, - struct hv_page_buffer *pb) -{ - int j = 0; - - hvpfn += offset >> HV_HYP_PAGE_SHIFT; - offset = offset & ~HV_HYP_PAGE_MASK; - - while (len > 0) { - unsigned long bytes; - - bytes = HV_HYP_PAGE_SIZE - offset; - if (bytes > len) - bytes = len; - pb[j].pfn = hvpfn; - pb[j].offset = offset; - pb[j].len = bytes; - - offset += bytes; - len -= bytes; - - if (offset == HV_HYP_PAGE_SIZE && len) { - hvpfn++; - offset = 0; - j++; - } - } - - return j + 1; -} - static u32 init_page_array(void *hdr, u32 len, struct sk_buff *skb, struct hv_netvsc_packet *packet, struct hv_page_buffer *pb) { - u32 slots_used = 0; - char *data = skb->data; int frags = skb_shinfo(skb)->nr_frags; int i; @@ -370,28 +337,27 @@ static u32 init_page_array(void *hdr, u32 len, struct sk_buff *skb, * 2. skb linear data * 3. skb fragment data */ - slots_used += fill_pg_buf(virt_to_hvpfn(hdr), - offset_in_hvpage(hdr), - len, - &pb[slots_used]); + pb[0].offset = offset_in_hvpage(hdr); + pb[0].len = len; + pb[0].pfn = virt_to_hvpfn(hdr); packet->rmsg_size = len; - packet->rmsg_pgcnt = slots_used; - slots_used += fill_pg_buf(virt_to_hvpfn(data), - offset_in_hvpage(data), - skb_headlen(skb), - &pb[slots_used]); + pb[1].offset = offset_in_hvpage(skb->data); + pb[1].len = skb_headlen(skb); + pb[1].pfn = virt_to_hvpfn(skb->data); for (i = 0; i < frags; i++) { skb_frag_t *frag = skb_shinfo(skb)->frags + i; + struct hv_page_buffer *cur_pb = &pb[i + 2]; + u64 pfn = page_to_hvpfn(skb_frag_page(frag)); + u32 offset = skb_frag_off(frag); - slots_used += fill_pg_buf(page_to_hvpfn(skb_frag_page(frag)), - skb_frag_off(frag), - skb_frag_size(frag), - &pb[slots_used]); + cur_pb->offset = offset_in_hvpage(offset); + cur_pb->len = skb_frag_size(frag); + cur_pb->pfn = pfn + (offset >> HV_HYP_PAGE_SHIFT); } - return slots_used; + return frags + 2; } static int count_skb_frag_slots(struct sk_buff *skb) @@ -482,7 +448,7 @@ static int netvsc_xmit(struct sk_buff *skb, struct net_device *net, bool xdp_tx) struct net_device *vf_netdev; u32 rndis_msg_size; u32 hash; - struct hv_page_buffer pb[MAX_PAGE_BUFFER_COUNT]; + struct hv_page_buffer pb[MAX_DATA_RANGES]; /* If VF is present and up then redirect packets to it. * Skip the VF if it is marked down or has no carrier. diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index eea777ec2541..bb656ea09773 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -225,8 +225,7 @@ static int rndis_filter_send_request(struct rndis_device *dev, struct rndis_request *req) { struct hv_netvsc_packet *packet; - struct hv_page_buffer page_buf[2]; - struct hv_page_buffer *pb = page_buf; + struct hv_page_buffer pb; int ret; /* Setup the packet to send it */ @@ -235,27 +234,14 @@ static int rndis_filter_send_request(struct rndis_device *dev, packet->total_data_buflen = req->request_msg.msg_len; packet->page_buf_cnt = 1; - pb[0].pfn = virt_to_phys(&req->request_msg) >> - HV_HYP_PAGE_SHIFT; - pb[0].len = req->request_msg.msg_len; - pb[0].offset = offset_in_hvpage(&req->request_msg); - - /* Add one page_buf when request_msg crossing page boundary */ - if (pb[0].offset + pb[0].len > HV_HYP_PAGE_SIZE) { - packet->page_buf_cnt++; - pb[0].len = HV_HYP_PAGE_SIZE - - pb[0].offset; - pb[1].pfn = virt_to_phys((void *)&req->request_msg - + pb[0].len) >> HV_HYP_PAGE_SHIFT; - pb[1].offset = 0; - pb[1].len = req->request_msg.msg_len - - pb[0].len; - } + pb.pfn = virt_to_phys(&req->request_msg) >> HV_HYP_PAGE_SHIFT; + pb.len = req->request_msg.msg_len; + pb.offset = offset_in_hvpage(&req->request_msg); trace_rndis_send(dev->ndev, 0, &req->request_msg); rcu_read_lock_bh(); - ret = netvsc_send(dev->ndev, packet, NULL, pb, NULL, false); + ret = netvsc_send(dev->ndev, packet, NULL, &pb, NULL, false); rcu_read_unlock_bh(); return ret; diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c index 1659bbffdb91..463be34a4ca4 100644 --- a/drivers/net/ieee802154/ca8210.c +++ b/drivers/net/ieee802154/ca8210.c @@ -1446,8 +1446,7 @@ static u8 mcps_data_request( command.pdata.data_req.src_addr_mode = src_addr_mode; command.pdata.data_req.dst.mode = dst_address_mode; if (dst_address_mode != MAC_MODE_NO_ADDR) { - command.pdata.data_req.dst.pan_id[0] = LS_BYTE(dst_pan_id); - command.pdata.data_req.dst.pan_id[1] = MS_BYTE(dst_pan_id); + put_unaligned_le16(dst_pan_id, command.pdata.data_req.dst.pan_id); if (dst_address_mode == MAC_MODE_SHORT_ADDR) { command.pdata.data_req.dst.address[0] = LS_BYTE( dst_addr->short_address @@ -1795,12 +1794,12 @@ static int ca8210_skb_rx( } hdr.source.mode = data_ind[0]; dev_dbg(&priv->spi->dev, "srcAddrMode: %#03x\n", hdr.source.mode); - hdr.source.pan_id = *(u16 *)&data_ind[1]; + hdr.source.pan_id = cpu_to_le16(get_unaligned_le16(&data_ind[1])); dev_dbg(&priv->spi->dev, "srcPanId: %#06x\n", hdr.source.pan_id); memcpy(&hdr.source.extended_addr, &data_ind[3], 8); hdr.dest.mode = data_ind[11]; dev_dbg(&priv->spi->dev, "dstAddrMode: %#03x\n", hdr.dest.mode); - hdr.dest.pan_id = *(u16 *)&data_ind[12]; + hdr.dest.pan_id = cpu_to_le16(get_unaligned_le16(&data_ind[12])); dev_dbg(&priv->spi->dev, "dstPanId: %#06x\n", hdr.dest.pan_id); memcpy(&hdr.dest.extended_addr, &data_ind[14], 8); @@ -1927,7 +1926,7 @@ static int ca8210_skb_tx( status = mcps_data_request( header.source.mode, header.dest.mode, - header.dest.pan_id, + le16_to_cpu(header.dest.pan_id), (union macaddr *)&header.dest.extended_addr, skb->len - mac_len, &skb->data[mac_len], diff --git a/drivers/net/phy/microchip.c b/drivers/net/phy/microchip.c index 623607fd2cef..0b88635f4fbc 100644 --- a/drivers/net/phy/microchip.c +++ b/drivers/net/phy/microchip.c @@ -31,6 +31,47 @@ static int lan88xx_write_page(struct phy_device *phydev, int page) return __phy_write(phydev, LAN88XX_EXT_PAGE_ACCESS, page); } +static int lan88xx_phy_config_intr(struct phy_device *phydev) +{ + int rc; + + if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { + /* unmask all source and clear them before enable */ + rc = phy_write(phydev, LAN88XX_INT_MASK, 0x7FFF); + rc = phy_read(phydev, LAN88XX_INT_STS); + rc = phy_write(phydev, LAN88XX_INT_MASK, + LAN88XX_INT_MASK_MDINTPIN_EN_ | + LAN88XX_INT_MASK_LINK_CHANGE_); + } else { + rc = phy_write(phydev, LAN88XX_INT_MASK, 0); + if (rc) + return rc; + + /* Ack interrupts after they have been disabled */ + rc = phy_read(phydev, LAN88XX_INT_STS); + } + + return rc < 0 ? rc : 0; +} + +static irqreturn_t lan88xx_handle_interrupt(struct phy_device *phydev) +{ + int irq_status; + + irq_status = phy_read(phydev, LAN88XX_INT_STS); + if (irq_status < 0) { + phy_error(phydev); + return IRQ_NONE; + } + + if (!(irq_status & LAN88XX_INT_STS_LINK_CHANGE_)) + return IRQ_NONE; + + phy_trigger_machine(phydev); + + return IRQ_HANDLED; +} + static int lan88xx_suspend(struct phy_device *phydev) { struct lan88xx_priv *priv = phydev->priv; @@ -351,9 +392,8 @@ static struct phy_driver microchip_phy_driver[] = { .config_aneg = lan88xx_config_aneg, .link_change_notify = lan88xx_link_change_notify, - /* Interrupt handling is broken, do not define related - * functions to force polling. - */ + .config_intr = lan88xx_phy_config_intr, + .handle_interrupt = lan88xx_handle_interrupt, .suspend = lan88xx_suspend, .resume = genphy_resume, diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index fc58e4afb38d..3069a7df25d3 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -1566,7 +1566,7 @@ bool phylink_expects_phy(struct phylink *pl) { if (pl->cfg_link_an_mode == MLO_AN_FIXED || (pl->cfg_link_an_mode == MLO_AN_INBAND && - phy_interface_mode_is_8023z(pl->link_config.interface))) + phy_interface_mode_is_8023z(pl->link_interface))) return false; return true; } diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 061a7a9afad0..c2b715541989 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -9880,6 +9880,7 @@ static const struct usb_device_id rtl8152_table[] = { { USB_DEVICE(VENDOR_ID_NVIDIA, 0x09ff) }, { USB_DEVICE(VENDOR_ID_TPLINK, 0x0601) }, { USB_DEVICE(VENDOR_ID_DLINK, 0xb301) }, + { USB_DEVICE(VENDOR_ID_DELL, 0xb097) }, { USB_DEVICE(VENDOR_ID_ASUS, 0x1976) }, {} }; diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 50be5a3c4779..ef61eab81707 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -274,9 +274,9 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan, be32_to_cpu(fdb->vni))) goto nla_put_failure; - ci.ndm_used = jiffies_to_clock_t(now - fdb->used); + ci.ndm_used = jiffies_to_clock_t(now - READ_ONCE(fdb->used)); ci.ndm_confirmed = 0; - ci.ndm_updated = jiffies_to_clock_t(now - fdb->updated); + ci.ndm_updated = jiffies_to_clock_t(now - READ_ONCE(fdb->updated)); ci.ndm_refcnt = 0; if (nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci)) @@ -482,8 +482,8 @@ static struct vxlan_fdb *vxlan_find_mac(struct vxlan_dev *vxlan, struct vxlan_fdb *f; f = __vxlan_find_mac(vxlan, mac, vni); - if (f && f->used != jiffies) - f->used = jiffies; + if (f && READ_ONCE(f->used) != jiffies) + WRITE_ONCE(f->used, jiffies); return f; } @@ -1057,12 +1057,12 @@ static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan, !(f->flags & NTF_VXLAN_ADDED_BY_USER)) { if (f->state != state) { f->state = state; - f->updated = jiffies; + WRITE_ONCE(f->updated, jiffies); notify = 1; } if (f->flags != fdb_flags) { f->flags = fdb_flags; - f->updated = jiffies; + WRITE_ONCE(f->updated, jiffies); notify = 1; } } @@ -1096,7 +1096,7 @@ static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan, } if (ndm_flags & NTF_USE) - f->used = jiffies; + WRITE_ONCE(f->used, jiffies); if (notify) { if (rd == NULL) @@ -1525,7 +1525,7 @@ static bool vxlan_snoop(struct net_device *dev, src_mac, &rdst->remote_ip.sa, &src_ip->sa); rdst->remote_ip = *src_ip; - f->updated = jiffies; + WRITE_ONCE(f->updated, jiffies); vxlan_fdb_notify(vxlan, f, rdst, RTM_NEWNEIGH, true, NULL); } else { u32 hash_index = fdb_head_index(vxlan, src_mac, vni); @@ -2936,7 +2936,7 @@ static void vxlan_cleanup(struct timer_list *t) if (f->flags & NTF_EXT_LEARNED) continue; - timeout = f->used + vxlan->cfg.age_interval * HZ; + timeout = READ_ONCE(f->used) + vxlan->cfg.age_interval * HZ; if (time_before_eq(timeout, jiffies)) { netdev_dbg(vxlan->dev, "garbage collect %pM\n", @@ -4231,6 +4231,7 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); + bool rem_ip_changed, change_igmp; struct net_device *lowerdev; struct vxlan_config conf; struct vxlan_rdst *dst; @@ -4254,8 +4255,13 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], if (err) return err; + rem_ip_changed = !vxlan_addr_equal(&conf.remote_ip, &dst->remote_ip); + change_igmp = vxlan->dev->flags & IFF_UP && + (rem_ip_changed || + dst->remote_ifindex != conf.remote_ifindex); + /* handle default dst entry */ - if (!vxlan_addr_equal(&conf.remote_ip, &dst->remote_ip)) { + if (rem_ip_changed) { u32 hash_index = fdb_head_index(vxlan, all_zeros_mac, conf.vni); spin_lock_bh(&vxlan->hash_lock[hash_index]); @@ -4299,6 +4305,9 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], } } + if (change_igmp && vxlan_addr_multicast(&dst->remote_ip)) + err = vxlan_multicast_leave(vxlan); + if (conf.age_interval != vxlan->cfg.age_interval) mod_timer(&vxlan->age_timer, jiffies); @@ -4306,7 +4315,12 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], if (lowerdev && lowerdev != dst->remote_dev) dst->remote_dev = lowerdev; vxlan_config_apply(dev, &conf, lowerdev, vxlan->net, true); - return 0; + + if (!err && change_igmp && + vxlan_addr_multicast(&dst->remote_ip)) + err = vxlan_multicast_join(vxlan); + + return err; } static void vxlan_dellink(struct net_device *dev, struct list_head *head) diff --git a/drivers/net/wireless/ath/ath9k/init.c b/drivers/net/wireless/ath/ath9k/init.c index 4f00400c7ffb..58386906598a 100644 --- a/drivers/net/wireless/ath/ath9k/init.c +++ b/drivers/net/wireless/ath/ath9k/init.c @@ -691,7 +691,9 @@ static int ath9k_of_init(struct ath_softc *sc) ah->ah_flags |= AH_NO_EEP_SWAP; } - of_get_mac_address(np, common->macaddr); + ret = of_get_mac_address(np, common->macaddr); + if (ret == -EPROBE_DEFER) + return ret; return 0; } diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index 7f30e6add993..39ac9d81d10d 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -552,6 +552,8 @@ static const struct iwl_dev_info iwl_dev_info_table[] = { IWL_DEV_INFO(0x7A70, 0x1692, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690i_name), IWL_DEV_INFO(0x7AF0, 0x1691, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690s_name), IWL_DEV_INFO(0x7AF0, 0x1692, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690i_name), + IWL_DEV_INFO(0x7F70, 0x1691, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690s_name), + IWL_DEV_INFO(0x7F70, 0x1692, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690i_name), IWL_DEV_INFO(0x271C, 0x0214, iwl9260_2ac_cfg, iwl9260_1_name), IWL_DEV_INFO(0x7E40, 0x1691, iwl_cfg_ma_a0_gf4_a0, iwl_ax411_killer_1690s_name), diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c index c406cb1a102f..e5c72a7d6e92 100644 --- a/drivers/net/wireless/mediatek/mt76/dma.c +++ b/drivers/net/wireless/mediatek/mt76/dma.c @@ -789,6 +789,7 @@ void mt76_dma_cleanup(struct mt76_dev *dev) int i; mt76_worker_disable(&dev->tx_worker); + napi_disable(&dev->tx_napi); netif_napi_del(&dev->tx_napi); for (i = 0; i < ARRAY_SIZE(dev->phys); i++) { diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c index 9ccf8550a067..cd22c756acc6 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c @@ -798,9 +798,10 @@ rtl8xxxu_writeN(struct rtl8xxxu_priv *priv, u16 addr, u8 *buf, u16 len) return len; write_error: - dev_info(&udev->dev, - "%s: Failed to write block at addr: %04x size: %04x\n", - __func__, addr, blocksize); + if (rtl8xxxu_debug & RTL8XXXU_DEBUG_REG_WRITE) + dev_info(&udev->dev, + "%s: Failed to write block at addr: %04x size: %04x\n", + __func__, addr, blocksize); return -EAGAIN; } @@ -3920,8 +3921,14 @@ static int rtl8xxxu_init_device(struct ieee80211_hw *hw) */ rtl8xxxu_write16(priv, REG_TRXFF_BNDY + 2, fops->trxff_boundary); - ret = rtl8xxxu_download_firmware(priv); - dev_dbg(dev, "%s: download_firmware %i\n", __func__, ret); + for (int retry = 5; retry >= 0 ; retry--) { + ret = rtl8xxxu_download_firmware(priv); + dev_dbg(dev, "%s: download_firmware %i\n", __func__, ret); + if (ret != -EAGAIN) + break; + if (retry) + dev_dbg(dev, "%s: retry firmware download\n", __func__); + } if (ret) goto exit; ret = rtl8xxxu_start_firmware(priv); diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c index 7c390c2c608d..0a913cf6a615 100644 --- a/drivers/net/wireless/realtek/rtw88/main.c +++ b/drivers/net/wireless/realtek/rtw88/main.c @@ -1516,6 +1516,7 @@ static void rtw_init_ht_cap(struct rtw_dev *rtwdev, { const struct rtw_chip_info *chip = rtwdev->chip; struct rtw_efuse *efuse = &rtwdev->efuse; + int i; ht_cap->ht_supported = true; ht_cap->cap = 0; @@ -1535,25 +1536,20 @@ static void rtw_init_ht_cap(struct rtw_dev *rtwdev, ht_cap->ampdu_factor = IEEE80211_HT_MAX_AMPDU_64K; ht_cap->ampdu_density = chip->ampdu_density; ht_cap->mcs.tx_params = IEEE80211_HT_MCS_TX_DEFINED; - if (efuse->hw_cap.nss > 1) { - ht_cap->mcs.rx_mask[0] = 0xFF; - ht_cap->mcs.rx_mask[1] = 0xFF; - ht_cap->mcs.rx_mask[4] = 0x01; - ht_cap->mcs.rx_highest = cpu_to_le16(300); - } else { - ht_cap->mcs.rx_mask[0] = 0xFF; - ht_cap->mcs.rx_mask[1] = 0x00; - ht_cap->mcs.rx_mask[4] = 0x01; - ht_cap->mcs.rx_highest = cpu_to_le16(150); - } + + for (i = 0; i < efuse->hw_cap.nss; i++) + ht_cap->mcs.rx_mask[i] = 0xFF; + ht_cap->mcs.rx_mask[4] = 0x01; + ht_cap->mcs.rx_highest = cpu_to_le16(150 * efuse->hw_cap.nss); } static void rtw_init_vht_cap(struct rtw_dev *rtwdev, struct ieee80211_sta_vht_cap *vht_cap) { struct rtw_efuse *efuse = &rtwdev->efuse; - u16 mcs_map; + u16 mcs_map = 0; __le16 highest; + int i; if (efuse->hw_cap.ptcl != EFUSE_HW_CAP_IGNORE && efuse->hw_cap.ptcl != EFUSE_HW_CAP_PTCL_VHT) @@ -1576,21 +1572,15 @@ static void rtw_init_vht_cap(struct rtw_dev *rtwdev, if (rtw_chip_has_rx_ldpc(rtwdev)) vht_cap->cap |= IEEE80211_VHT_CAP_RXLDPC; - mcs_map = IEEE80211_VHT_MCS_SUPPORT_0_9 << 0 | - IEEE80211_VHT_MCS_NOT_SUPPORTED << 4 | - IEEE80211_VHT_MCS_NOT_SUPPORTED << 6 | - IEEE80211_VHT_MCS_NOT_SUPPORTED << 8 | - IEEE80211_VHT_MCS_NOT_SUPPORTED << 10 | - IEEE80211_VHT_MCS_NOT_SUPPORTED << 12 | - IEEE80211_VHT_MCS_NOT_SUPPORTED << 14; - if (efuse->hw_cap.nss > 1) { - highest = cpu_to_le16(780); - mcs_map |= IEEE80211_VHT_MCS_SUPPORT_0_9 << 2; - } else { - highest = cpu_to_le16(390); - mcs_map |= IEEE80211_VHT_MCS_NOT_SUPPORTED << 2; + for (i = 0; i < 8; i++) { + if (i < efuse->hw_cap.nss) + mcs_map |= IEEE80211_VHT_MCS_SUPPORT_0_9 << (i * 2); + else + mcs_map |= IEEE80211_VHT_MCS_NOT_SUPPORTED << (i * 2); } + highest = cpu_to_le16(390 * efuse->hw_cap.nss); + vht_cap->vht_mcs.rx_mcs_map = cpu_to_le16(mcs_map); vht_cap->vht_mcs.tx_mcs_map = cpu_to_le16(mcs_map); vht_cap->vht_mcs.rx_highest = highest; diff --git a/drivers/net/wireless/realtek/rtw88/reg.h b/drivers/net/wireless/realtek/rtw88/reg.h index 03bd8dc53f72..08628ba3419d 100644 --- a/drivers/net/wireless/realtek/rtw88/reg.h +++ b/drivers/net/wireless/realtek/rtw88/reg.h @@ -107,6 +107,7 @@ #define BIT_SHIFT_ROM_PGE 16 #define BIT_FW_INIT_RDY BIT(15) #define BIT_FW_DW_RDY BIT(14) +#define BIT_CPU_CLK_SEL (BIT(12) | BIT(13)) #define BIT_RPWM_TOGGLE BIT(7) #define BIT_RAM_DL_SEL BIT(7) /* legacy only */ #define BIT_DMEM_CHKSUM_OK BIT(6) @@ -124,7 +125,7 @@ BIT_CHECK_SUM_OK) #define FW_READY_LEGACY (BIT_MCUFWDL_RDY | BIT_FWDL_CHK_RPT | \ BIT_WINTINI_RDY | BIT_RAM_DL_SEL) -#define FW_READY_MASK 0xffff +#define FW_READY_MASK (0xffff & ~BIT_CPU_CLK_SEL) #define REG_MCU_TST_CFG 0x84 #define VAL_FW_TRIGGER 0x1 diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822b.c b/drivers/net/wireless/realtek/rtw88/rtw8822b.c index 690e35c98f6e..0b071a116c58 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8822b.c +++ b/drivers/net/wireless/realtek/rtw88/rtw8822b.c @@ -957,11 +957,11 @@ static void rtw8822b_query_rx_desc(struct rtw_dev *rtwdev, u8 *rx_desc, } static void -rtw8822b_set_tx_power_index_by_rate(struct rtw_dev *rtwdev, u8 path, u8 rs) +rtw8822b_set_tx_power_index_by_rate(struct rtw_dev *rtwdev, u8 path, + u8 rs, u32 *phy_pwr_idx) { struct rtw_hal *hal = &rtwdev->hal; static const u32 offset_txagc[2] = {0x1d00, 0x1d80}; - static u32 phy_pwr_idx; u8 rate, rate_idx, pwr_index, shift; int j; @@ -969,12 +969,12 @@ rtw8822b_set_tx_power_index_by_rate(struct rtw_dev *rtwdev, u8 path, u8 rs) rate = rtw_rate_section[rs][j]; pwr_index = hal->tx_pwr_tbl[path][rate]; shift = rate & 0x3; - phy_pwr_idx |= ((u32)pwr_index << (shift * 8)); + *phy_pwr_idx |= ((u32)pwr_index << (shift * 8)); if (shift == 0x3) { rate_idx = rate & 0xfc; rtw_write32(rtwdev, offset_txagc[path] + rate_idx, - phy_pwr_idx); - phy_pwr_idx = 0; + *phy_pwr_idx); + *phy_pwr_idx = 0; } } } @@ -982,11 +982,13 @@ rtw8822b_set_tx_power_index_by_rate(struct rtw_dev *rtwdev, u8 path, u8 rs) static void rtw8822b_set_tx_power_index(struct rtw_dev *rtwdev) { struct rtw_hal *hal = &rtwdev->hal; + u32 phy_pwr_idx = 0; int rs, path; for (path = 0; path < hal->rf_path_num; path++) { for (rs = 0; rs < RTW_RATE_SECTION_MAX; rs++) - rtw8822b_set_tx_power_index_by_rate(rtwdev, path, rs); + rtw8822b_set_tx_power_index_by_rate(rtwdev, path, rs, + &phy_pwr_idx); } } diff --git a/drivers/net/wireless/realtek/rtw88/util.c b/drivers/net/wireless/realtek/rtw88/util.c index cdfd66a85075..43cd06aa39b1 100644 --- a/drivers/net/wireless/realtek/rtw88/util.c +++ b/drivers/net/wireless/realtek/rtw88/util.c @@ -101,7 +101,8 @@ void rtw_desc_to_mcsrate(u16 rate, u8 *mcs, u8 *nss) *nss = 4; *mcs = rate - DESC_RATEVHT4SS_MCS0; } else if (rate >= DESC_RATEMCS0 && - rate <= DESC_RATEMCS15) { + rate <= DESC_RATEMCS31) { + *nss = 0; *mcs = rate - DESC_RATEMCS0; } } diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c index 1d57a8c5e97d..0f022a5192ac 100644 --- a/drivers/net/wireless/realtek/rtw89/fw.c +++ b/drivers/net/wireless/realtek/rtw89/fw.c @@ -373,7 +373,6 @@ static int __rtw89_fw_download_hdr(struct rtw89_dev *rtwdev, const u8 *fw, u32 l ret = rtw89_h2c_tx(rtwdev, skb, false); if (ret) { rtw89_err(rtwdev, "failed to send h2c\n"); - ret = -1; goto fail; } @@ -434,7 +433,6 @@ static int __rtw89_fw_download_main(struct rtw89_dev *rtwdev, ret = rtw89_h2c_tx(rtwdev, skb, true); if (ret) { rtw89_err(rtwdev, "failed to send h2c\n"); - ret = -1; goto fail; } diff --git a/drivers/net/wireless/realtek/rtw89/regd.c b/drivers/net/wireless/realtek/rtw89/regd.c index 6e5a740b128f..2d31193fcc87 100644 --- a/drivers/net/wireless/realtek/rtw89/regd.c +++ b/drivers/net/wireless/realtek/rtw89/regd.c @@ -334,6 +334,7 @@ void rtw89_regd_notifier(struct wiphy *wiphy, struct regulatory_request *request struct ieee80211_hw *hw = wiphy_to_ieee80211_hw(wiphy); struct rtw89_dev *rtwdev = hw->priv; + wiphy_lock(wiphy); mutex_lock(&rtwdev->mutex); rtw89_leave_ps_mode(rtwdev); @@ -350,4 +351,5 @@ void rtw89_regd_notifier(struct wiphy *wiphy, struct regulatory_request *request exit: mutex_unlock(&rtwdev->mutex); + wiphy_unlock(wiphy); } diff --git a/drivers/net/wireless/realtek/rtw89/ser.c b/drivers/net/wireless/realtek/rtw89/ser.c index afb1b41e1a9a..f5dacdc4d11a 100644 --- a/drivers/net/wireless/realtek/rtw89/ser.c +++ b/drivers/net/wireless/realtek/rtw89/ser.c @@ -153,9 +153,11 @@ static void ser_state_run(struct rtw89_ser *ser, u8 evt) rtw89_debug(rtwdev, RTW89_DBG_SER, "ser: %s receive %s\n", ser_st_name(ser), ser_ev_name(ser, evt)); + wiphy_lock(rtwdev->hw->wiphy); mutex_lock(&rtwdev->mutex); rtw89_leave_lps(rtwdev); mutex_unlock(&rtwdev->mutex); + wiphy_unlock(rtwdev->hw->wiphy); ser->st_tbl[ser->state].st_func(ser, evt); } @@ -624,9 +626,11 @@ static void ser_l2_reset_st_hdl(struct rtw89_ser *ser, u8 evt) switch (evt) { case SER_EV_STATE_IN: + wiphy_lock(rtwdev->hw->wiphy); mutex_lock(&rtwdev->mutex); ser_l2_reset_st_pre_hdl(ser); mutex_unlock(&rtwdev->mutex); + wiphy_unlock(rtwdev->hw->wiphy); ieee80211_restart_hw(rtwdev->hw); ser_set_alarm(ser, SER_RECFG_TIMEOUT, SER_EV_L2_RECFG_TIMEOUT); diff --git a/drivers/nvdimm/label.c b/drivers/nvdimm/label.c index 082253a3a956..04f4a049599a 100644 --- a/drivers/nvdimm/label.c +++ b/drivers/nvdimm/label.c @@ -442,7 +442,8 @@ int nd_label_data_init(struct nvdimm_drvdata *ndd) if (ndd->data) return 0; - if (ndd->nsarea.status || ndd->nsarea.max_xfer == 0) { + if (ndd->nsarea.status || ndd->nsarea.max_xfer == 0 || + ndd->nsarea.config_size == 0) { dev_dbg(ndd->dev, "failed to init config data area: (%u:%u)\n", ndd->nsarea.max_xfer, ndd->nsarea.config_size); return -ENXIO; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index ca20afb3d94c..3d0004489d6d 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -4881,7 +4881,8 @@ static void nvme_fw_act_work(struct work_struct *work) msleep(100); } - if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE)) + if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_CONNECTING) || + !nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE)) return; nvme_start_queues(ctrl); diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 0531584d8775..676826e9d6d4 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -376,7 +376,7 @@ static bool nvme_dbbuf_update_and_check_event(u16 value, __le32 *dbbuf_db, * as it only leads to a small amount of wasted memory for the lifetime of * the I/O. */ -static int nvme_pci_npages_prp(void) +static __always_inline int nvme_pci_npages_prp(void) { unsigned max_bytes = (NVME_MAX_KB_SZ * 1024) + NVME_CTRL_PAGE_SIZE; unsigned nprps = DIV_ROUND_UP(max_bytes, NVME_CTRL_PAGE_SIZE); @@ -1154,7 +1154,9 @@ static void nvme_poll_irqdisable(struct nvme_queue *nvmeq) WARN_ON_ONCE(test_bit(NVMEQ_POLLED, &nvmeq->flags)); disable_irq(pci_irq_vector(pdev, nvmeq->cq_vector)); + spin_lock(&nvmeq->cq_poll_lock); nvme_poll_cq(nvmeq, NULL); + spin_unlock(&nvmeq->cq_poll_lock); enable_irq(pci_irq_vector(pdev, nvmeq->cq_vector)); } @@ -3591,6 +3593,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, { PCI_DEVICE(0x1e49, 0x0041), /* ZHITAI TiPro7000 NVMe SSD */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, + { PCI_DEVICE(0x025e, 0xf1ac), /* SOLIDIGM P44 pro SSDPFKKW020X7 */ + .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, { PCI_DEVICE(0xc0a9, 0x540a), /* Crucial P2 */ .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1d97, 0x2263), /* Lexar NM610 */ diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 125e22bd34e2..eee052dbf80c 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -1417,6 +1417,9 @@ static void nvmet_tcp_restore_socket_callbacks(struct nvmet_tcp_queue *queue) { struct socket *sock = queue->sock; + if (!queue->state_change) + return; + write_lock_bh(&sock->sk->sk_callback_lock); sock->sk->sk_data_ready = queue->data_ready; sock->sk->sk_state_change = queue->state_change; diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig index 55c028af4bd9..c4f9ac5c00c1 100644 --- a/drivers/pci/Kconfig +++ b/drivers/pci/Kconfig @@ -184,6 +184,12 @@ config PCI_P2PDMA P2P DMA transactions must be between devices behind the same root port. + Enabling this option will reduce the entropy of x86 KASLR memory + regions. For example - on a 46 bit system, the entropy goes down + from 16 bits to 15 bits. The actual reduction in entropy depends + on the physical address bits, on processor features, kernel config + (5 level page table) and physical memory present on the system. + If unsure, say N. config PCI_LABEL diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c index 449ad709495d..3b3f079d0d2d 100644 --- a/drivers/pci/controller/dwc/pcie-designware-ep.c +++ b/drivers/pci/controller/dwc/pcie-designware-ep.c @@ -283,7 +283,7 @@ static int dw_pcie_find_index(struct dw_pcie_ep *ep, phys_addr_t addr, u32 index; struct dw_pcie *pci = to_dw_pcie_from_ep(ep); - for (index = 0; index < pci->num_ob_windows; index++) { + for_each_set_bit(index, ep->ob_window_map, pci->num_ob_windows) { if (ep->outbound_addr[index] != addr) continue; *atu_index = index; diff --git a/drivers/pci/controller/pcie-brcmstb.c b/drivers/pci/controller/pcie-brcmstb.c index 425db793080d..c89ad1f92a07 100644 --- a/drivers/pci/controller/pcie-brcmstb.c +++ b/drivers/pci/controller/pcie-brcmstb.c @@ -281,8 +281,8 @@ static int brcm_pcie_encode_ibar_size(u64 size) if (log2_in >= 12 && log2_in <= 15) /* Covers 4KB to 32KB (inclusive) */ return (log2_in - 12) + 0x1c; - else if (log2_in >= 16 && log2_in <= 35) - /* Covers 64KB to 32GB, (inclusive) */ + else if (log2_in >= 16 && log2_in <= 36) + /* Covers 64KB to 64GB, (inclusive) */ return log2_in - 15; /* Something is awry so disable */ return 0; @@ -1619,3 +1619,4 @@ module_platform_driver(brcm_pcie_driver); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Broadcom STB PCIe RC driver"); MODULE_AUTHOR("Broadcom"); +MODULE_SOFTDEP("pre: irq_bcm2712_mip"); diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c index 09995b6e73bc..771ff0f6971f 100644 --- a/drivers/pci/controller/vmd.c +++ b/drivers/pci/controller/vmd.c @@ -17,6 +17,8 @@ #include #include +#include + #include #define VMD_CFGBAR 0 @@ -919,6 +921,24 @@ static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id) struct vmd_dev *vmd; int err; + if (xen_domain()) { + /* + * Xen doesn't have knowledge about devices in the VMD bus + * because the config space of devices behind the VMD bridge is + * not known to Xen, and hence Xen cannot discover or configure + * them in any way. + * + * Bypass of MSI remapping won't work in that case as direct + * write by Linux to the MSI entries won't result in functional + * interrupts, as Xen is the entity that manages the host + * interrupt controller and must configure interrupts. However + * multiplexing of interrupts by the VMD bridge will work under + * Xen, so force the usage of that mode which must always be + * supported by VMD bridges. + */ + features &= ~VMD_FEAT_CAN_BYPASS_MSI_REMAP; + } + if (resource_size(&dev->resource[VMD_CFGBAR]) < (1 << 20)) return -ENOMEM; diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index 8c1ad20a21ec..3ce68adda9b7 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -806,11 +806,9 @@ static resource_size_t calculate_iosize(resource_size_t size, size = (size & 0xff) + ((size & ~0xffUL) << 2); #endif size = size + size1; - if (size < old_size) - size = old_size; - size = ALIGN(max(size, add_size) + children_add_size, align); - return size; + size = max(size, add_size) + children_add_size; + return ALIGN(max(size, old_size), align); } static resource_size_t calculate_memsize(resource_size_t size, diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c index 4445cae427b2..b2e0a79254f1 100644 --- a/drivers/perf/arm-cmn.c +++ b/drivers/perf/arm-cmn.c @@ -675,8 +675,8 @@ static umode_t arm_cmn_event_attr_is_visible(struct kobject *kobj, if ((chan == 5 && cmn->rsp_vc_num < 2) || (chan == 6 && cmn->dat_vc_num < 2) || - (chan == 7 && cmn->snp_vc_num < 2) || - (chan == 8 && cmn->req_vc_num < 2)) + (chan == 7 && cmn->req_vc_num < 2) || + (chan == 8 && cmn->snp_vc_num < 2)) return 0; } @@ -794,8 +794,8 @@ static umode_t arm_cmn_event_attr_is_visible(struct kobject *kobj, _CMN_EVENT_XP(pub_##_name, (_event) | (4 << 5)), \ _CMN_EVENT_XP(rsp2_##_name, (_event) | (5 << 5)), \ _CMN_EVENT_XP(dat2_##_name, (_event) | (6 << 5)), \ - _CMN_EVENT_XP(snp2_##_name, (_event) | (7 << 5)), \ - _CMN_EVENT_XP(req2_##_name, (_event) | (8 << 5)) + _CMN_EVENT_XP(req2_##_name, (_event) | (7 << 5)), \ + _CMN_EVENT_XP(snp2_##_name, (_event) | (8 << 5)) static struct attribute *arm_cmn_event_attrs[] = { @@ -2313,6 +2313,7 @@ static int arm_cmn_probe(struct platform_device *pdev) cmn->dev = &pdev->dev; cmn->part = (unsigned long)device_get_match_data(cmn->dev); + cmn->cpu = cpumask_local_spread(0, dev_to_node(cmn->dev)); platform_set_drvdata(pdev, cmn); if (cmn->part == PART_CMN600 && has_acpi_companion(cmn->dev)) { @@ -2340,7 +2341,6 @@ static int arm_cmn_probe(struct platform_device *pdev) if (err) return err; - cmn->cpu = cpumask_local_spread(0, dev_to_node(cmn->dev)); cmn->pmu = (struct pmu) { .module = THIS_MODULE, .attr_groups = arm_cmn_attr_groups, diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c index 0730fe80dc3c..069bcf49ee8f 100644 --- a/drivers/phy/phy-core.c +++ b/drivers/phy/phy-core.c @@ -398,13 +398,14 @@ EXPORT_SYMBOL_GPL(phy_power_off); int phy_set_mode_ext(struct phy *phy, enum phy_mode mode, int submode) { - int ret; + int ret = 0; - if (!phy || !phy->ops->set_mode) + if (!phy) return 0; mutex_lock(&phy->mutex); - ret = phy->ops->set_mode(phy, mode, submode); + if (phy->ops->set_mode) + ret = phy->ops->set_mode(phy, mode, submode); if (!ret) phy->attrs.mode = mode; mutex_unlock(&phy->mutex); diff --git a/drivers/phy/renesas/phy-rcar-gen3-usb2.c b/drivers/phy/renesas/phy-rcar-gen3-usb2.c index 7e61c6b278a7..024cc5ce68a3 100644 --- a/drivers/phy/renesas/phy-rcar-gen3-usb2.c +++ b/drivers/phy/renesas/phy-rcar-gen3-usb2.c @@ -9,6 +9,7 @@ * Copyright (C) 2014 Cogent Embedded, Inc. */ +#include #include #include #include @@ -21,12 +22,14 @@ #include #include #include +#include #include #include #include /******* USB2.0 Host registers (original offset is +0x200) *******/ #define USB2_INT_ENABLE 0x000 +#define USB2_AHB_BUS_CTR 0x008 #define USB2_USBCTR 0x00c #define USB2_SPD_RSM_TIMSET 0x10c #define USB2_OC_TIMSET 0x110 @@ -42,6 +45,10 @@ #define USB2_INT_ENABLE_USBH_INTB_EN BIT(2) /* For EHCI */ #define USB2_INT_ENABLE_USBH_INTA_EN BIT(1) /* For OHCI */ +/* AHB_BUS_CTR */ +#define USB2_AHB_BUS_CTR_MBL_MASK GENMASK(1, 0) +#define USB2_AHB_BUS_CTR_MBL_INCR4 2 + /* USBCTR */ #define USB2_USBCTR_DIRPD BIT(2) #define USB2_USBCTR_PLL_RST BIT(1) @@ -103,7 +110,6 @@ struct rcar_gen3_phy { struct rcar_gen3_chan *ch; u32 int_enable_bits; bool initialized; - bool otg_initialized; bool powered; }; @@ -113,10 +119,10 @@ struct rcar_gen3_chan { struct extcon_dev *extcon; struct rcar_gen3_phy rphys[NUM_OF_PHYS]; struct regulator *vbus; + struct reset_control *rstc; struct work_struct work; - struct mutex lock; /* protects rphys[...].powered */ + spinlock_t lock; /* protects access to hardware and driver data structure. */ enum usb_dr_mode dr_mode; - int irq; u32 obint_enable_bits; bool extcon_host; bool is_otg_channel; @@ -127,6 +133,7 @@ struct rcar_gen3_chan { struct rcar_gen3_phy_drv_data { const struct phy_ops *phy_usb2_ops; bool no_adp_ctrl; + bool init_bus; }; /* @@ -311,16 +318,15 @@ static bool rcar_gen3_is_any_rphy_initialized(struct rcar_gen3_chan *ch) return false; } -static bool rcar_gen3_needs_init_otg(struct rcar_gen3_chan *ch) +static bool rcar_gen3_is_any_otg_rphy_initialized(struct rcar_gen3_chan *ch) { - int i; - - for (i = 0; i < NUM_OF_PHYS; i++) { - if (ch->rphys[i].otg_initialized) - return false; + for (enum rcar_gen3_phy_index i = PHY_INDEX_BOTH_HC; i <= PHY_INDEX_EHCI; + i++) { + if (ch->rphys[i].initialized) + return true; } - return true; + return false; } static bool rcar_gen3_are_all_rphys_power_off(struct rcar_gen3_chan *ch) @@ -342,7 +348,9 @@ static ssize_t role_store(struct device *dev, struct device_attribute *attr, bool is_b_device; enum phy_mode cur_mode, new_mode; - if (!ch->is_otg_channel || !rcar_gen3_is_any_rphy_initialized(ch)) + guard(spinlock_irqsave)(&ch->lock); + + if (!ch->is_otg_channel || !rcar_gen3_is_any_otg_rphy_initialized(ch)) return -EIO; if (sysfs_streq(buf, "host")) @@ -380,7 +388,7 @@ static ssize_t role_show(struct device *dev, struct device_attribute *attr, { struct rcar_gen3_chan *ch = dev_get_drvdata(dev); - if (!ch->is_otg_channel || !rcar_gen3_is_any_rphy_initialized(ch)) + if (!ch->is_otg_channel || !rcar_gen3_is_any_otg_rphy_initialized(ch)) return -EIO; return sprintf(buf, "%s\n", rcar_gen3_is_host(ch) ? "host" : @@ -393,6 +401,9 @@ static void rcar_gen3_init_otg(struct rcar_gen3_chan *ch) void __iomem *usb2_base = ch->base; u32 val; + if (!ch->is_otg_channel || rcar_gen3_is_any_otg_rphy_initialized(ch)) + return; + /* Should not use functions of read-modify-write a register */ val = readl(usb2_base + USB2_LINECTRL1); val = (val & ~USB2_LINECTRL1_DP_RPD) | USB2_LINECTRL1_DPRPD_EN | @@ -406,7 +417,7 @@ static void rcar_gen3_init_otg(struct rcar_gen3_chan *ch) val = readl(usb2_base + USB2_ADPCTRL); writel(val | USB2_ADPCTRL_IDPULLUP, usb2_base + USB2_ADPCTRL); } - msleep(20); + mdelay(20); writel(0xffffffff, usb2_base + USB2_OBINTSTA); writel(ch->obint_enable_bits, usb2_base + USB2_OBINTEN); @@ -418,16 +429,27 @@ static irqreturn_t rcar_gen3_phy_usb2_irq(int irq, void *_ch) { struct rcar_gen3_chan *ch = _ch; void __iomem *usb2_base = ch->base; - u32 status = readl(usb2_base + USB2_OBINTSTA); + struct device *dev = ch->dev; irqreturn_t ret = IRQ_NONE; + u32 status; - if (status & ch->obint_enable_bits) { - dev_vdbg(ch->dev, "%s: %08x\n", __func__, status); - writel(ch->obint_enable_bits, usb2_base + USB2_OBINTSTA); - rcar_gen3_device_recognition(ch); - ret = IRQ_HANDLED; + pm_runtime_get_noresume(dev); + + if (pm_runtime_suspended(dev)) + goto rpm_put; + + scoped_guard(spinlock, &ch->lock) { + status = readl(usb2_base + USB2_OBINTSTA); + if (status & ch->obint_enable_bits) { + dev_vdbg(dev, "%s: %08x\n", __func__, status); + writel(ch->obint_enable_bits, usb2_base + USB2_OBINTSTA); + rcar_gen3_device_recognition(ch); + ret = IRQ_HANDLED; + } } +rpm_put: + pm_runtime_put_noidle(dev); return ret; } @@ -437,32 +459,23 @@ static int rcar_gen3_phy_usb2_init(struct phy *p) struct rcar_gen3_chan *channel = rphy->ch; void __iomem *usb2_base = channel->base; u32 val; - int ret; - if (!rcar_gen3_is_any_rphy_initialized(channel) && channel->irq >= 0) { - INIT_WORK(&channel->work, rcar_gen3_phy_usb2_work); - ret = request_irq(channel->irq, rcar_gen3_phy_usb2_irq, - IRQF_SHARED, dev_name(channel->dev), channel); - if (ret < 0) { - dev_err(channel->dev, "No irq handler (%d)\n", channel->irq); - return ret; - } - } + guard(spinlock_irqsave)(&channel->lock); /* Initialize USB2 part */ val = readl(usb2_base + USB2_INT_ENABLE); val |= USB2_INT_ENABLE_UCOM_INTEN | rphy->int_enable_bits; writel(val, usb2_base + USB2_INT_ENABLE); - writel(USB2_SPD_RSM_TIMSET_INIT, usb2_base + USB2_SPD_RSM_TIMSET); - writel(USB2_OC_TIMSET_INIT, usb2_base + USB2_OC_TIMSET); - /* Initialize otg part */ - if (channel->is_otg_channel) { - if (rcar_gen3_needs_init_otg(channel)) - rcar_gen3_init_otg(channel); - rphy->otg_initialized = true; + if (!rcar_gen3_is_any_rphy_initialized(channel)) { + writel(USB2_SPD_RSM_TIMSET_INIT, usb2_base + USB2_SPD_RSM_TIMSET); + writel(USB2_OC_TIMSET_INIT, usb2_base + USB2_OC_TIMSET); } + /* Initialize otg part (only if we initialize a PHY with IRQs). */ + if (rphy->int_enable_bits) + rcar_gen3_init_otg(channel); + rphy->initialized = true; return 0; @@ -475,10 +488,9 @@ static int rcar_gen3_phy_usb2_exit(struct phy *p) void __iomem *usb2_base = channel->base; u32 val; - rphy->initialized = false; + guard(spinlock_irqsave)(&channel->lock); - if (channel->is_otg_channel) - rphy->otg_initialized = false; + rphy->initialized = false; val = readl(usb2_base + USB2_INT_ENABLE); val &= ~rphy->int_enable_bits; @@ -486,9 +498,6 @@ static int rcar_gen3_phy_usb2_exit(struct phy *p) val &= ~USB2_INT_ENABLE_UCOM_INTEN; writel(val, usb2_base + USB2_INT_ENABLE); - if (channel->irq >= 0 && !rcar_gen3_is_any_rphy_initialized(channel)) - free_irq(channel->irq, channel); - return 0; } @@ -500,16 +509,17 @@ static int rcar_gen3_phy_usb2_power_on(struct phy *p) u32 val; int ret = 0; - mutex_lock(&channel->lock); - if (!rcar_gen3_are_all_rphys_power_off(channel)) - goto out; - if (channel->vbus) { ret = regulator_enable(channel->vbus); if (ret) - goto out; + return ret; } + guard(spinlock_irqsave)(&channel->lock); + + if (!rcar_gen3_are_all_rphys_power_off(channel)) + goto out; + val = readl(usb2_base + USB2_USBCTR); val |= USB2_USBCTR_PLL_RST; writel(val, usb2_base + USB2_USBCTR); @@ -519,7 +529,6 @@ static int rcar_gen3_phy_usb2_power_on(struct phy *p) out: /* The powered flag should be set for any other phys anyway */ rphy->powered = true; - mutex_unlock(&channel->lock); return 0; } @@ -530,18 +539,20 @@ static int rcar_gen3_phy_usb2_power_off(struct phy *p) struct rcar_gen3_chan *channel = rphy->ch; int ret = 0; - mutex_lock(&channel->lock); - rphy->powered = false; + scoped_guard(spinlock_irqsave, &channel->lock) { + rphy->powered = false; - if (!rcar_gen3_are_all_rphys_power_off(channel)) - goto out; + if (rcar_gen3_are_all_rphys_power_off(channel)) { + u32 val = readl(channel->base + USB2_USBCTR); + + val |= USB2_USBCTR_PLL_RST; + writel(val, channel->base + USB2_USBCTR); + } + } if (channel->vbus) ret = regulator_disable(channel->vbus); -out: - mutex_unlock(&channel->lock); - return ret; } @@ -649,13 +660,42 @@ static enum usb_dr_mode rcar_gen3_get_dr_mode(struct device_node *np) return candidate; } +static int rcar_gen3_phy_usb2_init_bus(struct rcar_gen3_chan *channel) +{ + struct device *dev = channel->dev; + int ret; + u32 val; + + channel->rstc = devm_reset_control_array_get_shared(dev); + if (IS_ERR(channel->rstc)) + return PTR_ERR(channel->rstc); + + ret = pm_runtime_resume_and_get(dev); + if (ret) + return ret; + + ret = reset_control_deassert(channel->rstc); + if (ret) + goto rpm_put; + + val = readl(channel->base + USB2_AHB_BUS_CTR); + val &= ~USB2_AHB_BUS_CTR_MBL_MASK; + val |= USB2_AHB_BUS_CTR_MBL_INCR4; + writel(val, channel->base + USB2_AHB_BUS_CTR); + +rpm_put: + pm_runtime_put(dev); + + return ret; +} + static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev) { const struct rcar_gen3_phy_drv_data *phy_data; struct device *dev = &pdev->dev; struct rcar_gen3_chan *channel; struct phy_provider *provider; - int ret = 0, i; + int ret = 0, i, irq; if (!dev->of_node) { dev_err(dev, "This driver needs device tree\n"); @@ -671,8 +711,6 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev) return PTR_ERR(channel->base); channel->obint_enable_bits = USB2_OBINT_BITS; - /* get irq number here and request_irq for OTG in phy_init */ - channel->irq = platform_get_irq_optional(pdev, 0); channel->dr_mode = rcar_gen3_get_dr_mode(dev->of_node); if (channel->dr_mode != USB_DR_MODE_UNKNOWN) { channel->is_otg_channel = true; @@ -702,11 +740,20 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev) goto error; } + platform_set_drvdata(pdev, channel); + channel->dev = dev; + + if (phy_data->init_bus) { + ret = rcar_gen3_phy_usb2_init_bus(channel); + if (ret) + goto error; + } + channel->soc_no_adp_ctrl = phy_data->no_adp_ctrl; if (phy_data->no_adp_ctrl) channel->obint_enable_bits = USB2_OBINT_IDCHG_EN; - mutex_init(&channel->lock); + spin_lock_init(&channel->lock); for (i = 0; i < NUM_OF_PHYS; i++) { channel->rphys[i].phy = devm_phy_create(dev, NULL, phy_data->phy_usb2_ops); @@ -729,8 +776,19 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev) channel->vbus = NULL; } - platform_set_drvdata(pdev, channel); - channel->dev = dev; + irq = platform_get_irq_optional(pdev, 0); + if (irq < 0 && irq != -ENXIO) { + ret = irq; + goto error; + } else if (irq > 0) { + INIT_WORK(&channel->work, rcar_gen3_phy_usb2_work); + ret = devm_request_irq(dev, irq, rcar_gen3_phy_usb2_irq, + IRQF_SHARED, dev_name(dev), channel); + if (ret < 0) { + dev_err(dev, "Failed to request irq (%d)\n", irq); + goto error; + } + } provider = devm_of_phy_provider_register(dev, rcar_gen3_phy_usb2_xlate); if (IS_ERR(provider)) { @@ -758,6 +816,7 @@ static int rcar_gen3_phy_usb2_remove(struct platform_device *pdev) if (channel->is_otg_channel) device_remove_file(&pdev->dev, &dev_attr_role); + reset_control_assert(channel->rstc); pm_runtime_disable(&pdev->dev); return 0; diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c index dc22b1dd2c8b..e3acd40e7cbc 100644 --- a/drivers/phy/tegra/xusb.c +++ b/drivers/phy/tegra/xusb.c @@ -542,16 +542,16 @@ static int tegra_xusb_port_init(struct tegra_xusb_port *port, err = dev_set_name(&port->dev, "%s-%u", name, index); if (err < 0) - goto unregister; + goto put_device; err = device_add(&port->dev); if (err < 0) - goto unregister; + goto put_device; return 0; -unregister: - device_unregister(&port->dev); +put_device: + put_device(&port->dev); return err; } diff --git a/drivers/pinctrl/bcm/pinctrl-bcm281xx.c b/drivers/pinctrl/bcm/pinctrl-bcm281xx.c index bba5496335ee..c313f0178957 100644 --- a/drivers/pinctrl/bcm/pinctrl-bcm281xx.c +++ b/drivers/pinctrl/bcm/pinctrl-bcm281xx.c @@ -69,7 +69,7 @@ static enum bcm281xx_pin_type hdmi_pin = BCM281XX_PIN_TYPE_HDMI; struct bcm281xx_pin_function { const char *name; const char * const *groups; - const unsigned ngroups; + const unsigned int ngroups; }; /* @@ -81,10 +81,10 @@ struct bcm281xx_pinctrl_data { /* List of all pins */ const struct pinctrl_pin_desc *pins; - const unsigned npins; + const unsigned int npins; const struct bcm281xx_pin_function *functions; - const unsigned nfunctions; + const unsigned int nfunctions; struct regmap *regmap; }; @@ -938,7 +938,7 @@ static struct bcm281xx_pinctrl_data bcm281xx_pinctrl = { }; static inline enum bcm281xx_pin_type pin_type_get(struct pinctrl_dev *pctldev, - unsigned pin) + unsigned int pin) { struct bcm281xx_pinctrl_data *pdata = pinctrl_dev_get_drvdata(pctldev); @@ -982,7 +982,7 @@ static int bcm281xx_pinctrl_get_groups_count(struct pinctrl_dev *pctldev) } static const char *bcm281xx_pinctrl_get_group_name(struct pinctrl_dev *pctldev, - unsigned group) + unsigned int group) { struct bcm281xx_pinctrl_data *pdata = pinctrl_dev_get_drvdata(pctldev); @@ -990,9 +990,9 @@ static const char *bcm281xx_pinctrl_get_group_name(struct pinctrl_dev *pctldev, } static int bcm281xx_pinctrl_get_group_pins(struct pinctrl_dev *pctldev, - unsigned group, + unsigned int group, const unsigned **pins, - unsigned *num_pins) + unsigned int *num_pins) { struct bcm281xx_pinctrl_data *pdata = pinctrl_dev_get_drvdata(pctldev); @@ -1004,7 +1004,7 @@ static int bcm281xx_pinctrl_get_group_pins(struct pinctrl_dev *pctldev, static void bcm281xx_pinctrl_pin_dbg_show(struct pinctrl_dev *pctldev, struct seq_file *s, - unsigned offset) + unsigned int offset) { seq_printf(s, " %s", dev_name(pctldev->dev)); } @@ -1026,7 +1026,7 @@ static int bcm281xx_pinctrl_get_fcns_count(struct pinctrl_dev *pctldev) } static const char *bcm281xx_pinctrl_get_fcn_name(struct pinctrl_dev *pctldev, - unsigned function) + unsigned int function) { struct bcm281xx_pinctrl_data *pdata = pinctrl_dev_get_drvdata(pctldev); @@ -1034,9 +1034,9 @@ static const char *bcm281xx_pinctrl_get_fcn_name(struct pinctrl_dev *pctldev, } static int bcm281xx_pinctrl_get_fcn_groups(struct pinctrl_dev *pctldev, - unsigned function, + unsigned int function, const char * const **groups, - unsigned * const num_groups) + unsigned int * const num_groups) { struct bcm281xx_pinctrl_data *pdata = pinctrl_dev_get_drvdata(pctldev); @@ -1047,8 +1047,8 @@ static int bcm281xx_pinctrl_get_fcn_groups(struct pinctrl_dev *pctldev, } static int bcm281xx_pinmux_set(struct pinctrl_dev *pctldev, - unsigned function, - unsigned group) + unsigned int function, + unsigned int group) { struct bcm281xx_pinctrl_data *pdata = pinctrl_dev_get_drvdata(pctldev); const struct bcm281xx_pin_function *f = &pdata->functions[function]; @@ -1079,7 +1079,7 @@ static const struct pinmux_ops bcm281xx_pinctrl_pinmux_ops = { }; static int bcm281xx_pinctrl_pin_config_get(struct pinctrl_dev *pctldev, - unsigned pin, + unsigned int pin, unsigned long *config) { return -ENOTSUPP; @@ -1088,9 +1088,9 @@ static int bcm281xx_pinctrl_pin_config_get(struct pinctrl_dev *pctldev, /* Goes through the configs and update register val/mask */ static int bcm281xx_std_pin_update(struct pinctrl_dev *pctldev, - unsigned pin, + unsigned int pin, unsigned long *configs, - unsigned num_configs, + unsigned int num_configs, u32 *val, u32 *mask) { @@ -1204,9 +1204,9 @@ static const u16 bcm281xx_pullup_map[] = { /* Goes through the configs and update register val/mask */ static int bcm281xx_i2c_pin_update(struct pinctrl_dev *pctldev, - unsigned pin, + unsigned int pin, unsigned long *configs, - unsigned num_configs, + unsigned int num_configs, u32 *val, u32 *mask) { @@ -1274,9 +1274,9 @@ static int bcm281xx_i2c_pin_update(struct pinctrl_dev *pctldev, /* Goes through the configs and update register val/mask */ static int bcm281xx_hdmi_pin_update(struct pinctrl_dev *pctldev, - unsigned pin, + unsigned int pin, unsigned long *configs, - unsigned num_configs, + unsigned int num_configs, u32 *val, u32 *mask) { @@ -1318,9 +1318,9 @@ static int bcm281xx_hdmi_pin_update(struct pinctrl_dev *pctldev, } static int bcm281xx_pinctrl_pin_config_set(struct pinctrl_dev *pctldev, - unsigned pin, + unsigned int pin, unsigned long *configs, - unsigned num_configs) + unsigned int num_configs) { struct bcm281xx_pinctrl_data *pdata = pinctrl_dev_get_drvdata(pctldev); enum bcm281xx_pin_type pin_type; diff --git a/drivers/pinctrl/devicetree.c b/drivers/pinctrl/devicetree.c index 5ee746cb81f5..6520b88db110 100644 --- a/drivers/pinctrl/devicetree.c +++ b/drivers/pinctrl/devicetree.c @@ -143,10 +143,14 @@ static int dt_to_map_one_config(struct pinctrl *p, pctldev = get_pinctrl_dev_from_of_node(np_pctldev); if (pctldev) break; - /* Do not defer probing of hogs (circular loop) */ + /* + * Do not defer probing of hogs (circular loop) + * + * Return 1 to let the caller catch the case. + */ if (np_pctldev == p->dev->of_node) { of_node_put(np_pctldev); - return -ENODEV; + return 1; } } of_node_put(np_pctldev); @@ -265,6 +269,8 @@ int pinctrl_dt_to_map(struct pinctrl *p, struct pinctrl_dev *pctldev) ret = dt_to_map_one_config(p, pctldev, statename, np_config); of_node_put(np_config); + if (ret == 1) + continue; if (ret < 0) goto err; } diff --git a/drivers/pinctrl/meson/pinctrl-meson.c b/drivers/pinctrl/meson/pinctrl-meson.c index 530f3f934e19..1f05f7f1a9ae 100644 --- a/drivers/pinctrl/meson/pinctrl-meson.c +++ b/drivers/pinctrl/meson/pinctrl-meson.c @@ -487,7 +487,7 @@ static int meson_pinconf_get(struct pinctrl_dev *pcdev, unsigned int pin, case PIN_CONFIG_BIAS_PULL_DOWN: case PIN_CONFIG_BIAS_PULL_UP: if (meson_pinconf_get_pull(pc, pin) == param) - arg = 1; + arg = 60000; else return -EINVAL; break; diff --git a/drivers/pinctrl/tegra/pinctrl-tegra.c b/drivers/pinctrl/tegra/pinctrl-tegra.c index 30341c43da59..78de32666d56 100644 --- a/drivers/pinctrl/tegra/pinctrl-tegra.c +++ b/drivers/pinctrl/tegra/pinctrl-tegra.c @@ -278,8 +278,8 @@ static int tegra_pinctrl_set_mux(struct pinctrl_dev *pctldev, return 0; } -static const struct tegra_pingroup *tegra_pinctrl_get_group(struct pinctrl_dev *pctldev, - unsigned int offset) +static int tegra_pinctrl_get_group_index(struct pinctrl_dev *pctldev, + unsigned int offset) { struct tegra_pmx *pmx = pinctrl_dev_get_drvdata(pctldev); unsigned int group, num_pins, j; @@ -292,12 +292,35 @@ static const struct tegra_pingroup *tegra_pinctrl_get_group(struct pinctrl_dev * continue; for (j = 0; j < num_pins; j++) { if (offset == pins[j]) - return &pmx->soc->groups[group]; + return group; } } - dev_err(pctldev->dev, "Pingroup not found for pin %u\n", offset); - return NULL; + return -EINVAL; +} + +static const struct tegra_pingroup *tegra_pinctrl_get_group(struct pinctrl_dev *pctldev, + unsigned int offset, + int group_index) +{ + struct tegra_pmx *pmx = pinctrl_dev_get_drvdata(pctldev); + + if (group_index < 0 || group_index >= pmx->soc->ngroups) + return NULL; + + return &pmx->soc->groups[group_index]; +} + +static struct tegra_pingroup_config *tegra_pinctrl_get_group_config(struct pinctrl_dev *pctldev, + unsigned int offset, + int group_index) +{ + struct tegra_pmx *pmx = pinctrl_dev_get_drvdata(pctldev); + + if (group_index < 0) + return NULL; + + return &pmx->pingroup_configs[group_index]; } static int tegra_pinctrl_gpio_request_enable(struct pinctrl_dev *pctldev, @@ -306,12 +329,15 @@ static int tegra_pinctrl_gpio_request_enable(struct pinctrl_dev *pctldev, { struct tegra_pmx *pmx = pinctrl_dev_get_drvdata(pctldev); const struct tegra_pingroup *group; + struct tegra_pingroup_config *config; + int group_index; u32 value; if (!pmx->soc->sfsel_in_mux) return 0; - group = tegra_pinctrl_get_group(pctldev, offset); + group_index = tegra_pinctrl_get_group_index(pctldev, offset); + group = tegra_pinctrl_get_group(pctldev, offset, group_index); if (!group) return -EINVAL; @@ -319,7 +345,11 @@ static int tegra_pinctrl_gpio_request_enable(struct pinctrl_dev *pctldev, if (group->mux_reg < 0 || group->sfsel_bit < 0) return -EINVAL; + config = tegra_pinctrl_get_group_config(pctldev, offset, group_index); + if (!config) + return -EINVAL; value = pmx_readl(pmx, group->mux_bank, group->mux_reg); + config->is_sfsel = (value & BIT(group->sfsel_bit)) != 0; value &= ~BIT(group->sfsel_bit); pmx_writel(pmx, value, group->mux_bank, group->mux_reg); @@ -332,12 +362,15 @@ static void tegra_pinctrl_gpio_disable_free(struct pinctrl_dev *pctldev, { struct tegra_pmx *pmx = pinctrl_dev_get_drvdata(pctldev); const struct tegra_pingroup *group; + struct tegra_pingroup_config *config; + int group_index; u32 value; if (!pmx->soc->sfsel_in_mux) return; - group = tegra_pinctrl_get_group(pctldev, offset); + group_index = tegra_pinctrl_get_group_index(pctldev, offset); + group = tegra_pinctrl_get_group(pctldev, offset, group_index); if (!group) return; @@ -345,8 +378,12 @@ static void tegra_pinctrl_gpio_disable_free(struct pinctrl_dev *pctldev, if (group->mux_reg < 0 || group->sfsel_bit < 0) return; + config = tegra_pinctrl_get_group_config(pctldev, offset, group_index); + if (!config) + return; value = pmx_readl(pmx, group->mux_bank, group->mux_reg); - value |= BIT(group->sfsel_bit); + if (config->is_sfsel) + value |= BIT(group->sfsel_bit); pmx_writel(pmx, value, group->mux_bank, group->mux_reg); } @@ -799,6 +836,12 @@ int tegra_pinctrl_probe(struct platform_device *pdev, pmx->dev = &pdev->dev; pmx->soc = soc_data; + pmx->pingroup_configs = devm_kcalloc(&pdev->dev, + pmx->soc->ngroups, sizeof(*pmx->pingroup_configs), + GFP_KERNEL); + if (!pmx->pingroup_configs) + return -ENOMEM; + /* * Each mux group will appear in 4 functions' list of groups. * This over-allocates slightly, since not all groups are mux groups. diff --git a/drivers/pinctrl/tegra/pinctrl-tegra.h b/drivers/pinctrl/tegra/pinctrl-tegra.h index f8269858eb78..ec5198d391ea 100644 --- a/drivers/pinctrl/tegra/pinctrl-tegra.h +++ b/drivers/pinctrl/tegra/pinctrl-tegra.h @@ -8,6 +8,10 @@ #ifndef __PINMUX_TEGRA_H__ #define __PINMUX_TEGRA_H__ +struct tegra_pingroup_config { + bool is_sfsel; +}; + struct tegra_pmx { struct device *dev; struct pinctrl_dev *pctl; @@ -18,6 +22,8 @@ struct tegra_pmx { int nbanks; void __iomem **regs; u32 *backup_regs; + /* Array of size soc->ngroups */ + struct tegra_pingroup_config *pingroup_configs; }; enum tegra_pinconf_param { diff --git a/drivers/platform/x86/amd/pmc.c b/drivers/platform/x86/amd/pmc.c index f237c1ea8d35..8eaeb1e8f975 100644 --- a/drivers/platform/x86/amd/pmc.c +++ b/drivers/platform/x86/amd/pmc.c @@ -834,6 +834,10 @@ static int __maybe_unused amd_pmc_suspend_handler(struct device *dev) { struct amd_pmc_dev *pdev = dev_get_drvdata(dev); + /* + * Must be called only from the same set of dev_pm_ops handlers + * as i8042_pm_suspend() is called: currently just from .suspend. + */ if (pdev->cpu_id == AMD_CPU_ID_CZN) { int rc = amd_pmc_czn_wa_irq1(pdev); @@ -846,7 +850,9 @@ static int __maybe_unused amd_pmc_suspend_handler(struct device *dev) return 0; } -static SIMPLE_DEV_PM_OPS(amd_pmc_pm, amd_pmc_suspend_handler, NULL); +static const struct dev_pm_ops amd_pmc_pm = { + .suspend = amd_pmc_suspend_handler, +}; #endif diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 296150eaef92..33eacb4fc4c4 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -3804,7 +3804,8 @@ static int asus_wmi_add(struct platform_device *pdev) goto fail_leds; asus_wmi_get_devstate(asus, ASUS_WMI_DEVID_WLAN, &result); - if (result & (ASUS_WMI_DSTS_PRESENCE_BIT | ASUS_WMI_DSTS_USER_BIT)) + if ((result & (ASUS_WMI_DSTS_PRESENCE_BIT | ASUS_WMI_DSTS_USER_BIT)) == + (ASUS_WMI_DSTS_PRESENCE_BIT | ASUS_WMI_DSTS_USER_BIT)) asus->driver->wlan_ctrl_by_user = 1; if (!(asus->driver->wlan_ctrl_by_user && ashs_present())) { diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c b/drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c index 230e6ee96636..d8f1bf5e58a0 100644 --- a/drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c +++ b/drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c @@ -45,7 +45,7 @@ static ssize_t current_password_store(struct kobject *kobj, int length; length = strlen(buf); - if (buf[length-1] == '\n') + if (length && buf[length - 1] == '\n') length--; /* firmware does verifiation of min/max password length, diff --git a/drivers/platform/x86/fujitsu-laptop.c b/drivers/platform/x86/fujitsu-laptop.c index b543d117b12c..259eb2a2858f 100644 --- a/drivers/platform/x86/fujitsu-laptop.c +++ b/drivers/platform/x86/fujitsu-laptop.c @@ -17,13 +17,13 @@ /* * fujitsu-laptop.c - Fujitsu laptop support, providing access to additional * features made available on a range of Fujitsu laptops including the - * P2xxx/P5xxx/S6xxx/S7xxx series. + * P2xxx/P5xxx/S2xxx/S6xxx/S7xxx series. * * This driver implements a vendor-specific backlight control interface for * Fujitsu laptops and provides support for hotkeys present on certain Fujitsu * laptops. * - * This driver has been tested on a Fujitsu Lifebook S6410, S7020 and + * This driver has been tested on a Fujitsu Lifebook S2110, S6410, S7020 and * P8010. It should work on most P-series and S-series Lifebooks, but * YMMV. * @@ -102,7 +102,11 @@ #define KEY2_CODE 0x411 #define KEY3_CODE 0x412 #define KEY4_CODE 0x413 -#define KEY5_CODE 0x420 +#define KEY5_CODE 0x414 +#define KEY6_CODE 0x415 +#define KEY7_CODE 0x416 +#define KEY8_CODE 0x417 +#define KEY9_CODE 0x420 /* Hotkey ringbuffer limits */ #define MAX_HOTKEY_RINGBUFFER_SIZE 100 @@ -450,7 +454,7 @@ static const struct key_entry keymap_default[] = { { KE_KEY, KEY2_CODE, { KEY_PROG2 } }, { KE_KEY, KEY3_CODE, { KEY_PROG3 } }, { KE_KEY, KEY4_CODE, { KEY_PROG4 } }, - { KE_KEY, KEY5_CODE, { KEY_RFKILL } }, + { KE_KEY, KEY9_CODE, { KEY_RFKILL } }, /* Soft keys read from status flags */ { KE_KEY, FLAG_RFKILL, { KEY_RFKILL } }, { KE_KEY, FLAG_TOUCHPAD_TOGGLE, { KEY_TOUCHPAD_TOGGLE } }, @@ -474,6 +478,18 @@ static const struct key_entry keymap_p8010[] = { { KE_END, 0 } }; +static const struct key_entry keymap_s2110[] = { + { KE_KEY, KEY1_CODE, { KEY_PROG1 } }, /* "A" */ + { KE_KEY, KEY2_CODE, { KEY_PROG2 } }, /* "B" */ + { KE_KEY, KEY3_CODE, { KEY_WWW } }, /* "Internet" */ + { KE_KEY, KEY4_CODE, { KEY_EMAIL } }, /* "E-mail" */ + { KE_KEY, KEY5_CODE, { KEY_STOPCD } }, + { KE_KEY, KEY6_CODE, { KEY_PLAYPAUSE } }, + { KE_KEY, KEY7_CODE, { KEY_PREVIOUSSONG } }, + { KE_KEY, KEY8_CODE, { KEY_NEXTSONG } }, + { KE_END, 0 } +}; + static const struct key_entry *keymap = keymap_default; static int fujitsu_laptop_dmi_keymap_override(const struct dmi_system_id *id) @@ -511,6 +527,15 @@ static const struct dmi_system_id fujitsu_laptop_dmi_table[] = { }, .driver_data = (void *)keymap_p8010 }, + { + .callback = fujitsu_laptop_dmi_keymap_override, + .ident = "Fujitsu LifeBook S2110", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK S2110"), + }, + .driver_data = (void *)keymap_s2110 + }, {} }; diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 26ca9c453a59..17d74434e604 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -211,6 +211,7 @@ enum tpacpi_hkey_event_t { /* Thermal events */ TP_HKEY_EV_ALARM_BAT_HOT = 0x6011, /* battery too hot */ TP_HKEY_EV_ALARM_BAT_XHOT = 0x6012, /* battery critically hot */ + TP_HKEY_EV_ALARM_BAT_LIM_CHANGE = 0x6013, /* battery charge limit changed*/ TP_HKEY_EV_ALARM_SENSOR_HOT = 0x6021, /* sensor too hot */ TP_HKEY_EV_ALARM_SENSOR_XHOT = 0x6022, /* sensor critically hot */ TP_HKEY_EV_THM_TABLE_CHANGED = 0x6030, /* windows; thermal table changed */ @@ -3948,6 +3949,10 @@ static bool hotkey_notify_6xxx(const u32 hkey, pr_alert("THERMAL EMERGENCY: battery is extremely hot!\n"); /* recommended action: immediate sleep/hibernate */ break; + case TP_HKEY_EV_ALARM_BAT_LIM_CHANGE: + pr_debug("Battery Info: battery charge threshold changed\n"); + /* User changed charging threshold. No action needed */ + return true; case TP_HKEY_EV_ALARM_SENSOR_HOT: pr_crit("THERMAL ALARM: a sensor reports something is too hot!\n"); /* recommended action: warn user through gui, that */ @@ -11517,6 +11522,8 @@ static int __must_check __init get_thinkpad_model_data( tp->vendor = PCI_VENDOR_ID_IBM; else if (dmi_name_in_vendors("LENOVO")) tp->vendor = PCI_VENDOR_ID_LENOVO; + else if (dmi_name_in_vendors("NEC")) + tp->vendor = PCI_VENDOR_ID_LENOVO; else return 0; diff --git a/drivers/regulator/ad5398.c b/drivers/regulator/ad5398.c index 75f432f61e91..f4d6e62bd963 100644 --- a/drivers/regulator/ad5398.c +++ b/drivers/regulator/ad5398.c @@ -14,6 +14,7 @@ #include #include #include +#include #define AD5398_CURRENT_EN_MASK 0x8000 @@ -221,15 +222,20 @@ static int ad5398_probe(struct i2c_client *client, const struct ad5398_current_data_format *df = (struct ad5398_current_data_format *)id->driver_data; - if (!init_data) - return -EINVAL; - chip = devm_kzalloc(&client->dev, sizeof(*chip), GFP_KERNEL); if (!chip) return -ENOMEM; config.dev = &client->dev; + if (client->dev.of_node) + init_data = of_get_regulator_init_data(&client->dev, + client->dev.of_node, + &ad5398_reg); + if (!init_data) + return -EINVAL; + config.init_data = init_data; + config.of_node = client->dev.of_node; config.driver_data = chip; chip->client = client; diff --git a/drivers/regulator/max20086-regulator.c b/drivers/regulator/max20086-regulator.c index b8bf76c170fe..332fb58f9095 100644 --- a/drivers/regulator/max20086-regulator.c +++ b/drivers/regulator/max20086-regulator.c @@ -133,7 +133,7 @@ static int max20086_regulators_register(struct max20086 *chip) static int max20086_parse_regulators_dt(struct max20086 *chip, bool *boot_on) { - struct of_regulator_match matches[MAX20086_MAX_REGULATORS] = { }; + struct of_regulator_match *matches; struct device_node *node; unsigned int i; int ret; @@ -144,6 +144,11 @@ static int max20086_parse_regulators_dt(struct max20086 *chip, bool *boot_on) return -ENODEV; } + matches = devm_kcalloc(chip->dev, chip->info->num_outputs, + sizeof(*matches), GFP_KERNEL); + if (!matches) + return -ENOMEM; + for (i = 0; i < chip->info->num_outputs; ++i) matches[i].name = max20086_output_names[i]; diff --git a/drivers/remoteproc/qcom_wcnss.c b/drivers/remoteproc/qcom_wcnss.c index 68f37296b151..af96541c9b69 100644 --- a/drivers/remoteproc/qcom_wcnss.c +++ b/drivers/remoteproc/qcom_wcnss.c @@ -117,10 +117,10 @@ static const struct wcnss_data pronto_v1_data = { .pmu_offset = 0x1004, .spare_offset = 0x1088, - .pd_names = { "mx", "cx" }, + .pd_names = { "cx", "mx" }, .vregs = (struct wcnss_vreg_info[]) { - { "vddmx", 950000, 1150000, 0 }, { "vddcx", .super_turbo = true}, + { "vddmx", 950000, 1150000, 0 }, { "vddpx", 1800000, 1800000, 0 }, }, .num_pd_vregs = 2, @@ -131,10 +131,10 @@ static const struct wcnss_data pronto_v2_data = { .pmu_offset = 0x1004, .spare_offset = 0x1088, - .pd_names = { "mx", "cx" }, + .pd_names = { "cx", "mx" }, .vregs = (struct wcnss_vreg_info[]) { - { "vddmx", 1287500, 1287500, 0 }, { "vddcx", .super_turbo = true }, + { "vddmx", 1287500, 1287500, 0 }, { "vddpx", 1800000, 1800000, 0 }, }, .num_pd_vregs = 2, @@ -386,8 +386,17 @@ static irqreturn_t wcnss_stop_ack_interrupt(int irq, void *dev) static int wcnss_init_pds(struct qcom_wcnss *wcnss, const char * const pd_names[WCNSS_MAX_PDS]) { + struct device *dev = wcnss->dev; int i, ret; + /* Handle single power domain */ + if (dev->pm_domain) { + wcnss->pds[0] = dev; + wcnss->num_pds = 1; + pm_runtime_enable(dev); + return 0; + } + for (i = 0; i < WCNSS_MAX_PDS; i++) { if (!pd_names[i]) break; @@ -407,8 +416,15 @@ static int wcnss_init_pds(struct qcom_wcnss *wcnss, static void wcnss_release_pds(struct qcom_wcnss *wcnss) { + struct device *dev = wcnss->dev; int i; + /* Handle single power domain */ + if (wcnss->num_pds == 1 && dev->pm_domain) { + pm_runtime_disable(dev); + return; + } + for (i = 0; i < wcnss->num_pds; i++) dev_pm_domain_detach(wcnss->pds[i], false); } @@ -426,10 +442,14 @@ static int wcnss_init_regulators(struct qcom_wcnss *wcnss, * the regulators for the power domains. For old device trees we need to * reserve extra space to manage them through the regulator interface. */ - if (wcnss->num_pds) - info += num_pd_vregs; - else + if (wcnss->num_pds) { + info += wcnss->num_pds; + /* Handle single power domain case */ + if (wcnss->num_pds < num_pd_vregs) + num_vregs += num_pd_vregs - wcnss->num_pds; + } else { num_vregs += num_pd_vregs; + } bulk = devm_kcalloc(wcnss->dev, num_vregs, sizeof(struct regulator_bulk_data), diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c index d51565bcc189..b7f8b3f9b059 100644 --- a/drivers/rtc/rtc-ds1307.c +++ b/drivers/rtc/rtc-ds1307.c @@ -1802,10 +1802,8 @@ static int ds1307_probe(struct i2c_client *client, * For some variants, be sure alarms can trigger when we're * running on Vbackup (BBSQI/BBSQW) */ - if (want_irq || ds1307_can_wakeup_device) { + if (want_irq || ds1307_can_wakeup_device) regs[0] |= DS1337_BIT_INTCN | chip->bbsqi_bit; - regs[0] &= ~(DS1337_BIT_A2IE | DS1337_BIT_A1IE); - } regmap_write(ds1307->regmap, DS1337_REG_CONTROL, regs[0]); diff --git a/drivers/rtc/rtc-rv3032.c b/drivers/rtc/rtc-rv3032.c index c3bee305eacc..9c85ecd9afb8 100644 --- a/drivers/rtc/rtc-rv3032.c +++ b/drivers/rtc/rtc-rv3032.c @@ -69,7 +69,7 @@ #define RV3032_CLKOUT2_FD_MSK GENMASK(6, 5) #define RV3032_CLKOUT2_OS BIT(7) -#define RV3032_CTRL1_EERD BIT(3) +#define RV3032_CTRL1_EERD BIT(2) #define RV3032_CTRL1_WADA BIT(5) #define RV3032_CTRL2_STOP BIT(0) diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c index 86a8bd532489..11fe917fbd9d 100644 --- a/drivers/s390/crypto/vfio_ap_ops.c +++ b/drivers/s390/crypto/vfio_ap_ops.c @@ -789,48 +789,66 @@ static void vfio_ap_mdev_remove(struct mdev_device *mdev) vfio_put_device(&matrix_mdev->vdev); } -#define MDEV_SHARING_ERR "Userspace may not re-assign queue %02lx.%04lx " \ - "already assigned to %s" +#define MDEV_SHARING_ERR "Userspace may not assign queue %02lx.%04lx to mdev: already assigned to %s" -static void vfio_ap_mdev_log_sharing_err(struct ap_matrix_mdev *matrix_mdev, - unsigned long *apm, - unsigned long *aqm) +#define MDEV_IN_USE_ERR "Can not reserve queue %02lx.%04lx for host driver: in use by mdev" + +static void vfio_ap_mdev_log_sharing_err(struct ap_matrix_mdev *assignee, + struct ap_matrix_mdev *assigned_to, + unsigned long *apm, unsigned long *aqm) { unsigned long apid, apqi; - const struct device *dev = mdev_dev(matrix_mdev->mdev); - const char *mdev_name = dev_name(dev); - for_each_set_bit_inv(apid, apm, AP_DEVICES) + for_each_set_bit_inv(apid, apm, AP_DEVICES) { + for_each_set_bit_inv(apqi, aqm, AP_DOMAINS) { + dev_warn(mdev_dev(assignee->mdev), MDEV_SHARING_ERR, + apid, apqi, dev_name(mdev_dev(assigned_to->mdev))); + } + } +} + +static void vfio_ap_mdev_log_in_use_err(struct ap_matrix_mdev *assignee, + unsigned long *apm, unsigned long *aqm) +{ + unsigned long apid, apqi; + + for_each_set_bit_inv(apid, apm, AP_DEVICES) { for_each_set_bit_inv(apqi, aqm, AP_DOMAINS) - dev_warn(dev, MDEV_SHARING_ERR, apid, apqi, mdev_name); + dev_warn(mdev_dev(assignee->mdev), MDEV_IN_USE_ERR, apid, apqi); + } } /** * vfio_ap_mdev_verify_no_sharing - verify APQNs are not shared by matrix mdevs * + * @assignee: the matrix mdev to which @mdev_apm and @mdev_aqm are being + * assigned; or, NULL if this function was called by the AP bus + * driver in_use callback to verify none of the APQNs being reserved + * for the host device driver are in use by a vfio_ap mediated device * @mdev_apm: mask indicating the APIDs of the APQNs to be verified * @mdev_aqm: mask indicating the APQIs of the APQNs to be verified * - * Verifies that each APQN derived from the Cartesian product of a bitmap of - * AP adapter IDs and AP queue indexes is not configured for any matrix - * mediated device. AP queue sharing is not allowed. + * Verifies that each APQN derived from the Cartesian product of APIDs + * represented by the bits set in @mdev_apm and the APQIs of the bits set in + * @mdev_aqm is not assigned to a mediated device other than the mdev to which + * the APQN is being assigned (@assignee). AP queue sharing is not allowed. * * Return: 0 if the APQNs are not shared; otherwise return -EADDRINUSE. */ -static int vfio_ap_mdev_verify_no_sharing(unsigned long *mdev_apm, +static int vfio_ap_mdev_verify_no_sharing(struct ap_matrix_mdev *assignee, + unsigned long *mdev_apm, unsigned long *mdev_aqm) { - struct ap_matrix_mdev *matrix_mdev; + struct ap_matrix_mdev *assigned_to; DECLARE_BITMAP(apm, AP_DEVICES); DECLARE_BITMAP(aqm, AP_DOMAINS); - list_for_each_entry(matrix_mdev, &matrix_dev->mdev_list, node) { + list_for_each_entry(assigned_to, &matrix_dev->mdev_list, node) { /* - * If the input apm and aqm are fields of the matrix_mdev - * object, then move on to the next matrix_mdev. + * If the mdev to which the mdev_apm and mdev_aqm is being + * assigned is the same as the mdev being verified */ - if (mdev_apm == matrix_mdev->matrix.apm && - mdev_aqm == matrix_mdev->matrix.aqm) + if (assignee == assigned_to) continue; memset(apm, 0, sizeof(apm)); @@ -840,15 +858,16 @@ static int vfio_ap_mdev_verify_no_sharing(unsigned long *mdev_apm, * We work on full longs, as we can only exclude the leftover * bits in non-inverse order. The leftover is all zeros. */ - if (!bitmap_and(apm, mdev_apm, matrix_mdev->matrix.apm, - AP_DEVICES)) + if (!bitmap_and(apm, mdev_apm, assigned_to->matrix.apm, AP_DEVICES)) continue; - if (!bitmap_and(aqm, mdev_aqm, matrix_mdev->matrix.aqm, - AP_DOMAINS)) + if (!bitmap_and(aqm, mdev_aqm, assigned_to->matrix.aqm, AP_DOMAINS)) continue; - vfio_ap_mdev_log_sharing_err(matrix_mdev, apm, aqm); + if (assignee) + vfio_ap_mdev_log_sharing_err(assignee, assigned_to, apm, aqm); + else + vfio_ap_mdev_log_in_use_err(assigned_to, apm, aqm); return -EADDRINUSE; } @@ -877,7 +896,8 @@ static int vfio_ap_mdev_validate_masks(struct ap_matrix_mdev *matrix_mdev) matrix_mdev->matrix.aqm)) return -EADDRNOTAVAIL; - return vfio_ap_mdev_verify_no_sharing(matrix_mdev->matrix.apm, + return vfio_ap_mdev_verify_no_sharing(matrix_mdev, + matrix_mdev->matrix.apm, matrix_mdev->matrix.aqm); } @@ -1945,7 +1965,7 @@ int vfio_ap_mdev_resource_in_use(unsigned long *apm, unsigned long *aqm) mutex_lock(&matrix_dev->guests_lock); mutex_lock(&matrix_dev->mdevs_lock); - ret = vfio_ap_mdev_verify_no_sharing(apm, aqm); + ret = vfio_ap_mdev_verify_no_sharing(NULL, apm, aqm); mutex_unlock(&matrix_dev->mdevs_lock); mutex_unlock(&matrix_dev->guests_lock); diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index 57be02f8d5c1..b04112c77fcd 100644 --- a/drivers/scsi/lpfc/lpfc_hbadisc.c +++ b/drivers/scsi/lpfc/lpfc_hbadisc.c @@ -5619,6 +5619,7 @@ static struct lpfc_nodelist * __lpfc_findnode_did(struct lpfc_vport *vport, uint32_t did) { struct lpfc_nodelist *ndlp; + struct lpfc_nodelist *np = NULL; uint32_t data1; list_for_each_entry(ndlp, &vport->fc_nodes, nlp_listp) { @@ -5633,14 +5634,20 @@ __lpfc_findnode_did(struct lpfc_vport *vport, uint32_t did) ndlp, ndlp->nlp_DID, ndlp->nlp_flag, data1, ndlp->nlp_rpi, ndlp->active_rrqs_xri_bitmap); - return ndlp; + + /* Check for new or potentially stale node */ + if (ndlp->nlp_state != NLP_STE_UNUSED_NODE) + return ndlp; + np = ndlp; } } - /* FIND node did NOT FOUND */ - lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE, - "0932 FIND node did x%x NOT FOUND.\n", did); - return NULL; + if (!np) + /* FIND node did NOT FOUND */ + lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE, + "0932 FIND node did x%x NOT FOUND.\n", did); + + return np; } struct lpfc_nodelist * diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 1a0bafde34d8..97f3c5240d57 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -13204,6 +13204,7 @@ lpfc_sli4_enable_msi(struct lpfc_hba *phba) eqhdl = lpfc_get_eq_hdl(0); rc = pci_irq_vector(phba->pcidev, 0); if (rc < 0) { + free_irq(phba->pcidev->irq, phba); pci_free_irq_vectors(phba->pcidev); lpfc_printf_log(phba, KERN_WARNING, LOG_INIT, "0496 MSI pci_irq_vec failed (%d)\n", rc); @@ -13284,6 +13285,7 @@ lpfc_sli4_enable_intr(struct lpfc_hba *phba, uint32_t cfg_mode) eqhdl = lpfc_get_eq_hdl(0); retval = pci_irq_vector(phba->pcidev, 0); if (retval < 0) { + free_irq(phba->pcidev->irq, phba); lpfc_printf_log(phba, KERN_WARNING, LOG_INIT, "0502 INTR pci_irq_vec failed (%d)\n", retval); diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c index 41636c4c43af..015a875a46a1 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_fw.c +++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c @@ -174,6 +174,9 @@ static void mpi3mr_print_event_data(struct mpi3mr_ioc *mrioc, char *desc = NULL; u16 event; + if (!(mrioc->logging_level & MPI3_DEBUG_EVENT)) + return; + event = event_reply->event; switch (event) { diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c index fc5af6a5114e..863503e8a4d1 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c +++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c @@ -679,6 +679,7 @@ _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg, size_t data_in_sz = 0; long ret; u16 device_handle = MPT3SAS_INVALID_DEVICE_HANDLE; + int tm_ret; issue_reset = 0; @@ -1120,18 +1121,25 @@ _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg, if (pcie_device && (!ioc->tm_custom_handling) && (!(mpt3sas_scsih_is_pcie_scsi_device( pcie_device->device_info)))) - mpt3sas_scsih_issue_locked_tm(ioc, + tm_ret = mpt3sas_scsih_issue_locked_tm(ioc, le16_to_cpu(mpi_request->FunctionDependent1), 0, 0, 0, MPI2_SCSITASKMGMT_TASKTYPE_TARGET_RESET, 0, 0, pcie_device->reset_timeout, MPI26_SCSITASKMGMT_MSGFLAGS_PROTOCOL_LVL_RST_PCIE); else - mpt3sas_scsih_issue_locked_tm(ioc, + tm_ret = mpt3sas_scsih_issue_locked_tm(ioc, le16_to_cpu(mpi_request->FunctionDependent1), 0, 0, 0, MPI2_SCSITASKMGMT_TASKTYPE_TARGET_RESET, 0, 0, 30, MPI2_SCSITASKMGMT_MSGFLAGS_LINK_RESET); + + if (tm_ret != SUCCESS) { + ioc_info(ioc, + "target reset failed, issue hard reset: handle (0x%04x)\n", + le16_to_cpu(mpi_request->FunctionDependent1)); + mpt3sas_base_hard_reset_handler(ioc, FORCE_BIG_HAMMER); + } } else mpt3sas_base_hard_reset_handler(ioc, FORCE_BIG_HAMMER); } diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index 4321bc1fe5c0..d86bcd1ccd76 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -199,6 +199,7 @@ static void *sd_zbc_alloc_report_buffer(struct scsi_disk *sdkp, unsigned int nr_zones, size_t *buflen) { struct request_queue *q = sdkp->disk->queue; + unsigned int max_segments; size_t bufsize; void *buf; @@ -210,12 +211,15 @@ static void *sd_zbc_alloc_report_buffer(struct scsi_disk *sdkp, * Furthermore, since the report zone command cannot be split, make * sure that the allocated buffer can always be mapped by limiting the * number of pages allocated to the HBA max segments limit. + * Since max segments can be larger than the max inline bio vectors, + * further limit the allocated buffer to BIO_MAX_INLINE_VECS. */ nr_zones = min(nr_zones, sdkp->zone_info.nr_zones); bufsize = roundup((nr_zones + 1) * 64, SECTOR_SIZE); bufsize = min_t(size_t, bufsize, queue_max_hw_sectors(q) << SECTOR_SHIFT); - bufsize = min_t(size_t, bufsize, queue_max_segments(q) << PAGE_SHIFT); + max_segments = min(BIO_MAX_INLINE_VECS, queue_max_segments(q)); + bufsize = min_t(size_t, bufsize, max_segments << PAGE_SHIFT); while (bufsize >= SECTOR_SIZE) { buf = kvzalloc(bufsize, GFP_KERNEL | __GFP_NORETRY); diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c index 7f107be34423..9ba5ad106b65 100644 --- a/drivers/scsi/st.c +++ b/drivers/scsi/st.c @@ -950,7 +950,6 @@ static void reset_state(struct scsi_tape *STp) STp->partition = find_partition(STp); if (STp->partition < 0) STp->partition = 0; - STp->new_partition = STp->partition; } } @@ -2887,7 +2886,6 @@ static int st_int_ioctl(struct scsi_tape *STp, unsigned int cmd_in, unsigned lon timeout = STp->long_timeout * 8; DEBC_printk(STp, "Erasing tape.\n"); - fileno = blkno = at_sm = 0; break; case MTSETBLK: /* Set block length */ case MTSETDENSITY: /* Set tape density */ @@ -2920,14 +2918,17 @@ static int st_int_ioctl(struct scsi_tape *STp, unsigned int cmd_in, unsigned lon if (cmd_in == MTSETDENSITY) { (STp->buffer)->b_data[4] = arg; STp->density_changed = 1; /* At least we tried ;-) */ + STp->changed_density = arg; } else if (cmd_in == SET_DENS_AND_BLK) (STp->buffer)->b_data[4] = arg >> 24; else (STp->buffer)->b_data[4] = STp->density; if (cmd_in == MTSETBLK || cmd_in == SET_DENS_AND_BLK) { ltmp = arg & MT_ST_BLKSIZE_MASK; - if (cmd_in == MTSETBLK) + if (cmd_in == MTSETBLK) { STp->blksize_changed = 1; /* At least we tried ;-) */ + STp->changed_blksize = arg; + } } else ltmp = STp->block_size; (STp->buffer)->b_data[9] = (ltmp >> 16); @@ -3074,7 +3075,9 @@ static int st_int_ioctl(struct scsi_tape *STp, unsigned int cmd_in, unsigned lon cmd_in == MTSETDRVBUFFER || cmd_in == SET_DENS_AND_BLK) { if (cmdstatp->sense_hdr.sense_key == ILLEGAL_REQUEST && - !(STp->use_pf & PF_TESTED)) { + cmdstatp->sense_hdr.asc == 0x24 && + (STp->device)->scsi_level <= SCSI_2 && + !(STp->use_pf & PF_TESTED)) { /* Try the other possible state of Page Format if not already tried */ STp->use_pf = (STp->use_pf ^ USE_PF) | PF_TESTED; @@ -3626,9 +3629,25 @@ static long st_ioctl(struct file *file, unsigned int cmd_in, unsigned long arg) retval = (-EIO); goto out; } - reset_state(STp); + reset_state(STp); /* Clears pos_unknown */ /* remove this when the midlevel properly clears was_reset */ STp->device->was_reset = 0; + + /* Fix the device settings after reset, ignore errors */ + if (mtc.mt_op == MTREW || mtc.mt_op == MTSEEK || + mtc.mt_op == MTEOM) { + if (STp->can_partitions) { + /* STp->new_partition contains the + * latest partition set + */ + STp->partition = 0; + switch_partition(STp); + } + if (STp->density_changed) + st_int_ioctl(STp, MTSETDENSITY, STp->changed_density); + if (STp->blksize_changed) + st_int_ioctl(STp, MTSETBLK, STp->changed_blksize); + } } if (mtc.mt_op != MTNOP && mtc.mt_op != MTSETBLK && diff --git a/drivers/scsi/st.h b/drivers/scsi/st.h index 7a68eaba7e81..2105c6a5b458 100644 --- a/drivers/scsi/st.h +++ b/drivers/scsi/st.h @@ -165,12 +165,14 @@ struct scsi_tape { unsigned char compression_changed; unsigned char drv_buffer; unsigned char density; + unsigned char changed_density; unsigned char door_locked; unsigned char autorew_dev; /* auto-rewind device */ unsigned char rew_at_close; /* rewind necessary at close */ unsigned char inited; unsigned char cleaning_req; /* cleaning requested? */ int block_size; + int changed_blksize; int min_block; int max_block; int recover_count; /* From tape opening */ diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 3fcffa6a4bac..8567ac745358 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1810,6 +1810,7 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) return SCSI_MLQUEUE_DEVICE_BUSY; } + payload->rangecount = 1; payload->range.len = length; payload->range.offset = offset_in_hvpg; diff --git a/drivers/soc/apple/rtkit-internal.h b/drivers/soc/apple/rtkit-internal.h index 24bd619ec5e4..1da1dfd9cb19 100644 --- a/drivers/soc/apple/rtkit-internal.h +++ b/drivers/soc/apple/rtkit-internal.h @@ -48,6 +48,7 @@ struct apple_rtkit { struct apple_rtkit_shmem ioreport_buffer; struct apple_rtkit_shmem crashlog_buffer; + struct apple_rtkit_shmem oslog_buffer; struct apple_rtkit_shmem syslog_buffer; char *syslog_msg_buffer; diff --git a/drivers/soc/apple/rtkit.c b/drivers/soc/apple/rtkit.c index 8ec74d7539eb..968f9f633393 100644 --- a/drivers/soc/apple/rtkit.c +++ b/drivers/soc/apple/rtkit.c @@ -65,8 +65,9 @@ enum { #define APPLE_RTKIT_SYSLOG_MSG_SIZE GENMASK_ULL(31, 24) #define APPLE_RTKIT_OSLOG_TYPE GENMASK_ULL(63, 56) -#define APPLE_RTKIT_OSLOG_INIT 1 -#define APPLE_RTKIT_OSLOG_ACK 3 +#define APPLE_RTKIT_OSLOG_BUFFER_REQUEST 1 +#define APPLE_RTKIT_OSLOG_SIZE GENMASK_ULL(55, 36) +#define APPLE_RTKIT_OSLOG_IOVA GENMASK_ULL(35, 0) #define APPLE_RTKIT_MIN_SUPPORTED_VERSION 11 #define APPLE_RTKIT_MAX_SUPPORTED_VERSION 12 @@ -255,15 +256,21 @@ static int apple_rtkit_common_rx_get_buffer(struct apple_rtkit *rtk, struct apple_rtkit_shmem *buffer, u8 ep, u64 msg) { - size_t n_4kpages = FIELD_GET(APPLE_RTKIT_BUFFER_REQUEST_SIZE, msg); u64 reply; int err; + /* The different size vs. IOVA shifts look odd but are indeed correct this way */ + if (ep == APPLE_RTKIT_EP_OSLOG) { + buffer->size = FIELD_GET(APPLE_RTKIT_OSLOG_SIZE, msg); + buffer->iova = FIELD_GET(APPLE_RTKIT_OSLOG_IOVA, msg) << 12; + } else { + buffer->size = FIELD_GET(APPLE_RTKIT_BUFFER_REQUEST_SIZE, msg) << 12; + buffer->iova = FIELD_GET(APPLE_RTKIT_BUFFER_REQUEST_IOVA, msg); + } + buffer->buffer = NULL; buffer->iomem = NULL; buffer->is_mapped = false; - buffer->iova = FIELD_GET(APPLE_RTKIT_BUFFER_REQUEST_IOVA, msg); - buffer->size = n_4kpages << 12; dev_dbg(rtk->dev, "RTKit: buffer request for 0x%zx bytes at %pad\n", buffer->size, &buffer->iova); @@ -288,11 +295,21 @@ static int apple_rtkit_common_rx_get_buffer(struct apple_rtkit *rtk, } if (!buffer->is_mapped) { - reply = FIELD_PREP(APPLE_RTKIT_SYSLOG_TYPE, - APPLE_RTKIT_BUFFER_REQUEST); - reply |= FIELD_PREP(APPLE_RTKIT_BUFFER_REQUEST_SIZE, n_4kpages); - reply |= FIELD_PREP(APPLE_RTKIT_BUFFER_REQUEST_IOVA, - buffer->iova); + /* oslog uses different fields and needs a shifted IOVA instead of size */ + if (ep == APPLE_RTKIT_EP_OSLOG) { + reply = FIELD_PREP(APPLE_RTKIT_OSLOG_TYPE, + APPLE_RTKIT_OSLOG_BUFFER_REQUEST); + reply |= FIELD_PREP(APPLE_RTKIT_OSLOG_SIZE, buffer->size); + reply |= FIELD_PREP(APPLE_RTKIT_OSLOG_IOVA, + buffer->iova >> 12); + } else { + reply = FIELD_PREP(APPLE_RTKIT_SYSLOG_TYPE, + APPLE_RTKIT_BUFFER_REQUEST); + reply |= FIELD_PREP(APPLE_RTKIT_BUFFER_REQUEST_SIZE, + buffer->size >> 12); + reply |= FIELD_PREP(APPLE_RTKIT_BUFFER_REQUEST_IOVA, + buffer->iova); + } apple_rtkit_send_message(rtk, ep, reply, NULL, false); } @@ -474,25 +491,18 @@ static void apple_rtkit_syslog_rx(struct apple_rtkit *rtk, u64 msg) } } -static void apple_rtkit_oslog_rx_init(struct apple_rtkit *rtk, u64 msg) -{ - u64 ack; - - dev_dbg(rtk->dev, "RTKit: oslog init: msg: 0x%llx\n", msg); - ack = FIELD_PREP(APPLE_RTKIT_OSLOG_TYPE, APPLE_RTKIT_OSLOG_ACK); - apple_rtkit_send_message(rtk, APPLE_RTKIT_EP_OSLOG, ack, NULL, false); -} - static void apple_rtkit_oslog_rx(struct apple_rtkit *rtk, u64 msg) { u8 type = FIELD_GET(APPLE_RTKIT_OSLOG_TYPE, msg); switch (type) { - case APPLE_RTKIT_OSLOG_INIT: - apple_rtkit_oslog_rx_init(rtk, msg); + case APPLE_RTKIT_OSLOG_BUFFER_REQUEST: + apple_rtkit_common_rx_get_buffer(rtk, &rtk->oslog_buffer, + APPLE_RTKIT_EP_OSLOG, msg); break; default: - dev_warn(rtk->dev, "RTKit: Unknown oslog message: %llx\n", msg); + dev_warn(rtk->dev, "RTKit: Unknown oslog message: %llx\n", + msg); } } @@ -731,7 +741,7 @@ static struct apple_rtkit *apple_rtkit_init(struct device *dev, void *cookie, rtk->mbox_cl.rx_callback = &apple_rtkit_rx; rtk->mbox_cl.tx_done = &apple_rtkit_tx_done; - rtk->wq = alloc_ordered_workqueue("rtkit-%s", WQ_MEM_RECLAIM, + rtk->wq = alloc_ordered_workqueue("rtkit-%s", WQ_HIGHPRI | WQ_MEM_RECLAIM, dev_name(rtk->dev)); if (!rtk->wq) { ret = -ENOMEM; @@ -773,6 +783,7 @@ int apple_rtkit_reinit(struct apple_rtkit *rtk) apple_rtkit_free_buffer(rtk, &rtk->ioreport_buffer); apple_rtkit_free_buffer(rtk, &rtk->crashlog_buffer); + apple_rtkit_free_buffer(rtk, &rtk->oslog_buffer); apple_rtkit_free_buffer(rtk, &rtk->syslog_buffer); kfree(rtk->syslog_msg_buffer); @@ -935,6 +946,7 @@ static void apple_rtkit_free(void *data) apple_rtkit_free_buffer(rtk, &rtk->ioreport_buffer); apple_rtkit_free_buffer(rtk, &rtk->crashlog_buffer); + apple_rtkit_free_buffer(rtk, &rtk->oslog_buffer); apple_rtkit_free_buffer(rtk, &rtk->syslog_buffer); kfree(rtk->syslog_msg_buffer); diff --git a/drivers/soc/imx/gpcv2.c b/drivers/soc/imx/gpcv2.c index 88aee59730e3..6d5b6ed36169 100644 --- a/drivers/soc/imx/gpcv2.c +++ b/drivers/soc/imx/gpcv2.c @@ -1347,7 +1347,7 @@ static int imx_pgc_domain_probe(struct platform_device *pdev) } if (IS_ENABLED(CONFIG_LOCKDEP) && - of_property_read_bool(domain->dev->of_node, "power-domains")) + of_property_present(domain->dev->of_node, "power-domains")) lockdep_set_subclass(&domain->genpd.mlock, 1); ret = of_genpd_add_provider_simple(domain->dev->of_node, diff --git a/drivers/soc/ti/k3-socinfo.c b/drivers/soc/ti/k3-socinfo.c index 91f441ee6175..5b0d8260918d 100644 --- a/drivers/soc/ti/k3-socinfo.c +++ b/drivers/soc/ti/k3-socinfo.c @@ -60,6 +60,12 @@ k3_chipinfo_partno_to_names(unsigned int partno, return -EINVAL; } +static const struct regmap_config k3_chipinfo_regmap_cfg = { + .reg_bits = 32, + .val_bits = 32, + .reg_stride = 4, +}; + static int k3_chipinfo_probe(struct platform_device *pdev) { struct device_node *node = pdev->dev.of_node; @@ -67,13 +73,18 @@ static int k3_chipinfo_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct soc_device *soc_dev; struct regmap *regmap; + void __iomem *base; u32 partno_id; u32 variant; u32 jtag_id; u32 mfg; int ret; - regmap = device_node_to_regmap(node); + base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(base)) + return PTR_ERR(base); + + regmap = regmap_init_mmio(dev, base, &k3_chipinfo_regmap_cfg); if (IS_ERR(regmap)) return PTR_ERR(regmap); diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index 42861bc45073..02c5f00c8a57 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -1775,10 +1775,9 @@ static int cqspi_remove(struct platform_device *pdev) static int cqspi_suspend(struct device *dev) { struct cqspi_st *cqspi = dev_get_drvdata(dev); - struct spi_master *master = dev_get_drvdata(dev); int ret; - ret = spi_master_suspend(master); + ret = spi_master_suspend(cqspi->master); cqspi_controller_enable(cqspi, 0); clk_disable_unprepare(cqspi->clk); @@ -1789,7 +1788,6 @@ static int cqspi_suspend(struct device *dev) static int cqspi_resume(struct device *dev) { struct cqspi_st *cqspi = dev_get_drvdata(dev); - struct spi_master *master = dev_get_drvdata(dev); clk_prepare_enable(cqspi->clk); cqspi_wait_idle(cqspi); @@ -1798,7 +1796,7 @@ static int cqspi_resume(struct device *dev) cqspi->current_cs = -1; cqspi->sclk = 0; - return spi_master_resume(master); + return spi_master_resume(cqspi->master); } static DEFINE_SIMPLE_DEV_PM_OPS(cqspi_dev_pm_ops, cqspi_suspend, cqspi_resume); diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c index 01930b52c4fb..5374c6d44519 100644 --- a/drivers/spi/spi-fsl-dspi.c +++ b/drivers/spi/spi-fsl-dspi.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0+ // // Copyright 2013 Freescale Semiconductor, Inc. -// Copyright 2020 NXP +// Copyright 2020-2025 NXP // // Freescale DSPI driver // This file contains a driver for the Freescale DSPI @@ -61,6 +61,7 @@ #define SPI_SR_TFIWF BIT(18) #define SPI_SR_RFDF BIT(17) #define SPI_SR_CMDFFF BIT(16) +#define SPI_SR_TXRXS BIT(30) #define SPI_SR_CLEAR (SPI_SR_TCFQF | \ SPI_SR_TFUF | SPI_SR_TFFF | \ SPI_SR_CMDTCF | SPI_SR_SPEF | \ @@ -907,9 +908,20 @@ static int dspi_transfer_one_message(struct spi_controller *ctlr, struct spi_device *spi = message->spi; struct spi_transfer *transfer; int status = 0; + u32 val = 0; + bool cs_change = false; message->actual_length = 0; + /* Put DSPI in running mode if halted. */ + regmap_read(dspi->regmap, SPI_MCR, &val); + if (val & SPI_MCR_HALT) { + regmap_update_bits(dspi->regmap, SPI_MCR, SPI_MCR_HALT, 0); + while (regmap_read(dspi->regmap, SPI_SR, &val) >= 0 && + !(val & SPI_SR_TXRXS)) + ; + } + list_for_each_entry(transfer, &message->transfers, transfer_list) { dspi->cur_transfer = transfer; dspi->cur_msg = message; @@ -934,6 +946,7 @@ static int dspi_transfer_one_message(struct spi_controller *ctlr, dspi->tx_cmd |= SPI_PUSHR_CMD_CONT; } + cs_change = transfer->cs_change; dspi->tx = transfer->tx_buf; dspi->rx = transfer->rx_buf; dspi->len = transfer->len; @@ -943,6 +956,8 @@ static int dspi_transfer_one_message(struct spi_controller *ctlr, SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF, SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF); + regmap_write(dspi->regmap, SPI_SR, SPI_SR_CLEAR); + spi_take_timestamp_pre(dspi->ctlr, dspi->cur_transfer, dspi->progress, !dspi->irq); @@ -966,6 +981,15 @@ static int dspi_transfer_one_message(struct spi_controller *ctlr, spi_transfer_delay_exec(transfer); } + if (status || !cs_change) { + /* Put DSPI in stop mode */ + regmap_update_bits(dspi->regmap, SPI_MCR, + SPI_MCR_HALT, SPI_MCR_HALT); + while (regmap_read(dspi->regmap, SPI_SR, &val) >= 0 && + val & SPI_SR_TXRXS) + ; + } + message->status = status; spi_finalize_current_message(ctlr); @@ -1128,6 +1152,20 @@ static int dspi_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(dspi_pm, dspi_suspend, dspi_resume); +static const struct regmap_range dspi_yes_ranges[] = { + regmap_reg_range(SPI_MCR, SPI_MCR), + regmap_reg_range(SPI_TCR, SPI_CTAR(3)), + regmap_reg_range(SPI_SR, SPI_TXFR3), + regmap_reg_range(SPI_RXFR0, SPI_RXFR3), + regmap_reg_range(SPI_CTARE(0), SPI_CTARE(3)), + regmap_reg_range(SPI_SREX, SPI_SREX), +}; + +static const struct regmap_access_table dspi_access_table = { + .yes_ranges = dspi_yes_ranges, + .n_yes_ranges = ARRAY_SIZE(dspi_yes_ranges), +}; + static const struct regmap_range dspi_volatile_ranges[] = { regmap_reg_range(SPI_MCR, SPI_TCR), regmap_reg_range(SPI_SR, SPI_SR), @@ -1145,6 +1183,8 @@ static const struct regmap_config dspi_regmap_config = { .reg_stride = 4, .max_register = 0x88, .volatile_table = &dspi_volatile_table, + .rd_table = &dspi_access_table, + .wr_table = &dspi_access_table, }; static const struct regmap_range dspi_xspi_volatile_ranges[] = { @@ -1166,6 +1206,8 @@ static const struct regmap_config dspi_xspi_regmap_config[] = { .reg_stride = 4, .max_register = 0x13c, .volatile_table = &dspi_xspi_volatile_table, + .rd_table = &dspi_access_table, + .wr_table = &dspi_access_table, }, { .name = "pushr", @@ -1188,6 +1230,8 @@ static int dspi_init(struct fsl_dspi *dspi) if (!spi_controller_is_slave(dspi->ctlr)) mcr |= SPI_MCR_MASTER; + mcr |= SPI_MCR_HALT; + regmap_write(dspi->regmap, SPI_MCR, mcr); regmap_write(dspi->regmap, SPI_SR, SPI_SR_CLEAR); diff --git a/drivers/spi/spi-loopback-test.c b/drivers/spi/spi-loopback-test.c index dd7de8fa37d0..ab29ae463f67 100644 --- a/drivers/spi/spi-loopback-test.c +++ b/drivers/spi/spi-loopback-test.c @@ -410,7 +410,7 @@ MODULE_LICENSE("GPL"); static void spi_test_print_hex_dump(char *pre, const void *ptr, size_t len) { /* limit the hex_dump */ - if (len < 1024) { + if (len <= 1024) { print_hex_dump(KERN_INFO, pre, DUMP_PREFIX_OFFSET, 16, 1, ptr, len, 0); diff --git a/drivers/spi/spi-sun4i.c b/drivers/spi/spi-sun4i.c index 6000d0761206..6937f5c4d868 100644 --- a/drivers/spi/spi-sun4i.c +++ b/drivers/spi/spi-sun4i.c @@ -263,6 +263,9 @@ static int sun4i_spi_transfer_one(struct spi_master *master, else reg |= SUN4I_CTL_DHB; + /* Now that the settings are correct, enable the interface */ + reg |= SUN4I_CTL_ENABLE; + sun4i_spi_write(sspi, SUN4I_CTL_REG, reg); /* Ensure that we have a parent clock fast enough */ @@ -403,7 +406,7 @@ static int sun4i_spi_runtime_resume(struct device *dev) } sun4i_spi_write(sspi, SUN4I_CTL_REG, - SUN4I_CTL_ENABLE | SUN4I_CTL_MASTER | SUN4I_CTL_TP); + SUN4I_CTL_MASTER | SUN4I_CTL_TP); return 0; diff --git a/drivers/spi/spi-zynqmp-gqspi.c b/drivers/spi/spi-zynqmp-gqspi.c index c89544ae5ed9..fde7c3810359 100644 --- a/drivers/spi/spi-zynqmp-gqspi.c +++ b/drivers/spi/spi-zynqmp-gqspi.c @@ -698,7 +698,6 @@ static void zynqmp_process_dma_irq(struct zynqmp_qspi *xqspi) static irqreturn_t zynqmp_qspi_irq(int irq, void *dev_id) { struct zynqmp_qspi *xqspi = (struct zynqmp_qspi *)dev_id; - irqreturn_t ret = IRQ_NONE; u32 status, mask, dma_status = 0; status = zynqmp_gqspi_read(xqspi, GQSPI_ISR_OFST); @@ -713,27 +712,24 @@ static irqreturn_t zynqmp_qspi_irq(int irq, void *dev_id) dma_status); } - if (mask & GQSPI_ISR_TXNOT_FULL_MASK) { - zynqmp_qspi_filltxfifo(xqspi, GQSPI_TX_FIFO_FILL); - ret = IRQ_HANDLED; - } + if (!mask && !dma_status) + return IRQ_NONE; - if (dma_status & GQSPI_QSPIDMA_DST_I_STS_DONE_MASK) { + if (mask & GQSPI_ISR_TXNOT_FULL_MASK) + zynqmp_qspi_filltxfifo(xqspi, GQSPI_TX_FIFO_FILL); + + if (dma_status & GQSPI_QSPIDMA_DST_I_STS_DONE_MASK) zynqmp_process_dma_irq(xqspi); - ret = IRQ_HANDLED; - } else if (!(mask & GQSPI_IER_RXEMPTY_MASK) && - (mask & GQSPI_IER_GENFIFOEMPTY_MASK)) { + else if (!(mask & GQSPI_IER_RXEMPTY_MASK) && + (mask & GQSPI_IER_GENFIFOEMPTY_MASK)) zynqmp_qspi_readrxfifo(xqspi, GQSPI_RX_FIFO_FILL); - ret = IRQ_HANDLED; - } if (xqspi->bytes_to_receive == 0 && xqspi->bytes_to_transfer == 0 && ((status & GQSPI_IRQ_MASK) == GQSPI_IRQ_MASK)) { zynqmp_gqspi_write(xqspi, GQSPI_IDR_OFST, GQSPI_ISR_IDR_MASK); complete(&xqspi->data_completion); - ret = IRQ_HANDLED; } - return ret; + return IRQ_HANDLED; } /** diff --git a/drivers/staging/axis-fifo/axis-fifo.c b/drivers/staging/axis-fifo/axis-fifo.c index 0a85ea667a1b..3369892eacf4 100644 --- a/drivers/staging/axis-fifo/axis-fifo.c +++ b/drivers/staging/axis-fifo/axis-fifo.c @@ -400,16 +400,14 @@ static ssize_t axis_fifo_read(struct file *f, char __user *buf, bytes_available = ioread32(fifo->base_addr + XLLF_RLR_OFFSET); if (!bytes_available) { - dev_err(fifo->dt_device, "received a packet of length 0 - fifo core will be reset\n"); - reset_ip_core(fifo); + dev_err(fifo->dt_device, "received a packet of length 0\n"); ret = -EIO; goto end_unlock; } if (bytes_available > len) { - dev_err(fifo->dt_device, "user read buffer too small (available bytes=%zu user buffer bytes=%zu) - fifo core will be reset\n", + dev_err(fifo->dt_device, "user read buffer too small (available bytes=%zu user buffer bytes=%zu)\n", bytes_available, len); - reset_ip_core(fifo); ret = -EINVAL; goto end_unlock; } @@ -418,8 +416,7 @@ static ssize_t axis_fifo_read(struct file *f, char __user *buf, /* this probably can't happen unless IP * registers were previously mishandled */ - dev_err(fifo->dt_device, "received a packet that isn't word-aligned - fifo core will be reset\n"); - reset_ip_core(fifo); + dev_err(fifo->dt_device, "received a packet that isn't word-aligned\n"); ret = -EIO; goto end_unlock; } @@ -440,7 +437,6 @@ static ssize_t axis_fifo_read(struct file *f, char __user *buf, if (copy_to_user(buf + copied * sizeof(u32), tmp_buf, copy * sizeof(u32))) { - reset_ip_core(fifo); ret = -EFAULT; goto end_unlock; } @@ -549,7 +545,6 @@ static ssize_t axis_fifo_write(struct file *f, const char __user *buf, if (copy_from_user(tmp_buf, buf + copied * sizeof(u32), copy * sizeof(u32))) { - reset_ip_core(fifo); ret = -EFAULT; goto end_unlock; } @@ -782,9 +777,6 @@ static int axis_fifo_parse_dt(struct axis_fifo *fifo) goto end; } - /* IP sets TDFV to fifo depth - 4 so we will do the same */ - fifo->tx_fifo_depth -= 4; - ret = get_dts_property(fifo, "xlnx,use-rx-data", &fifo->has_rx_fifo); if (ret) { dev_err(fifo->dt_device, "missing xlnx,use-rx-data property\n"); diff --git a/drivers/staging/iio/adc/ad7816.c b/drivers/staging/iio/adc/ad7816.c index 6c14d7bcdd67..081b17f49863 100644 --- a/drivers/staging/iio/adc/ad7816.c +++ b/drivers/staging/iio/adc/ad7816.c @@ -136,7 +136,7 @@ static ssize_t ad7816_store_mode(struct device *dev, struct iio_dev *indio_dev = dev_to_iio_dev(dev); struct ad7816_chip_info *chip = iio_priv(indio_dev); - if (strcmp(buf, "full")) { + if (strcmp(buf, "full") == 0) { gpiod_set_value(chip->rdwr_pin, 1); chip->mode = AD7816_FULL; } else { diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 07e196b44b91..04d40e76772b 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -4314,8 +4314,8 @@ int iscsit_close_connection( spin_unlock(&iscsit_global->ts_bitmap_lock); iscsit_stop_timers_for_cmds(conn); - iscsit_stop_nopin_response_timer(conn); iscsit_stop_nopin_timer(conn); + iscsit_stop_nopin_response_timer(conn); if (conn->conn_transport->iscsit_wait_conn) conn->conn_transport->iscsit_wait_conn(conn); diff --git a/drivers/thermal/qoriq_thermal.c b/drivers/thermal/qoriq_thermal.c index d111e218f362..b33cb1d880b7 100644 --- a/drivers/thermal/qoriq_thermal.c +++ b/drivers/thermal/qoriq_thermal.c @@ -19,6 +19,7 @@ #define SITES_MAX 16 #define TMR_DISABLE 0x0 #define TMR_ME 0x80000000 +#define TMR_CMD BIT(29) #define TMR_ALPF 0x0c000000 #define TMR_ALPF_V2 0x03000000 #define TMTMIR_DEFAULT 0x0000000f @@ -345,6 +346,12 @@ static int __maybe_unused qoriq_tmu_suspend(struct device *dev) if (ret) return ret; + if (data->ver > TMU_VER1) { + ret = regmap_set_bits(data->regmap, REGS_TMR, TMR_CMD); + if (ret) + return ret; + } + clk_disable_unprepare(data->clk); return 0; @@ -359,6 +366,12 @@ static int __maybe_unused qoriq_tmu_resume(struct device *dev) if (ret) return ret; + if (data->ver > TMU_VER1) { + ret = regmap_clear_bits(data->regmap, REGS_TMR, TMR_CMD); + if (ret) + return ret; + } + /* Enable monitoring */ return regmap_update_bits(data->regmap, REGS_TMR, TMR_ME, TMR_ME); } diff --git a/drivers/thunderbolt/retimer.c b/drivers/thunderbolt/retimer.c index 5bd5c22a5085..d2038337ea03 100644 --- a/drivers/thunderbolt/retimer.c +++ b/drivers/thunderbolt/retimer.c @@ -89,9 +89,11 @@ static int tb_retimer_nvm_add(struct tb_retimer *rt) if (ret) goto err_nvm; - ret = tb_nvm_add_non_active(nvm, nvm_write); - if (ret) - goto err_nvm; + if (!rt->no_nvm_upgrade) { + ret = tb_nvm_add_non_active(nvm, nvm_write); + if (ret) + goto err_nvm; + } rt->nvm = nvm; return 0; diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index 6182ae5f6fa1..d33bd792d89a 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -105,6 +105,20 @@ struct plat_sci_reg { u8 offset, size; }; +struct sci_suspend_regs { + u16 scdl; + u16 sccks; + u16 scsmr; + u16 scscr; + u16 scfcr; + u16 scsptr; + u16 hssrr; + u16 scpcr; + u16 scpdr; + u8 scbrr; + u8 semr; +}; + struct sci_port_params { const struct plat_sci_reg regs[SCIx_NR_REGS]; unsigned int fifosize; @@ -135,6 +149,8 @@ struct sci_port { struct dma_chan *chan_tx; struct dma_chan *chan_rx; + struct reset_control *rstc; + #ifdef CONFIG_SERIAL_SH_SCI_DMA struct dma_chan *chan_tx_saved; struct dma_chan *chan_rx_saved; @@ -154,6 +170,7 @@ struct sci_port { int rx_trigger; struct timer_list rx_fifo_timer; int rx_fifo_timeout; + struct sci_suspend_regs suspend_regs; u16 hscif_tot; bool has_rtscts; @@ -3252,6 +3269,7 @@ static struct plat_sci_port *sci_parse_dt(struct platform_device *pdev, } sp = &sci_ports[id]; + sp->rstc = rstc; *dev_id = id; p->type = SCI_OF_TYPE(data); @@ -3400,13 +3418,77 @@ static int sci_probe(struct platform_device *dev) return 0; } +static void sci_console_save(struct sci_port *s) +{ + struct sci_suspend_regs *regs = &s->suspend_regs; + struct uart_port *port = &s->port; + + if (sci_getreg(port, SCDL)->size) + regs->scdl = sci_serial_in(port, SCDL); + if (sci_getreg(port, SCCKS)->size) + regs->sccks = sci_serial_in(port, SCCKS); + if (sci_getreg(port, SCSMR)->size) + regs->scsmr = sci_serial_in(port, SCSMR); + if (sci_getreg(port, SCSCR)->size) + regs->scscr = sci_serial_in(port, SCSCR); + if (sci_getreg(port, SCFCR)->size) + regs->scfcr = sci_serial_in(port, SCFCR); + if (sci_getreg(port, SCSPTR)->size) + regs->scsptr = sci_serial_in(port, SCSPTR); + if (sci_getreg(port, SCBRR)->size) + regs->scbrr = sci_serial_in(port, SCBRR); + if (sci_getreg(port, HSSRR)->size) + regs->hssrr = sci_serial_in(port, HSSRR); + if (sci_getreg(port, SCPCR)->size) + regs->scpcr = sci_serial_in(port, SCPCR); + if (sci_getreg(port, SCPDR)->size) + regs->scpdr = sci_serial_in(port, SCPDR); + if (sci_getreg(port, SEMR)->size) + regs->semr = sci_serial_in(port, SEMR); +} + +static void sci_console_restore(struct sci_port *s) +{ + struct sci_suspend_regs *regs = &s->suspend_regs; + struct uart_port *port = &s->port; + + if (sci_getreg(port, SCDL)->size) + sci_serial_out(port, SCDL, regs->scdl); + if (sci_getreg(port, SCCKS)->size) + sci_serial_out(port, SCCKS, regs->sccks); + if (sci_getreg(port, SCSMR)->size) + sci_serial_out(port, SCSMR, regs->scsmr); + if (sci_getreg(port, SCSCR)->size) + sci_serial_out(port, SCSCR, regs->scscr); + if (sci_getreg(port, SCFCR)->size) + sci_serial_out(port, SCFCR, regs->scfcr); + if (sci_getreg(port, SCSPTR)->size) + sci_serial_out(port, SCSPTR, regs->scsptr); + if (sci_getreg(port, SCBRR)->size) + sci_serial_out(port, SCBRR, regs->scbrr); + if (sci_getreg(port, HSSRR)->size) + sci_serial_out(port, HSSRR, regs->hssrr); + if (sci_getreg(port, SCPCR)->size) + sci_serial_out(port, SCPCR, regs->scpcr); + if (sci_getreg(port, SCPDR)->size) + sci_serial_out(port, SCPDR, regs->scpdr); + if (sci_getreg(port, SEMR)->size) + sci_serial_out(port, SEMR, regs->semr); +} + static __maybe_unused int sci_suspend(struct device *dev) { struct sci_port *sport = dev_get_drvdata(dev); - if (sport) + if (sport) { uart_suspend_port(&sci_uart_driver, &sport->port); + if (!console_suspend_enabled && uart_console(&sport->port)) + sci_console_save(sport); + else + return reset_control_assert(sport->rstc); + } + return 0; } @@ -3414,8 +3496,18 @@ static __maybe_unused int sci_resume(struct device *dev) { struct sci_port *sport = dev_get_drvdata(dev); - if (sport) + if (sport) { + if (!console_suspend_enabled && uart_console(&sport->port)) { + sci_console_restore(sport); + } else { + int ret = reset_control_deassert(sport->rstc); + + if (ret) + return ret; + } + uart_resume_port(&sci_uart_driver, &sport->port); + } return 0; } diff --git a/drivers/usb/cdns3/cdnsp-gadget.c b/drivers/usb/cdns3/cdnsp-gadget.c index 0044897ee800..913050230d1a 100644 --- a/drivers/usb/cdns3/cdnsp-gadget.c +++ b/drivers/usb/cdns3/cdnsp-gadget.c @@ -138,6 +138,26 @@ static void cdnsp_clear_port_change_bit(struct cdnsp_device *pdev, (portsc & PORT_CHANGE_BITS), port_regs); } +static void cdnsp_set_apb_timeout_value(struct cdnsp_device *pdev) +{ + struct cdns *cdns = dev_get_drvdata(pdev->dev); + __le32 __iomem *reg; + void __iomem *base; + u32 offset = 0; + u32 val; + + if (!cdns->override_apb_timeout) + return; + + base = &pdev->cap_regs->hc_capbase; + offset = cdnsp_find_next_ext_cap(base, offset, D_XEC_PRE_REGS_CAP); + reg = base + offset + REG_CHICKEN_BITS_3_OFFSET; + + val = le32_to_cpu(readl(reg)); + val = CHICKEN_APB_TIMEOUT_SET(val, cdns->override_apb_timeout); + writel(cpu_to_le32(val), reg); +} + static void cdnsp_set_chicken_bits_2(struct cdnsp_device *pdev, u32 bit) { __le32 __iomem *reg; @@ -1776,6 +1796,8 @@ static void cdnsp_get_rev_cap(struct cdnsp_device *pdev) reg += cdnsp_find_next_ext_cap(reg, 0, RTL_REV_CAP); pdev->rev_cap = reg; + pdev->rtl_revision = readl(&pdev->rev_cap->rtl_revision); + dev_info(pdev->dev, "Rev: %08x/%08x, eps: %08x, buff: %08x/%08x\n", readl(&pdev->rev_cap->ctrl_revision), readl(&pdev->rev_cap->rtl_revision), @@ -1801,6 +1823,15 @@ static int cdnsp_gen_setup(struct cdnsp_device *pdev) pdev->hci_version = HC_VERSION(pdev->hcc_params); pdev->hcc_params = readl(&pdev->cap_regs->hcc_params); + /* + * Override the APB timeout value to give the controller more time for + * enabling UTMI clock and synchronizing APB and UTMI clock domains. + * This fix is platform specific and is required to fixes issue with + * reading incorrect value from PORTSC register after resuming + * from L1 state. + */ + cdnsp_set_apb_timeout_value(pdev); + cdnsp_get_rev_cap(pdev); /* Make sure the Device Controller is halted. */ diff --git a/drivers/usb/cdns3/cdnsp-gadget.h b/drivers/usb/cdns3/cdnsp-gadget.h index a61aef0dc273..5cffc1444d3a 100644 --- a/drivers/usb/cdns3/cdnsp-gadget.h +++ b/drivers/usb/cdns3/cdnsp-gadget.h @@ -520,6 +520,9 @@ struct cdnsp_rev_cap { #define REG_CHICKEN_BITS_2_OFFSET 0x48 #define CHICKEN_XDMA_2_TP_CACHE_DIS BIT(28) +#define REG_CHICKEN_BITS_3_OFFSET 0x4C +#define CHICKEN_APB_TIMEOUT_SET(p, val) (((p) & ~GENMASK(21, 0)) | (val)) + /* XBUF Extended Capability ID. */ #define XBUF_CAP_ID 0xCB #define XBUF_RX_TAG_MASK_0_OFFSET 0x1C @@ -1359,6 +1362,7 @@ struct cdnsp_port { * @rev_cap: Controller Capabilities Registers. * @hcs_params1: Cached register copies of read-only HCSPARAMS1 * @hcc_params: Cached register copies of read-only HCCPARAMS1 + * @rtl_revision: Cached controller rtl revision. * @setup: Temporary buffer for setup packet. * @ep0_preq: Internal allocated request used during enumeration. * @ep0_stage: ep0 stage during enumeration process. @@ -1413,6 +1417,8 @@ struct cdnsp_device { __u32 hcs_params1; __u32 hcs_params3; __u32 hcc_params; + #define RTL_REVISION_NEW_LPM 0x2700 + __u32 rtl_revision; /* Lock used in interrupt thread context. */ spinlock_t lock; struct usb_ctrlrequest setup; diff --git a/drivers/usb/cdns3/cdnsp-pci.c b/drivers/usb/cdns3/cdnsp-pci.c index a85db23fa19f..b7a1f28faa1f 100644 --- a/drivers/usb/cdns3/cdnsp-pci.c +++ b/drivers/usb/cdns3/cdnsp-pci.c @@ -33,6 +33,8 @@ #define CDNS_DRD_ID 0x0100 #define CDNS_DRD_IF (PCI_CLASS_SERIAL_USB << 8 | 0x80) +#define CHICKEN_APB_TIMEOUT_VALUE 0x1C20 + static struct pci_dev *cdnsp_get_second_fun(struct pci_dev *pdev) { /* @@ -144,6 +146,14 @@ static int cdnsp_pci_probe(struct pci_dev *pdev, cdnsp->otg_irq = pdev->irq; } + /* + * Cadence PCI based platform require some longer timeout for APB + * to fixes domain clock synchronization issue after resuming + * controller from L1 state. + */ + cdnsp->override_apb_timeout = CHICKEN_APB_TIMEOUT_VALUE; + pci_set_drvdata(pdev, cdnsp); + if (pci_is_enabled(func)) { cdnsp->dev = dev; cdnsp->gadget_init = cdnsp_gadget_init; @@ -153,8 +163,6 @@ static int cdnsp_pci_probe(struct pci_dev *pdev, goto free_cdnsp; } - pci_set_drvdata(pdev, cdnsp); - device_wakeup_enable(&pdev->dev); if (pci_dev_run_wake(pdev)) pm_runtime_put_noidle(&pdev->dev); diff --git a/drivers/usb/cdns3/cdnsp-ring.c b/drivers/usb/cdns3/cdnsp-ring.c index 47096b8e3179..6247584cb939 100644 --- a/drivers/usb/cdns3/cdnsp-ring.c +++ b/drivers/usb/cdns3/cdnsp-ring.c @@ -308,7 +308,8 @@ static bool cdnsp_ring_ep_doorbell(struct cdnsp_device *pdev, writel(db_value, reg_addr); - cdnsp_force_l0_go(pdev); + if (pdev->rtl_revision < RTL_REVISION_NEW_LPM) + cdnsp_force_l0_go(pdev); /* Doorbell was set. */ return true; diff --git a/drivers/usb/cdns3/core.h b/drivers/usb/cdns3/core.h index 57d47348dc19..ac30ee21309d 100644 --- a/drivers/usb/cdns3/core.h +++ b/drivers/usb/cdns3/core.h @@ -79,6 +79,8 @@ struct cdns3_platform_data { * @pdata: platform data from glue layer * @lock: spinlock structure * @xhci_plat_data: xhci private data structure pointer + * @override_apb_timeout: hold value of APB timeout. For value 0 the default + * value in CHICKEN_BITS_3 will be preserved. * @gadget_init: pointer to gadget initialization function */ struct cdns { @@ -117,6 +119,7 @@ struct cdns { struct cdns3_platform_data *pdata; spinlock_t lock; struct xhci_plat_priv *xhci_plat_data; + u32 override_apb_timeout; int (*gadget_init)(struct cdns *cdns); }; diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c index c2e666e82857..2f92905e05ca 100644 --- a/drivers/usb/class/usbtmc.c +++ b/drivers/usb/class/usbtmc.c @@ -482,6 +482,7 @@ static int usbtmc_get_stb(struct usbtmc_file_data *file_data, __u8 *stb) u8 *buffer; u8 tag; int rv; + long wait_rv; dev_dbg(dev, "Enter ioctl_read_stb iin_ep_present: %d\n", data->iin_ep_present); @@ -511,16 +512,17 @@ static int usbtmc_get_stb(struct usbtmc_file_data *file_data, __u8 *stb) } if (data->iin_ep_present) { - rv = wait_event_interruptible_timeout( + wait_rv = wait_event_interruptible_timeout( data->waitq, atomic_read(&data->iin_data_valid) != 0, file_data->timeout); - if (rv < 0) { - dev_dbg(dev, "wait interrupted %d\n", rv); + if (wait_rv < 0) { + dev_dbg(dev, "wait interrupted %ld\n", wait_rv); + rv = wait_rv; goto exit; } - if (rv == 0) { + if (wait_rv == 0) { dev_dbg(dev, "wait timed out\n"); rv = -ETIMEDOUT; goto exit; @@ -539,6 +541,8 @@ static int usbtmc_get_stb(struct usbtmc_file_data *file_data, __u8 *stb) dev_dbg(dev, "stb:0x%02x received %d\n", (unsigned int)*stb, rv); + rv = 0; + exit: /* bump interrupt bTag */ data->iin_bTag += 1; @@ -602,9 +606,9 @@ static int usbtmc488_ioctl_wait_srq(struct usbtmc_file_data *file_data, { struct usbtmc_device_data *data = file_data->data; struct device *dev = &data->intf->dev; - int rv; u32 timeout; unsigned long expire; + long wait_rv; if (!data->iin_ep_present) { dev_dbg(dev, "no interrupt endpoint present\n"); @@ -618,25 +622,24 @@ static int usbtmc488_ioctl_wait_srq(struct usbtmc_file_data *file_data, mutex_unlock(&data->io_mutex); - rv = wait_event_interruptible_timeout( - data->waitq, - atomic_read(&file_data->srq_asserted) != 0 || - atomic_read(&file_data->closing), - expire); + wait_rv = wait_event_interruptible_timeout( + data->waitq, + atomic_read(&file_data->srq_asserted) != 0 || + atomic_read(&file_data->closing), + expire); mutex_lock(&data->io_mutex); /* Note! disconnect or close could be called in the meantime */ if (atomic_read(&file_data->closing) || data->zombie) - rv = -ENODEV; + return -ENODEV; - if (rv < 0) { - /* dev can be invalid now! */ - pr_debug("%s - wait interrupted %d\n", __func__, rv); - return rv; + if (wait_rv < 0) { + dev_dbg(dev, "%s - wait interrupted %ld\n", __func__, wait_rv); + return wait_rv; } - if (rv == 0) { + if (wait_rv == 0) { dev_dbg(dev, "%s - wait timed out\n", __func__); return -ETIMEDOUT; } @@ -830,6 +833,7 @@ static ssize_t usbtmc_generic_read(struct usbtmc_file_data *file_data, unsigned long expire; int bufcount = 1; int again = 0; + long wait_rv; /* mutex already locked */ @@ -942,19 +946,24 @@ static ssize_t usbtmc_generic_read(struct usbtmc_file_data *file_data, if (!(flags & USBTMC_FLAG_ASYNC)) { dev_dbg(dev, "%s: before wait time %lu\n", __func__, expire); - retval = wait_event_interruptible_timeout( + wait_rv = wait_event_interruptible_timeout( file_data->wait_bulk_in, usbtmc_do_transfer(file_data), expire); - dev_dbg(dev, "%s: wait returned %d\n", - __func__, retval); + dev_dbg(dev, "%s: wait returned %ld\n", + __func__, wait_rv); - if (retval <= 0) { - if (retval == 0) - retval = -ETIMEDOUT; + if (wait_rv < 0) { + retval = wait_rv; goto error; } + + if (wait_rv == 0) { + retval = -ETIMEDOUT; + goto error; + } + } urb = usb_get_from_anchor(&file_data->in_anchor); @@ -1380,7 +1389,10 @@ static ssize_t usbtmc_read(struct file *filp, char __user *buf, if (!buffer) return -ENOMEM; - mutex_lock(&data->io_mutex); + retval = mutex_lock_interruptible(&data->io_mutex); + if (retval < 0) + goto exit_nolock; + if (data->zombie) { retval = -ENODEV; goto exit; @@ -1503,6 +1515,7 @@ static ssize_t usbtmc_read(struct file *filp, char __user *buf, exit: mutex_unlock(&data->io_mutex); +exit_nolock: kfree(buffer); return retval; } diff --git a/drivers/usb/gadget/udc/tegra-xudc.c b/drivers/usb/gadget/udc/tegra-xudc.c index fd7a9535973e..771466cdf385 100644 --- a/drivers/usb/gadget/udc/tegra-xudc.c +++ b/drivers/usb/gadget/udc/tegra-xudc.c @@ -1743,6 +1743,10 @@ static int __tegra_xudc_ep_disable(struct tegra_xudc_ep *ep) val = xudc_readl(xudc, CTRL); val &= ~CTRL_RUN; xudc_writel(xudc, val, CTRL); + + val = xudc_readl(xudc, ST); + if (val & ST_RC) + xudc_writel(xudc, ST_RC, ST); } dev_info(xudc->dev, "ep %u disabled\n", ep->index); diff --git a/drivers/usb/host/uhci-platform.c b/drivers/usb/host/uhci-platform.c index b2049b47a08d..53d2fbee76e2 100644 --- a/drivers/usb/host/uhci-platform.c +++ b/drivers/usb/host/uhci-platform.c @@ -122,7 +122,7 @@ static int uhci_hcd_platform_probe(struct platform_device *pdev) } /* Get and enable clock if any specified */ - uhci->clk = devm_clk_get(&pdev->dev, NULL); + uhci->clk = devm_clk_get_optional(&pdev->dev, NULL); if (IS_ERR(uhci->clk)) { ret = PTR_ERR(uhci->clk); goto err_rmr; diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c index 51eabc5e8770..14a772feab79 100644 --- a/drivers/usb/host/xhci-tegra.c +++ b/drivers/usb/host/xhci-tegra.c @@ -1228,6 +1228,7 @@ static void tegra_xhci_id_work(struct work_struct *work) tegra->otg_usb3_port = tegra_xusb_padctl_get_usb3_companion(tegra->padctl, tegra->otg_usb2_port); + pm_runtime_get_sync(tegra->dev); if (tegra->host_mode) { /* switch to host mode */ if (tegra->otg_usb3_port >= 0) { @@ -1257,6 +1258,7 @@ static void tegra_xhci_id_work(struct work_struct *work) } tegra_xhci_set_port_power(tegra, true, true); + pm_runtime_mark_last_busy(tegra->dev); } else { if (tegra->otg_usb3_port >= 0) @@ -1264,6 +1266,7 @@ static void tegra_xhci_id_work(struct work_struct *work) tegra_xhci_set_port_power(tegra, true, false); } + pm_runtime_put_autosuspend(tegra->dev); } #if IS_ENABLED(CONFIG_PM) || IS_ENABLED(CONFIG_PM_SLEEP) diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index f3fd8d9d217b..aaec33a22ec6 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -5160,7 +5160,7 @@ static void _tcpm_cc_change(struct tcpm_port *port, enum typec_cc_status cc1, case SNK_TRY_WAIT_DEBOUNCE: if (!tcpm_port_is_sink(port)) { port->max_wait = 0; - tcpm_set_state(port, SRC_TRYWAIT, 0); + tcpm_set_state(port, SRC_TRYWAIT, PD_T_PD_DEBOUNCE); } break; case SRC_TRY_WAIT: diff --git a/drivers/usb/typec/ucsi/displayport.c b/drivers/usb/typec/ucsi/displayport.c index 2431febc4615..e3b5fa3b5f95 100644 --- a/drivers/usb/typec/ucsi/displayport.c +++ b/drivers/usb/typec/ucsi/displayport.c @@ -54,7 +54,8 @@ static int ucsi_displayport_enter(struct typec_altmode *alt, u32 *vdo) u8 cur = 0; int ret; - mutex_lock(&dp->con->lock); + if (!ucsi_con_mutex_lock(dp->con)) + return -ENOTCONN; if (!dp->override && dp->initialized) { const struct typec_altmode *p = typec_altmode_get_partner(alt); @@ -100,7 +101,7 @@ static int ucsi_displayport_enter(struct typec_altmode *alt, u32 *vdo) schedule_work(&dp->work); ret = 0; err_unlock: - mutex_unlock(&dp->con->lock); + ucsi_con_mutex_unlock(dp->con); return ret; } @@ -112,7 +113,8 @@ static int ucsi_displayport_exit(struct typec_altmode *alt) u64 command; int ret = 0; - mutex_lock(&dp->con->lock); + if (!ucsi_con_mutex_lock(dp->con)) + return -ENOTCONN; if (!dp->override) { const struct typec_altmode *p = typec_altmode_get_partner(alt); @@ -144,7 +146,7 @@ static int ucsi_displayport_exit(struct typec_altmode *alt) schedule_work(&dp->work); out_unlock: - mutex_unlock(&dp->con->lock); + ucsi_con_mutex_unlock(dp->con); return ret; } @@ -202,20 +204,21 @@ static int ucsi_displayport_vdm(struct typec_altmode *alt, int cmd = PD_VDO_CMD(header); int svdm_version; - mutex_lock(&dp->con->lock); + if (!ucsi_con_mutex_lock(dp->con)) + return -ENOTCONN; if (!dp->override && dp->initialized) { const struct typec_altmode *p = typec_altmode_get_partner(alt); dev_warn(&p->dev, "firmware doesn't support alternate mode overriding\n"); - mutex_unlock(&dp->con->lock); + ucsi_con_mutex_unlock(dp->con); return -EOPNOTSUPP; } svdm_version = typec_altmode_get_svdm_version(alt); if (svdm_version < 0) { - mutex_unlock(&dp->con->lock); + ucsi_con_mutex_unlock(dp->con); return svdm_version; } @@ -259,7 +262,7 @@ static int ucsi_displayport_vdm(struct typec_altmode *alt, break; } - mutex_unlock(&dp->con->lock); + ucsi_con_mutex_unlock(dp->con); return 0; } @@ -296,6 +299,8 @@ void ucsi_displayport_remove_partner(struct typec_altmode *alt) if (!dp) return; + cancel_work_sync(&dp->work); + dp->data.conf = 0; dp->data.status = 0; dp->initialized = false; diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index 2adf5fdc0c56..2a03bb992806 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -1398,6 +1398,40 @@ void ucsi_set_drvdata(struct ucsi *ucsi, void *data) } EXPORT_SYMBOL_GPL(ucsi_set_drvdata); +/** + * ucsi_con_mutex_lock - Acquire the connector mutex + * @con: The connector interface to lock + * + * Returns true on success, false if the connector is disconnected + */ +bool ucsi_con_mutex_lock(struct ucsi_connector *con) +{ + bool mutex_locked = false; + bool connected = true; + + while (connected && !mutex_locked) { + mutex_locked = mutex_trylock(&con->lock) != 0; + connected = con->status.flags & UCSI_CONSTAT_CONNECTED; + if (connected && !mutex_locked) + msleep(20); + } + + connected = connected && con->partner; + if (!connected && mutex_locked) + mutex_unlock(&con->lock); + + return connected; +} + +/** + * ucsi_con_mutex_unlock - Release the connector mutex + * @con: The connector interface to unlock + */ +void ucsi_con_mutex_unlock(struct ucsi_connector *con) +{ + mutex_unlock(&con->lock); +} + /** * ucsi_create - Allocate UCSI instance * @dev: Device interface to the PPM (Platform Policy Manager) diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h index 4a1a86e37fd5..793a8307dded 100644 --- a/drivers/usb/typec/ucsi/ucsi.h +++ b/drivers/usb/typec/ucsi/ucsi.h @@ -15,6 +15,7 @@ struct ucsi; struct ucsi_altmode; +struct ucsi_connector; /* UCSI offsets (Bytes) */ #define UCSI_VERSION 0 @@ -62,6 +63,8 @@ int ucsi_register(struct ucsi *ucsi); void ucsi_unregister(struct ucsi *ucsi); void *ucsi_get_drvdata(struct ucsi *ucsi); void ucsi_set_drvdata(struct ucsi *ucsi, void *data); +bool ucsi_con_mutex_lock(struct ucsi_connector *con); +void ucsi_con_mutex_unlock(struct ucsi_connector *con); void ucsi_connector_change(struct ucsi *ucsi, u8 num); diff --git a/drivers/usb/typec/ucsi/ucsi_ccg.c b/drivers/usb/typec/ucsi/ucsi_ccg.c index 8e500fe41e78..e690b6e53480 100644 --- a/drivers/usb/typec/ucsi/ucsi_ccg.c +++ b/drivers/usb/typec/ucsi/ucsi_ccg.c @@ -585,6 +585,10 @@ static int ucsi_ccg_sync_write(struct ucsi *ucsi, unsigned int offset, uc->has_multiple_dp) { con_index = (uc->last_cmd_sent >> 16) & UCSI_CMD_CONNECTOR_MASK; + if (con_index == 0) { + ret = -EINVAL; + goto err_put; + } con = &uc->ucsi->connector[con_index - 1]; ucsi_ccg_update_set_new_cam_cmd(uc, con, (u64 *)val); } @@ -599,6 +603,7 @@ static int ucsi_ccg_sync_write(struct ucsi *ucsi, unsigned int offset, err_clear_bit: clear_bit(DEV_CMD_PENDING, &uc->flags); +err_put: pm_runtime_put_sync(uc->dev); mutex_unlock(&uc->lock); diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c index 7902e1ec0fef..105243d83b2d 100644 --- a/drivers/vfio/pci/vfio_pci_config.c +++ b/drivers/vfio/pci/vfio_pci_config.c @@ -1806,7 +1806,8 @@ int vfio_config_init(struct vfio_pci_core_device *vdev) cpu_to_le16(PCI_COMMAND_MEMORY); } - if (!IS_ENABLED(CONFIG_VFIO_PCI_INTX) || vdev->nointx) + if (!IS_ENABLED(CONFIG_VFIO_PCI_INTX) || vdev->nointx || + vdev->pdev->irq == IRQ_NOTCONNECTED) vconfig[PCI_INTERRUPT_PIN] = 0; ret = vfio_cap_init(vdev); diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index f9ddf03a4b06..fe3a2b0ed910 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -719,15 +719,7 @@ EXPORT_SYMBOL_GPL(vfio_pci_core_finish_enable); static int vfio_pci_get_irq_count(struct vfio_pci_core_device *vdev, int irq_type) { if (irq_type == VFIO_PCI_INTX_IRQ_INDEX) { - u8 pin; - - if (!IS_ENABLED(CONFIG_VFIO_PCI_INTX) || - vdev->nointx || vdev->pdev->is_virtfn) - return 0; - - pci_read_config_byte(vdev->pdev, PCI_INTERRUPT_PIN, &pin); - - return pin ? 1 : 0; + return vdev->vconfig[PCI_INTERRUPT_PIN] ? 1 : 0; } else if (irq_type == VFIO_PCI_MSI_IRQ_INDEX) { u8 pos; u16 flags; diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c index 5cbcde32ff79..64d78944efa5 100644 --- a/drivers/vfio/pci/vfio_pci_intrs.c +++ b/drivers/vfio/pci/vfio_pci_intrs.c @@ -207,7 +207,7 @@ static int vfio_intx_enable(struct vfio_pci_core_device *vdev, if (!is_irq_none(vdev)) return -EINVAL; - if (!pdev->irq) + if (!pdev->irq || pdev->irq == IRQ_NOTCONNECTED) return -ENODEV; name = kasprintf(GFP_KERNEL_ACCOUNT, "vfio-intx(%s)", pci_name(pdev)); diff --git a/drivers/video/fbdev/core/bitblit.c b/drivers/video/fbdev/core/bitblit.c index 8587c9da0670..42e681a78136 100644 --- a/drivers/video/fbdev/core/bitblit.c +++ b/drivers/video/fbdev/core/bitblit.c @@ -59,12 +59,11 @@ static void bit_bmove(struct vc_data *vc, struct fb_info *info, int sy, } static void bit_clear(struct vc_data *vc, struct fb_info *info, int sy, - int sx, int height, int width) + int sx, int height, int width, int fg, int bg) { - int bgshift = (vc->vc_hi_font_mask) ? 13 : 12; struct fb_fillrect region; - region.color = attr_bgcol_ec(bgshift, vc, info); + region.color = bg; region.dx = sx * vc->vc_font.width; region.dy = sy * vc->vc_font.height; region.width = width * vc->vc_font.width; diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index e6640edec155..538e932055ca 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -1240,7 +1240,7 @@ static void fbcon_clear(struct vc_data *vc, int sy, int sx, int height, { struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_ops *ops = info->fbcon_par; - + int fg, bg; struct fbcon_display *p = &fb_display[vc->vc_num]; u_int y_break; @@ -1261,16 +1261,18 @@ static void fbcon_clear(struct vc_data *vc, int sy, int sx, int height, fbcon_clear_margins(vc, 0); } + fg = get_color(vc, info, vc->vc_video_erase_char, 1); + bg = get_color(vc, info, vc->vc_video_erase_char, 0); /* Split blits that cross physical y_wrap boundary */ y_break = p->vrows - p->yscroll; if (sy < y_break && sy + height - 1 >= y_break) { u_int b = y_break - sy; - ops->clear(vc, info, real_y(p, sy), sx, b, width); + ops->clear(vc, info, real_y(p, sy), sx, b, width, fg, bg); ops->clear(vc, info, real_y(p, sy + b), sx, height - b, - width); + width, fg, bg); } else - ops->clear(vc, info, real_y(p, sy), sx, height, width); + ops->clear(vc, info, real_y(p, sy), sx, height, width, fg, bg); } static void fbcon_putcs(struct vc_data *vc, const unsigned short *s, diff --git a/drivers/video/fbdev/core/fbcon.h b/drivers/video/fbdev/core/fbcon.h index 0eaf54a21151..25691d4b027b 100644 --- a/drivers/video/fbdev/core/fbcon.h +++ b/drivers/video/fbdev/core/fbcon.h @@ -55,7 +55,7 @@ struct fbcon_ops { void (*bmove)(struct vc_data *vc, struct fb_info *info, int sy, int sx, int dy, int dx, int height, int width); void (*clear)(struct vc_data *vc, struct fb_info *info, int sy, - int sx, int height, int width); + int sx, int height, int width, int fb, int bg); void (*putcs)(struct vc_data *vc, struct fb_info *info, const unsigned short *s, int count, int yy, int xx, int fg, int bg); @@ -116,42 +116,6 @@ static inline int mono_col(const struct fb_info *info) return (~(0xfff << max_len)) & 0xff; } -static inline int attr_col_ec(int shift, struct vc_data *vc, - struct fb_info *info, int is_fg) -{ - int is_mono01; - int col; - int fg; - int bg; - - if (!vc) - return 0; - - if (vc->vc_can_do_color) - return is_fg ? attr_fgcol(shift,vc->vc_video_erase_char) - : attr_bgcol(shift,vc->vc_video_erase_char); - - if (!info) - return 0; - - col = mono_col(info); - is_mono01 = info->fix.visual == FB_VISUAL_MONO01; - - if (attr_reverse(vc->vc_video_erase_char)) { - fg = is_mono01 ? col : 0; - bg = is_mono01 ? 0 : col; - } - else { - fg = is_mono01 ? 0 : col; - bg = is_mono01 ? col : 0; - } - - return is_fg ? fg : bg; -} - -#define attr_bgcol_ec(bgshift, vc, info) attr_col_ec(bgshift, vc, info, 0) -#define attr_fgcol_ec(fgshift, vc, info) attr_col_ec(fgshift, vc, info, 1) - /* * Scroll Method */ diff --git a/drivers/video/fbdev/core/fbcon_ccw.c b/drivers/video/fbdev/core/fbcon_ccw.c index 2789ace79634..9f4d65478554 100644 --- a/drivers/video/fbdev/core/fbcon_ccw.c +++ b/drivers/video/fbdev/core/fbcon_ccw.c @@ -78,14 +78,13 @@ static void ccw_bmove(struct vc_data *vc, struct fb_info *info, int sy, } static void ccw_clear(struct vc_data *vc, struct fb_info *info, int sy, - int sx, int height, int width) + int sx, int height, int width, int fg, int bg) { struct fbcon_ops *ops = info->fbcon_par; struct fb_fillrect region; - int bgshift = (vc->vc_hi_font_mask) ? 13 : 12; u32 vyres = GETVYRES(ops->p, info); - region.color = attr_bgcol_ec(bgshift,vc,info); + region.color = bg; region.dx = sy * vc->vc_font.height; region.dy = vyres - ((sx + width) * vc->vc_font.width); region.height = width * vc->vc_font.width; diff --git a/drivers/video/fbdev/core/fbcon_cw.c b/drivers/video/fbdev/core/fbcon_cw.c index 86a254c1b2b7..b18e31886da1 100644 --- a/drivers/video/fbdev/core/fbcon_cw.c +++ b/drivers/video/fbdev/core/fbcon_cw.c @@ -63,14 +63,13 @@ static void cw_bmove(struct vc_data *vc, struct fb_info *info, int sy, } static void cw_clear(struct vc_data *vc, struct fb_info *info, int sy, - int sx, int height, int width) + int sx, int height, int width, int fg, int bg) { struct fbcon_ops *ops = info->fbcon_par; struct fb_fillrect region; - int bgshift = (vc->vc_hi_font_mask) ? 13 : 12; u32 vxres = GETVXRES(ops->p, info); - region.color = attr_bgcol_ec(bgshift,vc,info); + region.color = bg; region.dx = vxres - ((sy + height) * vc->vc_font.height); region.dy = sx * vc->vc_font.width; region.height = width * vc->vc_font.width; diff --git a/drivers/video/fbdev/core/fbcon_ud.c b/drivers/video/fbdev/core/fbcon_ud.c index 23bc045769d0..b6b074cfd9dc 100644 --- a/drivers/video/fbdev/core/fbcon_ud.c +++ b/drivers/video/fbdev/core/fbcon_ud.c @@ -64,15 +64,14 @@ static void ud_bmove(struct vc_data *vc, struct fb_info *info, int sy, } static void ud_clear(struct vc_data *vc, struct fb_info *info, int sy, - int sx, int height, int width) + int sx, int height, int width, int fg, int bg) { struct fbcon_ops *ops = info->fbcon_par; struct fb_fillrect region; - int bgshift = (vc->vc_hi_font_mask) ? 13 : 12; u32 vyres = GETVYRES(ops->p, info); u32 vxres = GETVXRES(ops->p, info); - region.color = attr_bgcol_ec(bgshift,vc,info); + region.color = bg; region.dy = vyres - ((sy + height) * vc->vc_font.height); region.dx = vxres - ((sx + width) * vc->vc_font.width); region.width = width * vc->vc_font.width; diff --git a/drivers/video/fbdev/core/tileblit.c b/drivers/video/fbdev/core/tileblit.c index 2768eff247ba..b3aa0c6620c7 100644 --- a/drivers/video/fbdev/core/tileblit.c +++ b/drivers/video/fbdev/core/tileblit.c @@ -32,16 +32,14 @@ static void tile_bmove(struct vc_data *vc, struct fb_info *info, int sy, } static void tile_clear(struct vc_data *vc, struct fb_info *info, int sy, - int sx, int height, int width) + int sx, int height, int width, int fg, int bg) { struct fb_tilerect rect; - int bgshift = (vc->vc_hi_font_mask) ? 13 : 12; - int fgshift = (vc->vc_hi_font_mask) ? 9 : 8; rect.index = vc->vc_video_erase_char & ((vc->vc_hi_font_mask) ? 0x1ff : 0xff); - rect.fg = attr_fgcol_ec(fgshift, vc, info); - rect.bg = attr_bgcol_ec(bgshift, vc, info); + rect.fg = fg; + rect.bg = bg; rect.sx = sx; rect.sy = sy; rect.width = width; @@ -76,7 +74,42 @@ static void tile_putcs(struct vc_data *vc, struct fb_info *info, static void tile_clear_margins(struct vc_data *vc, struct fb_info *info, int color, int bottom_only) { - return; + unsigned int cw = vc->vc_font.width; + unsigned int ch = vc->vc_font.height; + unsigned int rw = info->var.xres - (vc->vc_cols*cw); + unsigned int bh = info->var.yres - (vc->vc_rows*ch); + unsigned int rs = info->var.xres - rw; + unsigned int bs = info->var.yres - bh; + unsigned int vwt = info->var.xres_virtual / cw; + unsigned int vht = info->var.yres_virtual / ch; + struct fb_tilerect rect; + + rect.index = vc->vc_video_erase_char & + ((vc->vc_hi_font_mask) ? 0x1ff : 0xff); + rect.fg = color; + rect.bg = color; + + if ((int) rw > 0 && !bottom_only) { + rect.sx = (info->var.xoffset + rs + cw - 1) / cw; + rect.sy = 0; + rect.width = (rw + cw - 1) / cw; + rect.height = vht; + if (rect.width + rect.sx > vwt) + rect.width = vwt - rect.sx; + if (rect.sx < vwt) + info->tileops->fb_tilefill(info, &rect); + } + + if ((int) bh > 0) { + rect.sx = info->var.xoffset / cw; + rect.sy = (info->var.yoffset + bs) / ch; + rect.width = rs / cw; + rect.height = (bh + ch - 1) / ch; + if (rect.height + rect.sy > vht) + rect.height = vht - rect.sy; + if (rect.sy < vht) + info->tileops->fb_tilefill(info, &rect); + } } static void tile_cursor(struct vc_data *vc, struct fb_info *info, int mode, diff --git a/drivers/video/fbdev/fsl-diu-fb.c b/drivers/video/fbdev/fsl-diu-fb.c index ce3c5b0b8f4e..53be4ab374cc 100644 --- a/drivers/video/fbdev/fsl-diu-fb.c +++ b/drivers/video/fbdev/fsl-diu-fb.c @@ -1829,6 +1829,7 @@ static int fsl_diu_remove(struct platform_device *pdev) int i; data = dev_get_drvdata(&pdev->dev); + device_remove_file(&pdev->dev, &data->dev_attr); disable_lcdc(&data->fsl_diu_info[0]); free_irq(data->irq, data->diu_reg); diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 93afbc0205ea..8e9e4d7964ee 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -2415,7 +2415,7 @@ bool virtqueue_enable_cb_delayed(struct virtqueue *_vq) struct vring_virtqueue *vq = to_vvq(_vq); if (vq->event_triggered) - vq->event_triggered = false; + data_race(vq->event_triggered = false); return vq->packed_ring ? virtqueue_enable_cb_delayed_packed(_vq) : virtqueue_enable_cb_delayed_split(_vq); diff --git a/drivers/xen/platform-pci.c b/drivers/xen/platform-pci.c index 544d3f9010b9..1db82da56db6 100644 --- a/drivers/xen/platform-pci.c +++ b/drivers/xen/platform-pci.c @@ -26,6 +26,8 @@ #define DRV_NAME "xen-platform-pci" +#define PCI_DEVICE_ID_XEN_PLATFORM_XS61 0x0002 + static unsigned long platform_mmio; static unsigned long platform_mmio_alloc; static unsigned long platform_mmiolen; @@ -174,6 +176,8 @@ pci_out: static const struct pci_device_id platform_pci_tbl[] = { {PCI_VENDOR_ID_XEN, PCI_DEVICE_ID_XEN_PLATFORM, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, + {PCI_VENDOR_ID_XEN, PCI_DEVICE_ID_XEN_PLATFORM_XS61, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, {0,} }; diff --git a/drivers/xen/xenbus/xenbus.h b/drivers/xen/xenbus/xenbus.h index 2754bdfadcb8..4ba73320694a 100644 --- a/drivers/xen/xenbus/xenbus.h +++ b/drivers/xen/xenbus/xenbus.h @@ -77,6 +77,7 @@ enum xb_req_state { struct xb_req_data { struct list_head list; wait_queue_head_t wq; + struct kref kref; struct xsd_sockmsg msg; uint32_t caller_req_id; enum xsd_sockmsg_type type; @@ -103,6 +104,7 @@ int xb_init_comms(void); void xb_deinit_comms(void); int xs_watch_msg(struct xs_watch_event *event); void xs_request_exit(struct xb_req_data *req); +void xs_free_req(struct kref *kref); int xenbus_match(struct device *_dev, struct device_driver *_drv); int xenbus_dev_probe(struct device *_dev); diff --git a/drivers/xen/xenbus/xenbus_comms.c b/drivers/xen/xenbus/xenbus_comms.c index e5fda0256feb..82df2da1b880 100644 --- a/drivers/xen/xenbus/xenbus_comms.c +++ b/drivers/xen/xenbus/xenbus_comms.c @@ -309,8 +309,8 @@ static int process_msg(void) virt_wmb(); req->state = xb_req_state_got_reply; req->cb(req); - } else - kfree(req); + } + kref_put(&req->kref, xs_free_req); } mutex_unlock(&xs_response_mutex); @@ -386,14 +386,13 @@ static int process_writes(void) state.req->msg.type = XS_ERROR; state.req->err = err; list_del(&state.req->list); - if (state.req->state == xb_req_state_aborted) - kfree(state.req); - else { + if (state.req->state != xb_req_state_aborted) { /* write err, then update state */ virt_wmb(); state.req->state = xb_req_state_got_reply; wake_up(&state.req->wq); } + kref_put(&state.req->kref, xs_free_req); mutex_unlock(&xb_write_mutex); diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c index 0792fda49a15..c495cff3da30 100644 --- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -406,7 +406,7 @@ void xenbus_dev_queue_reply(struct xb_req_data *req) mutex_unlock(&u->reply_mutex); kfree(req->body); - kfree(req); + kref_put(&req->kref, xs_free_req); kref_put(&u->kref, xenbus_file_free); diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index 25164d56c9d9..d3b6908110c6 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -966,9 +966,15 @@ static int __init xenbus_init(void) if (xen_pv_domain()) xen_store_domain_type = XS_PV; if (xen_hvm_domain()) + { xen_store_domain_type = XS_HVM; - if (xen_hvm_domain() && xen_initial_domain()) - xen_store_domain_type = XS_LOCAL; + err = hvm_get_parameter(HVM_PARAM_STORE_EVTCHN, &v); + if (err) + goto out_error; + xen_store_evtchn = (int)v; + if (!v && xen_initial_domain()) + xen_store_domain_type = XS_LOCAL; + } if (xen_pv_domain() && !xen_start_info->store_evtchn) xen_store_domain_type = XS_LOCAL; if (xen_pv_domain() && xen_start_info->store_evtchn) @@ -987,10 +993,6 @@ static int __init xenbus_init(void) xen_store_interface = gfn_to_virt(xen_store_gfn); break; case XS_HVM: - err = hvm_get_parameter(HVM_PARAM_STORE_EVTCHN, &v); - if (err) - goto out_error; - xen_store_evtchn = (int)v; err = hvm_get_parameter(HVM_PARAM_STORE_PFN, &v); if (err) goto out_error; diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c index 12e02eb01f59..a4dd92719e7a 100644 --- a/drivers/xen/xenbus/xenbus_xs.c +++ b/drivers/xen/xenbus/xenbus_xs.c @@ -112,6 +112,12 @@ static void xs_suspend_exit(void) wake_up_all(&xs_state_enter_wq); } +void xs_free_req(struct kref *kref) +{ + struct xb_req_data *req = container_of(kref, struct xb_req_data, kref); + kfree(req); +} + static uint32_t xs_request_enter(struct xb_req_data *req) { uint32_t rq_id; @@ -237,6 +243,12 @@ static void xs_send(struct xb_req_data *req, struct xsd_sockmsg *msg) req->caller_req_id = req->msg.req_id; req->msg.req_id = xs_request_enter(req); + /* + * Take 2nd ref. One for this thread, and the second for the + * xenbus_thread. + */ + kref_get(&req->kref); + mutex_lock(&xb_write_mutex); list_add_tail(&req->list, &xb_write_list); notify = list_is_singular(&xb_write_list); @@ -261,8 +273,8 @@ static void *xs_wait_for_reply(struct xb_req_data *req, struct xsd_sockmsg *msg) if (req->state == xb_req_state_queued || req->state == xb_req_state_wait_reply) req->state = xb_req_state_aborted; - else - kfree(req); + + kref_put(&req->kref, xs_free_req); mutex_unlock(&xb_write_mutex); return ret; @@ -291,6 +303,7 @@ int xenbus_dev_request_and_reply(struct xsd_sockmsg *msg, void *par) req->cb = xenbus_dev_queue_reply; req->par = par; req->user_req = true; + kref_init(&req->kref); xs_send(req, msg); @@ -319,6 +332,7 @@ static void *xs_talkv(struct xenbus_transaction t, req->num_vecs = num_vecs; req->cb = xs_wake_up; req->user_req = false; + kref_init(&req->kref); msg.req_id = 0; msg.tx_id = t.id; diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index dffce67fd288..2fa739f2f7bb 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -109,25 +109,6 @@ static struct linux_binfmt elf_format = { #define BAD_ADDR(x) (unlikely((unsigned long)(x) >= TASK_SIZE)) -static int set_brk(unsigned long start, unsigned long end, int prot) -{ - start = ELF_PAGEALIGN(start); - end = ELF_PAGEALIGN(end); - if (end > start) { - /* - * Map the last of the bss segment. - * If the header is requesting these pages to be - * executable, honour that (ppc32 needs this). - */ - int error = vm_brk_flags(start, end - start, - prot & PROT_EXEC ? VM_EXEC : 0); - if (error) - return error; - } - current->mm->start_brk = current->mm->brk = end; - return 0; -} - /* We need to explicitly zero any fractional pages after the data section (i.e. bss). This would contain the junk from the file that should not @@ -248,7 +229,7 @@ create_elf_tables(struct linux_binprm *bprm, const struct elfhdr *exec, } while (0) #ifdef ARCH_DLINFO - /* + /* * ARCH_DLINFO must come first so PPC can do its special alignment of * AUXV. * update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT() in @@ -401,6 +382,51 @@ static unsigned long elf_map(struct file *filep, unsigned long addr, return(map_addr); } +static unsigned long elf_load(struct file *filep, unsigned long addr, + const struct elf_phdr *eppnt, int prot, int type, + unsigned long total_size) +{ + unsigned long zero_start, zero_end; + unsigned long map_addr; + + if (eppnt->p_filesz) { + map_addr = elf_map(filep, addr, eppnt, prot, type, total_size); + if (BAD_ADDR(map_addr)) + return map_addr; + if (eppnt->p_memsz > eppnt->p_filesz) { + zero_start = map_addr + ELF_PAGEOFFSET(eppnt->p_vaddr) + + eppnt->p_filesz; + zero_end = map_addr + ELF_PAGEOFFSET(eppnt->p_vaddr) + + eppnt->p_memsz; + + /* Zero the end of the last mapped page */ + padzero(zero_start); + } + } else { + map_addr = zero_start = ELF_PAGESTART(addr); + zero_end = zero_start + ELF_PAGEOFFSET(eppnt->p_vaddr) + + eppnt->p_memsz; + } + if (eppnt->p_memsz > eppnt->p_filesz) { + /* + * Map the last of the segment. + * If the header is requesting these pages to be + * executable, honour that (ppc32 needs this). + */ + int error; + + zero_start = ELF_PAGEALIGN(zero_start); + zero_end = ELF_PAGEALIGN(zero_end); + + error = vm_brk_flags(zero_start, zero_end - zero_start, + prot & PROT_EXEC ? VM_EXEC : 0); + if (error) + map_addr = error; + } + return map_addr; +} + + static unsigned long total_mapping_size(const struct elf_phdr *phdr, int nr) { elf_addr_t min_addr = -1; @@ -829,8 +855,8 @@ static int load_elf_binary(struct linux_binprm *bprm) unsigned long error; struct elf_phdr *elf_ppnt, *elf_phdata, *interp_elf_phdata = NULL; struct elf_phdr *elf_property_phdata = NULL; - unsigned long elf_bss, elf_brk; - int bss_prot = 0; + unsigned long elf_brk; + bool brk_moved = false; int retval, i; unsigned long elf_entry; unsigned long e_entry; @@ -1021,8 +1047,7 @@ out_free_interp: executable_stack); if (retval < 0) goto out_free_dentry; - - elf_bss = 0; + elf_brk = 0; start_code = ~0UL; @@ -1042,33 +1067,6 @@ out_free_interp: if (elf_ppnt->p_type != PT_LOAD) continue; - if (unlikely (elf_brk > elf_bss)) { - unsigned long nbyte; - - /* There was a PT_LOAD segment with p_memsz > p_filesz - before this one. Map anonymous pages, if needed, - and clear the area. */ - retval = set_brk(elf_bss + load_bias, - elf_brk + load_bias, - bss_prot); - if (retval) - goto out_free_dentry; - nbyte = ELF_PAGEOFFSET(elf_bss); - if (nbyte) { - nbyte = ELF_MIN_ALIGN - nbyte; - if (nbyte > elf_brk - elf_bss) - nbyte = elf_brk - elf_bss; - if (clear_user((void __user *)elf_bss + - load_bias, nbyte)) { - /* - * This bss-zeroing can fail if the ELF - * file specifies odd protections. So - * we don't check the return value - */ - } - } - } - elf_prot = make_prot(elf_ppnt->p_flags, &arch_state, !!interpreter, false); @@ -1096,47 +1094,7 @@ out_free_interp: * Header for ET_DYN binaries to calculate the * randomization (load_bias) for all the LOAD * Program Headers. - * - * There are effectively two types of ET_DYN - * binaries: programs (i.e. PIE: ET_DYN with INTERP) - * and loaders (ET_DYN without INTERP, since they - * _are_ the ELF interpreter). The loaders must - * be loaded away from programs since the program - * may otherwise collide with the loader (especially - * for ET_EXEC which does not have a randomized - * position). For example to handle invocations of - * "./ld.so someprog" to test out a new version of - * the loader, the subsequent program that the - * loader loads must avoid the loader itself, so - * they cannot share the same load range. Sufficient - * room for the brk must be allocated with the - * loader as well, since brk must be available with - * the loader. - * - * Therefore, programs are loaded offset from - * ELF_ET_DYN_BASE and loaders are loaded into the - * independently randomized mmap region (0 load_bias - * without MAP_FIXED nor MAP_FIXED_NOREPLACE). */ - if (interpreter) { - load_bias = ELF_ET_DYN_BASE; - if (current->flags & PF_RANDOMIZE) - load_bias += arch_mmap_rnd(); - alignment = maximum_alignment(elf_phdata, elf_ex->e_phnum); - if (alignment) - load_bias &= ~(alignment - 1); - elf_flags |= MAP_FIXED_NOREPLACE; - } else - load_bias = 0; - - /* - * Since load_bias is used for all subsequent loading - * calculations, we must lower it by the first vaddr - * so that the remaining calculations based on the - * ELF vaddrs will be correctly offset. The result - * is then page aligned. - */ - load_bias = ELF_PAGESTART(load_bias - vaddr); /* * Calculate the entire size of the ELF mapping @@ -1162,9 +1120,90 @@ out_free_interp: retval = -EINVAL; goto out_free_dentry; } + + /* Calculate any requested alignment. */ + alignment = maximum_alignment(elf_phdata, elf_ex->e_phnum); + + /** + * DOC: PIE handling + * + * There are effectively two types of ET_DYN ELF + * binaries: programs (i.e. PIE: ET_DYN with + * PT_INTERP) and loaders (i.e. static PIE: ET_DYN + * without PT_INTERP, usually the ELF interpreter + * itself). Loaders must be loaded away from programs + * since the program may otherwise collide with the + * loader (especially for ET_EXEC which does not have + * a randomized position). + * + * For example, to handle invocations of + * "./ld.so someprog" to test out a new version of + * the loader, the subsequent program that the + * loader loads must avoid the loader itself, so + * they cannot share the same load range. Sufficient + * room for the brk must be allocated with the + * loader as well, since brk must be available with + * the loader. + * + * Therefore, programs are loaded offset from + * ELF_ET_DYN_BASE and loaders are loaded into the + * independently randomized mmap region (0 load_bias + * without MAP_FIXED nor MAP_FIXED_NOREPLACE). + * + * See below for "brk" handling details, which is + * also affected by program vs loader and ASLR. + */ + if (interpreter) { + /* On ET_DYN with PT_INTERP, we do the ASLR. */ + load_bias = ELF_ET_DYN_BASE; + if (current->flags & PF_RANDOMIZE) + load_bias += arch_mmap_rnd(); + /* Adjust alignment as requested. */ + if (alignment) + load_bias &= ~(alignment - 1); + elf_flags |= MAP_FIXED_NOREPLACE; + } else { + /* + * For ET_DYN without PT_INTERP, we rely on + * the architectures's (potentially ASLR) mmap + * base address (via a load_bias of 0). + * + * When a large alignment is requested, we + * must do the allocation at address "0" right + * now to discover where things will load so + * that we can adjust the resulting alignment. + * In this case (load_bias != 0), we can use + * MAP_FIXED_NOREPLACE to make sure the mapping + * doesn't collide with anything. + */ + if (alignment > ELF_MIN_ALIGN) { + load_bias = elf_load(bprm->file, 0, elf_ppnt, + elf_prot, elf_flags, total_size); + if (BAD_ADDR(load_bias)) { + retval = IS_ERR_VALUE(load_bias) ? + PTR_ERR((void*)load_bias) : -EINVAL; + goto out_free_dentry; + } + vm_munmap(load_bias, total_size); + /* Adjust alignment as requested. */ + if (alignment) + load_bias &= ~(alignment - 1); + elf_flags |= MAP_FIXED_NOREPLACE; + } else + load_bias = 0; + } + + /* + * Since load_bias is used for all subsequent loading + * calculations, we must lower it by the first vaddr + * so that the remaining calculations based on the + * ELF vaddrs will be correctly offset. The result + * is then page aligned. + */ + load_bias = ELF_PAGESTART(load_bias - vaddr); } - error = elf_map(bprm->file, load_bias + vaddr, elf_ppnt, + error = elf_load(bprm->file, load_bias + vaddr, elf_ppnt, elf_prot, elf_flags, total_size); if (BAD_ADDR(error)) { retval = IS_ERR((void *)error) ? @@ -1212,41 +1251,23 @@ out_free_interp: k = elf_ppnt->p_vaddr + elf_ppnt->p_filesz; - if (k > elf_bss) - elf_bss = k; if ((elf_ppnt->p_flags & PF_X) && end_code < k) end_code = k; if (end_data < k) end_data = k; k = elf_ppnt->p_vaddr + elf_ppnt->p_memsz; - if (k > elf_brk) { - bss_prot = elf_prot; + if (k > elf_brk) elf_brk = k; - } } e_entry = elf_ex->e_entry + load_bias; phdr_addr += load_bias; - elf_bss += load_bias; elf_brk += load_bias; start_code += load_bias; end_code += load_bias; start_data += load_bias; end_data += load_bias; - /* Calling set_brk effectively mmaps the pages that we need - * for the bss and break sections. We must do this before - * mapping in the interpreter, to make sure it doesn't wind - * up getting placed where the bss needs to go. - */ - retval = set_brk(elf_bss, elf_brk, bss_prot); - if (retval) - goto out_free_dentry; - if (likely(elf_bss != elf_brk) && unlikely(padzero(elf_bss))) { - retval = -EFAULT; /* Nobody gets to see this, but.. */ - goto out_free_dentry; - } - if (interpreter) { elf_entry = load_elf_interp(interp_elf_ex, interpreter, @@ -1302,24 +1323,44 @@ out_free_interp: mm->end_data = end_data; mm->start_stack = bprm->p; - if ((current->flags & PF_RANDOMIZE) && (snapshot_randomize_va_space > 1)) { + /** + * DOC: "brk" handling + * + * For architectures with ELF randomization, when executing a + * loader directly (i.e. static PIE: ET_DYN without PT_INTERP), + * move the brk area out of the mmap region and into the unused + * ELF_ET_DYN_BASE region. Since "brk" grows up it may collide + * early with the stack growing down or other regions being put + * into the mmap region by the kernel (e.g. vdso). + * + * In the CONFIG_COMPAT_BRK case, though, everything is turned + * off because we're not allowed to move the brk at all. + */ + if (!IS_ENABLED(CONFIG_COMPAT_BRK) && + IS_ENABLED(CONFIG_ARCH_HAS_ELF_RANDOMIZE) && + elf_ex->e_type == ET_DYN && !interpreter) { + elf_brk = ELF_ET_DYN_BASE; + /* This counts as moving the brk, so let brk(2) know. */ + brk_moved = true; + } + mm->start_brk = mm->brk = ELF_PAGEALIGN(elf_brk); + + if ((current->flags & PF_RANDOMIZE) && snapshot_randomize_va_space > 1) { /* - * For architectures with ELF randomization, when executing - * a loader directly (i.e. no interpreter listed in ELF - * headers), move the brk area out of the mmap region - * (since it grows up, and may collide early with the stack - * growing down), and into the unused ELF_ET_DYN_BASE region. + * If we didn't move the brk to ELF_ET_DYN_BASE (above), + * leave a gap between .bss and brk. */ - if (IS_ENABLED(CONFIG_ARCH_HAS_ELF_RANDOMIZE) && - elf_ex->e_type == ET_DYN && !interpreter) { - mm->brk = mm->start_brk = ELF_ET_DYN_BASE; - } + if (!brk_moved) + mm->brk = mm->start_brk = mm->brk + PAGE_SIZE; mm->brk = mm->start_brk = arch_randomize_brk(mm); + brk_moved = true; + } + #ifdef compat_brk_randomized + if (brk_moved) current->brk_randomized = 1; #endif - } if (current->personality & MMAP_PAGE_ZERO) { /* Why this, you ask??? Well SVr4 maps page 0 as read-only, @@ -1522,7 +1563,7 @@ static void fill_elf_note_phdr(struct elf_phdr *phdr, int sz, loff_t offset) phdr->p_align = 0; } -static void fill_note(struct memelfnote *note, const char *name, int type, +static void fill_note(struct memelfnote *note, const char *name, int type, unsigned int sz, void *data) { note->name = name; @@ -2005,8 +2046,8 @@ static int elf_dump_thread_status(long signr, struct elf_thread_status *t) t->num_notes = 0; fill_prstatus(&t->prstatus.common, p, signr); - elf_core_copy_task_regs(p, &t->prstatus.pr_reg); - + elf_core_copy_task_regs(p, &t->prstatus.pr_reg); + fill_note(&t->notes[0], "CORE", NT_PRSTATUS, sizeof(t->prstatus), &(t->prstatus)); t->num_notes++; @@ -2296,7 +2337,7 @@ static int elf_core_dump(struct coredump_params *cprm) if (!elf_core_write_extra_phdrs(cprm, offset)) goto end_coredump; - /* write out the notes section */ + /* write out the notes section */ if (!write_note_info(&info, cprm)) goto end_coredump; diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index c71a40927315..b2d3b6e43bb5 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -1603,7 +1603,7 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm) if (!elf_core_write_extra_phdrs(cprm, offset)) goto end_coredump; - /* write out the notes section */ + /* write out the notes section */ if (!writenote(thread_list->notes, cprm)) goto end_coredump; if (!writenote(&psinfo_note, cprm)) diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 0dcf7fecaf55..91440ef79a26 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1678,6 +1678,17 @@ void btrfs_reclaim_bgs_work(struct work_struct *work) up_write(&space_info->groups_sem); goto next; } + + /* + * Cache the zone_unusable value before turning the block group + * to read only. As soon as the block group is read only it's + * zone_unusable value gets moved to the block group's read-only + * bytes and isn't available for calculations anymore. We also + * cache it before unlocking the block group, to prevent races + * (reports from KCSAN and such tools) with tasks updating it. + */ + zone_unusable = bg->zone_unusable; + spin_unlock(&bg->lock); /* @@ -1693,13 +1704,6 @@ void btrfs_reclaim_bgs_work(struct work_struct *work) goto next; } - /* - * Cache the zone_unusable value before turning the block group - * to read only. As soon as the blog group is read only it's - * zone_unusable value gets moved to the block group's read-only - * bytes and isn't available for calculations anymore. - */ - zone_unusable = bg->zone_unusable; ret = inc_block_group_ro(bg, 0); up_write(&space_info->groups_sem); if (ret < 0) diff --git a/fs/btrfs/discard.c b/fs/btrfs/discard.c index bd9dde374e5d..a90f3cb83c70 100644 --- a/fs/btrfs/discard.c +++ b/fs/btrfs/discard.c @@ -78,8 +78,6 @@ static void __add_to_discard_list(struct btrfs_discard_ctl *discard_ctl, struct btrfs_block_group *block_group) { lockdep_assert_held(&discard_ctl->lock); - if (!btrfs_run_discard_work(discard_ctl)) - return; if (list_empty(&block_group->discard_list) || block_group->discard_index == BTRFS_DISCARD_INDEX_UNUSED) { @@ -102,6 +100,9 @@ static void add_to_discard_list(struct btrfs_discard_ctl *discard_ctl, if (!btrfs_is_block_group_data_only(block_group)) return; + if (!btrfs_run_discard_work(discard_ctl)) + return; + spin_lock(&discard_ctl->lock); __add_to_discard_list(discard_ctl, block_group); spin_unlock(&discard_ctl->lock); @@ -151,13 +152,7 @@ static bool remove_from_discard_list(struct btrfs_discard_ctl *discard_ctl, block_group->discard_eligible_time = 0; queued = !list_empty(&block_group->discard_list); list_del_init(&block_group->discard_list); - /* - * If the block group is currently running in the discard workfn, we - * don't want to deref it, since it's still being used by the workfn. - * The workfn will notice this case and deref the block group when it is - * finished. - */ - if (queued && !running) + if (queued) btrfs_put_block_group(block_group); spin_unlock(&discard_ctl->lock); @@ -233,6 +228,18 @@ again: block_group->used != 0) { if (btrfs_is_block_group_data_only(block_group)) { __add_to_discard_list(discard_ctl, block_group); + /* + * The block group must have been moved to other + * discard list even if discard was disabled in + * the meantime or a transaction abort happened, + * otherwise we can end up in an infinite loop, + * always jumping into the 'again' label and + * keep getting this block group over and over + * in case there are no other block groups in + * the discard lists. + */ + ASSERT(block_group->discard_index != + BTRFS_DISCARD_INDEX_UNUSED); } else { list_del_init(&block_group->discard_list); btrfs_put_block_group(block_group); @@ -243,9 +250,10 @@ again: block_group->discard_cursor = block_group->start; block_group->discard_state = BTRFS_DISCARD_EXTENTS; } - discard_ctl->block_group = block_group; } if (block_group) { + btrfs_get_block_group(block_group); + discard_ctl->block_group = block_group; *discard_state = block_group->discard_state; *discard_index = block_group->discard_index; } @@ -469,9 +477,20 @@ static void btrfs_discard_workfn(struct work_struct *work) block_group = peek_discard_list(discard_ctl, &discard_state, &discard_index, now); - if (!block_group || !btrfs_run_discard_work(discard_ctl)) + if (!block_group) return; + if (!btrfs_run_discard_work(discard_ctl)) { + spin_lock(&discard_ctl->lock); + btrfs_put_block_group(block_group); + discard_ctl->block_group = NULL; + spin_unlock(&discard_ctl->lock); + return; + } if (now < block_group->discard_eligible_time) { + spin_lock(&discard_ctl->lock); + btrfs_put_block_group(block_group); + discard_ctl->block_group = NULL; + spin_unlock(&discard_ctl->lock); btrfs_discard_schedule_work(discard_ctl, false); return; } @@ -523,15 +542,7 @@ static void btrfs_discard_workfn(struct work_struct *work) spin_lock(&discard_ctl->lock); discard_ctl->prev_discard = trimmed; discard_ctl->prev_discard_time = now; - /* - * If the block group was removed from the discard list while it was - * running in this workfn, then we didn't deref it, since this function - * still owned that reference. But we set the discard_ctl->block_group - * back to NULL, so we can use that condition to know that now we need - * to deref the block_group. - */ - if (discard_ctl->block_group == NULL) - btrfs_put_block_group(block_group); + btrfs_put_block_group(block_group); discard_ctl->block_group = NULL; __btrfs_discard_schedule_work(discard_ctl, now, false); spin_unlock(&discard_ctl->lock); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index de4f590fe30f..8c0da0025bc7 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -4641,6 +4641,14 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) /* clear out the rbtree of defraggable inodes */ btrfs_cleanup_defrag_inodes(fs_info); + /* + * Handle the error fs first, as it will flush and wait for all ordered + * extents. This will generate delayed iputs, thus we want to handle + * it first. + */ + if (unlikely(BTRFS_FS_ERROR(fs_info))) + btrfs_error_commit_super(fs_info); + /* * Wait for any fixup workers to complete. * If we don't wait for them here and they are still running by the time @@ -4661,6 +4669,19 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) */ btrfs_flush_workqueue(fs_info->delalloc_workers); + /* + * We can have ordered extents getting their last reference dropped from + * the fs_info->workers queue because for async writes for data bios we + * queue a work for that queue, at btrfs_wq_submit_bio(), that runs + * run_one_async_done() which calls btrfs_bio_end_io() in case the bio + * has an error, and that later function can do the final + * btrfs_put_ordered_extent() on the ordered extent attached to the bio, + * which adds a delayed iput for the inode. So we must flush the queue + * so that we don't have delayed iputs after committing the current + * transaction below and stopping the cleaner and transaction kthreads. + */ + btrfs_flush_workqueue(fs_info->workers); + /* * When finishing a compressed write bio we schedule a work queue item * to finish an ordered extent - btrfs_finish_compressed_write_work() @@ -4730,9 +4751,6 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) btrfs_err(fs_info, "commit super ret %d", ret); } - if (BTRFS_FS_ERROR(fs_info)) - btrfs_error_commit_super(fs_info); - kthread_stop(fs_info->transaction_kthread); kthread_stop(fs_info->cleaner_kthread); @@ -4888,10 +4906,6 @@ static void btrfs_error_commit_super(struct btrfs_fs_info *fs_info) /* cleanup FS via transaction */ btrfs_cleanup_transaction(fs_info); - mutex_lock(&fs_info->cleaner_mutex); - btrfs_run_delayed_iputs(fs_info); - mutex_unlock(&fs_info->cleaner_mutex); - down_write(&fs_info->cleanup_work_sem); up_write(&fs_info->cleanup_work_sem); } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 9040108eda64..5395e27f9e89 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -179,6 +179,14 @@ search_again: ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item); num_refs = btrfs_extent_refs(leaf, ei); + if (unlikely(num_refs == 0)) { + ret = -EUCLEAN; + btrfs_err(fs_info, + "unexpected zero reference count for extent item (%llu %u %llu)", + key.objectid, key.type, key.offset); + btrfs_abort_transaction(trans, ret); + goto out_free; + } extent_flags = btrfs_extent_flags(leaf, ei); } else { ret = -EINVAL; @@ -190,8 +198,6 @@ search_again: goto out_free; } - - BUG_ON(num_refs == 0); } else { num_refs = 0; extent_flags = 0; @@ -221,10 +227,19 @@ search_again: goto search_again; } spin_lock(&head->lock); - if (head->extent_op && head->extent_op->update_flags) + if (head->extent_op && head->extent_op->update_flags) { extent_flags |= head->extent_op->flags_to_set; - else - BUG_ON(num_refs == 0); + } else if (unlikely(num_refs == 0)) { + spin_unlock(&head->lock); + mutex_unlock(&head->mutex); + spin_unlock(&delayed_refs->lock); + ret = -EUCLEAN; + btrfs_err(fs_info, + "unexpected zero reference count for extent %llu (%s)", + bytenr, metadata ? "metadata" : "data"); + btrfs_abort_transaction(trans, ret); + goto out_free; + } num_refs += head->ref_mod; spin_unlock(&head->lock); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 76433c82b075..71f301326780 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4469,10 +4469,10 @@ struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info, return eb; } -#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info, u64 start) { +#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS struct extent_buffer *eb, *exists = NULL; int ret; @@ -4508,8 +4508,11 @@ again: free_eb: btrfs_release_extent_buffer(eb); return exists; -} +#else + /* Stub to avoid linker error when compiled with optimizations turned off. */ + return NULL; #endif +} static struct extent_buffer *grab_extent_buffer( struct btrfs_fs_info *fs_info, struct page *page) diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index d6cda0b2e925..fd6ea3fcab33 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -2977,6 +2977,7 @@ static int relocate_one_page(struct inode *inode, struct file_ra_state *ra, int ret; ASSERT(page_index <= last_index); +again: page = find_lock_page(inode->i_mapping, page_index); if (!page) { page_cache_sync_readahead(inode->i_mapping, ra, NULL, @@ -2998,6 +2999,11 @@ static int relocate_one_page(struct inode *inode, struct file_ra_state *ra, ret = -EIO; goto release_page; } + if (page->mapping != inode->i_mapping) { + unlock_page(page); + put_page(page); + goto again; + } } /* diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index a2b95ccb4cf5..0735decec99b 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -431,10 +431,8 @@ static int fs_path_ensure_buf(struct fs_path *p, int len) if (p->buf_len >= len) return 0; - if (len > PATH_MAX) { - WARN_ON(1); - return -ENOMEM; - } + if (WARN_ON(len > PATH_MAX)) + return -ENAMETOOLONG; path_len = p->end - p->start; old_buf_len = p->buf_len; diff --git a/fs/coredump.c b/fs/coredump.c index 4d332f147137..2e2b66aed59d 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -493,7 +493,9 @@ static int umh_pipe_setup(struct subprocess_info *info, struct cred *new) { struct file *files[2]; struct coredump_params *cp = (struct coredump_params *)info->data; - int err = create_pipe_files(files, 0); + int err; + + err = create_pipe_files(files, 0); if (err) return err; @@ -501,10 +503,13 @@ static int umh_pipe_setup(struct subprocess_info *info, struct cred *new) err = replace_fd(0, files[0], 0); fput(files[0]); + if (err < 0) + return err; + /* and disallow core files too */ current->signal->rlim[RLIMIT_CORE] = (struct rlimit){1, 1}; - return err; + return 0; } void do_coredump(const kernel_siginfo_t *siginfo) diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index 2c797eb519da..51a641822d6c 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -1863,8 +1863,8 @@ static int dlm_tcp_listen_validate(void) { /* We don't support multi-homed hosts */ if (dlm_local_count > 1) { - log_print("TCP protocol can't handle multi-homed hosts, try SCTP"); - return -EINVAL; + log_print("Detect multi-homed hosts but use only the first IP address."); + log_print("Try SCTP, if you want to enable multi-link."); } return 0; diff --git a/fs/exec.c b/fs/exec.c index 0149f828d409..05ec9e6966cf 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -170,7 +170,7 @@ SYSCALL_DEFINE1(uselib, const char __user *, library) exit: fput(file); out: - return error; + return error; } #endif /* #ifdef CONFIG_USELIB */ diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index fbd0329cf254..9efe97f3721b 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -638,8 +638,8 @@ static int ext4_has_free_clusters(struct ext4_sb_info *sbi, /* Hm, nope. Are (enough) root reserved clusters available? */ if (uid_eq(sbi->s_resuid, current_fsuid()) || (!gid_eq(sbi->s_resgid, GLOBAL_ROOT_GID) && in_group_p(sbi->s_resgid)) || - capable(CAP_SYS_RESOURCE) || - (flags & EXT4_MB_USE_ROOT_BLOCKS)) { + (flags & EXT4_MB_USE_ROOT_BLOCKS) || + capable(CAP_SYS_RESOURCE)) { if (free_clusters >= (nclusters + dirty_clusters + resv_clusters)) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index d2363b325cd8..935a6971fe27 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2731,6 +2731,13 @@ static int ext4_check_opt_consistency(struct fs_context *fc, } if (is_remount) { + if (!sbi->s_journal && + ctx_test_mount_opt(ctx, EXT4_MOUNT_DATA_ERR_ABORT)) { + ext4_msg(NULL, KERN_WARNING, + "Remounting fs w/o journal so ignoring data_err option"); + ctx_clear_mount_opt(ctx, EXT4_MOUNT_DATA_ERR_ABORT); + } + if (ctx_test_mount_opt(ctx, EXT4_MOUNT_DAX_ALWAYS) && (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)) { ext4_msg(NULL, KERN_ERR, "can't mount with " @@ -5310,6 +5317,11 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) "data=, fs mounted w/o journal"); goto failed_mount3a; } + if (test_opt(sb, DATA_ERR_ABORT)) { + ext4_msg(sb, KERN_ERR, + "can't mount with data_err=abort, fs mounted w/o journal"); + goto failed_mount3a; + } sbi->s_def_mount_opt &= ~EXT4_MOUNT_JOURNAL_CHECKSUM; clear_opt(sb, JOURNAL_CHECKSUM); clear_opt(sb, DATA_FLAGS); diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index dcf4a9e77ad4..3bdc3f1043fa 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1370,6 +1370,8 @@ static int fuse_link(struct dentry *entry, struct inode *newdir, else if (err == -EINTR) fuse_invalidate_attr(inode); + if (err == -ENOSYS) + err = -EPERM; return err; } diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 6ba8460f5331..428c1db295fa 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -885,11 +885,12 @@ static void run_queue(struct gfs2_glock *gl, const int nonblock) __releases(&gl->gl_lockref.lock) __acquires(&gl->gl_lockref.lock) { - struct gfs2_holder *gh = NULL; + struct gfs2_holder *gh; if (test_and_set_bit(GLF_LOCK, &gl->gl_flags)) return; + /* While a demote is in progress, the GLF_LOCK flag must be set. */ GLOCK_BUG_ON(gl, test_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags)); if (test_bit(GLF_DEMOTE, &gl->gl_flags) && @@ -901,18 +902,22 @@ __acquires(&gl->gl_lockref.lock) set_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags); GLOCK_BUG_ON(gl, gl->gl_demote_state == LM_ST_EXCLUSIVE); gl->gl_target = gl->gl_demote_state; + do_xmote(gl, NULL, gl->gl_target); + return; } else { if (test_bit(GLF_DEMOTE, &gl->gl_flags)) gfs2_demote_wake(gl); if (do_promote(gl) == 0) goto out_unlock; gh = find_first_waiter(gl); + if (!gh) + goto out_unlock; gl->gl_target = gh->gh_state; if (!(gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB))) do_error(gl, 0); /* Fail queued try locks */ + do_xmote(gl, gh, gl->gl_target); + return; } - do_xmote(gl, gh, gl->gl_target); - return; out_sched: clear_bit(GLF_LOCK, &gl->gl_flags); diff --git a/fs/namespace.c b/fs/namespace.c index 57166cc7e511..211a81240680 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -629,15 +629,11 @@ int __legitimize_mnt(struct vfsmount *bastard, unsigned seq) return 0; mnt = real_mount(bastard); mnt_add_count(mnt, 1); - smp_mb(); // see mntput_no_expire() + smp_mb(); // see mntput_no_expire() and do_umount() if (likely(!read_seqretry(&mount_lock, seq))) return 0; - if (bastard->mnt_flags & MNT_SYNC_UMOUNT) { - mnt_add_count(mnt, -1); - return 1; - } lock_mount_hash(); - if (unlikely(bastard->mnt_flags & MNT_DOOMED)) { + if (unlikely(bastard->mnt_flags & (MNT_SYNC_UMOUNT | MNT_DOOMED))) { mnt_add_count(mnt, -1); unlock_mount_hash(); return 1; @@ -1707,6 +1703,7 @@ static int do_umount(struct mount *mnt, int flags) umount_tree(mnt, UMOUNT_PROPAGATE); retval = 0; } else { + smp_mb(); // paired with __legitimize_mnt() shrink_submounts(mnt); retval = -EBUSY; if (!propagate_mount_busy(mnt, 2)) { diff --git a/fs/nfs/client.c b/fs/nfs/client.c index a8930e6c417f..de4ad41b14e2 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -1052,6 +1052,8 @@ struct nfs_server *nfs_create_server(struct fs_context *fc) if (server->namelen == 0 || server->namelen > NFS2_MAXNAMLEN) server->namelen = NFS2_MAXNAMLEN; } + /* Linux 'subtree_check' borkenness mandates this setting */ + server->fh_expire_type = NFS_FH_VOL_RENAME; if (!(fattr->valid & NFS_ATTR_FATTR)) { error = ctx->nfs_mod->rpc_ops->getattr(server, ctx->mntfh, diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 6363bbc37f42..17b38da17288 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -297,7 +297,8 @@ nfs_start_delegation_return_locked(struct nfs_inode *nfsi) if (delegation == NULL) goto out; spin_lock(&delegation->lock); - if (!test_and_set_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) { + if (delegation->inode && + !test_and_set_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) { clear_bit(NFS_DELEGATION_RETURN_DELAYED, &delegation->flags); /* Refcount matched in nfs_end_delegation_return() */ ret = nfs_get_delegation(delegation); diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 70660ff248b7..1876978107ca 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -2632,6 +2632,18 @@ nfs_unblock_rename(struct rpc_task *task, struct nfs_renamedata *data) unblock_revalidate(new_dentry); } +static bool nfs_rename_is_unsafe_cross_dir(struct dentry *old_dentry, + struct dentry *new_dentry) +{ + struct nfs_server *server = NFS_SB(old_dentry->d_sb); + + if (old_dentry->d_parent != new_dentry->d_parent) + return false; + if (server->fh_expire_type & NFS_FH_RENAME_UNSAFE) + return !(server->fh_expire_type & NFS_FH_NOEXPIRE_WITH_OPEN); + return true; +} + /* * RENAME * FIXME: Some nfsds, like the Linux user space nfsd, may generate a @@ -2719,7 +2731,8 @@ int nfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, } - if (S_ISREG(old_inode->i_mode)) + if (S_ISREG(old_inode->i_mode) && + nfs_rename_is_unsafe_cross_dir(old_dentry, new_dentry)) nfs_sync_inode(old_inode); task = nfs_async_rename(old_dir, new_dir, old_dentry, new_dentry, must_unblock ? nfs_unblock_rename : NULL); diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c index acf4b88889dc..d5f1fbfd9a0c 100644 --- a/fs/nfs/filelayout/filelayoutdev.c +++ b/fs/nfs/filelayout/filelayoutdev.c @@ -75,6 +75,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, struct page *scratch; struct list_head dsaddrs; struct nfs4_pnfs_ds_addr *da; + struct net *net = server->nfs_client->cl_net; /* set up xdr stream */ scratch = alloc_page(gfp_flags); @@ -158,8 +159,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, mp_count = be32_to_cpup(p); /* multipath count */ for (j = 0; j < mp_count; j++) { - da = nfs4_decode_mp_ds_addr(server->nfs_client->cl_net, - &stream, gfp_flags); + da = nfs4_decode_mp_ds_addr(net, &stream, gfp_flags); if (da) list_add_tail(&da->da_node, &dsaddrs); } @@ -169,7 +169,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, goto out_err_free_deviceid; } - dsaddr->ds_list[i] = nfs4_pnfs_ds_add(&dsaddrs, gfp_flags); + dsaddr->ds_list[i] = nfs4_pnfs_ds_add(net, &dsaddrs, gfp_flags); if (!dsaddr->ds_list[i]) goto out_err_drain_dsaddrs; diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 8056b05bd8dc..07e5ea64dcd6 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -1255,6 +1255,7 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg, case -ECONNRESET: case -EHOSTDOWN: case -EHOSTUNREACH: + case -ENETDOWN: case -ENETUNREACH: case -EADDRINUSE: case -ENOBUFS: diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index e028f5a0ef5f..d21c5ecfbf1c 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -49,6 +49,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, struct nfs4_pnfs_ds_addr *da; struct nfs4_ff_layout_ds *new_ds = NULL; struct nfs4_ff_ds_version *ds_versions = NULL; + struct net *net = server->nfs_client->cl_net; u32 mp_count; u32 version_count; __be32 *p; @@ -80,8 +81,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, for (i = 0; i < mp_count; i++) { /* multipath ds */ - da = nfs4_decode_mp_ds_addr(server->nfs_client->cl_net, - &stream, gfp_flags); + da = nfs4_decode_mp_ds_addr(net, &stream, gfp_flags); if (da) list_add_tail(&da->da_node, &dsaddrs); } @@ -149,7 +149,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, new_ds->ds_versions = ds_versions; new_ds->ds_versions_cnt = version_count; - new_ds->ds = nfs4_pnfs_ds_add(&dsaddrs, gfp_flags); + new_ds->ds = nfs4_pnfs_ds_add(net, &dsaddrs, gfp_flags); if (!new_ds->ds) goto out_err_drain_dsaddrs; diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 964df0725f4c..f2e66b946f4b 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -74,6 +74,8 @@ nfs_fattr_to_ino_t(struct nfs_fattr *fattr) int nfs_wait_bit_killable(struct wait_bit_key *key, int mode) { + if (unlikely(nfs_current_task_exiting())) + return -EINTR; schedule(); if (signal_pending_state(mode, current)) return -ERESTARTSYS; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index ece517ebcca0..84361674bffc 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -832,6 +832,11 @@ static inline u32 nfs_stateid_hash(const nfs4_stateid *stateid) NFS4_STATEID_OTHER_SIZE); } +static inline bool nfs_current_task_exiting(void) +{ + return (current->flags & PF_EXITING) != 0; +} + static inline bool nfs_error_is_fatal(int err) { switch (err) { diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 2e7579626cf0..f036d30f7515 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -39,7 +39,7 @@ nfs3_rpc_wrapper(struct rpc_clnt *clnt, struct rpc_message *msg, int flags) __set_current_state(TASK_KILLABLE|TASK_FREEZABLE_UNSAFE); schedule_timeout(NFS_JUKEBOX_RETRY_TIME); res = -ERESTARTSYS; - } while (!fatal_signal_pending(current)); + } while (!fatal_signal_pending(current) && !nfs_current_task_exiting()); return res; } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 5b06b8d4e014..0f28607c5747 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -422,6 +422,8 @@ static int nfs4_delay_killable(long *timeout) { might_sleep(); + if (unlikely(nfs_current_task_exiting())) + return -EINTR; __set_current_state(TASK_KILLABLE|TASK_FREEZABLE_UNSAFE); schedule_timeout(nfs4_update_delay(timeout)); if (!__fatal_signal_pending(current)) @@ -433,6 +435,8 @@ static int nfs4_delay_interruptible(long *timeout) { might_sleep(); + if (unlikely(nfs_current_task_exiting())) + return -EINTR; __set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE_UNSAFE); schedule_timeout(nfs4_update_delay(timeout)); if (!signal_pending(current)) @@ -1712,7 +1716,8 @@ static void nfs_set_open_stateid_locked(struct nfs4_state *state, rcu_read_unlock(); trace_nfs4_open_stateid_update_wait(state->inode, stateid, 0); - if (!fatal_signal_pending(current)) { + if (!fatal_signal_pending(current) && + !nfs_current_task_exiting()) { if (schedule_timeout(5*HZ) == 0) status = -EAGAIN; else @@ -3500,7 +3505,7 @@ static bool nfs4_refresh_open_old_stateid(nfs4_stateid *dst, write_sequnlock(&state->seqlock); trace_nfs4_close_stateid_update_wait(state->inode, dst, 0); - if (fatal_signal_pending(current)) + if (fatal_signal_pending(current) || nfs_current_task_exiting()) status = -EINTR; else if (schedule_timeout(5*HZ) != 0) @@ -6886,10 +6891,18 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl, struct nfs4_unlockdata *p; struct nfs4_state *state = lsp->ls_state; struct inode *inode = state->inode; + struct nfs_lock_context *l_ctx; p = kzalloc(sizeof(*p), GFP_KERNEL); if (p == NULL) return NULL; + l_ctx = nfs_get_lock_context(ctx); + if (!IS_ERR(l_ctx)) { + p->l_ctx = l_ctx; + } else { + kfree(p); + return NULL; + } p->arg.fh = NFS_FH(inode); p->arg.fl = &p->fl; p->arg.seqid = seqid; @@ -6897,7 +6910,6 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl, p->lsp = lsp; /* Ensure we don't close file until we're done freeing locks! */ p->ctx = get_nfs_open_context(ctx); - p->l_ctx = nfs_get_lock_context(ctx); locks_init_lock(&p->fl); locks_copy_lock(&p->fl, fl); p->server = NFS_SERVER(inode); diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 48ea40660422..80a7c5bd7a47 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -2737,7 +2737,15 @@ out_error: pr_warn_ratelimited("NFS: state manager%s%s failed on NFSv4 server %s" " with error %d\n", section_sep, section, clp->cl_hostname, -status); - ssleep(1); + switch (status) { + case -ENETDOWN: + case -ENETUNREACH: + nfs_mark_client_ready(clp, -EIO); + break; + default: + ssleep(1); + break; + } out_drain: memalloc_nofs_restore(memflags); nfs4_end_drain_session(clp); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index f68286932019..fe0ddbce3bcb 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -732,6 +732,14 @@ pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo, return remaining; } +static void pnfs_reset_return_info(struct pnfs_layout_hdr *lo) +{ + struct pnfs_layout_segment *lseg; + + list_for_each_entry(lseg, &lo->plh_return_segs, pls_list) + pnfs_set_plh_return_info(lo, lseg->pls_range.iomode, 0); +} + static void pnfs_free_returned_lsegs(struct pnfs_layout_hdr *lo, struct list_head *free_me, @@ -1180,6 +1188,7 @@ void pnfs_layoutreturn_free_lsegs(struct pnfs_layout_hdr *lo, pnfs_mark_matching_lsegs_invalid(lo, &freeme, range, seq); pnfs_free_returned_lsegs(lo, &freeme, range, seq); pnfs_set_layout_stateid(lo, stateid, NULL, true); + pnfs_reset_return_info(lo); } else pnfs_mark_layout_stateid_invalid(lo, &freeme); out_unlock: diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index e3e6a41f19de..f5173c188184 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -59,6 +59,7 @@ struct nfs4_pnfs_ds { struct list_head ds_node; /* nfs4_pnfs_dev_hlist dev_dslist */ char *ds_remotestr; /* comma sep list of addrs */ struct list_head ds_addrs; + const struct net *ds_net; struct nfs_client *ds_clp; refcount_t ds_count; unsigned long ds_state; @@ -405,7 +406,8 @@ int pnfs_generic_commit_pagelist(struct inode *inode, int pnfs_generic_scan_commit_lists(struct nfs_commit_info *cinfo, int max); void pnfs_generic_write_commit_done(struct rpc_task *task, void *data); void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds); -struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(struct list_head *dsaddrs, +struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(const struct net *net, + struct list_head *dsaddrs, gfp_t gfp_flags); void nfs4_pnfs_v3_ds_connect_unload(void); int nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds, diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 47a8da3f5c9f..31afa88742f6 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -651,12 +651,12 @@ _same_data_server_addrs_locked(const struct list_head *dsaddrs1, * Lookup DS by addresses. nfs4_ds_cache_lock is held */ static struct nfs4_pnfs_ds * -_data_server_lookup_locked(const struct list_head *dsaddrs) +_data_server_lookup_locked(const struct net *net, const struct list_head *dsaddrs) { struct nfs4_pnfs_ds *ds; list_for_each_entry(ds, &nfs4_data_server_cache, ds_node) - if (_same_data_server_addrs_locked(&ds->ds_addrs, dsaddrs)) + if (ds->ds_net == net && _same_data_server_addrs_locked(&ds->ds_addrs, dsaddrs)) return ds; return NULL; } @@ -763,7 +763,7 @@ out_err: * uncached and return cached struct nfs4_pnfs_ds. */ struct nfs4_pnfs_ds * -nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags) +nfs4_pnfs_ds_add(const struct net *net, struct list_head *dsaddrs, gfp_t gfp_flags) { struct nfs4_pnfs_ds *tmp_ds, *ds = NULL; char *remotestr; @@ -781,13 +781,14 @@ nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags) remotestr = nfs4_pnfs_remotestr(dsaddrs, gfp_flags); spin_lock(&nfs4_ds_cache_lock); - tmp_ds = _data_server_lookup_locked(dsaddrs); + tmp_ds = _data_server_lookup_locked(net, dsaddrs); if (tmp_ds == NULL) { INIT_LIST_HEAD(&ds->ds_addrs); list_splice_init(dsaddrs, &ds->ds_addrs); ds->ds_remotestr = remotestr; refcount_set(&ds->ds_count, 1); INIT_LIST_HEAD(&ds->ds_node); + ds->ds_net = net; ds->ds_clp = NULL; list_add(&ds->ds_node, &nfs4_data_server_cache); dprintk("%s add new data server %s\n", __func__, diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 775766856a54..7f5fd16d3740 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -173,7 +173,7 @@ int ocfs2_recovery_init(struct ocfs2_super *osb) struct ocfs2_recovery_map *rm; mutex_init(&osb->recovery_lock); - osb->disable_recovery = 0; + osb->recovery_state = OCFS2_REC_ENABLED; osb->recovery_thread_task = NULL; init_waitqueue_head(&osb->recovery_event); @@ -192,31 +192,53 @@ int ocfs2_recovery_init(struct ocfs2_super *osb) return 0; } -/* we can't grab the goofy sem lock from inside wait_event, so we use - * memory barriers to make sure that we'll see the null task before - * being woken up */ static int ocfs2_recovery_thread_running(struct ocfs2_super *osb) { - mb(); return osb->recovery_thread_task != NULL; } +static void ocfs2_recovery_disable(struct ocfs2_super *osb, + enum ocfs2_recovery_state state) +{ + mutex_lock(&osb->recovery_lock); + /* + * If recovery thread is not running, we can directly transition to + * final state. + */ + if (!ocfs2_recovery_thread_running(osb)) { + osb->recovery_state = state + 1; + goto out_lock; + } + osb->recovery_state = state; + /* Wait for recovery thread to acknowledge state transition */ + wait_event_cmd(osb->recovery_event, + !ocfs2_recovery_thread_running(osb) || + osb->recovery_state >= state + 1, + mutex_unlock(&osb->recovery_lock), + mutex_lock(&osb->recovery_lock)); +out_lock: + mutex_unlock(&osb->recovery_lock); + + /* + * At this point we know that no more recovery work can be queued so + * wait for any recovery completion work to complete. + */ + if (osb->ocfs2_wq) + flush_workqueue(osb->ocfs2_wq); +} + +void ocfs2_recovery_disable_quota(struct ocfs2_super *osb) +{ + ocfs2_recovery_disable(osb, OCFS2_REC_QUOTA_WANT_DISABLE); +} + void ocfs2_recovery_exit(struct ocfs2_super *osb) { struct ocfs2_recovery_map *rm; /* disable any new recovery threads and wait for any currently * running ones to exit. Do this before setting the vol_state. */ - mutex_lock(&osb->recovery_lock); - osb->disable_recovery = 1; - mutex_unlock(&osb->recovery_lock); - wait_event(osb->recovery_event, !ocfs2_recovery_thread_running(osb)); - - /* At this point, we know that no more recovery threads can be - * launched, so wait for any recovery completion work to - * complete. */ - if (osb->ocfs2_wq) - flush_workqueue(osb->ocfs2_wq); + ocfs2_recovery_disable(osb, OCFS2_REC_WANT_DISABLE); /* * Now that recovery is shut down, and the osb is about to be @@ -1439,6 +1461,18 @@ static int __ocfs2_recovery_thread(void *arg) } } restart: + if (quota_enabled) { + mutex_lock(&osb->recovery_lock); + /* Confirm that recovery thread will no longer recover quotas */ + if (osb->recovery_state == OCFS2_REC_QUOTA_WANT_DISABLE) { + osb->recovery_state = OCFS2_REC_QUOTA_DISABLED; + wake_up(&osb->recovery_event); + } + if (osb->recovery_state >= OCFS2_REC_QUOTA_DISABLED) + quota_enabled = 0; + mutex_unlock(&osb->recovery_lock); + } + status = ocfs2_super_lock(osb, 1); if (status < 0) { mlog_errno(status); @@ -1536,27 +1570,29 @@ bail: ocfs2_free_replay_slots(osb); osb->recovery_thread_task = NULL; - mb(); /* sync with ocfs2_recovery_thread_running */ + if (osb->recovery_state == OCFS2_REC_WANT_DISABLE) + osb->recovery_state = OCFS2_REC_DISABLED; wake_up(&osb->recovery_event); mutex_unlock(&osb->recovery_lock); - if (quota_enabled) - kfree(rm_quota); + kfree(rm_quota); return status; } void ocfs2_recovery_thread(struct ocfs2_super *osb, int node_num) { + int was_set = -1; + mutex_lock(&osb->recovery_lock); + if (osb->recovery_state < OCFS2_REC_WANT_DISABLE) + was_set = ocfs2_recovery_map_set(osb, node_num); trace_ocfs2_recovery_thread(node_num, osb->node_num, - osb->disable_recovery, osb->recovery_thread_task, - osb->disable_recovery ? - -1 : ocfs2_recovery_map_set(osb, node_num)); + osb->recovery_state, osb->recovery_thread_task, was_set); - if (osb->disable_recovery) + if (osb->recovery_state >= OCFS2_REC_WANT_DISABLE) goto out; if (osb->recovery_thread_task) diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h index 689c340c6363..5ebde794a653 100644 --- a/fs/ocfs2/journal.h +++ b/fs/ocfs2/journal.h @@ -148,6 +148,7 @@ void ocfs2_wait_for_recovery(struct ocfs2_super *osb); int ocfs2_recovery_init(struct ocfs2_super *osb); void ocfs2_recovery_exit(struct ocfs2_super *osb); +void ocfs2_recovery_disable_quota(struct ocfs2_super *osb); int ocfs2_compute_replay_slots(struct ocfs2_super *osb); void ocfs2_free_replay_slots(struct ocfs2_super *osb); diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 740b64238312..22882c636bfb 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -284,6 +284,21 @@ enum ocfs2_mount_options #define OCFS2_OSB_ERROR_FS 0x0004 #define OCFS2_DEFAULT_ATIME_QUANTUM 60 +enum ocfs2_recovery_state { + OCFS2_REC_ENABLED = 0, + OCFS2_REC_QUOTA_WANT_DISABLE, + /* + * Must be OCFS2_REC_QUOTA_WANT_DISABLE + 1 for + * ocfs2_recovery_disable_quota() to work. + */ + OCFS2_REC_QUOTA_DISABLED, + OCFS2_REC_WANT_DISABLE, + /* + * Must be OCFS2_REC_WANT_DISABLE + 1 for ocfs2_recovery_exit() to work + */ + OCFS2_REC_DISABLED, +}; + struct ocfs2_journal; struct ocfs2_slot_info; struct ocfs2_recovery_map; @@ -346,7 +361,7 @@ struct ocfs2_super struct ocfs2_recovery_map *recovery_map; struct ocfs2_replay_map *replay_map; struct task_struct *recovery_thread_task; - int disable_recovery; + enum ocfs2_recovery_state recovery_state; wait_queue_head_t checkpoint_event; struct ocfs2_journal *journal; unsigned long osb_commit_interval; diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c index 4b4fa58cd32f..0ca8975a1df4 100644 --- a/fs/ocfs2/quota_local.c +++ b/fs/ocfs2/quota_local.c @@ -453,8 +453,7 @@ out: /* Sync changes in local quota file into global quota file and * reinitialize local quota file. - * The function expects local quota file to be already locked and - * s_umount locked in shared mode. */ + * The function expects local quota file to be already locked. */ static int ocfs2_recover_local_quota_file(struct inode *lqinode, int type, struct ocfs2_quota_recovery *rec) @@ -585,7 +584,6 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb, { unsigned int ino[OCFS2_MAXQUOTAS] = { LOCAL_USER_QUOTA_SYSTEM_INODE, LOCAL_GROUP_QUOTA_SYSTEM_INODE }; - struct super_block *sb = osb->sb; struct ocfs2_local_disk_dqinfo *ldinfo; struct buffer_head *bh; handle_t *handle; @@ -597,7 +595,6 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb, printk(KERN_NOTICE "ocfs2: Finishing quota recovery on device (%s) for " "slot %u\n", osb->dev_str, slot_num); - down_read(&sb->s_umount); for (type = 0; type < OCFS2_MAXQUOTAS; type++) { if (list_empty(&(rec->r_list[type]))) continue; @@ -674,7 +671,6 @@ out_put: break; } out: - up_read(&sb->s_umount); kfree(rec); return status; } @@ -840,8 +836,7 @@ static int ocfs2_local_free_info(struct super_block *sb, int type) ocfs2_release_local_quota_bitmaps(&oinfo->dqi_chunk); /* - * s_umount held in exclusive mode protects us against racing with - * recovery thread... + * ocfs2_dismount_volume() has already aborted quota recovery... */ if (oinfo->dqi_rec) { ocfs2_free_quota_recovery(oinfo->dqi_rec); diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 8b2eac8fb223..0ed21cd5c700 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1870,6 +1870,9 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err) /* Orphan scan should be stopped as early as possible */ ocfs2_orphan_scan_stop(osb); + /* Stop quota recovery so that we can disable quotas */ + ocfs2_recovery_disable_quota(osb); + ocfs2_disable_quotas(osb); /* All dquots should be freed by now */ diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c index b3bbb5a5787a..cc81ff6ac735 100644 --- a/fs/orangefs/inode.c +++ b/fs/orangefs/inode.c @@ -23,9 +23,9 @@ static int orangefs_writepage_locked(struct page *page, struct orangefs_write_range *wr = NULL; struct iov_iter iter; struct bio_vec bv; - size_t len, wlen; + size_t wlen; ssize_t ret; - loff_t off; + loff_t len, off; set_page_writeback(page); @@ -94,8 +94,7 @@ static int orangefs_writepages_work(struct orangefs_writepages *ow, struct orangefs_write_range *wrp, wr; struct iov_iter iter; ssize_t ret; - size_t len; - loff_t off; + loff_t len, off; int i; len = i_size_read(inode); diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h index d1fd54fb3cc1..9a30425b75a9 100644 --- a/fs/smb/client/cifsproto.h +++ b/fs/smb/client/cifsproto.h @@ -30,6 +30,9 @@ extern void cifs_small_buf_release(void *); extern void free_rsp_buf(int, void *); extern int smb_send(struct TCP_Server_Info *, struct smb_hdr *, unsigned int /* length */); +extern int smb_send_kvec(struct TCP_Server_Info *server, + struct msghdr *msg, + size_t *sent); extern unsigned int _get_xid(void); extern void _free_xid(unsigned int); #define get_xid() \ diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 6aeb25006db8..76c04c4ed45f 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -2966,8 +2966,10 @@ ip_rfc1001_connect(struct TCP_Server_Info *server) * sessinit is sent but no second negprot */ struct rfc1002_session_packet req = {}; - struct smb_hdr *smb_buf = (struct smb_hdr *)&req; + struct msghdr msg = {}; + struct kvec iov = {}; unsigned int len; + size_t sent; req.trailer.session_req.called_len = sizeof(req.trailer.session_req.called_name); @@ -2996,10 +2998,18 @@ ip_rfc1001_connect(struct TCP_Server_Info *server) * As per rfc1002, @len must be the number of bytes that follows the * length field of a rfc1002 session request payload. */ - len = sizeof(req) - offsetof(struct rfc1002_session_packet, trailer.session_req); + len = sizeof(req.trailer.session_req); + req.type = RFC1002_SESSION_REQUEST; + req.flags = 0; + req.length = cpu_to_be16(len); + len += offsetof(typeof(req), trailer.session_req); + iov.iov_base = &req; + iov.iov_len = len; + iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, &iov, 1, len); + rc = smb_send_kvec(server, &msg, &sent); + if (rc < 0 || len != sent) + return (rc == -EINTR || rc == -EAGAIN) ? rc : -ECONNABORTED; - smb_buf->smb_buf_length = cpu_to_be32((RFC1002_SESSION_REQUEST << 24) | len); - rc = smb_send(server, smb_buf, len); /* * RFC1001 layer in at least one server requires very short break before * negprot presumably because not expecting negprot to follow so fast. @@ -3008,7 +3018,7 @@ ip_rfc1001_connect(struct TCP_Server_Info *server) */ usleep_range(1000, 2000); - return rc; + return 0; } static int @@ -4178,11 +4188,13 @@ int cifs_negotiate_protocol(const unsigned int xid, struct cifs_ses *ses, struct TCP_Server_Info *server) { + bool in_retry = false; int rc = 0; if (!server->ops->need_neg || !server->ops->negotiate) return -ENOSYS; +retry: /* only send once per connect */ spin_lock(&server->srv_lock); if (server->tcpStatus != CifsGood && @@ -4202,6 +4214,14 @@ cifs_negotiate_protocol(const unsigned int xid, struct cifs_ses *ses, spin_unlock(&server->srv_lock); rc = server->ops->negotiate(xid, ses, server); + if (rc == -EAGAIN) { + /* Allow one retry attempt */ + if (!in_retry) { + in_retry = true; + goto retry; + } + rc = -EHOSTDOWN; + } if (rc == 0) { spin_lock(&server->srv_lock); if (server->tcpStatus == CifsInNegotiate) diff --git a/fs/smb/client/link.c b/fs/smb/client/link.c index c0f101fc1e5d..d71feb3fdbd2 100644 --- a/fs/smb/client/link.c +++ b/fs/smb/client/link.c @@ -269,7 +269,7 @@ cifs_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, struct cifs_open_parms oparms; struct cifs_io_parms io_parms = {0}; int buf_type = CIFS_NO_BUFFER; - FILE_ALL_INFO file_info; + struct cifs_open_info_data query_data; oparms = (struct cifs_open_parms) { .tcon = tcon, @@ -281,11 +281,11 @@ cifs_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, .fid = &fid, }; - rc = CIFS_open(xid, &oparms, &oplock, &file_info); + rc = tcon->ses->server->ops->open(xid, &oparms, &oplock, &query_data); if (rc) return rc; - if (file_info.EndOfFile != cpu_to_le64(CIFS_MF_SYMLINK_FILE_SIZE)) { + if (query_data.fi.EndOfFile != cpu_to_le64(CIFS_MF_SYMLINK_FILE_SIZE)) { rc = -ENOENT; /* it's not a symlink */ goto out; @@ -324,7 +324,7 @@ cifs_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, .fid = &fid, }; - rc = CIFS_open(xid, &oparms, &oplock, NULL); + rc = tcon->ses->server->ops->open(xid, &oparms, &oplock, NULL); if (rc) return rc; diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c index 9a1f1913fb59..402ac06ae9b6 100644 --- a/fs/smb/client/readdir.c +++ b/fs/smb/client/readdir.c @@ -765,7 +765,10 @@ find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos, else cifs_buf_release(cfile->srch_inf. ntwrk_buf_start); + /* Reset all pointers to the network buffer to prevent stale references */ cfile->srch_inf.ntwrk_buf_start = NULL; + cfile->srch_inf.srch_entries_start = NULL; + cfile->srch_inf.last_entry = NULL; } rc = initiate_cifs_search(xid, file, full_path); if (rc) { @@ -788,11 +791,11 @@ find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos, rc = server->ops->query_dir_next(xid, tcon, &cfile->fid, search_flags, &cfile->srch_inf); + if (rc) + return -ENOENT; /* FindFirst/Next set last_entry to NULL on malformed reply */ if (cfile->srch_inf.last_entry) cifs_save_resume_key(cfile->srch_inf.last_entry, cfile); - if (rc) - return -ENOENT; } if (index_to_find < cfile->srch_inf.index_of_last_entry) { /* we found the buffer that contains the entry */ diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c index 225cc7e0304c..1489b9d21b60 100644 --- a/fs/smb/client/smb1ops.c +++ b/fs/smb/client/smb1ops.c @@ -426,13 +426,6 @@ cifs_negotiate(const unsigned int xid, { int rc; rc = CIFSSMBNegotiate(xid, ses, server); - if (rc == -EAGAIN) { - /* retry only once on 1st time connection */ - set_credits(server, 1); - rc = CIFSSMBNegotiate(xid, ses, server); - if (rc == -EAGAIN) - rc = -EHOSTDOWN; - } return rc; } diff --git a/fs/smb/client/smb2file.c b/fs/smb/client/smb2file.c index a7475bc05cac..afdc78e92ee9 100644 --- a/fs/smb/client/smb2file.c +++ b/fs/smb/client/smb2file.c @@ -108,16 +108,25 @@ int smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, __u32 int err_buftype = CIFS_NO_BUFFER; struct cifs_fid *fid = oparms->fid; struct network_resiliency_req nr_ioctl_req; + bool retry_without_read_attributes = false; smb2_path = cifs_convert_path_to_utf16(oparms->path, oparms->cifs_sb); if (smb2_path == NULL) return -ENOMEM; - oparms->desired_access |= FILE_READ_ATTRIBUTES; + if (!(oparms->desired_access & FILE_READ_ATTRIBUTES)) { + oparms->desired_access |= FILE_READ_ATTRIBUTES; + retry_without_read_attributes = true; + } smb2_oplock = SMB2_OPLOCK_LEVEL_BATCH; rc = SMB2_open(xid, oparms, smb2_path, &smb2_oplock, smb2_data, NULL, &err_iov, &err_buftype); + if (rc == -EACCES && retry_without_read_attributes) { + oparms->desired_access &= ~FILE_READ_ATTRIBUTES; + rc = SMB2_open(xid, oparms, smb2_path, &smb2_oplock, smb2_data, NULL, &err_iov, + &err_buftype); + } if (rc && data) { struct smb2_hdr *hdr = err_iov.iov_base; diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index a62f3e5a7689..c9b9892b510e 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -422,9 +422,6 @@ smb2_negotiate(const unsigned int xid, server->CurrentMid = 0; spin_unlock(&server->mid_lock); rc = SMB2_negotiate(xid, ses, server); - /* BB we probably don't need to retry with modern servers */ - if (rc == -EAGAIN) - rc = -EHOSTDOWN; return rc; } diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 96faa22b9cb6..c28e39c67c4f 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -2826,7 +2826,7 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode, /* Eventually save off posix specific response info and timestaps */ err_free_rsp_buf: - free_rsp_buf(resp_buftype, rsp); + free_rsp_buf(resp_buftype, rsp_iov.iov_base); kfree(pc_buf); err_free_req: cifs_small_buf_release(req); diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c index 3fdafb9297f1..d2867bd263c5 100644 --- a/fs/smb/client/transport.c +++ b/fs/smb/client/transport.c @@ -178,7 +178,7 @@ delete_mid(struct mid_q_entry *mid) * Our basic "send data to server" function. Should be called with srv_mutex * held. The caller is responsible for handling the results. */ -static int +int smb_send_kvec(struct TCP_Server_Info *server, struct msghdr *smb_msg, size_t *sent) { diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 2fcfabc35b06..258ed9978b90 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -1536,7 +1536,7 @@ struct lease_ctx_info *parse_lease_state(void *open_req, bool is_dir) if (le16_to_cpu(cc->DataOffset) + le32_to_cpu(cc->DataLength) < sizeof(struct create_lease_v2) - 4) - return NULL; + goto err_out; memcpy(lreq->lease_key, lc->lcontext.LeaseKey, SMB2_LEASE_KEY_SIZE); if (is_dir) { @@ -1557,7 +1557,7 @@ struct lease_ctx_info *parse_lease_state(void *open_req, bool is_dir) if (le16_to_cpu(cc->DataOffset) + le32_to_cpu(cc->DataLength) < sizeof(struct create_lease)) - return NULL; + goto err_out; memcpy(lreq->lease_key, lc->lcontext.LeaseKey, SMB2_LEASE_KEY_SIZE); lreq->req_state = lc->lcontext.LeaseState; @@ -1566,6 +1566,9 @@ struct lease_ctx_info *parse_lease_state(void *open_req, bool is_dir) lreq->version = 1; } return lreq; +err_out: + kfree(lreq); + return NULL; } /** diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index 25e8004a5905..fa647b75fba8 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -423,10 +423,15 @@ static int ksmbd_vfs_stream_write(struct ksmbd_file *fp, char *buf, loff_t *pos, ksmbd_debug(VFS, "write stream data pos : %llu, count : %zd\n", *pos, count); + if (*pos >= XATTR_SIZE_MAX) { + pr_err("stream write position %lld is out of bounds\n", *pos); + return -EINVAL; + } + size = *pos + count; if (size > XATTR_SIZE_MAX) { size = XATTR_SIZE_MAX; - count = (*pos + count) - XATTR_SIZE_MAX; + count = XATTR_SIZE_MAX - *pos; } v_len = ksmbd_vfs_getcasexattr(user_ns, diff --git a/include/drm/drm_atomic.h b/include/drm/drm_atomic.h index 10b1990bc1f6..36225aedf613 100644 --- a/include/drm/drm_atomic.h +++ b/include/drm/drm_atomic.h @@ -372,8 +372,27 @@ struct drm_atomic_state { * * Allow full modeset. This is used by the ATOMIC IOCTL handler to * implement the DRM_MODE_ATOMIC_ALLOW_MODESET flag. Drivers should - * never consult this flag, instead looking at the output of - * drm_atomic_crtc_needs_modeset(). + * generally not consult this flag, but instead look at the output of + * drm_atomic_crtc_needs_modeset(). The detailed rules are: + * + * - Drivers must not consult @allow_modeset in the atomic commit path. + * Use drm_atomic_crtc_needs_modeset() instead. + * + * - Drivers must consult @allow_modeset before adding unrelated struct + * drm_crtc_state to this commit by calling + * drm_atomic_get_crtc_state(). See also the warning in the + * documentation for that function. + * + * - Drivers must never change this flag, it is under the exclusive + * control of userspace. + * + * - Drivers may consult @allow_modeset in the atomic check path, if + * they have the choice between an optimal hardware configuration + * which requires a modeset, and a less optimal configuration which + * can be committed without a modeset. An example would be suboptimal + * scanout FIFO allocation resulting in increased idle power + * consumption. This allows userspace to avoid flickering and delays + * for the normal composition loop at reasonable cost. */ bool allow_modeset : 1; /** diff --git a/include/linux/bio.h b/include/linux/bio.h index 2b9fc5edf49d..00ab98ce1d43 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -11,6 +11,7 @@ #include #define BIO_MAX_VECS 256U +#define BIO_MAX_INLINE_VECS UIO_MAXIOV static inline unsigned int bio_max_segs(unsigned int nr_segs) { diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 4b06b1f1e267..186e0e0f2e40 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -76,6 +76,8 @@ extern ssize_t cpu_show_gds(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_reg_file_data_sampling(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_indirect_target_selection(struct device *dev, + struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index fc3b165dfb1f..56c9f1c94cd8 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -615,10 +615,14 @@ static inline int dma_mmap_wc(struct device *dev, #else #define DEFINE_DMA_UNMAP_ADDR(ADDR_NAME) #define DEFINE_DMA_UNMAP_LEN(LEN_NAME) -#define dma_unmap_addr(PTR, ADDR_NAME) (0) -#define dma_unmap_addr_set(PTR, ADDR_NAME, VAL) do { } while (0) -#define dma_unmap_len(PTR, LEN_NAME) (0) -#define dma_unmap_len_set(PTR, LEN_NAME, VAL) do { } while (0) +#define dma_unmap_addr(PTR, ADDR_NAME) \ + ({ typeof(PTR) __p __maybe_unused = PTR; 0; }) +#define dma_unmap_addr_set(PTR, ADDR_NAME, VAL) \ + do { typeof(PTR) __p __maybe_unused = PTR; } while (0) +#define dma_unmap_len(PTR, LEN_NAME) \ + ({ typeof(PTR) __p __maybe_unused = PTR; 0; }) +#define dma_unmap_len_set(PTR, LEN_NAME, VAL) \ + do { typeof(PTR) __p __maybe_unused = PTR; } while (0) #endif #endif /* _LINUX_DMA_MAPPING_H */ diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index afc204370901..80d876593caa 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1224,13 +1224,6 @@ extern int vmbus_sendpacket(struct vmbus_channel *channel, enum vmbus_packet_type type, u32 flags); -extern int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel, - struct hv_page_buffer pagebuffers[], - u32 pagecount, - void *buffer, - u32 bufferlen, - u64 requestid); - extern int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel, struct vmbus_packet_mpb_array *mpb, u32 desc_size, diff --git a/include/linux/lzo.h b/include/linux/lzo.h index e95c7d1092b2..4d30e3624acd 100644 --- a/include/linux/lzo.h +++ b/include/linux/lzo.h @@ -24,10 +24,18 @@ int lzo1x_1_compress(const unsigned char *src, size_t src_len, unsigned char *dst, size_t *dst_len, void *wrkmem); +/* Same as above but does not write more than dst_len to dst. */ +int lzo1x_1_compress_safe(const unsigned char *src, size_t src_len, + unsigned char *dst, size_t *dst_len, void *wrkmem); + /* This requires 'wrkmem' of size LZO1X_1_MEM_COMPRESS */ int lzorle1x_1_compress(const unsigned char *src, size_t src_len, unsigned char *dst, size_t *dst_len, void *wrkmem); +/* Same as above but does not write more than dst_len to dst. */ +int lzorle1x_1_compress_safe(const unsigned char *src, size_t src_len, + unsigned char *dst, size_t *dst_len, void *wrkmem); + /* safe decompression with overrun testing */ int lzo1x_decompress_safe(const unsigned char *src, size_t src_len, unsigned char *dst, size_t *dst_len); diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 6646634a0b9d..0cb296f0f8d1 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -1115,7 +1115,7 @@ int mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt, int mlx4_buf_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt, struct mlx4_buf *buf); -int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order); +int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, unsigned int order); void mlx4_db_free(struct mlx4_dev *dev, struct mlx4_db *db); int mlx4_alloc_hwq_res(struct mlx4_dev *dev, struct mlx4_hwq_resources *wqres, diff --git a/include/linux/module.h b/include/linux/module.h index 613ab627eb9a..2ba249d10d5c 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -540,6 +540,11 @@ struct module { atomic_t refcnt; #endif +#ifdef CONFIG_MITIGATION_ITS + int its_num_pages; + void **its_page_array; +#endif + #ifdef CONFIG_CONSTRUCTORS /* Constructor functions. */ ctor_fn_t *ctors; diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 9ea9f9087a71..a9671f930084 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -196,6 +196,15 @@ struct nfs_server { char *fscache_uniq; /* Uniquifier (or NULL) */ #endif + /* The following #defines numerically match the NFSv4 equivalents */ +#define NFS_FH_NOEXPIRE_WITH_OPEN (0x1) +#define NFS_FH_VOLATILE_ANY (0x2) +#define NFS_FH_VOL_MIGRATION (0x4) +#define NFS_FH_VOL_RENAME (0x8) +#define NFS_FH_RENAME_UNSAFE (NFS_FH_VOLATILE_ANY | NFS_FH_VOL_RENAME) + u32 fh_expire_type; /* V4 bitmask representing file + handle volatility type for + this filesystem */ u32 pnfs_blksize; /* layout_blksize attr */ #if IS_ENABLED(CONFIG_NFS_V4) u32 attr_bitmask[3];/* V4 bitmask representing the set @@ -219,9 +228,6 @@ struct nfs_server { u32 acl_bitmask; /* V4 bitmask representing the ACEs that are supported on this filesystem */ - u32 fh_expire_type; /* V4 bitmask representing file - handle volatility type for - this filesystem */ struct pnfs_layoutdriver_type *pnfs_curr_ld; /* Active layout driver */ struct rpc_wait_queue roc_rpcwaitq; void *pnfs_ld_data; /* per mount point data */ diff --git a/include/linux/pid.h b/include/linux/pid.h index 343abf22092e..b75de288a8c2 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -80,6 +80,7 @@ extern struct pid *pidfd_pid(const struct file *file); struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags); struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags); int pidfd_create(struct pid *pid, unsigned int flags); +int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret); static inline struct pid *get_pid(struct pid *pid) { diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 166f1f3ca19b..ea30672570bf 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -97,9 +97,9 @@ static inline void __rcu_read_lock(void) static inline void __rcu_read_unlock(void) { - preempt_enable(); if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)) rcu_read_unlock_strict(); + preempt_enable(); } static inline int rcu_preempt_depth(void) @@ -1040,6 +1040,9 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) #define kvfree_rcu(...) KVFREE_GET_MACRO(__VA_ARGS__, \ kvfree_rcu_arg_2, kvfree_rcu_arg_1)(__VA_ARGS__) +#define kvfree_rcu_mightsleep(ptr) kvfree_rcu_arg_1(ptr) +#define kfree_rcu_mightsleep(ptr) kvfree_rcu_mightsleep(ptr) + #define KVFREE_GET_MACRO(_1, _2, NAME, ...) NAME #define kvfree_rcu_arg_2(ptr, rhf) \ do { \ diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 5efb51486e8a..54483d5e6f91 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -105,7 +105,7 @@ extern int rcu_scheduler_active; void rcu_end_inkernel_boot(void); bool rcu_inkernel_boot_has_ended(void); bool rcu_is_watching(void); -#ifndef CONFIG_PREEMPTION +#ifndef CONFIG_PREEMPT_RCU void rcu_all_qs(void); #endif diff --git a/include/linux/tpm.h b/include/linux/tpm.h index dd0784a6e07d..4a4112bb1d1b 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -181,7 +181,7 @@ enum tpm2_const { enum tpm2_timeouts { TPM2_TIMEOUT_A = 750, - TPM2_TIMEOUT_B = 2000, + TPM2_TIMEOUT_B = 4000, TPM2_TIMEOUT_C = 200, TPM2_TIMEOUT_D = 30, TPM2_DURATION_SHORT = 20, diff --git a/include/linux/trace.h b/include/linux/trace.h index 2a70a447184c..bb4d84f1c58c 100644 --- a/include/linux/trace.h +++ b/include/linux/trace.h @@ -72,8 +72,8 @@ static inline int unregister_ftrace_export(struct trace_export *export) static inline void trace_printk_init_buffers(void) { } -static inline int trace_array_printk(struct trace_array *tr, unsigned long ip, - const char *fmt, ...) +static inline __printf(3, 4) +int trace_array_printk(struct trace_array *tr, unsigned long ip, const char *fmt, ...) { return 0; } diff --git a/include/linux/trace_seq.h b/include/linux/trace_seq.h index 5a2c650d9e1c..c230cbd25aee 100644 --- a/include/linux/trace_seq.h +++ b/include/linux/trace_seq.h @@ -77,8 +77,8 @@ extern __printf(2, 3) void trace_seq_printf(struct trace_seq *s, const char *fmt, ...); extern __printf(2, 0) void trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args); -extern void -trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary); +extern __printf(2, 0) +void trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary); extern int trace_print_seq(struct seq_file *m, struct trace_seq *s); extern int trace_seq_to_user(struct trace_seq *s, char __user *ubuf, int cnt); @@ -100,8 +100,8 @@ extern int trace_seq_hex_dump(struct trace_seq *s, const char *prefix_str, static inline void trace_seq_printf(struct trace_seq *s, const char *fmt, ...) { } -static inline void -trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary) +static inline __printf(2, 0) +void trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary) { } diff --git a/include/linux/types.h b/include/linux/types.h index ea8cf60a8a79..f1df5d8df2ef 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -109,8 +109,9 @@ typedef u64 u_int64_t; typedef s64 int64_t; #endif -/* this is a special 64bit data type that is 8-byte aligned */ +/* These are the special 64-bit data types that are 8-byte aligned */ #define aligned_u64 __aligned_u64 +#define aligned_s64 __aligned_s64 #define aligned_be64 __aligned_be64 #define aligned_le64 __aligned_le64 diff --git a/include/linux/usb/r8152.h b/include/linux/usb/r8152.h index 33a4c146dc19..2ca60828f28b 100644 --- a/include/linux/usb/r8152.h +++ b/include/linux/usb/r8152.h @@ -30,6 +30,7 @@ #define VENDOR_ID_NVIDIA 0x0955 #define VENDOR_ID_TPLINK 0x2357 #define VENDOR_ID_DLINK 0x2001 +#define VENDOR_ID_DELL 0x413c #define VENDOR_ID_ASUS 0x0b05 #if IS_REACHABLE(CONFIG_USB_RTL8152) diff --git a/include/net/af_unix.h b/include/net/af_unix.h index e07e3011df3e..093b9a236985 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -8,20 +8,46 @@ #include #include -void unix_inflight(struct user_struct *user, struct file *fp); -void unix_notinflight(struct user_struct *user, struct file *fp); -void unix_destruct_scm(struct sk_buff *skb); +#if IS_ENABLED(CONFIG_UNIX) +struct unix_sock *unix_get_socket(struct file *filp); +#else +static inline struct unix_sock *unix_get_socket(struct file *filp) +{ + return NULL; +} +#endif + +extern unsigned int unix_tot_inflight; +void unix_add_edges(struct scm_fp_list *fpl, struct unix_sock *receiver); +void unix_del_edges(struct scm_fp_list *fpl); +void unix_update_edges(struct unix_sock *receiver); +int unix_prepare_fpl(struct scm_fp_list *fpl); +void unix_destroy_fpl(struct scm_fp_list *fpl); void unix_gc(void); -void wait_for_unix_gc(void); -struct sock *unix_get_socket(struct file *filp); +void wait_for_unix_gc(struct scm_fp_list *fpl); + +struct unix_vertex { + struct list_head edges; + struct list_head entry; + struct list_head scc_entry; + unsigned long out_degree; + unsigned long index; + unsigned long scc_index; +}; + +struct unix_edge { + struct unix_sock *predecessor; + struct unix_sock *successor; + struct list_head vertex_entry; + struct list_head stack_entry; +}; + struct sock *unix_peer_get(struct sock *sk); #define UNIX_HASH_MOD (256 - 1) #define UNIX_HASH_SIZE (256 * 2) #define UNIX_HASH_BITS 8 -extern unsigned int unix_tot_inflight; - struct unix_address { refcount_t refcnt; int len; @@ -41,6 +67,7 @@ struct unix_skb_parms { struct scm_stat { atomic_t nr_fds; + unsigned long nr_unix_fds; }; #define UNIXCB(skb) (*(struct unix_skb_parms *)&((skb)->cb)) @@ -53,12 +80,9 @@ struct unix_sock { struct path path; struct mutex iolock, bindlock; struct sock *peer; - struct list_head link; - unsigned long inflight; + struct sock *listener; + struct unix_vertex *vertex; spinlock_t lock; - unsigned long gc_flags; -#define UNIX_GC_CANDIDATE 0 -#define UNIX_GC_MAYBE_CYCLE 1 struct socket_wq peer_wq; wait_queue_entry_t peer_wake; struct scm_stat scm_stat; diff --git a/include/net/flow.h b/include/net/flow.h index 2f0da4f0318b..5497b0d9357f 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -115,11 +115,10 @@ static inline void flowi4_init_output(struct flowi4 *fl4, int oif, } /* Reset some input parameters after previous lookup */ -static inline void flowi4_update_output(struct flowi4 *fl4, int oif, __u8 tos, +static inline void flowi4_update_output(struct flowi4 *fl4, int oif, __be32 daddr, __be32 saddr) { fl4->flowi4_oif = oif; - fl4->flowi4_tos = tos; fl4->daddr = daddr; fl4->saddr = saddr; } diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index d11398aa642e..7252a5aae069 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1045,6 +1045,7 @@ struct nft_rule_blob { * @use: number of jump references to this chain * @flags: bitmask of enum nft_chain_flags * @name: name of the chain + * @rcu_head: rcu head for deferred release */ struct nft_chain { struct nft_rule_blob __rcu *blob_gen_0; @@ -1121,7 +1122,7 @@ static inline bool nft_chain_is_bound(struct nft_chain *chain) int nft_chain_add(struct nft_table *table, struct nft_chain *chain); void nft_chain_del(struct nft_chain *chain); -void nf_tables_chain_destroy(struct nft_ctx *ctx); +void nf_tables_chain_destroy(struct nft_chain *chain); struct nft_stats { u64 bytes; diff --git a/include/net/route.h b/include/net/route.h index 4185e6da9ef8..cdca622c5c6f 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -325,8 +325,7 @@ static inline struct rtable *ip_route_connect(struct flowi4 *fl4, __be32 dst, if (IS_ERR(rt)) return rt; ip_rt_put(rt); - flowi4_update_output(fl4, oif, fl4->flowi4_tos, fl4->daddr, - fl4->saddr); + flowi4_update_output(fl4, oif, fl4->daddr, fl4->saddr); } security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4)); return ip_route_output_flow(net, fl4, sk); @@ -341,8 +340,7 @@ static inline struct rtable *ip_route_newports(struct flowi4 *fl4, struct rtable fl4->fl4_dport = dport; fl4->fl4_sport = sport; ip_rt_put(rt); - flowi4_update_output(fl4, sk->sk_bound_dev_if, - RT_CONN_FLAGS(sk), fl4->daddr, + flowi4_update_output(fl4, sk->sk_bound_dev_if, fl4->daddr, fl4->saddr); security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4)); return ip_route_output_flow(sock_net(sk), fl4, sk); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 785ab5a0665a..f897510b631f 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -1003,6 +1003,21 @@ static inline struct sk_buff *__qdisc_dequeue_head(struct qdisc_skb_head *qh) return skb; } +static inline struct sk_buff *qdisc_dequeue_internal(struct Qdisc *sch, bool direct) +{ + struct sk_buff *skb; + + skb = __skb_dequeue(&sch->gso_skb); + if (skb) { + sch->q.qlen--; + return skb; + } + if (direct) + return __qdisc_dequeue_head(&sch->q); + else + return sch->dequeue(sch); +} + static inline struct sk_buff *qdisc_dequeue_head(struct Qdisc *sch) { struct sk_buff *skb = __qdisc_dequeue_head(&sch->q); diff --git a/include/net/scm.h b/include/net/scm.h index 585adc1346bd..0be0dc3eb1dc 100644 --- a/include/net/scm.h +++ b/include/net/scm.h @@ -21,9 +21,20 @@ struct scm_creds { kgid_t gid; }; +#ifdef CONFIG_UNIX +struct unix_edge; +#endif + struct scm_fp_list { short count; + short count_unix; short max; +#ifdef CONFIG_UNIX + bool inflight; + bool dead; + struct list_head vertices; + struct unix_edge *edges; +#endif struct user_struct *user; struct file *fp[SCM_MAX_FD]; }; diff --git a/include/rdma/uverbs_std_types.h b/include/rdma/uverbs_std_types.h index fe0512116958..555ea3d142a4 100644 --- a/include/rdma/uverbs_std_types.h +++ b/include/rdma/uverbs_std_types.h @@ -34,7 +34,7 @@ static inline void *_uobj_get_obj_read(struct ib_uobject *uobj) { if (IS_ERR(uobj)) - return NULL; + return ERR_CAST(uobj); return uobj->object; } #define uobj_get_obj_read(_object, _type, _id, _attrs) \ diff --git a/include/sound/hda_codec.h b/include/sound/hda_codec.h index bbb7805e85d8..4ca45d5895df 100644 --- a/include/sound/hda_codec.h +++ b/include/sound/hda_codec.h @@ -199,6 +199,7 @@ struct hda_codec { /* beep device */ struct hda_beep *beep; unsigned int beep_mode; + bool beep_just_power_on; /* widget capabilities cache */ u32 *wcaps; diff --git a/include/sound/pcm.h b/include/sound/pcm.h index f9c6ad3297bd..6a4deab560c0 100644 --- a/include/sound/pcm.h +++ b/include/sound/pcm.h @@ -1436,6 +1436,8 @@ int snd_pcm_lib_mmap_iomem(struct snd_pcm_substream *substream, struct vm_area_s #define snd_pcm_lib_mmap_iomem NULL #endif +void snd_pcm_runtime_buffer_set_silence(struct snd_pcm_runtime *runtime); + /** * snd_pcm_limit_isa_dma_size - Get the max size fitting with ISA DMA transfer * @dma: DMA number diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 7a6c5a870d33..31847ccae493 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -1847,7 +1847,7 @@ DECLARE_EVENT_CLASS(btrfs__prelim_ref, TP_PROTO(const struct btrfs_fs_info *fs_info, const struct prelim_ref *oldref, const struct prelim_ref *newref, u64 tree_size), - TP_ARGS(fs_info, newref, oldref, tree_size), + TP_ARGS(fs_info, oldref, newref, tree_size), TP_STRUCT__entry_btrfs( __field( u64, root_id ) diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index c7b056af9ef0..3e5f07be26fc 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -91,7 +91,7 @@ typedef __s64 Elf64_Sxword; #define DT_INIT 12 #define DT_FINI 13 #define DT_SONAME 14 -#define DT_RPATH 15 +#define DT_RPATH 15 #define DT_SYMBOLIC 16 #define DT_REL 17 #define DT_RELSZ 18 diff --git a/include/uapi/linux/types.h b/include/uapi/linux/types.h index 308433be33c2..c39147653094 100644 --- a/include/uapi/linux/types.h +++ b/include/uapi/linux/types.h @@ -49,6 +49,7 @@ typedef __u32 __bitwise __wsum; * No conversions are necessary between 32-bit user-space and a 64-bit kernel. */ #define __aligned_u64 __u64 __attribute__((aligned(8))) +#define __aligned_s64 __s64 __attribute__((aligned(8))) #define __aligned_be64 __be64 __attribute__((aligned(8))) #define __aligned_le64 __le64 __attribute__((aligned(8))) diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c index 42d8461ac546..fa3dd5d0c221 100644 --- a/io_uring/fdinfo.c +++ b/io_uring/fdinfo.c @@ -79,11 +79,11 @@ static __cold void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, seq_printf(m, "SqMask:\t0x%x\n", sq_mask); seq_printf(m, "SqHead:\t%u\n", sq_head); seq_printf(m, "SqTail:\t%u\n", sq_tail); - seq_printf(m, "CachedSqHead:\t%u\n", ctx->cached_sq_head); + seq_printf(m, "CachedSqHead:\t%u\n", data_race(ctx->cached_sq_head)); seq_printf(m, "CqMask:\t0x%x\n", cq_mask); seq_printf(m, "CqHead:\t%u\n", cq_head); seq_printf(m, "CqTail:\t%u\n", cq_tail); - seq_printf(m, "CachedCqTail:\t%u\n", ctx->cached_cq_tail); + seq_printf(m, "CachedCqTail:\t%u\n", data_race(ctx->cached_cq_tail)); seq_printf(m, "SQEs:\t%u\n", sq_tail - sq_head); sq_entries = min(sq_tail - sq_head, ctx->sq_entries); for (i = 0; i < sq_entries; i++) { diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 447f8a0b062f..e7491e54c383 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -372,24 +372,6 @@ static struct io_kiocb *__io_prep_linked_timeout(struct io_kiocb *req) return req->link; } -static inline struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req) -{ - if (likely(!(req->flags & REQ_F_ARM_LTIMEOUT))) - return NULL; - return __io_prep_linked_timeout(req); -} - -static noinline void __io_arm_ltimeout(struct io_kiocb *req) -{ - io_queue_linked_timeout(__io_prep_linked_timeout(req)); -} - -static inline void io_arm_ltimeout(struct io_kiocb *req) -{ - if (unlikely(req->flags & REQ_F_ARM_LTIMEOUT)) - __io_arm_ltimeout(req); -} - static void io_prep_async_work(struct io_kiocb *req) { const struct io_op_def *def = &io_op_defs[req->opcode]; @@ -437,7 +419,6 @@ static void io_prep_async_link(struct io_kiocb *req) static void io_queue_iowq(struct io_kiocb *req) { - struct io_kiocb *link = io_prep_linked_timeout(req); struct io_uring_task *tctx = req->task->io_uring; BUG_ON(!tctx); @@ -462,8 +443,6 @@ static void io_queue_iowq(struct io_kiocb *req) trace_io_uring_queue_async_work(req, io_wq_is_hashed(&req->work)); io_wq_enqueue(tctx->io_wq, &req->work); - if (link) - io_queue_linked_timeout(link); } static __cold void io_queue_deferred(struct io_ring_ctx *ctx) @@ -648,6 +627,7 @@ static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) * to care for a non-real case. */ if (need_resched()) { + ctx->cqe_sentinel = ctx->cqe_cached; io_cq_unlock_post(ctx); mutex_unlock(&ctx->uring_lock); cond_resched(); @@ -840,6 +820,14 @@ bool io_post_aux_cqe(struct io_ring_ctx *ctx, { bool filled; + /* + * If multishot has already posted deferred completions, ensure that + * those are flushed first before posting this one. If not, CQEs + * could get reordered. + */ + if (!wq_list_empty(&ctx->submit_state.compl_reqs)) + __io_submit_flush_completions(ctx); + io_cq_lock(ctx); filled = io_fill_cqe_aux(ctx, user_data, res, cflags, allow_overflow); io_cq_unlock_post(ctx); @@ -1741,17 +1729,24 @@ static bool io_assign_file(struct io_kiocb *req, unsigned int issue_flags) return !!req->file; } +#define REQ_ISSUE_SLOW_FLAGS (REQ_F_CREDS | REQ_F_ARM_LTIMEOUT) + static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) { const struct io_op_def *def = &io_op_defs[req->opcode]; const struct cred *creds = NULL; + struct io_kiocb *link = NULL; int ret; if (unlikely(!io_assign_file(req, issue_flags))) return -EBADF; - if (unlikely((req->flags & REQ_F_CREDS) && req->creds != current_cred())) - creds = override_creds(req->creds); + if (unlikely(req->flags & REQ_ISSUE_SLOW_FLAGS)) { + if ((req->flags & REQ_F_CREDS) && req->creds != current_cred()) + creds = override_creds(req->creds); + if (req->flags & REQ_F_ARM_LTIMEOUT) + link = __io_prep_linked_timeout(req); + } if (!def->audit_skip) audit_uring_entry(req->opcode); @@ -1761,8 +1756,12 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) if (!def->audit_skip) audit_uring_exit(!ret, ret); - if (creds) - revert_creds(creds); + if (unlikely(creds || link)) { + if (creds) + revert_creds(creds); + if (link) + io_queue_linked_timeout(link); + } if (ret == IOU_OK) { if (issue_flags & IO_URING_F_COMPLETE_DEFER) @@ -1809,8 +1808,6 @@ void io_wq_submit_work(struct io_wq_work *work) else req_ref_get(req); - io_arm_ltimeout(req); - /* either cancelled or io-wq is dying, so don't touch tctx->iowq */ if (work->flags & IO_WQ_WORK_CANCEL) { fail: @@ -1908,15 +1905,11 @@ struct file *io_file_get_normal(struct io_kiocb *req, int fd) static void io_queue_async(struct io_kiocb *req, int ret) __must_hold(&req->ctx->uring_lock) { - struct io_kiocb *linked_timeout; - if (ret != -EAGAIN || (req->flags & REQ_F_NOWAIT)) { io_req_complete_failed(req, ret); return; } - linked_timeout = io_prep_linked_timeout(req); - switch (io_arm_poll_handler(req, 0)) { case IO_APOLL_READY: io_kbuf_recycle(req, 0); @@ -1929,9 +1922,6 @@ static void io_queue_async(struct io_kiocb *req, int ret) case IO_APOLL_OK: break; } - - if (linked_timeout) - io_queue_linked_timeout(linked_timeout); } static inline void io_queue_sqe(struct io_kiocb *req) @@ -1945,9 +1935,7 @@ static inline void io_queue_sqe(struct io_kiocb *req) * We async punt it if the file wasn't marked NOWAIT, or if the file * doesn't support non-blocking read/write attempts */ - if (likely(!ret)) - io_arm_ltimeout(req); - else + if (unlikely(ret)) io_queue_async(req, ret); } diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 3d0ded6921f2..a1e1881944a3 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -2172,7 +2172,7 @@ static int bpf_for_each_hash_elem(struct bpf_map *map, bpf_callback_t callback_f b = &htab->buckets[i]; rcu_read_lock(); head = &b->head; - hlist_nulls_for_each_entry_rcu(elem, n, head, hash_node) { + hlist_nulls_for_each_entry_safe(elem, n, head, hash_node) { key = elem->key; if (is_percpu) { /* current cpu value for percpu map */ diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 8a5f8e09c021..a5c05a211340 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -3985,6 +3985,8 @@ static int bpf_prog_get_info_by_fd(struct file *file, info.recursion_misses = stats.misses; info.verified_insns = prog->aux->verified_insns; + if (prog->aux->btf) + info.btf_id = btf_obj_id(prog->aux->btf); if (!bpf_capable()) { info.jited_prog_len = 0; @@ -4131,8 +4133,6 @@ static int bpf_prog_get_info_by_fd(struct file *file, } } - if (prog->aux->btf) - info.btf_id = btf_obj_id(prog->aux->btf); info.attach_btf_id = prog->aux->attach_btf_id; if (attach_btf) info.attach_btf_obj_id = btf_obj_id(attach_btf); diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 550f49a1e492..2bfdf521283e 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -93,7 +93,7 @@ DEFINE_MUTEX(cgroup_mutex); DEFINE_SPINLOCK(css_set_lock); -#ifdef CONFIG_PROVE_RCU +#if (defined CONFIG_PROVE_RCU || defined CONFIG_LOCKDEP) EXPORT_SYMBOL_GPL(cgroup_mutex); EXPORT_SYMBOL_GPL(css_set_lock); #endif diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c index c3797701339c..382a3b04f6d3 100644 --- a/kernel/events/hw_breakpoint.c +++ b/kernel/events/hw_breakpoint.c @@ -978,9 +978,10 @@ static int hw_breakpoint_event_init(struct perf_event *bp) return -ENOENT; /* - * no branch sampling for breakpoint events + * Check if breakpoint type is supported before proceeding. + * Also, no branch sampling for breakpoint events. */ - if (has_branch_stack(bp)) + if (!hw_breakpoint_slots_cached(find_slot_idx(bp->attr.bp_type)) || has_branch_stack(bp)) return -EOPNOTSUPP; err = register_perf_hw_breakpoint(bp); diff --git a/kernel/fork.c b/kernel/fork.c index 91357988f282..352d8dd64b4a 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2046,6 +2046,91 @@ const struct file_operations pidfd_fops = { #endif }; +/** + * __pidfd_prepare - allocate a new pidfd_file and reserve a pidfd + * @pid: the struct pid for which to create a pidfd + * @flags: flags of the new @pidfd + * @pidfd: the pidfd to return + * + * Allocate a new file that stashes @pid and reserve a new pidfd number in the + * caller's file descriptor table. The pidfd is reserved but not installed yet. + + * The helper doesn't perform checks on @pid which makes it useful for pidfds + * created via CLONE_PIDFD where @pid has no task attached when the pidfd and + * pidfd file are prepared. + * + * If this function returns successfully the caller is responsible to either + * call fd_install() passing the returned pidfd and pidfd file as arguments in + * order to install the pidfd into its file descriptor table or they must use + * put_unused_fd() and fput() on the returned pidfd and pidfd file + * respectively. + * + * This function is useful when a pidfd must already be reserved but there + * might still be points of failure afterwards and the caller wants to ensure + * that no pidfd is leaked into its file descriptor table. + * + * Return: On success, a reserved pidfd is returned from the function and a new + * pidfd file is returned in the last argument to the function. On + * error, a negative error code is returned from the function and the + * last argument remains unchanged. + */ +static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret) +{ + int pidfd; + struct file *pidfd_file; + + if (flags & ~(O_NONBLOCK | O_RDWR | O_CLOEXEC)) + return -EINVAL; + + pidfd = get_unused_fd_flags(O_RDWR | O_CLOEXEC); + if (pidfd < 0) + return pidfd; + + pidfd_file = anon_inode_getfile("[pidfd]", &pidfd_fops, pid, + flags | O_RDWR | O_CLOEXEC); + if (IS_ERR(pidfd_file)) { + put_unused_fd(pidfd); + return PTR_ERR(pidfd_file); + } + get_pid(pid); /* held by pidfd_file now */ + *ret = pidfd_file; + return pidfd; +} + +/** + * pidfd_prepare - allocate a new pidfd_file and reserve a pidfd + * @pid: the struct pid for which to create a pidfd + * @flags: flags of the new @pidfd + * @pidfd: the pidfd to return + * + * Allocate a new file that stashes @pid and reserve a new pidfd number in the + * caller's file descriptor table. The pidfd is reserved but not installed yet. + * + * The helper verifies that @pid is used as a thread group leader. + * + * If this function returns successfully the caller is responsible to either + * call fd_install() passing the returned pidfd and pidfd file as arguments in + * order to install the pidfd into its file descriptor table or they must use + * put_unused_fd() and fput() on the returned pidfd and pidfd file + * respectively. + * + * This function is useful when a pidfd must already be reserved but there + * might still be points of failure afterwards and the caller wants to ensure + * that no pidfd is leaked into its file descriptor table. + * + * Return: On success, a reserved pidfd is returned from the function and a new + * pidfd file is returned in the last argument to the function. On + * error, a negative error code is returned from the function and the + * last argument remains unchanged. + */ +int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret) +{ + if (!pid || !pid_has_task(pid, PIDTYPE_TGID)) + return -EINVAL; + + return __pidfd_prepare(pid, flags, ret); +} + static void __delayed_free_task(struct rcu_head *rhp) { struct task_struct *tsk = container_of(rhp, struct task_struct, rcu); @@ -2398,21 +2483,12 @@ static __latent_entropy struct task_struct *copy_process( * if the fd table isn't shared). */ if (clone_flags & CLONE_PIDFD) { - retval = get_unused_fd_flags(O_RDWR | O_CLOEXEC); + /* Note that no task has been attached to @pid yet. */ + retval = __pidfd_prepare(pid, O_RDWR | O_CLOEXEC, &pidfile); if (retval < 0) goto bad_fork_free_pid; - pidfd = retval; - pidfile = anon_inode_getfile("[pidfd]", &pidfd_fops, pid, - O_RDWR | O_CLOEXEC); - if (IS_ERR(pidfile)) { - put_unused_fd(pidfd); - retval = PTR_ERR(pidfile); - goto bad_fork_free_pid; - } - get_pid(pid); /* held by pidfile now */ - retval = put_user(pidfd, args->pidfd); if (retval) goto bad_fork_put_pidfd; diff --git a/kernel/padata.c b/kernel/padata.c index e2bef90e6fd0..b3f79f23060c 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -350,7 +350,8 @@ static void padata_reorder(struct parallel_data *pd) * To avoid UAF issue, add pd ref here, and put pd ref after reorder_work finish. */ padata_get_pd(pd); - queue_work(pinst->serial_wq, &pd->reorder_work); + if (!queue_work(pinst->serial_wq, &pd->reorder_work)) + padata_put_pd(pd); } } diff --git a/kernel/params.c b/kernel/params.c index 5b92310425c5..27954dfe3d20 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -945,7 +945,9 @@ int module_sysfs_initialized; static void module_kobj_release(struct kobject *kobj) { struct module_kobject *mk = to_module_kobject(kobj); - complete(mk->kobj_completion); + + if (mk->kobj_completion) + complete(mk->kobj_completion); } struct kobj_type module_ktype = { diff --git a/kernel/pid.c b/kernel/pid.c index 9efcf7178b01..087d1ac1ac2e 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -595,20 +595,15 @@ struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags) */ int pidfd_create(struct pid *pid, unsigned int flags) { - int fd; + int pidfd; + struct file *pidfd_file; - if (!pid || !pid_has_task(pid, PIDTYPE_TGID)) - return -EINVAL; + pidfd = pidfd_prepare(pid, flags, &pidfd_file); + if (pidfd < 0) + return pidfd; - if (flags & ~(O_NONBLOCK | O_RDWR | O_CLOEXEC)) - return -EINVAL; - - fd = anon_inode_getfd("[pidfd]", &pidfd_fops, get_pid(pid), - flags | O_RDWR | O_CLOEXEC); - if (fd < 0) - put_pid(pid); - - return fd; + fd_install(pidfd, pidfd_file); + return pidfd; } /** diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 044026abfdd7..3929ef8148c1 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -821,8 +821,17 @@ void rcu_read_unlock_strict(void) { struct rcu_data *rdp; - if (irqs_disabled() || preempt_count() || !rcu_state.gp_kthread) + if (irqs_disabled() || in_atomic_preempt_off() || !rcu_state.gp_kthread) return; + + /* + * rcu_report_qs_rdp() can only be invoked with a stable rdp and + * from the local CPU. + * + * The in_atomic_preempt_off() check ensures that we come here holding + * the last preempt_count (which will get dropped once we return to + * __rcu_read_unlock(). + */ rdp = this_cpu_ptr(&rcu_data); rdp->cpu_no_qs.b.norm = false; rcu_report_qs_rdp(rdp); @@ -963,13 +972,16 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) */ static void rcu_flavor_sched_clock_irq(int user) { - if (user || rcu_is_cpu_rrupt_from_idle()) { + if (user || rcu_is_cpu_rrupt_from_idle() || + (IS_ENABLED(CONFIG_PREEMPT_COUNT) && + (preempt_count() == HARDIRQ_OFFSET))) { /* * Get here if this CPU took its interrupt from user - * mode or from the idle loop, and if this is not a - * nested interrupt. In this case, the CPU is in - * a quiescent state, so note it. + * mode, from the idle loop without this being a nested + * interrupt, or while not holding the task preempt count + * (with PREEMPT_COUNT=y). In this case, the CPU is in a + * quiescent state, so note it. * * No memory barrier is required here because rcu_qs() * references only CPU-local variables that other CPUs diff --git a/kernel/softirq.c b/kernel/softirq.c index 86eae160815d..bb16cea18d7c 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -167,6 +167,18 @@ static DEFINE_PER_CPU(struct softirq_ctrl, softirq_ctrl) = { .lock = INIT_LOCAL_LOCK(softirq_ctrl.lock), }; +#ifdef CONFIG_DEBUG_LOCK_ALLOC +static struct lock_class_key bh_lock_key; +struct lockdep_map bh_lock_map = { + .name = "local_bh", + .key = &bh_lock_key, + .wait_type_outer = LD_WAIT_FREE, + .wait_type_inner = LD_WAIT_CONFIG, /* PREEMPT_RT makes BH preemptible. */ + .lock_type = LD_LOCK_PERCPU, +}; +EXPORT_SYMBOL_GPL(bh_lock_map); +#endif + /** * local_bh_blocked() - Check for idle whether BH processing is blocked * @@ -189,6 +201,8 @@ void __local_bh_disable_ip(unsigned long ip, unsigned int cnt) WARN_ON_ONCE(in_hardirq()); + lock_map_acquire_read(&bh_lock_map); + /* First entry of a task into a BH disabled section? */ if (!current->softirq_disable_cnt) { if (preemptible()) { @@ -252,6 +266,8 @@ void __local_bh_enable_ip(unsigned long ip, unsigned int cnt) WARN_ON_ONCE(in_hardirq()); lockdep_assert_irqs_enabled(); + lock_map_release(&bh_lock_map); + local_irq_save(flags); curcnt = __this_cpu_read(softirq_ctrl.cnt); @@ -302,6 +318,8 @@ static inline void ksoftirqd_run_begin(void) /* Counterpart to ksoftirqd_run_begin() */ static inline void ksoftirqd_run_end(void) { + /* pairs with the lock_map_acquire_read() in ksoftirqd_run_begin() */ + lock_map_release(&bh_lock_map); __local_bh_enable(SOFTIRQ_OFFSET, true); WARN_ON_ONCE(in_interrupt()); local_irq_enable(); diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index ed3c4a954398..192404805c0b 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -157,6 +157,7 @@ static int posix_timer_add(struct k_itimer *timer) /* Loop over all possible ids completed */ ret = -EAGAIN; spin_unlock(&hash_lock); + cond_resched(); } while (ret == -ENOENT); return ret; } diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index ed7d6ad694fb..20a5e6962b69 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -46,7 +46,7 @@ static void print_timer(struct seq_file *m, struct hrtimer *taddr, struct hrtimer *timer, int idx, u64 now) { - SEQ_printf(m, " #%d: <%pK>, %ps", idx, taddr, timer->function); + SEQ_printf(m, " #%d: <%p>, %ps", idx, taddr, timer->function); SEQ_printf(m, ", S:%02x", timer->state); SEQ_printf(m, "\n"); SEQ_printf(m, " # expires at %Lu-%Lu nsecs [in %Ld to %Ld nsecs]\n", @@ -98,7 +98,7 @@ next_one: static void print_base(struct seq_file *m, struct hrtimer_clock_base *base, u64 now) { - SEQ_printf(m, " .base: %pK\n", base); + SEQ_printf(m, " .base: %p\n", base); SEQ_printf(m, " .index: %d\n", base->index); SEQ_printf(m, " .resolution: %u nsecs\n", hrtimer_resolution); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 0732cf41ce3c..4d689465e8da 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3421,10 +3421,9 @@ out_nobuffer: } EXPORT_SYMBOL_GPL(trace_vbprintk); -__printf(3, 0) -static int -__trace_array_vprintk(struct trace_buffer *buffer, - unsigned long ip, const char *fmt, va_list args) +static __printf(3, 0) +int __trace_array_vprintk(struct trace_buffer *buffer, + unsigned long ip, const char *fmt, va_list args) { struct trace_event_call *call = &event_print; struct ring_buffer_event *event; @@ -3477,7 +3476,6 @@ out_nobuffer: return len; } -__printf(3, 0) int trace_array_vprintk(struct trace_array *tr, unsigned long ip, const char *fmt, va_list args) { @@ -3504,7 +3502,6 @@ int trace_array_vprintk(struct trace_array *tr, * Note, trace_array_init_printk() must be called on @tr before this * can be used. */ -__printf(3, 0) int trace_array_printk(struct trace_array *tr, unsigned long ip, const char *fmt, ...) { @@ -3549,7 +3546,6 @@ int trace_array_init_printk(struct trace_array *tr) } EXPORT_SYMBOL_GPL(trace_array_init_printk); -__printf(3, 4) int trace_array_printk_buf(struct trace_buffer *buffer, unsigned long ip, const char *fmt, ...) { @@ -3565,7 +3561,6 @@ int trace_array_printk_buf(struct trace_buffer *buffer, return ret; } -__printf(2, 0) int trace_vprintk(unsigned long ip, const char *fmt, va_list args) { return trace_array_vprintk(&global_trace, ip, fmt, args); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 5a9cbffb2dd3..a4ad0d30ba14 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -778,13 +778,15 @@ static inline void __init disable_tracing_selftest(const char *reason) extern void *head_page(struct trace_array_cpu *data); extern unsigned long long ns2usecs(u64 nsec); -extern int -trace_vbprintk(unsigned long ip, const char *fmt, va_list args); -extern int -trace_vprintk(unsigned long ip, const char *fmt, va_list args); -extern int -trace_array_vprintk(struct trace_array *tr, - unsigned long ip, const char *fmt, va_list args); + +__printf(2, 0) +int trace_vbprintk(unsigned long ip, const char *fmt, va_list args); +__printf(2, 0) +int trace_vprintk(unsigned long ip, const char *fmt, va_list args); +__printf(3, 0) +int trace_array_vprintk(struct trace_array *tr, + unsigned long ip, const char *fmt, va_list args); +__printf(3, 4) int trace_array_printk_buf(struct trace_buffer *buffer, unsigned long ip, const char *fmt, ...); void trace_printk_seq(struct trace_seq *s); diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c index 4376887e0d8a..c9b0533407ed 100644 --- a/kernel/trace/trace_dynevent.c +++ b/kernel/trace/trace_dynevent.c @@ -16,7 +16,7 @@ #include "trace_output.h" /* for trace_event_sem */ #include "trace_dynevent.h" -static DEFINE_MUTEX(dyn_event_ops_mutex); +DEFINE_MUTEX(dyn_event_ops_mutex); static LIST_HEAD(dyn_event_ops_list); bool trace_event_dyn_try_get_ref(struct trace_event_call *dyn_call) @@ -125,6 +125,20 @@ out: return ret; } +/* + * Locked version of event creation. The event creation must be protected by + * dyn_event_ops_mutex because of protecting trace_probe_log. + */ +int dyn_event_create(const char *raw_command, struct dyn_event_operations *type) +{ + int ret; + + mutex_lock(&dyn_event_ops_mutex); + ret = type->create(raw_command); + mutex_unlock(&dyn_event_ops_mutex); + return ret; +} + static int create_dyn_event(const char *raw_command) { struct dyn_event_operations *ops; diff --git a/kernel/trace/trace_dynevent.h b/kernel/trace/trace_dynevent.h index 936477a111d3..beee3f8d7544 100644 --- a/kernel/trace/trace_dynevent.h +++ b/kernel/trace/trace_dynevent.h @@ -100,6 +100,7 @@ void *dyn_event_seq_next(struct seq_file *m, void *v, loff_t *pos); void dyn_event_seq_stop(struct seq_file *m, void *v); int dyn_events_release_all(struct dyn_event_operations *type); int dyn_event_release(const char *raw_command, struct dyn_event_operations *type); +int dyn_event_create(const char *raw_command, struct dyn_event_operations *type); /* * for_each_dyn_event - iterate over the dyn_event list diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index f941ce01ee35..afdbad16d00a 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -1539,7 +1539,7 @@ stacktrace_trigger(struct event_trigger_data *data, struct trace_event_file *file = data->private_data; if (file) - __trace_stack(file->tr, tracing_gen_ctx(), STACK_SKIP); + __trace_stack(file->tr, tracing_gen_ctx_dec(), STACK_SKIP); else trace_dump_stack(STACK_SKIP); } diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 69e92c7359fb..44ae51d1dc45 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -561,11 +561,7 @@ ftrace_traceoff(unsigned long ip, unsigned long parent_ip, static __always_inline void trace_stack(struct trace_array *tr) { - unsigned int trace_ctx; - - trace_ctx = tracing_gen_ctx(); - - __trace_stack(tr, trace_ctx, FTRACE_STACK_SKIP); + __trace_stack(tr, tracing_gen_ctx_dec(), FTRACE_STACK_SKIP); } static void diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 72655d81b37d..cc155c411768 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -975,7 +975,7 @@ static int create_or_delete_trace_kprobe(const char *raw_command) if (raw_command[0] == '-') return dyn_event_release(raw_command, &trace_kprobe_ops); - ret = trace_kprobe_create(raw_command); + ret = dyn_event_create(raw_command, &trace_kprobe_ops); return ret == -ECANCELED ? -EINVAL : ret; } diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index ba48b5e270e1..3888a59c9dfe 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -143,9 +143,12 @@ fail: } static struct trace_probe_log trace_probe_log; +extern struct mutex dyn_event_ops_mutex; void trace_probe_log_init(const char *subsystem, int argc, const char **argv) { + lockdep_assert_held(&dyn_event_ops_mutex); + trace_probe_log.subsystem = subsystem; trace_probe_log.argc = argc; trace_probe_log.argv = argv; @@ -154,11 +157,15 @@ void trace_probe_log_init(const char *subsystem, int argc, const char **argv) void trace_probe_log_clear(void) { + lockdep_assert_held(&dyn_event_ops_mutex); + memset(&trace_probe_log, 0, sizeof(trace_probe_log)); } void trace_probe_log_set_index(int index) { + lockdep_assert_held(&dyn_event_ops_mutex); + trace_probe_log.index = index; } @@ -167,6 +174,8 @@ void __trace_probe_log_err(int offset, int err_type) char *command, *p; int i, len = 0, pos = 0; + lockdep_assert_held(&dyn_event_ops_mutex); + if (!trace_probe_log.argv) return; diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index a6a3ff2a441e..53ef3cb65098 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -732,7 +732,7 @@ static int create_or_delete_trace_uprobe(const char *raw_command) if (raw_command[0] == '-') return dyn_event_release(raw_command, &trace_uprobe_ops); - ret = trace_uprobe_create(raw_command); + ret = dyn_event_create(raw_command, &trace_uprobe_ops); return ret == -ECANCELED ? -EINVAL : ret; } diff --git a/lib/dynamic_queue_limits.c b/lib/dynamic_queue_limits.c index fde0aa244148..a75a9ca46b59 100644 --- a/lib/dynamic_queue_limits.c +++ b/lib/dynamic_queue_limits.c @@ -116,7 +116,7 @@ EXPORT_SYMBOL(dql_completed); void dql_reset(struct dql *dql) { /* Reset all dynamic values */ - dql->limit = 0; + dql->limit = dql->min_limit; dql->num_queued = 0; dql->num_completed = 0; dql->last_obj_cnt = 0; diff --git a/lib/lzo/Makefile b/lib/lzo/Makefile index 2f58fafbbddd..fc7b2b7ef4b2 100644 --- a/lib/lzo/Makefile +++ b/lib/lzo/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -lzo_compress-objs := lzo1x_compress.o +lzo_compress-objs := lzo1x_compress.o lzo1x_compress_safe.o lzo_decompress-objs := lzo1x_decompress_safe.o obj-$(CONFIG_LZO_COMPRESS) += lzo_compress.o diff --git a/lib/lzo/lzo1x_compress.c b/lib/lzo/lzo1x_compress.c index 9d31e7126606..f00dff9b9d4e 100644 --- a/lib/lzo/lzo1x_compress.c +++ b/lib/lzo/lzo1x_compress.c @@ -18,11 +18,22 @@ #include #include "lzodefs.h" -static noinline size_t -lzo1x_1_do_compress(const unsigned char *in, size_t in_len, - unsigned char *out, size_t *out_len, - size_t ti, void *wrkmem, signed char *state_offset, - const unsigned char bitstream_version) +#undef LZO_UNSAFE + +#ifndef LZO_SAFE +#define LZO_UNSAFE 1 +#define LZO_SAFE(name) name +#define HAVE_OP(x) 1 +#endif + +#define NEED_OP(x) if (!HAVE_OP(x)) goto output_overrun + +static noinline int +LZO_SAFE(lzo1x_1_do_compress)(const unsigned char *in, size_t in_len, + unsigned char **out, unsigned char *op_end, + size_t *tp, void *wrkmem, + signed char *state_offset, + const unsigned char bitstream_version) { const unsigned char *ip; unsigned char *op; @@ -30,8 +41,9 @@ lzo1x_1_do_compress(const unsigned char *in, size_t in_len, const unsigned char * const ip_end = in + in_len - 20; const unsigned char *ii; lzo_dict_t * const dict = (lzo_dict_t *) wrkmem; + size_t ti = *tp; - op = out; + op = *out; ip = in; ii = ip; ip += ti < 4 ? 4 - ti : 0; @@ -116,25 +128,32 @@ next: if (t != 0) { if (t <= 3) { op[*state_offset] |= t; + NEED_OP(4); COPY4(op, ii); op += t; } else if (t <= 16) { + NEED_OP(17); *op++ = (t - 3); COPY8(op, ii); COPY8(op + 8, ii + 8); op += t; } else { if (t <= 18) { + NEED_OP(1); *op++ = (t - 3); } else { size_t tt = t - 18; + NEED_OP(1); *op++ = 0; while (unlikely(tt > 255)) { tt -= 255; + NEED_OP(1); *op++ = 0; } + NEED_OP(1); *op++ = tt; } + NEED_OP(t); do { COPY8(op, ii); COPY8(op + 8, ii + 8); @@ -151,6 +170,7 @@ next: if (unlikely(run_length)) { ip += run_length; run_length -= MIN_ZERO_RUN_LENGTH; + NEED_OP(4); put_unaligned_le32((run_length << 21) | 0xfffc18 | (run_length & 0x7), op); op += 4; @@ -243,10 +263,12 @@ m_len_done: ip += m_len; if (m_len <= M2_MAX_LEN && m_off <= M2_MAX_OFFSET) { m_off -= 1; + NEED_OP(2); *op++ = (((m_len - 1) << 5) | ((m_off & 7) << 2)); *op++ = (m_off >> 3); } else if (m_off <= M3_MAX_OFFSET) { m_off -= 1; + NEED_OP(1); if (m_len <= M3_MAX_LEN) *op++ = (M3_MARKER | (m_len - 2)); else { @@ -254,14 +276,18 @@ m_len_done: *op++ = M3_MARKER | 0; while (unlikely(m_len > 255)) { m_len -= 255; + NEED_OP(1); *op++ = 0; } + NEED_OP(1); *op++ = (m_len); } + NEED_OP(2); *op++ = (m_off << 2); *op++ = (m_off >> 6); } else { m_off -= 0x4000; + NEED_OP(1); if (m_len <= M4_MAX_LEN) *op++ = (M4_MARKER | ((m_off >> 11) & 8) | (m_len - 2)); @@ -282,11 +308,14 @@ m_len_done: m_len -= M4_MAX_LEN; *op++ = (M4_MARKER | ((m_off >> 11) & 8)); while (unlikely(m_len > 255)) { + NEED_OP(1); m_len -= 255; *op++ = 0; } + NEED_OP(1); *op++ = (m_len); } + NEED_OP(2); *op++ = (m_off << 2); *op++ = (m_off >> 6); } @@ -295,14 +324,20 @@ finished_writing_instruction: ii = ip; goto next; } - *out_len = op - out; - return in_end - (ii - ti); + *out = op; + *tp = in_end - (ii - ti); + return LZO_E_OK; + +output_overrun: + return LZO_E_OUTPUT_OVERRUN; } -static int lzogeneric1x_1_compress(const unsigned char *in, size_t in_len, - unsigned char *out, size_t *out_len, - void *wrkmem, const unsigned char bitstream_version) +static int LZO_SAFE(lzogeneric1x_1_compress)( + const unsigned char *in, size_t in_len, + unsigned char *out, size_t *out_len, + void *wrkmem, const unsigned char bitstream_version) { + unsigned char * const op_end = out + *out_len; const unsigned char *ip = in; unsigned char *op = out; unsigned char *data_start; @@ -326,14 +361,18 @@ static int lzogeneric1x_1_compress(const unsigned char *in, size_t in_len, while (l > 20) { size_t ll = min_t(size_t, l, m4_max_offset + 1); uintptr_t ll_end = (uintptr_t) ip + ll; + int err; + if ((ll_end + ((t + ll) >> 5)) <= ll_end) break; BUILD_BUG_ON(D_SIZE * sizeof(lzo_dict_t) > LZO1X_1_MEM_COMPRESS); memset(wrkmem, 0, D_SIZE * sizeof(lzo_dict_t)); - t = lzo1x_1_do_compress(ip, ll, op, out_len, t, wrkmem, - &state_offset, bitstream_version); + err = LZO_SAFE(lzo1x_1_do_compress)( + ip, ll, &op, op_end, &t, wrkmem, + &state_offset, bitstream_version); + if (err != LZO_E_OK) + return err; ip += ll; - op += *out_len; l -= ll; } t += l; @@ -342,20 +381,26 @@ static int lzogeneric1x_1_compress(const unsigned char *in, size_t in_len, const unsigned char *ii = in + in_len - t; if (op == data_start && t <= 238) { + NEED_OP(1); *op++ = (17 + t); } else if (t <= 3) { op[state_offset] |= t; } else if (t <= 18) { + NEED_OP(1); *op++ = (t - 3); } else { size_t tt = t - 18; + NEED_OP(1); *op++ = 0; while (tt > 255) { tt -= 255; + NEED_OP(1); *op++ = 0; } + NEED_OP(1); *op++ = tt; } + NEED_OP(t); if (t >= 16) do { COPY8(op, ii); COPY8(op + 8, ii + 8); @@ -368,31 +413,38 @@ static int lzogeneric1x_1_compress(const unsigned char *in, size_t in_len, } while (--t > 0); } + NEED_OP(3); *op++ = M4_MARKER | 1; *op++ = 0; *op++ = 0; *out_len = op - out; return LZO_E_OK; + +output_overrun: + return LZO_E_OUTPUT_OVERRUN; } -int lzo1x_1_compress(const unsigned char *in, size_t in_len, - unsigned char *out, size_t *out_len, - void *wrkmem) +int LZO_SAFE(lzo1x_1_compress)(const unsigned char *in, size_t in_len, + unsigned char *out, size_t *out_len, + void *wrkmem) { - return lzogeneric1x_1_compress(in, in_len, out, out_len, wrkmem, 0); + return LZO_SAFE(lzogeneric1x_1_compress)( + in, in_len, out, out_len, wrkmem, 0); } -int lzorle1x_1_compress(const unsigned char *in, size_t in_len, - unsigned char *out, size_t *out_len, - void *wrkmem) +int LZO_SAFE(lzorle1x_1_compress)(const unsigned char *in, size_t in_len, + unsigned char *out, size_t *out_len, + void *wrkmem) { - return lzogeneric1x_1_compress(in, in_len, out, out_len, - wrkmem, LZO_VERSION); + return LZO_SAFE(lzogeneric1x_1_compress)( + in, in_len, out, out_len, wrkmem, LZO_VERSION); } -EXPORT_SYMBOL_GPL(lzo1x_1_compress); -EXPORT_SYMBOL_GPL(lzorle1x_1_compress); +EXPORT_SYMBOL_GPL(LZO_SAFE(lzo1x_1_compress)); +EXPORT_SYMBOL_GPL(LZO_SAFE(lzorle1x_1_compress)); +#ifndef LZO_UNSAFE MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("LZO1X-1 Compressor"); +#endif diff --git a/lib/lzo/lzo1x_compress_safe.c b/lib/lzo/lzo1x_compress_safe.c new file mode 100644 index 000000000000..371c9f849492 --- /dev/null +++ b/lib/lzo/lzo1x_compress_safe.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * LZO1X Compressor from LZO + * + * Copyright (C) 1996-2012 Markus F.X.J. Oberhumer + * + * The full LZO package can be found at: + * http://www.oberhumer.com/opensource/lzo/ + * + * Changed for Linux kernel use by: + * Nitin Gupta + * Richard Purdie + */ + +#define LZO_SAFE(name) name##_safe +#define HAVE_OP(x) ((size_t)(op_end - op) >= (size_t)(x)) + +#include "lzo1x_compress.c" diff --git a/mm/memcontrol.c b/mm/memcontrol.c index aa0ff7d81c70..bd6fd63cb7a5 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1267,7 +1267,6 @@ int mem_cgroup_scan_tasks(struct mem_cgroup *memcg, { struct mem_cgroup *iter; int ret = 0; - int i = 0; BUG_ON(memcg == root_mem_cgroup); @@ -1277,10 +1276,9 @@ int mem_cgroup_scan_tasks(struct mem_cgroup *memcg, css_task_iter_start(&iter->css, CSS_TASK_ITER_PROCS, &it); while (!ret && (task = css_task_iter_next(&it))) { - /* Avoid potential softlockup warning */ - if ((++i & 1023) == 0) - cond_resched(); ret = fn(task, arg); + /* Avoid potential softlockup warning */ + cond_resched(); } css_task_iter_end(&it); if (ret) { diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index dc17618bad8b..c8cc2f63c3ea 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1656,8 +1656,12 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) if (PageHWPoison(page)) { if (WARN_ON(folio_test_lru(folio))) folio_isolate_lru(folio); - if (folio_mapped(folio)) + if (folio_mapped(folio)) { + folio_lock(folio); try_to_unmap(folio, TTU_IGNORE_MLOCK); + folio_unlock(folio); + } + continue; } diff --git a/mm/migrate.c b/mm/migrate.c index 0ad9535a8e56..9df001685f83 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2430,6 +2430,14 @@ static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) if (managed_zone(pgdat->node_zones + z)) break; } + + /* + * If there are no managed zones, it should not proceed + * further. + */ + if (z < 0) + return 0; + wakeup_kswapd(pgdat->node_zones + z, 0, order, ZONE_MOVABLE); return 0; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 23a88efe9d86..7b3b6bfcede7 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5416,6 +5416,14 @@ restart: } retry: + /* + * Deal with possible cpuset update races or zonelist updates to avoid + * infinite retries. + */ + if (check_retry_cpuset(cpuset_mems_cookie, ac) || + check_retry_zonelist(zonelist_iter_cookie)) + goto restart; + /* Ensure kswapd doesn't accidentally go to sleep as long as we loop */ if (alloc_flags & ALLOC_KSWAPD) wake_all_kswapds(order, gfp_mask, ac); diff --git a/net/Makefile b/net/Makefile index 0914bea9c335..103cd8d61f68 100644 --- a/net/Makefile +++ b/net/Makefile @@ -17,7 +17,7 @@ obj-$(CONFIG_NETFILTER) += netfilter/ obj-$(CONFIG_INET) += ipv4/ obj-$(CONFIG_TLS) += tls/ obj-$(CONFIG_XFRM) += xfrm/ -obj-$(CONFIG_UNIX_SCM) += unix/ +obj-$(CONFIG_UNIX) += unix/ obj-y += ipv6/ obj-$(CONFIG_BPFILTER) += bpfilter/ obj-$(CONFIG_PACKET) += packet/ diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 812d6d0fe5e2..3d08c1919f90 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -1537,7 +1537,8 @@ static void l2cap_request_info(struct l2cap_conn *conn) sizeof(req), &req); } -static bool l2cap_check_enc_key_size(struct hci_conn *hcon) +static bool l2cap_check_enc_key_size(struct hci_conn *hcon, + struct l2cap_chan *chan) { /* The minimum encryption key size needs to be enforced by the * host stack before establishing any L2CAP connections. The @@ -1551,7 +1552,7 @@ static bool l2cap_check_enc_key_size(struct hci_conn *hcon) int min_key_size = hcon->hdev->min_enc_key_size; /* On FIPS security level, key size must be 16 bytes */ - if (hcon->sec_level == BT_SECURITY_FIPS) + if (chan->sec_level == BT_SECURITY_FIPS) min_key_size = 16; return (!test_bit(HCI_CONN_ENCRYPT, &hcon->flags) || @@ -1579,7 +1580,7 @@ static void l2cap_do_start(struct l2cap_chan *chan) !__l2cap_no_conn_pending(chan)) return; - if (l2cap_check_enc_key_size(conn->hcon)) + if (l2cap_check_enc_key_size(conn->hcon, chan)) l2cap_start_connection(chan); else __set_chan_timer(chan, L2CAP_DISC_TIMEOUT); @@ -1661,7 +1662,7 @@ static void l2cap_conn_start(struct l2cap_conn *conn) continue; } - if (l2cap_check_enc_key_size(conn->hcon)) + if (l2cap_check_enc_key_size(conn->hcon, chan)) l2cap_start_connection(chan); else l2cap_chan_close(chan, ECONNREFUSED); @@ -4163,7 +4164,7 @@ static struct l2cap_chan *l2cap_connect(struct l2cap_conn *conn, /* Check if the ACL is secure enough (if not SDP) */ if (psm != cpu_to_le16(L2CAP_PSM_SDP) && (!hci_conn_check_link_mode(conn->hcon) || - !l2cap_check_enc_key_size(conn->hcon))) { + !l2cap_check_enc_key_size(conn->hcon, pchan))) { conn->disc_reason = HCI_ERROR_AUTH_FAILURE; result = L2CAP_CR_SEC_BLOCK; goto response; @@ -8376,7 +8377,7 @@ static void l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) } if (chan->state == BT_CONNECT) { - if (!status && l2cap_check_enc_key_size(hcon)) + if (!status && l2cap_check_enc_key_size(hcon, chan)) l2cap_start_connection(chan); else __set_chan_timer(chan, L2CAP_DISC_TIMEOUT); @@ -8386,7 +8387,7 @@ static void l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) struct l2cap_conn_rsp rsp; __u16 res, stat; - if (!status && l2cap_check_enc_key_size(hcon)) { + if (!status && l2cap_check_enc_key_size(hcon, chan)) { if (test_bit(FLAG_DEFER_SETUP, &chan->flags)) { res = L2CAP_CR_PEND; stat = L2CAP_CS_AUTHOR_PEND; diff --git a/net/bridge/br_nf_core.c b/net/bridge/br_nf_core.c index 8c69f0c95a8e..b8c8deb87407 100644 --- a/net/bridge/br_nf_core.c +++ b/net/bridge/br_nf_core.c @@ -65,17 +65,14 @@ static struct dst_ops fake_dst_ops = { * ipt_REJECT needs it. Future netfilter modules might * require us to fill additional fields. */ -static const u32 br_dst_default_metrics[RTAX_MAX] = { - [RTAX_MTU - 1] = 1500, -}; - void br_netfilter_rtable_init(struct net_bridge *br) { struct rtable *rt = &br->fake_rtable; atomic_set(&rt->dst.__refcnt, 1); rt->dst.dev = br->dev; - dst_init_metrics(&rt->dst, br_dst_default_metrics, true); + dst_init_metrics(&rt->dst, br->metrics, false); + dst_metric_set(&rt->dst, RTAX_MTU, br->dev->mtu); rt->dst.flags = DST_NOXFRM | DST_FAKE_RTABLE; rt->dst.ops = &fake_dst_ops; } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 940de9516768..19fb50549252 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -478,6 +478,7 @@ struct net_bridge { struct rtable fake_rtable; struct rt6_info fake_rt6_info; }; + u32 metrics[RTAX_MAX]; #endif u16 group_fwd_mask; u16 group_fwd_mask_required; diff --git a/net/can/bcm.c b/net/can/bcm.c index 3817692e83af..4fb5cfaf74f3 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -58,6 +58,7 @@ #include #include #include +#include #include #include @@ -120,6 +121,7 @@ struct bcm_op { struct canfd_frame last_sframe; struct sock *sk; struct net_device *rx_reg_dev; + spinlock_t bcm_tx_lock; /* protect currframe/count in runtime updates */ }; struct bcm_sock { @@ -205,7 +207,9 @@ static int bcm_proc_show(struct seq_file *m, void *v) seq_printf(m, " / bound %s", bcm_proc_getifname(net, ifname, bo->ifindex)); seq_printf(m, " <<<\n"); - list_for_each_entry(op, &bo->rx_ops, list) { + rcu_read_lock(); + + list_for_each_entry_rcu(op, &bo->rx_ops, list) { unsigned long reduction; @@ -261,6 +265,9 @@ static int bcm_proc_show(struct seq_file *m, void *v) seq_printf(m, "# sent %ld\n", op->frames_abs); } seq_putc(m, '\n'); + + rcu_read_unlock(); + return 0; } #endif /* CONFIG_PROC_FS */ @@ -273,13 +280,18 @@ static void bcm_can_tx(struct bcm_op *op) { struct sk_buff *skb; struct net_device *dev; - struct canfd_frame *cf = op->frames + op->cfsiz * op->currframe; + struct canfd_frame *cf; int err; /* no target device? => exit */ if (!op->ifindex) return; + /* read currframe under lock protection */ + spin_lock_bh(&op->bcm_tx_lock); + cf = op->frames + op->cfsiz * op->currframe; + spin_unlock_bh(&op->bcm_tx_lock); + dev = dev_get_by_index(sock_net(op->sk), op->ifindex); if (!dev) { /* RFC: should this bcm_op remove itself here? */ @@ -300,6 +312,10 @@ static void bcm_can_tx(struct bcm_op *op) skb->dev = dev; can_skb_set_owner(skb, op->sk); err = can_send(skb, 1); + + /* update currframe and count under lock protection */ + spin_lock_bh(&op->bcm_tx_lock); + if (!err) op->frames_abs++; @@ -308,6 +324,11 @@ static void bcm_can_tx(struct bcm_op *op) /* reached last frame? */ if (op->currframe >= op->nframes) op->currframe = 0; + + if (op->count > 0) + op->count--; + + spin_unlock_bh(&op->bcm_tx_lock); out: dev_put(dev); } @@ -404,7 +425,7 @@ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer) struct bcm_msg_head msg_head; if (op->kt_ival1 && (op->count > 0)) { - op->count--; + bcm_can_tx(op); if (!op->count && (op->flags & TX_COUNTEVT)) { /* create notification to user */ @@ -419,7 +440,6 @@ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer) bcm_send_to_user(op, &msg_head, NULL, 0); } - bcm_can_tx(op); } else if (op->kt_ival2) { bcm_can_tx(op); @@ -801,7 +821,7 @@ static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh, REGMASK(op->can_id), bcm_rx_handler, op); - list_del(&op->list); + list_del_rcu(&op->list); bcm_remove_op(op); return 1; /* done */ } @@ -821,7 +841,7 @@ static int bcm_delete_tx_op(struct list_head *ops, struct bcm_msg_head *mh, list_for_each_entry_safe(op, n, ops, list) { if ((op->can_id == mh->can_id) && (op->ifindex == ifindex) && (op->flags & CAN_FD_FRAME) == (mh->flags & CAN_FD_FRAME)) { - list_del(&op->list); + list_del_rcu(&op->list); bcm_remove_op(op); return 1; /* done */ } @@ -914,6 +934,27 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, } op->flags = msg_head->flags; + /* only lock for unlikely count/nframes/currframe changes */ + if (op->nframes != msg_head->nframes || + op->flags & TX_RESET_MULTI_IDX || + op->flags & SETTIMER) { + + spin_lock_bh(&op->bcm_tx_lock); + + if (op->nframes != msg_head->nframes || + op->flags & TX_RESET_MULTI_IDX) { + /* potentially update changed nframes */ + op->nframes = msg_head->nframes; + /* restart multiple frame transmission */ + op->currframe = 0; + } + + if (op->flags & SETTIMER) + op->count = msg_head->count; + + spin_unlock_bh(&op->bcm_tx_lock); + } + } else { /* insert new BCM operation for the given can_id */ @@ -921,9 +962,14 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, if (!op) return -ENOMEM; + spin_lock_init(&op->bcm_tx_lock); op->can_id = msg_head->can_id; op->cfsiz = CFSIZ(msg_head->flags); op->flags = msg_head->flags; + op->nframes = msg_head->nframes; + + if (op->flags & SETTIMER) + op->count = msg_head->count; /* create array for CAN frames and copy the data */ if (msg_head->nframes > 1) { @@ -982,22 +1028,8 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, } /* if ((op = bcm_find_op(&bo->tx_ops, msg_head->can_id, ifindex))) */ - if (op->nframes != msg_head->nframes) { - op->nframes = msg_head->nframes; - /* start multiple frame transmission with index 0 */ - op->currframe = 0; - } - - /* check flags */ - - if (op->flags & TX_RESET_MULTI_IDX) { - /* start multiple frame transmission with index 0 */ - op->currframe = 0; - } - if (op->flags & SETTIMER) { /* set timer values */ - op->count = msg_head->count; op->ival1 = msg_head->ival1; op->ival2 = msg_head->ival2; op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1); @@ -1014,11 +1046,8 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, op->flags |= TX_ANNOUNCE; } - if (op->flags & TX_ANNOUNCE) { + if (op->flags & TX_ANNOUNCE) bcm_can_tx(op); - if (op->count) - op->count--; - } if (op->flags & STARTTIMER) bcm_tx_start_timer(op); @@ -1234,7 +1263,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, bcm_rx_handler, op, "bcm", sk); if (err) { /* this bcm rx op is broken -> remove it */ - list_del(&op->list); + list_del_rcu(&op->list); bcm_remove_op(op); return err; } diff --git a/net/can/gw.c b/net/can/gw.c index 23a3d89cad81..5933423663cd 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -130,7 +130,7 @@ struct cgw_job { u32 handled_frames; u32 dropped_frames; u32 deleted_frames; - struct cf_mod mod; + struct cf_mod __rcu *cf_mod; union { /* CAN frame data source */ struct net_device *dev; @@ -459,6 +459,7 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data) struct cgw_job *gwj = (struct cgw_job *)data; struct canfd_frame *cf; struct sk_buff *nskb; + struct cf_mod *mod; int modidx = 0; /* process strictly Classic CAN or CAN FD frames */ @@ -506,7 +507,8 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data) * When there is at least one modification function activated, * we need to copy the skb as we want to modify skb->data. */ - if (gwj->mod.modfunc[0]) + mod = rcu_dereference(gwj->cf_mod); + if (mod->modfunc[0]) nskb = skb_copy(skb, GFP_ATOMIC); else nskb = skb_clone(skb, GFP_ATOMIC); @@ -529,8 +531,8 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data) cf = (struct canfd_frame *)nskb->data; /* perform preprocessed modification functions if there are any */ - while (modidx < MAX_MODFUNCTIONS && gwj->mod.modfunc[modidx]) - (*gwj->mod.modfunc[modidx++])(cf, &gwj->mod); + while (modidx < MAX_MODFUNCTIONS && mod->modfunc[modidx]) + (*mod->modfunc[modidx++])(cf, mod); /* Has the CAN frame been modified? */ if (modidx) { @@ -546,11 +548,11 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data) } /* check for checksum updates */ - if (gwj->mod.csumfunc.crc8) - (*gwj->mod.csumfunc.crc8)(cf, &gwj->mod.csum.crc8); + if (mod->csumfunc.crc8) + (*mod->csumfunc.crc8)(cf, &mod->csum.crc8); - if (gwj->mod.csumfunc.xor) - (*gwj->mod.csumfunc.xor)(cf, &gwj->mod.csum.xor); + if (mod->csumfunc.xor) + (*mod->csumfunc.xor)(cf, &mod->csum.xor); } /* clear the skb timestamp if not configured the other way */ @@ -581,9 +583,20 @@ static void cgw_job_free_rcu(struct rcu_head *rcu_head) { struct cgw_job *gwj = container_of(rcu_head, struct cgw_job, rcu); + /* cgw_job::cf_mod is always accessed from the same cgw_job object within + * the same RCU read section. Once cgw_job is scheduled for removal, + * cf_mod can also be removed without mandating an additional grace period. + */ + kfree(rcu_access_pointer(gwj->cf_mod)); kmem_cache_free(cgw_cache, gwj); } +/* Return cgw_job::cf_mod with RTNL protected section */ +static struct cf_mod *cgw_job_cf_mod(struct cgw_job *gwj) +{ + return rcu_dereference_protected(gwj->cf_mod, rtnl_is_locked()); +} + static int cgw_notifier(struct notifier_block *nb, unsigned long msg, void *ptr) { @@ -616,6 +629,7 @@ static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj, int type, { struct rtcanmsg *rtcan; struct nlmsghdr *nlh; + struct cf_mod *mod; nlh = nlmsg_put(skb, pid, seq, type, sizeof(*rtcan), flags); if (!nlh) @@ -650,82 +664,83 @@ static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj, int type, goto cancel; } + mod = cgw_job_cf_mod(gwj); if (gwj->flags & CGW_FLAGS_CAN_FD) { struct cgw_fdframe_mod mb; - if (gwj->mod.modtype.and) { - memcpy(&mb.cf, &gwj->mod.modframe.and, sizeof(mb.cf)); - mb.modtype = gwj->mod.modtype.and; + if (mod->modtype.and) { + memcpy(&mb.cf, &mod->modframe.and, sizeof(mb.cf)); + mb.modtype = mod->modtype.and; if (nla_put(skb, CGW_FDMOD_AND, sizeof(mb), &mb) < 0) goto cancel; } - if (gwj->mod.modtype.or) { - memcpy(&mb.cf, &gwj->mod.modframe.or, sizeof(mb.cf)); - mb.modtype = gwj->mod.modtype.or; + if (mod->modtype.or) { + memcpy(&mb.cf, &mod->modframe.or, sizeof(mb.cf)); + mb.modtype = mod->modtype.or; if (nla_put(skb, CGW_FDMOD_OR, sizeof(mb), &mb) < 0) goto cancel; } - if (gwj->mod.modtype.xor) { - memcpy(&mb.cf, &gwj->mod.modframe.xor, sizeof(mb.cf)); - mb.modtype = gwj->mod.modtype.xor; + if (mod->modtype.xor) { + memcpy(&mb.cf, &mod->modframe.xor, sizeof(mb.cf)); + mb.modtype = mod->modtype.xor; if (nla_put(skb, CGW_FDMOD_XOR, sizeof(mb), &mb) < 0) goto cancel; } - if (gwj->mod.modtype.set) { - memcpy(&mb.cf, &gwj->mod.modframe.set, sizeof(mb.cf)); - mb.modtype = gwj->mod.modtype.set; + if (mod->modtype.set) { + memcpy(&mb.cf, &mod->modframe.set, sizeof(mb.cf)); + mb.modtype = mod->modtype.set; if (nla_put(skb, CGW_FDMOD_SET, sizeof(mb), &mb) < 0) goto cancel; } } else { struct cgw_frame_mod mb; - if (gwj->mod.modtype.and) { - memcpy(&mb.cf, &gwj->mod.modframe.and, sizeof(mb.cf)); - mb.modtype = gwj->mod.modtype.and; + if (mod->modtype.and) { + memcpy(&mb.cf, &mod->modframe.and, sizeof(mb.cf)); + mb.modtype = mod->modtype.and; if (nla_put(skb, CGW_MOD_AND, sizeof(mb), &mb) < 0) goto cancel; } - if (gwj->mod.modtype.or) { - memcpy(&mb.cf, &gwj->mod.modframe.or, sizeof(mb.cf)); - mb.modtype = gwj->mod.modtype.or; + if (mod->modtype.or) { + memcpy(&mb.cf, &mod->modframe.or, sizeof(mb.cf)); + mb.modtype = mod->modtype.or; if (nla_put(skb, CGW_MOD_OR, sizeof(mb), &mb) < 0) goto cancel; } - if (gwj->mod.modtype.xor) { - memcpy(&mb.cf, &gwj->mod.modframe.xor, sizeof(mb.cf)); - mb.modtype = gwj->mod.modtype.xor; + if (mod->modtype.xor) { + memcpy(&mb.cf, &mod->modframe.xor, sizeof(mb.cf)); + mb.modtype = mod->modtype.xor; if (nla_put(skb, CGW_MOD_XOR, sizeof(mb), &mb) < 0) goto cancel; } - if (gwj->mod.modtype.set) { - memcpy(&mb.cf, &gwj->mod.modframe.set, sizeof(mb.cf)); - mb.modtype = gwj->mod.modtype.set; + if (mod->modtype.set) { + memcpy(&mb.cf, &mod->modframe.set, sizeof(mb.cf)); + mb.modtype = mod->modtype.set; if (nla_put(skb, CGW_MOD_SET, sizeof(mb), &mb) < 0) goto cancel; } } - if (gwj->mod.uid) { - if (nla_put_u32(skb, CGW_MOD_UID, gwj->mod.uid) < 0) + if (mod->uid) { + if (nla_put_u32(skb, CGW_MOD_UID, mod->uid) < 0) goto cancel; } - if (gwj->mod.csumfunc.crc8) { + if (mod->csumfunc.crc8) { if (nla_put(skb, CGW_CS_CRC8, CGW_CS_CRC8_LEN, - &gwj->mod.csum.crc8) < 0) + &mod->csum.crc8) < 0) goto cancel; } - if (gwj->mod.csumfunc.xor) { + if (mod->csumfunc.xor) { if (nla_put(skb, CGW_CS_XOR, CGW_CS_XOR_LEN, - &gwj->mod.csum.xor) < 0) + &mod->csum.xor) < 0) goto cancel; } @@ -1059,7 +1074,7 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh, struct net *net = sock_net(skb->sk); struct rtcanmsg *r; struct cgw_job *gwj; - struct cf_mod mod; + struct cf_mod *mod; struct can_can_gw ccgw; u8 limhops = 0; int err = 0; @@ -1078,37 +1093,48 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh, if (r->gwtype != CGW_TYPE_CAN_CAN) return -EINVAL; - err = cgw_parse_attr(nlh, &mod, CGW_TYPE_CAN_CAN, &ccgw, &limhops); - if (err < 0) - return err; + mod = kmalloc(sizeof(*mod), GFP_KERNEL); + if (!mod) + return -ENOMEM; - if (mod.uid) { + err = cgw_parse_attr(nlh, mod, CGW_TYPE_CAN_CAN, &ccgw, &limhops); + if (err < 0) + goto out_free_cf; + + if (mod->uid) { ASSERT_RTNL(); /* check for updating an existing job with identical uid */ hlist_for_each_entry(gwj, &net->can.cgw_list, list) { - if (gwj->mod.uid != mod.uid) + struct cf_mod *old_cf; + + old_cf = cgw_job_cf_mod(gwj); + if (old_cf->uid != mod->uid) continue; /* interfaces & filters must be identical */ - if (memcmp(&gwj->ccgw, &ccgw, sizeof(ccgw))) - return -EINVAL; + if (memcmp(&gwj->ccgw, &ccgw, sizeof(ccgw))) { + err = -EINVAL; + goto out_free_cf; + } - /* update modifications with disabled softirq & quit */ - local_bh_disable(); - memcpy(&gwj->mod, &mod, sizeof(mod)); - local_bh_enable(); + rcu_assign_pointer(gwj->cf_mod, mod); + kfree_rcu_mightsleep(old_cf); return 0; } } /* ifindex == 0 is not allowed for job creation */ - if (!ccgw.src_idx || !ccgw.dst_idx) - return -ENODEV; + if (!ccgw.src_idx || !ccgw.dst_idx) { + err = -ENODEV; + goto out_free_cf; + } gwj = kmem_cache_alloc(cgw_cache, GFP_KERNEL); - if (!gwj) - return -ENOMEM; + if (!gwj) { + err = -ENOMEM; + goto out_free_cf; + } gwj->handled_frames = 0; gwj->dropped_frames = 0; @@ -1118,7 +1144,7 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh, gwj->limit_hops = limhops; /* insert already parsed information */ - memcpy(&gwj->mod, &mod, sizeof(mod)); + RCU_INIT_POINTER(gwj->cf_mod, mod); memcpy(&gwj->ccgw, &ccgw, sizeof(ccgw)); err = -ENODEV; @@ -1145,9 +1171,11 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh, if (!err) hlist_add_head_rcu(&gwj->list, &net->can.cgw_list); out: - if (err) + if (err) { kmem_cache_free(cgw_cache, gwj); - +out_free_cf: + kfree(mod); + } return err; } @@ -1207,19 +1235,22 @@ static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh, /* remove only the first matching entry */ hlist_for_each_entry_safe(gwj, nx, &net->can.cgw_list, list) { + struct cf_mod *cf_mod; + if (gwj->flags != r->flags) continue; if (gwj->limit_hops != limhops) continue; + cf_mod = cgw_job_cf_mod(gwj); /* we have a match when uid is enabled and identical */ - if (gwj->mod.uid || mod.uid) { - if (gwj->mod.uid != mod.uid) + if (cf_mod->uid || mod.uid) { + if (cf_mod->uid != mod.uid) continue; } else { /* no uid => check for identical modifications */ - if (memcmp(&gwj->mod, &mod, sizeof(mod))) + if (memcmp(cf_mod, &mod, sizeof(mod))) continue; } diff --git a/net/core/filter.c b/net/core/filter.c index 8d2e0694b93f..237af340972f 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2499,6 +2499,7 @@ int skb_do_redirect(struct sk_buff *skb) net_eq(net, dev_net(dev)))) goto out_drop; skb->dev = dev; + skb_scrub_packet(skb, false); return -EAGAIN; } return flags & BPF_F_NEIGH ? diff --git a/net/core/pktgen.c b/net/core/pktgen.c index a2fb951996b8..a2838c15aa9d 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -897,6 +897,10 @@ static ssize_t get_labels(const char __user *buffer, struct pktgen_dev *pkt_dev) pkt_dev->nr_labels = 0; do { __u32 tmp; + + if (n >= MAX_MPLS_LABELS) + return -E2BIG; + len = hex32_arg(&buffer[i], 8, &tmp); if (len <= 0) return len; @@ -908,8 +912,6 @@ static ssize_t get_labels(const char __user *buffer, struct pktgen_dev *pkt_dev) return -EFAULT; i++; n++; - if (n >= MAX_MPLS_LABELS) - return -E2BIG; } while (c == ','); pkt_dev->nr_labels = n; @@ -1875,8 +1877,8 @@ static ssize_t pktgen_thread_write(struct file *file, i = len; /* Read variable name */ - - len = strn_len(&user_buffer[i], sizeof(name) - 1); + max = min(sizeof(name) - 1, count - i); + len = strn_len(&user_buffer[i], max); if (len < 0) return len; @@ -1906,7 +1908,8 @@ static ssize_t pktgen_thread_write(struct file *file, if (!strcmp(name, "add_device")) { char f[32]; memset(f, 0, 32); - len = strn_len(&user_buffer[i], sizeof(f) - 1); + max = min(sizeof(f) - 1, count - i); + len = strn_len(&user_buffer[i], max); if (len < 0) { ret = len; goto out; diff --git a/net/core/scm.c b/net/core/scm.c index 7d337f1f9297..4ed8966252b2 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -38,6 +38,7 @@ #include #include #include +#include /* @@ -87,8 +88,15 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) return -ENOMEM; *fplp = fpl; fpl->count = 0; + fpl->count_unix = 0; fpl->max = SCM_MAX_FD; fpl->user = NULL; +#if IS_ENABLED(CONFIG_UNIX) + fpl->inflight = false; + fpl->dead = false; + fpl->edges = NULL; + INIT_LIST_HEAD(&fpl->vertices); +#endif } fpp = &fpl->fp[fpl->count]; @@ -111,6 +119,9 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) fput(file); return -EINVAL; } + if (unix_get_socket(file)) + fpl->count_unix++; + *fpp++ = file; fpl->count++; } @@ -369,8 +380,14 @@ struct scm_fp_list *scm_fp_dup(struct scm_fp_list *fpl) if (new_fpl) { for (i = 0; i < fpl->count; i++) get_file(fpl->fp[i]); + new_fpl->max = new_fpl->count; new_fpl->user = get_uid(fpl->user); +#if IS_ENABLED(CONFIG_UNIX) + new_fpl->inflight = false; + new_fpl->edges = NULL; + INIT_LIST_HEAD(&new_fpl->vertices); +#endif } return new_fpl; } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 90ce87ffed46..7993ff46de23 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -829,19 +829,33 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, } } + if (cfg->fc_dst_len > 32) { + NL_SET_ERR_MSG(extack, "Invalid prefix length"); + err = -EINVAL; + goto errout; + } + + if (cfg->fc_dst_len < 32 && (ntohl(cfg->fc_dst) << cfg->fc_dst_len)) { + NL_SET_ERR_MSG(extack, "Invalid prefix for given prefix length"); + err = -EINVAL; + goto errout; + } + if (cfg->fc_nh_id) { if (cfg->fc_oif || cfg->fc_gw_family || cfg->fc_encap || cfg->fc_mp) { NL_SET_ERR_MSG(extack, "Nexthop specification and nexthop id are mutually exclusive"); - return -EINVAL; + err = -EINVAL; + goto errout; } } if (has_gw && has_via) { NL_SET_ERR_MSG(extack, "Nexthop configuration can not contain both GATEWAY and VIA"); - return -EINVAL; + err = -EINVAL; + goto errout; } if (!cfg->fc_table) diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 513f475c6a53..298a9944a3d1 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -222,9 +222,9 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct nlattr **tb, struct netlink_ext_ack *extack) { - struct net *net = sock_net(skb->sk); + struct fib4_rule *rule4 = (struct fib4_rule *)rule; + struct net *net = rule->fr_net; int err = -EINVAL; - struct fib4_rule *rule4 = (struct fib4_rule *) rule; if (!inet_validate_dscp(frh->tos)) { NL_SET_ERR_MSG(extack, diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 30caa71dabbd..a9a2acc1d1f6 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1192,22 +1192,6 @@ static int fib_insert_alias(struct trie *t, struct key_vector *tp, return 0; } -static bool fib_valid_key_len(u32 key, u8 plen, struct netlink_ext_ack *extack) -{ - if (plen > KEYLENGTH) { - NL_SET_ERR_MSG(extack, "Invalid prefix length"); - return false; - } - - if ((plen < KEYLENGTH) && (key << plen)) { - NL_SET_ERR_MSG(extack, - "Invalid prefix for given prefix length"); - return false; - } - - return true; -} - static void fib_remove_alias(struct trie *t, struct key_vector *tp, struct key_vector *l, struct fib_alias *old); @@ -1228,9 +1212,6 @@ int fib_table_insert(struct net *net, struct fib_table *tb, key = ntohl(cfg->fc_dst); - if (!fib_valid_key_len(key, plen, extack)) - return -EINVAL; - pr_debug("Insert table=%u %08x/%d\n", tb->tb_id, key, plen); fi = fib_create_info(cfg, extack); @@ -1723,9 +1704,6 @@ int fib_table_delete(struct net *net, struct fib_table *tb, key = ntohl(cfg->fc_dst); - if (!fib_valid_key_len(key, plen, extack)) - return -EINVAL; - l = fib_find_node(t, &tp, key); if (!l) return -ESRCH; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 321f509f2347..5e7cdcebd64f 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -1218,22 +1218,37 @@ int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo) { unsigned int locksz = sizeof(spinlock_t); unsigned int i, nblocks = 1; + spinlock_t *ptr = NULL; - if (locksz != 0) { - /* allocate 2 cache lines or at least one spinlock per cpu */ - nblocks = max(2U * L1_CACHE_BYTES / locksz, 1U); - nblocks = roundup_pow_of_two(nblocks * num_possible_cpus()); + if (locksz == 0) + goto set_mask; - /* no more locks than number of hash buckets */ - nblocks = min(nblocks, hashinfo->ehash_mask + 1); + /* Allocate 2 cache lines or at least one spinlock per cpu. */ + nblocks = max(2U * L1_CACHE_BYTES / locksz, 1U) * num_possible_cpus(); - hashinfo->ehash_locks = kvmalloc_array(nblocks, locksz, GFP_KERNEL); - if (!hashinfo->ehash_locks) - return -ENOMEM; + /* At least one page per NUMA node. */ + nblocks = max(nblocks, num_online_nodes() * PAGE_SIZE / locksz); - for (i = 0; i < nblocks; i++) - spin_lock_init(&hashinfo->ehash_locks[i]); + nblocks = roundup_pow_of_two(nblocks); + + /* No more locks than number of hash buckets. */ + nblocks = min(nblocks, hashinfo->ehash_mask + 1); + + if (num_online_nodes() > 1) { + /* Use vmalloc() to allow NUMA policy to spread pages + * on all available nodes if desired. + */ + ptr = vmalloc_array(nblocks, locksz); } + if (!ptr) { + ptr = kvmalloc_array(nblocks, locksz, GFP_KERNEL); + if (!ptr) + return -ENOMEM; + } + for (i = 0; i < nblocks; i++) + spin_lock_init(&ptr[i]); + hashinfo->ehash_locks = ptr; +set_mask: hashinfo->ehash_locks_mask = nblocks - 1; return 0; } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index c82107bbd981..543d029102cf 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1580,7 +1580,8 @@ struct sk_buff *__ip_make_skb(struct sock *sk, * so icmphdr does not in skb linear region and can not get icmp_type * by icmp_hdr(skb)->type. */ - if (sk->sk_type == SOCK_RAW && !inet_sk(sk)->hdrincl) + if (sk->sk_type == SOCK_RAW && + !(fl4->flowi4_flags & FLOWI_FLAG_KNOWN_NH)) icmp_type = fl4->fl4_icmp_type; else icmp_type = icmp_hdr(skb)->type; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index ee0efd0efec4..c109bc376cc5 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -608,6 +608,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), daddr, saddr, 0, 0, sk->sk_uid); + fl4.fl4_icmp_type = 0; + fl4.fl4_icmp_code = 0; + if (!hdrincl) { rfv.msg = msg; rfv.hlen = 0; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 81d293ae7987..dc918aa06118 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -405,6 +405,20 @@ static bool tcp_ecn_rcv_ecn_echo(const struct tcp_sock *tp, const struct tcphdr return false; } +static void tcp_count_delivered_ce(struct tcp_sock *tp, u32 ecn_count) +{ + tp->delivered_ce += ecn_count; +} + +/* Updates the delivered and delivered_ce counts */ +static void tcp_count_delivered(struct tcp_sock *tp, u32 delivered, + bool ece_ack) +{ + tp->delivered += delivered; + if (ece_ack) + tcp_count_delivered_ce(tp, delivered); +} + /* Buffer size and advertised window tuning. * * 1. Tuning sk->sk_sndbuf, when connection enters established state. @@ -1122,15 +1136,6 @@ void tcp_mark_skb_lost(struct sock *sk, struct sk_buff *skb) } } -/* Updates the delivered and delivered_ce counts */ -static void tcp_count_delivered(struct tcp_sock *tp, u32 delivered, - bool ece_ack) -{ - tp->delivered += delivered; - if (ece_ack) - tp->delivered_ce += delivered; -} - /* This procedure tags the retransmission queue when SACKs arrive. * * We have three tag bits: SACKED(S), RETRANS(R) and LOST(L). @@ -3786,12 +3791,23 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag) } } -static inline void tcp_in_ack_event(struct sock *sk, u32 flags) +static void tcp_in_ack_event(struct sock *sk, int flag) { const struct inet_connection_sock *icsk = inet_csk(sk); - if (icsk->icsk_ca_ops->in_ack_event) - icsk->icsk_ca_ops->in_ack_event(sk, flags); + if (icsk->icsk_ca_ops->in_ack_event) { + u32 ack_ev_flags = 0; + + if (flag & FLAG_WIN_UPDATE) + ack_ev_flags |= CA_ACK_WIN_UPDATE; + if (flag & FLAG_SLOWPATH) { + ack_ev_flags |= CA_ACK_SLOWPATH; + if (flag & FLAG_ECE) + ack_ev_flags |= CA_ACK_ECE; + } + + icsk->icsk_ca_ops->in_ack_event(sk, ack_ev_flags); + } } /* Congestion control has updated the cwnd already. So if we're in @@ -3908,12 +3924,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) tcp_snd_una_update(tp, ack); flag |= FLAG_WIN_UPDATE; - tcp_in_ack_event(sk, CA_ACK_WIN_UPDATE); - NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHPACKS); } else { - u32 ack_ev_flags = CA_ACK_SLOWPATH; - if (ack_seq != TCP_SKB_CB(skb)->end_seq) flag |= FLAG_DATA; else @@ -3925,19 +3937,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una, &sack_state); - if (tcp_ecn_rcv_ecn_echo(tp, tcp_hdr(skb))) { + if (tcp_ecn_rcv_ecn_echo(tp, tcp_hdr(skb))) flag |= FLAG_ECE; - ack_ev_flags |= CA_ACK_ECE; - } if (sack_state.sack_delivered) tcp_count_delivered(tp, sack_state.sack_delivered, flag & FLAG_ECE); - - if (flag & FLAG_WIN_UPDATE) - ack_ev_flags |= CA_ACK_WIN_UPDATE; - - tcp_in_ack_event(sk, ack_ev_flags); } /* This is a deviation from RFC3168 since it states that: @@ -3964,6 +3969,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) tcp_rack_update_reo_wnd(sk, &rs); + tcp_in_ack_event(sk, flag); + if (tp->tlp_high_seq) tcp_process_tlp_ack(sk, ack, flag); @@ -3995,6 +4002,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) return 1; no_queue: + tcp_in_ack_event(sk, flag); /* If data was DSACKed, see if we can undo a cwnd reduction. */ if (flag & FLAG_DSACKING_ACK) { tcp_fastretrans_alert(sk, prior_snd_una, num_dupack, &flag, diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index f6a6a50cce08..2036fb1159db 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3184,16 +3184,13 @@ static void add_v4_addrs(struct inet6_dev *idev) struct in6_addr addr; struct net_device *dev; struct net *net = dev_net(idev->dev); - int scope, plen, offset = 0; + int scope, plen; u32 pflags = 0; ASSERT_RTNL(); memset(&addr, 0, sizeof(struct in6_addr)); - /* in case of IP6GRE the dev_addr is an IPv6 and therefore we use only the last 4 bytes */ - if (idev->dev->addr_len == sizeof(struct in6_addr)) - offset = sizeof(struct in6_addr) - 4; - memcpy(&addr.s6_addr32[3], idev->dev->dev_addr + offset, 4); + memcpy(&addr.s6_addr32[3], idev->dev->dev_addr, 4); if (!(idev->dev->flags & IFF_POINTOPOINT) && idev->dev->type == ARPHRD_SIT) { scope = IPV6_ADDR_COMPATv4; @@ -3503,7 +3500,13 @@ static void addrconf_gre_config(struct net_device *dev) return; } - if (dev->type == ARPHRD_ETHER) { + /* Generate the IPv6 link-local address using addrconf_addr_gen(), + * unless we have an IPv4 GRE device not bound to an IP address and + * which is in EUI64 mode (as __ipv6_isatap_ifid() would fail in this + * case). Such devices fall back to add_v4_addrs() instead. + */ + if (!(dev->type == ARPHRD_IPGRE && *(__be32 *)dev->dev_addr == 0 && + idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64)) { addrconf_addr_gen(idev, true); return; } diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 6eeab21512ba..e0f0c5f8cccd 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -350,9 +350,9 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct nlattr **tb, struct netlink_ext_ack *extack) { + struct fib6_rule *rule6 = (struct fib6_rule *)rule; + struct net *net = rule->fr_net; int err = -EINVAL; - struct net *net = sock_net(skb->sk); - struct fib6_rule *rule6 = (struct fib6_rule *) rule; if (!inet_validate_dscp(frh->tos)) { NL_SET_ERR_MSG(extack, diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index d7f7a714bd23..f7a225da8525 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1985,7 +1985,8 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); u8 icmp6_type; - if (sk->sk_socket->type == SOCK_RAW && !inet_sk(sk)->hdrincl) + if (sk->sk_socket->type == SOCK_RAW && + !(fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH)) icmp6_type = fl6->fl6_icmp_type; else icmp6_type = icmp6_hdr(skb)->icmp6_type; diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 8e3be0009f60..8f5c9d743f6a 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -888,15 +888,15 @@ static int llc_ui_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (sk->sk_type != SOCK_STREAM) goto copy_uaddr; + /* Partial read */ + if (used + offset < skb_len) + continue; + if (!(flags & MSG_PEEK)) { skb_unlink(skb, &sk->sk_receive_queue); kfree_skb(skb); *seq = 0; } - - /* Partial read */ - if (used + offset < skb_len) - continue; } while (len > 0); out: diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 0994bbfa819e..92f96493f599 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2896,7 +2896,8 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, if (tx) ieee80211_flush_queues(local, sdata, false); - drv_mgd_complete_tx(sdata->local, sdata, &info); + if (tx || frame_buf) + drv_mgd_complete_tx(sdata->local, sdata, &info); /* clear AP addr only after building the needed mgmt frames */ eth_zero_addr(sdata->deflink.u.mgd.bssid); @@ -7311,7 +7312,6 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, ieee80211_report_disconnect(sdata, frame_buf, sizeof(frame_buf), true, req->reason_code, false); - drv_mgd_complete_tx(sdata->local, sdata, &info); return 0; } diff --git a/net/mctp/route.c b/net/mctp/route.c index e72cdd4ce588..62952ad5cb63 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -274,8 +274,10 @@ static void mctp_flow_prepare_output(struct sk_buff *skb, struct mctp_dev *dev) key = flow->key; - if (WARN_ON(key->dev && key->dev != dev)) + if (key->dev) { + WARN_ON(key->dev != dev); return; + } mctp_dev_set_key(dev, key); } diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index ef04e556aadb..0bd6bf46f05f 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -63,7 +63,7 @@ struct hbucket { #define ahash_sizeof_regions(htable_bits) \ (ahash_numof_locks(htable_bits) * sizeof(struct ip_set_region)) #define ahash_region(n, htable_bits) \ - ((n) % ahash_numof_locks(htable_bits)) + ((n) / jhash_size(HTABLE_REGION_BITS)) #define ahash_bucket_start(h, htable_bits) \ ((htable_bits) < HTABLE_REGION_BITS ? 0 \ : (h) * jhash_size(HTABLE_REGION_BITS)) diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index d40a4ca2b27f..e1437c72ca6e 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -119,13 +119,12 @@ __mtu_check_toobig_v6(const struct sk_buff *skb, u32 mtu) return false; } -/* Get route to daddr, update *saddr, optionally bind route to saddr */ +/* Get route to daddr, optionally bind route to saddr */ static struct rtable *do_output_route4(struct net *net, __be32 daddr, - int rt_mode, __be32 *saddr) + int rt_mode, __be32 *ret_saddr) { struct flowi4 fl4; struct rtable *rt; - bool loop = false; memset(&fl4, 0, sizeof(fl4)); fl4.daddr = daddr; @@ -135,23 +134,17 @@ static struct rtable *do_output_route4(struct net *net, __be32 daddr, retry: rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) { - /* Invalid saddr ? */ - if (PTR_ERR(rt) == -EINVAL && *saddr && - rt_mode & IP_VS_RT_MODE_CONNECT && !loop) { - *saddr = 0; - flowi4_update_output(&fl4, 0, 0, daddr, 0); - goto retry; - } IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n", &daddr); return NULL; - } else if (!*saddr && rt_mode & IP_VS_RT_MODE_CONNECT && fl4.saddr) { + } + if (rt_mode & IP_VS_RT_MODE_CONNECT && fl4.saddr) { ip_rt_put(rt); - *saddr = fl4.saddr; - flowi4_update_output(&fl4, 0, 0, daddr, fl4.saddr); - loop = true; + flowi4_update_output(&fl4, 0, daddr, fl4.saddr); + rt_mode = 0; goto retry; } - *saddr = fl4.saddr; + if (ret_saddr) + *ret_saddr = fl4.saddr; return rt; } @@ -344,19 +337,15 @@ __ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, if (ret_saddr) *ret_saddr = dest_dst->dst_saddr.ip; } else { - __be32 saddr = htonl(INADDR_ANY); - noref = 0; /* For such unconfigured boxes avoid many route lookups * for performance reasons because we do not remember saddr */ rt_mode &= ~IP_VS_RT_MODE_CONNECT; - rt = do_output_route4(net, daddr, rt_mode, &saddr); + rt = do_output_route4(net, daddr, rt_mode, ret_saddr); if (!rt) goto err_unreach; - if (ret_saddr) - *ret_saddr = saddr; } local = (rt->rt_flags & RTCF_LOCAL) ? 1 : 0; diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 52245dbfae31..c333132e2079 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -631,7 +631,9 @@ static struct ctl_table nf_ct_sysctl_table[] = { .data = &nf_conntrack_max, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_INT_MAX, }, [NF_SYSCTL_CT_COUNT] = { .procname = "nf_conntrack_count", @@ -667,7 +669,9 @@ static struct ctl_table nf_ct_sysctl_table[] = { .data = &nf_ct_expect_max, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ONE, + .extra2 = SYSCTL_INT_MAX, }, [NF_SYSCTL_CT_ACCT] = { .procname = "nf_conntrack_acct", @@ -970,7 +974,9 @@ static struct ctl_table nf_ct_netfilter_table[] = { .data = &nf_conntrack_max, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_INT_MAX, }, { } }; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 656c4fb76773..0bf347a0a1dd 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2034,9 +2034,9 @@ static void nf_tables_chain_free_chain_rules(struct nft_chain *chain) kvfree(chain->blob_next); } -void nf_tables_chain_destroy(struct nft_ctx *ctx) +void nf_tables_chain_destroy(struct nft_chain *chain) { - struct nft_chain *chain = ctx->chain; + const struct nft_table *table = chain->table; struct nft_hook *hook, *next; if (WARN_ON(chain->use > 0)) @@ -2048,7 +2048,7 @@ void nf_tables_chain_destroy(struct nft_ctx *ctx) if (nft_is_base_chain(chain)) { struct nft_base_chain *basechain = nft_base_chain(chain); - if (nft_base_chain_netdev(ctx->family, basechain->ops.hooknum)) { + if (nft_base_chain_netdev(table->family, basechain->ops.hooknum)) { list_for_each_entry_safe(hook, next, &basechain->hook_list, list) { list_del_rcu(&hook->list); @@ -2515,7 +2515,7 @@ err_chain_add: err_trans: nft_use_dec_restore(&table->use); err_destroy_chain: - nf_tables_chain_destroy(ctx); + nf_tables_chain_destroy(chain); return err; } @@ -3510,8 +3510,11 @@ void nf_tables_rule_destroy(const struct nft_ctx *ctx, struct nft_rule *rule) kfree(rule); } +/* can only be used if rule is no longer visible to dumps */ static void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *rule) { + lockdep_commit_lock_is_held(ctx->net); + nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_RELEASE); nf_tables_rule_destroy(ctx, rule); } @@ -5247,6 +5250,8 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding, enum nft_trans_phase phase) { + lockdep_commit_lock_is_held(ctx->net); + switch (phase) { case NFT_TRANS_PREPARE_ERROR: nft_set_trans_unbind(ctx, set); @@ -8994,7 +8999,7 @@ static void nft_commit_release(struct nft_trans *trans) kfree(nft_trans_chain_name(trans)); break; case NFT_MSG_DELCHAIN: - nf_tables_chain_destroy(&trans->ctx); + nf_tables_chain_destroy(nft_trans_chain(trans)); break; case NFT_MSG_DELRULE: nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans)); @@ -9955,7 +9960,7 @@ static void nf_tables_abort_release(struct nft_trans *trans) nf_tables_table_destroy(&trans->ctx); break; case NFT_MSG_NEWCHAIN: - nf_tables_chain_destroy(&trans->ctx); + nf_tables_chain_destroy(nft_trans_chain(trans)); break; case NFT_MSG_NEWRULE: nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans)); @@ -10662,23 +10667,43 @@ int nft_data_dump(struct sk_buff *skb, int attr, const struct nft_data *data, } EXPORT_SYMBOL_GPL(nft_data_dump); -int __nft_release_basechain(struct nft_ctx *ctx) +static void __nft_release_basechain_now(struct nft_ctx *ctx) { struct nft_rule *rule, *nr; - if (WARN_ON(!nft_is_base_chain(ctx->chain))) + list_for_each_entry_safe(rule, nr, &ctx->chain->rules, list) { + list_del(&rule->list); + nf_tables_rule_release(ctx, rule); + } + nf_tables_chain_destroy(ctx->chain); +} + +int __nft_release_basechain(struct nft_ctx *ctx) +{ + struct nft_rule *rule; + + if (WARN_ON_ONCE(!nft_is_base_chain(ctx->chain))) return 0; nf_tables_unregister_hook(ctx->net, ctx->chain->table, ctx->chain); - list_for_each_entry_safe(rule, nr, &ctx->chain->rules, list) { - list_del(&rule->list); + list_for_each_entry(rule, &ctx->chain->rules, list) nft_use_dec(&ctx->chain->use); - nf_tables_rule_release(ctx, rule); - } + nft_chain_del(ctx->chain); nft_use_dec(&ctx->table->use); - nf_tables_chain_destroy(ctx); + if (!maybe_get_net(ctx->net)) { + __nft_release_basechain_now(ctx); + return 0; + } + + /* wait for ruleset dumps to complete. Owning chain is no longer in + * lists, so new dumps can't find any of these rules anymore. + */ + synchronize_rcu(); + + __nft_release_basechain_now(ctx); + put_net(ctx->net); return 0; } EXPORT_SYMBOL_GPL(__nft_release_basechain); @@ -10753,10 +10778,9 @@ static void __nft_release_table(struct net *net, struct nft_table *table) nft_obj_destroy(&ctx, obj); } list_for_each_entry_safe(chain, nc, &table->chains, list) { - ctx.chain = chain; nft_chain_del(chain); nft_use_dec(&table->use); - nf_tables_chain_destroy(&ctx); + nf_tables_chain_destroy(chain); } nf_tables_table_destroy(&ctx); } diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 55fcf0280c5c..731511d58b7c 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -221,7 +221,7 @@ static void nft_immediate_destroy(const struct nft_ctx *ctx, list_del(&rule->list); nf_tables_rule_destroy(&chain_ctx, rule); } - nf_tables_chain_destroy(&chain_ctx); + nf_tables_chain_destroy(chain); break; default: break; diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index c517b24b3093..a87c25e06baf 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -954,8 +954,7 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb, upcall.cmd = OVS_PACKET_CMD_ACTION; upcall.mru = OVS_CB(skb)->mru; - for (a = nla_data(attr), rem = nla_len(attr); rem > 0; - a = nla_next(a, &rem)) { + nla_for_each_nested(a, attr, rem) { switch (nla_type(a)) { case OVS_USERSPACE_ATTR_USERDATA: upcall.userdata = a; diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c index 5f2e06815745..63c02040b426 100644 --- a/net/sched/sch_codel.c +++ b/net/sched/sch_codel.c @@ -168,7 +168,7 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt, qlen = sch->q.qlen; while (sch->q.qlen > sch->limit) { - struct sk_buff *skb = __qdisc_dequeue_head(&sch->q); + struct sk_buff *skb = qdisc_dequeue_internal(sch, true); dropped += qdisc_pkt_len(skb); qdisc_qstats_backlog_dec(sch, skb); diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index f59a2cb2c803..91f5ef6be0f2 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -901,7 +901,7 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt, sch_tree_lock(sch); } while (sch->q.qlen > sch->limit) { - struct sk_buff *skb = fq_dequeue(sch); + struct sk_buff *skb = qdisc_dequeue_internal(sch, false); if (!skb) break; diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 9330923a624c..47b5a056165c 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -431,7 +431,7 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, while (sch->q.qlen > sch->limit || q->memory_usage > q->memory_limit) { - struct sk_buff *skb = fq_codel_dequeue(sch); + struct sk_buff *skb = qdisc_dequeue_internal(sch, false); q->cstats.drop_len += qdisc_pkt_len(skb); rtnl_kfree_skbs(skb, skb); diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index 68e6acd0f130..607c580d75e4 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -357,7 +357,7 @@ static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt, /* Drop excess packets if new limit is lower */ while (sch->q.qlen > sch->limit) { - struct sk_buff *skb = fq_pie_qdisc_dequeue(sch); + struct sk_buff *skb = qdisc_dequeue_internal(sch, false); len_dropped += qdisc_pkt_len(skb); num_dropped += 1; diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index fc1370c29373..61b91de8065f 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -176,6 +176,11 @@ struct hfsc_sched { #define HT_INFINITY 0xffffffffffffffffULL /* infinite time value */ +static bool cl_in_el_or_vttree(struct hfsc_class *cl) +{ + return ((cl->cl_flags & HFSC_FSC) && cl->cl_nactive) || + ((cl->cl_flags & HFSC_RSC) && !RB_EMPTY_NODE(&cl->el_node)); +} /* * eligible tree holds backlogged classes being sorted by their eligible times. @@ -1041,6 +1046,8 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (cl == NULL) return -ENOBUFS; + RB_CLEAR_NODE(&cl->el_node); + err = tcf_block_get(&cl->block, &cl->filter_list, sch, extack); if (err) { kfree(cl); @@ -1568,7 +1575,10 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) return err; } - if (first && !cl->cl_nactive) { + sch->qstats.backlog += len; + sch->q.qlen++; + + if (first && !cl_in_el_or_vttree(cl)) { if (cl->cl_flags & HFSC_RSC) init_ed(cl, len); if (cl->cl_flags & HFSC_FSC) @@ -1583,9 +1593,6 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) } - sch->qstats.backlog += len; - sch->q.qlen++; - return NET_XMIT_SUCCESS; } diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index d26cd436cbe3..83fc44f20e31 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -560,7 +560,7 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt, qlen = sch->q.qlen; prev_backlog = sch->qstats.backlog; while (sch->q.qlen > sch->limit) { - struct sk_buff *skb = hhf_dequeue(sch); + struct sk_buff *skb = qdisc_dequeue_internal(sch, false); rtnl_kfree_skbs(skb, skb); } diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 582d11a41bba..ca981b0c0708 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -345,7 +345,8 @@ static void htb_add_to_wait_tree(struct htb_sched *q, */ static inline void htb_next_rb_node(struct rb_node **n) { - *n = rb_next(*n); + if (*n) + *n = rb_next(*n); } /** @@ -606,8 +607,8 @@ static inline void htb_activate(struct htb_sched *q, struct htb_class *cl) */ static inline void htb_deactivate(struct htb_sched *q, struct htb_class *cl) { - WARN_ON(!cl->prio_activity); - + if (!cl->prio_activity) + return; htb_deactivate_prios(q, cl); cl->prio_activity = 0; } @@ -1491,8 +1492,6 @@ static void htb_qlen_notify(struct Qdisc *sch, unsigned long arg) { struct htb_class *cl = (struct htb_class *)arg; - if (!cl->prio_activity) - return; htb_deactivate(qdisc_priv(sch), cl); } @@ -1747,8 +1746,7 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg, if (cl->parent) cl->parent->children--; - if (cl->prio_activity) - htb_deactivate(q, cl); + htb_deactivate(q, cl); if (cl->cmode != HTB_CAN_SEND) htb_safe_rb_erase(&cl->pq_node, @@ -1964,8 +1962,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, /* turn parent into inner node */ qdisc_purge_queue(parent->leaf.q); parent_qdisc = parent->leaf.q; - if (parent->prio_activity) - htb_deactivate(q, parent); + htb_deactivate(q, parent); /* remove from evt list because of level change */ if (parent->cmode != HTB_CAN_SEND) { diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index b60b31ef71cc..e1bb151a9719 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -190,7 +190,7 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt, /* Drop excess packets if new limit is lower */ qlen = sch->q.qlen; while (sch->q.qlen > sch->limit) { - struct sk_buff *skb = __qdisc_dequeue_head(&sch->q); + struct sk_buff *skb = qdisc_dequeue_internal(sch, true); dropped += qdisc_pkt_len(skb); qdisc_qstats_backlog_dec(sch, skb); diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index bcd3384ab07a..036dc574af4f 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -497,9 +497,7 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr, continue; fl4->fl4_sport = laddr->a.v4.sin_port; - flowi4_update_output(fl4, - asoc->base.sk->sk_bound_dev_if, - RT_CONN_FLAGS_TOS(asoc->base.sk, tos), + flowi4_update_output(fl4, asoc->base.sk->sk_bound_dev_if, daddr->v4.sin_addr.s_addr, laddr->a.v4.sin_addr.s_addr); diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 916dc2e81e42..f3d09998c24d 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -518,6 +518,8 @@ static int proc_sctp_do_auth(struct ctl_table *ctl, int write, return ret; } +static DEFINE_MUTEX(sctp_sysctl_mutex); + static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -542,6 +544,7 @@ static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write, if (new_value > max || new_value < min) return -EINVAL; + mutex_lock(&sctp_sysctl_mutex); net->sctp.udp_port = new_value; sctp_udp_sock_stop(net); if (new_value) { @@ -554,6 +557,7 @@ static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write, lock_sock(sk); sctp_sk(sk)->udp_port = htons(net->sctp.udp_port); release_sock(sk); + mutex_unlock(&sctp_sysctl_mutex); } return ret; diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 399314cfab90..af12e0215274 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -1080,14 +1080,16 @@ static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev, struct smc_init_info *ini) { u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; + struct net_device *base_ndev; struct net *net; - ndev = pnet_find_base_ndev(ndev); + base_ndev = pnet_find_base_ndev(ndev); net = dev_net(ndev); - if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port, + if (smc_pnetid_by_dev_port(base_ndev->dev.parent, base_ndev->dev_port, ndev_pnetid) && + smc_pnet_find_ndev_pnetid_by_table(base_ndev, ndev_pnetid) && smc_pnet_find_ndev_pnetid_by_table(ndev, ndev_pnetid)) { - smc_pnet_find_rdma_dev(ndev, ini); + smc_pnet_find_rdma_dev(base_ndev, ini); return; /* pnetid could not be determined */ } _smc_pnet_find_roce_by_pnetid(ndev_pnetid, ini, NULL, net); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index b6529a9d37d3..a390a4e5592f 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -275,9 +275,6 @@ static struct rpc_xprt *rpc_clnt_set_transport(struct rpc_clnt *clnt, old = rcu_dereference_protected(clnt->cl_xprt, lockdep_is_held(&clnt->cl_lock)); - if (!xprt_bound(xprt)) - clnt->cl_autobind = 1; - clnt->cl_timeout = timeout; rcu_assign_pointer(clnt->cl_xprt, xprt); spin_unlock(&clnt->cl_lock); diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 82afb56695f8..1ec20163a0b7 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -797,9 +797,10 @@ static void rpcb_getport_done(struct rpc_task *child, void *data) } trace_rpcb_setport(child, map->r_status, map->r_port); - xprt->ops->set_port(xprt, map->r_port); - if (map->r_port) + if (map->r_port) { + xprt->ops->set_port(xprt, map->r_port); xprt_set_bound(xprt); + } } /* diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 9b45fbdc90ca..73bc39281ef5 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -276,6 +276,8 @@ EXPORT_SYMBOL_GPL(rpc_destroy_wait_queue); static int rpc_wait_bit_killable(struct wait_bit_key *key, int mode) { + if (unlikely(current->flags & PF_EXITING)) + return -EINTR; schedule(); if (signal_pending_state(mode, current)) return -ERESTARTSYS; diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index 25c18f8783ce..a9c02fac039b 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -817,12 +817,16 @@ static int tipc_aead_encrypt(struct tipc_aead *aead, struct sk_buff *skb, goto exit; } + /* Get net to avoid freed tipc_crypto when delete namespace */ + get_net(aead->crypto->net); + /* Now, do encrypt */ rc = crypto_aead_encrypt(req); if (rc == -EINPROGRESS || rc == -EBUSY) return rc; tipc_bearer_put(b); + put_net(aead->crypto->net); exit: kfree(ctx); @@ -860,6 +864,7 @@ static void tipc_aead_encrypt_done(struct crypto_async_request *base, int err) kfree(tx_ctx); tipc_bearer_put(b); tipc_aead_put(aead); + put_net(net); } /** diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index f37f4a0fcd3c..44d7f1aef9f1 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -396,7 +396,6 @@ static int tls_strp_read_copy(struct tls_strparser *strp, bool qshort) return 0; shinfo = skb_shinfo(strp->anchor); - shinfo->frag_list = NULL; /* If we don't know the length go max plus page for cipher overhead */ need_spc = strp->stm.full_len ?: TLS_MAX_PAYLOAD_SIZE + PAGE_SIZE; @@ -412,6 +411,8 @@ static int tls_strp_read_copy(struct tls_strparser *strp, bool qshort) page, 0, 0); } + shinfo->frag_list = NULL; + strp->copy_mode = 1; strp->stm.offset = 0; diff --git a/net/unix/Kconfig b/net/unix/Kconfig index b7f811216820..8b5d04210d7c 100644 --- a/net/unix/Kconfig +++ b/net/unix/Kconfig @@ -4,7 +4,7 @@ # config UNIX - tristate "Unix domain sockets" + bool "Unix domain sockets" help If you say Y here, you will include support for Unix domain sockets; sockets are the standard Unix mechanism for establishing and @@ -14,17 +14,8 @@ config UNIX an embedded system or something similar, you therefore definitely want to say Y here. - To compile this driver as a module, choose M here: the module will be - called unix. Note that several important services won't work - correctly if you say M here and then neglect to load the module. - Say Y unless you know what you are doing. -config UNIX_SCM - bool - depends on UNIX - default y - config AF_UNIX_OOB bool depends on UNIX diff --git a/net/unix/Makefile b/net/unix/Makefile index 20491825b4d0..4ddd125c4642 100644 --- a/net/unix/Makefile +++ b/net/unix/Makefile @@ -11,5 +11,3 @@ unix-$(CONFIG_BPF_SYSCALL) += unix_bpf.o obj-$(CONFIG_UNIX_DIAG) += unix_diag.o unix_diag-y := diag.o - -obj-$(CONFIG_UNIX_SCM) += scm.o diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 874457cdec18..4cbfbd48a83d 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -116,8 +116,6 @@ #include #include -#include "scm.h" - static atomic_long_t unix_nr_socks; static struct hlist_head bsd_socket_buckets[UNIX_HASH_SIZE / 2]; static spinlock_t bsd_socket_locks[UNIX_HASH_SIZE / 2]; @@ -958,11 +956,11 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern, sk->sk_max_ack_backlog = READ_ONCE(net->unx.sysctl_max_dgram_qlen); sk->sk_destruct = unix_sock_destructor; u = unix_sk(sk); - u->inflight = 0; + u->listener = NULL; + u->vertex = NULL; u->path.dentry = NULL; u->path.mnt = NULL; spin_lock_init(&u->lock); - INIT_LIST_HEAD(&u->link); mutex_init(&u->iolock); /* single task reading lock */ mutex_init(&u->bindlock); /* single task binding lock */ init_waitqueue_head(&u->peer_wait); @@ -1561,6 +1559,7 @@ restart: newsk->sk_type = sk->sk_type; init_peercred(newsk); newu = unix_sk(newsk); + newu->listener = other; RCU_INIT_POINTER(newsk->sk_wq, &newu->peer_wq); otheru = unix_sk(other); @@ -1654,8 +1653,8 @@ static int unix_accept(struct socket *sock, struct socket *newsock, int flags, bool kern) { struct sock *sk = sock->sk; - struct sock *tsk; struct sk_buff *skb; + struct sock *tsk; int err; err = -EOPNOTSUPP; @@ -1685,6 +1684,7 @@ static int unix_accept(struct socket *sock, struct socket *newsock, int flags, /* attach accepted sock to socket */ unix_state_lock(tsk); + unix_update_edges(unix_sk(tsk)); newsock->state = SS_CONNECTED; unix_sock_inherit_flags(sock, newsock); sock_graft(tsk, newsock); @@ -1728,51 +1728,65 @@ out: return err; } +/* The "user->unix_inflight" variable is protected by the garbage + * collection lock, and we just read it locklessly here. If you go + * over the limit, there might be a tiny race in actually noticing + * it across threads. Tough. + */ +static inline bool too_many_unix_fds(struct task_struct *p) +{ + struct user_struct *user = current_user(); + + if (unlikely(READ_ONCE(user->unix_inflight) > task_rlimit(p, RLIMIT_NOFILE))) + return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); + return false; +} + +static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) +{ + if (too_many_unix_fds(current)) + return -ETOOMANYREFS; + + /* Need to duplicate file references for the sake of garbage + * collection. Otherwise a socket in the fps might become a + * candidate for GC while the skb is not yet queued. + */ + UNIXCB(skb).fp = scm_fp_dup(scm->fp); + if (!UNIXCB(skb).fp) + return -ENOMEM; + + if (unix_prepare_fpl(UNIXCB(skb).fp)) + return -ENOMEM; + + return 0; +} + +static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb) +{ + scm->fp = UNIXCB(skb).fp; + UNIXCB(skb).fp = NULL; + + unix_destroy_fpl(scm->fp); +} + static void unix_peek_fds(struct scm_cookie *scm, struct sk_buff *skb) { scm->fp = scm_fp_dup(UNIXCB(skb).fp); +} - /* - * Garbage collection of unix sockets starts by selecting a set of - * candidate sockets which have reference only from being in flight - * (total_refs == inflight_refs). This condition is checked once during - * the candidate collection phase, and candidates are marked as such, so - * that non-candidates can later be ignored. While inflight_refs is - * protected by unix_gc_lock, total_refs (file count) is not, hence this - * is an instantaneous decision. - * - * Once a candidate, however, the socket must not be reinstalled into a - * file descriptor while the garbage collection is in progress. - * - * If the above conditions are met, then the directed graph of - * candidates (*) does not change while unix_gc_lock is held. - * - * Any operations that changes the file count through file descriptors - * (dup, close, sendmsg) does not change the graph since candidates are - * not installed in fds. - * - * Dequeing a candidate via recvmsg would install it into an fd, but - * that takes unix_gc_lock to decrement the inflight count, so it's - * serialized with garbage collection. - * - * MSG_PEEK is special in that it does not change the inflight count, - * yet does install the socket into an fd. The following lock/unlock - * pair is to ensure serialization with garbage collection. It must be - * done between incrementing the file count and installing the file into - * an fd. - * - * If garbage collection starts after the barrier provided by the - * lock/unlock, then it will see the elevated refcount and not mark this - * as a candidate. If a garbage collection is already in progress - * before the file count was incremented, then the lock/unlock pair will - * ensure that garbage collection is finished before progressing to - * installing the fd. - * - * (*) A -> B where B is on the queue of A or B is on the queue of C - * which is on the queue of listening socket A. - */ - spin_lock(&unix_gc_lock); - spin_unlock(&unix_gc_lock); +static void unix_destruct_scm(struct sk_buff *skb) +{ + struct scm_cookie scm; + + memset(&scm, 0, sizeof(scm)); + scm.pid = UNIXCB(skb).pid; + if (UNIXCB(skb).fp) + unix_detach_fds(&scm, skb); + + /* Alas, it calls VFS */ + /* So fscking what? fput() had been SMP-safe since the last Summer */ + scm_destroy(&scm); + sock_wfree(skb); } static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds) @@ -1847,8 +1861,10 @@ static void scm_stat_add(struct sock *sk, struct sk_buff *skb) struct scm_fp_list *fp = UNIXCB(skb).fp; struct unix_sock *u = unix_sk(sk); - if (unlikely(fp && fp->count)) + if (unlikely(fp && fp->count)) { atomic_add(fp->count, &u->scm_stat.nr_fds); + unix_add_edges(fp, u); + } } static void scm_stat_del(struct sock *sk, struct sk_buff *skb) @@ -1856,8 +1872,10 @@ static void scm_stat_del(struct sock *sk, struct sk_buff *skb) struct scm_fp_list *fp = UNIXCB(skb).fp; struct unix_sock *u = unix_sk(sk); - if (unlikely(fp && fp->count)) + if (unlikely(fp && fp->count)) { atomic_sub(fp->count, &u->scm_stat.nr_fds); + unix_del_edges(fp); + } } /* @@ -1877,11 +1895,12 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, long timeo; int err; - wait_for_unix_gc(); err = scm_send(sock, msg, &scm, false); if (err < 0) return err; + wait_for_unix_gc(scm.fp); + err = -EOPNOTSUPP; if (msg->msg_flags&MSG_OOB) goto out; @@ -2147,11 +2166,12 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, bool fds_sent = false; int data_len; - wait_for_unix_gc(); err = scm_send(sock, msg, &scm, false); if (err < 0) return err; + wait_for_unix_gc(scm.fp); + err = -EOPNOTSUPP; if (msg->msg_flags & MSG_OOB) { #if IS_ENABLED(CONFIG_AF_UNIX_OOB) diff --git a/net/unix/garbage.c b/net/unix/garbage.c index d2fc795394a5..23efb78fe9ef 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -81,278 +81,551 @@ #include #include -#include "scm.h" - -/* Internal data structures and random procedures: */ - -static LIST_HEAD(gc_candidates); -static DECLARE_WAIT_QUEUE_HEAD(unix_gc_wait); - -static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *), - struct sk_buff_head *hitlist) +struct unix_sock *unix_get_socket(struct file *filp) { - struct sk_buff *skb; - struct sk_buff *next; + struct inode *inode = file_inode(filp); - spin_lock(&x->sk_receive_queue.lock); - skb_queue_walk_safe(&x->sk_receive_queue, skb, next) { - /* Do we have file descriptors ? */ - if (UNIXCB(skb).fp) { - bool hit = false; - /* Process the descriptors of this socket */ - int nfd = UNIXCB(skb).fp->count; - struct file **fp = UNIXCB(skb).fp->fp; + /* Socket ? */ + if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) { + struct socket *sock = SOCKET_I(inode); + const struct proto_ops *ops; + struct sock *sk = sock->sk; - while (nfd--) { - /* Get the socket the fd matches if it indeed does so */ - struct sock *sk = unix_get_socket(*fp++); + ops = READ_ONCE(sock->ops); - if (sk) { - struct unix_sock *u = unix_sk(sk); - - /* Ignore non-candidates, they could - * have been added to the queues after - * starting the garbage collection - */ - if (test_bit(UNIX_GC_CANDIDATE, &u->gc_flags)) { - hit = true; - - func(u); - } - } - } - if (hit && hitlist != NULL) { - __skb_unlink(skb, &x->sk_receive_queue); - __skb_queue_tail(hitlist, skb); - } - } + /* PF_UNIX ? */ + if (sk && ops && ops->family == PF_UNIX) + return unix_sk(sk); } - spin_unlock(&x->sk_receive_queue.lock); + + return NULL; } -static void scan_children(struct sock *x, void (*func)(struct unix_sock *), - struct sk_buff_head *hitlist) +static struct unix_vertex *unix_edge_successor(struct unix_edge *edge) { - if (x->sk_state != TCP_LISTEN) { - scan_inflight(x, func, hitlist); - } else { - struct sk_buff *skb; - struct sk_buff *next; - struct unix_sock *u; - LIST_HEAD(embryos); - - /* For a listening socket collect the queued embryos - * and perform a scan on them as well. - */ - spin_lock(&x->sk_receive_queue.lock); - skb_queue_walk_safe(&x->sk_receive_queue, skb, next) { - u = unix_sk(skb->sk); - - /* An embryo cannot be in-flight, so it's safe - * to use the list link. - */ - BUG_ON(!list_empty(&u->link)); - list_add_tail(&u->link, &embryos); - } - spin_unlock(&x->sk_receive_queue.lock); - - while (!list_empty(&embryos)) { - u = list_entry(embryos.next, struct unix_sock, link); - scan_inflight(&u->sk, func, hitlist); - list_del_init(&u->link); - } - } -} - -static void dec_inflight(struct unix_sock *usk) -{ - usk->inflight--; -} - -static void inc_inflight(struct unix_sock *usk) -{ - usk->inflight++; -} - -static void inc_inflight_move_tail(struct unix_sock *u) -{ - u->inflight++; - - /* If this still might be part of a cycle, move it to the end - * of the list, so that it's checked even if it was already - * passed over + /* If an embryo socket has a fd, + * the listener indirectly holds the fd's refcnt. */ - if (test_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags)) - list_move_tail(&u->link, &gc_candidates); + if (edge->successor->listener) + return unix_sk(edge->successor->listener)->vertex; + + return edge->successor->vertex; +} + +static bool unix_graph_maybe_cyclic; +static bool unix_graph_grouped; + +static void unix_update_graph(struct unix_vertex *vertex) +{ + /* If the receiver socket is not inflight, no cyclic + * reference could be formed. + */ + if (!vertex) + return; + + unix_graph_maybe_cyclic = true; + unix_graph_grouped = false; +} + +static LIST_HEAD(unix_unvisited_vertices); + +enum unix_vertex_index { + UNIX_VERTEX_INDEX_MARK1, + UNIX_VERTEX_INDEX_MARK2, + UNIX_VERTEX_INDEX_START, +}; + +static unsigned long unix_vertex_unvisited_index = UNIX_VERTEX_INDEX_MARK1; + +static void unix_add_edge(struct scm_fp_list *fpl, struct unix_edge *edge) +{ + struct unix_vertex *vertex = edge->predecessor->vertex; + + if (!vertex) { + vertex = list_first_entry(&fpl->vertices, typeof(*vertex), entry); + vertex->index = unix_vertex_unvisited_index; + vertex->out_degree = 0; + INIT_LIST_HEAD(&vertex->edges); + INIT_LIST_HEAD(&vertex->scc_entry); + + list_move_tail(&vertex->entry, &unix_unvisited_vertices); + edge->predecessor->vertex = vertex; + } + + vertex->out_degree++; + list_add_tail(&edge->vertex_entry, &vertex->edges); + + unix_update_graph(unix_edge_successor(edge)); +} + +static void unix_del_edge(struct scm_fp_list *fpl, struct unix_edge *edge) +{ + struct unix_vertex *vertex = edge->predecessor->vertex; + + if (!fpl->dead) + unix_update_graph(unix_edge_successor(edge)); + + list_del(&edge->vertex_entry); + vertex->out_degree--; + + if (!vertex->out_degree) { + edge->predecessor->vertex = NULL; + list_move_tail(&vertex->entry, &fpl->vertices); + } +} + +static void unix_free_vertices(struct scm_fp_list *fpl) +{ + struct unix_vertex *vertex, *next_vertex; + + list_for_each_entry_safe(vertex, next_vertex, &fpl->vertices, entry) { + list_del(&vertex->entry); + kfree(vertex); + } +} + +static DEFINE_SPINLOCK(unix_gc_lock); +unsigned int unix_tot_inflight; + +void unix_add_edges(struct scm_fp_list *fpl, struct unix_sock *receiver) +{ + int i = 0, j = 0; + + spin_lock(&unix_gc_lock); + + if (!fpl->count_unix) + goto out; + + do { + struct unix_sock *inflight = unix_get_socket(fpl->fp[j++]); + struct unix_edge *edge; + + if (!inflight) + continue; + + edge = fpl->edges + i++; + edge->predecessor = inflight; + edge->successor = receiver; + + unix_add_edge(fpl, edge); + } while (i < fpl->count_unix); + + receiver->scm_stat.nr_unix_fds += fpl->count_unix; + WRITE_ONCE(unix_tot_inflight, unix_tot_inflight + fpl->count_unix); +out: + WRITE_ONCE(fpl->user->unix_inflight, fpl->user->unix_inflight + fpl->count); + + spin_unlock(&unix_gc_lock); + + fpl->inflight = true; + + unix_free_vertices(fpl); +} + +void unix_del_edges(struct scm_fp_list *fpl) +{ + struct unix_sock *receiver; + int i = 0; + + spin_lock(&unix_gc_lock); + + if (!fpl->count_unix) + goto out; + + do { + struct unix_edge *edge = fpl->edges + i++; + + unix_del_edge(fpl, edge); + } while (i < fpl->count_unix); + + if (!fpl->dead) { + receiver = fpl->edges[0].successor; + receiver->scm_stat.nr_unix_fds -= fpl->count_unix; + } + WRITE_ONCE(unix_tot_inflight, unix_tot_inflight - fpl->count_unix); +out: + WRITE_ONCE(fpl->user->unix_inflight, fpl->user->unix_inflight - fpl->count); + + spin_unlock(&unix_gc_lock); + + fpl->inflight = false; +} + +void unix_update_edges(struct unix_sock *receiver) +{ + /* nr_unix_fds is only updated under unix_state_lock(). + * If it's 0 here, the embryo socket is not part of the + * inflight graph, and GC will not see it, so no lock needed. + */ + if (!receiver->scm_stat.nr_unix_fds) { + receiver->listener = NULL; + } else { + spin_lock(&unix_gc_lock); + unix_update_graph(unix_sk(receiver->listener)->vertex); + receiver->listener = NULL; + spin_unlock(&unix_gc_lock); + } +} + +int unix_prepare_fpl(struct scm_fp_list *fpl) +{ + struct unix_vertex *vertex; + int i; + + if (!fpl->count_unix) + return 0; + + for (i = 0; i < fpl->count_unix; i++) { + vertex = kmalloc(sizeof(*vertex), GFP_KERNEL); + if (!vertex) + goto err; + + list_add(&vertex->entry, &fpl->vertices); + } + + fpl->edges = kvmalloc_array(fpl->count_unix, sizeof(*fpl->edges), + GFP_KERNEL_ACCOUNT); + if (!fpl->edges) + goto err; + + return 0; + +err: + unix_free_vertices(fpl); + return -ENOMEM; +} + +void unix_destroy_fpl(struct scm_fp_list *fpl) +{ + if (fpl->inflight) + unix_del_edges(fpl); + + kvfree(fpl->edges); + unix_free_vertices(fpl); +} + +static bool unix_vertex_dead(struct unix_vertex *vertex) +{ + struct unix_edge *edge; + struct unix_sock *u; + long total_ref; + + list_for_each_entry(edge, &vertex->edges, vertex_entry) { + struct unix_vertex *next_vertex = unix_edge_successor(edge); + + /* The vertex's fd can be received by a non-inflight socket. */ + if (!next_vertex) + return false; + + /* The vertex's fd can be received by an inflight socket in + * another SCC. + */ + if (next_vertex->scc_index != vertex->scc_index) + return false; + } + + /* No receiver exists out of the same SCC. */ + + edge = list_first_entry(&vertex->edges, typeof(*edge), vertex_entry); + u = edge->predecessor; + total_ref = file_count(u->sk.sk_socket->file); + + /* If not close()d, total_ref > out_degree. */ + if (total_ref != vertex->out_degree) + return false; + + return true; +} + +enum unix_recv_queue_lock_class { + U_RECVQ_LOCK_NORMAL, + U_RECVQ_LOCK_EMBRYO, +}; + +static void unix_collect_queue(struct unix_sock *u, struct sk_buff_head *hitlist) +{ + skb_queue_splice_init(&u->sk.sk_receive_queue, hitlist); + +#if IS_ENABLED(CONFIG_AF_UNIX_OOB) + if (u->oob_skb) { + WARN_ON_ONCE(skb_unref(u->oob_skb)); + u->oob_skb = NULL; + } +#endif +} + +static void unix_collect_skb(struct list_head *scc, struct sk_buff_head *hitlist) +{ + struct unix_vertex *vertex; + + list_for_each_entry_reverse(vertex, scc, scc_entry) { + struct sk_buff_head *queue; + struct unix_edge *edge; + struct unix_sock *u; + + edge = list_first_entry(&vertex->edges, typeof(*edge), vertex_entry); + u = edge->predecessor; + queue = &u->sk.sk_receive_queue; + + spin_lock(&queue->lock); + + if (u->sk.sk_state == TCP_LISTEN) { + struct sk_buff *skb; + + skb_queue_walk(queue, skb) { + struct sk_buff_head *embryo_queue = &skb->sk->sk_receive_queue; + + /* listener -> embryo order, the inversion never happens. */ + spin_lock_nested(&embryo_queue->lock, U_RECVQ_LOCK_EMBRYO); + unix_collect_queue(unix_sk(skb->sk), hitlist); + spin_unlock(&embryo_queue->lock); + } + } else { + unix_collect_queue(u, hitlist); + } + + spin_unlock(&queue->lock); + } +} + +static bool unix_scc_cyclic(struct list_head *scc) +{ + struct unix_vertex *vertex; + struct unix_edge *edge; + + /* SCC containing multiple vertices ? */ + if (!list_is_singular(scc)) + return true; + + vertex = list_first_entry(scc, typeof(*vertex), scc_entry); + + /* Self-reference or a embryo-listener circle ? */ + list_for_each_entry(edge, &vertex->edges, vertex_entry) { + if (unix_edge_successor(edge) == vertex) + return true; + } + + return false; +} + +static LIST_HEAD(unix_visited_vertices); +static unsigned long unix_vertex_grouped_index = UNIX_VERTEX_INDEX_MARK2; + +static void __unix_walk_scc(struct unix_vertex *vertex, unsigned long *last_index, + struct sk_buff_head *hitlist) +{ + LIST_HEAD(vertex_stack); + struct unix_edge *edge; + LIST_HEAD(edge_stack); + +next_vertex: + /* Push vertex to vertex_stack and mark it as on-stack + * (index >= UNIX_VERTEX_INDEX_START). + * The vertex will be popped when finalising SCC later. + */ + list_add(&vertex->scc_entry, &vertex_stack); + + vertex->index = *last_index; + vertex->scc_index = *last_index; + (*last_index)++; + + /* Explore neighbour vertices (receivers of the current vertex's fd). */ + list_for_each_entry(edge, &vertex->edges, vertex_entry) { + struct unix_vertex *next_vertex = unix_edge_successor(edge); + + if (!next_vertex) + continue; + + if (next_vertex->index == unix_vertex_unvisited_index) { + /* Iterative deepening depth first search + * + * 1. Push a forward edge to edge_stack and set + * the successor to vertex for the next iteration. + */ + list_add(&edge->stack_entry, &edge_stack); + + vertex = next_vertex; + goto next_vertex; + + /* 2. Pop the edge directed to the current vertex + * and restore the ancestor for backtracking. + */ +prev_vertex: + edge = list_first_entry(&edge_stack, typeof(*edge), stack_entry); + list_del_init(&edge->stack_entry); + + next_vertex = vertex; + vertex = edge->predecessor->vertex; + + /* If the successor has a smaller scc_index, two vertices + * are in the same SCC, so propagate the smaller scc_index + * to skip SCC finalisation. + */ + vertex->scc_index = min(vertex->scc_index, next_vertex->scc_index); + } else if (next_vertex->index != unix_vertex_grouped_index) { + /* Loop detected by a back/cross edge. + * + * The successor is on vertex_stack, so two vertices are in + * the same SCC. If the successor has a smaller *scc_index*, + * propagate it to skip SCC finalisation. + */ + vertex->scc_index = min(vertex->scc_index, next_vertex->scc_index); + } else { + /* The successor was already grouped as another SCC */ + } + } + + if (vertex->index == vertex->scc_index) { + struct unix_vertex *v; + struct list_head scc; + bool scc_dead = true; + + /* SCC finalised. + * + * If the scc_index was not updated, all the vertices above on + * vertex_stack are in the same SCC. Group them using scc_entry. + */ + __list_cut_position(&scc, &vertex_stack, &vertex->scc_entry); + + list_for_each_entry_reverse(v, &scc, scc_entry) { + /* Don't restart DFS from this vertex in unix_walk_scc(). */ + list_move_tail(&v->entry, &unix_visited_vertices); + + /* Mark vertex as off-stack. */ + v->index = unix_vertex_grouped_index; + + if (scc_dead) + scc_dead = unix_vertex_dead(v); + } + + if (scc_dead) + unix_collect_skb(&scc, hitlist); + else if (!unix_graph_maybe_cyclic) + unix_graph_maybe_cyclic = unix_scc_cyclic(&scc); + + list_del(&scc); + } + + /* Need backtracking ? */ + if (!list_empty(&edge_stack)) + goto prev_vertex; +} + +static void unix_walk_scc(struct sk_buff_head *hitlist) +{ + unsigned long last_index = UNIX_VERTEX_INDEX_START; + + unix_graph_maybe_cyclic = false; + + /* Visit every vertex exactly once. + * __unix_walk_scc() moves visited vertices to unix_visited_vertices. + */ + while (!list_empty(&unix_unvisited_vertices)) { + struct unix_vertex *vertex; + + vertex = list_first_entry(&unix_unvisited_vertices, typeof(*vertex), entry); + __unix_walk_scc(vertex, &last_index, hitlist); + } + + list_replace_init(&unix_visited_vertices, &unix_unvisited_vertices); + swap(unix_vertex_unvisited_index, unix_vertex_grouped_index); + + unix_graph_grouped = true; +} + +static void unix_walk_scc_fast(struct sk_buff_head *hitlist) +{ + unix_graph_maybe_cyclic = false; + + while (!list_empty(&unix_unvisited_vertices)) { + struct unix_vertex *vertex; + struct list_head scc; + bool scc_dead = true; + + vertex = list_first_entry(&unix_unvisited_vertices, typeof(*vertex), entry); + list_add(&scc, &vertex->scc_entry); + + list_for_each_entry_reverse(vertex, &scc, scc_entry) { + list_move_tail(&vertex->entry, &unix_visited_vertices); + + if (scc_dead) + scc_dead = unix_vertex_dead(vertex); + } + + if (scc_dead) + unix_collect_skb(&scc, hitlist); + else if (!unix_graph_maybe_cyclic) + unix_graph_maybe_cyclic = unix_scc_cyclic(&scc); + + list_del(&scc); + } + + list_replace_init(&unix_visited_vertices, &unix_unvisited_vertices); } static bool gc_in_progress; -#define UNIX_INFLIGHT_TRIGGER_GC 16000 -void wait_for_unix_gc(void) +static void __unix_gc(struct work_struct *work) +{ + struct sk_buff_head hitlist; + struct sk_buff *skb; + + spin_lock(&unix_gc_lock); + + if (!unix_graph_maybe_cyclic) { + spin_unlock(&unix_gc_lock); + goto skip_gc; + } + + __skb_queue_head_init(&hitlist); + + if (unix_graph_grouped) + unix_walk_scc_fast(&hitlist); + else + unix_walk_scc(&hitlist); + + spin_unlock(&unix_gc_lock); + + skb_queue_walk(&hitlist, skb) { + if (UNIXCB(skb).fp) + UNIXCB(skb).fp->dead = true; + } + + __skb_queue_purge(&hitlist); +skip_gc: + WRITE_ONCE(gc_in_progress, false); +} + +static DECLARE_WORK(unix_gc_work, __unix_gc); + +void unix_gc(void) +{ + WRITE_ONCE(gc_in_progress, true); + queue_work(system_unbound_wq, &unix_gc_work); +} + +#define UNIX_INFLIGHT_TRIGGER_GC 16000 +#define UNIX_INFLIGHT_SANE_USER (SCM_MAX_FD * 8) + +void wait_for_unix_gc(struct scm_fp_list *fpl) { /* If number of inflight sockets is insane, * force a garbage collect right now. + * * Paired with the WRITE_ONCE() in unix_inflight(), - * unix_notinflight() and gc_in_progress(). + * unix_notinflight(), and __unix_gc(). */ if (READ_ONCE(unix_tot_inflight) > UNIX_INFLIGHT_TRIGGER_GC && !READ_ONCE(gc_in_progress)) unix_gc(); - wait_event(unix_gc_wait, !READ_ONCE(gc_in_progress)); -} - -/* The external entry point: unix_gc() */ -void unix_gc(void) -{ - struct sk_buff *next_skb, *skb; - struct unix_sock *u; - struct unix_sock *next; - struct sk_buff_head hitlist; - struct list_head cursor; - LIST_HEAD(not_cycle_list); - - spin_lock(&unix_gc_lock); - - /* Avoid a recursive GC. */ - if (gc_in_progress) - goto out; - - /* Paired with READ_ONCE() in wait_for_unix_gc(). */ - WRITE_ONCE(gc_in_progress, true); - - /* First, select candidates for garbage collection. Only - * in-flight sockets are considered, and from those only ones - * which don't have any external reference. - * - * Holding unix_gc_lock will protect these candidates from - * being detached, and hence from gaining an external - * reference. Since there are no possible receivers, all - * buffers currently on the candidates' queues stay there - * during the garbage collection. - * - * We also know that no new candidate can be added onto the - * receive queues. Other, non candidate sockets _can_ be - * added to queue, so we must make sure only to touch - * candidates. - * - * Embryos, though never candidates themselves, affect which - * candidates are reachable by the garbage collector. Before - * being added to a listener's queue, an embryo may already - * receive data carrying SCM_RIGHTS, potentially making the - * passed socket a candidate that is not yet reachable by the - * collector. It becomes reachable once the embryo is - * enqueued. Therefore, we must ensure that no SCM-laden - * embryo appears in a (candidate) listener's queue between - * consecutive scan_children() calls. - */ - list_for_each_entry_safe(u, next, &gc_inflight_list, link) { - struct sock *sk = &u->sk; - long total_refs; - - total_refs = file_count(sk->sk_socket->file); - - BUG_ON(!u->inflight); - BUG_ON(total_refs < u->inflight); - if (total_refs == u->inflight) { - list_move_tail(&u->link, &gc_candidates); - __set_bit(UNIX_GC_CANDIDATE, &u->gc_flags); - __set_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags); - - if (sk->sk_state == TCP_LISTEN) { - unix_state_lock_nested(sk, U_LOCK_GC_LISTENER); - unix_state_unlock(sk); - } - } - } - - /* Now remove all internal in-flight reference to children of - * the candidates. - */ - list_for_each_entry(u, &gc_candidates, link) - scan_children(&u->sk, dec_inflight, NULL); - - /* Restore the references for children of all candidates, - * which have remaining references. Do this recursively, so - * only those remain, which form cyclic references. - * - * Use a "cursor" link, to make the list traversal safe, even - * though elements might be moved about. - */ - list_add(&cursor, &gc_candidates); - while (cursor.next != &gc_candidates) { - u = list_entry(cursor.next, struct unix_sock, link); - - /* Move cursor to after the current position. */ - list_move(&cursor, &u->link); - - if (u->inflight) { - list_move_tail(&u->link, ¬_cycle_list); - __clear_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags); - scan_children(&u->sk, inc_inflight_move_tail, NULL); - } - } - list_del(&cursor); - - /* Now gc_candidates contains only garbage. Restore original - * inflight counters for these as well, and remove the skbuffs - * which are creating the cycle(s). - */ - skb_queue_head_init(&hitlist); - list_for_each_entry(u, &gc_candidates, link) { - scan_children(&u->sk, inc_inflight, &hitlist); - -#if IS_ENABLED(CONFIG_AF_UNIX_OOB) - if (u->oob_skb) { - kfree_skb(u->oob_skb); - u->oob_skb = NULL; - } -#endif - } - - /* not_cycle_list contains those sockets which do not make up a - * cycle. Restore these to the inflight list. - */ - while (!list_empty(¬_cycle_list)) { - u = list_entry(not_cycle_list.next, struct unix_sock, link); - __clear_bit(UNIX_GC_CANDIDATE, &u->gc_flags); - list_move_tail(&u->link, &gc_inflight_list); - } - - spin_unlock(&unix_gc_lock); - - /* We need io_uring to clean its registered files, ignore all io_uring - * originated skbs. It's fine as io_uring doesn't keep references to - * other io_uring instances and so killing all other files in the cycle - * will put all io_uring references forcing it to go through normal - * release.path eventually putting registered files. - */ - skb_queue_walk_safe(&hitlist, skb, next_skb) { - if (skb->scm_io_uring) { - __skb_unlink(skb, &hitlist); - skb_queue_tail(&skb->sk->sk_receive_queue, skb); - } - } - - /* Here we are. Hitlist is filled. Die. */ - __skb_queue_purge(&hitlist); - - spin_lock(&unix_gc_lock); - - /* There could be io_uring registered files, just push them back to - * the inflight list - */ - list_for_each_entry_safe(u, next, &gc_candidates, link) - list_move_tail(&u->link, &gc_inflight_list); - - /* All candidates should have been detached by now. */ - BUG_ON(!list_empty(&gc_candidates)); - - /* Paired with READ_ONCE() in wait_for_unix_gc(). */ - WRITE_ONCE(gc_in_progress, false); - - wake_up(&unix_gc_wait); - - out: - spin_unlock(&unix_gc_lock); + + /* Penalise users who want to send AF_UNIX sockets + * but whose sockets have not been received yet. + */ + if (!fpl || !fpl->count_unix || + READ_ONCE(fpl->user->unix_inflight) < UNIX_INFLIGHT_SANE_USER) + return; + + if (READ_ONCE(gc_in_progress)) + flush_work(&unix_gc_work); } diff --git a/net/unix/scm.c b/net/unix/scm.c deleted file mode 100644 index 4eff7da9f6f9..000000000000 --- a/net/unix/scm.c +++ /dev/null @@ -1,154 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "scm.h" - -unsigned int unix_tot_inflight; -EXPORT_SYMBOL(unix_tot_inflight); - -LIST_HEAD(gc_inflight_list); -EXPORT_SYMBOL(gc_inflight_list); - -DEFINE_SPINLOCK(unix_gc_lock); -EXPORT_SYMBOL(unix_gc_lock); - -struct sock *unix_get_socket(struct file *filp) -{ - struct sock *u_sock = NULL; - struct inode *inode = file_inode(filp); - - /* Socket ? */ - if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) { - struct socket *sock = SOCKET_I(inode); - struct sock *s = sock->sk; - - /* PF_UNIX ? */ - if (s && sock->ops && sock->ops->family == PF_UNIX) - u_sock = s; - } - - return u_sock; -} -EXPORT_SYMBOL(unix_get_socket); - -/* Keep the number of times in flight count for the file - * descriptor if it is for an AF_UNIX socket. - */ -void unix_inflight(struct user_struct *user, struct file *fp) -{ - struct sock *s = unix_get_socket(fp); - - spin_lock(&unix_gc_lock); - - if (s) { - struct unix_sock *u = unix_sk(s); - - if (!u->inflight) { - BUG_ON(!list_empty(&u->link)); - list_add_tail(&u->link, &gc_inflight_list); - } else { - BUG_ON(list_empty(&u->link)); - } - u->inflight++; - /* Paired with READ_ONCE() in wait_for_unix_gc() */ - WRITE_ONCE(unix_tot_inflight, unix_tot_inflight + 1); - } - WRITE_ONCE(user->unix_inflight, user->unix_inflight + 1); - spin_unlock(&unix_gc_lock); -} - -void unix_notinflight(struct user_struct *user, struct file *fp) -{ - struct sock *s = unix_get_socket(fp); - - spin_lock(&unix_gc_lock); - - if (s) { - struct unix_sock *u = unix_sk(s); - - BUG_ON(!u->inflight); - BUG_ON(list_empty(&u->link)); - - u->inflight--; - if (!u->inflight) - list_del_init(&u->link); - /* Paired with READ_ONCE() in wait_for_unix_gc() */ - WRITE_ONCE(unix_tot_inflight, unix_tot_inflight - 1); - } - WRITE_ONCE(user->unix_inflight, user->unix_inflight - 1); - spin_unlock(&unix_gc_lock); -} - -/* - * The "user->unix_inflight" variable is protected by the garbage - * collection lock, and we just read it locklessly here. If you go - * over the limit, there might be a tiny race in actually noticing - * it across threads. Tough. - */ -static inline bool too_many_unix_fds(struct task_struct *p) -{ - struct user_struct *user = current_user(); - - if (unlikely(READ_ONCE(user->unix_inflight) > task_rlimit(p, RLIMIT_NOFILE))) - return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); - return false; -} - -int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) -{ - int i; - - if (too_many_unix_fds(current)) - return -ETOOMANYREFS; - - /* - * Need to duplicate file references for the sake of garbage - * collection. Otherwise a socket in the fps might become a - * candidate for GC while the skb is not yet queued. - */ - UNIXCB(skb).fp = scm_fp_dup(scm->fp); - if (!UNIXCB(skb).fp) - return -ENOMEM; - - for (i = scm->fp->count - 1; i >= 0; i--) - unix_inflight(scm->fp->user, scm->fp->fp[i]); - return 0; -} -EXPORT_SYMBOL(unix_attach_fds); - -void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb) -{ - int i; - - scm->fp = UNIXCB(skb).fp; - UNIXCB(skb).fp = NULL; - - for (i = scm->fp->count-1; i >= 0; i--) - unix_notinflight(scm->fp->user, scm->fp->fp[i]); -} -EXPORT_SYMBOL(unix_detach_fds); - -void unix_destruct_scm(struct sk_buff *skb) -{ - struct scm_cookie scm; - - memset(&scm, 0, sizeof(scm)); - scm.pid = UNIXCB(skb).pid; - if (UNIXCB(skb).fp) - unix_detach_fds(&scm, skb); - - /* Alas, it calls VFS */ - /* So fscking what? fput() had been SMP-safe since the last Summer */ - scm_destroy(&scm); - sock_wfree(skb); -} -EXPORT_SYMBOL(unix_destruct_scm); diff --git a/net/unix/scm.h b/net/unix/scm.h deleted file mode 100644 index 5a255a477f16..000000000000 --- a/net/unix/scm.h +++ /dev/null @@ -1,10 +0,0 @@ -#ifndef NET_UNIX_SCM_H -#define NET_UNIX_SCM_H - -extern struct list_head gc_inflight_list; -extern spinlock_t unix_gc_lock; - -int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb); -void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb); - -#endif diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 3dd47b7fb80e..39d260c90383 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1599,6 +1599,9 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) struct xfrm_policy *delpol; struct hlist_head *chain; + /* Sanitize mark before store */ + policy->mark.v &= policy->mark.m; + spin_lock_bh(&net->xfrm.xfrm_policy_lock); chain = policy_hash_bysel(net, &policy->selector, policy->family, dir); if (chain) diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 6e0fbc11e71c..a38ea5ae9d5c 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1278,6 +1278,9 @@ static void __xfrm_state_insert(struct xfrm_state *x) list_add(&x->km.all, &net->xfrm.state_all); + /* Sanitize mark before store */ + x->mark.v &= x->mark.m; + h = xfrm_dst_hash(net, &x->id.daddr, &x->props.saddr, x->props.reqid, x->props.family); hlist_add_head_rcu(&x->bydst, net->xfrm.state_bydst + h); diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 727da3c5879b..77bf18cfdae7 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -434,7 +434,7 @@ $(obj)/%.o: $(src)/%.c @echo " CLANG-bpf " $@ $(Q)$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(BPF_EXTRA_CFLAGS) \ -I$(obj) -I$(srctree)/tools/testing/selftests/bpf/ \ - -I$(LIBBPF_INCLUDE) \ + -I$(LIBBPF_INCLUDE) $(CLANG_SYS_INCLUDES) \ -D__KERNEL__ -D__BPF_TRACING__ -Wno-unused-value -Wno-pointer-sign \ -D__TARGET_ARCH_$(SRCARCH) -Wno-compare-distinct-pointer-types \ -Wno-gnu-variable-sized-type-not-at-end \ diff --git a/samples/ftrace/sample-trace-array.c b/samples/ftrace/sample-trace-array.c index 6aba02a31c96..77685a7eb767 100644 --- a/samples/ftrace/sample-trace-array.c +++ b/samples/ftrace/sample-trace-array.c @@ -112,7 +112,7 @@ static int __init sample_trace_array_init(void) /* * If context specific per-cpu buffers havent already been allocated. */ - trace_printk_init_buffers(); + trace_array_init_printk(tr); simple_tsk = kthread_run(simple_thread, NULL, "sample-instance"); if (IS_ERR(simple_tsk)) { diff --git a/scripts/config b/scripts/config index ff88e2faefd3..ea475c07de28 100755 --- a/scripts/config +++ b/scripts/config @@ -32,6 +32,7 @@ commands: Disable option directly after other option --module-after|-M beforeopt option Turn option into module directly after other option + --refresh Refresh the config using old settings commands can be repeated multiple times @@ -124,16 +125,22 @@ undef_var() { txt_delete "^# $name is not set" "$FN" } -if [ "$1" = "--file" ]; then - FN="$2" - if [ "$FN" = "" ] ; then - usage +FN=.config +CMDS=() +while [[ $# -gt 0 ]]; do + if [ "$1" = "--file" ]; then + if [ "$2" = "" ]; then + usage + fi + FN="$2" + shift 2 + else + CMDS+=("$1") + shift fi - shift 2 -else - FN=.config -fi +done +set -- "${CMDS[@]}" if [ "$1" = "" ] ; then usage fi @@ -217,9 +224,8 @@ while [ "$1" != "" ] ; do set_var "${CONFIG_}$B" "${CONFIG_}$B=m" "${CONFIG_}$A" ;; - # undocumented because it ignores --file (fixme) --refresh) - yes "" | make oldconfig + yes "" | make oldconfig KCONFIG_CONFIG=$FN ;; *) diff --git a/scripts/kconfig/merge_config.sh b/scripts/kconfig/merge_config.sh index 72da3b8d6f30..151f9938abaa 100755 --- a/scripts/kconfig/merge_config.sh +++ b/scripts/kconfig/merge_config.sh @@ -105,8 +105,8 @@ INITFILE=$1 shift; if [ ! -r "$INITFILE" ]; then - echo "The base file '$INITFILE' does not exist. Exit." >&2 - exit 1 + echo "The base file '$INITFILE' does not exist. Creating one..." >&2 + touch "$INITFILE" fi MERGE_LIST=$* diff --git a/security/smack/smackfs.c b/security/smack/smackfs.c index d955f3dcb3a5..9dca3672d82b 100644 --- a/security/smack/smackfs.c +++ b/security/smack/smackfs.c @@ -922,6 +922,10 @@ static ssize_t smk_set_cipso(struct file *file, const char __user *buf, if (rc >= 0) { old_cat = skp->smk_netlabel.attr.mls.cat; rcu_assign_pointer(skp->smk_netlabel.attr.mls.cat, ncats.attr.mls.cat); + if (ncats.attr.mls.cat) + skp->smk_netlabel.flags |= NETLBL_SECATTR_MLS_CAT; + else + skp->smk_netlabel.flags &= ~(u32)NETLBL_SECATTR_MLS_CAT; skp->smk_netlabel.attr.mls.lvl = ncats.attr.mls.lvl; synchronize_rcu(); netlbl_catmap_free(old_cat); diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c index 728c211142d1..471de2d1b37a 100644 --- a/sound/core/oss/pcm_oss.c +++ b/sound/core/oss/pcm_oss.c @@ -1085,8 +1085,7 @@ static int snd_pcm_oss_change_params_locked(struct snd_pcm_substream *substream) runtime->oss.params = 0; runtime->oss.prepare = 1; runtime->oss.buffer_used = 0; - if (runtime->dma_area) - snd_pcm_format_set_silence(runtime->format, runtime->dma_area, bytes_to_samples(runtime, runtime->dma_bytes)); + snd_pcm_runtime_buffer_set_silence(runtime); runtime->oss.period_frames = snd_pcm_alsa_frames(substream, oss_period_size); diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 7a7d5acb423d..31095f66ebc9 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -703,6 +703,17 @@ static void snd_pcm_buffer_access_unlock(struct snd_pcm_runtime *runtime) atomic_inc(&runtime->buffer_accessing); } +/* fill the PCM buffer with the current silence format; called from pcm_oss.c */ +void snd_pcm_runtime_buffer_set_silence(struct snd_pcm_runtime *runtime) +{ + snd_pcm_buffer_access_lock(runtime); + if (runtime->dma_area) + snd_pcm_format_set_silence(runtime->format, runtime->dma_area, + bytes_to_samples(runtime, runtime->dma_bytes)); + snd_pcm_buffer_access_unlock(runtime); +} +EXPORT_SYMBOL_GPL(snd_pcm_runtime_buffer_set_silence); + #if IS_ENABLED(CONFIG_SND_PCM_OSS) #define is_oss_stream(substream) ((substream)->oss.oss) #else diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 2d707afa1ef1..1252ea7ad55e 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -1140,8 +1140,7 @@ static __poll_t snd_seq_poll(struct file *file, poll_table * wait) if (snd_seq_file_flags(file) & SNDRV_SEQ_LFLG_OUTPUT) { /* check if data is available in the pool */ - if (!snd_seq_write_pool_allocated(client) || - snd_seq_pool_poll_wait(client->pool, file, wait)) + if (snd_seq_pool_poll_wait(client->pool, file, wait)) mask |= EPOLLOUT | EPOLLWRNORM; } @@ -2382,8 +2381,6 @@ int snd_seq_kernel_client_write_poll(int clientid, struct file *file, poll_table if (client == NULL) return -ENXIO; - if (! snd_seq_write_pool_allocated(client)) - return 1; if (snd_seq_pool_poll_wait(client->pool, file, wait)) return 1; return 0; diff --git a/sound/core/seq/seq_memory.c b/sound/core/seq/seq_memory.c index 47ef6bc30c0e..e30b92d85079 100644 --- a/sound/core/seq/seq_memory.c +++ b/sound/core/seq/seq_memory.c @@ -366,6 +366,7 @@ int snd_seq_pool_poll_wait(struct snd_seq_pool *pool, struct file *file, poll_table *wait) { poll_wait(file, &pool->output_sleep, wait); + guard(spinlock_irq)(&pool->lock); return snd_seq_output_ok(pool); } diff --git a/sound/pci/es1968.c b/sound/pci/es1968.c index 4a7e20bb11bc..802c5ed4a5ba 100644 --- a/sound/pci/es1968.c +++ b/sound/pci/es1968.c @@ -1569,7 +1569,7 @@ static int snd_es1968_capture_open(struct snd_pcm_substream *substream) struct snd_pcm_runtime *runtime = substream->runtime; struct es1968 *chip = snd_pcm_substream_chip(substream); struct esschan *es; - int apu1, apu2; + int err, apu1, apu2; apu1 = snd_es1968_alloc_apu_pair(chip, ESM_APU_PCM_CAPTURE); if (apu1 < 0) @@ -1613,7 +1613,9 @@ static int snd_es1968_capture_open(struct snd_pcm_substream *substream) runtime->hw = snd_es1968_capture; runtime->hw.buffer_bytes_max = runtime->hw.period_bytes_max = calc_available_memory_size(chip) - 1024; /* keep MIXBUF size */ - snd_pcm_hw_constraint_pow2(runtime, 0, SNDRV_PCM_HW_PARAM_BUFFER_BYTES); + err = snd_pcm_hw_constraint_pow2(runtime, 0, SNDRV_PCM_HW_PARAM_BUFFER_BYTES); + if (err < 0) + return err; spin_lock_irq(&chip->substream_lock); list_add(&es->list, &chip->substream_list); diff --git a/sound/pci/hda/hda_beep.c b/sound/pci/hda/hda_beep.c index e63621bcb214..1a684e47d4d1 100644 --- a/sound/pci/hda/hda_beep.c +++ b/sound/pci/hda/hda_beep.c @@ -31,8 +31,9 @@ static void generate_tone(struct hda_beep *beep, int tone) beep->power_hook(beep, true); beep->playing = 1; } - snd_hda_codec_write(codec, beep->nid, 0, - AC_VERB_SET_BEEP_CONTROL, tone); + if (!codec->beep_just_power_on) + snd_hda_codec_write(codec, beep->nid, 0, + AC_VERB_SET_BEEP_CONTROL, tone); if (!tone && beep->playing) { beep->playing = 0; if (beep->power_hook) @@ -212,10 +213,12 @@ int snd_hda_attach_beep_device(struct hda_codec *codec, int nid) struct hda_beep *beep; int err; - if (!snd_hda_get_bool_hint(codec, "beep")) - return 0; /* disabled explicitly by hints */ - if (codec->beep_mode == HDA_BEEP_MODE_OFF) - return 0; /* disabled by module option */ + if (!codec->beep_just_power_on) { + if (!snd_hda_get_bool_hint(codec, "beep")) + return 0; /* disabled explicitly by hints */ + if (codec->beep_mode == HDA_BEEP_MODE_OFF) + return 0; /* disabled by module option */ + } beep = kzalloc(sizeof(*beep), GFP_KERNEL); if (beep == NULL) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 61b48f2418bf..115c675819e6 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -24,6 +24,7 @@ #include #include "hda_local.h" #include "hda_auto_parser.h" +#include "hda_beep.h" #include "hda_jack.h" #include "hda_generic.h" #include "hda_component.h" @@ -6786,6 +6787,41 @@ static void alc285_fixup_hp_spectre_x360_eb1(struct hda_codec *codec, } } +/* GPIO1 = amplifier on/off */ +static void alc285_fixup_hp_spectre_x360_df1(struct hda_codec *codec, + const struct hda_fixup *fix, + int action) +{ + struct alc_spec *spec = codec->spec; + static const hda_nid_t conn[] = { 0x02 }; + static const struct hda_pintbl pincfgs[] = { + { 0x14, 0x90170110 }, /* front/high speakers */ + { 0x17, 0x90170130 }, /* back/bass speakers */ + { } + }; + + // enable mute led + alc285_fixup_hp_mute_led_coefbit(codec, fix, action); + + switch (action) { + case HDA_FIXUP_ACT_PRE_PROBE: + /* needed for amp of back speakers */ + spec->gpio_mask |= 0x01; + spec->gpio_dir |= 0x01; + snd_hda_apply_pincfgs(codec, pincfgs); + /* share DAC to have unified volume control */ + snd_hda_override_conn_list(codec, 0x14, ARRAY_SIZE(conn), conn); + snd_hda_override_conn_list(codec, 0x17, ARRAY_SIZE(conn), conn); + break; + case HDA_FIXUP_ACT_INIT: + /* need to toggle GPIO to enable the amp of back speakers */ + alc_update_gpio_data(codec, 0x01, true); + msleep(100); + alc_update_gpio_data(codec, 0x01, false); + break; + } +} + static void alc285_fixup_hp_spectre_x360(struct hda_codec *codec, const struct hda_fixup *fix, int action) { @@ -6858,6 +6894,30 @@ static void alc285_fixup_hp_envy_x360(struct hda_codec *codec, } } +static void alc285_fixup_hp_beep(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + if (action == HDA_FIXUP_ACT_PRE_PROBE) { + codec->beep_just_power_on = true; + } else if (action == HDA_FIXUP_ACT_INIT) { +#ifdef CONFIG_SND_HDA_INPUT_BEEP + /* + * Just enable loopback to internal speaker and headphone jack. + * Disable amplification to get about the same beep volume as + * was on pure BIOS setup before loading the driver. + */ + alc_update_coef_idx(codec, 0x36, 0x7070, BIT(13)); + + snd_hda_enable_beep_device(codec, 1); + +#if !IS_ENABLED(CONFIG_INPUT_PCSPKR) + dev_warn_once(hda_codec_dev(codec), + "enable CONFIG_INPUT_PCSPKR to get PC beeps\n"); +#endif +#endif + } +} + /* for hda_fixup_thinkpad_acpi() */ #include "thinkpad_helper.c" @@ -7301,6 +7361,7 @@ enum { ALC280_FIXUP_HP_9480M, ALC245_FIXUP_HP_X360_AMP, ALC285_FIXUP_HP_SPECTRE_X360_EB1, + ALC285_FIXUP_HP_SPECTRE_X360_DF1, ALC285_FIXUP_HP_ENVY_X360, ALC288_FIXUP_DELL_HEADSET_MODE, ALC288_FIXUP_DELL1_MIC_NO_PRESENCE, @@ -7400,6 +7461,7 @@ enum { ALC285_FIXUP_HP_GPIO_LED, ALC285_FIXUP_HP_MUTE_LED, ALC285_FIXUP_HP_SPECTRE_X360_MUTE_LED, + ALC285_FIXUP_HP_BEEP_MICMUTE_LED, ALC236_FIXUP_HP_MUTE_LED_COEFBIT2, ALC236_FIXUP_HP_GPIO_LED, ALC236_FIXUP_HP_MUTE_LED, @@ -8947,6 +9009,12 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc285_fixup_hp_spectre_x360_mute_led, }, + [ALC285_FIXUP_HP_BEEP_MICMUTE_LED] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_hp_beep, + .chained = true, + .chain_id = ALC285_FIXUP_HP_MUTE_LED, + }, [ALC236_FIXUP_HP_MUTE_LED_COEFBIT2] = { .type = HDA_FIXUP_FUNC, .v.func = alc236_fixup_hp_mute_led_coefbit2, @@ -9290,6 +9358,10 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc285_fixup_hp_spectre_x360_eb1 }, + [ALC285_FIXUP_HP_SPECTRE_X360_DF1] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_hp_spectre_x360_df1 + }, [ALC285_FIXUP_HP_ENVY_X360] = { .type = HDA_FIXUP_FUNC, .v.func = alc285_fixup_hp_envy_x360, @@ -9850,6 +9922,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x86c1, "HP Laptop 15-da3001TU", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x86c7, "HP Envy AiO 32", ALC274_FIXUP_HP_ENVY_GPIO), SND_PCI_QUIRK(0x103c, 0x86e7, "HP Spectre x360 15-eb0xxx", ALC285_FIXUP_HP_SPECTRE_X360_EB1), + SND_PCI_QUIRK(0x103c, 0x863e, "HP Spectre x360 15-df1xxx", ALC285_FIXUP_HP_SPECTRE_X360_DF1), SND_PCI_QUIRK(0x103c, 0x86e8, "HP Spectre x360 15-eb0xxx", ALC285_FIXUP_HP_SPECTRE_X360_EB1), SND_PCI_QUIRK(0x103c, 0x86f9, "HP Spectre x360 13-aw0xxx", ALC285_FIXUP_HP_SPECTRE_X360_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x8716, "HP Elite Dragonfly G2 Notebook PC", ALC285_FIXUP_HP_GPIO_AMP_INIT), @@ -9860,7 +9933,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8730, "HP ProBook 445 G7", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8735, "HP ProBook 435 G7", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8736, "HP", ALC285_FIXUP_HP_GPIO_AMP_INIT), - SND_PCI_QUIRK(0x103c, 0x8760, "HP", ALC285_FIXUP_HP_MUTE_LED), + SND_PCI_QUIRK(0x103c, 0x8760, "HP EliteBook 8{4,5}5 G7", ALC285_FIXUP_HP_BEEP_MICMUTE_LED), SND_PCI_QUIRK(0x103c, 0x876e, "HP ENVY x360 Convertible 13-ay0xxx", ALC245_FIXUP_HP_X360_MUTE_LEDS), SND_PCI_QUIRK(0x103c, 0x877a, "HP", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x877d, "HP", ALC236_FIXUP_HP_MUTE_LED), @@ -10306,6 +10379,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x3866, "Lenovo 13X", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x3869, "Lenovo Yoga7 14IAL7", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI), + SND_PCI_QUIRK(0x17aa, 0x390d, "Lenovo Yoga Pro 7 14ASP10", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), SND_PCI_QUIRK(0x17aa, 0x3913, "Lenovo 145", ALC236_FIXUP_LENOVO_INV_DMIC), SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC), SND_PCI_QUIRK(0x17aa, 0x3978, "Lenovo B50-70", ALC269_FIXUP_DMIC_THINKPAD_ACPI), @@ -10559,6 +10633,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {.id = ALC295_FIXUP_HP_OMEN, .name = "alc295-hp-omen"}, {.id = ALC285_FIXUP_HP_SPECTRE_X360, .name = "alc285-hp-spectre-x360"}, {.id = ALC285_FIXUP_HP_SPECTRE_X360_EB1, .name = "alc285-hp-spectre-x360-eb1"}, + {.id = ALC285_FIXUP_HP_SPECTRE_X360_DF1, .name = "alc285-hp-spectre-x360-df1"}, {.id = ALC285_FIXUP_HP_ENVY_X360, .name = "alc285-hp-envy-x360"}, {.id = ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP, .name = "alc287-ideapad-bass-spk-amp"}, {.id = ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN, .name = "alc287-yoga9-bass-spk-pin"}, diff --git a/sound/sh/Kconfig b/sound/sh/Kconfig index b75fbb3236a7..f5fa09d740b4 100644 --- a/sound/sh/Kconfig +++ b/sound/sh/Kconfig @@ -14,7 +14,7 @@ if SND_SUPERH config SND_AICA tristate "Dreamcast Yamaha AICA sound" - depends on SH_DREAMCAST + depends on SH_DREAMCAST && SH_DMA_API select SND_PCM select G2_DMA help diff --git a/sound/soc/codecs/mt6359-accdet.h b/sound/soc/codecs/mt6359-accdet.h index c234f2f4276a..78ada3a5bfae 100644 --- a/sound/soc/codecs/mt6359-accdet.h +++ b/sound/soc/codecs/mt6359-accdet.h @@ -123,6 +123,15 @@ struct mt6359_accdet { struct workqueue_struct *jd_workqueue; }; +#if IS_ENABLED(CONFIG_SND_SOC_MT6359_ACCDET) int mt6359_accdet_enable_jack_detect(struct snd_soc_component *component, struct snd_soc_jack *jack); +#else +static inline int +mt6359_accdet_enable_jack_detect(struct snd_soc_component *component, + struct snd_soc_jack *jack) +{ + return -EOPNOTSUPP; +} +#endif #endif diff --git a/sound/soc/codecs/pcm3168a.c b/sound/soc/codecs/pcm3168a.c index 9d6431338fb7..329549936bd5 100644 --- a/sound/soc/codecs/pcm3168a.c +++ b/sound/soc/codecs/pcm3168a.c @@ -494,9 +494,9 @@ static int pcm3168a_hw_params(struct snd_pcm_substream *substream, } break; case 24: - if (provider_mode || (format == SND_SOC_DAIFMT_DSP_A) || - (format == SND_SOC_DAIFMT_DSP_B)) { - dev_err(component->dev, "24-bit slots not supported in provider mode, or consumer mode using DSP\n"); + if (!provider_mode && ((format == SND_SOC_DAIFMT_DSP_A) || + (format == SND_SOC_DAIFMT_DSP_B))) { + dev_err(component->dev, "24-bit slots not supported in consumer mode using DSP\n"); return -EINVAL; } break; diff --git a/sound/soc/codecs/tas2764.c b/sound/soc/codecs/tas2764.c index fc8479d3d285..10f0f07b90ff 100644 --- a/sound/soc/codecs/tas2764.c +++ b/sound/soc/codecs/tas2764.c @@ -182,33 +182,6 @@ static SOC_ENUM_SINGLE_DECL( static const struct snd_kcontrol_new tas2764_asi1_mux = SOC_DAPM_ENUM("ASI1 Source", tas2764_ASI1_src_enum); -static int tas2764_dac_event(struct snd_soc_dapm_widget *w, - struct snd_kcontrol *kcontrol, int event) -{ - struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm); - struct tas2764_priv *tas2764 = snd_soc_component_get_drvdata(component); - int ret; - - switch (event) { - case SND_SOC_DAPM_POST_PMU: - tas2764->dac_powered = true; - ret = tas2764_update_pwr_ctrl(tas2764); - break; - case SND_SOC_DAPM_PRE_PMD: - tas2764->dac_powered = false; - ret = tas2764_update_pwr_ctrl(tas2764); - break; - default: - dev_err(tas2764->dev, "Unsupported event\n"); - return -EINVAL; - } - - if (ret < 0) - return ret; - - return 0; -} - static const struct snd_kcontrol_new isense_switch = SOC_DAPM_SINGLE("Switch", TAS2764_PWR_CTRL, TAS2764_ISENSE_POWER_EN, 1, 1); static const struct snd_kcontrol_new vsense_switch = @@ -221,8 +194,7 @@ static const struct snd_soc_dapm_widget tas2764_dapm_widgets[] = { 1, &isense_switch), SND_SOC_DAPM_SWITCH("VSENSE", TAS2764_PWR_CTRL, TAS2764_VSENSE_POWER_EN, 1, &vsense_switch), - SND_SOC_DAPM_DAC_E("DAC", NULL, SND_SOC_NOPM, 0, 0, tas2764_dac_event, - SND_SOC_DAPM_POST_PMU | SND_SOC_DAPM_PRE_PMD), + SND_SOC_DAPM_DAC("DAC", NULL, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_OUTPUT("OUT"), SND_SOC_DAPM_SIGGEN("VMON"), SND_SOC_DAPM_SIGGEN("IMON") @@ -243,9 +215,28 @@ static int tas2764_mute(struct snd_soc_dai *dai, int mute, int direction) { struct tas2764_priv *tas2764 = snd_soc_component_get_drvdata(dai->component); + int ret; + + if (!mute) { + tas2764->dac_powered = true; + ret = tas2764_update_pwr_ctrl(tas2764); + if (ret) + return ret; + } tas2764->unmuted = !mute; - return tas2764_update_pwr_ctrl(tas2764); + ret = tas2764_update_pwr_ctrl(tas2764); + if (ret) + return ret; + + if (mute) { + tas2764->dac_powered = false; + ret = tas2764_update_pwr_ctrl(tas2764); + if (ret) + return ret; + } + + return 0; } static int tas2764_set_bitwidth(struct tas2764_priv *tas2764, int bitwidth) @@ -636,6 +627,7 @@ static const struct reg_default tas2764_reg_defaults[] = { { TAS2764_TDM_CFG2, 0x0a }, { TAS2764_TDM_CFG3, 0x10 }, { TAS2764_TDM_CFG5, 0x42 }, + { TAS2764_INT_CLK_CFG, 0x19 }, }; static const struct regmap_range_cfg tas2764_regmap_ranges[] = { @@ -653,6 +645,7 @@ static const struct regmap_range_cfg tas2764_regmap_ranges[] = { static bool tas2764_volatile_register(struct device *dev, unsigned int reg) { switch (reg) { + case TAS2764_SW_RST: case TAS2764_INT_LTCH0 ... TAS2764_INT_LTCH4: case TAS2764_INT_CLK_CFG: return true; diff --git a/sound/soc/fsl/imx-card.c b/sound/soc/fsl/imx-card.c index c6d55b21f949..11430f9f4996 100644 --- a/sound/soc/fsl/imx-card.c +++ b/sound/soc/fsl/imx-card.c @@ -517,7 +517,7 @@ static int imx_card_parse_of(struct imx_card_data *data) if (!card->dai_link) return -ENOMEM; - data->link_data = devm_kcalloc(dev, num_links, sizeof(*link), GFP_KERNEL); + data->link_data = devm_kcalloc(dev, num_links, sizeof(*link_data), GFP_KERNEL); if (!data->link_data) return -ENOMEM; diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c index 67b343632a10..b00a9fdd7a9c 100644 --- a/sound/soc/intel/boards/bytcr_rt5640.c +++ b/sound/soc/intel/boards/bytcr_rt5640.c @@ -576,6 +576,19 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { BYT_RT5640_SSP0_AIF2 | BYT_RT5640_MCLK_EN), }, + { /* Acer Aspire SW3-013 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire SW3-013"), + }, + .driver_data = (void *)(BYT_RT5640_DMIC1_MAP | + BYT_RT5640_JD_SRC_JD2_IN4N | + BYT_RT5640_OVCD_TH_2000UA | + BYT_RT5640_OVCD_SF_0P75 | + BYT_RT5640_DIFF_MIC | + BYT_RT5640_SSP0_AIF1 | + BYT_RT5640_MCLK_EN), + }, { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Acer"), diff --git a/sound/soc/qcom/sm8250.c b/sound/soc/qcom/sm8250.c index 41be09a07ca7..65e51b6b46ff 100644 --- a/sound/soc/qcom/sm8250.c +++ b/sound/soc/qcom/sm8250.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include @@ -39,9 +40,11 @@ static int sm8250_be_hw_params_fixup(struct snd_soc_pcm_runtime *rtd, SNDRV_PCM_HW_PARAM_RATE); struct snd_interval *channels = hw_param_interval(params, SNDRV_PCM_HW_PARAM_CHANNELS); + struct snd_mask *fmt = hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT); rate->min = rate->max = 48000; channels->min = channels->max = 2; + snd_mask_set_format(fmt, SNDRV_PCM_FORMAT_S16_LE); return 0; } diff --git a/sound/soc/soc-dai.c b/sound/soc/soc-dai.c index 49752af0e205..ba38b6e6b264 100644 --- a/sound/soc/soc-dai.c +++ b/sound/soc/soc-dai.c @@ -270,10 +270,11 @@ int snd_soc_dai_set_tdm_slot(struct snd_soc_dai *dai, if (dai->driver->ops && dai->driver->ops->xlate_tdm_slot_mask) - dai->driver->ops->xlate_tdm_slot_mask(slots, - &tx_mask, &rx_mask); + ret = dai->driver->ops->xlate_tdm_slot_mask(slots, &tx_mask, &rx_mask); else - snd_soc_xlate_tdm_slot_mask(slots, &tx_mask, &rx_mask); + ret = snd_soc_xlate_tdm_slot_mask(slots, &tx_mask, &rx_mask); + if (ret) + goto err; dai->tx_mask = tx_mask; dai->rx_mask = rx_mask; @@ -282,6 +283,7 @@ int snd_soc_dai_set_tdm_slot(struct snd_soc_dai *dai, dai->driver->ops->set_tdm_slot) ret = dai->driver->ops->set_tdm_slot(dai, tx_mask, rx_mask, slots, slot_width); +err: return soc_dai_ret(dai, ret); } EXPORT_SYMBOL_GPL(snd_soc_dai_set_tdm_slot); diff --git a/sound/soc/soc-ops.c b/sound/soc/soc-ops.c index b4cfc34d00ee..eff1355cc3df 100644 --- a/sound/soc/soc-ops.c +++ b/sound/soc/soc-ops.c @@ -638,6 +638,33 @@ int snd_soc_get_volsw_range(struct snd_kcontrol *kcontrol, } EXPORT_SYMBOL_GPL(snd_soc_get_volsw_range); +static int snd_soc_clip_to_platform_max(struct snd_kcontrol *kctl) +{ + struct soc_mixer_control *mc = (struct soc_mixer_control *)kctl->private_value; + struct snd_ctl_elem_value uctl; + int ret; + + if (!mc->platform_max) + return 0; + + ret = kctl->get(kctl, &uctl); + if (ret < 0) + return ret; + + if (uctl.value.integer.value[0] > mc->platform_max) + uctl.value.integer.value[0] = mc->platform_max; + + if (snd_soc_volsw_is_stereo(mc) && + uctl.value.integer.value[1] > mc->platform_max) + uctl.value.integer.value[1] = mc->platform_max; + + ret = kctl->put(kctl, &uctl); + if (ret < 0) + return ret; + + return 0; +} + /** * snd_soc_limit_volume - Set new limit to an existing volume control. * @@ -662,7 +689,7 @@ int snd_soc_limit_volume(struct snd_soc_card *card, struct soc_mixer_control *mc = (struct soc_mixer_control *)kctl->private_value; if (max <= mc->max - mc->min) { mc->platform_max = max; - ret = 0; + ret = snd_soc_clip_to_platform_max(kctl); } } return ret; diff --git a/sound/soc/sunxi/sun4i-codec.c b/sound/soc/sunxi/sun4i-codec.c index 835dc3404367..1e310958f8c0 100644 --- a/sound/soc/sunxi/sun4i-codec.c +++ b/sound/soc/sunxi/sun4i-codec.c @@ -25,6 +25,7 @@ #include #include +#include #include #include #include @@ -239,6 +240,7 @@ struct sun4i_codec { struct clk *clk_module; struct reset_control *rst; struct gpio_desc *gpio_pa; + struct gpio_desc *gpio_hp; /* ADC_FIFOC register is at different offset on different SoCs */ struct regmap_field *reg_adc_fifoc; @@ -1273,6 +1275,49 @@ static struct snd_soc_dai_driver dummy_cpu_dai = { }, }; +static struct snd_soc_jack sun4i_headphone_jack; + +static struct snd_soc_jack_pin sun4i_headphone_jack_pins[] = { + { .pin = "Headphone", .mask = SND_JACK_HEADPHONE }, +}; + +static struct snd_soc_jack_gpio sun4i_headphone_jack_gpio = { + .name = "hp-det", + .report = SND_JACK_HEADPHONE, + .debounce_time = 150, +}; + +static int sun4i_codec_machine_init(struct snd_soc_pcm_runtime *rtd) +{ + struct snd_soc_card *card = rtd->card; + struct sun4i_codec *scodec = snd_soc_card_get_drvdata(card); + int ret; + + if (scodec->gpio_hp) { + ret = snd_soc_card_jack_new_pins(card, "Headphone Jack", + SND_JACK_HEADPHONE, + &sun4i_headphone_jack, + sun4i_headphone_jack_pins, + ARRAY_SIZE(sun4i_headphone_jack_pins)); + if (ret) { + dev_err(rtd->dev, + "Headphone jack creation failed: %d\n", ret); + return ret; + } + + sun4i_headphone_jack_gpio.desc = scodec->gpio_hp; + ret = snd_soc_jack_add_gpios(&sun4i_headphone_jack, 1, + &sun4i_headphone_jack_gpio); + + if (ret) { + dev_err(rtd->dev, "Headphone GPIO not added: %d\n", ret); + return ret; + } + } + + return 0; +} + static struct snd_soc_dai_link *sun4i_codec_create_link(struct device *dev, int *num_links) { @@ -1298,6 +1343,7 @@ static struct snd_soc_dai_link *sun4i_codec_create_link(struct device *dev, link->codecs->name = dev_name(dev); link->platforms->name = dev_name(dev); link->dai_fmt = SND_SOC_DAIFMT_I2S; + link->init = sun4i_codec_machine_init; *num_links = 1; @@ -1738,6 +1784,13 @@ static int sun4i_codec_probe(struct platform_device *pdev) return ret; } + scodec->gpio_hp = devm_gpiod_get_optional(&pdev->dev, "hp-det", GPIOD_IN); + if (IS_ERR(scodec->gpio_hp)) { + ret = PTR_ERR(scodec->gpio_hp); + dev_err_probe(&pdev->dev, ret, "Failed to get hp-det gpio\n"); + return ret; + } + /* reg_field setup */ scodec->reg_adc_fifoc = devm_regmap_field_alloc(&pdev->dev, scodec->regmap, diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 42302c7812c7..b2a612c5b299 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -2138,6 +2138,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_CTL_MSG_DELAY_1M), DEVICE_FLG(0x0c45, 0x6340, /* Sonix HD USB Camera */ QUIRK_FLAG_GET_SAMPLE_RATE), + DEVICE_FLG(0x0c45, 0x636b, /* Microdia JP001 USB Camera */ + QUIRK_FLAG_GET_SAMPLE_RATE), DEVICE_FLG(0x0d8c, 0x0014, /* USB Audio Device */ QUIRK_FLAG_CTL_MSG_DELAY_1M), DEVICE_FLG(0x0ecb, 0x205c, /* JBL Quantum610 Wireless */ @@ -2146,6 +2148,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_FIXED_RATE), DEVICE_FLG(0x0fd9, 0x0008, /* Hauppauge HVR-950Q */ QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER), + DEVICE_FLG(0x1101, 0x0003, /* Audioengine D1 */ + QUIRK_FLAG_GET_SAMPLE_RATE), DEVICE_FLG(0x1224, 0x2a25, /* Jieli Technology USB PHY 2.0 */ QUIRK_FLAG_GET_SAMPLE_RATE | QUIRK_FLAG_MIC_RES_16), DEVICE_FLG(0x1395, 0x740a, /* Sennheiser DECT */ diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index db02b000fbeb..eea00bc15b5c 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -384,10 +384,11 @@ int get_fd_type(int fd) p_err("can't read link type: %s", strerror(errno)); return -1; } - if (n == sizeof(path)) { + if (n == sizeof(buf)) { p_err("can't read link type: path too long!"); return -1; } + buf[n] = '\0'; if (strstr(buf, "bpf-map")) return BPF_OBJ_MAP; diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build index 715092fc6a23..6a043b729b36 100644 --- a/tools/build/Makefile.build +++ b/tools/build/Makefile.build @@ -130,6 +130,10 @@ objprefix := $(subst ./,,$(OUTPUT)$(dir)/) obj-y := $(addprefix $(objprefix),$(obj-y)) subdir-obj-y := $(addprefix $(objprefix),$(subdir-obj-y)) +# Separate out test log files from real build objects. +test-y := $(filter %_log, $(obj-y)) +obj-y := $(filter-out %_log, $(obj-y)) + # Final '$(obj)-in.o' object in-target := $(objprefix)$(obj)-in.o @@ -140,7 +144,7 @@ $(subdir-y): $(sort $(subdir-obj-y)): $(subdir-y) ; -$(in-target): $(obj-y) FORCE +$(in-target): $(obj-y) $(test-y) FORCE $(call rule_mkdir) $(call if_changed,$(host)ld_multi) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index a0fb50718dae..98d5e566e058 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -1751,7 +1751,7 @@ static int set_kcfg_value_str(struct extern_desc *ext, char *ext_val, } len = strlen(value); - if (value[len - 1] != '"') { + if (len < 2 || value[len - 1] != '"') { pr_warn("extern (kcfg) '%s': invalid string config '%s'\n", ext->name, value); return -EINVAL; diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 828c91aaf55b..bf75628c5389 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -3083,7 +3083,7 @@ static int handle_insn_ops(struct instruction *insn, if (update_cfi_state(insn, next_insn, &state->cfi, op)) return 1; - if (!insn->alt_group) + if (!opts.uaccess || !insn->alt_group) continue; if (op->dest.type == OP_DEST_PUSHF) { @@ -3535,6 +3535,9 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, return 0; case INSN_STAC: + if (!opts.uaccess) + break; + if (state.uaccess) { WARN_FUNC("recursive UACCESS enable", sec, insn->offset); return 1; @@ -3544,6 +3547,9 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, break; case INSN_CLAC: + if (!opts.uaccess) + break; + if (!state.uaccess && func) { WARN_FUNC("redundant UACCESS disable", sec, insn->offset); return 1; @@ -3956,7 +3962,8 @@ static int validate_symbol(struct objtool_file *file, struct section *sec, if (!insn || insn->ignore || insn->visited) return 0; - state->uaccess = sym->uaccess_safe; + if (opts.uaccess) + state->uaccess = sym->uaccess_safe; ret = validate_branch(file, insn->func, insn, *state); if (ret && opts.backtrace) diff --git a/tools/testing/kunit/qemu_configs/x86_64.py b/tools/testing/kunit/qemu_configs/x86_64.py index dc7949076863..4a6bf4e048f5 100644 --- a/tools/testing/kunit/qemu_configs/x86_64.py +++ b/tools/testing/kunit/qemu_configs/x86_64.py @@ -7,4 +7,6 @@ CONFIG_SERIAL_8250_CONSOLE=y''', qemu_arch='x86_64', kernel_path='arch/x86/boot/bzImage', kernel_command_line='console=ttyS0', - extra_qemu_params=[]) + # qboot is faster than SeaBIOS and doesn't mess up + # the terminal. + extra_qemu_params=['-bios', 'qboot.rom']) diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c index 2d0796314862..0a99fd404f6d 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c @@ -68,7 +68,6 @@ static void test_sockmap_ktls_disconnect_after_delete(int family, int map) goto close_cli; err = disconnect(cli); - ASSERT_OK(err, "disconnect"); close_cli: close(cli); diff --git a/tools/testing/selftests/exec/Makefile b/tools/testing/selftests/exec/Makefile index a0b8688b0836..a705493c04bb 100644 --- a/tools/testing/selftests/exec/Makefile +++ b/tools/testing/selftests/exec/Makefile @@ -3,8 +3,13 @@ CFLAGS = -Wall CFLAGS += -Wno-nonnull CFLAGS += -D_GNU_SOURCE +ALIGNS := 0x1000 0x200000 0x1000000 +ALIGN_PIES := $(patsubst %,load_address.%,$(ALIGNS)) +ALIGN_STATIC_PIES := $(patsubst %,load_address.static.%,$(ALIGNS)) +ALIGNMENT_TESTS := $(ALIGN_PIES) $(ALIGN_STATIC_PIES) + TEST_PROGS := binfmt_script.py -TEST_GEN_PROGS := execveat load_address_4096 load_address_2097152 load_address_16777216 non-regular +TEST_GEN_PROGS := execveat non-regular $(ALIGNMENT_TESTS) TEST_GEN_FILES := execveat.symlink execveat.denatured script subdir # Makefile is a run-time dependency, since it's accessed by the execveat test TEST_FILES := Makefile @@ -28,9 +33,9 @@ $(OUTPUT)/execveat.symlink: $(OUTPUT)/execveat $(OUTPUT)/execveat.denatured: $(OUTPUT)/execveat cp $< $@ chmod -x $@ -$(OUTPUT)/load_address_4096: load_address.c - $(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x1000 -pie -static $< -o $@ -$(OUTPUT)/load_address_2097152: load_address.c - $(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x200000 -pie -static $< -o $@ -$(OUTPUT)/load_address_16777216: load_address.c - $(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x1000000 -pie -static $< -o $@ +$(OUTPUT)/load_address.0x%: load_address.c + $(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=$(lastword $(subst ., ,$@)) \ + -fPIE -pie $< -o $@ +$(OUTPUT)/load_address.static.0x%: load_address.c + $(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=$(lastword $(subst ., ,$@)) \ + -fPIE -static-pie $< -o $@ diff --git a/tools/testing/selftests/exec/load_address.c b/tools/testing/selftests/exec/load_address.c index d487c2f6a615..8257fddba8c8 100644 --- a/tools/testing/selftests/exec/load_address.c +++ b/tools/testing/selftests/exec/load_address.c @@ -5,10 +5,13 @@ #include #include #include +#include +#include "../kselftest.h" struct Statistics { unsigned long long load_address; unsigned long long alignment; + bool interp; }; int ExtractStatistics(struct dl_phdr_info *info, size_t size, void *data) @@ -25,11 +28,20 @@ int ExtractStatistics(struct dl_phdr_info *info, size_t size, void *data) stats->alignment = 0; for (i = 0; i < info->dlpi_phnum; i++) { + unsigned long long align; + + if (info->dlpi_phdr[i].p_type == PT_INTERP) { + stats->interp = true; + continue; + } + if (info->dlpi_phdr[i].p_type != PT_LOAD) continue; - if (info->dlpi_phdr[i].p_align > stats->alignment) - stats->alignment = info->dlpi_phdr[i].p_align; + align = info->dlpi_phdr[i].p_align; + + if (align > stats->alignment) + stats->alignment = align; } return 1; // Terminate dl_iterate_phdr. @@ -37,32 +49,57 @@ int ExtractStatistics(struct dl_phdr_info *info, size_t size, void *data) int main(int argc, char **argv) { - struct Statistics extracted; - unsigned long long misalign; + struct Statistics extracted = { }; + unsigned long long misalign, pow2; + bool interp_needed; + char buf[1024]; + FILE *maps; int ret; + ksft_print_header(); + ksft_set_plan(4); + + /* Dump maps file for debugging reference. */ + maps = fopen("/proc/self/maps", "r"); + if (!maps) + ksft_exit_fail_msg("FAILED: /proc/self/maps: %s\n", strerror(errno)); + while (fgets(buf, sizeof(buf), maps)) { + ksft_print_msg("%s", buf); + } + fclose(maps); + + /* Walk the program headers. */ ret = dl_iterate_phdr(ExtractStatistics, &extracted); - if (ret != 1) { - fprintf(stderr, "FAILED\n"); - return 1; - } + if (ret != 1) + ksft_exit_fail_msg("FAILED: dl_iterate_phdr\n"); - if (extracted.alignment == 0) { - fprintf(stderr, "No alignment found\n"); - return 1; - } else if (extracted.alignment & (extracted.alignment - 1)) { - fprintf(stderr, "Alignment is not a power of 2\n"); - return 1; - } + /* Report our findings. */ + ksft_print_msg("load_address=%#llx alignment=%#llx\n", + extracted.load_address, extracted.alignment); + /* If we're named with ".static." we expect no INTERP. */ + interp_needed = strstr(argv[0], ".static.") == NULL; + + /* Were we built as expected? */ + ksft_test_result(interp_needed == extracted.interp, + "%s INTERP program header %s\n", + interp_needed ? "Wanted" : "Unwanted", + extracted.interp ? "seen" : "missing"); + + /* Did we find an alignment? */ + ksft_test_result(extracted.alignment != 0, + "Alignment%s found\n", extracted.alignment ? "" : " NOT"); + + /* Is the alignment sane? */ + pow2 = extracted.alignment & (extracted.alignment - 1); + ksft_test_result(pow2 == 0, + "Alignment is%s a power of 2: %#llx\n", + pow2 == 0 ? "" : " NOT", extracted.alignment); + + /* Is the load address aligned? */ misalign = extracted.load_address & (extracted.alignment - 1); - if (misalign) { - printf("alignment = %llu, load_address = %llu\n", - extracted.alignment, extracted.load_address); - fprintf(stderr, "FAILED\n"); - return 1; - } + ksft_test_result(misalign == 0, "Load Address is %saligned (%#llx)\n", + misalign ? "MIS" : "", misalign); - fprintf(stderr, "PASS\n"); - return 0; + ksft_finished(); } diff --git a/tools/testing/selftests/net/gro.sh b/tools/testing/selftests/net/gro.sh index 342ad27f631b..e771f5f7faa2 100755 --- a/tools/testing/selftests/net/gro.sh +++ b/tools/testing/selftests/net/gro.sh @@ -95,5 +95,6 @@ trap cleanup EXIT if [[ "${test}" == "all" ]]; then run_all_tests else - run_test "${proto}" "${test}" + exit_code=$(run_test "${proto}" "${test}") + exit $exit_code fi; diff --git a/tools/testing/selftests/vm/compaction_test.c b/tools/testing/selftests/vm/compaction_test.c index 309b3750e57e..38fec412206b 100644 --- a/tools/testing/selftests/vm/compaction_test.c +++ b/tools/testing/selftests/vm/compaction_test.c @@ -89,6 +89,8 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size) int compaction_index = 0; char initial_nr_hugepages[20] = {0}; char nr_hugepages[20] = {0}; + char target_nr_hugepages[24] = {0}; + int slen; /* We want to test with 80% of available memory. Else, OOM killer comes in to play */ @@ -119,11 +121,18 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size) lseek(fd, 0, SEEK_SET); - /* Request a large number of huge pages. The Kernel will allocate - as much as it can */ - if (write(fd, "100000", (6*sizeof(char))) != (6*sizeof(char))) { - ksft_print_msg("Failed to write 100000 to /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + /* + * Request huge pages for about half of the free memory. The Kernel + * will allocate as much as it can, and we expect it will get at least 1/3 + */ + nr_hugepages_ul = mem_free / hugepage_size / 2; + snprintf(target_nr_hugepages, sizeof(target_nr_hugepages), + "%lu", nr_hugepages_ul); + + slen = strlen(target_nr_hugepages); + if (write(fd, target_nr_hugepages, slen) != slen) { + ksft_print_msg("Failed to write %lu to /proc/sys/vm/nr_hugepages: %s\n", + nr_hugepages_ul, strerror(errno)); goto close_fd; }