diff options
348 files changed, 2817 insertions, 1577 deletions
diff --git a/.get_maintainer.ignore b/.get_maintainer.ignore index a64d21913745..c298bab3d320 100644 --- a/.get_maintainer.ignore +++ b/.get_maintainer.ignore @@ -1,2 +1,4 @@ +Alan Cox <alan@lxorguk.ukuu.org.uk> +Alan Cox <root@hraefn.swansea.linux.org.uk> Christoph Hellwig <hch@lst.de> Marc Gonzalez <marc.w.gonzalez@free.fr> diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index 5bf61881f012..760c889b6cd1 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -523,6 +523,7 @@ What: /sys/devices/system/cpu/vulnerabilities /sys/devices/system/cpu/vulnerabilities/tsx_async_abort /sys/devices/system/cpu/vulnerabilities/itlb_multihit /sys/devices/system/cpu/vulnerabilities/mmio_stale_data + /sys/devices/system/cpu/vulnerabilities/retbleed Date: January 2018 Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org> Description: Information about CPU vulnerabilities diff --git a/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst b/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst index 9393c50b5afc..c98fd11907cc 100644 --- a/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst +++ b/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst @@ -230,6 +230,20 @@ The possible values in this file are: * - 'Mitigation: Clear CPU buffers' - The processor is vulnerable and the CPU buffer clearing mitigation is enabled. + * - 'Unknown: No mitigations' + - The processor vulnerability status is unknown because it is + out of Servicing period. Mitigation is not attempted. + +Definitions: +------------ + +Servicing period: The process of providing functional and security updates to +Intel processors or platforms, utilizing the Intel Platform Update (IPU) +process or other similar mechanisms. + +End of Servicing Updates (ESU): ESU is the date at which Intel will no +longer provide Servicing, such as through IPU or other similar update +processes. ESU dates will typically be aligned to end of quarter. If the processor is vulnerable then the following information is appended to the above information: diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index d7f30902fda0..426fa892d311 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -5331,6 +5331,8 @@ rodata= [KNL] on Mark read-only kernel memory as read-only (default). off Leave read-only kernel memory writable for debugging. + full Mark read-only kernel memory and aliases as read-only + [arm64] rockchip.usb_uart Enable the uart passthrough on the designated usb port diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst index 805f2281e000..60d44165fba7 100644 --- a/Documentation/admin-guide/sysctl/net.rst +++ b/Documentation/admin-guide/sysctl/net.rst @@ -271,7 +271,7 @@ poll cycle or the number of packets processed reaches netdev_budget. netdev_max_backlog ------------------ -Maximum number of packets, queued on the INPUT side, when the interface +Maximum number of packets, queued on the INPUT side, when the interface receives packets faster than kernel can process them. netdev_rss_key diff --git a/Documentation/arm64/elf_hwcaps.rst b/Documentation/arm64/elf_hwcaps.rst index 52b75a25c205..311021f2e560 100644 --- a/Documentation/arm64/elf_hwcaps.rst +++ b/Documentation/arm64/elf_hwcaps.rst @@ -242,44 +242,34 @@ HWCAP2_MTE3 by Documentation/arm64/memory-tagging-extension.rst. HWCAP2_SME - Functionality implied by ID_AA64PFR1_EL1.SME == 0b0001, as described by Documentation/arm64/sme.rst. HWCAP2_SME_I16I64 - Functionality implied by ID_AA64SMFR0_EL1.I16I64 == 0b1111. HWCAP2_SME_F64F64 - Functionality implied by ID_AA64SMFR0_EL1.F64F64 == 0b1. HWCAP2_SME_I8I32 - Functionality implied by ID_AA64SMFR0_EL1.I8I32 == 0b1111. HWCAP2_SME_F16F32 - Functionality implied by ID_AA64SMFR0_EL1.F16F32 == 0b1. HWCAP2_SME_B16F32 - Functionality implied by ID_AA64SMFR0_EL1.B16F32 == 0b1. HWCAP2_SME_F32F32 - Functionality implied by ID_AA64SMFR0_EL1.F32F32 == 0b1. HWCAP2_SME_FA64 - Functionality implied by ID_AA64SMFR0_EL1.FA64 == 0b1. HWCAP2_WFXT - Functionality implied by ID_AA64ISAR2_EL1.WFXT == 0b0010. HWCAP2_EBF16 - Functionality implied by ID_AA64ISAR1_EL1.BF16 == 0b0010. 4. Unused AT_HWCAP bits diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 33b04db8408f..fda97b3fcf01 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -52,6 +52,8 @@ stable kernels. | Allwinner | A64/R18 | UNKNOWN1 | SUN50I_ERRATUM_UNKNOWN1 | +----------------+-----------------+-----------------+-----------------------------+ +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A510 | #2457168 | ARM64_ERRATUM_2457168 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A510 | #2064142 | ARM64_ERRATUM_2064142 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A510 | #2038923 | ARM64_ERRATUM_2038923 | diff --git a/Documentation/atomic_bitops.txt b/Documentation/atomic_bitops.txt index d8b101c97031..edea4656c5c0 100644 --- a/Documentation/atomic_bitops.txt +++ b/Documentation/atomic_bitops.txt @@ -58,13 +58,11 @@ Like with atomic_t, the rule of thumb is: - RMW operations that have a return value are fully ordered. - - RMW operations that are conditional are unordered on FAILURE, - otherwise the above rules apply. In the case of test_and_set_bit_lock(), - if the bit in memory is unchanged by the operation then it is deemed to have - failed. + - RMW operations that are conditional are fully ordered. -Except for a successful test_and_set_bit_lock() which has ACQUIRE semantics and -clear_bit_unlock() which has RELEASE semantics. +Except for a successful test_and_set_bit_lock() which has ACQUIRE semantics, +clear_bit_unlock() which has RELEASE semantics and test_bit_acquire which has +ACQUIRE semantics. Since a platform only has a single means of achieving atomic operations the same barriers as for atomic_t are used, see atomic_t.txt. diff --git a/Documentation/devicetree/bindings/thermal/thermal-zones.yaml b/Documentation/devicetree/bindings/thermal/thermal-zones.yaml index 2d34f3ccb257..8d2c6d74b605 100644 --- a/Documentation/devicetree/bindings/thermal/thermal-zones.yaml +++ b/Documentation/devicetree/bindings/thermal/thermal-zones.yaml @@ -214,6 +214,7 @@ patternProperties: - polling-delay - polling-delay-passive - thermal-sensors + - trips additionalProperties: false diff --git a/MAINTAINERS b/MAINTAINERS index 59b3718e66d1..589517372408 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3680,6 +3680,7 @@ F: Documentation/networking/bonding.rst F: drivers/net/bonding/ F: include/net/bond* F: include/uapi/linux/if_bonding.h +F: tools/testing/selftests/drivers/net/bonding/ BOSCH SENSORTEC BMA400 ACCELEROMETER IIO DRIVER M: Dan Robertson <dan@dlrobertson.com> @@ -9782,7 +9783,7 @@ M: Christian Brauner <brauner@kernel.org> M: Seth Forshee <sforshee@kernel.org> L: linux-fsdevel@vger.kernel.org S: Maintained -T: git git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux.git +T: git://git.kernel.org/pub/scm/linux/kernel/git/vfs/idmapping.git F: Documentation/filesystems/idmappings.rst F: tools/testing/selftests/mount_setattr/ F: include/linux/mnt_idmapping.h @@ -10659,6 +10660,7 @@ T: git git://git.kernel.dk/linux-block T: git git://git.kernel.dk/liburing F: io_uring/ F: include/linux/io_uring.h +F: include/linux/io_uring_types.h F: include/uapi/linux/io_uring.h F: tools/io_uring/ diff --git a/arch/alpha/include/asm/bitops.h b/arch/alpha/include/asm/bitops.h index 492c7713ddae..bafb1c1f0fdc 100644 --- a/arch/alpha/include/asm/bitops.h +++ b/arch/alpha/include/asm/bitops.h @@ -283,11 +283,8 @@ arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr) return (old & mask) != 0; } -static __always_inline bool -arch_test_bit(unsigned long nr, const volatile unsigned long *addr) -{ - return (1UL & (((const int *) addr)[nr >> 5] >> (nr & 31))) != 0UL; -} +#define arch_test_bit generic_test_bit +#define arch_test_bit_acquire generic_test_bit_acquire /* * ffz = Find First Zero in word. Undefined if no zero exists, diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 571cc234d0b3..9fb9fff08c94 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -917,6 +917,23 @@ config ARM64_ERRATUM_1902691 If unsure, say Y. +config ARM64_ERRATUM_2457168 + bool "Cortex-A510: 2457168: workaround for AMEVCNTR01 incrementing incorrectly" + depends on ARM64_AMU_EXTN + default y + help + This option adds the workaround for ARM Cortex-A510 erratum 2457168. + + The AMU counter AMEVCNTR01 (constant counter) should increment at the same rate + as the system counter. On affected Cortex-A510 cores AMEVCNTR01 increments + incorrectly giving a significantly higher output value. + + Work around this problem by returning 0 when reading the affected counter in + key locations that results in disabling all users of this counter. This effect + is the same to firmware disabling affected counters. + + If unsure, say Y. + config CAVIUM_ERRATUM_22375 bool "Cavium erratum 22375, 24313" default y diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h index ca9b487112cc..34256bda0da9 100644 --- a/arch/arm64/include/asm/cache.h +++ b/arch/arm64/include/asm/cache.h @@ -71,7 +71,7 @@ static __always_inline int icache_is_vpipt(void) static inline u32 cache_type_cwg(void) { - return (read_cpuid_cachetype() >> CTR_EL0_CWG_SHIFT) & CTR_EL0_CWG_MASK; + return SYS_FIELD_GET(CTR_EL0, CWG, read_cpuid_cachetype()); } #define __read_mostly __section(".data..read_mostly") diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index 9bb1873f5295..6f86b7ab6c28 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -153,7 +153,7 @@ struct vl_info { #ifdef CONFIG_ARM64_SVE -extern void sve_alloc(struct task_struct *task); +extern void sve_alloc(struct task_struct *task, bool flush); extern void fpsimd_release_task(struct task_struct *task); extern void fpsimd_sync_to_sve(struct task_struct *task); extern void fpsimd_force_sync_to_sve(struct task_struct *task); @@ -256,7 +256,7 @@ size_t sve_state_size(struct task_struct const *task); #else /* ! CONFIG_ARM64_SVE */ -static inline void sve_alloc(struct task_struct *task) { } +static inline void sve_alloc(struct task_struct *task, bool flush) { } static inline void fpsimd_release_task(struct task_struct *task) { } static inline void sve_sync_to_fpsimd(struct task_struct *task) { } static inline void sve_sync_from_fpsimd_zeropad(struct task_struct *task) { } diff --git a/arch/arm64/include/asm/setup.h b/arch/arm64/include/asm/setup.h index 6437df661700..f4af547ef54c 100644 --- a/arch/arm64/include/asm/setup.h +++ b/arch/arm64/include/asm/setup.h @@ -3,6 +3,8 @@ #ifndef __ARM64_ASM_SETUP_H #define __ARM64_ASM_SETUP_H +#include <linux/string.h> + #include <uapi/asm/setup.h> void *get_early_fdt_ptr(void); @@ -14,4 +16,19 @@ void early_fdt_map(u64 dt_phys); extern phys_addr_t __fdt_pointer __initdata; extern u64 __cacheline_aligned boot_args[4]; +static inline bool arch_parse_debug_rodata(char *arg) +{ + extern bool rodata_enabled; + extern bool rodata_full; + + if (arg && !strcmp(arg, "full")) { + rodata_enabled = true; + rodata_full = true; + return true; + } + + return false; +} +#define arch_parse_debug_rodata arch_parse_debug_rodata + #endif diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 7c71358d44c4..818df938a7ad 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -1116,6 +1116,7 @@ #else +#include <linux/bitfield.h> #include <linux/build_bug.h> #include <linux/types.h> #include <asm/alternative.h> @@ -1209,8 +1210,6 @@ par; \ }) -#endif - #define SYS_FIELD_GET(reg, field, val) \ FIELD_GET(reg##_##field##_MASK, val) @@ -1220,4 +1219,6 @@ #define SYS_FIELD_PREP_ENUM(reg, field, val) \ FIELD_PREP(reg##_##field##_MASK, reg##_##field##_##val) +#endif + #endif /* __ASM_SYSREG_H */ diff --git a/arch/arm64/kernel/cacheinfo.c b/arch/arm64/kernel/cacheinfo.c index 587543c6c51c..97c42be71338 100644 --- a/arch/arm64/kernel/cacheinfo.c +++ b/arch/arm64/kernel/cacheinfo.c @@ -45,7 +45,8 @@ static void ci_leaf_init(struct cacheinfo *this_leaf, int init_cache_level(unsigned int cpu) { - unsigned int ctype, level, leaves, fw_level; + unsigned int ctype, level, leaves; + int fw_level; struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); for (level = 1, leaves = 0; level <= MAX_CACHE_LEVEL; level++) { @@ -63,6 +64,9 @@ int init_cache_level(unsigned int cpu) else fw_level = acpi_find_last_cache_level(cpu); + if (fw_level < 0) + return fw_level; + if (level < fw_level) { /* * some external caches not specified in CLIDR_EL1 diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 7e6289e709fc..53b973b6059f 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -208,6 +208,8 @@ static const struct arm64_cpu_capabilities arm64_repeat_tlbi_list[] = { #ifdef CONFIG_ARM64_ERRATUM_1286807 { ERRATA_MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 0), + }, + { /* Kryo4xx Gold (rcpe to rfpe) => (r0p0 to r3p0) */ ERRATA_MIDR_RANGE(MIDR_QCOM_KRYO_4XX_GOLD, 0xc, 0xe, 0xf, 0xe), }, @@ -654,6 +656,16 @@ const struct arm64_cpu_capabilities arm64_errata[] = { ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A510, 0, 0, 2) }, #endif +#ifdef CONFIG_ARM64_ERRATUM_2457168 + { + .desc = "ARM erratum 2457168", + .capability = ARM64_WORKAROUND_2457168, + .type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE, + + /* Cortex-A510 r0p0-r1p1 */ + CAP_MIDR_RANGE(MIDR_CORTEX_A510, 0, 0, 1, 1) + }, +#endif #ifdef CONFIG_ARM64_ERRATUM_2038923 { .desc = "ARM erratum 2038923", diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 907401e4fffb..af4de817d712 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1870,7 +1870,10 @@ static void cpu_amu_enable(struct arm64_cpu_capabilities const *cap) pr_info("detected CPU%d: Activity Monitors Unit (AMU)\n", smp_processor_id()); cpumask_set_cpu(smp_processor_id(), &amu_cpus); - update_freq_counters_refs(); + + /* 0 reference values signal broken/disabled counters */ + if (!this_cpu_has_cap(ARM64_WORKAROUND_2457168)) + update_freq_counters_refs(); } } diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 254fe31c03a0..2d73b3e793b2 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -502,7 +502,7 @@ tsk .req x28 // current thread_info SYM_CODE_START(vectors) kernel_ventry 1, t, 64, sync // Synchronous EL1t kernel_ventry 1, t, 64, irq // IRQ EL1t - kernel_ventry 1, t, 64, fiq // FIQ EL1h + kernel_ventry 1, t, 64, fiq // FIQ EL1t kernel_ventry 1, t, 64, error // Error EL1t kernel_ventry 1, h, 64, sync // Synchronous EL1h diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index dd63ffc3a2fa..23834d96d1e7 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -715,10 +715,12 @@ size_t sve_state_size(struct task_struct const *task) * do_sve_acc() case, there is no ABI requirement to hide stale data * written previously be task. */ -void sve_alloc(struct task_struct *task) +void sve_alloc(struct task_struct *task, bool flush) { if (task->thread.sve_state) { - memset(task->thread.sve_state, 0, sve_state_size(task)); + if (flush) + memset(task->thread.sve_state, 0, + sve_state_size(task)); return; } @@ -1388,7 +1390,7 @@ void do_sve_acc(unsigned long esr, struct pt_regs *regs) return; } - sve_alloc(current); + sve_alloc(current, true); if (!current->thread.sve_state) { force_sig(SIGKILL); return; @@ -1439,7 +1441,7 @@ void do_sme_acc(unsigned long esr, struct pt_regs *regs) return; } - sve_alloc(current); + sve_alloc(current, false); sme_alloc(current); if (!current->thread.sve_state || !current->thread.za_state) { force_sig(SIGKILL); @@ -1460,17 +1462,6 @@ void do_sme_acc(unsigned long esr, struct pt_regs *regs) fpsimd_bind_task_to_cpu(); } - /* - * If SVE was not already active initialise the SVE registers, - * any non-shared state between the streaming and regular SVE - * registers is architecturally guaranteed to be zeroed when - * we enter streaming mode. We do not need to initialize ZA - * since ZA must be disabled at this point and enabling ZA is - * architecturally defined to zero ZA. - */ - if (system_supports_sve() && !test_thread_flag(TIF_SVE)) - sve_init_regs(); - put_cpu_fpsimd_context(); } diff --git a/arch/arm64/kernel/pi/kaslr_early.c b/arch/arm64/kernel/pi/kaslr_early.c index 6c3855e69395..17bff6e399e4 100644 --- a/arch/arm64/kernel/pi/kaslr_early.c +++ b/arch/arm64/kernel/pi/kaslr_early.c @@ -94,11 +94,9 @@ asmlinkage u64 kaslr_early_init(void *fdt) seed = get_kaslr_seed(fdt); if (!seed) { -#ifdef CONFIG_ARCH_RANDOM - if (!__early_cpu_has_rndr() || - !__arm64_rndr((unsigned long *)&seed)) -#endif - return 0; + if (!__early_cpu_has_rndr() || + !__arm64_rndr((unsigned long *)&seed)) + return 0; } /* diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 21da83187a60..eb7c08dfb834 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -882,7 +882,7 @@ static int sve_set_common(struct task_struct *target, * state and ensure there's storage. */ if (target->thread.svcr != old_svcr) - sve_alloc(target); + sve_alloc(target, true); } /* Registers: FPSIMD-only case */ @@ -912,7 +912,7 @@ static int sve_set_common(struct task_struct *target, goto out; } - sve_alloc(target); + sve_alloc(target, true); if (!target->thread.sve_state) { ret = -ENOMEM; clear_tsk_thread_flag(target, TIF_SVE); @@ -1082,7 +1082,7 @@ static int za_set(struct task_struct *target, /* Ensure there is some SVE storage for streaming mode */ if (!target->thread.sve_state) { - sve_alloc(target); + sve_alloc(target, false); if (!target->thread.sve_state) { clear_thread_flag(TIF_SME); ret = -ENOMEM; diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 3e6d0352d7d3..9ad911f1647c 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -91,7 +91,7 @@ static size_t sigframe_size(struct rt_sigframe_user_layout const *user) * not taken into account. This limit is not a guarantee and is * NOT ABI. */ -#define SIGFRAME_MAXSZ SZ_64K +#define SIGFRAME_MAXSZ SZ_256K static int __sigframe_alloc(struct rt_sigframe_user_layout *user, unsigned long *offset, size_t size, bool extend) @@ -310,7 +310,7 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user) fpsimd_flush_task_state(current); /* From now, fpsimd_thread_switch() won't touch thread.sve_state */ - sve_alloc(current); + sve_alloc(current, true); if (!current->thread.sve_state) { clear_thread_flag(TIF_SVE); return -ENOMEM; @@ -926,6 +926,16 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka, /* Signal handlers are invoked with ZA and streaming mode disabled */ if (system_supports_sme()) { + /* + * If we were in streaming mode the saved register + * state was SVE but we will exit SM and use the + * FPSIMD register state - flush the saved FPSIMD + * register state in case it gets loaded. + */ + if (current->thread.svcr & SVCR_SM_MASK) + memset(¤t->thread.uw.fpsimd_state, 0, + sizeof(current->thread.uw.fpsimd_state)); + current->thread.svcr &= ~(SVCR_ZA_MASK | SVCR_SM_MASK); sme_smstop(); diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 869ffc4d4484..ad2bfc794257 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -296,12 +296,25 @@ core_initcall(init_amu_fie); static void cpu_read_corecnt(void *val) { + /* + * A value of 0 can be returned if the current CPU does not support AMUs + * or if the counter is disabled for this CPU. A return value of 0 at + * counter read is properly handled as an error case by the users of the + * counter. + */ *(u64 *)val = read_corecnt(); } static void cpu_read_constcnt(void *val) { - *(u64 *)val = read_constcnt(); + /* + * Return 0 if the current CPU is affected by erratum 2457168. A value + * of 0 is also returned if the current CPU does not support AMUs or if + * the counter is disabled. A return value of 0 at counter read is + * properly handled as an error case by the users of the counter. + */ + *(u64 *)val = this_cpu_has_cap(ARM64_WORKAROUND_2457168) ? + 0UL : read_constcnt(); } static inline @@ -328,7 +341,22 @@ int counters_read_on_cpu(int cpu, smp_call_func_t func, u64 *val) */ bool cpc_ffh_supported(void) { - return freq_counters_valid(get_cpu_with_amu_feat()); + int cpu = get_cpu_with_amu_feat(); + + /* + * FFH is considered supported if there is at least one present CPU that + * supports AMUs. Using FFH to read core and reference counters for CPUs + * that do not support AMUs, have counters disabled or that are affected + * by errata, will result in a return value of 0. + * + * This is done to allow any enabled and valid counters to be read + * through FFH, knowing that potentially returning 0 as counter value is + * properly handled by the users of these counters. + */ + if ((cpu >= nr_cpu_ids) || !cpumask_test_cpu(cpu, cpu_present_mask)) + return false; + + return true; } int cpc_read_ffh(int cpu, struct cpc_reg *reg, u64 *val) diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index db7c4e6ae57b..e7ad44585f40 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -642,24 +642,6 @@ static void __init map_kernel_segment(pgd_t *pgdp, void *va_start, void *va_end, vm_area_add_early(vma); } -static int __init parse_rodata(char *arg) -{ - int ret = strtobool(arg, &rodata_enabled); - if (!ret) { - rodata_full = false; - return 0; - } - - /* permit 'full' in addition to boolean options */ - if (strcmp(arg, "full")) - return -EINVAL; - - rodata_enabled = true; - rodata_full = true; - return 0; -} -early_param("rodata", parse_rodata); - #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 static int __init map_entry_trampoline(void) { diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index 779653771507..63b2484ce6c3 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -67,6 +67,7 @@ WORKAROUND_1902691 WORKAROUND_2038923 WORKAROUND_2064142 WORKAROUND_2077057 +WORKAROUND_2457168 WORKAROUND_TRBE_OVERWRITE_FILL_MODE WORKAROUND_TSB_FLUSH_FAILURE WORKAROUND_TRBE_WRITE_OUT_OF_RANGE diff --git a/arch/hexagon/include/asm/bitops.h b/arch/hexagon/include/asm/bitops.h index da500471ac73..160d8f37fa1a 100644 --- a/arch/hexagon/include/asm/bitops.h +++ b/arch/hexagon/include/asm/bitops.h @@ -179,6 +179,21 @@ arch_test_bit(unsigned long nr, const volatile unsigned long *addr) return retval; } +static __always_inline bool +arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr) +{ + int retval; + + asm volatile( + "{P0 = tstbit(%1,%2); if (P0.new) %0 = #1; if (!P0.new) %0 = #0;}\n" + : "=&r" (retval) + : "r" (addr[BIT_WORD(nr)]), "r" (nr % BITS_PER_LONG) + : "p0", "memory" + ); + + return retval; +} + /* * ffz - find first zero in word. * @word: The word to search diff --git a/arch/ia64/include/asm/bitops.h b/arch/ia64/include/asm/bitops.h index 9f62af7fd7c4..1accb7842f58 100644 --- a/arch/ia64/include/asm/bitops.h +++ b/arch/ia64/include/asm/bitops.h @@ -331,11 +331,8 @@ arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr) return (old & bit) != 0; } -static __always_inline bool -arch_test_bit(unsigned long nr, const volatile unsigned long *addr) -{ - return 1 & (((const volatile __u32 *) addr)[nr >> 5] >> (nr & 31)); -} +#define arch_test_bit generic_test_bit +#define arch_test_bit_acquire generic_test_bit_acquire /** * ffz - find the first zero bit in a long word diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index 4abc9a28aba4..26aeb1408e56 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -111,6 +111,7 @@ config LOONGARCH select PCI_ECAM if ACPI select PCI_LOONGSON select PCI_MSI_ARCH_FALLBACKS + select PCI_QUIRKS select PERF_USE_VMALLOC select RTC_LIB select SMP diff --git a/arch/loongarch/include/asm/addrspace.h b/arch/loongarch/include/asm/addrspace.h index b91e0733b2e5..d342935e5a72 100644 --- a/arch/loongarch/include/asm/addrspace.h +++ b/arch/loongarch/include/asm/addrspace.h @@ -109,4 +109,20 @@ extern unsigned long vm_map_base; */ #define PHYSADDR(a) ((_ACAST64_(a)) & TO_PHYS_MASK) +/* + * On LoongArch, I/O ports mappring is following: + * + * | .... | + * |-----------------------| + * | pci io ports(16K~32M) | + * |-----------------------| + * | isa io ports(0 ~16K) | + * PCI_IOBASE ->|-----------------------| + * | .... | + */ +#define PCI_IOBASE ((void __iomem *)(vm_map_base + (2 * PAGE_SIZE))) +#define PCI_IOSIZE SZ_32M +#define ISA_IOSIZE SZ_16K +#define IO_SPACE_LIMIT (PCI_IOSIZE - 1) + #endif /* _ASM_ADDRSPACE_H */ diff --git a/arch/loongarch/include/asm/cmpxchg.h b/arch/loongarch/include/asm/cmpxchg.h index 0a9b0fac1eee..ae19e33c7754 100644 --- a/arch/loongarch/include/asm/cmpxchg.h +++ b/arch/loongarch/include/asm/cmpxchg.h @@ -5,8 +5,9 @@ #ifndef __ASM_CMPXCHG_H #define __ASM_CMPXCHG_H -#include <asm/barrier.h> +#include <linux/bits.h> #include <linux/build_bug.h> +#include <asm/barrier.h> #define __xchg_asm(amswap_db, m, val) \ ({ \ @@ -21,10 +22,53 @@ __ret; \ }) +static inline unsigned int __xchg_small(volatile void *ptr, unsigned int val, + unsigned int size) +{ + unsigned int shift; + u32 old32, mask, temp; + volatile u32 *ptr32; + + /* Mask value to the correct size. */ + mask = GENMASK((size * BITS_PER_BYTE) - 1, 0); + val &= mask; + + /* + * Calculate a shift & mask that correspond to the value we wish to + * exchange within the naturally aligned 4 byte integerthat includes + * it. + */ + shift = (unsigned long)ptr & 0x3; + shift *= BITS_PER_BYTE; + mask <<= shift; + + /* + * Calculate a pointer to the naturally aligned 4 byte integer that + * includes our byte of interest, and load its value. + */ + ptr32 = (volatile u32 *)((unsigned long)ptr & ~0x3); + + asm volatile ( + "1: ll.w %0, %3 \n" + " andn %1, %0, %z4 \n" + " or %1, %1, %z5 \n" + " sc.w %1, %2 \n" + " beqz %1, 1b \n" + : "=&r" (old32), "=&r" (temp), "=ZC" (*ptr32) + : "ZC" (*ptr32), "Jr" (mask), "Jr" (val << shift) + : "memory"); + + return (old32 & mask) >> shift; +} + static inline unsigned long __xchg(volatile void *ptr, unsigned long x, int size) { switch (size) { + case 1: + case 2: + return __xchg_small(ptr, x, size); + case 4: return __xchg_asm("amswap_db.w", (volatile u32 *)ptr, (u32)x); @@ -67,10 +111,62 @@ static inline unsigned long __xchg(volatile void *ptr, unsigned long x, __ret; \ }) +static inline unsigned int __cmpxchg_small(volatile void *ptr, unsigned int old, + unsigned int new, unsigned int size) +{ + unsigned int shift; + u32 old32, mask, temp; + volatile u32 *ptr32; + + /* Mask inputs to the correct size. */ + mask = GENMASK((size * BITS_PER_BYTE) - 1, 0); + old &= mask; + new &= mask; + + /* + * Calculate a shift & mask that correspond to the value we wish to + * compare & exchange within the naturally aligned 4 byte integer + * that includes it. + */ + shift = (unsigned long)ptr & 0x3; + shift *= BITS_PER_BYTE; + old <<= shift; + new <<= shift; + mask <<= shift; + + /* + * Calculate a pointer to the naturally aligned 4 byte integer that + * includes our byte of interest, and load its value. + */ + ptr32 = (volatile u32 *)((unsigned long)ptr & ~0x3); + + asm volatile ( + "1: ll.w %0, %3 \n" + " and %1, %0, %z4 \n" + " bne %1, %z5, 2f \n" + " andn %1, %0, %z4 \n" + " or %1, %1, %z6 \n" + " sc.w %1, %2 \n" + " beqz %1, 1b \n" + " b 3f \n" + "2: \n" + __WEAK_LLSC_MB + "3: \n" + : "=&r" (old32), "=&r" (temp), "=ZC" (*ptr32) + : "ZC" (*ptr32), "Jr" (mask), "Jr" (old), "Jr" (new) + : "memory"); + + return (old32 & mask) >> shift; +} + static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, unsigned int size) { switch (size) { + case 1: + case 2: + return __cmpxchg_small(ptr, old, new, size); + case 4: return __cmpxchg_asm("ll.w", "sc.w", (volatile u32 *)ptr, (u32)old, new); diff --git a/arch/loongarch/include/asm/io.h b/arch/loongarch/include/asm/io.h index 884599739b36..999944ea1cea 100644 --- a/arch/loongarch/include/asm/io.h +++ b/arch/loongarch/include/asm/io.h @@ -7,35 +7,16 @@ #define ARCH_HAS_IOREMAP_WC -#include <linux/compiler.h> #include <linux/kernel.h> #include <linux/types.h> #include <asm/addrspace.h> -#include <asm/bug.h> -#include <asm/byteorder.h> #include <asm/cpu.h> #include <asm/page.h> #include <asm/pgtable-bits.h> #include <asm/string.h> /* - * On LoongArch, I/O ports mappring is following: - * - * | .... | - * |-----------------------| - * | pci io ports(64K~32M) | - * |-----------------------| - * | isa io ports(0 ~16K) | - * PCI_IOBASE ->|-----------------------| - * | .... | - */ -#define PCI_IOBASE ((void __iomem *)(vm_map_base + (2 * PAGE_SIZE))) -#define PCI_IOSIZE SZ_32M -#define ISA_IOSIZE SZ_16K -#define IO_SPACE_LIMIT (PCI_IOSIZE - 1) - -/* * Change "struct page" to physical address. */ #define page_to_phys(page) ((phys_addr_t)page_to_pfn(page) << PAGE_SHIFT) diff --git a/arch/loongarch/include/asm/page.h b/arch/loongarch/include/asm/page.h index a37324ac460b..53f284a96182 100644 --- a/arch/loongarch/include/asm/page.h +++ b/arch/loongarch/include/asm/page.h @@ -95,7 +95,7 @@ static inline int pfn_valid(unsigned long pfn) #endif -#define virt_to_pfn(kaddr) PFN_DOWN(virt_to_phys((void *)(kaddr))) +#define virt_to_pfn(kaddr) PFN_DOWN(PHYSADDR(kaddr)) #define virt_to_page(kaddr) pfn_to_page(virt_to_pfn(kaddr)) extern int __virt_addr_valid(volatile void *kaddr); diff --git a/arch/loongarch/include/asm/percpu.h b/arch/loongarch/include/asm/percpu.h index e6569f18c6dd..0bd6b0110198 100644 --- a/arch/loongarch/include/asm/percpu.h +++ b/arch/loongarch/include/asm/percpu.h @@ -123,6 +123,10 @@ static inline unsigned long __percpu_xchg(void *ptr, unsigned long val, int size) { switch (size) { + case 1: + case 2: + return __xchg_small((volatile void *)ptr, val, size); + case 4: return __xchg_asm("amswap.w", (volatile u32 *)ptr, (u32)val); @@ -204,9 +208,13 @@ do { \ #define this_cpu_write_4(pcp, val) _percpu_write(pcp, val) #define this_cpu_write_8(pcp, val) _percpu_write(pcp, val) +#define this_cpu_xchg_1(pcp, val) _percpu_xchg(pcp, val) +#define this_cpu_xchg_2(pcp, val) _percpu_xchg(pcp, val) #define this_cpu_xchg_4(pcp, val) _percpu_xchg(pcp, val) #define this_cpu_xchg_8(pcp, val) _percpu_xchg(pcp, val) +#define this_cpu_cmpxchg_1(ptr, o, n) _protect_cmpxchg_local(ptr, o, n) +#define this_cpu_cmpxchg_2(ptr, o, n) _protect_cmpxchg_local(ptr, o, n) #define this_cpu_cmpxchg_4(ptr, o, n) _protect_cmpxchg_local(ptr, o, n) #define this_cpu_cmpxchg_8(ptr, o, n) _protect_cmpxchg_local(ptr, o, n) diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h index e03443abaf7d..8ea57e2f0e04 100644 --- a/arch/loongarch/include/asm/pgtable.h +++ b/arch/loongarch/include/asm/pgtable.h @@ -59,7 +59,6 @@ #include <linux/mm_types.h> #include <linux/mmzone.h> #include <asm/fixmap.h> -#include <asm/io.h> struct mm_struct; struct vm_area_struct; @@ -145,7 +144,7 @@ static inline void set_p4d(p4d_t *p4d, p4d_t p4dval) *p4d = p4dval; } -#define p4d_phys(p4d) virt_to_phys((void *)p4d_val(p4d)) +#define p4d_phys(p4d) PHYSADDR(p4d_val(p4d)) #define p4d_page(p4d) (pfn_to_page(p4d_phys(p4d) >> PAGE_SHIFT)) #endif @@ -188,7 +187,7 @@ static inline pmd_t *pud_pgtable(pud_t pud) #define set_pud(pudptr, pudval) do { *(pudptr) = (pudval); } while (0) -#define pud_phys(pud) virt_to_phys((void *)pud_val(pud)) +#define pud_phys(pud) PHYSADDR(pud_val(pud)) #define pud_page(pud) (pfn_to_page(pud_phys(pud) >> PAGE_SHIFT)) #endif @@ -221,7 +220,7 @@ static inline void pmd_clear(pmd_t *pmdp) #define set_pmd(pmdptr, pmdval) do { *(pmdptr) = (pmdval); } while (0) -#define pmd_phys(pmd) virt_to_phys((void *)pmd_val(pmd)) +#define pmd_phys(pmd) PHYSADDR(pmd_val(pmd)) #ifndef CONFIG_TRANSPARENT_HUGEPAGE #define pmd_page(pmd) (pfn_to_page(pmd_phys(pmd) >> PAGE_SHIFT)) diff --git a/arch/loongarch/include/asm/reboot.h b/arch/loongarch/include/asm/reboot.h deleted file mode 100644 index 51151749d8f0..000000000000 --- a/arch/loongarch/include/asm/reboot.h +++ /dev/null @@ -1,10 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C) 2020-2022 Loongson Technology Corporation Limited - */ -#ifndef _ASM_REBOOT_H -#define _ASM_REBOOT_H - -extern void (*pm_restart)(void); - -#endif /* _ASM_REBOOT_H */ diff --git a/arch/loongarch/kernel/reset.c b/arch/loongarch/kernel/reset.c index 800c965a17ea..8c82021eb2f4 100644 --- a/arch/loongarch/kernel/reset.c +++ b/arch/loongarch/kernel/reset.c @@ -15,10 +15,16 @@ #include <acpi/reboot.h> #include <asm/idle.h> #include <asm/loongarch.h> -#include <asm/reboot.h> -static void default_halt(void) +void (*pm_power_off)(void); +EXPORT_SYMBOL(pm_power_off); + +void machine_halt(void) { +#ifdef CONFIG_SMP + preempt_disable(); + smp_send_stop(); +#endif local_irq_disable(); clear_csr_ecfg(ECFG0_IM); @@ -30,18 +36,29 @@ static void default_halt(void) } } -static void default_poweroff(void) +void machine_power_off(void) { +#ifdef CONFIG_SMP + preempt_disable(); + smp_send_stop(); +#endif + do_kernel_power_off(); #ifdef CONFIG_EFI efi.reset_system(EFI_RESET_SHUTDOWN, EFI_SUCCESS, 0, NULL); #endif + while (true) { __arch_cpu_idle(); } } -static void default_restart(void) +void machine_restart(char *command) { +#ifdef CONFIG_SMP + preempt_disable(); + smp_send_stop(); +#endif + do_kernel_restart(command); #ifdef CONFIG_EFI if (efi_capsule_pending(NULL)) efi_reboot(REBOOT_WARM, NULL); @@ -55,47 +72,3 @@ static void default_restart(void) __arch_cpu_idle(); } } - -void (*pm_restart)(void); -EXPORT_SYMBOL(pm_restart); - -void (*pm_power_off)(void); -EXPORT_SYMBOL(pm_power_off); - -void machine_halt(void) -{ -#ifdef CONFIG_SMP - preempt_disable(); - smp_send_stop(); -#endif - default_halt(); -} - -void machine_power_off(void) -{ -#ifdef CONFIG_SMP - preempt_disable(); - smp_send_stop(); -#endif - pm_power_off(); -} - -void machine_restart(char *command) -{ -#ifdef CONFIG_SMP - preempt_disable(); - smp_send_stop(); -#endif - do_kernel_restart(command); - pm_restart(); -} - -static int __init loongarch_reboot_setup(void) -{ - pm_restart = default_restart; - pm_power_off = default_poweroff; - - return 0; -} - -arch_initcall(loongarch_reboot_setup); diff --git a/arch/loongarch/mm/fault.c b/arch/loongarch/mm/fault.c index 605579b19a00..1ccd53655cab 100644 --- a/arch/loongarch/mm/fault.c +++ b/arch/loongarch/mm/fault.c @@ -216,6 +216,10 @@ good_area: return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_RETRY)) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/loongarch/mm/mmap.c b/arch/loongarch/mm/mmap.c index 52e40f0ba732..381a569635a9 100644 --- a/arch/loongarch/mm/mmap.c +++ b/arch/loongarch/mm/mmap.c @@ -2,16 +2,9 @@ /* * Copyright (C) 2020-2022 Loongson Technology Corporation Limited */ -#include <linux/compiler.h> -#include <linux/elf-randomize.h> -#include <linux/errno.h> +#include <linux/export.h> #include <linux/mm.h> #include <linux/mman.h> -#include <linux/export.h> -#include <linux/personality.h> -#include <linux/random.h> -#include <linux/sched/signal.h> -#include <linux/sched/mm.h> unsigned long shm_align_mask = PAGE_SIZE - 1; /* Sane caches */ EXPORT_SYMBOL(shm_align_mask); @@ -120,6 +113,6 @@ int __virt_addr_valid(volatile void *kaddr) if ((vaddr < PAGE_OFFSET) || (vaddr >= vm_map_base)) return 0; - return pfn_valid(PFN_DOWN(virt_to_phys(kaddr))); + return pfn_valid(PFN_DOWN(PHYSADDR(kaddr))); } EXPORT_SYMBOL_GPL(__virt_addr_valid); diff --git a/arch/loongarch/vdso/vgetcpu.c b/arch/loongarch/vdso/vgetcpu.c index 43a0078e4418..e02e775f5360 100644 --- a/arch/loongarch/vdso/vgetcpu.c +++ b/arch/loongarch/vdso/vgetcpu.c @@ -24,6 +24,8 @@ static __always_inline const struct vdso_pcpu_data *get_pcpu_data(void) return (struct vdso_pcpu_data *)(get_vdso_base() - VDSO_DATA_SIZE); } +extern +int __vdso_getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *unused); int __vdso_getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *unused) { int cpu_id; diff --git a/arch/loongarch/vdso/vgettimeofday.c b/arch/loongarch/vdso/vgettimeofday.c index b1f4548dae92..8f22863bd7ea 100644 --- a/arch/loongarch/vdso/vgettimeofday.c +++ b/arch/loongarch/vdso/vgettimeofday.c @@ -6,20 +6,23 @@ */ #include <linux/types.h> -int __vdso_clock_gettime(clockid_t clock, - struct __kernel_timespec *ts) +extern +int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts); +int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts) { return __cvdso_clock_gettime(clock, ts); } -int __vdso_gettimeofday(struct __kernel_old_timeval *tv, - struct timezone *tz) +extern +int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz); +int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz) { return __cvdso_gettimeofday(tv, tz); } -int __vdso_clock_getres(clockid_t clock_id, - struct __kernel_timespec *res) +extern +int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res); +int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res) { return __cvdso_clock_getres(clock_id, res); } diff --git a/arch/m68k/include/asm/bitops.h b/arch/m68k/include/asm/bitops.h index 470aed978590..e984af71df6b 100644 --- a/arch/m68k/include/asm/bitops.h +++ b/arch/m68k/include/asm/bitops.h @@ -157,11 +157,8 @@ arch___change_bit(unsigned long nr, volatile unsigned long *addr) change_bit(nr, addr); } -static __always_inline bool -arch_test_bit(unsigned long nr, const volatile unsigned long *addr) -{ - return (addr[nr >> 5] & (1UL << (nr & 31))) != 0; -} +#define arch_test_bit generic_test_bit +#define arch_test_bit_acquire generic_test_bit_acquire static inline int bset_reg_test_and_set_bit(int nr, volatile unsigned long *vaddr) diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 7f059cd1196a..9aede2447011 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -146,10 +146,10 @@ menu "Processor type and features" choice prompt "Processor type" - default PA7000 + default PA7000 if "$(ARCH)" = "parisc" config PA7000 - bool "PA7000/PA7100" + bool "PA7000/PA7100" if "$(ARCH)" = "parisc" help This is the processor type of your CPU. This information is used for optimizing purposes. In order to compile a kernel @@ -160,21 +160,21 @@ config PA7000 which is required on some machines. config PA7100LC - bool "PA7100LC" + bool "PA7100LC" if "$(ARCH)" = "parisc" help Select this option for the PCX-L processor, as used in the 712, 715/64, 715/80, 715/100, 715/100XC, 725/100, 743, 748, D200, D210, D300, D310 and E-class config PA7200 - bool "PA7200" + bool "PA7200" if "$(ARCH)" = "parisc" help Select this option for the PCX-T' processor, as used in the C100, C110, J100, J110, J210XC, D250, D260, D350, D360, K100, K200, K210, K220, K400, K410 and K420 config PA7300LC - bool "PA7300LC" + bool "PA7300LC" if "$(ARCH)" = "parisc" help Select this option for the PCX-L2 processor, as used in the 744, A180, B132L, B160L, B180L, C132L, C160L, C180L, @@ -224,17 +224,8 @@ config MLONGCALLS Enabling this option will probably slow down your kernel. config 64BIT - bool "64-bit kernel" + def_bool "$(ARCH)" = "parisc64" depends on PA8X00 - help - Enable this if you want to support 64bit kernel on PA-RISC platform. - - At the moment, only people willing to use more than 2GB of RAM, - or having a 64bit-only capable PA-RISC machine should say Y here. - - Since there is no 64bit userland on PA-RISC, there is no point to - enable this option otherwise. The 64bit kernel is significantly bigger - and slower than the 32bit one. choice prompt "Kernel page size" diff --git a/arch/parisc/include/asm/bitops.h b/arch/parisc/include/asm/bitops.h index 56ffd260c669..0ec9cfc5131f 100644 --- a/arch/parisc/include/asm/bitops.h +++ b/arch/parisc/include/asm/bitops.h @@ -12,14 +12,6 @@ #include <asm/barrier.h> #include <linux/atomic.h> -/* compiler build environment sanity checks: */ -#if !defined(CONFIG_64BIT) && defined(__LP64__) -#error "Please use 'ARCH=parisc' to build the 32-bit kernel." -#endif -#if defined(CONFIG_64BIT) && !defined(__LP64__) -#error "Please use 'ARCH=parisc64' to build the 64-bit kernel." -#endif - /* See http://marc.theaimsgroup.com/?t=108826637900003 for discussion * on use of volatile and __*_bit() (set/clear/change): * *_bit() want use of volatile. diff --git a/arch/parisc/kernel/head.S b/arch/parisc/kernel/head.S index e0a9e9657622..fd15fd4bbb61 100644 --- a/arch/parisc/kernel/head.S +++ b/arch/parisc/kernel/head.S @@ -22,7 +22,7 @@ #include <linux/init.h> #include <linux/pgtable.h> - .level PA_ASM_LEVEL + .level 1.1 __INITDATA ENTRY(boot_args) @@ -70,6 +70,47 @@ $bss_loop: stw,ma %arg2,4(%r1) stw,ma %arg3,4(%r1) +#if !defined(CONFIG_64BIT) && defined(CONFIG_PA20) + /* This 32-bit kernel was compiled for PA2.0 CPUs. Check current CPU + * and halt kernel if we detect a PA1.x CPU. */ + ldi 32,%r10 + mtctl %r10,%cr11 + .level 2.0 + mfctl,w %cr11,%r10 + .level 1.1 + comib,<>,n 0,%r10,$cpu_ok + + load32 PA(msg1),%arg0 + ldi msg1_end-msg1,%arg1 +$iodc_panic: + copy %arg0, %r10 + copy %arg1, %r11 + load32 PA(init_stack),%sp +#define MEM_CONS 0x3A0 + ldw MEM_CONS+32(%r0),%arg0 // HPA + ldi ENTRY_IO_COUT,%arg1 + ldw MEM_CONS+36(%r0),%arg2 // SPA + ldw MEM_CONS+8(%r0),%arg3 // layers + load32 PA(__bss_start),%r1 + stw %r1,-52(%sp) // arg4 + stw %r0,-56(%sp) // arg5 + stw %r10,-60(%sp) // arg6 = ptr to text + stw %r11,-64(%sp) // arg7 = len + stw %r0,-68(%sp) // arg8 + load32 PA(.iodc_panic_ret), %rp + ldw MEM_CONS+40(%r0),%r1 // ENTRY_IODC + bv,n (%r1) +.iodc_panic_ret: + b . /* wait endless with ... */ + or %r10,%r10,%r10 /* qemu idle sleep */ +msg1: .ascii "Can't boot kernel which was built for PA8x00 CPUs on this machine.\r\n" +msg1_end: + +$cpu_ok: +#endif + + .level PA_ASM_LEVEL + /* Initialize startup VM. Just map first 16/32 MB of memory */ load32 PA(swapper_pg_dir),%r4 mtctl %r4,%cr24 /* Initialize kernel root pointer */ diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c index bac581b5ecfc..e8a4d77cff53 100644 --- a/arch/parisc/kernel/unaligned.c +++ b/arch/parisc/kernel/unaligned.c @@ -93,7 +93,7 @@ #define R1(i) (((i)>>21)&0x1f) #define R2(i) (((i)>>16)&0x1f) #define R3(i) ((i)&0x1f) -#define FR3(i) ((((i)<<1)&0x1f)|(((i)>>6)&1)) +#define FR3(i) ((((i)&0x1f)<<1)|(((i)>>6)&1)) #define IM(i,n) (((i)>>1&((1<<(n-1))-1))|((i)&1?((0-1L)<<(n-1)):0)) #define IM5_2(i) IM((i)>>16,5) #define IM5_3(i) IM((i),5) diff --git a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts index 044982a11df5..f3f87ed2007f 100644 --- a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts +++ b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts @@ -84,12 +84,10 @@ phy1: ethernet-phy@9 { reg = <9>; - ti,fifo-depth = <0x1>; }; phy0: ethernet-phy@8 { reg = <8>; - ti,fifo-depth = <0x1>; }; }; @@ -102,7 +100,6 @@ disable-wp; cap-sd-highspeed; cap-mmc-highspeed; - card-detect-delay = <200>; mmc-ddr-1_8v; mmc-hs200-1_8v; sd-uhs-sdr12; diff --git a/arch/riscv/boot/dts/microchip/mpfs-polarberry.dts b/arch/riscv/boot/dts/microchip/mpfs-polarberry.dts index 82c93c8f5c17..c87cc2d8fe29 100644 --- a/arch/riscv/boot/dts/microchip/mpfs-polarberry.dts +++ b/arch/riscv/boot/dts/microchip/mpfs-polarberry.dts @@ -54,12 +54,10 @@ phy1: ethernet-phy@5 { reg = <5>; - ti,fifo-depth = <0x01>; }; phy0: ethernet-phy@4 { reg = <4>; - ti,fifo-depth = <0x01>; }; }; @@ -72,7 +70,6 @@ disable-wp; cap-sd-highspeed; cap-mmc-highspeed; - card-detect-delay = <200>; mmc-ddr-1_8v; mmc-hs200-1_8v; sd-uhs-sdr12; diff --git a/arch/riscv/boot/dts/microchip/mpfs.dtsi b/arch/riscv/boot/dts/microchip/mpfs.dtsi index 499c2e63ad35..74493344ea41 100644 --- a/arch/riscv/boot/dts/microchip/mpfs.dtsi +++ b/arch/riscv/boot/dts/microchip/mpfs.dtsi @@ -193,7 +193,7 @@ cache-size = <2097152>; cache-unified; interrupt-parent = <&plic>; - interrupts = <1>, <2>, <3>; + interrupts = <1>, <3>, <4>, <2>; }; clint: clint@2000000 { @@ -485,9 +485,8 @@ ranges = <0x3000000 0x0 0x8000000 0x20 0x8000000 0x0 0x80000000>; msi-parent = <&pcie>; msi-controller; - microchip,axi-m-atr0 = <0x10 0x0>; status = "disabled"; - pcie_intc: legacy-interrupt-controller { + pcie_intc: interrupt-controller { #address-cells = <0>; #interrupt-cells = <1>; interrupt-controller; diff --git a/arch/riscv/include/asm/signal.h b/arch/riscv/include/asm/signal.h new file mode 100644 index 000000000000..532c29ef0376 --- /dev/null +++ b/arch/riscv/include/asm/signal.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __ASM_SIGNAL_H +#define __ASM_SIGNAL_H + +#include <uapi/asm/signal.h> +#include <uapi/asm/ptrace.h> + +asmlinkage __visible +void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags); + +#endif diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h index 78933ac04995..67322f878e0d 100644 --- a/arch/riscv/include/asm/thread_info.h +++ b/arch/riscv/include/asm/thread_info.h @@ -42,6 +42,8 @@ #ifndef __ASSEMBLY__ +extern long shadow_stack[SHADOW_OVERFLOW_STACK_SIZE / sizeof(long)]; + #include <asm/processor.h> #include <asm/csr.h> diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c index 38b05ca6fe66..5a2de6b6f882 100644 --- a/arch/riscv/kernel/signal.c +++ b/arch/riscv/kernel/signal.c @@ -15,6 +15,7 @@ #include <asm/ucontext.h> #include <asm/vdso.h> +#include <asm/signal.h> #include <asm/signal32.h> #include <asm/switch_to.h> #include <asm/csr.h> diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 39d0f8bba4b4..635e6ec26938 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -20,9 +20,10 @@ #include <asm/asm-prototypes.h> #include <asm/bug.h> +#include <asm/csr.h> #include <asm/processor.h> #include <asm/ptrace.h> -#include <asm/csr.h> +#include <asm/thread_info.h> int show_unhandled_signals = 1; diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h index 9a7d15da966e..2de74fcd0578 100644 --- a/arch/s390/include/asm/bitops.h +++ b/arch/s390/include/asm/bitops.h @@ -176,14 +176,8 @@ arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr) return old & mask; } -static __always_inline bool -arch_test_bit(unsigned long nr, const volatile unsigned long *addr) -{ - const volatile unsigned long *p = __bitops_word(nr, addr); - unsigned long mask = __bitops_mask(nr); - - return *p & mask; -} +#define arch_test_bit generic_test_bit +#define arch_test_bit_acquire generic_test_bit_acquire static inline bool arch_test_and_set_bit_lock(unsigned long nr, volatile unsigned long *ptr) diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 89949b9f3cf8..d5119e039d85 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -91,6 +91,18 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) memcpy(dst, src, arch_task_struct_size); dst->thread.fpu.regs = dst->thread.fpu.fprs; + + /* + * Don't transfer over the runtime instrumentation or the guarded + * storage control block pointers. These fields are cleared here instead + * of in copy_thread() to avoid premature freeing of associated memory + * on fork() failure. Wait to clear the RI flag because ->stack still + * refers to the source thread. + */ + dst->thread.ri_cb = NULL; + dst->thread.gs_cb = NULL; + dst->thread.gs_bc_cb = NULL; + return 0; } @@ -150,13 +162,11 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) frame->childregs.flags = 0; if (new_stackp) frame->childregs.gprs[15] = new_stackp; - - /* Don't copy runtime instrumentation info */ - p->thread.ri_cb = NULL; + /* + * Clear the runtime instrumentation flag after the above childregs + * copy. The CB pointer was already cleared in arch_dup_task_struct(). + */ frame->childregs.psw.mask &= ~PSW_MASK_RI; - /* Don't copy guarded storage control block */ - p->thread.gs_cb = NULL; - p->thread.gs_bc_cb = NULL; /* Set a new TLS ? */ if (clone_flags & CLONE_SETTLS) { diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 13449941516c..09b6e756d521 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -379,7 +379,9 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access) flags = FAULT_FLAG_DEFAULT; if (user_mode(regs)) flags |= FAULT_FLAG_USER; - if (access == VM_WRITE || is_write) + if (is_write) + access = VM_WRITE; + if (access == VM_WRITE) flags |= FAULT_FLAG_WRITE; mmap_read_lock(mm); diff --git a/arch/sh/include/asm/bitops-op32.h b/arch/sh/include/asm/bitops-op32.h index 565a85d8b7fb..5ace89b46507 100644 --- a/arch/sh/include/asm/bitops-op32.h +++ b/arch/sh/include/asm/bitops-op32.h @@ -135,16 +135,8 @@ arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr) return (old & mask) != 0; } -/** - * arch_test_bit - Determine whether a bit is set - * @nr: bit number to test - * @addr: Address to start counting from - */ -static __always_inline bool -arch_test_bit(unsigned long nr, const volatile unsigned long *addr) -{ - return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1))); -} +#define arch_test_bit generic_test_bit +#define arch_test_bit_acquire generic_test_bit_acquire #include <asm-generic/bitops/non-instrumented-non-atomic.h> diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 4910bf230d7b..62208ec04ca4 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -132,7 +132,17 @@ void snp_set_page_private(unsigned long paddr); void snp_set_page_shared(unsigned long paddr); void sev_prep_identity_maps(unsigned long top_level_pgt); #else -static inline void sev_enable(struct boot_params *bp) { } +static inline void sev_enable(struct boot_params *bp) +{ + /* + * bp->cc_blob_address should only be set by boot/compressed kernel. + * Initialize it to 0 unconditionally (thus here in this stub too) to + * ensure that uninitialized values from buggy bootloaders aren't + * propagated. + */ + if (bp) + bp->cc_blob_address = 0; +} static inline void sev_es_shutdown_ghcb(void) { } static inline bool sev_es_check_ghcb_fault(unsigned long address) { diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index 52f989f6acc2..c93930d5ccbd 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -277,6 +277,14 @@ void sev_enable(struct boot_params *bp) bool snp; /* + * bp->cc_blob_address should only be set by boot/compressed kernel. + * Initialize it to 0 to ensure that uninitialized values from + * buggy bootloaders aren't propagated. + */ + if (bp) + bp->cc_blob_address = 0; + + /* * Setup/preliminary detection of SNP. This will be sanity-checked * against CPUID/MSR values later. */ diff --git a/arch/x86/configs/xen.config b/arch/x86/configs/xen.config index d9fc7139fd46..581296255b39 100644 --- a/arch/x86/configs/xen.config +++ b/arch/x86/configs/xen.config @@ -14,7 +14,6 @@ CONFIG_CPU_FREQ=y # x86 xen specific config options CONFIG_XEN_PVH=y -CONFIG_XEN_MAX_DOMAIN_MEMORY=500 CONFIG_XEN_SAVE_RESTORE=y # CONFIG_XEN_DEBUG_FS is not set CONFIG_XEN_MCE_LOG=y diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 682338e7e2a3..4dd19819053a 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -311,7 +311,7 @@ SYM_CODE_START(entry_INT80_compat) * Interrupts are off on entry. */ ASM_CLAC /* Do this early to minimize exposure */ - SWAPGS + ALTERNATIVE "swapgs", "", X86_FEATURE_XENPV /* * User tracing code (ptrace or signal handlers) might assume that diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 2db93498ff71..cb98a05ee743 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -6291,10 +6291,8 @@ __init int intel_pmu_init(void) x86_pmu.pebs_aliases = NULL; x86_pmu.pebs_prec_dist = true; x86_pmu.pebs_block = true; - x86_pmu.pebs_capable = ~0ULL; x86_pmu.flags |= PMU_FL_HAS_RSP_1; x86_pmu.flags |= PMU_FL_NO_HT_SHARING; - x86_pmu.flags |= PMU_FL_PEBS_ALL; x86_pmu.flags |= PMU_FL_INSTR_LATENCY; x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX; @@ -6337,10 +6335,8 @@ __init int intel_pmu_init(void) x86_pmu.pebs_aliases = NULL; x86_pmu.pebs_prec_dist = true; x86_pmu.pebs_block = true; - x86_pmu.pebs_capable = ~0ULL; x86_pmu.flags |= PMU_FL_HAS_RSP_1; x86_pmu.flags |= PMU_FL_NO_HT_SHARING; - x86_pmu.flags |= PMU_FL_PEBS_ALL; x86_pmu.flags |= PMU_FL_INSTR_LATENCY; x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX; x86_pmu.lbr_pt_coexist = true; diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index ba60427caa6d..de1f55d51784 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -291,6 +291,7 @@ static u64 load_latency_data(struct perf_event *event, u64 status) static u64 store_latency_data(struct perf_event *event, u64 status) { union intel_x86_pebs_dse dse; + union perf_mem_data_src src; u64 val; dse.val = status; @@ -304,7 +305,14 @@ static u64 store_latency_data(struct perf_event *event, u64 status) val |= P(BLK, NA); - return val; + /* + * the pebs_data_source table is only for loads + * so override the mem_op to say STORE instead + */ + src.val = val; + src.mem_op = P(OP,STORE); + + return src.val; } struct pebs_record_core { @@ -822,7 +830,7 @@ struct event_constraint intel_glm_pebs_event_constraints[] = { struct event_constraint intel_grt_pebs_event_constraints[] = { /* Allow all events as PEBS with no flags */ - INTEL_HYBRID_LAT_CONSTRAINT(0x5d0, 0xf), + INTEL_HYBRID_LAT_CONSTRAINT(0x5d0, 0x3), INTEL_HYBRID_LAT_CONSTRAINT(0x6d0, 0xf), EVENT_CONSTRAINT_END }; @@ -2262,6 +2270,7 @@ void __init intel_ds_init(void) PERF_SAMPLE_BRANCH_STACK | PERF_SAMPLE_TIME; x86_pmu.flags |= PMU_FL_PEBS_ALL; + x86_pmu.pebs_capable = ~0ULL; pebs_qual = "-baseline"; x86_get_pmu(smp_processor_id())->capabilities |= PERF_PMU_CAP_EXTENDED_REGS; } else { diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 4f70fb6c2c1e..47fca6a7a8bc 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -1097,6 +1097,14 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event) if (static_cpu_has(X86_FEATURE_ARCH_LBR)) { reg->config = mask; + + /* + * The Arch LBR HW can retrieve the common branch types + * from the LBR_INFO. It doesn't require the high overhead + * SW disassemble. + * Enable the branch type by default for the Arch LBR. + */ + reg->reg |= X86_BR_TYPE_SAVE; return 0; } diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index ce440011cc4e..1ef4f7861e2e 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -841,6 +841,22 @@ int snb_pci2phy_map_init(int devid) return 0; } +static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + /* + * SNB IMC counters are 32-bit and are laid out back to back + * in MMIO space. Therefore we must use a 32-bit accessor function + * using readq() from uncore_mmio_read_counter() causes problems + * because it is reading 64-bit at a time. This is okay for the + * uncore_perf_event_update() function because it drops the upper + * 32-bits but not okay for plain uncore_read_counter() as invoked + * in uncore_pmu_event_start(). + */ + return (u64)readl(box->io_addr + hwc->event_base); +} + static struct pmu snb_uncore_imc_pmu = { .task_ctx_nr = perf_invalid_context, .event_init = snb_uncore_imc_event_init, @@ -860,7 +876,7 @@ static struct intel_uncore_ops snb_uncore_imc_ops = { .disable_event = snb_uncore_imc_disable_event, .enable_event = snb_uncore_imc_enable_event, .hw_config = snb_uncore_imc_hw_config, - .read_counter = uncore_mmio_read_counter, + .read_counter = snb_uncore_imc_read_counter, }; static struct intel_uncore_type snb_uncore_imc = { diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 973c6bd17f98..0fe9de58af31 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -207,6 +207,20 @@ static __always_inline bool constant_test_bit(long nr, const volatile unsigned l (addr[nr >> _BITOPS_LONG_SHIFT])) != 0; } +static __always_inline bool constant_test_bit_acquire(long nr, const volatile unsigned long *addr) +{ + bool oldbit; + + asm volatile("testb %2,%1" + CC_SET(nz) + : CC_OUT(nz) (oldbit) + : "m" (((unsigned char *)addr)[nr >> 3]), + "i" (1 << (nr & 7)) + :"memory"); + + return oldbit; +} + static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr) { bool oldbit; @@ -226,6 +240,13 @@ arch_test_bit(unsigned long nr, const volatile unsigned long *addr) variable_test_bit(nr, addr); } +static __always_inline bool +arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr) +{ + return __builtin_constant_p(nr) ? constant_test_bit_acquire(nr, addr) : + variable_test_bit(nr, addr); +} + /** * __ffs - find first set bit in word * @word: The word to search diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 235dc85c91c3..ef4775c6db01 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -457,7 +457,8 @@ #define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */ #define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */ #define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */ -#define X86_BUG_RETBLEED X86_BUG(26) /* CPU is affected by RETBleed */ -#define X86_BUG_EIBRS_PBRSB X86_BUG(27) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ +#define X86_BUG_MMIO_UNKNOWN X86_BUG(26) /* CPU is too old and its MMIO Stale Data status is unknown */ +#define X86_BUG_RETBLEED X86_BUG(27) /* CPU is affected by RETBleed */ +#define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index def6ca121111..aeb38023a703 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -27,6 +27,7 @@ * _X - regular server parts * _D - micro server parts * _N,_P - other mobile parts + * _S - other client parts * * Historical OPTDIFFs: * @@ -112,6 +113,7 @@ #define INTEL_FAM6_RAPTORLAKE 0xB7 #define INTEL_FAM6_RAPTORLAKE_P 0xBA +#define INTEL_FAM6_RAPTORLAKE_S 0xBF /* "Small Core" Processors (Atom) */ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index e64fd20778b6..c936ce9f0c47 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -35,33 +35,56 @@ #define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ /* + * Common helper for __FILL_RETURN_BUFFER and __FILL_ONE_RETURN. + */ +#define __FILL_RETURN_SLOT \ + ANNOTATE_INTRA_FUNCTION_CALL; \ + call 772f; \ + int3; \ +772: + +/* + * Stuff the entire RSB. + * * Google experimented with loop-unrolling and this turned out to be * the optimal version - two calls, each with their own speculation * trap should their return address end up getting used, in a loop. */ -#define __FILL_RETURN_BUFFER(reg, nr, sp) \ - mov $(nr/2), reg; \ -771: \ - ANNOTATE_INTRA_FUNCTION_CALL; \ - call 772f; \ -773: /* speculation trap */ \ - UNWIND_HINT_EMPTY; \ - pause; \ - lfence; \ - jmp 773b; \ -772: \ - ANNOTATE_INTRA_FUNCTION_CALL; \ - call 774f; \ -775: /* speculation trap */ \ - UNWIND_HINT_EMPTY; \ - pause; \ - lfence; \ - jmp 775b; \ -774: \ - add $(BITS_PER_LONG/8) * 2, sp; \ - dec reg; \ - jnz 771b; \ - /* barrier for jnz misprediction */ \ +#ifdef CONFIG_X86_64 +#define __FILL_RETURN_BUFFER(reg, nr) \ + mov $(nr/2), reg; \ +771: \ + __FILL_RETURN_SLOT \ + __FILL_RETURN_SLOT \ + add $(BITS_PER_LONG/8) * 2, %_ASM_SP; \ + dec reg; \ + jnz 771b; \ + /* barrier for jnz misprediction */ \ + lfence; +#else +/* + * i386 doesn't unconditionally have LFENCE, as such it can't + * do a loop. + */ +#define __FILL_RETURN_BUFFER(reg, nr) \ + .rept nr; \ + __FILL_RETURN_SLOT; \ + .endr; \ + add $(BITS_PER_LONG/8) * nr, %_ASM_SP; +#endif + +/* + * Stuff a single RSB slot. + * + * To mitigate Post-Barrier RSB speculation, one CALL instruction must be + * forced to retire before letting a RET instruction execute. + * + * On PBRSB-vulnerable CPUs, it is not safe for a RET to be executed + * before this point. + */ +#define __FILL_ONE_RETURN \ + __FILL_RETURN_SLOT \ + add $(BITS_PER_LONG/8), %_ASM_SP; \ lfence; #ifdef __ASSEMBLY__ @@ -132,28 +155,15 @@ #endif .endm -.macro ISSUE_UNBALANCED_RET_GUARD - ANNOTATE_INTRA_FUNCTION_CALL - call .Lunbalanced_ret_guard_\@ - int3 -.Lunbalanced_ret_guard_\@: - add $(BITS_PER_LONG/8), %_ASM_SP - lfence -.endm - /* * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP * monstrosity above, manually. */ -.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req ftr2 -.ifb \ftr2 - ALTERNATIVE "jmp .Lskip_rsb_\@", "", \ftr -.else - ALTERNATIVE_2 "jmp .Lskip_rsb_\@", "", \ftr, "jmp .Lunbalanced_\@", \ftr2 -.endif - __FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP) -.Lunbalanced_\@: - ISSUE_UNBALANCED_RET_GUARD +.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req ftr2=ALT_NOT(X86_FEATURE_ALWAYS) + ALTERNATIVE_2 "jmp .Lskip_rsb_\@", \ + __stringify(__FILL_RETURN_BUFFER(\reg,\nr)), \ftr, \ + __stringify(__FILL_ONE_RETURN), \ftr2 + .Lskip_rsb_\@: .endm diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index 4a23e52fe0ee..ebc271bb6d8e 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -195,7 +195,7 @@ void snp_set_memory_shared(unsigned long vaddr, unsigned int npages); void snp_set_memory_private(unsigned long vaddr, unsigned int npages); void snp_set_wakeup_secondary_cpu(void); bool snp_init(struct boot_params *bp); -void snp_abort(void); +void __init __noreturn snp_abort(void); int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, unsigned long *fw_err); #else static inline void sev_es_ist_enter(struct pt_regs *regs) { } diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 510d85261132..da7c361f47e0 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -433,7 +433,8 @@ static void __init mmio_select_mitigation(void) u64 ia32_cap; if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA) || - cpu_mitigations_off()) { + boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN) || + cpu_mitigations_off()) { mmio_mitigation = MMIO_MITIGATION_OFF; return; } @@ -538,6 +539,8 @@ out: pr_info("TAA: %s\n", taa_strings[taa_mitigation]); if (boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) pr_info("MMIO Stale Data: %s\n", mmio_strings[mmio_mitigation]); + else if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN)) + pr_info("MMIO Stale Data: Unknown: No mitigations\n"); } static void __init md_clear_select_mitigation(void) @@ -2275,6 +2278,9 @@ static ssize_t tsx_async_abort_show_state(char *buf) static ssize_t mmio_stale_data_show_state(char *buf) { + if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN)) + return sysfs_emit(buf, "Unknown: No mitigations\n"); + if (mmio_mitigation == MMIO_MITIGATION_OFF) return sysfs_emit(buf, "%s\n", mmio_strings[mmio_mitigation]); @@ -2421,6 +2427,7 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr return srbds_show_state(buf); case X86_BUG_MMIO_STALE_DATA: + case X86_BUG_MMIO_UNKNOWN: return mmio_stale_data_show_state(buf); case X86_BUG_RETBLEED: @@ -2480,7 +2487,10 @@ ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, char * ssize_t cpu_show_mmio_stale_data(struct device *dev, struct device_attribute *attr, char *buf) { - return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_STALE_DATA); + if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN)) + return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_UNKNOWN); + else + return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_STALE_DATA); } ssize_t cpu_show_retbleed(struct device *dev, struct device_attribute *attr, char *buf) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 64a73f415f03..3e508f239098 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1135,7 +1135,8 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) #define NO_SWAPGS BIT(6) #define NO_ITLB_MULTIHIT BIT(7) #define NO_SPECTRE_V2 BIT(8) -#define NO_EIBRS_PBRSB BIT(9) +#define NO_MMIO BIT(9) +#define NO_EIBRS_PBRSB BIT(10) #define VULNWL(vendor, family, model, whitelist) \ X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, whitelist) @@ -1158,6 +1159,11 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { VULNWL(VORTEX, 6, X86_MODEL_ANY, NO_SPECULATION), /* Intel Family 6 */ + VULNWL_INTEL(TIGERLAKE, NO_MMIO), + VULNWL_INTEL(TIGERLAKE_L, NO_MMIO), + VULNWL_INTEL(ALDERLAKE, NO_MMIO), + VULNWL_INTEL(ALDERLAKE_L, NO_MMIO), + VULNWL_INTEL(ATOM_SALTWELL, NO_SPECULATION | NO_ITLB_MULTIHIT), VULNWL_INTEL(ATOM_SALTWELL_TABLET, NO_SPECULATION | NO_ITLB_MULTIHIT), VULNWL_INTEL(ATOM_SALTWELL_MID, NO_SPECULATION | NO_ITLB_MULTIHIT), @@ -1176,9 +1182,9 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), VULNWL_INTEL(ATOM_AIRMONT_NP, NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_INTEL(ATOM_GOLDMONT_D, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB), + VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_INTEL(ATOM_GOLDMONT_D, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB), /* * Technically, swapgs isn't serializing on AMD (despite it previously @@ -1193,18 +1199,18 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { VULNWL_INTEL(ATOM_TREMONT_D, NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB), /* AMD Family 0xf - 0x12 */ - VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), /* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */ - VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), /* Zhaoxin Family 7 */ - VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS), - VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS), + VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO), + VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO), {} }; @@ -1358,10 +1364,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) * Affected CPU list is generally enough to enumerate the vulnerability, * but for virtualization case check for ARCH_CAP MSR bits also, VMM may * not want the guest to enumerate the bug. + * + * Set X86_BUG_MMIO_UNKNOWN for CPUs that are neither in the blacklist, + * nor in the whitelist and also don't enumerate MSR ARCH_CAP MMIO bits. */ - if (cpu_matches(cpu_vuln_blacklist, MMIO) && - !arch_cap_mmio_immune(ia32_cap)) - setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA); + if (!arch_cap_mmio_immune(ia32_cap)) { + if (cpu_matches(cpu_vuln_blacklist, MMIO)) + setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA); + else if (!cpu_matches(cpu_vuln_whitelist, NO_MMIO)) + setup_force_cpu_bug(X86_BUG_MMIO_UNKNOWN); + } if (!cpu_has(c, X86_FEATURE_BTC_NO)) { if (cpu_matches(cpu_vuln_blacklist, RETBLEED) || (ia32_cap & ARCH_CAP_RSBA)) diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index 63dc626627a0..a428c62330d3 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -701,7 +701,13 @@ e_term: void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, unsigned int npages) { - if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + /* + * This can be invoked in early boot while running identity mapped, so + * use an open coded check for SNP instead of using cc_platform_has(). + * This eliminates worries about jump tables or checking boot_cpu_data + * in the cc_platform_has() function. + */ + if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) return; /* @@ -717,7 +723,13 @@ void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long padd void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, unsigned int npages) { - if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + /* + * This can be invoked in early boot while running identity mapped, so + * use an open coded check for SNP instead of using cc_platform_has(). + * This eliminates worries about jump tables or checking boot_cpu_data + * in the cc_platform_has() function. + */ + if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) return; /* Invalidate the memory pages before they are marked shared in the RMP table. */ @@ -2100,7 +2112,7 @@ bool __init snp_init(struct boot_params *bp) return true; } -void __init snp_abort(void) +void __init __noreturn snp_abort(void) { sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); } diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 38185aedf7d1..0ea57da92940 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -93,22 +93,27 @@ static struct orc_entry *orc_find(unsigned long ip); static struct orc_entry *orc_ftrace_find(unsigned long ip) { struct ftrace_ops *ops; - unsigned long caller; + unsigned long tramp_addr, offset; ops = ftrace_ops_trampoline(ip); if (!ops) return NULL; + /* Set tramp_addr to the start of the code copied by the trampoline */ if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) - caller = (unsigned long)ftrace_regs_call; + tramp_addr = (unsigned long)ftrace_regs_caller; else - caller = (unsigned long)ftrace_call; + tramp_addr = (unsigned long)ftrace_caller; + + /* Now place tramp_addr to the location within the trampoline ip is at */ + offset = ip - ops->trampoline; + tramp_addr += offset; /* Prevent unlikely recursion */ - if (ip == caller) + if (ip == tramp_addr) return NULL; - return orc_find(caller); + return orc_find(tramp_addr); } #else static struct orc_entry *orc_ftrace_find(unsigned long ip) diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index d5ef64ddd35e..66a209f7eb86 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -62,6 +62,7 @@ static bool __read_mostly pat_bp_initialized; static bool __read_mostly pat_disabled = !IS_ENABLED(CONFIG_X86_PAT); +static bool __initdata pat_force_disabled = !IS_ENABLED(CONFIG_X86_PAT); static bool __read_mostly pat_bp_enabled; static bool __read_mostly pat_cm_initialized; @@ -86,6 +87,7 @@ void pat_disable(const char *msg_reason) static int __init nopat(char *str) { pat_disable("PAT support disabled via boot option."); + pat_force_disabled = true; return 0; } early_param("nopat", nopat); @@ -272,7 +274,7 @@ static void pat_ap_init(u64 pat) wrmsrl(MSR_IA32_CR_PAT, pat); } -void init_cache_modes(void) +void __init init_cache_modes(void) { u64 pat = 0; @@ -313,6 +315,12 @@ void init_cache_modes(void) */ pat = PAT(0, WB) | PAT(1, WT) | PAT(2, UC_MINUS) | PAT(3, UC) | PAT(4, WB) | PAT(5, WT) | PAT(6, UC_MINUS) | PAT(7, UC); + } else if (!pat_force_disabled && cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) { + /* + * Clearly PAT is enabled underneath. Allow pat_enabled() to + * reflect this. + */ + pat_bp_enabled = true; } __init_cache_modes(pat); diff --git a/block/blk-mq.c b/block/blk-mq.c index 3c1e6b6d991d..c96c8c4f751b 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1931,7 +1931,8 @@ out: /* If we didn't flush the entire list, we could have told the driver * there was more coming, but that turned out to be a lie. */ - if ((!list_empty(list) || errors) && q->mq_ops->commit_rqs && queued) + if ((!list_empty(list) || errors || needs_resource || + ret == BLK_STS_DEV_RESOURCE) && q->mq_ops->commit_rqs && queued) q->mq_ops->commit_rqs(hctx); /* * Any items that need requeuing? Stuff them into hctx->dispatch, @@ -2660,6 +2661,7 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, list_del_init(&rq->queuelist); ret = blk_mq_request_issue_directly(rq, list_empty(list)); if (ret != BLK_STS_OK) { + errors++; if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) { blk_mq_request_bypass_insert(rq, false, @@ -2667,7 +2669,6 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, break; } blk_mq_end_request(rq, ret); - errors++; } else queued++; } diff --git a/drivers/acpi/processor_thermal.c b/drivers/acpi/processor_thermal.c index db6ac540e924..e534fd49a67e 100644 --- a/drivers/acpi/processor_thermal.c +++ b/drivers/acpi/processor_thermal.c @@ -151,7 +151,7 @@ void acpi_thermal_cpufreq_exit(struct cpufreq_policy *policy) unsigned int cpu; for_each_cpu(cpu, policy->related_cpus) { - struct acpi_processor *pr = per_cpu(processors, policy->cpu); + struct acpi_processor *pr = per_cpu(processors, cpu); if (pr) freq_qos_remove_request(&pr->thermal_req); diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c index 7b3ad8ed2f4e..d4c168ce428c 100644 --- a/drivers/acpi/property.c +++ b/drivers/acpi/property.c @@ -370,7 +370,7 @@ static bool acpi_tie_nondev_subnodes(struct acpi_device_data *data) bool ret; status = acpi_attach_data(dn->handle, acpi_nondev_subnode_tag, dn); - if (ACPI_FAILURE(status)) { + if (ACPI_FAILURE(status) && status != AE_ALREADY_EXISTS) { acpi_handle_err(dn->handle, "Can't tag data node\n"); return false; } @@ -1043,11 +1043,10 @@ static int acpi_data_prop_read_single(const struct acpi_device_data *data, break; \ } \ if (__items[i].integer.value > _Generic(__val, \ - u8: U8_MAX, \ - u16: U16_MAX, \ - u32: U32_MAX, \ - u64: U64_MAX, \ - default: 0U)) { \ + u8 *: U8_MAX, \ + u16 *: U16_MAX, \ + u32 *: U32_MAX, \ + u64 *: U64_MAX)) { \ ret = -EOVERFLOW; \ break; \ } \ diff --git a/drivers/block/loop.c b/drivers/block/loop.c index e3c0ba93c1a3..ad92192c7d61 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -979,6 +979,11 @@ loop_set_status_from_info(struct loop_device *lo, lo->lo_offset = info->lo_offset; lo->lo_sizelimit = info->lo_sizelimit; + + /* loff_t vars have been assigned __u64 */ + if (lo->lo_offset < 0 || lo->lo_sizelimit < 0) + return -EOVERFLOW; + memcpy(lo->lo_file_name, info->lo_file_name, LO_NAME_SIZE); lo->lo_file_name[LO_NAME_SIZE-1] = 0; lo->lo_flags = info->lo_flags; diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 92cb929a45b7..226ea76cc819 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1146,14 +1146,15 @@ static ssize_t bd_stat_show(struct device *dev, static ssize_t debug_stat_show(struct device *dev, struct device_attribute *attr, char *buf) { - int version = 2; + int version = 1; struct zram *zram = dev_to_zram(dev); ssize_t ret; down_read(&zram->init_lock); ret = scnprintf(buf, PAGE_SIZE, - "version: %d\n%8llu\n", + "version: %d\n%8llu %8llu\n", version, + (u64)atomic64_read(&zram->stats.writestall), (u64)atomic64_read(&zram->stats.miss_free)); up_read(&zram->init_lock); @@ -1351,7 +1352,7 @@ static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec, { int ret = 0; unsigned long alloced_pages; - unsigned long handle = 0; + unsigned long handle = -ENOMEM; unsigned int comp_len = 0; void *src, *dst, *mem; struct zcomp_strm *zstrm; @@ -1369,6 +1370,7 @@ static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec, } kunmap_atomic(mem); +compress_again: zstrm = zcomp_stream_get(zram->comp); src = kmap_atomic(page); ret = zcomp_compress(zstrm, src, &comp_len); @@ -1377,20 +1379,39 @@ static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec, if (unlikely(ret)) { zcomp_stream_put(zram->comp); pr_err("Compression failed! err=%d\n", ret); + zs_free(zram->mem_pool, handle); return ret; } if (comp_len >= huge_class_size) comp_len = PAGE_SIZE; - - handle = zs_malloc(zram->mem_pool, comp_len, - __GFP_KSWAPD_RECLAIM | - __GFP_NOWARN | - __GFP_HIGHMEM | - __GFP_MOVABLE); - + /* + * handle allocation has 2 paths: + * a) fast path is executed with preemption disabled (for + * per-cpu streams) and has __GFP_DIRECT_RECLAIM bit clear, + * since we can't sleep; + * b) slow path enables preemption and attempts to allocate + * the page with __GFP_DIRECT_RECLAIM bit set. we have to + * put per-cpu compression stream and, thus, to re-do + * the compression once handle is allocated. + * + * if we have a 'non-null' handle here then we are coming + * from the slow path and handle has already been allocated. + */ + if (IS_ERR((void *)handle)) + handle = zs_malloc(zram->mem_pool, comp_len, + __GFP_KSWAPD_RECLAIM | + __GFP_NOWARN | + __GFP_HIGHMEM | + __GFP_MOVABLE); if (IS_ERR((void *)handle)) { zcomp_stream_put(zram->comp); + atomic64_inc(&zram->stats.writestall); + handle = zs_malloc(zram->mem_pool, comp_len, + GFP_NOIO | __GFP_HIGHMEM | + __GFP_MOVABLE); + if (!IS_ERR((void *)handle)) + goto compress_again; return PTR_ERR((void *)handle); } @@ -1948,6 +1969,7 @@ static int zram_add(void) if (ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE) blk_queue_max_write_zeroes_sectors(zram->disk->queue, UINT_MAX); + blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, zram->disk->queue); ret = device_add_disk(NULL, zram->disk, zram_disk_groups); if (ret) goto out_cleanup_disk; diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index 158c91e54850..80c3b43b4828 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -81,6 +81,7 @@ struct zram_stats { atomic64_t huge_pages_since; /* no. of huge pages since zram set up */ atomic64_t pages_stored; /* no. of pages currently stored */ atomic_long_t max_used_pages; /* no. of maximum pages stored */ + atomic64_t writestall; /* no. of write slow paths */ atomic64_t miss_free; /* no. of missed free */ #ifdef CONFIG_ZRAM_WRITEBACK atomic64_t bd_count; /* no. of pages in backing device */ diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 7820c4e74289..69b3d61852ac 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -532,7 +532,7 @@ static unsigned int __resolve_freq(struct cpufreq_policy *policy, target_freq = clamp_val(target_freq, policy->min, policy->max); - if (!cpufreq_driver->target_index) + if (!policy->freq_table) return target_freq; idx = cpufreq_frequency_table_target(policy, target_freq, relation); diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c index f191a1f901ac..0eb6b617f709 100644 --- a/drivers/firmware/dmi_scan.c +++ b/drivers/firmware/dmi_scan.c @@ -630,7 +630,7 @@ static int __init dmi_smbios3_present(const u8 *buf) { if (memcmp(buf, "_SM3_", 5) == 0 && buf[6] < 32 && dmi_checksum(buf, buf[6])) { - dmi_ver = get_unaligned_be32(buf + 6) & 0xFFFFFF; + dmi_ver = get_unaligned_be24(buf + 7); dmi_num = 0; /* No longer specified */ dmi_len = get_unaligned_le32(buf + 12); dmi_base = get_unaligned_le64(buf + 16); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index e8a0b19b7398..f095a2513aff 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2456,12 +2456,14 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev) if (!hive->reset_domain || !amdgpu_reset_get_reset_domain(hive->reset_domain)) { r = -ENOENT; + amdgpu_put_xgmi_hive(hive); goto init_failed; } /* Drop the early temporary reset domain we created for device */ amdgpu_reset_put_reset_domain(adev->reset_domain); adev->reset_domain = hive->reset_domain; + amdgpu_put_xgmi_hive(hive); } } @@ -4413,8 +4415,6 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev, retry: amdgpu_amdkfd_pre_reset(adev); - amdgpu_amdkfd_pre_reset(adev); - if (from_hypervisor) r = amdgpu_virt_request_full_gpu(adev, true); else diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index b067ce45d226..1036446abc30 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -2641,6 +2641,9 @@ static int psp_hw_fini(void *handle) psp_rap_terminate(psp); psp_dtm_terminate(psp); psp_hdcp_terminate(psp); + + if (adev->gmc.xgmi.num_physical_nodes > 1) + psp_xgmi_terminate(psp); } psp_asd_terminate(psp); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c index 1b108d03e785..f2aebbf3fbe3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c @@ -742,7 +742,7 @@ int amdgpu_xgmi_remove_device(struct amdgpu_device *adev) amdgpu_put_xgmi_hive(hive); } - return psp_xgmi_terminate(&adev->psp); + return 0; } static int amdgpu_xgmi_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *ras_block) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index 158d87e6805d..f6b1bb40e503 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -131,6 +131,8 @@ static void gfx_v11_0_ring_invalidate_tlbs(struct amdgpu_ring *ring, bool all_hub, uint8_t dst_sel); static void gfx_v11_0_set_safe_mode(struct amdgpu_device *adev); static void gfx_v11_0_unset_safe_mode(struct amdgpu_device *adev); +static void gfx_v11_0_update_perf_clk(struct amdgpu_device *adev, + bool enable); static void gfx11_kiq_set_resources(struct amdgpu_ring *kiq_ring, uint64_t queue_mask) { @@ -1139,6 +1141,7 @@ static const struct amdgpu_gfx_funcs gfx_v11_0_gfx_funcs = { .read_wave_vgprs = &gfx_v11_0_read_wave_vgprs, .select_me_pipe_q = &gfx_v11_0_select_me_pipe_q, .init_spm_golden = &gfx_v11_0_init_spm_golden_registers, + .update_perfmon_mgcg = &gfx_v11_0_update_perf_clk, }; static int gfx_v11_0_gpu_early_init(struct amdgpu_device *adev) @@ -5182,9 +5185,12 @@ static void gfx_v11_0_update_coarse_grain_clock_gating(struct amdgpu_device *ade data = REG_SET_FIELD(data, SDMA0_RLC_CGCG_CTRL, CGCG_INT_ENABLE, 1); WREG32_SOC15(GC, 0, regSDMA0_RLC_CGCG_CTRL, data); - data = RREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL); - data = REG_SET_FIELD(data, SDMA1_RLC_CGCG_CTRL, CGCG_INT_ENABLE, 1); - WREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL, data); + /* Some ASICs only have one SDMA instance, not need to configure SDMA1 */ + if (adev->sdma.num_instances > 1) { + data = RREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL); + data = REG_SET_FIELD(data, SDMA1_RLC_CGCG_CTRL, CGCG_INT_ENABLE, 1); + WREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL, data); + } } else { /* Program RLC_CGCG_CGLS_CTRL */ def = data = RREG32_SOC15(GC, 0, regRLC_CGCG_CGLS_CTRL); @@ -5213,9 +5219,12 @@ static void gfx_v11_0_update_coarse_grain_clock_gating(struct amdgpu_device *ade data &= ~SDMA0_RLC_CGCG_CTRL__CGCG_INT_ENABLE_MASK; WREG32_SOC15(GC, 0, regSDMA0_RLC_CGCG_CTRL, data); - data = RREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL); - data &= ~SDMA1_RLC_CGCG_CTRL__CGCG_INT_ENABLE_MASK; - WREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL, data); + /* Some ASICs only have one SDMA instance, not need to configure SDMA1 */ + if (adev->sdma.num_instances > 1) { + data = RREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL); + data &= ~SDMA1_RLC_CGCG_CTRL__CGCG_INT_ENABLE_MASK; + WREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL, data); + } } } @@ -5328,8 +5337,7 @@ static int gfx_v11_0_set_powergating_state(void *handle, break; case IP_VERSION(11, 0, 1): gfx_v11_cntl_pg(adev, enable); - /* TODO: Enable this when GFXOFF is ready */ - // amdgpu_gfx_off_ctrl(adev, enable); + amdgpu_gfx_off_ctrl(adev, enable); break; default: break; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index c6e0f9313a7f..fc9c1043244c 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -2587,7 +2587,8 @@ static void gfx_v9_0_constants_init(struct amdgpu_device *adev) gfx_v9_0_tiling_mode_table_init(adev); - gfx_v9_0_setup_rb(adev); + if (adev->gfx.num_gfx_rings) + gfx_v9_0_setup_rb(adev); gfx_v9_0_get_cu_info(adev, &adev->gfx.cu_info); adev->gfx.config.db_debug2 = RREG32_SOC15(GC, 0, mmDB_DEBUG2); diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c index 3f44a099c52a..3e51e773f92b 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c @@ -176,6 +176,7 @@ static void mmhub_v1_0_init_cache_regs(struct amdgpu_device *adev) tmp = REG_SET_FIELD(tmp, VM_L2_CNTL2, INVALIDATE_L2_CACHE, 1); WREG32_SOC15(MMHUB, 0, mmVM_L2_CNTL2, tmp); + tmp = mmVM_L2_CNTL3_DEFAULT; if (adev->gmc.translate_further) { tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3, BANK_SELECT, 12); tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3, diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c index 6e0145b2b408..445cb06b9d26 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c @@ -295,9 +295,17 @@ static void mmhub_v9_4_disable_identity_aperture(struct amdgpu_device *adev, static void mmhub_v9_4_setup_vmid_config(struct amdgpu_device *adev, int hubid) { struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_MMHUB_0]; + unsigned int num_level, block_size; uint32_t tmp; int i; + num_level = adev->vm_manager.num_level; + block_size = adev->vm_manager.block_size; + if (adev->gmc.translate_further) + num_level -= 1; + else + block_size -= 9; + for (i = 0; i <= 14; i++) { tmp = RREG32_SOC15_OFFSET(MMHUB, 0, mmVML2VC0_VM_CONTEXT1_CNTL, hubid * MMHUB_INSTANCE_REGISTER_OFFSET + i); @@ -305,7 +313,7 @@ static void mmhub_v9_4_setup_vmid_config(struct amdgpu_device *adev, int hubid) ENABLE_CONTEXT, 1); tmp = REG_SET_FIELD(tmp, VML2VC0_VM_CONTEXT1_CNTL, PAGE_TABLE_DEPTH, - adev->vm_manager.num_level); + num_level); tmp = REG_SET_FIELD(tmp, VML2VC0_VM_CONTEXT1_CNTL, RANGE_PROTECTION_FAULT_ENABLE_DEFAULT, 1); tmp = REG_SET_FIELD(tmp, VML2VC0_VM_CONTEXT1_CNTL, @@ -323,7 +331,7 @@ static void mmhub_v9_4_setup_vmid_config(struct amdgpu_device *adev, int hubid) EXECUTE_PROTECTION_FAULT_ENABLE_DEFAULT, 1); tmp = REG_SET_FIELD(tmp, VML2VC0_VM_CONTEXT1_CNTL, PAGE_TABLE_BLOCK_SIZE, - adev->vm_manager.block_size - 9); + block_size); /* Send no-retry XNACK on fault to suppress VM fault storm. */ tmp = REG_SET_FIELD(tmp, VML2VC0_VM_CONTEXT1_CNTL, RETRY_PERMISSION_OR_INVALID_PAGE_FAULT, diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c index 01e8288d09a8..1dc95ef21da6 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c @@ -247,6 +247,81 @@ static void nbio_v7_7_init_registers(struct amdgpu_device *adev) } +static void nbio_v7_7_update_medium_grain_clock_gating(struct amdgpu_device *adev, + bool enable) +{ + uint32_t def, data; + + if (enable && !(adev->cg_flags & AMD_CG_SUPPORT_BIF_MGCG)) + return; + + def = data = RREG32_SOC15(NBIO, 0, regBIF0_CPM_CONTROL); + if (enable) { + data |= (BIF0_CPM_CONTROL__LCLK_DYN_GATE_ENABLE_MASK | + BIF0_CPM_CONTROL__TXCLK_DYN_GATE_ENABLE_MASK | + BIF0_CPM_CONTROL__TXCLK_LCNT_GATE_ENABLE_MASK | + BIF0_CPM_CONTROL__TXCLK_REGS_GATE_ENABLE_MASK | + BIF0_CPM_CONTROL__TXCLK_PRBS_GATE_ENABLE_MASK | + BIF0_CPM_CONTROL__REFCLK_REGS_GATE_ENABLE_MASK); + } else { + data &= ~(BIF0_CPM_CONTROL__LCLK_DYN_GATE_ENABLE_MASK | + BIF0_CPM_CONTROL__TXCLK_DYN_GATE_ENABLE_MASK | + BIF0_CPM_CONTROL__TXCLK_LCNT_GATE_ENABLE_MASK | + BIF0_CPM_CONTROL__TXCLK_REGS_GATE_ENABLE_MASK | + BIF0_CPM_CONTROL__TXCLK_PRBS_GATE_ENABLE_MASK | + BIF0_CPM_CONTROL__REFCLK_REGS_GATE_ENABLE_MASK); + } + + if (def != data) + WREG32_SOC15(NBIO, 0, regBIF0_CPM_CONTROL, data); +} + +static void nbio_v7_7_update_medium_grain_light_sleep(struct amdgpu_device *adev, + bool enable) +{ + uint32_t def, data; + + if (enable && !(adev->cg_flags & AMD_CG_SUPPORT_BIF_LS)) + return; + + def = data = RREG32_SOC15(NBIO, 0, regBIF0_PCIE_CNTL2); + if (enable) + data |= BIF0_PCIE_CNTL2__SLV_MEM_LS_EN_MASK; + else + data &= ~BIF0_PCIE_CNTL2__SLV_MEM_LS_EN_MASK; + + if (def != data) + WREG32_SOC15(NBIO, 0, regBIF0_PCIE_CNTL2, data); + + def = data = RREG32_SOC15(NBIO, 0, regBIF0_PCIE_TX_POWER_CTRL_1); + if (enable) { + data |= (BIF0_PCIE_TX_POWER_CTRL_1__MST_MEM_LS_EN_MASK | + BIF0_PCIE_TX_POWER_CTRL_1__REPLAY_MEM_LS_EN_MASK); + } else { + data &= ~(BIF0_PCIE_TX_POWER_CTRL_1__MST_MEM_LS_EN_MASK | + BIF0_PCIE_TX_POWER_CTRL_1__REPLAY_MEM_LS_EN_MASK); + } + + if (def != data) + WREG32_SOC15(NBIO, 0, regBIF0_PCIE_TX_POWER_CTRL_1, data); +} + +static void nbio_v7_7_get_clockgating_state(struct amdgpu_device *adev, + u64 *flags) +{ + uint32_t data; + + /* AMD_CG_SUPPORT_BIF_MGCG */ + data = RREG32_SOC15(NBIO, 0, regBIF0_CPM_CONTROL); + if (data & BIF0_CPM_CONTROL__LCLK_DYN_GATE_ENABLE_MASK) + *flags |= AMD_CG_SUPPORT_BIF_MGCG; + + /* AMD_CG_SUPPORT_BIF_LS */ + data = RREG32_SOC15(NBIO, 0, regBIF0_PCIE_CNTL2); + if (data & BIF0_PCIE_CNTL2__SLV_MEM_LS_EN_MASK) + *flags |= AMD_CG_SUPPORT_BIF_LS; +} + const struct amdgpu_nbio_funcs nbio_v7_7_funcs = { .get_hdp_flush_req_offset = nbio_v7_7_get_hdp_flush_req_offset, .get_hdp_flush_done_offset = nbio_v7_7_get_hdp_flush_done_offset, @@ -262,6 +337,9 @@ const struct amdgpu_nbio_funcs nbio_v7_7_funcs = { .enable_doorbell_aperture = nbio_v7_7_enable_doorbell_aperture, .enable_doorbell_selfring_aperture = nbio_v7_7_enable_doorbell_selfring_aperture, .ih_doorbell_range = nbio_v7_7_ih_doorbell_range, + .update_medium_grain_clock_gating = nbio_v7_7_update_medium_grain_clock_gating, + .update_medium_grain_light_sleep = nbio_v7_7_update_medium_grain_light_sleep, + .get_clockgating_state = nbio_v7_7_get_clockgating_state, .ih_control = nbio_v7_7_ih_control, .init_registers = nbio_v7_7_init_registers, }; diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c index 1ff7fc7bb340..55284b24f113 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc21.c +++ b/drivers/gpu/drm/amd/amdgpu/soc21.c @@ -494,6 +494,20 @@ static void soc21_pre_asic_init(struct amdgpu_device *adev) { } +static int soc21_update_umd_stable_pstate(struct amdgpu_device *adev, + bool enter) +{ + if (enter) + amdgpu_gfx_rlc_enter_safe_mode(adev); + else + amdgpu_gfx_rlc_exit_safe_mode(adev); + + if (adev->gfx.funcs->update_perfmon_mgcg) + adev->gfx.funcs->update_perfmon_mgcg(adev, !enter); + + return 0; +} + static const struct amdgpu_asic_funcs soc21_asic_funcs = { .read_disabled_bios = &soc21_read_disabled_bios, @@ -513,6 +527,7 @@ static const struct amdgpu_asic_funcs soc21_asic_funcs = .supports_baco = &amdgpu_dpm_is_baco_supported, .pre_asic_init = &soc21_pre_asic_init, .query_video_codecs = &soc21_query_video_codecs, + .update_umd_stable_pstate = &soc21_update_umd_stable_pstate, }; static int soc21_common_early_init(void *handle) @@ -603,6 +618,8 @@ static int soc21_common_early_init(void *handle) AMD_CG_SUPPORT_ATHUB_MGCG | AMD_CG_SUPPORT_ATHUB_LS | AMD_CG_SUPPORT_IH_CG | + AMD_CG_SUPPORT_BIF_MGCG | + AMD_CG_SUPPORT_BIF_LS | AMD_CG_SUPPORT_VCN_MGCG | AMD_CG_SUPPORT_JPEG_MGCG; adev->pg_flags = @@ -702,6 +719,7 @@ static int soc21_common_set_clockgating_state(void *handle, switch (adev->ip_versions[NBIO_HWIP][0]) { case IP_VERSION(4, 3, 0): case IP_VERSION(4, 3, 1): + case IP_VERSION(7, 7, 0): adev->nbio.funcs->update_medium_grain_clock_gating(adev, state == AMD_CG_STATE_GATE); adev->nbio.funcs->update_medium_grain_light_sleep(adev, @@ -709,10 +727,6 @@ static int soc21_common_set_clockgating_state(void *handle, adev->hdp.funcs->update_clock_gating(adev, state == AMD_CG_STATE_GATE); break; - case IP_VERSION(7, 7, 0): - adev->hdp.funcs->update_clock_gating(adev, - state == AMD_CG_STATE_GATE); - break; default: break; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 357298e69495..22c0929d410b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -382,12 +382,8 @@ struct kfd_dev *kgd2kfd_probe(struct amdgpu_device *adev, bool vf) f2g = &gfx_v10_3_kfd2kgd; break; case IP_VERSION(10, 3, 6): - gfx_target_version = 100306; - if (!vf) - f2g = &gfx_v10_3_kfd2kgd; - break; case IP_VERSION(10, 3, 7): - gfx_target_version = 100307; + gfx_target_version = 100306; if (!vf) f2g = &gfx_v10_3_kfd2kgd; break; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c index fca7cf9dbaee..987bde4dca3d 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c @@ -34,6 +34,7 @@ #include "dal_asic_id.h" #include "amdgpu_display.h" #include "amdgpu_dm_trace.h" +#include "amdgpu_dm_plane.h" #include "gc/gc_11_0_0_offset.h" #include "gc/gc_11_0_0_sh_mask.h" @@ -149,12 +150,12 @@ static void add_modifier(uint64_t **mods, uint64_t *size, uint64_t *cap, uint64_ *size += 1; } -bool modifier_has_dcc(uint64_t modifier) +static bool modifier_has_dcc(uint64_t modifier) { return IS_AMD_FMT_MOD(modifier) && AMD_FMT_MOD_GET(DCC, modifier); } -unsigned modifier_gfx9_swizzle_mode(uint64_t modifier) +static unsigned modifier_gfx9_swizzle_mode(uint64_t modifier) { if (modifier == DRM_FORMAT_MOD_LINEAR) return 0; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.h index 95168c2cfa6f..286981a2dd40 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.h @@ -36,17 +36,9 @@ int fill_dc_scaling_info(struct amdgpu_device *adev, const struct drm_plane_state *state, struct dc_scaling_info *scaling_info); -void get_min_max_dc_plane_scaling(struct drm_device *dev, - struct drm_framebuffer *fb, - int *min_downscale, int *max_upscale); - int dm_plane_helper_check_state(struct drm_plane_state *state, struct drm_crtc_state *new_crtc_state); -bool modifier_has_dcc(uint64_t modifier); - -unsigned int modifier_gfx9_swizzle_mode(uint64_t modifier); - int fill_plane_buffer_attributes(struct amdgpu_device *adev, const struct amdgpu_framebuffer *afb, const enum surface_pixel_format format, diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c index 85f32206a766..3a9e3870b3a9 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c @@ -1750,6 +1750,7 @@ static bool dcn314_resource_construct( dc->caps.post_blend_color_processing = true; dc->caps.force_dp_tps4_for_cp2520 = true; dc->caps.dp_hpo = true; + dc->caps.dp_hdmi21_pcon_support = true; dc->caps.edp_dsc_support = true; dc->caps.extended_aux_timeout_support = true; dc->caps.dmcub_support = true; diff --git a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_7_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_7_0_offset.h index 2ed95790a600..cf8d60c4df1b 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_7_0_offset.h +++ b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_7_0_offset.h @@ -15243,6 +15243,8 @@ #define regBIF0_PCIE_TX_TRACKING_ADDR_HI_BASE_IDX 5 #define regBIF0_PCIE_TX_TRACKING_CTRL_STATUS 0x420186 #define regBIF0_PCIE_TX_TRACKING_CTRL_STATUS_BASE_IDX 5 +#define regBIF0_PCIE_TX_POWER_CTRL_1 0x420187 +#define regBIF0_PCIE_TX_POWER_CTRL_1_BASE_IDX 5 #define regBIF0_PCIE_TX_CTRL_4 0x42018b #define regBIF0_PCIE_TX_CTRL_4_BASE_IDX 5 #define regBIF0_PCIE_TX_STATUS 0x420194 diff --git a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_7_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_7_0_sh_mask.h index eb62a18fcc48..3d60c9e92548 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_7_0_sh_mask.h +++ b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_7_0_sh_mask.h @@ -85627,6 +85627,19 @@ #define BIF0_PCIE_TX_TRACKING_CTRL_STATUS__TX_TRACKING_PORT_MASK 0x0000000EL #define BIF0_PCIE_TX_TRACKING_CTRL_STATUS__TX_TRACKING_UNIT_ID_MASK 0x00007F00L #define BIF0_PCIE_TX_TRACKING_CTRL_STATUS__TX_TRACKING_STATUS_VALID_MASK 0x00008000L +//BIF0_PCIE_TX_POWER_CTRL_1 +#define BIF0_PCIE_TX_POWER_CTRL_1__MST_MEM_LS_EN__SHIFT 0x0 +#define BIF0_PCIE_TX_POWER_CTRL_1__MST_MEM_DS_EN__SHIFT 0x1 +#define BIF0_PCIE_TX_POWER_CTRL_1__MST_MEM_SD_EN__SHIFT 0x2 +#define BIF0_PCIE_TX_POWER_CTRL_1__REPLAY_MEM_LS_EN__SHIFT 0x3 +#define BIF0_PCIE_TX_POWER_CTRL_1__REPLAY_MEM_DS_EN__SHIFT 0x4 +#define BIF0_PCIE_TX_POWER_CTRL_1__REPLAY_MEM_SD_EN__SHIFT 0x5 +#define BIF0_PCIE_TX_POWER_CTRL_1__MST_MEM_LS_EN_MASK 0x00000001L +#define BIF0_PCIE_TX_POWER_CTRL_1__MST_MEM_DS_EN_MASK 0x00000002L +#define BIF0_PCIE_TX_POWER_CTRL_1__MST_MEM_SD_EN_MASK 0x00000004L +#define BIF0_PCIE_TX_POWER_CTRL_1__REPLAY_MEM_LS_EN_MASK 0x00000008L +#define BIF0_PCIE_TX_POWER_CTRL_1__REPLAY_MEM_DS_EN_MASK 0x00000010L +#define BIF0_PCIE_TX_POWER_CTRL_1__REPLAY_MEM_SD_EN_MASK 0x00000020L //BIF0_PCIE_TX_CTRL_4 #define BIF0_PCIE_TX_CTRL_4__TX_PORT_ACCESS_TIMER_SKEW__SHIFT 0x0 #define BIF0_PCIE_TX_CTRL_4__TX_PORT_ACCESS_TIMER_SKEW_MASK 0x0000000FL diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h index 78620b0bd279..f745cd8f1ab7 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h @@ -24,12 +24,8 @@ #ifndef SMU13_DRIVER_IF_V13_0_0_H #define SMU13_DRIVER_IF_V13_0_0_H -// *** IMPORTANT *** -// PMFW TEAM: Always increment the interface version on any change to this file -#define SMU13_DRIVER_IF_VERSION 0x23 - //Increment this version if SkuTable_t or BoardTable_t change -#define PPTABLE_VERSION 0x1D +#define PPTABLE_VERSION 0x22 #define NUM_GFXCLK_DPM_LEVELS 16 #define NUM_SOCCLK_DPM_LEVELS 8 @@ -1193,8 +1189,17 @@ typedef struct { // SECTION: Advanced Options uint32_t DebugOverrides; + // Section: Total Board Power idle vs active coefficients + uint8_t TotalBoardPowerSupport; + uint8_t TotalBoardPowerPadding[3]; + + int16_t TotalIdleBoardPowerM; + int16_t TotalIdleBoardPowerB; + int16_t TotalBoardPowerM; + int16_t TotalBoardPowerB; + // SECTION: Sku Reserved - uint32_t Spare[64]; + uint32_t Spare[61]; // Padding for MMHUB - do not modify this uint32_t MmHubPadding[8]; @@ -1259,7 +1264,8 @@ typedef struct { // SECTION: Clock Spread Spectrum // UCLK Spread Spectrum - uint16_t UclkSpreadPadding; + uint8_t UclkTrainingModeSpreadPercent; + uint8_t UclkSpreadPadding; uint16_t UclkSpreadFreq; // kHz // UCLK Spread Spectrum @@ -1272,11 +1278,7 @@ typedef struct { // Section: Memory Config uint8_t DramWidth; // Width of interface to the channel for each DRAM module. See DRAM_BIT_WIDTH_TYPE_e - uint8_t PaddingMem1[3]; - - // Section: Total Board Power - uint16_t TotalBoardPower; //Only needed for TCP Estimated case, where TCP = TGP+Total Board Power - uint16_t BoardPowerPadding; + uint8_t PaddingMem1[7]; // SECTION: UMC feature flags uint8_t HsrEnabled; @@ -1375,8 +1377,11 @@ typedef struct { uint16_t Vcn1ActivityPercentage ; uint32_t EnergyAccumulator; - uint16_t AverageSocketPower ; + uint16_t AverageSocketPower; + uint16_t AverageTotalBoardPower; + uint16_t AvgTemperature[TEMP_COUNT]; + uint16_t TempPadding; uint8_t PcieRate ; uint8_t PcieWidth ; diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h index 6fe2fe92ebd7..ac308e72241a 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h @@ -30,7 +30,7 @@ #define SMU13_DRIVER_IF_VERSION_ALDE 0x08 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_4 0x05 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_5 0x04 -#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0 0x2C +#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0 0x2E #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_7 0x2C #define SMU13_MODE1_RESET_WAIT_TIME_IN_MS 500 //500ms diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 86d670c71286..ad068865ba20 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -168,21 +168,6 @@ void drm_gem_private_object_init(struct drm_device *dev, } EXPORT_SYMBOL(drm_gem_private_object_init); -static void -drm_gem_remove_prime_handles(struct drm_gem_object *obj, struct drm_file *filp) -{ - /* - * Note: obj->dma_buf can't disappear as long as we still hold a - * handle reference in obj->handle_count. - */ - mutex_lock(&filp->prime.lock); - if (obj->dma_buf) { - drm_prime_remove_buf_handle_locked(&filp->prime, - obj->dma_buf); - } - mutex_unlock(&filp->prime.lock); -} - /** * drm_gem_object_handle_free - release resources bound to userspace handles * @obj: GEM object to clean up. @@ -253,7 +238,7 @@ drm_gem_object_release_handle(int id, void *ptr, void *data) if (obj->funcs->close) obj->funcs->close(obj, file_priv); - drm_gem_remove_prime_handles(obj, file_priv); + drm_prime_remove_buf_handle(&file_priv->prime, id); drm_vma_node_revoke(&obj->vma_node, file_priv); drm_gem_object_handle_put_unlocked(obj); diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h index 1fbbc19f1ac0..7bb98e6a446d 100644 --- a/drivers/gpu/drm/drm_internal.h +++ b/drivers/gpu/drm/drm_internal.h @@ -74,8 +74,8 @@ int drm_prime_fd_to_handle_ioctl(struct drm_device *dev, void *data, void drm_prime_init_file_private(struct drm_prime_file_private *prime_fpriv); void drm_prime_destroy_file_private(struct drm_prime_file_private *prime_fpriv); -void drm_prime_remove_buf_handle_locked(struct drm_prime_file_private *prime_fpriv, - struct dma_buf *dma_buf); +void drm_prime_remove_buf_handle(struct drm_prime_file_private *prime_fpriv, + uint32_t handle); /* drm_drv.c */ struct drm_minor *drm_minor_acquire(unsigned int minor_id); diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index a3f180653b8b..eb09e86044c6 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -190,29 +190,33 @@ static int drm_prime_lookup_buf_handle(struct drm_prime_file_private *prime_fpri return -ENOENT; } -void drm_prime_remove_buf_handle_locked(struct drm_prime_file_private *prime_fpriv, - struct dma_buf *dma_buf) +void drm_prime_remove_buf_handle(struct drm_prime_file_private *prime_fpriv, + uint32_t handle) { struct rb_node *rb; - rb = prime_fpriv->dmabufs.rb_node; + mutex_lock(&prime_fpriv->lock); + + rb = prime_fpriv->handles.rb_node; while (rb) { struct drm_prime_member *member; - member = rb_entry(rb, struct drm_prime_member, dmabuf_rb); - if (member->dma_buf == dma_buf) { + member = rb_entry(rb, struct drm_prime_member, handle_rb); + if (member->handle == handle) { rb_erase(&member->handle_rb, &prime_fpriv->handles); rb_erase(&member->dmabuf_rb, &prime_fpriv->dmabufs); - dma_buf_put(dma_buf); + dma_buf_put(member->dma_buf); kfree(member); - return; - } else if (member->dma_buf < dma_buf) { + break; + } else if (member->handle < handle) { rb = rb->rb_right; } else { rb = rb->rb_left; } } + + mutex_unlock(&prime_fpriv->lock); } void drm_prime_init_file_private(struct drm_prime_file_private *prime_fpriv) diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 05076e530e7d..e29175e4b44c 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -820,6 +820,15 @@ nouveau_bo_move_m2mf(struct ttm_buffer_object *bo, int evict, if (ret == 0) { ret = nouveau_fence_new(chan, false, &fence); if (ret == 0) { + /* TODO: figure out a better solution here + * + * wait on the fence here explicitly as going through + * ttm_bo_move_accel_cleanup somehow doesn't seem to do it. + * + * Without this the operation can timeout and we'll fallback to a + * software copy, which might take several minutes to finish. + */ + nouveau_fence_wait(fence, false, false); ret = ttm_bo_move_accel_cleanup(bo, &fence->base, evict, false, diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index 2b12389f841a..ee0165687239 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -1605,6 +1605,9 @@ int radeon_suspend_kms(struct drm_device *dev, bool suspend, if (r) { /* delay GPU reset to resume */ radeon_fence_driver_force_completion(rdev, i); + } else { + /* finish executing delayed work */ + flush_delayed_work(&rdev->fence_drv[i].lockup_work); } } diff --git a/drivers/gpu/drm/vc4/Kconfig b/drivers/gpu/drm/vc4/Kconfig index 061be9a6619d..b0f3117102ca 100644 --- a/drivers/gpu/drm/vc4/Kconfig +++ b/drivers/gpu/drm/vc4/Kconfig @@ -8,6 +8,7 @@ config DRM_VC4 depends on DRM depends on SND && SND_SOC depends on COMMON_CLK + depends on PM select DRM_DISPLAY_HDMI_HELPER select DRM_DISPLAY_HELPER select DRM_KMS_HELPER diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 592c3b5d03e6..1e5f68704d7d 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -2855,7 +2855,7 @@ static int vc5_hdmi_init_resources(struct vc4_hdmi *vc4_hdmi) return 0; } -static int __maybe_unused vc4_hdmi_runtime_suspend(struct device *dev) +static int vc4_hdmi_runtime_suspend(struct device *dev) { struct vc4_hdmi *vc4_hdmi = dev_get_drvdata(dev); @@ -2972,17 +2972,15 @@ static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data) vc4_hdmi->disable_4kp60 = true; } + pm_runtime_enable(dev); + /* - * We need to have the device powered up at this point to call - * our reset hook and for the CEC init. + * We need to have the device powered up at this point to call + * our reset hook and for the CEC init. */ - ret = vc4_hdmi_runtime_resume(dev); + ret = pm_runtime_resume_and_get(dev); if (ret) - goto err_put_ddc; - - pm_runtime_get_noresume(dev); - pm_runtime_set_active(dev); - pm_runtime_enable(dev); + goto err_disable_runtime_pm; if ((of_device_is_compatible(dev->of_node, "brcm,bcm2711-hdmi0") || of_device_is_compatible(dev->of_node, "brcm,bcm2711-hdmi1")) && @@ -3028,6 +3026,7 @@ err_destroy_conn: err_destroy_encoder: drm_encoder_cleanup(encoder); pm_runtime_put_sync(dev); +err_disable_runtime_pm: pm_runtime_disable(dev); err_put_ddc: put_device(&vc4_hdmi->ddc->dev); diff --git a/drivers/md/md.c b/drivers/md/md.c index afaf36b2f6ab..729be2c5296c 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5620,6 +5620,7 @@ struct mddev *md_alloc(dev_t dev, char *name) * removed (mddev_delayed_delete). */ flush_workqueue(md_misc_wq); + flush_workqueue(md_rdev_misc_wq); mutex_lock(&disks_mutex); mddev = mddev_alloc(dev); @@ -6238,11 +6239,11 @@ static void mddev_detach(struct mddev *mddev) static void __md_stop(struct mddev *mddev) { struct md_personality *pers = mddev->pers; + md_bitmap_destroy(mddev); mddev_detach(mddev); /* Ensure ->event_work is done */ if (mddev->event_work.func) flush_workqueue(md_misc_wq); - md_bitmap_destroy(mddev); spin_lock(&mddev->lock); mddev->pers = NULL; spin_unlock(&mddev->lock); @@ -6260,6 +6261,7 @@ void md_stop(struct mddev *mddev) /* stop the array and free an attached data structures. * This is called from dm-raid */ + __md_stop_writes(mddev); __md_stop(mddev); bioset_exit(&mddev->bio_set); bioset_exit(&mddev->sync_set); diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 9117fcdee1be..64d6e4cd8a3a 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -2639,18 +2639,18 @@ static void check_decay_read_errors(struct mddev *mddev, struct md_rdev *rdev) } static int r10_sync_page_io(struct md_rdev *rdev, sector_t sector, - int sectors, struct page *page, int rw) + int sectors, struct page *page, enum req_op op) { sector_t first_bad; int bad_sectors; if (is_badblock(rdev, sector, sectors, &first_bad, &bad_sectors) - && (rw == READ || test_bit(WriteErrorSeen, &rdev->flags))) + && (op == REQ_OP_READ || test_bit(WriteErrorSeen, &rdev->flags))) return -1; - if (sync_page_io(rdev, sector, sectors << 9, page, rw, false)) + if (sync_page_io(rdev, sector, sectors << 9, page, op, false)) /* success */ return 1; - if (rw == WRITE) { + if (op == REQ_OP_WRITE) { set_bit(WriteErrorSeen, &rdev->flags); if (!test_and_set_bit(WantReplacement, &rdev->flags)) set_bit(MD_RECOVERY_NEEDED, @@ -2780,7 +2780,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10 if (r10_sync_page_io(rdev, r10_bio->devs[sl].addr + sect, - s, conf->tmppage, WRITE) + s, conf->tmppage, REQ_OP_WRITE) == 0) { /* Well, this device is dead */ pr_notice("md/raid10:%s: read correction write failed (%d sectors at %llu on %pg)\n", @@ -2814,8 +2814,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10 switch (r10_sync_page_io(rdev, r10_bio->devs[sl].addr + sect, - s, conf->tmppage, - READ)) { + s, conf->tmppage, REQ_OP_READ)) { case 0: /* Well, this device is dead */ pr_notice("md/raid10:%s: unable to read back corrected sectors (%d sectors at %llu on %pg)\n", diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig index 10c563999d3d..e63608834411 100644 --- a/drivers/mmc/host/Kconfig +++ b/drivers/mmc/host/Kconfig @@ -171,6 +171,7 @@ config MMC_SDHCI_OF_ASPEED config MMC_SDHCI_OF_ASPEED_TEST bool "Tests for the ASPEED SDHCI driver" if !KUNIT_ALL_TESTS depends on MMC_SDHCI_OF_ASPEED && KUNIT + depends on (MMC_SDHCI_OF_ASPEED=m || KUNIT=y) default KUNIT_ALL_TESTS help Enable KUnit tests for the ASPEED SDHCI driver. Select this diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index d7fb33c078e8..184608bd8999 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -84,7 +84,8 @@ enum ad_link_speed_type { static const u8 null_mac_addr[ETH_ALEN + 2] __long_aligned = { 0, 0, 0, 0, 0, 0 }; -static u16 ad_ticks_per_sec; + +static const u16 ad_ticks_per_sec = 1000 / AD_TIMER_INTERVAL; static const int ad_delta_in_ticks = (AD_TIMER_INTERVAL * HZ) / 1000; static const u8 lacpdu_mcast_addr[ETH_ALEN + 2] __long_aligned = @@ -2001,36 +2002,24 @@ void bond_3ad_initiate_agg_selection(struct bonding *bond, int timeout) /** * bond_3ad_initialize - initialize a bond's 802.3ad parameters and structures * @bond: bonding struct to work on - * @tick_resolution: tick duration (millisecond resolution) * * Can be called only after the mac address of the bond is set. */ -void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution) +void bond_3ad_initialize(struct bonding *bond) { - /* check that the bond is not initialized yet */ - if (!MAC_ADDRESS_EQUAL(&(BOND_AD_INFO(bond).system.sys_mac_addr), - bond->dev->dev_addr)) { - - BOND_AD_INFO(bond).aggregator_identifier = 0; - - BOND_AD_INFO(bond).system.sys_priority = - bond->params.ad_actor_sys_prio; - if (is_zero_ether_addr(bond->params.ad_actor_system)) - BOND_AD_INFO(bond).system.sys_mac_addr = - *((struct mac_addr *)bond->dev->dev_addr); - else - BOND_AD_INFO(bond).system.sys_mac_addr = - *((struct mac_addr *)bond->params.ad_actor_system); - - /* initialize how many times this module is called in one - * second (should be about every 100ms) - */ - ad_ticks_per_sec = tick_resolution; + BOND_AD_INFO(bond).aggregator_identifier = 0; + BOND_AD_INFO(bond).system.sys_priority = + bond->params.ad_actor_sys_prio; + if (is_zero_ether_addr(bond->params.ad_actor_system)) + BOND_AD_INFO(bond).system.sys_mac_addr = + *((struct mac_addr *)bond->dev->dev_addr); + else + BOND_AD_INFO(bond).system.sys_mac_addr = + *((struct mac_addr *)bond->params.ad_actor_system); - bond_3ad_initiate_agg_selection(bond, - AD_AGGREGATOR_SELECTION_TIMER * - ad_ticks_per_sec); - } + bond_3ad_initiate_agg_selection(bond, + AD_AGGREGATOR_SELECTION_TIMER * + ad_ticks_per_sec); } /** diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 50e60843020c..2f4da2c13c0a 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2081,7 +2081,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, /* Initialize AD with the number of times that the AD timer is called in 1 second * can be called only after the mac address of the bond is set */ - bond_3ad_initialize(bond, 1000/AD_TIMER_INTERVAL); + bond_3ad_initialize(bond); } else { SLAVE_AD_INFO(new_slave)->id = SLAVE_AD_INFO(prev_slave)->id + 1; diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index ed7d137cba99..6bd69a7e6809 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -803,9 +803,15 @@ static void ksz_phylink_get_caps(struct dsa_switch *ds, int port, if (dev->info->supports_rgmii[port]) phy_interface_set_rgmii(config->supported_interfaces); - if (dev->info->internal_phy[port]) + if (dev->info->internal_phy[port]) { __set_bit(PHY_INTERFACE_MODE_INTERNAL, config->supported_interfaces); + /* Compatibility for phylib's default interface type when the + * phy-mode property is absent + */ + __set_bit(PHY_INTERFACE_MODE_GMII, + config->supported_interfaces); + } if (dev->dev_ops->get_caps) dev->dev_ops->get_caps(dev, port, config); @@ -962,6 +968,7 @@ static void ksz_update_port_member(struct ksz_device *dev, int port) static int ksz_setup(struct dsa_switch *ds) { struct ksz_device *dev = ds->priv; + struct ksz_port *p; const u16 *regs; int ret; @@ -1001,6 +1008,14 @@ static int ksz_setup(struct dsa_switch *ds) return ret; } + /* Start with learning disabled on standalone user ports, and enabled + * on the CPU port. In lack of other finer mechanisms, learning on the + * CPU port will avoid flooding bridge local addresses on the network + * in some cases. + */ + p = &dev->ports[dev->cpu_port]; + p->learning = true; + /* start switch */ regmap_update_bits(dev->regmap[0], regs[S_START_CTRL], SW_START, SW_START); @@ -1277,6 +1292,8 @@ void ksz_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) ksz_pread8(dev, port, regs[P_STP_CTRL], &data); data &= ~(PORT_TX_ENABLE | PORT_RX_ENABLE | PORT_LEARN_DISABLE); + p = &dev->ports[port]; + switch (state) { case BR_STATE_DISABLED: data |= PORT_LEARN_DISABLE; @@ -1286,9 +1303,13 @@ void ksz_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) break; case BR_STATE_LEARNING: data |= PORT_RX_ENABLE; + if (!p->learning) + data |= PORT_LEARN_DISABLE; break; case BR_STATE_FORWARDING: data |= (PORT_TX_ENABLE | PORT_RX_ENABLE); + if (!p->learning) + data |= PORT_LEARN_DISABLE; break; case BR_STATE_BLOCKING: data |= PORT_LEARN_DISABLE; @@ -1300,12 +1321,38 @@ void ksz_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) ksz_pwrite8(dev, port, regs[P_STP_CTRL], data); - p = &dev->ports[port]; p->stp_state = state; ksz_update_port_member(dev, port); } +static int ksz_port_pre_bridge_flags(struct dsa_switch *ds, int port, + struct switchdev_brport_flags flags, + struct netlink_ext_ack *extack) +{ + if (flags.mask & ~BR_LEARNING) + return -EINVAL; + + return 0; +} + +static int ksz_port_bridge_flags(struct dsa_switch *ds, int port, + struct switchdev_brport_flags flags, + struct netlink_ext_ack *extack) +{ + struct ksz_device *dev = ds->priv; + struct ksz_port *p = &dev->ports[port]; + + if (flags.mask & BR_LEARNING) { + p->learning = !!(flags.val & BR_LEARNING); + + /* Make the change take effect immediately */ + ksz_port_stp_state_set(ds, port, p->stp_state); + } + + return 0; +} + static enum dsa_tag_protocol ksz_get_tag_protocol(struct dsa_switch *ds, int port, enum dsa_tag_protocol mp) @@ -1719,6 +1766,8 @@ static const struct dsa_switch_ops ksz_switch_ops = { .port_bridge_join = ksz_port_bridge_join, .port_bridge_leave = ksz_port_bridge_leave, .port_stp_state_set = ksz_port_stp_state_set, + .port_pre_bridge_flags = ksz_port_pre_bridge_flags, + .port_bridge_flags = ksz_port_bridge_flags, .port_fast_age = ksz_port_fast_age, .port_vlan_filtering = ksz_port_vlan_filtering, .port_vlan_add = ksz_port_vlan_add, diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index 764ada3a0f42..0d9520dc6d2d 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -65,6 +65,7 @@ struct ksz_chip_data { struct ksz_port { bool remove_tag; /* Remove Tag flag set, for ksz8795 only */ + bool learning; int stp_state; struct phy_device phydev; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index ba0f1ffac507..f46eefb5a029 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -11178,10 +11178,7 @@ static netdev_features_t bnxt_fix_features(struct net_device *dev, if ((features & NETIF_F_NTUPLE) && !bnxt_rfs_capable(bp)) features &= ~NETIF_F_NTUPLE; - if (bp->flags & BNXT_FLAG_NO_AGG_RINGS) - features &= ~(NETIF_F_LRO | NETIF_F_GRO_HW); - - if (!(bp->flags & BNXT_FLAG_TPA)) + if ((bp->flags & BNXT_FLAG_NO_AGG_RINGS) || bp->xdp_prog) features &= ~(NETIF_F_LRO | NETIF_F_GRO_HW); if (!(features & NETIF_F_GRO)) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 075c6206325c..b1b17f911300 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -2130,6 +2130,7 @@ struct bnxt { #define BNXT_DUMP_CRASH 1 struct bpf_prog *xdp_prog; + u8 xdp_has_frags; struct bnxt_ptp_cfg *ptp_cfg; u8 ptp_all_rx_tstamp; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index 059f96f7a96f..a36803e79e92 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -1306,6 +1306,7 @@ int bnxt_dl_register(struct bnxt *bp) if (rc) goto err_dl_port_unreg; + devlink_set_features(dl, DEVLINK_F_RELOAD); out: devlink_register(dl); return 0; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index 730febd19330..a4cba7cb2783 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -623,7 +623,7 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs, bool reset) hw_resc->max_stat_ctxs -= le16_to_cpu(req->min_stat_ctx) * n; hw_resc->max_vnics -= le16_to_cpu(req->min_vnics) * n; if (bp->flags & BNXT_FLAG_CHIP_P5) - hw_resc->max_irqs -= vf_msix * n; + hw_resc->max_nqs -= vf_msix; rc = pf->active_vfs; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index f53387ed0167..c3065ec0a479 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -181,6 +181,7 @@ void bnxt_xdp_buff_init(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, struct xdp_buff *xdp) { struct bnxt_sw_rx_bd *rx_buf; + u32 buflen = PAGE_SIZE; struct pci_dev *pdev; dma_addr_t mapping; u32 offset; @@ -192,7 +193,10 @@ void bnxt_xdp_buff_init(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, mapping = rx_buf->mapping - bp->rx_dma_offset; dma_sync_single_for_cpu(&pdev->dev, mapping + offset, *len, bp->rx_dir); - xdp_init_buff(xdp, BNXT_PAGE_MODE_BUF_SIZE + offset, &rxr->xdp_rxq); + if (bp->xdp_has_frags) + buflen = BNXT_PAGE_MODE_BUF_SIZE + offset; + + xdp_init_buff(xdp, buflen, &rxr->xdp_rxq); xdp_prepare_buff(xdp, *data_ptr - offset, offset, *len, false); } @@ -397,8 +401,10 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog) netdev_warn(dev, "ethtool rx/tx channels must be combined to support XDP.\n"); return -EOPNOTSUPP; } - if (prog) + if (prog) { tx_xdp = bp->rx_nr_rings; + bp->xdp_has_frags = prog->aux->xdp_has_frags; + } tc = netdev_get_num_tc(dev); if (!tc) diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 45634579adb6..a770bab4d1ed 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -2886,6 +2886,7 @@ static void dpaa_adjust_link(struct net_device *net_dev) /* The Aquantia PHYs are capable of performing rate adaptation */ #define PHY_VEND_AQUANTIA 0x03a1b400 +#define PHY_VEND_AQUANTIA2 0x31c31c00 static int dpaa_phy_init(struct net_device *net_dev) { @@ -2893,6 +2894,7 @@ static int dpaa_phy_init(struct net_device *net_dev) struct mac_device *mac_dev; struct phy_device *phy_dev; struct dpaa_priv *priv; + u32 phy_vendor; priv = netdev_priv(net_dev); mac_dev = priv->mac_dev; @@ -2905,9 +2907,11 @@ static int dpaa_phy_init(struct net_device *net_dev) return -ENODEV; } + phy_vendor = phy_dev->drv->phy_id & GENMASK(31, 10); /* Unless the PHY is capable of rate adaptation */ if (mac_dev->phy_if != PHY_INTERFACE_MODE_XGMII || - ((phy_dev->drv->phy_id & GENMASK(31, 10)) != PHY_VEND_AQUANTIA)) { + (phy_vendor != PHY_VEND_AQUANTIA && + phy_vendor != PHY_VEND_AQUANTIA2)) { /* remove any features not supported by the controller */ ethtool_convert_legacy_u32_to_link_mode(mask, mac_dev->if_support); diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index ed7301b69169..0cebe4b63adb 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -634,6 +634,13 @@ struct fec_enet_private { int pps_enable; unsigned int next_counter; + struct { + struct timespec64 ts_phc; + u64 ns_sys; + u32 at_corr; + u8 at_inc_corr; + } ptp_saved_state; + u64 ethtool_stats[]; }; @@ -644,5 +651,8 @@ void fec_ptp_disable_hwts(struct net_device *ndev); int fec_ptp_set(struct net_device *ndev, struct ifreq *ifr); int fec_ptp_get(struct net_device *ndev, struct ifreq *ifr); +void fec_ptp_save_state(struct fec_enet_private *fep); +int fec_ptp_restore_state(struct fec_enet_private *fep); + /****************************************************************************/ #endif /* FEC_H */ diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index e8e2aa1e7f01..b0d60f898249 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -285,8 +285,11 @@ MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address"); #define FEC_MMFR_TA (2 << 16) #define FEC_MMFR_DATA(v) (v & 0xffff) /* FEC ECR bits definition */ -#define FEC_ECR_MAGICEN (1 << 2) -#define FEC_ECR_SLEEP (1 << 3) +#define FEC_ECR_RESET BIT(0) +#define FEC_ECR_ETHEREN BIT(1) +#define FEC_ECR_MAGICEN BIT(2) +#define FEC_ECR_SLEEP BIT(3) +#define FEC_ECR_EN1588 BIT(4) #define FEC_MII_TIMEOUT 30000 /* us */ @@ -982,6 +985,9 @@ fec_restart(struct net_device *ndev) u32 temp_mac[2]; u32 rcntl = OPT_FRAME_SIZE | 0x04; u32 ecntl = 0x2; /* ETHEREN */ + struct ptp_clock_request ptp_rq = { .type = PTP_CLK_REQ_PPS }; + + fec_ptp_save_state(fep); /* Whack a reset. We should wait for this. * For i.MX6SX SOC, enet use AXI bus, we use disable MAC @@ -1135,7 +1141,7 @@ fec_restart(struct net_device *ndev) } if (fep->bufdesc_ex) - ecntl |= (1 << 4); + ecntl |= FEC_ECR_EN1588; if (fep->quirks & FEC_QUIRK_DELAYED_CLKS_SUPPORT && fep->rgmii_txc_dly) @@ -1156,6 +1162,14 @@ fec_restart(struct net_device *ndev) if (fep->bufdesc_ex) fec_ptp_start_cyclecounter(ndev); + /* Restart PPS if needed */ + if (fep->pps_enable) { + /* Clear flag so fec_ptp_enable_pps() doesn't return immediately */ + fep->pps_enable = 0; + fec_ptp_restore_state(fep); + fep->ptp_caps.enable(&fep->ptp_caps, &ptp_rq, 1); + } + /* Enable interrupts we wish to service */ if (fep->link) writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK); @@ -1206,6 +1220,8 @@ fec_stop(struct net_device *ndev) struct fec_enet_private *fep = netdev_priv(ndev); u32 rmii_mode = readl(fep->hwp + FEC_R_CNTRL) & (1 << 8); u32 val; + struct ptp_clock_request ptp_rq = { .type = PTP_CLK_REQ_PPS }; + u32 ecntl = 0; /* We cannot expect a graceful transmit stop without link !!! */ if (fep->link) { @@ -1215,6 +1231,8 @@ fec_stop(struct net_device *ndev) netdev_err(ndev, "Graceful transmit stop did not complete!\n"); } + fec_ptp_save_state(fep); + /* Whack a reset. We should wait for this. * For i.MX6SX SOC, enet use AXI bus, we use disable MAC * instead of reset MAC itself. @@ -1234,12 +1252,28 @@ fec_stop(struct net_device *ndev) writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED); writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK); + if (fep->bufdesc_ex) + ecntl |= FEC_ECR_EN1588; + /* We have to keep ENET enabled to have MII interrupt stay working */ if (fep->quirks & FEC_QUIRK_ENET_MAC && !(fep->wol_flag & FEC_WOL_FLAG_SLEEP_ON)) { - writel(2, fep->hwp + FEC_ECNTRL); + ecntl |= FEC_ECR_ETHEREN; writel(rmii_mode, fep->hwp + FEC_R_CNTRL); } + + writel(ecntl, fep->hwp + FEC_ECNTRL); + + if (fep->bufdesc_ex) + fec_ptp_start_cyclecounter(ndev); + + /* Restart PPS if needed */ + if (fep->pps_enable) { + /* Clear flag so fec_ptp_enable_pps() doesn't return immediately */ + fep->pps_enable = 0; + fec_ptp_restore_state(fep); + fep->ptp_caps.enable(&fep->ptp_caps, &ptp_rq, 1); + } } diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index 3dc3c0b626c2..c74d04f4b2fd 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -633,7 +633,36 @@ void fec_ptp_stop(struct platform_device *pdev) struct net_device *ndev = platform_get_drvdata(pdev); struct fec_enet_private *fep = netdev_priv(ndev); + if (fep->pps_enable) + fec_ptp_enable_pps(fep, 0); + cancel_delayed_work_sync(&fep->time_keep); if (fep->ptp_clock) ptp_clock_unregister(fep->ptp_clock); } + +void fec_ptp_save_state(struct fec_enet_private *fep) +{ + u32 atime_inc_corr; + + fec_ptp_gettime(&fep->ptp_caps, &fep->ptp_saved_state.ts_phc); + fep->ptp_saved_state.ns_sys = ktime_get_ns(); + + fep->ptp_saved_state.at_corr = readl(fep->hwp + FEC_ATIME_CORR); + atime_inc_corr = readl(fep->hwp + FEC_ATIME_INC) & FEC_T_INC_CORR_MASK; + fep->ptp_saved_state.at_inc_corr = (u8)(atime_inc_corr >> FEC_T_INC_CORR_OFFSET); +} + +int fec_ptp_restore_state(struct fec_enet_private *fep) +{ + u32 atime_inc = readl(fep->hwp + FEC_ATIME_INC) & FEC_T_INC_MASK; + u64 ns_sys; + + writel(fep->ptp_saved_state.at_corr, fep->hwp + FEC_ATIME_CORR); + atime_inc |= ((u32)fep->ptp_saved_state.at_inc_corr) << FEC_T_INC_CORR_OFFSET; + writel(atime_inc, fep->hwp + FEC_ATIME_INC); + + ns_sys = ktime_get_ns() - fep->ptp_saved_state.ns_sys; + timespec64_add_ns(&fep->ptp_saved_state.ts_phc, ns_sys); + return fec_ptp_settime(&fep->ptp_caps, &fep->ptp_saved_state.ts_phc); +} diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 156e92c43780..e9cd0fa6a0d2 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -4485,7 +4485,7 @@ static int i40e_check_fdir_input_set(struct i40e_vsi *vsi, (struct in6_addr *)&ipv6_full_mask)) new_mask |= I40E_L3_V6_DST_MASK; else if (ipv6_addr_any((struct in6_addr *) - &usr_ip6_spec->ip6src)) + &usr_ip6_spec->ip6dst)) new_mask &= ~I40E_L3_V6_DST_MASK; else return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index cc5b85afd437..841fa149c407 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -684,8 +684,8 @@ static inline void ice_set_ring_xdp(struct ice_tx_ring *ring) * ice_xsk_pool - get XSK buffer pool bound to a ring * @ring: Rx ring to use * - * Returns a pointer to xdp_umem structure if there is a buffer pool present, - * NULL otherwise. + * Returns a pointer to xsk_buff_pool structure if there is a buffer pool + * present, NULL otherwise. */ static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_rx_ring *ring) { @@ -699,23 +699,33 @@ static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_rx_ring *ring) } /** - * ice_tx_xsk_pool - get XSK buffer pool bound to a ring - * @ring: Tx ring to use + * ice_tx_xsk_pool - assign XSK buff pool to XDP ring + * @vsi: pointer to VSI + * @qid: index of a queue to look at XSK buff pool presence * - * Returns a pointer to xdp_umem structure if there is a buffer pool present, - * NULL otherwise. Tx equivalent of ice_xsk_pool. + * Sets XSK buff pool pointer on XDP ring. + * + * XDP ring is picked from Rx ring, whereas Rx ring is picked based on provided + * queue id. Reason for doing so is that queue vectors might have assigned more + * than one XDP ring, e.g. when user reduced the queue count on netdev; Rx ring + * carries a pointer to one of these XDP rings for its own purposes, such as + * handling XDP_TX action, therefore we can piggyback here on the + * rx_ring->xdp_ring assignment that was done during XDP rings initialization. */ -static inline struct xsk_buff_pool *ice_tx_xsk_pool(struct ice_tx_ring *ring) +static inline void ice_tx_xsk_pool(struct ice_vsi *vsi, u16 qid) { - struct ice_vsi *vsi = ring->vsi; - u16 qid; + struct ice_tx_ring *ring; - qid = ring->q_index - vsi->alloc_txq; + ring = vsi->rx_rings[qid]->xdp_ring; + if (!ring) + return; - if (!ice_is_xdp_ena_vsi(vsi) || !test_bit(qid, vsi->af_xdp_zc_qps)) - return NULL; + if (!ice_is_xdp_ena_vsi(vsi) || !test_bit(qid, vsi->af_xdp_zc_qps)) { + ring->xsk_pool = NULL; + return; + } - return xsk_get_pool_from_qid(vsi->netdev, qid); + ring->xsk_pool = xsk_get_pool_from_qid(vsi->netdev, qid); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 733c455f6574..0c4ec9264071 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -1986,8 +1986,8 @@ int ice_vsi_cfg_xdp_txqs(struct ice_vsi *vsi) if (ret) return ret; - ice_for_each_xdp_txq(vsi, i) - vsi->xdp_rings[i]->xsk_pool = ice_tx_xsk_pool(vsi->xdp_rings[i]); + ice_for_each_rxq(vsi, i) + ice_tx_xsk_pool(vsi, i); return ret; } diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 4ecaf40cf946..173fe6c31341 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2581,7 +2581,6 @@ static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi) if (ice_setup_tx_ring(xdp_ring)) goto free_xdp_rings; ice_set_ring_xdp(xdp_ring); - xdp_ring->xsk_pool = ice_tx_xsk_pool(xdp_ring); spin_lock_init(&xdp_ring->tx_lock); for (j = 0; j < xdp_ring->count; j++) { tx_desc = ICE_TX_DESC(xdp_ring, j); @@ -2589,13 +2588,6 @@ static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi) } } - ice_for_each_rxq(vsi, i) { - if (static_key_enabled(&ice_xdp_locking_key)) - vsi->rx_rings[i]->xdp_ring = vsi->xdp_rings[i % vsi->num_xdp_txq]; - else - vsi->rx_rings[i]->xdp_ring = vsi->xdp_rings[i]; - } - return 0; free_xdp_rings: @@ -2685,6 +2677,23 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) xdp_rings_rem -= xdp_rings_per_v; } + ice_for_each_rxq(vsi, i) { + if (static_key_enabled(&ice_xdp_locking_key)) { + vsi->rx_rings[i]->xdp_ring = vsi->xdp_rings[i % vsi->num_xdp_txq]; + } else { + struct ice_q_vector *q_vector = vsi->rx_rings[i]->q_vector; + struct ice_tx_ring *ring; + + ice_for_each_tx_ring(ring, q_vector->tx) { + if (ice_ring_is_xdp(ring)) { + vsi->rx_rings[i]->xdp_ring = ring; + break; + } + } + } + ice_tx_xsk_pool(vsi, i); + } + /* omit the scheduler update if in reset path; XDP queues will be * taken into account at the end of ice_vsi_rebuild, where * ice_cfg_vsi_lan is being called diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 49ba8bfdbf04..e48e29258450 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -243,7 +243,7 @@ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx) if (err) goto free_buf; ice_set_ring_xdp(xdp_ring); - xdp_ring->xsk_pool = ice_tx_xsk_pool(xdp_ring); + ice_tx_xsk_pool(vsi, q_idx); } err = ice_vsi_cfg_rxq(rx_ring); @@ -329,6 +329,12 @@ int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid) bool if_running, pool_present = !!pool; int ret = 0, pool_failure = 0; + if (qid >= vsi->num_rxq || qid >= vsi->num_txq) { + netdev_err(vsi->netdev, "Please use queue id in scope of combined queues count\n"); + pool_failure = -EINVAL; + goto failure; + } + if (!is_power_of_2(vsi->rx_rings[qid]->count) || !is_power_of_2(vsi->tx_rings[qid]->count)) { netdev_err(vsi->netdev, "Please align ring sizes to power of 2\n"); @@ -353,7 +359,7 @@ xsk_pool_if_up: if (if_running) { ret = ice_qp_ena(vsi, qid); if (!ret && pool_present) - napi_schedule(&vsi->xdp_rings[qid]->q_vector->napi); + napi_schedule(&vsi->rx_rings[qid]->xdp_ring->q_vector->napi); else if (ret) netdev_err(vsi->netdev, "ice_qp_ena error = %d\n", ret); } @@ -944,13 +950,13 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, if (!ice_is_xdp_ena_vsi(vsi)) return -EINVAL; - if (queue_id >= vsi->num_txq) + if (queue_id >= vsi->num_txq || queue_id >= vsi->num_rxq) return -EINVAL; - if (!vsi->xdp_rings[queue_id]->xsk_pool) - return -EINVAL; + ring = vsi->rx_rings[queue_id]->xdp_ring; - ring = vsi->xdp_rings[queue_id]; + if (!ring->xsk_pool) + return -EINVAL; /* The idea here is that if NAPI is running, mark a miss, so * it will run again. If not, trigger an interrupt and diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c index 9f06896a049b..f8605f57bd06 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c @@ -1214,7 +1214,6 @@ void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter) struct cyclecounter cc; unsigned long flags; u32 incval = 0; - u32 tsauxc = 0; u32 fuse0 = 0; /* For some of the boards below this mask is technically incorrect. @@ -1249,18 +1248,6 @@ void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter) case ixgbe_mac_x550em_a: case ixgbe_mac_X550: cc.read = ixgbe_ptp_read_X550; - - /* enable SYSTIME counter */ - IXGBE_WRITE_REG(hw, IXGBE_SYSTIMR, 0); - IXGBE_WRITE_REG(hw, IXGBE_SYSTIML, 0); - IXGBE_WRITE_REG(hw, IXGBE_SYSTIMH, 0); - tsauxc = IXGBE_READ_REG(hw, IXGBE_TSAUXC); - IXGBE_WRITE_REG(hw, IXGBE_TSAUXC, - tsauxc & ~IXGBE_TSAUXC_DISABLE_SYSTIME); - IXGBE_WRITE_REG(hw, IXGBE_TSIM, IXGBE_TSIM_TXTS); - IXGBE_WRITE_REG(hw, IXGBE_EIMS, IXGBE_EIMS_TIMESYNC); - - IXGBE_WRITE_FLUSH(hw); break; case ixgbe_mac_X540: cc.read = ixgbe_ptp_read_82599; @@ -1293,6 +1280,50 @@ void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter) } /** + * ixgbe_ptp_init_systime - Initialize SYSTIME registers + * @adapter: the ixgbe private board structure + * + * Initialize and start the SYSTIME registers. + */ +static void ixgbe_ptp_init_systime(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 tsauxc; + + switch (hw->mac.type) { + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + case ixgbe_mac_X550: + tsauxc = IXGBE_READ_REG(hw, IXGBE_TSAUXC); + + /* Reset SYSTIME registers to 0 */ + IXGBE_WRITE_REG(hw, IXGBE_SYSTIMR, 0); + IXGBE_WRITE_REG(hw, IXGBE_SYSTIML, 0); + IXGBE_WRITE_REG(hw, IXGBE_SYSTIMH, 0); + + /* Reset interrupt settings */ + IXGBE_WRITE_REG(hw, IXGBE_TSIM, IXGBE_TSIM_TXTS); + IXGBE_WRITE_REG(hw, IXGBE_EIMS, IXGBE_EIMS_TIMESYNC); + + /* Activate the SYSTIME counter */ + IXGBE_WRITE_REG(hw, IXGBE_TSAUXC, + tsauxc & ~IXGBE_TSAUXC_DISABLE_SYSTIME); + break; + case ixgbe_mac_X540: + case ixgbe_mac_82599EB: + /* Reset SYSTIME registers to 0 */ + IXGBE_WRITE_REG(hw, IXGBE_SYSTIML, 0); + IXGBE_WRITE_REG(hw, IXGBE_SYSTIMH, 0); + break; + default: + /* Other devices aren't supported */ + return; + }; + + IXGBE_WRITE_FLUSH(hw); +} + +/** * ixgbe_ptp_reset * @adapter: the ixgbe private board structure * @@ -1318,6 +1349,8 @@ void ixgbe_ptp_reset(struct ixgbe_adapter *adapter) ixgbe_ptp_start_cyclecounter(adapter); + ixgbe_ptp_init_systime(adapter); + spin_lock_irqsave(&adapter->tmreg_lock, flags); timecounter_init(&adapter->hw_tc, &adapter->hw_cc, ktime_to_ns(ktime_get_real())); diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c index 5edb68a8aab1..57f27cc7724e 100644 --- a/drivers/net/ethernet/lantiq_xrx200.c +++ b/drivers/net/ethernet/lantiq_xrx200.c @@ -193,6 +193,7 @@ static int xrx200_alloc_buf(struct xrx200_chan *ch, void *(*alloc)(unsigned int ch->rx_buff[ch->dma.desc] = alloc(priv->rx_skb_size); if (!ch->rx_buff[ch->dma.desc]) { + ch->rx_buff[ch->dma.desc] = buf; ret = -ENOMEM; goto skip; } @@ -239,6 +240,12 @@ static int xrx200_hw_receive(struct xrx200_chan *ch) } skb = build_skb(buf, priv->rx_skb_size); + if (!skb) { + skb_free_frag(buf); + net_dev->stats.rx_dropped++; + return -ENOMEM; + } + skb_reserve(skb, NET_SKB_PAD); skb_put(skb, len); @@ -288,7 +295,7 @@ static int xrx200_poll_rx(struct napi_struct *napi, int budget) if (ret == XRX200_DMA_PACKET_IN_PROGRESS) continue; if (ret != XRX200_DMA_PACKET_COMPLETE) - return ret; + break; rx++; } else { break; diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 8aff4c0c28bd..5ace4609de47 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -1891,10 +1891,19 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, skb->dev = netdev; bytes += skb->len; - if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) + if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) { + hash = trxd.rxd5 & MTK_RXD5_FOE_ENTRY; + if (hash != MTK_RXD5_FOE_ENTRY) + skb_set_hash(skb, jhash_1word(hash, 0), + PKT_HASH_TYPE_L4); rxdcsum = &trxd.rxd3; - else + } else { + hash = trxd.rxd4 & MTK_RXD4_FOE_ENTRY; + if (hash != MTK_RXD4_FOE_ENTRY) + skb_set_hash(skb, jhash_1word(hash, 0), + PKT_HASH_TYPE_L4); rxdcsum = &trxd.rxd4; + } if (*rxdcsum & eth->soc->txrx.rx_dma_l4_valid) skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -1902,16 +1911,9 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, skb_checksum_none_assert(skb); skb->protocol = eth_type_trans(skb, netdev); - hash = trxd.rxd4 & MTK_RXD4_FOE_ENTRY; - if (hash != MTK_RXD4_FOE_ENTRY) { - hash = jhash_1word(hash, 0); - skb_set_hash(skb, hash, PKT_HASH_TYPE_L4); - } - reason = FIELD_GET(MTK_RXD4_PPE_CPU_REASON, trxd.rxd4); if (reason == MTK_PPE_CPU_REASON_HIT_UNBIND_RATE_REACHED) - mtk_ppe_check_skb(eth->ppe, skb, - trxd.rxd4 & MTK_RXD4_FOE_ENTRY); + mtk_ppe_check_skb(eth->ppe, skb, hash); if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX) { if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) { diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index 7405c97cda66..ecf85e9ed824 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -314,6 +314,11 @@ #define RX_DMA_L4_VALID_PDMA BIT(30) /* when PDMA is used */ #define RX_DMA_SPECIAL_TAG BIT(22) +/* PDMA descriptor rxd5 */ +#define MTK_RXD5_FOE_ENTRY GENMASK(14, 0) +#define MTK_RXD5_PPE_CPU_REASON GENMASK(22, 18) +#define MTK_RXD5_SRC_PORT GENMASK(29, 26) + #define RX_DMA_GET_SPORT(x) (((x) >> 19) & 0xf) #define RX_DMA_GET_SPORT_V2(x) (((x) >> 26) & 0x7) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/police.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/police.c index 37522352e4b2..c8e5ca65bb6e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/police.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/police.c @@ -79,6 +79,10 @@ tc_act_police_offload(struct mlx5e_priv *priv, struct mlx5e_flow_meter_handle *meter; int err = 0; + err = mlx5e_policer_validate(&fl_act->action, act, fl_act->extack); + if (err) + return err; + err = fill_meter_params_from_act(act, ¶ms); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c index 0aef69527226..3a1f76eac542 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c @@ -246,7 +246,7 @@ static void mlx5e_tls_priv_tx_cleanup(struct mlx5e_ktls_offload_context_tx *priv static void mlx5e_tls_priv_tx_list_cleanup(struct mlx5_core_dev *mdev, struct list_head *list, int size) { - struct mlx5e_ktls_offload_context_tx *obj; + struct mlx5e_ktls_offload_context_tx *obj, *n; struct mlx5e_async_ctx *bulk_async; int i; @@ -255,7 +255,7 @@ static void mlx5e_tls_priv_tx_list_cleanup(struct mlx5_core_dev *mdev, return; i = 0; - list_for_each_entry(obj, list, list_node) { + list_for_each_entry_safe(obj, n, list, list_node) { mlx5e_tls_priv_tx_cleanup(obj, &bulk_async[i]); i++; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index e2a9b9be5c1f..e0ce5a233d0b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -1395,10 +1395,11 @@ struct mlx5e_flow_steering *mlx5e_fs_init(const struct mlx5e_profile *profile, } return fs; -err_free_fs: - kvfree(fs); + err_free_vlan: mlx5e_fs_vlan_free(fs); +err_free_fs: + kvfree(fs); err: return NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index d858667736a3..02eb2f0fa2ae 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3682,7 +3682,9 @@ static int set_feature_hw_tc(struct net_device *netdev, bool enable) int err = 0; #if IS_ENABLED(CONFIG_MLX5_CLS_ACT) - if (!enable && mlx5e_tc_num_filters(priv, MLX5_TC_FLAG(NIC_OFFLOAD))) { + int tc_flag = mlx5e_is_uplink_rep(priv) ? MLX5_TC_FLAG(ESW_OFFLOAD) : + MLX5_TC_FLAG(NIC_OFFLOAD); + if (!enable && mlx5e_tc_num_filters(priv, tc_flag)) { netdev_err(netdev, "Active offloaded tc filters, can't turn hw_tc_offload off\n"); return -EINVAL; @@ -4769,14 +4771,6 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 /* RQ */ mlx5e_build_rq_params(mdev, params); - /* HW LRO */ - if (MLX5_CAP_ETH(mdev, lro_cap) && - params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) { - /* No XSK params: checking the availability of striding RQ in general. */ - if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL)) - params->packet_merge.type = slow_pci_heuristic(mdev) ? - MLX5E_PACKET_MERGE_NONE : MLX5E_PACKET_MERGE_LRO; - } params->packet_merge.timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT); /* CQ moderation params */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 0c66774a1720..759f7d3c2cfd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -662,6 +662,8 @@ static void mlx5e_build_rep_params(struct net_device *netdev) params->mqprio.num_tc = 1; params->tunneled_offload_en = false; + if (rep->vport != MLX5_VPORT_UPLINK) + params->vlan_strip_disable = true; mlx5_query_min_inline(mdev, ¶ms->tx_min_inline_mode); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index ed73132129aa..a9f4c652f859 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -427,7 +427,8 @@ esw_setup_vport_dest(struct mlx5_flow_destination *dest, struct mlx5_flow_act *f dest[dest_idx].vport.vhca_id = MLX5_CAP_GEN(esw_attr->dests[attr_idx].mdev, vhca_id); dest[dest_idx].vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID; - if (mlx5_lag_mpesw_is_activated(esw->dev)) + if (dest[dest_idx].vport.num == MLX5_VPORT_UPLINK && + mlx5_lag_mpesw_is_activated(esw->dev)) dest[dest_idx].type = MLX5_FLOW_DESTINATION_TYPE_UPLINK; } if (esw_attr->dests[attr_idx].flags & MLX5_ESW_DEST_ENCAP) { @@ -3115,8 +3116,10 @@ esw_vfs_changed_event_handler(struct mlx5_eswitch *esw, const u32 *out) err = mlx5_eswitch_load_vf_vports(esw, new_num_vfs, MLX5_VPORT_UC_ADDR_CHANGE); - if (err) + if (err) { + devl_unlock(devlink); return; + } } esw->esw_funcs.num_vfs = new_num_vfs; devl_unlock(devlink); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index 0f34e3c80d1f..065102278cb8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -1067,30 +1067,32 @@ static void mlx5_ldev_add_netdev(struct mlx5_lag *ldev, struct net_device *netdev) { unsigned int fn = mlx5_get_dev_index(dev); + unsigned long flags; if (fn >= ldev->ports) return; - spin_lock(&lag_lock); + spin_lock_irqsave(&lag_lock, flags); ldev->pf[fn].netdev = netdev; ldev->tracker.netdev_state[fn].link_up = 0; ldev->tracker.netdev_state[fn].tx_enabled = 0; - spin_unlock(&lag_lock); + spin_unlock_irqrestore(&lag_lock, flags); } static void mlx5_ldev_remove_netdev(struct mlx5_lag *ldev, struct net_device *netdev) { + unsigned long flags; int i; - spin_lock(&lag_lock); + spin_lock_irqsave(&lag_lock, flags); for (i = 0; i < ldev->ports; i++) { if (ldev->pf[i].netdev == netdev) { ldev->pf[i].netdev = NULL; break; } } - spin_unlock(&lag_lock); + spin_unlock_irqrestore(&lag_lock, flags); } static void mlx5_ldev_add_mdev(struct mlx5_lag *ldev, @@ -1234,7 +1236,7 @@ void mlx5_lag_add_netdev(struct mlx5_core_dev *dev, mlx5_ldev_add_netdev(ldev, dev, netdev); for (i = 0; i < ldev->ports; i++) - if (!ldev->pf[i].dev) + if (!ldev->pf[i].netdev) break; if (i >= ldev->ports) @@ -1246,12 +1248,13 @@ void mlx5_lag_add_netdev(struct mlx5_core_dev *dev, bool mlx5_lag_is_roce(struct mlx5_core_dev *dev) { struct mlx5_lag *ldev; + unsigned long flags; bool res; - spin_lock(&lag_lock); + spin_lock_irqsave(&lag_lock, flags); ldev = mlx5_lag_dev(dev); res = ldev && __mlx5_lag_is_roce(ldev); - spin_unlock(&lag_lock); + spin_unlock_irqrestore(&lag_lock, flags); return res; } @@ -1260,12 +1263,13 @@ EXPORT_SYMBOL(mlx5_lag_is_roce); bool mlx5_lag_is_active(struct mlx5_core_dev *dev) { struct mlx5_lag *ldev; + unsigned long flags; bool res; - spin_lock(&lag_lock); + spin_lock_irqsave(&lag_lock, flags); ldev = mlx5_lag_dev(dev); res = ldev && __mlx5_lag_is_active(ldev); - spin_unlock(&lag_lock); + spin_unlock_irqrestore(&lag_lock, flags); return res; } @@ -1274,13 +1278,14 @@ EXPORT_SYMBOL(mlx5_lag_is_active); bool mlx5_lag_is_master(struct mlx5_core_dev *dev) { struct mlx5_lag *ldev; + unsigned long flags; bool res; - spin_lock(&lag_lock); + spin_lock_irqsave(&lag_lock, flags); ldev = mlx5_lag_dev(dev); res = ldev && __mlx5_lag_is_active(ldev) && dev == ldev->pf[MLX5_LAG_P1].dev; - spin_unlock(&lag_lock); + spin_unlock_irqrestore(&lag_lock, flags); return res; } @@ -1289,12 +1294,13 @@ EXPORT_SYMBOL(mlx5_lag_is_master); bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev) { struct mlx5_lag *ldev; + unsigned long flags; bool res; - spin_lock(&lag_lock); + spin_lock_irqsave(&lag_lock, flags); ldev = mlx5_lag_dev(dev); res = ldev && __mlx5_lag_is_sriov(ldev); - spin_unlock(&lag_lock); + spin_unlock_irqrestore(&lag_lock, flags); return res; } @@ -1303,13 +1309,14 @@ EXPORT_SYMBOL(mlx5_lag_is_sriov); bool mlx5_lag_is_shared_fdb(struct mlx5_core_dev *dev) { struct mlx5_lag *ldev; + unsigned long flags; bool res; - spin_lock(&lag_lock); + spin_lock_irqsave(&lag_lock, flags); ldev = mlx5_lag_dev(dev); res = ldev && __mlx5_lag_is_sriov(ldev) && test_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &ldev->mode_flags); - spin_unlock(&lag_lock); + spin_unlock_irqrestore(&lag_lock, flags); return res; } @@ -1352,9 +1359,10 @@ struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev) { struct net_device *ndev = NULL; struct mlx5_lag *ldev; + unsigned long flags; int i; - spin_lock(&lag_lock); + spin_lock_irqsave(&lag_lock, flags); ldev = mlx5_lag_dev(dev); if (!(ldev && __mlx5_lag_is_roce(ldev))) @@ -1373,7 +1381,7 @@ struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev) dev_hold(ndev); unlock: - spin_unlock(&lag_lock); + spin_unlock_irqrestore(&lag_lock, flags); return ndev; } @@ -1383,10 +1391,11 @@ u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev, struct net_device *slave) { struct mlx5_lag *ldev; + unsigned long flags; u8 port = 0; int i; - spin_lock(&lag_lock); + spin_lock_irqsave(&lag_lock, flags); ldev = mlx5_lag_dev(dev); if (!(ldev && __mlx5_lag_is_roce(ldev))) goto unlock; @@ -1401,7 +1410,7 @@ u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev, port = ldev->v2p_map[port * ldev->buckets]; unlock: - spin_unlock(&lag_lock); + spin_unlock_irqrestore(&lag_lock, flags); return port; } EXPORT_SYMBOL(mlx5_lag_get_slave_port); @@ -1422,8 +1431,9 @@ struct mlx5_core_dev *mlx5_lag_get_peer_mdev(struct mlx5_core_dev *dev) { struct mlx5_core_dev *peer_dev = NULL; struct mlx5_lag *ldev; + unsigned long flags; - spin_lock(&lag_lock); + spin_lock_irqsave(&lag_lock, flags); ldev = mlx5_lag_dev(dev); if (!ldev) goto unlock; @@ -1433,7 +1443,7 @@ struct mlx5_core_dev *mlx5_lag_get_peer_mdev(struct mlx5_core_dev *dev) ldev->pf[MLX5_LAG_P1].dev; unlock: - spin_unlock(&lag_lock); + spin_unlock_irqrestore(&lag_lock, flags); return peer_dev; } EXPORT_SYMBOL(mlx5_lag_get_peer_mdev); @@ -1446,6 +1456,7 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, int outlen = MLX5_ST_SZ_BYTES(query_cong_statistics_out); struct mlx5_core_dev **mdev; struct mlx5_lag *ldev; + unsigned long flags; int num_ports; int ret, i, j; void *out; @@ -1462,7 +1473,7 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, memset(values, 0, sizeof(*values) * num_counters); - spin_lock(&lag_lock); + spin_lock_irqsave(&lag_lock, flags); ldev = mlx5_lag_dev(dev); if (ldev && __mlx5_lag_is_active(ldev)) { num_ports = ldev->ports; @@ -1472,7 +1483,7 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, num_ports = 1; mdev[MLX5_LAG_P1] = dev; } - spin_unlock(&lag_lock); + spin_unlock_irqrestore(&lag_lock, flags); for (i = 0; i < num_ports; ++i) { u32 in[MLX5_ST_SZ_DW(query_cong_statistics_in)] = {}; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index bec8d6d0b5f6..c085b031abfc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1530,7 +1530,9 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx) memcpy(&dev->profile, &profile[profile_idx], sizeof(dev->profile)); INIT_LIST_HEAD(&priv->ctx_list); spin_lock_init(&priv->ctx_lock); + lockdep_register_key(&dev->lock_key); mutex_init(&dev->intf_state_mutex); + lockdep_set_class(&dev->intf_state_mutex, &dev->lock_key); mutex_init(&priv->bfregs.reg_head.lock); mutex_init(&priv->bfregs.wc_head.lock); @@ -1597,6 +1599,7 @@ err_timeout_init: mutex_destroy(&priv->bfregs.wc_head.lock); mutex_destroy(&priv->bfregs.reg_head.lock); mutex_destroy(&dev->intf_state_mutex); + lockdep_unregister_key(&dev->lock_key); return err; } @@ -1618,6 +1621,7 @@ void mlx5_mdev_uninit(struct mlx5_core_dev *dev) mutex_destroy(&priv->bfregs.wc_head.lock); mutex_destroy(&priv->bfregs.reg_head.lock); mutex_destroy(&dev->intf_state_mutex); + lockdep_unregister_key(&dev->lock_key); } static int probe_one(struct pci_dev *pdev, const struct pci_device_id *id) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index ec76a8b1acc1..60596357bfc7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -376,8 +376,8 @@ retry: goto out_dropped; } } + err = mlx5_cmd_check(dev, err, in, out); if (err) { - err = mlx5_cmd_check(dev, err, in, out); mlx5_core_warn(dev, "func_id 0x%x, npages %d, err %d\n", func_id, npages, err); goto out_dropped; @@ -524,10 +524,13 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u16 func_id, int npages, dev->priv.reclaim_pages_discard += npages; } /* if triggered by FW event and failed by FW then ignore */ - if (event && err == -EREMOTEIO) + if (event && err == -EREMOTEIO) { err = 0; + goto out_free; + } + + err = mlx5_cmd_check(dev, err, in, out); if (err) { - err = mlx5_cmd_check(dev, err, in, out); mlx5_core_err(dev, "failed reclaiming pages: err %d\n", err); goto out_free; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c index ee2e1b7c1310..c0e6c487c63c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c @@ -159,11 +159,11 @@ static int mlx5_sriov_enable(struct pci_dev *pdev, int num_vfs) devl_lock(devlink); err = mlx5_device_enable_sriov(dev, num_vfs); + devl_unlock(devlink); if (err) { mlx5_core_warn(dev, "mlx5_device_enable_sriov failed : %d\n", err); return err; } - devl_unlock(devlink); err = pci_enable_sriov(pdev, num_vfs); if (err) { diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c index 19009a6bd33a..9e57d23e57bf 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.c +++ b/drivers/net/ethernet/moxa/moxart_ether.c @@ -71,11 +71,6 @@ static int moxart_set_mac_address(struct net_device *ndev, void *addr) static void moxart_mac_free_memory(struct net_device *ndev) { struct moxart_mac_priv_t *priv = netdev_priv(ndev); - int i; - - for (i = 0; i < RX_DESC_NUM; i++) - dma_unmap_single(&priv->pdev->dev, priv->rx_mapping[i], - priv->rx_buf_size, DMA_FROM_DEVICE); if (priv->tx_desc_base) dma_free_coherent(&priv->pdev->dev, @@ -187,6 +182,7 @@ static int moxart_mac_open(struct net_device *ndev) static int moxart_mac_stop(struct net_device *ndev) { struct moxart_mac_priv_t *priv = netdev_priv(ndev); + int i; napi_disable(&priv->napi); @@ -198,6 +194,11 @@ static int moxart_mac_stop(struct net_device *ndev) /* disable all functions */ writel(0, priv->base + REG_MAC_CTRL); + /* unmap areas mapped in moxart_mac_setup_desc_ring() */ + for (i = 0; i < RX_DESC_NUM; i++) + dma_unmap_single(&priv->pdev->dev, priv->rx_mapping[i], + priv->rx_buf_size, DMA_FROM_DEVICE); + return 0; } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 1443f788ee37..0be79c516781 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -1564,8 +1564,67 @@ static int ionic_set_features(struct net_device *netdev, return err; } +static int ionic_set_attr_mac(struct ionic_lif *lif, u8 *mac) +{ + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.lif_setattr = { + .opcode = IONIC_CMD_LIF_SETATTR, + .index = cpu_to_le16(lif->index), + .attr = IONIC_LIF_ATTR_MAC, + }, + }; + + ether_addr_copy(ctx.cmd.lif_setattr.mac, mac); + return ionic_adminq_post_wait(lif, &ctx); +} + +static int ionic_get_attr_mac(struct ionic_lif *lif, u8 *mac_addr) +{ + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.lif_getattr = { + .opcode = IONIC_CMD_LIF_GETATTR, + .index = cpu_to_le16(lif->index), + .attr = IONIC_LIF_ATTR_MAC, + }, + }; + int err; + + err = ionic_adminq_post_wait(lif, &ctx); + if (err) + return err; + + ether_addr_copy(mac_addr, ctx.comp.lif_getattr.mac); + return 0; +} + +static int ionic_program_mac(struct ionic_lif *lif, u8 *mac) +{ + u8 get_mac[ETH_ALEN]; + int err; + + err = ionic_set_attr_mac(lif, mac); + if (err) + return err; + + err = ionic_get_attr_mac(lif, get_mac); + if (err) + return err; + + /* To deal with older firmware that silently ignores the set attr mac: + * doesn't actually change the mac and doesn't return an error, so we + * do the get attr to verify whether or not the set actually happened + */ + if (!ether_addr_equal(get_mac, mac)) + return 1; + + return 0; +} + static int ionic_set_mac_address(struct net_device *netdev, void *sa) { + struct ionic_lif *lif = netdev_priv(netdev); struct sockaddr *addr = sa; u8 *mac; int err; @@ -1574,6 +1633,14 @@ static int ionic_set_mac_address(struct net_device *netdev, void *sa) if (ether_addr_equal(netdev->dev_addr, mac)) return 0; + err = ionic_program_mac(lif, mac); + if (err < 0) + return err; + + if (err > 0) + netdev_dbg(netdev, "%s: SET and GET ATTR Mac are not equal-due to old FW running\n", + __func__); + err = eth_prepare_mac_addr_change(netdev, addr); if (err) return err; @@ -2963,6 +3030,9 @@ static void ionic_lif_handle_fw_up(struct ionic_lif *lif) mutex_lock(&lif->queue_lock); + if (test_and_clear_bit(IONIC_LIF_F_BROKEN, lif->state)) + dev_info(ionic->dev, "FW Up: clearing broken state\n"); + err = ionic_qcqs_alloc(lif); if (err) goto err_unlock; @@ -3169,6 +3239,7 @@ static int ionic_station_set(struct ionic_lif *lif) .attr = IONIC_LIF_ATTR_MAC, }, }; + u8 mac_address[ETH_ALEN]; struct sockaddr addr; int err; @@ -3177,8 +3248,23 @@ static int ionic_station_set(struct ionic_lif *lif) return err; netdev_dbg(lif->netdev, "found initial MAC addr %pM\n", ctx.comp.lif_getattr.mac); - if (is_zero_ether_addr(ctx.comp.lif_getattr.mac)) - return 0; + ether_addr_copy(mac_address, ctx.comp.lif_getattr.mac); + + if (is_zero_ether_addr(mac_address)) { + eth_hw_addr_random(netdev); + netdev_dbg(netdev, "Random Mac generated: %pM\n", netdev->dev_addr); + ether_addr_copy(mac_address, netdev->dev_addr); + + err = ionic_program_mac(lif, mac_address); + if (err < 0) + return err; + + if (err > 0) { + netdev_dbg(netdev, "%s:SET/GET ATTR Mac are not same-due to old FW running\n", + __func__); + return 0; + } + } if (!is_zero_ether_addr(netdev->dev_addr)) { /* If the netdev mac is non-zero and doesn't match the default @@ -3186,12 +3272,11 @@ static int ionic_station_set(struct ionic_lif *lif) * likely here again after a fw-upgrade reset. We need to be * sure the netdev mac is in our filter list. */ - if (!ether_addr_equal(ctx.comp.lif_getattr.mac, - netdev->dev_addr)) + if (!ether_addr_equal(mac_address, netdev->dev_addr)) ionic_lif_addr_add(lif, netdev->dev_addr); } else { /* Update the netdev mac with the device's mac */ - memcpy(addr.sa_data, ctx.comp.lif_getattr.mac, netdev->addr_len); + ether_addr_copy(addr.sa_data, mac_address); addr.sa_family = AF_INET; err = eth_prepare_mac_addr_change(netdev, &addr); if (err) { diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c index 4029b4e021f8..56f93b030551 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_main.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c @@ -474,8 +474,8 @@ try_again: ionic_opcode_to_str(opcode), opcode, ionic_error_to_str(err), err); - msleep(1000); iowrite32(0, &idev->dev_cmd_regs->done); + msleep(1000); iowrite32(1, &idev->dev_cmd_regs->doorbell); goto try_again; } @@ -488,6 +488,8 @@ try_again: return ionic_error_to_errno(err); } + ionic_dev_cmd_clean(ionic); + return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c index caa4bfc4c1d6..9b6138b11776 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c @@ -258,14 +258,18 @@ EXPORT_SYMBOL_GPL(stmmac_set_mac_addr); /* Enable disable MAC RX/TX */ void stmmac_set_mac(void __iomem *ioaddr, bool enable) { - u32 value = readl(ioaddr + MAC_CTRL_REG); + u32 old_val, value; + + old_val = readl(ioaddr + MAC_CTRL_REG); + value = old_val; if (enable) value |= MAC_ENABLE_RX | MAC_ENABLE_TX; else value &= ~(MAC_ENABLE_TX | MAC_ENABLE_RX); - writel(value, ioaddr + MAC_CTRL_REG); + if (value != old_val) + writel(value, ioaddr + MAC_CTRL_REG); } void stmmac_get_mac_addr(void __iomem *ioaddr, unsigned char *addr, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 070b5ef165eb..592d29abcb1c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -986,10 +986,10 @@ static void stmmac_mac_link_up(struct phylink_config *config, bool tx_pause, bool rx_pause) { struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev)); - u32 ctrl; + u32 old_ctrl, ctrl; - ctrl = readl(priv->ioaddr + MAC_CTRL_REG); - ctrl &= ~priv->hw->link.speed_mask; + old_ctrl = readl(priv->ioaddr + MAC_CTRL_REG); + ctrl = old_ctrl & ~priv->hw->link.speed_mask; if (interface == PHY_INTERFACE_MODE_USXGMII) { switch (speed) { @@ -1064,7 +1064,8 @@ static void stmmac_mac_link_up(struct phylink_config *config, if (tx_pause && rx_pause) stmmac_mac_flow_ctrl(priv, duplex); - writel(ctrl, priv->ioaddr + MAC_CTRL_REG); + if (ctrl != old_ctrl) + writel(ctrl, priv->ioaddr + MAC_CTRL_REG); stmmac_mac_set(priv, priv->ioaddr, true); if (phy && priv->dma_cap.eee) { diff --git a/drivers/net/ipa/ipa_mem.c b/drivers/net/ipa/ipa_mem.c index 1e9eae208e44..53a1dbeaffa6 100644 --- a/drivers/net/ipa/ipa_mem.c +++ b/drivers/net/ipa/ipa_mem.c @@ -568,7 +568,7 @@ static int ipa_smem_init(struct ipa *ipa, u32 item, size_t size) } /* Align the address down and the size up to a page boundary */ - addr = qcom_smem_virt_to_phys(virt) & PAGE_MASK; + addr = qcom_smem_virt_to_phys(virt); phys = addr & PAGE_MASK; size = PAGE_ALIGN(size + addr - phys); iova = phys; /* We just want a direct mapping */ diff --git a/drivers/net/ipvlan/ipvtap.c b/drivers/net/ipvlan/ipvtap.c index ef02f2cf5ce1..cbabca167a07 100644 --- a/drivers/net/ipvlan/ipvtap.c +++ b/drivers/net/ipvlan/ipvtap.c @@ -194,7 +194,7 @@ static struct notifier_block ipvtap_notifier_block __read_mostly = { .notifier_call = ipvtap_device_event, }; -static int ipvtap_init(void) +static int __init ipvtap_init(void) { int err; @@ -228,7 +228,7 @@ out1: } module_init(ipvtap_init); -static void ipvtap_exit(void) +static void __exit ipvtap_exit(void) { rtnl_link_unregister(&ipvtap_link_ops); unregister_netdevice_notifier(&ipvtap_notifier_block); diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index ee6087e7b2bf..c6d271e5687e 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -462,11 +462,6 @@ static struct macsec_eth_header *macsec_ethhdr(struct sk_buff *skb) return (struct macsec_eth_header *)skb_mac_header(skb); } -static sci_t dev_to_sci(struct net_device *dev, __be16 port) -{ - return make_sci(dev->dev_addr, port); -} - static void __macsec_pn_wrapped(struct macsec_secy *secy, struct macsec_tx_sa *tx_sa) { @@ -3661,7 +3656,6 @@ static int macsec_set_mac_address(struct net_device *dev, void *p) out: eth_hw_addr_set(dev, addr->sa_data); - macsec->secy.sci = dev_to_sci(dev, MACSEC_PORT_ES); /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) { @@ -4000,6 +3994,11 @@ static bool sci_exists(struct net_device *dev, sci_t sci) return false; } +static sci_t dev_to_sci(struct net_device *dev, __be16 port) +{ + return make_sci(dev->dev_addr, port); +} + static int macsec_add_dev(struct net_device *dev, sci_t sci, u8 icv_len) { struct macsec_dev *macsec = macsec_priv(dev); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 0c6efd792690..12ff276b80ae 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -316,11 +316,11 @@ static __maybe_unused int mdio_bus_phy_resume(struct device *dev) phydev->suspended_by_mdio_bus = 0; - /* If we managed to get here with the PHY state machine in a state other - * than PHY_HALTED this is an indication that something went wrong and - * we should most likely be using MAC managed PM and we are not. + /* If we manged to get here with the PHY state machine in a state neither + * PHY_HALTED nor PHY_READY this is an indication that something went wrong + * and we should most likely be using MAC managed PM and we are not. */ - WARN_ON(phydev->state != PHY_HALTED && !phydev->mac_managed_pm); + WARN_ON(phydev->state != PHY_HALTED && phydev->state != PHY_READY); ret = phy_init_hw(phydev); if (ret < 0) diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 0f6efaabaa32..d142ac8fcf6e 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -5906,6 +5906,11 @@ static void r8153_enter_oob(struct r8152 *tp) ocp_data &= ~NOW_IS_OOB; ocp_write_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL, ocp_data); + /* RX FIFO settings for OOB */ + ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RXFIFO_CTRL0, RXFIFO_THR1_OOB); + ocp_write_word(tp, MCU_TYPE_PLA, PLA_RXFIFO_CTRL1, RXFIFO_THR2_OOB); + ocp_write_word(tp, MCU_TYPE_PLA, PLA_RXFIFO_CTRL2, RXFIFO_THR3_OOB); + rtl_disable(tp); rtl_reset_bmu(tp); @@ -6431,21 +6436,8 @@ static void r8156_fc_parameter(struct r8152 *tp) u32 pause_on = tp->fc_pause_on ? tp->fc_pause_on : fc_pause_on_auto(tp); u32 pause_off = tp->fc_pause_off ? tp->fc_pause_off : fc_pause_off_auto(tp); - switch (tp->version) { - case RTL_VER_10: - case RTL_VER_11: - ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_FULL, pause_on / 8); - ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_EMPTY, pause_off / 8); - break; - case RTL_VER_12: - case RTL_VER_13: - case RTL_VER_15: - ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_FULL, pause_on / 16); - ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_EMPTY, pause_off / 16); - break; - default: - break; - } + ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_FULL, pause_on / 16); + ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_EMPTY, pause_off / 16); } static void rtl8156_change_mtu(struct r8152 *tp) @@ -6557,6 +6549,11 @@ static void rtl8156_down(struct r8152 *tp) ocp_data &= ~NOW_IS_OOB; ocp_write_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL, ocp_data); + /* RX FIFO settings for OOB */ + ocp_write_word(tp, MCU_TYPE_PLA, PLA_RXFIFO_FULL, 64 / 16); + ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_FULL, 1024 / 16); + ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_EMPTY, 4096 / 16); + rtl_disable(tp); rtl_reset_bmu(tp); diff --git a/drivers/nfc/pn533/uart.c b/drivers/nfc/pn533/uart.c index 2caf997f9bc9..07596bf5f7d6 100644 --- a/drivers/nfc/pn533/uart.c +++ b/drivers/nfc/pn533/uart.c @@ -310,6 +310,7 @@ static void pn532_uart_remove(struct serdev_device *serdev) pn53x_unregister_nfc(pn532->priv); serdev_device_close(serdev); pn53x_common_clean(pn532->priv); + del_timer_sync(&pn532->cmd_timeout); kfree_skb(pn532->recv_skb); kfree(pn532); } diff --git a/drivers/parisc/ccio-dma.c b/drivers/parisc/ccio-dma.c index 9be007c9420f..f223afe47d10 100644 --- a/drivers/parisc/ccio-dma.c +++ b/drivers/parisc/ccio-dma.c @@ -268,7 +268,7 @@ static int ioc_count; * Each bit can represent a number of pages. * LSbs represent lower addresses (IOVA's). * -* This was was copied from sba_iommu.c. Don't try to unify +* This was copied from sba_iommu.c. Don't try to unify * the two resource managers unless a way to have different * allocation policies is also adjusted. We'd like to avoid * I/O TLB thrashing by having resource allocation policy @@ -1380,15 +1380,17 @@ ccio_init_resource(struct resource *res, char *name, void __iomem *ioaddr) } } -static void __init ccio_init_resources(struct ioc *ioc) +static int __init ccio_init_resources(struct ioc *ioc) { struct resource *res = ioc->mmio_region; char *name = kmalloc(14, GFP_KERNEL); - + if (unlikely(!name)) + return -ENOMEM; snprintf(name, 14, "GSC Bus [%d/]", ioc->hw_path); ccio_init_resource(res, name, &ioc->ioc_regs->io_io_low); ccio_init_resource(res + 1, name, &ioc->ioc_regs->io_io_low_hv); + return 0; } static int new_ioc_area(struct resource *res, unsigned long size, @@ -1543,7 +1545,10 @@ static int __init ccio_probe(struct parisc_device *dev) return -ENOMEM; } ccio_ioc_init(ioc); - ccio_init_resources(ioc); + if (ccio_init_resources(ioc)) { + kfree(ioc); + return -ENOMEM; + } hppa_dma_ops = &ccio_ops; hba = kzalloc(sizeof(*hba), GFP_KERNEL); diff --git a/drivers/parisc/led.c b/drivers/parisc/led.c index 1e4a5663d011..d4be9d2ee74d 100644 --- a/drivers/parisc/led.c +++ b/drivers/parisc/led.c @@ -646,7 +646,7 @@ int lcd_print( const char *str ) cancel_delayed_work_sync(&led_task); /* copy display string to buffer for procfs */ - strlcpy(lcd_text, str, sizeof(lcd_text)); + strscpy(lcd_text, str, sizeof(lcd_text)); /* Set LCD Cursor to 1st character */ gsc_writeb(lcd_info.reset_cmd1, LCD_CMD_REG); diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index a3e117a4b8e7..f6c37a97544e 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -7153,22 +7153,18 @@ static int megasas_alloc_ctrl_mem(struct megasas_instance *instance) switch (instance->adapter_type) { case MFI_SERIES: if (megasas_alloc_mfi_ctrl_mem(instance)) - goto fail; + return -ENOMEM; break; case AERO_SERIES: case VENTURA_SERIES: case THUNDERBOLT_SERIES: case INVADER_SERIES: if (megasas_alloc_fusion_context(instance)) - goto fail; + return -ENOMEM; break; } return 0; - fail: - kfree(instance->reply_map); - instance->reply_map = NULL; - return -ENOMEM; } /* diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c index e48d4261d0bc..09c5fe37754c 100644 --- a/drivers/scsi/megaraid/megaraid_sas_fusion.c +++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c @@ -5310,7 +5310,6 @@ megasas_alloc_fusion_context(struct megasas_instance *instance) if (!fusion->log_to_span) { dev_err(&instance->pdev->dev, "Failed from %s %d\n", __func__, __LINE__); - kfree(instance->ctrl_context); return -ENOMEM; } } diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 2b2f68288375..62666df1a59e 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -6935,14 +6935,8 @@ qlt_24xx_config_rings(struct scsi_qla_host *vha) if (ha->flags.msix_enabled) { if (IS_QLA83XX(ha) || IS_QLA27XX(ha) || IS_QLA28XX(ha)) { - if (IS_QLA2071(ha)) { - /* 4 ports Baker: Enable Interrupt Handshake */ - icb->msix_atio = 0; - icb->firmware_options_2 |= cpu_to_le32(BIT_26); - } else { - icb->msix_atio = cpu_to_le16(msix->entry); - icb->firmware_options_2 &= cpu_to_le32(~BIT_26); - } + icb->msix_atio = cpu_to_le16(msix->entry); + icb->firmware_options_2 &= cpu_to_le32(~BIT_26); ql_dbg(ql_dbg_init, vha, 0xf072, "Registering ICB vector 0x%x for atio que.\n", msix->entry); diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 4dbd29ab1dcc..ef08029a0079 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -111,7 +111,7 @@ scsi_set_blocked(struct scsi_cmnd *cmd, int reason) } } -static void scsi_mq_requeue_cmd(struct scsi_cmnd *cmd) +static void scsi_mq_requeue_cmd(struct scsi_cmnd *cmd, unsigned long msecs) { struct request *rq = scsi_cmd_to_rq(cmd); @@ -121,7 +121,12 @@ static void scsi_mq_requeue_cmd(struct scsi_cmnd *cmd) } else { WARN_ON_ONCE(true); } - blk_mq_requeue_request(rq, true); + + if (msecs) { + blk_mq_requeue_request(rq, false); + blk_mq_delay_kick_requeue_list(rq->q, msecs); + } else + blk_mq_requeue_request(rq, true); } /** @@ -651,14 +656,6 @@ static unsigned int scsi_rq_err_bytes(const struct request *rq) return bytes; } -/* Helper for scsi_io_completion() when "reprep" action required. */ -static void scsi_io_completion_reprep(struct scsi_cmnd *cmd, - struct request_queue *q) -{ - /* A new command will be prepared and issued. */ - scsi_mq_requeue_cmd(cmd); -} - static bool scsi_cmd_runtime_exceeced(struct scsi_cmnd *cmd) { struct request *req = scsi_cmd_to_rq(cmd); @@ -676,14 +673,21 @@ static bool scsi_cmd_runtime_exceeced(struct scsi_cmnd *cmd) return false; } +/* + * When ALUA transition state is returned, reprep the cmd to + * use the ALUA handler's transition timeout. Delay the reprep + * 1 sec to avoid aggressive retries of the target in that + * state. + */ +#define ALUA_TRANSITION_REPREP_DELAY 1000 + /* Helper for scsi_io_completion() when special action required. */ static void scsi_io_completion_action(struct scsi_cmnd *cmd, int result) { - struct request_queue *q = cmd->device->request_queue; struct request *req = scsi_cmd_to_rq(cmd); int level = 0; - enum {ACTION_FAIL, ACTION_REPREP, ACTION_RETRY, - ACTION_DELAYED_RETRY} action; + enum {ACTION_FAIL, ACTION_REPREP, ACTION_DELAYED_REPREP, + ACTION_RETRY, ACTION_DELAYED_RETRY} action; struct scsi_sense_hdr sshdr; bool sense_valid; bool sense_current = true; /* false implies "deferred sense" */ @@ -772,8 +776,8 @@ static void scsi_io_completion_action(struct scsi_cmnd *cmd, int result) action = ACTION_DELAYED_RETRY; break; case 0x0a: /* ALUA state transition */ - blk_stat = BLK_STS_TRANSPORT; - fallthrough; + action = ACTION_DELAYED_REPREP; + break; default: action = ACTION_FAIL; break; @@ -832,7 +836,10 @@ static void scsi_io_completion_action(struct scsi_cmnd *cmd, int result) return; fallthrough; case ACTION_REPREP: - scsi_io_completion_reprep(cmd, q); + scsi_mq_requeue_cmd(cmd, 0); + break; + case ACTION_DELAYED_REPREP: + scsi_mq_requeue_cmd(cmd, ALUA_TRANSITION_REPREP_DELAY); break; case ACTION_RETRY: /* Retry the same command immediately */ @@ -926,7 +933,7 @@ static int scsi_io_completion_nz_result(struct scsi_cmnd *cmd, int result, * command block will be released and the queue function will be goosed. If we * are not done then we have to figure out what to do next: * - * a) We can call scsi_io_completion_reprep(). The request will be + * a) We can call scsi_mq_requeue_cmd(). The request will be * unprepared and put back on the queue. Then a new command will * be created for it. This should be used if we made forward * progress, or if we want to switch from READ(10) to READ(6) for @@ -942,7 +949,6 @@ static int scsi_io_completion_nz_result(struct scsi_cmnd *cmd, int result, void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) { int result = cmd->result; - struct request_queue *q = cmd->device->request_queue; struct request *req = scsi_cmd_to_rq(cmd); blk_status_t blk_stat = BLK_STS_OK; @@ -979,7 +985,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) * request just queue the command up again. */ if (likely(result == 0)) - scsi_io_completion_reprep(cmd, q); + scsi_mq_requeue_cmd(cmd, 0); else scsi_io_completion_action(cmd, result); } @@ -1542,7 +1548,6 @@ static blk_status_t scsi_prepare_cmd(struct request *req) scsi_init_command(sdev, cmd); cmd->eh_eflags = 0; - cmd->allowed = 0; cmd->prot_type = 0; cmd->prot_flags = 0; cmd->submitter = 0; @@ -1593,6 +1598,8 @@ static blk_status_t scsi_prepare_cmd(struct request *req) return ret; } + /* Usually overridden by the ULP */ + cmd->allowed = 0; memset(cmd->cmnd, 0, sizeof(cmd->cmnd)); return scsi_cmd_to_driver(cmd)->init_command(cmd); } diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 8f79fa6318fe..eb76ba055021 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -103,7 +103,6 @@ static void sd_config_discard(struct scsi_disk *, unsigned int); static void sd_config_write_same(struct scsi_disk *); static int sd_revalidate_disk(struct gendisk *); static void sd_unlock_native_capacity(struct gendisk *disk); -static void sd_start_done_work(struct work_struct *work); static int sd_probe(struct device *); static int sd_remove(struct device *); static void sd_shutdown(struct device *); @@ -3471,7 +3470,6 @@ static int sd_probe(struct device *dev) sdkp->max_retries = SD_MAX_RETRIES; atomic_set(&sdkp->openers, 0); atomic_set(&sdkp->device->ioerr_cnt, 0); - INIT_WORK(&sdkp->start_done_work, sd_start_done_work); if (!sdp->request_queue->rq_timeout) { if (sdp->type != TYPE_MOD) @@ -3594,69 +3592,12 @@ static void scsi_disk_release(struct device *dev) kfree(sdkp); } -/* Process sense data after a START command finished. */ -static void sd_start_done_work(struct work_struct *work) -{ - struct scsi_disk *sdkp = container_of(work, typeof(*sdkp), - start_done_work); - struct scsi_sense_hdr sshdr; - int res = sdkp->start_result; - - if (res == 0) - return; - - sd_print_result(sdkp, "Start/Stop Unit failed", res); - - if (res < 0) - return; - - if (scsi_normalize_sense(sdkp->start_sense_buffer, - sdkp->start_sense_len, &sshdr)) - sd_print_sense_hdr(sdkp, &sshdr); -} - -/* A START command finished. May be called from interrupt context. */ -static void sd_start_done(struct request *req, blk_status_t status) -{ - const struct scsi_cmnd *scmd = blk_mq_rq_to_pdu(req); - struct scsi_disk *sdkp = scsi_disk(req->q->disk); - - sdkp->start_result = scmd->result; - WARN_ON_ONCE(scmd->sense_len > SCSI_SENSE_BUFFERSIZE); - sdkp->start_sense_len = scmd->sense_len; - memcpy(sdkp->start_sense_buffer, scmd->sense_buffer, - ARRAY_SIZE(sdkp->start_sense_buffer)); - WARN_ON_ONCE(!schedule_work(&sdkp->start_done_work)); -} - -/* Submit a START command asynchronously. */ -static int sd_submit_start(struct scsi_disk *sdkp, u8 cmd[], u8 cmd_len) -{ - struct scsi_device *sdev = sdkp->device; - struct request_queue *q = sdev->request_queue; - struct request *req; - struct scsi_cmnd *scmd; - - req = scsi_alloc_request(q, REQ_OP_DRV_IN, BLK_MQ_REQ_PM); - if (IS_ERR(req)) - return PTR_ERR(req); - - scmd = blk_mq_rq_to_pdu(req); - scmd->cmd_len = cmd_len; - memcpy(scmd->cmnd, cmd, cmd_len); - scmd->allowed = sdkp->max_retries; - req->timeout = SD_TIMEOUT; - req->rq_flags |= RQF_PM | RQF_QUIET; - req->end_io = sd_start_done; - blk_execute_rq_nowait(req, /*at_head=*/true); - - return 0; -} - static int sd_start_stop_device(struct scsi_disk *sdkp, int start) { unsigned char cmd[6] = { START_STOP }; /* START_VALID */ + struct scsi_sense_hdr sshdr; struct scsi_device *sdp = sdkp->device; + int res; if (start) cmd[4] |= 1; /* START */ @@ -3667,10 +3608,23 @@ static int sd_start_stop_device(struct scsi_disk *sdkp, int start) if (!scsi_device_online(sdp)) return -ENODEV; - /* Wait until processing of sense data has finished. */ - flush_work(&sdkp->start_done_work); + res = scsi_execute(sdp, cmd, DMA_NONE, NULL, 0, NULL, &sshdr, + SD_TIMEOUT, sdkp->max_retries, 0, RQF_PM, NULL); + if (res) { + sd_print_result(sdkp, "Start/Stop Unit failed", res); + if (res > 0 && scsi_sense_valid(&sshdr)) { + sd_print_sense_hdr(sdkp, &sshdr); + /* 0x3a is medium not present */ + if (sshdr.asc == 0x3a) + res = 0; + } + } - return sd_submit_start(sdkp, cmd, sizeof(cmd)); + /* SCSI error codes must not go to the generic layer */ + if (res) + return -EIO; + + return 0; } /* @@ -3697,8 +3651,6 @@ static void sd_shutdown(struct device *dev) sd_printk(KERN_NOTICE, sdkp, "Stopping disk\n"); sd_start_stop_device(sdkp, 0); } - - flush_work(&sdkp->start_done_work); } static int sd_suspend_common(struct device *dev, bool ignore_stop_errors) diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h index b89187761d61..5eea762f84d1 100644 --- a/drivers/scsi/sd.h +++ b/drivers/scsi/sd.h @@ -150,11 +150,6 @@ struct scsi_disk { unsigned urswrz : 1; unsigned security : 1; unsigned ignore_medium_access_errors : 1; - - int start_result; - u32 start_sense_len; - u8 start_sense_buffer[SCSI_SENSE_BUFFERSIZE]; - struct work_struct start_done_work; }; #define to_scsi_disk(obj) container_of(obj, struct scsi_disk, disk_dev) diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index fe000da11332..8ced292c4b96 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -2012,7 +2012,7 @@ static int storvsc_probe(struct hv_device *device, */ host_dev->handle_error_wq = alloc_ordered_workqueue("storvsc_error_wq_%d", - WQ_MEM_RECLAIM, + 0, host->host_no); if (!host_dev->handle_error_wq) { ret = -ENOMEM; diff --git a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c index 80d4e0676083..365489bf4b8c 100644 --- a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c +++ b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c @@ -527,7 +527,7 @@ static void int3400_setup_gddv(struct int3400_thermal_priv *priv) priv->data_vault = kmemdup(obj->package.elements[0].buffer.pointer, obj->package.elements[0].buffer.length, GFP_KERNEL); - if (!priv->data_vault) + if (ZERO_OR_NULL_PTR(priv->data_vault)) goto out_free; bin_attr_data_vault.private = priv->data_vault; @@ -597,7 +597,7 @@ static int int3400_thermal_probe(struct platform_device *pdev) goto free_imok; } - if (priv->data_vault) { + if (!ZERO_OR_NULL_PTR(priv->data_vault)) { result = sysfs_create_group(&pdev->dev.kobj, &data_attribute_group); if (result) @@ -615,7 +615,8 @@ static int int3400_thermal_probe(struct platform_device *pdev) free_sysfs: cleanup_odvp(priv); if (priv->data_vault) { - sysfs_remove_group(&pdev->dev.kobj, &data_attribute_group); + if (!ZERO_OR_NULL_PTR(priv->data_vault)) + sysfs_remove_group(&pdev->dev.kobj, &data_attribute_group); kfree(priv->data_vault); } free_uuid: @@ -647,7 +648,7 @@ static int int3400_thermal_remove(struct platform_device *pdev) if (!priv->rel_misc_dev_res) acpi_thermal_rel_misc_device_remove(priv->adev->handle); - if (priv->data_vault) + if (!ZERO_OR_NULL_PTR(priv->data_vault)) sysfs_remove_group(&pdev->dev.kobj, &data_attribute_group); sysfs_remove_group(&pdev->dev.kobj, &uuid_attribute_group); sysfs_remove_group(&pdev->dev.kobj, &imok_attribute_group); diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 6a5d0ae5d7a4..50d50cec7774 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -1329,6 +1329,7 @@ free_tz: kfree(tz); return ERR_PTR(result); } +EXPORT_SYMBOL_GPL(thermal_zone_device_register_with_trips); struct thermal_zone_device *thermal_zone_device_register(const char *type, int ntrips, int mask, void *devdata, struct thermal_zone_device_ops *ops, diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 6bc679d22927..a202d7d5240d 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -8741,6 +8741,8 @@ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba, struct scsi_device *sdp; unsigned long flags; int ret, retries; + unsigned long deadline; + int32_t remaining; spin_lock_irqsave(hba->host->host_lock, flags); sdp = hba->ufs_device_wlun; @@ -8773,9 +8775,14 @@ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba, * callbacks hence set the RQF_PM flag so that it doesn't resume the * already suspended childs. */ + deadline = jiffies + 10 * HZ; for (retries = 3; retries > 0; --retries) { + ret = -ETIMEDOUT; + remaining = deadline - jiffies; + if (remaining <= 0) + break; ret = scsi_execute(sdp, cmd, DMA_NONE, NULL, 0, NULL, &sshdr, - START_STOP_TIMEOUT, 0, 0, RQF_PM, NULL); + remaining / HZ, 0, 0, RQF_PM, NULL); if (!scsi_status_is_check_condition(ret) || !scsi_sense_valid(&sshdr) || sshdr.sense_key != UNIT_ATTENTION) diff --git a/drivers/ufs/host/ufs-exynos.c b/drivers/ufs/host/ufs-exynos.c index eced97538082..c3628a8645a5 100644 --- a/drivers/ufs/host/ufs-exynos.c +++ b/drivers/ufs/host/ufs-exynos.c @@ -1711,7 +1711,7 @@ static struct exynos_ufs_uic_attr fsd_uic_attr = { .pa_dbg_option_suite = 0x2E820183, }; -struct exynos_ufs_drv_data fsd_ufs_drvs = { +static const struct exynos_ufs_drv_data fsd_ufs_drvs = { .uic_attr = &fsd_uic_attr, .quirks = UFSHCD_QUIRK_PRDT_BYTE_GRAN | UFSHCI_QUIRK_BROKEN_REQ_LIST_CLR | diff --git a/drivers/video/console/sticore.c b/drivers/video/console/sticore.c index bd4dc97d4d34..db568f67e4dc 100644 --- a/drivers/video/console/sticore.c +++ b/drivers/video/console/sticore.c @@ -290,7 +290,7 @@ static char default_sti_path[21] __read_mostly; static int __init sti_setup(char *str) { if (str) - strlcpy (default_sti_path, str, sizeof (default_sti_path)); + strscpy(default_sti_path, str, sizeof(default_sti_path)); return 1; } diff --git a/drivers/video/fbdev/aty/atyfb_base.c b/drivers/video/fbdev/aty/atyfb_base.c index a3e6faed7745..14eb718bd67c 100644 --- a/drivers/video/fbdev/aty/atyfb_base.c +++ b/drivers/video/fbdev/aty/atyfb_base.c @@ -3891,7 +3891,7 @@ static int __init atyfb_setup(char *options) && (!strncmp(this_opt, "Mach64:", 7))) { static unsigned char m64_num; static char mach64_str[80]; - strlcpy(mach64_str, this_opt + 7, sizeof(mach64_str)); + strscpy(mach64_str, this_opt + 7, sizeof(mach64_str)); if (!store_video_par(mach64_str, m64_num)) { m64_num++; mach64_count = m64_num; diff --git a/drivers/video/fbdev/aty/radeon_base.c b/drivers/video/fbdev/aty/radeon_base.c index 6851f47613e1..a14a8d73035c 100644 --- a/drivers/video/fbdev/aty/radeon_base.c +++ b/drivers/video/fbdev/aty/radeon_base.c @@ -1980,7 +1980,7 @@ static int radeon_set_fbinfo(struct radeonfb_info *rinfo) info->screen_base = rinfo->fb_base; info->screen_size = rinfo->mapped_vram; /* Fill fix common fields */ - strlcpy(info->fix.id, rinfo->name, sizeof(info->fix.id)); + strscpy(info->fix.id, rinfo->name, sizeof(info->fix.id)); info->fix.smem_start = rinfo->fb_base_phys; info->fix.smem_len = rinfo->video_ram; info->fix.type = FB_TYPE_PACKED_PIXELS; @@ -2094,34 +2094,34 @@ static void radeon_identify_vram(struct radeonfb_info *rinfo) u32 tmp; /* framebuffer size */ - if ((rinfo->family == CHIP_FAMILY_RS100) || + if ((rinfo->family == CHIP_FAMILY_RS100) || (rinfo->family == CHIP_FAMILY_RS200) || (rinfo->family == CHIP_FAMILY_RS300) || (rinfo->family == CHIP_FAMILY_RC410) || (rinfo->family == CHIP_FAMILY_RS400) || (rinfo->family == CHIP_FAMILY_RS480) ) { - u32 tom = INREG(NB_TOM); - tmp = ((((tom >> 16) - (tom & 0xffff) + 1) << 6) * 1024); - - radeon_fifo_wait(6); - OUTREG(MC_FB_LOCATION, tom); - OUTREG(DISPLAY_BASE_ADDR, (tom & 0xffff) << 16); - OUTREG(CRTC2_DISPLAY_BASE_ADDR, (tom & 0xffff) << 16); - OUTREG(OV0_BASE_ADDR, (tom & 0xffff) << 16); - - /* This is supposed to fix the crtc2 noise problem. */ - OUTREG(GRPH2_BUFFER_CNTL, INREG(GRPH2_BUFFER_CNTL) & ~0x7f0000); - - if ((rinfo->family == CHIP_FAMILY_RS100) || - (rinfo->family == CHIP_FAMILY_RS200)) { - /* This is to workaround the asic bug for RMX, some versions - of BIOS doesn't have this register initialized correctly. - */ - OUTREGP(CRTC_MORE_CNTL, CRTC_H_CUTOFF_ACTIVE_EN, - ~CRTC_H_CUTOFF_ACTIVE_EN); - } - } else { - tmp = INREG(CNFG_MEMSIZE); + u32 tom = INREG(NB_TOM); + + tmp = ((((tom >> 16) - (tom & 0xffff) + 1) << 6) * 1024); + radeon_fifo_wait(6); + OUTREG(MC_FB_LOCATION, tom); + OUTREG(DISPLAY_BASE_ADDR, (tom & 0xffff) << 16); + OUTREG(CRTC2_DISPLAY_BASE_ADDR, (tom & 0xffff) << 16); + OUTREG(OV0_BASE_ADDR, (tom & 0xffff) << 16); + + /* This is supposed to fix the crtc2 noise problem. */ + OUTREG(GRPH2_BUFFER_CNTL, INREG(GRPH2_BUFFER_CNTL) & ~0x7f0000); + + if ((rinfo->family == CHIP_FAMILY_RS100) || + (rinfo->family == CHIP_FAMILY_RS200)) { + /* This is to workaround the asic bug for RMX, some versions + * of BIOS doesn't have this register initialized correctly. + */ + OUTREGP(CRTC_MORE_CNTL, CRTC_H_CUTOFF_ACTIVE_EN, + ~CRTC_H_CUTOFF_ACTIVE_EN); + } + } else { + tmp = INREG(CNFG_MEMSIZE); } /* mem size is bits [28:0], mask off the rest */ diff --git a/drivers/video/fbdev/bw2.c b/drivers/video/fbdev/bw2.c index e7702fe1fe7d..6403ae07970d 100644 --- a/drivers/video/fbdev/bw2.c +++ b/drivers/video/fbdev/bw2.c @@ -182,7 +182,7 @@ static int bw2_ioctl(struct fb_info *info, unsigned int cmd, unsigned long arg) static void bw2_init_fix(struct fb_info *info, int linebytes) { - strlcpy(info->fix.id, "bwtwo", sizeof(info->fix.id)); + strscpy(info->fix.id, "bwtwo", sizeof(info->fix.id)); info->fix.type = FB_TYPE_PACKED_PIXELS; info->fix.visual = FB_VISUAL_MONO01; diff --git a/drivers/video/fbdev/chipsfb.c b/drivers/video/fbdev/chipsfb.c index 393894af26f8..2b00a9d554fc 100644 --- a/drivers/video/fbdev/chipsfb.c +++ b/drivers/video/fbdev/chipsfb.c @@ -430,6 +430,7 @@ static int chipsfb_pci_init(struct pci_dev *dp, const struct pci_device_id *ent) err_release_fb: framebuffer_release(p); err_disable: + pci_disable_device(dp); err_out: return rc; } diff --git a/drivers/video/fbdev/cirrusfb.c b/drivers/video/fbdev/cirrusfb.c index a41a75841e10..2a9fa06881b5 100644 --- a/drivers/video/fbdev/cirrusfb.c +++ b/drivers/video/fbdev/cirrusfb.c @@ -1999,7 +1999,7 @@ static int cirrusfb_set_fbinfo(struct fb_info *info) } /* Fill fix common fields */ - strlcpy(info->fix.id, cirrusfb_board_info[cinfo->btype].name, + strscpy(info->fix.id, cirrusfb_board_info[cinfo->btype].name, sizeof(info->fix.id)); /* monochrome: only 1 memory plane */ diff --git a/drivers/video/fbdev/clps711x-fb.c b/drivers/video/fbdev/clps711x-fb.c index 771ce1f76951..a1061c2f1640 100644 --- a/drivers/video/fbdev/clps711x-fb.c +++ b/drivers/video/fbdev/clps711x-fb.c @@ -326,7 +326,7 @@ static int clps711x_fb_probe(struct platform_device *pdev) info->var.vmode = FB_VMODE_NONINTERLACED; info->fix.type = FB_TYPE_PACKED_PIXELS; info->fix.accel = FB_ACCEL_NONE; - strlcpy(info->fix.id, CLPS711X_FB_NAME, sizeof(info->fix.id)); + strscpy(info->fix.id, CLPS711X_FB_NAME, sizeof(info->fix.id)); fb_videomode_to_var(&info->var, &cfb->mode); ret = fb_alloc_cmap(&info->cmap, BIT(CLPS711X_FB_BPP_MAX), 0); diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index cf9ac4da0a82..098b62f7b701 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -412,7 +412,7 @@ static int __init fb_console_setup(char *this_opt) while ((options = strsep(&this_opt, ",")) != NULL) { if (!strncmp(options, "font:", 5)) { - strlcpy(fontname, options + 5, sizeof(fontname)); + strscpy(fontname, options + 5, sizeof(fontname)); continue; } @@ -2401,15 +2401,21 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount, struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_ops *ops = info->fbcon_par; struct fbcon_display *p = &fb_display[vc->vc_num]; - int resize; + int resize, ret, old_userfont, old_width, old_height, old_charcount; char *old_data = NULL; resize = (w != vc->vc_font.width) || (h != vc->vc_font.height); if (p->userfont) old_data = vc->vc_font.data; vc->vc_font.data = (void *)(p->fontdata = data); + old_userfont = p->userfont; if ((p->userfont = userfont)) REFCOUNT(data)++; + + old_width = vc->vc_font.width; + old_height = vc->vc_font.height; + old_charcount = vc->vc_font.charcount; + vc->vc_font.width = w; vc->vc_font.height = h; vc->vc_font.charcount = charcount; @@ -2425,7 +2431,9 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount, rows = FBCON_SWAP(ops->rotate, info->var.yres, info->var.xres); cols /= w; rows /= h; - vc_resize(vc, cols, rows); + ret = vc_resize(vc, cols, rows); + if (ret) + goto err_out; } else if (con_is_visible(vc) && vc->vc_mode == KD_TEXT) { fbcon_clear_margins(vc, 0); @@ -2435,6 +2443,21 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount, if (old_data && (--REFCOUNT(old_data) == 0)) kfree(old_data - FONT_EXTRA_WORDS * sizeof(int)); return 0; + +err_out: + p->fontdata = old_data; + vc->vc_font.data = (void *)old_data; + + if (userfont) { + p->userfont = old_userfont; + REFCOUNT(data)--; + } + + vc->vc_font.width = old_width; + vc->vc_font.height = old_height; + vc->vc_font.charcount = old_charcount; + + return ret; } /* diff --git a/drivers/video/fbdev/core/fbsysfs.c b/drivers/video/fbdev/core/fbsysfs.c index c2a60b187467..4d7f63892dcc 100644 --- a/drivers/video/fbdev/core/fbsysfs.c +++ b/drivers/video/fbdev/core/fbsysfs.c @@ -84,6 +84,10 @@ void framebuffer_release(struct fb_info *info) if (WARN_ON(refcount_read(&info->count))) return; +#if IS_ENABLED(CONFIG_FB_BACKLIGHT) + mutex_destroy(&info->bl_curve_mutex); +#endif + kfree(info->apertures); kfree(info); } diff --git a/drivers/video/fbdev/cyber2000fb.c b/drivers/video/fbdev/cyber2000fb.c index d45355b9a58c..8f041f9b14c7 100644 --- a/drivers/video/fbdev/cyber2000fb.c +++ b/drivers/video/fbdev/cyber2000fb.c @@ -1134,7 +1134,7 @@ int cyber2000fb_attach(struct cyberpro_info *info, int idx) info->fb_size = int_cfb_info->fb.fix.smem_len; info->info = int_cfb_info; - strlcpy(info->dev_name, int_cfb_info->fb.fix.id, + strscpy(info->dev_name, int_cfb_info->fb.fix.id, sizeof(info->dev_name)); } @@ -1229,7 +1229,7 @@ static int cyber2000fb_ddc_getsda(void *data) static int cyber2000fb_setup_ddc_bus(struct cfb_info *cfb) { - strlcpy(cfb->ddc_adapter.name, cfb->fb.fix.id, + strscpy(cfb->ddc_adapter.name, cfb->fb.fix.id, sizeof(cfb->ddc_adapter.name)); cfb->ddc_adapter.owner = THIS_MODULE; cfb->ddc_adapter.class = I2C_CLASS_DDC; @@ -1304,7 +1304,7 @@ static int cyber2000fb_i2c_getscl(void *data) static int cyber2000fb_i2c_register(struct cfb_info *cfb) { - strlcpy(cfb->i2c_adapter.name, cfb->fb.fix.id, + strscpy(cfb->i2c_adapter.name, cfb->fb.fix.id, sizeof(cfb->i2c_adapter.name)); cfb->i2c_adapter.owner = THIS_MODULE; cfb->i2c_adapter.algo_data = &cfb->i2c_algo; @@ -1500,7 +1500,7 @@ static int cyber2000fb_setup(char *options) if (strncmp(opt, "font:", 5) == 0) { static char default_font_storage[40]; - strlcpy(default_font_storage, opt + 5, + strscpy(default_font_storage, opt + 5, sizeof(default_font_storage)); default_font = default_font_storage; continue; diff --git a/drivers/video/fbdev/ffb.c b/drivers/video/fbdev/ffb.c index b3d580e57221..7cba3969a970 100644 --- a/drivers/video/fbdev/ffb.c +++ b/drivers/video/fbdev/ffb.c @@ -883,7 +883,7 @@ static void ffb_init_fix(struct fb_info *info) } else ffb_type_name = "Elite 3D"; - strlcpy(info->fix.id, ffb_type_name, sizeof(info->fix.id)); + strscpy(info->fix.id, ffb_type_name, sizeof(info->fix.id)); info->fix.type = FB_TYPE_PACKED_PIXELS; info->fix.visual = FB_VISUAL_TRUECOLOR; diff --git a/drivers/video/fbdev/geode/gx1fb_core.c b/drivers/video/fbdev/geode/gx1fb_core.c index 5d34d89fb665..e41204ecb0e3 100644 --- a/drivers/video/fbdev/geode/gx1fb_core.c +++ b/drivers/video/fbdev/geode/gx1fb_core.c @@ -410,13 +410,13 @@ static void __init gx1fb_setup(char *options) continue; if (!strncmp(this_opt, "mode:", 5)) - strlcpy(mode_option, this_opt + 5, sizeof(mode_option)); + strscpy(mode_option, this_opt + 5, sizeof(mode_option)); else if (!strncmp(this_opt, "crt:", 4)) crt_option = !!simple_strtoul(this_opt + 4, NULL, 0); else if (!strncmp(this_opt, "panel:", 6)) - strlcpy(panel_option, this_opt + 6, sizeof(panel_option)); + strscpy(panel_option, this_opt + 6, sizeof(panel_option)); else - strlcpy(mode_option, this_opt, sizeof(mode_option)); + strscpy(mode_option, this_opt, sizeof(mode_option)); } } #endif diff --git a/drivers/video/fbdev/gxt4500.c b/drivers/video/fbdev/gxt4500.c index e5475ae1e158..94588b809ebf 100644 --- a/drivers/video/fbdev/gxt4500.c +++ b/drivers/video/fbdev/gxt4500.c @@ -650,7 +650,7 @@ static int gxt4500_probe(struct pci_dev *pdev, const struct pci_device_id *ent) cardtype = ent->driver_data; par->refclk_ps = cardinfo[cardtype].refclk_ps; info->fix = gxt4500_fix; - strlcpy(info->fix.id, cardinfo[cardtype].cardname, + strscpy(info->fix.id, cardinfo[cardtype].cardname, sizeof(info->fix.id)); info->pseudo_palette = par->pseudo_palette; diff --git a/drivers/video/fbdev/i740fb.c b/drivers/video/fbdev/i740fb.c index 7f09a0daaaa2..bd30d8314b68 100644 --- a/drivers/video/fbdev/i740fb.c +++ b/drivers/video/fbdev/i740fb.c @@ -159,7 +159,7 @@ static int i740fb_setup_ddc_bus(struct fb_info *info) { struct i740fb_par *par = info->par; - strlcpy(par->ddc_adapter.name, info->fix.id, + strscpy(par->ddc_adapter.name, info->fix.id, sizeof(par->ddc_adapter.name)); par->ddc_adapter.owner = THIS_MODULE; par->ddc_adapter.class = I2C_CLASS_DDC; diff --git a/drivers/video/fbdev/imxfb.c b/drivers/video/fbdev/imxfb.c index d97d7456d15a..94f3bc637fc8 100644 --- a/drivers/video/fbdev/imxfb.c +++ b/drivers/video/fbdev/imxfb.c @@ -681,7 +681,7 @@ static int imxfb_init_fbinfo(struct platform_device *pdev) fbi->devtype = pdev->id_entry->driver_data; - strlcpy(info->fix.id, IMX_NAME, sizeof(info->fix.id)); + strscpy(info->fix.id, IMX_NAME, sizeof(info->fix.id)); info->fix.type = FB_TYPE_PACKED_PIXELS; info->fix.type_aux = 0; diff --git a/drivers/video/fbdev/matrox/matroxfb_base.c b/drivers/video/fbdev/matrox/matroxfb_base.c index 236521b19daf..68bba2688f4c 100644 --- a/drivers/video/fbdev/matrox/matroxfb_base.c +++ b/drivers/video/fbdev/matrox/matroxfb_base.c @@ -2383,9 +2383,9 @@ static int __init matroxfb_setup(char *options) { else if (!strncmp(this_opt, "mem:", 4)) mem = simple_strtoul(this_opt+4, NULL, 0); else if (!strncmp(this_opt, "mode:", 5)) - strlcpy(videomode, this_opt+5, sizeof(videomode)); + strscpy(videomode, this_opt + 5, sizeof(videomode)); else if (!strncmp(this_opt, "outputs:", 8)) - strlcpy(outputs, this_opt+8, sizeof(outputs)); + strscpy(outputs, this_opt + 8, sizeof(outputs)); else if (!strncmp(this_opt, "dfp:", 4)) { dfp_type = simple_strtoul(this_opt+4, NULL, 0); dfp = 1; @@ -2455,7 +2455,7 @@ static int __init matroxfb_setup(char *options) { else if (!strcmp(this_opt, "dfp")) dfp = value; else { - strlcpy(videomode, this_opt, sizeof(videomode)); + strscpy(videomode, this_opt, sizeof(videomode)); } } } diff --git a/drivers/video/fbdev/omap/omapfb_main.c b/drivers/video/fbdev/omap/omapfb_main.c index dfb4ddc45701..17cda5765683 100644 --- a/drivers/video/fbdev/omap/omapfb_main.c +++ b/drivers/video/fbdev/omap/omapfb_main.c @@ -1642,15 +1642,13 @@ static int omapfb_do_probe(struct platform_device *pdev, goto cleanup; } fbdev->int_irq = platform_get_irq(pdev, 0); - if (!fbdev->int_irq) { - dev_err(&pdev->dev, "unable to get irq\n"); + if (fbdev->int_irq < 0) { r = ENXIO; goto cleanup; } fbdev->ext_irq = platform_get_irq(pdev, 1); - if (!fbdev->ext_irq) { - dev_err(&pdev->dev, "unable to get irq\n"); + if (fbdev->ext_irq < 0) { r = ENXIO; goto cleanup; } diff --git a/drivers/video/fbdev/omap2/omapfb/omapfb-main.c b/drivers/video/fbdev/omap2/omapfb/omapfb-main.c index afa688e754b9..5ccddcfce722 100644 --- a/drivers/video/fbdev/omap2/omapfb/omapfb-main.c +++ b/drivers/video/fbdev/omap2/omapfb/omapfb-main.c @@ -1331,7 +1331,7 @@ static void clear_fb_info(struct fb_info *fbi) { memset(&fbi->var, 0, sizeof(fbi->var)); memset(&fbi->fix, 0, sizeof(fbi->fix)); - strlcpy(fbi->fix.id, MODULE_NAME, sizeof(fbi->fix.id)); + strscpy(fbi->fix.id, MODULE_NAME, sizeof(fbi->fix.id)); } static int omapfb_free_all_fbmem(struct omapfb2_device *fbdev) diff --git a/drivers/video/fbdev/pm2fb.c b/drivers/video/fbdev/pm2fb.c index d3be2c64f1c0..8fd79deb1e2a 100644 --- a/drivers/video/fbdev/pm2fb.c +++ b/drivers/video/fbdev/pm2fb.c @@ -617,6 +617,11 @@ static int pm2fb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) return -EINVAL; } + if (!var->pixclock) { + DPRINTK("pixclock is zero\n"); + return -EINVAL; + } + if (PICOS2KHZ(var->pixclock) > PM2_MAX_PIXCLOCK) { DPRINTK("pixclock too high (%ldKHz)\n", PICOS2KHZ(var->pixclock)); diff --git a/drivers/video/fbdev/pxa168fb.c b/drivers/video/fbdev/pxa168fb.c index e943300d23e8..d5d0bbd39213 100644 --- a/drivers/video/fbdev/pxa168fb.c +++ b/drivers/video/fbdev/pxa168fb.c @@ -640,7 +640,7 @@ static int pxa168fb_probe(struct platform_device *pdev) info->flags = FBINFO_DEFAULT | FBINFO_PARTIAL_PAN_OK | FBINFO_HWACCEL_XPAN | FBINFO_HWACCEL_YPAN; info->node = -1; - strlcpy(info->fix.id, mi->id, 16); + strscpy(info->fix.id, mi->id, 16); info->fix.type = FB_TYPE_PACKED_PIXELS; info->fix.type_aux = 0; info->fix.xpanstep = 0; diff --git a/drivers/video/fbdev/pxafb.c b/drivers/video/fbdev/pxafb.c index 66cfc3e9d3cf..696ac5431180 100644 --- a/drivers/video/fbdev/pxafb.c +++ b/drivers/video/fbdev/pxafb.c @@ -2042,7 +2042,7 @@ static int __init pxafb_setup_options(void) return -ENODEV; if (options) - strlcpy(g_options, options, sizeof(g_options)); + strscpy(g_options, options, sizeof(g_options)); return 0; } diff --git a/drivers/video/fbdev/s3fb.c b/drivers/video/fbdev/s3fb.c index 5069f6f67923..67b63a753cb2 100644 --- a/drivers/video/fbdev/s3fb.c +++ b/drivers/video/fbdev/s3fb.c @@ -248,7 +248,7 @@ static int s3fb_setup_ddc_bus(struct fb_info *info) { struct s3fb_info *par = info->par; - strlcpy(par->ddc_adapter.name, info->fix.id, + strscpy(par->ddc_adapter.name, info->fix.id, sizeof(par->ddc_adapter.name)); par->ddc_adapter.owner = THIS_MODULE; par->ddc_adapter.class = I2C_CLASS_DDC; diff --git a/drivers/video/fbdev/simplefb.c b/drivers/video/fbdev/simplefb.c index cf2a90ecd64e..e770b4a356b5 100644 --- a/drivers/video/fbdev/simplefb.c +++ b/drivers/video/fbdev/simplefb.c @@ -355,7 +355,7 @@ static int simplefb_regulators_get(struct simplefb_par *par, if (!p || p == prop->name) continue; - strlcpy(name, prop->name, + strscpy(name, prop->name, strlen(prop->name) - strlen(SUPPLY_SUFFIX) + 1); regulator = devm_regulator_get_optional(&pdev->dev, name); if (IS_ERR(regulator)) { diff --git a/drivers/video/fbdev/sis/sis_main.c b/drivers/video/fbdev/sis/sis_main.c index f28fd69d5eb7..c9e77429dfa3 100644 --- a/drivers/video/fbdev/sis/sis_main.c +++ b/drivers/video/fbdev/sis/sis_main.c @@ -649,37 +649,37 @@ sisfb_validate_mode(struct sis_video_info *ivideo, int myindex, u32 vbflags) u16 xres=0, yres, myres; #ifdef CONFIG_FB_SIS_300 - if(ivideo->sisvga_engine == SIS_300_VGA) { - if(!(sisbios_mode[myindex].chipset & MD_SIS300)) + if (ivideo->sisvga_engine == SIS_300_VGA) { + if (!(sisbios_mode[myindex].chipset & MD_SIS300)) return -1 ; } #endif #ifdef CONFIG_FB_SIS_315 - if(ivideo->sisvga_engine == SIS_315_VGA) { - if(!(sisbios_mode[myindex].chipset & MD_SIS315)) + if (ivideo->sisvga_engine == SIS_315_VGA) { + if (!(sisbios_mode[myindex].chipset & MD_SIS315)) return -1; } #endif myres = sisbios_mode[myindex].yres; - switch(vbflags & VB_DISPTYPE_DISP2) { + switch (vbflags & VB_DISPTYPE_DISP2) { case CRT2_LCD: xres = ivideo->lcdxres; yres = ivideo->lcdyres; - if((ivideo->SiS_Pr.SiS_CustomT != CUT_PANEL848) && - (ivideo->SiS_Pr.SiS_CustomT != CUT_PANEL856)) { - if(sisbios_mode[myindex].xres > xres) + if ((ivideo->SiS_Pr.SiS_CustomT != CUT_PANEL848) && + (ivideo->SiS_Pr.SiS_CustomT != CUT_PANEL856)) { + if (sisbios_mode[myindex].xres > xres) return -1; - if(myres > yres) + if (myres > yres) return -1; } - if(ivideo->sisfb_fstn) { - if(sisbios_mode[myindex].xres == 320) { - if(myres == 240) { - switch(sisbios_mode[myindex].mode_no[1]) { + if (ivideo->sisfb_fstn) { + if (sisbios_mode[myindex].xres == 320) { + if (myres == 240) { + switch (sisbios_mode[myindex].mode_no[1]) { case 0x50: myindex = MODE_FSTN_8; break; case 0x56: myindex = MODE_FSTN_16; break; case 0x53: return -1; @@ -688,7 +688,7 @@ sisfb_validate_mode(struct sis_video_info *ivideo, int myindex, u32 vbflags) } } - if(SiS_GetModeID_LCD(ivideo->sisvga_engine, vbflags, sisbios_mode[myindex].xres, + if (SiS_GetModeID_LCD(ivideo->sisvga_engine, vbflags, sisbios_mode[myindex].xres, sisbios_mode[myindex].yres, 0, ivideo->sisfb_fstn, ivideo->SiS_Pr.SiS_CustomT, xres, yres, ivideo->vbflags2) < 0x14) { return -1; @@ -696,14 +696,14 @@ sisfb_validate_mode(struct sis_video_info *ivideo, int myindex, u32 vbflags) break; case CRT2_TV: - if(SiS_GetModeID_TV(ivideo->sisvga_engine, vbflags, sisbios_mode[myindex].xres, + if (SiS_GetModeID_TV(ivideo->sisvga_engine, vbflags, sisbios_mode[myindex].xres, sisbios_mode[myindex].yres, 0, ivideo->vbflags2) < 0x14) { return -1; } break; case CRT2_VGA: - if(SiS_GetModeID_VGA2(ivideo->sisvga_engine, vbflags, sisbios_mode[myindex].xres, + if (SiS_GetModeID_VGA2(ivideo->sisvga_engine, vbflags, sisbios_mode[myindex].xres, sisbios_mode[myindex].yres, 0, ivideo->vbflags2) < 0x14) { return -1; } @@ -1872,7 +1872,7 @@ sisfb_get_fix(struct fb_fix_screeninfo *fix, int con, struct fb_info *info) memset(fix, 0, sizeof(struct fb_fix_screeninfo)); - strlcpy(fix->id, ivideo->myid, sizeof(fix->id)); + strscpy(fix->id, ivideo->myid, sizeof(fix->id)); mutex_lock(&info->mm_lock); fix->smem_start = ivideo->video_base + ivideo->video_offset; @@ -2204,82 +2204,88 @@ static bool sisfb_test_DDC1(struct sis_video_info *ivideo) static void sisfb_sense_crt1(struct sis_video_info *ivideo) { - bool mustwait = false; - u8 sr1F, cr17; + bool mustwait = false; + u8 sr1F, cr17; #ifdef CONFIG_FB_SIS_315 - u8 cr63=0; + u8 cr63 = 0; #endif - u16 temp = 0xffff; - int i; + u16 temp = 0xffff; + int i; + + sr1F = SiS_GetReg(SISSR, 0x1F); + SiS_SetRegOR(SISSR, 0x1F, 0x04); + SiS_SetRegAND(SISSR, 0x1F, 0x3F); - sr1F = SiS_GetReg(SISSR, 0x1F); - SiS_SetRegOR(SISSR, 0x1F, 0x04); - SiS_SetRegAND(SISSR, 0x1F, 0x3F); - if(sr1F & 0xc0) mustwait = true; + if (sr1F & 0xc0) + mustwait = true; #ifdef CONFIG_FB_SIS_315 - if(ivideo->sisvga_engine == SIS_315_VGA) { - cr63 = SiS_GetReg(SISCR, ivideo->SiS_Pr.SiS_MyCR63); - cr63 &= 0x40; - SiS_SetRegAND(SISCR, ivideo->SiS_Pr.SiS_MyCR63, 0xBF); - } + if (ivideo->sisvga_engine == SIS_315_VGA) { + cr63 = SiS_GetReg(SISCR, ivideo->SiS_Pr.SiS_MyCR63); + cr63 &= 0x40; + SiS_SetRegAND(SISCR, ivideo->SiS_Pr.SiS_MyCR63, 0xBF); + } #endif - cr17 = SiS_GetReg(SISCR, 0x17); - cr17 &= 0x80; - if(!cr17) { - SiS_SetRegOR(SISCR, 0x17, 0x80); - mustwait = true; - SiS_SetReg(SISSR, 0x00, 0x01); - SiS_SetReg(SISSR, 0x00, 0x03); - } + cr17 = SiS_GetReg(SISCR, 0x17); + cr17 &= 0x80; - if(mustwait) { - for(i=0; i < 10; i++) sisfbwaitretracecrt1(ivideo); - } + if (!cr17) { + SiS_SetRegOR(SISCR, 0x17, 0x80); + mustwait = true; + SiS_SetReg(SISSR, 0x00, 0x01); + SiS_SetReg(SISSR, 0x00, 0x03); + } + if (mustwait) { + for (i = 0; i < 10; i++) + sisfbwaitretracecrt1(ivideo); + } #ifdef CONFIG_FB_SIS_315 - if(ivideo->chip >= SIS_330) { - SiS_SetRegAND(SISCR, 0x32, ~0x20); - if(ivideo->chip >= SIS_340) { - SiS_SetReg(SISCR, 0x57, 0x4a); - } else { - SiS_SetReg(SISCR, 0x57, 0x5f); - } - SiS_SetRegOR(SISCR, 0x53, 0x02); - while ((SiS_GetRegByte(SISINPSTAT)) & 0x01) break; - while (!((SiS_GetRegByte(SISINPSTAT)) & 0x01)) break; - if ((SiS_GetRegByte(SISMISCW)) & 0x10) temp = 1; - SiS_SetRegAND(SISCR, 0x53, 0xfd); - SiS_SetRegAND(SISCR, 0x57, 0x00); - } + if (ivideo->chip >= SIS_330) { + SiS_SetRegAND(SISCR, 0x32, ~0x20); + if (ivideo->chip >= SIS_340) + SiS_SetReg(SISCR, 0x57, 0x4a); + else + SiS_SetReg(SISCR, 0x57, 0x5f); + + SiS_SetRegOR(SISCR, 0x53, 0x02); + while ((SiS_GetRegByte(SISINPSTAT)) & 0x01) + break; + while (!((SiS_GetRegByte(SISINPSTAT)) & 0x01)) + break; + if ((SiS_GetRegByte(SISMISCW)) & 0x10) + temp = 1; + + SiS_SetRegAND(SISCR, 0x53, 0xfd); + SiS_SetRegAND(SISCR, 0x57, 0x00); + } #endif - if(temp == 0xffff) { - i = 3; - do { - temp = SiS_HandleDDC(&ivideo->SiS_Pr, ivideo->vbflags, - ivideo->sisvga_engine, 0, 0, NULL, ivideo->vbflags2); - } while(((temp == 0) || (temp == 0xffff)) && i--); + if (temp == 0xffff) { + i = 3; - if((temp == 0) || (temp == 0xffff)) { - if(sisfb_test_DDC1(ivideo)) temp = 1; - } - } + do { + temp = SiS_HandleDDC(&ivideo->SiS_Pr, ivideo->vbflags, + ivideo->sisvga_engine, 0, 0, NULL, ivideo->vbflags2); + } while (((temp == 0) || (temp == 0xffff)) && i--); - if((temp) && (temp != 0xffff)) { - SiS_SetRegOR(SISCR, 0x32, 0x20); - } + if ((temp == 0) || (temp == 0xffff)) { + if (sisfb_test_DDC1(ivideo)) + temp = 1; + } + } + + if ((temp) && (temp != 0xffff)) + SiS_SetRegOR(SISCR, 0x32, 0x20); #ifdef CONFIG_FB_SIS_315 - if(ivideo->sisvga_engine == SIS_315_VGA) { - SiS_SetRegANDOR(SISCR, ivideo->SiS_Pr.SiS_MyCR63, 0xBF, cr63); - } + if (ivideo->sisvga_engine == SIS_315_VGA) + SiS_SetRegANDOR(SISCR, ivideo->SiS_Pr.SiS_MyCR63, 0xBF, cr63); #endif - SiS_SetRegANDOR(SISCR, 0x17, 0x7F, cr17); - - SiS_SetReg(SISSR, 0x1F, sr1F); + SiS_SetRegANDOR(SISCR, 0x17, 0x7F, cr17); + SiS_SetReg(SISSR, 0x1F, sr1F); } /* Determine and detect attached devices on SiS30x */ @@ -2293,25 +2299,25 @@ static void SiS_SenseLCD(struct sis_video_info *ivideo) ivideo->SiS_Pr.PanelSelfDetected = false; /* LCD detection only for TMDS bridges */ - if(!(ivideo->vbflags2 & VB2_SISTMDSBRIDGE)) + if (!(ivideo->vbflags2 & VB2_SISTMDSBRIDGE)) return; - if(ivideo->vbflags2 & VB2_30xBDH) + if (ivideo->vbflags2 & VB2_30xBDH) return; /* If LCD already set up by BIOS, skip it */ reg = SiS_GetReg(SISCR, 0x32); - if(reg & 0x08) + if (reg & 0x08) return; realcrtno = 1; - if(ivideo->SiS_Pr.DDCPortMixup) + if (ivideo->SiS_Pr.DDCPortMixup) realcrtno = 0; /* Check DDC capabilities */ temp = SiS_HandleDDC(&ivideo->SiS_Pr, ivideo->vbflags, ivideo->sisvga_engine, realcrtno, 0, &buffer[0], ivideo->vbflags2); - if((!temp) || (temp == 0xffff) || (!(temp & 0x02))) + if ((!temp) || (temp == 0xffff) || (!(temp & 0x02))) return; /* Read DDC data */ @@ -2320,17 +2326,17 @@ static void SiS_SenseLCD(struct sis_video_info *ivideo) temp = SiS_HandleDDC(&ivideo->SiS_Pr, ivideo->vbflags, ivideo->sisvga_engine, realcrtno, 1, &buffer[0], ivideo->vbflags2); - } while((temp) && i--); + } while ((temp) && i--); - if(temp) + if (temp) return; /* No digital device */ - if(!(buffer[0x14] & 0x80)) + if (!(buffer[0x14] & 0x80)) return; /* First detailed timing preferred timing? */ - if(!(buffer[0x18] & 0x02)) + if (!(buffer[0x18] & 0x02)) return; xres = buffer[0x38] | ((buffer[0x3a] & 0xf0) << 4); @@ -2338,26 +2344,26 @@ static void SiS_SenseLCD(struct sis_video_info *ivideo) switch(xres) { case 1024: - if(yres == 768) + if (yres == 768) paneltype = 0x02; break; case 1280: - if(yres == 1024) + if (yres == 1024) paneltype = 0x03; break; case 1600: - if((yres == 1200) && (ivideo->vbflags2 & VB2_30xC)) + if ((yres == 1200) && (ivideo->vbflags2 & VB2_30xC)) paneltype = 0x0b; break; } - if(!paneltype) + if (!paneltype) return; - if(buffer[0x23]) + if (buffer[0x23]) cr37 |= 0x10; - if((buffer[0x47] & 0x18) == 0x18) + if ((buffer[0x47] & 0x18) == 0x18) cr37 |= ((((buffer[0x47] & 0x06) ^ 0x06) << 5) | 0x20); else cr37 |= 0xc0; @@ -2372,31 +2378,34 @@ static void SiS_SenseLCD(struct sis_video_info *ivideo) static int SISDoSense(struct sis_video_info *ivideo, u16 type, u16 test) { - int temp, mytest, result, i, j; - - for(j = 0; j < 10; j++) { - result = 0; - for(i = 0; i < 3; i++) { - mytest = test; - SiS_SetReg(SISPART4, 0x11, (type & 0x00ff)); - temp = (type >> 8) | (mytest & 0x00ff); - SiS_SetRegANDOR(SISPART4, 0x10, 0xe0, temp); - SiS_DDC2Delay(&ivideo->SiS_Pr, 0x1500); - mytest >>= 8; - mytest &= 0x7f; - temp = SiS_GetReg(SISPART4, 0x03); - temp ^= 0x0e; - temp &= mytest; - if(temp == mytest) result++; + int temp, mytest, result, i, j; + + for (j = 0; j < 10; j++) { + result = 0; + for (i = 0; i < 3; i++) { + mytest = test; + SiS_SetReg(SISPART4, 0x11, (type & 0x00ff)); + temp = (type >> 8) | (mytest & 0x00ff); + SiS_SetRegANDOR(SISPART4, 0x10, 0xe0, temp); + SiS_DDC2Delay(&ivideo->SiS_Pr, 0x1500); + mytest >>= 8; + mytest &= 0x7f; + temp = SiS_GetReg(SISPART4, 0x03); + temp ^= 0x0e; + temp &= mytest; + if (temp == mytest) + result++; #if 1 - SiS_SetReg(SISPART4, 0x11, 0x00); - SiS_SetRegAND(SISPART4, 0x10, 0xe0); - SiS_DDC2Delay(&ivideo->SiS_Pr, 0x1000); + SiS_SetReg(SISPART4, 0x11, 0x00); + SiS_SetRegAND(SISPART4, 0x10, 0xe0); + SiS_DDC2Delay(&ivideo->SiS_Pr, 0x1000); #endif - } - if((result == 0) || (result >= 2)) break; - } - return result; + } + + if ((result == 0) || (result >= 2)) + break; + } + return result; } static void SiS_Sense30x(struct sis_video_info *ivideo) @@ -4262,18 +4271,17 @@ static int sisfb_post_300_rwtest(struct sis_video_info *ivideo, int iteration, unsigned int k, RankCapacity, PageCapacity, BankNumHigh, BankNumMid; unsigned int PhysicalAdrOtherPage, PhysicalAdrHigh, PhysicalAdrHalfPage; - for(k = 0; k < ARRAY_SIZE(SiS_DRAMType); k++) { - + for (k = 0; k < ARRAY_SIZE(SiS_DRAMType); k++) { RankCapacity = buswidth * SiS_DRAMType[k][3]; - if(RankCapacity != PseudoRankCapacity) + if (RankCapacity != PseudoRankCapacity) continue; - if((SiS_DRAMType[k][2] + SiS_DRAMType[k][0]) > PseudoAdrPinCount) + if ((SiS_DRAMType[k][2] + SiS_DRAMType[k][0]) > PseudoAdrPinCount) continue; BankNumHigh = RankCapacity * 16 * iteration - 1; - if(iteration == 3) { /* Rank No */ + if (iteration == 3) { /* Rank No */ BankNumMid = RankCapacity * 16 - 1; } else { BankNumMid = RankCapacity * 16 * iteration / 2 - 1; @@ -4287,18 +4295,22 @@ static int sisfb_post_300_rwtest(struct sis_video_info *ivideo, int iteration, SiS_SetRegAND(SISSR, 0x15, 0xFB); /* Test */ SiS_SetRegOR(SISSR, 0x15, 0x04); /* Test */ sr14 = (SiS_DRAMType[k][3] * buswidth) - 1; - if(buswidth == 4) sr14 |= 0x80; - else if(buswidth == 2) sr14 |= 0x40; + + if (buswidth == 4) + sr14 |= 0x80; + else if (buswidth == 2) + sr14 |= 0x40; + SiS_SetReg(SISSR, 0x13, SiS_DRAMType[k][4]); SiS_SetReg(SISSR, 0x14, sr14); BankNumHigh <<= 16; BankNumMid <<= 16; - if((BankNumHigh + PhysicalAdrHigh >= mapsize) || - (BankNumMid + PhysicalAdrHigh >= mapsize) || - (BankNumHigh + PhysicalAdrHalfPage >= mapsize) || - (BankNumHigh + PhysicalAdrOtherPage >= mapsize)) + if ((BankNumHigh + PhysicalAdrHigh >= mapsize) || + (BankNumMid + PhysicalAdrHigh >= mapsize) || + (BankNumHigh + PhysicalAdrHalfPage >= mapsize) || + (BankNumHigh + PhysicalAdrOtherPage >= mapsize)) continue; /* Write data */ @@ -4312,7 +4324,7 @@ static int sisfb_post_300_rwtest(struct sis_video_info *ivideo, int iteration, (FBAddr + BankNumHigh + PhysicalAdrOtherPage)); /* Read data */ - if(readw(FBAddr + BankNumHigh + PhysicalAdrHigh) == PhysicalAdrHigh) + if (readw(FBAddr + BankNumHigh + PhysicalAdrHigh) == PhysicalAdrHigh) return 1; } @@ -5867,7 +5879,7 @@ static int sisfb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) ivideo->cardnumber++; } - strlcpy(ivideo->myid, chipinfo->chip_name, sizeof(ivideo->myid)); + strscpy(ivideo->myid, chipinfo->chip_name, sizeof(ivideo->myid)); ivideo->warncount = 0; ivideo->chip_id = pdev->device; @@ -6150,24 +6162,20 @@ static int sisfb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) #endif #ifdef CONFIG_FB_SIS_315 - if(ivideo->sisvga_engine == SIS_315_VGA) { + if (ivideo->sisvga_engine == SIS_315_VGA) { int result = 1; - /* if((ivideo->chip == SIS_315H) || - (ivideo->chip == SIS_315) || - (ivideo->chip == SIS_315PRO) || - (ivideo->chip == SIS_330)) { - sisfb_post_sis315330(pdev); - } else */ if(ivideo->chip == XGI_20) { + + if (ivideo->chip == XGI_20) { result = sisfb_post_xgi(pdev); ivideo->sisfb_can_post = 1; - } else if((ivideo->chip == XGI_40) && ivideo->haveXGIROM) { + } else if ((ivideo->chip == XGI_40) && ivideo->haveXGIROM) { result = sisfb_post_xgi(pdev); ivideo->sisfb_can_post = 1; } else { printk(KERN_INFO "sisfb: Card is not " "POSTed and sisfb can't do this either.\n"); } - if(!result) { + if (!result) { printk(KERN_ERR "sisfb: Failed to POST card\n"); ret = -ENODEV; goto error_3; diff --git a/drivers/video/fbdev/sm501fb.c b/drivers/video/fbdev/sm501fb.c index 6a52eba64559..fce6cfbadfd6 100644 --- a/drivers/video/fbdev/sm501fb.c +++ b/drivers/video/fbdev/sm501fb.c @@ -1719,7 +1719,7 @@ static int sm501fb_init_fb(struct fb_info *fb, enum sm501_controller head, enable = 0; } - strlcpy(fb->fix.id, fbname, sizeof(fb->fix.id)); + strscpy(fb->fix.id, fbname, sizeof(fb->fix.id)); memcpy(&par->ops, (head == HEAD_CRT) ? &sm501fb_ops_crt : &sm501fb_ops_pnl, diff --git a/drivers/video/fbdev/ssd1307fb.c b/drivers/video/fbdev/ssd1307fb.c index 5c765655d000..52e4ed9da78c 100644 --- a/drivers/video/fbdev/ssd1307fb.c +++ b/drivers/video/fbdev/ssd1307fb.c @@ -450,7 +450,7 @@ static int ssd1307fb_init(struct ssd1307fb_par *par) if (ret < 0) return ret; - /* Set Set Area Color Mode ON/OFF & Low Power Display Mode */ + /* Set Area Color Mode ON/OFF & Low Power Display Mode */ if (par->area_color_enable || par->low_power) { u32 mode; diff --git a/drivers/video/fbdev/sstfb.c b/drivers/video/fbdev/sstfb.c index 27d4b0ace2d6..cd4d640f9477 100644 --- a/drivers/video/fbdev/sstfb.c +++ b/drivers/video/fbdev/sstfb.c @@ -1382,7 +1382,7 @@ static int sstfb_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto fail; } sst_get_memsize(info, &fix->smem_len); - strlcpy(fix->id, spec->name, sizeof(fix->id)); + strscpy(fix->id, spec->name, sizeof(fix->id)); printk(KERN_INFO "%s (revision %d) with %s dac\n", fix->id, par->revision, par->dac_sw.name); diff --git a/drivers/video/fbdev/sunxvr1000.c b/drivers/video/fbdev/sunxvr1000.c index 15b079505a00..490bd9a14763 100644 --- a/drivers/video/fbdev/sunxvr1000.c +++ b/drivers/video/fbdev/sunxvr1000.c @@ -80,7 +80,7 @@ static int gfb_set_fbinfo(struct gfb_info *gp) info->pseudo_palette = gp->pseudo_palette; /* Fill fix common fields */ - strlcpy(info->fix.id, "gfb", sizeof(info->fix.id)); + strscpy(info->fix.id, "gfb", sizeof(info->fix.id)); info->fix.smem_start = gp->fb_base_phys; info->fix.smem_len = gp->fb_size; info->fix.type = FB_TYPE_PACKED_PIXELS; diff --git a/drivers/video/fbdev/sunxvr2500.c b/drivers/video/fbdev/sunxvr2500.c index 1d3bacd9d5ac..1279b02234f8 100644 --- a/drivers/video/fbdev/sunxvr2500.c +++ b/drivers/video/fbdev/sunxvr2500.c @@ -84,7 +84,7 @@ static int s3d_set_fbinfo(struct s3d_info *sp) info->pseudo_palette = sp->pseudo_palette; /* Fill fix common fields */ - strlcpy(info->fix.id, "s3d", sizeof(info->fix.id)); + strscpy(info->fix.id, "s3d", sizeof(info->fix.id)); info->fix.smem_start = sp->fb_base_phys; info->fix.smem_len = sp->fb_size; info->fix.type = FB_TYPE_PACKED_PIXELS; diff --git a/drivers/video/fbdev/sunxvr500.c b/drivers/video/fbdev/sunxvr500.c index 9daf17b11106..f7b463633ba0 100644 --- a/drivers/video/fbdev/sunxvr500.c +++ b/drivers/video/fbdev/sunxvr500.c @@ -207,7 +207,7 @@ static int e3d_set_fbinfo(struct e3d_info *ep) info->pseudo_palette = ep->pseudo_palette; /* Fill fix common fields */ - strlcpy(info->fix.id, "e3d", sizeof(info->fix.id)); + strscpy(info->fix.id, "e3d", sizeof(info->fix.id)); info->fix.smem_start = ep->fb_base_phys; info->fix.smem_len = ep->fb_size; info->fix.type = FB_TYPE_PACKED_PIXELS; diff --git a/drivers/video/fbdev/tcx.c b/drivers/video/fbdev/tcx.c index 1638a40fed22..01d87f53324d 100644 --- a/drivers/video/fbdev/tcx.c +++ b/drivers/video/fbdev/tcx.c @@ -333,7 +333,7 @@ tcx_init_fix(struct fb_info *info, int linebytes) else tcx_name = "TCX24"; - strlcpy(info->fix.id, tcx_name, sizeof(info->fix.id)); + strscpy(info->fix.id, tcx_name, sizeof(info->fix.id)); info->fix.type = FB_TYPE_PACKED_PIXELS; info->fix.visual = FB_VISUAL_PSEUDOCOLOR; diff --git a/drivers/video/fbdev/tdfxfb.c b/drivers/video/fbdev/tdfxfb.c index 67e37a62b07c..8a8122f8bfeb 100644 --- a/drivers/video/fbdev/tdfxfb.c +++ b/drivers/video/fbdev/tdfxfb.c @@ -1264,7 +1264,7 @@ static int tdfxfb_setup_ddc_bus(struct tdfxfb_i2c_chan *chan, const char *name, { int rc; - strlcpy(chan->adapter.name, name, sizeof(chan->adapter.name)); + strscpy(chan->adapter.name, name, sizeof(chan->adapter.name)); chan->adapter.owner = THIS_MODULE; chan->adapter.class = I2C_CLASS_DDC; chan->adapter.algo_data = &chan->algo; @@ -1293,7 +1293,7 @@ static int tdfxfb_setup_i2c_bus(struct tdfxfb_i2c_chan *chan, const char *name, { int rc; - strlcpy(chan->adapter.name, name, sizeof(chan->adapter.name)); + strscpy(chan->adapter.name, name, sizeof(chan->adapter.name)); chan->adapter.owner = THIS_MODULE; chan->adapter.algo_data = &chan->algo; chan->adapter.dev.parent = dev; diff --git a/drivers/video/fbdev/tgafb.c b/drivers/video/fbdev/tgafb.c index ae0cf5540636..1fff5fd7ab51 100644 --- a/drivers/video/fbdev/tgafb.c +++ b/drivers/video/fbdev/tgafb.c @@ -1344,7 +1344,7 @@ tgafb_init_fix(struct fb_info *info) memory_size = 16777216; } - strlcpy(info->fix.id, tga_type_name, sizeof(info->fix.id)); + strscpy(info->fix.id, tga_type_name, sizeof(info->fix.id)); info->fix.type = FB_TYPE_PACKED_PIXELS; info->fix.type_aux = 0; diff --git a/drivers/video/fbdev/tridentfb.c b/drivers/video/fbdev/tridentfb.c index 319131bd72cf..cda095420ee8 100644 --- a/drivers/video/fbdev/tridentfb.c +++ b/drivers/video/fbdev/tridentfb.c @@ -270,7 +270,7 @@ static int tridentfb_setup_ddc_bus(struct fb_info *info) { struct tridentfb_par *par = info->par; - strlcpy(par->ddc_adapter.name, info->fix.id, + strscpy(par->ddc_adapter.name, info->fix.id, sizeof(par->ddc_adapter.name)); par->ddc_adapter.owner = THIS_MODULE; par->ddc_adapter.class = I2C_CLASS_DDC; diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c index 3369734108af..e88e8f6f0a33 100644 --- a/drivers/xen/privcmd.c +++ b/drivers/xen/privcmd.c @@ -581,27 +581,30 @@ static int lock_pages( struct privcmd_dm_op_buf kbufs[], unsigned int num, struct page *pages[], unsigned int nr_pages, unsigned int *pinned) { - unsigned int i; + unsigned int i, off = 0; - for (i = 0; i < num; i++) { + for (i = 0; i < num; ) { unsigned int requested; int page_count; requested = DIV_ROUND_UP( offset_in_page(kbufs[i].uptr) + kbufs[i].size, - PAGE_SIZE); + PAGE_SIZE) - off; if (requested > nr_pages) return -ENOSPC; page_count = pin_user_pages_fast( - (unsigned long) kbufs[i].uptr, + (unsigned long)kbufs[i].uptr + off * PAGE_SIZE, requested, FOLL_WRITE, pages); - if (page_count < 0) - return page_count; + if (page_count <= 0) + return page_count ? : -EFAULT; *pinned += page_count; nr_pages -= page_count; pages += page_count; + + off = (requested == page_count) ? 0 : off + page_count; + i += !off; } return 0; @@ -677,10 +680,8 @@ static long privcmd_ioctl_dm_op(struct file *file, void __user *udata) } rc = lock_pages(kbufs, kdata.num, pages, nr_pages, &pinned); - if (rc < 0) { - nr_pages = pinned; + if (rc < 0) goto out; - } for (i = 0; i < kdata.num; i++) { set_xen_guest_handle(xbufs[i].h, kbufs[i].uptr); @@ -692,7 +693,7 @@ static long privcmd_ioctl_dm_op(struct file *file, void __user *udata) xen_preemptible_hcall_end(); out: - unlock_pages(pages, nr_pages); + unlock_pages(pages, pinned); kfree(xbufs); kfree(pages); kfree(kbufs); diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index 7a0c93acc2c5..d3dcda344989 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -1121,7 +1121,7 @@ static void scsiback_do_1lun_hotplug(struct vscsibk_info *info, int op, "%s: writing %s", __func__, state); return; } - strlcpy(phy, val, VSCSI_NAMELEN); + strscpy(phy, val, VSCSI_NAMELEN); kfree(val); /* virtual SCSI device */ diff --git a/drivers/xen/xenbus/xenbus_probe_frontend.c b/drivers/xen/xenbus/xenbus_probe_frontend.c index 07b010a68fcf..f44d5a64351e 100644 --- a/drivers/xen/xenbus/xenbus_probe_frontend.c +++ b/drivers/xen/xenbus/xenbus_probe_frontend.c @@ -40,7 +40,7 @@ static int frontend_bus_id(char bus_id[XEN_BUS_ID_SIZE], const char *nodename) return -EINVAL; } - strlcpy(bus_id, nodename + 1, XEN_BUS_ID_SIZE); + strscpy(bus_id, nodename + 1, XEN_BUS_ID_SIZE); if (!strchr(bus_id, '/')) { pr_warn("bus_id %s no slash\n", bus_id); return -EINVAL; diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 993aca2f1e18..e0375ba9d0fe 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -440,39 +440,26 @@ void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache, btrfs_put_caching_control(caching_ctl); } -int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache) +static int btrfs_caching_ctl_wait_done(struct btrfs_block_group *cache, + struct btrfs_caching_control *caching_ctl) +{ + wait_event(caching_ctl->wait, btrfs_block_group_done(cache)); + return cache->cached == BTRFS_CACHE_ERROR ? -EIO : 0; +} + +static int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache) { struct btrfs_caching_control *caching_ctl; - int ret = 0; + int ret; caching_ctl = btrfs_get_caching_control(cache); if (!caching_ctl) return (cache->cached == BTRFS_CACHE_ERROR) ? -EIO : 0; - - wait_event(caching_ctl->wait, btrfs_block_group_done(cache)); - if (cache->cached == BTRFS_CACHE_ERROR) - ret = -EIO; + ret = btrfs_caching_ctl_wait_done(cache, caching_ctl); btrfs_put_caching_control(caching_ctl); return ret; } -static bool space_cache_v1_done(struct btrfs_block_group *cache) -{ - bool ret; - - spin_lock(&cache->lock); - ret = cache->cached != BTRFS_CACHE_FAST; - spin_unlock(&cache->lock); - - return ret; -} - -void btrfs_wait_space_cache_v1_finished(struct btrfs_block_group *cache, - struct btrfs_caching_control *caching_ctl) -{ - wait_event(caching_ctl->wait, space_cache_v1_done(cache)); -} - #ifdef CONFIG_BTRFS_DEBUG static void fragment_free_space(struct btrfs_block_group *block_group) { @@ -750,9 +737,8 @@ done: btrfs_put_block_group(block_group); } -int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only) +int btrfs_cache_block_group(struct btrfs_block_group *cache, bool wait) { - DEFINE_WAIT(wait); struct btrfs_fs_info *fs_info = cache->fs_info; struct btrfs_caching_control *caching_ctl = NULL; int ret = 0; @@ -785,10 +771,7 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only } WARN_ON(cache->caching_ctl); cache->caching_ctl = caching_ctl; - if (btrfs_test_opt(fs_info, SPACE_CACHE)) - cache->cached = BTRFS_CACHE_FAST; - else - cache->cached = BTRFS_CACHE_STARTED; + cache->cached = BTRFS_CACHE_STARTED; cache->has_caching_ctl = 1; spin_unlock(&cache->lock); @@ -801,8 +784,8 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only btrfs_queue_work(fs_info->caching_workers, &caching_ctl->work); out: - if (load_cache_only && caching_ctl) - btrfs_wait_space_cache_v1_finished(cache, caching_ctl); + if (wait && caching_ctl) + ret = btrfs_caching_ctl_wait_done(cache, caching_ctl); if (caching_ctl) btrfs_put_caching_control(caching_ctl); @@ -3312,7 +3295,7 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans, * space back to the block group, otherwise we will leak space. */ if (!alloc && !btrfs_block_group_done(cache)) - btrfs_cache_block_group(cache, 1); + btrfs_cache_block_group(cache, true); byte_in_group = bytenr - cache->start; WARN_ON(byte_in_group > cache->length); diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index 35e0e860cc0b..6b3cdc4cbc41 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -263,9 +263,7 @@ void btrfs_dec_nocow_writers(struct btrfs_block_group *bg); void btrfs_wait_nocow_writers(struct btrfs_block_group *bg); void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache, u64 num_bytes); -int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache); -int btrfs_cache_block_group(struct btrfs_block_group *cache, - int load_cache_only); +int btrfs_cache_block_group(struct btrfs_block_group *cache, bool wait); void btrfs_put_caching_control(struct btrfs_caching_control *ctl); struct btrfs_caching_control *btrfs_get_caching_control( struct btrfs_block_group *cache); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 4edb4bfb2166..9ef162dbd4bc 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -505,7 +505,6 @@ struct btrfs_free_cluster { enum btrfs_caching_type { BTRFS_CACHE_NO, BTRFS_CACHE_STARTED, - BTRFS_CACHE_FAST, BTRFS_CACHE_FINISHED, BTRFS_CACHE_ERROR, }; diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index f43196a893ca..41cddd3ff059 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -165,7 +165,7 @@ no_valid_dev_replace_entry_found: */ if (btrfs_find_device(fs_info->fs_devices, &args)) { btrfs_err(fs_info, - "replace devid present without an active replace item"); +"replace without active item, run 'device scan --forget' on the target device"); ret = -EUCLEAN; } else { dev_replace->srcdev = NULL; @@ -1129,8 +1129,7 @@ int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info) up_write(&dev_replace->rwsem); /* Scrub for replace must not be running in suspended state */ - ret = btrfs_scrub_cancel(fs_info); - ASSERT(ret != -ENOTCONN); + btrfs_scrub_cancel(fs_info); trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index ab944d1f94ef..6914cd8024ba 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2551,17 +2551,10 @@ int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans, return -EINVAL; /* - * pull in the free space cache (if any) so that our pin - * removes the free space from the cache. We have load_only set - * to one because the slow code to read in the free extents does check - * the pinned extents. + * Fully cache the free space first so that our pin removes the free space + * from the cache. */ - btrfs_cache_block_group(cache, 1); - /* - * Make sure we wait until the cache is completely built in case it is - * missing or is invalid and therefore needs to be rebuilt. - */ - ret = btrfs_wait_block_group_cache_done(cache); + ret = btrfs_cache_block_group(cache, true); if (ret) goto out; @@ -2584,12 +2577,7 @@ static int __exclude_logged_extent(struct btrfs_fs_info *fs_info, if (!block_group) return -EINVAL; - btrfs_cache_block_group(block_group, 1); - /* - * Make sure we wait until the cache is completely built in case it is - * missing or is invalid and therefore needs to be rebuilt. - */ - ret = btrfs_wait_block_group_cache_done(block_group); + ret = btrfs_cache_block_group(block_group, true); if (ret) goto out; @@ -4399,7 +4387,7 @@ have_block_group: ffe_ctl->cached = btrfs_block_group_done(block_group); if (unlikely(!ffe_ctl->cached)) { ffe_ctl->have_caching_bg = true; - ret = btrfs_cache_block_group(block_group, 0); + ret = btrfs_cache_block_group(block_group, false); /* * If we get ENOMEM here or something else we want to @@ -6169,13 +6157,7 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range) if (end - start >= range->minlen) { if (!btrfs_block_group_done(cache)) { - ret = btrfs_cache_block_group(cache, 0); - if (ret) { - bg_failed++; - bg_ret = ret; - continue; - } - ret = btrfs_wait_block_group_cache_done(cache); + ret = btrfs_cache_block_group(cache, true); if (ret) { bg_failed++; bg_ret = ret; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index eed81a7e36a4..cf4f19e80e2f 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3233,7 +3233,7 @@ static int btrfs_bio_add_page(struct btrfs_bio_ctrl *bio_ctrl, u32 bio_size = bio->bi_iter.bi_size; u32 real_size; const sector_t sector = disk_bytenr >> SECTOR_SHIFT; - bool contig; + bool contig = false; int ret; ASSERT(bio); @@ -3242,10 +3242,35 @@ static int btrfs_bio_add_page(struct btrfs_bio_ctrl *bio_ctrl, if (bio_ctrl->compress_type != compress_type) return 0; - if (bio_ctrl->compress_type != BTRFS_COMPRESS_NONE) + + if (bio->bi_iter.bi_size == 0) { + /* We can always add a page into an empty bio. */ + contig = true; + } else if (bio_ctrl->compress_type == BTRFS_COMPRESS_NONE) { + struct bio_vec *bvec = bio_last_bvec_all(bio); + + /* + * The contig check requires the following conditions to be met: + * 1) The pages are belonging to the same inode + * This is implied by the call chain. + * + * 2) The range has adjacent logical bytenr + * + * 3) The range has adjacent file offset + * This is required for the usage of btrfs_bio->file_offset. + */ + if (bio_end_sector(bio) == sector && + page_offset(bvec->bv_page) + bvec->bv_offset + + bvec->bv_len == page_offset(page) + pg_offset) + contig = true; + } else { + /* + * For compression, all IO should have its logical bytenr + * set to the starting bytenr of the compressed extent. + */ contig = bio->bi_iter.bi_sector == sector; - else - contig = bio_end_sector(bio) == sector; + } + if (!contig) return 0; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 66c822182ecc..5a3f6e0d9688 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2482,6 +2482,7 @@ static int fill_holes(struct btrfs_trans_handle *trans, btrfs_set_file_extent_num_bytes(leaf, fi, num_bytes); btrfs_set_file_extent_ram_bytes(leaf, fi, num_bytes); btrfs_set_file_extent_offset(leaf, fi, 0); + btrfs_set_file_extent_generation(leaf, fi, trans->transid); btrfs_mark_buffer_dirty(leaf); goto out; } @@ -2498,6 +2499,7 @@ static int fill_holes(struct btrfs_trans_handle *trans, btrfs_set_file_extent_num_bytes(leaf, fi, num_bytes); btrfs_set_file_extent_ram_bytes(leaf, fi, num_bytes); btrfs_set_file_extent_offset(leaf, fi, 0); + btrfs_set_file_extent_generation(leaf, fi, trans->transid); btrfs_mark_buffer_dirty(leaf); goto out; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index f0c97d25b4a0..ad250892028d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7694,6 +7694,20 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start, bool unlock_extents = false; /* + * We could potentially fault if we have a buffer > PAGE_SIZE, and if + * we're NOWAIT we may submit a bio for a partial range and return + * EIOCBQUEUED, which would result in an errant short read. + * + * The best way to handle this would be to allow for partial completions + * of iocb's, so we could submit the partial bio, return and fault in + * the rest of the pages, and then submit the io for the rest of the + * range. However we don't have that currently, so simply return + * -EAGAIN at this point so that the normal path is used. + */ + if (!write && (flags & IOMAP_NOWAIT) && length > PAGE_SIZE) + return -EAGAIN; + + /* * Cap the size of reads to that usually seen in buffered I/O as we need * to allocate a contiguous array for the checksums. */ diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index a64b26b16904..d647cb2938c0 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -349,9 +349,10 @@ int btrfs_del_root_ref(struct btrfs_trans_handle *trans, u64 root_id, key.offset = ref_id; again: ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1); - if (ret < 0) + if (ret < 0) { + err = ret; goto out; - if (ret == 0) { + } else if (ret == 0) { leaf = path->nodes[0]; ref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_root_ref); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 272901514b0c..064ab2a79c80 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -2345,8 +2345,11 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info, ret = btrfs_get_bdev_and_sb(path, FMODE_READ, fs_info->bdev_holder, 0, &bdev, &disk_super); - if (ret) + if (ret) { + btrfs_put_dev_args_from_path(args); return ret; + } + args->devid = btrfs_stack_device_id(&disk_super->dev_item); memcpy(args->uuid, disk_super->dev_item.uuid, BTRFS_UUID_SIZE); if (btrfs_fs_incompat(fs_info, METADATA_UUID)) diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 7421abcf325a..5bb8d8c86311 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -371,6 +371,9 @@ static int btrfs_xattr_handler_set(const struct xattr_handler *handler, const char *name, const void *buffer, size_t size, int flags) { + if (btrfs_root_readonly(BTRFS_I(inode)->root)) + return -EROFS; + name = xattr_full_name(handler, name); return btrfs_setxattr_trans(inode, name, buffer, size, flags); } diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index 8f7835ccbca1..46f5718754f9 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -32,10 +32,9 @@ int __cifs_calc_signature(struct smb_rqst *rqst, int rc; struct kvec *iov = rqst->rq_iov; int n_vec = rqst->rq_nvec; - int is_smb2 = server->vals->header_preamble_size == 0; /* iov[0] is actual data and not the rfc1002 length for SMB2+ */ - if (is_smb2) { + if (!is_smb1(server)) { if (iov[0].iov_len <= 4) return -EIO; i = 0; diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index f15d7b0c123d..ae7f571a7dba 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -557,6 +557,8 @@ struct smb_version_values { #define HEADER_SIZE(server) (server->vals->header_size) #define MAX_HEADER_SIZE(server) (server->vals->max_header_size) +#define HEADER_PREAMBLE_SIZE(server) (server->vals->header_preamble_size) +#define MID_HEADER_SIZE(server) (HEADER_SIZE(server) - 1 - HEADER_PREAMBLE_SIZE(server)) /** * CIFS superblock mount flags (mnt_cifs_flags) to consider when @@ -750,6 +752,11 @@ struct TCP_Server_Info { #endif }; +static inline bool is_smb1(struct TCP_Server_Info *server) +{ + return HEADER_PREAMBLE_SIZE(server) != 0; +} + static inline void cifs_server_lock(struct TCP_Server_Info *server) { unsigned int nofs_flag = memalloc_nofs_save(); diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 3da5da9f16b0..a0a06b6f252b 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -871,7 +871,7 @@ smb2_get_credits_from_hdr(char *buffer, struct TCP_Server_Info *server) /* * SMB1 does not use credits. */ - if (server->vals->header_preamble_size) + if (is_smb1(server)) return 0; return le16_to_cpu(shdr->CreditRequest); @@ -1050,7 +1050,7 @@ standard_receive3(struct TCP_Server_Info *server, struct mid_q_entry *mid) /* make sure this will fit in a large buffer */ if (pdu_length > CIFSMaxBufSize + MAX_HEADER_SIZE(server) - - server->vals->header_preamble_size) { + HEADER_PREAMBLE_SIZE(server)) { cifs_server_dbg(VFS, "SMB response too long (%u bytes)\n", pdu_length); cifs_reconnect(server, true); return -ECONNABORTED; @@ -1065,8 +1065,7 @@ standard_receive3(struct TCP_Server_Info *server, struct mid_q_entry *mid) /* now read the rest */ length = cifs_read_from_socket(server, buf + HEADER_SIZE(server) - 1, - pdu_length - HEADER_SIZE(server) + 1 - + server->vals->header_preamble_size); + pdu_length - MID_HEADER_SIZE(server)); if (length < 0) return length; @@ -1122,7 +1121,7 @@ smb2_add_credits_from_hdr(char *buffer, struct TCP_Server_Info *server) /* * SMB1 does not use credits. */ - if (server->vals->header_preamble_size) + if (is_smb1(server)) return; if (shdr->CreditRequest) { @@ -1180,10 +1179,10 @@ cifs_demultiplex_thread(void *p) if (length < 0) continue; - if (server->vals->header_preamble_size == 0) - server->total_read = 0; - else + if (is_smb1(server)) server->total_read = length; + else + server->total_read = 0; /* * The right amount was read from socket - 4 bytes, @@ -1198,8 +1197,7 @@ next_pdu: server->pdu_size = pdu_length; /* make sure we have enough to get to the MID */ - if (server->pdu_size < HEADER_SIZE(server) - 1 - - server->vals->header_preamble_size) { + if (server->pdu_size < MID_HEADER_SIZE(server)) { cifs_server_dbg(VFS, "SMB response too short (%u bytes)\n", server->pdu_size); cifs_reconnect(server, true); @@ -1208,9 +1206,8 @@ next_pdu: /* read down to the MID */ length = cifs_read_from_socket(server, - buf + server->vals->header_preamble_size, - HEADER_SIZE(server) - 1 - - server->vals->header_preamble_size); + buf + HEADER_PREAMBLE_SIZE(server), + MID_HEADER_SIZE(server)); if (length < 0) continue; server->total_read += length; diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 96f3b0573606..4810bd62266a 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -3307,26 +3307,43 @@ get_smb2_acl(struct cifs_sb_info *cifs_sb, return pntsd; } +static long smb3_zero_data(struct file *file, struct cifs_tcon *tcon, + loff_t offset, loff_t len, unsigned int xid) +{ + struct cifsFileInfo *cfile = file->private_data; + struct file_zero_data_information fsctl_buf; + + cifs_dbg(FYI, "Offset %lld len %lld\n", offset, len); + + fsctl_buf.FileOffset = cpu_to_le64(offset); + fsctl_buf.BeyondFinalZero = cpu_to_le64(offset + len); + + return SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, + cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA, + (char *)&fsctl_buf, + sizeof(struct file_zero_data_information), + 0, NULL, NULL); +} + static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, loff_t offset, loff_t len, bool keep_size) { struct cifs_ses *ses = tcon->ses; - struct inode *inode; - struct cifsInodeInfo *cifsi; + struct inode *inode = file_inode(file); + struct cifsInodeInfo *cifsi = CIFS_I(inode); struct cifsFileInfo *cfile = file->private_data; - struct file_zero_data_information fsctl_buf; long rc; unsigned int xid; __le64 eof; xid = get_xid(); - inode = d_inode(cfile->dentry); - cifsi = CIFS_I(inode); - trace_smb3_zero_enter(xid, cfile->fid.persistent_fid, tcon->tid, ses->Suid, offset, len); + inode_lock(inode); + filemap_invalidate_lock(inode->i_mapping); + /* * We zero the range through ioctl, so we need remove the page caches * first, otherwise the data may be inconsistent with the server. @@ -3334,26 +3351,12 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, truncate_pagecache_range(inode, offset, offset + len - 1); /* if file not oplocked can't be sure whether asking to extend size */ - if (!CIFS_CACHE_READ(cifsi)) - if (keep_size == false) { - rc = -EOPNOTSUPP; - trace_smb3_zero_err(xid, cfile->fid.persistent_fid, - tcon->tid, ses->Suid, offset, len, rc); - free_xid(xid); - return rc; - } - - cifs_dbg(FYI, "Offset %lld len %lld\n", offset, len); - - fsctl_buf.FileOffset = cpu_to_le64(offset); - fsctl_buf.BeyondFinalZero = cpu_to_le64(offset + len); + rc = -EOPNOTSUPP; + if (keep_size == false && !CIFS_CACHE_READ(cifsi)) + goto zero_range_exit; - rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, - cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA, - (char *)&fsctl_buf, - sizeof(struct file_zero_data_information), - 0, NULL, NULL); - if (rc) + rc = smb3_zero_data(file, tcon, offset, len, xid); + if (rc < 0) goto zero_range_exit; /* @@ -3366,6 +3369,8 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, } zero_range_exit: + filemap_invalidate_unlock(inode->i_mapping); + inode_unlock(inode); free_xid(xid); if (rc) trace_smb3_zero_err(xid, cfile->fid.persistent_fid, tcon->tid, @@ -3379,7 +3384,7 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, loff_t offset, loff_t len) { - struct inode *inode; + struct inode *inode = file_inode(file); struct cifsFileInfo *cfile = file->private_data; struct file_zero_data_information fsctl_buf; long rc; @@ -3388,14 +3393,12 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, xid = get_xid(); - inode = d_inode(cfile->dentry); - + inode_lock(inode); /* Need to make file sparse, if not already, before freeing range. */ /* Consider adding equivalent for compressed since it could also work */ if (!smb2_set_sparse(xid, tcon, cfile, inode, set_sparse)) { rc = -EOPNOTSUPP; - free_xid(xid); - return rc; + goto out; } filemap_invalidate_lock(inode->i_mapping); @@ -3415,8 +3418,10 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, (char *)&fsctl_buf, sizeof(struct file_zero_data_information), CIFSMaxBufSize, NULL, NULL); - free_xid(xid); filemap_invalidate_unlock(inode->i_mapping); +out: + inode_unlock(inode); + free_xid(xid); return rc; } diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 91cfc5b47ac7..128e44e57528 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -2572,19 +2572,15 @@ alloc_path_with_tree_prefix(__le16 **out_path, int *out_size, int *out_len, path_len = UniStrnlen((wchar_t *)path, PATH_MAX); - /* - * make room for one path separator between the treename and - * path - */ - *out_len = treename_len + 1 + path_len; + /* make room for one path separator only if @path isn't empty */ + *out_len = treename_len + (path[0] ? 1 : 0) + path_len; /* - * final path needs to be null-terminated UTF16 with a - * size aligned to 8 + * final path needs to be 8-byte aligned as specified in + * MS-SMB2 2.2.13 SMB2 CREATE Request. */ - - *out_size = roundup((*out_len+1)*2, 8); - *out_path = kzalloc(*out_size, GFP_KERNEL); + *out_size = roundup(*out_len * sizeof(__le16), 8); + *out_path = kzalloc(*out_size + sizeof(__le16) /* null */, GFP_KERNEL); if (!*out_path) return -ENOMEM; diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index de7aeced7e16..c2fe035e573b 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -261,8 +261,8 @@ smb_rqst_len(struct TCP_Server_Info *server, struct smb_rqst *rqst) int nvec; unsigned long buflen = 0; - if (server->vals->header_preamble_size == 0 && - rqst->rq_nvec >= 2 && rqst->rq_iov[0].iov_len == 4) { + if (!is_smb1(server) && rqst->rq_nvec >= 2 && + rqst->rq_iov[0].iov_len == 4) { iov = &rqst->rq_iov[1]; nvec = rqst->rq_nvec - 1; } else { @@ -346,7 +346,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, sigprocmask(SIG_BLOCK, &mask, &oldmask); /* Generate a rfc1002 marker for SMB2+ */ - if (server->vals->header_preamble_size == 0) { + if (!is_smb1(server)) { struct kvec hiov = { .iov_base = &rfc1002_marker, .iov_len = 4 @@ -1238,7 +1238,7 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, buf = (char *)midQ[i]->resp_buf; resp_iov[i].iov_base = buf; resp_iov[i].iov_len = midQ[i]->resp_buf_size + - server->vals->header_preamble_size; + HEADER_PREAMBLE_SIZE(server); if (midQ[i]->large_buf) resp_buf_type[i] = CIFS_LARGE_BUFFER; @@ -1643,7 +1643,7 @@ int cifs_discard_remaining_data(struct TCP_Server_Info *server) { unsigned int rfclen = server->pdu_size; - int remaining = rfclen + server->vals->header_preamble_size - + int remaining = rfclen + HEADER_PREAMBLE_SIZE(server) - server->total_read; while (remaining > 0) { @@ -1689,8 +1689,7 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) unsigned int data_offset, data_len; struct cifs_readdata *rdata = mid->callback_data; char *buf = server->smallbuf; - unsigned int buflen = server->pdu_size + - server->vals->header_preamble_size; + unsigned int buflen = server->pdu_size + HEADER_PREAMBLE_SIZE(server); bool use_rdma_mr = false; cifs_dbg(FYI, "%s: mid=%llu offset=%llu bytes=%u\n", @@ -1724,10 +1723,10 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) /* set up first two iov for signature check and to get credits */ rdata->iov[0].iov_base = buf; - rdata->iov[0].iov_len = server->vals->header_preamble_size; - rdata->iov[1].iov_base = buf + server->vals->header_preamble_size; + rdata->iov[0].iov_len = HEADER_PREAMBLE_SIZE(server); + rdata->iov[1].iov_base = buf + HEADER_PREAMBLE_SIZE(server); rdata->iov[1].iov_len = - server->total_read - server->vals->header_preamble_size; + server->total_read - HEADER_PREAMBLE_SIZE(server); cifs_dbg(FYI, "0: iov_base=%p iov_len=%zu\n", rdata->iov[0].iov_base, rdata->iov[0].iov_len); cifs_dbg(FYI, "1: iov_base=%p iov_len=%zu\n", @@ -1752,7 +1751,7 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) } data_offset = server->ops->read_data_offset(buf) + - server->vals->header_preamble_size; + HEADER_PREAMBLE_SIZE(server); if (data_offset < server->total_read) { /* * win2k8 sometimes sends an offset of 0 when the read diff --git a/fs/inode.c b/fs/inode.c index 6462276dfdf0..ba1de23c13c1 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -2018,23 +2018,25 @@ static int __file_remove_privs(struct file *file, unsigned int flags) { struct dentry *dentry = file_dentry(file); struct inode *inode = file_inode(file); - int error; + int error = 0; int kill; if (IS_NOSEC(inode) || !S_ISREG(inode->i_mode)) return 0; kill = dentry_needs_remove_privs(dentry); - if (kill <= 0) + if (kill < 0) return kill; - if (flags & IOCB_NOWAIT) - return -EAGAIN; + if (kill) { + if (flags & IOCB_NOWAIT) + return -EAGAIN; + + error = __remove_privs(file_mnt_user_ns(file), dentry, kill); + } - error = __remove_privs(file_mnt_user_ns(file), dentry, kill); if (!error) inode_has_no_xattr(inode); - return error; } diff --git a/fs/locks.c b/fs/locks.c index c266cfdc3291..607f94a0e789 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -2129,6 +2129,7 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd) else error = locks_lock_file_wait(f.file, &fl); + locks_release_private(&fl); out_putf: fdput(f); diff --git a/fs/namespace.c b/fs/namespace.c index 68789f896f08..df137ba19d37 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -4238,6 +4238,13 @@ static int build_mount_idmapped(const struct mount_attr *attr, size_t usize, err = -EPERM; goto out_fput; } + + /* We're not controlling the target namespace. */ + if (!ns_capable(mnt_userns, CAP_SYS_ADMIN)) { + err = -EPERM; + goto out_fput; + } + kattr->mnt_userns = get_user_ns(mnt_userns); out_fput: diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index dbab3caa15ed..5d6c2ddc7ea6 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -2382,7 +2382,8 @@ static void nfs_dentry_remove_handle_error(struct inode *dir, { switch (error) { case -ENOENT: - d_delete(dentry); + if (d_really_is_positive(dentry)) + d_delete(dentry); nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); break; case 0: @@ -2484,8 +2485,10 @@ int nfs_unlink(struct inode *dir, struct dentry *dentry) */ error = -ETXTBSY; if (WARN_ON(dentry->d_flags & DCACHE_NFSFS_RENAMED) || - WARN_ON(dentry->d_fsdata == NFS_FSDATA_BLOCKED)) + WARN_ON(dentry->d_fsdata == NFS_FSDATA_BLOCKED)) { + spin_unlock(&dentry->d_lock); goto out; + } if (dentry->d_fsdata) /* old devname */ kfree(dentry->d_fsdata); diff --git a/fs/nfs/file.c b/fs/nfs/file.c index d2bcd4834c0e..e032fe201a36 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -221,8 +221,10 @@ nfs_file_fsync_commit(struct file *file, int datasync) int nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) { - struct nfs_open_context *ctx = nfs_file_open_context(file); struct inode *inode = file_inode(file); + struct nfs_inode *nfsi = NFS_I(inode); + long save_nredirtied = atomic_long_read(&nfsi->redirtied_pages); + long nredirtied; int ret; trace_nfs_fsync_enter(inode); @@ -237,15 +239,10 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) ret = pnfs_sync_inode(inode, !!datasync); if (ret != 0) break; - if (!test_and_clear_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags)) + nredirtied = atomic_long_read(&nfsi->redirtied_pages); + if (nredirtied == save_nredirtied) break; - /* - * If nfs_file_fsync_commit detected a server reboot, then - * resend all dirty pages that might have been covered by - * the NFS_CONTEXT_RESEND_WRITES flag - */ - start = 0; - end = LLONG_MAX; + save_nredirtied = nredirtied; } trace_nfs_fsync_exit(inode, ret); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index b4e46b0ffa2d..bea7c005119c 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -426,6 +426,7 @@ nfs_ilookup(struct super_block *sb, struct nfs_fattr *fattr, struct nfs_fh *fh) static void nfs_inode_init_regular(struct nfs_inode *nfsi) { atomic_long_set(&nfsi->nrequests, 0); + atomic_long_set(&nfsi->redirtied_pages, 0); INIT_LIST_HEAD(&nfsi->commit_info.list); atomic_long_set(&nfsi->commit_info.ncommit, 0); atomic_set(&nfsi->commit_info.rpcs_out, 0); diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index e88f6b18445e..9eb181287879 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -340,6 +340,11 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt, goto out; } + if (!S_ISREG(fattr->mode)) { + res = ERR_PTR(-EBADF); + goto out; + } + res = ERR_PTR(-ENOMEM); len = strlen(SSC_READ_NAME_BODY) + 16; read_name = kzalloc(len, GFP_KERNEL); @@ -357,6 +362,7 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt, r_ino->i_fop); if (IS_ERR(filep)) { res = ERR_CAST(filep); + iput(r_ino); goto out_free_name; } diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 41a9b6b58fb9..2613b7e36eb9 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -2817,7 +2817,6 @@ int pnfs_write_done_resend_to_mds(struct nfs_pgio_header *hdr) /* Resend all requests through the MDS */ nfs_pageio_init_write(&pgio, hdr->inode, FLUSH_STABLE, true, hdr->completion_ops); - set_bit(NFS_CONTEXT_RESEND_WRITES, &hdr->args.context->flags); return nfs_pageio_resend(&pgio, hdr); } EXPORT_SYMBOL_GPL(pnfs_write_done_resend_to_mds); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 51a7e202d6e5..1843fa235d9b 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1420,10 +1420,12 @@ static void nfs_initiate_write(struct nfs_pgio_header *hdr, */ static void nfs_redirty_request(struct nfs_page *req) { + struct nfs_inode *nfsi = NFS_I(page_file_mapping(req->wb_page)->host); + /* Bump the transmission count */ req->wb_nio++; nfs_mark_request_dirty(req); - set_bit(NFS_CONTEXT_RESEND_WRITES, &nfs_req_openctx(req)->flags); + atomic_long_inc(&nfsi->redirtied_pages); nfs_end_page_writeback(req); nfs_release_request(req); } @@ -1904,7 +1906,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data) /* We have a mismatch. Write the page again */ dprintk_cont(" mismatch\n"); nfs_mark_request_dirty(req); - set_bit(NFS_CONTEXT_RESEND_WRITES, &nfs_req_openctx(req)->flags); + atomic_long_inc(&NFS_I(data->inode)->redirtied_pages); next: nfs_unlock_and_release_request(req); /* Latency breaker */ diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c index 5bdff12a1232..6ae1f56b7358 100644 --- a/fs/ntfs3/xattr.c +++ b/fs/ntfs3/xattr.c @@ -483,8 +483,7 @@ out: } #ifdef CONFIG_NTFS3_FS_POSIX_ACL -static struct posix_acl *ntfs_get_acl_ex(struct user_namespace *mnt_userns, - struct inode *inode, int type, +static struct posix_acl *ntfs_get_acl_ex(struct inode *inode, int type, int locked) { struct ntfs_inode *ni = ntfs_i(inode); @@ -519,7 +518,7 @@ static struct posix_acl *ntfs_get_acl_ex(struct user_namespace *mnt_userns, /* Translate extended attribute to acl. */ if (err >= 0) { - acl = posix_acl_from_xattr(mnt_userns, buf, err); + acl = posix_acl_from_xattr(&init_user_ns, buf, err); } else if (err == -ENODATA) { acl = NULL; } else { @@ -542,8 +541,7 @@ struct posix_acl *ntfs_get_acl(struct inode *inode, int type, bool rcu) if (rcu) return ERR_PTR(-ECHILD); - /* TODO: init_user_ns? */ - return ntfs_get_acl_ex(&init_user_ns, inode, type, 0); + return ntfs_get_acl_ex(inode, type, 0); } static noinline int ntfs_set_acl_ex(struct user_namespace *mnt_userns, @@ -595,7 +593,7 @@ static noinline int ntfs_set_acl_ex(struct user_namespace *mnt_userns, value = kmalloc(size, GFP_NOFS); if (!value) return -ENOMEM; - err = posix_acl_to_xattr(mnt_userns, acl, value, size); + err = posix_acl_to_xattr(&init_user_ns, acl, value, size); if (err < 0) goto out; flags = 0; @@ -646,7 +644,7 @@ static int ntfs_xattr_get_acl(struct user_namespace *mnt_userns, if (!acl) return -ENODATA; - err = posix_acl_to_xattr(mnt_userns, acl, buffer, size); + err = posix_acl_to_xattr(&init_user_ns, acl, buffer, size); posix_acl_release(acl); return err; @@ -670,12 +668,12 @@ static int ntfs_xattr_set_acl(struct user_namespace *mnt_userns, if (!value) { acl = NULL; } else { - acl = posix_acl_from_xattr(mnt_userns, value, size); + acl = posix_acl_from_xattr(&init_user_ns, value, size); if (IS_ERR(acl)) return PTR_ERR(acl); if (acl) { - err = posix_acl_valid(mnt_userns, acl); + err = posix_acl_valid(&init_user_ns, acl); if (err) goto release_and_out; } diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index b45fea69fff3..0fbcb590af84 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -460,9 +460,12 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size) * of the POSIX ACLs retrieved from the lower layer to this function to not * alter the POSIX ACLs for the underlying filesystem. */ -static void ovl_idmap_posix_acl(struct user_namespace *mnt_userns, +static void ovl_idmap_posix_acl(struct inode *realinode, + struct user_namespace *mnt_userns, struct posix_acl *acl) { + struct user_namespace *fs_userns = i_user_ns(realinode); + for (unsigned int i = 0; i < acl->a_count; i++) { vfsuid_t vfsuid; vfsgid_t vfsgid; @@ -470,11 +473,11 @@ static void ovl_idmap_posix_acl(struct user_namespace *mnt_userns, struct posix_acl_entry *e = &acl->a_entries[i]; switch (e->e_tag) { case ACL_USER: - vfsuid = make_vfsuid(mnt_userns, &init_user_ns, e->e_uid); + vfsuid = make_vfsuid(mnt_userns, fs_userns, e->e_uid); e->e_uid = vfsuid_into_kuid(vfsuid); break; case ACL_GROUP: - vfsgid = make_vfsgid(mnt_userns, &init_user_ns, e->e_gid); + vfsgid = make_vfsgid(mnt_userns, fs_userns, e->e_gid); e->e_gid = vfsgid_into_kgid(vfsgid); break; } @@ -536,7 +539,7 @@ struct posix_acl *ovl_get_acl(struct inode *inode, int type, bool rcu) if (!clone) clone = ERR_PTR(-ENOMEM); else - ovl_idmap_posix_acl(mnt_user_ns(realpath.mnt), clone); + ovl_idmap_posix_acl(realinode, mnt_user_ns(realpath.mnt), clone); /* * Since we're not in RCU path walk we always need to release the * original ACLs. diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 1d17d7b13dcd..5af33800743e 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -361,6 +361,7 @@ posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode, const struct posix_acl *acl, int want) { const struct posix_acl_entry *pa, *pe, *mask_obj; + struct user_namespace *fs_userns = i_user_ns(inode); int found = 0; vfsuid_t vfsuid; vfsgid_t vfsgid; @@ -376,7 +377,7 @@ posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode, goto check_perm; break; case ACL_USER: - vfsuid = make_vfsuid(mnt_userns, &init_user_ns, + vfsuid = make_vfsuid(mnt_userns, fs_userns, pa->e_uid); if (vfsuid_eq_kuid(vfsuid, current_fsuid())) goto mask; @@ -390,7 +391,7 @@ posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode, } break; case ACL_GROUP: - vfsgid = make_vfsgid(mnt_userns, &init_user_ns, + vfsgid = make_vfsgid(mnt_userns, fs_userns, pa->e_gid); if (vfsgid_in_group_p(vfsgid)) { found = 1; @@ -736,6 +737,7 @@ void posix_acl_getxattr_idmapped_mnt(struct user_namespace *mnt_userns, { struct posix_acl_xattr_header *header = value; struct posix_acl_xattr_entry *entry = (void *)(header + 1), *end; + struct user_namespace *fs_userns = i_user_ns(inode); int count; vfsuid_t vfsuid; vfsgid_t vfsgid; @@ -753,13 +755,13 @@ void posix_acl_getxattr_idmapped_mnt(struct user_namespace *mnt_userns, switch (le16_to_cpu(entry->e_tag)) { case ACL_USER: uid = make_kuid(&init_user_ns, le32_to_cpu(entry->e_id)); - vfsuid = make_vfsuid(mnt_userns, &init_user_ns, uid); + vfsuid = make_vfsuid(mnt_userns, fs_userns, uid); entry->e_id = cpu_to_le32(from_kuid(&init_user_ns, vfsuid_into_kuid(vfsuid))); break; case ACL_GROUP: gid = make_kgid(&init_user_ns, le32_to_cpu(entry->e_id)); - vfsgid = make_vfsgid(mnt_userns, &init_user_ns, gid); + vfsgid = make_vfsgid(mnt_userns, fs_userns, gid); entry->e_id = cpu_to_le32(from_kgid(&init_user_ns, vfsgid_into_kgid(vfsgid))); break; @@ -775,6 +777,7 @@ void posix_acl_setxattr_idmapped_mnt(struct user_namespace *mnt_userns, { struct posix_acl_xattr_header *header = value; struct posix_acl_xattr_entry *entry = (void *)(header + 1), *end; + struct user_namespace *fs_userns = i_user_ns(inode); int count; vfsuid_t vfsuid; vfsgid_t vfsgid; @@ -793,13 +796,13 @@ void posix_acl_setxattr_idmapped_mnt(struct user_namespace *mnt_userns, case ACL_USER: uid = make_kuid(&init_user_ns, le32_to_cpu(entry->e_id)); vfsuid = VFSUIDT_INIT(uid); - uid = from_vfsuid(mnt_userns, &init_user_ns, vfsuid); + uid = from_vfsuid(mnt_userns, fs_userns, vfsuid); entry->e_id = cpu_to_le32(from_kuid(&init_user_ns, uid)); break; case ACL_GROUP: gid = make_kgid(&init_user_ns, le32_to_cpu(entry->e_id)); vfsgid = VFSGIDT_INIT(gid); - gid = from_vfsgid(mnt_userns, &init_user_ns, vfsgid); + gid = from_vfsgid(mnt_userns, fs_userns, vfsgid); entry->e_id = cpu_to_le32(from_kgid(&init_user_ns, gid)); break; default: diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index a3398d0f1927..4e0023643f8b 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -527,10 +527,12 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, struct vm_area_struct *vma = walk->vma; bool locked = !!(vma->vm_flags & VM_LOCKED); struct page *page = NULL; - bool migration = false; + bool migration = false, young = false, dirty = false; if (pte_present(*pte)) { page = vm_normal_page(vma, addr, *pte); + young = pte_young(*pte); + dirty = pte_dirty(*pte); } else if (is_swap_pte(*pte)) { swp_entry_t swpent = pte_to_swp_entry(*pte); @@ -560,8 +562,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, if (!page) return; - smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte), - locked, migration); + smaps_account(mss, page, false, young, dirty, locked, migration); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 1c44bf75f916..175de70e3adf 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1601,6 +1601,10 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, wake_userfault(vma->vm_userfaultfd_ctx.ctx, &range); } + /* Reset ptes for the whole vma range if wr-protected */ + if (userfaultfd_wp(vma)) + uffd_wp_range(mm, vma, start, vma_end - start, false); + new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS; prev = vma_merge(mm, prev, start, vma_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, diff --git a/include/asm-generic/bitops/generic-non-atomic.h b/include/asm-generic/bitops/generic-non-atomic.h index 3d5ebd24652b..564a8c675d85 100644 --- a/include/asm-generic/bitops/generic-non-atomic.h +++ b/include/asm-generic/bitops/generic-non-atomic.h @@ -4,6 +4,7 @@ #define __ASM_GENERIC_BITOPS_GENERIC_NON_ATOMIC_H #include <linux/bits.h> +#include <asm/barrier.h> #ifndef _LINUX_BITOPS_H #error only <linux/bitops.h> can be included directly @@ -127,6 +128,18 @@ generic_test_bit(unsigned long nr, const volatile unsigned long *addr) return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1))); } +/** + * generic_test_bit_acquire - Determine, with acquire semantics, whether a bit is set + * @nr: bit number to test + * @addr: Address to start counting from + */ +static __always_inline bool +generic_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr) +{ + unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); + return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1))); +} + /* * const_*() definitions provide good compile-time optimizations when * the passed arguments can be resolved at compile time. @@ -137,6 +150,7 @@ generic_test_bit(unsigned long nr, const volatile unsigned long *addr) #define const___test_and_set_bit generic___test_and_set_bit #define const___test_and_clear_bit generic___test_and_clear_bit #define const___test_and_change_bit generic___test_and_change_bit +#define const_test_bit_acquire generic_test_bit_acquire /** * const_test_bit - Determine whether a bit is set diff --git a/include/asm-generic/bitops/instrumented-non-atomic.h b/include/asm-generic/bitops/instrumented-non-atomic.h index 988a3bbfba34..2b238b161a62 100644 --- a/include/asm-generic/bitops/instrumented-non-atomic.h +++ b/include/asm-generic/bitops/instrumented-non-atomic.h @@ -142,4 +142,16 @@ _test_bit(unsigned long nr, const volatile unsigned long *addr) return arch_test_bit(nr, addr); } +/** + * _test_bit_acquire - Determine, with acquire semantics, whether a bit is set + * @nr: bit number to test + * @addr: Address to start counting from + */ +static __always_inline bool +_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr) +{ + instrument_atomic_read(addr + BIT_WORD(nr), sizeof(long)); + return arch_test_bit_acquire(nr, addr); +} + #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */ diff --git a/include/asm-generic/bitops/non-atomic.h b/include/asm-generic/bitops/non-atomic.h index 5c37ced343ae..71f8d54a5195 100644 --- a/include/asm-generic/bitops/non-atomic.h +++ b/include/asm-generic/bitops/non-atomic.h @@ -13,6 +13,7 @@ #define arch___test_and_change_bit generic___test_and_change_bit #define arch_test_bit generic_test_bit +#define arch_test_bit_acquire generic_test_bit_acquire #include <asm-generic/bitops/non-instrumented-non-atomic.h> diff --git a/include/asm-generic/bitops/non-instrumented-non-atomic.h b/include/asm-generic/bitops/non-instrumented-non-atomic.h index bdb9b1ffaee9..0ddc78dfc358 100644 --- a/include/asm-generic/bitops/non-instrumented-non-atomic.h +++ b/include/asm-generic/bitops/non-instrumented-non-atomic.h @@ -12,5 +12,6 @@ #define ___test_and_change_bit arch___test_and_change_bit #define _test_bit arch_test_bit +#define _test_bit_acquire arch_test_bit_acquire #endif /* __ASM_GENERIC_BITOPS_NON_INSTRUMENTED_NON_ATOMIC_H */ diff --git a/include/linux/bitops.h b/include/linux/bitops.h index cf9bf65039f2..3b89c64bcfd8 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -59,6 +59,7 @@ extern unsigned long __sw_hweight64(__u64 w); #define __test_and_clear_bit(nr, addr) bitop(___test_and_clear_bit, nr, addr) #define __test_and_change_bit(nr, addr) bitop(___test_and_change_bit, nr, addr) #define test_bit(nr, addr) bitop(_test_bit, nr, addr) +#define test_bit_acquire(nr, addr) bitop(_test_bit_acquire, nr, addr) /* * Include this here because some architectures need generic_ffs/fls in diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index def8b8d30ccc..089c9ade4325 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -156,7 +156,7 @@ static __always_inline int buffer_uptodate(const struct buffer_head *bh) * make it consistent with folio_test_uptodate * pairs with smp_mb__before_atomic in set_buffer_uptodate */ - return (smp_load_acquire(&bh->b_state) & (1UL << BH_Uptodate)) != 0; + return test_bit_acquire(BH_Uptodate, &bh->b_state); } #define bh_offset(bh) ((unsigned long)(bh)->b_data & ~PAGE_MASK) diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index ed53bfe7c46c..ac5d0515680e 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -734,11 +734,6 @@ static inline struct cgroup *cgroup_parent(struct cgroup *cgrp) return NULL; } -static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) -{ - return NULL; -} - static inline bool cgroup_psi_enabled(void) { return false; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 96b16fbe1aa4..7b7ce602c808 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -779,6 +779,7 @@ struct mlx5_core_dev { enum mlx5_device_state state; /* sync interface state */ struct mutex intf_state_mutex; + struct lock_class_key lock_key; unsigned long intf_state; struct mlx5_priv priv; struct mlx5_profile profile; diff --git a/include/linux/mm.h b/include/linux/mm.h index 3bedc449c14d..982f2607180b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2885,7 +2885,6 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, #define FOLL_MIGRATION 0x400 /* wait for page to replace migration entry */ #define FOLL_TRIED 0x800 /* a retry, previous pass started an IO */ #define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */ -#define FOLL_COW 0x4000 /* internal GUP flag */ #define FOLL_ANON 0x8000 /* don't do file mappings */ #define FOLL_LONGTERM 0x10000 /* mapping lifetime is indefinite: see below */ #define FOLL_SPLIT_PMD 0x20000 /* split huge pmd before returning */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1a3cb93c3dcc..05d6f3facd5a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -640,9 +640,23 @@ extern int sysctl_devconf_inherit_init_net; */ static inline bool net_has_fallback_tunnels(const struct net *net) { - return !IS_ENABLED(CONFIG_SYSCTL) || - !sysctl_fb_tunnels_only_for_init_net || - (net == &init_net && sysctl_fb_tunnels_only_for_init_net == 1); +#if IS_ENABLED(CONFIG_SYSCTL) + int fb_tunnels_only_for_init_net = READ_ONCE(sysctl_fb_tunnels_only_for_init_net); + + return !fb_tunnels_only_for_init_net || + (net_eq(net, &init_net) && fb_tunnels_only_for_init_net == 1); +#else + return true; +#endif +} + +static inline int net_inherit_devconf(void) +{ +#if IS_ENABLED(CONFIG_SYSCTL) + return READ_ONCE(sysctl_devconf_inherit_init_net); +#else + return 0; +#endif } static inline int netdev_queue_numa_node_read(const struct netdev_queue *q) diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index a13296d6c7ce..fd533552a062 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -94,10 +94,6 @@ struct ebt_table { struct ebt_replace_kernel *table; unsigned int valid_hooks; rwlock_t lock; - /* e.g. could be the table explicitly only allows certain - * matches, targets, ... 0 == let it in */ - int (*check)(const struct ebt_table_info *info, - unsigned int valid_hooks); /* the data used by the kernel */ struct ebt_table_info *private; struct nf_hook_ops *ops; diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index b32ed68e7dc4..7931fa472561 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -83,7 +83,6 @@ struct nfs_open_context { fmode_t mode; unsigned long flags; -#define NFS_CONTEXT_RESEND_WRITES (1) #define NFS_CONTEXT_BAD (2) #define NFS_CONTEXT_UNLOCK (3) #define NFS_CONTEXT_FILE_OPEN (4) @@ -182,6 +181,7 @@ struct nfs_inode { /* Regular file */ struct { atomic_long_t nrequests; + atomic_long_t redirtied_pages; struct nfs_mds_commit_info commit_info; struct mutex commit_mutex; }; diff --git a/include/linux/psi.h b/include/linux/psi.h index 89784763d19e..dd74411ac21d 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -27,7 +27,7 @@ void psi_memstall_leave(unsigned long *flags); int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res); struct psi_trigger *psi_trigger_create(struct psi_group *group, - char *buf, size_t nbytes, enum psi_res res); + char *buf, enum psi_res res); void psi_trigger_destroy(struct psi_trigger *t); __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 1b6c4013f691..ff0b990de83d 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -29,15 +29,10 @@ struct shmem_inode_info { struct inode vfs_inode; }; -#define SHMEM_FL_USER_VISIBLE FS_FL_USER_VISIBLE -#define SHMEM_FL_USER_MODIFIABLE FS_FL_USER_MODIFIABLE -#define SHMEM_FL_INHERITED FS_FL_USER_MODIFIABLE - -/* Flags that are appropriate for regular files (all but dir-specific ones). */ -#define SHMEM_REG_FLMASK (~(FS_DIRSYNC_FL | FS_TOPDIR_FL)) - -/* Flags that are appropriate for non-directories/regular files. */ -#define SHMEM_OTHER_FLMASK (FS_NODUMP_FL | FS_NOATIME_FL) +#define SHMEM_FL_USER_VISIBLE FS_FL_USER_VISIBLE +#define SHMEM_FL_USER_MODIFIABLE \ + (FS_IMMUTABLE_FL | FS_APPEND_FL | FS_NODUMP_FL | FS_NOATIME_FL) +#define SHMEM_FL_INHERITED (FS_NODUMP_FL | FS_NOATIME_FL) struct shmem_sb_info { unsigned long max_blocks; /* How many blocks are allowed */ diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 732b522bacb7..e1b8a915e9e9 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -73,6 +73,8 @@ extern ssize_t mcopy_continue(struct mm_struct *dst_mm, unsigned long dst_start, extern int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, unsigned long len, bool enable_wp, atomic_t *mmap_changing); +extern void uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *vma, + unsigned long start, unsigned long len, bool enable_wp); /* mm helpers */ static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma, diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 404024486fa5..f3fc36cd2276 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -20,12 +20,19 @@ #define HIGHMEM_ZONE(xx) #endif -#define FOR_ALL_ZONES(xx) DMA_ZONE(xx) DMA32_ZONE(xx) xx##_NORMAL, HIGHMEM_ZONE(xx) xx##_MOVABLE +#ifdef CONFIG_ZONE_DEVICE +#define DEVICE_ZONE(xx) xx##_DEVICE, +#else +#define DEVICE_ZONE(xx) +#endif + +#define FOR_ALL_ZONES(xx) DMA_ZONE(xx) DMA32_ZONE(xx) xx##_NORMAL, \ + HIGHMEM_ZONE(xx) xx##_MOVABLE, DEVICE_ZONE(xx) enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, - FOR_ALL_ZONES(PGALLOC), - FOR_ALL_ZONES(ALLOCSTALL), - FOR_ALL_ZONES(PGSCAN_SKIP), + FOR_ALL_ZONES(PGALLOC) + FOR_ALL_ZONES(ALLOCSTALL) + FOR_ALL_ZONES(PGSCAN_SKIP) PGFREE, PGACTIVATE, PGDEACTIVATE, PGLAZYFREE, PGFAULT, PGMAJFAULT, PGLAZYFREED, diff --git a/include/linux/wait_bit.h b/include/linux/wait_bit.h index 7dec36aecbd9..7725b7579b78 100644 --- a/include/linux/wait_bit.h +++ b/include/linux/wait_bit.h @@ -71,7 +71,7 @@ static inline int wait_on_bit(unsigned long *word, int bit, unsigned mode) { might_sleep(); - if (!test_bit(bit, word)) + if (!test_bit_acquire(bit, word)) return 0; return out_of_line_wait_on_bit(word, bit, bit_wait, @@ -96,7 +96,7 @@ static inline int wait_on_bit_io(unsigned long *word, int bit, unsigned mode) { might_sleep(); - if (!test_bit(bit, word)) + if (!test_bit_acquire(bit, word)) return 0; return out_of_line_wait_on_bit(word, bit, bit_wait_io, @@ -123,7 +123,7 @@ wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode, unsigned long timeout) { might_sleep(); - if (!test_bit(bit, word)) + if (!test_bit_acquire(bit, word)) return 0; return out_of_line_wait_on_bit_timeout(word, bit, bit_wait_timeout, @@ -151,7 +151,7 @@ wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action, unsigned mode) { might_sleep(); - if (!test_bit(bit, word)) + if (!test_bit_acquire(bit, word)) return 0; return out_of_line_wait_on_bit(word, bit, action, mode); } diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h index 184105d68294..be2992e6de5d 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -290,7 +290,7 @@ static inline const char *bond_3ad_churn_desc(churn_state_t state) } /* ========== AD Exported functions to the main bonding code ========== */ -void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution); +void bond_3ad_initialize(struct bonding *bond); void bond_3ad_bind_slave(struct slave *slave); void bond_3ad_unbind_slave(struct slave *slave); void bond_3ad_state_machine_handler(struct work_struct *); diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index c4898fcbf923..f90f0021f5f2 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -33,7 +33,7 @@ extern unsigned int sysctl_net_busy_poll __read_mostly; static inline bool net_busy_loop_on(void) { - return sysctl_net_busy_poll; + return READ_ONCE(sysctl_net_busy_poll); } static inline bool sk_can_busy_loop(const struct sock *sk) diff --git a/include/net/gro.h b/include/net/gro.h index 867656b0739c..24003dea8fa4 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -439,7 +439,7 @@ static inline void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb, { list_add_tail(&skb->list, &napi->rx_list); napi->rx_count += segs; - if (napi->rx_count >= gro_normal_batch) + if (napi->rx_count >= READ_ONCE(gro_normal_batch)) gro_normal_list(napi); } diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index d5326c44b453..cd982f4a0f50 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -270,6 +270,7 @@ void flow_offload_refresh(struct nf_flowtable *flow_table, struct flow_offload_tuple_rhash *flow_offload_lookup(struct nf_flowtable *flow_table, struct flow_offload_tuple *tuple); +void nf_flow_table_gc_run(struct nf_flowtable *flow_table); void nf_flow_table_gc_cleanup(struct nf_flowtable *flowtable, struct net_device *dev); void nf_flow_table_cleanup(struct net_device *dev); @@ -306,6 +307,8 @@ void nf_flow_offload_stats(struct nf_flowtable *flowtable, struct flow_offload *flow); void nf_flow_table_offload_flush(struct nf_flowtable *flowtable); +void nf_flow_table_offload_flush_cleanup(struct nf_flowtable *flowtable); + int nf_flow_table_offload_setup(struct nf_flowtable *flowtable, struct net_device *dev, enum flow_block_command cmd); diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 99aae36c04b9..cdb7db9b0e25 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1652,6 +1652,7 @@ struct nftables_pernet { struct list_head module_list; struct list_head notify_list; struct mutex commit_mutex; + u64 table_handle; unsigned int base_seq; u8 validate_state; }; diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 1463cfecb56b..9e0b5c8d92ce 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -12,6 +12,10 @@ #include <linux/types.h> #include <linux/time_types.h> +#ifdef __cplusplus +extern "C" { +#endif + /* * IO submission data structure (Submission Queue Entry) */ @@ -661,4 +665,8 @@ struct io_uring_recvmsg_out { __u32 flags; }; +#ifdef __cplusplus +} +#endif + #endif diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index b1f3e6a8f11a..4f84ea7ee14c 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -296,7 +296,7 @@ enum xfrm_attr_type_t { XFRMA_ETIMER_THRESH, XFRMA_SRCADDR, /* xfrm_address_t */ XFRMA_COADDR, /* xfrm_address_t */ - XFRMA_LASTUSED, /* unsigned long */ + XFRMA_LASTUSED, /* __u64 */ XFRMA_POLICY_TYPE, /* struct xfrm_userpolicy_type */ XFRMA_MIGRATE, XFRMA_ALG_AEAD, /* struct xfrm_algo_aead */ diff --git a/include/ufs/ufshci.h b/include/ufs/ufshci.h index f81aa95ffbc4..f525566a0864 100644 --- a/include/ufs/ufshci.h +++ b/include/ufs/ufshci.h @@ -135,11 +135,7 @@ static inline u32 ufshci_version(u32 major, u32 minor) #define UFSHCD_UIC_MASK (UIC_COMMAND_COMPL | UFSHCD_UIC_PWR_MASK) -#define UFSHCD_ERROR_MASK (UIC_ERROR |\ - DEVICE_FATAL_ERROR |\ - CONTROLLER_FATAL_ERROR |\ - SYSTEM_BUS_FATAL_ERROR |\ - CRYPTO_ENGINE_FATAL_ERROR) +#define UFSHCD_ERROR_MASK (UIC_ERROR | INT_FATAL_ERRORS) #define INT_FATAL_ERRORS (DEVICE_FATAL_ERROR |\ CONTROLLER_FATAL_ERROR |\ diff --git a/init/main.c b/init/main.c index 91642a4e69be..1fe7942f5d4a 100644 --- a/init/main.c +++ b/init/main.c @@ -1446,13 +1446,25 @@ static noinline void __init kernel_init_freeable(void); #if defined(CONFIG_STRICT_KERNEL_RWX) || defined(CONFIG_STRICT_MODULE_RWX) bool rodata_enabled __ro_after_init = true; + +#ifndef arch_parse_debug_rodata +static inline bool arch_parse_debug_rodata(char *str) { return false; } +#endif + static int __init set_debug_rodata(char *str) { - if (strtobool(str, &rodata_enabled)) + if (arch_parse_debug_rodata(str)) + return 0; + + if (str && !strcmp(str, "on")) + rodata_enabled = true; + else if (str && !strcmp(str, "off")) + rodata_enabled = false; + else pr_warn("Invalid option string for rodata: '%s'\n", str); - return 1; + return 0; } -__setup("rodata=", set_debug_rodata); +early_param("rodata", set_debug_rodata); #endif #ifdef CONFIG_STRICT_KERNEL_RWX diff --git a/io_uring/cancel.c b/io_uring/cancel.c index e4e1dc0325f0..5fc5d3e80fcb 100644 --- a/io_uring/cancel.c +++ b/io_uring/cancel.c @@ -218,7 +218,7 @@ static int __io_sync_cancel(struct io_uring_task *tctx, (cd->flags & IORING_ASYNC_CANCEL_FD_FIXED)) { unsigned long file_ptr; - if (unlikely(fd > ctx->nr_user_files)) + if (unlikely(fd >= ctx->nr_user_files)) return -EBADF; fd = array_index_nospec(fd, ctx->nr_user_files); file_ptr = io_fixed_file_slot(&ctx->file_table, fd)->file_ptr; diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index ebfdb2212ec2..77616279000b 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -1450,9 +1450,10 @@ int io_req_prep_async(struct io_kiocb *req) return 0; if (WARN_ON_ONCE(req_has_async_data(req))) return -EFAULT; - if (io_alloc_async_data(req)) - return -EAGAIN; - + if (!io_op_defs[req->opcode].manual_alloc) { + if (io_alloc_async_data(req)) + return -EAGAIN; + } return def->prep_async(req); } diff --git a/io_uring/net.c b/io_uring/net.c index f8cdf1dc3863..0af8a02df580 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -182,6 +182,37 @@ static int io_sendmsg_copy_hdr(struct io_kiocb *req, &iomsg->free_iov); } +int io_sendzc_prep_async(struct io_kiocb *req) +{ + struct io_sendzc *zc = io_kiocb_to_cmd(req, struct io_sendzc); + struct io_async_msghdr *io; + int ret; + + if (!zc->addr || req_has_async_data(req)) + return 0; + if (io_alloc_async_data(req)) + return -ENOMEM; + + io = req->async_data; + ret = move_addr_to_kernel(zc->addr, zc->addr_len, &io->addr); + return ret; +} + +static int io_setup_async_addr(struct io_kiocb *req, + struct sockaddr_storage *addr, + unsigned int issue_flags) +{ + struct io_async_msghdr *io; + + if (!addr || req_has_async_data(req)) + return -EAGAIN; + if (io_alloc_async_data(req)) + return -ENOMEM; + io = req->async_data; + memcpy(&io->addr, addr, sizeof(io->addr)); + return -EAGAIN; +} + int io_sendmsg_prep_async(struct io_kiocb *req) { int ret; @@ -944,7 +975,7 @@ static int io_sg_from_iter(struct sock *sk, struct sk_buff *skb, int io_sendzc(struct io_kiocb *req, unsigned int issue_flags) { - struct sockaddr_storage address; + struct sockaddr_storage __address, *addr = NULL; struct io_ring_ctx *ctx = req->ctx; struct io_sendzc *zc = io_kiocb_to_cmd(req, struct io_sendzc); struct io_notif_slot *notif_slot; @@ -978,10 +1009,17 @@ int io_sendzc(struct io_kiocb *req, unsigned int issue_flags) msg.msg_namelen = 0; if (zc->addr) { - ret = move_addr_to_kernel(zc->addr, zc->addr_len, &address); - if (unlikely(ret < 0)) - return ret; - msg.msg_name = (struct sockaddr *)&address; + if (req_has_async_data(req)) { + struct io_async_msghdr *io = req->async_data; + + msg.msg_name = addr = &io->addr; + } else { + ret = move_addr_to_kernel(zc->addr, zc->addr_len, &__address); + if (unlikely(ret < 0)) + return ret; + msg.msg_name = (struct sockaddr *)&__address; + addr = &__address; + } msg.msg_namelen = zc->addr_len; } @@ -989,7 +1027,7 @@ int io_sendzc(struct io_kiocb *req, unsigned int issue_flags) ret = io_import_fixed(WRITE, &msg.msg_iter, req->imu, (u64)(uintptr_t)zc->buf, zc->len); if (unlikely(ret)) - return ret; + return ret; } else { ret = import_single_range(WRITE, zc->buf, zc->len, &iov, &msg.msg_iter); @@ -1013,16 +1051,18 @@ int io_sendzc(struct io_kiocb *req, unsigned int issue_flags) if (unlikely(ret < min_ret)) { if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK)) - return -EAGAIN; + return io_setup_async_addr(req, addr, issue_flags); + if (ret > 0 && io_net_retry(sock, msg.msg_flags)) { zc->len -= ret; zc->buf += ret; zc->done_io += ret; req->flags |= REQ_F_PARTIAL_IO; - return -EAGAIN; + return io_setup_async_addr(req, addr, issue_flags); } if (ret == -ERESTARTSYS) ret = -EINTR; + req_set_fail(req); } else if (zc->flags & IORING_RECVSEND_NOTIF_FLUSH) { io_notif_slot_flush_submit(notif_slot, 0); } diff --git a/io_uring/net.h b/io_uring/net.h index 7c438d39c089..f91f56c6eeac 100644 --- a/io_uring/net.h +++ b/io_uring/net.h @@ -31,6 +31,7 @@ struct io_async_connect { int io_shutdown_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_shutdown(struct io_kiocb *req, unsigned int issue_flags); +int io_sendzc_prep_async(struct io_kiocb *req); int io_sendmsg_prep_async(struct io_kiocb *req); void io_sendmsg_recvmsg_cleanup(struct io_kiocb *req); int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); diff --git a/io_uring/notif.c b/io_uring/notif.c index 977736e82c1a..96f076b175e0 100644 --- a/io_uring/notif.c +++ b/io_uring/notif.c @@ -73,7 +73,7 @@ struct io_kiocb *io_alloc_notif(struct io_ring_ctx *ctx, } void io_notif_slot_flush(struct io_notif_slot *slot) - __must_hold(&ctx->uring_lock) + __must_hold(&slot->notif->ctx->uring_lock) { struct io_kiocb *notif = slot->notif; struct io_notif_data *nd = io_notif_to_data(notif); @@ -81,8 +81,10 @@ void io_notif_slot_flush(struct io_notif_slot *slot) slot->notif = NULL; /* drop slot's master ref */ - if (refcount_dec_and_test(&nd->uarg.refcnt)) - io_notif_complete(notif); + if (refcount_dec_and_test(&nd->uarg.refcnt)) { + notif->io_task_work.func = __io_notif_complete_tw; + io_req_task_work_add(notif); + } } __cold int io_notif_unregister(struct io_ring_ctx *ctx) diff --git a/io_uring/opdef.c b/io_uring/opdef.c index 72dd2b2d8a9d..41410126c1c6 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -478,13 +478,15 @@ const struct io_op_def io_op_defs[] = { .pollout = 1, .audit_skip = 1, .ioprio = 1, + .manual_alloc = 1, #if defined(CONFIG_NET) + .async_size = sizeof(struct io_async_msghdr), .prep = io_sendzc_prep, .issue = io_sendzc, + .prep_async = io_sendzc_prep_async, #else .prep = io_eopnotsupp_prep, #endif - }, }; diff --git a/io_uring/opdef.h b/io_uring/opdef.h index ece8ed4f96c4..763c6e54e2ee 100644 --- a/io_uring/opdef.h +++ b/io_uring/opdef.h @@ -25,6 +25,8 @@ struct io_op_def { unsigned ioprio : 1; /* supports iopoll */ unsigned iopoll : 1; + /* opcode specific path will handle ->async_data allocation if needed */ + unsigned manual_alloc : 1; /* size of async data needed, if any */ unsigned short async_size; diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index 8e0cc2d9205e..b9989ae7b957 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -112,7 +112,7 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags) if (ret < 0) req_set_fail(req); io_req_set_res(req, ret, 0); - return IOU_OK; + return ret; } return IOU_ISSUE_SKIP_COMPLETE; diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c index 6432a37ac1c9..c565fbf66ac8 100644 --- a/kernel/audit_fsnotify.c +++ b/kernel/audit_fsnotify.c @@ -102,6 +102,7 @@ struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule, char *pa ret = fsnotify_add_inode_mark(&audit_mark->mark, inode, 0); if (ret < 0) { + audit_mark->path = NULL; fsnotify_put_mark(&audit_mark->mark); audit_mark = ERR_PTR(ret); } diff --git a/kernel/auditsc.c b/kernel/auditsc.c index dd8d9ab747c3..79a5da1bc5bb 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1940,6 +1940,7 @@ void __audit_uring_exit(int success, long code) goto out; } + audit_return_fixup(ctx, success, code); if (ctx->context == AUDIT_CTX_SYSCALL) { /* * NOTE: See the note in __audit_uring_entry() about the case @@ -1981,7 +1982,6 @@ void __audit_uring_exit(int success, long code) audit_filter_inodes(current, ctx); if (ctx->current_state != AUDIT_STATE_RECORD) goto out; - audit_return_fixup(ctx, success, code); audit_log_exit(); out: @@ -2065,13 +2065,13 @@ void __audit_syscall_exit(int success, long return_code) if (!list_empty(&context->killed_trees)) audit_kill_trees(context); + audit_return_fixup(context, success, return_code); /* run through both filters to ensure we set the filterkey properly */ audit_filter_syscall(current, context); audit_filter_inodes(current, context); if (context->current_state < AUDIT_STATE_RECORD) goto out; - audit_return_fixup(context, success, return_code); audit_log_exit(); out: diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 2ade21b54dc4..ff6a8099eb2a 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -59,6 +59,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) int retval = 0; mutex_lock(&cgroup_mutex); + cpus_read_lock(); percpu_down_write(&cgroup_threadgroup_rwsem); for_each_root(root) { struct cgroup *from_cgrp; @@ -72,6 +73,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) break; } percpu_up_write(&cgroup_threadgroup_rwsem); + cpus_read_unlock(); mutex_unlock(&cgroup_mutex); return retval; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index ffaccd6373f1..e4bb5d57f4d1 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1820,6 +1820,7 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) if (ss->css_rstat_flush) { list_del_rcu(&css->rstat_css_node); + synchronize_rcu(); list_add_rcu(&css->rstat_css_node, &dcgrp->rstat_css_list); } @@ -2370,6 +2371,47 @@ int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen) EXPORT_SYMBOL_GPL(task_cgroup_path); /** + * cgroup_attach_lock - Lock for ->attach() + * @lock_threadgroup: whether to down_write cgroup_threadgroup_rwsem + * + * cgroup migration sometimes needs to stabilize threadgroups against forks and + * exits by write-locking cgroup_threadgroup_rwsem. However, some ->attach() + * implementations (e.g. cpuset), also need to disable CPU hotplug. + * Unfortunately, letting ->attach() operations acquire cpus_read_lock() can + * lead to deadlocks. + * + * Bringing up a CPU may involve creating and destroying tasks which requires + * read-locking threadgroup_rwsem, so threadgroup_rwsem nests inside + * cpus_read_lock(). If we call an ->attach() which acquires the cpus lock while + * write-locking threadgroup_rwsem, the locking order is reversed and we end up + * waiting for an on-going CPU hotplug operation which in turn is waiting for + * the threadgroup_rwsem to be released to create new tasks. For more details: + * + * http://lkml.kernel.org/r/20220711174629.uehfmqegcwn2lqzu@wubuntu + * + * Resolve the situation by always acquiring cpus_read_lock() before optionally + * write-locking cgroup_threadgroup_rwsem. This allows ->attach() to assume that + * CPU hotplug is disabled on entry. + */ +static void cgroup_attach_lock(bool lock_threadgroup) +{ + cpus_read_lock(); + if (lock_threadgroup) + percpu_down_write(&cgroup_threadgroup_rwsem); +} + +/** + * cgroup_attach_unlock - Undo cgroup_attach_lock() + * @lock_threadgroup: whether to up_write cgroup_threadgroup_rwsem + */ +static void cgroup_attach_unlock(bool lock_threadgroup) +{ + if (lock_threadgroup) + percpu_up_write(&cgroup_threadgroup_rwsem); + cpus_read_unlock(); +} + +/** * cgroup_migrate_add_task - add a migration target task to a migration context * @task: target task * @mgctx: target migration context @@ -2841,8 +2883,7 @@ int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader, } struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup, - bool *locked) - __acquires(&cgroup_threadgroup_rwsem) + bool *threadgroup_locked) { struct task_struct *tsk; pid_t pid; @@ -2859,12 +2900,8 @@ struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup, * Therefore, we can skip the global lock. */ lockdep_assert_held(&cgroup_mutex); - if (pid || threadgroup) { - percpu_down_write(&cgroup_threadgroup_rwsem); - *locked = true; - } else { - *locked = false; - } + *threadgroup_locked = pid || threadgroup; + cgroup_attach_lock(*threadgroup_locked); rcu_read_lock(); if (pid) { @@ -2895,17 +2932,14 @@ struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup, goto out_unlock_rcu; out_unlock_threadgroup: - if (*locked) { - percpu_up_write(&cgroup_threadgroup_rwsem); - *locked = false; - } + cgroup_attach_unlock(*threadgroup_locked); + *threadgroup_locked = false; out_unlock_rcu: rcu_read_unlock(); return tsk; } -void cgroup_procs_write_finish(struct task_struct *task, bool locked) - __releases(&cgroup_threadgroup_rwsem) +void cgroup_procs_write_finish(struct task_struct *task, bool threadgroup_locked) { struct cgroup_subsys *ss; int ssid; @@ -2913,8 +2947,8 @@ void cgroup_procs_write_finish(struct task_struct *task, bool locked) /* release reference from cgroup_procs_write_start() */ put_task_struct(task); - if (locked) - percpu_up_write(&cgroup_threadgroup_rwsem); + cgroup_attach_unlock(threadgroup_locked); + for_each_subsys(ss, ssid) if (ss->post_attach) ss->post_attach(); @@ -3000,8 +3034,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) * write-locking can be skipped safely. */ has_tasks = !list_empty(&mgctx.preloaded_src_csets); - if (has_tasks) - percpu_down_write(&cgroup_threadgroup_rwsem); + cgroup_attach_lock(has_tasks); /* NULL dst indicates self on default hierarchy */ ret = cgroup_migrate_prepare_dst(&mgctx); @@ -3022,8 +3055,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) ret = cgroup_migrate_execute(&mgctx); out_finish: cgroup_migrate_finish(&mgctx); - if (has_tasks) - percpu_up_write(&cgroup_threadgroup_rwsem); + cgroup_attach_unlock(has_tasks); return ret; } @@ -3698,7 +3730,7 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, } psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi; - new = psi_trigger_create(psi, buf, nbytes, res); + new = psi_trigger_create(psi, buf, res); if (IS_ERR(new)) { cgroup_put(cgrp); return PTR_ERR(new); @@ -4971,13 +5003,13 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, struct task_struct *task; const struct cred *saved_cred; ssize_t ret; - bool locked; + bool threadgroup_locked; dst_cgrp = cgroup_kn_lock_live(of->kn, false); if (!dst_cgrp) return -ENODEV; - task = cgroup_procs_write_start(buf, threadgroup, &locked); + task = cgroup_procs_write_start(buf, threadgroup, &threadgroup_locked); ret = PTR_ERR_OR_ZERO(task); if (ret) goto out_unlock; @@ -5003,7 +5035,7 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, ret = cgroup_attach_task(dst_cgrp, task, threadgroup); out_finish: - cgroup_procs_write_finish(task, locked); + cgroup_procs_write_finish(task, threadgroup_locked); out_unlock: cgroup_kn_unlock(of->kn); diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 58aadfda9b8b..1f3a55297f39 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -2289,7 +2289,7 @@ static void cpuset_attach(struct cgroup_taskset *tset) cgroup_taskset_first(tset, &css); cs = css_cs(css); - cpus_read_lock(); + lockdep_assert_cpus_held(); /* see cgroup_attach_lock() */ percpu_down_write(&cpuset_rwsem); guarantee_online_mems(cs, &cpuset_attach_nodemask_to); @@ -2343,7 +2343,6 @@ static void cpuset_attach(struct cgroup_taskset *tset) wake_up(&cpuset_attach_wq); percpu_up_write(&cpuset_rwsem); - cpus_read_unlock(); } /* The various types of files and directories in a cpuset file system */ diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 80697e5e03e4..08350e35aba2 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1707,11 +1707,12 @@ static struct kprobe *__disable_kprobe(struct kprobe *p) /* Try to disarm and disable this/parent probe */ if (p == orig_p || aggr_kprobe_disabled(orig_p)) { /* - * If 'kprobes_all_disarmed' is set, 'orig_p' - * should have already been disarmed, so - * skip unneed disarming process. + * Don't be lazy here. Even if 'kprobes_all_disarmed' + * is false, 'orig_p' might not have been armed yet. + * Note arm_all_kprobes() __tries__ to arm all kprobes + * on the best effort basis. */ - if (!kprobes_all_disarmed) { + if (!kprobes_all_disarmed && !kprobe_disabled(orig_p)) { ret = disarm_kprobe(orig_p, true); if (ret) { p->flags &= ~KPROBE_FLAG_DISABLED; diff --git a/kernel/module/main.c b/kernel/module/main.c index 6a477c622544..a4e4d84b6f4e 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -2099,7 +2099,7 @@ static int find_module_sections(struct module *mod, struct load_info *info) sizeof(*mod->static_call_sites), &mod->num_static_call_sites); #endif -#ifdef CONFIG_KUNIT +#if IS_ENABLED(CONFIG_KUNIT) mod->kunit_suites = section_objs(info, ".kunit_test_suites", sizeof(*mod->kunit_suites), &mod->num_kunit_suites); diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index ec66b40bdd40..ecb4b4ff4ce0 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -190,12 +190,8 @@ static void group_init(struct psi_group *group) /* Init trigger-related members */ mutex_init(&group->trigger_lock); INIT_LIST_HEAD(&group->triggers); - memset(group->nr_triggers, 0, sizeof(group->nr_triggers)); - group->poll_states = 0; group->poll_min_period = U32_MAX; - memset(group->polling_total, 0, sizeof(group->polling_total)); group->polling_next_update = ULLONG_MAX; - group->polling_until = 0; init_waitqueue_head(&group->poll_wait); timer_setup(&group->poll_timer, poll_timer_fn, 0); rcu_assign_pointer(group->poll_task, NULL); @@ -957,7 +953,7 @@ int psi_cgroup_alloc(struct cgroup *cgroup) if (static_branch_likely(&psi_disabled)) return 0; - cgroup->psi = kmalloc(sizeof(struct psi_group), GFP_KERNEL); + cgroup->psi = kzalloc(sizeof(struct psi_group), GFP_KERNEL); if (!cgroup->psi) return -ENOMEM; @@ -1091,7 +1087,7 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) } struct psi_trigger *psi_trigger_create(struct psi_group *group, - char *buf, size_t nbytes, enum psi_res res) + char *buf, enum psi_res res) { struct psi_trigger *t; enum psi_states state; @@ -1320,7 +1316,7 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf, return -EBUSY; } - new = psi_trigger_create(&psi_system, buf, nbytes, res); + new = psi_trigger_create(&psi_system, buf, res); if (IS_ERR(new)) { mutex_unlock(&seq->lock); return PTR_ERR(new); diff --git a/kernel/sched/wait_bit.c b/kernel/sched/wait_bit.c index d4788f810b55..0b1cd985dc27 100644 --- a/kernel/sched/wait_bit.c +++ b/kernel/sched/wait_bit.c @@ -47,7 +47,7 @@ __wait_on_bit(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_ prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode); if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags)) ret = (*action)(&wbq_entry->key, mode); - } while (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret); + } while (test_bit_acquire(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret); finish_wait(wq_head, &wbq_entry->wq_entry); diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index a492f159624f..860b2dcf3ac4 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -277,6 +277,7 @@ COND_SYSCALL(landlock_restrict_self); /* mm/fadvise.c */ COND_SYSCALL(fadvise64_64); +COND_SYSCALL_COMPAT(fadvise64_64); /* mm/, CONFIG_MMU only */ COND_SYSCALL(swapon); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 126c769d36c3..439e2ab6905e 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1861,8 +1861,6 @@ static void ftrace_hash_rec_enable_modify(struct ftrace_ops *ops, ftrace_hash_rec_update_modify(ops, filter_hash, 1); } -static bool ops_references_ip(struct ftrace_ops *ops, unsigned long ip); - /* * Try to update IPMODIFY flag on each ftrace_rec. Return 0 if it is OK * or no-needed to update, -EBUSY if it detects a conflict of the flag @@ -3118,49 +3116,6 @@ static inline int ops_traces_mod(struct ftrace_ops *ops) ftrace_hash_empty(ops->func_hash->notrace_hash); } -/* - * Check if the current ops references the given ip. - * - * If the ops traces all functions, then it was already accounted for. - * If the ops does not trace the current record function, skip it. - * If the ops ignores the function via notrace filter, skip it. - */ -static bool -ops_references_ip(struct ftrace_ops *ops, unsigned long ip) -{ - /* If ops isn't enabled, ignore it */ - if (!(ops->flags & FTRACE_OPS_FL_ENABLED)) - return false; - - /* If ops traces all then it includes this function */ - if (ops_traces_mod(ops)) - return true; - - /* The function must be in the filter */ - if (!ftrace_hash_empty(ops->func_hash->filter_hash) && - !__ftrace_lookup_ip(ops->func_hash->filter_hash, ip)) - return false; - - /* If in notrace hash, we ignore it too */ - if (ftrace_lookup_ip(ops->func_hash->notrace_hash, ip)) - return false; - - return true; -} - -/* - * Check if the current ops references the record. - * - * If the ops traces all functions, then it was already accounted for. - * If the ops does not trace the current record function, skip it. - * If the ops ignores the function via notrace filter, skip it. - */ -static bool -ops_references_rec(struct ftrace_ops *ops, struct dyn_ftrace *rec) -{ - return ops_references_ip(ops, rec->ip); -} - static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs) { bool init_nop = ftrace_need_init_nop(); @@ -6822,6 +6777,38 @@ static int ftrace_get_trampoline_kallsym(unsigned int symnum, return -ERANGE; } +#if defined(CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS) || defined(CONFIG_MODULES) +/* + * Check if the current ops references the given ip. + * + * If the ops traces all functions, then it was already accounted for. + * If the ops does not trace the current record function, skip it. + * If the ops ignores the function via notrace filter, skip it. + */ +static bool +ops_references_ip(struct ftrace_ops *ops, unsigned long ip) +{ + /* If ops isn't enabled, ignore it */ + if (!(ops->flags & FTRACE_OPS_FL_ENABLED)) + return false; + + /* If ops traces all then it includes this function */ + if (ops_traces_mod(ops)) + return true; + + /* The function must be in the filter */ + if (!ftrace_hash_empty(ops->func_hash->filter_hash) && + !__ftrace_lookup_ip(ops->func_hash->filter_hash, ip)) + return false; + + /* If in notrace hash, we ignore it too */ + if (ftrace_lookup_ip(ops->func_hash->notrace_hash, ip)) + return false; + + return true; +} +#endif + #ifdef CONFIG_MODULES #define next_to_ftrace_page(p) container_of(p, struct ftrace_page, next) @@ -6834,7 +6821,7 @@ static int referenced_filters(struct dyn_ftrace *rec) int cnt = 0; for (ops = ftrace_ops_list; ops != &ftrace_list_end; ops = ops->next) { - if (ops_references_rec(ops, rec)) { + if (ops_references_ip(ops, rec->ip)) { if (WARN_ON_ONCE(ops->flags & FTRACE_OPS_FL_DIRECT)) continue; if (WARN_ON_ONCE(ops->flags & FTRACE_OPS_FL_IPMODIFY)) diff --git a/lib/ratelimit.c b/lib/ratelimit.c index e01a93f46f83..ce945c17980b 100644 --- a/lib/ratelimit.c +++ b/lib/ratelimit.c @@ -26,10 +26,16 @@ */ int ___ratelimit(struct ratelimit_state *rs, const char *func) { + /* Paired with WRITE_ONCE() in .proc_handler(). + * Changing two values seperately could be inconsistent + * and some message could be lost. (See: net_ratelimit_state). + */ + int interval = READ_ONCE(rs->interval); + int burst = READ_ONCE(rs->burst); unsigned long flags; int ret; - if (!rs->interval) + if (!interval) return 1; /* @@ -44,7 +50,7 @@ int ___ratelimit(struct ratelimit_state *rs, const char *func) if (!rs->begin) rs->begin = jiffies; - if (time_is_before_jiffies(rs->begin + rs->interval)) { + if (time_is_before_jiffies(rs->begin + interval)) { if (rs->missed) { if (!(rs->flags & RATELIMIT_MSG_ON_RELEASE)) { printk_deferred(KERN_WARNING @@ -56,7 +62,7 @@ int ___ratelimit(struct ratelimit_state *rs, const char *func) rs->begin = jiffies; rs->printed = 0; } - if (rs->burst && rs->burst > rs->printed) { + if (burst && burst > rs->printed) { rs->printed++; ret = 1; } else { @@ -478,14 +478,42 @@ static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address, return -EEXIST; } -/* - * FOLL_FORCE can write to even unwritable pte's, but only - * after we've gone through a COW cycle and they are dirty. - */ -static inline bool can_follow_write_pte(pte_t pte, unsigned int flags) +/* FOLL_FORCE can write to even unwritable PTEs in COW mappings. */ +static inline bool can_follow_write_pte(pte_t pte, struct page *page, + struct vm_area_struct *vma, + unsigned int flags) { - return pte_write(pte) || - ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte)); + /* If the pte is writable, we can write to the page. */ + if (pte_write(pte)) + return true; + + /* Maybe FOLL_FORCE is set to override it? */ + if (!(flags & FOLL_FORCE)) + return false; + + /* But FOLL_FORCE has no effect on shared mappings */ + if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED)) + return false; + + /* ... or read-only private ones */ + if (!(vma->vm_flags & VM_MAYWRITE)) + return false; + + /* ... or already writable ones that just need to take a write fault */ + if (vma->vm_flags & VM_WRITE) + return false; + + /* + * See can_change_pte_writable(): we broke COW and could map the page + * writable if we have an exclusive anonymous page ... + */ + if (!page || !PageAnon(page) || !PageAnonExclusive(page)) + return false; + + /* ... and a write-fault isn't required for other reasons. */ + if (vma_soft_dirty_enabled(vma) && !pte_soft_dirty(pte)) + return false; + return !userfaultfd_pte_wp(vma, pte); } static struct page *follow_page_pte(struct vm_area_struct *vma, @@ -528,12 +556,19 @@ retry: } if ((flags & FOLL_NUMA) && pte_protnone(pte)) goto no_page; - if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, flags)) { - pte_unmap_unlock(ptep, ptl); - return NULL; - } page = vm_normal_page(vma, address, pte); + + /* + * We only care about anon pages in can_follow_write_pte() and don't + * have to worry about pte_devmap() because they are never anon. + */ + if ((flags & FOLL_WRITE) && + !can_follow_write_pte(pte, page, vma, flags)) { + page = NULL; + goto out; + } + if (!page && pte_devmap(pte) && (flags & (FOLL_GET | FOLL_PIN))) { /* * Only return device mapping pages in the FOLL_GET or FOLL_PIN @@ -986,17 +1021,6 @@ static int faultin_page(struct vm_area_struct *vma, return -EBUSY; } - /* - * The VM_FAULT_WRITE bit tells us that do_wp_page has broken COW when - * necessary, even if maybe_mkwrite decided not to set pte_write. We - * can thus safely do subsequent page lookups as if they were reads. - * But only do so when looping for pte_write is futile: in some cases - * userspace may also be wanting to write to the gotten user page, - * which a read fault here might prevent (a readonly page might get - * reCOWed by userspace write). - */ - if ((ret & VM_FAULT_WRITE) && !(vma->vm_flags & VM_WRITE)) - *flags |= FOLL_COW; return 0; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 8a7c1b344abe..e9414ee57c5b 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1040,12 +1040,6 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, assert_spin_locked(pmd_lockptr(mm, pmd)); - /* - * When we COW a devmap PMD entry, we split it into PTEs, so we should - * not be in this function with `flags & FOLL_COW` set. - */ - WARN_ONCE(flags & FOLL_COW, "mm: In follow_devmap_pmd with FOLL_COW set"); - /* FOLL_GET and FOLL_PIN are mutually exclusive. */ if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) == (FOLL_PIN | FOLL_GET))) @@ -1395,14 +1389,42 @@ fallback: return VM_FAULT_FALLBACK; } -/* - * FOLL_FORCE can write to even unwritable pmd's, but only - * after we've gone through a COW cycle and they are dirty. - */ -static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags) +/* FOLL_FORCE can write to even unwritable PMDs in COW mappings. */ +static inline bool can_follow_write_pmd(pmd_t pmd, struct page *page, + struct vm_area_struct *vma, + unsigned int flags) { - return pmd_write(pmd) || - ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd)); + /* If the pmd is writable, we can write to the page. */ + if (pmd_write(pmd)) + return true; + + /* Maybe FOLL_FORCE is set to override it? */ + if (!(flags & FOLL_FORCE)) + return false; + + /* But FOLL_FORCE has no effect on shared mappings */ + if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED)) + return false; + + /* ... or read-only private ones */ + if (!(vma->vm_flags & VM_MAYWRITE)) + return false; + + /* ... or already writable ones that just need to take a write fault */ + if (vma->vm_flags & VM_WRITE) + return false; + + /* + * See can_change_pte_writable(): we broke COW and could map the page + * writable if we have an exclusive anonymous page ... + */ + if (!page || !PageAnon(page) || !PageAnonExclusive(page)) + return false; + + /* ... and a write-fault isn't required for other reasons. */ + if (vma_soft_dirty_enabled(vma) && !pmd_soft_dirty(pmd)) + return false; + return !userfaultfd_huge_pmd_wp(vma, pmd); } struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, @@ -1411,12 +1433,16 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, unsigned int flags) { struct mm_struct *mm = vma->vm_mm; - struct page *page = NULL; + struct page *page; assert_spin_locked(pmd_lockptr(mm, pmd)); - if (flags & FOLL_WRITE && !can_follow_write_pmd(*pmd, flags)) - goto out; + page = pmd_page(*pmd); + VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page); + + if ((flags & FOLL_WRITE) && + !can_follow_write_pmd(*pmd, page, vma, flags)) + return NULL; /* Avoid dumping huge zero page */ if ((flags & FOLL_DUMP) && is_huge_zero_pmd(*pmd)) @@ -1424,10 +1450,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, /* Full NUMA hinting faults to serialise migration in fault paths */ if ((flags & FOLL_NUMA) && pmd_protnone(*pmd)) - goto out; - - page = pmd_page(*pmd); - VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page); + return NULL; if (!pmd_write(*pmd) && gup_must_unshare(flags, page)) return ERR_PTR(-EMLINK); @@ -1444,7 +1467,6 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT; VM_BUG_ON_PAGE(!PageCompound(page) && !is_zone_device_page(page), page); -out: return page; } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 0aee2f3ae15c..2480ba627aa5 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5241,6 +5241,21 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma, VM_BUG_ON(unshare && (flags & FOLL_WRITE)); VM_BUG_ON(!unshare && !(flags & FOLL_WRITE)); + /* + * hugetlb does not support FOLL_FORCE-style write faults that keep the + * PTE mapped R/O such as maybe_mkwrite() would do. + */ + if (WARN_ON_ONCE(!unshare && !(vma->vm_flags & VM_WRITE))) + return VM_FAULT_SIGSEGV; + + /* Let's take out MAP_SHARED mappings first. */ + if (vma->vm_flags & VM_MAYSHARE) { + if (unlikely(unshare)) + return 0; + set_huge_ptep_writable(vma, haddr, ptep); + return 0; + } + pte = huge_ptep_get(ptep); old_page = pte_page(pte); @@ -5781,12 +5796,11 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, * If we are going to COW/unshare the mapping later, we examine the * pending reservations for this page now. This will ensure that any * allocations necessary to record that reservation occur outside the - * spinlock. For private mappings, we also lookup the pagecache - * page now as it is used to determine if a reservation has been - * consumed. + * spinlock. Also lookup the pagecache page now as it is used to + * determine if a reservation has been consumed. */ if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) && - !huge_pte_write(entry)) { + !(vma->vm_flags & VM_MAYSHARE) && !huge_pte_write(entry)) { if (vma_needs_reservation(h, vma, haddr) < 0) { ret = VM_FAULT_OOM; goto out_mutex; @@ -5794,9 +5808,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, /* Just decrements count, does not deallocate */ vma_end_reservation(h, vma, haddr); - if (!(vma->vm_flags & VM_MAYSHARE)) - pagecache_page = hugetlbfs_pagecache_page(h, - vma, haddr); + pagecache_page = hugetlbfs_pagecache_page(h, vma, haddr); } ptl = huge_pte_lock(h, mm, ptep); diff --git a/mm/mmap.c b/mm/mmap.c index c035020d0c89..9d780f415be3 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1646,8 +1646,11 @@ int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot) pgprot_val(vm_pgprot_modify(vm_page_prot, vm_flags))) return 0; - /* Do we need to track softdirty? */ - if (vma_soft_dirty_enabled(vma)) + /* + * Do we need to track softdirty? hugetlb does not support softdirty + * tracking yet. + */ + if (vma_soft_dirty_enabled(vma) && !is_vm_hugetlb_page(vma)) return 1; /* Specialty mapping? */ diff --git a/mm/shmem.c b/mm/shmem.c index 5783f11351bb..d075dd2dcc48 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1659,7 +1659,9 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, new = page_folio(newpage); mem_cgroup_migrate(old, new); __inc_lruvec_page_state(newpage, NR_FILE_PAGES); + __inc_lruvec_page_state(newpage, NR_SHMEM); __dec_lruvec_page_state(oldpage, NR_FILE_PAGES); + __dec_lruvec_page_state(oldpage, NR_SHMEM); } xa_unlock_irq(&swap_mapping->i_pages); @@ -2281,16 +2283,34 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma) return 0; } -/* Mask out flags that are inappropriate for the given type of inode. */ -static unsigned shmem_mask_flags(umode_t mode, __u32 flags) +#ifdef CONFIG_TMPFS_XATTR +static int shmem_initxattrs(struct inode *, const struct xattr *, void *); + +/* + * chattr's fsflags are unrelated to extended attributes, + * but tmpfs has chosen to enable them under the same config option. + */ +static void shmem_set_inode_flags(struct inode *inode, unsigned int fsflags) +{ + unsigned int i_flags = 0; + + if (fsflags & FS_NOATIME_FL) + i_flags |= S_NOATIME; + if (fsflags & FS_APPEND_FL) + i_flags |= S_APPEND; + if (fsflags & FS_IMMUTABLE_FL) + i_flags |= S_IMMUTABLE; + /* + * But FS_NODUMP_FL does not require any action in i_flags. + */ + inode_set_flags(inode, i_flags, S_NOATIME | S_APPEND | S_IMMUTABLE); +} +#else +static void shmem_set_inode_flags(struct inode *inode, unsigned int fsflags) { - if (S_ISDIR(mode)) - return flags; - else if (S_ISREG(mode)) - return flags & SHMEM_REG_FLMASK; - else - return flags & SHMEM_OTHER_FLMASK; } +#define shmem_initxattrs NULL +#endif static struct inode *shmem_get_inode(struct super_block *sb, struct inode *dir, umode_t mode, dev_t dev, unsigned long flags) @@ -2319,7 +2339,8 @@ static struct inode *shmem_get_inode(struct super_block *sb, struct inode *dir, info->i_crtime = inode->i_mtime; info->fsflags = (dir == NULL) ? 0 : SHMEM_I(dir)->fsflags & SHMEM_FL_INHERITED; - info->fsflags = shmem_mask_flags(mode, info->fsflags); + if (info->fsflags) + shmem_set_inode_flags(inode, info->fsflags); INIT_LIST_HEAD(&info->shrinklist); INIT_LIST_HEAD(&info->swaplist); simple_xattrs_init(&info->xattrs); @@ -2468,12 +2489,6 @@ out_unacct_blocks: static const struct inode_operations shmem_symlink_inode_operations; static const struct inode_operations shmem_short_symlink_operations; -#ifdef CONFIG_TMPFS_XATTR -static int shmem_initxattrs(struct inode *, const struct xattr *, void *); -#else -#define shmem_initxattrs NULL -#endif - static int shmem_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, @@ -2826,12 +2841,13 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size) i_size_write(inode, offset + len); - inode->i_ctime = current_time(inode); undone: spin_lock(&inode->i_lock); inode->i_private = NULL; spin_unlock(&inode->i_lock); out: + if (!error) + file_modified(file); inode_unlock(inode); return error; } @@ -3179,18 +3195,13 @@ static int shmem_fileattr_set(struct user_namespace *mnt_userns, if (fileattr_has_fsx(fa)) return -EOPNOTSUPP; + if (fa->flags & ~SHMEM_FL_USER_MODIFIABLE) + return -EOPNOTSUPP; info->fsflags = (info->fsflags & ~SHMEM_FL_USER_MODIFIABLE) | (fa->flags & SHMEM_FL_USER_MODIFIABLE); - inode->i_flags &= ~(S_APPEND | S_IMMUTABLE | S_NOATIME); - if (info->fsflags & FS_APPEND_FL) - inode->i_flags |= S_APPEND; - if (info->fsflags & FS_IMMUTABLE_FL) - inode->i_flags |= S_IMMUTABLE; - if (info->fsflags & FS_NOATIME_FL) - inode->i_flags |= S_NOATIME; - + shmem_set_inode_flags(inode, info->fsflags); inode->i_ctime = current_time(inode); return 0; } diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 07d3befc80e4..7327b2573f7c 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -703,14 +703,29 @@ ssize_t mcopy_continue(struct mm_struct *dst_mm, unsigned long start, mmap_changing, 0); } +void uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *dst_vma, + unsigned long start, unsigned long len, bool enable_wp) +{ + struct mmu_gather tlb; + pgprot_t newprot; + + if (enable_wp) + newprot = vm_get_page_prot(dst_vma->vm_flags & ~(VM_WRITE)); + else + newprot = vm_get_page_prot(dst_vma->vm_flags); + + tlb_gather_mmu(&tlb, dst_mm); + change_protection(&tlb, dst_vma, start, start + len, newprot, + enable_wp ? MM_CP_UFFD_WP : MM_CP_UFFD_WP_RESOLVE); + tlb_finish_mmu(&tlb); +} + int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, unsigned long len, bool enable_wp, atomic_t *mmap_changing) { struct vm_area_struct *dst_vma; unsigned long page_mask; - struct mmu_gather tlb; - pgprot_t newprot; int err; /* @@ -750,15 +765,7 @@ int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, goto out_unlock; } - if (enable_wp) - newprot = vm_get_page_prot(dst_vma->vm_flags & ~(VM_WRITE)); - else - newprot = vm_get_page_prot(dst_vma->vm_flags); - - tlb_gather_mmu(&tlb, dst_mm); - change_protection(&tlb, dst_vma, start, start + len, newprot, - enable_wp ? MM_CP_UFFD_WP : MM_CP_UFFD_WP_RESOLVE); - tlb_finish_mmu(&tlb); + uffd_wp_range(dst_mm, dst_vma, start, len, enable_wp); err = 0; out_unlock: diff --git a/mm/vmstat.c b/mm/vmstat.c index 373d2730fcf2..90af9a8572f5 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1168,8 +1168,15 @@ int fragmentation_index(struct zone *zone, unsigned int order) #define TEXT_FOR_HIGHMEM(xx) #endif +#ifdef CONFIG_ZONE_DEVICE +#define TEXT_FOR_DEVICE(xx) xx "_device", +#else +#define TEXT_FOR_DEVICE(xx) +#endif + #define TEXTS_FOR_ZONES(xx) TEXT_FOR_DMA(xx) TEXT_FOR_DMA32(xx) xx "_normal", \ - TEXT_FOR_HIGHMEM(xx) xx "_movable", + TEXT_FOR_HIGHMEM(xx) xx "_movable", \ + TEXT_FOR_DEVICE(xx) const char * const vmstat_text[] = { /* enum zone_stat_item counters */ diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c index 1a11064f9990..8f19253024b0 100644 --- a/net/bridge/netfilter/ebtable_broute.c +++ b/net/bridge/netfilter/ebtable_broute.c @@ -36,18 +36,10 @@ static struct ebt_replace_kernel initial_table = { .entries = (char *)&initial_chain, }; -static int check(const struct ebt_table_info *info, unsigned int valid_hooks) -{ - if (valid_hooks & ~(1 << NF_BR_BROUTING)) - return -EINVAL; - return 0; -} - static const struct ebt_table broute_table = { .name = "broute", .table = &initial_table, .valid_hooks = 1 << NF_BR_BROUTING, - .check = check, .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index cb949436bc0e..278f324e6752 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -43,18 +43,10 @@ static struct ebt_replace_kernel initial_table = { .entries = (char *)initial_chains, }; -static int check(const struct ebt_table_info *info, unsigned int valid_hooks) -{ - if (valid_hooks & ~FILTER_VALID_HOOKS) - return -EINVAL; - return 0; -} - static const struct ebt_table frame_filter = { .name = "filter", .table = &initial_table, .valid_hooks = FILTER_VALID_HOOKS, - .check = check, .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index 5ee0531ae506..9066f7f376d5 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -43,18 +43,10 @@ static struct ebt_replace_kernel initial_table = { .entries = (char *)initial_chains, }; -static int check(const struct ebt_table_info *info, unsigned int valid_hooks) -{ - if (valid_hooks & ~NAT_VALID_HOOKS) - return -EINVAL; - return 0; -} - static const struct ebt_table frame_nat = { .name = "nat", .table = &initial_table, .valid_hooks = NAT_VALID_HOOKS, - .check = check, .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index f2dbefb61ce8..9a0ae59cdc50 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1040,8 +1040,7 @@ static int do_replace_finish(struct net *net, struct ebt_replace *repl, goto free_iterate; } - /* the table doesn't like it */ - if (t->check && (ret = t->check(newinfo, repl->valid_hooks))) + if (repl->valid_hooks != t->valid_hooks) goto free_unlock; if (repl->num_counters && repl->num_counters != t->private->nentries) { @@ -1231,11 +1230,6 @@ int ebt_register_table(struct net *net, const struct ebt_table *input_table, if (ret != 0) goto free_chainstack; - if (table->check && table->check(newinfo, table->valid_hooks)) { - ret = -EINVAL; - goto free_chainstack; - } - table->private = newinfo; rwlock_init(&table->lock); mutex_lock(&ebt_mutex); diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 1b7f385643b4..94374d529ea4 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -310,11 +310,12 @@ BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk) static int bpf_sk_storage_charge(struct bpf_local_storage_map *smap, void *owner, u32 size) { + int optmem_max = READ_ONCE(sysctl_optmem_max); struct sock *sk = (struct sock *)owner; /* same check as in sock_kmalloc() */ - if (size <= sysctl_optmem_max && - atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) { + if (size <= optmem_max && + atomic_read(&sk->sk_omem_alloc) + size < optmem_max) { atomic_add(size, &sk->sk_omem_alloc); return 0; } diff --git a/net/core/dev.c b/net/core/dev.c index 716df64fcfa5..56c8b0921c9f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4624,7 +4624,7 @@ static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen) struct softnet_data *sd; unsigned int old_flow, new_flow; - if (qlen < (netdev_max_backlog >> 1)) + if (qlen < (READ_ONCE(netdev_max_backlog) >> 1)) return false; sd = this_cpu_ptr(&softnet_data); @@ -4672,7 +4672,7 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu, if (!netif_running(skb->dev)) goto drop; qlen = skb_queue_len(&sd->input_pkt_queue); - if (qlen <= netdev_max_backlog && !skb_flow_limit(skb, qlen)) { + if (qlen <= READ_ONCE(netdev_max_backlog) && !skb_flow_limit(skb, qlen)) { if (qlen) { enqueue: __skb_queue_tail(&sd->input_pkt_queue, skb); @@ -4928,7 +4928,7 @@ static int netif_rx_internal(struct sk_buff *skb) { int ret; - net_timestamp_check(netdev_tstamp_prequeue, skb); + net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb); trace_netif_rx(skb); @@ -5281,7 +5281,7 @@ static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc, int ret = NET_RX_DROP; __be16 type; - net_timestamp_check(!netdev_tstamp_prequeue, skb); + net_timestamp_check(!READ_ONCE(netdev_tstamp_prequeue), skb); trace_netif_receive_skb(skb); @@ -5664,7 +5664,7 @@ static int netif_receive_skb_internal(struct sk_buff *skb) { int ret; - net_timestamp_check(netdev_tstamp_prequeue, skb); + net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb); if (skb_defer_rx_timestamp(skb)) return NET_RX_SUCCESS; @@ -5694,7 +5694,7 @@ void netif_receive_skb_list_internal(struct list_head *head) INIT_LIST_HEAD(&sublist); list_for_each_entry_safe(skb, next, head, list) { - net_timestamp_check(netdev_tstamp_prequeue, skb); + net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb); skb_list_del_init(skb); if (!skb_defer_rx_timestamp(skb)) list_add_tail(&skb->list, &sublist); @@ -5918,7 +5918,7 @@ static int process_backlog(struct napi_struct *napi, int quota) net_rps_action_and_irq_enable(sd); } - napi->weight = dev_rx_weight; + napi->weight = READ_ONCE(dev_rx_weight); while (again) { struct sk_buff *skb; @@ -6665,8 +6665,8 @@ static __latent_entropy void net_rx_action(struct softirq_action *h) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); unsigned long time_limit = jiffies + - usecs_to_jiffies(netdev_budget_usecs); - int budget = netdev_budget; + usecs_to_jiffies(READ_ONCE(netdev_budget_usecs)); + int budget = READ_ONCE(netdev_budget); LIST_HEAD(list); LIST_HEAD(repoll); @@ -10284,7 +10284,7 @@ static struct net_device *netdev_wait_allrefs_any(struct list_head *list) return dev; if (time_after(jiffies, warning_time + - netdev_unregister_timeout_secs * HZ)) { + READ_ONCE(netdev_unregister_timeout_secs) * HZ)) { list_for_each_entry(dev, list, todo_list) { pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n", dev->name, netdev_refcnt_read(dev)); diff --git a/net/core/filter.c b/net/core/filter.c index e8508aaafd27..c191db80ce93 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1214,10 +1214,11 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp) static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp) { u32 filter_size = bpf_prog_size(fp->prog->len); + int optmem_max = READ_ONCE(sysctl_optmem_max); /* same check as in sock_kmalloc() */ - if (filter_size <= sysctl_optmem_max && - atomic_read(&sk->sk_omem_alloc) + filter_size < sysctl_optmem_max) { + if (filter_size <= optmem_max && + atomic_read(&sk->sk_omem_alloc) + filter_size < optmem_max) { atomic_add(filter_size, &sk->sk_omem_alloc); return true; } @@ -1548,7 +1549,7 @@ int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk) if (IS_ERR(prog)) return PTR_ERR(prog); - if (bpf_prog_size(prog->len) > sysctl_optmem_max) + if (bpf_prog_size(prog->len) > READ_ONCE(sysctl_optmem_max)) err = -ENOMEM; else err = reuseport_attach_prog(sk, prog); @@ -1615,7 +1616,7 @@ int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk) } } else { /* BPF_PROG_TYPE_SOCKET_FILTER */ - if (bpf_prog_size(prog->len) > sysctl_optmem_max) { + if (bpf_prog_size(prog->len) > READ_ONCE(sysctl_optmem_max)) { err = -ENOMEM; goto err_prog_put; } @@ -5034,14 +5035,14 @@ static int __bpf_setsockopt(struct sock *sk, int level, int optname, /* Only some socketops are supported */ switch (optname) { case SO_RCVBUF: - val = min_t(u32, val, sysctl_rmem_max); + val = min_t(u32, val, READ_ONCE(sysctl_rmem_max)); val = min_t(int, val, INT_MAX / 2); sk->sk_userlocks |= SOCK_RCVBUF_LOCK; WRITE_ONCE(sk->sk_rcvbuf, max_t(int, val * 2, SOCK_MIN_RCVBUF)); break; case SO_SNDBUF: - val = min_t(u32, val, sysctl_wmem_max); + val = min_t(u32, val, READ_ONCE(sysctl_wmem_max)); val = min_t(int, val, INT_MAX / 2); sk->sk_userlocks |= SOCK_SNDBUF_LOCK; WRITE_ONCE(sk->sk_sndbuf, diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c index 541c7a72a28a..21619c70a82b 100644 --- a/net/core/gro_cells.c +++ b/net/core/gro_cells.c @@ -26,7 +26,7 @@ int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb) cell = this_cpu_ptr(gcells->cells); - if (skb_queue_len(&cell->napi_skbs) > netdev_max_backlog) { + if (skb_queue_len(&cell->napi_skbs) > READ_ONCE(netdev_max_backlog)) { drop: dev_core_stats_rx_dropped_inc(dev); kfree_skb(skb); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 5b669eb80270..78cc8fb68814 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -309,14 +309,17 @@ static int neigh_del_timer(struct neighbour *n) static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net) { + struct sk_buff_head tmp; unsigned long flags; struct sk_buff *skb; + skb_queue_head_init(&tmp); spin_lock_irqsave(&list->lock, flags); skb = skb_peek(list); while (skb != NULL) { struct sk_buff *skb_next = skb_peek_next(skb, list); struct net_device *dev = skb->dev; + if (net == NULL || net_eq(dev_net(dev), net)) { struct in_device *in_dev; @@ -326,13 +329,16 @@ static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net) in_dev->arp_parms->qlen--; rcu_read_unlock(); __skb_unlink(skb, list); - - dev_put(dev); - kfree_skb(skb); + __skb_queue_tail(&tmp, skb); } skb = skb_next; } spin_unlock_irqrestore(&list->lock, flags); + + while ((skb = __skb_dequeue(&tmp))) { + dev_put(skb->dev); + kfree_skb(skb); + } } static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 974bbbbe7138..84bb5e188d0d 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4205,9 +4205,8 @@ normal: SKB_GSO_CB(nskb)->csum_start = skb_headroom(nskb) + doffset; } else { - skb_copy_bits(head_skb, offset, - skb_put(nskb, len), - len); + if (skb_copy_bits(head_skb, offset, skb_put(nskb, len), len)) + goto err; } continue; } @@ -4798,7 +4797,7 @@ static bool skb_may_tx_timestamp(struct sock *sk, bool tsonly) { bool ret; - if (likely(sysctl_tstamp_allow_data || tsonly)) + if (likely(READ_ONCE(sysctl_tstamp_allow_data) || tsonly)) return true; read_lock_bh(&sk->sk_callback_lock); diff --git a/net/core/sock.c b/net/core/sock.c index 4cb957d934a2..788c1372663c 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1101,7 +1101,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname, * play 'guess the biggest size' games. RCVBUF/SNDBUF * are treated in BSD as hints */ - val = min_t(u32, val, sysctl_wmem_max); + val = min_t(u32, val, READ_ONCE(sysctl_wmem_max)); set_sndbuf: /* Ensure val * 2 fits into an int, to prevent max_t() * from treating it as a negative value. @@ -1133,7 +1133,7 @@ set_sndbuf: * play 'guess the biggest size' games. RCVBUF/SNDBUF * are treated in BSD as hints */ - __sock_set_rcvbuf(sk, min_t(u32, val, sysctl_rmem_max)); + __sock_set_rcvbuf(sk, min_t(u32, val, READ_ONCE(sysctl_rmem_max))); break; case SO_RCVBUFFORCE: @@ -2536,7 +2536,7 @@ struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size, /* small safe race: SKB_TRUESIZE may differ from final skb->truesize */ if (atomic_read(&sk->sk_omem_alloc) + SKB_TRUESIZE(size) > - sysctl_optmem_max) + READ_ONCE(sysctl_optmem_max)) return NULL; skb = alloc_skb(size, priority); @@ -2554,8 +2554,10 @@ struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size, */ void *sock_kmalloc(struct sock *sk, int size, gfp_t priority) { - if ((unsigned int)size <= sysctl_optmem_max && - atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) { + int optmem_max = READ_ONCE(sysctl_optmem_max); + + if ((unsigned int)size <= optmem_max && + atomic_read(&sk->sk_omem_alloc) + size < optmem_max) { void *mem; /* First do the add, to avoid the race if kmalloc * might sleep. @@ -3309,8 +3311,8 @@ void sock_init_data(struct socket *sock, struct sock *sk) timer_setup(&sk->sk_timer, NULL, 0); sk->sk_allocation = GFP_KERNEL; - sk->sk_rcvbuf = sysctl_rmem_default; - sk->sk_sndbuf = sysctl_wmem_default; + sk->sk_rcvbuf = READ_ONCE(sysctl_rmem_default); + sk->sk_sndbuf = READ_ONCE(sysctl_wmem_default); sk->sk_state = TCP_CLOSE; sk_set_socket(sk, sock); @@ -3365,7 +3367,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) #ifdef CONFIG_NET_RX_BUSY_POLL sk->sk_napi_id = 0; - sk->sk_ll_usec = sysctl_net_busy_read; + sk->sk_ll_usec = READ_ONCE(sysctl_net_busy_read); #endif sk->sk_max_pacing_rate = ~0UL; diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 71a13596ea2b..725891527814 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -234,14 +234,17 @@ static int set_default_qdisc(struct ctl_table *table, int write, static int proc_do_dev_weight(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { - int ret; + static DEFINE_MUTEX(dev_weight_mutex); + int ret, weight; + mutex_lock(&dev_weight_mutex); ret = proc_dointvec(table, write, buffer, lenp, ppos); - if (ret != 0) - return ret; - - dev_rx_weight = weight_p * dev_weight_rx_bias; - dev_tx_weight = weight_p * dev_weight_tx_bias; + if (!ret && write) { + weight = READ_ONCE(weight_p); + WRITE_ONCE(dev_rx_weight, weight * dev_weight_rx_bias); + WRITE_ONCE(dev_tx_weight, weight * dev_weight_tx_bias); + } + mutex_unlock(&dev_weight_mutex); return ret; } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index ad6a6663feeb..1291c2431d44 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -2484,7 +2484,7 @@ static int dsa_slave_changeupper(struct net_device *dev, if (!err) dsa_bridge_mtu_normalization(dp); if (err == -EOPNOTSUPP) { - if (!extack->_msg) + if (extack && !extack->_msg) NL_SET_ERR_MSG_MOD(extack, "Offloading not supported"); err = 0; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 92b778e423df..e8b9a9202fec 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -2682,23 +2682,27 @@ static __net_init int devinet_init_net(struct net *net) #endif if (!net_eq(net, &init_net)) { - if (IS_ENABLED(CONFIG_SYSCTL) && - sysctl_devconf_inherit_init_net == 3) { + switch (net_inherit_devconf()) { + case 3: /* copy from the current netns */ memcpy(all, current->nsproxy->net_ns->ipv4.devconf_all, sizeof(ipv4_devconf)); memcpy(dflt, current->nsproxy->net_ns->ipv4.devconf_dflt, sizeof(ipv4_devconf_dflt)); - } else if (!IS_ENABLED(CONFIG_SYSCTL) || - sysctl_devconf_inherit_init_net != 2) { - /* inherit == 0 or 1: copy from init_net */ + break; + case 0: + case 1: + /* copy from init_net */ memcpy(all, init_net.ipv4.devconf_all, sizeof(ipv4_devconf)); memcpy(dflt, init_net.ipv4.devconf_dflt, sizeof(ipv4_devconf_dflt)); + break; + case 2: + /* use compiled values */ + break; } - /* else inherit == 2: use compiled values */ } #ifdef CONFIG_SYSCTL diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index d7bd1daf022b..04e2034f2f8e 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1730,7 +1730,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, sk->sk_protocol = ip_hdr(skb)->protocol; sk->sk_bound_dev_if = arg->bound_dev_if; - sk->sk_sndbuf = sysctl_wmem_default; + sk->sk_sndbuf = READ_ONCE(sysctl_wmem_default); ipc.sockc.mark = fl4.flowi4_mark; err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, len, 0, &ipc, &rt, MSG_DONTWAIT); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index a8a323ecbb54..e49a61a053a6 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -772,7 +772,7 @@ static int ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen) if (optlen < GROUP_FILTER_SIZE(0)) return -EINVAL; - if (optlen > sysctl_optmem_max) + if (optlen > READ_ONCE(sysctl_optmem_max)) return -ENOBUFS; gsf = memdup_sockptr(optval, optlen); @@ -808,7 +808,7 @@ static int compat_ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, if (optlen < size0) return -EINVAL; - if (optlen > sysctl_optmem_max - 4) + if (optlen > READ_ONCE(sysctl_optmem_max) - 4) return -ENOBUFS; p = kmalloc(optlen + 4, GFP_KERNEL); @@ -1233,7 +1233,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, int optname, if (optlen < IP_MSFILTER_SIZE(0)) goto e_inval; - if (optlen > sysctl_optmem_max) { + if (optlen > READ_ONCE(sysctl_optmem_max)) { err = -ENOBUFS; break; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index bbe218753662..e5011c136fdb 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1000,7 +1000,7 @@ new_segment: i = skb_shinfo(skb)->nr_frags; can_coalesce = skb_can_coalesce(skb, i, page, offset); - if (!can_coalesce && i >= sysctl_max_skb_frags) { + if (!can_coalesce && i >= READ_ONCE(sysctl_max_skb_frags)) { tcp_mark_push(tp, skb); goto new_segment; } @@ -1354,7 +1354,7 @@ new_segment: if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { - if (i >= sysctl_max_skb_frags) { + if (i >= READ_ONCE(sysctl_max_skb_frags)) { tcp_mark_push(tp, skb); goto new_segment; } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 78b654ff421b..290019de766d 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -239,7 +239,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss, if (wscale_ok) { /* Set window scaling on max possible window */ space = max_t(u32, space, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])); - space = max_t(u32, space, sysctl_rmem_max); + space = max_t(u32, space, READ_ONCE(sysctl_rmem_max)); space = min_t(u32, space, *window_clamp); *rcv_wscale = clamp_t(int, ilog2(space) - 15, 0, TCP_MAX_WSCALE); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index b624e3d8c5f0..e15f64f22fa8 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -7162,9 +7162,8 @@ static int __net_init addrconf_init_net(struct net *net) if (!dflt) goto err_alloc_dflt; - if (IS_ENABLED(CONFIG_SYSCTL) && - !net_eq(net, &init_net)) { - switch (sysctl_devconf_inherit_init_net) { + if (!net_eq(net, &init_net)) { + switch (net_inherit_devconf()) { case 1: /* copy from init_net */ memcpy(all, init_net.ipv6.devconf_all, sizeof(ipv6_devconf)); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 222f6bf220ba..e0dcc7a193df 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -210,7 +210,7 @@ static int ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval, if (optlen < GROUP_FILTER_SIZE(0)) return -EINVAL; - if (optlen > sysctl_optmem_max) + if (optlen > READ_ONCE(sysctl_optmem_max)) return -ENOBUFS; gsf = memdup_sockptr(optval, optlen); @@ -244,7 +244,7 @@ static int compat_ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval, if (optlen < size0) return -EINVAL; - if (optlen > sysctl_optmem_max - 4) + if (optlen > READ_ONCE(sysctl_optmem_max) - 4) return -ENOBUFS; p = kmalloc(optlen + 4, GFP_KERNEL); diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 7dd3629dd19e..38db0064d661 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -86,7 +86,6 @@ static int nf_ct_frag6_sysctl_register(struct net *net) table[1].extra2 = &nf_frag->fqdir->high_thresh; table[2].data = &nf_frag->fqdir->high_thresh; table[2].extra1 = &nf_frag->fqdir->low_thresh; - table[2].extra2 = &nf_frag->fqdir->high_thresh; hdr = register_net_sysctl(net, "net/netfilter", table); if (hdr == NULL) diff --git a/net/key/af_key.c b/net/key/af_key.c index fda2dcc8a383..c85df5b958d2 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1697,9 +1697,12 @@ static int pfkey_register(struct sock *sk, struct sk_buff *skb, const struct sad pfk->registered |= (1<<hdr->sadb_msg_satype); } + mutex_lock(&pfkey_mutex); xfrm_probe_algs(); supp_skb = compose_sadb_supported(hdr, GFP_KERNEL | __GFP_ZERO); + mutex_unlock(&pfkey_mutex); + if (!supp_skb) { if (hdr->sadb_msg_satype != SADB_SATYPE_UNSPEC) pfk->registered &= ~(1<<hdr->sadb_msg_satype); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index da4257504fad..d398f3810662 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1263,7 +1263,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, i = skb_shinfo(skb)->nr_frags; can_coalesce = skb_can_coalesce(skb, i, dfrag->page, offset); - if (!can_coalesce && i >= sysctl_max_skb_frags) { + if (!can_coalesce && i >= READ_ONCE(sysctl_max_skb_frags)) { tcp_mark_push(tcp_sk(ssk), skb); goto alloc_skb; } diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 9d43277b8b4f..a56fd0b5a430 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1280,12 +1280,12 @@ static void set_sock_size(struct sock *sk, int mode, int val) lock_sock(sk); if (mode) { val = clamp_t(int, val, (SOCK_MIN_SNDBUF + 1) / 2, - sysctl_wmem_max); + READ_ONCE(sysctl_wmem_max)); sk->sk_sndbuf = val * 2; sk->sk_userlocks |= SOCK_SNDBUF_LOCK; } else { val = clamp_t(int, val, (SOCK_MIN_RCVBUF + 1) / 2, - sysctl_rmem_max); + READ_ONCE(sysctl_rmem_max)); sk->sk_rcvbuf = val * 2; sk->sk_userlocks |= SOCK_RCVBUF_LOCK; } diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index a63b51dceaf2..a634c72b1ffc 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -655,6 +655,37 @@ static bool tcp_in_window(struct nf_conn *ct, tn->tcp_be_liberal) res = true; if (!res) { + bool seq_ok = before(seq, sender->td_maxend + 1); + + if (!seq_ok) { + u32 overshot = end - sender->td_maxend + 1; + bool ack_ok; + + ack_ok = after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1); + + if (in_recv_win && + ack_ok && + overshot <= receiver->td_maxwin && + before(sack, receiver->td_end + 1)) { + /* Work around TCPs that send more bytes than allowed by + * the receive window. + * + * If the (marked as invalid) packet is allowed to pass by + * the ruleset and the peer acks this data, then its possible + * all future packets will trigger 'ACK is over upper bound' check. + * + * Thus if only the sequence check fails then do update td_end so + * possible ACK for this data can update internal state. + */ + sender->td_end = end; + sender->flags |= IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED; + + nf_ct_l4proto_log_invalid(skb, ct, hook_state, + "%u bytes more than expected", overshot); + return res; + } + } + nf_ct_l4proto_log_invalid(skb, ct, hook_state, "%s", before(seq, sender->td_maxend + 1) ? diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 765ac779bfc8..81c26a96c30b 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -437,12 +437,17 @@ static void nf_flow_offload_gc_step(struct nf_flowtable *flow_table, } } +void nf_flow_table_gc_run(struct nf_flowtable *flow_table) +{ + nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, NULL); +} + static void nf_flow_offload_work_gc(struct work_struct *work) { struct nf_flowtable *flow_table; flow_table = container_of(work, struct nf_flowtable, gc_work.work); - nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, NULL); + nf_flow_table_gc_run(flow_table); queue_delayed_work(system_power_efficient_wq, &flow_table->gc_work, HZ); } @@ -600,11 +605,11 @@ void nf_flow_table_free(struct nf_flowtable *flow_table) mutex_unlock(&flowtable_lock); cancel_delayed_work_sync(&flow_table->gc_work); - nf_flow_table_iterate(flow_table, nf_flow_table_do_cleanup, NULL); - nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, NULL); nf_flow_table_offload_flush(flow_table); - if (nf_flowtable_hw_offload(flow_table)) - nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, NULL); + /* ... no more pending work after this stage ... */ + nf_flow_table_iterate(flow_table, nf_flow_table_do_cleanup, NULL); + nf_flow_table_gc_run(flow_table); + nf_flow_table_offload_flush_cleanup(flow_table); rhashtable_destroy(&flow_table->rhashtable); } EXPORT_SYMBOL_GPL(nf_flow_table_free); diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index 103b6cbf257f..b04645ced89b 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -1074,6 +1074,14 @@ void nf_flow_offload_stats(struct nf_flowtable *flowtable, flow_offload_queue_work(offload); } +void nf_flow_table_offload_flush_cleanup(struct nf_flowtable *flowtable) +{ + if (nf_flowtable_hw_offload(flowtable)) { + flush_workqueue(nf_flow_offload_del_wq); + nf_flow_table_gc_run(flowtable); + } +} + void nf_flow_table_offload_flush(struct nf_flowtable *flowtable) { if (nf_flowtable_hw_offload(flowtable)) { diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 62cfb0e31c40..2ee50e23c9b7 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -32,7 +32,6 @@ static LIST_HEAD(nf_tables_objects); static LIST_HEAD(nf_tables_flowtables); static LIST_HEAD(nf_tables_destroy_list); static DEFINE_SPINLOCK(nf_tables_destroy_list_lock); -static u64 table_handle; enum { NFT_VALIDATE_SKIP = 0, @@ -1235,7 +1234,7 @@ static int nf_tables_newtable(struct sk_buff *skb, const struct nfnl_info *info, INIT_LIST_HEAD(&table->flowtables); table->family = family; table->flags = flags; - table->handle = ++table_handle; + table->handle = ++nft_net->table_handle; if (table->flags & NFT_TABLE_F_OWNER) table->nlpid = NETLINK_CB(skb).portid; @@ -2196,9 +2195,9 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, struct netlink_ext_ack *extack) { const struct nlattr * const *nla = ctx->nla; + struct nft_stats __percpu *stats = NULL; struct nft_table *table = ctx->table; struct nft_base_chain *basechain; - struct nft_stats __percpu *stats; struct net *net = ctx->net; char name[NFT_NAME_MAXLEN]; struct nft_rule_blob *blob; @@ -2236,7 +2235,6 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, return PTR_ERR(stats); } rcu_assign_pointer(basechain->stats, stats); - static_branch_inc(&nft_counters_enabled); } err = nft_basechain_init(basechain, family, &hook, flags); @@ -2319,6 +2317,9 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, goto err_unregister_hook; } + if (stats) + static_branch_inc(&nft_counters_enabled); + table->use++; return 0; @@ -2574,6 +2575,9 @@ static int nf_tables_newchain(struct sk_buff *skb, const struct nfnl_info *info, nft_ctx_init(&ctx, net, skb, info->nlh, family, table, chain, nla); if (chain != NULL) { + if (chain->flags & NFT_CHAIN_BINDING) + return -EINVAL; + if (info->nlh->nlmsg_flags & NLM_F_EXCL) { NL_SET_BAD_ATTR(extack, attr); return -EEXIST; @@ -9707,6 +9711,8 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, return PTR_ERR(chain); if (nft_is_base_chain(chain)) return -EOPNOTSUPP; + if (nft_chain_is_bound(chain)) + return -EINVAL; if (desc->flags & NFT_DATA_DESC_SETELEM && chain->flags & NFT_CHAIN_BINDING) return -EINVAL; diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c index 0053a697c931..89342ccccdcc 100644 --- a/net/netfilter/nft_osf.c +++ b/net/netfilter/nft_osf.c @@ -115,9 +115,21 @@ static int nft_osf_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nft_data **data) { - return nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_LOCAL_IN) | - (1 << NF_INET_PRE_ROUTING) | - (1 << NF_INET_FORWARD)); + unsigned int hooks; + + switch (ctx->family) { + case NFPROTO_IPV4: + case NFPROTO_IPV6: + case NFPROTO_INET: + hooks = (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_FORWARD); + break; + default: + return -EOPNOTSUPP; + } + + return nft_chain_validate_hooks(ctx->chain, hooks); } static bool nft_osf_reduce(struct nft_regs_track *track, diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 2e7ac007cb30..eb0e40c29712 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -740,17 +740,23 @@ static int nft_payload_set_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_payload_set *priv = nft_expr_priv(expr); + u32 csum_offset, csum_type = NFT_PAYLOAD_CSUM_NONE; + int err; priv->base = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_BASE])); priv->offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET])); priv->len = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN])); if (tb[NFTA_PAYLOAD_CSUM_TYPE]) - priv->csum_type = - ntohl(nla_get_be32(tb[NFTA_PAYLOAD_CSUM_TYPE])); - if (tb[NFTA_PAYLOAD_CSUM_OFFSET]) - priv->csum_offset = - ntohl(nla_get_be32(tb[NFTA_PAYLOAD_CSUM_OFFSET])); + csum_type = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_CSUM_TYPE])); + if (tb[NFTA_PAYLOAD_CSUM_OFFSET]) { + err = nft_parse_u32_check(tb[NFTA_PAYLOAD_CSUM_OFFSET], U8_MAX, + &csum_offset); + if (err < 0) + return err; + + priv->csum_offset = csum_offset; + } if (tb[NFTA_PAYLOAD_CSUM_FLAGS]) { u32 flags; @@ -761,7 +767,7 @@ static int nft_payload_set_init(const struct nft_ctx *ctx, priv->csum_flags = flags; } - switch (priv->csum_type) { + switch (csum_type) { case NFT_PAYLOAD_CSUM_NONE: case NFT_PAYLOAD_CSUM_INET: break; @@ -775,6 +781,7 @@ static int nft_payload_set_init(const struct nft_ctx *ctx, default: return -EOPNOTSUPP; } + priv->csum_type = csum_type; return nft_parse_register_load(tb[NFTA_PAYLOAD_SREG], &priv->sreg, priv->len); @@ -833,6 +840,7 @@ nft_payload_select_ops(const struct nft_ctx *ctx, { enum nft_payload_bases base; unsigned int offset, len; + int err; if (tb[NFTA_PAYLOAD_BASE] == NULL || tb[NFTA_PAYLOAD_OFFSET] == NULL || @@ -859,8 +867,13 @@ nft_payload_select_ops(const struct nft_ctx *ctx, if (tb[NFTA_PAYLOAD_DREG] == NULL) return ERR_PTR(-EINVAL); - offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET])); - len = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN])); + err = nft_parse_u32_check(tb[NFTA_PAYLOAD_OFFSET], U8_MAX, &offset); + if (err < 0) + return ERR_PTR(err); + + err = nft_parse_u32_check(tb[NFTA_PAYLOAD_LEN], U8_MAX, &len); + if (err < 0) + return ERR_PTR(err); if (len <= 4 && is_power_of_2(len) && IS_ALIGNED(offset, len) && base != NFT_PAYLOAD_LL_HEADER && base != NFT_PAYLOAD_INNER_HEADER) diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c index 68b2eed742df..62da25ad264b 100644 --- a/net/netfilter/nft_tproxy.c +++ b/net/netfilter/nft_tproxy.c @@ -312,6 +312,13 @@ static int nft_tproxy_dump(struct sk_buff *skb, return 0; } +static int nft_tproxy_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **data) +{ + return nft_chain_validate_hooks(ctx->chain, 1 << NF_INET_PRE_ROUTING); +} + static struct nft_expr_type nft_tproxy_type; static const struct nft_expr_ops nft_tproxy_ops = { .type = &nft_tproxy_type, @@ -321,6 +328,7 @@ static const struct nft_expr_ops nft_tproxy_ops = { .destroy = nft_tproxy_destroy, .dump = nft_tproxy_dump, .reduce = NFT_REDUCE_READONLY, + .validate = nft_tproxy_validate, }; static struct nft_expr_type nft_tproxy_type __read_mostly = { diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index 5edaaded706d..983ade4be3b3 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -161,6 +161,7 @@ static const struct nft_expr_ops nft_tunnel_get_ops = { static struct nft_expr_type nft_tunnel_type __read_mostly = { .name = "tunnel", + .family = NFPROTO_NETDEV, .ops = &nft_tunnel_get_ops, .policy = nft_tunnel_policy, .maxattr = NFTA_TUNNEL_MAX, diff --git a/net/rose/rose_loopback.c b/net/rose/rose_loopback.c index 11c45c8c6c16..036d92c0ad79 100644 --- a/net/rose/rose_loopback.c +++ b/net/rose/rose_loopback.c @@ -96,7 +96,8 @@ static void rose_loopback_timer(struct timer_list *unused) } if (frametype == ROSE_CALL_REQUEST) { - if (!rose_loopback_neigh->dev) { + if (!rose_loopback_neigh->dev && + !rose_loopback_neigh->loopback) { kfree_skb(skb); continue; } diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 84d0a4109645..6401cdf7a624 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -285,8 +285,10 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, _enter("%p,%lx", rx, p->user_call_ID); limiter = rxrpc_get_call_slot(p, gfp); - if (!limiter) + if (!limiter) { + release_sock(&rx->sk); return ERR_PTR(-ERESTARTSYS); + } call = rxrpc_alloc_client_call(rx, srx, gfp, debug_id); if (IS_ERR(call)) { diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 1d38e279e2ef..3c3a626459de 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -51,10 +51,7 @@ static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx, return sock_intr_errno(*timeo); trace_rxrpc_transmit(call, rxrpc_transmit_wait); - mutex_unlock(&call->user_mutex); *timeo = schedule_timeout(*timeo); - if (mutex_lock_interruptible(&call->user_mutex) < 0) - return sock_intr_errno(*timeo); } } @@ -290,37 +287,48 @@ out: static int rxrpc_send_data(struct rxrpc_sock *rx, struct rxrpc_call *call, struct msghdr *msg, size_t len, - rxrpc_notify_end_tx_t notify_end_tx) + rxrpc_notify_end_tx_t notify_end_tx, + bool *_dropped_lock) { struct rxrpc_skb_priv *sp; struct sk_buff *skb; struct sock *sk = &rx->sk; + enum rxrpc_call_state state; long timeo; - bool more; - int ret, copied; + bool more = msg->msg_flags & MSG_MORE; + int ret, copied = 0; timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); /* this should be in poll */ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); +reload: + ret = -EPIPE; if (sk->sk_shutdown & SEND_SHUTDOWN) - return -EPIPE; - - more = msg->msg_flags & MSG_MORE; - + goto maybe_error; + state = READ_ONCE(call->state); + ret = -ESHUTDOWN; + if (state >= RXRPC_CALL_COMPLETE) + goto maybe_error; + ret = -EPROTO; + if (state != RXRPC_CALL_CLIENT_SEND_REQUEST && + state != RXRPC_CALL_SERVER_ACK_REQUEST && + state != RXRPC_CALL_SERVER_SEND_REPLY) + goto maybe_error; + + ret = -EMSGSIZE; if (call->tx_total_len != -1) { - if (len > call->tx_total_len) - return -EMSGSIZE; - if (!more && len != call->tx_total_len) - return -EMSGSIZE; + if (len - copied > call->tx_total_len) + goto maybe_error; + if (!more && len - copied != call->tx_total_len) + goto maybe_error; } skb = call->tx_pending; call->tx_pending = NULL; rxrpc_see_skb(skb, rxrpc_skb_seen); - copied = 0; do { /* Check to see if there's a ping ACK to reply to. */ if (call->ackr_reason == RXRPC_ACK_PING_RESPONSE) @@ -331,16 +339,8 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, _debug("alloc"); - if (!rxrpc_check_tx_space(call, NULL)) { - ret = -EAGAIN; - if (msg->msg_flags & MSG_DONTWAIT) - goto maybe_error; - ret = rxrpc_wait_for_tx_window(rx, call, - &timeo, - msg->msg_flags & MSG_WAITALL); - if (ret < 0) - goto maybe_error; - } + if (!rxrpc_check_tx_space(call, NULL)) + goto wait_for_space; /* Work out the maximum size of a packet. Assume that * the security header is going to be in the padded @@ -468,6 +468,27 @@ maybe_error: efault: ret = -EFAULT; goto out; + +wait_for_space: + ret = -EAGAIN; + if (msg->msg_flags & MSG_DONTWAIT) + goto maybe_error; + mutex_unlock(&call->user_mutex); + *_dropped_lock = true; + ret = rxrpc_wait_for_tx_window(rx, call, &timeo, + msg->msg_flags & MSG_WAITALL); + if (ret < 0) + goto maybe_error; + if (call->interruptibility == RXRPC_INTERRUPTIBLE) { + if (mutex_lock_interruptible(&call->user_mutex) < 0) { + ret = sock_intr_errno(timeo); + goto maybe_error; + } + } else { + mutex_lock(&call->user_mutex); + } + *_dropped_lock = false; + goto reload; } /* @@ -629,6 +650,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) enum rxrpc_call_state state; struct rxrpc_call *call; unsigned long now, j; + bool dropped_lock = false; int ret; struct rxrpc_send_params p = { @@ -737,21 +759,13 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) ret = rxrpc_send_abort_packet(call); } else if (p.command != RXRPC_CMD_SEND_DATA) { ret = -EINVAL; - } else if (rxrpc_is_client_call(call) && - state != RXRPC_CALL_CLIENT_SEND_REQUEST) { - /* request phase complete for this client call */ - ret = -EPROTO; - } else if (rxrpc_is_service_call(call) && - state != RXRPC_CALL_SERVER_ACK_REQUEST && - state != RXRPC_CALL_SERVER_SEND_REPLY) { - /* Reply phase not begun or not complete for service call. */ - ret = -EPROTO; } else { - ret = rxrpc_send_data(rx, call, msg, len, NULL); + ret = rxrpc_send_data(rx, call, msg, len, NULL, &dropped_lock); } out_put_unlock: - mutex_unlock(&call->user_mutex); + if (!dropped_lock) + mutex_unlock(&call->user_mutex); error_put: rxrpc_put_call(call, rxrpc_call_put); _leave(" = %d", ret); @@ -779,6 +793,7 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call, struct msghdr *msg, size_t len, rxrpc_notify_end_tx_t notify_end_tx) { + bool dropped_lock = false; int ret; _enter("{%d,%s},", call->debug_id, rxrpc_call_states[call->state]); @@ -796,7 +811,7 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call, case RXRPC_CALL_SERVER_ACK_REQUEST: case RXRPC_CALL_SERVER_SEND_REPLY: ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len, - notify_end_tx); + notify_end_tx, &dropped_lock); break; case RXRPC_CALL_COMPLETE: read_lock_bh(&call->state_lock); @@ -810,7 +825,8 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call, break; } - mutex_unlock(&call->user_mutex); + if (!dropped_lock) + mutex_unlock(&call->user_mutex); _leave(" = %d", ret); return ret; } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index d47b9689eba6..99b697ad2b98 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -409,7 +409,7 @@ static inline bool qdisc_restart(struct Qdisc *q, int *packets) void __qdisc_run(struct Qdisc *q) { - int quota = dev_tx_weight; + int quota = READ_ONCE(dev_tx_weight); int packets; while (qdisc_restart(q, &packets)) { diff --git a/net/socket.c b/net/socket.c index 9b27c5e4e5ba..7378375d3a5b 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1801,7 +1801,7 @@ int __sys_listen(int fd, int backlog) sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock) { - somaxconn = sock_net(sock->sk)->core.sysctl_somaxconn; + somaxconn = READ_ONCE(sock_net(sock->sk)->core.sysctl_somaxconn); if ((unsigned int)backlog > somaxconn) backlog = somaxconn; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index b098e707ad41..7d268a291486 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1902,7 +1902,7 @@ call_encode(struct rpc_task *task) break; case -EKEYEXPIRED: if (!task->tk_cred_retry) { - rpc_exit(task, task->tk_status); + rpc_call_rpcerror(task, task->tk_status); } else { task->tk_action = call_refresh; task->tk_cred_retry--; diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c index 82d14eea1b5a..974eb97b77d2 100644 --- a/net/xfrm/espintcp.c +++ b/net/xfrm/espintcp.c @@ -168,7 +168,7 @@ int espintcp_queue_out(struct sock *sk, struct sk_buff *skb) { struct espintcp_ctx *ctx = espintcp_getctx(sk); - if (skb_queue_len(&ctx->out_queue) >= netdev_max_backlog) + if (skb_queue_len(&ctx->out_queue) >= READ_ONCE(netdev_max_backlog)) return -ENOBUFS; __skb_queue_tail(&ctx->out_queue, skb); diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 144238a50f3d..b2f4ec9c537f 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -669,7 +669,6 @@ resume: x->curlft.bytes += skb->len; x->curlft.packets++; - x->curlft.use_time = ktime_get_real_seconds(); spin_unlock(&x->lock); @@ -783,7 +782,7 @@ int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb, trans = this_cpu_ptr(&xfrm_trans_tasklet); - if (skb_queue_len(&trans->queue) >= netdev_max_backlog) + if (skb_queue_len(&trans->queue) >= READ_ONCE(netdev_max_backlog)) return -ENOBUFS; BUILD_BUG_ON(sizeof(struct xfrm_trans_cb) > sizeof(skb->cb)); diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 555ab35cd119..9a5e79a38c67 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -534,7 +534,6 @@ static int xfrm_output_one(struct sk_buff *skb, int err) x->curlft.bytes += skb->len; x->curlft.packets++; - x->curlft.use_time = ktime_get_real_seconds(); spin_unlock_bh(&x->lock); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index f1a0bab920a5..cc6ab79609e2 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3162,7 +3162,7 @@ ok: return dst; nopol: - if (!(dst_orig->dev->flags & IFF_LOOPBACK) && + if ((!dst_orig->dev || !(dst_orig->dev->flags & IFF_LOOPBACK)) && net->xfrm.policy_default[dir] == XFRM_USERPOLICY_BLOCK) { err = -EPERM; goto error; @@ -3599,6 +3599,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, if (pols[1]) { if (IS_ERR(pols[1])) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); + xfrm_pol_put(pols[0]); return 0; } pols[1]->curlft.use_time = ktime_get_real_seconds(); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 52e60e607f8a..91c32a3b6924 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1592,6 +1592,7 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, x->replay = orig->replay; x->preplay = orig->preplay; x->mapping_maxage = orig->mapping_maxage; + x->lastused = orig->lastused; x->new_mapping = 0; x->new_mapping_sport = 0; diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index 3bb134355874..316917b98707 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -75,9 +75,11 @@ struct kvm_regs { /* KVM_ARM_SET_DEVICE_ADDR ioctl id encoding */ #define KVM_ARM_DEVICE_TYPE_SHIFT 0 -#define KVM_ARM_DEVICE_TYPE_MASK (0xffff << KVM_ARM_DEVICE_TYPE_SHIFT) +#define KVM_ARM_DEVICE_TYPE_MASK GENMASK(KVM_ARM_DEVICE_TYPE_SHIFT + 15, \ + KVM_ARM_DEVICE_TYPE_SHIFT) #define KVM_ARM_DEVICE_ID_SHIFT 16 -#define KVM_ARM_DEVICE_ID_MASK (0xffff << KVM_ARM_DEVICE_ID_SHIFT) +#define KVM_ARM_DEVICE_ID_MASK GENMASK(KVM_ARM_DEVICE_ID_SHIFT + 15, \ + KVM_ARM_DEVICE_ID_SHIFT) /* Supported device IDs */ #define KVM_ARM_DEVICE_VGIC_V2 0 diff --git a/tools/include/linux/compiler_types.h b/tools/include/linux/compiler_types.h index 24ae3054f304..1bdd834bdd57 100644 --- a/tools/include/linux/compiler_types.h +++ b/tools/include/linux/compiler_types.h @@ -36,4 +36,8 @@ #include <linux/compiler-gcc.h> #endif +#ifndef asm_volatile_goto +#define asm_volatile_goto(x...) asm goto(x) +#endif + #endif /* __LINUX_COMPILER_TYPES_H */ diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 91678252a9b6..e55fdf952a3a 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -162,32 +162,34 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, /* * Unfortunately these have to be hard coded because the noreturn - * attribute isn't provided in ELF data. + * attribute isn't provided in ELF data. Keep 'em sorted. */ static const char * const global_noreturns[] = { + "__invalid_creds", + "__module_put_and_kthread_exit", + "__reiserfs_panic", "__stack_chk_fail", - "panic", + "__ubsan_handle_builtin_unreachable", + "cpu_bringup_and_idle", + "cpu_startup_entry", "do_exit", + "do_group_exit", "do_task_dead", - "kthread_exit", - "make_task_dead", - "__module_put_and_kthread_exit", + "ex_handler_msr_mce", + "fortify_panic", "kthread_complete_and_exit", - "__reiserfs_panic", + "kthread_exit", + "kunit_try_catch_throw", "lbug_with_loc", - "fortify_panic", - "usercopy_abort", "machine_real_restart", + "make_task_dead", + "panic", "rewind_stack_and_make_dead", - "kunit_try_catch_throw", - "xen_start_kernel", - "cpu_bringup_and_idle", - "do_group_exit", + "sev_es_terminate", + "snp_abort", "stop_this_cpu", - "__invalid_creds", - "cpu_startup_entry", - "__ubsan_handle_builtin_unreachable", - "ex_handler_msr_mce", + "usercopy_abort", + "xen_start_kernel", }; if (!func) diff --git a/tools/perf/Documentation/intel-hybrid.txt b/tools/perf/Documentation/intel-hybrid.txt index c9302096dc46..e7a776ad25d7 100644 --- a/tools/perf/Documentation/intel-hybrid.txt +++ b/tools/perf/Documentation/intel-hybrid.txt @@ -21,11 +21,6 @@ cat /sys/devices/cpu_atom/cpus It indicates cpu0-cpu15 are core cpus and cpu16-cpu23 are atom cpus. -Quickstart - -List hybrid event ------------------ - As before, use perf-list to list the symbolic event. perf list @@ -40,7 +35,6 @@ the event is belong to. Same event name but with different pmu can be supported. Enable hybrid event with a specific pmu ---------------------------------------- To enable a core only event or atom only event, following syntax is supported: @@ -53,7 +47,6 @@ For example, count the 'cycles' event on core cpus. perf stat -e cpu_core/cycles/ Create two events for one hardware event automatically ------------------------------------------------------- When creating one event and the event is available on both atom and core, two events are created automatically. One is for atom, the other is for @@ -132,7 +125,6 @@ For perf-stat result, it displays two events: The first 'cycles' is core event, the second 'cycles' is atom event. Thread mode example: --------------------- perf-stat reports the scaled counts for hybrid event and with a percentage displayed. The percentage is the event's running time/enabling time. @@ -176,14 +168,12 @@ perf_event_attr: 604,097,080 cpu_atom/cycles/ (99.57%) perf-record: ------------- If there is no '-e' specified in perf record, on hybrid platform, it creates two default 'cycles' and adds them to event list. One is for core, the other is for atom. perf-stat: ----------- If there is no '-e' specified in perf stat, on hybrid platform, besides of software events, following events are created and diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 099817ef5150..0228efc96686 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -397,6 +397,9 @@ following filters are defined: - abort_tx: only when the target is a hardware transaction abort - cond: conditional branches - save_type: save branch type during sampling in case binary is not available later + For the platforms with Intel Arch LBR support (12th-Gen+ client or + 4th-Gen Xeon+ server), the save branch type is unconditionally enabled + when the taken branch stack sampling is enabled. + The option requires at least one branch type among any, any_call, any_ret, ind_call, cond. @@ -757,8 +760,6 @@ events in data directory files. Option specified with no or empty value defaults to CPU layout. Masks defined or provided by the option value are filtered through the mask provided by -C option. -include::intel-hybrid.txt[] - --debuginfod[=URLs]:: Specify debuginfod URL to be used when cacheing perf.data binaries, it follows the same syntax as the DEBUGINFOD_URLS variable, like: @@ -778,6 +779,8 @@ include::intel-hybrid.txt[] only, as of now. So the applications built without the frame pointer might see bogus addresses. +include::intel-hybrid.txt[] + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-list[1], linkperf:perf-intel-pt[1] diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 0661a1cf9855..2171f02daf59 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -265,7 +265,7 @@ endif # defined. get-executable-or-default fails with an error if the first argument is supplied but # doesn't exist. override PYTHON_CONFIG := $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON_AUTO)) -override PYTHON := $(call get-executable-or-default,PYTHON,$(subst -config,,$(PYTHON_AUTO))) +override PYTHON := $(call get-executable-or-default,PYTHON,$(subst -config,,$(PYTHON_CONFIG))) grep-libs = $(filter -l%,$(1)) strip-libs = $(filter-out -l%,$(1)) diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 2f6cd1b8b662..a5cf243c337f 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -3355,7 +3355,8 @@ static bool schedstat_events_exposed(void) static int __cmd_record(int argc, const char **argv) { unsigned int rec_argc, i, j; - const char **rec_argv; + char **rec_argv; + const char **rec_argv_copy; const char * const record_args[] = { "record", "-a", @@ -3384,6 +3385,7 @@ static int __cmd_record(int argc, const char **argv) ARRAY_SIZE(schedstat_args) : 0; struct tep_event *waking_event; + int ret; /* * +2 for either "-e", "sched:sched_wakeup" or @@ -3391,14 +3393,18 @@ static int __cmd_record(int argc, const char **argv) */ rec_argc = ARRAY_SIZE(record_args) + 2 + schedstat_argc + argc - 1; rec_argv = calloc(rec_argc + 1, sizeof(char *)); - if (rec_argv == NULL) return -ENOMEM; + rec_argv_copy = calloc(rec_argc + 1, sizeof(char *)); + if (rec_argv_copy == NULL) { + free(rec_argv); + return -ENOMEM; + } for (i = 0; i < ARRAY_SIZE(record_args); i++) rec_argv[i] = strdup(record_args[i]); - rec_argv[i++] = "-e"; + rec_argv[i++] = strdup("-e"); waking_event = trace_event__tp_format("sched", "sched_waking"); if (!IS_ERR(waking_event)) rec_argv[i++] = strdup("sched:sched_waking"); @@ -3409,11 +3415,19 @@ static int __cmd_record(int argc, const char **argv) rec_argv[i++] = strdup(schedstat_args[j]); for (j = 1; j < (unsigned int)argc; j++, i++) - rec_argv[i] = argv[j]; + rec_argv[i] = strdup(argv[j]); BUG_ON(i != rec_argc); - return cmd_record(i, rec_argv); + memcpy(rec_argv_copy, rec_argv, sizeof(char *) * rec_argc); + ret = cmd_record(rec_argc, rec_argv_copy); + + for (i = 0; i < rec_argc; i++) + free(rec_argv[i]); + free(rec_argv); + free(rec_argv_copy); + + return ret; } int cmd_sched(int argc, const char **argv) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 7fb81a44672d..54cd29d07ca8 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -826,6 +826,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx) } evlist__for_each_entry(evsel_list, counter) { + counter->reset_group = false; if (bpf_counter__load(counter, &target)) return -1; if (!evsel__is_bpf(counter)) diff --git a/tools/perf/tests/shell/stat.sh b/tools/perf/tests/shell/stat.sh index 9313ef2739e0..26a51b48aee4 100755 --- a/tools/perf/tests/shell/stat.sh +++ b/tools/perf/tests/shell/stat.sh @@ -28,6 +28,24 @@ test_stat_record_report() { echo "stat record and report test [Success]" } +test_stat_repeat_weak_groups() { + echo "stat repeat weak groups test" + if ! perf stat -e '{cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles}' \ + true 2>&1 | grep -q 'seconds time elapsed' + then + echo "stat repeat weak groups test [Skipped event parsing failed]" + return + fi + if ! perf stat -r2 -e '{cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles}:W' \ + true > /dev/null 2>&1 + then + echo "stat repeat weak groups test [Failed]" + err=1 + return + fi + echo "stat repeat weak groups test [Success]" +} + test_topdown_groups() { # Topdown events must be grouped with the slots event first. Test that # parse-events reorders this. @@ -75,6 +93,7 @@ test_topdown_weak_groups() { test_default_stat test_stat_record_report +test_stat_repeat_weak_groups test_topdown_groups test_topdown_weak_groups exit $err diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 979c8cb918f7..788ce5e46470 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -1193,7 +1193,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, &rsd); if (retiring > 0.7) color = PERF_COLOR_GREEN; - print_metric(config, ctxp, color, "%8.1f%%", "retiring", + print_metric(config, ctxp, color, "%8.1f%%", "Retiring", retiring * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_FE_BOUND) && full_td(cpu_map_idx, st, &rsd)) { @@ -1202,7 +1202,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, &rsd); if (fe_bound > 0.2) color = PERF_COLOR_RED; - print_metric(config, ctxp, color, "%8.1f%%", "frontend bound", + print_metric(config, ctxp, color, "%8.1f%%", "Frontend Bound", fe_bound * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_BE_BOUND) && full_td(cpu_map_idx, st, &rsd)) { @@ -1211,7 +1211,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, &rsd); if (be_bound > 0.2) color = PERF_COLOR_RED; - print_metric(config, ctxp, color, "%8.1f%%", "backend bound", + print_metric(config, ctxp, color, "%8.1f%%", "Backend Bound", be_bound * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_BAD_SPEC) && full_td(cpu_map_idx, st, &rsd)) { @@ -1220,7 +1220,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, &rsd); if (bad_spec > 0.1) color = PERF_COLOR_RED; - print_metric(config, ctxp, color, "%8.1f%%", "bad speculation", + print_metric(config, ctxp, color, "%8.1f%%", "Bad Speculation", bad_spec * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_HEAVY_OPS) && full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) { @@ -1234,13 +1234,13 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, if (retiring > 0.7 && heavy_ops > 0.1) color = PERF_COLOR_GREEN; - print_metric(config, ctxp, color, "%8.1f%%", "heavy operations", + print_metric(config, ctxp, color, "%8.1f%%", "Heavy Operations", heavy_ops * 100.); if (retiring > 0.7 && light_ops > 0.6) color = PERF_COLOR_GREEN; else color = NULL; - print_metric(config, ctxp, color, "%8.1f%%", "light operations", + print_metric(config, ctxp, color, "%8.1f%%", "Light Operations", light_ops * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_BR_MISPREDICT) && full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) { @@ -1254,13 +1254,13 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, if (bad_spec > 0.1 && br_mis > 0.05) color = PERF_COLOR_RED; - print_metric(config, ctxp, color, "%8.1f%%", "branch mispredict", + print_metric(config, ctxp, color, "%8.1f%%", "Branch Mispredict", br_mis * 100.); if (bad_spec > 0.1 && m_clears > 0.05) color = PERF_COLOR_RED; else color = NULL; - print_metric(config, ctxp, color, "%8.1f%%", "machine clears", + print_metric(config, ctxp, color, "%8.1f%%", "Machine Clears", m_clears * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_LAT) && full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) { @@ -1274,13 +1274,13 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, if (fe_bound > 0.2 && fetch_lat > 0.15) color = PERF_COLOR_RED; - print_metric(config, ctxp, color, "%8.1f%%", "fetch latency", + print_metric(config, ctxp, color, "%8.1f%%", "Fetch Latency", fetch_lat * 100.); if (fe_bound > 0.2 && fetch_bw > 0.1) color = PERF_COLOR_RED; else color = NULL; - print_metric(config, ctxp, color, "%8.1f%%", "fetch bandwidth", + print_metric(config, ctxp, color, "%8.1f%%", "Fetch Bandwidth", fetch_bw * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_MEM_BOUND) && full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) { @@ -1294,13 +1294,13 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, if (be_bound > 0.2 && mem_bound > 0.2) color = PERF_COLOR_RED; - print_metric(config, ctxp, color, "%8.1f%%", "memory bound", + print_metric(config, ctxp, color, "%8.1f%%", "Memory Bound", mem_bound * 100.); if (be_bound > 0.2 && core_bound > 0.1) color = PERF_COLOR_RED; else color = NULL; - print_metric(config, ctxp, color, "%8.1f%%", "Core bound", + print_metric(config, ctxp, color, "%8.1f%%", "Core Bound", core_bound * 100.); } else if (evsel->metric_expr) { generic_metric(config, evsel->metric_expr, evsel->metric_events, NULL, diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 10b34bb03bc1..c2064a35688b 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -12,6 +12,7 @@ TARGETS += cpu-hotplug TARGETS += damon TARGETS += drivers/dma-buf TARGETS += drivers/s390x/uvdevice +TARGETS += drivers/net/bonding TARGETS += efivarfs TARGETS += exec TARGETS += filesystems diff --git a/tools/testing/selftests/drivers/net/bonding/Makefile b/tools/testing/selftests/drivers/net/bonding/Makefile new file mode 100644 index 000000000000..ab6c54b12098 --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 +# Makefile for net selftests + +TEST_PROGS := bond-break-lacpdu-tx.sh + +include ../../../lib.mk diff --git a/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh b/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh new file mode 100755 index 000000000000..47ab90596acb --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh @@ -0,0 +1,81 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +# Regression Test: +# Verify LACPDUs get transmitted after setting the MAC address of +# the bond. +# +# https://bugzilla.redhat.com/show_bug.cgi?id=2020773 +# +# +---------+ +# | fab-br0 | +# +---------+ +# | +# +---------+ +# | fbond | +# +---------+ +# | | +# +------+ +------+ +# |veth1 | |veth2 | +# +------+ +------+ +# +# We use veths instead of physical interfaces + +set -e +tmp=$(mktemp -q dump.XXXXXX) +cleanup() { + ip link del fab-br0 >/dev/null 2>&1 || : + ip link del fbond >/dev/null 2>&1 || : + ip link del veth1-bond >/dev/null 2>&1 || : + ip link del veth2-bond >/dev/null 2>&1 || : + modprobe -r bonding >/dev/null 2>&1 || : + rm -f -- ${tmp} +} + +trap cleanup 0 1 2 +cleanup +sleep 1 + +# create the bridge +ip link add fab-br0 address 52:54:00:3B:7C:A6 mtu 1500 type bridge \ + forward_delay 15 + +# create the bond +ip link add fbond type bond mode 4 miimon 200 xmit_hash_policy 1 \ + ad_actor_sys_prio 65535 lacp_rate fast + +# set bond address +ip link set fbond address 52:54:00:3B:7C:A6 +ip link set fbond up + +# set again bond sysfs parameters +ip link set fbond type bond ad_actor_sys_prio 65535 + +# create veths +ip link add name veth1-bond type veth peer name veth1-end +ip link add name veth2-bond type veth peer name veth2-end + +# add ports +ip link set fbond master fab-br0 +ip link set veth1-bond down master fbond +ip link set veth2-bond down master fbond + +# bring up +ip link set veth1-end up +ip link set veth2-end up +ip link set fab-br0 up +ip link set fbond up +ip addr add dev fab-br0 10.0.0.3 + +tcpdump -n -i veth1-end -e ether proto 0x8809 >${tmp} 2>&1 & +sleep 15 +pkill tcpdump >/dev/null 2>&1 +rc=0 +num=$(grep "packets captured" ${tmp} | awk '{print $1}') +if test "$num" -gt 0; then + echo "PASS, captured ${num}" +else + echo "FAIL" + rc=1 +fi +exit $rc diff --git a/tools/testing/selftests/drivers/net/bonding/config b/tools/testing/selftests/drivers/net/bonding/config new file mode 100644 index 000000000000..dc1c22de3c92 --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/config @@ -0,0 +1 @@ +CONFIG_BONDING=y diff --git a/tools/testing/selftests/drivers/net/bonding/settings b/tools/testing/selftests/drivers/net/bonding/settings new file mode 100644 index 000000000000..867e118223cd --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/settings @@ -0,0 +1 @@ +timeout=60 diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 947fc72413e9..d44c72b3abe3 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -40,6 +40,7 @@ ifeq (0,$(MAKELEVEL)) endif endif selfdir = $(realpath $(dir $(filter %/lib.mk,$(MAKEFILE_LIST)))) +top_srcdir = $(selfdir)/../../.. # The following are built by lib.mk common compile rules. # TEST_CUSTOM_PROGS should be used by tests that require diff --git a/tools/testing/selftests/sgx/sigstruct.c b/tools/testing/selftests/sgx/sigstruct.c index 50c5ab1aa6fa..a07896a46364 100644 --- a/tools/testing/selftests/sgx/sigstruct.c +++ b/tools/testing/selftests/sgx/sigstruct.c @@ -17,6 +17,12 @@ #include "defines.h" #include "main.h" +/* + * FIXME: OpenSSL 3.0 has deprecated some functions. For now just ignore + * the warnings. + */ +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" + struct q1q2_ctx { BN_CTX *bn_ctx; BIGNUM *m; |