diff options
408 files changed, 4403 insertions, 1892 deletions
@@ -605,7 +605,8 @@ Oleksij Rempel <o.rempel@pengutronix.de> Oleksij Rempel <o.rempel@pengutronix.de> <ore@pengutronix.de> Oliver Hartkopp <socketcan@hartkopp.net> <oliver.hartkopp@volkswagen.de> Oliver Hartkopp <socketcan@hartkopp.net> <oliver@hartkopp.net> -Oliver Upton <oliver.upton@linux.dev> <oupton@google.com> +Oliver Upton <oupton@kernel.org> <oupton@google.com> +Oliver Upton <oupton@kernel.org> <oliver.upton@linux.dev> OndÅ™ej Jirman <megi@xff.cz> <megous@megous.com> Oza Pawandeep <quic_poza@quicinc.com> <poza@codeaurora.org> Pali Rohár <pali@kernel.org> <pali.rohar@gmail.com> diff --git a/Documentation/devicetree/bindings/gpio/ti,twl4030-gpio.yaml b/Documentation/devicetree/bindings/gpio/ti,twl4030-gpio.yaml index 5e3e199fd9a4..96d50d14c071 100644 --- a/Documentation/devicetree/bindings/gpio/ti,twl4030-gpio.yaml +++ b/Documentation/devicetree/bindings/gpio/ti,twl4030-gpio.yaml @@ -1,7 +1,7 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) %YAML 1.2 --- -$id: http://devicetree.org/schemas/ti,twl4030-gpio.yaml# +$id: http://devicetree.org/schemas/gpio/ti,twl4030-gpio.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: TI TWL4030 GPIO controller diff --git a/Documentation/firmware-guide/acpi/i2c-muxes.rst b/Documentation/firmware-guide/acpi/i2c-muxes.rst index f366539acd79..96ef4012d78f 100644 --- a/Documentation/firmware-guide/acpi/i2c-muxes.rst +++ b/Documentation/firmware-guide/acpi/i2c-muxes.rst @@ -37,8 +37,8 @@ which corresponds to the following ASL (in the scope of \_SB):: Name (_HID, ...) Name (_CRS, ResourceTemplate () { I2cSerialBus (0x50, ControllerInitiated, I2C_SPEED, - AddressingMode7Bit, "\\_SB.SMB1.CH00", 0x00, - ResourceConsumer,,) + AddressingMode7Bit, "\\_SB.SMB1.MUX0.CH00", + 0x00, ResourceConsumer,,) } } } @@ -52,8 +52,8 @@ which corresponds to the following ASL (in the scope of \_SB):: Name (_HID, ...) Name (_CRS, ResourceTemplate () { I2cSerialBus (0x50, ControllerInitiated, I2C_SPEED, - AddressingMode7Bit, "\\_SB.SMB1.CH01", 0x00, - ResourceConsumer,,) + AddressingMode7Bit, "\\_SB.SMB1.MUX0.CH01", + 0x00, ResourceConsumer,,) } } } diff --git a/Documentation/userspace-api/netlink/intro-specs.rst b/Documentation/userspace-api/netlink/intro-specs.rst index a4435ae4628d..e5ebc617754a 100644 --- a/Documentation/userspace-api/netlink/intro-specs.rst +++ b/Documentation/userspace-api/netlink/intro-specs.rst @@ -13,10 +13,10 @@ Simple CLI Kernel comes with a simple CLI tool which should be useful when developing Netlink related code. The tool is implemented in Python and can use a YAML specification to issue Netlink requests -to the kernel. Only Generic Netlink is supported. +to the kernel. The tool is located at ``tools/net/ynl/pyynl/cli.py``. It accepts -a handul of arguments, the most important ones are: +a handful of arguments, the most important ones are: - ``--spec`` - point to the spec file - ``--do $name`` / ``--dump $name`` - issue request ``$name`` diff --git a/MAINTAINERS b/MAINTAINERS index 46bd8e033042..8a4d9c0c7b8a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -915,6 +915,7 @@ F: drivers/staging/media/sunxi/cedrus/ ALPHA PORT M: Richard Henderson <richard.henderson@linaro.org> M: Matt Turner <mattst88@gmail.com> +M: Magnus Lindholm <linmag7@gmail.com> L: linux-alpha@vger.kernel.org S: Odd Fixes F: arch/alpha/ @@ -4818,6 +4819,7 @@ F: drivers/net/dsa/b53/* F: drivers/net/dsa/bcm_sf2* F: include/linux/dsa/brcm.h F: include/linux/platform_data/b53.h +F: net/dsa/tag_brcm.c BROADCOM BCM2711/BCM2835 ARM ARCHITECTURE M: Florian Fainelli <florian.fainelli@broadcom.com> @@ -9207,6 +9209,7 @@ R: Yue Hu <zbestahu@gmail.com> R: Jeffle Xu <jefflexu@linux.alibaba.com> R: Sandeep Dhavale <dhavale@google.com> R: Hongbo Li <lihongbo22@huawei.com> +R: Chunhai Guo <guochunhai@vivo.com> L: linux-erofs@lists.ozlabs.org S: Maintained W: https://erofs.docs.kernel.org @@ -12521,6 +12524,7 @@ F: include/linux/avf/virtchnl.h F: include/linux/net/intel/*/ INTEL ETHERNET PROTOCOL DRIVER FOR RDMA +M: Krzysztof Czurylo <krzysztof.czurylo@intel.com> M: Tatyana Nikolova <tatyana.e.nikolova@intel.com> L: linux-rdma@vger.kernel.org S: Supported @@ -12861,7 +12865,8 @@ F: tools/testing/selftests/sgx/* K: \bSGX_ INTEL SKYLAKE INT3472 ACPI DEVICE DRIVER -M: Daniel Scally <djrscally@gmail.com> +M: Daniel Scally <dan.scally@ideasonboard.com> +M: Sakari Ailus <sakari.ailus@linux.intel.com> S: Maintained F: drivers/platform/x86/intel/int3472/ F: include/linux/platform_data/x86/int3472.h @@ -13656,7 +13661,7 @@ F: virt/kvm/* KERNEL VIRTUAL MACHINE FOR ARM64 (KVM/arm64) M: Marc Zyngier <maz@kernel.org> -M: Oliver Upton <oliver.upton@linux.dev> +M: Oliver Upton <oupton@kernel.org> R: Joey Gouly <joey.gouly@arm.com> R: Suzuki K Poulose <suzuki.poulose@arm.com> R: Zenghui Yu <yuzenghui@huawei.com> @@ -16495,12 +16500,12 @@ F: mm/secretmem.c MEMORY MANAGEMENT - SWAP M: Andrew Morton <akpm@linux-foundation.org> +M: Chris Li <chrisl@kernel.org> +M: Kairui Song <kasong@tencent.com> R: Kemeng Shi <shikemeng@huaweicloud.com> -R: Kairui Song <kasong@tencent.com> R: Nhat Pham <nphamcs@gmail.com> R: Baoquan He <bhe@redhat.com> R: Barry Song <baohua@kernel.org> -R: Chris Li <chrisl@kernel.org> L: linux-mm@kvack.org S: Maintained F: Documentation/mm/swap-table.rst @@ -20160,6 +20165,7 @@ R: Alexander Shishkin <alexander.shishkin@linux.intel.com> R: Jiri Olsa <jolsa@kernel.org> R: Ian Rogers <irogers@google.com> R: Adrian Hunter <adrian.hunter@intel.com> +R: James Clark <james.clark@linaro.org> L: linux-perf-users@vger.kernel.org L: linux-kernel@vger.kernel.org S: Supported @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 18 SUBLEVEL = 0 -EXTRAVERSION = -rc4 +EXTRAVERSION = -rc5 NAME = Baby Opossum Posse # *DOCUMENTATION* diff --git a/arch/Kconfig b/arch/Kconfig index 74ff01133532..61130b88964b 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -917,6 +917,13 @@ config ARCH_USES_CFI_TRAPS An architecture should select this option if it requires the .kcfi_traps section for KCFI trap handling. +config ARCH_USES_CFI_GENERIC_LLVM_PASS + bool + help + An architecture should select this option if it uses the generic + KCFIPass in LLVM to expand kCFI bundles instead of architecture-specific + lowering. + config CFI bool "Use Kernel Control Flow Integrity (kCFI)" default CFI_CLANG diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 2e3f93b690f4..4fb985b76e97 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -44,6 +44,8 @@ config ARM select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF select ARCH_USE_MEMTEST + # https://github.com/llvm/llvm-project/commit/d130f402642fba3d065aacb506cb061c899558de + select ARCH_USES_CFI_GENERIC_LLVM_PASS if CLANG_VERSION < 220000 select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU select ARCH_WANT_GENERAL_HUGETLB select ARCH_WANT_IPC_PARSE_VERSION diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h index 00d97b8a757f..51746005239b 100644 --- a/arch/arm64/include/asm/alternative.h +++ b/arch/arm64/include/asm/alternative.h @@ -26,9 +26,12 @@ void __init apply_alternatives_all(void); bool alternative_is_applied(u16 cpucap); #ifdef CONFIG_MODULES -void apply_alternatives_module(void *start, size_t length); +int apply_alternatives_module(void *start, size_t length); #else -static inline void apply_alternatives_module(void *start, size_t length) { } +static inline int apply_alternatives_module(void *start, size_t length) +{ + return 0; +} #endif void alt_cb_patch_nops(struct alt_instr *alt, __le32 *origptr, diff --git a/arch/arm64/include/asm/kfence.h b/arch/arm64/include/asm/kfence.h index a81937fae9f6..21dbc9dda747 100644 --- a/arch/arm64/include/asm/kfence.h +++ b/arch/arm64/include/asm/kfence.h @@ -10,8 +10,6 @@ #include <asm/set_memory.h> -static inline bool arch_kfence_init_pool(void) { return true; } - static inline bool kfence_protect_page(unsigned long addr, bool protect) { set_memory_valid(addr, 1, !protect); @@ -25,6 +23,7 @@ static inline bool arm64_kfence_can_set_direct_map(void) { return !kfence_early_init; } +bool arch_kfence_init_pool(void); #else /* CONFIG_KFENCE */ static inline bool arm64_kfence_can_set_direct_map(void) { return false; } #endif /* CONFIG_KFENCE */ diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h index 9abcc8ef3087..b57b2bb00967 100644 --- a/arch/arm64/include/asm/percpu.h +++ b/arch/arm64/include/asm/percpu.h @@ -77,7 +77,7 @@ __percpu_##name##_case_##sz(void *ptr, unsigned long val) \ " stxr" #sfx "\t%w[loop], %" #w "[tmp], %[ptr]\n" \ " cbnz %w[loop], 1b", \ /* LSE atomics */ \ - #op_lse "\t%" #w "[val], %[ptr]\n" \ + #op_lse "\t%" #w "[val], %" #w "[tmp], %[ptr]\n" \ __nops(3)) \ : [loop] "=&r" (loop), [tmp] "=&r" (tmp), \ [ptr] "+Q"(*(u##sz *)ptr) \ @@ -124,9 +124,16 @@ PERCPU_RW_OPS(8) PERCPU_RW_OPS(16) PERCPU_RW_OPS(32) PERCPU_RW_OPS(64) -PERCPU_OP(add, add, stadd) -PERCPU_OP(andnot, bic, stclr) -PERCPU_OP(or, orr, stset) + +/* + * Use value-returning atomics for CPU-local ops as they are more likely + * to execute "near" to the CPU (e.g. in L1$). + * + * https://lore.kernel.org/r/e7d539ed-ced0-4b96-8ecd-048a5b803b85@paulmck-laptop + */ +PERCPU_OP(add, add, ldadd) +PERCPU_OP(andnot, bic, ldclr) +PERCPU_OP(or, orr, ldset) PERCPU_RET_OP(add, add, ldadd) #undef PERCPU_RW_OPS diff --git a/arch/arm64/include/asm/scs.h b/arch/arm64/include/asm/scs.h index a76f9b387a26..c59f6324f2bb 100644 --- a/arch/arm64/include/asm/scs.h +++ b/arch/arm64/include/asm/scs.h @@ -53,7 +53,7 @@ enum { EDYNSCS_INVALID_CFA_OPCODE = 4, }; -int __pi_scs_patch(const u8 eh_frame[], int size); +int __pi_scs_patch(const u8 eh_frame[], int size, bool skip_dry_run); #endif /* __ASSEMBLY __ */ diff --git a/arch/arm64/include/asm/spectre.h b/arch/arm64/include/asm/spectre.h index 8fef12626090..900454aaa292 100644 --- a/arch/arm64/include/asm/spectre.h +++ b/arch/arm64/include/asm/spectre.h @@ -117,6 +117,7 @@ void spectre_bhb_patch_wa3(struct alt_instr *alt, __le32 *origptr, __le32 *updptr, int nr_inst); void spectre_bhb_patch_clearbhb(struct alt_instr *alt, __le32 *origptr, __le32 *updptr, int nr_inst); +void spectre_print_disabled_mitigations(void); #endif /* __ASSEMBLY__ */ #endif /* __ASM_SPECTRE_H */ diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c index 7aca29e1d30b..c022c1acb8c7 100644 --- a/arch/arm64/kernel/acpi.c +++ b/arch/arm64/kernel/acpi.c @@ -197,8 +197,6 @@ out: */ void __init acpi_boot_table_init(void) { - int ret; - /* * Enable ACPI instead of device tree unless * - ACPI has been disabled explicitly (acpi=off), or @@ -252,12 +250,8 @@ done: * behaviour, use acpi=nospcr to disable console in ACPI SPCR * table as default serial console. */ - ret = acpi_parse_spcr(earlycon_acpi_spcr_enable, + acpi_parse_spcr(earlycon_acpi_spcr_enable, !param_acpi_nospcr); - if (!ret || param_acpi_nospcr || !IS_ENABLED(CONFIG_ACPI_SPCR_TABLE)) - pr_info("Use ACPI SPCR as default console: No\n"); - else - pr_info("Use ACPI SPCR as default console: Yes\n"); if (IS_ENABLED(CONFIG_ACPI_BGRT)) acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt); diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c index 8ff6610af496..f5ec7e7c1d3f 100644 --- a/arch/arm64/kernel/alternative.c +++ b/arch/arm64/kernel/alternative.c @@ -139,9 +139,9 @@ static noinstr void clean_dcache_range_nopatch(u64 start, u64 end) } while (cur += d_size, cur < end); } -static void __apply_alternatives(const struct alt_region *region, - bool is_module, - unsigned long *cpucap_mask) +static int __apply_alternatives(const struct alt_region *region, + bool is_module, + unsigned long *cpucap_mask) { struct alt_instr *alt; __le32 *origptr, *updptr; @@ -166,10 +166,13 @@ static void __apply_alternatives(const struct alt_region *region, updptr = is_module ? origptr : lm_alias(origptr); nr_inst = alt->orig_len / AARCH64_INSN_SIZE; - if (ALT_HAS_CB(alt)) + if (ALT_HAS_CB(alt)) { alt_cb = ALT_REPL_PTR(alt); - else + if (is_module && !core_kernel_text((unsigned long)alt_cb)) + return -ENOEXEC; + } else { alt_cb = patch_alternative; + } alt_cb(alt, origptr, updptr, nr_inst); @@ -193,6 +196,8 @@ static void __apply_alternatives(const struct alt_region *region, bitmap_and(applied_alternatives, applied_alternatives, system_cpucaps, ARM64_NCAPS); } + + return 0; } static void __init apply_alternatives_vdso(void) @@ -277,7 +282,7 @@ void __init apply_boot_alternatives(void) } #ifdef CONFIG_MODULES -void apply_alternatives_module(void *start, size_t length) +int apply_alternatives_module(void *start, size_t length) { struct alt_region region = { .begin = start, @@ -287,7 +292,7 @@ void apply_alternatives_module(void *start, size_t length) bitmap_fill(all_capabilities, ARM64_NCAPS); - __apply_alternatives(®ion, true, &all_capabilities[0]); + return __apply_alternatives(®ion, true, &all_capabilities[0]); } #endif diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 5ed401ff79e3..e25b0f84a22d 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -95,6 +95,7 @@ #include <asm/vectors.h> #include <asm/virt.h> +#include <asm/spectre.h> /* Kernel representation of AT_HWCAP and AT_HWCAP2 */ static DECLARE_BITMAP(elf_hwcap, MAX_CPU_FEATURES) __read_mostly; @@ -3875,6 +3876,11 @@ static void __init setup_system_capabilities(void) */ if (system_uses_ttbr0_pan()) pr_info("emulated: Privileged Access Never (PAN) using TTBR0_EL1 switching\n"); + + /* + * Report Spectre mitigations status. + */ + spectre_print_disabled_mitigations(); } void __init setup_system_features(void) diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index d6d443c4a01a..24adb581af0e 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -489,16 +489,29 @@ int module_finalize(const Elf_Ehdr *hdr, int ret; s = find_section(hdr, sechdrs, ".altinstructions"); - if (s) - apply_alternatives_module((void *)s->sh_addr, s->sh_size); + if (s) { + ret = apply_alternatives_module((void *)s->sh_addr, s->sh_size); + if (ret < 0) { + pr_err("module %s: error occurred when applying alternatives\n", me->name); + return ret; + } + } if (scs_is_dynamic()) { s = find_section(hdr, sechdrs, ".init.eh_frame"); if (s) { - ret = __pi_scs_patch((void *)s->sh_addr, s->sh_size); - if (ret) + /* + * Because we can reject modules that are malformed + * so SCS patching fails, skip dry run and try to patch + * it in place. If patching fails, the module would not + * be loaded anyway. + */ + ret = __pi_scs_patch((void *)s->sh_addr, s->sh_size, true); + if (ret) { pr_err("module %s: error occurred during dynamic SCS patching (%d)\n", me->name, ret); + return -ENOEXEC; + } } } diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index 43f7a2f39403..32148bf09c1d 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -476,7 +476,8 @@ static int __access_remote_tags(struct mm_struct *mm, unsigned long addr, folio = page_folio(page); if (folio_test_hugetlb(folio)) - WARN_ON_ONCE(!folio_test_hugetlb_mte_tagged(folio)); + WARN_ON_ONCE(!folio_test_hugetlb_mte_tagged(folio) && + !is_huge_zero_folio(folio)); else WARN_ON_ONCE(!page_mte_tagged(page) && !is_zero_page(page)); diff --git a/arch/arm64/kernel/pi/map_kernel.c b/arch/arm64/kernel/pi/map_kernel.c index e8ddbde31a83..659297f87cfa 100644 --- a/arch/arm64/kernel/pi/map_kernel.c +++ b/arch/arm64/kernel/pi/map_kernel.c @@ -104,7 +104,7 @@ static void __init map_kernel(u64 kaslr_offset, u64 va_offset, int root_level) if (enable_scs) { scs_patch(__eh_frame_start + va_offset, - __eh_frame_end - __eh_frame_start); + __eh_frame_end - __eh_frame_start, false); asm("ic ialluis"); dynamic_scs_is_enabled = true; diff --git a/arch/arm64/kernel/pi/patch-scs.c b/arch/arm64/kernel/pi/patch-scs.c index 55d0cd64ef71..bbe7d30ed12b 100644 --- a/arch/arm64/kernel/pi/patch-scs.c +++ b/arch/arm64/kernel/pi/patch-scs.c @@ -225,7 +225,7 @@ static int scs_handle_fde_frame(const struct eh_frame *frame, return 0; } -int scs_patch(const u8 eh_frame[], int size) +int scs_patch(const u8 eh_frame[], int size, bool skip_dry_run) { int code_alignment_factor = 1; bool fde_use_sdata8 = false; @@ -277,11 +277,13 @@ int scs_patch(const u8 eh_frame[], int size) } } else { ret = scs_handle_fde_frame(frame, code_alignment_factor, - fde_use_sdata8, true); + fde_use_sdata8, !skip_dry_run); if (ret) return ret; - scs_handle_fde_frame(frame, code_alignment_factor, - fde_use_sdata8, false); + + if (!skip_dry_run) + scs_handle_fde_frame(frame, code_alignment_factor, + fde_use_sdata8, false); } p += sizeof(frame->size) + frame->size; diff --git a/arch/arm64/kernel/pi/pi.h b/arch/arm64/kernel/pi/pi.h index 08ef9f80456b..aec3172d4003 100644 --- a/arch/arm64/kernel/pi/pi.h +++ b/arch/arm64/kernel/pi/pi.h @@ -27,7 +27,7 @@ extern pgd_t init_pg_dir[], init_pg_end[]; void init_feature_override(u64 boot_status, const void *fdt, int chosen); u64 kaslr_early_init(void *fdt, int chosen); void relocate_kernel(u64 offset); -int scs_patch(const u8 eh_frame[], int size); +int scs_patch(const u8 eh_frame[], int size, bool skip_dry_run); void map_range(phys_addr_t *pte, u64 start, u64 end, phys_addr_t pa, pgprot_t prot, int level, pte_t *tbl, bool may_use_cont, diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index 8ab6104a4883..43a0361a8bf0 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -49,7 +49,10 @@ void *alloc_insn_page(void) addr = execmem_alloc(EXECMEM_KPROBES, PAGE_SIZE); if (!addr) return NULL; - set_memory_rox((unsigned long)addr, 1); + if (set_memory_rox((unsigned long)addr, 1)) { + execmem_free(addr); + return NULL; + } return addr; } diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index f9a32dfde006..c7d70d04c164 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -91,12 +91,7 @@ early_param("nospectre_v2", parse_spectre_v2_param); static bool spectre_v2_mitigations_off(void) { - bool ret = __nospectre_v2 || cpu_mitigations_off(); - - if (ret) - pr_info_once("spectre-v2 mitigation disabled by command line option\n"); - - return ret; + return __nospectre_v2 || cpu_mitigations_off(); } static const char *get_bhb_affected_string(enum mitigation_state bhb_state) @@ -421,13 +416,8 @@ early_param("ssbd", parse_spectre_v4_param); */ static bool spectre_v4_mitigations_off(void) { - bool ret = cpu_mitigations_off() || - __spectre_v4_policy == SPECTRE_V4_POLICY_MITIGATION_DISABLED; - - if (ret) - pr_info_once("spectre-v4 mitigation disabled by command-line option\n"); - - return ret; + return cpu_mitigations_off() || + __spectre_v4_policy == SPECTRE_V4_POLICY_MITIGATION_DISABLED; } /* Do we need to toggle the mitigation state on entry to/exit from the kernel? */ @@ -1042,10 +1032,6 @@ void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *entry) if (arm64_get_spectre_v2_state() == SPECTRE_VULNERABLE) { /* No point mitigating Spectre-BHB alone. */ - } else if (!IS_ENABLED(CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY)) { - pr_info_once("spectre-bhb mitigation disabled by compile time option\n"); - } else if (cpu_mitigations_off() || __nospectre_bhb) { - pr_info_once("spectre-bhb mitigation disabled by command line option\n"); } else if (supports_ecbhb(SCOPE_LOCAL_CPU)) { state = SPECTRE_MITIGATED; set_bit(BHB_HW, &system_bhb_mitigations); @@ -1199,3 +1185,18 @@ void unpriv_ebpf_notify(int new_state) pr_err("WARNING: %s", EBPF_WARN); } #endif + +void spectre_print_disabled_mitigations(void) +{ + /* Keep a single copy of the common message suffix to avoid duplication. */ + const char *spectre_disabled_suffix = "mitigation disabled by command-line option\n"; + + if (spectre_v2_mitigations_off()) + pr_info("spectre-v2 %s", spectre_disabled_suffix); + + if (spectre_v4_mitigations_off()) + pr_info("spectre-v4 %s", spectre_disabled_suffix); + + if (__nospectre_bhb || cpu_mitigations_off()) + pr_info("spectre-bhb %s", spectre_disabled_suffix); +} diff --git a/arch/arm64/kvm/hyp/nvhe/ffa.c b/arch/arm64/kvm/hyp/nvhe/ffa.c index 4e16f9b96f63..58b7d0c477d7 100644 --- a/arch/arm64/kvm/hyp/nvhe/ffa.c +++ b/arch/arm64/kvm/hyp/nvhe/ffa.c @@ -479,7 +479,7 @@ static void __do_ffa_mem_xfer(const u64 func_id, struct ffa_mem_region_attributes *ep_mem_access; struct ffa_composite_mem_region *reg; struct ffa_mem_region *buf; - u32 offset, nr_ranges; + u32 offset, nr_ranges, checked_offset; int ret = 0; if (addr_mbz || npages_mbz || fraglen > len || @@ -516,7 +516,12 @@ static void __do_ffa_mem_xfer(const u64 func_id, goto out_unlock; } - if (fraglen < offset + sizeof(struct ffa_composite_mem_region)) { + if (check_add_overflow(offset, sizeof(struct ffa_composite_mem_region), &checked_offset)) { + ret = FFA_RET_INVALID_PARAMETERS; + goto out_unlock; + } + + if (fraglen < checked_offset) { ret = FFA_RET_INVALID_PARAMETERS; goto out_unlock; } diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index ddc8beb55eee..49db32f3ddf7 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -367,6 +367,19 @@ static int host_stage2_unmap_dev_all(void) return kvm_pgtable_stage2_unmap(pgt, addr, BIT(pgt->ia_bits) - addr); } +/* + * Ensure the PFN range is contained within PA-range. + * + * This check is also robust to overflows and is therefore a requirement before + * using a pfn/nr_pages pair from an untrusted source. + */ +static bool pfn_range_is_valid(u64 pfn, u64 nr_pages) +{ + u64 limit = BIT(kvm_phys_shift(&host_mmu.arch.mmu) - PAGE_SHIFT); + + return pfn < limit && ((limit - pfn) >= nr_pages); +} + struct kvm_mem_range { u64 start; u64 end; @@ -776,6 +789,9 @@ int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages) void *virt = __hyp_va(phys); int ret; + if (!pfn_range_is_valid(pfn, nr_pages)) + return -EINVAL; + host_lock_component(); hyp_lock_component(); @@ -804,6 +820,9 @@ int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages) u64 virt = (u64)__hyp_va(phys); int ret; + if (!pfn_range_is_valid(pfn, nr_pages)) + return -EINVAL; + host_lock_component(); hyp_lock_component(); @@ -887,6 +906,9 @@ int __pkvm_host_share_ffa(u64 pfn, u64 nr_pages) u64 size = PAGE_SIZE * nr_pages; int ret; + if (!pfn_range_is_valid(pfn, nr_pages)) + return -EINVAL; + host_lock_component(); ret = __host_check_page_state_range(phys, size, PKVM_PAGE_OWNED); if (!ret) @@ -902,6 +924,9 @@ int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages) u64 size = PAGE_SIZE * nr_pages; int ret; + if (!pfn_range_is_valid(pfn, nr_pages)) + return -EINVAL; + host_lock_component(); ret = __host_check_page_state_range(phys, size, PKVM_PAGE_SHARED_OWNED); if (!ret) @@ -945,6 +970,9 @@ int __pkvm_host_share_guest(u64 pfn, u64 gfn, u64 nr_pages, struct pkvm_hyp_vcpu if (prot & ~KVM_PGTABLE_PROT_RWX) return -EINVAL; + if (!pfn_range_is_valid(pfn, nr_pages)) + return -EINVAL; + ret = __guest_check_transition_size(phys, ipa, nr_pages, &size); if (ret) return ret; diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index e67eb39ddc11..8ae2bca81614 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -2595,19 +2595,23 @@ static bool bad_redir_trap(struct kvm_vcpu *vcpu, .val = 0, \ } -/* sys_reg_desc initialiser for known cpufeature ID registers */ -#define AA32_ID_SANITISED(name) { \ - ID_DESC(name), \ - .visibility = aa32_id_visibility, \ - .val = 0, \ -} - /* sys_reg_desc initialiser for writable ID registers */ #define ID_WRITABLE(name, mask) { \ ID_DESC(name), \ .val = mask, \ } +/* + * 32bit ID regs are fully writable when the guest is 32bit + * capable. Nothing in the KVM code should rely on 32bit features + * anyway, only 64bit, so let the VMM do its worse. + */ +#define AA32_ID_WRITABLE(name) { \ + ID_DESC(name), \ + .visibility = aa32_id_visibility, \ + .val = GENMASK(31, 0), \ +} + /* sys_reg_desc initialiser for cpufeature ID registers that need filtering */ #define ID_FILTERED(sysreg, name, mask) { \ ID_DESC(sysreg), \ @@ -3128,40 +3132,39 @@ static const struct sys_reg_desc sys_reg_descs[] = { /* AArch64 mappings of the AArch32 ID registers */ /* CRm=1 */ - AA32_ID_SANITISED(ID_PFR0_EL1), - AA32_ID_SANITISED(ID_PFR1_EL1), + AA32_ID_WRITABLE(ID_PFR0_EL1), + AA32_ID_WRITABLE(ID_PFR1_EL1), { SYS_DESC(SYS_ID_DFR0_EL1), .access = access_id_reg, .get_user = get_id_reg, .set_user = set_id_dfr0_el1, .visibility = aa32_id_visibility, .reset = read_sanitised_id_dfr0_el1, - .val = ID_DFR0_EL1_PerfMon_MASK | - ID_DFR0_EL1_CopDbg_MASK, }, + .val = GENMASK(31, 0) }, ID_HIDDEN(ID_AFR0_EL1), - AA32_ID_SANITISED(ID_MMFR0_EL1), - AA32_ID_SANITISED(ID_MMFR1_EL1), - AA32_ID_SANITISED(ID_MMFR2_EL1), - AA32_ID_SANITISED(ID_MMFR3_EL1), + AA32_ID_WRITABLE(ID_MMFR0_EL1), + AA32_ID_WRITABLE(ID_MMFR1_EL1), + AA32_ID_WRITABLE(ID_MMFR2_EL1), + AA32_ID_WRITABLE(ID_MMFR3_EL1), /* CRm=2 */ - AA32_ID_SANITISED(ID_ISAR0_EL1), - AA32_ID_SANITISED(ID_ISAR1_EL1), - AA32_ID_SANITISED(ID_ISAR2_EL1), - AA32_ID_SANITISED(ID_ISAR3_EL1), - AA32_ID_SANITISED(ID_ISAR4_EL1), - AA32_ID_SANITISED(ID_ISAR5_EL1), - AA32_ID_SANITISED(ID_MMFR4_EL1), - AA32_ID_SANITISED(ID_ISAR6_EL1), + AA32_ID_WRITABLE(ID_ISAR0_EL1), + AA32_ID_WRITABLE(ID_ISAR1_EL1), + AA32_ID_WRITABLE(ID_ISAR2_EL1), + AA32_ID_WRITABLE(ID_ISAR3_EL1), + AA32_ID_WRITABLE(ID_ISAR4_EL1), + AA32_ID_WRITABLE(ID_ISAR5_EL1), + AA32_ID_WRITABLE(ID_MMFR4_EL1), + AA32_ID_WRITABLE(ID_ISAR6_EL1), /* CRm=3 */ - AA32_ID_SANITISED(MVFR0_EL1), - AA32_ID_SANITISED(MVFR1_EL1), - AA32_ID_SANITISED(MVFR2_EL1), + AA32_ID_WRITABLE(MVFR0_EL1), + AA32_ID_WRITABLE(MVFR1_EL1), + AA32_ID_WRITABLE(MVFR2_EL1), ID_UNALLOCATED(3,3), - AA32_ID_SANITISED(ID_PFR2_EL1), + AA32_ID_WRITABLE(ID_PFR2_EL1), ID_HIDDEN(ID_DFR1_EL1), - AA32_ID_SANITISED(ID_MMFR5_EL1), + AA32_ID_WRITABLE(ID_MMFR5_EL1), ID_UNALLOCATED(3,7), /* AArch64 ID registers */ @@ -5606,11 +5609,13 @@ int kvm_finalize_sys_regs(struct kvm_vcpu *vcpu) guard(mutex)(&kvm->arch.config_lock); - if (!(static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif) && - irqchip_in_kernel(kvm) && - kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)) { - kvm->arch.id_regs[IDREG_IDX(SYS_ID_AA64PFR0_EL1)] &= ~ID_AA64PFR0_EL1_GIC_MASK; - kvm->arch.id_regs[IDREG_IDX(SYS_ID_PFR1_EL1)] &= ~ID_PFR1_EL1_GIC_MASK; + if (!irqchip_in_kernel(kvm)) { + u64 val; + + val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1) & ~ID_AA64PFR0_EL1_GIC; + kvm_set_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1, val); + val = kvm_read_vm_id_reg(kvm, SYS_ID_PFR1_EL1) & ~ID_PFR1_EL1_GIC; + kvm_set_vm_id_reg(kvm, SYS_ID_PFR1_EL1, val); } if (vcpu_has_nv(vcpu)) { diff --git a/arch/arm64/kvm/vgic/vgic-debug.c b/arch/arm64/kvm/vgic/vgic-debug.c index 4c1209261b65..bb92853d1fd3 100644 --- a/arch/arm64/kvm/vgic/vgic-debug.c +++ b/arch/arm64/kvm/vgic/vgic-debug.c @@ -64,29 +64,37 @@ static void iter_next(struct kvm *kvm, struct vgic_state_iter *iter) static int iter_mark_lpis(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; + unsigned long intid, flags; struct vgic_irq *irq; - unsigned long intid; int nr_lpis = 0; + xa_lock_irqsave(&dist->lpi_xa, flags); + xa_for_each(&dist->lpi_xa, intid, irq) { if (!vgic_try_get_irq_ref(irq)) continue; - xa_set_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER); + __xa_set_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER); nr_lpis++; } + xa_unlock_irqrestore(&dist->lpi_xa, flags); + return nr_lpis; } static void iter_unmark_lpis(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; + unsigned long intid, flags; struct vgic_irq *irq; - unsigned long intid; xa_for_each_marked(&dist->lpi_xa, intid, irq, LPI_XA_MARK_DEBUG_ITER) { - xa_clear_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER); + xa_lock_irqsave(&dist->lpi_xa, flags); + __xa_clear_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER); + xa_unlock_irqrestore(&dist->lpi_xa, flags); + + /* vgic_put_irq() expects to be called outside of the xa_lock */ vgic_put_irq(kvm, irq); } } diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index 1796b1a22a72..da62edbc1205 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -53,7 +53,7 @@ void kvm_vgic_early_init(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; - xa_init(&dist->lpi_xa); + xa_init_flags(&dist->lpi_xa, XA_FLAGS_LOCK_IRQ); } /* CREATION */ @@ -71,6 +71,7 @@ static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu, u32 type); int kvm_vgic_create(struct kvm *kvm, u32 type) { struct kvm_vcpu *vcpu; + u64 aa64pfr0, pfr1; unsigned long i; int ret; @@ -161,10 +162,19 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF; - if (type == KVM_DEV_TYPE_ARM_VGIC_V2) + aa64pfr0 = kvm_read_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1) & ~ID_AA64PFR0_EL1_GIC; + pfr1 = kvm_read_vm_id_reg(kvm, SYS_ID_PFR1_EL1) & ~ID_PFR1_EL1_GIC; + + if (type == KVM_DEV_TYPE_ARM_VGIC_V2) { kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF; - else + } else { INIT_LIST_HEAD(&kvm->arch.vgic.rd_regions); + aa64pfr0 |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, GIC, IMP); + pfr1 |= SYS_FIELD_PREP_ENUM(ID_PFR1_EL1, GIC, GICv3); + } + + kvm_set_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1, aa64pfr0); + kvm_set_vm_id_reg(kvm, SYS_ID_PFR1_EL1, pfr1); if (type == KVM_DEV_TYPE_ARM_VGIC_V3) kvm->arch.vgic.nassgicap = system_supports_direct_sgis(); diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index ce3e3ed3f29f..3f1c4b10fed9 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -78,6 +78,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, { struct vgic_dist *dist = &kvm->arch.vgic; struct vgic_irq *irq = vgic_get_irq(kvm, intid), *oldirq; + unsigned long flags; int ret; /* In this case there is no put, since we keep the reference. */ @@ -88,7 +89,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, if (!irq) return ERR_PTR(-ENOMEM); - ret = xa_reserve(&dist->lpi_xa, intid, GFP_KERNEL_ACCOUNT); + ret = xa_reserve_irq(&dist->lpi_xa, intid, GFP_KERNEL_ACCOUNT); if (ret) { kfree(irq); return ERR_PTR(ret); @@ -103,7 +104,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, irq->target_vcpu = vcpu; irq->group = 1; - xa_lock(&dist->lpi_xa); + xa_lock_irqsave(&dist->lpi_xa, flags); /* * There could be a race with another vgic_add_lpi(), so we need to @@ -114,21 +115,18 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, /* Someone was faster with adding this LPI, lets use that. */ kfree(irq); irq = oldirq; - - goto out_unlock; + } else { + ret = xa_err(__xa_store(&dist->lpi_xa, intid, irq, 0)); } - ret = xa_err(__xa_store(&dist->lpi_xa, intid, irq, 0)); + xa_unlock_irqrestore(&dist->lpi_xa, flags); + if (ret) { xa_release(&dist->lpi_xa, intid); kfree(irq); - } - -out_unlock: - xa_unlock(&dist->lpi_xa); - if (ret) return ERR_PTR(ret); + } /* * We "cache" the configuration table entries in our struct vgic_irq's. diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index 6fbb4b099855..2f75ef14d339 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -301,7 +301,8 @@ void vcpu_set_ich_hcr(struct kvm_vcpu *vcpu) return; /* Hide GICv3 sysreg if necessary */ - if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2) { + if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2 || + !irqchip_in_kernel(vcpu->kvm)) { vgic_v3->vgic_hcr |= (ICH_HCR_EL2_TALL0 | ICH_HCR_EL2_TALL1 | ICH_HCR_EL2_TC); return; diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c index 6dd5a10081e2..8d20c53faef0 100644 --- a/arch/arm64/kvm/vgic/vgic.c +++ b/arch/arm64/kvm/vgic/vgic.c @@ -28,7 +28,7 @@ struct vgic_global kvm_vgic_global_state __ro_after_init = { * kvm->arch.config_lock (mutex) * its->cmd_lock (mutex) * its->its_lock (mutex) - * vgic_dist->lpi_xa.xa_lock + * vgic_dist->lpi_xa.xa_lock must be taken with IRQs disabled * vgic_cpu->ap_list_lock must be taken with IRQs disabled * vgic_irq->irq_lock must be taken with IRQs disabled * @@ -141,32 +141,39 @@ static __must_check bool vgic_put_irq_norelease(struct kvm *kvm, struct vgic_irq void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq) { struct vgic_dist *dist = &kvm->arch.vgic; + unsigned long flags; - if (irq->intid >= VGIC_MIN_LPI) - might_lock(&dist->lpi_xa.xa_lock); + /* + * Normally the lock is only taken when the refcount drops to 0. + * Acquire/release it early on lockdep kernels to make locking issues + * in rare release paths a bit more obvious. + */ + if (IS_ENABLED(CONFIG_LOCKDEP) && irq->intid >= VGIC_MIN_LPI) { + guard(spinlock_irqsave)(&dist->lpi_xa.xa_lock); + } if (!__vgic_put_irq(kvm, irq)) return; - xa_lock(&dist->lpi_xa); + xa_lock_irqsave(&dist->lpi_xa, flags); vgic_release_lpi_locked(dist, irq); - xa_unlock(&dist->lpi_xa); + xa_unlock_irqrestore(&dist->lpi_xa, flags); } static void vgic_release_deleted_lpis(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; - unsigned long intid; + unsigned long flags, intid; struct vgic_irq *irq; - xa_lock(&dist->lpi_xa); + xa_lock_irqsave(&dist->lpi_xa, flags); xa_for_each(&dist->lpi_xa, intid, irq) { if (irq->pending_release) vgic_release_lpi_locked(dist, irq); } - xa_unlock(&dist->lpi_xa); + xa_unlock_irqrestore(&dist->lpi_xa, flags); } void vgic_flush_pending_lpis(struct kvm_vcpu *vcpu) diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index d816ff44faff..125dfa6c613b 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -969,6 +969,16 @@ struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, void tag_clear_highpage(struct page *page) { + /* + * Check if MTE is supported and fall back to clear_highpage(). + * get_huge_zero_folio() unconditionally passes __GFP_ZEROTAGS and + * post_alloc_hook() will invoke tag_clear_highpage(). + */ + if (!system_supports_mte()) { + clear_highpage(page); + return; + } + /* Newly allocated page, shouldn't have been tagged yet */ WARN_ON_ONCE(!try_page_mte_tagging(page)); mte_zero_clear_page_tags(page_address(page)); diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index b8d37eb037fc..2ba01dc8ef82 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -708,6 +708,30 @@ out: return ret; } +static inline bool force_pte_mapping(void) +{ + const bool bbml2 = system_capabilities_finalized() ? + system_supports_bbml2_noabort() : cpu_supports_bbml2_noabort(); + + if (debug_pagealloc_enabled()) + return true; + if (bbml2) + return false; + return rodata_full || arm64_kfence_can_set_direct_map() || is_realm_world(); +} + +static inline bool split_leaf_mapping_possible(void) +{ + /* + * !BBML2_NOABORT systems should never run into scenarios where we would + * have to split. So exit early and let calling code detect it and raise + * a warning. + */ + if (!system_supports_bbml2_noabort()) + return false; + return !force_pte_mapping(); +} + static DEFINE_MUTEX(pgtable_split_lock); int split_kernel_leaf_mapping(unsigned long start, unsigned long end) @@ -715,12 +739,11 @@ int split_kernel_leaf_mapping(unsigned long start, unsigned long end) int ret; /* - * !BBML2_NOABORT systems should not be trying to change permissions on - * anything that is not pte-mapped in the first place. Just return early - * and let the permission change code raise a warning if not already - * pte-mapped. + * Exit early if the region is within a pte-mapped area or if we can't + * split. For the latter case, the permission change code will raise a + * warning if not already pte-mapped. */ - if (!system_supports_bbml2_noabort()) + if (!split_leaf_mapping_possible() || is_kfence_address((void *)start)) return 0; /* @@ -758,30 +781,30 @@ int split_kernel_leaf_mapping(unsigned long start, unsigned long end) return ret; } -static int __init split_to_ptes_pud_entry(pud_t *pudp, unsigned long addr, - unsigned long next, - struct mm_walk *walk) +static int split_to_ptes_pud_entry(pud_t *pudp, unsigned long addr, + unsigned long next, struct mm_walk *walk) { + gfp_t gfp = *(gfp_t *)walk->private; pud_t pud = pudp_get(pudp); int ret = 0; if (pud_leaf(pud)) - ret = split_pud(pudp, pud, GFP_ATOMIC, false); + ret = split_pud(pudp, pud, gfp, false); return ret; } -static int __init split_to_ptes_pmd_entry(pmd_t *pmdp, unsigned long addr, - unsigned long next, - struct mm_walk *walk) +static int split_to_ptes_pmd_entry(pmd_t *pmdp, unsigned long addr, + unsigned long next, struct mm_walk *walk) { + gfp_t gfp = *(gfp_t *)walk->private; pmd_t pmd = pmdp_get(pmdp); int ret = 0; if (pmd_leaf(pmd)) { if (pmd_cont(pmd)) split_contpmd(pmdp); - ret = split_pmd(pmdp, pmd, GFP_ATOMIC, false); + ret = split_pmd(pmdp, pmd, gfp, false); /* * We have split the pmd directly to ptes so there is no need to @@ -793,9 +816,8 @@ static int __init split_to_ptes_pmd_entry(pmd_t *pmdp, unsigned long addr, return ret; } -static int __init split_to_ptes_pte_entry(pte_t *ptep, unsigned long addr, - unsigned long next, - struct mm_walk *walk) +static int split_to_ptes_pte_entry(pte_t *ptep, unsigned long addr, + unsigned long next, struct mm_walk *walk) { pte_t pte = __ptep_get(ptep); @@ -805,12 +827,24 @@ static int __init split_to_ptes_pte_entry(pte_t *ptep, unsigned long addr, return 0; } -static const struct mm_walk_ops split_to_ptes_ops __initconst = { +static const struct mm_walk_ops split_to_ptes_ops = { .pud_entry = split_to_ptes_pud_entry, .pmd_entry = split_to_ptes_pmd_entry, .pte_entry = split_to_ptes_pte_entry, }; +static int range_split_to_ptes(unsigned long start, unsigned long end, gfp_t gfp) +{ + int ret; + + arch_enter_lazy_mmu_mode(); + ret = walk_kernel_page_table_range_lockless(start, end, + &split_to_ptes_ops, NULL, &gfp); + arch_leave_lazy_mmu_mode(); + + return ret; +} + static bool linear_map_requires_bbml2 __initdata; u32 idmap_kpti_bbml2_flag; @@ -847,11 +881,9 @@ static int __init linear_map_split_to_ptes(void *__unused) * PTE. The kernel alias remains static throughout runtime so * can continue to be safely mapped with large mappings. */ - ret = walk_kernel_page_table_range_lockless(lstart, kstart, - &split_to_ptes_ops, NULL, NULL); + ret = range_split_to_ptes(lstart, kstart, GFP_ATOMIC); if (!ret) - ret = walk_kernel_page_table_range_lockless(kend, lend, - &split_to_ptes_ops, NULL, NULL); + ret = range_split_to_ptes(kend, lend, GFP_ATOMIC); if (ret) panic("Failed to split linear map\n"); flush_tlb_kernel_range(lstart, lend); @@ -1002,6 +1034,33 @@ static void __init arm64_kfence_map_pool(phys_addr_t kfence_pool, pgd_t *pgdp) memblock_clear_nomap(kfence_pool, KFENCE_POOL_SIZE); __kfence_pool = phys_to_virt(kfence_pool); } + +bool arch_kfence_init_pool(void) +{ + unsigned long start = (unsigned long)__kfence_pool; + unsigned long end = start + KFENCE_POOL_SIZE; + int ret; + + /* Exit early if we know the linear map is already pte-mapped. */ + if (!split_leaf_mapping_possible()) + return true; + + /* Kfence pool is already pte-mapped for the early init case. */ + if (kfence_early_init) + return true; + + mutex_lock(&pgtable_split_lock); + ret = range_split_to_ptes(start, end, GFP_PGTABLE_KERNEL); + mutex_unlock(&pgtable_split_lock); + + /* + * Since the system supports bbml2_noabort, tlb invalidation is not + * required here; the pgtable mappings have been split to pte but larger + * entries may safely linger in the TLB. + */ + + return !ret; +} #else /* CONFIG_KFENCE */ static inline phys_addr_t arm64_kfence_alloc_pool(void) { return 0; } @@ -1009,16 +1068,6 @@ static inline void arm64_kfence_map_pool(phys_addr_t kfence_pool, pgd_t *pgdp) { #endif /* CONFIG_KFENCE */ -static inline bool force_pte_mapping(void) -{ - bool bbml2 = system_capabilities_finalized() ? - system_supports_bbml2_noabort() : cpu_supports_bbml2_noabort(); - - return (!bbml2 && (rodata_full || arm64_kfence_can_set_direct_map() || - is_realm_world())) || - debug_pagealloc_enabled(); -} - static void __init map_mem(pgd_t *pgdp) { static const u64 direct_map_end = _PAGE_END(VA_BITS_MIN); diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile index dc5bd3f1b8d2..96ca1a688984 100644 --- a/arch/loongarch/Makefile +++ b/arch/loongarch/Makefile @@ -109,7 +109,7 @@ endif ifdef CONFIG_RUSTC_HAS_ANNOTATE_TABLEJUMP KBUILD_RUSTFLAGS += -Cllvm-args=--loongarch-annotate-tablejump else -KBUILD_RUSTFLAGS += -Zno-jump-tables # keep compatibility with older compilers +KBUILD_RUSTFLAGS += $(if $(call rustc-min-version,109300),-Cjump-tables=n,-Zno-jump-tables) # keep compatibility with older compilers endif ifdef CONFIG_LTO_CLANG # The annotate-tablejump option can not be passed to LLVM backend when LTO is enabled. diff --git a/arch/loongarch/include/asm/cpu-features.h b/arch/loongarch/include/asm/cpu-features.h index fc83bb32f9f0..bd5f0457ad21 100644 --- a/arch/loongarch/include/asm/cpu-features.h +++ b/arch/loongarch/include/asm/cpu-features.h @@ -67,6 +67,8 @@ #define cpu_has_hypervisor cpu_opt(LOONGARCH_CPU_HYPERVISOR) #define cpu_has_ptw cpu_opt(LOONGARCH_CPU_PTW) #define cpu_has_lspw cpu_opt(LOONGARCH_CPU_LSPW) +#define cpu_has_msgint cpu_opt(LOONGARCH_CPU_MSGINT) #define cpu_has_avecint cpu_opt(LOONGARCH_CPU_AVECINT) +#define cpu_has_redirectint cpu_opt(LOONGARCH_CPU_REDIRECTINT) #endif /* __ASM_CPU_FEATURES_H */ diff --git a/arch/loongarch/include/asm/cpu.h b/arch/loongarch/include/asm/cpu.h index dfb982fe8701..d4cd4041bee7 100644 --- a/arch/loongarch/include/asm/cpu.h +++ b/arch/loongarch/include/asm/cpu.h @@ -101,7 +101,9 @@ enum cpu_type_enum { #define CPU_FEATURE_HYPERVISOR 26 /* CPU has hypervisor (running in VM) */ #define CPU_FEATURE_PTW 27 /* CPU has hardware page table walker */ #define CPU_FEATURE_LSPW 28 /* CPU has LSPW (lddir/ldpte instructions) */ -#define CPU_FEATURE_AVECINT 29 /* CPU has AVEC interrupt */ +#define CPU_FEATURE_MSGINT 29 /* CPU has MSG interrupt */ +#define CPU_FEATURE_AVECINT 30 /* CPU has AVEC interrupt */ +#define CPU_FEATURE_REDIRECTINT 31 /* CPU has interrupt remapping */ #define LOONGARCH_CPU_CPUCFG BIT_ULL(CPU_FEATURE_CPUCFG) #define LOONGARCH_CPU_LAM BIT_ULL(CPU_FEATURE_LAM) @@ -132,6 +134,8 @@ enum cpu_type_enum { #define LOONGARCH_CPU_HYPERVISOR BIT_ULL(CPU_FEATURE_HYPERVISOR) #define LOONGARCH_CPU_PTW BIT_ULL(CPU_FEATURE_PTW) #define LOONGARCH_CPU_LSPW BIT_ULL(CPU_FEATURE_LSPW) +#define LOONGARCH_CPU_MSGINT BIT_ULL(CPU_FEATURE_MSGINT) #define LOONGARCH_CPU_AVECINT BIT_ULL(CPU_FEATURE_AVECINT) +#define LOONGARCH_CPU_REDIRECTINT BIT_ULL(CPU_FEATURE_REDIRECTINT) #endif /* _ASM_CPU_H */ diff --git a/arch/loongarch/include/asm/hw_breakpoint.h b/arch/loongarch/include/asm/hw_breakpoint.h index 13b2462f3d8c..5faa97a87a9e 100644 --- a/arch/loongarch/include/asm/hw_breakpoint.h +++ b/arch/loongarch/include/asm/hw_breakpoint.h @@ -134,13 +134,13 @@ static inline void hw_breakpoint_thread_switch(struct task_struct *next) /* Determine number of BRP registers available. */ static inline int get_num_brps(void) { - return csr_read64(LOONGARCH_CSR_FWPC) & CSR_FWPC_NUM; + return csr_read32(LOONGARCH_CSR_FWPC) & CSR_FWPC_NUM; } /* Determine number of WRP registers available. */ static inline int get_num_wrps(void) { - return csr_read64(LOONGARCH_CSR_MWPC) & CSR_MWPC_NUM; + return csr_read32(LOONGARCH_CSR_MWPC) & CSR_MWPC_NUM; } #endif /* __KERNEL__ */ diff --git a/arch/loongarch/include/asm/io.h b/arch/loongarch/include/asm/io.h index eaff72b38dc8..0130185e0349 100644 --- a/arch/loongarch/include/asm/io.h +++ b/arch/loongarch/include/asm/io.h @@ -14,7 +14,7 @@ #include <asm/pgtable-bits.h> #include <asm/string.h> -extern void __init __iomem *early_ioremap(u64 phys_addr, unsigned long size); +extern void __init __iomem *early_ioremap(phys_addr_t phys_addr, unsigned long size); extern void __init early_iounmap(void __iomem *addr, unsigned long size); #define early_memremap early_ioremap @@ -25,6 +25,9 @@ extern void __init early_iounmap(void __iomem *addr, unsigned long size); static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size, pgprot_t prot) { + if (offset > TO_PHYS_MASK) + return NULL; + switch (pgprot_val(prot) & _CACHE_MASK) { case _CACHE_CC: return (void __iomem *)(unsigned long)(CACHE_BASE + offset); diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h index 09dfd7eb406e..3de03cb864b2 100644 --- a/arch/loongarch/include/asm/loongarch.h +++ b/arch/loongarch/include/asm/loongarch.h @@ -128,6 +128,7 @@ #define CPUCFG6_PMNUM GENMASK(7, 4) #define CPUCFG6_PMNUM_SHIFT 4 #define CPUCFG6_PMBITS GENMASK(13, 8) +#define CPUCFG6_PMBITS_SHIFT 8 #define CPUCFG6_UPM BIT(14) #define LOONGARCH_CPUCFG16 0x10 @@ -1137,6 +1138,7 @@ #define IOCSRF_FLATMODE BIT_ULL(10) #define IOCSRF_VM BIT_ULL(11) #define IOCSRF_AVEC BIT_ULL(15) +#define IOCSRF_REDIRECT BIT_ULL(16) #define LOONGARCH_IOCSR_VENDOR 0x10 diff --git a/arch/loongarch/include/asm/pgalloc.h b/arch/loongarch/include/asm/pgalloc.h index 1c63a9d9a6d3..08dcc698ec18 100644 --- a/arch/loongarch/include/asm/pgalloc.h +++ b/arch/loongarch/include/asm/pgalloc.h @@ -88,7 +88,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address) static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) { pud_t *pud; - struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL & ~__GFP_HIGHMEM, 0); + struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL, 0); if (!ptdesc) return NULL; diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h index bd128696e96d..03fb60432fde 100644 --- a/arch/loongarch/include/asm/pgtable.h +++ b/arch/loongarch/include/asm/pgtable.h @@ -424,6 +424,9 @@ static inline unsigned long pte_accessible(struct mm_struct *mm, pte_t a) static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { + if (pte_val(pte) & _PAGE_DIRTY) + pte_val(pte) |= _PAGE_MODIFIED; + return __pte((pte_val(pte) & _PAGE_CHG_MASK) | (pgprot_val(newprot) & ~_PAGE_CHG_MASK)); } @@ -547,9 +550,11 @@ static inline struct page *pmd_page(pmd_t pmd) static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) { - pmd_val(pmd) = (pmd_val(pmd) & _HPAGE_CHG_MASK) | - (pgprot_val(newprot) & ~_HPAGE_CHG_MASK); - return pmd; + if (pmd_val(pmd) & _PAGE_DIRTY) + pmd_val(pmd) |= _PAGE_MODIFIED; + + return __pmd((pmd_val(pmd) & _HPAGE_CHG_MASK) | + (pgprot_val(newprot) & ~_HPAGE_CHG_MASK)); } static inline pmd_t pmd_mkinvalid(pmd_t pmd) diff --git a/arch/loongarch/kernel/cpu-probe.c b/arch/loongarch/kernel/cpu-probe.c index cbfce2872d71..6f943d1391ff 100644 --- a/arch/loongarch/kernel/cpu-probe.c +++ b/arch/loongarch/kernel/cpu-probe.c @@ -157,6 +157,8 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c) c->options |= LOONGARCH_CPU_TLB; if (config & CPUCFG1_IOCSR) c->options |= LOONGARCH_CPU_IOCSR; + if (config & CPUCFG1_MSGINT) + c->options |= LOONGARCH_CPU_MSGINT; if (config & CPUCFG1_UAL) { c->options |= LOONGARCH_CPU_UAL; elf_hwcap |= HWCAP_LOONGARCH_UAL; @@ -331,6 +333,8 @@ static inline void cpu_probe_loongson(struct cpuinfo_loongarch *c, unsigned int c->options |= LOONGARCH_CPU_EIODECODE; if (config & IOCSRF_AVEC) c->options |= LOONGARCH_CPU_AVECINT; + if (config & IOCSRF_REDIRECT) + c->options |= LOONGARCH_CPU_REDIRECTINT; if (config & IOCSRF_VM) c->options |= LOONGARCH_CPU_HYPERVISOR; } diff --git a/arch/loongarch/kernel/kexec_efi.c b/arch/loongarch/kernel/kexec_efi.c index 45121b914f8f..5ee78ebb1546 100644 --- a/arch/loongarch/kernel/kexec_efi.c +++ b/arch/loongarch/kernel/kexec_efi.c @@ -42,7 +42,7 @@ static void *efi_kexec_load(struct kimage *image, { int ret; unsigned long text_offset, kernel_segment_number; - struct kexec_buf kbuf; + struct kexec_buf kbuf = {}; struct kexec_segment *kernel_segment; struct loongarch_image_header *h; diff --git a/arch/loongarch/kernel/kexec_elf.c b/arch/loongarch/kernel/kexec_elf.c index 97b2f049801a..1b6b64744c7f 100644 --- a/arch/loongarch/kernel/kexec_elf.c +++ b/arch/loongarch/kernel/kexec_elf.c @@ -59,7 +59,7 @@ static void *elf_kexec_load(struct kimage *image, int ret; unsigned long text_offset, kernel_segment_number; struct elfhdr ehdr; - struct kexec_buf kbuf; + struct kexec_buf kbuf = {}; struct kexec_elf_info elf_info; struct kexec_segment *kernel_segment; diff --git a/arch/loongarch/kernel/machine_kexec.c b/arch/loongarch/kernel/machine_kexec.c index e4b2bbc47e62..2d64b7c81e5e 100644 --- a/arch/loongarch/kernel/machine_kexec.c +++ b/arch/loongarch/kernel/machine_kexec.c @@ -39,34 +39,12 @@ static unsigned long systable_ptr; static unsigned long start_addr; static unsigned long first_ind_entry; -static void kexec_image_info(const struct kimage *kimage) -{ - unsigned long i; - - pr_debug("kexec kimage info:\n"); - pr_debug("\ttype: %d\n", kimage->type); - pr_debug("\tstart: %lx\n", kimage->start); - pr_debug("\thead: %lx\n", kimage->head); - pr_debug("\tnr_segments: %lu\n", kimage->nr_segments); - - for (i = 0; i < kimage->nr_segments; i++) { - pr_debug("\t segment[%lu]: %016lx - %016lx", i, - kimage->segment[i].mem, - kimage->segment[i].mem + kimage->segment[i].memsz); - pr_debug("\t\t0x%lx bytes, %lu pages\n", - (unsigned long)kimage->segment[i].memsz, - (unsigned long)kimage->segment[i].memsz / PAGE_SIZE); - } -} - int machine_kexec_prepare(struct kimage *kimage) { int i; char *bootloader = "kexec"; void *cmdline_ptr = (void *)KEXEC_CMDLINE_ADDR; - kexec_image_info(kimage); - kimage->arch.efi_boot = fw_arg0; kimage->arch.systable_ptr = fw_arg2; diff --git a/arch/loongarch/kernel/machine_kexec_file.c b/arch/loongarch/kernel/machine_kexec_file.c index dda236b51a88..fb57026f5f25 100644 --- a/arch/loongarch/kernel/machine_kexec_file.c +++ b/arch/loongarch/kernel/machine_kexec_file.c @@ -143,7 +143,7 @@ int load_other_segments(struct kimage *image, unsigned long initrd_load_addr = 0; unsigned long orig_segments = image->nr_segments; char *modified_cmdline = NULL; - struct kexec_buf kbuf; + struct kexec_buf kbuf = {}; kbuf.image = image; /* Don't allocate anything below the kernel */ diff --git a/arch/loongarch/kernel/mem.c b/arch/loongarch/kernel/mem.c index aed901c57fb4..8ab1ffedc52c 100644 --- a/arch/loongarch/kernel/mem.c +++ b/arch/loongarch/kernel/mem.c @@ -13,7 +13,7 @@ void __init memblock_init(void) { u32 mem_type; - u64 mem_start, mem_end, mem_size; + u64 mem_start, mem_size; efi_memory_desc_t *md; /* Parse memory information */ @@ -21,7 +21,6 @@ void __init memblock_init(void) mem_type = md->type; mem_start = md->phys_addr; mem_size = md->num_pages << EFI_PAGE_SHIFT; - mem_end = mem_start + mem_size; switch (mem_type) { case EFI_LOADER_CODE: @@ -31,8 +30,6 @@ void __init memblock_init(void) case EFI_PERSISTENT_MEMORY: case EFI_CONVENTIONAL_MEMORY: memblock_add(mem_start, mem_size); - if (max_low_pfn < (mem_end >> PAGE_SHIFT)) - max_low_pfn = mem_end >> PAGE_SHIFT; break; case EFI_PAL_CODE: case EFI_UNUSABLE_MEMORY: @@ -49,6 +46,8 @@ void __init memblock_init(void) } } + max_pfn = PFN_DOWN(memblock_end_of_DRAM()); + max_low_pfn = min(PFN_DOWN(HIGHMEM_START), max_pfn); memblock_set_current_limit(PFN_PHYS(max_low_pfn)); /* Reserve the first 2MB */ diff --git a/arch/loongarch/kernel/numa.c b/arch/loongarch/kernel/numa.c index d6e73e8f9c0b..ab9c660526a3 100644 --- a/arch/loongarch/kernel/numa.c +++ b/arch/loongarch/kernel/numa.c @@ -272,7 +272,8 @@ int __init init_numa_memory(void) node_mem_init(node); node_set_online(node); } - max_low_pfn = PHYS_PFN(memblock_end_of_DRAM()); + max_pfn = PFN_DOWN(memblock_end_of_DRAM()); + max_low_pfn = min(PFN_DOWN(HIGHMEM_START), max_pfn); setup_nr_node_ids(); loongson_sysconf.nr_nodes = nr_node_ids; @@ -283,26 +284,6 @@ int __init init_numa_memory(void) #endif -void __init paging_init(void) -{ - unsigned int node; - unsigned long zones_size[MAX_NR_ZONES] = {0, }; - - for_each_online_node(node) { - unsigned long start_pfn, end_pfn; - - get_pfn_range_for_nid(node, &start_pfn, &end_pfn); - - if (end_pfn > max_low_pfn) - max_low_pfn = end_pfn; - } -#ifdef CONFIG_ZONE_DMA32 - zones_size[ZONE_DMA32] = MAX_DMA32_PFN; -#endif - zones_size[ZONE_NORMAL] = max_low_pfn; - free_area_init(zones_size); -} - int pcibus_to_node(struct pci_bus *bus) { return dev_to_node(&bus->dev); diff --git a/arch/loongarch/kernel/perf_event.c b/arch/loongarch/kernel/perf_event.c index 8ad098703488..9d257c8519c9 100644 --- a/arch/loongarch/kernel/perf_event.c +++ b/arch/loongarch/kernel/perf_event.c @@ -845,13 +845,14 @@ static const struct loongarch_perf_event *loongarch_pmu_map_raw_event(u64 config static int __init init_hw_perf_events(void) { - int counters; + int bits, counters; if (!cpu_has_pmp) return -ENODEV; pr_info("Performance counters: "); - counters = ((read_cpucfg(LOONGARCH_CPUCFG6) & CPUCFG6_PMNUM) >> 4) + 1; + bits = ((read_cpucfg(LOONGARCH_CPUCFG6) & CPUCFG6_PMBITS) >> CPUCFG6_PMBITS_SHIFT) + 1; + counters = ((read_cpucfg(LOONGARCH_CPUCFG6) & CPUCFG6_PMNUM) >> CPUCFG6_PMNUM_SHIFT) + 1; loongarch_pmu.num_counters = counters; loongarch_pmu.max_period = (1ULL << 63) - 1; @@ -867,7 +868,7 @@ static int __init init_hw_perf_events(void) on_each_cpu(reset_counters, NULL, 1); pr_cont("%s PMU enabled, %d %d-bit counters available to each CPU.\n", - loongarch_pmu.name, counters, 64); + loongarch_pmu.name, counters, bits); perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW); diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index 69c17d162fff..25a87378e48e 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -294,8 +294,6 @@ static void __init fdt_setup(void) early_init_dt_scan(fdt_pointer, __pa(fdt_pointer)); early_init_fdt_reserve_self(); - - max_low_pfn = PFN_PHYS(memblock_end_of_DRAM()); #endif } @@ -390,7 +388,8 @@ static void __init check_kernel_sections_mem(void) static void __init arch_mem_init(char **cmdline_p) { /* Recalculate max_low_pfn for "mem=xxx" */ - max_pfn = max_low_pfn = PHYS_PFN(memblock_end_of_DRAM()); + max_pfn = PFN_DOWN(memblock_end_of_DRAM()); + max_low_pfn = min(PFN_DOWN(HIGHMEM_START), max_pfn); if (usermem) pr_info("User-defined physical RAM map overwrite\n"); diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c index 3d9be6ca7ec5..da5926fead4a 100644 --- a/arch/loongarch/kernel/traps.c +++ b/arch/loongarch/kernel/traps.c @@ -1131,8 +1131,8 @@ static void configure_exception_vector(void) tlbrentry = (unsigned long)exception_handlers + 80*VECSIZE; csr_write64(eentry, LOONGARCH_CSR_EENTRY); - csr_write64(eentry, LOONGARCH_CSR_MERRENTRY); - csr_write64(tlbrentry, LOONGARCH_CSR_TLBRENTRY); + csr_write64(__pa(eentry), LOONGARCH_CSR_MERRENTRY); + csr_write64(__pa(tlbrentry), LOONGARCH_CSR_TLBRENTRY); } void per_cpu_trap_init(int cpu) diff --git a/arch/loongarch/kvm/intc/eiointc.c b/arch/loongarch/kvm/intc/eiointc.c index c32333695381..a1cc116b4dac 100644 --- a/arch/loongarch/kvm/intc/eiointc.c +++ b/arch/loongarch/kvm/intc/eiointc.c @@ -439,7 +439,7 @@ static int kvm_eiointc_ctrl_access(struct kvm_device *dev, spin_lock_irqsave(&s->lock, flags); switch (type) { case KVM_DEV_LOONGARCH_EXTIOI_CTRL_INIT_NUM_CPU: - if (val >= EIOINTC_ROUTE_MAX_VCPUS) + if (val > EIOINTC_ROUTE_MAX_VCPUS) ret = -EINVAL; else s->num_cpu = val; diff --git a/arch/loongarch/kvm/mmu.c b/arch/loongarch/kvm/mmu.c index 7c8143e79c12..a7fa458e3360 100644 --- a/arch/loongarch/kvm/mmu.c +++ b/arch/loongarch/kvm/mmu.c @@ -857,7 +857,7 @@ retry: if (writeable) { prot_bits = kvm_pte_mkwriteable(prot_bits); - if (write) + if (write || !kvm_slot_dirty_track_enabled(memslot)) prot_bits = kvm_pte_mkdirty(prot_bits); } diff --git a/arch/loongarch/kvm/timer.c b/arch/loongarch/kvm/timer.c index 32dc213374be..29c2aaba63c3 100644 --- a/arch/loongarch/kvm/timer.c +++ b/arch/loongarch/kvm/timer.c @@ -4,6 +4,7 @@ */ #include <linux/kvm_host.h> +#include <asm/delay.h> #include <asm/kvm_csr.h> #include <asm/kvm_vcpu.h> @@ -95,6 +96,7 @@ void kvm_restore_timer(struct kvm_vcpu *vcpu) * and set CSR TVAL with -1 */ write_gcsr_timertick(0); + __delay(2); /* Wait cycles until timer interrupt injected */ /* * Writing CSR_TINTCLR_TI to LOONGARCH_CSR_TINTCLR will clear diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c index 30e3b089a596..1245a6b35896 100644 --- a/arch/loongarch/kvm/vcpu.c +++ b/arch/loongarch/kvm/vcpu.c @@ -132,6 +132,9 @@ static void kvm_lose_pmu(struct kvm_vcpu *vcpu) * Clear KVM_LARCH_PMU if the guest is not using PMU CSRs when * exiting the guest, so that the next time trap into the guest. * We don't need to deal with PMU CSRs contexts. + * + * Otherwise set the request bit KVM_REQ_PMU to restore guest PMU + * before entering guest VM */ val = kvm_read_sw_gcsr(csr, LOONGARCH_CSR_PERFCTRL0); val |= kvm_read_sw_gcsr(csr, LOONGARCH_CSR_PERFCTRL1); @@ -139,16 +142,12 @@ static void kvm_lose_pmu(struct kvm_vcpu *vcpu) val |= kvm_read_sw_gcsr(csr, LOONGARCH_CSR_PERFCTRL3); if (!(val & KVM_PMU_EVENT_ENABLED)) vcpu->arch.aux_inuse &= ~KVM_LARCH_PMU; + else + kvm_make_request(KVM_REQ_PMU, vcpu); kvm_restore_host_pmu(vcpu); } -static void kvm_restore_pmu(struct kvm_vcpu *vcpu) -{ - if ((vcpu->arch.aux_inuse & KVM_LARCH_PMU)) - kvm_make_request(KVM_REQ_PMU, vcpu); -} - static void kvm_check_pmu(struct kvm_vcpu *vcpu) { if (kvm_check_request(KVM_REQ_PMU, vcpu)) { @@ -299,7 +298,10 @@ static int kvm_pre_enter_guest(struct kvm_vcpu *vcpu) vcpu->arch.aux_inuse &= ~KVM_LARCH_SWCSR_LATEST; if (kvm_request_pending(vcpu) || xfer_to_guest_mode_work_pending()) { - kvm_lose_pmu(vcpu); + if (vcpu->arch.aux_inuse & KVM_LARCH_PMU) { + kvm_lose_pmu(vcpu); + kvm_make_request(KVM_REQ_PMU, vcpu); + } /* make sure the vcpu mode has been written */ smp_store_mb(vcpu->mode, OUTSIDE_GUEST_MODE); local_irq_enable(); @@ -1604,9 +1606,6 @@ static int _kvm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_restore_timer(vcpu); kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); - /* Restore hardware PMU CSRs */ - kvm_restore_pmu(vcpu); - /* Don't bother restoring registers multiple times unless necessary */ if (vcpu->arch.aux_inuse & KVM_LARCH_HWCSR_USABLE) return 0; diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c index c3e4586a7975..6bfd4b8dad1b 100644 --- a/arch/loongarch/mm/init.c +++ b/arch/loongarch/mm/init.c @@ -60,7 +60,6 @@ int __ref page_is_ram(unsigned long pfn) return memblock_is_memory(addr) && !memblock_is_reserved(addr); } -#ifndef CONFIG_NUMA void __init paging_init(void) { unsigned long max_zone_pfns[MAX_NR_ZONES]; @@ -72,7 +71,6 @@ void __init paging_init(void) free_area_init(max_zone_pfns); } -#endif /* !CONFIG_NUMA */ void __ref free_initmem(void) { diff --git a/arch/loongarch/mm/ioremap.c b/arch/loongarch/mm/ioremap.c index df949a3d0f34..27c336959fe8 100644 --- a/arch/loongarch/mm/ioremap.c +++ b/arch/loongarch/mm/ioremap.c @@ -6,7 +6,7 @@ #include <asm/io.h> #include <asm-generic/early_ioremap.h> -void __init __iomem *early_ioremap(u64 phys_addr, unsigned long size) +void __init __iomem *early_ioremap(phys_addr_t phys_addr, unsigned long size) { return ((void __iomem *)TO_CACHE(phys_addr)); } diff --git a/arch/parisc/kernel/unwind.c b/arch/parisc/kernel/unwind.c index f7e0fee5ee55..7ac88ff13d3c 100644 --- a/arch/parisc/kernel/unwind.c +++ b/arch/parisc/kernel/unwind.c @@ -35,6 +35,8 @@ #define KERNEL_START (KERNEL_BINARY_TEXT_START) +#define ALIGNMENT_OK(ptr, type) (((ptr) & (sizeof(type) - 1)) == 0) + extern struct unwind_table_entry __start___unwind[]; extern struct unwind_table_entry __stop___unwind[]; @@ -257,12 +259,15 @@ static int unwind_special(struct unwind_frame_info *info, unsigned long pc, int if (pc_is_kernel_fn(pc, _switch_to) || pc == (unsigned long)&_switch_to_ret) { info->prev_sp = info->sp - CALLEE_SAVE_FRAME_SIZE; - info->prev_ip = *(unsigned long *)(info->prev_sp - RP_OFFSET); + if (ALIGNMENT_OK(info->prev_sp, long)) + info->prev_ip = *(unsigned long *)(info->prev_sp - RP_OFFSET); + else + info->prev_ip = info->prev_sp = 0; return 1; } #ifdef CONFIG_IRQSTACKS - if (pc == (unsigned long)&_call_on_stack) { + if (pc == (unsigned long)&_call_on_stack && ALIGNMENT_OK(info->sp, long)) { info->prev_sp = *(unsigned long *)(info->sp - FRAME_SIZE - REG_SZ); info->prev_ip = *(unsigned long *)(info->sp - FRAME_SIZE - RP_OFFSET); return 1; @@ -370,8 +375,10 @@ static void unwind_frame_regs(struct unwind_frame_info *info) info->prev_sp = info->sp - frame_size; if (e->Millicode) info->rp = info->r31; - else if (rpoffset) + else if (rpoffset && ALIGNMENT_OK(info->prev_sp, long)) info->rp = *(unsigned long *)(info->prev_sp - rpoffset); + else + info->rp = 0; info->prev_ip = info->rp; info->rp = 0; } diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 22cda9c452d2..fadec20b87a8 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -367,7 +367,7 @@ config RISCV_NONSTANDARD_CACHE_OPS systems to handle cache management. config AS_HAS_INSN - def_bool $(as-instr,.insn r 51$(comma) 0$(comma) 0$(comma) t0$(comma) t0$(comma) zero) + def_bool $(as-instr,.insn 0x100000f) config AS_HAS_OPTION_ARCH # https://github.com/llvm/llvm-project/commit/9e8ed3403c191ab9c4903e8eeb8f732ff8a43cb4 diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index ecf2fcce2d92..4c6de57f65ef 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -134,21 +134,6 @@ endif CHECKFLAGS += -D__riscv -D__riscv_xlen=$(BITS) # Default target when executing plain make -boot := arch/riscv/boot -ifeq ($(CONFIG_XIP_KERNEL),y) -KBUILD_IMAGE := $(boot)/xipImage -else -ifeq ($(CONFIG_RISCV_M_MODE)$(CONFIG_SOC_CANAAN_K210),yy) -KBUILD_IMAGE := $(boot)/loader.bin -else -ifeq ($(CONFIG_EFI_ZBOOT),) -KBUILD_IMAGE := $(boot)/Image.gz -else -KBUILD_IMAGE := $(boot)/vmlinuz.efi -endif -endif -endif - boot := arch/riscv/boot boot-image-y := Image boot-image-$(CONFIG_KERNEL_BZIP2) := Image.bz2 @@ -159,7 +144,7 @@ boot-image-$(CONFIG_KERNEL_LZO) := Image.lzo boot-image-$(CONFIG_KERNEL_ZSTD) := Image.zst boot-image-$(CONFIG_KERNEL_XZ) := Image.xz ifdef CONFIG_RISCV_M_MODE -boot-image-$(CONFIG_ARCH_CANAAN) := loader.bin +boot-image-$(CONFIG_SOC_CANAAN_K210) := loader.bin endif boot-image-$(CONFIG_EFI_ZBOOT) := vmlinuz.efi boot-image-$(CONFIG_XIP_KERNEL) := xipImage diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h index ac28066bb564..e9e8ba83e632 100644 --- a/arch/riscv/include/asm/asm.h +++ b/arch/riscv/include/asm/asm.h @@ -12,6 +12,12 @@ #define __ASM_STR(x) #x #endif +#ifdef CONFIG_AS_HAS_INSN +#define ASM_INSN_I(__x) ".insn " __x +#else +#define ASM_INSN_I(__x) ".4byte " __x +#endif + #if __riscv_xlen == 64 #define __REG_SEL(a, b) __ASM_STR(a) #elif __riscv_xlen == 32 diff --git a/arch/riscv/include/asm/insn-def.h b/arch/riscv/include/asm/insn-def.h index c9cfcea52cbb..d29da6ccd3dd 100644 --- a/arch/riscv/include/asm/insn-def.h +++ b/arch/riscv/include/asm/insn-def.h @@ -256,10 +256,10 @@ INSN_S(OPCODE_OP_IMM, FUNC3(6), __RS2(3), \ SIMM12((offset) & 0xfe0), RS1(base)) -#define RISCV_PAUSE ".4byte 0x100000f" -#define ZAWRS_WRS_NTO ".4byte 0x00d00073" -#define ZAWRS_WRS_STO ".4byte 0x01d00073" -#define RISCV_NOP4 ".4byte 0x00000013" +#define RISCV_PAUSE ASM_INSN_I("0x100000f") +#define ZAWRS_WRS_NTO ASM_INSN_I("0x00d00073") +#define ZAWRS_WRS_STO ASM_INSN_I("0x01d00073") +#define RISCV_NOP4 ASM_INSN_I("0x00000013") #define RISCV_INSN_NOP4 _AC(0x00000013, U) diff --git a/arch/riscv/include/asm/vendor_extensions/mips.h b/arch/riscv/include/asm/vendor_extensions/mips.h index ea8ca747d691..ffeb12dc17a3 100644 --- a/arch/riscv/include/asm/vendor_extensions/mips.h +++ b/arch/riscv/include/asm/vendor_extensions/mips.h @@ -30,8 +30,8 @@ extern struct riscv_isa_vendor_ext_data_list riscv_isa_vendor_ext_list_mips; * allowing any subsequent instructions to fetch. */ -#define MIPS_PAUSE ".4byte 0x00501013\n\t" -#define MIPS_EHB ".4byte 0x00301013\n\t" -#define MIPS_IHB ".4byte 0x00101013\n\t" +#define MIPS_PAUSE ASM_INSN_I("0x00501013\n\t") +#define MIPS_EHB ASM_INSN_I("0x00301013\n\t") +#define MIPS_IHB ASM_INSN_I("0x00101013\n\t") #endif // _ASM_RISCV_VENDOR_EXTENSIONS_MIPS_H diff --git a/arch/riscv/kernel/kgdb.c b/arch/riscv/kernel/kgdb.c index 9f3db3503dab..15fec5d1e6de 100644 --- a/arch/riscv/kernel/kgdb.c +++ b/arch/riscv/kernel/kgdb.c @@ -265,10 +265,10 @@ void kgdb_arch_handle_qxfer_pkt(char *remcom_in_buffer, { if (!strncmp(remcom_in_buffer, gdb_xfer_read_target, sizeof(gdb_xfer_read_target))) - strcpy(remcom_out_buffer, riscv_gdb_stub_target_desc); + strscpy(remcom_out_buffer, riscv_gdb_stub_target_desc, BUFMAX); else if (!strncmp(remcom_in_buffer, gdb_xfer_read_cpuxml, sizeof(gdb_xfer_read_cpuxml))) - strcpy(remcom_out_buffer, riscv_gdb_stub_cpuxml); + strscpy(remcom_out_buffer, riscv_gdb_stub_cpuxml, BUFMAX); } static inline void kgdb_arch_update_addr(struct pt_regs *regs, diff --git a/arch/riscv/kernel/module-sections.c b/arch/riscv/kernel/module-sections.c index 75551ac6504c..1675cbad8619 100644 --- a/arch/riscv/kernel/module-sections.c +++ b/arch/riscv/kernel/module-sections.c @@ -119,6 +119,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, unsigned int num_plts = 0; unsigned int num_gots = 0; Elf_Rela *scratch = NULL; + Elf_Rela *new_scratch; size_t scratch_size = 0; int i; @@ -168,9 +169,12 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, scratch_size_needed = (num_scratch_relas + num_relas) * sizeof(*scratch); if (scratch_size_needed > scratch_size) { scratch_size = scratch_size_needed; - scratch = kvrealloc(scratch, scratch_size, GFP_KERNEL); - if (!scratch) + new_scratch = kvrealloc(scratch, scratch_size, GFP_KERNEL); + if (!new_scratch) { + kvfree(scratch); return -ENOMEM; + } + scratch = new_scratch; } for (size_t j = 0; j < num_relas; j++) diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 3fe9e6edef8f..b41b6255751c 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -16,6 +16,22 @@ #ifdef CONFIG_FRAME_POINTER +/* + * This disables KASAN checking when reading a value from another task's stack, + * since the other task could be running on another CPU and could have poisoned + * the stack in the meantime. + */ +#define READ_ONCE_TASK_STACK(task, x) \ +({ \ + unsigned long val; \ + unsigned long addr = x; \ + if ((task) == current) \ + val = READ_ONCE(addr); \ + else \ + val = READ_ONCE_NOCHECK(addr); \ + val; \ +}) + extern asmlinkage void handle_exception(void); extern unsigned long ret_from_exception_end; @@ -69,8 +85,9 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, fp = frame->ra; pc = regs->ra; } else { - fp = frame->fp; - pc = ftrace_graph_ret_addr(current, &graph_idx, frame->ra, + fp = READ_ONCE_TASK_STACK(task, frame->fp); + pc = READ_ONCE_TASK_STACK(task, frame->ra); + pc = ftrace_graph_ret_addr(current, &graph_idx, pc, &frame->ra); if (pc >= (unsigned long)handle_exception && pc < (unsigned long)&ret_from_exception_end) { diff --git a/arch/riscv/kernel/tests/Kconfig.debug b/arch/riscv/kernel/tests/Kconfig.debug index 5db4df44279e..40f8dafffa0a 100644 --- a/arch/riscv/kernel/tests/Kconfig.debug +++ b/arch/riscv/kernel/tests/Kconfig.debug @@ -31,7 +31,7 @@ config RISCV_MODULE_LINKING_KUNIT If unsure, say N. config RISCV_KPROBES_KUNIT - bool "KUnit test for riscv kprobes" if !KUNIT_ALL_TESTS + tristate "KUnit test for riscv kprobes" if !KUNIT_ALL_TESTS depends on KUNIT depends on KPROBES default KUNIT_ALL_TESTS diff --git a/arch/riscv/kernel/tests/kprobes/Makefile b/arch/riscv/kernel/tests/kprobes/Makefile index 4cb6c66a98e8..df7256f62313 100644 --- a/arch/riscv/kernel/tests/kprobes/Makefile +++ b/arch/riscv/kernel/tests/kprobes/Makefile @@ -1 +1,3 @@ -obj-y += test-kprobes.o test-kprobes-asm.o +obj-$(CONFIG_RISCV_KPROBES_KUNIT) += kprobes_riscv_kunit.o + +kprobes_riscv_kunit-objs := test-kprobes.o test-kprobes-asm.o diff --git a/arch/riscv/kernel/tests/kprobes/test-kprobes.c b/arch/riscv/kernel/tests/kprobes/test-kprobes.c index 6f6cdfbf5a95..664535ca0a98 100644 --- a/arch/riscv/kernel/tests/kprobes/test-kprobes.c +++ b/arch/riscv/kernel/tests/kprobes/test-kprobes.c @@ -49,8 +49,11 @@ static struct kunit_case kprobes_testcases[] = { }; static struct kunit_suite kprobes_test_suite = { - .name = "kprobes_test_riscv", + .name = "kprobes_riscv", .test_cases = kprobes_testcases, }; kunit_test_suites(&kprobes_test_suite); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("KUnit test for riscv kprobes"); diff --git a/arch/riscv/kvm/aia_imsic.c b/arch/riscv/kvm/aia_imsic.c index fda0346f0ea1..11422cb95a64 100644 --- a/arch/riscv/kvm/aia_imsic.c +++ b/arch/riscv/kvm/aia_imsic.c @@ -689,8 +689,20 @@ bool kvm_riscv_vcpu_aia_imsic_has_interrupt(struct kvm_vcpu *vcpu) */ read_lock_irqsave(&imsic->vsfile_lock, flags); - if (imsic->vsfile_cpu > -1) - ret = !!(csr_read(CSR_HGEIP) & BIT(imsic->vsfile_hgei)); + if (imsic->vsfile_cpu > -1) { + /* + * This function is typically called from kvm_vcpu_block() via + * kvm_arch_vcpu_runnable() upon WFI trap. The kvm_vcpu_block() + * can be preempted and the blocking VCPU might resume on a + * different CPU. This means it is possible that current CPU + * does not match the imsic->vsfile_cpu hence this function + * must check imsic->vsfile_cpu before accessing HGEIP CSR. + */ + if (imsic->vsfile_cpu != vcpu->cpu) + ret = true; + else + ret = !!(csr_read(CSR_HGEIP) & BIT(imsic->vsfile_hgei)); + } read_unlock_irqrestore(&imsic->vsfile_lock, flags); return ret; diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c index 525fb5a330c0..58f5f3536ffd 100644 --- a/arch/riscv/kvm/mmu.c +++ b/arch/riscv/kvm/mmu.c @@ -171,7 +171,6 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, enum kvm_mr_change change) { hva_t hva, reg_end, size; - gpa_t base_gpa; bool writable; int ret = 0; @@ -190,15 +189,13 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, hva = new->userspace_addr; size = new->npages << PAGE_SHIFT; reg_end = hva + size; - base_gpa = new->base_gfn << PAGE_SHIFT; writable = !(new->flags & KVM_MEM_READONLY); mmap_read_lock(current->mm); /* * A memory region could potentially cover multiple VMAs, and - * any holes between them, so iterate over all of them to find - * out if we can map any of them right now. + * any holes between them, so iterate over all of them. * * +--------------------------------------------+ * +---------------+----------------+ +----------------+ @@ -209,7 +206,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, */ do { struct vm_area_struct *vma; - hva_t vm_start, vm_end; + hva_t vm_end; vma = find_vma_intersection(current->mm, hva, reg_end); if (!vma) @@ -225,36 +222,18 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, } /* Take the intersection of this VMA with the memory region */ - vm_start = max(hva, vma->vm_start); vm_end = min(reg_end, vma->vm_end); if (vma->vm_flags & VM_PFNMAP) { - gpa_t gpa = base_gpa + (vm_start - hva); - phys_addr_t pa; - - pa = (phys_addr_t)vma->vm_pgoff << PAGE_SHIFT; - pa += vm_start - vma->vm_start; - /* IO region dirty page logging not allowed */ if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) { ret = -EINVAL; goto out; } - - ret = kvm_riscv_mmu_ioremap(kvm, gpa, pa, vm_end - vm_start, - writable, false); - if (ret) - break; } hva = vm_end; } while (hva < reg_end); - if (change == KVM_MR_FLAGS_ONLY) - goto out; - - if (ret) - kvm_riscv_mmu_iounmap(kvm, base_gpa, size); - out: mmap_read_unlock(current->mm); return ret; diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index bccb919ca615..5ce35aba6069 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -212,7 +212,7 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) { - return (kvm_riscv_vcpu_has_interrupts(vcpu, -1UL) && + return (kvm_riscv_vcpu_has_interrupts(vcpu, -1ULL) && !kvm_riscv_vcpu_stopped(vcpu) && !vcpu->arch.pause); } diff --git a/arch/riscv/mm/ptdump.c b/arch/riscv/mm/ptdump.c index 3b51690cc876..34299c2b231f 100644 --- a/arch/riscv/mm/ptdump.c +++ b/arch/riscv/mm/ptdump.c @@ -21,7 +21,7 @@ #define pt_dump_seq_puts(m, fmt) \ ({ \ if (m) \ - seq_printf(m, fmt); \ + seq_puts(m, fmt); \ }) /* diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 8fbff3106c56..1a27efcf3c20 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -98,7 +98,7 @@ ifeq ($(CONFIG_X86_KERNEL_IBT),y) # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=104816 # KBUILD_CFLAGS += $(call cc-option,-fcf-protection=branch -fno-jump-tables) -KBUILD_RUSTFLAGS += -Zcf-protection=branch -Zno-jump-tables +KBUILD_RUSTFLAGS += -Zcf-protection=branch $(if $(call rustc-min-version,109300),-Cjump-tables=n,-Zno-jump-tables) else KBUILD_CFLAGS += $(call cc-option,-fcf-protection=none) endif diff --git a/arch/x86/include/asm/amd/node.h b/arch/x86/include/asm/amd/node.h index 23fe617898a8..a672b8765fa8 100644 --- a/arch/x86/include/asm/amd/node.h +++ b/arch/x86/include/asm/amd/node.h @@ -23,7 +23,6 @@ #define AMD_NODE0_PCI_SLOT 0x18 struct pci_dev *amd_node_get_func(u16 node, u8 func); -struct pci_dev *amd_node_get_root(u16 node); static inline u16 amd_num_nodes(void) { diff --git a/arch/x86/include/asm/runtime-const.h b/arch/x86/include/asm/runtime-const.h index 8d983cfd06ea..e5a13dc8816e 100644 --- a/arch/x86/include/asm/runtime-const.h +++ b/arch/x86/include/asm/runtime-const.h @@ -2,6 +2,10 @@ #ifndef _ASM_RUNTIME_CONST_H #define _ASM_RUNTIME_CONST_H +#ifdef MODULE + #error "Cannot use runtime-const infrastructure from modules" +#endif + #ifdef __ASSEMBLY__ .macro RUNTIME_CONST_PTR sym reg diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index c8a5ae35c871..641f45c22f9d 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -12,12 +12,12 @@ #include <asm/cpufeatures.h> #include <asm/page.h> #include <asm/percpu.h> -#include <asm/runtime-const.h> -/* - * Virtual variable: there's no actual backing store for this, - * it can purely be used as 'runtime_const_ptr(USER_PTR_MAX)' - */ +#ifdef MODULE + #define runtime_const_ptr(sym) (sym) +#else + #include <asm/runtime-const.h> +#endif extern unsigned long USER_PTR_MAX; #ifdef CONFIG_ADDRESS_MASKING diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h index 9792e329343e..1baa86dfe029 100644 --- a/arch/x86/include/uapi/asm/vmx.h +++ b/arch/x86/include/uapi/asm/vmx.h @@ -93,6 +93,7 @@ #define EXIT_REASON_TPAUSE 68 #define EXIT_REASON_BUS_LOCK 74 #define EXIT_REASON_NOTIFY 75 +#define EXIT_REASON_SEAMCALL 76 #define EXIT_REASON_TDCALL 77 #define EXIT_REASON_MSR_READ_IMM 84 #define EXIT_REASON_MSR_WRITE_IMM 85 diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c index 7047124490f6..d7c8ef1e354d 100644 --- a/arch/x86/kernel/acpi/cppc.c +++ b/arch/x86/kernel/acpi/cppc.c @@ -196,7 +196,7 @@ int amd_detect_prefcore(bool *detected) break; } - for_each_present_cpu(cpu) { + for_each_online_cpu(cpu) { u32 tmp; int ret; diff --git a/arch/x86/kernel/amd_node.c b/arch/x86/kernel/amd_node.c index a40176b62eb5..3d0a4768d603 100644 --- a/arch/x86/kernel/amd_node.c +++ b/arch/x86/kernel/amd_node.c @@ -34,62 +34,6 @@ struct pci_dev *amd_node_get_func(u16 node, u8 func) return pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(AMD_NODE0_PCI_SLOT + node, func)); } -#define DF_BLK_INST_CNT 0x040 -#define DF_CFG_ADDR_CNTL_LEGACY 0x084 -#define DF_CFG_ADDR_CNTL_DF4 0xC04 - -#define DF_MAJOR_REVISION GENMASK(27, 24) - -static u16 get_cfg_addr_cntl_offset(struct pci_dev *df_f0) -{ - u32 reg; - - /* - * Revision fields added for DF4 and later. - * - * Major revision of '0' is found pre-DF4. Field is Read-as-Zero. - */ - if (pci_read_config_dword(df_f0, DF_BLK_INST_CNT, ®)) - return 0; - - if (reg & DF_MAJOR_REVISION) - return DF_CFG_ADDR_CNTL_DF4; - - return DF_CFG_ADDR_CNTL_LEGACY; -} - -struct pci_dev *amd_node_get_root(u16 node) -{ - struct pci_dev *root; - u16 cntl_off; - u8 bus; - - if (!cpu_feature_enabled(X86_FEATURE_ZEN)) - return NULL; - - /* - * D18F0xXXX [Config Address Control] (DF::CfgAddressCntl) - * Bits [7:0] (SecBusNum) holds the bus number of the root device for - * this Data Fabric instance. The segment, device, and function will be 0. - */ - struct pci_dev *df_f0 __free(pci_dev_put) = amd_node_get_func(node, 0); - if (!df_f0) - return NULL; - - cntl_off = get_cfg_addr_cntl_offset(df_f0); - if (!cntl_off) - return NULL; - - if (pci_read_config_byte(df_f0, cntl_off, &bus)) - return NULL; - - /* Grab the pointer for the actual root device instance. */ - root = pci_get_domain_bus_and_slot(0, bus, 0); - - pci_dbg(root, "is root for AMD node %u\n", node); - return root; -} - static struct pci_dev **amd_roots; /* Protect the PCI config register pairs used for SMN. */ @@ -274,51 +218,21 @@ DEFINE_SHOW_STORE_ATTRIBUTE(smn_node); DEFINE_SHOW_STORE_ATTRIBUTE(smn_address); DEFINE_SHOW_STORE_ATTRIBUTE(smn_value); -static int amd_cache_roots(void) -{ - u16 node, num_nodes = amd_num_nodes(); - - amd_roots = kcalloc(num_nodes, sizeof(*amd_roots), GFP_KERNEL); - if (!amd_roots) - return -ENOMEM; - - for (node = 0; node < num_nodes; node++) - amd_roots[node] = amd_node_get_root(node); - - return 0; -} - -static int reserve_root_config_spaces(void) +static struct pci_dev *get_next_root(struct pci_dev *root) { - struct pci_dev *root = NULL; - struct pci_bus *bus = NULL; - - while ((bus = pci_find_next_bus(bus))) { - /* Root device is Device 0 Function 0 on each Primary Bus. */ - root = pci_get_slot(bus, 0); - if (!root) + while ((root = pci_get_class(PCI_CLASS_BRIDGE_HOST << 8, root))) { + /* Root device is Device 0 Function 0. */ + if (root->devfn) continue; if (root->vendor != PCI_VENDOR_ID_AMD && root->vendor != PCI_VENDOR_ID_HYGON) continue; - pci_dbg(root, "Reserving PCI config space\n"); - - /* - * There are a few SMN index/data pairs and other registers - * that shouldn't be accessed by user space. - * So reserve the entire PCI config space for simplicity rather - * than covering specific registers piecemeal. - */ - if (!pci_request_config_region_exclusive(root, 0, PCI_CFG_SPACE_SIZE, NULL)) { - pci_err(root, "Failed to reserve config space\n"); - return -EEXIST; - } + break; } - smn_exclusive = true; - return 0; + return root; } static bool enable_dfs; @@ -332,7 +246,8 @@ __setup("amd_smn_debugfs_enable", amd_smn_enable_dfs); static int __init amd_smn_init(void) { - int err; + u16 count, num_roots, roots_per_node, node, num_nodes; + struct pci_dev *root; if (!cpu_feature_enabled(X86_FEATURE_ZEN)) return 0; @@ -342,13 +257,48 @@ static int __init amd_smn_init(void) if (amd_roots) return 0; - err = amd_cache_roots(); - if (err) - return err; + num_roots = 0; + root = NULL; + while ((root = get_next_root(root))) { + pci_dbg(root, "Reserving PCI config space\n"); - err = reserve_root_config_spaces(); - if (err) - return err; + /* + * There are a few SMN index/data pairs and other registers + * that shouldn't be accessed by user space. So reserve the + * entire PCI config space for simplicity rather than covering + * specific registers piecemeal. + */ + if (!pci_request_config_region_exclusive(root, 0, PCI_CFG_SPACE_SIZE, NULL)) { + pci_err(root, "Failed to reserve config space\n"); + return -EEXIST; + } + + num_roots++; + } + + pr_debug("Found %d AMD root devices\n", num_roots); + + if (!num_roots) + return -ENODEV; + + num_nodes = amd_num_nodes(); + amd_roots = kcalloc(num_nodes, sizeof(*amd_roots), GFP_KERNEL); + if (!amd_roots) + return -ENOMEM; + + roots_per_node = num_roots / num_nodes; + + count = 0; + node = 0; + root = NULL; + while (node < num_nodes && (root = get_next_root(root))) { + /* Use one root for each node and skip the rest. */ + if (count++ % roots_per_node) + continue; + + pci_dbg(root, "is root for AMD node %u\n", node); + amd_roots[node++] = root; + } if (enable_dfs) { debugfs_dir = debugfs_create_dir("amd_smn", arch_debugfs_dir); @@ -358,6 +308,8 @@ static int __init amd_smn_init(void) debugfs_create_file("value", 0600, debugfs_dir, NULL, &smn_value_fops); } + smn_exclusive = true; + return 0; } diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 8e36964a7721..2ba9f2d42d8c 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -1038,6 +1038,7 @@ static void init_amd_zen4(struct cpuinfo_x86 *c) static const struct x86_cpu_id zen5_rdseed_microcode[] = { ZEN_MODEL_STEP_UCODE(0x1a, 0x02, 0x1, 0x0b00215a), ZEN_MODEL_STEP_UCODE(0x1a, 0x11, 0x0, 0x0b101054), + {}, }; static void init_amd_zen5(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index c7d3512914ca..02d97834a1d4 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -78,6 +78,10 @@ DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info); EXPORT_PER_CPU_SYMBOL(cpu_info); +/* Used for modules: built-in code uses runtime constants */ +unsigned long USER_PTR_MAX; +EXPORT_SYMBOL(USER_PTR_MAX); + u32 elf_hwcap2 __read_mostly; /* Number of siblings per CPU package */ @@ -2579,7 +2583,7 @@ void __init arch_cpu_finalize_init(void) alternative_instructions(); if (IS_ENABLED(CONFIG_X86_64)) { - unsigned long USER_PTR_MAX = TASK_SIZE_MAX; + USER_PTR_MAX = TASK_SIZE_MAX; /* * Enable this when LAM is gated on LASS support diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index b7c797dc94f4..dc82153009da 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -220,10 +220,12 @@ static bool need_sha_check(u32 cur_rev) case 0xaa001: return cur_rev <= 0xaa00116; break; case 0xaa002: return cur_rev <= 0xaa00218; break; case 0xb0021: return cur_rev <= 0xb002146; break; + case 0xb0081: return cur_rev <= 0xb008111; break; case 0xb1010: return cur_rev <= 0xb101046; break; case 0xb2040: return cur_rev <= 0xb204031; break; case 0xb4040: return cur_rev <= 0xb404031; break; case 0xb6000: return cur_rev <= 0xb600031; break; + case 0xb6080: return cur_rev <= 0xb608031; break; case 0xb7000: return cur_rev <= 0xb700031; break; default: break; } diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index f286b5706d7c..fef00546c885 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -216,7 +216,7 @@ static void avic_deactivate_vmcb(struct vcpu_svm *svm) * This function is called from IOMMU driver to notify * SVM to schedule in a particular vCPU of a particular VM. */ -int avic_ga_log_notifier(u32 ga_tag) +static int avic_ga_log_notifier(u32 ga_tag) { unsigned long flags; struct kvm_svm *kvm_svm; @@ -788,7 +788,7 @@ int avic_init_vcpu(struct vcpu_svm *svm) struct kvm_vcpu *vcpu = &svm->vcpu; INIT_LIST_HEAD(&svm->ir_list); - spin_lock_init(&svm->ir_list_lock); + raw_spin_lock_init(&svm->ir_list_lock); if (!enable_apicv || !irqchip_in_kernel(vcpu->kvm)) return 0; @@ -816,9 +816,9 @@ static void svm_ir_list_del(struct kvm_kernel_irqfd *irqfd) if (!vcpu) return; - spin_lock_irqsave(&to_svm(vcpu)->ir_list_lock, flags); + raw_spin_lock_irqsave(&to_svm(vcpu)->ir_list_lock, flags); list_del(&irqfd->vcpu_list); - spin_unlock_irqrestore(&to_svm(vcpu)->ir_list_lock, flags); + raw_spin_unlock_irqrestore(&to_svm(vcpu)->ir_list_lock, flags); } int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm, @@ -855,7 +855,7 @@ int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm, * list of IRQs being posted to the vCPU, to ensure the IRTE * isn't programmed with stale pCPU/IsRunning information. */ - guard(spinlock_irqsave)(&svm->ir_list_lock); + guard(raw_spinlock_irqsave)(&svm->ir_list_lock); /* * Update the target pCPU for IOMMU doorbells if the vCPU is @@ -972,7 +972,7 @@ static void __avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu, * up-to-date entry information, or that this task will wait until * svm_ir_list_add() completes to set the new target pCPU. */ - spin_lock_irqsave(&svm->ir_list_lock, flags); + raw_spin_lock_irqsave(&svm->ir_list_lock, flags); entry = svm->avic_physical_id_entry; WARN_ON_ONCE(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK); @@ -997,7 +997,7 @@ static void __avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu, avic_update_iommu_vcpu_affinity(vcpu, h_physical_id, action); - spin_unlock_irqrestore(&svm->ir_list_lock, flags); + raw_spin_unlock_irqrestore(&svm->ir_list_lock, flags); } void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) @@ -1035,7 +1035,7 @@ static void __avic_vcpu_put(struct kvm_vcpu *vcpu, enum avic_vcpu_action action) * or that this task will wait until svm_ir_list_add() completes to * mark the vCPU as not running. */ - spin_lock_irqsave(&svm->ir_list_lock, flags); + raw_spin_lock_irqsave(&svm->ir_list_lock, flags); avic_update_iommu_vcpu_affinity(vcpu, -1, action); @@ -1059,7 +1059,7 @@ static void __avic_vcpu_put(struct kvm_vcpu *vcpu, enum avic_vcpu_action action) svm->avic_physical_id_entry = entry; - spin_unlock_irqrestore(&svm->ir_list_lock, flags); + raw_spin_unlock_irqrestore(&svm->ir_list_lock, flags); } void avic_vcpu_put(struct kvm_vcpu *vcpu) @@ -1243,3 +1243,9 @@ bool __init avic_hardware_setup(void) return true; } + +void avic_hardware_unsetup(void) +{ + if (avic) + amd_iommu_register_ga_log_notifier(NULL); +} diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index a6443feab252..da6e80b3ac35 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -677,11 +677,10 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12 */ svm_copy_lbrs(vmcb02, vmcb12); vmcb02->save.dbgctl &= ~DEBUGCTL_RESERVED_BITS; - svm_update_lbrv(&svm->vcpu); - - } else if (unlikely(vmcb01->control.virt_ext & LBR_CTL_ENABLE_MASK)) { + } else { svm_copy_lbrs(vmcb02, vmcb01); } + svm_update_lbrv(&svm->vcpu); } static inline bool is_evtinj_soft(u32 evtinj) @@ -833,11 +832,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, svm->soft_int_next_rip = vmcb12_rip; } - vmcb02->control.virt_ext = vmcb01->control.virt_ext & - LBR_CTL_ENABLE_MASK; - if (guest_cpu_cap_has(vcpu, X86_FEATURE_LBRV)) - vmcb02->control.virt_ext |= - (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK); + /* LBR_CTL_ENABLE_MASK is controlled by svm_update_lbrv() */ if (!nested_vmcb_needs_vls_intercept(svm)) vmcb02->control.virt_ext |= VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK; @@ -1189,13 +1184,12 @@ int nested_svm_vmexit(struct vcpu_svm *svm) kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); if (unlikely(guest_cpu_cap_has(vcpu, X86_FEATURE_LBRV) && - (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK))) { + (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK))) svm_copy_lbrs(vmcb12, vmcb02); - svm_update_lbrv(vcpu); - } else if (unlikely(vmcb01->control.virt_ext & LBR_CTL_ENABLE_MASK)) { + else svm_copy_lbrs(vmcb01, vmcb02); - svm_update_lbrv(vcpu); - } + + svm_update_lbrv(vcpu); if (vnmi) { if (vmcb02->control.int_ctl & V_NMI_BLOCKING_MASK) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 153c12dbf3eb..10c21e4c5406 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -806,60 +806,43 @@ void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb) vmcb_mark_dirty(to_vmcb, VMCB_LBR); } -void svm_enable_lbrv(struct kvm_vcpu *vcpu) +static void __svm_enable_lbrv(struct kvm_vcpu *vcpu) { - struct vcpu_svm *svm = to_svm(vcpu); - - svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK; - svm_recalc_lbr_msr_intercepts(vcpu); - - /* Move the LBR msrs to the vmcb02 so that the guest can see them. */ - if (is_guest_mode(vcpu)) - svm_copy_lbrs(svm->vmcb, svm->vmcb01.ptr); + to_svm(vcpu)->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK; } -static void svm_disable_lbrv(struct kvm_vcpu *vcpu) +void svm_enable_lbrv(struct kvm_vcpu *vcpu) { - struct vcpu_svm *svm = to_svm(vcpu); - - KVM_BUG_ON(sev_es_guest(vcpu->kvm), vcpu->kvm); - svm->vmcb->control.virt_ext &= ~LBR_CTL_ENABLE_MASK; + __svm_enable_lbrv(vcpu); svm_recalc_lbr_msr_intercepts(vcpu); - - /* - * Move the LBR msrs back to the vmcb01 to avoid copying them - * on nested guest entries. - */ - if (is_guest_mode(vcpu)) - svm_copy_lbrs(svm->vmcb01.ptr, svm->vmcb); } -static struct vmcb *svm_get_lbr_vmcb(struct vcpu_svm *svm) +static void __svm_disable_lbrv(struct kvm_vcpu *vcpu) { - /* - * If LBR virtualization is disabled, the LBR MSRs are always kept in - * vmcb01. If LBR virtualization is enabled and L1 is running VMs of - * its own, the MSRs are moved between vmcb01 and vmcb02 as needed. - */ - return svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK ? svm->vmcb : - svm->vmcb01.ptr; + KVM_BUG_ON(sev_es_guest(vcpu->kvm), vcpu->kvm); + to_svm(vcpu)->vmcb->control.virt_ext &= ~LBR_CTL_ENABLE_MASK; } void svm_update_lbrv(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); bool current_enable_lbrv = svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK; - bool enable_lbrv = (svm_get_lbr_vmcb(svm)->save.dbgctl & DEBUGCTLMSR_LBR) || + bool enable_lbrv = (svm->vmcb->save.dbgctl & DEBUGCTLMSR_LBR) || (is_guest_mode(vcpu) && guest_cpu_cap_has(vcpu, X86_FEATURE_LBRV) && (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK)); - if (enable_lbrv == current_enable_lbrv) - return; + if (enable_lbrv && !current_enable_lbrv) + __svm_enable_lbrv(vcpu); + else if (!enable_lbrv && current_enable_lbrv) + __svm_disable_lbrv(vcpu); - if (enable_lbrv) - svm_enable_lbrv(vcpu); - else - svm_disable_lbrv(vcpu); + /* + * During nested transitions, it is possible that the current VMCB has + * LBR_CTL set, but the previous LBR_CTL had it cleared (or vice versa). + * In this case, even though LBR_CTL does not need an update, intercepts + * do, so always recalculate the intercepts here. + */ + svm_recalc_lbr_msr_intercepts(vcpu); } void disable_nmi_singlestep(struct vcpu_svm *svm) @@ -921,6 +904,8 @@ static void svm_hardware_unsetup(void) { int cpu; + avic_hardware_unsetup(); + sev_hardware_unsetup(); for_each_possible_cpu(cpu) @@ -2722,19 +2707,19 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = svm->tsc_aux; break; case MSR_IA32_DEBUGCTLMSR: - msr_info->data = svm_get_lbr_vmcb(svm)->save.dbgctl; + msr_info->data = svm->vmcb->save.dbgctl; break; case MSR_IA32_LASTBRANCHFROMIP: - msr_info->data = svm_get_lbr_vmcb(svm)->save.br_from; + msr_info->data = svm->vmcb->save.br_from; break; case MSR_IA32_LASTBRANCHTOIP: - msr_info->data = svm_get_lbr_vmcb(svm)->save.br_to; + msr_info->data = svm->vmcb->save.br_to; break; case MSR_IA32_LASTINTFROMIP: - msr_info->data = svm_get_lbr_vmcb(svm)->save.last_excp_from; + msr_info->data = svm->vmcb->save.last_excp_from; break; case MSR_IA32_LASTINTTOIP: - msr_info->data = svm_get_lbr_vmcb(svm)->save.last_excp_to; + msr_info->data = svm->vmcb->save.last_excp_to; break; case MSR_VM_HSAVE_PA: msr_info->data = svm->nested.hsave_msr; @@ -3002,7 +2987,11 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) if (data & DEBUGCTL_RESERVED_BITS) return 1; - svm_get_lbr_vmcb(svm)->save.dbgctl = data; + if (svm->vmcb->save.dbgctl == data) + break; + + svm->vmcb->save.dbgctl = data; + vmcb_mark_dirty(svm->vmcb, VMCB_LBR); svm_update_lbrv(vcpu); break; case MSR_VM_HSAVE_PA: @@ -5386,12 +5375,6 @@ static __init int svm_hardware_setup(void) svm_hv_hardware_setup(); - for_each_possible_cpu(cpu) { - r = svm_cpu_init(cpu); - if (r) - goto err; - } - enable_apicv = avic_hardware_setup(); if (!enable_apicv) { enable_ipiv = false; @@ -5435,6 +5418,13 @@ static __init int svm_hardware_setup(void) svm_set_cpu_caps(); kvm_caps.inapplicable_quirks &= ~KVM_X86_QUIRK_CD_NW_CLEARED; + + for_each_possible_cpu(cpu) { + r = svm_cpu_init(cpu); + if (r) + goto err; + } + return 0; err: diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index e4b04f435b3d..c856d8e0f95e 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -329,7 +329,7 @@ struct vcpu_svm { * back into remapped mode). */ struct list_head ir_list; - spinlock_t ir_list_lock; + raw_spinlock_t ir_list_lock; struct vcpu_sev_es_state sev_es; @@ -805,7 +805,7 @@ extern struct kvm_x86_nested_ops svm_nested_ops; ) bool __init avic_hardware_setup(void); -int avic_ga_log_notifier(u32 ga_tag); +void avic_hardware_unsetup(void); void avic_vm_destroy(struct kvm *kvm); int avic_vm_init(struct kvm *kvm); void avic_init_vmcb(struct vcpu_svm *svm, struct vmcb *vmcb); diff --git a/arch/x86/kvm/vmx/common.h b/arch/x86/kvm/vmx/common.h index bc5ece76533a..412d0829d7a2 100644 --- a/arch/x86/kvm/vmx/common.h +++ b/arch/x86/kvm/vmx/common.h @@ -98,7 +98,7 @@ static inline int __vmx_handle_ept_violation(struct kvm_vcpu *vcpu, gpa_t gpa, error_code |= (exit_qualification & EPT_VIOLATION_PROT_MASK) ? PFERR_PRESENT_MASK : 0; - if (error_code & EPT_VIOLATION_GVA_IS_VALID) + if (exit_qualification & EPT_VIOLATION_GVA_IS_VALID) error_code |= (exit_qualification & EPT_VIOLATION_GVA_TRANSLATED) ? PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 76271962cb70..bcea087b642f 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -6728,6 +6728,14 @@ static bool nested_vmx_l1_wants_exit(struct kvm_vcpu *vcpu, case EXIT_REASON_NOTIFY: /* Notify VM exit is not exposed to L1 */ return false; + case EXIT_REASON_SEAMCALL: + case EXIT_REASON_TDCALL: + /* + * SEAMCALL and TDCALL unconditionally VM-Exit, but aren't + * virtualized by KVM for L1 hypervisors, i.e. L1 should + * never want or expect such an exit. + */ + return false; default: return true; } diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index f87c216d976d..91b6f2f3edc2 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6032,6 +6032,12 @@ static int handle_vmx_instruction(struct kvm_vcpu *vcpu) return 1; } +static int handle_tdx_instruction(struct kvm_vcpu *vcpu) +{ + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; +} + #ifndef CONFIG_X86_SGX_KVM static int handle_encls(struct kvm_vcpu *vcpu) { @@ -6157,6 +6163,8 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_ENCLS] = handle_encls, [EXIT_REASON_BUS_LOCK] = handle_bus_lock_vmexit, [EXIT_REASON_NOTIFY] = handle_notify, + [EXIT_REASON_SEAMCALL] = handle_tdx_instruction, + [EXIT_REASON_TDCALL] = handle_tdx_instruction, [EXIT_REASON_MSR_READ_IMM] = handle_rdmsr_imm, [EXIT_REASON_MSR_WRITE_IMM] = handle_wrmsr_imm, }; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index b4b5d2d09634..c9c2aa6f4705 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3874,15 +3874,9 @@ static void record_steal_time(struct kvm_vcpu *vcpu) /* * Returns true if the MSR in question is managed via XSTATE, i.e. is context - * switched with the rest of guest FPU state. Note! S_CET is _not_ context - * switched via XSTATE even though it _is_ saved/restored via XSAVES/XRSTORS. - * Because S_CET is loaded on VM-Enter and VM-Exit via dedicated VMCS fields, - * the value saved/restored via XSTATE is always the host's value. That detail - * is _extremely_ important, as the guest's S_CET must _never_ be resident in - * hardware while executing in the host. Loading guest values for U_CET and - * PL[0-3]_SSP while executing in the kernel is safe, as U_CET is specific to - * userspace, and PL[0-3]_SSP are only consumed when transitioning to lower - * privilege levels, i.e. are effectively only consumed by userspace as well. + * switched with the rest of guest FPU state. + * + * Note, S_CET is _not_ saved/restored via XSAVES/XRSTORS. */ static bool is_xstate_managed_msr(struct kvm_vcpu *vcpu, u32 msr) { @@ -3905,6 +3899,11 @@ static bool is_xstate_managed_msr(struct kvm_vcpu *vcpu, u32 msr) * MSR that is managed via XSTATE. Note, the caller is responsible for doing * the initial FPU load, this helper only ensures that guest state is resident * in hardware (the kernel can load its FPU state in IRQ context). + * + * Note, loading guest values for U_CET and PL[0-3]_SSP while executing in the + * kernel is safe, as U_CET is specific to userspace, and PL[0-3]_SSP are only + * consumed when transitioning to lower privilege levels, i.e. are effectively + * only consumed by userspace as well. */ static __always_inline void kvm_access_xstate_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info, @@ -11807,6 +11806,9 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu) /* Swap (qemu) user FPU context for the guest FPU context. */ static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) { + if (KVM_BUG_ON(vcpu->arch.guest_fpu.fpstate->in_use, vcpu->kvm)) + return; + /* Exclude PKRU, it's restored separately immediately after VM-Exit. */ fpu_swap_kvm_fpstate(&vcpu->arch.guest_fpu, true); trace_kvm_fpu(1); @@ -11815,6 +11817,9 @@ static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) /* When vcpu_run ends, restore user space FPU context. */ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) { + if (KVM_BUG_ON(!vcpu->arch.guest_fpu.fpstate->in_use, vcpu->kvm)) + return; + fpu_swap_kvm_fpstate(&vcpu->arch.guest_fpu, false); ++vcpu->stat.fpu_reload; trace_kvm_fpu(0); @@ -12137,9 +12142,6 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, int r; vcpu_load(vcpu); - if (kvm_mpx_supported()) - kvm_load_guest_fpu(vcpu); - kvm_vcpu_srcu_read_lock(vcpu); r = kvm_apic_accept_events(vcpu); @@ -12156,9 +12158,6 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, out: kvm_vcpu_srcu_read_unlock(vcpu); - - if (kvm_mpx_supported()) - kvm_put_guest_fpu(vcpu); vcpu_put(vcpu); return r; } @@ -12788,6 +12787,7 @@ static void kvm_xstate_reset(struct kvm_vcpu *vcpu, bool init_event) { struct fpstate *fpstate = vcpu->arch.guest_fpu.fpstate; u64 xfeatures_mask; + bool fpu_in_use; int i; /* @@ -12811,13 +12811,23 @@ static void kvm_xstate_reset(struct kvm_vcpu *vcpu, bool init_event) BUILD_BUG_ON(sizeof(xfeatures_mask) * BITS_PER_BYTE <= XFEATURE_MAX); /* - * All paths that lead to INIT are required to load the guest's FPU - * state (because most paths are buried in KVM_RUN). - */ - kvm_put_guest_fpu(vcpu); + * Unload guest FPU state (if necessary) before zeroing XSTATE fields + * as the kernel can only modify the state when its resident in memory, + * i.e. when it's not loaded into hardware. + * + * WARN if the vCPU's desire to run, i.e. whether or not its in KVM_RUN, + * doesn't match the loaded/in-use state of the FPU, as KVM_RUN is the + * only path that can trigger INIT emulation _and_ loads FPU state, and + * KVM_RUN should _always_ load FPU state. + */ + WARN_ON_ONCE(vcpu->wants_to_run != fpstate->in_use); + fpu_in_use = fpstate->in_use; + if (fpu_in_use) + kvm_put_guest_fpu(vcpu); for_each_set_bit(i, (unsigned long *)&xfeatures_mask, XFEATURE_MAX) fpstate_clear_xstate_component(fpstate, i); - kvm_load_guest_fpu(vcpu); + if (fpu_in_use) + kvm_load_guest_fpu(vcpu); } void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) diff --git a/drivers/acpi/acpi_mrrm.c b/drivers/acpi/acpi_mrrm.c index a6dbf623e557..6d69554c940e 100644 --- a/drivers/acpi/acpi_mrrm.c +++ b/drivers/acpi/acpi_mrrm.c @@ -152,26 +152,49 @@ ATTRIBUTE_GROUPS(memory_range); static __init int add_boot_memory_ranges(void) { - struct kobject *pkobj, *kobj; + struct kobject *pkobj, *kobj, **kobjs; int ret = -EINVAL; - char *name; + char name[16]; + int i; pkobj = kobject_create_and_add("memory_ranges", acpi_kobj); + if (!pkobj) + return -ENOMEM; - for (int i = 0; i < mrrm_mem_entry_num; i++) { - name = kasprintf(GFP_KERNEL, "range%d", i); - if (!name) { - ret = -ENOMEM; - break; - } + kobjs = kcalloc(mrrm_mem_entry_num, sizeof(*kobjs), GFP_KERNEL); + if (!kobjs) { + kobject_put(pkobj); + return -ENOMEM; + } + for (i = 0; i < mrrm_mem_entry_num; i++) { + scnprintf(name, sizeof(name), "range%d", i); kobj = kobject_create_and_add(name, pkobj); + if (!kobj) { + ret = -ENOMEM; + goto cleanup; + } ret = sysfs_create_groups(kobj, memory_range_groups); - if (ret) - return ret; + if (ret) { + kobject_put(kobj); + goto cleanup; + } + kobjs[i] = kobj; } + kfree(kobjs); + return 0; + +cleanup: + for (int j = 0; j < i; j++) { + if (kobjs[j]) { + sysfs_remove_groups(kobjs[j], memory_range_groups); + kobject_put(kobjs[j]); + } + } + kfree(kobjs); + kobject_put(pkobj); return ret; } diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index ab4651205e8a..3bdeeee3414e 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -460,7 +460,7 @@ bool acpi_cpc_valid(void) if (acpi_disabled) return false; - for_each_present_cpu(cpu) { + for_each_online_cpu(cpu) { cpc_ptr = per_cpu(cpc_desc_ptr, cpu); if (!cpc_ptr) return false; @@ -476,7 +476,7 @@ bool cppc_allow_fast_switch(void) struct cpc_desc *cpc_ptr; int cpu; - for_each_present_cpu(cpu) { + for_each_online_cpu(cpu) { cpc_ptr = per_cpu(cpc_desc_ptr, cpu); desired_reg = &cpc_ptr->cpc_regs[DESIRED_PERF]; if (!CPC_IN_SYSTEM_MEMORY(desired_reg) && @@ -750,7 +750,7 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr) } /* - * Disregard _CPC if the number of entries in the return pachage is not + * Disregard _CPC if the number of entries in the return package is not * as expected, but support future revisions being proper supersets of * the v3 and only causing more entries to be returned by _CPC. */ @@ -1435,7 +1435,7 @@ bool cppc_perf_ctrs_in_pcc(void) { int cpu; - for_each_present_cpu(cpu) { + for_each_online_cpu(cpu) { struct cpc_register_resource *ref_perf_reg; struct cpc_desc *cpc_desc; diff --git a/drivers/acpi/sbs.c b/drivers/acpi/sbs.c index a3f95a3fffde..d3edc3bcbf01 100644 --- a/drivers/acpi/sbs.c +++ b/drivers/acpi/sbs.c @@ -487,7 +487,7 @@ static int acpi_battery_read(struct acpi_battery *battery) if (result) return result; - battery->present = state & (1 << battery->id); + battery->present = !!(state & (1 << battery->id)); if (!battery->present) return 0; diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c index 6abd962502e3..52794db2739b 100644 --- a/drivers/bluetooth/btrtl.c +++ b/drivers/bluetooth/btrtl.c @@ -50,7 +50,7 @@ #define RTL_CHIP_SUBVER (&(struct rtl_vendor_cmd) {{0x10, 0x38, 0x04, 0x28, 0x80}}) #define RTL_CHIP_REV (&(struct rtl_vendor_cmd) {{0x10, 0x3A, 0x04, 0x28, 0x80}}) -#define RTL_SEC_PROJ (&(struct rtl_vendor_cmd) {{0x10, 0xA4, 0x0D, 0x00, 0xb0}}) +#define RTL_SEC_PROJ (&(struct rtl_vendor_cmd) {{0x10, 0xA4, 0xAD, 0x00, 0xb0}}) #define RTL_PATCH_SNIPPETS 0x01 #define RTL_PATCH_DUMMY_HEADER 0x02 @@ -534,7 +534,6 @@ static int rtlbt_parse_firmware_v2(struct hci_dev *hdev, { struct rtl_epatch_header_v2 *hdr; int rc; - u8 reg_val[2]; u8 key_id; u32 num_sections; struct rtl_section *section; @@ -549,14 +548,7 @@ static int rtlbt_parse_firmware_v2(struct hci_dev *hdev, .len = btrtl_dev->fw_len - 7, /* Cut the tail */ }; - rc = btrtl_vendor_read_reg16(hdev, RTL_SEC_PROJ, reg_val); - if (rc < 0) - return -EIO; - key_id = reg_val[0]; - - rtl_dev_dbg(hdev, "%s: key id %u", __func__, key_id); - - btrtl_dev->key_id = key_id; + key_id = btrtl_dev->key_id; hdr = rtl_iov_pull_data(&iov, sizeof(*hdr)); if (!hdr) @@ -625,8 +617,10 @@ static int rtlbt_parse_firmware_v2(struct hci_dev *hdev, len += entry->len; } - if (!len) + if (!len) { + kvfree(ptr); return -EPERM; + } *_buf = ptr; return len; @@ -1068,6 +1062,8 @@ struct btrtl_device_info *btrtl_initialize(struct hci_dev *hdev, u16 hci_rev, lmp_subver; u8 hci_ver, lmp_ver, chip_type = 0; int ret; + int rc; + u8 key_id; u8 reg_val[2]; btrtl_dev = kzalloc(sizeof(*btrtl_dev), GFP_KERNEL); @@ -1178,6 +1174,14 @@ next: goto err_free; } + rc = btrtl_vendor_read_reg16(hdev, RTL_SEC_PROJ, reg_val); + if (rc < 0) + goto err_free; + + key_id = reg_val[0]; + btrtl_dev->key_id = key_id; + rtl_dev_info(hdev, "%s: key id %u", __func__, key_id); + btrtl_dev->fw_len = -EIO; if (lmp_subver == RTL_ROM_LMP_8852A && hci_rev == 0x000c) { snprintf(fw_name, sizeof(fw_name), "%s_v2.bin", @@ -1200,7 +1204,7 @@ next: goto err_free; } - if (btrtl_dev->ic_info->cfg_name) { + if (btrtl_dev->ic_info->cfg_name && !btrtl_dev->key_id) { if (postfix) { snprintf(cfg_name, sizeof(cfg_name), "%s-%s.bin", btrtl_dev->ic_info->cfg_name, postfix); diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 5e9ebf0c5312..a722446ec73d 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -4361,6 +4361,11 @@ static void btusb_disconnect(struct usb_interface *intf) hci_unregister_dev(hdev); + if (data->oob_wake_irq) + device_init_wakeup(&data->udev->dev, false); + if (data->reset_gpio) + gpiod_put(data->reset_gpio); + if (intf == data->intf) { if (data->isoc) usb_driver_release_interface(&btusb_driver, data->isoc); @@ -4371,17 +4376,11 @@ static void btusb_disconnect(struct usb_interface *intf) usb_driver_release_interface(&btusb_driver, data->diag); usb_driver_release_interface(&btusb_driver, data->intf); } else if (intf == data->diag) { - usb_driver_release_interface(&btusb_driver, data->intf); if (data->isoc) usb_driver_release_interface(&btusb_driver, data->isoc); + usb_driver_release_interface(&btusb_driver, data->intf); } - if (data->oob_wake_irq) - device_init_wakeup(&data->udev->dev, false); - - if (data->reset_gpio) - gpiod_put(data->reset_gpio); - hci_free_dev(hdev); } diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 38897bb14a2c..492a10f1bdbf 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -603,9 +603,6 @@ static bool turbo_is_disabled(void) { u64 misc_en; - if (!cpu_feature_enabled(X86_FEATURE_IDA)) - return true; - rdmsrq(MSR_IA32_MISC_ENABLE, misc_en); return !!(misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE); @@ -2106,7 +2103,8 @@ static u64 atom_get_val(struct cpudata *cpudata, int pstate) u32 vid; val = (u64)pstate << 8; - if (READ_ONCE(global.no_turbo) && !READ_ONCE(global.turbo_disabled)) + if (READ_ONCE(global.no_turbo) && !READ_ONCE(global.turbo_disabled) && + cpu_feature_enabled(X86_FEATURE_IDA)) val |= (u64)1 << 32; vid_fp = cpudata->vid.min + mul_fp( @@ -2271,7 +2269,8 @@ static u64 core_get_val(struct cpudata *cpudata, int pstate) u64 val; val = (u64)pstate << 8; - if (READ_ONCE(global.no_turbo) && !READ_ONCE(global.turbo_disabled)) + if (READ_ONCE(global.no_turbo) && !READ_ONCE(global.turbo_disabled) && + cpu_feature_enabled(X86_FEATURE_IDA)) val |= (u64)1 << 32; return val; diff --git a/drivers/cpuidle/cpuidle-riscv-sbi.c b/drivers/cpuidle/cpuidle-riscv-sbi.c index a360bc4d20b7..19be6475d356 100644 --- a/drivers/cpuidle/cpuidle-riscv-sbi.c +++ b/drivers/cpuidle/cpuidle-riscv-sbi.c @@ -18,6 +18,7 @@ #include <linux/module.h> #include <linux/of.h> #include <linux/slab.h> +#include <linux/string.h> #include <linux/platform_device.h> #include <linux/pm_domain.h> #include <linux/pm_runtime.h> @@ -303,8 +304,8 @@ static int sbi_cpuidle_init_cpu(struct device *dev, int cpu) drv->states[0].exit_latency = 1; drv->states[0].target_residency = 1; drv->states[0].power_usage = UINT_MAX; - strcpy(drv->states[0].name, "WFI"); - strcpy(drv->states[0].desc, "RISC-V WFI"); + strscpy(drv->states[0].name, "WFI"); + strscpy(drv->states[0].desc, "RISC-V WFI"); /* * If no DT idle states are detected (ret == 0) let the driver diff --git a/drivers/edac/versalnet_edac.c b/drivers/edac/versalnet_edac.c index 7c5db8bf0595..1ded4c3f0213 100644 --- a/drivers/edac/versalnet_edac.c +++ b/drivers/edac/versalnet_edac.c @@ -433,7 +433,7 @@ static void handle_error(struct mc_priv *priv, struct ecc_status *stat, phys_addr_t pfn; int err; - if (WARN_ON_ONCE(ctl_num > NUM_CONTROLLERS)) + if (WARN_ON_ONCE(ctl_num >= NUM_CONTROLLERS)) return; mci = priv->mci[ctl_num]; diff --git a/drivers/gpio/gpio-aggregator.c b/drivers/gpio/gpio-aggregator.c index 37600faf4a4b..416f265d09d0 100644 --- a/drivers/gpio/gpio-aggregator.c +++ b/drivers/gpio/gpio-aggregator.c @@ -723,6 +723,7 @@ struct gpiochip_fwd *devm_gpiochip_fwd_alloc(struct device *dev, chip->get_multiple = gpio_fwd_get_multiple_locked; chip->set = gpio_fwd_set; chip->set_multiple = gpio_fwd_set_multiple_locked; + chip->set_config = gpio_fwd_set_config; chip->to_irq = gpio_fwd_to_irq; chip->base = -1; chip->ngpio = ngpios; diff --git a/drivers/gpio/gpio-tb10x.c b/drivers/gpio/gpio-tb10x.c index 09a448ce3eec..3c8fd322a713 100644 --- a/drivers/gpio/gpio-tb10x.c +++ b/drivers/gpio/gpio-tb10x.c @@ -50,25 +50,6 @@ static inline u32 tb10x_reg_read(struct tb10x_gpio *gpio, unsigned int offs) return ioread32(gpio->base + offs); } -static inline void tb10x_reg_write(struct tb10x_gpio *gpio, unsigned int offs, - u32 val) -{ - iowrite32(val, gpio->base + offs); -} - -static inline void tb10x_set_bits(struct tb10x_gpio *gpio, unsigned int offs, - u32 mask, u32 val) -{ - u32 r; - - guard(gpio_generic_lock_irqsave)(&gpio->chip); - - r = tb10x_reg_read(gpio, offs); - r = (r & ~mask) | (val & mask); - - tb10x_reg_write(gpio, offs, r); -} - static int tb10x_gpio_to_irq(struct gpio_chip *chip, unsigned offset) { struct tb10x_gpio *tb10x_gpio = gpiochip_get_data(chip); diff --git a/drivers/gpio/gpiolib-swnode.c b/drivers/gpio/gpiolib-swnode.c index f21dbc28cf2c..e3806db1c0e0 100644 --- a/drivers/gpio/gpiolib-swnode.c +++ b/drivers/gpio/gpiolib-swnode.c @@ -41,7 +41,7 @@ static struct gpio_device *swnode_get_gpio_device(struct fwnode_handle *fwnode) !strcmp(gdev_node->name, GPIOLIB_SWNODE_UNDEFINED_NAME)) return ERR_PTR(-ENOENT); - gdev = gpio_device_find_by_label(gdev_node->name); + gdev = gpio_device_find_by_fwnode(fwnode); return gdev ?: ERR_PTR(-EPROBE_DEFER); } diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 9952e412da50..cd8800ba5825 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -5296,6 +5296,8 @@ static void *gpiolib_seq_start(struct seq_file *s, loff_t *pos) struct gpio_device *gdev; loff_t index = *pos; + s->private = NULL; + priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) return NULL; @@ -5329,7 +5331,11 @@ static void *gpiolib_seq_next(struct seq_file *s, void *v, loff_t *pos) static void gpiolib_seq_stop(struct seq_file *s, void *v) { - struct gpiolib_seq_priv *priv = s->private; + struct gpiolib_seq_priv *priv; + + priv = s->private; + if (!priv) + return; srcu_read_unlock(&gpio_devices_srcu, priv->idx); kfree(priv); diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile index 4b2f7d794275..da2565e6de71 100644 --- a/drivers/gpu/drm/Makefile +++ b/drivers/gpu/drm/Makefile @@ -245,7 +245,7 @@ always-$(CONFIG_DRM_HEADER_TEST) += \ quiet_cmd_hdrtest = HDRTEST $(patsubst %.hdrtest,%.h,$@) cmd_hdrtest = \ $(CC) $(c_flags) -fsyntax-only -x c /dev/null -include $< -include $<; \ - PYTHONDONTWRITEBYTECODE=1 $(KERNELDOC) -none $(if $(CONFIG_WERROR)$(CONFIG_DRM_WERROR),-Werror) $<; \ + PYTHONDONTWRITEBYTECODE=1 $(PYTHON3) $(KERNELDOC) -none $(if $(CONFIG_WERROR)$(CONFIG_DRM_WERROR),-Werror) $<; \ touch $@ $(obj)/%.hdrtest: $(src)/%.h FORCE diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index a2ca9acf8c4e..923f0fa7350c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1267,6 +1267,10 @@ static int unmap_bo_from_gpuvm(struct kgd_mem *mem, (void)amdgpu_vm_bo_unmap(adev, bo_va, entry->va); + /* VM entity stopped if process killed, don't clear freed pt bo */ + if (!amdgpu_vm_ready(vm)) + return 0; + (void)amdgpu_vm_clear_freed(adev, vm, &bo_va->last_pt_update); (void)amdgpu_sync_fence(sync, bo_va->last_pt_update, GFP_KERNEL); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 3d032c4e2dce..2819aceaab74 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -5243,10 +5243,6 @@ int amdgpu_device_suspend(struct drm_device *dev, bool notify_clients) if (amdgpu_sriov_vf(adev)) amdgpu_virt_release_full_gpu(adev, false); - r = amdgpu_dpm_notify_rlc_state(adev, false); - if (r) - return r; - return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 61268aa82df4..7333e19291cf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2632,9 +2632,14 @@ static int amdgpu_pmops_suspend_noirq(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); struct amdgpu_device *adev = drm_to_adev(drm_dev); + int r; - if (amdgpu_acpi_should_gpu_reset(adev)) - return amdgpu_asic_reset(adev); + if (amdgpu_acpi_should_gpu_reset(adev)) { + amdgpu_device_lock_reset_domain(adev->reset_domain); + r = amdgpu_asic_reset(adev); + amdgpu_device_unlock_reset_domain(adev->reset_domain); + return r; + } return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 8c0e5d03de50..aa7987d0806c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -2355,8 +2355,11 @@ static int psp_securedisplay_initialize(struct psp_context *psp) if (!ret && !psp->securedisplay_context.context.resp_status) { psp->securedisplay_context.context.initialized = true; mutex_init(&psp->securedisplay_context.mutex); - } else + } else { + /* don't try again */ + psp->securedisplay_context.context.bin_desc.size_bytes = 0; return ret; + } mutex_lock(&psp->securedisplay_context.mutex); diff --git a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c index 811124ff88a8..f9e2edf5260b 100644 --- a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c +++ b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c @@ -407,7 +407,8 @@ static int aqua_vanjaram_switch_partition_mode(struct amdgpu_xcp_mgr *xcp_mgr, return -EINVAL; } - if (adev->kfd.init_complete && !amdgpu_in_reset(adev)) + if (adev->kfd.init_complete && !amdgpu_in_reset(adev) && + !adev->in_suspend) flags |= AMDGPU_XCP_OPS_KFD; if (flags & AMDGPU_XCP_OPS_KFD) { diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c index 7693b7953426..80565392313f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c @@ -3102,6 +3102,11 @@ static int gfx_v6_0_sw_init(struct amdgpu_ip_block *ip_block) return r; } + adev->gfx.gfx_supported_reset = + amdgpu_get_soft_full_reset_mask(&adev->gfx.gfx_ring[0]); + adev->gfx.compute_supported_reset = + amdgpu_get_soft_full_reset_mask(&adev->gfx.compute_ring[0]); + return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c index 5976ed55d9db..2b7aba22ecc1 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c @@ -4399,6 +4399,11 @@ static int gfx_v7_0_sw_init(struct amdgpu_ip_block *ip_block) gfx_v7_0_gpu_early_init(adev); + adev->gfx.gfx_supported_reset = + amdgpu_get_soft_full_reset_mask(&adev->gfx.gfx_ring[0]); + adev->gfx.compute_supported_reset = + amdgpu_get_soft_full_reset_mask(&adev->gfx.compute_ring[0]); + return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 0856ff65288c..8a81713d97aa 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -2023,6 +2023,11 @@ static int gfx_v8_0_sw_init(struct amdgpu_ip_block *ip_block) if (r) return r; + adev->gfx.gfx_supported_reset = + amdgpu_get_soft_full_reset_mask(&adev->gfx.gfx_ring[0]); + adev->gfx.compute_supported_reset = + amdgpu_get_soft_full_reset_mask(&adev->gfx.compute_ring[0]); + return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c index 77f9d5b9a556..c90cbe053ef3 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c @@ -2292,7 +2292,9 @@ static int gfx_v9_4_3_cp_resume(struct amdgpu_device *adev) r = amdgpu_xcp_init(adev->xcp_mgr, num_xcp, mode); } else { - if (amdgpu_xcp_query_partition_mode(adev->xcp_mgr, + if (adev->in_suspend) + amdgpu_xcp_restore_partition_mode(adev->xcp_mgr); + else if (amdgpu_xcp_query_partition_mode(adev->xcp_mgr, AMDGPU_XCP_FL_NONE) == AMDGPU_UNKNOWN_COMPUTE_PARTITION_MODE) r = amdgpu_xcp_switch_partition_mode( diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c index 64b240b51f1a..a9be7a505026 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c @@ -142,13 +142,37 @@ static int psp_v11_0_init_microcode(struct psp_context *psp) return err; } -static int psp_v11_0_wait_for_bootloader(struct psp_context *psp) +static int psp_v11_wait_for_tos_unload(struct psp_context *psp) { struct amdgpu_device *adev = psp->adev; + uint32_t sol_reg1, sol_reg2; + int retry_loop; + /* Wait for the TOS to be unloaded */ + for (retry_loop = 0; retry_loop < 20; retry_loop++) { + sol_reg1 = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81); + usleep_range(1000, 2000); + sol_reg2 = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81); + if (sol_reg1 == sol_reg2) + return 0; + } + dev_err(adev->dev, "TOS unload failed, C2PMSG_33: %x C2PMSG_81: %x", + RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_33), + RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81)); + + return -ETIME; +} + +static int psp_v11_0_wait_for_bootloader(struct psp_context *psp) +{ + struct amdgpu_device *adev = psp->adev; int ret; int retry_loop; + /* For a reset done at the end of S3, only wait for TOS to be unloaded */ + if (adev->in_s3 && !(adev->flags & AMD_IS_APU) && amdgpu_in_reset(adev)) + return psp_v11_wait_for_tos_unload(psp); + for (retry_loop = 0; retry_loop < 20; retry_loop++) { /* Wait for bootloader to signify that is ready having bit 31 of C2PMSG_35 set to 1 */ diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index bfa3199591b6..91c0188a29b2 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -3563,6 +3563,7 @@ static int dm_resume(struct amdgpu_ip_block *ip_block) /* Do mst topology probing after resuming cached state*/ drm_connector_list_iter_begin(ddev, &iter); drm_for_each_connector_iter(connector, &iter) { + bool init = false; if (connector->connector_type == DRM_MODE_CONNECTOR_WRITEBACK) continue; @@ -3572,7 +3573,14 @@ static int dm_resume(struct amdgpu_ip_block *ip_block) aconnector->mst_root) continue; - drm_dp_mst_topology_queue_probe(&aconnector->mst_mgr); + scoped_guard(mutex, &aconnector->mst_mgr.lock) { + init = !aconnector->mst_mgr.mst_primary; + } + if (init) + dm_helpers_dp_mst_start_top_mgr(aconnector->dc_link->ctx, + aconnector->dc_link, false); + else + drm_dp_mst_topology_queue_probe(&aconnector->mst_mgr); } drm_connector_list_iter_end(&iter); @@ -8030,7 +8038,7 @@ static int dm_encoder_helper_atomic_check(struct drm_encoder *encoder, "mode %dx%d@%dHz is not native, enabling scaling\n", adjusted_mode->hdisplay, adjusted_mode->vdisplay, drm_mode_vrefresh(adjusted_mode)); - dm_new_connector_state->scaling = RMX_FULL; + dm_new_connector_state->scaling = RMX_ASPECT; } return 0; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c index f263e1a4537e..00dac862b665 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c @@ -1302,7 +1302,8 @@ static int odm_combine_segments_show(struct seq_file *m, void *unused) if (connector->status != connector_status_connected) return -ENODEV; - if (pipe_ctx != NULL && pipe_ctx->stream_res.tg->funcs->get_odm_combine_segments) + if (pipe_ctx && pipe_ctx->stream_res.tg && + pipe_ctx->stream_res.tg->funcs->get_odm_combine_segments) pipe_ctx->stream_res.tg->funcs->get_odm_combine_segments(pipe_ctx->stream_res.tg, &segments); seq_printf(m, "%d\n", segments); diff --git a/drivers/gpu/drm/amd/display/dc/link/link_detection.c b/drivers/gpu/drm/amd/display/dc/link/link_detection.c index 85303167a553..1173c53359b0 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_detection.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_detection.c @@ -1141,6 +1141,7 @@ static bool detect_link_and_local_sink(struct dc_link *link, !sink->edid_caps.edid_hdmi) sink->sink_signal = SIGNAL_TYPE_DVI_SINGLE_LINK; else if (dc_is_dvi_signal(sink->sink_signal) && + dc_is_dvi_signal(link->connector_signal) && aud_support->hdmi_audio_native && sink->edid_caps.edid_hdmi) sink->sink_signal = SIGNAL_TYPE_HDMI_TYPE_A; diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c index 518d07afc7df..bc29a923fa6e 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c @@ -195,24 +195,6 @@ int amdgpu_dpm_set_mp1_state(struct amdgpu_device *adev, return ret; } -int amdgpu_dpm_notify_rlc_state(struct amdgpu_device *adev, bool en) -{ - int ret = 0; - const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; - - if (pp_funcs && pp_funcs->notify_rlc_state) { - mutex_lock(&adev->pm.mutex); - - ret = pp_funcs->notify_rlc_state( - adev->powerplay.pp_handle, - en); - - mutex_unlock(&adev->pm.mutex); - } - - return ret; -} - int amdgpu_dpm_is_baco_supported(struct amdgpu_device *adev) { const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index b5fbb0fd1dc0..a7e6d7854b7b 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -4724,14 +4724,14 @@ int amdgpu_pm_sysfs_init(struct amdgpu_device *adev) ret = devm_device_add_group(adev->dev, &amdgpu_pm_policy_attr_group); if (ret) - goto err_out0; + goto err_out1; } if (amdgpu_dpm_is_temp_metrics_supported(adev, SMU_TEMP_METRIC_GPUBOARD)) { ret = devm_device_add_group(adev->dev, &amdgpu_board_attr_group); if (ret) - goto err_out0; + goto err_out1; if (amdgpu_pm_get_sensor_generic(adev, AMDGPU_PP_SENSOR_MAXNODEPOWERLIMIT, (void *)&tmp) != -EOPNOTSUPP) { sysfs_add_file_to_group(&adev->dev->kobj, diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h index 65c1d98af26c..af48aead12f7 100644 --- a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h +++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h @@ -424,8 +424,6 @@ int amdgpu_dpm_mode1_reset(struct amdgpu_device *adev); int amdgpu_dpm_set_mp1_state(struct amdgpu_device *adev, enum pp_mp1_state mp1_state); -int amdgpu_dpm_notify_rlc_state(struct amdgpu_device *adev, bool en); - int amdgpu_dpm_set_gfx_power_up_by_imu(struct amdgpu_device *adev); int amdgpu_dpm_baco_exit(struct amdgpu_device *adev); diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index fb8086859857..244b8c364d45 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -2040,6 +2040,12 @@ static int smu_disable_dpms(struct smu_context *smu) smu->is_apu && (amdgpu_in_reset(adev) || adev->in_s0ix)) return 0; + /* vangogh s0ix */ + if ((amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(11, 5, 0) || + amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(11, 5, 2)) && + adev->in_s0ix) + return 0; + /* * For gpu reset, runpm and hibernation through BACO, * BACO feature has to be kept enabled. diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c index 2c9869feba61..0708d0f0938b 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c @@ -2217,6 +2217,9 @@ static int vangogh_post_smu_init(struct smu_context *smu) uint32_t total_cu = adev->gfx.config.max_cu_per_sh * adev->gfx.config.max_sh_per_se * adev->gfx.config.max_shader_engines; + if (adev->in_s0ix) + return 0; + /* allow message will be sent after enable message on Vangogh*/ if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_DPM_GFXCLK_BIT) && (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG)) { diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index e58c0c158b3a..b91575380708 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -413,7 +413,7 @@ obj-$(CONFIG_DRM_I915_GVT_KVMGT) += kvmgt.o # # Enable locally for CONFIG_DRM_I915_WERROR=y. See also scripts/Makefile.build ifdef CONFIG_DRM_I915_WERROR - cmd_checkdoc = PYTHONDONTWRITEBYTECODE=1 $(KERNELDOC) -none -Werror $< + cmd_checkdoc = PYTHONDONTWRITEBYTECODE=1 $(PYTHON3) $(KERNELDOC) -none -Werror $< endif # header test diff --git a/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c b/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c index 88b147fa5cb1..c90b35881a26 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c @@ -205,7 +205,7 @@ static u64 div_u64_roundup(u64 nom, u32 den) u64 intel_gt_clock_interval_to_ns(const struct intel_gt *gt, u64 count) { - return div_u64_roundup(count * NSEC_PER_SEC, gt->clock_frequency); + return mul_u64_u32_div(count, NSEC_PER_SEC, gt->clock_frequency); } u64 intel_gt_pm_interval_to_ns(const struct intel_gt *gt, u64 count) @@ -215,7 +215,7 @@ u64 intel_gt_pm_interval_to_ns(const struct intel_gt *gt, u64 count) u64 intel_gt_ns_to_clock_interval(const struct intel_gt *gt, u64 ns) { - return div_u64_roundup(gt->clock_frequency * ns, NSEC_PER_SEC); + return mul_u64_u32_div(ns, gt->clock_frequency, NSEC_PER_SEC); } u64 intel_gt_ns_to_pm_interval(const struct intel_gt *gt, u64 ns) diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 25e97031d76e..30d5889fc809 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -1595,8 +1595,20 @@ err_unlock: err_vma_res: i915_vma_resource_free(vma_res); err_fence: - if (work) - dma_fence_work_commit_imm(&work->base); + if (work) { + /* + * When pinning VMA to GGTT on CHV or BXT with VTD enabled, + * commit VMA binding asynchronously to avoid risk of lock + * inversion among reservation_ww locks held here and + * cpu_hotplug_lock acquired from stop_machine(), which we + * wrap around GGTT updates when running in those environments. + */ + if (i915_vma_is_ggtt(vma) && + intel_vm_no_concurrent_access_wa(vma->vm->i915)) + dma_fence_work_commit(&work->base); + else + dma_fence_work_commit_imm(&work->base); + } err_rpm: intel_runtime_pm_put(&vma->vm->i915->runtime_pm, wakeref); diff --git a/drivers/gpu/drm/imagination/Kconfig b/drivers/gpu/drm/imagination/Kconfig index 682dd2633d0c..0482bfcefdde 100644 --- a/drivers/gpu/drm/imagination/Kconfig +++ b/drivers/gpu/drm/imagination/Kconfig @@ -7,6 +7,7 @@ config DRM_POWERVR depends on DRM depends on MMU depends on PM + depends on POWER_SEQUENCING || !POWER_SEQUENCING select DRM_EXEC select DRM_GEM_SHMEM_HELPER select DRM_SCHED diff --git a/drivers/gpu/drm/mediatek/mtk_crtc.c b/drivers/gpu/drm/mediatek/mtk_crtc.c index bc7527542fdc..c4c6d0249df5 100644 --- a/drivers/gpu/drm/mediatek/mtk_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_crtc.c @@ -283,6 +283,10 @@ static void ddp_cmdq_cb(struct mbox_client *cl, void *mssg) unsigned int i; unsigned long flags; + /* release GCE HW usage and start autosuspend */ + pm_runtime_mark_last_busy(cmdq_cl->chan->mbox->dev); + pm_runtime_put_autosuspend(cmdq_cl->chan->mbox->dev); + if (data->sta < 0) return; @@ -618,6 +622,9 @@ static void mtk_crtc_update_config(struct mtk_crtc *mtk_crtc, bool needs_vblank) mtk_crtc->config_updating = false; spin_unlock_irqrestore(&mtk_crtc->config_lock, flags); + if (pm_runtime_resume_and_get(mtk_crtc->cmdq_client.chan->mbox->dev) < 0) + goto update_config_out; + mbox_send_message(mtk_crtc->cmdq_client.chan, cmdq_handle); mbox_client_txdone(mtk_crtc->cmdq_client.chan, 0); goto update_config_out; diff --git a/drivers/gpu/drm/mediatek/mtk_plane.c b/drivers/gpu/drm/mediatek/mtk_plane.c index 02349bd44001..788b52c1d10c 100644 --- a/drivers/gpu/drm/mediatek/mtk_plane.c +++ b/drivers/gpu/drm/mediatek/mtk_plane.c @@ -21,9 +21,6 @@ static const u64 modifiers[] = { DRM_FORMAT_MOD_LINEAR, - DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 | - AFBC_FORMAT_MOD_SPLIT | - AFBC_FORMAT_MOD_SPARSE), DRM_FORMAT_MOD_INVALID, }; @@ -71,26 +68,7 @@ static bool mtk_plane_format_mod_supported(struct drm_plane *plane, uint32_t format, uint64_t modifier) { - if (modifier == DRM_FORMAT_MOD_LINEAR) - return true; - - if (modifier != DRM_FORMAT_MOD_ARM_AFBC( - AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 | - AFBC_FORMAT_MOD_SPLIT | - AFBC_FORMAT_MOD_SPARSE)) - return false; - - if (format != DRM_FORMAT_XRGB8888 && - format != DRM_FORMAT_ARGB8888 && - format != DRM_FORMAT_BGRX8888 && - format != DRM_FORMAT_BGRA8888 && - format != DRM_FORMAT_ABGR8888 && - format != DRM_FORMAT_XBGR8888 && - format != DRM_FORMAT_RGB888 && - format != DRM_FORMAT_BGR888) - return false; - - return true; + return modifier == DRM_FORMAT_MOD_LINEAR; } static void mtk_plane_destroy_state(struct drm_plane *plane, diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index e97e39abf3a2..12b1dba8e05d 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -2867,7 +2867,9 @@ nv50_display_create(struct drm_device *dev) } /* Assign the correct format modifiers */ - if (disp->disp->object.oclass >= TU102_DISP) + if (disp->disp->object.oclass >= GB202_DISP) + nouveau_display(dev)->format_modifiers = wndwca7e_modifiers; + else if (disp->disp->object.oclass >= TU102_DISP) nouveau_display(dev)->format_modifiers = wndwc57e_modifiers; else if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_FERMI) diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.h b/drivers/gpu/drm/nouveau/dispnv50/disp.h index 15f9242b72ac..5d998f0319dc 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.h +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.h @@ -104,4 +104,5 @@ struct nouveau_encoder *nv50_real_outp(struct drm_encoder *encoder); extern const u64 disp50xx_modifiers[]; extern const u64 disp90xx_modifiers[]; extern const u64 wndwc57e_modifiers[]; +extern const u64 wndwca7e_modifiers[]; #endif diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c index e2c55f4b9c5a..ef9e410babbf 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c +++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c @@ -786,13 +786,14 @@ nv50_wndw_destroy(struct drm_plane *plane) } /* This function assumes the format has already been validated against the plane - * and the modifier was validated against the device-wides modifier list at FB + * and the modifier was validated against the device-wide modifier list at FB * creation time. */ static bool nv50_plane_format_mod_supported(struct drm_plane *plane, u32 format, u64 modifier) { struct nouveau_drm *drm = nouveau_drm(plane->dev); + const struct drm_format_info *info = drm_format_info(format); uint8_t i; /* All chipsets can display all formats in linear layout */ @@ -800,13 +801,32 @@ static bool nv50_plane_format_mod_supported(struct drm_plane *plane, return true; if (drm->client.device.info.chipset < 0xc0) { - const struct drm_format_info *info = drm_format_info(format); const uint8_t kind = (modifier >> 12) & 0xff; if (!format) return false; for (i = 0; i < info->num_planes; i++) if ((info->cpp[i] != 4) && kind != 0x70) return false; + } else if (drm->client.device.info.chipset >= 0x1b2) { + const uint8_t slayout = ((modifier >> 22) & 0x1) | + ((modifier >> 25) & 0x6); + + if (!format) + return false; + + /* + * Note in practice this implies only formats where cpp is equal + * for each plane, or >= 4 for all planes, are supported. + */ + for (i = 0; i < info->num_planes; i++) { + if (((info->cpp[i] == 2) && slayout != 3) || + ((info->cpp[i] == 1) && slayout != 2) || + ((info->cpp[i] >= 4) && slayout != 1)) + return false; + + /* 24-bit not supported. It has yet another layout */ + WARN_ON(info->cpp[i] == 3); + } } return true; diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndwca7e.c b/drivers/gpu/drm/nouveau/dispnv50/wndwca7e.c index 0d8e9a9d1a57..2cec8cfbd546 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/wndwca7e.c +++ b/drivers/gpu/drm/nouveau/dispnv50/wndwca7e.c @@ -179,6 +179,39 @@ wndwca7e_ntfy_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw) return 0; } +/**************************************************************** + * Log2(block height) ----------------------------+ * + * Page Kind ----------------------------------+ | * + * Gob Height/Page Kind Generation ------+ | | * + * Sector layout -------+ | | | * + * Compression ------+ | | | | */ +const u64 wndwca7e_modifiers[] = { /* | | | | | */ + /* 4cpp+ modifiers */ + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 1, 2, 0x06, 0), + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 1, 2, 0x06, 1), + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 1, 2, 0x06, 2), + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 1, 2, 0x06, 3), + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 1, 2, 0x06, 4), + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 1, 2, 0x06, 5), + /* 1cpp/8bpp modifiers */ + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 2, 2, 0x06, 0), + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 2, 2, 0x06, 1), + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 2, 2, 0x06, 2), + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 2, 2, 0x06, 3), + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 2, 2, 0x06, 4), + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 2, 2, 0x06, 5), + /* 2cpp/16bpp modifiers */ + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 3, 2, 0x06, 0), + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 3, 2, 0x06, 1), + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 3, 2, 0x06, 2), + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 3, 2, 0x06, 3), + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 3, 2, 0x06, 4), + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 3, 2, 0x06, 5), + /* All formats support linear */ + DRM_FORMAT_MOD_LINEAR, + DRM_FORMAT_MOD_INVALID +}; + static const struct nv50_wndw_func wndwca7e = { .acquire = wndwc37e_acquire, diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index c8e949f4a568..fe174a4857be 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -173,26 +173,15 @@ int drm_sched_entity_error(struct drm_sched_entity *entity) } EXPORT_SYMBOL(drm_sched_entity_error); +static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f, + struct dma_fence_cb *cb); + static void drm_sched_entity_kill_jobs_work(struct work_struct *wrk) { struct drm_sched_job *job = container_of(wrk, typeof(*job), work); - - drm_sched_fence_scheduled(job->s_fence, NULL); - drm_sched_fence_finished(job->s_fence, -ESRCH); - WARN_ON(job->s_fence->parent); - job->sched->ops->free_job(job); -} - -/* Signal the scheduler finished fence when the entity in question is killed. */ -static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f, - struct dma_fence_cb *cb) -{ - struct drm_sched_job *job = container_of(cb, struct drm_sched_job, - finish_cb); + struct dma_fence *f; unsigned long index; - dma_fence_put(f); - /* Wait for all dependencies to avoid data corruptions */ xa_for_each(&job->dependencies, index, f) { struct drm_sched_fence *s_fence = to_drm_sched_fence(f); @@ -220,6 +209,21 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f, dma_fence_put(f); } + drm_sched_fence_scheduled(job->s_fence, NULL); + drm_sched_fence_finished(job->s_fence, -ESRCH); + WARN_ON(job->s_fence->parent); + job->sched->ops->free_job(job); +} + +/* Signal the scheduler finished fence when the entity in question is killed. */ +static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f, + struct dma_fence_cb *cb) +{ + struct drm_sched_job *job = container_of(cb, struct drm_sched_job, + finish_cb); + + dma_fence_put(f); + INIT_WORK(&job->work, drm_sched_entity_kill_jobs_work); schedule_work(&job->work); } diff --git a/drivers/gpu/drm/tiny/Kconfig b/drivers/gpu/drm/tiny/Kconfig index 7d9e85e932d7..f0e72d4b6a47 100644 --- a/drivers/gpu/drm/tiny/Kconfig +++ b/drivers/gpu/drm/tiny/Kconfig @@ -85,6 +85,7 @@ config DRM_PANEL_MIPI_DBI config DRM_PIXPAPER tristate "DRM support for PIXPAPER display panels" depends on DRM && SPI + depends on MMU select DRM_CLIENT_SELECTION select DRM_GEM_SHMEM_HELPER select DRM_KMS_HELPER diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index 34d33965eac2..456899238377 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -988,16 +988,16 @@ void xe_device_shutdown(struct xe_device *xe) drm_dbg(&xe->drm, "Shutting down device\n"); - if (xe_driver_flr_disabled(xe)) { - xe_display_pm_shutdown(xe); + xe_display_pm_shutdown(xe); - xe_irq_suspend(xe); + xe_irq_suspend(xe); - for_each_gt(gt, xe, id) - xe_gt_shutdown(gt); + for_each_gt(gt, xe, id) + xe_gt_shutdown(gt); - xe_display_pm_shutdown_late(xe); - } else { + xe_display_pm_shutdown_late(xe); + + if (!xe_driver_flr_disabled(xe)) { /* BOOM! */ __xe_driver_flr(xe); } diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c index 7715e74bb945..a8ab363a8046 100644 --- a/drivers/gpu/drm/xe/xe_exec.c +++ b/drivers/gpu/drm/xe/xe_exec.c @@ -165,7 +165,8 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file) for (num_syncs = 0; num_syncs < args->num_syncs; num_syncs++) { err = xe_sync_entry_parse(xe, xef, &syncs[num_syncs], - &syncs_user[num_syncs], SYNC_PARSE_FLAG_EXEC | + &syncs_user[num_syncs], NULL, 0, + SYNC_PARSE_FLAG_EXEC | (xe_vm_in_lr_mode(vm) ? SYNC_PARSE_FLAG_LR_MODE : 0)); if (err) diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c index 37b2b93b73d6..cb5f204c08ed 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.c +++ b/drivers/gpu/drm/xe/xe_exec_queue.c @@ -10,6 +10,7 @@ #include <drm/drm_device.h> #include <drm/drm_drv.h> #include <drm/drm_file.h> +#include <drm/drm_syncobj.h> #include <uapi/drm/xe_drm.h> #include "xe_dep_scheduler.h" @@ -324,6 +325,16 @@ struct xe_exec_queue *xe_exec_queue_create_bind(struct xe_device *xe, } xe_vm_put(migrate_vm); + if (!IS_ERR(q)) { + int err = drm_syncobj_create(&q->ufence_syncobj, + DRM_SYNCOBJ_CREATE_SIGNALED, + NULL); + if (err) { + xe_exec_queue_put(q); + return ERR_PTR(err); + } + } + return q; } ALLOW_ERROR_INJECTION(xe_exec_queue_create_bind, ERRNO); @@ -333,6 +344,9 @@ void xe_exec_queue_destroy(struct kref *ref) struct xe_exec_queue *q = container_of(ref, struct xe_exec_queue, refcount); struct xe_exec_queue *eq, *next; + if (q->ufence_syncobj) + drm_syncobj_put(q->ufence_syncobj); + if (xe_exec_queue_uses_pxp(q)) xe_pxp_exec_queue_remove(gt_to_xe(q->gt)->pxp, q); diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h index 27b76cf9da89..df1c69dc81f1 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue_types.h +++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h @@ -15,6 +15,7 @@ #include "xe_hw_fence_types.h" #include "xe_lrc_types.h" +struct drm_syncobj; struct xe_execlist_exec_queue; struct xe_gt; struct xe_guc_exec_queue; @@ -155,6 +156,12 @@ struct xe_exec_queue { struct list_head link; } pxp; + /** @ufence_syncobj: User fence syncobj */ + struct drm_syncobj *ufence_syncobj; + + /** @ufence_timeline_value: User fence timeline value */ + u64 ufence_timeline_value; + /** @ops: submission backend exec queue operations */ const struct xe_exec_queue_ops *ops; diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c index 18f6327bf552..283d846c3512 100644 --- a/drivers/gpu/drm/xe/xe_guc_ct.c +++ b/drivers/gpu/drm/xe/xe_guc_ct.c @@ -200,6 +200,9 @@ static void guc_ct_fini(struct drm_device *drm, void *arg) { struct xe_guc_ct *ct = arg; +#if IS_ENABLED(CONFIG_DRM_XE_DEBUG) + cancel_work_sync(&ct->dead.worker); +#endif ct_exit_safe_mode(ct); destroy_workqueue(ct->g2h_wq); xa_destroy(&ct->fence_lookup); diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c index a4894eb0d7f3..125698a9ecf1 100644 --- a/drivers/gpu/drm/xe/xe_oa.c +++ b/drivers/gpu/drm/xe/xe_oa.c @@ -10,6 +10,7 @@ #include <drm/drm_drv.h> #include <drm/drm_managed.h> +#include <drm/drm_syncobj.h> #include <uapi/drm/xe_drm.h> #include <generated/xe_wa_oob.h> @@ -1389,7 +1390,9 @@ static int xe_oa_user_extensions(struct xe_oa *oa, enum xe_oa_user_extn_from fro return 0; } -static int xe_oa_parse_syncs(struct xe_oa *oa, struct xe_oa_open_param *param) +static int xe_oa_parse_syncs(struct xe_oa *oa, + struct xe_oa_stream *stream, + struct xe_oa_open_param *param) { int ret, num_syncs, num_ufence = 0; @@ -1409,7 +1412,9 @@ static int xe_oa_parse_syncs(struct xe_oa *oa, struct xe_oa_open_param *param) for (num_syncs = 0; num_syncs < param->num_syncs; num_syncs++) { ret = xe_sync_entry_parse(oa->xe, param->xef, ¶m->syncs[num_syncs], - ¶m->syncs_user[num_syncs], 0); + ¶m->syncs_user[num_syncs], + stream->ufence_syncobj, + ++stream->ufence_timeline_value, 0); if (ret) goto err_syncs; @@ -1539,7 +1544,7 @@ static long xe_oa_config_locked(struct xe_oa_stream *stream, u64 arg) return -ENODEV; param.xef = stream->xef; - err = xe_oa_parse_syncs(stream->oa, ¶m); + err = xe_oa_parse_syncs(stream->oa, stream, ¶m); if (err) goto err_config_put; @@ -1635,6 +1640,7 @@ static void xe_oa_destroy_locked(struct xe_oa_stream *stream) if (stream->exec_q) xe_exec_queue_put(stream->exec_q); + drm_syncobj_put(stream->ufence_syncobj); kfree(stream); } @@ -1826,6 +1832,7 @@ static int xe_oa_stream_open_ioctl_locked(struct xe_oa *oa, struct xe_oa_open_param *param) { struct xe_oa_stream *stream; + struct drm_syncobj *ufence_syncobj; int stream_fd; int ret; @@ -1836,17 +1843,31 @@ static int xe_oa_stream_open_ioctl_locked(struct xe_oa *oa, goto exit; } + ret = drm_syncobj_create(&ufence_syncobj, DRM_SYNCOBJ_CREATE_SIGNALED, + NULL); + if (ret) + goto exit; + stream = kzalloc(sizeof(*stream), GFP_KERNEL); if (!stream) { ret = -ENOMEM; - goto exit; + goto err_syncobj; } - + stream->ufence_syncobj = ufence_syncobj; stream->oa = oa; - ret = xe_oa_stream_init(stream, param); + + ret = xe_oa_parse_syncs(oa, stream, param); if (ret) goto err_free; + ret = xe_oa_stream_init(stream, param); + if (ret) { + while (param->num_syncs--) + xe_sync_entry_cleanup(¶m->syncs[param->num_syncs]); + kfree(param->syncs); + goto err_free; + } + if (!param->disabled) { ret = xe_oa_enable_locked(stream); if (ret) @@ -1870,6 +1891,8 @@ err_destroy: xe_oa_stream_destroy(stream); err_free: kfree(stream); +err_syncobj: + drm_syncobj_put(ufence_syncobj); exit: return ret; } @@ -2083,22 +2106,14 @@ int xe_oa_stream_open_ioctl(struct drm_device *dev, u64 data, struct drm_file *f goto err_exec_q; } - ret = xe_oa_parse_syncs(oa, ¶m); - if (ret) - goto err_exec_q; - mutex_lock(¶m.hwe->gt->oa.gt_lock); ret = xe_oa_stream_open_ioctl_locked(oa, ¶m); mutex_unlock(¶m.hwe->gt->oa.gt_lock); if (ret < 0) - goto err_sync_cleanup; + goto err_exec_q; return ret; -err_sync_cleanup: - while (param.num_syncs--) - xe_sync_entry_cleanup(¶m.syncs[param.num_syncs]); - kfree(param.syncs); err_exec_q: if (param.exec_q) xe_exec_queue_put(param.exec_q); diff --git a/drivers/gpu/drm/xe/xe_oa_types.h b/drivers/gpu/drm/xe/xe_oa_types.h index 2628f78c4e8d..daf701b5d48b 100644 --- a/drivers/gpu/drm/xe/xe_oa_types.h +++ b/drivers/gpu/drm/xe/xe_oa_types.h @@ -15,6 +15,8 @@ #include "regs/xe_reg_defs.h" #include "xe_hw_engine_types.h" +struct drm_syncobj; + #define DEFAULT_XE_OA_BUFFER_SIZE SZ_16M enum xe_oa_report_header { @@ -248,6 +250,12 @@ struct xe_oa_stream { /** @xef: xe_file with which the stream was opened */ struct xe_file *xef; + /** @ufence_syncobj: User fence syncobj */ + struct drm_syncobj *ufence_syncobj; + + /** @ufence_timeline_value: User fence timeline value */ + u64 ufence_timeline_value; + /** @last_fence: fence to use in stream destroy when needed */ struct dma_fence *last_fence; diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c index 82872a51f098..d48ab7b32ca5 100644 --- a/drivers/gpu/drm/xe/xe_sync.c +++ b/drivers/gpu/drm/xe/xe_sync.c @@ -113,6 +113,8 @@ static void user_fence_cb(struct dma_fence *fence, struct dma_fence_cb *cb) int xe_sync_entry_parse(struct xe_device *xe, struct xe_file *xef, struct xe_sync_entry *sync, struct drm_xe_sync __user *sync_user, + struct drm_syncobj *ufence_syncobj, + u64 ufence_timeline_value, unsigned int flags) { struct drm_xe_sync sync_in; @@ -192,10 +194,15 @@ int xe_sync_entry_parse(struct xe_device *xe, struct xe_file *xef, if (exec) { sync->addr = sync_in.addr; } else { + sync->ufence_timeline_value = ufence_timeline_value; sync->ufence = user_fence_create(xe, sync_in.addr, sync_in.timeline_value); if (XE_IOCTL_DBG(xe, IS_ERR(sync->ufence))) return PTR_ERR(sync->ufence); + sync->ufence_chain_fence = dma_fence_chain_alloc(); + if (!sync->ufence_chain_fence) + return -ENOMEM; + sync->ufence_syncobj = ufence_syncobj; } break; @@ -239,7 +246,12 @@ void xe_sync_entry_signal(struct xe_sync_entry *sync, struct dma_fence *fence) } else if (sync->ufence) { int err; - dma_fence_get(fence); + drm_syncobj_add_point(sync->ufence_syncobj, + sync->ufence_chain_fence, + fence, sync->ufence_timeline_value); + sync->ufence_chain_fence = NULL; + + fence = drm_syncobj_fence_get(sync->ufence_syncobj); user_fence_get(sync->ufence); err = dma_fence_add_callback(fence, &sync->ufence->cb, user_fence_cb); @@ -259,7 +271,8 @@ void xe_sync_entry_cleanup(struct xe_sync_entry *sync) drm_syncobj_put(sync->syncobj); dma_fence_put(sync->fence); dma_fence_chain_free(sync->chain_fence); - if (sync->ufence) + dma_fence_chain_free(sync->ufence_chain_fence); + if (!IS_ERR_OR_NULL(sync->ufence)) user_fence_put(sync->ufence); } diff --git a/drivers/gpu/drm/xe/xe_sync.h b/drivers/gpu/drm/xe/xe_sync.h index 256ffc1e54dc..51f2d803e977 100644 --- a/drivers/gpu/drm/xe/xe_sync.h +++ b/drivers/gpu/drm/xe/xe_sync.h @@ -8,6 +8,7 @@ #include "xe_sync_types.h" +struct drm_syncobj; struct xe_device; struct xe_exec_queue; struct xe_file; @@ -21,6 +22,8 @@ struct xe_vm; int xe_sync_entry_parse(struct xe_device *xe, struct xe_file *xef, struct xe_sync_entry *sync, struct drm_xe_sync __user *sync_user, + struct drm_syncobj *ufence_syncobj, + u64 ufence_timeline_value, unsigned int flags); int xe_sync_entry_add_deps(struct xe_sync_entry *sync, struct xe_sched_job *job); diff --git a/drivers/gpu/drm/xe/xe_sync_types.h b/drivers/gpu/drm/xe/xe_sync_types.h index 30ac3f51993b..b88f1833e28c 100644 --- a/drivers/gpu/drm/xe/xe_sync_types.h +++ b/drivers/gpu/drm/xe/xe_sync_types.h @@ -18,9 +18,12 @@ struct xe_sync_entry { struct drm_syncobj *syncobj; struct dma_fence *fence; struct dma_fence_chain *chain_fence; + struct dma_fence_chain *ufence_chain_fence; + struct drm_syncobj *ufence_syncobj; struct xe_user_fence *ufence; u64 addr; u64 timeline_value; + u64 ufence_timeline_value; u32 type; u32 flags; }; diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 63c65e3d207b..ccb09ef4ec9e 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -3606,8 +3606,12 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file) syncs_user = u64_to_user_ptr(args->syncs); for (num_syncs = 0; num_syncs < args->num_syncs; num_syncs++) { + struct xe_exec_queue *__q = q ?: vm->q[0]; + err = xe_sync_entry_parse(xe, xef, &syncs[num_syncs], &syncs_user[num_syncs], + __q->ufence_syncobj, + ++__q->ufence_timeline_value, (xe_vm_in_lr_mode(vm) ? SYNC_PARSE_FLAG_LR_MODE : 0) | (!args->num_binds ? diff --git a/drivers/hwmon/gpd-fan.c b/drivers/hwmon/gpd-fan.c index 321794807e8d..f81c3bc422f4 100644 --- a/drivers/hwmon/gpd-fan.c +++ b/drivers/hwmon/gpd-fan.c @@ -12,9 +12,9 @@ * Copyright (c) 2024 Cryolitia PukNgae */ -#include <linux/acpi.h> #include <linux/dmi.h> #include <linux/hwmon.h> +#include <linux/io.h> #include <linux/ioport.h> #include <linux/kernel.h> #include <linux/module.h> @@ -276,31 +276,6 @@ static int gpd_generic_read_rpm(void) return (u16)high << 8 | low; } -static void gpd_win4_init_ec(void) -{ - u8 chip_id, chip_ver; - - gpd_ecram_read(0x2000, &chip_id); - - if (chip_id == 0x55) { - gpd_ecram_read(0x1060, &chip_ver); - gpd_ecram_write(0x1060, chip_ver | 0x80); - } -} - -static int gpd_win4_read_rpm(void) -{ - int ret; - - ret = gpd_generic_read_rpm(); - - if (ret == 0) - // Re-init EC when speed is 0 - gpd_win4_init_ec(); - - return ret; -} - static int gpd_wm2_read_rpm(void) { for (u16 pwm_ctr_offset = GPD_PWM_CTR_OFFSET; @@ -320,11 +295,10 @@ static int gpd_wm2_read_rpm(void) static int gpd_read_rpm(void) { switch (gpd_driver_priv.drvdata->board) { + case win4_6800u: case win_mini: case duo: return gpd_generic_read_rpm(); - case win4_6800u: - return gpd_win4_read_rpm(); case win_max_2: return gpd_wm2_read_rpm(); } @@ -607,6 +581,28 @@ static struct hwmon_chip_info gpd_fan_chip_info = { .info = gpd_fan_hwmon_channel_info }; +static void gpd_win4_init_ec(void) +{ + u8 chip_id, chip_ver; + + gpd_ecram_read(0x2000, &chip_id); + + if (chip_id == 0x55) { + gpd_ecram_read(0x1060, &chip_ver); + gpd_ecram_write(0x1060, chip_ver | 0x80); + } +} + +static void gpd_init_ec(void) +{ + // The buggy firmware won't initialize EC properly on boot. + // Before its initialization, reading RPM will always return 0, + // and writing PWM will have no effect. + // Initialize it manually on driver load. + if (gpd_driver_priv.drvdata->board == win4_6800u) + gpd_win4_init_ec(); +} + static int gpd_fan_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -634,6 +630,8 @@ static int gpd_fan_probe(struct platform_device *pdev) return dev_err_probe(dev, PTR_ERR(hwdev), "Failed to register hwmon device\n"); + gpd_init_ec(); + return 0; } diff --git a/drivers/i2c/muxes/i2c-mux-pca954x.c b/drivers/i2c/muxes/i2c-mux-pca954x.c index 75c8d08fa24e..b9f370c9f018 100644 --- a/drivers/i2c/muxes/i2c-mux-pca954x.c +++ b/drivers/i2c/muxes/i2c-mux-pca954x.c @@ -118,6 +118,7 @@ struct pca954x { raw_spinlock_t lock; struct regulator *supply; + struct gpio_desc *reset_gpio; struct reset_control *reset_cont; }; @@ -315,25 +316,6 @@ static u8 pca954x_regval(struct pca954x *data, u8 chan) return 1 << chan; } -static void pca954x_reset_assert(struct pca954x *data) -{ - if (data->reset_cont) - reset_control_assert(data->reset_cont); -} - -static void pca954x_reset_deassert(struct pca954x *data) -{ - if (data->reset_cont) - reset_control_deassert(data->reset_cont); -} - -static void pca954x_reset_mux(struct pca954x *data) -{ - pca954x_reset_assert(data); - udelay(1); - pca954x_reset_deassert(data); -} - static int pca954x_select_chan(struct i2c_mux_core *muxc, u32 chan) { struct pca954x *data = i2c_mux_priv(muxc); @@ -347,8 +329,6 @@ static int pca954x_select_chan(struct i2c_mux_core *muxc, u32 chan) ret = pca954x_reg_write(muxc->parent, client, regval); data->last_chan = ret < 0 ? 0 : regval; } - if (ret == -ETIMEDOUT && data->reset_cont) - pca954x_reset_mux(data); return ret; } @@ -358,7 +338,6 @@ static int pca954x_deselect_mux(struct i2c_mux_core *muxc, u32 chan) struct pca954x *data = i2c_mux_priv(muxc); struct i2c_client *client = data->client; s32 idle_state; - int ret = 0; idle_state = READ_ONCE(data->idle_state); if (idle_state >= 0) @@ -368,10 +347,8 @@ static int pca954x_deselect_mux(struct i2c_mux_core *muxc, u32 chan) if (idle_state == MUX_IDLE_DISCONNECT) { /* Deselect active channel */ data->last_chan = 0; - ret = pca954x_reg_write(muxc->parent, client, - data->last_chan); - if (ret == -ETIMEDOUT && data->reset_cont) - pca954x_reset_mux(data); + return pca954x_reg_write(muxc->parent, client, + data->last_chan); } /* otherwise leave as-is */ @@ -550,10 +527,29 @@ static int pca954x_get_reset(struct device *dev, struct pca954x *data) if (IS_ERR(data->reset_cont)) return dev_err_probe(dev, PTR_ERR(data->reset_cont), "Failed to get reset\n"); + else if (data->reset_cont) + return 0; + + /* + * fallback to legacy reset-gpios + */ + data->reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH); + if (IS_ERR(data->reset_gpio)) { + return dev_err_probe(dev, PTR_ERR(data->reset_gpio), + "Failed to get reset gpio"); + } return 0; } +static void pca954x_reset_deassert(struct pca954x *data) +{ + if (data->reset_cont) + reset_control_deassert(data->reset_cont); + else + gpiod_set_value_cansleep(data->reset_gpio, 0); +} + /* * I2C init/probing/exit functions */ @@ -593,7 +589,7 @@ static int pca954x_probe(struct i2c_client *client) if (ret) goto fail_cleanup; - if (data->reset_cont) { + if (data->reset_cont || data->reset_gpio) { udelay(1); pca954x_reset_deassert(data); /* Give the chip some time to recover. */ diff --git a/drivers/infiniband/core/uverbs_std_types_cq.c b/drivers/infiniband/core/uverbs_std_types_cq.c index 37cd37556510..fab5d914029d 100644 --- a/drivers/infiniband/core/uverbs_std_types_cq.c +++ b/drivers/infiniband/core/uverbs_std_types_cq.c @@ -206,6 +206,7 @@ static int UVERBS_HANDLER(UVERBS_METHOD_CQ_CREATE)( return ret; err_free: + ib_umem_release(umem); rdma_restrack_put(&cq->res); kfree(cq); err_event_file: diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index 4dab5ca7362b..84ce3fce2826 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -913,7 +913,7 @@ void bnxt_re_unlock_cqs(struct bnxt_re_qp *qp, spin_unlock_irqrestore(&qp->scq->cq_lock, flags); } -static int bnxt_re_destroy_gsi_sqp(struct bnxt_re_qp *qp) +static void bnxt_re_destroy_gsi_sqp(struct bnxt_re_qp *qp) { struct bnxt_re_qp *gsi_sqp; struct bnxt_re_ah *gsi_sah; @@ -933,10 +933,9 @@ static int bnxt_re_destroy_gsi_sqp(struct bnxt_re_qp *qp) ibdev_dbg(&rdev->ibdev, "Destroy the shadow QP\n"); rc = bnxt_qplib_destroy_qp(&rdev->qplib_res, &gsi_sqp->qplib_qp); - if (rc) { + if (rc) ibdev_err(&rdev->ibdev, "Destroy Shadow QP failed"); - goto fail; - } + bnxt_qplib_free_qp_res(&rdev->qplib_res, &gsi_sqp->qplib_qp); /* remove from active qp list */ @@ -951,10 +950,6 @@ static int bnxt_re_destroy_gsi_sqp(struct bnxt_re_qp *qp) rdev->gsi_ctx.gsi_sqp = NULL; rdev->gsi_ctx.gsi_sah = NULL; rdev->gsi_ctx.sqp_tbl = NULL; - - return 0; -fail: - return rc; } static void bnxt_re_del_unique_gid(struct bnxt_re_dev *rdev) diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c index d9a12681f843..22d3e25c3b9d 100644 --- a/drivers/infiniband/hw/efa/efa_verbs.c +++ b/drivers/infiniband/hw/efa/efa_verbs.c @@ -1216,13 +1216,13 @@ int efa_create_cq_umem(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, if (umem->length < cq->size) { ibdev_dbg(&dev->ibdev, "External memory too small\n"); err = -EINVAL; - goto err_free_mem; + goto err_out; } if (!ib_umem_is_contiguous(umem)) { ibdev_dbg(&dev->ibdev, "Non contiguous CQ unsupported\n"); err = -EINVAL; - goto err_free_mem; + goto err_out; } cq->cpu_addr = NULL; @@ -1251,7 +1251,7 @@ int efa_create_cq_umem(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, err = efa_com_create_cq(&dev->edev, ¶ms, &result); if (err) - goto err_free_mem; + goto err_free_mapped; resp.db_off = result.db_off; resp.cq_idx = result.cq_idx; @@ -1299,12 +1299,10 @@ err_remove_mmap: efa_cq_user_mmap_entries_remove(cq); err_destroy_cq: efa_destroy_cq_idx(dev, cq->cq_idx); -err_free_mem: - if (umem) - ib_umem_release(umem); - else - efa_free_mapped(dev, cq->cpu_addr, cq->dma_addr, cq->size, DMA_FROM_DEVICE); - +err_free_mapped: + if (!umem) + efa_free_mapped(dev, cq->cpu_addr, cq->dma_addr, cq->size, + DMA_FROM_DEVICE); err_out: atomic64_inc(&dev->stats.create_cq_err); return err; diff --git a/drivers/infiniband/hw/hns/hns_roce_cq.c b/drivers/infiniband/hw/hns/hns_roce_cq.c index 3a5c93c9fb3e..6aa82fe9dd3d 100644 --- a/drivers/infiniband/hw/hns/hns_roce_cq.c +++ b/drivers/infiniband/hw/hns/hns_roce_cq.c @@ -30,6 +30,7 @@ * SOFTWARE. */ +#include <linux/pci.h> #include <rdma/ib_umem.h> #include <rdma/uverbs_ioctl.h> #include "hns_roce_device.h" @@ -37,6 +38,43 @@ #include "hns_roce_hem.h" #include "hns_roce_common.h" +void hns_roce_put_cq_bankid_for_uctx(struct hns_roce_ucontext *uctx) +{ + struct hns_roce_dev *hr_dev = to_hr_dev(uctx->ibucontext.device); + struct hns_roce_cq_table *cq_table = &hr_dev->cq_table; + + if (hr_dev->pci_dev->revision < PCI_REVISION_ID_HIP09) + return; + + mutex_lock(&cq_table->bank_mutex); + cq_table->ctx_num[uctx->cq_bank_id]--; + mutex_unlock(&cq_table->bank_mutex); +} + +void hns_roce_get_cq_bankid_for_uctx(struct hns_roce_ucontext *uctx) +{ + struct hns_roce_dev *hr_dev = to_hr_dev(uctx->ibucontext.device); + struct hns_roce_cq_table *cq_table = &hr_dev->cq_table; + u32 least_load = cq_table->ctx_num[0]; + u8 bankid = 0; + u8 i; + + if (hr_dev->pci_dev->revision < PCI_REVISION_ID_HIP09) + return; + + mutex_lock(&cq_table->bank_mutex); + for (i = 1; i < HNS_ROCE_CQ_BANK_NUM; i++) { + if (cq_table->ctx_num[i] < least_load) { + least_load = cq_table->ctx_num[i]; + bankid = i; + } + } + cq_table->ctx_num[bankid]++; + mutex_unlock(&cq_table->bank_mutex); + + uctx->cq_bank_id = bankid; +} + static u8 get_least_load_bankid_for_cq(struct hns_roce_bank *bank) { u32 least_load = bank[0].inuse; @@ -55,7 +93,21 @@ static u8 get_least_load_bankid_for_cq(struct hns_roce_bank *bank) return bankid; } -static int alloc_cqn(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq) +static u8 select_cq_bankid(struct hns_roce_dev *hr_dev, + struct hns_roce_bank *bank, struct ib_udata *udata) +{ + struct hns_roce_ucontext *uctx = udata ? + rdma_udata_to_drv_context(udata, struct hns_roce_ucontext, + ibucontext) : NULL; + + if (hr_dev->pci_dev->revision >= PCI_REVISION_ID_HIP09) + return uctx ? uctx->cq_bank_id : 0; + + return get_least_load_bankid_for_cq(bank); +} + +static int alloc_cqn(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq, + struct ib_udata *udata) { struct hns_roce_cq_table *cq_table = &hr_dev->cq_table; struct hns_roce_bank *bank; @@ -63,7 +115,7 @@ static int alloc_cqn(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq) int id; mutex_lock(&cq_table->bank_mutex); - bankid = get_least_load_bankid_for_cq(cq_table->bank); + bankid = select_cq_bankid(hr_dev, cq_table->bank, udata); bank = &cq_table->bank[bankid]; id = ida_alloc_range(&bank->ida, bank->min, bank->max, GFP_KERNEL); @@ -396,7 +448,7 @@ int hns_roce_create_cq(struct ib_cq *ib_cq, const struct ib_cq_init_attr *attr, goto err_cq_buf; } - ret = alloc_cqn(hr_dev, hr_cq); + ret = alloc_cqn(hr_dev, hr_cq, udata); if (ret) { ibdev_err(ibdev, "failed to alloc CQN, ret = %d.\n", ret); goto err_cq_db; diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h index 78ee04a48a74..06832c0ac055 100644 --- a/drivers/infiniband/hw/hns/hns_roce_device.h +++ b/drivers/infiniband/hw/hns/hns_roce_device.h @@ -217,6 +217,7 @@ struct hns_roce_ucontext { struct mutex page_mutex; struct hns_user_mmap_entry *db_mmap_entry; u32 config; + u8 cq_bank_id; }; struct hns_roce_pd { @@ -495,6 +496,7 @@ struct hns_roce_cq_table { struct hns_roce_hem_table table; struct hns_roce_bank bank[HNS_ROCE_CQ_BANK_NUM]; struct mutex bank_mutex; + u32 ctx_num[HNS_ROCE_CQ_BANK_NUM]; }; struct hns_roce_srq_table { @@ -1305,5 +1307,7 @@ hns_roce_user_mmap_entry_insert(struct ib_ucontext *ucontext, u64 address, size_t length, enum hns_roce_mmap_type mmap_type); bool check_sl_valid(struct hns_roce_dev *hr_dev, u8 sl); +void hns_roce_put_cq_bankid_for_uctx(struct hns_roce_ucontext *uctx); +void hns_roce_get_cq_bankid_for_uctx(struct hns_roce_ucontext *uctx); #endif /* _HNS_ROCE_DEVICE_H */ diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index f82bdd46a917..63052c0e7613 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -165,6 +165,8 @@ static void set_frmr_seg(struct hns_roce_v2_rc_send_wqe *rc_sq_wqe, hr_reg_write(fseg, FRMR_PBL_BUF_PG_SZ, to_hr_hw_page_shift(mr->pbl_mtr.hem_cfg.buf_pg_shift)); hr_reg_clear(fseg, FRMR_BLK_MODE); + hr_reg_clear(fseg, FRMR_BLOCK_SIZE); + hr_reg_clear(fseg, FRMR_ZBVA); } static void set_atomic_seg(const struct ib_send_wr *wr, @@ -339,9 +341,6 @@ static int set_rwqe_data_seg(struct ib_qp *ibqp, const struct ib_send_wr *wr, int j = 0; int i; - hr_reg_write(rc_sq_wqe, RC_SEND_WQE_MSG_START_SGE_IDX, - (*sge_ind) & (qp->sge.sge_cnt - 1)); - hr_reg_write(rc_sq_wqe, RC_SEND_WQE_INLINE, !!(wr->send_flags & IB_SEND_INLINE)); if (wr->send_flags & IB_SEND_INLINE) @@ -586,6 +585,9 @@ static inline int set_rc_wqe(struct hns_roce_qp *qp, hr_reg_write(rc_sq_wqe, RC_SEND_WQE_CQE, (wr->send_flags & IB_SEND_SIGNALED) ? 1 : 0); + hr_reg_write(rc_sq_wqe, RC_SEND_WQE_MSG_START_SGE_IDX, + curr_idx & (qp->sge.sge_cnt - 1)); + if (wr->opcode == IB_WR_ATOMIC_CMP_AND_SWP || wr->opcode == IB_WR_ATOMIC_FETCH_AND_ADD) { if (msg_len != ATOMIC_WR_LEN) @@ -734,6 +736,9 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp, owner_bit = ~(((qp->sq.head + nreq) >> ilog2(qp->sq.wqe_cnt)) & 0x1); + /* RC and UD share the same DirectWQE field layout */ + ((struct hns_roce_v2_rc_send_wqe *)wqe)->byte_4 = 0; + /* Corresponding to the QP type, wqe process separately */ if (ibqp->qp_type == IB_QPT_RC) ret = set_rc_wqe(qp, wr, wqe, &sge_idx, owner_bit); @@ -7048,7 +7053,6 @@ static int __hns_roce_hw_v2_init_instance(struct hnae3_handle *handle) goto error_failed_roce_init; } - handle->priv = hr_dev; return 0; diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c index d50f36f8a110..f3607fe107a7 100644 --- a/drivers/infiniband/hw/hns/hns_roce_main.c +++ b/drivers/infiniband/hw/hns/hns_roce_main.c @@ -425,6 +425,8 @@ static int hns_roce_alloc_ucontext(struct ib_ucontext *uctx, if (ret) goto error_fail_copy_to_udata; + hns_roce_get_cq_bankid_for_uctx(context); + return 0; error_fail_copy_to_udata: @@ -447,6 +449,8 @@ static void hns_roce_dealloc_ucontext(struct ib_ucontext *ibcontext) struct hns_roce_ucontext *context = to_hr_ucontext(ibcontext); struct hns_roce_dev *hr_dev = to_hr_dev(ibcontext->device); + hns_roce_put_cq_bankid_for_uctx(context); + if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_CQ_RECORD_DB || hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_QP_RECORD_DB) mutex_destroy(&context->page_mutex); diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c index 6ff1b8ce580c..bdd879ac12dd 100644 --- a/drivers/infiniband/hw/hns/hns_roce_qp.c +++ b/drivers/infiniband/hw/hns/hns_roce_qp.c @@ -662,7 +662,6 @@ static int set_user_sq_size(struct hns_roce_dev *hr_dev, hr_qp->sq.wqe_shift = ucmd->log_sq_stride; hr_qp->sq.wqe_cnt = cnt; - cap->max_send_sge = hr_qp->sq.max_gs; return 0; } @@ -744,7 +743,6 @@ static int set_kernel_sq_size(struct hns_roce_dev *hr_dev, /* sync the parameters of kernel QP to user's configuration */ cap->max_send_wr = cnt; - cap->max_send_sge = hr_qp->sq.max_gs; return 0; } diff --git a/drivers/infiniband/hw/irdma/pble.c b/drivers/infiniband/hw/irdma/pble.c index 3091f9345f12..fa6325adaede 100644 --- a/drivers/infiniband/hw/irdma/pble.c +++ b/drivers/infiniband/hw/irdma/pble.c @@ -71,7 +71,7 @@ int irdma_hmc_init_pble(struct irdma_sc_dev *dev, static void get_sd_pd_idx(struct irdma_hmc_pble_rsrc *pble_rsrc, struct sd_pd_idx *idx) { - idx->sd_idx = (u32)pble_rsrc->next_fpm_addr / IRDMA_HMC_DIRECT_BP_SIZE; + idx->sd_idx = pble_rsrc->next_fpm_addr / IRDMA_HMC_DIRECT_BP_SIZE; idx->pd_idx = (u32)(pble_rsrc->next_fpm_addr / IRDMA_HMC_PAGED_BP_SIZE); idx->rel_pd_idx = (idx->pd_idx % IRDMA_HMC_PD_CNT_IN_SD); } diff --git a/drivers/infiniband/hw/irdma/type.h b/drivers/infiniband/hw/irdma/type.h index 4ae77cdde9dc..c1b8f81ea283 100644 --- a/drivers/infiniband/hw/irdma/type.h +++ b/drivers/infiniband/hw/irdma/type.h @@ -706,7 +706,7 @@ struct irdma_sc_dev { u32 vchnl_ver; u16 num_vfs; u16 hmc_fn_id; - u8 vf_id; + u16 vf_id; bool privileged:1; bool vchnl_up:1; bool ceq_valid:1; diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index 76ce6137f2ba..c883c9ea5a83 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -2503,6 +2503,7 @@ static int irdma_create_cq(struct ib_cq *ibcq, spin_lock_init(&iwcq->lock); INIT_LIST_HEAD(&iwcq->resize_list); INIT_LIST_HEAD(&iwcq->cmpl_generated); + iwcq->cq_num = cq_num; info.dev = dev; ukinfo->cq_size = max(entries, 4); ukinfo->cq_id = cq_num; diff --git a/drivers/infiniband/hw/irdma/verbs.h b/drivers/infiniband/hw/irdma/verbs.h index ed21c1b56e8e..ac8b38701835 100644 --- a/drivers/infiniband/hw/irdma/verbs.h +++ b/drivers/infiniband/hw/irdma/verbs.h @@ -140,7 +140,7 @@ struct irdma_srq { struct irdma_cq { struct ib_cq ibcq; struct irdma_sc_cq sc_cq; - u16 cq_num; + u32 cq_num; bool user_mode; atomic_t armed; enum irdma_cmpl_notify last_notify; diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c index a23b364e24ff..651d76bca114 100644 --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@ -1020,15 +1020,18 @@ int mlx5_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, if (cq->create_flags & IB_UVERBS_CQ_FLAGS_IGNORE_OVERRUN) MLX5_SET(cqc, cqc, oi, 1); + if (udata) { + cq->mcq.comp = mlx5_add_cq_to_tasklet; + cq->mcq.tasklet_ctx.comp = mlx5_ib_cq_comp; + } else { + cq->mcq.comp = mlx5_ib_cq_comp; + } + err = mlx5_core_create_cq(dev->mdev, &cq->mcq, cqb, inlen, out, sizeof(out)); if (err) goto err_cqb; mlx5_ib_dbg(dev, "cqn 0x%x\n", cq->mcq.cqn); - if (udata) - cq->mcq.tasklet_ctx.comp = mlx5_ib_cq_comp; - else - cq->mcq.comp = mlx5_ib_cq_comp; cq->mcq.event = mlx5_ib_cq_event; INIT_LIST_HEAD(&cq->wc_list); diff --git a/drivers/iommu/iommufd/io_pagetable.c b/drivers/iommu/iommufd/io_pagetable.c index c0360c450880..75d60f2ad900 100644 --- a/drivers/iommu/iommufd/io_pagetable.c +++ b/drivers/iommu/iommufd/io_pagetable.c @@ -707,7 +707,8 @@ static int iopt_unmap_iova_range(struct io_pagetable *iopt, unsigned long start, struct iopt_area *area; unsigned long unmapped_bytes = 0; unsigned int tries = 0; - int rc = -ENOENT; + /* If there are no mapped entries then success */ + int rc = 0; /* * The domains_rwsem must be held in read mode any time any area->pages @@ -777,8 +778,6 @@ again: down_write(&iopt->iova_rwsem); } - if (unmapped_bytes) - rc = 0; out_unlock_iova: up_write(&iopt->iova_rwsem); @@ -815,13 +814,8 @@ int iopt_unmap_iova(struct io_pagetable *iopt, unsigned long iova, int iopt_unmap_all(struct io_pagetable *iopt, unsigned long *unmapped) { - int rc; - - rc = iopt_unmap_iova_range(iopt, 0, ULONG_MAX, unmapped); /* If the IOVAs are empty then unmap all succeeds */ - if (rc == -ENOENT) - return 0; - return rc; + return iopt_unmap_iova_range(iopt, 0, ULONG_MAX, unmapped); } /* The caller must always free all the nodes in the allowed_iova rb_root. */ diff --git a/drivers/iommu/iommufd/ioas.c b/drivers/iommu/iommufd/ioas.c index 1542c5fd10a8..459a7c516915 100644 --- a/drivers/iommu/iommufd/ioas.c +++ b/drivers/iommu/iommufd/ioas.c @@ -367,6 +367,10 @@ int iommufd_ioas_unmap(struct iommufd_ucmd *ucmd) &unmapped); if (rc) goto out_put; + if (!unmapped) { + rc = -ENOENT; + goto out_put; + } } cmd->length = unmapped; diff --git a/drivers/iommu/iommufd/iova_bitmap.c b/drivers/iommu/iommufd/iova_bitmap.c index 4514575818fc..b5b67a9d3fb3 100644 --- a/drivers/iommu/iommufd/iova_bitmap.c +++ b/drivers/iommu/iommufd/iova_bitmap.c @@ -130,9 +130,8 @@ struct iova_bitmap { static unsigned long iova_bitmap_offset_to_index(struct iova_bitmap *bitmap, unsigned long iova) { - unsigned long pgsize = 1UL << bitmap->mapped.pgshift; - - return iova / (BITS_PER_TYPE(*bitmap->bitmap) * pgsize); + return (iova >> bitmap->mapped.pgshift) / + BITS_PER_TYPE(*bitmap->bitmap); } /* diff --git a/drivers/isdn/hardware/mISDN/hfcsusb.c b/drivers/isdn/hardware/mISDN/hfcsusb.c index e54419a4e731..541a20cb58f1 100644 --- a/drivers/isdn/hardware/mISDN/hfcsusb.c +++ b/drivers/isdn/hardware/mISDN/hfcsusb.c @@ -1904,13 +1904,13 @@ out: mISDN_freebchannel(&hw->bch[1]); mISDN_freebchannel(&hw->bch[0]); mISDN_freedchannel(&hw->dch); - kfree(hw); return err; } static int hfcsusb_probe(struct usb_interface *intf, const struct usb_device_id *id) { + int err; struct hfcsusb *hw; struct usb_device *dev = interface_to_usbdev(intf); struct usb_host_interface *iface = intf->cur_altsetting; @@ -2101,20 +2101,28 @@ hfcsusb_probe(struct usb_interface *intf, const struct usb_device_id *id) if (!hw->ctrl_urb) { pr_warn("%s: No memory for control urb\n", driver_info->vend_name); - kfree(hw); - return -ENOMEM; + err = -ENOMEM; + goto err_free_hw; } pr_info("%s: %s: detected \"%s\" (%s, if=%d alt=%d)\n", hw->name, __func__, driver_info->vend_name, conf_str[small_match], ifnum, alt_used); - if (setup_instance(hw, dev->dev.parent)) - return -EIO; + if (setup_instance(hw, dev->dev.parent)) { + err = -EIO; + goto err_free_urb; + } hw->intf = intf; usb_set_intfdata(hw->intf, hw); return 0; + +err_free_urb: + usb_free_urb(hw->ctrl_urb); +err_free_hw: + kfree(hw); + return err; } /* function called when an active device is removed */ diff --git a/drivers/media/common/videobuf2/videobuf2-v4l2.c b/drivers/media/common/videobuf2/videobuf2-v4l2.c index d911021c1bb0..83862d57b126 100644 --- a/drivers/media/common/videobuf2/videobuf2-v4l2.c +++ b/drivers/media/common/videobuf2/videobuf2-v4l2.c @@ -1010,6 +1010,11 @@ int vb2_ioctl_remove_bufs(struct file *file, void *priv, if (vb2_queue_is_busy(vdev->queue, file)) return -EBUSY; + if (vb2_fileio_is_active(vdev->queue)) { + dprintk(vdev->queue, 1, "file io in progress\n"); + return -EBUSY; + } + return vb2_core_remove_bufs(vdev->queue, d->index, d->count); } EXPORT_SYMBOL_GPL(vb2_ioctl_remove_bufs); diff --git a/drivers/media/pci/cx18/cx18-driver.c b/drivers/media/pci/cx18/cx18-driver.c index b62fd12c93c1..74c59a94b2b0 100644 --- a/drivers/media/pci/cx18/cx18-driver.c +++ b/drivers/media/pci/cx18/cx18-driver.c @@ -1136,11 +1136,8 @@ int cx18_init_on_first_open(struct cx18 *cx) int video_input; int fw_retry_count = 3; struct v4l2_frequency vf; - struct cx18_open_id fh; v4l2_std_id std; - fh.cx = cx; - if (test_bit(CX18_F_I_FAILED, &cx->i_flags)) return -ENXIO; @@ -1220,14 +1217,14 @@ int cx18_init_on_first_open(struct cx18 *cx) video_input = cx->active_input; cx->active_input++; /* Force update of input */ - cx18_s_input(NULL, &fh, video_input); + cx18_do_s_input(cx, video_input); /* Let the VIDIOC_S_STD ioctl do all the work, keeps the code in one place. */ cx->std++; /* Force full standard initialization */ std = (cx->tuner_std == V4L2_STD_ALL) ? V4L2_STD_NTSC_M : cx->tuner_std; - cx18_s_std(NULL, &fh, std); - cx18_s_frequency(NULL, &fh, &vf); + cx18_do_s_std(cx, std); + cx18_do_s_frequency(cx, &vf); return 0; } diff --git a/drivers/media/pci/cx18/cx18-ioctl.c b/drivers/media/pci/cx18/cx18-ioctl.c index 0f3019739d03..0d676a57e24e 100644 --- a/drivers/media/pci/cx18/cx18-ioctl.c +++ b/drivers/media/pci/cx18/cx18-ioctl.c @@ -521,10 +521,8 @@ static int cx18_g_input(struct file *file, void *fh, unsigned int *i) return 0; } -int cx18_s_input(struct file *file, void *fh, unsigned int inp) +int cx18_do_s_input(struct cx18 *cx, unsigned int inp) { - struct cx18_open_id *id = file2id(file); - struct cx18 *cx = id->cx; v4l2_std_id std = V4L2_STD_ALL; const struct cx18_card_video_input *card_input = cx->card->video_inputs + inp; @@ -558,6 +556,11 @@ int cx18_s_input(struct file *file, void *fh, unsigned int inp) return 0; } +static int cx18_s_input(struct file *file, void *fh, unsigned int inp) +{ + return cx18_do_s_input(file2id(file)->cx, inp); +} + static int cx18_g_frequency(struct file *file, void *fh, struct v4l2_frequency *vf) { @@ -570,11 +573,8 @@ static int cx18_g_frequency(struct file *file, void *fh, return 0; } -int cx18_s_frequency(struct file *file, void *fh, const struct v4l2_frequency *vf) +int cx18_do_s_frequency(struct cx18 *cx, const struct v4l2_frequency *vf) { - struct cx18_open_id *id = file2id(file); - struct cx18 *cx = id->cx; - if (vf->tuner != 0) return -EINVAL; @@ -585,6 +585,12 @@ int cx18_s_frequency(struct file *file, void *fh, const struct v4l2_frequency *v return 0; } +static int cx18_s_frequency(struct file *file, void *fh, + const struct v4l2_frequency *vf) +{ + return cx18_do_s_frequency(file2id(file)->cx, vf); +} + static int cx18_g_std(struct file *file, void *fh, v4l2_std_id *std) { struct cx18 *cx = file2id(file)->cx; @@ -593,11 +599,8 @@ static int cx18_g_std(struct file *file, void *fh, v4l2_std_id *std) return 0; } -int cx18_s_std(struct file *file, void *fh, v4l2_std_id std) +int cx18_do_s_std(struct cx18 *cx, v4l2_std_id std) { - struct cx18_open_id *id = file2id(file); - struct cx18 *cx = id->cx; - if ((std & V4L2_STD_ALL) == 0) return -EINVAL; @@ -642,6 +645,11 @@ int cx18_s_std(struct file *file, void *fh, v4l2_std_id std) return 0; } +static int cx18_s_std(struct file *file, void *fh, v4l2_std_id std) +{ + return cx18_do_s_std(file2id(file)->cx, std); +} + static int cx18_s_tuner(struct file *file, void *fh, const struct v4l2_tuner *vt) { struct cx18_open_id *id = file2id(file); diff --git a/drivers/media/pci/cx18/cx18-ioctl.h b/drivers/media/pci/cx18/cx18-ioctl.h index 97cd9f99e22d..42a8acd69735 100644 --- a/drivers/media/pci/cx18/cx18-ioctl.h +++ b/drivers/media/pci/cx18/cx18-ioctl.h @@ -12,6 +12,8 @@ u16 cx18_service2vbi(int type); void cx18_expand_service_set(struct v4l2_sliced_vbi_format *fmt, int is_pal); u16 cx18_get_service_set(struct v4l2_sliced_vbi_format *fmt); void cx18_set_funcs(struct video_device *vdev); -int cx18_s_std(struct file *file, void *fh, v4l2_std_id std); -int cx18_s_frequency(struct file *file, void *fh, const struct v4l2_frequency *vf); -int cx18_s_input(struct file *file, void *fh, unsigned int inp); + +struct cx18; +int cx18_do_s_std(struct cx18 *cx, v4l2_std_id std); +int cx18_do_s_frequency(struct cx18 *cx, const struct v4l2_frequency *vf); +int cx18_do_s_input(struct cx18 *cx, unsigned int inp); diff --git a/drivers/media/pci/ivtv/ivtv-driver.c b/drivers/media/pci/ivtv/ivtv-driver.c index 72a8f76a41f4..459eb6cc370c 100644 --- a/drivers/media/pci/ivtv/ivtv-driver.c +++ b/drivers/media/pci/ivtv/ivtv-driver.c @@ -1247,15 +1247,12 @@ err: int ivtv_init_on_first_open(struct ivtv *itv) { - struct v4l2_frequency vf; /* Needed to call ioctls later */ - struct ivtv_open_id fh; + struct ivtv_stream *s = &itv->streams[IVTV_ENC_STREAM_TYPE_MPG]; + struct v4l2_frequency vf; int fw_retry_count = 3; int video_input; - fh.itv = itv; - fh.type = IVTV_ENC_STREAM_TYPE_MPG; - if (test_bit(IVTV_F_I_FAILED, &itv->i_flags)) return -ENXIO; @@ -1297,13 +1294,13 @@ int ivtv_init_on_first_open(struct ivtv *itv) video_input = itv->active_input; itv->active_input++; /* Force update of input */ - ivtv_s_input(NULL, &fh, video_input); + ivtv_do_s_input(itv, video_input); /* Let the VIDIOC_S_STD ioctl do all the work, keeps the code in one place. */ itv->std++; /* Force full standard initialization */ itv->std_out = itv->std; - ivtv_s_frequency(NULL, &fh, &vf); + ivtv_do_s_frequency(s, &vf); if (itv->card->v4l2_capabilities & V4L2_CAP_VIDEO_OUTPUT) { /* Turn on the TV-out: ivtv_init_mpeg_decoder() initializes diff --git a/drivers/media/pci/ivtv/ivtv-ioctl.c b/drivers/media/pci/ivtv/ivtv-ioctl.c index 84c73bd22f2d..8d5ea3aec06f 100644 --- a/drivers/media/pci/ivtv/ivtv-ioctl.c +++ b/drivers/media/pci/ivtv/ivtv-ioctl.c @@ -974,9 +974,8 @@ static int ivtv_g_input(struct file *file, void *fh, unsigned int *i) return 0; } -int ivtv_s_input(struct file *file, void *fh, unsigned int inp) +int ivtv_do_s_input(struct ivtv *itv, unsigned int inp) { - struct ivtv *itv = file2id(file)->itv; v4l2_std_id std; int i; @@ -1017,6 +1016,11 @@ int ivtv_s_input(struct file *file, void *fh, unsigned int inp) return 0; } +static int ivtv_s_input(struct file *file, void *fh, unsigned int inp) +{ + return ivtv_do_s_input(file2id(file)->itv, inp); +} + static int ivtv_g_output(struct file *file, void *fh, unsigned int *i) { struct ivtv *itv = file2id(file)->itv; @@ -1065,10 +1069,9 @@ static int ivtv_g_frequency(struct file *file, void *fh, struct v4l2_frequency * return 0; } -int ivtv_s_frequency(struct file *file, void *fh, const struct v4l2_frequency *vf) +int ivtv_do_s_frequency(struct ivtv_stream *s, const struct v4l2_frequency *vf) { - struct ivtv *itv = file2id(file)->itv; - struct ivtv_stream *s = &itv->streams[file2id(file)->type]; + struct ivtv *itv = s->itv; if (s->vdev.vfl_dir) return -ENOTTY; @@ -1082,6 +1085,15 @@ int ivtv_s_frequency(struct file *file, void *fh, const struct v4l2_frequency *v return 0; } +static int ivtv_s_frequency(struct file *file, void *fh, + const struct v4l2_frequency *vf) +{ + struct ivtv_open_id *id = file2id(file); + struct ivtv *itv = id->itv; + + return ivtv_do_s_frequency(&itv->streams[id->type], vf); +} + static int ivtv_g_std(struct file *file, void *fh, v4l2_std_id *std) { struct ivtv *itv = file2id(file)->itv; diff --git a/drivers/media/pci/ivtv/ivtv-ioctl.h b/drivers/media/pci/ivtv/ivtv-ioctl.h index 7f8c6f43d397..96ca7e2ef973 100644 --- a/drivers/media/pci/ivtv/ivtv-ioctl.h +++ b/drivers/media/pci/ivtv/ivtv-ioctl.h @@ -9,6 +9,8 @@ #ifndef IVTV_IOCTL_H #define IVTV_IOCTL_H +struct ivtv; + u16 ivtv_service2vbi(int type); void ivtv_expand_service_set(struct v4l2_sliced_vbi_format *fmt, int is_pal); u16 ivtv_get_service_set(struct v4l2_sliced_vbi_format *fmt); @@ -17,7 +19,7 @@ int ivtv_set_speed(struct ivtv *itv, int speed); void ivtv_set_funcs(struct video_device *vdev); void ivtv_s_std_enc(struct ivtv *itv, v4l2_std_id std); void ivtv_s_std_dec(struct ivtv *itv, v4l2_std_id std); -int ivtv_s_frequency(struct file *file, void *fh, const struct v4l2_frequency *vf); -int ivtv_s_input(struct file *file, void *fh, unsigned int inp); +int ivtv_do_s_frequency(struct ivtv_stream *s, const struct v4l2_frequency *vf); +int ivtv_do_s_input(struct ivtv *itv, unsigned int inp); #endif diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c index fb6afb8e84f0..ee4f54d68349 100644 --- a/drivers/media/usb/uvc/uvc_driver.c +++ b/drivers/media/usb/uvc/uvc_driver.c @@ -167,13 +167,26 @@ static struct uvc_entity *uvc_entity_by_reference(struct uvc_device *dev, static struct uvc_streaming *uvc_stream_by_id(struct uvc_device *dev, int id) { - struct uvc_streaming *stream; + struct uvc_streaming *stream, *last_stream; + unsigned int count = 0; list_for_each_entry(stream, &dev->streams, list) { + count += 1; + last_stream = stream; if (stream->header.bTerminalLink == id) return stream; } + /* + * If the streaming entity is referenced by an invalid ID, notify the + * user and use heuristics to guess the correct entity. + */ + if (count == 1 && id == UVC_INVALID_ENTITY_ID) { + dev_warn(&dev->intf->dev, + "UVC non compliance: Invalid USB header. The streaming entity has an invalid ID, guessing the correct one."); + return last_stream; + } + return NULL; } diff --git a/drivers/media/v4l2-core/v4l2-subdev.c b/drivers/media/v4l2-core/v4l2-subdev.c index 1da953629010..25e66bf18f5f 100644 --- a/drivers/media/v4l2-core/v4l2-subdev.c +++ b/drivers/media/v4l2-core/v4l2-subdev.c @@ -2608,7 +2608,7 @@ EXPORT_SYMBOL_GPL(v4l2_subdev_is_streaming); int v4l2_subdev_get_privacy_led(struct v4l2_subdev *sd) { #if IS_REACHABLE(CONFIG_LEDS_CLASS) - sd->privacy_led = led_get(sd->dev, "privacy-led"); + sd->privacy_led = led_get(sd->dev, "privacy"); if (IS_ERR(sd->privacy_led) && PTR_ERR(sd->privacy_led) != -ENOENT) return dev_err_probe(sd->dev, PTR_ERR(sd->privacy_led), "getting privacy LED\n"); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index e95e593cd12d..5abef8a3b775 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2120,7 +2120,7 @@ skip_mac_set: /* check for initial state */ new_slave->link = BOND_LINK_NOCHANGE; if (bond->params.miimon) { - if (netif_carrier_ok(slave_dev)) { + if (netif_running(slave_dev) && netif_carrier_ok(slave_dev)) { if (bond->params.updelay) { bond_set_slave_link_state(new_slave, BOND_LINK_BACK, @@ -2665,7 +2665,8 @@ static int bond_miimon_inspect(struct bonding *bond) bond_for_each_slave_rcu(bond, slave, iter) { bond_propose_link_state(slave, BOND_LINK_NOCHANGE); - link_state = netif_carrier_ok(slave->dev); + link_state = netif_running(slave->dev) && + netif_carrier_ok(slave->dev); switch (slave->link) { case BOND_LINK_UP: diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 495a87f2ea7c..384499c869b8 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -225,13 +225,6 @@ static const struct bond_opt_value bond_ad_actor_sys_prio_tbl[] = { { NULL, -1, 0}, }; -static const struct bond_opt_value bond_actor_port_prio_tbl[] = { - { "minval", 0, BOND_VALFLAG_MIN}, - { "maxval", 65535, BOND_VALFLAG_MAX}, - { "default", 255, BOND_VALFLAG_DEFAULT}, - { NULL, -1, 0}, -}; - static const struct bond_opt_value bond_ad_user_port_key_tbl[] = { { "minval", 0, BOND_VALFLAG_MIN | BOND_VALFLAG_DEFAULT}, { "maxval", 1023, BOND_VALFLAG_MAX}, @@ -497,7 +490,7 @@ static const struct bond_option bond_opts[BOND_OPT_LAST] = { .id = BOND_OPT_ACTOR_PORT_PRIO, .name = "actor_port_prio", .unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_8023AD)), - .values = bond_actor_port_prio_tbl, + .flags = BOND_OPTFLAG_RAWVAL, .set = bond_option_actor_port_prio_set, }, [BOND_OPT_AD_ACTOR_SYSTEM] = { diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 2f846381d5a7..eb767edc4c13 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -371,11 +371,11 @@ static void b53_set_forwarding(struct b53_device *dev, int enable) * frames should be flooded or not. */ b53_read8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, &mgmt); - mgmt |= B53_UC_FWD_EN | B53_MC_FWD_EN | B53_IPMC_FWD_EN; + mgmt |= B53_UC_FWD_EN | B53_MC_FWD_EN | B53_IP_MC; b53_write8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, mgmt); } else { b53_read8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, &mgmt); - mgmt |= B53_IP_MCAST_25; + mgmt |= B53_IP_MC; b53_write8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, mgmt); } } @@ -1372,6 +1372,10 @@ static void b53_force_port_config(struct b53_device *dev, int port, else reg &= ~PORT_OVERRIDE_FULL_DUPLEX; + reg &= ~(0x3 << GMII_PO_SPEED_S); + if (is5301x(dev) || is58xx(dev)) + reg &= ~PORT_OVERRIDE_SPEED_2000M; + switch (speed) { case 2000: reg |= PORT_OVERRIDE_SPEED_2000M; @@ -1390,6 +1394,11 @@ static void b53_force_port_config(struct b53_device *dev, int port, return; } + if (is5325(dev)) + reg &= ~PORT_OVERRIDE_LP_FLOW_25; + else + reg &= ~(PORT_OVERRIDE_RX_FLOW | PORT_OVERRIDE_TX_FLOW); + if (rx_pause) { if (is5325(dev)) reg |= PORT_OVERRIDE_LP_FLOW_25; @@ -1593,8 +1602,11 @@ static void b53_phylink_mac_link_down(struct phylink_config *config, struct b53_device *dev = dp->ds->priv; int port = dp->index; - if (mode == MLO_AN_PHY) + if (mode == MLO_AN_PHY) { + if (is63xx(dev) && in_range(port, B53_63XX_RGMII0, 4)) + b53_force_link(dev, port, false); return; + } if (mode == MLO_AN_FIXED) { b53_force_link(dev, port, false); @@ -1622,6 +1634,13 @@ static void b53_phylink_mac_link_up(struct phylink_config *config, if (mode == MLO_AN_PHY) { /* Re-negotiate EEE if it was enabled already */ p->eee_enabled = b53_eee_init(ds, port, phydev); + + if (is63xx(dev) && in_range(port, B53_63XX_RGMII0, 4)) { + b53_force_port_config(dev, port, speed, duplex, + tx_pause, rx_pause); + b53_force_link(dev, port, true); + } + return; } @@ -2018,7 +2037,7 @@ static int b53_arl_search_wait(struct b53_device *dev) do { b53_read8(dev, B53_ARLIO_PAGE, offset, ®); if (!(reg & ARL_SRCH_STDN)) - return 0; + return -ENOENT; if (reg & ARL_SRCH_VLID) return 0; @@ -2068,13 +2087,16 @@ static int b53_fdb_copy(int port, const struct b53_arl_entry *ent, int b53_fdb_dump(struct dsa_switch *ds, int port, dsa_fdb_dump_cb_t *cb, void *data) { + unsigned int count = 0, results_per_hit = 1; struct b53_device *priv = ds->priv; struct b53_arl_entry results[2]; - unsigned int count = 0; u8 offset; int ret; u8 reg; + if (priv->num_arl_bins > 2) + results_per_hit = 2; + mutex_lock(&priv->arl_mutex); if (is5325(priv) || is5365(priv)) @@ -2096,7 +2118,7 @@ int b53_fdb_dump(struct dsa_switch *ds, int port, if (ret) break; - if (priv->num_arl_bins > 2) { + if (results_per_hit == 2) { b53_arl_search_rd(priv, 1, &results[1]); ret = b53_fdb_copy(port, &results[1], cb, data); if (ret) @@ -2106,7 +2128,7 @@ int b53_fdb_dump(struct dsa_switch *ds, int port, break; } - } while (count++ < b53_max_arl_entries(priv) / 2); + } while (count++ < b53_max_arl_entries(priv) / results_per_hit); mutex_unlock(&priv->arl_mutex); diff --git a/drivers/net/dsa/b53/b53_regs.h b/drivers/net/dsa/b53/b53_regs.h index 309fe0e46dad..8ce1ce72e938 100644 --- a/drivers/net/dsa/b53/b53_regs.h +++ b/drivers/net/dsa/b53/b53_regs.h @@ -111,8 +111,7 @@ /* IP Multicast control (8 bit) */ #define B53_IP_MULTICAST_CTRL 0x21 -#define B53_IP_MCAST_25 BIT(0) -#define B53_IPMC_FWD_EN BIT(1) +#define B53_IP_MC BIT(0) #define B53_UC_FWD_EN BIT(6) #define B53_MC_FWD_EN BIT(7) diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index d747ea1c41a7..5df8f153d511 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -1355,9 +1355,15 @@ void ksz9477_config_cpu_port(struct dsa_switch *ds) } } +#define RESV_MCAST_CNT 8 + +static u8 reserved_mcast_map[RESV_MCAST_CNT] = { 0, 1, 3, 16, 32, 33, 2, 17 }; + int ksz9477_enable_stp_addr(struct ksz_device *dev) { + u8 i, ports, update; const u32 *masks; + bool override; u32 data; int ret; @@ -1366,23 +1372,87 @@ int ksz9477_enable_stp_addr(struct ksz_device *dev) /* Enable Reserved multicast table */ ksz_cfg(dev, REG_SW_LUE_CTRL_0, SW_RESV_MCAST_ENABLE, true); - /* Set the Override bit for forwarding BPDU packet to CPU */ - ret = ksz_write32(dev, REG_SW_ALU_VAL_B, - ALU_V_OVERRIDE | BIT(dev->cpu_port)); - if (ret < 0) - return ret; + /* The reserved multicast address table has 8 entries. Each entry has + * a default value of which port to forward. It is assumed the host + * port is the last port in most of the switches, but that is not the + * case for KSZ9477 or maybe KSZ9897. For LAN937X family the default + * port is port 5, the first RGMII port. It is okay for LAN9370, a + * 5-port switch, but may not be correct for the other 8-port + * versions. It is necessary to update the whole table to forward to + * the right ports. + * Furthermore PTP messages can use a reserved multicast address and + * the host will not receive them if this table is not correct. + */ + for (i = 0; i < RESV_MCAST_CNT; i++) { + data = reserved_mcast_map[i] << + dev->info->shifts[ALU_STAT_INDEX]; + data |= ALU_STAT_START | + masks[ALU_STAT_DIRECT] | + masks[ALU_RESV_MCAST_ADDR] | + masks[ALU_STAT_READ]; + ret = ksz_write32(dev, REG_SW_ALU_STAT_CTRL__4, data); + if (ret < 0) + return ret; - data = ALU_STAT_START | ALU_RESV_MCAST_ADDR | masks[ALU_STAT_WRITE]; + /* wait to be finished */ + ret = ksz9477_wait_alu_sta_ready(dev); + if (ret < 0) + return ret; - ret = ksz_write32(dev, REG_SW_ALU_STAT_CTRL__4, data); - if (ret < 0) - return ret; + ret = ksz_read32(dev, REG_SW_ALU_VAL_B, &data); + if (ret < 0) + return ret; - /* wait to be finished */ - ret = ksz9477_wait_alu_sta_ready(dev); - if (ret < 0) { - dev_err(dev->dev, "Failed to update Reserved Multicast table\n"); - return ret; + override = false; + ports = data & dev->port_mask; + switch (i) { + case 0: + case 6: + /* Change the host port. */ + update = BIT(dev->cpu_port); + override = true; + break; + case 2: + /* Change the host port. */ + update = BIT(dev->cpu_port); + break; + case 4: + case 5: + case 7: + /* Skip the host port. */ + update = dev->port_mask & ~BIT(dev->cpu_port); + break; + default: + update = ports; + break; + } + if (update != ports || override) { + data &= ~dev->port_mask; + data |= update; + /* Set Override bit to receive frame even when port is + * closed. + */ + if (override) + data |= ALU_V_OVERRIDE; + ret = ksz_write32(dev, REG_SW_ALU_VAL_B, data); + if (ret < 0) + return ret; + + data = reserved_mcast_map[i] << + dev->info->shifts[ALU_STAT_INDEX]; + data |= ALU_STAT_START | + masks[ALU_STAT_DIRECT] | + masks[ALU_RESV_MCAST_ADDR] | + masks[ALU_STAT_WRITE]; + ret = ksz_write32(dev, REG_SW_ALU_STAT_CTRL__4, data); + if (ret < 0) + return ret; + + /* wait to be finished */ + ret = ksz9477_wait_alu_sta_ready(dev); + if (ret < 0) + return ret; + } } return 0; diff --git a/drivers/net/dsa/microchip/ksz9477_reg.h b/drivers/net/dsa/microchip/ksz9477_reg.h index ff579920078e..61ea11e3338e 100644 --- a/drivers/net/dsa/microchip/ksz9477_reg.h +++ b/drivers/net/dsa/microchip/ksz9477_reg.h @@ -2,7 +2,7 @@ /* * Microchip KSZ9477 register definitions * - * Copyright (C) 2017-2024 Microchip Technology Inc. + * Copyright (C) 2017-2025 Microchip Technology Inc. */ #ifndef __KSZ9477_REGS_H @@ -397,7 +397,6 @@ #define ALU_RESV_MCAST_INDEX_M (BIT(6) - 1) #define ALU_STAT_START BIT(7) -#define ALU_RESV_MCAST_ADDR BIT(1) #define REG_SW_ALU_VAL_A 0x0420 diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index a962055bfdbd..933ae8dc6337 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -808,6 +808,8 @@ static const u16 ksz9477_regs[] = { static const u32 ksz9477_masks[] = { [ALU_STAT_WRITE] = 0, [ALU_STAT_READ] = 1, + [ALU_STAT_DIRECT] = 0, + [ALU_RESV_MCAST_ADDR] = BIT(1), [P_MII_TX_FLOW_CTRL] = BIT(5), [P_MII_RX_FLOW_CTRL] = BIT(3), }; @@ -835,6 +837,8 @@ static const u8 ksz9477_xmii_ctrl1[] = { static const u32 lan937x_masks[] = { [ALU_STAT_WRITE] = 1, [ALU_STAT_READ] = 2, + [ALU_STAT_DIRECT] = BIT(3), + [ALU_RESV_MCAST_ADDR] = BIT(2), [P_MII_TX_FLOW_CTRL] = BIT(5), [P_MII_RX_FLOW_CTRL] = BIT(3), }; diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index a1eb39771bb9..c65188cd3c0a 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -294,6 +294,8 @@ enum ksz_masks { DYNAMIC_MAC_TABLE_TIMESTAMP, ALU_STAT_WRITE, ALU_STAT_READ, + ALU_STAT_DIRECT, + ALU_RESV_MCAST_ADDR, P_MII_TX_FLOW_CTRL, P_MII_RX_FLOW_CTRL, }; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 3fc33b1b4dfb..a625e7c311dd 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -12439,7 +12439,7 @@ static int bnxt_try_recover_fw(struct bnxt *bp) return -ENODEV; } -static void bnxt_clear_reservations(struct bnxt *bp, bool fw_reset) +void bnxt_clear_reservations(struct bnxt *bp, bool fw_reset) { struct bnxt_hw_resc *hw_resc = &bp->hw_resc; @@ -16892,6 +16892,10 @@ static void bnxt_shutdown(struct pci_dev *pdev) if (netif_running(dev)) netif_close(dev); + if (bnxt_hwrm_func_drv_unrgtr(bp)) { + pcie_flr(pdev); + goto shutdown_exit; + } bnxt_ptp_clear(bp); bnxt_clear_int_mode(bp); pci_disable_device(pdev); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 741b2d854789..3613a172483a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -2149,7 +2149,7 @@ struct bnxt_bs_trace_info { static inline void bnxt_bs_trace_check_wrap(struct bnxt_bs_trace_info *bs_trace, u32 offset) { - if (!bs_trace->wrapped && + if (!bs_trace->wrapped && bs_trace->magic_byte && *bs_trace->magic_byte != BNXT_TRACE_BUF_MAGIC_BYTE) bs_trace->wrapped = 1; bs_trace->last_offset = offset; @@ -2941,6 +2941,7 @@ void bnxt_report_link(struct bnxt *bp); int bnxt_update_link(struct bnxt *bp, bool chng_link_state); int bnxt_hwrm_set_pause(struct bnxt *); int bnxt_hwrm_set_link_setting(struct bnxt *, bool, bool); +void bnxt_clear_reservations(struct bnxt *bp, bool fw_reset); int bnxt_cancel_reservations(struct bnxt *bp, bool fw_reset); int bnxt_hwrm_alloc_wol_fltr(struct bnxt *bp); int bnxt_hwrm_free_wol_fltr(struct bnxt *bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c index 0181ab1f2dfd..ccb8b509662d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c @@ -333,13 +333,14 @@ static void bnxt_fill_drv_seg_record(struct bnxt *bp, u32 offset = 0; int rc = 0; + record->max_entries = cpu_to_le32(ctxm->max_entries); + record->entry_size = cpu_to_le32(ctxm->entry_size); + rc = bnxt_dbg_hwrm_log_buffer_flush(bp, type, 0, &offset); if (rc) return; bnxt_bs_trace_check_wrap(bs_trace, offset); - record->max_entries = cpu_to_le32(ctxm->max_entries); - record->entry_size = cpu_to_le32(ctxm->entry_size); record->offset = cpu_to_le32(bs_trace->last_offset); record->wrapped = bs_trace->wrapped; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index 02961d93ed35..67ca02d84c97 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -461,7 +461,7 @@ static int bnxt_dl_reload_down(struct devlink *dl, bool netns_change, rtnl_unlock(); break; } - bnxt_cancel_reservations(bp, false); + bnxt_clear_reservations(bp, false); bnxt_free_ctx_mem(bp, false); break; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c index db81cf6d5289..0abaa2bbe357 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c @@ -1051,9 +1051,9 @@ static void bnxt_ptp_free(struct bnxt *bp) if (ptp->ptp_clock) { ptp_clock_unregister(ptp->ptp_clock); ptp->ptp_clock = NULL; - kfree(ptp->ptp_info.pin_config); - ptp->ptp_info.pin_config = NULL; } + kfree(ptp->ptp_info.pin_config); + ptp->ptp_info.pin_config = NULL; } int bnxt_ptp_init(struct bnxt *bp) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 1edcfaee6819..3222359ac15b 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1835,6 +1835,8 @@ fec_enet_rx_queue(struct net_device *ndev, u16 queue_id, int budget) ndev->stats.rx_packets++; pkt_len = fec16_to_cpu(bdp->cbd_datlen); ndev->stats.rx_bytes += pkt_len; + if (fep->quirks & FEC_QUIRK_HAS_RACC) + ndev->stats.rx_bytes -= 2; index = fec_enet_get_bd_index(bdp, &rxq->bd); page = rxq->rx_skb_info[index].page; diff --git a/drivers/net/ethernet/google/gve/gve_ptp.c b/drivers/net/ethernet/google/gve/gve_ptp.c index e96247c9d68d..a384a9ed4914 100644 --- a/drivers/net/ethernet/google/gve/gve_ptp.c +++ b/drivers/net/ethernet/google/gve/gve_ptp.c @@ -26,6 +26,19 @@ int gve_clock_nic_ts_read(struct gve_priv *priv) return 0; } +static int gve_ptp_gettimex64(struct ptp_clock_info *info, + struct timespec64 *ts, + struct ptp_system_timestamp *sts) +{ + return -EOPNOTSUPP; +} + +static int gve_ptp_settime64(struct ptp_clock_info *info, + const struct timespec64 *ts) +{ + return -EOPNOTSUPP; +} + static long gve_ptp_do_aux_work(struct ptp_clock_info *info) { const struct gve_ptp *ptp = container_of(info, struct gve_ptp, info); @@ -47,6 +60,8 @@ out: static const struct ptp_clock_info gve_ptp_caps = { .owner = THIS_MODULE, .name = "gve clock", + .gettimex64 = gve_ptp_gettimex64, + .settime64 = gve_ptp_settime64, .do_aux_work = gve_ptp_do_aux_work, }; diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig index a563a94e2780..122ee23497e6 100644 --- a/drivers/net/ethernet/intel/Kconfig +++ b/drivers/net/ethernet/intel/Kconfig @@ -146,7 +146,7 @@ config IXGBE tristate "Intel(R) 10GbE PCI Express adapters support" depends on PCI depends on PTP_1588_CLOCK_OPTIONAL - select LIBIE_FWLOG + select LIBIE_FWLOG if DEBUG_FS select MDIO select NET_DEVLINK select PLDMFW @@ -298,7 +298,7 @@ config ICE select DIMLIB select LIBIE select LIBIE_ADMINQ - select LIBIE_FWLOG + select LIBIE_FWLOG if DEBUG_FS select NET_DEVLINK select PACKING select PLDMFW diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 14d275270123..dce4936708eb 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -821,9 +821,7 @@ struct ixgbe_adapter { #ifdef CONFIG_IXGBE_HWMON struct hwmon_buff *ixgbe_hwmon_buff; #endif /* CONFIG_IXGBE_HWMON */ -#ifdef CONFIG_DEBUG_FS struct dentry *ixgbe_dbg_adapter; -#endif /*CONFIG_DEBUG_FS*/ u8 default_up; /* Bitmask indicating in use pools */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index aff17c37ddde..902d6abaa3ec 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -1516,10 +1516,8 @@ int otx2_pool_init(struct otx2_nic *pfvf, u16 pool_id, pool->xdp_cnt = numptrs; pool->xdp = devm_kcalloc(pfvf->dev, numptrs, sizeof(struct xdp_buff *), GFP_KERNEL); - if (IS_ERR(pool->xdp)) { - netdev_err(pfvf->netdev, "Creation of xsk pool failed\n"); - return PTR_ERR(pool->xdp); - } + if (!pool->xdp) + return -ENOMEM; } return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c index e9f319a9bdd6..60f7ab1d72e7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c @@ -66,8 +66,8 @@ void mlx5_cq_tasklet_cb(struct tasklet_struct *t) tasklet_schedule(&ctx->task); } -static void mlx5_add_cq_to_tasklet(struct mlx5_core_cq *cq, - struct mlx5_eqe *eqe) +void mlx5_add_cq_to_tasklet(struct mlx5_core_cq *cq, + struct mlx5_eqe *eqe) { unsigned long flags; struct mlx5_eq_tasklet *tasklet_ctx = cq->tasklet_ctx.priv; @@ -95,7 +95,15 @@ static void mlx5_add_cq_to_tasklet(struct mlx5_core_cq *cq, if (schedule_tasklet) tasklet_schedule(&tasklet_ctx->task); } +EXPORT_SYMBOL(mlx5_add_cq_to_tasklet); +static void mlx5_core_cq_dummy_cb(struct mlx5_core_cq *cq, struct mlx5_eqe *eqe) +{ + mlx5_core_err(cq->eq->core.dev, + "CQ default completion callback, CQ #%u\n", cq->cqn); +} + +#define MLX5_CQ_INIT_CMD_SN cpu_to_be32(2 << 28) /* Callers must verify outbox status in case of err */ int mlx5_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, u32 *in, int inlen, u32 *out, int outlen) @@ -121,10 +129,19 @@ int mlx5_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, cq->arm_sn = 0; cq->eq = eq; cq->uid = MLX5_GET(create_cq_in, in, uid); + + /* Kernel CQs must set the arm_db address prior to calling + * this function, allowing for the proper value to be + * initialized. User CQs are responsible for their own + * initialization since they do not use the arm_db field. + */ + if (cq->arm_db) + *cq->arm_db = MLX5_CQ_INIT_CMD_SN; + refcount_set(&cq->refcount, 1); init_completion(&cq->free); if (!cq->comp) - cq->comp = mlx5_add_cq_to_tasklet; + cq->comp = mlx5_core_cq_dummy_cb; /* assuming CQ will be deleted before the EQ */ cq->tasklet_ctx.priv = &eq->tasklet_ctx; INIT_LIST_HEAD(&cq->tasklet_ctx.list); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index fceea83abbd7..887adf4807d1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -541,7 +541,7 @@ static int mlx5_devlink_num_doorbells_validate(struct devlink *devlink, u32 id, max_num_channels = mlx5e_get_max_num_channels(mdev); if (val32 > max_num_channels) { NL_SET_ERR_MSG_FMT_MOD(extack, - "Requested num_doorbells (%u) exceeds maximum number of channels (%u)", + "Requested num_doorbells (%u) exceeds max number of channels (%u)", val32, max_num_channels); return -EINVAL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 14e3207b14e7..a163f81f07c1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -634,7 +634,10 @@ struct mlx5e_dma_info { struct mlx5e_shampo_hd { struct mlx5e_frag_page *pages; u32 hd_per_wq; + u32 hd_per_page; u16 hd_per_wqe; + u8 log_hd_per_page; + u8 log_hd_entry_size; unsigned long *bitmap; u16 pi; u16 ci; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c index 0a4fb8c92268..35d9530037a6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c @@ -804,7 +804,8 @@ static int mlx5e_xfrm_add_state(struct net_device *dev, goto err_xfrm; } - if (mlx5_eswitch_block_mode(priv->mdev)) + err = mlx5_eswitch_block_mode(priv->mdev); + if (err) goto unblock_ipsec; if (x->props.mode == XFRM_MODE_TUNNEL && diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index d166c0d5189e..9b93da4d52f6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -595,32 +595,55 @@ static int mlx5e_dcbnl_ieee_setmaxrate(struct net_device *netdev, struct mlx5_core_dev *mdev = priv->mdev; u8 max_bw_value[IEEE_8021QAZ_MAX_TCS]; u8 max_bw_unit[IEEE_8021QAZ_MAX_TCS]; - __u64 upper_limit_mbps = roundup(255 * MLX5E_100MB, MLX5E_1GB); + __u64 upper_limit_mbps; + __u64 upper_limit_gbps; int i; + struct { + int scale; + const char *units_str; + } units[] = { + [MLX5_100_MBPS_UNIT] = { + .scale = 100, + .units_str = "Mbps", + }, + [MLX5_GBPS_UNIT] = { + .scale = 1, + .units_str = "Gbps", + }, + }; memset(max_bw_value, 0, sizeof(max_bw_value)); memset(max_bw_unit, 0, sizeof(max_bw_unit)); + upper_limit_mbps = 255 * MLX5E_100MB; + upper_limit_gbps = 255 * MLX5E_1GB; for (i = 0; i <= mlx5_max_tc(mdev); i++) { if (!maxrate->tc_maxrate[i]) { max_bw_unit[i] = MLX5_BW_NO_LIMIT; continue; } - if (maxrate->tc_maxrate[i] < upper_limit_mbps) { + if (maxrate->tc_maxrate[i] <= upper_limit_mbps) { max_bw_value[i] = div_u64(maxrate->tc_maxrate[i], MLX5E_100MB); max_bw_value[i] = max_bw_value[i] ? max_bw_value[i] : 1; max_bw_unit[i] = MLX5_100_MBPS_UNIT; - } else { + } else if (max_bw_value[i] <= upper_limit_gbps) { max_bw_value[i] = div_u64(maxrate->tc_maxrate[i], MLX5E_1GB); max_bw_unit[i] = MLX5_GBPS_UNIT; + } else { + netdev_err(netdev, + "tc_%d maxrate %llu Kbps exceeds limit %llu\n", + i, maxrate->tc_maxrate[i], + upper_limit_gbps); + return -EINVAL; } } for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { - netdev_dbg(netdev, "%s: tc_%d <=> max_bw %d Gbps\n", - __func__, i, max_bw_value[i]); + netdev_dbg(netdev, "%s: tc_%d <=> max_bw %u %s\n", __func__, i, + max_bw_value[i] * units[max_bw_unit[i]].scale, + units[max_bw_unit[i]].units_str); } return mlx5_modify_port_ets_rate_limit(mdev, max_bw_value, max_bw_unit); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 53e5ae252eac..893e1380a7c9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -2125,14 +2125,12 @@ static int mlx5e_get_module_eeprom_by_page(struct net_device *netdev, if (!size_read) return i; - if (size_read == -EINVAL) - return -EINVAL; if (size_read < 0) { NL_SET_ERR_MSG_FMT_MOD( extack, "Query module eeprom by page failed, read %u bytes, err %d", i, size_read); - return i; + return size_read; } i += size_read; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 9c46511e7b43..5e17eae81f4b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -791,8 +791,9 @@ static int mlx5_rq_shampo_alloc(struct mlx5_core_dev *mdev, int node) { void *wqc = MLX5_ADDR_OF(rqc, rqp->rqc, wq); + u8 log_hd_per_page, log_hd_entry_size; + u16 hd_per_wq, hd_per_wqe; u32 hd_pool_size; - u16 hd_per_wq; int wq_size; int err; @@ -815,11 +816,24 @@ static int mlx5_rq_shampo_alloc(struct mlx5_core_dev *mdev, if (err) goto err_umr_mkey; - rq->mpwqe.shampo->hd_per_wqe = - mlx5e_shampo_hd_per_wqe(mdev, params, rqp); + hd_per_wqe = mlx5e_shampo_hd_per_wqe(mdev, params, rqp); wq_size = BIT(MLX5_GET(wq, wqc, log_wq_sz)); - hd_pool_size = (rq->mpwqe.shampo->hd_per_wqe * wq_size) / - MLX5E_SHAMPO_WQ_HEADER_PER_PAGE; + + BUILD_BUG_ON(MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE > PAGE_SHIFT); + if (hd_per_wqe >= MLX5E_SHAMPO_WQ_HEADER_PER_PAGE) { + log_hd_per_page = MLX5E_SHAMPO_LOG_WQ_HEADER_PER_PAGE; + log_hd_entry_size = MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE; + } else { + log_hd_per_page = order_base_2(hd_per_wqe); + log_hd_entry_size = order_base_2(PAGE_SIZE / hd_per_wqe); + } + + rq->mpwqe.shampo->hd_per_wqe = hd_per_wqe; + rq->mpwqe.shampo->hd_per_page = BIT(log_hd_per_page); + rq->mpwqe.shampo->log_hd_per_page = log_hd_per_page; + rq->mpwqe.shampo->log_hd_entry_size = log_hd_entry_size; + + hd_pool_size = (hd_per_wqe * wq_size) >> log_hd_per_page; if (netif_rxq_has_unreadable_mp(rq->netdev, rq->ix)) { /* Separate page pool for shampo headers */ @@ -2205,7 +2219,6 @@ static int mlx5e_alloc_cq_common(struct mlx5_core_dev *mdev, mcq->set_ci_db = cq->wq_ctrl.db.db; mcq->arm_db = cq->wq_ctrl.db.db + 1; *mcq->set_ci_db = 0; - *mcq->arm_db = 0; mcq->vector = param->eq_ix; mcq->comp = mlx5e_completion_event; mcq->event = mlx5e_cq_error_event; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 26621a2972ec..687cf123211d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -648,17 +648,20 @@ static void build_ksm_umr(struct mlx5e_icosq *sq, struct mlx5e_umr_wqe *umr_wqe, umr_wqe->hdr.uctrl.mkey_mask = cpu_to_be64(MLX5_MKEY_MASK_FREE); } -static struct mlx5e_frag_page *mlx5e_shampo_hd_to_frag_page(struct mlx5e_rq *rq, int header_index) +static struct mlx5e_frag_page *mlx5e_shampo_hd_to_frag_page(struct mlx5e_rq *rq, + int header_index) { - BUILD_BUG_ON(MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE > PAGE_SHIFT); + struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo; - return &rq->mpwqe.shampo->pages[header_index >> MLX5E_SHAMPO_LOG_WQ_HEADER_PER_PAGE]; + return &shampo->pages[header_index >> shampo->log_hd_per_page]; } -static u64 mlx5e_shampo_hd_offset(int header_index) +static u64 mlx5e_shampo_hd_offset(struct mlx5e_rq *rq, int header_index) { - return (header_index & (MLX5E_SHAMPO_WQ_HEADER_PER_PAGE - 1)) << - MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE; + struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo; + u32 hd_per_page = shampo->hd_per_page; + + return (header_index & (hd_per_page - 1)) << shampo->log_hd_entry_size; } static void mlx5e_free_rx_shampo_hd_entry(struct mlx5e_rq *rq, u16 header_index); @@ -671,7 +674,7 @@ static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq, u16 pi, header_offset, err, wqe_bbs; u32 lkey = rq->mdev->mlx5e_res.hw_objs.mkey; struct mlx5e_umr_wqe *umr_wqe; - int headroom, i = 0; + int headroom, i; headroom = rq->buff.headroom; wqe_bbs = MLX5E_KSM_UMR_WQEBBS(ksm_entries); @@ -679,25 +682,24 @@ static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq, umr_wqe = mlx5_wq_cyc_get_wqe(&sq->wq, pi); build_ksm_umr(sq, umr_wqe, shampo->mkey_be, index, ksm_entries); - WARN_ON_ONCE(ksm_entries & (MLX5E_SHAMPO_WQ_HEADER_PER_PAGE - 1)); - while (i < ksm_entries) { - struct mlx5e_frag_page *frag_page = mlx5e_shampo_hd_to_frag_page(rq, index); + for (i = 0; i < ksm_entries; i++, index++) { + struct mlx5e_frag_page *frag_page; u64 addr; - err = mlx5e_page_alloc_fragmented(rq->hd_page_pool, frag_page); - if (unlikely(err)) - goto err_unmap; + frag_page = mlx5e_shampo_hd_to_frag_page(rq, index); + header_offset = mlx5e_shampo_hd_offset(rq, index); + if (!header_offset) { + err = mlx5e_page_alloc_fragmented(rq->hd_page_pool, + frag_page); + if (err) + goto err_unmap; + } addr = page_pool_get_dma_addr_netmem(frag_page->netmem); - - for (int j = 0; j < MLX5E_SHAMPO_WQ_HEADER_PER_PAGE; j++) { - header_offset = mlx5e_shampo_hd_offset(index++); - - umr_wqe->inline_ksms[i++] = (struct mlx5_ksm) { - .key = cpu_to_be32(lkey), - .va = cpu_to_be64(addr + header_offset + headroom), - }; - } + umr_wqe->inline_ksms[i] = (struct mlx5_ksm) { + .key = cpu_to_be32(lkey), + .va = cpu_to_be64(addr + header_offset + headroom), + }; } sq->db.wqe_info[pi] = (struct mlx5e_icosq_wqe_info) { @@ -713,9 +715,9 @@ static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq, return 0; err_unmap: - while (--i) { + while (--i >= 0) { --index; - header_offset = mlx5e_shampo_hd_offset(index); + header_offset = mlx5e_shampo_hd_offset(rq, index); if (!header_offset) { struct mlx5e_frag_page *frag_page = mlx5e_shampo_hd_to_frag_page(rq, index); @@ -735,12 +737,11 @@ static int mlx5e_alloc_rx_hd_mpwqe(struct mlx5e_rq *rq) struct mlx5e_icosq *sq = rq->icosq; int i, err, max_ksm_entries, len; - max_ksm_entries = ALIGN_DOWN(MLX5E_MAX_KSM_PER_WQE(rq->mdev), - MLX5E_SHAMPO_WQ_HEADER_PER_PAGE); + max_ksm_entries = MLX5E_MAX_KSM_PER_WQE(rq->mdev); ksm_entries = bitmap_find_window(shampo->bitmap, shampo->hd_per_wqe, shampo->hd_per_wq, shampo->pi); - ksm_entries = ALIGN_DOWN(ksm_entries, MLX5E_SHAMPO_WQ_HEADER_PER_PAGE); + ksm_entries = ALIGN_DOWN(ksm_entries, shampo->hd_per_page); if (!ksm_entries) return 0; @@ -858,7 +859,7 @@ mlx5e_free_rx_shampo_hd_entry(struct mlx5e_rq *rq, u16 header_index) { struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo; - if (((header_index + 1) & (MLX5E_SHAMPO_WQ_HEADER_PER_PAGE - 1)) == 0) { + if (((header_index + 1) & (shampo->hd_per_page - 1)) == 0) { struct mlx5e_frag_page *frag_page = mlx5e_shampo_hd_to_frag_page(rq, header_index); mlx5e_page_release_fragmented(rq->hd_page_pool, frag_page); @@ -1225,9 +1226,10 @@ static unsigned int mlx5e_lro_update_hdr(struct sk_buff *skb, static void *mlx5e_shampo_get_packet_hd(struct mlx5e_rq *rq, u16 header_index) { struct mlx5e_frag_page *frag_page = mlx5e_shampo_hd_to_frag_page(rq, header_index); - u16 head_offset = mlx5e_shampo_hd_offset(header_index) + rq->buff.headroom; + u16 head_offset = mlx5e_shampo_hd_offset(rq, header_index); + void *addr = netmem_address(frag_page->netmem); - return netmem_address(frag_page->netmem) + head_offset; + return addr + head_offset + rq->buff.headroom; } static void mlx5e_shampo_update_ipv4_udp_hdr(struct mlx5e_rq *rq, struct iphdr *ipv4) @@ -2267,7 +2269,8 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, struct mlx5_cqe64 *cqe, u16 header_index) { struct mlx5e_frag_page *frag_page = mlx5e_shampo_hd_to_frag_page(rq, header_index); - u16 head_offset = mlx5e_shampo_hd_offset(header_index); + u16 head_offset = mlx5e_shampo_hd_offset(rq, header_index); + struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo; u16 head_size = cqe->shampo.header_size; u16 rx_headroom = rq->buff.headroom; struct sk_buff *skb = NULL; @@ -2283,7 +2286,7 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, data = hdr + rx_headroom; frag_size = MLX5_SKB_FRAG_SZ(rx_headroom + head_size); - if (likely(frag_size <= BIT(MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE))) { + if (likely(frag_size <= BIT(shampo->log_hd_entry_size))) { /* build SKB around header */ dma_sync_single_range_for_cpu(rq->pdev, dma_addr, 0, frag_size, rq->buff.map_dir); net_prefetchw(hdr); @@ -2356,7 +2359,10 @@ mlx5e_hw_gro_skb_has_enough_space(struct sk_buff *skb, u16 data_bcnt) { int nr_frags = skb_shinfo(skb)->nr_frags; - return PAGE_SIZE * nr_frags + data_bcnt <= GRO_LEGACY_MAX_SIZE; + if (PAGE_SIZE >= GRO_LEGACY_MAX_SIZE) + return skb->len + data_bcnt <= GRO_LEGACY_MAX_SIZE; + else + return PAGE_SIZE * nr_frags + data_bcnt <= GRO_LEGACY_MAX_SIZE; } static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c index cb1319974f83..ccef64fb40b6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c @@ -421,6 +421,13 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size) __be64 *pas; u32 i; + conn->cq.mcq.cqe_sz = 64; + conn->cq.mcq.set_ci_db = conn->cq.wq_ctrl.db.db; + conn->cq.mcq.arm_db = conn->cq.wq_ctrl.db.db + 1; + *conn->cq.mcq.set_ci_db = 0; + conn->cq.mcq.vector = 0; + conn->cq.mcq.comp = mlx5_fpga_conn_cq_complete; + cq_size = roundup_pow_of_two(cq_size); MLX5_SET(cqc, temp_cqc, log_cq_size, ilog2(cq_size)); @@ -468,15 +475,7 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size) if (err) goto err_cqwq; - conn->cq.mcq.cqe_sz = 64; - conn->cq.mcq.set_ci_db = conn->cq.wq_ctrl.db.db; - conn->cq.mcq.arm_db = conn->cq.wq_ctrl.db.db + 1; - *conn->cq.mcq.set_ci_db = 0; - *conn->cq.mcq.arm_db = 0; - conn->cq.mcq.vector = 0; - conn->cq.mcq.comp = mlx5_fpga_conn_cq_complete; tasklet_setup(&conn->cq.tasklet, mlx5_fpga_conn_cq_tasklet); - mlx5_fpga_dbg(fdev, "Created CQ #0x%x\n", conn->cq.mcq.cqn); goto out; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c index 24ef7d66fa8a..7510c46e58a5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c @@ -873,12 +873,6 @@ err_free_sqc: return err; } -static void hws_cq_complete(struct mlx5_core_cq *mcq, - struct mlx5_eqe *eqe) -{ - pr_err("CQ completion CQ: #%u\n", mcq->cqn); -} - static int hws_send_ring_alloc_cq(struct mlx5_core_dev *mdev, int numa_node, struct mlx5hws_send_engine *queue, @@ -901,7 +895,6 @@ static int hws_send_ring_alloc_cq(struct mlx5_core_dev *mdev, mcq->cqe_sz = 64; mcq->set_ci_db = cq->wq_ctrl.db.db; mcq->arm_db = cq->wq_ctrl.db.db + 1; - mcq->comp = hws_cq_complete; for (i = 0; i < mlx5_cqwq_get_size(&cq->wq); i++) { cqe = mlx5_cqwq_get_wqe(&cq->wq, i); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c index 077a77fde670..d034372fa047 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c @@ -1049,12 +1049,6 @@ static int dr_prepare_qp_to_rts(struct mlx5dr_domain *dmn) return 0; } -static void dr_cq_complete(struct mlx5_core_cq *mcq, - struct mlx5_eqe *eqe) -{ - pr_err("CQ completion CQ: #%u\n", mcq->cqn); -} - static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, struct mlx5_uars_page *uar, size_t ncqe) @@ -1089,6 +1083,13 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, cqe->op_own = MLX5_CQE_INVALID << 4 | MLX5_CQE_OWNER_MASK; } + cq->mcq.cqe_sz = 64; + cq->mcq.set_ci_db = cq->wq_ctrl.db.db; + cq->mcq.arm_db = cq->wq_ctrl.db.db + 1; + *cq->mcq.set_ci_db = 0; + cq->mcq.vector = 0; + cq->mdev = mdev; + inlen = MLX5_ST_SZ_BYTES(create_cq_in) + sizeof(u64) * cq->wq_ctrl.buf.npages; in = kvzalloc(inlen, GFP_KERNEL); @@ -1112,27 +1113,12 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, pas = (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas); mlx5_fill_page_frag_array(&cq->wq_ctrl.buf, pas); - cq->mcq.comp = dr_cq_complete; - err = mlx5_core_create_cq(mdev, &cq->mcq, in, inlen, out, sizeof(out)); kvfree(in); if (err) goto err_cqwq; - cq->mcq.cqe_sz = 64; - cq->mcq.set_ci_db = cq->wq_ctrl.db.db; - cq->mcq.arm_db = cq->wq_ctrl.db.db + 1; - *cq->mcq.set_ci_db = 0; - - /* set no-zero value, in order to avoid the HW to run db-recovery on - * CQ that used in polling mode. - */ - *cq->mcq.arm_db = cpu_to_be32(2 << 28); - - cq->mcq.vector = 0; - cq->mdev = mdev; - return cq; err_cqwq: diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_ethtool.c b/drivers/net/ethernet/microchip/lan966x/lan966x_ethtool.c index 2474dfd330f4..fe4e61405284 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_ethtool.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_ethtool.c @@ -294,7 +294,7 @@ static void lan966x_stats_update(struct lan966x *lan966x) { int i, j; - mutex_lock(&lan966x->stats_lock); + spin_lock(&lan966x->stats_lock); for (i = 0; i < lan966x->num_phys_ports; i++) { uint idx = i * lan966x->num_stats; @@ -310,7 +310,7 @@ static void lan966x_stats_update(struct lan966x *lan966x) } } - mutex_unlock(&lan966x->stats_lock); + spin_unlock(&lan966x->stats_lock); } static int lan966x_get_sset_count(struct net_device *dev, int sset) @@ -365,7 +365,7 @@ static void lan966x_get_eth_mac_stats(struct net_device *dev, idx = port->chip_port * lan966x->num_stats; - mutex_lock(&lan966x->stats_lock); + spin_lock(&lan966x->stats_lock); mac_stats->FramesTransmittedOK = lan966x->stats[idx + SYS_COUNT_TX_UC] + @@ -416,7 +416,7 @@ static void lan966x_get_eth_mac_stats(struct net_device *dev, lan966x->stats[idx + SYS_COUNT_RX_LONG] + lan966x->stats[idx + SYS_COUNT_RX_PMAC_LONG]; - mutex_unlock(&lan966x->stats_lock); + spin_unlock(&lan966x->stats_lock); } static const struct ethtool_rmon_hist_range lan966x_rmon_ranges[] = { @@ -442,7 +442,7 @@ static void lan966x_get_eth_rmon_stats(struct net_device *dev, idx = port->chip_port * lan966x->num_stats; - mutex_lock(&lan966x->stats_lock); + spin_lock(&lan966x->stats_lock); rmon_stats->undersize_pkts = lan966x->stats[idx + SYS_COUNT_RX_SHORT] + @@ -500,7 +500,7 @@ static void lan966x_get_eth_rmon_stats(struct net_device *dev, lan966x->stats[idx + SYS_COUNT_TX_SZ_1024_1526] + lan966x->stats[idx + SYS_COUNT_TX_PMAC_SZ_1024_1526]; - mutex_unlock(&lan966x->stats_lock); + spin_unlock(&lan966x->stats_lock); *ranges = lan966x_rmon_ranges; } @@ -603,7 +603,7 @@ void lan966x_stats_get(struct net_device *dev, idx = port->chip_port * lan966x->num_stats; - mutex_lock(&lan966x->stats_lock); + spin_lock(&lan966x->stats_lock); stats->rx_bytes = lan966x->stats[idx + SYS_COUNT_RX_OCT] + lan966x->stats[idx + SYS_COUNT_RX_PMAC_OCT]; @@ -685,7 +685,7 @@ void lan966x_stats_get(struct net_device *dev, stats->collisions = lan966x->stats[idx + SYS_COUNT_TX_COL]; - mutex_unlock(&lan966x->stats_lock); + spin_unlock(&lan966x->stats_lock); } int lan966x_stats_init(struct lan966x *lan966x) @@ -701,7 +701,7 @@ int lan966x_stats_init(struct lan966x *lan966x) return -ENOMEM; /* Init stats worker */ - mutex_init(&lan966x->stats_lock); + spin_lock_init(&lan966x->stats_lock); snprintf(queue_name, sizeof(queue_name), "%s-stats", dev_name(lan966x->dev)); lan966x->stats_queue = create_singlethread_workqueue(queue_name); diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c index 7001584f1b7a..47752d3fde0b 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c @@ -1261,7 +1261,6 @@ cleanup_ports: cancel_delayed_work_sync(&lan966x->stats_work); destroy_workqueue(lan966x->stats_queue); - mutex_destroy(&lan966x->stats_lock); debugfs_remove_recursive(lan966x->debugfs_root); @@ -1279,7 +1278,6 @@ static void lan966x_remove(struct platform_device *pdev) cancel_delayed_work_sync(&lan966x->stats_work); destroy_workqueue(lan966x->stats_queue); - mutex_destroy(&lan966x->stats_lock); lan966x_mac_purge_entries(lan966x); lan966x_mdb_deinit(lan966x); diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h index 4f75f0688369..eea286c29474 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h @@ -295,8 +295,8 @@ struct lan966x { const struct lan966x_stat_layout *stats_layout; u32 num_stats; - /* workqueue for reading stats */ - struct mutex stats_lock; + /* lock for reading stats */ + spinlock_t stats_lock; u64 *stats; struct delayed_work stats_work; struct workqueue_struct *stats_queue; diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c b/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c index a1471e38d118..2a37fc1ba4bc 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c @@ -403,11 +403,11 @@ static void lan966x_es0_read_esdx_counter(struct lan966x *lan966x, u32 counter; id = id & 0xff; /* counter limit */ - mutex_lock(&lan966x->stats_lock); + spin_lock(&lan966x->stats_lock); lan_wr(SYS_STAT_CFG_STAT_VIEW_SET(id), lan966x, SYS_STAT_CFG); counter = lan_rd(lan966x, SYS_CNT(LAN966X_STAT_ESDX_GRN_PKTS)) + lan_rd(lan966x, SYS_CNT(LAN966X_STAT_ESDX_YEL_PKTS)); - mutex_unlock(&lan966x->stats_lock); + spin_unlock(&lan966x->stats_lock); if (counter) admin->cache.counter = counter; } @@ -417,14 +417,14 @@ static void lan966x_es0_write_esdx_counter(struct lan966x *lan966x, { id = id & 0xff; /* counter limit */ - mutex_lock(&lan966x->stats_lock); + spin_lock(&lan966x->stats_lock); lan_wr(SYS_STAT_CFG_STAT_VIEW_SET(id), lan966x, SYS_STAT_CFG); lan_wr(0, lan966x, SYS_CNT(LAN966X_STAT_ESDX_GRN_BYTES)); lan_wr(admin->cache.counter, lan966x, SYS_CNT(LAN966X_STAT_ESDX_GRN_PKTS)); lan_wr(0, lan966x, SYS_CNT(LAN966X_STAT_ESDX_YEL_BYTES)); lan_wr(0, lan966x, SYS_CNT(LAN966X_STAT_ESDX_YEL_PKTS)); - mutex_unlock(&lan966x->stats_lock); + spin_unlock(&lan966x->stats_lock); } static void lan966x_vcap_cache_write(struct net_device *dev, diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c index d10b58ebf603..301ebee2fdc5 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -29,6 +29,10 @@ static void ionic_tx_clean(struct ionic_queue *q, static inline void ionic_txq_post(struct ionic_queue *q, bool ring_dbell) { + /* Ensure TX descriptor writes reach memory before NIC reads them. + * Prevents device from fetching stale descriptors. + */ + dma_wmb(); ionic_q_post(q, ring_dbell); } @@ -1444,19 +1448,6 @@ static int ionic_tx_tso(struct net_device *netdev, struct ionic_queue *q, bool encap; int err; - desc_info = &q->tx_info[q->head_idx]; - - if (unlikely(ionic_tx_map_skb(q, skb, desc_info))) - return -EIO; - - len = skb->len; - mss = skb_shinfo(skb)->gso_size; - outer_csum = (skb_shinfo(skb)->gso_type & (SKB_GSO_GRE | - SKB_GSO_GRE_CSUM | - SKB_GSO_IPXIP4 | - SKB_GSO_IPXIP6 | - SKB_GSO_UDP_TUNNEL | - SKB_GSO_UDP_TUNNEL_CSUM)); has_vlan = !!skb_vlan_tag_present(skb); vlan_tci = skb_vlan_tag_get(skb); encap = skb->encapsulation; @@ -1470,12 +1461,21 @@ static int ionic_tx_tso(struct net_device *netdev, struct ionic_queue *q, err = ionic_tx_tcp_inner_pseudo_csum(skb); else err = ionic_tx_tcp_pseudo_csum(skb); - if (unlikely(err)) { - /* clean up mapping from ionic_tx_map_skb */ - ionic_tx_desc_unmap_bufs(q, desc_info); + if (unlikely(err)) return err; - } + desc_info = &q->tx_info[q->head_idx]; + if (unlikely(ionic_tx_map_skb(q, skb, desc_info))) + return -EIO; + + len = skb->len; + mss = skb_shinfo(skb)->gso_size; + outer_csum = (skb_shinfo(skb)->gso_type & (SKB_GSO_GRE | + SKB_GSO_GRE_CSUM | + SKB_GSO_IPXIP4 | + SKB_GSO_IPXIP6 | + SKB_GSO_UDP_TUNNEL | + SKB_GSO_UDP_TUNNEL_CSUM)); if (encap) hdrlen = skb_inner_tcp_all_headers(skb); else diff --git a/drivers/net/ethernet/spacemit/k1_emac.c b/drivers/net/ethernet/spacemit/k1_emac.c index e1c5faff3b71..220eb5ce7583 100644 --- a/drivers/net/ethernet/spacemit/k1_emac.c +++ b/drivers/net/ethernet/spacemit/k1_emac.c @@ -1441,6 +1441,9 @@ static int emac_set_pauseparam(struct net_device *dev, struct emac_priv *priv = netdev_priv(dev); u8 fc = 0; + if (!netif_running(dev)) + return -ENETDOWN; + priv->flow_control_autoneg = pause->autoneg; if (pause->autoneg) { diff --git a/drivers/net/ethernet/ti/am65-cpsw-qos.c b/drivers/net/ethernet/ti/am65-cpsw-qos.c index fa96db7c1a13..66e8b224827b 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-qos.c +++ b/drivers/net/ethernet/ti/am65-cpsw-qos.c @@ -276,9 +276,31 @@ static int am65_cpsw_iet_set_verify_timeout_count(struct am65_cpsw_port *port) /* The number of wireside clocks contained in the verify * timeout counter. The default is 0x1312d0 * (10ms at 125Mhz in 1G mode). + * The frequency of the clock depends on the link speed + * and the PHY interface. */ - val = 125 * HZ_PER_MHZ; /* assuming 125MHz wireside clock */ + switch (port->slave.phy_if) { + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: + if (port->qos.link_speed == SPEED_1000) + val = 125 * HZ_PER_MHZ; /* 125 MHz at 1000Mbps*/ + else if (port->qos.link_speed == SPEED_100) + val = 25 * HZ_PER_MHZ; /* 25 MHz at 100Mbps*/ + else + val = (25 * HZ_PER_MHZ) / 10; /* 2.5 MHz at 10Mbps*/ + break; + + case PHY_INTERFACE_MODE_QSGMII: + case PHY_INTERFACE_MODE_SGMII: + val = 125 * HZ_PER_MHZ; /* 125 MHz */ + break; + default: + netdev_err(port->ndev, "selected mode does not supported IET\n"); + return -EOPNOTSUPP; + } val /= MILLIHZ_PER_HZ; /* count per ms timeout */ val *= verify_time_ms; /* count for timeout ms */ @@ -295,20 +317,21 @@ static int am65_cpsw_iet_verify_wait(struct am65_cpsw_port *port) u32 ctrl, status; int try; - try = 20; - do { - /* Reset the verify state machine by writing 1 - * to LINKFAIL - */ - ctrl = readl(port->port_base + AM65_CPSW_PN_REG_IET_CTRL); - ctrl |= AM65_CPSW_PN_IET_MAC_LINKFAIL; - writel(ctrl, port->port_base + AM65_CPSW_PN_REG_IET_CTRL); + try = 3; - /* Clear MAC_LINKFAIL bit to start Verify. */ - ctrl = readl(port->port_base + AM65_CPSW_PN_REG_IET_CTRL); - ctrl &= ~AM65_CPSW_PN_IET_MAC_LINKFAIL; - writel(ctrl, port->port_base + AM65_CPSW_PN_REG_IET_CTRL); + /* Reset the verify state machine by writing 1 + * to LINKFAIL + */ + ctrl = readl(port->port_base + AM65_CPSW_PN_REG_IET_CTRL); + ctrl |= AM65_CPSW_PN_IET_MAC_LINKFAIL; + writel(ctrl, port->port_base + AM65_CPSW_PN_REG_IET_CTRL); + /* Clear MAC_LINKFAIL bit to start Verify. */ + ctrl = readl(port->port_base + AM65_CPSW_PN_REG_IET_CTRL); + ctrl &= ~AM65_CPSW_PN_IET_MAC_LINKFAIL; + writel(ctrl, port->port_base + AM65_CPSW_PN_REG_IET_CTRL); + + do { msleep(port->qos.iet.verify_time_ms); status = readl(port->port_base + AM65_CPSW_PN_REG_IET_STATUS); @@ -330,7 +353,7 @@ static int am65_cpsw_iet_verify_wait(struct am65_cpsw_port *port) netdev_dbg(port->ndev, "MAC Merge verify error\n"); return -ENODEV; } - } while (try-- > 0); + } while (--try > 0); netdev_dbg(port->ndev, "MAC Merge verify timeout\n"); return -ETIMEDOUT; diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.c b/drivers/net/ethernet/ti/icssg/icssg_config.c index da53eb04b0a4..3f8237c17d09 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_config.c +++ b/drivers/net/ethernet/ti/icssg/icssg_config.c @@ -66,6 +66,9 @@ #define FDB_GEN_CFG1 0x60 #define SMEM_VLAN_OFFSET 8 #define SMEM_VLAN_OFFSET_MASK GENMASK(25, 8) +#define FDB_HASH_SIZE_MASK GENMASK(6, 3) +#define FDB_HASH_SIZE_SHIFT 3 +#define FDB_HASH_SIZE 3 #define FDB_GEN_CFG2 0x64 #define FDB_VLAN_EN BIT(6) @@ -463,6 +466,8 @@ void icssg_init_emac_mode(struct prueth *prueth) /* Set VLAN TABLE address base */ regmap_update_bits(prueth->miig_rt, FDB_GEN_CFG1, SMEM_VLAN_OFFSET_MASK, addr << SMEM_VLAN_OFFSET); + regmap_update_bits(prueth->miig_rt, FDB_GEN_CFG1, FDB_HASH_SIZE_MASK, + FDB_HASH_SIZE << FDB_HASH_SIZE_SHIFT); /* Set enable VLAN aware mode, and FDBs for all PRUs */ regmap_write(prueth->miig_rt, FDB_GEN_CFG2, (FDB_PRU0_EN | FDB_PRU1_EN | FDB_HOST_EN)); prueth->vlan_tbl = (struct prueth_vlan_tbl __force *)(prueth->shram.va + @@ -484,6 +489,8 @@ void icssg_init_fw_offload_mode(struct prueth *prueth) /* Set VLAN TABLE address base */ regmap_update_bits(prueth->miig_rt, FDB_GEN_CFG1, SMEM_VLAN_OFFSET_MASK, addr << SMEM_VLAN_OFFSET); + regmap_update_bits(prueth->miig_rt, FDB_GEN_CFG1, FDB_HASH_SIZE_MASK, + FDB_HASH_SIZE << FDB_HASH_SIZE_SHIFT); /* Set enable VLAN aware mode, and FDBs for all PRUs */ regmap_write(prueth->miig_rt, FDB_GEN_CFG2, FDB_EN_ALL); prueth->vlan_tbl = (struct prueth_vlan_tbl __force *)(prueth->shram.va + diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index 857820657bac..5ee13db568f0 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -1338,10 +1338,10 @@ int netcp_txpipe_open(struct netcp_tx_pipe *tx_pipe) tx_pipe->dma_channel = knav_dma_open_channel(dev, tx_pipe->dma_chan_name, &config); - if (IS_ERR(tx_pipe->dma_channel)) { + if (!tx_pipe->dma_channel) { dev_err(dev, "failed opening tx chan(%s)\n", tx_pipe->dma_chan_name); - ret = PTR_ERR(tx_pipe->dma_channel); + ret = -EINVAL; goto err; } @@ -1359,7 +1359,7 @@ int netcp_txpipe_open(struct netcp_tx_pipe *tx_pipe) return 0; err: - if (!IS_ERR_OR_NULL(tx_pipe->dma_channel)) + if (tx_pipe->dma_channel) knav_dma_close_channel(tx_pipe->dma_channel); tx_pipe->dma_channel = NULL; return ret; @@ -1678,10 +1678,10 @@ static int netcp_setup_navigator_resources(struct net_device *ndev) netcp->rx_channel = knav_dma_open_channel(netcp->netcp_device->device, netcp->dma_chan_name, &config); - if (IS_ERR(netcp->rx_channel)) { + if (!netcp->rx_channel) { dev_err(netcp->ndev_dev, "failed opening rx chan(%s\n", netcp->dma_chan_name); - ret = PTR_ERR(netcp->rx_channel); + ret = -EINVAL; goto fail; } diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c index 1e2713f0c921..b37d6cfbfbe9 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c @@ -2427,7 +2427,8 @@ int wx_sw_init(struct wx *wx) wx->oem_svid = pdev->subsystem_vendor; wx->oem_ssid = pdev->subsystem_device; wx->bus.device = PCI_SLOT(pdev->devfn); - wx->bus.func = PCI_FUNC(pdev->devfn); + wx->bus.func = FIELD_GET(WX_CFG_PORT_ST_LANID, + rd32(wx, WX_CFG_PORT_ST)); if (wx->oem_svid == PCI_VENDOR_ID_WANGXUN || pdev->is_virtfn) { diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h index d89b9b8a0a2c..2f8319e03182 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_type.h +++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h @@ -97,6 +97,8 @@ #define WX_CFG_PORT_CTL_DRV_LOAD BIT(3) #define WX_CFG_PORT_CTL_QINQ BIT(2) #define WX_CFG_PORT_CTL_D_VLAN BIT(0) /* double vlan*/ +#define WX_CFG_PORT_ST 0x14404 +#define WX_CFG_PORT_ST_LANID GENMASK(9, 8) #define WX_CFG_TAG_TPID(_i) (0x14430 + ((_i) * 4)) #define WX_CFG_PORT_CTL_NUM_VT_MASK GENMASK(13, 12) /* number of TVs */ @@ -557,8 +559,6 @@ enum WX_MSCA_CMD_value { #define TXD_USE_COUNT(S) DIV_ROUND_UP((S), WX_MAX_DATA_PER_TXD) #define DESC_NEEDED (MAX_SKB_FRAGS + 4) -#define WX_CFG_PORT_ST 0x14404 - /******************* Receive Descriptor bit definitions **********************/ #define WX_RXD_STAT_DD BIT(0) /* Done */ #define WX_RXD_STAT_EOP BIT(1) /* End of Packet */ diff --git a/drivers/net/mdio/mdio-airoha.c b/drivers/net/mdio/mdio-airoha.c index 1dc9939c8d7d..52e7475121ea 100644 --- a/drivers/net/mdio/mdio-airoha.c +++ b/drivers/net/mdio/mdio-airoha.c @@ -219,6 +219,8 @@ static int airoha_mdio_probe(struct platform_device *pdev) priv = bus->priv; priv->base_addr = addr; priv->regmap = device_node_to_regmap(dev->parent->of_node); + if (IS_ERR(priv->regmap)) + return PTR_ERR(priv->regmap); priv->clk = devm_clk_get_enabled(dev, NULL); if (IS_ERR(priv->clk)) diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index 5d8d0214786c..bb6e03a92956 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -936,6 +936,7 @@ static ssize_t userdatum_value_store(struct config_item *item, const char *buf, if (count > MAX_EXTRADATA_VALUE_LEN) return -EMSGSIZE; + mutex_lock(&netconsole_subsys.su_mutex); mutex_lock(&dynamic_netconsole_mutex); ret = strscpy(udm->value, buf, sizeof(udm->value)); @@ -949,6 +950,7 @@ static ssize_t userdatum_value_store(struct config_item *item, const char *buf, ret = count; out_unlock: mutex_unlock(&dynamic_netconsole_mutex); + mutex_unlock(&netconsole_subsys.su_mutex); return ret; } @@ -974,6 +976,7 @@ static ssize_t sysdata_msgid_enabled_store(struct config_item *item, if (ret) return ret; + mutex_lock(&netconsole_subsys.su_mutex); mutex_lock(&dynamic_netconsole_mutex); curr = !!(nt->sysdata_fields & SYSDATA_MSGID); if (msgid_enabled == curr) @@ -994,6 +997,7 @@ unlock_ok: ret = strnlen(buf, count); unlock: mutex_unlock(&dynamic_netconsole_mutex); + mutex_unlock(&netconsole_subsys.su_mutex); return ret; } @@ -1008,6 +1012,7 @@ static ssize_t sysdata_release_enabled_store(struct config_item *item, if (ret) return ret; + mutex_lock(&netconsole_subsys.su_mutex); mutex_lock(&dynamic_netconsole_mutex); curr = !!(nt->sysdata_fields & SYSDATA_RELEASE); if (release_enabled == curr) @@ -1028,6 +1033,7 @@ unlock_ok: ret = strnlen(buf, count); unlock: mutex_unlock(&dynamic_netconsole_mutex); + mutex_unlock(&netconsole_subsys.su_mutex); return ret; } @@ -1042,6 +1048,7 @@ static ssize_t sysdata_taskname_enabled_store(struct config_item *item, if (ret) return ret; + mutex_lock(&netconsole_subsys.su_mutex); mutex_lock(&dynamic_netconsole_mutex); curr = !!(nt->sysdata_fields & SYSDATA_TASKNAME); if (taskname_enabled == curr) @@ -1062,6 +1069,7 @@ unlock_ok: ret = strnlen(buf, count); unlock: mutex_unlock(&dynamic_netconsole_mutex); + mutex_unlock(&netconsole_subsys.su_mutex); return ret; } @@ -1077,6 +1085,7 @@ static ssize_t sysdata_cpu_nr_enabled_store(struct config_item *item, if (ret) return ret; + mutex_lock(&netconsole_subsys.su_mutex); mutex_lock(&dynamic_netconsole_mutex); curr = !!(nt->sysdata_fields & SYSDATA_CPU_NR); if (cpu_nr_enabled == curr) @@ -1105,6 +1114,7 @@ unlock_ok: ret = strnlen(buf, count); unlock: mutex_unlock(&dynamic_netconsole_mutex); + mutex_unlock(&netconsole_subsys.su_mutex); return ret; } diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index cad6ed3aa10b..4354241137d5 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -73,8 +73,11 @@ int mdiobus_register_device(struct mdio_device *mdiodev) return err; err = mdiobus_register_reset(mdiodev); - if (err) + if (err) { + gpiod_put(mdiodev->reset_gpio); + mdiodev->reset_gpio = NULL; return err; + } /* Assert the reset signal */ mdio_device_reset(mdiodev, 1); diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 604b5de0c158..01c87c9b7702 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -466,6 +466,12 @@ struct lan8842_priv { u16 rev; }; +struct lanphy_reg_data { + int page; + u16 addr; + u16 val; +}; + static const struct kszphy_type lan8814_type = { .led_mode_reg = ~LAN8814_LED_CTRL_1, .cable_diag_reg = LAN8814_CABLE_DIAG, @@ -2836,6 +2842,13 @@ static int ksz886x_cable_test_get_status(struct phy_device *phydev, #define LAN8814_PAGE_PCS_DIGITAL 2 /** + * LAN8814_PAGE_EEE - Selects Extended Page 3. + * + * This page contains EEE registers + */ +#define LAN8814_PAGE_EEE 3 + +/** * LAN8814_PAGE_COMMON_REGS - Selects Extended Page 4. * * This page contains device-common registers that affect the entire chip. @@ -2854,6 +2867,13 @@ static int ksz886x_cable_test_get_status(struct phy_device *phydev, #define LAN8814_PAGE_PORT_REGS 5 /** + * LAN8814_PAGE_POWER_REGS - Selects Extended Page 28. + * + * This page contains analog control registers and power mode registers. + */ +#define LAN8814_PAGE_POWER_REGS 28 + +/** * LAN8814_PAGE_SYSTEM_CTRL - Selects Extended Page 31. * * This page appears to hold fundamental system or global controls. In the @@ -4360,12 +4380,6 @@ static int lan8814_config_init(struct phy_device *phydev) { struct kszphy_priv *lan8814 = phydev->priv; - /* Reset the PHY */ - lanphy_modify_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, - LAN8814_QSGMII_SOFT_RESET, - LAN8814_QSGMII_SOFT_RESET_BIT, - LAN8814_QSGMII_SOFT_RESET_BIT); - /* Disable ANEG with QSGMII PCS Host side */ lanphy_modify_page_reg(phydev, LAN8814_PAGE_PORT_REGS, LAN8814_QSGMII_PCS1G_ANEG_CONFIG, @@ -4451,6 +4465,12 @@ static int lan8814_probe(struct phy_device *phydev) addr, sizeof(struct lan8814_shared_priv)); if (phy_package_init_once(phydev)) { + /* Reset the PHY */ + lanphy_modify_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + LAN8814_QSGMII_SOFT_RESET, + LAN8814_QSGMII_SOFT_RESET_BIT, + LAN8814_QSGMII_SOFT_RESET_BIT); + err = lan8814_release_coma_mode(phydev); if (err) return err; @@ -5884,6 +5904,144 @@ static int lan8842_probe(struct phy_device *phydev) return 0; } +#define LAN8814_POWER_MGMT_MODE_3_ANEG_MDI 0x13 +#define LAN8814_POWER_MGMT_MODE_4_ANEG_MDIX 0x14 +#define LAN8814_POWER_MGMT_MODE_5_10BT_MDI 0x15 +#define LAN8814_POWER_MGMT_MODE_6_10BT_MDIX 0x16 +#define LAN8814_POWER_MGMT_MODE_7_100BT_TRAIN 0x17 +#define LAN8814_POWER_MGMT_MODE_8_100BT_MDI 0x18 +#define LAN8814_POWER_MGMT_MODE_9_100BT_EEE_MDI_TX 0x19 +#define LAN8814_POWER_MGMT_MODE_10_100BT_EEE_MDI_RX 0x1a +#define LAN8814_POWER_MGMT_MODE_11_100BT_MDIX 0x1b +#define LAN8814_POWER_MGMT_MODE_12_100BT_EEE_MDIX_TX 0x1c +#define LAN8814_POWER_MGMT_MODE_13_100BT_EEE_MDIX_RX 0x1d +#define LAN8814_POWER_MGMT_MODE_14_100BTX_EEE_TX_RX 0x1e + +#define LAN8814_POWER_MGMT_DLLPD_D BIT(0) +#define LAN8814_POWER_MGMT_ADCPD_D BIT(1) +#define LAN8814_POWER_MGMT_PGAPD_D BIT(2) +#define LAN8814_POWER_MGMT_TXPD_D BIT(3) +#define LAN8814_POWER_MGMT_DLLPD_C BIT(4) +#define LAN8814_POWER_MGMT_ADCPD_C BIT(5) +#define LAN8814_POWER_MGMT_PGAPD_C BIT(6) +#define LAN8814_POWER_MGMT_TXPD_C BIT(7) +#define LAN8814_POWER_MGMT_DLLPD_B BIT(8) +#define LAN8814_POWER_MGMT_ADCPD_B BIT(9) +#define LAN8814_POWER_MGMT_PGAPD_B BIT(10) +#define LAN8814_POWER_MGMT_TXPD_B BIT(11) +#define LAN8814_POWER_MGMT_DLLPD_A BIT(12) +#define LAN8814_POWER_MGMT_ADCPD_A BIT(13) +#define LAN8814_POWER_MGMT_PGAPD_A BIT(14) +#define LAN8814_POWER_MGMT_TXPD_A BIT(15) + +#define LAN8814_POWER_MGMT_C_D (LAN8814_POWER_MGMT_DLLPD_D | \ + LAN8814_POWER_MGMT_ADCPD_D | \ + LAN8814_POWER_MGMT_PGAPD_D | \ + LAN8814_POWER_MGMT_DLLPD_C | \ + LAN8814_POWER_MGMT_ADCPD_C | \ + LAN8814_POWER_MGMT_PGAPD_C) + +#define LAN8814_POWER_MGMT_B_C_D (LAN8814_POWER_MGMT_C_D | \ + LAN8814_POWER_MGMT_DLLPD_B | \ + LAN8814_POWER_MGMT_ADCPD_B | \ + LAN8814_POWER_MGMT_PGAPD_B) + +#define LAN8814_POWER_MGMT_VAL1 (LAN8814_POWER_MGMT_C_D | \ + LAN8814_POWER_MGMT_ADCPD_B | \ + LAN8814_POWER_MGMT_PGAPD_B | \ + LAN8814_POWER_MGMT_ADCPD_A | \ + LAN8814_POWER_MGMT_PGAPD_A) + +#define LAN8814_POWER_MGMT_VAL2 LAN8814_POWER_MGMT_C_D + +#define LAN8814_POWER_MGMT_VAL3 (LAN8814_POWER_MGMT_C_D | \ + LAN8814_POWER_MGMT_DLLPD_B | \ + LAN8814_POWER_MGMT_ADCPD_B | \ + LAN8814_POWER_MGMT_PGAPD_A) + +#define LAN8814_POWER_MGMT_VAL4 (LAN8814_POWER_MGMT_B_C_D | \ + LAN8814_POWER_MGMT_ADCPD_A | \ + LAN8814_POWER_MGMT_PGAPD_A) + +#define LAN8814_POWER_MGMT_VAL5 LAN8814_POWER_MGMT_B_C_D + +#define LAN8814_EEE_WAKE_TX_TIMER 0x0e +#define LAN8814_EEE_WAKE_TX_TIMER_MAX_VAL 0x1f + +static const struct lanphy_reg_data short_center_tap_errata[] = { + { LAN8814_PAGE_POWER_REGS, + LAN8814_POWER_MGMT_MODE_3_ANEG_MDI, + LAN8814_POWER_MGMT_VAL1 }, + { LAN8814_PAGE_POWER_REGS, + LAN8814_POWER_MGMT_MODE_4_ANEG_MDIX, + LAN8814_POWER_MGMT_VAL1 }, + { LAN8814_PAGE_POWER_REGS, + LAN8814_POWER_MGMT_MODE_5_10BT_MDI, + LAN8814_POWER_MGMT_VAL1 }, + { LAN8814_PAGE_POWER_REGS, + LAN8814_POWER_MGMT_MODE_6_10BT_MDIX, + LAN8814_POWER_MGMT_VAL1 }, + { LAN8814_PAGE_POWER_REGS, + LAN8814_POWER_MGMT_MODE_7_100BT_TRAIN, + LAN8814_POWER_MGMT_VAL2 }, + { LAN8814_PAGE_POWER_REGS, + LAN8814_POWER_MGMT_MODE_8_100BT_MDI, + LAN8814_POWER_MGMT_VAL3 }, + { LAN8814_PAGE_POWER_REGS, + LAN8814_POWER_MGMT_MODE_9_100BT_EEE_MDI_TX, + LAN8814_POWER_MGMT_VAL3 }, + { LAN8814_PAGE_POWER_REGS, + LAN8814_POWER_MGMT_MODE_10_100BT_EEE_MDI_RX, + LAN8814_POWER_MGMT_VAL4 }, + { LAN8814_PAGE_POWER_REGS, + LAN8814_POWER_MGMT_MODE_11_100BT_MDIX, + LAN8814_POWER_MGMT_VAL5 }, + { LAN8814_PAGE_POWER_REGS, + LAN8814_POWER_MGMT_MODE_12_100BT_EEE_MDIX_TX, + LAN8814_POWER_MGMT_VAL5 }, + { LAN8814_PAGE_POWER_REGS, + LAN8814_POWER_MGMT_MODE_13_100BT_EEE_MDIX_RX, + LAN8814_POWER_MGMT_VAL4 }, + { LAN8814_PAGE_POWER_REGS, + LAN8814_POWER_MGMT_MODE_14_100BTX_EEE_TX_RX, + LAN8814_POWER_MGMT_VAL4 }, +}; + +static const struct lanphy_reg_data waketx_timer_errata[] = { + { LAN8814_PAGE_EEE, + LAN8814_EEE_WAKE_TX_TIMER, + LAN8814_EEE_WAKE_TX_TIMER_MAX_VAL }, +}; + +static int lanphy_write_reg_data(struct phy_device *phydev, + const struct lanphy_reg_data *data, + size_t num) +{ + int ret = 0; + + while (num--) { + ret = lanphy_write_page_reg(phydev, data->page, data->addr, + data->val); + if (ret) + break; + } + + return ret; +} + +static int lan8842_erratas(struct phy_device *phydev) +{ + int ret; + + ret = lanphy_write_reg_data(phydev, short_center_tap_errata, + ARRAY_SIZE(short_center_tap_errata)); + if (ret) + return ret; + + return lanphy_write_reg_data(phydev, waketx_timer_errata, + ARRAY_SIZE(waketx_timer_errata)); +} + static int lan8842_config_init(struct phy_device *phydev) { int ret; @@ -5896,6 +6054,11 @@ static int lan8842_config_init(struct phy_device *phydev) if (ret < 0) return ret; + /* Apply the erratas for this device */ + ret = lan8842_erratas(phydev); + if (ret < 0) + return ret; + /* Even if the GPIOs are set to control the LEDs the behaviour of the * LEDs is wrong, they are not blinking when there is traffic. * To fix this it is required to set extended LED mode diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 11352d85475a..3a4985b582cb 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -192,6 +192,12 @@ static int qmimux_rx_fixup(struct usbnet *dev, struct sk_buff *skb) if (!skbn) return 0; + /* Raw IP packets don't have a MAC header, but other subsystems + * (like xfrm) may still access MAC header offsets, so they must + * be initialized. + */ + skb_reset_mac_header(skbn); + switch (skb->data[offset + qmimux_hdr_sz] & 0xf0) { case 0x40: skbn->protocol = htons(ETH_P_IP); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 8e8a179aaa49..0369dda5ed60 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -910,17 +910,6 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi, goto ok; } - /* - * Verify that we can indeed put this data into a skb. - * This is here to handle cases when the device erroneously - * tries to receive more than is possible. This is usually - * the case of a broken device. - */ - if (unlikely(len > MAX_SKB_FRAGS * PAGE_SIZE)) { - net_dbg_ratelimited("%s: too much data\n", skb->dev->name); - dev_kfree_skb(skb); - return NULL; - } BUG_ON(offset >= PAGE_SIZE); while (len) { unsigned int frag_size = min((unsigned)PAGE_SIZE - offset, len); @@ -2112,9 +2101,19 @@ static struct sk_buff *receive_big(struct net_device *dev, struct virtnet_rq_stats *stats) { struct page *page = buf; - struct sk_buff *skb = - page_to_skb(vi, rq, page, 0, len, PAGE_SIZE, 0); + struct sk_buff *skb; + /* Make sure that len does not exceed the size allocated in + * add_recvbuf_big. + */ + if (unlikely(len > (vi->big_packets_num_skbfrags + 1) * PAGE_SIZE)) { + pr_debug("%s: rx error: len %u exceeds allocated size %lu\n", + dev->name, len, + (vi->big_packets_num_skbfrags + 1) * PAGE_SIZE); + goto err; + } + + skb = page_to_skb(vi, rq, page, 0, len, PAGE_SIZE, 0); u64_stats_add(&stats->bytes, len - vi->hdr_len); if (unlikely(!skb)) goto err; @@ -2539,6 +2538,13 @@ err_buf: return NULL; } +static inline u32 +virtio_net_hash_value(const struct virtio_net_hdr_v1_hash *hdr_hash) +{ + return __le16_to_cpu(hdr_hash->hash_value_lo) | + (__le16_to_cpu(hdr_hash->hash_value_hi) << 16); +} + static void virtio_skb_set_hash(const struct virtio_net_hdr_v1_hash *hdr_hash, struct sk_buff *skb) { @@ -2565,7 +2571,7 @@ static void virtio_skb_set_hash(const struct virtio_net_hdr_v1_hash *hdr_hash, default: rss_hash_type = PKT_HASH_TYPE_NONE; } - skb_set_hash(skb, __le32_to_cpu(hdr_hash->hash_value), rss_hash_type); + skb_set_hash(skb, virtio_net_hash_value(hdr_hash), rss_hash_type); } static void virtnet_receive_done(struct virtnet_info *vi, struct receive_queue *rq, @@ -2625,22 +2631,28 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq, return; } - /* 1. Save the flags early, as the XDP program might overwrite them. + /* About the flags below: + * 1. Save the flags early, as the XDP program might overwrite them. * These flags ensure packets marked as VIRTIO_NET_HDR_F_DATA_VALID * stay valid after XDP processing. * 2. XDP doesn't work with partially checksummed packets (refer to * virtnet_xdp_set()), so packets marked as * VIRTIO_NET_HDR_F_NEEDS_CSUM get dropped during XDP processing. */ - flags = ((struct virtio_net_common_hdr *)buf)->hdr.flags; - if (vi->mergeable_rx_bufs) + if (vi->mergeable_rx_bufs) { + flags = ((struct virtio_net_common_hdr *)buf)->hdr.flags; skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit, stats); - else if (vi->big_packets) + } else if (vi->big_packets) { + void *p = page_address((struct page *)buf); + + flags = ((struct virtio_net_common_hdr *)p)->hdr.flags; skb = receive_big(dev, vi, rq, buf, len, stats); - else + } else { + flags = ((struct virtio_net_common_hdr *)buf)->hdr.flags; skb = receive_small(dev, vi, rq, buf, ctx, len, xdp_xmit, stats); + } if (unlikely(!skb)) return; @@ -3311,6 +3323,10 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb, bool orphan) pr_debug("%s: xmit %p %pM\n", vi->dev->name, skb, dest); + /* Make sure it's safe to cast between formats */ + BUILD_BUG_ON(__alignof__(*hdr) != __alignof__(hdr->hash_hdr)); + BUILD_BUG_ON(__alignof__(*hdr) != __alignof__(hdr->hash_hdr.hdr)); + can_push = vi->any_header_sg && !((unsigned long)skb->data & (__alignof__(*hdr) - 1)) && !skb_header_cloned(skb) && skb_headroom(skb) >= hdr_len; @@ -6750,7 +6766,7 @@ static int virtnet_xdp_rx_hash(const struct xdp_md *_ctx, u32 *hash, hash_report = VIRTIO_NET_HASH_REPORT_NONE; *rss_type = virtnet_xdp_rss_type[hash_report]; - *hash = __le32_to_cpu(hdr_hash->hash_value); + *hash = virtio_net_hash_value(hdr_hash); return 0; } diff --git a/drivers/net/wan/framer/pef2256/pef2256.c b/drivers/net/wan/framer/pef2256/pef2256.c index c5501826db1e..c058cc79137d 100644 --- a/drivers/net/wan/framer/pef2256/pef2256.c +++ b/drivers/net/wan/framer/pef2256/pef2256.c @@ -648,7 +648,8 @@ static int pef2256_add_audio_devices(struct pef2256 *pef2256) audio_devs[i].id = i; } - ret = mfd_add_devices(pef2256->dev, 0, audio_devs, count, NULL, 0, NULL); + ret = devm_mfd_add_devices(pef2256->dev, 0, audio_devs, count, + NULL, 0, NULL); kfree(audio_devs); return ret; } @@ -822,8 +823,8 @@ static int pef2256_probe(struct platform_device *pdev) platform_set_drvdata(pdev, pef2256); - ret = mfd_add_devices(pef2256->dev, 0, pef2256_devs, - ARRAY_SIZE(pef2256_devs), NULL, 0, NULL); + ret = devm_mfd_add_devices(pef2256->dev, 0, pef2256_devs, + ARRAY_SIZE(pef2256_devs), NULL, 0, NULL); if (ret) { dev_err(pef2256->dev, "add devices failed (%d)\n", ret); return ret; diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c index b3b00d324075..b4aad6604d6d 100644 --- a/drivers/net/wireless/ath/ath10k/wmi.c +++ b/drivers/net/wireless/ath/ath10k/wmi.c @@ -1764,32 +1764,33 @@ void ath10k_wmi_put_wmi_channel(struct ath10k *ar, struct wmi_channel *ch, int ath10k_wmi_wait_for_service_ready(struct ath10k *ar) { - unsigned long timeout = jiffies + WMI_SERVICE_READY_TIMEOUT_HZ; unsigned long time_left, i; - /* Sometimes the PCI HIF doesn't receive interrupt - * for the service ready message even if the buffer - * was completed. PCIe sniffer shows that it's - * because the corresponding CE ring doesn't fires - * it. Workaround here by polling CE rings. Since - * the message could arrive at any time, continue - * polling until timeout. - */ - do { + time_left = wait_for_completion_timeout(&ar->wmi.service_ready, + WMI_SERVICE_READY_TIMEOUT_HZ); + if (!time_left) { + /* Sometimes the PCI HIF doesn't receive interrupt + * for the service ready message even if the buffer + * was completed. PCIe sniffer shows that it's + * because the corresponding CE ring doesn't fires + * it. Workaround here by polling CE rings once. + */ + ath10k_warn(ar, "failed to receive service ready completion, polling..\n"); + for (i = 0; i < CE_COUNT; i++) ath10k_hif_send_complete_check(ar, i, 1); - /* The 100 ms granularity is a tradeoff considering scheduler - * overhead and response latency - */ time_left = wait_for_completion_timeout(&ar->wmi.service_ready, - msecs_to_jiffies(100)); - if (time_left) - return 0; - } while (time_before(jiffies, timeout)); + WMI_SERVICE_READY_TIMEOUT_HZ); + if (!time_left) { + ath10k_warn(ar, "polling timed out\n"); + return -ETIMEDOUT; + } + + ath10k_warn(ar, "service ready completion received, continuing normally\n"); + } - ath10k_warn(ar, "failed to receive service ready completion\n"); - return -ETIMEDOUT; + return 0; } int ath10k_wmi_wait_for_unified_ready(struct ath10k *ar) diff --git a/drivers/net/wireless/ath/ath11k/wmi.c b/drivers/net/wireless/ath/ath11k/wmi.c index 0491e3fd6b5e..e3b444333dee 100644 --- a/drivers/net/wireless/ath/ath11k/wmi.c +++ b/drivers/net/wireless/ath/ath11k/wmi.c @@ -5961,6 +5961,9 @@ static int wmi_process_mgmt_tx_comp(struct ath11k *ar, dma_unmap_single(ar->ab->dev, skb_cb->paddr, msdu->len, DMA_TO_DEVICE); info = IEEE80211_SKB_CB(msdu); + memset(&info->status, 0, sizeof(info->status)); + info->status.rates[0].idx = -1; + if ((!(info->flags & IEEE80211_TX_CTL_NO_ACK)) && !tx_compl_param->status) { info->flags |= IEEE80211_TX_STAT_ACK; diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c index eacab798630a..db351c922018 100644 --- a/drivers/net/wireless/ath/ath12k/mac.c +++ b/drivers/net/wireless/ath/ath12k/mac.c @@ -4064,68 +4064,12 @@ static int ath12k_mac_fils_discovery(struct ath12k_link_vif *arvif, return ret; } -static void ath12k_mac_vif_setup_ps(struct ath12k_link_vif *arvif) -{ - struct ath12k *ar = arvif->ar; - struct ieee80211_vif *vif = arvif->ahvif->vif; - struct ieee80211_conf *conf = &ath12k_ar_to_hw(ar)->conf; - enum wmi_sta_powersave_param param; - struct ieee80211_bss_conf *info; - enum wmi_sta_ps_mode psmode; - int ret; - int timeout; - bool enable_ps; - - lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); - - if (vif->type != NL80211_IFTYPE_STATION) - return; - - enable_ps = arvif->ahvif->ps; - if (enable_ps) { - psmode = WMI_STA_PS_MODE_ENABLED; - param = WMI_STA_PS_PARAM_INACTIVITY_TIME; - - timeout = conf->dynamic_ps_timeout; - if (timeout == 0) { - info = ath12k_mac_get_link_bss_conf(arvif); - if (!info) { - ath12k_warn(ar->ab, "unable to access bss link conf in setup ps for vif %pM link %u\n", - vif->addr, arvif->link_id); - return; - } - - /* firmware doesn't like 0 */ - timeout = ieee80211_tu_to_usec(info->beacon_int) / 1000; - } - - ret = ath12k_wmi_set_sta_ps_param(ar, arvif->vdev_id, param, - timeout); - if (ret) { - ath12k_warn(ar->ab, "failed to set inactivity time for vdev %d: %i\n", - arvif->vdev_id, ret); - return; - } - } else { - psmode = WMI_STA_PS_MODE_DISABLED; - } - - ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac vdev %d psmode %s\n", - arvif->vdev_id, psmode ? "enable" : "disable"); - - ret = ath12k_wmi_pdev_set_ps_mode(ar, arvif->vdev_id, psmode); - if (ret) - ath12k_warn(ar->ab, "failed to set sta power save mode %d for vdev %d: %d\n", - psmode, arvif->vdev_id, ret); -} - static void ath12k_mac_op_vif_cfg_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u64 changed) { struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif); unsigned long links = ahvif->links_map; - struct ieee80211_vif_cfg *vif_cfg; struct ieee80211_bss_conf *info; struct ath12k_link_vif *arvif; struct ieee80211_sta *sta; @@ -4189,24 +4133,61 @@ static void ath12k_mac_op_vif_cfg_changed(struct ieee80211_hw *hw, } } } +} - if (changed & BSS_CHANGED_PS) { - links = ahvif->links_map; - vif_cfg = &vif->cfg; +static void ath12k_mac_vif_setup_ps(struct ath12k_link_vif *arvif) +{ + struct ath12k *ar = arvif->ar; + struct ieee80211_vif *vif = arvif->ahvif->vif; + struct ieee80211_conf *conf = &ath12k_ar_to_hw(ar)->conf; + enum wmi_sta_powersave_param param; + struct ieee80211_bss_conf *info; + enum wmi_sta_ps_mode psmode; + int ret; + int timeout; + bool enable_ps; - for_each_set_bit(link_id, &links, IEEE80211_MLD_MAX_NUM_LINKS) { - arvif = wiphy_dereference(hw->wiphy, ahvif->link[link_id]); - if (!arvif || !arvif->ar) - continue; + lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); - ar = arvif->ar; + if (vif->type != NL80211_IFTYPE_STATION) + return; + + enable_ps = arvif->ahvif->ps; + if (enable_ps) { + psmode = WMI_STA_PS_MODE_ENABLED; + param = WMI_STA_PS_PARAM_INACTIVITY_TIME; - if (ar->ab->hw_params->supports_sta_ps) { - ahvif->ps = vif_cfg->ps; - ath12k_mac_vif_setup_ps(arvif); + timeout = conf->dynamic_ps_timeout; + if (timeout == 0) { + info = ath12k_mac_get_link_bss_conf(arvif); + if (!info) { + ath12k_warn(ar->ab, "unable to access bss link conf in setup ps for vif %pM link %u\n", + vif->addr, arvif->link_id); + return; } + + /* firmware doesn't like 0 */ + timeout = ieee80211_tu_to_usec(info->beacon_int) / 1000; } + + ret = ath12k_wmi_set_sta_ps_param(ar, arvif->vdev_id, param, + timeout); + if (ret) { + ath12k_warn(ar->ab, "failed to set inactivity time for vdev %d: %i\n", + arvif->vdev_id, ret); + return; + } + } else { + psmode = WMI_STA_PS_MODE_DISABLED; } + + ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac vdev %d psmode %s\n", + arvif->vdev_id, psmode ? "enable" : "disable"); + + ret = ath12k_wmi_pdev_set_ps_mode(ar, arvif->vdev_id, psmode); + if (ret) + ath12k_warn(ar->ab, "failed to set sta power save mode %d for vdev %d: %d\n", + psmode, arvif->vdev_id, ret); } static bool ath12k_mac_supports_tpc(struct ath12k *ar, struct ath12k_vif *ahvif, @@ -4228,6 +4209,7 @@ static void ath12k_mac_bss_info_changed(struct ath12k *ar, { struct ath12k_vif *ahvif = arvif->ahvif; struct ieee80211_vif *vif = ath12k_ahvif_to_vif(ahvif); + struct ieee80211_vif_cfg *vif_cfg = &vif->cfg; struct cfg80211_chan_def def; u32 param_id, param_value; enum nl80211_band band; @@ -4514,6 +4496,12 @@ static void ath12k_mac_bss_info_changed(struct ath12k *ar, } ath12k_mac_fils_discovery(arvif, info); + + if (changed & BSS_CHANGED_PS && + ar->ab->hw_params->supports_sta_ps) { + ahvif->ps = vif_cfg->ps; + ath12k_mac_vif_setup_ps(arvif); + } } static struct ath12k_vif_cache *ath12k_ahvif_get_link_cache(struct ath12k_vif *ahvif, diff --git a/drivers/net/wireless/intel/iwlwifi/mld/link.c b/drivers/net/wireless/intel/iwlwifi/mld/link.c index 60d814bf5779..f6f52d297a72 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/link.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/link.c @@ -708,18 +708,13 @@ static int iwl_mld_get_chan_load_from_element(struct iwl_mld *mld, struct ieee80211_bss_conf *link_conf) { - struct ieee80211_vif *vif = link_conf->vif; const struct cfg80211_bss_ies *ies; const struct element *bss_load_elem = NULL; const struct ieee80211_bss_load_elem *bss_load; guard(rcu)(); - if (ieee80211_vif_link_active(vif, link_conf->link_id)) - ies = rcu_dereference(link_conf->bss->beacon_ies); - else - ies = rcu_dereference(link_conf->bss->ies); - + ies = rcu_dereference(link_conf->bss->beacon_ies); if (ies) bss_load_elem = cfg80211_find_elem(WLAN_EID_QBSS_LOAD, ies->data, ies->len); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c index 9c9e0e1c6e1d..867807abde66 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c @@ -938,19 +938,12 @@ u8 iwl_mvm_mac_ctxt_get_lowest_rate(struct iwl_mvm *mvm, u16 iwl_mvm_mac_ctxt_get_beacon_flags(const struct iwl_fw *fw, u8 rate_idx) { + u16 flags = iwl_mvm_mac80211_idx_to_hwrate(fw, rate_idx); bool is_new_rate = iwl_fw_lookup_cmd_ver(fw, BEACON_TEMPLATE_CMD, 0) > 10; - u16 flags, cck_flag; - - if (is_new_rate) { - flags = iwl_mvm_mac80211_idx_to_hwrate(fw, rate_idx); - cck_flag = IWL_MAC_BEACON_CCK; - } else { - cck_flag = IWL_MAC_BEACON_CCK_V1; - flags = iwl_fw_rate_idx_to_plcp(rate_idx); - } if (rate_idx <= IWL_LAST_CCK_RATE) - flags |= cck_flag; + flags |= is_new_rate ? IWL_MAC_BEACON_CCK + : IWL_MAC_BEACON_CCK_V1; return flags; } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c index 0c9c2492d8a7..0b12ee8ad618 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c @@ -463,7 +463,7 @@ static int iwl_mvm_aux_roc_te_handle_notif(struct iwl_mvm *mvm, if (!aux_roc_te) /* Not a Aux ROC time event */ return -EINVAL; - iwl_mvm_te_check_trigger(mvm, notif, te_data); + iwl_mvm_te_check_trigger(mvm, notif, aux_roc_te); IWL_DEBUG_TE(mvm, "Aux ROC time event notification - UID = 0x%x action %d (error = %d)\n", @@ -475,14 +475,14 @@ static int iwl_mvm_aux_roc_te_handle_notif(struct iwl_mvm *mvm, /* End TE, notify mac80211 */ ieee80211_remain_on_channel_expired(mvm->hw); iwl_mvm_roc_finished(mvm); /* flush aux queue */ - list_del(&te_data->list); /* remove from list */ - te_data->running = false; - te_data->vif = NULL; - te_data->uid = 0; - te_data->id = TE_MAX; + list_del(&aux_roc_te->list); /* remove from list */ + aux_roc_te->running = false; + aux_roc_te->vif = NULL; + aux_roc_te->uid = 0; + aux_roc_te->id = TE_MAX; } else if (le32_to_cpu(notif->action) == TE_V2_NOTIF_HOST_EVENT_START) { set_bit(IWL_MVM_STATUS_ROC_AUX_RUNNING, &mvm->status); - te_data->running = true; + aux_roc_te->running = true; ieee80211_ready_on_channel(mvm->hw); /* Start TE */ } else { IWL_DEBUG_TE(mvm, diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c index 22602c32faa5..fa995e235d9b 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c @@ -159,9 +159,15 @@ int iwl_mvm_legacy_rate_to_mac80211_idx(u32 rate_n_flags, u8 iwl_mvm_mac80211_idx_to_hwrate(const struct iwl_fw *fw, int rate_idx) { - return (rate_idx >= IWL_FIRST_OFDM_RATE ? - rate_idx - IWL_FIRST_OFDM_RATE : - rate_idx); + if (iwl_fw_lookup_cmd_ver(fw, TX_CMD, 0) > 8) + /* In the new rate legacy rates are indexed: + * 0 - 3 for CCK and 0 - 7 for OFDM. + */ + return (rate_idx >= IWL_FIRST_OFDM_RATE ? + rate_idx - IWL_FIRST_OFDM_RATE : + rate_idx); + + return iwl_fw_rate_idx_to_plcp(rate_idx); } u8 iwl_mvm_mac80211_ac_to_ucode_ac(enum ieee80211_ac_numbers ac) diff --git a/drivers/net/wireless/marvell/mwl8k.c b/drivers/net/wireless/marvell/mwl8k.c index 891e125ad30b..54d6d00ecdf1 100644 --- a/drivers/net/wireless/marvell/mwl8k.c +++ b/drivers/net/wireless/marvell/mwl8k.c @@ -2966,6 +2966,51 @@ mwl8k_cmd_rf_antenna(struct ieee80211_hw *hw, int antenna, int mask) /* * CMD_SET_BEACON. */ + +static bool mwl8k_beacon_has_ds_params(const u8 *buf, int len) +{ + const struct ieee80211_mgmt *mgmt = (const void *)buf; + int ies_len; + + if (len <= offsetof(struct ieee80211_mgmt, u.beacon.variable)) + return false; + + ies_len = len - offsetof(struct ieee80211_mgmt, u.beacon.variable); + + return cfg80211_find_ie(WLAN_EID_DS_PARAMS, mgmt->u.beacon.variable, + ies_len) != NULL; +} + +static void mwl8k_beacon_copy_inject_ds_params(struct ieee80211_hw *hw, + u8 *buf_dst, const u8 *buf_src, + int src_len) +{ + const struct ieee80211_mgmt *mgmt = (const void *)buf_src; + static const u8 before_ds_params[] = { + WLAN_EID_SSID, + WLAN_EID_SUPP_RATES, + }; + const u8 *ies; + int hdr_len, left, offs, pos; + + ies = mgmt->u.beacon.variable; + hdr_len = offsetof(struct ieee80211_mgmt, u.beacon.variable); + + offs = ieee80211_ie_split(ies, src_len - hdr_len, before_ds_params, + ARRAY_SIZE(before_ds_params), 0); + + pos = hdr_len + offs; + left = src_len - pos; + + memcpy(buf_dst, buf_src, pos); + + /* Inject a DSSS Parameter Set after SSID + Supp Rates */ + buf_dst[pos + 0] = WLAN_EID_DS_PARAMS; + buf_dst[pos + 1] = 1; + buf_dst[pos + 2] = hw->conf.chandef.chan->hw_value; + + memcpy(buf_dst + pos + 3, buf_src + pos, left); +} struct mwl8k_cmd_set_beacon { struct mwl8k_cmd_pkt_hdr header; __le16 beacon_len; @@ -2975,17 +3020,33 @@ struct mwl8k_cmd_set_beacon { static int mwl8k_cmd_set_beacon(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u8 *beacon, int len) { + bool ds_params_present = mwl8k_beacon_has_ds_params(beacon, len); struct mwl8k_cmd_set_beacon *cmd; - int rc; + int rc, final_len = len; - cmd = kzalloc(sizeof(*cmd) + len, GFP_KERNEL); + if (!ds_params_present) { + /* + * mwl8k firmware requires a DS Params IE with the current + * channel in AP beacons. If mac80211/hostapd does not + * include it, inject one here. IE ID + length + channel + * number = 3 bytes. + */ + final_len += 3; + } + + cmd = kzalloc(sizeof(*cmd) + final_len, GFP_KERNEL); if (cmd == NULL) return -ENOMEM; cmd->header.code = cpu_to_le16(MWL8K_CMD_SET_BEACON); - cmd->header.length = cpu_to_le16(sizeof(*cmd) + len); - cmd->beacon_len = cpu_to_le16(len); - memcpy(cmd->beacon, beacon, len); + cmd->header.length = cpu_to_le16(sizeof(*cmd) + final_len); + cmd->beacon_len = cpu_to_le16(final_len); + + if (ds_params_present) + memcpy(cmd->beacon, beacon, len); + else + mwl8k_beacon_copy_inject_ds_params(hw, cmd->beacon, beacon, + len); rc = mwl8k_post_pervif_cmd(hw, vif, &cmd->header); kfree(cmd); diff --git a/drivers/net/wireless/virtual/mac80211_hwsim.c b/drivers/net/wireless/virtual/mac80211_hwsim.c index 9f856042a67a..5903d82e1ab1 100644 --- a/drivers/net/wireless/virtual/mac80211_hwsim.c +++ b/drivers/net/wireless/virtual/mac80211_hwsim.c @@ -2003,8 +2003,14 @@ static void mac80211_hwsim_tx(struct ieee80211_hw *hw, struct ieee80211_sta *sta = control->sta; struct ieee80211_bss_conf *bss_conf; + /* This can happen in case of monitor injection */ + if (!vif) { + ieee80211_free_txskb(hw, skb); + return; + } + if (link != IEEE80211_LINK_UNSPECIFIED) { - bss_conf = rcu_dereference(txi->control.vif->link_conf[link]); + bss_conf = rcu_dereference(vif->link_conf[link]); if (sta) link_sta = rcu_dereference(sta->link[link]); } else { @@ -2065,13 +2071,13 @@ static void mac80211_hwsim_tx(struct ieee80211_hw *hw, return; } - if (txi->control.vif) - hwsim_check_magic(txi->control.vif); + if (vif) + hwsim_check_magic(vif); if (control->sta) hwsim_check_sta_magic(control->sta); if (ieee80211_hw_check(hw, SUPPORTS_RC_TABLE)) - ieee80211_get_tx_rates(txi->control.vif, control->sta, skb, + ieee80211_get_tx_rates(vif, control->sta, skb, txi->control.rates, ARRAY_SIZE(txi->control.rates)); @@ -6698,14 +6704,15 @@ static struct genl_family hwsim_genl_family __ro_after_init = { .n_mcgrps = ARRAY_SIZE(hwsim_mcgrps), }; -static void remove_user_radios(u32 portid) +static void remove_user_radios(u32 portid, int netgroup) { struct mac80211_hwsim_data *entry, *tmp; LIST_HEAD(list); spin_lock_bh(&hwsim_radio_lock); list_for_each_entry_safe(entry, tmp, &hwsim_radios, list) { - if (entry->destroy_on_close && entry->portid == portid) { + if (entry->destroy_on_close && entry->portid == portid && + entry->netgroup == netgroup) { list_move(&entry->list, &list); rhashtable_remove_fast(&hwsim_radios_rht, &entry->rht, hwsim_rht_params); @@ -6730,7 +6737,7 @@ static int mac80211_hwsim_netlink_notify(struct notifier_block *nb, if (state != NETLINK_URELEASE) return NOTIFY_DONE; - remove_user_radios(notify->portid); + remove_user_radios(notify->portid, hwsim_net_get_netgroup(notify->net)); if (notify->portid == hwsim_net_get_wmediumd(notify->net)) { printk(KERN_INFO "mac80211_hwsim: wmediumd released netlink" diff --git a/drivers/net/wireless/zydas/zd1211rw/zd_usb.c b/drivers/net/wireless/zydas/zd1211rw/zd_usb.c index 2faa0de2a36e..8ee15a15f4ca 100644 --- a/drivers/net/wireless/zydas/zd1211rw/zd_usb.c +++ b/drivers/net/wireless/zydas/zd1211rw/zd_usb.c @@ -791,6 +791,7 @@ error: if (urbs) { for (i = 0; i < RX_URBS_COUNT; i++) free_rx_urb(urbs[i]); + kfree(urbs); } return r; } diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index 46e62feeda3c..c122016d82f1 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -432,7 +432,7 @@ config WIRELESS_HOTKEY depends on INPUT help This driver provides supports for the wireless buttons found on some AMD, - HP, & Xioami laptops. + HP, & Xiaomi laptops. On such systems the driver should load automatically (via ACPI alias). To compile this driver as a module, choose M here: the module will diff --git a/drivers/platform/x86/dell/dell-wmi-base.c b/drivers/platform/x86/dell/dell-wmi-base.c index 841a5414d28a..28076929d6af 100644 --- a/drivers/platform/x86/dell/dell-wmi-base.c +++ b/drivers/platform/x86/dell/dell-wmi-base.c @@ -365,6 +365,13 @@ static const struct key_entry dell_wmi_keymap_type_0012[] = { /* Backlight brightness change event */ { KE_IGNORE, 0x0003, { KEY_RESERVED } }, + /* + * Electronic privacy screen toggled, extended data gives state, + * separate entries for on/off see handling in dell_wmi_process_key(). + */ + { KE_KEY, 0x000c, { KEY_EPRIVACY_SCREEN_OFF } }, + { KE_KEY, 0x000c, { KEY_EPRIVACY_SCREEN_ON } }, + /* Ultra-performance mode switch request */ { KE_IGNORE, 0x000d, { KEY_RESERVED } }, @@ -435,6 +442,11 @@ static int dell_wmi_process_key(struct wmi_device *wdev, int type, int code, u16 "Dell tablet mode switch", SW_TABLET_MODE, !buffer[0]); return 1; + } else if (type == 0x0012 && code == 0x000c && remaining > 0) { + /* Eprivacy toggle, switch to "on" key entry for on events */ + if (buffer[0] == 2) + key++; + used = 1; } else if (type == 0x0012 && code == 0x000d && remaining > 0) { value = (buffer[2] == 2); used = 1; diff --git a/drivers/platform/x86/intel/int3472/clk_and_regulator.c b/drivers/platform/x86/intel/int3472/clk_and_regulator.c index 476ec24d3702..9e052b164a1a 100644 --- a/drivers/platform/x86/intel/int3472/clk_and_regulator.c +++ b/drivers/platform/x86/intel/int3472/clk_and_regulator.c @@ -245,15 +245,12 @@ int skl_int3472_register_regulator(struct int3472_discrete_device *int3472, if (IS_ERR(regulator->rdev)) return PTR_ERR(regulator->rdev); - int3472->regulators[int3472->n_regulator_gpios].ena_gpio = gpio; int3472->n_regulator_gpios++; return 0; } void skl_int3472_unregister_regulator(struct int3472_discrete_device *int3472) { - for (int i = 0; i < int3472->n_regulator_gpios; i++) { + for (int i = 0; i < int3472->n_regulator_gpios; i++) regulator_unregister(int3472->regulators[i].rdev); - gpiod_put(int3472->regulators[i].ena_gpio); - } } diff --git a/drivers/platform/x86/intel/int3472/led.c b/drivers/platform/x86/intel/int3472/led.c index f1d6d7b0cb75..b1d84b968112 100644 --- a/drivers/platform/x86/intel/int3472/led.c +++ b/drivers/platform/x86/intel/int3472/led.c @@ -43,7 +43,7 @@ int skl_int3472_register_pled(struct int3472_discrete_device *int3472, struct gp int3472->pled.lookup.provider = int3472->pled.name; int3472->pled.lookup.dev_id = int3472->sensor_name; - int3472->pled.lookup.con_id = "privacy-led"; + int3472->pled.lookup.con_id = "privacy"; led_add_lookup(&int3472->pled.lookup); return 0; diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c index 8106eb617c8c..c61cf9edac48 100644 --- a/drivers/ptp/ptp_chardev.c +++ b/drivers/ptp/ptp_chardev.c @@ -561,10 +561,14 @@ long ptp_ioctl(struct posix_clock_context *pccontext, unsigned int cmd, return ptp_mask_en_single(pccontext->private_clkdata, argptr); case PTP_SYS_OFFSET_PRECISE_CYCLES: + if (!ptp->has_cycles) + return -EOPNOTSUPP; return ptp_sys_offset_precise(ptp, argptr, ptp->info->getcrosscycles); case PTP_SYS_OFFSET_EXTENDED_CYCLES: + if (!ptp->has_cycles) + return -EOPNOTSUPP; return ptp_sys_offset_extended(ptp, argptr, ptp->info->getcyclesx64); default: diff --git a/drivers/rtc/rtc-cpcap.c b/drivers/rtc/rtc-cpcap.c index 8b6b35716f53..c170345ac076 100644 --- a/drivers/rtc/rtc-cpcap.c +++ b/drivers/rtc/rtc-cpcap.c @@ -268,7 +268,6 @@ static int cpcap_rtc_probe(struct platform_device *pdev) return err; rtc->alarm_irq = platform_get_irq(pdev, 0); - rtc->alarm_enabled = true; err = devm_request_threaded_irq(dev, rtc->alarm_irq, NULL, cpcap_rtc_alarm_irq, IRQF_TRIGGER_NONE | IRQF_ONESHOT, diff --git a/drivers/rtc/rtc-rx8025.c b/drivers/rtc/rtc-rx8025.c index aabe62c283a1..7e9f7cb90c28 100644 --- a/drivers/rtc/rtc-rx8025.c +++ b/drivers/rtc/rtc-rx8025.c @@ -316,7 +316,7 @@ static int rx8025_init_client(struct i2c_client *client) return hour_reg; rx8025->is_24 = (hour_reg & RX8035_BIT_HOUR_1224); } else { - rx8025->is_24 = (ctrl[1] & RX8025_BIT_CTRL1_1224); + rx8025->is_24 = (ctrl[0] & RX8025_BIT_CTRL1_1224); } out: return err; diff --git a/drivers/rtc/rtc-tps6586x.c b/drivers/rtc/rtc-tps6586x.c index 76ecf7b798f0..54c8429b16bf 100644 --- a/drivers/rtc/rtc-tps6586x.c +++ b/drivers/rtc/rtc-tps6586x.c @@ -258,7 +258,6 @@ static int tps6586x_rtc_probe(struct platform_device *pdev) irq_set_status_flags(rtc->irq, IRQ_NOAUTOEN); - rtc->irq_en = true; ret = devm_request_threaded_irq(&pdev->dev, rtc->irq, NULL, tps6586x_rtc_irq, IRQF_ONESHOT, diff --git a/drivers/soc/ti/knav_dma.c b/drivers/soc/ti/knav_dma.c index a25ebe6cd503..553ae7ee20f1 100644 --- a/drivers/soc/ti/knav_dma.c +++ b/drivers/soc/ti/knav_dma.c @@ -402,7 +402,7 @@ static int of_channel_match_helper(struct device_node *np, const char *name, * @name: slave channel name * @config: dma configuration parameters * - * Returns pointer to appropriate DMA channel on success or error. + * Return: Pointer to appropriate DMA channel on success or NULL on error. */ void *knav_dma_open_channel(struct device *dev, const char *name, struct knav_dma_cfg *config) @@ -414,13 +414,13 @@ void *knav_dma_open_channel(struct device *dev, const char *name, if (!kdev) { pr_err("keystone-navigator-dma driver not registered\n"); - return (void *)-EINVAL; + return NULL; } chan_num = of_channel_match_helper(dev->of_node, name, &instance); if (chan_num < 0) { dev_err(kdev->dev, "No DMA instance with name %s\n", name); - return (void *)-EINVAL; + return NULL; } dev_dbg(kdev->dev, "initializing %s channel %d from DMA %s\n", @@ -431,7 +431,7 @@ void *knav_dma_open_channel(struct device *dev, const char *name, if (config->direction != DMA_MEM_TO_DEV && config->direction != DMA_DEV_TO_MEM) { dev_err(kdev->dev, "bad direction\n"); - return (void *)-EINVAL; + return NULL; } /* Look for correct dma instance */ @@ -443,7 +443,7 @@ void *knav_dma_open_channel(struct device *dev, const char *name, } if (!dma) { dev_err(kdev->dev, "No DMA instance with name %s\n", instance); - return (void *)-EINVAL; + return NULL; } /* Look for correct dma channel from dma instance */ @@ -463,14 +463,14 @@ void *knav_dma_open_channel(struct device *dev, const char *name, if (!chan) { dev_err(kdev->dev, "channel %d is not in DMA %s\n", chan_num, instance); - return (void *)-EINVAL; + return NULL; } if (atomic_read(&chan->ref_count) >= 1) { if (!check_config(chan, config)) { dev_err(kdev->dev, "channel %d config miss-match\n", chan_num); - return (void *)-EINVAL; + return NULL; } } diff --git a/drivers/ufs/core/ufs-sysfs.c b/drivers/ufs/core/ufs-sysfs.c index c040afc6668e..0086816b27cd 100644 --- a/drivers/ufs/core/ufs-sysfs.c +++ b/drivers/ufs/core/ufs-sysfs.c @@ -1949,7 +1949,7 @@ static umode_t ufs_sysfs_hid_is_visible(struct kobject *kobj, return hba->dev_info.hid_sup ? attr->mode : 0; } -const struct attribute_group ufs_sysfs_hid_group = { +static const struct attribute_group ufs_sysfs_hid_group = { .name = "hid", .attrs = ufs_sysfs_hid, .is_visible = ufs_sysfs_hid_is_visible, diff --git a/drivers/ufs/core/ufs-sysfs.h b/drivers/ufs/core/ufs-sysfs.h index 6efb82a082fd..8d94af3b8077 100644 --- a/drivers/ufs/core/ufs-sysfs.h +++ b/drivers/ufs/core/ufs-sysfs.h @@ -14,6 +14,5 @@ void ufs_sysfs_remove_nodes(struct device *dev); extern const struct attribute_group ufs_sysfs_unit_descriptor_group; extern const struct attribute_group ufs_sysfs_lun_attributes_group; -extern const struct attribute_group ufs_sysfs_hid_group; #endif diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 9ca27de4767a..d6a060a72461 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -5066,7 +5066,8 @@ static int ufshcd_link_startup(struct ufs_hba *hba) * If UFS device isn't active then we will have to issue link startup * 2 times to make sure the device state move to active. */ - if (!ufshcd_is_ufs_dev_active(hba)) + if (!(hba->quirks & UFSHCD_QUIRK_PERFORM_LINK_STARTUP_ONCE) && + !ufshcd_is_ufs_dev_active(hba)) link_startup_again = true; link_startup: @@ -5131,12 +5132,8 @@ link_startup: ufshcd_readl(hba, REG_UIC_ERROR_CODE_PHY_ADAPTER_LAYER); ret = ufshcd_make_hba_operational(hba); out: - if (ret) { + if (ret) dev_err(hba->dev, "link startup failed %d\n", ret); - ufshcd_print_host_state(hba); - ufshcd_print_pwr_info(hba); - ufshcd_print_evt_hist(hba); - } return ret; } @@ -8503,8 +8500,6 @@ static int ufs_get_device_desc(struct ufs_hba *hba) DEVICE_DESC_PARAM_EXT_UFS_FEATURE_SUP) & UFS_DEV_HID_SUPPORT; - sysfs_update_group(&hba->dev->kobj, &ufs_sysfs_hid_group); - model_index = desc_buf[DEVICE_DESC_PARAM_PRDCT_NAME]; err = ufshcd_read_string_desc(hba, model_index, @@ -10661,7 +10656,7 @@ remove_scsi_host: * @mmio_base: base register address * @irq: Interrupt line of device * - * Return: 0 on success, non-zero value on failure. + * Return: 0 on success; < 0 on failure. */ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq) { @@ -10891,8 +10886,8 @@ initialized: if (err) goto out_disable; - async_schedule(ufshcd_async_scan, hba); ufs_sysfs_add_nodes(hba->dev); + async_schedule(ufshcd_async_scan, hba); device_enable_async_suspend(dev); ufshcd_pm_qos_init(hba); @@ -10902,7 +10897,7 @@ out_disable: hba->is_irq_enabled = false; ufshcd_hba_exit(hba); out_error: - return err; + return err > 0 ? -EIO : err; } EXPORT_SYMBOL_GPL(ufshcd_init); diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c index 3e83dc51d538..eba0e6617483 100644 --- a/drivers/ufs/host/ufs-qcom.c +++ b/drivers/ufs/host/ufs-qcom.c @@ -740,8 +740,21 @@ static int ufs_qcom_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op, /* reset the connected UFS device during power down */ - if (ufs_qcom_is_link_off(hba) && host->device_reset) + if (ufs_qcom_is_link_off(hba) && host->device_reset) { ufs_qcom_device_reset_ctrl(hba, true); + /* + * After sending the SSU command, asserting the rst_n + * line causes the device firmware to wake up and + * execute its reset routine. + * + * During this process, the device may draw current + * beyond the permissible limit for low-power mode (LPM). + * A 10ms delay, based on experimental observations, + * allows the UFS device to complete its hardware reset + * before transitioning the power rail to LPM. + */ + usleep_range(10000, 11000); + } return ufs_qcom_ice_suspend(host); } diff --git a/drivers/ufs/host/ufshcd-pci.c b/drivers/ufs/host/ufshcd-pci.c index b87e03777395..5f65dfad1a71 100644 --- a/drivers/ufs/host/ufshcd-pci.c +++ b/drivers/ufs/host/ufshcd-pci.c @@ -15,6 +15,7 @@ #include <linux/pci.h> #include <linux/pm_runtime.h> #include <linux/pm_qos.h> +#include <linux/suspend.h> #include <linux/debugfs.h> #include <linux/uuid.h> #include <linux/acpi.h> @@ -31,6 +32,7 @@ struct intel_host { u32 dsm_fns; u32 active_ltr; u32 idle_ltr; + int saved_spm_lvl; struct dentry *debugfs_root; struct gpio_desc *reset_gpio; }; @@ -347,6 +349,7 @@ static int ufs_intel_common_init(struct ufs_hba *hba) host = devm_kzalloc(hba->dev, sizeof(*host), GFP_KERNEL); if (!host) return -ENOMEM; + host->saved_spm_lvl = -1; ufshcd_set_variant(hba, host); intel_dsm_init(host, hba->dev); if (INTEL_DSM_SUPPORTED(host, RESET)) { @@ -425,7 +428,8 @@ static int ufs_intel_lkf_init(struct ufs_hba *hba) static int ufs_intel_adl_init(struct ufs_hba *hba) { hba->nop_out_timeout = 200; - hba->quirks |= UFSHCD_QUIRK_BROKEN_AUTO_HIBERN8; + hba->quirks |= UFSHCD_QUIRK_BROKEN_AUTO_HIBERN8 | + UFSHCD_QUIRK_PERFORM_LINK_STARTUP_ONCE; hba->caps |= UFSHCD_CAP_WB_EN; return ufs_intel_common_init(hba); } @@ -538,6 +542,66 @@ static int ufshcd_pci_restore(struct device *dev) return ufshcd_system_resume(dev); } + +static int ufs_intel_suspend_prepare(struct device *dev) +{ + struct ufs_hba *hba = dev_get_drvdata(dev); + struct intel_host *host = ufshcd_get_variant(hba); + int err; + + /* + * Only s2idle (S0ix) retains link state. Force power-off + * (UFS_PM_LVL_5) for any other case. + */ + if (pm_suspend_target_state != PM_SUSPEND_TO_IDLE && hba->spm_lvl < UFS_PM_LVL_5) { + host->saved_spm_lvl = hba->spm_lvl; + hba->spm_lvl = UFS_PM_LVL_5; + } + + err = ufshcd_suspend_prepare(dev); + + if (err < 0 && host->saved_spm_lvl != -1) { + hba->spm_lvl = host->saved_spm_lvl; + host->saved_spm_lvl = -1; + } + + return err; +} + +static void ufs_intel_resume_complete(struct device *dev) +{ + struct ufs_hba *hba = dev_get_drvdata(dev); + struct intel_host *host = ufshcd_get_variant(hba); + + ufshcd_resume_complete(dev); + + if (host->saved_spm_lvl != -1) { + hba->spm_lvl = host->saved_spm_lvl; + host->saved_spm_lvl = -1; + } +} + +static int ufshcd_pci_suspend_prepare(struct device *dev) +{ + struct ufs_hba *hba = dev_get_drvdata(dev); + + if (!strcmp(hba->vops->name, "intel-pci")) + return ufs_intel_suspend_prepare(dev); + + return ufshcd_suspend_prepare(dev); +} + +static void ufshcd_pci_resume_complete(struct device *dev) +{ + struct ufs_hba *hba = dev_get_drvdata(dev); + + if (!strcmp(hba->vops->name, "intel-pci")) { + ufs_intel_resume_complete(dev); + return; + } + + ufshcd_resume_complete(dev); +} #endif /** @@ -611,8 +675,8 @@ static const struct dev_pm_ops ufshcd_pci_pm_ops = { .thaw = ufshcd_system_resume, .poweroff = ufshcd_system_suspend, .restore = ufshcd_pci_restore, - .prepare = ufshcd_suspend_prepare, - .complete = ufshcd_resume_complete, + .prepare = ufshcd_pci_suspend_prepare, + .complete = ufshcd_pci_resume_complete, #endif }; diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 82034efb74fc..a7936bd1aabe 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -573,6 +573,8 @@ static int cq_create(struct mlx5_vdpa_net *ndev, u16 idx, u32 num_ent) vcq->mcq.set_ci_db = vcq->db.db; vcq->mcq.arm_db = vcq->db.db + 1; vcq->mcq.cqe_sz = 64; + vcq->mcq.comp = mlx5_vdpa_cq_comp; + vcq->cqe = num_ent; err = cq_frag_buf_alloc(ndev, &vcq->buf, num_ent); if (err) @@ -612,10 +614,6 @@ static int cq_create(struct mlx5_vdpa_net *ndev, u16 idx, u32 num_ent) if (err) goto err_vec; - vcq->mcq.comp = mlx5_vdpa_cq_comp; - vcq->cqe = num_ent; - vcq->mcq.set_ci_db = vcq->db.db; - vcq->mcq.arm_db = vcq->db.db + 1; mlx5_cq_arm(&mvq->cq.mcq, MLX5_CQ_DB_REQ_NOT, uar_page, mvq->cq.mcq.cons_index); kfree(in); return 0; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 755ec6dfd51c..23273d0e6f22 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2228,6 +2228,14 @@ static noinline_for_stack void write_one_eb(struct extent_buffer *eb, wbc_account_cgroup_owner(wbc, folio, range_len); folio_unlock(folio); } + /* + * If the fs is already in error status, do not submit any writeback + * but immediately finish it. + */ + if (unlikely(BTRFS_FS_ERROR(fs_info))) { + btrfs_bio_end_io(bbio, errno_to_blk_status(BTRFS_FS_ERROR(fs_info))); + return; + } btrfs_submit_bbio(bbio, 0); } diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 7efd1f8a1912..fa82def46e39 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2854,12 +2854,22 @@ static int btrfs_fallocate_update_isize(struct inode *inode, { struct btrfs_trans_handle *trans; struct btrfs_root *root = BTRFS_I(inode)->root; + u64 range_start; + u64 range_end; int ret; int ret2; if (mode & FALLOC_FL_KEEP_SIZE || end <= i_size_read(inode)) return 0; + range_start = round_down(i_size_read(inode), root->fs_info->sectorsize); + range_end = round_up(end, root->fs_info->sectorsize); + + ret = btrfs_inode_set_file_extent_range(BTRFS_I(inode), range_start, + range_end - range_start); + if (ret) + return ret; + trans = btrfs_start_transaction(root, 1); if (IS_ERR(trans)) return PTR_ERR(trans); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 3b1b3a0553ee..6282911e536f 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -177,8 +177,10 @@ static int data_reloc_print_warning_inode(u64 inum, u64 offset, u64 num_bytes, return ret; } ret = paths_from_inode(inum, ipath); - if (ret < 0) + if (ret < 0) { + btrfs_put_root(local_root); goto err; + } /* * We deliberately ignore the bit ipath might have been too small to @@ -6873,7 +6875,6 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, BTRFS_I(inode)->dir_index = 0ULL; inode_inc_iversion(inode); inode_set_ctime_current(inode); - set_bit(BTRFS_INODE_COPY_EVERYTHING, &BTRFS_I(inode)->runtime_flags); ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode), &fname.disk_name, 1, index); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 1175b8192cd7..31ad8580322a 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1539,8 +1539,10 @@ int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src, u64 dst ASSERT(prealloc); /* Check the level of src and dst first */ - if (btrfs_qgroup_level(src) >= btrfs_qgroup_level(dst)) + if (btrfs_qgroup_level(src) >= btrfs_qgroup_level(dst)) { + kfree(prealloc); return -EINVAL; + } mutex_lock(&fs_info->qgroup_ioctl_lock); if (!fs_info->quota_root) { diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 651b11884f82..ba20d9286a34 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -2203,6 +2203,7 @@ static int scrub_raid56_parity_stripe(struct scrub_ctx *sctx, ret = btrfs_map_block(fs_info, BTRFS_MAP_WRITE, full_stripe_start, &length, &bioc, NULL, NULL); if (ret < 0) { + bio_put(bio); btrfs_put_bioc(bioc); btrfs_bio_counter_dec(fs_info); goto out; @@ -2212,6 +2213,7 @@ static int scrub_raid56_parity_stripe(struct scrub_ctx *sctx, btrfs_put_bioc(bioc); if (!rbio) { ret = -ENOMEM; + bio_put(bio); btrfs_bio_counter_dec(fs_info); goto out; } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 621e0df097e3..30f3c3b849c1 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -7122,7 +7122,7 @@ log_extents: * a power failure unless the log was synced as part of an fsync * against any other unrelated inode. */ - if (inode_only != LOG_INODE_EXISTS) + if (!ctx->logging_new_name && inode_only != LOG_INODE_EXISTS) inode->last_log_commit = inode->last_sub_trans; spin_unlock(&inode->lock); @@ -7910,6 +7910,9 @@ void btrfs_log_new_name(struct btrfs_trans_handle *trans, bool log_pinned = false; int ret; + /* The inode has a new name (ref/extref), so make sure we log it. */ + set_bit(BTRFS_INODE_COPY_EVERYTHING, &inode->runtime_flags); + btrfs_init_log_ctx(&ctx, inode); ctx.logging_new_name = true; diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 0ea0df18a8e4..d1db7fa1fe58 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1317,6 +1317,7 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx, if (!btrfs_dev_is_sequential(device, info->physical)) { up_read(&dev_replace->rwsem); info->alloc_offset = WP_CONVENTIONAL; + info->capacity = device->zone_info->zone_size; return 0; } @@ -1522,6 +1523,8 @@ static int btrfs_load_block_group_raid0(struct btrfs_block_group *bg, u64 last_alloc) { struct btrfs_fs_info *fs_info = bg->fs_info; + u64 stripe_nr = 0, stripe_offset = 0; + u32 stripe_index = 0; if ((map->type & BTRFS_BLOCK_GROUP_DATA) && !fs_info->stripe_root) { btrfs_err(fs_info, "zoned: data %s needs raid-stripe-tree", @@ -1529,28 +1532,26 @@ static int btrfs_load_block_group_raid0(struct btrfs_block_group *bg, return -EINVAL; } + if (last_alloc) { + u32 factor = map->num_stripes; + + stripe_nr = last_alloc >> BTRFS_STRIPE_LEN_SHIFT; + stripe_offset = last_alloc & BTRFS_STRIPE_LEN_MASK; + stripe_nr = div_u64_rem(stripe_nr, factor, &stripe_index); + } + for (int i = 0; i < map->num_stripes; i++) { if (zone_info[i].alloc_offset == WP_MISSING_DEV) continue; if (zone_info[i].alloc_offset == WP_CONVENTIONAL) { - u64 stripe_nr, full_stripe_nr; - u64 stripe_offset; - int stripe_index; - stripe_nr = div64_u64(last_alloc, map->stripe_size); - stripe_offset = stripe_nr * map->stripe_size; - full_stripe_nr = div_u64(stripe_nr, map->num_stripes); - div_u64_rem(stripe_nr, map->num_stripes, &stripe_index); - - zone_info[i].alloc_offset = - full_stripe_nr * map->stripe_size; + zone_info[i].alloc_offset = btrfs_stripe_nr_to_offset(stripe_nr); if (stripe_index > i) - zone_info[i].alloc_offset += map->stripe_size; + zone_info[i].alloc_offset += BTRFS_STRIPE_LEN; else if (stripe_index == i) - zone_info[i].alloc_offset += - (last_alloc - stripe_offset); + zone_info[i].alloc_offset += stripe_offset; } if (test_bit(0, active) != test_bit(i, active)) { @@ -1574,6 +1575,8 @@ static int btrfs_load_block_group_raid10(struct btrfs_block_group *bg, u64 last_alloc) { struct btrfs_fs_info *fs_info = bg->fs_info; + u64 stripe_nr = 0, stripe_offset = 0; + u32 stripe_index = 0; if ((map->type & BTRFS_BLOCK_GROUP_DATA) && !fs_info->stripe_root) { btrfs_err(fs_info, "zoned: data %s needs raid-stripe-tree", @@ -1581,6 +1584,14 @@ static int btrfs_load_block_group_raid10(struct btrfs_block_group *bg, return -EINVAL; } + if (last_alloc) { + u32 factor = map->num_stripes / map->sub_stripes; + + stripe_nr = last_alloc >> BTRFS_STRIPE_LEN_SHIFT; + stripe_offset = last_alloc & BTRFS_STRIPE_LEN_MASK; + stripe_nr = div_u64_rem(stripe_nr, factor, &stripe_index); + } + for (int i = 0; i < map->num_stripes; i++) { if (zone_info[i].alloc_offset == WP_MISSING_DEV) continue; @@ -1594,26 +1605,12 @@ static int btrfs_load_block_group_raid10(struct btrfs_block_group *bg, } if (zone_info[i].alloc_offset == WP_CONVENTIONAL) { - u64 stripe_nr, full_stripe_nr; - u64 stripe_offset; - int stripe_index; - - stripe_nr = div64_u64(last_alloc, map->stripe_size); - stripe_offset = stripe_nr * map->stripe_size; - full_stripe_nr = div_u64(stripe_nr, - map->num_stripes / map->sub_stripes); - div_u64_rem(stripe_nr, - (map->num_stripes / map->sub_stripes), - &stripe_index); - - zone_info[i].alloc_offset = - full_stripe_nr * map->stripe_size; + zone_info[i].alloc_offset = btrfs_stripe_nr_to_offset(stripe_nr); if (stripe_index > (i / map->sub_stripes)) - zone_info[i].alloc_offset += map->stripe_size; + zone_info[i].alloc_offset += BTRFS_STRIPE_LEN; else if (stripe_index == (i / map->sub_stripes)) - zone_info[i].alloc_offset += - (last_alloc - stripe_offset); + zone_info[i].alloc_offset += stripe_offset; } if ((i % map->sub_stripes) == 0) { @@ -1683,8 +1680,6 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) set_bit(BLOCK_GROUP_FLAG_SEQUENTIAL_ZONE, &cache->runtime_flags); if (num_conventional > 0) { - /* Zone capacity is always zone size in emulation */ - cache->zone_capacity = cache->length; ret = calculate_alloc_pointer(cache, &last_alloc, new); if (ret) { btrfs_err(fs_info, @@ -1693,6 +1688,7 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) goto out; } else if (map->num_stripes == num_conventional) { cache->alloc_offset = last_alloc; + cache->zone_capacity = cache->length; set_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &cache->runtime_flags); goto out; } diff --git a/fs/crypto/inline_crypt.c b/fs/crypto/inline_crypt.c index 5dee7c498bc8..ed6e926226b5 100644 --- a/fs/crypto/inline_crypt.c +++ b/fs/crypto/inline_crypt.c @@ -333,8 +333,7 @@ static bool bh_get_inode_and_lblk_num(const struct buffer_head *bh, inode = mapping->host; *inode_ret = inode; - *lblk_num_ret = ((u64)folio->index << (PAGE_SHIFT - inode->i_blkbits)) + - (bh_offset(bh) >> inode->i_blkbits); + *lblk_num_ret = (folio_pos(folio) + bh_offset(bh)) >> inode->i_blkbits; return true; } diff --git a/fs/erofs/decompressor_zstd.c b/fs/erofs/decompressor_zstd.c index b4bfe14229f9..e38d93bb2104 100644 --- a/fs/erofs/decompressor_zstd.c +++ b/fs/erofs/decompressor_zstd.c @@ -172,7 +172,6 @@ static int z_erofs_zstd_decompress(struct z_erofs_decompress_req *rq, dctx.bounce = strm->bounce; do { - dctx.avail_out = out_buf.size - out_buf.pos; dctx.inbuf_sz = in_buf.size; dctx.inbuf_pos = in_buf.pos; err = z_erofs_stream_switch_bufs(&dctx, &out_buf.dst, @@ -188,14 +187,18 @@ static int z_erofs_zstd_decompress(struct z_erofs_decompress_req *rq, in_buf.pos = dctx.inbuf_pos; zerr = zstd_decompress_stream(stream, &out_buf, &in_buf); - if (zstd_is_error(zerr) || (!zerr && rq->outputsize)) { + dctx.avail_out = out_buf.size - out_buf.pos; + if (zstd_is_error(zerr) || + ((rq->outputsize + dctx.avail_out) && (!zerr || (zerr > 0 && + !(rq->inputsize + in_buf.size - in_buf.pos))))) { erofs_err(sb, "failed to decompress in[%u] out[%u]: %s", rq->inputsize, rq->outputsize, - zerr ? zstd_get_error_name(zerr) : "unexpected end of stream"); + zstd_is_error(zerr) ? zstd_get_error_name(zerr) : + "unexpected end of stream"); err = -EFSCORRUPTED; break; } - } while (rq->outputsize || out_buf.pos < out_buf.size); + } while (rq->outputsize + dctx.avail_out); if (dctx.kout) kunmap_local(dctx.kout); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index c1b54322c412..8a6960500217 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1542,7 +1542,8 @@ static void nfs4_free_ol_stateid(struct nfs4_stid *stid) release_all_access(stp); if (stp->st_stateowner) nfs4_put_stateowner(stp->st_stateowner); - WARN_ON(!list_empty(&stid->sc_cp_list)); + if (!list_empty(&stid->sc_cp_list)) + nfs4_free_cpntf_statelist(stid->sc_client->net, stid); kmem_cache_free(stateid_slab, stid); } @@ -3486,7 +3487,20 @@ nfsd4_store_cache_entry(struct nfsd4_compoundres *resp) struct nfsd4_slot *slot = resp->cstate.slot; unsigned int base; - dprintk("--> %s slot %p\n", __func__, slot); + /* + * RFC 5661 Section 2.10.6.1.2: + * + * Any time SEQUENCE ... returns an error ... [t]he replier MUST NOT + * modify the reply cache entry for the slot whenever an error is + * returned from SEQUENCE ... + * + * Because nfsd4_store_cache_entry is called only by + * nfsd4_sequence_done(), nfsd4_store_cache_entry() is called only + * when a SEQUENCE operation was part of the COMPOUND. + * nfs41_check_op_ordering() ensures SEQUENCE is the first op. + */ + if (resp->opcnt == 1 && resp->cstate.status != nfs_ok) + return; slot->sl_flags |= NFSD4_SLOT_INITIALIZED; slot->sl_opcnt = resp->opcnt; @@ -4349,6 +4363,36 @@ static bool replay_matches_cache(struct svc_rqst *rqstp, return true; } +/* + * Note that the response is constructed here both for the case + * of a new SEQUENCE request and for a replayed SEQUENCE request. + * We do not cache SEQUENCE responses as SEQUENCE is idempotent. + */ +static void nfsd4_construct_sequence_response(struct nfsd4_session *session, + struct nfsd4_sequence *seq) +{ + struct nfs4_client *clp = session->se_client; + + seq->maxslots_response = max(session->se_target_maxslots, + seq->maxslots); + seq->target_maxslots = session->se_target_maxslots; + + switch (clp->cl_cb_state) { + case NFSD4_CB_DOWN: + seq->status_flags = SEQ4_STATUS_CB_PATH_DOWN; + break; + case NFSD4_CB_FAULT: + seq->status_flags = SEQ4_STATUS_BACKCHANNEL_FAULT; + break; + default: + seq->status_flags = 0; + } + if (!list_empty(&clp->cl_revoked)) + seq->status_flags |= SEQ4_STATUS_RECALLABLE_STATE_REVOKED; + if (atomic_read(&clp->cl_admin_revoked)) + seq->status_flags |= SEQ4_STATUS_ADMIN_STATE_REVOKED; +} + __be32 nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) @@ -4398,6 +4442,9 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, dprintk("%s: slotid %d\n", __func__, seq->slotid); trace_nfsd_slot_seqid_sequence(clp, seq, slot); + + nfsd4_construct_sequence_response(session, seq); + status = check_slot_seqid(seq->seqid, slot->sl_seqid, slot->sl_flags); if (status == nfserr_replay_cache) { status = nfserr_seq_misordered; @@ -4495,23 +4542,6 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, } out: - seq->maxslots = max(session->se_target_maxslots, seq->maxslots); - seq->target_maxslots = session->se_target_maxslots; - - switch (clp->cl_cb_state) { - case NFSD4_CB_DOWN: - seq->status_flags = SEQ4_STATUS_CB_PATH_DOWN; - break; - case NFSD4_CB_FAULT: - seq->status_flags = SEQ4_STATUS_BACKCHANNEL_FAULT; - break; - default: - seq->status_flags = 0; - } - if (!list_empty(&clp->cl_revoked)) - seq->status_flags |= SEQ4_STATUS_RECALLABLE_STATE_REVOKED; - if (atomic_read(&clp->cl_admin_revoked)) - seq->status_flags |= SEQ4_STATUS_ADMIN_STATE_REVOKED; trace_nfsd_seq4_status(rqstp, seq); out_no_session: if (conn) diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 6040a6145dad..67bb9c0b9fcb 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -5073,7 +5073,7 @@ nfsd4_encode_sequence(struct nfsd4_compoundres *resp, __be32 nfserr, return nfserr; /* Note slotid's are numbered from zero: */ /* sr_highest_slotid */ - nfserr = nfsd4_encode_slotid4(xdr, seq->maxslots - 1); + nfserr = nfsd4_encode_slotid4(xdr, seq->maxslots_response - 1); if (nfserr != nfs_ok) return nfserr; /* sr_target_highest_slotid */ @@ -5925,8 +5925,7 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) */ warn_on_nonidempotent_op(op); xdr_truncate_encode(xdr, op_status_offset + XDR_UNIT); - } - if (so) { + } else if (so) { int len = xdr->buf->len - (op_status_offset + XDR_UNIT); so->so_replay.rp_status = op->status; diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index f19320018639..b752433c3c2c 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -458,6 +458,7 @@ enum { #define NFSD4_2_SUPPORTED_ATTRS_WORD2 \ (NFSD4_1_SUPPORTED_ATTRS_WORD2 | \ FATTR4_WORD2_MODE_UMASK | \ + FATTR4_WORD2_CLONE_BLKSIZE | \ NFSD4_2_SECURITY_ATTRS | \ FATTR4_WORD2_XATTR_SUPPORT | \ FATTR4_WORD2_TIME_DELEG_ACCESS | \ diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 3eb724ec9566..ed85dd43da18 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -269,9 +269,6 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct net *net, dentry); } - fhp->fh_dentry = dentry; - fhp->fh_export = exp; - switch (fhp->fh_maxsize) { case NFS4_FHSIZE: if (dentry->d_sb->s_export_op->flags & EXPORT_OP_NOATOMIC_ATTR) @@ -293,6 +290,9 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct net *net, goto out; } + fhp->fh_dentry = dentry; + fhp->fh_export = exp; + return 0; out: exp_put(exp); diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index ee0570cbdd9e..1ce8e12ae335 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -574,8 +574,9 @@ struct nfsd4_sequence { struct nfs4_sessionid sessionid; /* request/response */ u32 seqid; /* request/response */ u32 slotid; /* request/response */ - u32 maxslots; /* request/response */ + u32 maxslots; /* request */ u32 cachethis; /* request */ + u32 maxslots_response; /* response */ u32 target_maxslots; /* response */ u32 status_flags; /* response */ }; diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index f15ca6fc400d..deee16bc9d4e 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -2768,7 +2768,12 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci) if (sci->sc_task) { wake_up(&sci->sc_wait_daemon); - kthread_stop(sci->sc_task); + if (kthread_stop(sci->sc_task)) { + spin_lock(&sci->sc_state_lock); + sci->sc_task = NULL; + timer_shutdown_sync(&sci->sc_timer); + spin_unlock(&sci->sc_state_lock); + } } spin_lock(&sci->sc_state_lock); diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 176281112273..501889856461 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -698,6 +698,12 @@ void pde_put(struct proc_dir_entry *pde) } } +static void pde_erase(struct proc_dir_entry *pde, struct proc_dir_entry *parent) +{ + rb_erase(&pde->subdir_node, &parent->subdir); + RB_CLEAR_NODE(&pde->subdir_node); +} + /* * Remove a /proc entry and free it if it's not currently in use. */ @@ -720,7 +726,7 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent) WARN(1, "removing permanent /proc entry '%s'", de->name); de = NULL; } else { - rb_erase(&de->subdir_node, &parent->subdir); + pde_erase(de, parent); if (S_ISDIR(de->mode)) parent->nlink--; } @@ -764,7 +770,7 @@ int remove_proc_subtree(const char *name, struct proc_dir_entry *parent) root->parent->name, root->name); return -EINVAL; } - rb_erase(&root->subdir_node, &parent->subdir); + pde_erase(root, parent); de = root; while (1) { @@ -776,7 +782,7 @@ int remove_proc_subtree(const char *name, struct proc_dir_entry *parent) next->parent->name, next->name); return -EINVAL; } - rb_erase(&next->subdir_node, &de->subdir); + pde_erase(next, de); de = next; continue; } diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c index b8ac7b7faf61..018055fd2cdb 100644 --- a/fs/smb/client/cached_dir.c +++ b/fs/smb/client/cached_dir.c @@ -388,11 +388,11 @@ out: * lease. Release one here, and the second below. */ cfid->has_lease = false; - kref_put(&cfid->refcount, smb2_close_cached_fid); + close_cached_dir(cfid); } spin_unlock(&cfids->cfid_list_lock); - kref_put(&cfid->refcount, smb2_close_cached_fid); + close_cached_dir(cfid); } else { *ret_cfid = cfid; atomic_inc(&tcon->num_remote_opens); @@ -438,12 +438,14 @@ int open_cached_dir_by_dentry(struct cifs_tcon *tcon, static void smb2_close_cached_fid(struct kref *ref) +__releases(&cfid->cfids->cfid_list_lock) { struct cached_fid *cfid = container_of(ref, struct cached_fid, refcount); int rc; - spin_lock(&cfid->cfids->cfid_list_lock); + lockdep_assert_held(&cfid->cfids->cfid_list_lock); + if (cfid->on_list) { list_del(&cfid->entry); cfid->on_list = false; @@ -478,7 +480,7 @@ void drop_cached_dir_by_name(const unsigned int xid, struct cifs_tcon *tcon, spin_lock(&cfid->cfids->cfid_list_lock); if (cfid->has_lease) { cfid->has_lease = false; - kref_put(&cfid->refcount, smb2_close_cached_fid); + close_cached_dir(cfid); } spin_unlock(&cfid->cfids->cfid_list_lock); close_cached_dir(cfid); @@ -487,7 +489,7 @@ void drop_cached_dir_by_name(const unsigned int xid, struct cifs_tcon *tcon, void close_cached_dir(struct cached_fid *cfid) { - kref_put(&cfid->refcount, smb2_close_cached_fid); + kref_put_lock(&cfid->refcount, smb2_close_cached_fid, &cfid->cfids->cfid_list_lock); } /* @@ -596,7 +598,7 @@ cached_dir_offload_close(struct work_struct *work) WARN_ON(cfid->on_list); - kref_put(&cfid->refcount, smb2_close_cached_fid); + close_cached_dir(cfid); cifs_put_tcon(tcon, netfs_trace_tcon_ref_put_cached_close); } @@ -762,7 +764,7 @@ static void cfids_laundromat_worker(struct work_struct *work) * Drop the ref-count from above, either the lease-ref (if there * was one) or the extra one acquired. */ - kref_put(&cfid->refcount, smb2_close_cached_fid); + close_cached_dir(cfid); } queue_delayed_work(cfid_put_wq, &cfids->laundromat_work, dir_cache_timeout * HZ); diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c index 09e3fc81d7cb..69cb81fa0d3a 100644 --- a/fs/smb/client/smb2inode.c +++ b/fs/smb/client/smb2inode.c @@ -1294,6 +1294,8 @@ static int smb2_set_path_attr(const unsigned int xid, struct cifs_tcon *tcon, smb2_to_name = cifs_convert_path_to_utf16(to_name, cifs_sb); if (smb2_to_name == NULL) { rc = -ENOMEM; + if (cfile) + cifsFileInfo_put(cfile); goto smb2_rename_path; } in_iov.iov_base = smb2_to_name; diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index b0739a2661bf..8b4a4573e9c3 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -4054,9 +4054,12 @@ replay_again: smb_rsp = (struct smb2_change_notify_rsp *)rsp_iov.iov_base; - smb2_validate_iov(le16_to_cpu(smb_rsp->OutputBufferOffset), - le32_to_cpu(smb_rsp->OutputBufferLength), &rsp_iov, + rc = smb2_validate_iov(le16_to_cpu(smb_rsp->OutputBufferOffset), + le32_to_cpu(smb_rsp->OutputBufferLength), + &rsp_iov, sizeof(struct file_notify_information)); + if (rc) + goto cnotify_exit; *out_data = kmemdup((char *)smb_rsp + le16_to_cpu(smb_rsp->OutputBufferOffset), le32_to_cpu(smb_rsp->OutputBufferLength), GFP_KERNEL); diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c index 7d86553fcc7c..e2be9a496154 100644 --- a/fs/smb/server/transport_rdma.c +++ b/fs/smb/server/transport_rdma.c @@ -334,6 +334,9 @@ smb_direct_disconnect_rdma_connection(struct smbdirect_socket *sc) break; case SMBDIRECT_SOCKET_CREATED: + sc->status = SMBDIRECT_SOCKET_DISCONNECTED; + break; + case SMBDIRECT_SOCKET_CONNECTED: sc->status = SMBDIRECT_SOCKET_ERROR; break; @@ -1883,6 +1886,7 @@ static int smb_direct_accept_client(struct smbdirect_socket *sc) static int smb_direct_prepare_negotiation(struct smbdirect_socket *sc) { struct smbdirect_recv_io *recvmsg; + bool recv_posted = false; int ret; WARN_ON_ONCE(sc->status != SMBDIRECT_SOCKET_CREATED); @@ -1899,6 +1903,7 @@ static int smb_direct_prepare_negotiation(struct smbdirect_socket *sc) pr_err("Can't post recv: %d\n", ret); goto out_err; } + recv_posted = true; ret = smb_direct_accept_client(sc); if (ret) { @@ -1908,7 +1913,14 @@ static int smb_direct_prepare_negotiation(struct smbdirect_socket *sc) return 0; out_err: - put_recvmsg(sc, recvmsg); + /* + * If the recv was never posted, return it to the free list. + * If it was posted, leave it alone so disconnect teardown can + * drain the QP and complete it (flush) and the completion path + * will unmap it exactly once. + */ + if (!recv_posted) + put_recvmsg(sc, recvmsg); return ret; } @@ -2606,7 +2618,7 @@ void ksmbd_rdma_destroy(void) } } -bool ksmbd_rdma_capable_netdev(struct net_device *netdev) +static bool ksmbd_find_rdma_capable_netdev(struct net_device *netdev) { struct smb_direct_device *smb_dev; int i; @@ -2648,6 +2660,28 @@ out: return rdma_capable; } +bool ksmbd_rdma_capable_netdev(struct net_device *netdev) +{ + struct net_device *lower_dev; + struct list_head *iter; + + if (ksmbd_find_rdma_capable_netdev(netdev)) + return true; + + /* check if netdev is bridge or VLAN */ + if (netif_is_bridge_master(netdev) || + netdev->priv_flags & IFF_802_1Q_VLAN) + netdev_for_each_lower_dev(netdev, lower_dev, iter) + if (ksmbd_find_rdma_capable_netdev(lower_dev)) + return true; + + /* check if netdev is IPoIB safely without layer violation */ + if (netdev->type == ARPHRD_INFINIBAND) + return true; + + return false; +} + static const struct ksmbd_transport_ops ksmbd_smb_direct_transport_ops = { .prepare = smb_direct_prepare, .disconnect = smb_direct_disconnect, diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c index 7a1e3dcc2cde..d2e391c29464 100644 --- a/fs/smb/server/transport_tcp.c +++ b/fs/smb/server/transport_tcp.c @@ -290,8 +290,11 @@ static int ksmbd_kthread_fn(void *p) } } up_read(&conn_list_lock); - if (ret == -EAGAIN) + if (ret == -EAGAIN) { + /* Per-IP limit hit: release the just-accepted socket. */ + sock_release(client_sk); continue; + } skip_max_ip_conns_limit: if (server_conf.max_connections && diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c index ee49f20875af..6917de832191 100644 --- a/fs/xfs/xfs_discard.c +++ b/fs/xfs/xfs_discard.c @@ -726,8 +726,10 @@ xfs_trim_rtgroup_extents( break; } - if (!tr.queued) + if (!tr.queued) { + kfree(tr.extents); break; + } /* * We hand the extent list to the discard function here so the diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index d3f6e3e42a11..490e12cb99be 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1091,6 +1091,29 @@ const struct iomap_ops xfs_zoned_direct_write_iomap_ops = { }; #endif /* CONFIG_XFS_RT */ +#ifdef DEBUG +static void +xfs_check_atomic_cow_conversion( + struct xfs_inode *ip, + xfs_fileoff_t offset_fsb, + xfs_filblks_t count_fsb, + const struct xfs_bmbt_irec *cmap) +{ + struct xfs_iext_cursor icur; + struct xfs_bmbt_irec cmap2 = { }; + + if (xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &cmap2)) + xfs_trim_extent(&cmap2, offset_fsb, count_fsb); + + ASSERT(cmap2.br_startoff == cmap->br_startoff); + ASSERT(cmap2.br_blockcount == cmap->br_blockcount); + ASSERT(cmap2.br_startblock == cmap->br_startblock); + ASSERT(cmap2.br_state == cmap->br_state); +} +#else +# define xfs_check_atomic_cow_conversion(...) ((void)0) +#endif + static int xfs_atomic_write_cow_iomap_begin( struct inode *inode, @@ -1102,9 +1125,10 @@ xfs_atomic_write_cow_iomap_begin( { struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; - const xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset); - xfs_fileoff_t end_fsb = xfs_iomap_end_fsb(mp, offset, length); - xfs_filblks_t count_fsb = end_fsb - offset_fsb; + const xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset); + const xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, offset + length); + const xfs_filblks_t count_fsb = end_fsb - offset_fsb; + xfs_filblks_t hole_count_fsb; int nmaps = 1; xfs_filblks_t resaligned; struct xfs_bmbt_irec cmap; @@ -1130,7 +1154,7 @@ xfs_atomic_write_cow_iomap_begin( return -EAGAIN; trace_xfs_iomap_atomic_write_cow(ip, offset, length); - +retry: xfs_ilock(ip, XFS_ILOCK_EXCL); if (!ip->i_cowfp) { @@ -1141,14 +1165,22 @@ xfs_atomic_write_cow_iomap_begin( if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &cmap)) cmap.br_startoff = end_fsb; if (cmap.br_startoff <= offset_fsb) { + if (isnullstartblock(cmap.br_startblock)) + goto convert_delay; + + /* + * cmap could extend outside the write range due to previous + * speculative preallocations. We must trim cmap to the write + * range because the cow fork treats written mappings to mean + * "write in progress". + */ xfs_trim_extent(&cmap, offset_fsb, count_fsb); goto found; } - end_fsb = cmap.br_startoff; - count_fsb = end_fsb - offset_fsb; + hole_count_fsb = cmap.br_startoff - offset_fsb; - resaligned = xfs_aligned_fsb_count(offset_fsb, count_fsb, + resaligned = xfs_aligned_fsb_count(offset_fsb, hole_count_fsb, xfs_get_cowextsz_hint(ip)); xfs_iunlock(ip, XFS_ILOCK_EXCL); @@ -1169,8 +1201,10 @@ xfs_atomic_write_cow_iomap_begin( if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &cmap)) cmap.br_startoff = end_fsb; if (cmap.br_startoff <= offset_fsb) { - xfs_trim_extent(&cmap, offset_fsb, count_fsb); xfs_trans_cancel(tp); + if (isnullstartblock(cmap.br_startblock)) + goto convert_delay; + xfs_trim_extent(&cmap, offset_fsb, count_fsb); goto found; } @@ -1182,7 +1216,7 @@ xfs_atomic_write_cow_iomap_begin( * atomic writes to that same range will be aligned (and don't require * this COW-based method). */ - error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb, + error = xfs_bmapi_write(tp, ip, offset_fsb, hole_count_fsb, XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC | XFS_BMAPI_EXTSZALIGN, 0, &cmap, &nmaps); if (error) { @@ -1195,21 +1229,43 @@ xfs_atomic_write_cow_iomap_begin( if (error) goto out_unlock; + /* + * cmap could map more blocks than the range we passed into bmapi_write + * because of EXTSZALIGN or adjacent pre-existing unwritten mappings + * that were merged. Trim cmap to the original write range so that we + * don't convert more than we were asked to do for this write. + */ + xfs_trim_extent(&cmap, offset_fsb, count_fsb); + found: if (cmap.br_state != XFS_EXT_NORM) { - error = xfs_reflink_convert_cow_locked(ip, offset_fsb, - count_fsb); + error = xfs_reflink_convert_cow_locked(ip, cmap.br_startoff, + cmap.br_blockcount); if (error) goto out_unlock; cmap.br_state = XFS_EXT_NORM; + xfs_check_atomic_cow_conversion(ip, offset_fsb, count_fsb, + &cmap); } - length = XFS_FSB_TO_B(mp, cmap.br_startoff + cmap.br_blockcount); - trace_xfs_iomap_found(ip, offset, length - offset, XFS_COW_FORK, &cmap); + trace_xfs_iomap_found(ip, offset, length, XFS_COW_FORK, &cmap); seq = xfs_iomap_inode_sequence(ip, IOMAP_F_SHARED); xfs_iunlock(ip, XFS_ILOCK_EXCL); return xfs_bmbt_to_iomap(ip, iomap, &cmap, flags, IOMAP_F_SHARED, seq); +convert_delay: + xfs_iunlock(ip, XFS_ILOCK_EXCL); + error = xfs_bmapi_convert_delalloc(ip, XFS_COW_FORK, offset, iomap, + NULL); + if (error) + return error; + + /* + * Try the lookup again, because the delalloc conversion might have + * turned the COW mapping into unwritten, but we need it to be in + * written state. + */ + goto retry; out_unlock: xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c index 040402240807..ef7a931ebde5 100644 --- a/fs/xfs/xfs_zone_alloc.c +++ b/fs/xfs/xfs_zone_alloc.c @@ -615,7 +615,7 @@ xfs_select_open_zone_mru( lockdep_assert_held(&zi->zi_open_zones_lock); list_for_each_entry_reverse(oz, &zi->zi_open_zones, oz_entry) - if (xfs_try_use_zone(zi, file_hint, oz, false)) + if (xfs_try_use_zone(zi, file_hint, oz, XFS_ZONE_ALLOC_OK)) return oz; cond_resched_lock(&zi->zi_open_zones_lock); @@ -1249,8 +1249,10 @@ xfs_mount_zones( while ((rtg = xfs_rtgroup_next(mp, rtg))) { error = xfs_init_zone(&iz, rtg, NULL); - if (error) + if (error) { + xfs_rtgroup_rele(rtg); goto out_free_zone_info; + } } } diff --git a/include/drm/Makefile b/include/drm/Makefile index 1df6962556ef..48fae3f167c7 100644 --- a/include/drm/Makefile +++ b/include/drm/Makefile @@ -11,7 +11,7 @@ always-$(CONFIG_DRM_HEADER_TEST) += \ quiet_cmd_hdrtest = HDRTEST $(patsubst %.hdrtest,%.h,$@) cmd_hdrtest = \ $(CC) $(c_flags) -fsyntax-only -x c /dev/null -include $< -include $<; \ - PYTHONDONTWRITEBYTECODE=1 $(KERNELDOC) -none $(if $(CONFIG_WERROR)$(CONFIG_DRM_WERROR),-Werror) $<; \ + PYTHONDONTWRITEBYTECODE=1 $(PYTHON3) $(KERNELDOC) -none $(if $(CONFIG_WERROR)$(CONFIG_DRM_WERROR),-Werror) $<; \ touch $@ $(obj)/%.hdrtest: $(src)/%.h FORCE diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 59288a2c1ad2..0a1b9598940d 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -250,10 +250,9 @@ struct ftrace_likely_data { /* * GCC does not warn about unused static inline functions for -Wunused-function. * Suppress the warning in clang as well by using __maybe_unused, but enable it - * for W=1 build. This will allow clang to find unused functions. Remove the - * __inline_maybe_unused entirely after fixing most of -Wunused-function warnings. + * for W=2 build. This will allow clang to find unused functions. */ -#ifdef KBUILD_EXTRA_WARN1 +#ifdef KBUILD_EXTRA_WARN2 #define __inline_maybe_unused #else #define __inline_maybe_unused __maybe_unused @@ -461,6 +460,12 @@ struct ftrace_likely_data { # define __nocfi #endif +#if defined(CONFIG_ARCH_USES_CFI_GENERIC_LLVM_PASS) +# define __nocfi_generic __nocfi +#else +# define __nocfi_generic +#endif + /* * Any place that could be marked with the "alloc_size" attribute is also * a place to be marked with the "malloc" attribute, except those that may diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 8248ff9363ee..2ceda49c609f 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -90,7 +90,7 @@ */ #define DMA_MAPPING_ERROR (~(dma_addr_t)0) -#define DMA_BIT_MASK(n) (((n) == 64) ? ~0ULL : ((1ULL<<(n))-1)) +#define DMA_BIT_MASK(n) GENMASK_ULL(n - 1, 0) struct dma_iova_state { dma_addr_t addr; diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index c2d8b4ec62eb..5c9162193d26 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -492,7 +492,7 @@ struct ethtool_pause_stats { }; #define ETHTOOL_MAX_LANES 8 -/** +/* * IEEE 802.3ck/df defines 16 bins for FEC histogram plus one more for * the end-of-list marker, total 17 items */ diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 0ceb4e09306c..623bee335383 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -7,6 +7,7 @@ #include <linux/mmzone.h> #include <linux/topology.h> #include <linux/alloc_tag.h> +#include <linux/cleanup.h> #include <linux/sched.h> struct vm_area_struct; @@ -463,4 +464,6 @@ static inline struct folio *folio_alloc_gigantic_noprof(int order, gfp_t gfp, /* This should be paired with folio_put() rather than free_contig_range(). */ #define folio_alloc_gigantic(...) alloc_hooks(folio_alloc_gigantic_noprof(__VA_ARGS__)) +DEFINE_FREE(free_page, void *, free_page((unsigned long)_T)) + #endif /* __LINUX_GFP_H */ diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index f327d62fc985..71ac78b9f834 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -376,45 +376,30 @@ bool non_uniform_split_supported(struct folio *folio, unsigned int new_order, int folio_split(struct folio *folio, unsigned int new_order, struct page *page, struct list_head *list); /* - * try_folio_split - try to split a @folio at @page using non uniform split. + * try_folio_split_to_order - try to split a @folio at @page to @new_order using + * non uniform split. * @folio: folio to be split - * @page: split to order-0 at the given page - * @list: store the after-split folios + * @page: split to @new_order at the given page + * @new_order: the target split order * - * Try to split a @folio at @page using non uniform split to order-0, if - * non uniform split is not supported, fall back to uniform split. + * Try to split a @folio at @page using non uniform split to @new_order, if + * non uniform split is not supported, fall back to uniform split. After-split + * folios are put back to LRU list. Use min_order_for_split() to get the lower + * bound of @new_order. * * Return: 0: split is successful, otherwise split failed. */ -static inline int try_folio_split(struct folio *folio, struct page *page, - struct list_head *list) +static inline int try_folio_split_to_order(struct folio *folio, + struct page *page, unsigned int new_order) { - int ret = min_order_for_split(folio); - - if (ret < 0) - return ret; - - if (!non_uniform_split_supported(folio, 0, false)) - return split_huge_page_to_list_to_order(&folio->page, list, - ret); - return folio_split(folio, ret, page, list); + if (!non_uniform_split_supported(folio, new_order, /* warns= */ false)) + return split_huge_page_to_list_to_order(&folio->page, NULL, + new_order); + return folio_split(folio, new_order, page, NULL); } static inline int split_huge_page(struct page *page) { - struct folio *folio = page_folio(page); - int ret = min_order_for_split(folio); - - if (ret < 0) - return ret; - - /* - * split_huge_page() locks the page before splitting and - * expects the same page that has been split to be locked when - * returned. split_folio(page_folio(page)) cannot be used here - * because it converts the page to folio and passes the head - * page to be split. - */ - return split_huge_page_to_list_to_order(page, NULL, ret); + return split_huge_page_to_list_to_order(page, NULL, 0); } void deferred_split_folio(struct folio *folio, bool partially_mapped); @@ -597,14 +582,20 @@ static inline int split_huge_page(struct page *page) return -EINVAL; } +static inline int min_order_for_split(struct folio *folio) +{ + VM_WARN_ON_ONCE_FOLIO(1, folio); + return -EINVAL; +} + static inline int split_folio_to_list(struct folio *folio, struct list_head *list) { VM_WARN_ON_ONCE_FOLIO(1, folio); return -EINVAL; } -static inline int try_folio_split(struct folio *folio, struct page *page, - struct list_head *list) +static inline int try_folio_split_to_order(struct folio *folio, + struct page *page, unsigned int new_order) { VM_WARN_ON_ONCE_FOLIO(1, folio); return -EINVAL; diff --git a/include/linux/map_benchmark.h b/include/linux/map_benchmark.h index 62674c83bde4..48e2ff95332f 100644 --- a/include/linux/map_benchmark.h +++ b/include/linux/map_benchmark.h @@ -27,5 +27,6 @@ struct map_benchmark { __u32 dma_dir; /* DMA data direction */ __u32 dma_trans_ns; /* time for DMA transmission in ns */ __u32 granule; /* how many PAGE_SIZE will do map/unmap once a time */ + __u8 expansion[76]; /* For future use */ }; #endif /* _KERNEL_DMA_BENCHMARK_H */ diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index 7ef2c7c7d803..9d47cdc727ad 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -183,6 +183,7 @@ static inline void mlx5_cq_put(struct mlx5_core_cq *cq) complete(&cq->free); } +void mlx5_add_cq_to_tasklet(struct mlx5_core_cq *cq, struct mlx5_eqe *eqe); int mlx5_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, u32 *in, int inlen, u32 *out, int outlen); int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, diff --git a/include/linux/net/intel/libie/fwlog.h b/include/linux/net/intel/libie/fwlog.h index 36b13fabca9e..7273c78c826b 100644 --- a/include/linux/net/intel/libie/fwlog.h +++ b/include/linux/net/intel/libie/fwlog.h @@ -78,8 +78,20 @@ struct libie_fwlog { ); }; +#if IS_ENABLED(CONFIG_LIBIE_FWLOG) int libie_fwlog_init(struct libie_fwlog *fwlog, struct libie_fwlog_api *api); void libie_fwlog_deinit(struct libie_fwlog *fwlog); void libie_fwlog_reregister(struct libie_fwlog *fwlog); void libie_get_fwlog_data(struct libie_fwlog *fwlog, u8 *buf, u16 len); +#else +static inline int libie_fwlog_init(struct libie_fwlog *fwlog, + struct libie_fwlog_api *api) +{ + return -EOPNOTSUPP; +} +static inline void libie_fwlog_deinit(struct libie_fwlog *fwlog) { } +static inline void libie_fwlog_reregister(struct libie_fwlog *fwlog) { } +static inline void libie_get_fwlog_data(struct libie_fwlog *fwlog, u8 *buf, + u16 len) { } +#endif /* CONFIG_LIBIE_FWLOG */ #endif /* _LIBIE_FWLOG_H_ */ diff --git a/include/linux/platform_data/x86/int3472.h b/include/linux/platform_data/x86/int3472.h index 1571e9157fa5..b1b837583d54 100644 --- a/include/linux/platform_data/x86/int3472.h +++ b/include/linux/platform_data/x86/int3472.h @@ -100,7 +100,6 @@ struct int3472_gpio_regulator { struct regulator_consumer_supply supply_map[GPIO_REGULATOR_SUPPLY_MAP_COUNT * 2]; char supply_name_upper[GPIO_SUPPLY_NAME_LENGTH]; char regulator_name[GPIO_REGULATOR_NAME_LENGTH]; - struct gpio_desc *ena_gpio; struct regulator_dev *rdev; struct regulator_desc rdesc; }; diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 4d1780848d0e..b673c31569f3 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -401,7 +401,8 @@ virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb, if (!tnl_hdr_negotiated) return -EINVAL; - vhdr->hash_hdr.hash_value = 0; + vhdr->hash_hdr.hash_value_lo = 0; + vhdr->hash_hdr.hash_value_hi = 0; vhdr->hash_hdr.hash_report = 0; vhdr->hash_hdr.padding = 0; diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 8d0e703bc929..cb4c02d00759 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -2783,6 +2783,11 @@ struct hci_ev_le_per_adv_report { __u8 data[]; } __packed; +#define HCI_EV_LE_PA_SYNC_LOST 0x10 +struct hci_ev_le_pa_sync_lost { + __le16 handle; +} __packed; + #define LE_PA_DATA_COMPLETE 0x00 #define LE_PA_DATA_MORE_TO_COME 0x01 #define LE_PA_DATA_TRUNCATED 0x02 diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index bca0333f1e99..f5be96f08b9d 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -780,7 +780,7 @@ struct mgmt_adv_pattern { __u8 ad_type; __u8 offset; __u8 length; - __u8 value[31]; + __u8 value[HCI_MAX_AD_LENGTH]; } __packed; #define MGMT_OP_ADD_ADV_PATTERNS_MONITOR 0x0052 diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 781624f5913a..820e299f06b5 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -6435,6 +6435,11 @@ static inline void wiphy_delayed_work_init(struct wiphy_delayed_work *dwork, * after wiphy_lock() was called. Therefore, wiphy_cancel_work() can * use just cancel_work() instead of cancel_work_sync(), it requires * being in a section protected by wiphy_lock(). + * + * Note that these are scheduled with a timer where the accuracy + * becomes less the longer in the future the scheduled timer is. Use + * wiphy_hrtimer_work_queue() if the timer must be not be late by more + * than approximately 10 percent. */ void wiphy_delayed_work_queue(struct wiphy *wiphy, struct wiphy_delayed_work *dwork, @@ -6506,6 +6511,79 @@ void wiphy_delayed_work_flush(struct wiphy *wiphy, bool wiphy_delayed_work_pending(struct wiphy *wiphy, struct wiphy_delayed_work *dwork); +struct wiphy_hrtimer_work { + struct wiphy_work work; + struct wiphy *wiphy; + struct hrtimer timer; +}; + +enum hrtimer_restart wiphy_hrtimer_work_timer(struct hrtimer *t); + +static inline void wiphy_hrtimer_work_init(struct wiphy_hrtimer_work *hrwork, + wiphy_work_func_t func) +{ + hrtimer_setup(&hrwork->timer, wiphy_hrtimer_work_timer, + CLOCK_BOOTTIME, HRTIMER_MODE_REL); + wiphy_work_init(&hrwork->work, func); +} + +/** + * wiphy_hrtimer_work_queue - queue hrtimer work for the wiphy + * @wiphy: the wiphy to queue for + * @hrwork: the high resolution timer worker + * @delay: the delay given as a ktime_t + * + * Please refer to wiphy_delayed_work_queue(). The difference is that + * the hrtimer work uses a high resolution timer for scheduling. This + * may be needed if timeouts might be scheduled further in the future + * and the accuracy of the normal timer is not sufficient. + * + * Expect a delay of a few milliseconds as the timer is scheduled + * with some slack and some more time may pass between queueing the + * work and its start. + */ +void wiphy_hrtimer_work_queue(struct wiphy *wiphy, + struct wiphy_hrtimer_work *hrwork, + ktime_t delay); + +/** + * wiphy_hrtimer_work_cancel - cancel previously queued hrtimer work + * @wiphy: the wiphy, for debug purposes + * @hrtimer: the hrtimer work to cancel + * + * Cancel the work *without* waiting for it, this assumes being + * called under the wiphy mutex acquired by wiphy_lock(). + */ +void wiphy_hrtimer_work_cancel(struct wiphy *wiphy, + struct wiphy_hrtimer_work *hrtimer); + +/** + * wiphy_hrtimer_work_flush - flush previously queued hrtimer work + * @wiphy: the wiphy, for debug purposes + * @hrwork: the hrtimer work to flush + * + * Flush the work (i.e. run it if pending). This must be called + * under the wiphy mutex acquired by wiphy_lock(). + */ +void wiphy_hrtimer_work_flush(struct wiphy *wiphy, + struct wiphy_hrtimer_work *hrwork); + +/** + * wiphy_hrtimer_work_pending - Find out whether a wiphy hrtimer + * work item is currently pending. + * + * @wiphy: the wiphy, for debug purposes + * @hrwork: the hrtimer work in question + * + * Return: true if timer is pending, false otherwise + * + * Please refer to the wiphy_delayed_work_pending() documentation as + * this is the equivalent function for hrtimer based delayed work + * items. + */ +bool wiphy_hrtimer_work_pending(struct wiphy *wiphy, + struct wiphy_hrtimer_work *hrwork); + /** * enum ieee80211_ap_reg_power - regulatory power for an Access Point * diff --git a/include/net/libeth/xdp.h b/include/net/libeth/xdp.h index bc3507edd589..898723ab62e8 100644 --- a/include/net/libeth/xdp.h +++ b/include/net/libeth/xdp.h @@ -513,7 +513,7 @@ struct libeth_xdp_tx_desc { * can't fail, but can send less frames if there's no enough free descriptors * available. The actual free space is returned by @prep from the driver. */ -static __always_inline u32 +static __always_inline __nocfi_generic u32 libeth_xdp_tx_xmit_bulk(const struct libeth_xdp_tx_frame *bulk, void *xdpsq, u32 n, bool unroll, u64 priv, u32 (*prep)(void *xdpsq, struct libeth_xdpsq *sq), diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index ea91aa8afde9..e527b24bd824 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -979,14 +979,20 @@ extern "C" { * 2 = Gob Height 8, Turing+ Page Kind mapping * 3 = Reserved for future use. * - * 22:22 s Sector layout. On Tegra GPUs prior to Xavier, there is a further - * bit remapping step that occurs at an even lower level than the - * page kind and block linear swizzles. This causes the layout of - * surfaces mapped in those SOC's GPUs to be incompatible with the - * equivalent mapping on other GPUs in the same system. - * - * 0 = Tegra K1 - Tegra Parker/TX2 Layout. - * 1 = Desktop GPU and Tegra Xavier+ Layout + * 22:22 s Sector layout. There is a further bit remapping step that occurs + * 26:27 at an even lower level than the page kind and block linear + * swizzles. This causes the bit arrangement of surfaces in memory + * to differ subtly, and prevents direct sharing of surfaces between + * GPUs with different layouts. + * + * 0 = Tegra K1 - Tegra Parker/TX2 Layout + * 1 = Pre-GB20x, GB20x 32+ bpp, GB10, Tegra Xavier-Orin Layout + * 2 = GB20x(Blackwell 2)+ 8 bpp surface layout + * 3 = GB20x(Blackwell 2)+ 16 bpp surface layout + * 4 = Reserved for future use. + * 5 = Reserved for future use. + * 6 = Reserved for future use. + * 7 = Reserved for future use. * * 25:23 c Lossless Framebuffer Compression type. * @@ -1001,7 +1007,7 @@ extern "C" { * 6 = Reserved for future use * 7 = Reserved for future use * - * 55:25 - Reserved for future use. Must be zero. + * 55:28 - Reserved for future use. Must be zero. */ #define DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(c, s, g, k, h) \ fourcc_mod_code(NVIDIA, (0x10 | \ @@ -1009,6 +1015,7 @@ extern "C" { (((k) & 0xff) << 12) | \ (((g) & 0x3) << 20) | \ (((s) & 0x1) << 22) | \ + (((s) & 0x6) << 25) | \ (((c) & 0x7) << 23))) /* To grandfather in prior block linear format modifiers to the above layout, diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index 4a9fbf42aa9f..9cd89bcc1d9c 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -631,6 +631,18 @@ #define KEY_BRIGHTNESS_MIN 0x250 /* Set Brightness to Minimum */ #define KEY_BRIGHTNESS_MAX 0x251 /* Set Brightness to Maximum */ +/* + * Keycodes for hotkeys toggling the electronic privacy screen found on some + * laptops on/off. Note when the embedded-controller turns on/off the eprivacy + * screen itself then the state should be reported through drm connecter props: + * https://www.kernel.org/doc/html/latest/gpu/drm-kms.html#standard-connector-properties + * Except when implementing the drm connecter properties API is not possible + * because e.g. the firmware does not allow querying the presence and/or status + * of the eprivacy screen at boot. + */ +#define KEY_EPRIVACY_SCREEN_ON 0x252 +#define KEY_EPRIVACY_SCREEN_OFF 0x253 + #define KEY_KBDINPUTASSIST_PREV 0x260 #define KEY_KBDINPUTASSIST_NEXT 0x261 #define KEY_KBDINPUTASSIST_PREVGROUP 0x262 diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 263bed13473e..b7c8dad26690 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -689,9 +689,6 @@ enum io_uring_register_op { /* query various aspects of io_uring, see linux/io_uring/query.h */ IORING_REGISTER_QUERY = 35, - /* return zcrx buffers back into circulation */ - IORING_REGISTER_ZCRX_REFILL = 36, - /* this goes last */ IORING_REGISTER_LAST, @@ -1073,15 +1070,6 @@ struct io_uring_zcrx_ifq_reg { __u64 __resv[3]; }; -struct io_uring_zcrx_sync_refill { - __u32 zcrx_id; - /* the number of entries to return */ - __u32 nr_entries; - /* pointer to an array of struct io_uring_zcrx_rqe */ - __u64 rqes; - __u64 __resv[2]; -}; - #ifdef __cplusplus } #endif diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h index 8bf27ab8bcb4..1db45b01532b 100644 --- a/include/uapi/linux/virtio_net.h +++ b/include/uapi/linux/virtio_net.h @@ -193,7 +193,8 @@ struct virtio_net_hdr_v1 { struct virtio_net_hdr_v1_hash { struct virtio_net_hdr_v1 hdr; - __le32 hash_value; + __le16 hash_value_lo; + __le16 hash_value_hi; #define VIRTIO_NET_HASH_REPORT_NONE 0 #define VIRTIO_NET_HASH_REPORT_IPv4 1 #define VIRTIO_NET_HASH_REPORT_TCPv4 2 diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h index 9425cfd9d00e..0f95576bf1f6 100644 --- a/include/ufs/ufshcd.h +++ b/include/ufs/ufshcd.h @@ -688,6 +688,13 @@ enum ufshcd_quirks { * single doorbell mode. */ UFSHCD_QUIRK_BROKEN_LSDBS_CAP = 1 << 25, + + /* + * This quirk indicates that DME_LINKSTARTUP should not be issued a 2nd + * time (refer link_startup_again) after the 1st time was successful, + * because it causes link startup to become unreliable. + */ + UFSHCD_QUIRK_PERFORM_LINK_STARTUP_ONCE = 1 << 26, }; enum ufshcd_caps { diff --git a/io_uring/memmap.c b/io_uring/memmap.c index 2e99dffddfc5..add03ca75cb9 100644 --- a/io_uring/memmap.c +++ b/io_uring/memmap.c @@ -135,7 +135,7 @@ static int io_region_pin_pages(struct io_ring_ctx *ctx, struct io_mapped_region *mr, struct io_uring_region_desc *reg) { - unsigned long size = mr->nr_pages << PAGE_SHIFT; + unsigned long size = (size_t) mr->nr_pages << PAGE_SHIFT; struct page **pages; int nr_pages; diff --git a/io_uring/register.c b/io_uring/register.c index 2e4717f1357c..d189b266b8cc 100644 --- a/io_uring/register.c +++ b/io_uring/register.c @@ -827,9 +827,6 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, case IORING_REGISTER_QUERY: ret = io_query(ctx, arg, nr_args); break; - case IORING_REGISTER_ZCRX_REFILL: - ret = io_zcrx_return_bufs(ctx, arg, nr_args); - break; default: ret = -EINVAL; break; diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index d787c16dc1c3..2602d76d5ff0 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -1403,8 +1403,11 @@ static int io_estimate_bvec_size(struct iovec *iov, unsigned nr_iovs, size_t max_segs = 0; unsigned i; - for (i = 0; i < nr_iovs; i++) + for (i = 0; i < nr_iovs; i++) { max_segs += (iov[i].iov_len >> shift) + 2; + if (max_segs > INT_MAX) + return -EOVERFLOW; + } return max_segs; } @@ -1510,7 +1513,11 @@ int io_import_reg_vec(int ddir, struct iov_iter *iter, if (unlikely(ret)) return ret; } else { - nr_segs = io_estimate_bvec_size(iov, nr_iovs, imu); + int ret = io_estimate_bvec_size(iov, nr_iovs, imu); + + if (ret < 0) + return ret; + nr_segs = ret; } if (sizeof(struct bio_vec) > sizeof(struct iovec)) { diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c index a816f5902091..b1b723222cdb 100644 --- a/io_uring/zcrx.c +++ b/io_uring/zcrx.c @@ -928,74 +928,6 @@ static const struct memory_provider_ops io_uring_pp_zc_ops = { .uninstall = io_pp_uninstall, }; -#define IO_ZCRX_MAX_SYS_REFILL_BUFS (1 << 16) -#define IO_ZCRX_SYS_REFILL_BATCH 32 - -static void io_return_buffers(struct io_zcrx_ifq *ifq, - struct io_uring_zcrx_rqe *rqes, unsigned nr) -{ - int i; - - for (i = 0; i < nr; i++) { - struct net_iov *niov; - netmem_ref netmem; - - if (!io_parse_rqe(&rqes[i], ifq, &niov)) - continue; - - scoped_guard(spinlock_bh, &ifq->rq_lock) { - if (!io_zcrx_put_niov_uref(niov)) - continue; - } - - netmem = net_iov_to_netmem(niov); - if (!page_pool_unref_and_test(netmem)) - continue; - io_zcrx_return_niov(niov); - } -} - -int io_zcrx_return_bufs(struct io_ring_ctx *ctx, - void __user *arg, unsigned nr_arg) -{ - struct io_uring_zcrx_rqe rqes[IO_ZCRX_SYS_REFILL_BATCH]; - struct io_uring_zcrx_rqe __user *user_rqes; - struct io_uring_zcrx_sync_refill zr; - struct io_zcrx_ifq *ifq; - unsigned nr, i; - - if (nr_arg) - return -EINVAL; - if (copy_from_user(&zr, arg, sizeof(zr))) - return -EFAULT; - if (!zr.nr_entries || zr.nr_entries > IO_ZCRX_MAX_SYS_REFILL_BUFS) - return -EINVAL; - if (!mem_is_zero(&zr.__resv, sizeof(zr.__resv))) - return -EINVAL; - - ifq = xa_load(&ctx->zcrx_ctxs, zr.zcrx_id); - if (!ifq) - return -EINVAL; - nr = zr.nr_entries; - user_rqes = u64_to_user_ptr(zr.rqes); - - for (i = 0; i < nr;) { - unsigned batch = min(nr - i, IO_ZCRX_SYS_REFILL_BATCH); - size_t size = batch * sizeof(rqes[0]); - - if (copy_from_user(rqes, user_rqes + i, size)) - return i ? i : -EFAULT; - io_return_buffers(ifq, rqes, batch); - - i += batch; - - if (fatal_signal_pending(current)) - return i; - cond_resched(); - } - return nr; -} - static bool io_zcrx_queue_cqe(struct io_kiocb *req, struct net_iov *niov, struct io_zcrx_ifq *ifq, int off, int len) { diff --git a/io_uring/zcrx.h b/io_uring/zcrx.h index 33ef61503092..a48871b5adad 100644 --- a/io_uring/zcrx.h +++ b/io_uring/zcrx.h @@ -63,8 +63,6 @@ struct io_zcrx_ifq { }; #if defined(CONFIG_IO_URING_ZCRX) -int io_zcrx_return_bufs(struct io_ring_ctx *ctx, - void __user *arg, unsigned nr_arg); int io_register_zcrx_ifq(struct io_ring_ctx *ctx, struct io_uring_zcrx_ifq_reg __user *arg); void io_unregister_zcrx_ifqs(struct io_ring_ctx *ctx); @@ -97,11 +95,6 @@ static inline struct io_mapped_region *io_zcrx_get_region(struct io_ring_ctx *ct { return NULL; } -static inline int io_zcrx_return_bufs(struct io_ring_ctx *ctx, - void __user *arg, unsigned nr_arg) -{ - return -EOPNOTSUPP; -} #endif int io_recvzc(struct io_kiocb *req, unsigned int issue_flags); diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec index 422270d64820..54e581072617 100644 --- a/kernel/Kconfig.kexec +++ b/kernel/Kconfig.kexec @@ -109,6 +109,15 @@ config KEXEC_HANDOVER to keep data or state alive across the kexec. For this to work, both source and target kernels need to have this option enabled. +config KEXEC_HANDOVER_DEBUG + bool "Enable Kexec Handover debug checks" + depends on KEXEC_HANDOVER + help + This option enables extra sanity checks for the Kexec Handover + subsystem. Since, KHO performance is crucial in live update + scenarios and the extra code might be adding overhead it is + only optionally enabled. + config CRASH_DUMP bool "kernel crash dumps" default ARCH_DEFAULT_CRASH_DUMP diff --git a/kernel/Makefile b/kernel/Makefile index df3dd8291bb6..9fe722305c9b 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -83,6 +83,7 @@ obj-$(CONFIG_KEXEC) += kexec.o obj-$(CONFIG_KEXEC_FILE) += kexec_file.o obj-$(CONFIG_KEXEC_ELF) += kexec_elf.o obj-$(CONFIG_KEXEC_HANDOVER) += kexec_handover.o +obj-$(CONFIG_KEXEC_HANDOVER_DEBUG) += kexec_handover_debug.o obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o obj-$(CONFIG_COMPAT) += compat.o obj-$(CONFIG_CGROUPS) += cgroup/ diff --git a/kernel/events/core.c b/kernel/events/core.c index 177e57c1a362..1fd347da9026 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -11773,7 +11773,8 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer) event = container_of(hrtimer, struct perf_event, hw.hrtimer); - if (event->state != PERF_EVENT_STATE_ACTIVE) + if (event->state != PERF_EVENT_STATE_ACTIVE || + event->hw.state & PERF_HES_STOPPED) return HRTIMER_NORESTART; event->pmu->read(event); @@ -11819,15 +11820,20 @@ static void perf_swevent_cancel_hrtimer(struct perf_event *event) struct hw_perf_event *hwc = &event->hw; /* - * The throttle can be triggered in the hrtimer handler. - * The HRTIMER_NORESTART should be used to stop the timer, - * rather than hrtimer_cancel(). See perf_swevent_hrtimer() + * Careful: this function can be triggered in the hrtimer handler, + * for cpu-clock events, so hrtimer_cancel() would cause a + * deadlock. + * + * So use hrtimer_try_to_cancel() to try to stop the hrtimer, + * and the cpu-clock handler also sets the PERF_HES_STOPPED flag, + * which guarantees that perf_swevent_hrtimer() will stop the + * hrtimer once it sees the PERF_HES_STOPPED flag. */ if (is_sampling_event(event) && (hwc->interrupts != MAX_INTERRUPTS)) { ktime_t remaining = hrtimer_get_remaining(&hwc->hrtimer); local64_set(&hwc->period_left, ktime_to_ns(remaining)); - hrtimer_cancel(&hwc->hrtimer); + hrtimer_try_to_cancel(&hwc->hrtimer); } } @@ -11871,12 +11877,14 @@ static void cpu_clock_event_update(struct perf_event *event) static void cpu_clock_event_start(struct perf_event *event, int flags) { + event->hw.state = 0; local64_set(&event->hw.prev_count, local_clock()); perf_swevent_start_hrtimer(event); } static void cpu_clock_event_stop(struct perf_event *event, int flags) { + event->hw.state = PERF_HES_STOPPED; perf_swevent_cancel_hrtimer(event); if (flags & PERF_EF_UPDATE) cpu_clock_event_update(event); @@ -11950,12 +11958,14 @@ static void task_clock_event_update(struct perf_event *event, u64 now) static void task_clock_event_start(struct perf_event *event, int flags) { + event->hw.state = 0; local64_set(&event->hw.prev_count, event->ctx->time); perf_swevent_start_hrtimer(event); } static void task_clock_event_stop(struct perf_event *event, int flags) { + event->hw.state = PERF_HES_STOPPED; perf_swevent_cancel_hrtimer(event); if (flags & PERF_EF_UPDATE) task_clock_event_update(event, event->ctx->time); diff --git a/kernel/futex/core.c b/kernel/futex/core.c index 125804fbb5cb..2e77a6e5c865 100644 --- a/kernel/futex/core.c +++ b/kernel/futex/core.c @@ -1680,10 +1680,10 @@ static bool futex_ref_get(struct futex_private_hash *fph) { struct mm_struct *mm = fph->mm; - guard(rcu)(); + guard(preempt)(); - if (smp_load_acquire(&fph->state) == FR_PERCPU) { - this_cpu_inc(*mm->futex_ref); + if (READ_ONCE(fph->state) == FR_PERCPU) { + __this_cpu_inc(*mm->futex_ref); return true; } @@ -1694,10 +1694,10 @@ static bool futex_ref_put(struct futex_private_hash *fph) { struct mm_struct *mm = fph->mm; - guard(rcu)(); + guard(preempt)(); - if (smp_load_acquire(&fph->state) == FR_PERCPU) { - this_cpu_dec(*mm->futex_ref); + if (READ_ONCE(fph->state) == FR_PERCPU) { + __this_cpu_dec(*mm->futex_ref); return false; } diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c index a08cc076f332..ffde93d051a4 100644 --- a/kernel/gcov/gcc_4_7.c +++ b/kernel/gcov/gcc_4_7.c @@ -18,7 +18,9 @@ #include <linux/mm.h> #include "gcov.h" -#if (__GNUC__ >= 14) +#if (__GNUC__ >= 15) +#define GCOV_COUNTERS 10 +#elif (__GNUC__ >= 14) #define GCOV_COUNTERS 9 #elif (__GNUC__ >= 10) #define GCOV_COUNTERS 8 diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c index 76f0940fb485..03d12e27189f 100644 --- a/kernel/kexec_handover.c +++ b/kernel/kexec_handover.c @@ -8,6 +8,7 @@ #define pr_fmt(fmt) "KHO: " fmt +#include <linux/cleanup.h> #include <linux/cma.h> #include <linux/count_zeros.h> #include <linux/debugfs.h> @@ -22,6 +23,7 @@ #include <asm/early_ioremap.h> +#include "kexec_handover_internal.h" /* * KHO is tightly coupled with mm init and needs access to some of mm * internal APIs. @@ -67,10 +69,10 @@ early_param("kho", kho_parse_enable); * Keep track of memory that is to be preserved across KHO. * * The serializing side uses two levels of xarrays to manage chunks of per-order - * 512 byte bitmaps. For instance if PAGE_SIZE = 4096, the entire 1G order of a - * 1TB system would fit inside a single 512 byte bitmap. For order 0 allocations - * each bitmap will cover 16M of address space. Thus, for 16G of memory at most - * 512K of bitmap memory will be needed for order 0. + * PAGE_SIZE byte bitmaps. For instance if PAGE_SIZE = 4096, the entire 1G order + * of a 8TB system would fit inside a single 4096 byte bitmap. For order 0 + * allocations each bitmap will cover 128M of address space. Thus, for 16G of + * memory at most 512K of bitmap memory will be needed for order 0. * * This approach is fully incremental, as the serialization progresses folios * can continue be aggregated to the tracker. The final step, immediately prior @@ -78,12 +80,14 @@ early_param("kho", kho_parse_enable); * successor kernel to parse. */ -#define PRESERVE_BITS (512 * 8) +#define PRESERVE_BITS (PAGE_SIZE * 8) struct kho_mem_phys_bits { DECLARE_BITMAP(preserve, PRESERVE_BITS); }; +static_assert(sizeof(struct kho_mem_phys_bits) == PAGE_SIZE); + struct kho_mem_phys { /* * Points to kho_mem_phys_bits, a sparse bitmap array. Each bit is sized @@ -131,28 +135,28 @@ static struct kho_out kho_out = { .finalized = false, }; -static void *xa_load_or_alloc(struct xarray *xa, unsigned long index, size_t sz) +static void *xa_load_or_alloc(struct xarray *xa, unsigned long index) { - void *elm, *res; + void *res = xa_load(xa, index); + + if (res) + return res; - elm = xa_load(xa, index); - if (elm) - return elm; + void *elm __free(free_page) = (void *)get_zeroed_page(GFP_KERNEL); - elm = kzalloc(sz, GFP_KERNEL); if (!elm) return ERR_PTR(-ENOMEM); + if (WARN_ON(kho_scratch_overlap(virt_to_phys(elm), PAGE_SIZE))) + return ERR_PTR(-EINVAL); + res = xa_cmpxchg(xa, index, NULL, elm, GFP_KERNEL); if (xa_is_err(res)) - res = ERR_PTR(xa_err(res)); - - if (res) { - kfree(elm); + return ERR_PTR(xa_err(res)); + else if (res) return res; - } - return elm; + return no_free_ptr(elm); } static void __kho_unpreserve(struct kho_mem_track *track, unsigned long pfn, @@ -167,12 +171,12 @@ static void __kho_unpreserve(struct kho_mem_track *track, unsigned long pfn, const unsigned long pfn_high = pfn >> order; physxa = xa_load(&track->orders, order); - if (!physxa) - continue; + if (WARN_ON_ONCE(!physxa)) + return; bits = xa_load(&physxa->phys_bits, pfn_high / PRESERVE_BITS); - if (!bits) - continue; + if (WARN_ON_ONCE(!bits)) + return; clear_bit(pfn_high % PRESERVE_BITS, bits->preserve); @@ -216,8 +220,7 @@ static int __kho_preserve_order(struct kho_mem_track *track, unsigned long pfn, } } - bits = xa_load_or_alloc(&physxa->phys_bits, pfn_high / PRESERVE_BITS, - sizeof(*bits)); + bits = xa_load_or_alloc(&physxa->phys_bits, pfn_high / PRESERVE_BITS); if (IS_ERR(bits)) return PTR_ERR(bits); @@ -345,15 +348,19 @@ static_assert(sizeof(struct khoser_mem_chunk) == PAGE_SIZE); static struct khoser_mem_chunk *new_chunk(struct khoser_mem_chunk *cur_chunk, unsigned long order) { - struct khoser_mem_chunk *chunk; + struct khoser_mem_chunk *chunk __free(free_page) = NULL; - chunk = kzalloc(PAGE_SIZE, GFP_KERNEL); + chunk = (void *)get_zeroed_page(GFP_KERNEL); if (!chunk) - return NULL; + return ERR_PTR(-ENOMEM); + + if (WARN_ON(kho_scratch_overlap(virt_to_phys(chunk), PAGE_SIZE))) + return ERR_PTR(-EINVAL); + chunk->hdr.order = order; if (cur_chunk) KHOSER_STORE_PTR(cur_chunk->hdr.next, chunk); - return chunk; + return no_free_ptr(chunk); } static void kho_mem_ser_free(struct khoser_mem_chunk *first_chunk) @@ -374,14 +381,17 @@ static int kho_mem_serialize(struct kho_serialization *ser) struct khoser_mem_chunk *chunk = NULL; struct kho_mem_phys *physxa; unsigned long order; + int err = -ENOMEM; xa_for_each(&ser->track.orders, order, physxa) { struct kho_mem_phys_bits *bits; unsigned long phys; chunk = new_chunk(chunk, order); - if (!chunk) + if (IS_ERR(chunk)) { + err = PTR_ERR(chunk); goto err_free; + } if (!first_chunk) first_chunk = chunk; @@ -391,8 +401,10 @@ static int kho_mem_serialize(struct kho_serialization *ser) if (chunk->hdr.num_elms == ARRAY_SIZE(chunk->bitmaps)) { chunk = new_chunk(chunk, order); - if (!chunk) + if (IS_ERR(chunk)) { + err = PTR_ERR(chunk); goto err_free; + } } elm = &chunk->bitmaps[chunk->hdr.num_elms]; @@ -409,7 +421,7 @@ static int kho_mem_serialize(struct kho_serialization *ser) err_free: kho_mem_ser_free(first_chunk); - return -ENOMEM; + return err; } static void __init deserialize_bitmap(unsigned int order, @@ -465,8 +477,8 @@ static void __init kho_mem_deserialize(const void *fdt) * area for early allocations that happen before page allocator is * initialized. */ -static struct kho_scratch *kho_scratch; -static unsigned int kho_scratch_cnt; +struct kho_scratch *kho_scratch; +unsigned int kho_scratch_cnt; /* * The scratch areas are scaled by default as percent of memory allocated from @@ -752,6 +764,9 @@ int kho_preserve_folio(struct folio *folio) const unsigned int order = folio_order(folio); struct kho_mem_track *track = &kho_out.ser.track; + if (WARN_ON(kho_scratch_overlap(pfn << PAGE_SHIFT, PAGE_SIZE << order))) + return -EINVAL; + return __kho_preserve_order(track, pfn, order); } EXPORT_SYMBOL_GPL(kho_preserve_folio); @@ -775,6 +790,11 @@ int kho_preserve_pages(struct page *page, unsigned int nr_pages) unsigned long failed_pfn = 0; int err = 0; + if (WARN_ON(kho_scratch_overlap(start_pfn << PAGE_SHIFT, + nr_pages << PAGE_SHIFT))) { + return -EINVAL; + } + while (pfn < end_pfn) { const unsigned int order = min(count_trailing_zeros(pfn), ilog2(end_pfn - pfn)); @@ -862,16 +882,17 @@ err_free: return NULL; } -static void kho_vmalloc_unpreserve_chunk(struct kho_vmalloc_chunk *chunk) +static void kho_vmalloc_unpreserve_chunk(struct kho_vmalloc_chunk *chunk, + unsigned short order) { struct kho_mem_track *track = &kho_out.ser.track; unsigned long pfn = PHYS_PFN(virt_to_phys(chunk)); __kho_unpreserve(track, pfn, pfn + 1); - for (int i = 0; chunk->phys[i]; i++) { + for (int i = 0; i < ARRAY_SIZE(chunk->phys) && chunk->phys[i]; i++) { pfn = PHYS_PFN(chunk->phys[i]); - __kho_unpreserve(track, pfn, pfn + 1); + __kho_unpreserve(track, pfn, pfn + (1 << order)); } } @@ -882,7 +903,7 @@ static void kho_vmalloc_free_chunks(struct kho_vmalloc *kho_vmalloc) while (chunk) { struct kho_vmalloc_chunk *tmp = chunk; - kho_vmalloc_unpreserve_chunk(chunk); + kho_vmalloc_unpreserve_chunk(chunk, kho_vmalloc->order); chunk = KHOSER_LOAD_PTR(chunk->hdr.next); free_page((unsigned long)tmp); @@ -992,7 +1013,7 @@ void *kho_restore_vmalloc(const struct kho_vmalloc *preservation) while (chunk) { struct page *page; - for (int i = 0; chunk->phys[i]; i++) { + for (int i = 0; i < ARRAY_SIZE(chunk->phys) && chunk->phys[i]; i++) { phys_addr_t phys = chunk->phys[i]; if (idx + contig_pages > total_pages) diff --git a/kernel/kexec_handover_debug.c b/kernel/kexec_handover_debug.c new file mode 100644 index 000000000000..6efb696f5426 --- /dev/null +++ b/kernel/kexec_handover_debug.c @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * kexec_handover_debug.c - kexec handover optional debug functionality + * Copyright (C) 2025 Google LLC, Pasha Tatashin <pasha.tatashin@soleen.com> + */ + +#define pr_fmt(fmt) "KHO: " fmt + +#include "kexec_handover_internal.h" + +bool kho_scratch_overlap(phys_addr_t phys, size_t size) +{ + phys_addr_t scratch_start, scratch_end; + unsigned int i; + + for (i = 0; i < kho_scratch_cnt; i++) { + scratch_start = kho_scratch[i].addr; + scratch_end = kho_scratch[i].addr + kho_scratch[i].size; + + if (phys < scratch_end && (phys + size) > scratch_start) + return true; + } + + return false; +} diff --git a/kernel/kexec_handover_internal.h b/kernel/kexec_handover_internal.h new file mode 100644 index 000000000000..3c3c7148ceed --- /dev/null +++ b/kernel/kexec_handover_internal.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef LINUX_KEXEC_HANDOVER_INTERNAL_H +#define LINUX_KEXEC_HANDOVER_INTERNAL_H + +#include <linux/kexec_handover.h> +#include <linux/types.h> + +extern struct kho_scratch *kho_scratch; +extern unsigned int kho_scratch_cnt; + +#ifdef CONFIG_KEXEC_HANDOVER_DEBUG +bool kho_scratch_overlap(phys_addr_t phys, size_t size); +#else +static inline bool kho_scratch_overlap(phys_addr_t phys, size_t size) +{ + return false; +} +#endif /* CONFIG_KEXEC_HANDOVER_DEBUG */ + +#endif /* LINUX_KEXEC_HANDOVER_INTERNAL_H */ diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 0beff7eeaaba..70ae21f7370d 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -635,7 +635,7 @@ struct cmp_data { }; /* Indicates the image size after compression */ -static atomic_t compressed_size = ATOMIC_INIT(0); +static atomic64_t compressed_size = ATOMIC_INIT(0); /* * Compression function that runs in its own thread. @@ -664,7 +664,7 @@ static int compress_threadfn(void *data) d->ret = crypto_acomp_compress(d->cr); d->cmp_len = d->cr->dlen; - atomic_set(&compressed_size, atomic_read(&compressed_size) + d->cmp_len); + atomic64_add(d->cmp_len, &compressed_size); atomic_set_release(&d->stop, 1); wake_up(&d->done); } @@ -689,14 +689,14 @@ static int save_compressed_image(struct swap_map_handle *handle, ktime_t start; ktime_t stop; size_t off; - unsigned thr, run_threads, nr_threads; + unsigned int thr, run_threads, nr_threads; unsigned char *page = NULL; struct cmp_data *data = NULL; struct crc_data *crc = NULL; hib_init_batch(&hb); - atomic_set(&compressed_size, 0); + atomic64_set(&compressed_size, 0); /* * We'll limit the number of threads for compression to limit memory @@ -877,11 +877,14 @@ out_finish: stop = ktime_get(); if (!ret) ret = err2; - if (!ret) + if (!ret) { + swsusp_show_speed(start, stop, nr_to_write, "Wrote"); + pr_info("Image size after compression: %lld kbytes\n", + (atomic64_read(&compressed_size) / 1024)); pr_info("Image saving done\n"); - swsusp_show_speed(start, stop, nr_to_write, "Wrote"); - pr_info("Image size after compression: %d kbytes\n", - (atomic_read(&compressed_size) / 1024)); + } else { + pr_err("Image saving failed: %d\n", ret); + } out_clean: hib_finish_batch(&hb); @@ -899,7 +902,8 @@ out_clean: } vfree(data); } - if (page) free_page((unsigned long)page); + if (page) + free_page((unsigned long)page); return ret; } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f1ebf67b48e2..f754a60de848 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -9606,7 +9606,7 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, guard(rq_lock_irq)(rq); cfs_rq->runtime_enabled = runtime_enabled; - cfs_rq->runtime_remaining = 0; + cfs_rq->runtime_remaining = 1; if (cfs_rq->throttled) unthrottle_cfs_rq(cfs_rq); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 25970dbbb279..5b752324270b 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6024,20 +6024,17 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) struct sched_entity *se = cfs_rq->tg->se[cpu_of(rq)]; /* - * It's possible we are called with !runtime_remaining due to things - * like user changed quota setting(see tg_set_cfs_bandwidth()) or async - * unthrottled us with a positive runtime_remaining but other still - * running entities consumed those runtime before we reached here. + * It's possible we are called with runtime_remaining < 0 due to things + * like async unthrottled us with a positive runtime_remaining but other + * still running entities consumed those runtime before we reached here. * - * Anyway, we can't unthrottle this cfs_rq without any runtime remaining - * because any enqueue in tg_unthrottle_up() will immediately trigger a - * throttle, which is not supposed to happen on unthrottle path. + * We can't unthrottle this cfs_rq without any runtime remaining because + * any enqueue in tg_unthrottle_up() will immediately trigger a throttle, + * which is not supposed to happen on unthrottle path. */ if (cfs_rq->runtime_enabled && cfs_rq->runtime_remaining <= 0) return; - se = cfs_rq->tg->se[cpu_of(rq)]; - cfs_rq->throttled = 0; update_rq_clock(rq); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 1244d2c5c384..afcd3747264d 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -7344,6 +7344,10 @@ consume: goto out; } + /* Did the reader catch up with the writer? */ + if (cpu_buffer->reader_page == cpu_buffer->commit_page) + goto out; + reader = rb_get_reader_page(cpu_buffer); if (WARN_ON(!reader)) goto out; diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 1d536219b624..6bfaf1210dd2 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -3272,14 +3272,16 @@ static struct field_var *create_field_var(struct hist_trigger_data *hist_data, var = create_var(hist_data, file, field_name, val->size, val->type); if (IS_ERR(var)) { hist_err(tr, HIST_ERR_VAR_CREATE_FIND_FAIL, errpos(field_name)); - kfree(val); + destroy_hist_field(val, 0); ret = PTR_ERR(var); goto err; } field_var = kzalloc(sizeof(struct field_var), GFP_KERNEL); if (!field_var) { - kfree(val); + destroy_hist_field(val, 0); + kfree_const(var->type); + kfree(var->var.name); kfree(var); ret = -ENOMEM; goto err; diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c index ad9d6347b5fa..8001dbf16891 100644 --- a/kernel/trace/trace_fprobe.c +++ b/kernel/trace/trace_fprobe.c @@ -106,13 +106,14 @@ static struct tracepoint_user *__tracepoint_user_init(const char *name, struct t if (!tuser->name) return NULL; + /* Register tracepoint if it is loaded. */ if (tpoint) { + tuser->tpoint = tpoint; ret = tracepoint_user_register(tuser); if (ret) return ERR_PTR(ret); } - tuser->tpoint = tpoint; tuser->refcount = 1; INIT_LIST_HEAD(&tuser->list); list_add(&tuser->list, &tracepoint_user_list); @@ -1513,6 +1514,10 @@ static int disable_trace_fprobe(struct trace_event_call *call, if (!trace_probe_is_enabled(tp)) { list_for_each_entry(tf, trace_probe_probe_list(tp), tp.list) { unregister_fprobe(&tf->fp); + if (tf->tuser) { + tracepoint_user_put(tf->tuser); + tf->tuser = NULL; + } } } diff --git a/lib/crypto/Kconfig b/lib/crypto/Kconfig index 8886055e938f..16859c6226dd 100644 --- a/lib/crypto/Kconfig +++ b/lib/crypto/Kconfig @@ -64,7 +64,7 @@ config CRYPTO_LIB_CURVE25519 config CRYPTO_LIB_CURVE25519_ARCH bool depends on CRYPTO_LIB_CURVE25519 && !UML && !KMSAN - default y if ARM && KERNEL_MODE_NEON + default y if ARM && KERNEL_MODE_NEON && !CPU_BIG_ENDIAN default y if PPC64 && CPU_LITTLE_ENDIAN default y if X86_64 diff --git a/lib/crypto/Makefile b/lib/crypto/Makefile index bded351aeace..d2845b214585 100644 --- a/lib/crypto/Makefile +++ b/lib/crypto/Makefile @@ -90,7 +90,7 @@ else libcurve25519-$(CONFIG_CRYPTO_LIB_CURVE25519_GENERIC) += curve25519-fiat32.o endif # clang versions prior to 18 may blow out the stack with KASAN -ifeq ($(call clang-min-version, 180000),) +ifeq ($(CONFIG_CC_IS_CLANG)_$(call clang-min-version, 180000),y_) KASAN_SANITIZE_curve25519-hacl64.o := n endif diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 39bb779cb311..5aa4c9500018 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -64,6 +64,8 @@ #define CREATE_TRACE_POINTS #include <trace/events/maple_tree.h> +#define TP_FCT tracepoint_string(__func__) + /* * Kernel pointer hashing renders much of the maple tree dump useless as tagged * pointers get hashed to arbitrary values. @@ -2756,7 +2758,7 @@ static inline void mas_rebalance(struct ma_state *mas, MA_STATE(l_mas, mas->tree, mas->index, mas->last); MA_STATE(r_mas, mas->tree, mas->index, mas->last); - trace_ma_op(__func__, mas); + trace_ma_op(TP_FCT, mas); /* * Rebalancing occurs if a node is insufficient. Data is rebalanced @@ -2997,7 +2999,7 @@ static void mas_split(struct ma_state *mas, struct maple_big_node *b_node) MA_STATE(prev_l_mas, mas->tree, mas->index, mas->last); MA_STATE(prev_r_mas, mas->tree, mas->index, mas->last); - trace_ma_op(__func__, mas); + trace_ma_op(TP_FCT, mas); mast.l = &l_mas; mast.r = &r_mas; @@ -3172,7 +3174,7 @@ static bool mas_is_span_wr(struct ma_wr_state *wr_mas) return false; } - trace_ma_write(__func__, wr_mas->mas, wr_mas->r_max, entry); + trace_ma_write(TP_FCT, wr_mas->mas, wr_mas->r_max, entry); return true; } @@ -3416,7 +3418,7 @@ static noinline void mas_wr_spanning_store(struct ma_wr_state *wr_mas) * of data may happen. */ mas = wr_mas->mas; - trace_ma_op(__func__, mas); + trace_ma_op(TP_FCT, mas); if (unlikely(!mas->index && mas->last == ULONG_MAX)) return mas_new_root(mas, wr_mas->entry); @@ -3552,7 +3554,7 @@ done: } else { memcpy(wr_mas->node, newnode, sizeof(struct maple_node)); } - trace_ma_write(__func__, mas, 0, wr_mas->entry); + trace_ma_write(TP_FCT, mas, 0, wr_mas->entry); mas_update_gap(mas); mas->end = new_end; return; @@ -3596,7 +3598,7 @@ static inline void mas_wr_slot_store(struct ma_wr_state *wr_mas) mas->offset++; /* Keep mas accurate. */ } - trace_ma_write(__func__, mas, 0, wr_mas->entry); + trace_ma_write(TP_FCT, mas, 0, wr_mas->entry); /* * Only update gap when the new entry is empty or there is an empty * entry in the original two ranges. @@ -3717,7 +3719,7 @@ static inline void mas_wr_append(struct ma_wr_state *wr_mas, mas_update_gap(mas); mas->end = new_end; - trace_ma_write(__func__, mas, new_end, wr_mas->entry); + trace_ma_write(TP_FCT, mas, new_end, wr_mas->entry); return; } @@ -3731,7 +3733,7 @@ static void mas_wr_bnode(struct ma_wr_state *wr_mas) { struct maple_big_node b_node; - trace_ma_write(__func__, wr_mas->mas, 0, wr_mas->entry); + trace_ma_write(TP_FCT, wr_mas->mas, 0, wr_mas->entry); memset(&b_node, 0, sizeof(struct maple_big_node)); mas_store_b_node(wr_mas, &b_node, wr_mas->offset_end); mas_commit_b_node(wr_mas, &b_node); @@ -5062,7 +5064,7 @@ void *mas_store(struct ma_state *mas, void *entry) { MA_WR_STATE(wr_mas, mas, entry); - trace_ma_write(__func__, mas, 0, entry); + trace_ma_write(TP_FCT, mas, 0, entry); #ifdef CONFIG_DEBUG_MAPLE_TREE if (MAS_WARN_ON(mas, mas->index > mas->last)) pr_err("Error %lX > %lX " PTR_FMT "\n", mas->index, mas->last, @@ -5163,7 +5165,7 @@ void mas_store_prealloc(struct ma_state *mas, void *entry) } store: - trace_ma_write(__func__, mas, 0, entry); + trace_ma_write(TP_FCT, mas, 0, entry); mas_wr_store_entry(&wr_mas); MAS_WR_BUG_ON(&wr_mas, mas_is_err(mas)); mas_destroy(mas); @@ -5882,7 +5884,7 @@ void *mtree_load(struct maple_tree *mt, unsigned long index) MA_STATE(mas, mt, index, index); void *entry; - trace_ma_read(__func__, &mas); + trace_ma_read(TP_FCT, &mas); rcu_read_lock(); retry: entry = mas_start(&mas); @@ -5925,7 +5927,7 @@ int mtree_store_range(struct maple_tree *mt, unsigned long index, MA_STATE(mas, mt, index, last); int ret = 0; - trace_ma_write(__func__, &mas, 0, entry); + trace_ma_write(TP_FCT, &mas, 0, entry); if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; @@ -6148,7 +6150,7 @@ void *mtree_erase(struct maple_tree *mt, unsigned long index) void *entry = NULL; MA_STATE(mas, mt, index, index); - trace_ma_op(__func__, &mas); + trace_ma_op(TP_FCT, &mas); mtree_lock(mt); entry = mas_erase(&mas); @@ -6485,7 +6487,7 @@ void *mt_find(struct maple_tree *mt, unsigned long *index, unsigned long max) unsigned long copy = *index; #endif - trace_ma_read(__func__, &mas); + trace_ma_read(TP_FCT, &mas); if ((*index) > max) return NULL; diff --git a/mm/damon/stat.c b/mm/damon/stat.c index d8010968bbed..bf8626859902 100644 --- a/mm/damon/stat.c +++ b/mm/damon/stat.c @@ -46,6 +46,8 @@ MODULE_PARM_DESC(aggr_interval_us, static struct damon_ctx *damon_stat_context; +static unsigned long damon_stat_last_refresh_jiffies; + static void damon_stat_set_estimated_memory_bandwidth(struct damon_ctx *c) { struct damon_target *t; @@ -130,13 +132,12 @@ static void damon_stat_set_idletime_percentiles(struct damon_ctx *c) static int damon_stat_damon_call_fn(void *data) { struct damon_ctx *c = data; - static unsigned long last_refresh_jiffies; /* avoid unnecessarily frequent stat update */ - if (time_before_eq(jiffies, last_refresh_jiffies + + if (time_before_eq(jiffies, damon_stat_last_refresh_jiffies + msecs_to_jiffies(5 * MSEC_PER_SEC))) return 0; - last_refresh_jiffies = jiffies; + damon_stat_last_refresh_jiffies = jiffies; aggr_interval_us = c->attrs.aggr_interval; damon_stat_set_estimated_memory_bandwidth(c); @@ -210,6 +211,8 @@ static int damon_stat_start(void) err = damon_start(&damon_stat_context, 1, true); if (err) return err; + + damon_stat_last_refresh_jiffies = jiffies; call_control.data = damon_stat_context; return damon_call(damon_stat_context, &call_control); } diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c index cd6815ecc04e..3c0d727788c8 100644 --- a/mm/damon/sysfs.c +++ b/mm/damon/sysfs.c @@ -1552,16 +1552,17 @@ static struct damon_ctx *damon_sysfs_build_ctx( return ctx; } +static unsigned long damon_sysfs_next_update_jiffies; + static int damon_sysfs_repeat_call_fn(void *data) { struct damon_sysfs_kdamond *sysfs_kdamond = data; - static unsigned long next_update_jiffies; if (!sysfs_kdamond->refresh_ms) return 0; - if (time_before(jiffies, next_update_jiffies)) + if (time_before(jiffies, damon_sysfs_next_update_jiffies)) return 0; - next_update_jiffies = jiffies + + damon_sysfs_next_update_jiffies = jiffies + msecs_to_jiffies(sysfs_kdamond->refresh_ms); if (!mutex_trylock(&damon_sysfs_lock)) @@ -1607,6 +1608,9 @@ static int damon_sysfs_turn_damon_on(struct damon_sysfs_kdamond *kdamond) } kdamond->damon_ctx = ctx; + damon_sysfs_next_update_jiffies = + jiffies + msecs_to_jiffies(kdamond->refresh_ms); + repeat_call_control->fn = damon_sysfs_repeat_call_fn; repeat_call_control->data = kdamond; repeat_call_control->repeat = true; diff --git a/mm/filemap.c b/mm/filemap.c index 13f0259d993c..2f1e7e283a51 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3681,7 +3681,8 @@ skip: static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf, struct folio *folio, unsigned long start, unsigned long addr, unsigned int nr_pages, - unsigned long *rss, unsigned short *mmap_miss) + unsigned long *rss, unsigned short *mmap_miss, + bool can_map_large) { unsigned int ref_from_caller = 1; vm_fault_t ret = 0; @@ -3696,7 +3697,7 @@ static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf, * The folio must not cross VMA or page table boundary. */ addr0 = addr - start * PAGE_SIZE; - if (folio_within_vma(folio, vmf->vma) && + if (can_map_large && folio_within_vma(folio, vmf->vma) && (addr0 & PMD_MASK) == ((addr0 + folio_size(folio) - 1) & PMD_MASK)) { vmf->pte -= start; page -= start; @@ -3811,13 +3812,27 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf, unsigned long rss = 0; unsigned int nr_pages = 0, folio_type; unsigned short mmap_miss = 0, mmap_miss_saved; + bool can_map_large; rcu_read_lock(); folio = next_uptodate_folio(&xas, mapping, end_pgoff); if (!folio) goto out; - if (filemap_map_pmd(vmf, folio, start_pgoff)) { + file_end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE) - 1; + end_pgoff = min(end_pgoff, file_end); + + /* + * Do not allow to map with PTEs beyond i_size and with PMD + * across i_size to preserve SIGBUS semantics. + * + * Make an exception for shmem/tmpfs that for long time + * intentionally mapped with PMDs across i_size. + */ + can_map_large = shmem_mapping(mapping) || + file_end >= folio_next_index(folio); + + if (can_map_large && filemap_map_pmd(vmf, folio, start_pgoff)) { ret = VM_FAULT_NOPAGE; goto out; } @@ -3830,10 +3845,6 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf, goto out; } - file_end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE) - 1; - if (end_pgoff > file_end) - end_pgoff = file_end; - folio_type = mm_counter_file(folio); do { unsigned long end; @@ -3850,7 +3861,8 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf, else ret |= filemap_map_folio_range(vmf, folio, xas.xa_index - folio->index, addr, - nr_pages, &rss, &mmap_miss); + nr_pages, &rss, &mmap_miss, + can_map_large); folio_unlock(folio); } while ((folio = next_uptodate_folio(&xas, mapping, end_pgoff)) != NULL); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 1d1b74950332..323654fb4f8c 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -214,7 +214,8 @@ retry: if (likely(atomic_inc_not_zero(&huge_zero_refcount))) return true; - zero_folio = folio_alloc((GFP_TRANSHUGE | __GFP_ZERO) & ~__GFP_MOVABLE, + zero_folio = folio_alloc((GFP_TRANSHUGE | __GFP_ZERO | __GFP_ZEROTAGS) & + ~__GFP_MOVABLE, HPAGE_PMD_ORDER); if (!zero_folio) { count_vm_event(THP_ZERO_PAGE_ALLOC_FAILED); @@ -3263,6 +3264,14 @@ bool can_split_folio(struct folio *folio, int caller_pins, int *pextra_pins) caller_pins; } +static bool page_range_has_hwpoisoned(struct page *page, long nr_pages) +{ + for (; nr_pages; page++, nr_pages--) + if (PageHWPoison(page)) + return true; + return false; +} + /* * It splits @folio into @new_order folios and copies the @folio metadata to * all the resulting folios. @@ -3270,17 +3279,24 @@ bool can_split_folio(struct folio *folio, int caller_pins, int *pextra_pins) static void __split_folio_to_order(struct folio *folio, int old_order, int new_order) { + /* Scan poisoned pages when split a poisoned folio to large folios */ + const bool handle_hwpoison = folio_test_has_hwpoisoned(folio) && new_order; long new_nr_pages = 1 << new_order; long nr_pages = 1 << old_order; long i; + folio_clear_has_hwpoisoned(folio); + + /* Check first new_nr_pages since the loop below skips them */ + if (handle_hwpoison && + page_range_has_hwpoisoned(folio_page(folio, 0), new_nr_pages)) + folio_set_has_hwpoisoned(folio); /* * Skip the first new_nr_pages, since the new folio from them have all * the flags from the original folio. */ for (i = new_nr_pages; i < nr_pages; i += new_nr_pages) { struct page *new_head = &folio->page + i; - /* * Careful: new_folio is not a "real" folio before we cleared PageTail. * Don't pass it around before clear_compound_head(). @@ -3322,6 +3338,10 @@ static void __split_folio_to_order(struct folio *folio, int old_order, (1L << PG_dirty) | LRU_GEN_MASK | LRU_REFS_MASK)); + if (handle_hwpoison && + page_range_has_hwpoisoned(new_head, new_nr_pages)) + folio_set_has_hwpoisoned(new_folio); + new_folio->mapping = folio->mapping; new_folio->index = folio->index + i; @@ -3422,8 +3442,6 @@ static int __split_unmapped_folio(struct folio *folio, int new_order, if (folio_test_anon(folio)) mod_mthp_stat(order, MTHP_STAT_NR_ANON, -1); - folio_clear_has_hwpoisoned(folio); - /* * split to new_order one order at a time. For uniform split, * folio is split to new_order directly. @@ -3653,8 +3671,6 @@ static int __folio_split(struct folio *folio, unsigned int new_order, min_order = mapping_min_folio_order(folio->mapping); if (new_order < min_order) { - VM_WARN_ONCE(1, "Cannot split mapped folio below min-order: %u", - min_order); ret = -EINVAL; goto out; } @@ -3986,12 +4002,7 @@ int min_order_for_split(struct folio *folio) int split_folio_to_list(struct folio *folio, struct list_head *list) { - int ret = min_order_for_split(folio); - - if (ret < 0) - return ret; - - return split_huge_page_to_list_to_order(&folio->page, list, ret); + return split_huge_page_to_list_to_order(&folio->page, list, 0); } /* diff --git a/mm/kmsan/core.c b/mm/kmsan/core.c index 8bca7fece47f..35ceaa8adb41 100644 --- a/mm/kmsan/core.c +++ b/mm/kmsan/core.c @@ -72,9 +72,6 @@ depot_stack_handle_t kmsan_save_stack_with_flags(gfp_t flags, nr_entries = stack_trace_save(entries, KMSAN_STACK_DEPTH, 0); - /* Don't sleep. */ - flags &= ~(__GFP_DIRECT_RECLAIM | __GFP_KSWAPD_RECLAIM); - handle = stack_depot_save(entries, nr_entries, flags); return stack_depot_set_extra_bits(handle, extra); } diff --git a/mm/kmsan/hooks.c b/mm/kmsan/hooks.c index 2cee59d89c80..8f22d1f22981 100644 --- a/mm/kmsan/hooks.c +++ b/mm/kmsan/hooks.c @@ -84,7 +84,8 @@ void kmsan_slab_free(struct kmem_cache *s, void *object) if (s->ctor) return; kmsan_enter_runtime(); - kmsan_internal_poison_memory(object, s->object_size, GFP_KERNEL, + kmsan_internal_poison_memory(object, s->object_size, + GFP_KERNEL & ~(__GFP_RECLAIM), KMSAN_POISON_CHECK | KMSAN_POISON_FREE); kmsan_leave_runtime(); } @@ -114,7 +115,8 @@ void kmsan_kfree_large(const void *ptr) kmsan_enter_runtime(); page = virt_to_head_page((void *)ptr); KMSAN_WARN_ON(ptr != page_address(page)); - kmsan_internal_poison_memory((void *)ptr, page_size(page), GFP_KERNEL, + kmsan_internal_poison_memory((void *)ptr, page_size(page), + GFP_KERNEL & ~(__GFP_RECLAIM), KMSAN_POISON_CHECK | KMSAN_POISON_FREE); kmsan_leave_runtime(); } diff --git a/mm/kmsan/shadow.c b/mm/kmsan/shadow.c index 54f3c3c962f0..55fdea199aaf 100644 --- a/mm/kmsan/shadow.c +++ b/mm/kmsan/shadow.c @@ -208,7 +208,7 @@ void kmsan_free_page(struct page *page, unsigned int order) return; kmsan_enter_runtime(); kmsan_internal_poison_memory(page_address(page), page_size(page), - GFP_KERNEL, + GFP_KERNEL & ~(__GFP_RECLAIM), KMSAN_POISON_CHECK | KMSAN_POISON_FREE); kmsan_leave_runtime(); } @@ -2455,6 +2455,95 @@ static bool should_skip_rmap_item(struct folio *folio, return true; } +struct ksm_next_page_arg { + struct folio *folio; + struct page *page; + unsigned long addr; +}; + +static int ksm_next_page_pmd_entry(pmd_t *pmdp, unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + struct ksm_next_page_arg *private = walk->private; + struct vm_area_struct *vma = walk->vma; + pte_t *start_ptep = NULL, *ptep, pte; + struct mm_struct *mm = walk->mm; + struct folio *folio; + struct page *page; + spinlock_t *ptl; + pmd_t pmd; + + if (ksm_test_exit(mm)) + return 0; + + cond_resched(); + + pmd = pmdp_get_lockless(pmdp); + if (!pmd_present(pmd)) + return 0; + + if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && pmd_leaf(pmd)) { + ptl = pmd_lock(mm, pmdp); + pmd = pmdp_get(pmdp); + + if (!pmd_present(pmd)) { + goto not_found_unlock; + } else if (pmd_leaf(pmd)) { + page = vm_normal_page_pmd(vma, addr, pmd); + if (!page) + goto not_found_unlock; + folio = page_folio(page); + + if (folio_is_zone_device(folio) || !folio_test_anon(folio)) + goto not_found_unlock; + + page += ((addr & (PMD_SIZE - 1)) >> PAGE_SHIFT); + goto found_unlock; + } + spin_unlock(ptl); + } + + start_ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl); + if (!start_ptep) + return 0; + + for (ptep = start_ptep; addr < end; ptep++, addr += PAGE_SIZE) { + pte = ptep_get(ptep); + + if (!pte_present(pte)) + continue; + + page = vm_normal_page(vma, addr, pte); + if (!page) + continue; + folio = page_folio(page); + + if (folio_is_zone_device(folio) || !folio_test_anon(folio)) + continue; + goto found_unlock; + } + +not_found_unlock: + spin_unlock(ptl); + if (start_ptep) + pte_unmap(start_ptep); + return 0; +found_unlock: + folio_get(folio); + spin_unlock(ptl); + if (start_ptep) + pte_unmap(start_ptep); + private->page = page; + private->folio = folio; + private->addr = addr; + return 1; +} + +static struct mm_walk_ops ksm_next_page_ops = { + .pmd_entry = ksm_next_page_pmd_entry, + .walk_lock = PGWALK_RDLOCK, +}; + static struct ksm_rmap_item *scan_get_next_rmap_item(struct page **page) { struct mm_struct *mm; @@ -2542,21 +2631,27 @@ next_mm: ksm_scan.address = vma->vm_end; while (ksm_scan.address < vma->vm_end) { + struct ksm_next_page_arg ksm_next_page_arg; struct page *tmp_page = NULL; - struct folio_walk fw; struct folio *folio; if (ksm_test_exit(mm)) break; - folio = folio_walk_start(&fw, vma, ksm_scan.address, 0); - if (folio) { - if (!folio_is_zone_device(folio) && - folio_test_anon(folio)) { - folio_get(folio); - tmp_page = fw.page; - } - folio_walk_end(&fw, vma); + int found; + + found = walk_page_range_vma(vma, ksm_scan.address, + vma->vm_end, + &ksm_next_page_ops, + &ksm_next_page_arg); + + if (found > 0) { + folio = ksm_next_page_arg.folio; + tmp_page = ksm_next_page_arg.page; + ksm_scan.address = ksm_next_page_arg.addr; + } else { + VM_WARN_ON_ONCE(found < 0); + ksm_scan.address = vma->vm_end - PAGE_SIZE; } if (tmp_page) { diff --git a/mm/memory.c b/mm/memory.c index 74b45e258323..b59ae7ce42eb 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -65,6 +65,7 @@ #include <linux/gfp.h> #include <linux/migrate.h> #include <linux/string.h> +#include <linux/shmem_fs.h> #include <linux/memory-tiers.h> #include <linux/debugfs.h> #include <linux/userfaultfd_k.h> @@ -5501,8 +5502,25 @@ fallback: return ret; } + if (!needs_fallback && vma->vm_file) { + struct address_space *mapping = vma->vm_file->f_mapping; + pgoff_t file_end; + + file_end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE); + + /* + * Do not allow to map with PTEs beyond i_size and with PMD + * across i_size to preserve SIGBUS semantics. + * + * Make an exception for shmem/tmpfs that for long time + * intentionally mapped with PMDs across i_size. + */ + needs_fallback = !shmem_mapping(mapping) && + file_end < folio_next_index(folio); + } + if (pmd_none(*vmf->pmd)) { - if (folio_test_pmd_mappable(folio)) { + if (!needs_fallback && folio_test_pmd_mappable(folio)) { ret = do_set_pmd(vmf, folio, page); if (ret != VM_FAULT_FALLBACK) return ret; diff --git a/mm/mm_init.c b/mm/mm_init.c index 3db2dea7db4c..7712d887b696 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -2469,7 +2469,7 @@ void *__init alloc_large_system_hash(const char *tablename, panic("Failed to allocate %s hash table\n", tablename); pr_info("%s hash table entries: %ld (order: %d, %lu bytes, %s)\n", - tablename, 1UL << log2qty, ilog2(size) - PAGE_SHIFT, size, + tablename, 1UL << log2qty, get_order(size), size, virt ? (huge ? "vmalloc hugepage" : "vmalloc") : "linear"); if (_hash_shift) diff --git a/mm/mremap.c b/mm/mremap.c index bd7314898ec5..419a0ea0a870 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -187,7 +187,7 @@ static int mremap_folio_pte_batch(struct vm_area_struct *vma, unsigned long addr if (!folio || !folio_test_large(folio)) return 1; - return folio_pte_batch(folio, ptep, pte, max_nr); + return folio_pte_batch_flags(folio, NULL, ptep, &pte, max_nr, FPB_RESPECT_WRITE); } static int move_ptes(struct pagetable_move_control *pmc, diff --git a/mm/secretmem.c b/mm/secretmem.c index 60137305bc20..b59350daffe3 100644 --- a/mm/secretmem.c +++ b/mm/secretmem.c @@ -82,13 +82,13 @@ retry: __folio_mark_uptodate(folio); err = filemap_add_folio(mapping, folio, offset, gfp); if (unlikely(err)) { - folio_put(folio); /* * If a split of large page was required, it * already happened when we marked the page invalid * which guarantees that this call won't fail */ set_direct_map_default_noflush(folio_page(folio, 0)); + folio_put(folio); if (err == -EEXIST) goto retry; diff --git a/mm/shmem.c b/mm/shmem.c index b9081b817d28..58701d14dd96 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1882,6 +1882,7 @@ static struct folio *shmem_alloc_and_add_folio(struct vm_fault *vmf, struct shmem_inode_info *info = SHMEM_I(inode); unsigned long suitable_orders = 0; struct folio *folio = NULL; + pgoff_t aligned_index; long pages; int error, order; @@ -1895,10 +1896,12 @@ static struct folio *shmem_alloc_and_add_folio(struct vm_fault *vmf, order = highest_order(suitable_orders); while (suitable_orders) { pages = 1UL << order; - index = round_down(index, pages); - folio = shmem_alloc_folio(gfp, order, info, index); - if (folio) + aligned_index = round_down(index, pages); + folio = shmem_alloc_folio(gfp, order, info, aligned_index); + if (folio) { + index = aligned_index; goto allocated; + } if (pages == HPAGE_PMD_NR) count_vm_event(THP_FILE_FALLBACK); diff --git a/mm/slub.c b/mm/slub.c index d4367f25b20d..a0b905c2a557 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2046,7 +2046,11 @@ static inline void mark_objexts_empty(struct slabobj_ext *obj_exts) if (slab_exts) { unsigned int offs = obj_to_index(obj_exts_slab->slab_cache, obj_exts_slab, obj_exts); - /* codetag should be NULL */ + + if (unlikely(is_codetag_empty(&slab_exts[offs].ref))) + return; + + /* codetag should be NULL here */ WARN_ON(slab_exts[offs].ref.ct); set_codetag_empty(&slab_exts[offs].ref); } @@ -4666,8 +4670,12 @@ new_objects: if (kmem_cache_debug(s)) { freelist = alloc_single_from_new_slab(s, slab, orig_size, gfpflags); - if (unlikely(!freelist)) + if (unlikely(!freelist)) { + /* This could cause an endless loop. Fail instead. */ + if (!allow_spin) + return NULL; goto new_objects; + } if (s->flags & SLAB_STORE_USER) set_track(s, freelist, TRACK_ALLOC, addr, @@ -6328,8 +6336,6 @@ next_remote_batch: if (unlikely(!slab_free_hook(s, p[i], init, false))) { p[i] = p[--size]; - if (!size) - goto flush_remote; continue; } @@ -6344,6 +6350,9 @@ next_remote_batch: i++; } + if (!size) + goto flush_remote; + next_batch: if (!local_trylock(&s->cpu_sheaves->lock)) goto fallback; @@ -6398,6 +6407,9 @@ do_free: goto next_batch; } + if (remote_nr) + goto flush_remote; + return; no_empty: diff --git a/mm/truncate.c b/mm/truncate.c index 91eb92a5ce4f..3c5a50ae3274 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -177,6 +177,32 @@ int truncate_inode_folio(struct address_space *mapping, struct folio *folio) return 0; } +static int try_folio_split_or_unmap(struct folio *folio, struct page *split_at, + unsigned long min_order) +{ + enum ttu_flags ttu_flags = + TTU_SYNC | + TTU_SPLIT_HUGE_PMD | + TTU_IGNORE_MLOCK; + int ret; + + ret = try_folio_split_to_order(folio, split_at, min_order); + + /* + * If the split fails, unmap the folio, so it will be refaulted + * with PTEs to respect SIGBUS semantics. + * + * Make an exception for shmem/tmpfs that for long time + * intentionally mapped with PMDs across i_size. + */ + if (ret && !shmem_mapping(folio->mapping)) { + try_to_unmap(folio, ttu_flags); + WARN_ON(folio_mapped(folio)); + } + + return ret; +} + /* * Handle partial folios. The folio may be entirely within the * range if a split has raced with us. If not, we zero the part of the @@ -194,6 +220,7 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end) size_t size = folio_size(folio); unsigned int offset, length; struct page *split_at, *split_at2; + unsigned int min_order; if (pos < start) offset = start - pos; @@ -223,8 +250,9 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end) if (!folio_test_large(folio)) return true; + min_order = mapping_min_folio_order(folio->mapping); split_at = folio_page(folio, PAGE_ALIGN_DOWN(offset) / PAGE_SIZE); - if (!try_folio_split(folio, split_at, NULL)) { + if (!try_folio_split_or_unmap(folio, split_at, min_order)) { /* * try to split at offset + length to make sure folios within * the range can be dropped, especially to avoid memory waste @@ -248,13 +276,10 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end) if (!folio_trylock(folio2)) goto out; - /* - * make sure folio2 is large and does not change its mapping. - * Its split result does not matter here. - */ + /* make sure folio2 is large and does not change its mapping */ if (folio_test_large(folio2) && folio2->mapping == folio->mapping) - try_folio_split(folio2, split_at2, NULL); + try_folio_split_or_unmap(folio2, split_at2, min_order); folio_unlock(folio2); out: diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index fda3a80e9340..2b74ed56eb16 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -193,6 +193,8 @@ int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack) vlan_group_set_device(grp, vlan->vlan_proto, vlan_id, dev); grp->nr_vlan_devs++; + netdev_update_features(dev); + return 0; out_unregister_netdev: diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index f0c862091bff..2c21ae8abadc 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -53,6 +53,11 @@ static bool enable_6lowpan; static struct l2cap_chan *listen_chan; static DEFINE_MUTEX(set_lock); +enum { + LOWPAN_PEER_CLOSING, + LOWPAN_PEER_MAXBITS +}; + struct lowpan_peer { struct list_head list; struct rcu_head rcu; @@ -61,6 +66,8 @@ struct lowpan_peer { /* peer addresses in various formats */ unsigned char lladdr[ETH_ALEN]; struct in6_addr peer_addr; + + DECLARE_BITMAP(flags, LOWPAN_PEER_MAXBITS); }; struct lowpan_btle_dev { @@ -289,6 +296,7 @@ static int recv_pkt(struct sk_buff *skb, struct net_device *dev, local_skb->pkt_type = PACKET_HOST; local_skb->dev = dev; + skb_reset_mac_header(local_skb); skb_set_transport_header(local_skb, sizeof(struct ipv6hdr)); if (give_skb_to_upper(local_skb, dev) != NET_RX_SUCCESS) { @@ -919,7 +927,9 @@ static int bt_6lowpan_disconnect(struct l2cap_conn *conn, u8 dst_type) BT_DBG("peer %p chan %p", peer, peer->chan); + l2cap_chan_lock(peer->chan); l2cap_chan_close(peer->chan, ENOENT); + l2cap_chan_unlock(peer->chan); return 0; } @@ -956,10 +966,11 @@ static struct l2cap_chan *bt_6lowpan_listen(void) } static int get_l2cap_conn(char *buf, bdaddr_t *addr, u8 *addr_type, - struct l2cap_conn **conn) + struct l2cap_conn **conn, bool disconnect) { struct hci_conn *hcon; struct hci_dev *hdev; + int le_addr_type; int n; n = sscanf(buf, "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx %hhu", @@ -970,13 +981,32 @@ static int get_l2cap_conn(char *buf, bdaddr_t *addr, u8 *addr_type, if (n < 7) return -EINVAL; + if (disconnect) { + /* The "disconnect" debugfs command has used different address + * type constants than "connect" since 2015. Let's retain that + * for now even though it's obviously buggy... + */ + *addr_type += 1; + } + + switch (*addr_type) { + case BDADDR_LE_PUBLIC: + le_addr_type = ADDR_LE_DEV_PUBLIC; + break; + case BDADDR_LE_RANDOM: + le_addr_type = ADDR_LE_DEV_RANDOM; + break; + default: + return -EINVAL; + } + /* The LE_PUBLIC address type is ignored because of BDADDR_ANY */ hdev = hci_get_route(addr, BDADDR_ANY, BDADDR_LE_PUBLIC); if (!hdev) return -ENOENT; hci_dev_lock(hdev); - hcon = hci_conn_hash_lookup_le(hdev, addr, *addr_type); + hcon = hci_conn_hash_lookup_le(hdev, addr, le_addr_type); hci_dev_unlock(hdev); hci_dev_put(hdev); @@ -993,41 +1023,52 @@ static int get_l2cap_conn(char *buf, bdaddr_t *addr, u8 *addr_type, static void disconnect_all_peers(void) { struct lowpan_btle_dev *entry; - struct lowpan_peer *peer, *tmp_peer, *new_peer; - struct list_head peers; - - INIT_LIST_HEAD(&peers); + struct lowpan_peer *peer; + int nchans; - /* We make a separate list of peers as the close_cb() will - * modify the device peers list so it is better not to mess - * with the same list at the same time. + /* l2cap_chan_close() cannot be called from RCU, and lock ordering + * chan->lock > devices_lock prevents taking write side lock, so copy + * then close. */ rcu_read_lock(); + list_for_each_entry_rcu(entry, &bt_6lowpan_devices, list) + list_for_each_entry_rcu(peer, &entry->peers, list) + clear_bit(LOWPAN_PEER_CLOSING, peer->flags); + rcu_read_unlock(); - list_for_each_entry_rcu(entry, &bt_6lowpan_devices, list) { - list_for_each_entry_rcu(peer, &entry->peers, list) { - new_peer = kmalloc(sizeof(*new_peer), GFP_ATOMIC); - if (!new_peer) - break; + do { + struct l2cap_chan *chans[32]; + int i; - new_peer->chan = peer->chan; - INIT_LIST_HEAD(&new_peer->list); + nchans = 0; - list_add(&new_peer->list, &peers); - } - } + spin_lock(&devices_lock); - rcu_read_unlock(); + list_for_each_entry_rcu(entry, &bt_6lowpan_devices, list) { + list_for_each_entry_rcu(peer, &entry->peers, list) { + if (test_and_set_bit(LOWPAN_PEER_CLOSING, + peer->flags)) + continue; - spin_lock(&devices_lock); - list_for_each_entry_safe(peer, tmp_peer, &peers, list) { - l2cap_chan_close(peer->chan, ENOENT); + l2cap_chan_hold(peer->chan); + chans[nchans++] = peer->chan; - list_del_rcu(&peer->list); - kfree_rcu(peer, rcu); - } - spin_unlock(&devices_lock); + if (nchans >= ARRAY_SIZE(chans)) + goto done; + } + } + +done: + spin_unlock(&devices_lock); + + for (i = 0; i < nchans; ++i) { + l2cap_chan_lock(chans[i]); + l2cap_chan_close(chans[i], ENOENT); + l2cap_chan_unlock(chans[i]); + l2cap_chan_put(chans[i]); + } + } while (nchans); } struct set_enable { @@ -1050,7 +1091,9 @@ static void do_enable_set(struct work_struct *work) mutex_lock(&set_lock); if (listen_chan) { + l2cap_chan_lock(listen_chan); l2cap_chan_close(listen_chan, 0); + l2cap_chan_unlock(listen_chan); l2cap_chan_put(listen_chan); } @@ -1103,13 +1146,15 @@ static ssize_t lowpan_control_write(struct file *fp, buf[buf_size] = '\0'; if (memcmp(buf, "connect ", 8) == 0) { - ret = get_l2cap_conn(&buf[8], &addr, &addr_type, &conn); + ret = get_l2cap_conn(&buf[8], &addr, &addr_type, &conn, false); if (ret == -EINVAL) return ret; mutex_lock(&set_lock); if (listen_chan) { + l2cap_chan_lock(listen_chan); l2cap_chan_close(listen_chan, 0); + l2cap_chan_unlock(listen_chan); l2cap_chan_put(listen_chan); listen_chan = NULL; } @@ -1140,7 +1185,7 @@ static ssize_t lowpan_control_write(struct file *fp, } if (memcmp(buf, "disconnect ", 11) == 0) { - ret = get_l2cap_conn(&buf[11], &addr, &addr_type, &conn); + ret = get_l2cap_conn(&buf[11], &addr, &addr_type, &conn, true); if (ret < 0) return ret; @@ -1271,7 +1316,9 @@ static void __exit bt_6lowpan_exit(void) debugfs_remove(lowpan_control_debugfs); if (listen_chan) { + l2cap_chan_lock(listen_chan); l2cap_chan_close(listen_chan, 0); + l2cap_chan_unlock(listen_chan); l2cap_chan_put(listen_chan); } diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index c5dedf39a129..6fc0692abf05 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -769,21 +769,23 @@ static void find_bis(struct hci_conn *conn, void *data) d->count++; } -static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, struct hci_conn *conn) +static int hci_le_big_terminate(struct hci_dev *hdev, struct hci_conn *conn) { struct iso_list_data *d; int ret; - bt_dev_dbg(hdev, "big 0x%2.2x sync_handle 0x%4.4x", big, conn->sync_handle); + bt_dev_dbg(hdev, "hcon %p big 0x%2.2x sync_handle 0x%4.4x", conn, + conn->iso_qos.bcast.big, conn->sync_handle); d = kzalloc(sizeof(*d), GFP_KERNEL); if (!d) return -ENOMEM; - d->big = big; + d->big = conn->iso_qos.bcast.big; d->sync_handle = conn->sync_handle; - if (test_and_clear_bit(HCI_CONN_PA_SYNC, &conn->flags)) { + if (conn->type == PA_LINK && + test_and_clear_bit(HCI_CONN_PA_SYNC, &conn->flags)) { hci_conn_hash_list_flag(hdev, find_bis, PA_LINK, HCI_CONN_PA_SYNC, d); @@ -801,6 +803,9 @@ static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, struct hci_conn *c d->big_sync_term = true; } + if (!d->pa_sync_term && !d->big_sync_term) + return 0; + ret = hci_cmd_sync_queue(hdev, big_terminate_sync, d, terminate_big_destroy); if (ret) @@ -852,8 +857,7 @@ static void bis_cleanup(struct hci_conn *conn) hci_le_terminate_big(hdev, conn); } else { - hci_le_big_terminate(hdev, conn->iso_qos.bcast.big, - conn); + hci_le_big_terminate(hdev, conn); } } @@ -994,19 +998,20 @@ static struct hci_conn *__hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t conn->mtu = hdev->le_mtu ? hdev->le_mtu : hdev->acl_mtu; break; case CIS_LINK: - case BIS_LINK: - case PA_LINK: /* conn->src should reflect the local identity address */ hci_copy_identity_address(hdev, &conn->src, &conn->src_type); - /* set proper cleanup function */ - if (!bacmp(dst, BDADDR_ANY)) - conn->cleanup = bis_cleanup; - else if (conn->role == HCI_ROLE_MASTER) + if (conn->role == HCI_ROLE_MASTER) conn->cleanup = cis_cleanup; - conn->mtu = hdev->iso_mtu ? hdev->iso_mtu : - hdev->le_mtu ? hdev->le_mtu : hdev->acl_mtu; + conn->mtu = hdev->iso_mtu; + break; + case PA_LINK: + case BIS_LINK: + /* conn->src should reflect the local identity address */ + hci_copy_identity_address(hdev, &conn->src, &conn->src_type); + conn->cleanup = bis_cleanup; + conn->mtu = hdev->iso_mtu; break; case SCO_LINK: if (lmp_esco_capable(hdev)) diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index d37db364acf7..3838b90343d9 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -4218,6 +4218,13 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, void *data, } if (i == ARRAY_SIZE(hci_cc_table)) { + if (!skb->len) { + bt_dev_err(hdev, "Unexpected cc 0x%4.4x with no status", + *opcode); + *status = HCI_ERROR_UNSPECIFIED; + return; + } + /* Unknown opcode, assume byte 0 contains the status, so * that e.g. __hci_cmd_sync() properly returns errors * for vendor specific commands send by HCI drivers. @@ -5836,6 +5843,29 @@ static void hci_le_enh_conn_complete_evt(struct hci_dev *hdev, void *data, le16_to_cpu(ev->supervision_timeout)); } +static void hci_le_pa_sync_lost_evt(struct hci_dev *hdev, void *data, + struct sk_buff *skb) +{ + struct hci_ev_le_pa_sync_lost *ev = data; + u16 handle = le16_to_cpu(ev->handle); + struct hci_conn *conn; + + bt_dev_dbg(hdev, "sync handle 0x%4.4x", handle); + + hci_dev_lock(hdev); + + /* Delete the pa sync connection */ + conn = hci_conn_hash_lookup_pa_sync_handle(hdev, handle); + if (conn) { + clear_bit(HCI_CONN_BIG_SYNC, &conn->flags); + clear_bit(HCI_CONN_PA_SYNC, &conn->flags); + hci_disconn_cfm(conn, HCI_ERROR_REMOTE_USER_TERM); + hci_conn_del(conn); + } + + hci_dev_unlock(hdev); +} + static void hci_le_ext_adv_term_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { @@ -6994,14 +7024,9 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data, continue; } - if (ev->status != 0x42) { + if (ev->status != 0x42) /* Mark PA sync as established */ set_bit(HCI_CONN_PA_SYNC, &bis->flags); - /* Reset cleanup callback of PA Sync so it doesn't - * terminate the sync when deleting the connection. - */ - conn->cleanup = NULL; - } bis->sync_handle = conn->sync_handle; bis->iso_qos.bcast.big = ev->handle; @@ -7044,29 +7069,24 @@ static void hci_le_big_sync_lost_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_evt_le_big_sync_lost *ev = data; - struct hci_conn *bis, *conn; - bool mgmt_conn; + struct hci_conn *bis; + bool mgmt_conn = false; bt_dev_dbg(hdev, "big handle 0x%2.2x", ev->handle); hci_dev_lock(hdev); - /* Delete the pa sync connection */ - bis = hci_conn_hash_lookup_pa_sync_big_handle(hdev, ev->handle); - if (bis) { - conn = hci_conn_hash_lookup_pa_sync_handle(hdev, - bis->sync_handle); - if (conn) - hci_conn_del(conn); - } - /* Delete each bis connection */ while ((bis = hci_conn_hash_lookup_big_state(hdev, ev->handle, BT_CONNECTED, HCI_ROLE_SLAVE))) { - mgmt_conn = test_and_clear_bit(HCI_CONN_MGMT_CONNECTED, &bis->flags); - mgmt_device_disconnected(hdev, &bis->dst, bis->type, bis->dst_type, - ev->reason, mgmt_conn); + if (!mgmt_conn) { + mgmt_conn = test_and_clear_bit(HCI_CONN_MGMT_CONNECTED, + &bis->flags); + mgmt_device_disconnected(hdev, &bis->dst, bis->type, + bis->dst_type, ev->reason, + mgmt_conn); + } clear_bit(HCI_CONN_BIG_SYNC, &bis->flags); hci_disconn_cfm(bis, ev->reason); @@ -7180,6 +7200,9 @@ static const struct hci_le_ev { hci_le_per_adv_report_evt, sizeof(struct hci_ev_le_per_adv_report), HCI_MAX_EVENT_SIZE), + /* [0x10 = HCI_EV_LE_PA_SYNC_LOST] */ + HCI_LE_EV(HCI_EV_LE_PA_SYNC_LOST, hci_le_pa_sync_lost_evt, + sizeof(struct hci_ev_le_pa_sync_lost)), /* [0x12 = HCI_EV_LE_EXT_ADV_SET_TERM] */ HCI_LE_EV(HCI_EV_LE_EXT_ADV_SET_TERM, hci_le_ext_adv_term_evt, sizeof(struct hci_evt_le_ext_adv_set_term)), diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 73fc41b68b68..6e76798ec786 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -6999,7 +6999,7 @@ static void create_pa_complete(struct hci_dev *hdev, void *data, int err) hci_dev_lock(hdev); - if (!hci_conn_valid(hdev, conn)) + if (hci_conn_valid(hdev, conn)) clear_bit(HCI_CONN_CREATE_PA_SYNC, &conn->flags); if (!err) diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index d08320380ad6..35c57657bcf4 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -497,6 +497,7 @@ void l2cap_chan_hold(struct l2cap_chan *c) kref_get(&c->kref); } +EXPORT_SYMBOL_GPL(l2cap_chan_hold); struct l2cap_chan *l2cap_chan_hold_unless_zero(struct l2cap_chan *c) { diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 24e335e3a727..262bf984d2aa 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -5395,9 +5395,9 @@ static u8 parse_adv_monitor_pattern(struct adv_monitor *m, u8 pattern_count, for (i = 0; i < pattern_count; i++) { offset = patterns[i].offset; length = patterns[i].length; - if (offset >= HCI_MAX_EXT_AD_LENGTH || - length > HCI_MAX_EXT_AD_LENGTH || - (offset + length) > HCI_MAX_EXT_AD_LENGTH) + if (offset >= HCI_MAX_AD_LENGTH || + length > HCI_MAX_AD_LENGTH || + (offset + length) > HCI_MAX_AD_LENGTH) return MGMT_STATUS_INVALID_PARAMS; p = kmalloc(sizeof(*p), GFP_KERNEL); @@ -9497,6 +9497,7 @@ void mgmt_index_removed(struct hci_dev *hdev) cancel_delayed_work_sync(&hdev->discov_off); cancel_delayed_work_sync(&hdev->service_cache); cancel_delayed_work_sync(&hdev->rpa_expired); + cancel_delayed_work_sync(&hdev->mesh_send_done); } void mgmt_power_on(struct hci_dev *hdev, int err) diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 870bdf2e082c..dea09096ad0f 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -25,7 +25,7 @@ static inline int should_deliver(const struct net_bridge_port *p, vg = nbp_vlan_group_rcu(p); return ((p->flags & BR_HAIRPIN_MODE) || skb->dev != p->dev) && - (br_mst_is_enabled(p->br) || p->state == BR_STATE_FORWARDING) && + (br_mst_is_enabled(p) || p->state == BR_STATE_FORWARDING) && br_allowed_egress(vg, skb) && nbp_switchdev_allowed_egress(p, skb) && !br_skb_isolated(p, skb); } diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 98c5b9c3145f..ca3a637d7cca 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -386,6 +386,7 @@ void br_dev_delete(struct net_device *dev, struct list_head *head) del_nbp(p); } + br_mst_uninit(br); br_recalculate_neigh_suppress_enabled(br); br_fdb_delete_by_port(br, NULL, 0, 1); diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 67b4c905e49a..777fa869c1a1 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -94,7 +94,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb br = p->br; - if (br_mst_is_enabled(br)) { + if (br_mst_is_enabled(p)) { state = BR_STATE_FORWARDING; } else { if (p->state == BR_STATE_DISABLED) { @@ -429,7 +429,7 @@ static rx_handler_result_t br_handle_frame(struct sk_buff **pskb) return RX_HANDLER_PASS; forward: - if (br_mst_is_enabled(p->br)) + if (br_mst_is_enabled(p)) goto defer_stp_filtering; switch (p->state) { diff --git a/net/bridge/br_mst.c b/net/bridge/br_mst.c index 3f24b4ee49c2..43a300ae6bfa 100644 --- a/net/bridge/br_mst.c +++ b/net/bridge/br_mst.c @@ -22,6 +22,12 @@ bool br_mst_enabled(const struct net_device *dev) } EXPORT_SYMBOL_GPL(br_mst_enabled); +void br_mst_uninit(struct net_bridge *br) +{ + if (br_opt_get(br, BROPT_MST_ENABLED)) + static_branch_dec(&br_mst_used); +} + int br_mst_get_info(const struct net_device *dev, u16 msti, unsigned long *vids) { const struct net_bridge_vlan_group *vg; @@ -225,9 +231,9 @@ int br_mst_set_enabled(struct net_bridge *br, bool on, return err; if (on) - static_branch_enable(&br_mst_used); + static_branch_inc(&br_mst_used); else - static_branch_disable(&br_mst_used); + static_branch_dec(&br_mst_used); br_opt_toggle(br, BROPT_MST_ENABLED, on); return 0; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 16be5d250402..7280c4e9305f 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -1935,10 +1935,12 @@ static inline bool br_vlan_state_allowed(u8 state, bool learn_allow) /* br_mst.c */ #ifdef CONFIG_BRIDGE_VLAN_FILTERING DECLARE_STATIC_KEY_FALSE(br_mst_used); -static inline bool br_mst_is_enabled(struct net_bridge *br) +static inline bool br_mst_is_enabled(const struct net_bridge_port *p) { + /* check the port's vlan group to avoid racing with port deletion */ return static_branch_unlikely(&br_mst_used) && - br_opt_get(br, BROPT_MST_ENABLED); + br_opt_get(p->br, BROPT_MST_ENABLED) && + rcu_access_pointer(p->vlgrp); } int br_mst_set_state(struct net_bridge_port *p, u16 msti, u8 state, @@ -1952,8 +1954,9 @@ int br_mst_fill_info(struct sk_buff *skb, const struct net_bridge_vlan_group *vg); int br_mst_process(struct net_bridge_port *p, const struct nlattr *mst_attr, struct netlink_ext_ack *extack); +void br_mst_uninit(struct net_bridge *br); #else -static inline bool br_mst_is_enabled(struct net_bridge *br) +static inline bool br_mst_is_enabled(const struct net_bridge_port *p) { return false; } @@ -1987,6 +1990,10 @@ static inline int br_mst_process(struct net_bridge_port *p, { return -EOPNOTSUPP; } + +static inline void br_mst_uninit(struct net_bridge *br) +{ +} #endif struct nf_br_ops { diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c index fd57b845de33..a725d21159a6 100644 --- a/net/core/gro_cells.c +++ b/net/core/gro_cells.c @@ -60,9 +60,10 @@ static int gro_cell_poll(struct napi_struct *napi, int budget) struct sk_buff *skb; int work_done = 0; - __local_lock_nested_bh(&cell->bh_lock); while (work_done < budget) { + __local_lock_nested_bh(&cell->bh_lock); skb = __skb_dequeue(&cell->napi_skbs); + __local_unlock_nested_bh(&cell->bh_lock); if (!skb) break; napi_gro_receive(napi, skb); @@ -71,7 +72,6 @@ static int gro_cell_poll(struct napi_struct *napi, int budget) if (work_done < budget) napi_complete_done(napi, work_done); - __local_unlock_nested_bh(&cell->bh_lock); return work_done; } diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 60a05d3b7c24..331764845e8f 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -228,19 +228,16 @@ static void refill_skbs(struct netpoll *np) { struct sk_buff_head *skb_pool; struct sk_buff *skb; - unsigned long flags; skb_pool = &np->skb_pool; - spin_lock_irqsave(&skb_pool->lock, flags); - while (skb_pool->qlen < MAX_SKBS) { + while (READ_ONCE(skb_pool->qlen) < MAX_SKBS) { skb = alloc_skb(MAX_SKB_SIZE, GFP_ATOMIC); if (!skb) break; - __skb_queue_tail(skb_pool, skb); + skb_queue_tail(skb_pool, skb); } - spin_unlock_irqrestore(&skb_pool->lock, flags); } static void zap_completion_queue(void) @@ -814,6 +811,10 @@ static void __netpoll_cleanup(struct netpoll *np) if (!npinfo) return; + /* At this point, there is a single npinfo instance per netdevice, and + * its refcnt tracks how many netpoll structures are linked to it. We + * only perform npinfo cleanup when the refcnt decrements to zero. + */ if (refcount_dec_and_test(&npinfo->refcnt)) { const struct net_device_ops *ops; @@ -823,8 +824,7 @@ static void __netpoll_cleanup(struct netpoll *np) RCU_INIT_POINTER(np->dev->npinfo, NULL); call_rcu(&npinfo->rcu, rcu_cleanup_netpoll_info); - } else - RCU_INIT_POINTER(np->dev->npinfo, NULL); + } skb_pool_flush(np); } diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index 26bb657ceac3..eadb358179ce 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -176,7 +176,8 @@ static struct sk_buff *brcm_tag_rcv_ll(struct sk_buff *skb, /* Remove Broadcom tag and update checksum */ skb_pull_rcsum(skb, BRCM_TAG_LEN); - dsa_default_offload_fwd_mark(skb); + if (likely(!is_link_local_ether_addr(eth_hdr(skb)->h_dest))) + dsa_default_offload_fwd_mark(skb); return skb; } @@ -224,12 +225,14 @@ static struct sk_buff *brcm_leg_tag_rcv(struct sk_buff *skb, { int len = BRCM_LEG_TAG_LEN; int source_port; + __be16 *proto; u8 *brcm_tag; if (unlikely(!pskb_may_pull(skb, BRCM_LEG_TAG_LEN + VLAN_HLEN))) return NULL; brcm_tag = dsa_etype_header_pos_rx(skb); + proto = (__be16 *)(brcm_tag + BRCM_LEG_TAG_LEN); source_port = brcm_tag[5] & BRCM_LEG_PORT_ID; @@ -237,14 +240,19 @@ static struct sk_buff *brcm_leg_tag_rcv(struct sk_buff *skb, if (!skb->dev) return NULL; - /* VLAN tag is added by BCM63xx internal switch */ - if (netdev_uses_dsa(skb->dev)) + /* The internal switch in BCM63XX SoCs always tags on egress on the CPU + * port. We use VID 0 internally for untagged traffic, so strip the tag + * if the TCI field is all 0, and keep it otherwise to also retain + * e.g. 802.1p tagged packets. + */ + if (proto[0] == htons(ETH_P_8021Q) && proto[1] == 0) len += VLAN_HLEN; /* Remove Broadcom tag and update checksum */ skb_pull_rcsum(skb, len); - dsa_default_offload_fwd_mark(skb); + if (likely(!is_link_local_ether_addr(eth_hdr(skb)->h_dest))) + dsa_default_offload_fwd_mark(skb); dsa_strip_etype_header(skb, len); diff --git a/net/handshake/tlshd.c b/net/handshake/tlshd.c index 081093dfd553..8f9532a15f43 100644 --- a/net/handshake/tlshd.c +++ b/net/handshake/tlshd.c @@ -259,6 +259,7 @@ static int tls_handshake_accept(struct handshake_req *req, out_cancel: genlmsg_cancel(msg, hdr); + nlmsg_free(msg); out: return ret; } diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index fbbc3ccf9df6..492cbc78ab75 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -320,6 +320,9 @@ static void send_hsr_supervision_frame(struct hsr_port *port, } hsr_stag = skb_put(skb, sizeof(struct hsr_sup_tag)); + skb_set_network_header(skb, ETH_HLEN + HSR_HLEN); + skb_reset_mac_len(skb); + set_hsr_stag_path(hsr_stag, (hsr->prot_version ? 0x0 : 0xf)); set_hsr_stag_HSR_ver(hsr_stag, hsr->prot_version); @@ -334,7 +337,7 @@ static void send_hsr_supervision_frame(struct hsr_port *port, } hsr_stag->tlv.HSR_TLV_type = type; - /* TODO: Why 12 in HSRv0? */ + /* HSRv0 has 6 unused bytes after the MAC */ hsr_stag->tlv.HSR_TLV_length = hsr->prot_version ? sizeof(struct hsr_sup_payload) : 12; diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index c67c0d35921d..339f0d220212 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -262,15 +262,23 @@ static struct sk_buff *prp_fill_rct(struct sk_buff *skb, return skb; } -static void hsr_set_path_id(struct hsr_ethhdr *hsr_ethhdr, +static void hsr_set_path_id(struct hsr_frame_info *frame, + struct hsr_ethhdr *hsr_ethhdr, struct hsr_port *port) { int path_id; - if (port->type == HSR_PT_SLAVE_A) - path_id = 0; - else - path_id = 1; + if (port->hsr->prot_version) { + if (port->type == HSR_PT_SLAVE_A) + path_id = 0; + else + path_id = 1; + } else { + if (frame->is_supervision) + path_id = 0xf; + else + path_id = 1; + } set_hsr_tag_path(&hsr_ethhdr->hsr_tag, path_id); } @@ -304,7 +312,7 @@ static struct sk_buff *hsr_fill_tag(struct sk_buff *skb, else hsr_ethhdr = (struct hsr_ethhdr *)pc; - hsr_set_path_id(hsr_ethhdr, port); + hsr_set_path_id(frame, hsr_ethhdr, port); set_hsr_tag_LSDU_size(&hsr_ethhdr->hsr_tag, lsdu_size); hsr_ethhdr->hsr_tag.sequence_nr = htons(frame->sequence_nr); hsr_ethhdr->hsr_tag.encap_proto = hsr_ethhdr->ethhdr.h_proto; @@ -330,7 +338,7 @@ struct sk_buff *hsr_create_tagged_frame(struct hsr_frame_info *frame, (struct hsr_ethhdr *)skb_mac_header(frame->skb_hsr); /* set the lane id properly */ - hsr_set_path_id(hsr_ethhdr, port); + hsr_set_path_id(frame, hsr_ethhdr, port); return skb_clone(frame->skb_hsr, GFP_ATOMIC); } else if (port->dev->features & NETIF_F_HW_HSR_TAG_INS) { return skb_clone(frame->skb_std, GFP_ATOMIC); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 6d27d3610c1c..b549d6a57307 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -607,6 +607,11 @@ static void fnhe_remove_oldest(struct fnhe_hash_bucket *hash) oldest_p = fnhe_p; } } + + /* Clear oldest->fnhe_daddr to prevent this fnhe from being + * rebound with new dsts in rt_bind_exception(). + */ + oldest->fnhe_daddr = 0; fnhe_flush_routes(oldest); *oldest_p = oldest->fnhe_next; kfree_rcu(oldest, rcu); diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index 57065714cf8c..7f8799fd673e 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -1290,7 +1290,7 @@ ieee80211_link_chanctx_reservation_complete(struct ieee80211_link_data *link) &link->csa.finalize_work); break; case NL80211_IFTYPE_STATION: - wiphy_delayed_work_queue(sdata->local->hw.wiphy, + wiphy_hrtimer_work_queue(sdata->local->hw.wiphy, &link->u.mgd.csa.switch_work, 0); break; case NL80211_IFTYPE_UNSPECIFIED: diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 73fd86ec1bce..878c3b14aeb8 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -612,11 +612,11 @@ struct ieee80211_if_managed { u8 *assoc_req_ies; size_t assoc_req_ies_len; - struct wiphy_delayed_work ml_reconf_work; + struct wiphy_hrtimer_work ml_reconf_work; u16 removed_links; /* TID-to-link mapping support */ - struct wiphy_delayed_work ttlm_work; + struct wiphy_hrtimer_work ttlm_work; struct ieee80211_adv_ttlm_info ttlm_info; struct wiphy_work teardown_ttlm_work; @@ -1017,10 +1017,10 @@ struct ieee80211_link_data_managed { bool operating_11g_mode; struct { - struct wiphy_delayed_work switch_work; + struct wiphy_hrtimer_work switch_work; struct cfg80211_chan_def ap_chandef; struct ieee80211_parsed_tpe tpe; - unsigned long time; + ktime_t time; bool waiting_bcn; bool ignored_same_chan; bool blocked_tx; diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index a7873832d4fa..0ca55b9655a7 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -223,6 +223,10 @@ static int ieee80211_can_powered_addr_change(struct ieee80211_sub_if_data *sdata if (netif_carrier_ok(sdata->dev)) return -EBUSY; + /* if any stations are set known (so they know this vif too), reject */ + if (sta_info_get_by_idx(sdata, 0)) + return -EBUSY; + /* First check no ROC work is happening on this iface */ list_for_each_entry(roc, &local->roc_list, list) { if (roc->sdata != sdata) @@ -242,12 +246,16 @@ static int ieee80211_can_powered_addr_change(struct ieee80211_sub_if_data *sdata ret = -EBUSY; } + /* + * More interface types could be added here but changing the + * address while powered makes the most sense in client modes. + */ switch (sdata->vif.type) { case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_P2P_CLIENT: - /* More interface types could be added here but changing the - * address while powered makes the most sense in client modes. - */ + /* refuse while connecting */ + if (sdata->u.mgd.auth_data || sdata->u.mgd.assoc_data) + return -EBUSY; break; default: ret = -EOPNOTSUPP; diff --git a/net/mac80211/link.c b/net/mac80211/link.c index d71eabe5abf8..4a19b765ccb6 100644 --- a/net/mac80211/link.c +++ b/net/mac80211/link.c @@ -472,10 +472,10 @@ static int _ieee80211_set_active_links(struct ieee80211_sub_if_data *sdata, * from there. */ if (link->conf->csa_active) - wiphy_delayed_work_queue(local->hw.wiphy, + wiphy_hrtimer_work_queue(local->hw.wiphy, &link->u.mgd.csa.switch_work, link->u.mgd.csa.time - - jiffies); + ktime_get_boottime()); } for_each_set_bit(link_id, &add, IEEE80211_MLD_MAX_NUM_LINKS) { diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 3b5827ea438e..f3138d158535 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -45,7 +45,7 @@ #define IEEE80211_ASSOC_TIMEOUT_SHORT (HZ / 10) #define IEEE80211_ASSOC_MAX_TRIES 3 -#define IEEE80211_ADV_TTLM_SAFETY_BUFFER_MS msecs_to_jiffies(100) +#define IEEE80211_ADV_TTLM_SAFETY_BUFFER_MS (100 * USEC_PER_MSEC) #define IEEE80211_ADV_TTLM_ST_UNDERFLOW 0xff00 #define IEEE80211_NEG_TTLM_REQ_TIMEOUT (HZ / 5) @@ -2594,7 +2594,7 @@ void ieee80211_chswitch_done(struct ieee80211_vif *vif, bool success, return; } - wiphy_delayed_work_queue(sdata->local->hw.wiphy, + wiphy_hrtimer_work_queue(sdata->local->hw.wiphy, &link->u.mgd.csa.switch_work, 0); } @@ -2753,7 +2753,8 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link, .timestamp = timestamp, .device_timestamp = device_timestamp, }; - unsigned long now; + u32 csa_time_tu; + ktime_t now; int res; lockdep_assert_wiphy(local->hw.wiphy); @@ -2983,10 +2984,9 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link, csa_ie.mode); /* we may have to handle timeout for deactivated link in software */ - now = jiffies; - link->u.mgd.csa.time = now + - TU_TO_JIFFIES((max_t(int, csa_ie.count, 1) - 1) * - link->conf->beacon_int); + now = ktime_get_boottime(); + csa_time_tu = (max_t(int, csa_ie.count, 1) - 1) * link->conf->beacon_int; + link->u.mgd.csa.time = now + us_to_ktime(ieee80211_tu_to_usec(csa_time_tu)); if (ieee80211_vif_link_active(&sdata->vif, link->link_id) && local->ops->channel_switch) { @@ -3001,7 +3001,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link, } /* channel switch handled in software */ - wiphy_delayed_work_queue(local->hw.wiphy, + wiphy_hrtimer_work_queue(local->hw.wiphy, &link->u.mgd.csa.switch_work, link->u.mgd.csa.time - now); return; @@ -4242,14 +4242,14 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, memset(&sdata->u.mgd.ttlm_info, 0, sizeof(sdata->u.mgd.ttlm_info)); - wiphy_delayed_work_cancel(sdata->local->hw.wiphy, &ifmgd->ttlm_work); + wiphy_hrtimer_work_cancel(sdata->local->hw.wiphy, &ifmgd->ttlm_work); memset(&sdata->vif.neg_ttlm, 0, sizeof(sdata->vif.neg_ttlm)); wiphy_delayed_work_cancel(sdata->local->hw.wiphy, &ifmgd->neg_ttlm_timeout_work); sdata->u.mgd.removed_links = 0; - wiphy_delayed_work_cancel(sdata->local->hw.wiphy, + wiphy_hrtimer_work_cancel(sdata->local->hw.wiphy, &sdata->u.mgd.ml_reconf_work); wiphy_work_cancel(sdata->local->hw.wiphy, @@ -6876,7 +6876,7 @@ static void ieee80211_ml_reconfiguration(struct ieee80211_sub_if_data *sdata, /* In case the removal was cancelled, abort it */ if (sdata->u.mgd.removed_links) { sdata->u.mgd.removed_links = 0; - wiphy_delayed_work_cancel(sdata->local->hw.wiphy, + wiphy_hrtimer_work_cancel(sdata->local->hw.wiphy, &sdata->u.mgd.ml_reconf_work); } return; @@ -6906,9 +6906,9 @@ static void ieee80211_ml_reconfiguration(struct ieee80211_sub_if_data *sdata, } sdata->u.mgd.removed_links = removed_links; - wiphy_delayed_work_queue(sdata->local->hw.wiphy, + wiphy_hrtimer_work_queue(sdata->local->hw.wiphy, &sdata->u.mgd.ml_reconf_work, - TU_TO_JIFFIES(delay)); + us_to_ktime(ieee80211_tu_to_usec(delay))); } static int ieee80211_ttlm_set_links(struct ieee80211_sub_if_data *sdata, @@ -7095,7 +7095,7 @@ static void ieee80211_process_adv_ttlm(struct ieee80211_sub_if_data *sdata, /* if a planned TID-to-link mapping was cancelled - * abort it */ - wiphy_delayed_work_cancel(sdata->local->hw.wiphy, + wiphy_hrtimer_work_cancel(sdata->local->hw.wiphy, &sdata->u.mgd.ttlm_work); } else if (sdata->u.mgd.ttlm_info.active) { /* if no TID-to-link element, set to default mapping in @@ -7130,7 +7130,7 @@ static void ieee80211_process_adv_ttlm(struct ieee80211_sub_if_data *sdata, if (ttlm_info.switch_time) { u16 beacon_ts_tu, st_tu, delay; - u32 delay_jiffies; + u64 delay_usec; u64 mask; /* The t2l map switch time is indicated with a partial @@ -7152,23 +7152,23 @@ static void ieee80211_process_adv_ttlm(struct ieee80211_sub_if_data *sdata, if (delay > IEEE80211_ADV_TTLM_ST_UNDERFLOW) return; - delay_jiffies = TU_TO_JIFFIES(delay); + delay_usec = ieee80211_tu_to_usec(delay); /* Link switching can take time, so schedule it * 100ms before to be ready on time */ - if (delay_jiffies > IEEE80211_ADV_TTLM_SAFETY_BUFFER_MS) - delay_jiffies -= + if (delay_usec > IEEE80211_ADV_TTLM_SAFETY_BUFFER_MS) + delay_usec -= IEEE80211_ADV_TTLM_SAFETY_BUFFER_MS; else - delay_jiffies = 0; + delay_usec = 0; sdata->u.mgd.ttlm_info = ttlm_info; - wiphy_delayed_work_cancel(sdata->local->hw.wiphy, + wiphy_hrtimer_work_cancel(sdata->local->hw.wiphy, &sdata->u.mgd.ttlm_work); - wiphy_delayed_work_queue(sdata->local->hw.wiphy, + wiphy_hrtimer_work_queue(sdata->local->hw.wiphy, &sdata->u.mgd.ttlm_work, - delay_jiffies); + us_to_ktime(delay_usec)); return; } } @@ -8793,7 +8793,7 @@ void ieee80211_sta_setup_sdata(struct ieee80211_sub_if_data *sdata) ieee80211_csa_connection_drop_work); wiphy_delayed_work_init(&ifmgd->tdls_peer_del_work, ieee80211_tdls_peer_del_work); - wiphy_delayed_work_init(&ifmgd->ml_reconf_work, + wiphy_hrtimer_work_init(&ifmgd->ml_reconf_work, ieee80211_ml_reconf_work); wiphy_delayed_work_init(&ifmgd->reconf.wk, ieee80211_ml_sta_reconf_timeout); @@ -8802,7 +8802,7 @@ void ieee80211_sta_setup_sdata(struct ieee80211_sub_if_data *sdata) timer_setup(&ifmgd->conn_mon_timer, ieee80211_sta_conn_mon_timer, 0); wiphy_delayed_work_init(&ifmgd->tx_tspec_wk, ieee80211_sta_handle_tspec_ac_params_wk); - wiphy_delayed_work_init(&ifmgd->ttlm_work, + wiphy_hrtimer_work_init(&ifmgd->ttlm_work, ieee80211_tid_to_link_map_work); wiphy_delayed_work_init(&ifmgd->neg_ttlm_timeout_work, ieee80211_neg_ttlm_timeout_work); @@ -8849,7 +8849,7 @@ void ieee80211_mgd_setup_link(struct ieee80211_link_data *link) else link->u.mgd.req_smps = IEEE80211_SMPS_OFF; - wiphy_delayed_work_init(&link->u.mgd.csa.switch_work, + wiphy_hrtimer_work_init(&link->u.mgd.csa.switch_work, ieee80211_csa_switch_work); ieee80211_clear_tpe(&link->conf->tpe); @@ -10064,7 +10064,7 @@ void ieee80211_mgd_stop_link(struct ieee80211_link_data *link) &link->u.mgd.request_smps_work); wiphy_work_cancel(link->sdata->local->hw.wiphy, &link->u.mgd.recalc_smps); - wiphy_delayed_work_cancel(link->sdata->local->hw.wiphy, + wiphy_hrtimer_work_cancel(link->sdata->local->hw.wiphy, &link->u.mgd.csa.switch_work); } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 6af43dfefdd6..5b4c3fe9970a 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -5360,10 +5360,14 @@ void ieee80211_rx_list(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta, if (WARN_ON(!local->started)) goto drop; - if (likely(!(status->flag & RX_FLAG_FAILED_PLCP_CRC))) { + if (likely(!(status->flag & RX_FLAG_FAILED_PLCP_CRC) && + !(status->flag & RX_FLAG_NO_PSDU && + status->zero_length_psdu_type == + IEEE80211_RADIOTAP_ZERO_LEN_PSDU_NOT_CAPTURED))) { /* - * Validate the rate, unless a PLCP error means that - * we probably can't have a valid rate here anyway. + * Validate the rate, unless there was a PLCP error which may + * have an invalid rate or the PSDU was not capture and may be + * missing rate information. */ switch (status->encoding) { diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 3e89927d7116..26ba8c2d20ab 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -195,13 +195,15 @@ static inline int tcf_connmark_dump(struct sk_buff *skb, struct tc_action *a, const struct tcf_connmark_info *ci = to_connmark(a); unsigned char *b = skb_tail_pointer(skb); const struct tcf_connmark_parms *parms; - struct tc_connmark opt = { - .index = ci->tcf_index, - .refcnt = refcount_read(&ci->tcf_refcnt) - ref, - .bindcnt = atomic_read(&ci->tcf_bindcnt) - bind, - }; + struct tc_connmark opt; struct tcf_t t; + memset(&opt, 0, sizeof(opt)); + + opt.index = ci->tcf_index; + opt.refcnt = refcount_read(&ci->tcf_refcnt) - ref; + opt.bindcnt = atomic_read(&ci->tcf_bindcnt) - bind; + rcu_read_lock(); parms = rcu_dereference(ci->parms); diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 107c6d83dc5c..7c6975632fc2 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -644,13 +644,15 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind, unsigned char *b = skb_tail_pointer(skb); struct tcf_ife_info *ife = to_ife(a); struct tcf_ife_params *p; - struct tc_ife opt = { - .index = ife->tcf_index, - .refcnt = refcount_read(&ife->tcf_refcnt) - ref, - .bindcnt = atomic_read(&ife->tcf_bindcnt) - bind, - }; + struct tc_ife opt; struct tcf_t t; + memset(&opt, 0, sizeof(opt)); + + opt.index = ife->tcf_index, + opt.refcnt = refcount_read(&ife->tcf_refcnt) - ref, + opt.bindcnt = atomic_read(&ife->tcf_bindcnt) - bind, + spin_lock_bh(&ife->tcf_lock); opt.action = ife->tcf_action; p = rcu_dereference_protected(ife->params, diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 1e058b46d3e1..f56b18c8aebf 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1599,6 +1599,11 @@ static int __tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, NL_SET_ERR_MSG(extack, "Failed to find specified qdisc"); return -ENOENT; } + if (p->flags & TCQ_F_INGRESS) { + NL_SET_ERR_MSG(extack, + "Cannot add children to ingress/clsact qdisc"); + return -EOPNOTSUPP; + } q = qdisc_leaf(p, clid, extack); if (IS_ERR(q)) return PTR_ERR(q); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 1e008a228ebd..7dee9748a56b 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -180,9 +180,10 @@ static inline void dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q) static void try_bulk_dequeue_skb(struct Qdisc *q, struct sk_buff *skb, const struct netdev_queue *txq, - int *packets) + int *packets, int budget) { int bytelimit = qdisc_avail_bulklimit(txq) - skb->len; + int cnt = 0; while (bytelimit > 0) { struct sk_buff *nskb = q->dequeue(q); @@ -193,8 +194,10 @@ static void try_bulk_dequeue_skb(struct Qdisc *q, bytelimit -= nskb->len; /* covers GSO len */ skb->next = nskb; skb = nskb; - (*packets)++; /* GSO counts as one pkt */ + if (++cnt >= budget) + break; } + (*packets) += cnt; skb_mark_not_on_list(skb); } @@ -228,7 +231,7 @@ static void try_bulk_dequeue_skb_slow(struct Qdisc *q, * A requeued skb (via q->gso_skb) can also be a SKB list. */ static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate, - int *packets) + int *packets, int budget) { const struct netdev_queue *txq = q->dev_queue; struct sk_buff *skb = NULL; @@ -295,7 +298,7 @@ validate: if (skb) { bulk: if (qdisc_may_bulk(q)) - try_bulk_dequeue_skb(q, skb, txq, packets); + try_bulk_dequeue_skb(q, skb, txq, packets, budget); else try_bulk_dequeue_skb_slow(q, skb, packets); } @@ -387,7 +390,7 @@ bool sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, * >0 - queue is not empty. * */ -static inline bool qdisc_restart(struct Qdisc *q, int *packets) +static inline bool qdisc_restart(struct Qdisc *q, int *packets, int budget) { spinlock_t *root_lock = NULL; struct netdev_queue *txq; @@ -396,7 +399,7 @@ static inline bool qdisc_restart(struct Qdisc *q, int *packets) bool validate; /* Dequeue packet */ - skb = dequeue_skb(q, &validate, packets); + skb = dequeue_skb(q, &validate, packets, budget); if (unlikely(!skb)) return false; @@ -414,7 +417,7 @@ void __qdisc_run(struct Qdisc *q) int quota = READ_ONCE(net_hotdata.dev_tx_weight); int packets; - while (qdisc_restart(q, &packets)) { + while (qdisc_restart(q, &packets, quota)) { quota -= packets; if (quota <= 0) { if (q->flags & TCQ_F_NOLOCK) diff --git a/net/sctp/diag.c b/net/sctp/diag.c index 996c2018f0e6..2afb376299fe 100644 --- a/net/sctp/diag.c +++ b/net/sctp/diag.c @@ -73,19 +73,26 @@ static int inet_diag_msg_sctpladdrs_fill(struct sk_buff *skb, struct nlattr *attr; void *info = NULL; + rcu_read_lock(); list_for_each_entry_rcu(laddr, address_list, list) addrcnt++; + rcu_read_unlock(); attr = nla_reserve(skb, INET_DIAG_LOCALS, addrlen * addrcnt); if (!attr) return -EMSGSIZE; info = nla_data(attr); + rcu_read_lock(); list_for_each_entry_rcu(laddr, address_list, list) { memcpy(info, &laddr->a, sizeof(laddr->a)); memset(info + sizeof(laddr->a), 0, addrlen - sizeof(laddr->a)); info += addrlen; + + if (!--addrcnt) + break; } + rcu_read_unlock(); return 0; } @@ -223,14 +230,15 @@ struct sctp_comm_param { bool net_admin; }; -static size_t inet_assoc_attr_size(struct sctp_association *asoc) +static size_t inet_assoc_attr_size(struct sock *sk, + struct sctp_association *asoc) { int addrlen = sizeof(struct sockaddr_storage); int addrcnt = 0; struct sctp_sockaddr_entry *laddr; list_for_each_entry_rcu(laddr, &asoc->base.bind_addr.address_list, - list) + list, lockdep_sock_is_held(sk)) addrcnt++; return nla_total_size(sizeof(struct sctp_info)) @@ -256,11 +264,14 @@ static int sctp_sock_dump_one(struct sctp_endpoint *ep, struct sctp_transport *t if (err) return err; - rep = nlmsg_new(inet_assoc_attr_size(assoc), GFP_KERNEL); - if (!rep) + lock_sock(sk); + + rep = nlmsg_new(inet_assoc_attr_size(sk, assoc), GFP_KERNEL); + if (!rep) { + release_sock(sk); return -ENOMEM; + } - lock_sock(sk); if (ep != assoc->ep) { err = -EAGAIN; goto out; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 4d258a6e8033..0c56d9673cc1 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -37,10 +37,10 @@ /* 1st Level Abstractions. */ /* Initialize a new transport from provided memory. */ -static struct sctp_transport *sctp_transport_init(struct net *net, - struct sctp_transport *peer, - const union sctp_addr *addr, - gfp_t gfp) +static void sctp_transport_init(struct net *net, + struct sctp_transport *peer, + const union sctp_addr *addr, + gfp_t gfp) { /* Copy in the address. */ peer->af_specific = sctp_get_af_specific(addr->sa.sa_family); @@ -83,8 +83,6 @@ static struct sctp_transport *sctp_transport_init(struct net *net, get_random_bytes(&peer->hb_nonce, sizeof(peer->hb_nonce)); refcount_set(&peer->refcnt, 1); - - return peer; } /* Allocate and initialize a new transport. */ @@ -96,20 +94,13 @@ struct sctp_transport *sctp_transport_new(struct net *net, transport = kzalloc(sizeof(*transport), gfp); if (!transport) - goto fail; + return NULL; - if (!sctp_transport_init(net, transport, addr, gfp)) - goto fail_init; + sctp_transport_init(net, transport, addr, gfp); SCTP_DBG_OBJCNT_INC(transport); return transport; - -fail_init: - kfree(transport); - -fail: - return NULL; } /* This transport is no longer needed. Free up if possible, or @@ -495,6 +486,7 @@ void sctp_transport_update_rto(struct sctp_transport *tp, __u32 rtt) if (tp->rttvar || tp->srtt) { struct net *net = tp->asoc->base.net; + unsigned int rto_beta, rto_alpha; /* 6.3.1 C3) When a new RTT measurement R' is made, set * RTTVAR <- (1 - RTO.Beta) * RTTVAR + RTO.Beta * |SRTT - R'| * SRTT <- (1 - RTO.Alpha) * SRTT + RTO.Alpha * R' @@ -506,10 +498,14 @@ void sctp_transport_update_rto(struct sctp_transport *tp, __u32 rtt) * For example, assuming the default value of RTO.Alpha of * 1/8, rto_alpha would be expressed as 3. */ - tp->rttvar = tp->rttvar - (tp->rttvar >> net->sctp.rto_beta) - + (((__u32)abs((__s64)tp->srtt - (__s64)rtt)) >> net->sctp.rto_beta); - tp->srtt = tp->srtt - (tp->srtt >> net->sctp.rto_alpha) - + (rtt >> net->sctp.rto_alpha); + rto_beta = READ_ONCE(net->sctp.rto_beta); + if (rto_beta < 32) + tp->rttvar = tp->rttvar - (tp->rttvar >> rto_beta) + + (((__u32)abs((__s64)tp->srtt - (__s64)rtt)) >> rto_beta); + rto_alpha = READ_ONCE(net->sctp.rto_alpha); + if (rto_alpha < 32) + tp->srtt = tp->srtt - (tp->srtt >> rto_alpha) + + (rtt >> rto_alpha); } else { /* 6.3.1 C2) When the first RTT measurement R is made, set * SRTT <- R, RTTVAR <- R/2. diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 157aace169d4..87c87edadde7 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -890,6 +890,7 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) return SMC_CLC_DECL_CNFERR; } pclc_base->hdr.typev1 = SMC_TYPE_N; + ini->smc_type_v1 = SMC_TYPE_N; } else { pclc_base->iparea_offset = htons(sizeof(*pclc_smcd)); plen += sizeof(*pclc_prfx) + diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c index 43b1f558b33d..e659fea2da70 100644 --- a/net/strparser/strparser.c +++ b/net/strparser/strparser.c @@ -238,7 +238,7 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, strp_parser_err(strp, -EMSGSIZE, desc); break; } else if (len <= (ssize_t)head->len - - skb->len - stm->strp.offset) { + (ssize_t)skb->len - stm->strp.offset) { /* Length must be into new skb (and also * greater than zero) */ diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig index 984e0cf9bf8a..a570e7adf270 100644 --- a/net/sunrpc/Kconfig +++ b/net/sunrpc/Kconfig @@ -18,10 +18,9 @@ config SUNRPC_SWAP config RPCSEC_GSS_KRB5 tristate "Secure RPC: Kerberos V mechanism" - depends on SUNRPC + depends on SUNRPC && CRYPTO default y select SUNRPC_GSS - select CRYPTO select CRYPTO_SKCIPHER select CRYPTO_HASH help diff --git a/net/tipc/net.c b/net/tipc/net.c index 0e95572e56b4..7e65d0b0c4a8 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -145,7 +145,9 @@ void tipc_net_finalize_work(struct work_struct *work) { struct tipc_net *tn = container_of(work, struct tipc_net, work); + rtnl_lock(); tipc_net_finalize(tipc_link_net(tn->bcl), tn->trial_addr); + rtnl_unlock(); } void tipc_net_stop(struct net *net) diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 684ab03137b6..65396a4e1b07 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -145,6 +145,7 @@ enum unix_vertex_index { }; static unsigned long unix_vertex_unvisited_index = UNIX_VERTEX_INDEX_MARK1; +static unsigned long unix_vertex_max_scc_index = UNIX_VERTEX_INDEX_START; static void unix_add_edge(struct scm_fp_list *fpl, struct unix_edge *edge) { @@ -153,6 +154,7 @@ static void unix_add_edge(struct scm_fp_list *fpl, struct unix_edge *edge) if (!vertex) { vertex = list_first_entry(&fpl->vertices, typeof(*vertex), entry); vertex->index = unix_vertex_unvisited_index; + vertex->scc_index = ++unix_vertex_max_scc_index; vertex->out_degree = 0; INIT_LIST_HEAD(&vertex->edges); INIT_LIST_HEAD(&vertex->scc_entry); @@ -489,10 +491,15 @@ prev_vertex: scc_dead = unix_vertex_dead(v); } - if (scc_dead) + if (scc_dead) { unix_collect_skb(&scc, hitlist); - else if (!unix_graph_maybe_cyclic) - unix_graph_maybe_cyclic = unix_scc_cyclic(&scc); + } else { + if (unix_vertex_max_scc_index < vertex->scc_index) + unix_vertex_max_scc_index = vertex->scc_index; + + if (!unix_graph_maybe_cyclic) + unix_graph_maybe_cyclic = unix_scc_cyclic(&scc); + } list_del(&scc); } @@ -507,6 +514,7 @@ static void unix_walk_scc(struct sk_buff_head *hitlist) unsigned long last_index = UNIX_VERTEX_INDEX_START; unix_graph_maybe_cyclic = false; + unix_vertex_max_scc_index = UNIX_VERTEX_INDEX_START; /* Visit every vertex exactly once. * __unix_walk_scc() moves visited vertices to unix_visited_vertices. diff --git a/net/wireless/core.c b/net/wireless/core.c index 797f9f2004a6..54a34d8d356e 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1787,6 +1787,62 @@ bool wiphy_delayed_work_pending(struct wiphy *wiphy, } EXPORT_SYMBOL_GPL(wiphy_delayed_work_pending); +enum hrtimer_restart wiphy_hrtimer_work_timer(struct hrtimer *t) +{ + struct wiphy_hrtimer_work *hrwork = + container_of(t, struct wiphy_hrtimer_work, timer); + + wiphy_work_queue(hrwork->wiphy, &hrwork->work); + + return HRTIMER_NORESTART; +} +EXPORT_SYMBOL_GPL(wiphy_hrtimer_work_timer); + +void wiphy_hrtimer_work_queue(struct wiphy *wiphy, + struct wiphy_hrtimer_work *hrwork, + ktime_t delay) +{ + trace_wiphy_hrtimer_work_queue(wiphy, &hrwork->work, delay); + + if (!delay) { + hrtimer_cancel(&hrwork->timer); + wiphy_work_queue(wiphy, &hrwork->work); + return; + } + + hrwork->wiphy = wiphy; + hrtimer_start_range_ns(&hrwork->timer, delay, + 1000 * NSEC_PER_USEC, HRTIMER_MODE_REL); +} +EXPORT_SYMBOL_GPL(wiphy_hrtimer_work_queue); + +void wiphy_hrtimer_work_cancel(struct wiphy *wiphy, + struct wiphy_hrtimer_work *hrwork) +{ + lockdep_assert_held(&wiphy->mtx); + + hrtimer_cancel(&hrwork->timer); + wiphy_work_cancel(wiphy, &hrwork->work); +} +EXPORT_SYMBOL_GPL(wiphy_hrtimer_work_cancel); + +void wiphy_hrtimer_work_flush(struct wiphy *wiphy, + struct wiphy_hrtimer_work *hrwork) +{ + lockdep_assert_held(&wiphy->mtx); + + hrtimer_cancel(&hrwork->timer); + wiphy_work_flush(wiphy, &hrwork->work); +} +EXPORT_SYMBOL_GPL(wiphy_hrtimer_work_flush); + +bool wiphy_hrtimer_work_pending(struct wiphy *wiphy, + struct wiphy_hrtimer_work *hrwork) +{ + return hrtimer_is_queued(&hrwork->timer); +} +EXPORT_SYMBOL_GPL(wiphy_hrtimer_work_pending); + static int __init cfg80211_init(void) { int err; diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 8a4c34112eb5..2b71f1d867a0 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -304,6 +304,27 @@ TRACE_EVENT(wiphy_delayed_work_queue, __entry->delay) ); +TRACE_EVENT(wiphy_hrtimer_work_queue, + TP_PROTO(struct wiphy *wiphy, struct wiphy_work *work, + ktime_t delay), + TP_ARGS(wiphy, work, delay), + TP_STRUCT__entry( + WIPHY_ENTRY + __field(void *, instance) + __field(void *, func) + __field(ktime_t, delay) + ), + TP_fast_assign( + WIPHY_ASSIGN; + __entry->instance = work; + __entry->func = work->func; + __entry->delay = delay; + ), + TP_printk(WIPHY_PR_FMT " instance=%p func=%pS delay=%llu", + WIPHY_PR_ARG, __entry->instance, __entry->func, + __entry->delay) +); + TRACE_EVENT(wiphy_work_worker_start, TP_PROTO(struct wiphy *wiphy), TP_ARGS(wiphy), diff --git a/rust/Makefile b/rust/Makefile index 23c7ae905bd2..7842ad0a4ea7 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -69,6 +69,9 @@ core-edition := $(if $(call rustc-min-version,108700),2024,2021) # the time being (https://github.com/rust-lang/rust/issues/144521). rustdoc_modifiers_workaround := $(if $(call rustc-min-version,108800),-Cunsafe-allow-abi-mismatch=fixed-x18) +# Similarly, for doctests (https://github.com/rust-lang/rust/issues/146465). +doctests_modifiers_workaround := $(rustdoc_modifiers_workaround)$(if $(call rustc-min-version,109100),$(comma)sanitizer) + # `rustc` recognizes `--remap-path-prefix` since 1.26.0, but `rustdoc` only # since Rust 1.81.0. Moreover, `rustdoc` ICEs on out-of-tree builds since Rust # 1.82.0 (https://github.com/rust-lang/rust/issues/138520). Thus workaround both @@ -127,9 +130,14 @@ rustdoc-core: private rustc_target_flags = --edition=$(core-edition) $(core-cfgs rustdoc-core: $(RUST_LIB_SRC)/core/src/lib.rs rustdoc-clean FORCE +$(call if_changed,rustdoc) +# Even if `rustdoc` targets are not kernel objects, they should still be +# treated as such so that we pass the same flags. Otherwise, for instance, +# `rustdoc` will complain about missing sanitizer flags causing an ABI mismatch. +rustdoc-compiler_builtins: private is-kernel-object := y rustdoc-compiler_builtins: $(src)/compiler_builtins.rs rustdoc-core FORCE +$(call if_changed,rustdoc) +rustdoc-ffi: private is-kernel-object := y rustdoc-ffi: $(src)/ffi.rs rustdoc-core FORCE +$(call if_changed,rustdoc) @@ -147,6 +155,7 @@ rustdoc-pin_init: $(src)/pin-init/src/lib.rs rustdoc-pin_init_internal \ rustdoc-macros FORCE +$(call if_changed,rustdoc) +rustdoc-kernel: private is-kernel-object := y rustdoc-kernel: private rustc_target_flags = --extern ffi --extern pin_init \ --extern build_error --extern macros \ --extern bindings --extern uapi @@ -230,7 +239,7 @@ quiet_cmd_rustdoc_test_kernel = RUSTDOC TK $< --extern bindings --extern uapi \ --no-run --crate-name kernel -Zunstable-options \ --sysroot=/dev/null \ - $(rustdoc_modifiers_workaround) \ + $(doctests_modifiers_workaround) \ --test-builder $(objtree)/scripts/rustdoc_test_builder \ $< $(rustdoc_test_kernel_quiet); \ $(objtree)/scripts/rustdoc_test_gen @@ -289,7 +298,7 @@ bindgen_skip_c_flags := -mno-fp-ret-in-387 -mpreferred-stack-boundary=% \ -fno-inline-functions-called-once -fsanitize=bounds-strict \ -fstrict-flex-arrays=% -fmin-function-alignment=% \ -fzero-init-padding-bits=% -mno-fdpic \ - --param=% --param asan-% + --param=% --param asan-% -fno-isolate-erroneous-paths-dereference # Derived from `scripts/Makefile.clang`. BINDGEN_TARGET_x86 := x86_64-linux-gnu @@ -522,6 +531,10 @@ $(obj)/pin_init.o: $(src)/pin-init/src/lib.rs $(obj)/compiler_builtins.o \ $(obj)/$(libpin_init_internal_name) $(obj)/$(libmacros_name) FORCE +$(call if_changed_rule,rustc_library) +# Even if normally `build_error` is not a kernel object, it should still be +# treated as such so that we pass the same flags. Otherwise, for instance, +# `rustc` will complain about missing sanitizer flags causing an ABI mismatch. +$(obj)/build_error.o: private is-kernel-object := y $(obj)/build_error.o: private skip_gendwarfksyms = 1 $(obj)/build_error.o: $(src)/build_error.rs $(obj)/compiler_builtins.o FORCE +$(call if_changed_rule,rustc_library) diff --git a/rust/kernel/devres.rs b/rust/kernel/devres.rs index 10a6a1789854..2392c281459e 100644 --- a/rust/kernel/devres.rs +++ b/rust/kernel/devres.rs @@ -103,7 +103,7 @@ struct Inner<T: Send> { /// /// # Invariants /// -/// [`Self::inner`] is guaranteed to be initialized and is always accessed read-only. +/// `Self::inner` is guaranteed to be initialized and is always accessed read-only. #[pin_data(PinnedDrop)] pub struct Devres<T: Send> { dev: ARef<Device>, diff --git a/rust/kernel/sync/condvar.rs b/rust/kernel/sync/condvar.rs index c6ec64295c9f..aa5b9a7a726d 100644 --- a/rust/kernel/sync/condvar.rs +++ b/rust/kernel/sync/condvar.rs @@ -36,7 +36,7 @@ pub use new_condvar; /// spuriously. /// /// Instances of [`CondVar`] need a lock class and to be pinned. The recommended way to create such -/// instances is with the [`pin_init`](crate::pin_init!) and [`new_condvar`] macros. +/// instances is with the [`pin_init`](pin_init::pin_init!) and [`new_condvar`] macros. /// /// # Examples /// diff --git a/scripts/Makefile.build b/scripts/Makefile.build index d0ee33a487be..52c08c4eb0b9 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -167,7 +167,7 @@ else ifeq ($(KBUILD_CHECKSRC),2) endif ifneq ($(KBUILD_EXTRA_WARN),) - cmd_checkdoc = PYTHONDONTWRITEBYTECODE=1 $(KERNELDOC) -none $(KDOCFLAGS) \ + cmd_checkdoc = PYTHONDONTWRITEBYTECODE=1 $(PYTHON3) $(KERNELDOC) -none $(KDOCFLAGS) \ $(if $(findstring 2, $(KBUILD_EXTRA_WARN)), -Wall) \ $< endif diff --git a/scripts/Makefile.vmlinux b/scripts/Makefile.vmlinux index ced4379550d7..cd788cac9d91 100644 --- a/scripts/Makefile.vmlinux +++ b/scripts/Makefile.vmlinux @@ -102,11 +102,24 @@ vmlinux: vmlinux.unstripped FORCE # modules.builtin.modinfo # --------------------------------------------------------------------------- +# .modinfo in vmlinux.unstripped is aligned to 8 bytes for compatibility with +# tools that expect vmlinux to have sufficiently aligned sections but the +# additional bytes used for padding .modinfo to satisfy this requirement break +# certain versions of kmod with +# +# depmod: ERROR: kmod_builtin_iter_next: unexpected string without modname prefix +# +# Strip the trailing padding bytes after extracting .modinfo to comply with +# what kmod expects to parse. +quiet_cmd_modules_builtin_modinfo = GEN $@ + cmd_modules_builtin_modinfo = $(cmd_objcopy); \ + sed -i 's/\x00\+$$/\x00/g' $@ + OBJCOPYFLAGS_modules.builtin.modinfo := -j .modinfo -O binary targets += modules.builtin.modinfo modules.builtin.modinfo: vmlinux.unstripped FORCE - $(call if_changed,objcopy) + $(call if_changed,modules_builtin_modinfo) # modules.builtin # --------------------------------------------------------------------------- diff --git a/scripts/decode_stacktrace.sh b/scripts/decode_stacktrace.sh index c73cb802a0a3..8d01b741de62 100755 --- a/scripts/decode_stacktrace.sh +++ b/scripts/decode_stacktrace.sh @@ -277,12 +277,6 @@ handle_line() { fi done - if [[ ${words[$last]} =~ ^[0-9a-f]+\] ]]; then - words[$last-1]="${words[$last-1]} ${words[$last]}" - unset words[$last] spaces[$last] - last=$(( $last - 1 )) - fi - # Extract info after the symbol if present. E.g.: # func_name+0x54/0x80 (P) # ^^^ @@ -295,6 +289,14 @@ handle_line() { last=$(( $last - 1 )) fi + # Join module name with its build id if present, as these were + # split during tokenization (e.g. "[module" and "modbuildid]"). + if [[ ${words[$last]} =~ ^[0-9a-f]+\] ]]; then + words[$last-1]="${words[$last-1]} ${words[$last]}" + unset words[$last] spaces[$last] + last=$(( $last - 1 )) + fi + if [[ ${words[$last]} =~ \[([^]]+)\] ]]; then module=${words[$last]} # some traces format is "(%pS)", which like "(foo+0x0/0x1 [bar])" diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 06fc0479a23f..4091a776e37a 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -444,6 +444,7 @@ #define X86_FEATURE_VM_PAGE_FLUSH (19*32+ 2) /* VM Page Flush MSR is supported */ #define X86_FEATURE_SEV_ES (19*32+ 3) /* "sev_es" Secure Encrypted Virtualization - Encrypted State */ #define X86_FEATURE_SEV_SNP (19*32+ 4) /* "sev_snp" Secure Encrypted Virtualization - Secure Nested Paging */ +#define X86_FEATURE_SNP_SECURE_TSC (19*32+ 8) /* SEV-SNP Secure TSC */ #define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* Virtual TSC_AUX */ #define X86_FEATURE_SME_COHERENT (19*32+10) /* hardware-enforced cache coherency */ #define X86_FEATURE_DEBUG_SWAP (19*32+14) /* "debug_swap" SEV-ES full debug state swap support */ @@ -495,6 +496,9 @@ #define X86_FEATURE_TSA_SQ_NO (21*32+11) /* AMD CPU not vulnerable to TSA-SQ */ #define X86_FEATURE_TSA_L1_NO (21*32+12) /* AMD CPU not vulnerable to TSA-L1 */ #define X86_FEATURE_CLEAR_CPU_BUF_VM (21*32+13) /* Clear CPU buffers using VERW before VMRUN */ +#define X86_FEATURE_IBPB_EXIT_TO_USER (21*32+14) /* Use IBPB on exit-to-userspace, see VMSCAPE bug */ +#define X86_FEATURE_ABMC (21*32+15) /* Assignable Bandwidth Monitoring Counters */ +#define X86_FEATURE_MSR_IMM (21*32+16) /* MSR immediate form instructions */ /* * BUG word(s) @@ -551,4 +555,5 @@ #define X86_BUG_ITS X86_BUG( 1*32+ 7) /* "its" CPU is affected by Indirect Target Selection */ #define X86_BUG_ITS_NATIVE_ONLY X86_BUG( 1*32+ 8) /* "its_native_only" CPU is affected by ITS, VMX is not affected */ #define X86_BUG_TSA X86_BUG( 1*32+ 9) /* "tsa" CPU is affected by Transient Scheduler Attacks */ +#define X86_BUG_VMSCAPE X86_BUG( 1*32+10) /* "vmscape" CPU is affected by VMSCAPE attacks from guests */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index f627196eb796..9e1720d73244 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -315,9 +315,12 @@ #define PERF_CAP_PT_IDX 16 #define MSR_PEBS_LD_LAT_THRESHOLD 0x000003f6 + +#define PERF_CAP_LBR_FMT 0x3f #define PERF_CAP_PEBS_TRAP BIT_ULL(6) #define PERF_CAP_ARCH_REG BIT_ULL(7) #define PERF_CAP_PEBS_FORMAT 0xf00 +#define PERF_CAP_FW_WRITES BIT_ULL(13) #define PERF_CAP_PEBS_BASELINE BIT_ULL(14) #define PERF_CAP_PEBS_TIMING_INFO BIT_ULL(17) #define PERF_CAP_PEBS_MASK (PERF_CAP_PEBS_TRAP | PERF_CAP_ARCH_REG | \ @@ -633,6 +636,11 @@ #define MSR_AMD_PPIN 0xc00102f1 #define MSR_AMD64_CPUID_FN_7 0xc0011002 #define MSR_AMD64_CPUID_FN_1 0xc0011004 + +#define MSR_AMD64_CPUID_EXT_FEAT 0xc0011005 +#define MSR_AMD64_CPUID_EXT_FEAT_TOPOEXT_BIT 54 +#define MSR_AMD64_CPUID_EXT_FEAT_TOPOEXT BIT_ULL(MSR_AMD64_CPUID_EXT_FEAT_TOPOEXT_BIT) + #define MSR_AMD64_LS_CFG 0xc0011020 #define MSR_AMD64_DC_CFG 0xc0011022 #define MSR_AMD64_TW_CFG 0xc0011023 @@ -701,8 +709,15 @@ #define MSR_AMD64_SNP_VMSA_REG_PROT BIT_ULL(MSR_AMD64_SNP_VMSA_REG_PROT_BIT) #define MSR_AMD64_SNP_SMT_PROT_BIT 17 #define MSR_AMD64_SNP_SMT_PROT BIT_ULL(MSR_AMD64_SNP_SMT_PROT_BIT) -#define MSR_AMD64_SNP_RESV_BIT 18 +#define MSR_AMD64_SNP_SECURE_AVIC_BIT 18 +#define MSR_AMD64_SNP_SECURE_AVIC BIT_ULL(MSR_AMD64_SNP_SECURE_AVIC_BIT) +#define MSR_AMD64_SNP_RESV_BIT 19 #define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, MSR_AMD64_SNP_RESV_BIT) +#define MSR_AMD64_SAVIC_CONTROL 0xc0010138 +#define MSR_AMD64_SAVIC_EN_BIT 0 +#define MSR_AMD64_SAVIC_EN BIT_ULL(MSR_AMD64_SAVIC_EN_BIT) +#define MSR_AMD64_SAVIC_ALLOWEDNMI_BIT 1 +#define MSR_AMD64_SAVIC_ALLOWEDNMI BIT_ULL(MSR_AMD64_SAVIC_ALLOWEDNMI_BIT) #define MSR_AMD64_RMP_BASE 0xc0010132 #define MSR_AMD64_RMP_END 0xc0010133 #define MSR_AMD64_RMP_CFG 0xc0010136 @@ -735,6 +750,7 @@ #define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS 0xc0000300 #define MSR_AMD64_PERF_CNTR_GLOBAL_CTL 0xc0000301 #define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR 0xc0000302 +#define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_SET 0xc0000303 /* AMD Hardware Feedback Support MSRs */ #define MSR_AMD_WORKLOAD_CLASS_CONFIG 0xc0000500 @@ -1225,6 +1241,8 @@ /* - AMD: */ #define MSR_IA32_MBA_BW_BASE 0xc0000200 #define MSR_IA32_SMBA_BW_BASE 0xc0000280 +#define MSR_IA32_L3_QOS_ABMC_CFG 0xc00003fd +#define MSR_IA32_L3_QOS_EXT_CFG 0xc00003ff #define MSR_IA32_EVT_CFG_BASE 0xc0000400 /* AMD-V MSRs */ diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 0f15d683817d..d420c9c066d4 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -35,6 +35,11 @@ #define MC_VECTOR 18 #define XM_VECTOR 19 #define VE_VECTOR 20 +#define CP_VECTOR 21 + +#define HV_VECTOR 28 +#define VC_VECTOR 29 +#define SX_VECTOR 30 /* Select x86 specific features in <linux/kvm.h> */ #define __KVM_HAVE_PIT @@ -411,6 +416,35 @@ struct kvm_xcrs { __u64 padding[16]; }; +#define KVM_X86_REG_TYPE_MSR 2 +#define KVM_X86_REG_TYPE_KVM 3 + +#define KVM_X86_KVM_REG_SIZE(reg) \ +({ \ + reg == KVM_REG_GUEST_SSP ? KVM_REG_SIZE_U64 : 0; \ +}) + +#define KVM_X86_REG_TYPE_SIZE(type, reg) \ +({ \ + __u64 type_size = (__u64)type << 32; \ + \ + type_size |= type == KVM_X86_REG_TYPE_MSR ? KVM_REG_SIZE_U64 : \ + type == KVM_X86_REG_TYPE_KVM ? KVM_X86_KVM_REG_SIZE(reg) : \ + 0; \ + type_size; \ +}) + +#define KVM_X86_REG_ID(type, index) \ + (KVM_REG_X86 | KVM_X86_REG_TYPE_SIZE(type, index) | index) + +#define KVM_X86_REG_MSR(index) \ + KVM_X86_REG_ID(KVM_X86_REG_TYPE_MSR, index) +#define KVM_X86_REG_KVM(index) \ + KVM_X86_REG_ID(KVM_X86_REG_TYPE_KVM, index) + +/* KVM-defined registers starting from 0 */ +#define KVM_REG_GUEST_SSP 0 + #define KVM_SYNC_X86_REGS (1UL << 0) #define KVM_SYNC_X86_SREGS (1UL << 1) #define KVM_SYNC_X86_EVENTS (1UL << 2) diff --git a/tools/arch/x86/include/uapi/asm/svm.h b/tools/arch/x86/include/uapi/asm/svm.h index 9c640a521a67..650e3256ea7d 100644 --- a/tools/arch/x86/include/uapi/asm/svm.h +++ b/tools/arch/x86/include/uapi/asm/svm.h @@ -118,6 +118,10 @@ #define SVM_VMGEXIT_AP_CREATE 1 #define SVM_VMGEXIT_AP_DESTROY 2 #define SVM_VMGEXIT_SNP_RUN_VMPL 0x80000018 +#define SVM_VMGEXIT_SAVIC 0x8000001a +#define SVM_VMGEXIT_SAVIC_REGISTER_GPA 0 +#define SVM_VMGEXIT_SAVIC_UNREGISTER_GPA 1 +#define SVM_VMGEXIT_SAVIC_SELF_GPA ~0ULL #define SVM_VMGEXIT_HV_FEATURES 0x8000fffd #define SVM_VMGEXIT_TERM_REQUEST 0x8000fffe #define SVM_VMGEXIT_TERM_REASON(reason_set, reason_code) \ diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h index f0f4a4cf84a7..9792e329343e 100644 --- a/tools/arch/x86/include/uapi/asm/vmx.h +++ b/tools/arch/x86/include/uapi/asm/vmx.h @@ -94,6 +94,8 @@ #define EXIT_REASON_BUS_LOCK 74 #define EXIT_REASON_NOTIFY 75 #define EXIT_REASON_TDCALL 77 +#define EXIT_REASON_MSR_READ_IMM 84 +#define EXIT_REASON_MSR_WRITE_IMM 85 #define VMX_EXIT_REASONS \ { EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \ @@ -158,7 +160,9 @@ { EXIT_REASON_TPAUSE, "TPAUSE" }, \ { EXIT_REASON_BUS_LOCK, "BUS_LOCK" }, \ { EXIT_REASON_NOTIFY, "NOTIFY" }, \ - { EXIT_REASON_TDCALL, "TDCALL" } + { EXIT_REASON_TDCALL, "TDCALL" }, \ + { EXIT_REASON_MSR_READ_IMM, "MSR_READ_IMM" }, \ + { EXIT_REASON_MSR_WRITE_IMM, "MSR_WRITE_IMM" } #define VMX_EXIT_REASON_FLAGS \ { VMX_EXIT_REASONS_FAILED_VMENTRY, "FAILED_VMENTRY" } diff --git a/tools/include/asm-generic/bitops/__fls.h b/tools/include/asm-generic/bitops/__fls.h index e974ec932ec1..35f33780ca6c 100644 --- a/tools/include/asm-generic/bitops/__fls.h +++ b/tools/include/asm-generic/bitops/__fls.h @@ -10,7 +10,7 @@ * * Undefined if no set bit exists, so code should check against 0 first. */ -static __always_inline unsigned int generic___fls(unsigned long word) +static __always_inline __attribute_const__ unsigned int generic___fls(unsigned long word) { unsigned int num = BITS_PER_LONG - 1; diff --git a/tools/include/asm-generic/bitops/fls.h b/tools/include/asm-generic/bitops/fls.h index 26f3ce1dd6e4..8eed3437edb9 100644 --- a/tools/include/asm-generic/bitops/fls.h +++ b/tools/include/asm-generic/bitops/fls.h @@ -10,7 +10,7 @@ * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32. */ -static __always_inline int generic_fls(unsigned int x) +static __always_inline __attribute_const__ int generic_fls(unsigned int x) { int r = 32; diff --git a/tools/include/asm-generic/bitops/fls64.h b/tools/include/asm-generic/bitops/fls64.h index 866f2b2304ff..b5f58dd261a3 100644 --- a/tools/include/asm-generic/bitops/fls64.h +++ b/tools/include/asm-generic/bitops/fls64.h @@ -16,7 +16,7 @@ * at position 64. */ #if BITS_PER_LONG == 32 -static __always_inline int fls64(__u64 x) +static __always_inline __attribute_const__ int fls64(__u64 x) { __u32 h = x >> 32; if (h) @@ -24,7 +24,7 @@ static __always_inline int fls64(__u64 x) return fls(x); } #elif BITS_PER_LONG == 64 -static __always_inline int fls64(__u64 x) +static __always_inline __attribute_const__ int fls64(__u64 x) { if (x == 0) return 0; diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index e63a71d3c607..3cd5cf15e3c9 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -597,35 +597,66 @@ struct drm_set_version { int drm_dd_minor; }; -/* DRM_IOCTL_GEM_CLOSE ioctl argument type */ +/** + * struct drm_gem_close - Argument for &DRM_IOCTL_GEM_CLOSE ioctl. + * @handle: Handle of the object to be closed. + * @pad: Padding. + * + * Releases the handle to an mm object. + */ struct drm_gem_close { - /** Handle of the object to be closed. */ __u32 handle; __u32 pad; }; -/* DRM_IOCTL_GEM_FLINK ioctl argument type */ +/** + * struct drm_gem_flink - Argument for &DRM_IOCTL_GEM_FLINK ioctl. + * @handle: Handle for the object being named. + * @name: Returned global name. + * + * Create a global name for an object, returning the name. + * + * Note that the name does not hold a reference; when the object + * is freed, the name goes away. + */ struct drm_gem_flink { - /** Handle for the object being named */ __u32 handle; - - /** Returned global name */ __u32 name; }; -/* DRM_IOCTL_GEM_OPEN ioctl argument type */ +/** + * struct drm_gem_open - Argument for &DRM_IOCTL_GEM_OPEN ioctl. + * @name: Name of object being opened. + * @handle: Returned handle for the object. + * @size: Returned size of the object + * + * Open an object using the global name, returning a handle and the size. + * + * This handle (of course) holds a reference to the object, so the object + * will not go away until the handle is deleted. + */ struct drm_gem_open { - /** Name of object being opened */ __u32 name; - - /** Returned handle for the object */ __u32 handle; - - /** Returned size of the object */ __u64 size; }; /** + * struct drm_gem_change_handle - Argument for &DRM_IOCTL_GEM_CHANGE_HANDLE ioctl. + * @handle: The handle of a gem object. + * @new_handle: An available gem handle. + * + * This ioctl changes the handle of a GEM object to the specified one. + * The new handle must be unused. On success the old handle is closed + * and all further IOCTL should refer to the new handle only. + * Calls to DRM_IOCTL_PRIME_FD_TO_HANDLE will return the new handle. + */ +struct drm_gem_change_handle { + __u32 handle; + __u32 new_handle; +}; + +/** * DRM_CAP_DUMB_BUFFER * * If set to 1, the driver supports creating dumb buffers via the @@ -1309,6 +1340,14 @@ extern "C" { */ #define DRM_IOCTL_SET_CLIENT_NAME DRM_IOWR(0xD1, struct drm_set_client_name) +/** + * DRM_IOCTL_GEM_CHANGE_HANDLE - Move an object to a different handle + * + * Some applications (notably CRIU) need objects to have specific gem handles. + * This ioctl changes the object at one gem handle to use a new gem handle. + */ +#define DRM_IOCTL_GEM_CHANGE_HANDLE DRM_IOWR(0xD2, struct drm_gem_change_handle) + /* * Device specific ioctls should only be in their respective headers * The device specific ioctl range is from 0x40 to 0x9f. diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index f0f0d49d2544..52f6000ab020 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -962,6 +962,7 @@ struct kvm_enable_cap { #define KVM_CAP_ARM_EL2_E2H0 241 #define KVM_CAP_RISCV_MP_STATE_RESET 242 #define KVM_CAP_ARM_CACHEABLE_PFNMAP_SUPPORTED 243 +#define KVM_CAP_GUEST_MEMFD_FLAGS 244 struct kvm_irq_routing_irqchip { __u32 irqchip; @@ -1598,6 +1599,8 @@ struct kvm_memory_attributes { #define KVM_MEMORY_ATTRIBUTE_PRIVATE (1ULL << 3) #define KVM_CREATE_GUEST_MEMFD _IOWR(KVMIO, 0xd4, struct kvm_create_guest_memfd) +#define GUEST_MEMFD_FLAG_MMAP (1ULL << 0) +#define GUEST_MEMFD_FLAG_INIT_SHARED (1ULL << 1) struct kvm_create_guest_memfd { __u64 size; diff --git a/tools/net/ynl/pyynl/ynl_gen_c.py b/tools/net/ynl/pyynl/ynl_gen_c.py index 58086b101057..aadeb3abcad8 100755 --- a/tools/net/ynl/pyynl/ynl_gen_c.py +++ b/tools/net/ynl/pyynl/ynl_gen_c.py @@ -861,6 +861,18 @@ class TypeIndexedArray(Type): return [f"{member} = {self.c_name};", f"{presence} = n_{self.c_name};"] + def free_needs_iter(self): + return self.sub_type == 'nest' + + def _free_lines(self, ri, var, ref): + lines = [] + if self.sub_type == 'nest': + lines += [ + f"for (i = 0; i < {var}->{ref}_count.{self.c_name}; i++)", + f'{self.nested_render_name}_free(&{var}->{ref}{self.c_name}[i]);', + ] + lines += f"free({var}->{ref}{self.c_name});", + return lines class TypeNestTypeValue(Type): def _complex_member_type(self, ri): diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index 92cf0fe2291e..ced2a1deecd7 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -345,6 +345,7 @@ 333 common io_pgetevents sys_io_pgetevents 334 common rseq sys_rseq 335 common uretprobe sys_uretprobe +336 common uprobe sys_uprobe # don't use numbers 387 through 423, add new calls after the last # 'common' entry 424 common pidfd_send_signal sys_pidfd_send_signal diff --git a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h index f291ab4f94eb..3741ea1b73d8 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h +++ b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h @@ -111,6 +111,7 @@ #define PIDFD_SELF_THREAD_GROUP -10001 /* Current thread group leader. */ #define FD_PIDFS_ROOT -10002 /* Root of the pidfs filesystem */ +#define FD_NSFS_ROOT -10003 /* Root of the nsfs filesystem */ #define FD_INVALID -10009 /* Invalid file descriptor: -10000 - EBADF = -10009 */ /* Generic flags for the *at(2) family of syscalls. */ diff --git a/tools/perf/trace/beauty/include/uapi/linux/fs.h b/tools/perf/trace/beauty/include/uapi/linux/fs.h index 0bd678a4a10e..beb4c2d1e41c 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/fs.h +++ b/tools/perf/trace/beauty/include/uapi/linux/fs.h @@ -430,10 +430,13 @@ typedef int __bitwise __kernel_rwf_t; /* buffered IO that drops the cache after reading or writing data */ #define RWF_DONTCACHE ((__force __kernel_rwf_t)0x00000080) +/* prevent pipe and socket writes from raising SIGPIPE */ +#define RWF_NOSIGNAL ((__force __kernel_rwf_t)0x00000100) + /* mask of flags supported by the kernel */ #define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\ RWF_APPEND | RWF_NOAPPEND | RWF_ATOMIC |\ - RWF_DONTCACHE) + RWF_DONTCACHE | RWF_NOSIGNAL) #define PROCFS_IOCTL_MAGIC 'f' diff --git a/tools/perf/trace/beauty/include/uapi/linux/prctl.h b/tools/perf/trace/beauty/include/uapi/linux/prctl.h index ed3aed264aeb..51c4e8c82b1e 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/prctl.h +++ b/tools/perf/trace/beauty/include/uapi/linux/prctl.h @@ -177,7 +177,17 @@ struct prctl_mm_map { #define PR_GET_TID_ADDRESS 40 +/* + * Flags for PR_SET_THP_DISABLE are only applicable when disabling. Bit 0 + * is reserved, so PR_GET_THP_DISABLE can return "1 | flags", to effectively + * return "1" when no flags were specified for PR_SET_THP_DISABLE. + */ #define PR_SET_THP_DISABLE 41 +/* + * Don't disable THPs when explicitly advised (e.g., MADV_HUGEPAGE / + * VM_HUGEPAGE, MADV_COLLAPSE). + */ +# define PR_THP_DISABLE_EXCEPT_ADVISED (1 << 1) #define PR_GET_THP_DISABLE 42 /* diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index cc26b7bf302b..948d3e8ad782 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -112,9 +112,13 @@ static bool symbol_type__filter(char __symbol_type) // 'N' first seen in: // ffffffff9b35d130 N __pfx__RNCINvNtNtNtCsbDUBuN8AbD4_4core4iter8adapters3map12map_try_foldjNtCs6vVzKs5jPr6_12drm_panic_qr7VersionuINtNtNtBa_3ops12control_flow11ControlFlowB10_ENcB10_0NCINvNvNtNtNtB8_6traits8iterator8Iterator4find5checkB10_NCNvMB12_B10_13from_segments0E0E0B12_ // a seemingly Rust mangled name + // Ditto for '1': + // root@x1:~# grep ' 1 ' /proc/kallsyms + // ffffffffb098bc00 1 __pfx__RNCINvNtNtNtCsfwaGRd4cjqE_4core4iter8adapters3map12map_try_foldjNtCskFudTml27HW_12drm_panic_qr7VersionuINtNtNtBa_3ops12control_flow11ControlFlowB10_ENcB10_0NCINvNvNtNtNtB8_6traits8iterator8Iterator4find5checkB10_NCNvMB12_B10_13from_segments0E0E0B12_ + // ffffffffb098bc10 1 _RNCINvNtNtNtCsfwaGRd4cjqE_4core4iter8adapters3map12map_try_foldjNtCskFudTml27HW_12drm_panic_qr7VersionuINtNtNtBa_3ops12control_flow11ControlFlowB10_ENcB10_0NCINvNvNtNtNtB8_6traits8iterator8Iterator4find5checkB10_NCNvMB12_B10_13from_segments0E0E0B12_ char symbol_type = toupper(__symbol_type); return symbol_type == 'T' || symbol_type == 'W' || symbol_type == 'D' || symbol_type == 'B' || - __symbol_type == 'u' || __symbol_type == 'l' || __symbol_type == 'N'; + __symbol_type == 'u' || __symbol_type == 'l' || __symbol_type == 'N' || __symbol_type == '1'; } static int prefix_underscores_count(const char *str) diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile index 6e41635bd55a..71ee69e524d7 100644 --- a/tools/testing/selftests/drivers/net/Makefile +++ b/tools/testing/selftests/drivers/net/Makefile @@ -18,6 +18,7 @@ TEST_PROGS := \ netcons_fragmented_msg.sh \ netcons_overflow.sh \ netcons_sysdata.sh \ + netcons_torture.sh \ netpoll_basic.py \ ping.py \ psp.py \ diff --git a/tools/testing/selftests/drivers/net/bonding/Makefile b/tools/testing/selftests/drivers/net/bonding/Makefile index 402d4ee84f2e..6c5c60adb5e8 100644 --- a/tools/testing/selftests/drivers/net/bonding/Makefile +++ b/tools/testing/selftests/drivers/net/bonding/Makefile @@ -14,6 +14,7 @@ TEST_PROGS := \ dev_addr_lists.sh \ mode-1-recovery-updelay.sh \ mode-2-recovery-updelay.sh \ + netcons_over_bonding.sh \ # end of TEST_PROGS TEST_FILES := \ @@ -24,6 +25,7 @@ TEST_FILES := \ TEST_INCLUDES := \ ../../../net/lib.sh \ + ../lib/sh/lib_netcons.sh \ ../../../net/forwarding/lib.sh \ # end of TEST_INCLUDES diff --git a/tools/testing/selftests/drivers/net/bonding/config b/tools/testing/selftests/drivers/net/bonding/config index 6bb290abd48b..991494376223 100644 --- a/tools/testing/selftests/drivers/net/bonding/config +++ b/tools/testing/selftests/drivers/net/bonding/config @@ -1,5 +1,6 @@ CONFIG_BONDING=y CONFIG_BRIDGE=y +CONFIG_CONFIGFS_FS=y CONFIG_DUMMY=y CONFIG_INET_ESP=y CONFIG_INET_ESP_OFFLOAD=y @@ -9,6 +10,9 @@ CONFIG_MACVLAN=y CONFIG_NET_ACT_GACT=y CONFIG_NET_CLS_FLOWER=y CONFIG_NET_CLS_MATCHALL=m +CONFIG_NETCONSOLE=m +CONFIG_NETCONSOLE_DYNAMIC=y +CONFIG_NETCONSOLE_EXTENDED_LOG=y CONFIG_NETDEVSIM=m CONFIG_NET_SCH_INGRESS=y CONFIG_NLMON=y diff --git a/tools/testing/selftests/drivers/net/bonding/netcons_over_bonding.sh b/tools/testing/selftests/drivers/net/bonding/netcons_over_bonding.sh new file mode 100755 index 000000000000..477cc9379500 --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/netcons_over_bonding.sh @@ -0,0 +1,361 @@ +#!/usr/bin/env bash +# SPDX-License-Identifier: GPL-2.0 +# +# This selftest exercises trying to have multiple netpoll users at the same +# time. +# +# This selftest has multiple smalls test inside, and the goal is to +# get interfaces with bonding and netconsole in different orders in order +# to catch any possible issue. +# +# The main test composes of four interfaces being created using netdevsim; two +# of them are bonded to serve as the netconsole's transmit interface. The +# remaining two interfaces are similarly bonded and assigned to a separate +# network namespace, which acts as the receive interface, where socat monitors +# for incoming messages. +# +# A netconsole message is then sent to ensure it is properly received across +# this configuration. +# +# Later, run a few other tests, to make sure that bonding and netconsole +# cannot coexist. +# +# The test's objective is to exercise netpoll usage when managed simultaneously +# by multiple subsystems (netconsole and bonding). +# +# Author: Breno Leitao <leitao@debian.org> + +set -euo pipefail + +SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") + +source "${SCRIPTDIR}"/../lib/sh/lib_netcons.sh + +modprobe netdevsim 2> /dev/null || true +modprobe netconsole 2> /dev/null || true +modprobe bonding 2> /dev/null || true +modprobe veth 2> /dev/null || true + +# The content of kmsg will be save to the following file +OUTPUT_FILE="/tmp/${TARGET}" + +# Check for basic system dependency and exit if not found +check_for_dependencies +# Set current loglevel to KERN_INFO(6), and default to KERN_NOTICE(5) +echo "6 5" > /proc/sys/kernel/printk +# Remove the namespace, interfaces and netconsole target on exit +trap cleanup_bond EXIT + +FORMAT="extended" +IP_VERSION="ipv4" +VETH0="veth"$(( RANDOM % 256)) +VETH1="veth"$((256 + RANDOM % 256)) +TXNS="" +RXNS="" + +# Create "bond_tx_XX" and "bond_rx_XX" interfaces, and set DSTIF and SRCIF with +# the bonding interfaces +function setup_bonding_ifaces() { + local RAND=$(( RANDOM % 100 )) + BOND_TX_MAIN_IF="bond_tx_$RAND" + BOND_RX_MAIN_IF="bond_rx_$RAND" + + # Setup TX + if ! ip -n "${TXNS}" link add "${BOND_TX_MAIN_IF}" type bond mode balance-rr + then + echo "Failed to create bond TX interface. Is CONFIG_BONDING set?" >&2 + # only clean nsim ifaces and namespace. Nothing else has been + # initialized + cleanup_bond_nsim + trap - EXIT + exit "${ksft_skip}" + fi + + # create_netdevsim() got the interface up, but it needs to be down + # before being enslaved. + ip -n "${TXNS}" \ + link set "${BOND_TX1_SLAVE_IF}" down + ip -n "${TXNS}" \ + link set "${BOND_TX2_SLAVE_IF}" down + ip -n "${TXNS}" \ + link set "${BOND_TX1_SLAVE_IF}" master "${BOND_TX_MAIN_IF}" + ip -n "${TXNS}" \ + link set "${BOND_TX2_SLAVE_IF}" master "${BOND_TX_MAIN_IF}" + ip -n "${TXNS}" \ + link set "${BOND_TX_MAIN_IF}" up + + # Setup RX + ip -n "${RXNS}" \ + link add "${BOND_RX_MAIN_IF}" type bond mode balance-rr + ip -n "${RXNS}" \ + link set "${BOND_RX1_SLAVE_IF}" down + ip -n "${RXNS}" \ + link set "${BOND_RX2_SLAVE_IF}" down + ip -n "${RXNS}" \ + link set "${BOND_RX1_SLAVE_IF}" master "${BOND_RX_MAIN_IF}" + ip -n "${RXNS}" \ + link set "${BOND_RX2_SLAVE_IF}" master "${BOND_RX_MAIN_IF}" + ip -n "${RXNS}" \ + link set "${BOND_RX_MAIN_IF}" up + + export DSTIF="${BOND_RX_MAIN_IF}" + export SRCIF="${BOND_TX_MAIN_IF}" +} + +# Create 4 netdevsim interfaces. Two of them will be bound to TX bonding iface +# and the other two will be bond to the RX interface (on the other namespace) +function create_ifaces_bond() { + BOND_TX1_SLAVE_IF=$(create_netdevsim "${NSIM_BOND_TX_1}" "${TXNS}") + BOND_TX2_SLAVE_IF=$(create_netdevsim "${NSIM_BOND_TX_2}" "${TXNS}") + BOND_RX1_SLAVE_IF=$(create_netdevsim "${NSIM_BOND_RX_1}" "${RXNS}") + BOND_RX2_SLAVE_IF=$(create_netdevsim "${NSIM_BOND_RX_2}" "${RXNS}") +} + +# netdevsim link BOND_TX to BOND_RX interfaces +function link_ifaces_bond() { + local BOND_TX1_SLAVE_IFIDX + local BOND_TX2_SLAVE_IFIDX + local BOND_RX1_SLAVE_IFIDX + local BOND_RX2_SLAVE_IFIDX + local TXNS_FD + local RXNS_FD + + BOND_TX1_SLAVE_IFIDX=$(ip netns exec "${TXNS}" \ + cat /sys/class/net/"$BOND_TX1_SLAVE_IF"/ifindex) + BOND_TX2_SLAVE_IFIDX=$(ip netns exec "${TXNS}" \ + cat /sys/class/net/"$BOND_TX2_SLAVE_IF"/ifindex) + BOND_RX1_SLAVE_IFIDX=$(ip netns exec "${RXNS}" \ + cat /sys/class/net/"$BOND_RX1_SLAVE_IF"/ifindex) + BOND_RX2_SLAVE_IFIDX=$(ip netns exec "${RXNS}" \ + cat /sys/class/net/"$BOND_RX2_SLAVE_IF"/ifindex) + + exec {TXNS_FD}</var/run/netns/"${TXNS}" + exec {RXNS_FD}</var/run/netns/"${RXNS}" + + # Linking TX ifaces to the RX ones (on the other namespace) + echo "${TXNS_FD}:$BOND_TX1_SLAVE_IFIDX $RXNS_FD:$BOND_RX1_SLAVE_IFIDX" \ + > "$NSIM_DEV_SYS_LINK" + echo "${TXNS_FD}:$BOND_TX2_SLAVE_IFIDX $RXNS_FD:$BOND_RX2_SLAVE_IFIDX" \ + > "$NSIM_DEV_SYS_LINK" + + exec {TXNS_FD}<&- + exec {RXNS_FD}<&- +} + +function create_all_ifaces() { + # setup_ns function is coming from lib.sh + setup_ns TXNS RXNS + export NAMESPACE="${RXNS}" + + # Create two interfaces for RX and two for TX + create_ifaces_bond + # Link netlink ifaces + link_ifaces_bond +} + +# configure DSTIF and SRCIF IPs +function configure_ifaces_ips() { + local IP_VERSION=${1:-"ipv4"} + select_ipv4_or_ipv6 "${IP_VERSION}" + + ip -n "${RXNS}" addr add "${DSTIP}"/24 dev "${DSTIF}" + ip -n "${RXNS}" link set "${DSTIF}" up + + ip -n "${TXNS}" addr add "${SRCIP}"/24 dev "${SRCIF}" + ip -n "${TXNS}" link set "${SRCIF}" up +} + +function test_enable_netpoll_on_enslaved_iface() { + echo 0 > "${NETCONS_PATH}"/enabled + + # At this stage, BOND_TX1_SLAVE_IF is enslaved to BOND_TX_MAIN_IF, and + # linked to BOND_RX1_SLAVE_IF inside the namespace. + echo "${BOND_TX1_SLAVE_IF}" > "${NETCONS_PATH}"/dev_name + + # This should fail with the following message in dmesg: + # netpoll: netconsole: ethX is a slave device, aborting + set +e + enable_netcons_ns 2> /dev/null + set -e + + if [[ $(cat "${NETCONS_PATH}"/enabled) -eq 1 ]] + then + echo "test failed: Bonding and netpoll cannot co-exists." >&2 + exit "${ksft_fail}" + fi +} + +function test_delete_bond_and_reenable_target() { + ip -n "${TXNS}" \ + link delete "${BOND_TX_MAIN_IF}" type bond + + # BOND_TX1_SLAVE_IF is not attached to a bond interface anymore + # netpoll can be plugged in there + echo "${BOND_TX1_SLAVE_IF}" > "${NETCONS_PATH}"/dev_name + + # this should work, since the interface is not enslaved + enable_netcons_ns + + if [[ $(cat "${NETCONS_PATH}"/enabled) -eq 0 ]] + then + echo "test failed: Unable to start netpoll on an unbond iface." >&2 + exit "${ksft_fail}" + fi +} + +# Send a netconsole message to the netconsole target +function test_send_netcons_msg_through_bond_iface() { + # Listen for netconsole port inside the namespace and + # destination interface + listen_port_and_save_to "${OUTPUT_FILE}" "${IP_VERSION}" & + # Wait for socat to start and listen to the port. + wait_for_port "${RXNS}" "${PORT}" "${IP_VERSION}" + # Send the message + echo "${MSG}: ${TARGET}" > /dev/kmsg + # Wait until socat saves the file to disk + busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" + # Make sure the message was received in the dst part + # and exit + validate_result "${OUTPUT_FILE}" "${FORMAT}" + # kill socat in case it is still running + pkill_socat +} + +# BOND_TX1_SLAVE_IF has netconsole enabled on it, bind it to BOND_TX_MAIN_IF. +# Given BOND_TX_MAIN_IF was deleted, recreate it first +function test_enslave_netcons_enabled_iface { + # netconsole got disabled while the interface was down + if [[ $(cat "${NETCONS_PATH}"/enabled) -eq 0 ]] + then + echo "test failed: netconsole expected to be enabled against BOND_TX1_SLAVE_IF" >&2 + exit "${ksft_fail}" + fi + + # recreate the bonding iface. it got deleted by previous + # test (test_delete_bond_and_reenable_target) + ip -n "${TXNS}" \ + link add "${BOND_TX_MAIN_IF}" type bond mode balance-rr + + # sub-interface need to be down before attaching to bonding + # This will also disable netconsole. + ip -n "${TXNS}" \ + link set "${BOND_TX1_SLAVE_IF}" down + ip -n "${TXNS}" \ + link set "${BOND_TX1_SLAVE_IF}" master "${BOND_TX_MAIN_IF}" + ip -n "${TXNS}" \ + link set "${BOND_TX_MAIN_IF}" up + + # netconsole got disabled while the interface was down + if [[ $(cat "${NETCONS_PATH}"/enabled) -eq 1 ]] + then + echo "test failed: Device is part of a bond iface, cannot have netcons enabled" >&2 + exit "${ksft_fail}" + fi +} + +# Get netconsole enabled on a bonding interface and attach a second +# sub-interface. +function test_enslave_iface_to_bond { + # BOND_TX_MAIN_IF has only BOND_TX1_SLAVE_IF right now + echo "${BOND_TX_MAIN_IF}" > "${NETCONS_PATH}"/dev_name + enable_netcons_ns + + # netcons is attached to bond0 and BOND_TX1_SLAVE_IF is + # part of BOND_TX_MAIN_IF. Attach BOND_TX2_SLAVE_IF to BOND_TX_MAIN_IF. + ip -n "${TXNS}" \ + link set "${BOND_TX2_SLAVE_IF}" master "${BOND_TX_MAIN_IF}" + if [[ $(cat "${NETCONS_PATH}"/enabled) -eq 0 ]] + then + echo "test failed: Netconsole should be enabled on bonding interface. Failed" >&2 + exit "${ksft_fail}" + fi +} + +function test_enslave_iff_disabled_netpoll_iface { + local ret + + # Create two interfaces. veth interfaces it known to have + # IFF_DISABLE_NETPOLL set + if ! ip link add "${VETH0}" type veth peer name "${VETH1}" + then + echo "Failed to create veth TX interface. Is CONFIG_VETH set?" >&2 + exit "${ksft_skip}" + fi + set +e + # This will print RTNETLINK answers: Device or resource busy + ip link set "${VETH0}" master "${BOND_TX_MAIN_IF}" 2> /dev/null + ret=$? + set -e + if [[ $ret -eq 0 ]] + then + echo "test failed: veth interface could not be enslaved" + exit "${ksft_fail}" + fi +} + +# Given that netconsole picks the current net namespace, we need to enable it +# from inside the TXNS namespace +function enable_netcons_ns() { + ip netns exec "${TXNS}" sh -c \ + "mount -t configfs configfs /sys/kernel/config && echo 1 > $NETCONS_PATH/enabled" +} + +#################### +# Tests start here # +#################### + +# Create regular interfaces using netdevsim and link them +create_all_ifaces + +# Setup the bonding interfaces +# BOND_RX_MAIN_IF has BOND_RX{1,2}_SLAVE_IF +# BOND_TX_MAIN_IF has BOND_TX{1,2}_SLAVE_IF +setup_bonding_ifaces + +# Configure the ips as BOND_RX1_SLAVE_IF and BOND_TX1_SLAVE_IF +configure_ifaces_ips "${IP_VERSION}" + +_create_dynamic_target "${FORMAT}" "${NETCONS_PATH}" +enable_netcons_ns +set_user_data + +# Test #1 : Create an bonding interface and attach netpoll into +# the bonding interface. Netconsole/netpoll should work on +# the bonding interface. +test_send_netcons_msg_through_bond_iface +echo "test #1: netpoll on bonding interface worked. Test passed" >&2 + +# Test #2: Attach netpoll to an enslaved interface +# Try to attach netpoll to an enslaved sub-interface (while still being part of +# a bonding interface), which shouldn't be allowed +test_enable_netpoll_on_enslaved_iface +echo "test #2: netpoll correctly rejected enslaved interface (expected behavior). Test passed." >&2 + +# Test #3: Unplug the sub-interface from bond and enable netconsole +# Detach the interface from a bonding interface and attach netpoll again +test_delete_bond_and_reenable_target +echo "test #3: Able to attach to an unbound interface. Test passed." >&2 + +# Test #4: Enslave a sub-interface that had netconsole enabled +# Try to enslave an interface that has netconsole/netpoll enabled. +# Previous test has netconsole enabled in BOND_TX1_SLAVE_IF, try to enslave it +test_enslave_netcons_enabled_iface +echo "test #4: Enslaving an interface with netpoll attached. Test passed." >&2 + +# Test #5: Enslave a sub-interface to a bonding interface +# Enslave an interface to a bond interface that has netpoll attached +# At this stage, BOND_TX_MAIN_IF is created and BOND_TX1_SLAVE_IF is part of +# it. Netconsole is currently disabled +test_enslave_iface_to_bond +echo "test #5: Enslaving an interface to bond+netpoll. Test passed." >&2 + +# Test #6: Enslave a IFF_DISABLE_NETPOLL sub-interface to a bonding interface +# At this stage, BOND_TX_MAIN_IF has both sub interface and netconsole is +# enabled. This test will try to enslave an a veth (IFF_DISABLE_NETPOLL) interface +# and it should fail, with netpoll: veth0 doesn't support polling +test_enslave_iff_disabled_netpoll_iface +echo "test #6: Enslaving IFF_DISABLE_NETPOLL ifaces to bond iface is not supported. Test passed." >&2 + +cleanup_bond +trap - EXIT +exit "${EXIT_STATUS}" diff --git a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh index 8e1085e89647..87f89fd92f8c 100644 --- a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh +++ b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh @@ -11,9 +11,11 @@ set -euo pipefail LIBDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") SRCIF="" # to be populated later +SRCIP="" # to be populated later SRCIP4="192.0.2.1" SRCIP6="fc00::1" DSTIF="" # to be populated later +DSTIP="" # to be populated later DSTIP4="192.0.2.2" DSTIP6="fc00::2" @@ -28,17 +30,23 @@ NETCONS_PATH="${NETCONS_CONFIGFS}"/"${TARGET}" # NAMESPACE will be populated by setup_ns with a random value NAMESPACE="" -# IDs for netdevsim +# IDs for netdevsim. We either use NSIM_DEV_{1,2}_ID for standard test +# or NSIM_BOND_{T,R}X_{1,2} for the bonding tests. Not both at the +# same time. NSIM_DEV_1_ID=$((256 + RANDOM % 256)) NSIM_DEV_2_ID=$((512 + RANDOM % 256)) +NSIM_BOND_TX_1=$((768 + RANDOM % 256)) +NSIM_BOND_TX_2=$((1024 + RANDOM % 256)) +NSIM_BOND_RX_1=$((1280 + RANDOM % 256)) +NSIM_BOND_RX_2=$((1536 + RANDOM % 256)) NSIM_DEV_SYS_NEW="/sys/bus/netdevsim/new_device" +NSIM_DEV_SYS_LINK="/sys/bus/netdevsim/link_device" # Used to create and delete namespaces source "${LIBDIR}"/../../../../net/lib.sh # Create netdevsim interfaces create_ifaces() { - echo "$NSIM_DEV_2_ID" > "$NSIM_DEV_SYS_NEW" echo "$NSIM_DEV_1_ID" > "$NSIM_DEV_SYS_NEW" udevadm settle 2> /dev/null || true @@ -113,31 +121,38 @@ function set_network() { configure_ip } -function create_dynamic_target() { - local FORMAT=${1:-"extended"} +function _create_dynamic_target() { + local FORMAT="${1:?FORMAT parameter required}" + local NCPATH="${2:?NCPATH parameter required}" DSTMAC=$(ip netns exec "${NAMESPACE}" \ ip link show "${DSTIF}" | awk '/ether/ {print $2}') # Create a dynamic target - mkdir "${NETCONS_PATH}" + mkdir "${NCPATH}" - echo "${DSTIP}" > "${NETCONS_PATH}"/remote_ip - echo "${SRCIP}" > "${NETCONS_PATH}"/local_ip - echo "${DSTMAC}" > "${NETCONS_PATH}"/remote_mac - echo "${SRCIF}" > "${NETCONS_PATH}"/dev_name + echo "${DSTIP}" > "${NCPATH}"/remote_ip + echo "${SRCIP}" > "${NCPATH}"/local_ip + echo "${DSTMAC}" > "${NCPATH}"/remote_mac + echo "${SRCIF}" > "${NCPATH}"/dev_name if [ "${FORMAT}" == "basic" ] then # Basic target does not support release - echo 0 > "${NETCONS_PATH}"/release - echo 0 > "${NETCONS_PATH}"/extended + echo 0 > "${NCPATH}"/release + echo 0 > "${NCPATH}"/extended elif [ "${FORMAT}" == "extended" ] then - echo 1 > "${NETCONS_PATH}"/extended + echo 1 > "${NCPATH}"/extended fi +} - echo 1 > "${NETCONS_PATH}"/enabled +function create_dynamic_target() { + local FORMAT=${1:-"extended"} + local NCPATH=${2:-"$NETCONS_PATH"} + _create_dynamic_target "${FORMAT}" "${NCPATH}" + + echo 1 > "${NCPATH}"/enabled # This will make sure that the kernel was able to # load the netconsole driver configuration. The console message @@ -185,14 +200,26 @@ function do_cleanup() { echo "${DEFAULT_PRINTK_VALUES}" > /proc/sys/kernel/printk } -function cleanup() { +function cleanup_netcons() { # delete netconsole dynamic reconfiguration - echo 0 > "${NETCONS_PATH}"/enabled + # do not fail if the target is already disabled + if [[ ! -d "${NETCONS_PATH}" ]] + then + # in some cases this is called before netcons path is created + return + fi + if [[ $(cat "${NETCONS_PATH}"/enabled) != 0 ]] + then + echo 0 > "${NETCONS_PATH}"/enabled || true + fi # Remove all the keys that got created during the selftest find "${NETCONS_PATH}/userdata/" -mindepth 1 -type d -delete # Remove the configfs entry rmdir "${NETCONS_PATH}" +} +function cleanup() { + cleanup_netcons do_cleanup } @@ -369,3 +396,24 @@ function wait_for_port() { # more frequently on IPv6 sleep 1 } + +# Clean up netdevsim ifaces created for bonding test +function cleanup_bond_nsim() { + ip -n "${TXNS}" \ + link delete "${BOND_TX_MAIN_IF}" type bond || true + ip -n "${RXNS}" \ + link delete "${BOND_RX_MAIN_IF}" type bond || true + + cleanup_netdevsim "$NSIM_BOND_TX_1" + cleanup_netdevsim "$NSIM_BOND_TX_2" + cleanup_netdevsim "$NSIM_BOND_RX_1" + cleanup_netdevsim "$NSIM_BOND_RX_2" +} + +# cleanup tests that use bonding interfaces +function cleanup_bond() { + cleanup_netcons + cleanup_bond_nsim + cleanup_all_ns + ip link delete "${VETH0}" || true +} diff --git a/tools/testing/selftests/drivers/net/netcons_torture.sh b/tools/testing/selftests/drivers/net/netcons_torture.sh new file mode 100755 index 000000000000..2ce9ee3719d1 --- /dev/null +++ b/tools/testing/selftests/drivers/net/netcons_torture.sh @@ -0,0 +1,130 @@ +#!/usr/bin/env bash +# SPDX-License-Identifier: GPL-2.0 + +# Repeatedly send kernel messages, toggles netconsole targets on and off, +# creates and deletes targets in parallel, and toggles the source interface to +# simulate stress conditions. +# +# This test aims to verify the robustness of netconsole under dynamic +# configurations and concurrent operations. +# +# The major goal is to run this test with LOCKDEP, Kmemleak and KASAN to make +# sure no issues is reported. +# +# Author: Breno Leitao <leitao@debian.org> + +set -euo pipefail + +SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") + +source "${SCRIPTDIR}"/lib/sh/lib_netcons.sh + +# Number of times the main loop run +ITERATIONS=${1:-150} + +# Only test extended format +FORMAT="extended" +# And ipv6 only +IP_VERSION="ipv6" + +# Create, enable and delete some targets. +create_and_delete_random_target() { + COUNT=2 + RND_PREFIX=$(mktemp -u netcons_rnd_XXXX_) + + if [ -d "${NETCONS_CONFIGFS}/${RND_PREFIX}${COUNT}" ] || \ + [ -d "${NETCONS_CONFIGFS}/${RND_PREFIX}0" ]; then + echo "Function didn't finish yet, skipping it." >&2 + return + fi + + # enable COUNT targets + for i in $(seq ${COUNT}) + do + RND_TARGET="${RND_PREFIX}"${i} + RND_TARGET_PATH="${NETCONS_CONFIGFS}"/"${RND_TARGET}" + + # Basic population so the target can come up + _create_dynamic_target "${FORMAT}" "${RND_TARGET_PATH}" + done + + echo "netconsole selftest: ${COUNT} additional targets were created" > /dev/kmsg + # disable them all + for i in $(seq ${COUNT}) + do + RND_TARGET="${RND_PREFIX}"${i} + RND_TARGET_PATH="${NETCONS_CONFIGFS}"/"${RND_TARGET}" + if [[ $(cat "${RND_TARGET_PATH}/enabled") -eq 1 ]] + then + echo 0 > "${RND_TARGET_PATH}"/enabled + fi + rmdir "${RND_TARGET_PATH}" + done +} + +# Disable and enable the target mid-air, while messages +# are being transmitted. +toggle_netcons_target() { + for i in $(seq 2) + do + if [ ! -d "${NETCONS_PATH}" ] + then + break + fi + echo 0 > "${NETCONS_PATH}"/enabled 2> /dev/null || true + # Try to enable a bit harder, given it might fail to enable + # Write to `enabled` might fail depending on the lock, which is + # highly contentious here + for _ in $(seq 5) + do + echo 1 > "${NETCONS_PATH}"/enabled 2> /dev/null || true + done + done +} + +toggle_iface(){ + ip link set "${SRCIF}" down + ip link set "${SRCIF}" up +} + +# Start here + +modprobe netdevsim 2> /dev/null || true +modprobe netconsole 2> /dev/null || true + +# Check for basic system dependency and exit if not found +check_for_dependencies +# Set current loglevel to KERN_INFO(6), and default to KERN_NOTICE(5) +echo "6 5" > /proc/sys/kernel/printk +# Remove the namespace, interfaces and netconsole target on exit +trap cleanup EXIT +# Create one namespace and two interfaces +set_network "${IP_VERSION}" +# Create a dynamic target for netconsole +create_dynamic_target "${FORMAT}" + +for i in $(seq "$ITERATIONS") +do + for _ in $(seq 10) + do + echo "${MSG}: ${TARGET} ${i}" > /dev/kmsg + done + wait + + if (( i % 30 == 0 )); then + toggle_netcons_target & + fi + + if (( i % 50 == 0 )); then + # create some targets, enable them, send msg and disable + # all in a parallel thread + create_and_delete_random_target & + fi + + if (( i % 70 == 0 )); then + toggle_iface & + fi +done +wait + +exit "${EXIT_STATUS}" diff --git a/tools/testing/selftests/drivers/net/netdevsim/Makefile b/tools/testing/selftests/drivers/net/netdevsim/Makefile index daf51113c827..df10c7243511 100644 --- a/tools/testing/selftests/drivers/net/netdevsim/Makefile +++ b/tools/testing/selftests/drivers/net/netdevsim/Makefile @@ -20,4 +20,8 @@ TEST_PROGS := \ udp_tunnel_nic.sh \ # end of TEST_PROGS +TEST_FILES := \ + ethtool-common.sh +# end of TEST_FILES + include ../../../lib.mk diff --git a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc index c62165fabd0c..cfa16aa1f39a 100644 --- a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc +++ b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc @@ -20,6 +20,10 @@ sample_events() { echo 0 > tracing_on echo 0 > events/enable +# Clear functions caused by page cache; run sample_events twice +sample_events +sample_events + echo "Get the most frequently calling function" echo > trace sample_events diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index 3eebf5e3b974..bb4d33dde3c8 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -2638,6 +2638,8 @@ TEST_F(vfio_compat_mock_domain, map) ASSERT_EQ(0, ioctl(self->fd, VFIO_IOMMU_MAP_DMA, &map_cmd)); ASSERT_EQ(0, ioctl(self->fd, VFIO_IOMMU_UNMAP_DMA, &unmap_cmd)); ASSERT_EQ(BUFFER_SIZE, unmap_cmd.size); + /* Unmap of empty is success */ + ASSERT_EQ(0, ioctl(self->fd, VFIO_IOMMU_UNMAP_DMA, &unmap_cmd)); /* UNMAP_FLAG_ALL requires 0 iova/size */ ASSERT_EQ(0, ioctl(self->fd, VFIO_IOMMU_MAP_DMA, &map_cmd)); diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h index 772ca1db6e59..9f472c20c190 100644 --- a/tools/testing/selftests/iommu/iommufd_utils.h +++ b/tools/testing/selftests/iommu/iommufd_utils.h @@ -1044,8 +1044,8 @@ static int _test_cmd_trigger_vevents(int fd, __u32 dev_id, __u32 nvevents) }; while (nvevents--) { - if (!ioctl(fd, _IOMMU_TEST_CMD(IOMMU_TEST_OP_TRIGGER_VEVENT), - &trigger_vevent_cmd)) + if (ioctl(fd, _IOMMU_TEST_CMD(IOMMU_TEST_OP_TRIGGER_VEVENT), + &trigger_vevent_cmd)) return -1; } return 0; diff --git a/tools/testing/selftests/kvm/arm64/get-reg-list.c b/tools/testing/selftests/kvm/arm64/get-reg-list.c index c9b84eeaab6b..0a3a94c4cca1 100644 --- a/tools/testing/selftests/kvm/arm64/get-reg-list.c +++ b/tools/testing/selftests/kvm/arm64/get-reg-list.c @@ -63,11 +63,13 @@ static struct feature_id_reg feat_id_regs[] = { REG_FEAT(HDFGWTR2_EL2, ID_AA64MMFR0_EL1, FGT, FGT2), REG_FEAT(ZCR_EL2, ID_AA64PFR0_EL1, SVE, IMP), REG_FEAT(SCTLR2_EL1, ID_AA64MMFR3_EL1, SCTLRX, IMP), + REG_FEAT(SCTLR2_EL2, ID_AA64MMFR3_EL1, SCTLRX, IMP), REG_FEAT(VDISR_EL2, ID_AA64PFR0_EL1, RAS, IMP), REG_FEAT(VSESR_EL2, ID_AA64PFR0_EL1, RAS, IMP), REG_FEAT(VNCR_EL2, ID_AA64MMFR4_EL1, NV_frac, NV2_ONLY), REG_FEAT(CNTHV_CTL_EL2, ID_AA64MMFR1_EL1, VH, IMP), REG_FEAT(CNTHV_CVAL_EL2,ID_AA64MMFR1_EL1, VH, IMP), + REG_FEAT(ZCR_EL2, ID_AA64PFR0_EL1, SVE, IMP), }; bool filter_reg(__u64 reg) @@ -718,6 +720,7 @@ static __u64 el2_regs[] = { SYS_REG(VMPIDR_EL2), SYS_REG(SCTLR_EL2), SYS_REG(ACTLR_EL2), + SYS_REG(SCTLR2_EL2), SYS_REG(HCR_EL2), SYS_REG(MDCR_EL2), SYS_REG(CPTR_EL2), diff --git a/tools/testing/selftests/kvm/lib/arm64/gic_v3_its.c b/tools/testing/selftests/kvm/lib/arm64/gic_v3_its.c index 09f270545646..0e2f8ed90f30 100644 --- a/tools/testing/selftests/kvm/lib/arm64/gic_v3_its.c +++ b/tools/testing/selftests/kvm/lib/arm64/gic_v3_its.c @@ -15,6 +15,8 @@ #include "gic_v3.h" #include "processor.h" +#define GITS_COLLECTION_TARGET_SHIFT 16 + static u64 its_read_u64(unsigned long offset) { return readq_relaxed(GITS_BASE_GVA + offset); @@ -163,6 +165,11 @@ static void its_encode_collection(struct its_cmd_block *cmd, u16 col) its_mask_encode(&cmd->raw_cmd[2], col, 15, 0); } +static u64 procnum_to_rdbase(u32 vcpu_id) +{ + return vcpu_id << GITS_COLLECTION_TARGET_SHIFT; +} + #define GITS_CMDQ_POLL_ITERATIONS 0 static void its_send_cmd(void *cmdq_base, struct its_cmd_block *cmd) @@ -217,7 +224,7 @@ void its_send_mapc_cmd(void *cmdq_base, u32 vcpu_id, u32 collection_id, bool val its_encode_cmd(&cmd, GITS_CMD_MAPC); its_encode_collection(&cmd, collection_id); - its_encode_target(&cmd, vcpu_id); + its_encode_target(&cmd, procnum_to_rdbase(vcpu_id)); its_encode_valid(&cmd, valid); its_send_cmd(cmdq_base, &cmd); diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh index ecd34f364125..892895659c7e 100755 --- a/tools/testing/selftests/net/forwarding/local_termination.sh +++ b/tools/testing/selftests/net/forwarding/local_termination.sh @@ -176,6 +176,8 @@ run_test() local rcv_dmac=$(mac_get $rcv_if_name) local should_receive + setup_wait + tcpdump_start $rcv_if_name mc_route_prepare $send_if_name diff --git a/tools/testing/selftests/net/gro.c b/tools/testing/selftests/net/gro.c index 2b1d9f2b3e9e..cfc39f70635d 100644 --- a/tools/testing/selftests/net/gro.c +++ b/tools/testing/selftests/net/gro.c @@ -754,11 +754,11 @@ static void send_ipv6_exthdr(int fd, struct sockaddr_ll *daddr, char *ext_data1, static char exthdr_pck[sizeof(buf) + MIN_EXTHDR_SIZE]; create_packet(buf, 0, 0, PAYLOAD_LEN, 0); - add_ipv6_exthdr(buf, exthdr_pck, IPPROTO_HOPOPTS, ext_data1); + add_ipv6_exthdr(buf, exthdr_pck, IPPROTO_DSTOPTS, ext_data1); write_packet(fd, exthdr_pck, total_hdr_len + PAYLOAD_LEN + MIN_EXTHDR_SIZE, daddr); create_packet(buf, PAYLOAD_LEN * 1, 0, PAYLOAD_LEN, 0); - add_ipv6_exthdr(buf, exthdr_pck, IPPROTO_HOPOPTS, ext_data2); + add_ipv6_exthdr(buf, exthdr_pck, IPPROTO_DSTOPTS, ext_data2); write_packet(fd, exthdr_pck, total_hdr_len + PAYLOAD_LEN + MIN_EXTHDR_SIZE, daddr); } @@ -989,6 +989,7 @@ static void check_recv_pkts(int fd, int *correct_payload, static void gro_sender(void) { + const int fin_delay_us = 100 * 1000; static char fin_pkt[MAX_HDR_LEN]; struct sockaddr_ll daddr = {}; int txfd = -1; @@ -1032,15 +1033,22 @@ static void gro_sender(void) write_packet(txfd, fin_pkt, total_hdr_len, &daddr); } else if (strcmp(testname, "tcp") == 0) { send_changed_checksum(txfd, &daddr); + /* Adding sleep before sending FIN so that it is not + * received prior to other packets. + */ + usleep(fin_delay_us); write_packet(txfd, fin_pkt, total_hdr_len, &daddr); send_changed_seq(txfd, &daddr); + usleep(fin_delay_us); write_packet(txfd, fin_pkt, total_hdr_len, &daddr); send_changed_ts(txfd, &daddr); + usleep(fin_delay_us); write_packet(txfd, fin_pkt, total_hdr_len, &daddr); send_diff_opt(txfd, &daddr); + usleep(fin_delay_us); write_packet(txfd, fin_pkt, total_hdr_len, &daddr); } else if (strcmp(testname, "ip") == 0) { send_changed_ECN(txfd, &daddr); diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index b148cadb96d0..fc7e22b503d3 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -710,8 +710,14 @@ static int copyfd_io_poll(int infd, int peerfd, int outfd, bw = do_rnd_write(peerfd, winfo->buf + winfo->off, winfo->len); if (bw < 0) { - if (cfg_rcv_trunc) - return 0; + /* expected reset, continue to read */ + if (cfg_rcv_trunc && + (errno == ECONNRESET || + errno == EPIPE)) { + fds.events &= ~POLLOUT; + continue; + } + perror("write"); return 111; } @@ -737,8 +743,10 @@ static int copyfd_io_poll(int infd, int peerfd, int outfd, } if (fds.revents & (POLLERR | POLLNVAL)) { - if (cfg_rcv_trunc) - return 0; + if (cfg_rcv_trunc) { + fds.events &= ~(POLLERR | POLLNVAL); + continue; + } fprintf(stderr, "Unexpected revents: " "POLLERR/POLLNVAL(%x)\n", fds.revents); return 5; @@ -1433,7 +1441,7 @@ static void parse_opts(int argc, char **argv) */ if (cfg_truncate < 0) { cfg_rcv_trunc = true; - signal(SIGPIPE, handle_signal); + signal(SIGPIPE, SIG_IGN); } break; case 'j': diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index 47ecb5b3836e..9b7b93f8eb0c 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -492,7 +492,7 @@ do_transfer() "than expected (${expect_synrx})" retc=1 fi - if [ ${stat_ackrx_now_l} -lt ${expect_ackrx} ] && [ ${stat_ooo_now} -eq 0 ]; then + if [ ${stat_ackrx_now_l} -lt ${expect_ackrx} ]; then if [ ${stat_ooo_now} -eq 0 ]; then mptcp_lib_pr_fail "lower MPC ACK rx (${stat_ackrx_now_l})" \ "than expected (${expect_ackrx})" diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 78a1aa4ecff2..41503c241989 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -2532,7 +2532,7 @@ remove_tests() if reset "remove single subflow"; then pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow,backup addr_nr_ns2=-1 speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 1 @@ -2545,8 +2545,8 @@ remove_tests() if reset "remove multiple subflows"; then pm_nl_set_limits $ns1 0 2 pm_nl_set_limits $ns2 0 2 - pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow,backup + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow,backup addr_nr_ns2=-2 speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 2 2 2 @@ -2557,7 +2557,7 @@ remove_tests() # single address, remove if reset "remove single address"; then pm_nl_set_limits $ns1 0 1 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal,backup pm_nl_set_limits $ns2 1 1 addr_nr_ns1=-1 speed=slow \ run_tests $ns1 $ns2 10.0.1.1 @@ -2570,9 +2570,9 @@ remove_tests() # subflow and signal, remove if reset "remove subflow and signal"; then pm_nl_set_limits $ns1 0 2 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal,backup pm_nl_set_limits $ns2 1 2 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow,backup addr_nr_ns1=-1 addr_nr_ns2=-1 speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 2 2 2 @@ -2584,10 +2584,10 @@ remove_tests() # subflows and signal, remove if reset "remove subflows and signal"; then pm_nl_set_limits $ns1 0 3 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal,backup pm_nl_set_limits $ns2 1 3 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow,backup + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow,backup addr_nr_ns1=-1 addr_nr_ns2=-2 speed=10 \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 3 3 3 @@ -2599,9 +2599,9 @@ remove_tests() # addresses remove if reset "remove addresses"; then pm_nl_set_limits $ns1 3 3 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal id 250 - pm_nl_add_endpoint $ns1 10.0.3.1 flags signal - pm_nl_add_endpoint $ns1 10.0.4.1 flags signal + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal,backup id 250 + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal,backup + pm_nl_add_endpoint $ns1 10.0.4.1 flags signal,backup pm_nl_set_limits $ns2 3 3 addr_nr_ns1=-3 speed=10 \ run_tests $ns1 $ns2 10.0.1.1 @@ -2614,10 +2614,10 @@ remove_tests() # invalid addresses remove if reset "remove invalid addresses"; then pm_nl_set_limits $ns1 3 3 - pm_nl_add_endpoint $ns1 10.0.12.1 flags signal + pm_nl_add_endpoint $ns1 10.0.12.1 flags signal,backup # broadcast IP: no packet for this address will be received on ns1 - pm_nl_add_endpoint $ns1 224.0.0.1 flags signal - pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 224.0.0.1 flags signal,backup + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal,backup pm_nl_set_limits $ns2 2 2 addr_nr_ns1=-3 speed=10 \ run_tests $ns1 $ns2 10.0.1.1 @@ -2631,10 +2631,10 @@ remove_tests() # subflows and signal, flush if reset "flush subflows and signal"; then pm_nl_set_limits $ns1 0 3 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal,backup pm_nl_set_limits $ns2 1 3 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow,backup + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow,backup addr_nr_ns1=-8 addr_nr_ns2=-8 speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 3 3 3 @@ -2647,9 +2647,9 @@ remove_tests() if reset "flush subflows"; then pm_nl_set_limits $ns1 3 3 pm_nl_set_limits $ns2 3 3 - pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow id 150 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow,backup id 150 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow,backup + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow,backup addr_nr_ns1=-8 addr_nr_ns2=-8 speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 3 3 3 @@ -2666,9 +2666,9 @@ remove_tests() # addresses flush if reset "flush addresses"; then pm_nl_set_limits $ns1 3 3 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal id 250 - pm_nl_add_endpoint $ns1 10.0.3.1 flags signal - pm_nl_add_endpoint $ns1 10.0.4.1 flags signal + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal,backup id 250 + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal,backup + pm_nl_add_endpoint $ns1 10.0.4.1 flags signal,backup pm_nl_set_limits $ns2 3 3 addr_nr_ns1=-8 addr_nr_ns2=-8 speed=slow \ run_tests $ns1 $ns2 10.0.1.1 @@ -2681,9 +2681,9 @@ remove_tests() # invalid addresses flush if reset "flush invalid addresses"; then pm_nl_set_limits $ns1 3 3 - pm_nl_add_endpoint $ns1 10.0.12.1 flags signal - pm_nl_add_endpoint $ns1 10.0.3.1 flags signal - pm_nl_add_endpoint $ns1 10.0.14.1 flags signal + pm_nl_add_endpoint $ns1 10.0.12.1 flags signal,backup + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal,backup + pm_nl_add_endpoint $ns1 10.0.14.1 flags signal,backup pm_nl_set_limits $ns2 3 3 addr_nr_ns1=-8 speed=slow \ run_tests $ns1 $ns2 10.0.1.1 @@ -3806,7 +3806,7 @@ userspace_tests() continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 pm_nl_set_limits $ns2 2 2 - { speed=5 \ + { test_linkfail=128 speed=5 \ run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null local tests_pid=$! wait_mpj $ns1 @@ -3831,7 +3831,7 @@ userspace_tests() chk_mptcp_info subflows 0 subflows 0 chk_subflows_total 1 1 kill_events_pids - mptcp_lib_kill_wait $tests_pid + mptcp_lib_kill_group_wait $tests_pid fi # userspace pm create destroy subflow @@ -3839,7 +3839,7 @@ userspace_tests() continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns2 pm_nl_set_limits $ns1 0 1 - { speed=5 \ + { test_linkfail=128 speed=5 \ run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null local tests_pid=$! wait_mpj $ns2 @@ -3859,7 +3859,7 @@ userspace_tests() chk_mptcp_info subflows 0 subflows 0 chk_subflows_total 1 1 kill_events_pids - mptcp_lib_kill_wait $tests_pid + mptcp_lib_kill_group_wait $tests_pid fi # userspace pm create id 0 subflow @@ -3867,7 +3867,7 @@ userspace_tests() continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns2 pm_nl_set_limits $ns1 0 1 - { speed=5 \ + { test_linkfail=128 speed=5 \ run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null local tests_pid=$! wait_mpj $ns2 @@ -3880,7 +3880,7 @@ userspace_tests() chk_mptcp_info subflows 1 subflows 1 chk_subflows_total 2 2 kill_events_pids - mptcp_lib_kill_wait $tests_pid + mptcp_lib_kill_group_wait $tests_pid fi # userspace pm remove initial subflow @@ -3888,7 +3888,7 @@ userspace_tests() continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns2 pm_nl_set_limits $ns1 0 1 - { speed=5 \ + { test_linkfail=128 speed=5 \ run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null local tests_pid=$! wait_mpj $ns2 @@ -3904,7 +3904,7 @@ userspace_tests() chk_mptcp_info subflows 1 subflows 1 chk_subflows_total 1 1 kill_events_pids - mptcp_lib_kill_wait $tests_pid + mptcp_lib_kill_group_wait $tests_pid fi # userspace pm send RM_ADDR for ID 0 @@ -3912,7 +3912,7 @@ userspace_tests() continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 pm_nl_set_limits $ns2 1 1 - { speed=5 \ + { test_linkfail=128 speed=5 \ run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null local tests_pid=$! wait_mpj $ns1 @@ -3930,7 +3930,7 @@ userspace_tests() chk_mptcp_info subflows 1 subflows 1 chk_subflows_total 1 1 kill_events_pids - mptcp_lib_kill_wait $tests_pid + mptcp_lib_kill_group_wait $tests_pid fi } @@ -3943,7 +3943,7 @@ endpoint_tests() pm_nl_set_limits $ns1 2 2 pm_nl_set_limits $ns2 2 2 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - { speed=slow \ + { test_linkfail=128 speed=slow \ run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null local tests_pid=$! @@ -3960,7 +3960,7 @@ endpoint_tests() pm_nl_add_endpoint $ns2 10.0.2.2 flags signal pm_nl_check_endpoint "modif is allowed" \ $ns2 10.0.2.2 id 1 flags signal - mptcp_lib_kill_wait $tests_pid + mptcp_lib_kill_group_wait $tests_pid fi if reset_with_tcp_filter "delete and re-add" ns2 10.0.3.2 REJECT OUTPUT && @@ -3970,7 +3970,7 @@ endpoint_tests() pm_nl_set_limits $ns2 0 3 pm_nl_add_endpoint $ns2 10.0.1.2 id 1 dev ns2eth1 flags subflow pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow - { test_linkfail=4 speed=5 \ + { test_linkfail=128 speed=5 \ run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null local tests_pid=$! @@ -4015,7 +4015,7 @@ endpoint_tests() chk_mptcp_info subflows 3 subflows 3 done - mptcp_lib_kill_wait $tests_pid + mptcp_lib_kill_group_wait $tests_pid kill_events_pids chk_evt_nr ns1 MPTCP_LIB_EVENT_LISTENER_CREATED 1 @@ -4048,7 +4048,7 @@ endpoint_tests() # broadcast IP: no packet for this address will be received on ns1 pm_nl_add_endpoint $ns1 224.0.0.1 id 2 flags signal pm_nl_add_endpoint $ns1 10.0.1.1 id 42 flags signal - { test_linkfail=4 speed=5 \ + { test_linkfail=128 speed=5 \ run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null local tests_pid=$! @@ -4089,7 +4089,7 @@ endpoint_tests() wait_mpj $ns2 chk_subflow_nr "after re-re-add ID 0" 3 chk_mptcp_info subflows 3 subflows 3 - mptcp_lib_kill_wait $tests_pid + mptcp_lib_kill_group_wait $tests_pid kill_events_pids chk_evt_nr ns1 MPTCP_LIB_EVENT_LISTENER_CREATED 1 @@ -4121,7 +4121,7 @@ endpoint_tests() # broadcast IP: no packet for this address will be received on ns1 pm_nl_add_endpoint $ns1 224.0.0.1 id 2 flags signal pm_nl_add_endpoint $ns2 10.0.3.2 id 3 flags subflow - { test_linkfail=4 speed=20 \ + { test_linkfail=128 speed=20 \ run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null local tests_pid=$! @@ -4137,7 +4137,7 @@ endpoint_tests() wait_mpj $ns2 pm_nl_add_endpoint $ns1 10.0.3.1 id 2 flags signal wait_mpj $ns2 - mptcp_lib_kill_wait $tests_pid + mptcp_lib_kill_group_wait $tests_pid join_syn_tx=3 join_connect_err=1 \ chk_join_nr 2 2 2 diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index d62e653d48b0..f4388900016a 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -350,6 +350,27 @@ mptcp_lib_kill_wait() { wait "${1}" 2>/dev/null } +# $1: PID +mptcp_lib_pid_list_children() { + local curr="${1}" + # evoke 'ps' only once + local pids="${2:-"$(ps o pid,ppid)"}" + + echo "${curr}" + + local pid + for pid in $(echo "${pids}" | awk "\$2 == ${curr} { print \$1 }"); do + mptcp_lib_pid_list_children "${pid}" "${pids}" + done +} + +# $1: PID +mptcp_lib_kill_group_wait() { + # Some users might not have procps-ng: cannot use "kill -- -PID" + mptcp_lib_pid_list_children "${1}" | xargs -r kill &>/dev/null + wait "${1}" 2>/dev/null +} + # $1: IP address mptcp_lib_is_v6() { [ -z "${1##*:*}" ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json index 998e5a2f4579..0091bcd91c2c 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json +++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json @@ -961,5 +961,49 @@ "teardown": [ "$TC qdisc del dev $DUMMY root" ] + }, + { + "id": "4989", + "name": "Try to add an fq child to an ingress qdisc", + "category": [ + "qdisc", + "ingress" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DUMMY handle ffff:0 ingress" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY parent ffff:0 handle ffe0:0 fq", + "expExitCode": "2", + "verifyCmd": "$TC -j qdisc ls dev $DUMMY handle ffe0:", + "matchJSON": [], + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY ingress" + ] + }, + { + "id": "c2b0", + "name": "Try to add an fq child to a clsact qdisc", + "category": [ + "qdisc", + "ingress" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DUMMY handle ffff:0 clsact" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY parent ffff:0 handle ffe0:0 fq", + "expExitCode": "2", + "verifyCmd": "$TC -j qdisc ls dev $DUMMY handle ffe0:", + "matchJSON": [], + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY clsact" + ] } ] diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh index edacebfc1632..8ceeb8a7894f 100755 --- a/tools/testing/selftests/vsock/vmtest.sh +++ b/tools/testing/selftests/vsock/vmtest.sh @@ -389,9 +389,9 @@ run_test() { local rc host_oops_cnt_before=$(dmesg | grep -c -i 'Oops') - host_warn_cnt_before=$(dmesg --level=warn | wc -l) + host_warn_cnt_before=$(dmesg --level=warn | grep -c -i 'vsock') vm_oops_cnt_before=$(vm_ssh -- dmesg | grep -c -i 'Oops') - vm_warn_cnt_before=$(vm_ssh -- dmesg --level=warn | wc -l) + vm_warn_cnt_before=$(vm_ssh -- dmesg --level=warn | grep -c -i 'vsock') name=$(echo "${1}" | awk '{ print $1 }') eval test_"${name}" @@ -403,7 +403,7 @@ run_test() { rc=$KSFT_FAIL fi - host_warn_cnt_after=$(dmesg --level=warn | wc -l) + host_warn_cnt_after=$(dmesg --level=warn | grep -c -i 'vsock') if [[ ${host_warn_cnt_after} -gt ${host_warn_cnt_before} ]]; then echo "FAIL: kernel warning detected on host" | log_host "${name}" rc=$KSFT_FAIL @@ -415,7 +415,7 @@ run_test() { rc=$KSFT_FAIL fi - vm_warn_cnt_after=$(vm_ssh -- dmesg --level=warn | wc -l) + vm_warn_cnt_after=$(vm_ssh -- dmesg --level=warn | grep -c -i 'vsock') if [[ ${vm_warn_cnt_after} -gt ${vm_warn_cnt_before} ]]; then echo "FAIL: kernel warning detected on vm" | log_host "${name}" rc=$KSFT_FAIL diff --git a/tools/tracing/latency/latency-collector.c b/tools/tracing/latency/latency-collector.c index cf263fe9deaf..ef97916e3873 100644 --- a/tools/tracing/latency/latency-collector.c +++ b/tools/tracing/latency/latency-collector.c @@ -1725,7 +1725,7 @@ static void show_usage(void) "-n, --notrace\t\tIf latency is detected, do not print out the content of\n" "\t\t\tthe trace file to standard output\n\n" -"-t, --threads NRTHR\tRun NRTHR threads for printing. Default is %d.\n\n" +"-e, --threads NRTHR\tRun NRTHR threads for printing. Default is %d.\n\n" "-r, --random\t\tArbitrarily sleep a certain amount of time, default\n" "\t\t\t%ld ms, before reading the trace file. The\n" diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index fbca8c0972da..ffadc5ee8e04 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -623,31 +623,50 @@ err: return r; } -void kvm_gmem_unbind(struct kvm_memory_slot *slot) +static void __kvm_gmem_unbind(struct kvm_memory_slot *slot, struct kvm_gmem *gmem) { unsigned long start = slot->gmem.pgoff; unsigned long end = start + slot->npages; - struct kvm_gmem *gmem; + + xa_store_range(&gmem->bindings, start, end - 1, NULL, GFP_KERNEL); + + /* + * synchronize_srcu(&kvm->srcu) ensured that kvm_gmem_get_pfn() + * cannot see this memslot. + */ + WRITE_ONCE(slot->gmem.file, NULL); +} + +void kvm_gmem_unbind(struct kvm_memory_slot *slot) +{ struct file *file; /* - * Nothing to do if the underlying file was already closed (or is being - * closed right now), kvm_gmem_release() invalidates all bindings. + * Nothing to do if the underlying file was _already_ closed, as + * kvm_gmem_release() invalidates and nullifies all bindings. */ - file = kvm_gmem_get_file(slot); - if (!file) + if (!slot->gmem.file) return; - gmem = file->private_data; - - filemap_invalidate_lock(file->f_mapping); - xa_store_range(&gmem->bindings, start, end - 1, NULL, GFP_KERNEL); + file = kvm_gmem_get_file(slot); /* - * synchronize_srcu(&kvm->srcu) ensured that kvm_gmem_get_pfn() - * cannot see this memslot. + * However, if the file is _being_ closed, then the bindings need to be + * removed as kvm_gmem_release() might not run until after the memslot + * is freed. Note, modifying the bindings is safe even though the file + * is dying as kvm_gmem_release() nullifies slot->gmem.file under + * slots_lock, and only puts its reference to KVM after destroying all + * bindings. I.e. reaching this point means kvm_gmem_release() hasn't + * yet destroyed the bindings or freed the gmem_file, and can't do so + * until the caller drops slots_lock. */ - WRITE_ONCE(slot->gmem.file, NULL); + if (!file) { + __kvm_gmem_unbind(slot, slot->gmem.file->private_data); + return; + } + + filemap_invalidate_lock(file->f_mapping); + __kvm_gmem_unbind(slot, file->private_data); filemap_invalidate_unlock(file->f_mapping); fput(file); |