diff options
107 files changed, 1041 insertions, 592 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> Ondřej 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/MAINTAINERS b/MAINTAINERS index ddecf1ef3bed..69e27908f74c 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/ @@ -13659,7 +13660,7 @@ 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> @@ -16498,12 +16499,12 @@ 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 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/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/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/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/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/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/fs/btrfs/inode.c b/fs/btrfs/inode.c index 3df5f36185a0..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 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 c90b2d2cb08f..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); 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/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/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/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/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/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/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 f1a5373eee7b..1bf65c421325 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); } 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/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/rust/Makefile b/rust/Makefile index 3e545c1a0ff4..7842ad0a4ea7 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -298,7 +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 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/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/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); |