diff options
| author |  Ingo Molnar <mingo@kernel.org>
| 2023-01-18 11:56:01 +0100 |
|---|---|---|
| committer | Ingo Molnar <mingo@kernel.org>
| 2023-01-18 11:56:57 +0100 |
| commit | 65adf3a57c0c2e79c5c2b72a4bdcabcab9e99ec1 (patch) | |
| tree | ee08845127f4cd8d6fc816fbaf0e5f6f4330bc58 /arch | |
| parent | x86/kprobes: Use switch-case for 0xFF opcodes in prepare_emulation (diff) | |
| parent | Linux 6.2-rc4 (diff) | |
| download | linux-65adf3a57c0c2e79c5c2b72a4bdcabcab9e99ec1.tar.gz linux-65adf3a57c0c2e79c5c2b72a4bdcabcab9e99ec1.tar.bz2 linux-65adf3a57c0c2e79c5c2b72a4bdcabcab9e99ec1.zip | |
Merge tag 'v6.2-rc4' into perf/core, to pick up fixes
Move from the -rc1 base to the fresher -rc4 kernel that
has various fixes included, before applying a larger
patchset.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'arch')
88 files changed, 805 insertions, 542 deletions
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h index aecc403b2880..7f092cb55a41 100644 --- a/arch/arm/include/asm/thread_info.h +++ b/arch/arm/include/asm/thread_info.h @@ -128,15 +128,16 @@ extern int vfp_restore_user_hwstate(struct user_vfp *, #define TIF_NEED_RESCHED 1 /* rescheduling necessary */ #define TIF_NOTIFY_RESUME 2 /* callback before returning to user */ #define TIF_UPROBE 3 /* breakpointed or singlestepping */ -#define TIF_SYSCALL_TRACE 4 /* syscall trace active */ -#define TIF_SYSCALL_AUDIT 5 /* syscall auditing active */ -#define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */ -#define TIF_SECCOMP 7 /* seccomp syscall filtering active */ -#define TIF_NOTIFY_SIGNAL 8 /* signal notifications exist */ +#define TIF_NOTIFY_SIGNAL 4 /* signal notifications exist */ #define TIF_USING_IWMMXT 17 #define TIF_MEMDIE 18 /* is terminating due to OOM killer */ -#define TIF_RESTORE_SIGMASK 20 +#define TIF_RESTORE_SIGMASK 19 +#define TIF_SYSCALL_TRACE 20 /* syscall trace active */ +#define TIF_SYSCALL_AUDIT 21 /* syscall auditing active */ +#define TIF_SYSCALL_TRACEPOINT 22 /* syscall tracepoint instrumentation */ +#define TIF_SECCOMP 23 /* seccomp syscall filtering active */ + #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 03934808b2ed..c5ccca26a408 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -184,8 +184,6 @@ config ARM64 select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE - select HAVE_DYNAMIC_FTRACE_WITH_ARGS \ - if $(cc-option,-fpatchable-function-entry=2) select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \ if DYNAMIC_FTRACE_WITH_ARGS select HAVE_EFFICIENT_UNALIGNED_ACCESS @@ -972,6 +970,22 @@ config ARM64_ERRATUM_2457168 If unsure, say Y. +config ARM64_ERRATUM_2645198 + bool "Cortex-A715: 2645198: Workaround possible [ESR|FAR]_ELx corruption" + default y + help + This option adds the workaround for ARM Cortex-A715 erratum 2645198. + + If a Cortex-A715 cpu sees a page mapping permissions change from executable + to non-executable, it may corrupt the ESR_ELx and FAR_ELx registers on the + next instruction abort caused by permission fault. + + Only user-space does executable to non-executable permission transition via + mprotect() system call. Workaround the problem by doing a break-before-make + TLB invalidation, for all changes to executable user space mappings. + + If unsure, say Y. + config CAVIUM_ERRATUM_22375 bool "Cavium erratum 22375, 24313" default y diff --git a/arch/arm64/crypto/sm4-ce-ccm-core.S b/arch/arm64/crypto/sm4-ce-ccm-core.S index 028207c4afd0..fa85856f33ce 100644 --- a/arch/arm64/crypto/sm4-ce-ccm-core.S +++ b/arch/arm64/crypto/sm4-ce-ccm-core.S @@ -8,6 +8,7 @@ */ #include <linux/linkage.h> +#include <linux/cfi_types.h> #include <asm/assembler.h> #include "sm4-ce-asm.h" @@ -104,7 +105,7 @@ SYM_FUNC_START(sm4_ce_ccm_final) SYM_FUNC_END(sm4_ce_ccm_final) .align 3 -SYM_FUNC_START(sm4_ce_ccm_enc) +SYM_TYPED_FUNC_START(sm4_ce_ccm_enc) /* input: * x0: round key array, CTX * x1: dst @@ -216,7 +217,7 @@ SYM_FUNC_START(sm4_ce_ccm_enc) SYM_FUNC_END(sm4_ce_ccm_enc) .align 3 -SYM_FUNC_START(sm4_ce_ccm_dec) +SYM_TYPED_FUNC_START(sm4_ce_ccm_dec) /* input: * x0: round key array, CTX * x1: dst diff --git a/arch/arm64/crypto/sm4-ce-gcm-core.S b/arch/arm64/crypto/sm4-ce-gcm-core.S index 7aa3ec18a289..347f25d75727 100644 --- a/arch/arm64/crypto/sm4-ce-gcm-core.S +++ b/arch/arm64/crypto/sm4-ce-gcm-core.S @@ -9,6 +9,7 @@ */ #include <linux/linkage.h> +#include <linux/cfi_types.h> #include <asm/assembler.h> #include "sm4-ce-asm.h" @@ -370,7 +371,7 @@ SYM_FUNC_START(pmull_ghash_update) SYM_FUNC_END(pmull_ghash_update) .align 3 -SYM_FUNC_START(sm4_ce_pmull_gcm_enc) +SYM_TYPED_FUNC_START(sm4_ce_pmull_gcm_enc) /* input: * x0: round key array, CTX * x1: dst @@ -581,7 +582,7 @@ SYM_FUNC_END(sm4_ce_pmull_gcm_enc) #define RH3 v20 .align 3 -SYM_FUNC_START(sm4_ce_pmull_gcm_dec) +SYM_TYPED_FUNC_START(sm4_ce_pmull_gcm_dec) /* input: * x0: round key array, CTX * x1: dst diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h index 0890e4f568fb..cbb3d961123b 100644 --- a/arch/arm64/include/asm/atomic_ll_sc.h +++ b/arch/arm64/include/asm/atomic_ll_sc.h @@ -315,7 +315,7 @@ __ll_sc__cmpxchg_double##name(unsigned long old1, \ " cbnz %w0, 1b\n" \ " " #mb "\n" \ "2:" \ - : "=&r" (tmp), "=&r" (ret), "+Q" (*(unsigned long *)ptr) \ + : "=&r" (tmp), "=&r" (ret), "+Q" (*(__uint128_t *)ptr) \ : "r" (old1), "r" (old2), "r" (new1), "r" (new2) \ : cl); \ \ diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h index 52075e93de6c..a94d6dacc029 100644 --- a/arch/arm64/include/asm/atomic_lse.h +++ b/arch/arm64/include/asm/atomic_lse.h @@ -311,7 +311,7 @@ __lse__cmpxchg_double##name(unsigned long old1, \ " eor %[old2], %[old2], %[oldval2]\n" \ " orr %[old1], %[old1], %[old2]" \ : [old1] "+&r" (x0), [old2] "+&r" (x1), \ - [v] "+Q" (*(unsigned long *)ptr) \ + [v] "+Q" (*(__uint128_t *)ptr) \ : [new1] "r" (x2), [new2] "r" (x3), [ptr] "r" (x4), \ [oldval1] "r" (oldval1), [oldval2] "r" (oldval2) \ : cl); \ diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 4e8b66c74ea2..683ca3af4084 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -124,6 +124,8 @@ #define APPLE_CPU_PART_M1_FIRESTORM_PRO 0x025 #define APPLE_CPU_PART_M1_ICESTORM_MAX 0x028 #define APPLE_CPU_PART_M1_FIRESTORM_MAX 0x029 +#define APPLE_CPU_PART_M2_BLIZZARD 0x032 +#define APPLE_CPU_PART_M2_AVALANCHE 0x033 #define AMPERE_CPU_PART_AMPERE1 0xAC3 @@ -177,6 +179,8 @@ #define MIDR_APPLE_M1_FIRESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_PRO) #define MIDR_APPLE_M1_ICESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_MAX) #define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX) +#define MIDR_APPLE_M2_BLIZZARD MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD) +#define MIDR_APPLE_M2_AVALANCHE MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE) #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1) /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */ diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index 15b34fbfca66..206de10524e3 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -114,6 +114,15 @@ #define ESR_ELx_FSC_ACCESS (0x08) #define ESR_ELx_FSC_FAULT (0x04) #define ESR_ELx_FSC_PERM (0x0C) +#define ESR_ELx_FSC_SEA_TTW0 (0x14) +#define ESR_ELx_FSC_SEA_TTW1 (0x15) +#define ESR_ELx_FSC_SEA_TTW2 (0x16) +#define ESR_ELx_FSC_SEA_TTW3 (0x17) +#define ESR_ELx_FSC_SECC (0x18) +#define ESR_ELx_FSC_SECC_TTW0 (0x1c) +#define ESR_ELx_FSC_SECC_TTW1 (0x1d) +#define ESR_ELx_FSC_SECC_TTW2 (0x1e) +#define ESR_ELx_FSC_SECC_TTW3 (0x1f) /* ISS field definitions for Data Aborts */ #define ESR_ELx_ISV_SHIFT (24) diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h index d20f5da2d76f..6a4a1ab8eb23 100644 --- a/arch/arm64/include/asm/hugetlb.h +++ b/arch/arm64/include/asm/hugetlb.h @@ -49,6 +49,15 @@ extern pte_t huge_ptep_get(pte_t *ptep); void __init arm64_hugetlb_cma_reserve(void); +#define huge_ptep_modify_prot_start huge_ptep_modify_prot_start +extern pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep); + +#define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit +extern void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t old_pte, pte_t new_pte); + #include <asm-generic/hugetlb.h> #endif /* __ASM_HUGETLB_H */ diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 0df3fc3a0173..26b0c97df986 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -319,21 +319,6 @@ BIT(18) | \ GENMASK(16, 15)) -/* For compatibility with fault code shared with 32-bit */ -#define FSC_FAULT ESR_ELx_FSC_FAULT -#define FSC_ACCESS ESR_ELx_FSC_ACCESS -#define FSC_PERM ESR_ELx_FSC_PERM -#define FSC_SEA ESR_ELx_FSC_EXTABT -#define FSC_SEA_TTW0 (0x14) -#define FSC_SEA_TTW1 (0x15) -#define FSC_SEA_TTW2 (0x16) -#define FSC_SEA_TTW3 (0x17) -#define FSC_SECC (0x18) -#define FSC_SECC_TTW0 (0x1c) -#define FSC_SECC_TTW1 (0x1d) -#define FSC_SECC_TTW2 (0x1e) -#define FSC_SECC_TTW3 (0x1f) - /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */ #define HPFAR_MASK (~UL(0xf)) /* diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 9bdba47f7e14..193583df2d9c 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -349,16 +349,16 @@ static __always_inline u8 kvm_vcpu_trap_get_fault_level(const struct kvm_vcpu *v static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu) { switch (kvm_vcpu_trap_get_fault(vcpu)) { - case FSC_SEA: - case FSC_SEA_TTW0: - case FSC_SEA_TTW1: - case FSC_SEA_TTW2: - case FSC_SEA_TTW3: - case FSC_SECC: - case FSC_SECC_TTW0: - case FSC_SECC_TTW1: - case FSC_SECC_TTW2: - case FSC_SECC_TTW3: + case ESR_ELx_FSC_EXTABT: + case ESR_ELx_FSC_SEA_TTW0: + case ESR_ELx_FSC_SEA_TTW1: + case ESR_ELx_FSC_SEA_TTW2: + case ESR_ELx_FSC_SEA_TTW3: + case ESR_ELx_FSC_SECC: + case ESR_ELx_FSC_SECC_TTW0: + case ESR_ELx_FSC_SECC_TTW1: + case ESR_ELx_FSC_SECC_TTW2: + case ESR_ELx_FSC_SECC_TTW3: return true; default: return false; @@ -373,8 +373,26 @@ static __always_inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu) static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu) { - if (kvm_vcpu_abt_iss1tw(vcpu)) - return true; + if (kvm_vcpu_abt_iss1tw(vcpu)) { + /* + * Only a permission fault on a S1PTW should be + * considered as a write. Otherwise, page tables baked + * in a read-only memslot will result in an exception + * being delivered in the guest. + * + * The drawback is that we end-up faulting twice if the + * guest is using any of HW AF/DB: a translation fault + * to map the page containing the PT (read only at + * first), then a permission fault to allow the flags + * to be set. + */ + switch (kvm_vcpu_trap_get_fault_type(vcpu)) { + case ESR_ELx_FSC_PERM: + return true; + default: + return false; + } + } if (kvm_vcpu_trap_is_iabt(vcpu)) return false; diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index b4bbeed80fb6..65e78999c75d 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -681,7 +681,7 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd) #define pud_leaf(pud) (pud_present(pud) && !pud_table(pud)) #define pud_valid(pud) pte_valid(pud_pte(pud)) #define pud_user(pud) pte_user(pud_pte(pud)) - +#define pud_user_exec(pud) pte_user_exec(pud_pte(pud)) static inline void set_pud(pud_t *pudp, pud_t pud) { @@ -730,6 +730,7 @@ static inline pmd_t *pud_pgtable(pud_t pud) #else #define pud_page_paddr(pud) ({ BUILD_BUG(); 0; }) +#define pud_user_exec(pud) pud_user(pud) /* Always 0 with folding */ /* Match pmd_offset folding in <asm/generic/pgtable-nopmd.h> */ #define pmd_set_fixmap(addr) NULL @@ -862,12 +863,12 @@ static inline bool pte_user_accessible_page(pte_t pte) static inline bool pmd_user_accessible_page(pmd_t pmd) { - return pmd_leaf(pmd) && (pmd_user(pmd) || pmd_user_exec(pmd)); + return pmd_leaf(pmd) && !pmd_present_invalid(pmd) && (pmd_user(pmd) || pmd_user_exec(pmd)); } static inline bool pud_user_accessible_page(pud_t pud) { - return pud_leaf(pud) && pud_user(pud); + return pud_leaf(pud) && (pud_user(pud) || pud_user_exec(pud)); } #endif @@ -1093,6 +1094,15 @@ static inline bool pud_sect_supported(void) } +#define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION +#define ptep_modify_prot_start ptep_modify_prot_start +extern pte_t ptep_modify_prot_start(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep); + +#define ptep_modify_prot_commit ptep_modify_prot_commit +extern void ptep_modify_prot_commit(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t old_pte, pte_t new_pte); #endif /* !__ASSEMBLY__ */ #endif /* __ASM_PGTABLE_H */ diff --git a/arch/arm64/include/asm/uprobes.h b/arch/arm64/include/asm/uprobes.h index ba4bff5ca674..2b09495499c6 100644 --- a/arch/arm64/include/asm/uprobes.h +++ b/arch/arm64/include/asm/uprobes.h @@ -16,7 +16,7 @@ #define UPROBE_SWBP_INSN_SIZE AARCH64_INSN_SIZE #define UPROBE_XOL_SLOT_BYTES MAX_UINSN_BYTES -typedef u32 uprobe_opcode_t; +typedef __le32 uprobe_opcode_t; struct arch_uprobe_task { }; diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 89ac00084f38..307faa2b4395 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -661,6 +661,13 @@ const struct arm64_cpu_capabilities arm64_errata[] = { CAP_MIDR_RANGE_LIST(trbe_write_out_of_range_cpus), }, #endif +#ifdef CONFIG_ARM64_ERRATUM_2645198 + { + .desc = "ARM erratum 2645198", + .capability = ARM64_WORKAROUND_2645198, + ERRATA_MIDR_ALL_VERSIONS(MIDR_CORTEX_A715) + }, +#endif #ifdef CONFIG_ARM64_ERRATUM_2077057 { .desc = "ARM erratum 2077057", diff --git a/arch/arm64/kernel/efi-rt-wrapper.S b/arch/arm64/kernel/efi-rt-wrapper.S index a00886410537..d872d18101d8 100644 --- a/arch/arm64/kernel/efi-rt-wrapper.S +++ b/arch/arm64/kernel/efi-rt-wrapper.S @@ -4,6 +4,7 @@ */ #include <linux/linkage.h> +#include <asm/assembler.h> SYM_FUNC_START(__efi_rt_asm_wrapper) stp x29, x30, [sp, #-112]! diff --git a/arch/arm64/kernel/elfcore.c b/arch/arm64/kernel/elfcore.c index 353009d7f307..2e94d20c4ac7 100644 --- a/arch/arm64/kernel/elfcore.c +++ b/arch/arm64/kernel/elfcore.c @@ -8,28 +8,27 @@ #include <asm/cpufeature.h> #include <asm/mte.h> -#define for_each_mte_vma(vmi, vma) \ +#define for_each_mte_vma(cprm, i, m) \ if (system_supports_mte()) \ - for_each_vma(vmi, vma) \ - if (vma->vm_flags & VM_MTE) + for (i = 0, m = cprm->vma_meta; \ + i < cprm->vma_count; \ + i++, m = cprm->vma_meta + i) \ + if (m->flags & VM_MTE) -static unsigned long mte_vma_tag_dump_size(struct vm_area_struct *vma) +static unsigned long mte_vma_tag_dump_size(struct core_vma_metadata *m) { - if (vma->vm_flags & VM_DONTDUMP) - return 0; - - return vma_pages(vma) * MTE_PAGE_TAG_STORAGE; + return (m->dump_size >> PAGE_SHIFT) * MTE_PAGE_TAG_STORAGE; } /* Derived from dump_user_range(); start/end must be page-aligned */ static int mte_dump_tag_range(struct coredump_params *cprm, - unsigned long start, unsigned long end) + unsigned long start, unsigned long len) { int ret = 1; unsigned long addr; void *tags = NULL; - for (addr = start; addr < end; addr += PAGE_SIZE) { + for (addr = start; addr < start + len; addr += PAGE_SIZE) { struct page *page = get_dump_page(addr); /* @@ -65,7 +64,6 @@ static int mte_dump_tag_range(struct coredump_params *cprm, mte_save_page_tags(page_address(page), tags); put_page(page); if (!dump_emit(cprm, tags, MTE_PAGE_TAG_STORAGE)) { - mte_free_tag_storage(tags); ret = 0; break; } @@ -77,13 +75,13 @@ static int mte_dump_tag_range(struct coredump_params *cprm, return ret; } -Elf_Half elf_core_extra_phdrs(void) +Elf_Half elf_core_extra_phdrs(struct coredump_params *cprm) { - struct vm_area_struct *vma; + int i; + struct core_vma_metadata *m; int vma_count = 0; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) + for_each_mte_vma(cprm, i, m) vma_count++; return vma_count; @@ -91,18 +89,18 @@ Elf_Half elf_core_extra_phdrs(void) int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset) { - struct vm_area_struct *vma; - VMA_ITERATOR(vmi, current->mm, 0); + int i; + struct core_vma_metadata *m; - for_each_mte_vma(vmi, vma) { + for_each_mte_vma(cprm, i, m) { struct elf_phdr phdr; phdr.p_type = PT_AARCH64_MEMTAG_MTE; phdr.p_offset = offset; - phdr.p_vaddr = vma->vm_start; + phdr.p_vaddr = m->start; phdr.p_paddr = 0; - phdr.p_filesz = mte_vma_tag_dump_size(vma); - phdr.p_memsz = vma->vm_end - vma->vm_start; + phdr.p_filesz = mte_vma_tag_dump_size(m); + phdr.p_memsz = m->end - m->start; offset += phdr.p_filesz; phdr.p_flags = 0; phdr.p_align = 0; @@ -114,28 +112,25 @@ int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset) return 1; } -size_t elf_core_extra_data_size(void) +size_t elf_core_extra_data_size(struct coredump_params *cprm) { - struct vm_area_struct *vma; + int i; + struct core_vma_metadata *m; size_t data_size = 0; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) - data_size += mte_vma_tag_dump_size(vma); + for_each_mte_vma(cprm, i, m) + data_size += mte_vma_tag_dump_size(m); return data_size; } int elf_core_write_extra_data(struct coredump_params *cprm) { - struct vm_area_struct *vma; - VMA_ITERATOR(vmi, current->mm, 0); - - for_each_mte_vma(vmi, vma) { - if (vma->vm_flags & VM_DONTDUMP) - continue; + int i; + struct core_vma_metadata *m; - if (!mte_dump_tag_range(cprm, vma->vm_start, vma->vm_end)) + for_each_mte_vma(cprm, i, m) { + if (!mte_dump_tag_range(cprm, m->start, m->dump_size)) return 0; } diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index dcc81e7200d4..b6ef1af0122e 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -385,7 +385,7 @@ static void task_fpsimd_load(void) WARN_ON(!system_supports_fpsimd()); WARN_ON(!have_cpu_fpsimd_context()); - if (system_supports_sve()) { + if (system_supports_sve() || system_supports_sme()) { switch (current->thread.fp_type) { case FP_STATE_FPSIMD: /* Stop tracking SVE for this task until next use. */ diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 2686ab157601..0c321ad23cd3 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -1357,7 +1357,7 @@ enum aarch64_regset { #ifdef CONFIG_ARM64_SVE REGSET_SVE, #endif -#ifdef CONFIG_ARM64_SVE +#ifdef CONFIG_ARM64_SME REGSET_SSVE, REGSET_ZA, #endif diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index e0d09bf5b01b..be279fd48248 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -281,7 +281,12 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user) vl = task_get_sme_vl(current); } else { - if (!system_supports_sve()) + /* + * A SME only system use SVE for streaming mode so can + * have a SVE formatted context with a zero VL and no + * payload data. + */ + if (!system_supports_sve() && !system_supports_sme()) return -EINVAL; vl = task_get_sve_vl(current); @@ -732,7 +737,7 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user, return err; } - if (system_supports_sve()) { + if (system_supports_sve() || system_supports_sme()) { unsigned int vq = 0; if (add_all || test_thread_flag(TIF_SVE) || diff --git a/arch/arm64/kvm/hyp/include/hyp/fault.h b/arch/arm64/kvm/hyp/include/hyp/fault.h index 1b8a2dcd712f..9ddcfe2c3e57 100644 --- a/arch/arm64/kvm/hyp/include/hyp/fault.h +++ b/arch/arm64/kvm/hyp/include/hyp/fault.h @@ -60,7 +60,7 @@ static inline bool __get_fault_info(u64 esr, struct kvm_vcpu_fault_info *fault) */ if (!(esr & ESR_ELx_S1PTW) && (cpus_have_final_cap(ARM64_WORKAROUND_834220) || - (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) { + (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_PERM)) { if (!__translate_far_to_hpfar(far, &hpfar)) return false; } else { diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 3330d1b76bdd..07d37ff88a3f 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -367,7 +367,7 @@ static bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code) if (static_branch_unlikely(&vgic_v2_cpuif_trap)) { bool valid; - valid = kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT && + valid = kvm_vcpu_trap_get_fault_type(vcpu) == ESR_ELx_FSC_FAULT && kvm_vcpu_dabt_isvalid(vcpu) && !kvm_vcpu_abt_issea(vcpu) && !kvm_vcpu_abt_iss1tw(vcpu); diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 31d7fa4c7c14..a3ee3b605c9b 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1212,7 +1212,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu); VM_BUG_ON(write_fault && exec_fault); - if (fault_status == FSC_PERM && !write_fault && !exec_fault) { + if (fault_status == ESR_ELx_FSC_PERM && !write_fault && !exec_fault) { kvm_err("Unexpected L2 read permission error\n"); return -EFAULT; } @@ -1277,7 +1277,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, * only exception to this is when dirty logging is enabled at runtime * and a write fault needs to collapse a block entry into a table. */ - if (fault_status != FSC_PERM || (logging_active && write_fault)) { + if (fault_status != ESR_ELx_FSC_PERM || + (logging_active && write_fault)) { ret = kvm_mmu_topup_memory_cache(memcache, kvm_mmu_cache_min_pages(kvm)); if (ret) @@ -1342,7 +1343,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, * backed by a THP and thus use block mapping if possible. */ if (vma_pagesize == PAGE_SIZE && !(force_pte || device)) { - if (fault_status == FSC_PERM && fault_granule > PAGE_SIZE) + if (fault_status == ESR_ELx_FSC_PERM && + fault_granule > PAGE_SIZE) vma_pagesize = fault_granule; else vma_pagesize = transparent_hugepage_adjust(kvm, memslot, @@ -1350,7 +1352,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, &fault_ipa); } - if (fault_status != FSC_PERM && !device && kvm_has_mte(kvm)) { + if (fault_status != ESR_ELx_FSC_PERM && !device && kvm_has_mte(kvm)) { /* Check the VMM hasn't introduced a new disallowed VMA */ if (kvm_vma_mte_allowed(vma)) { sanitise_mte_tags(kvm, pfn, vma_pagesize); @@ -1376,7 +1378,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, * permissions only if vma_pagesize equals fault_granule. Otherwise, * kvm_pgtable_stage2_map() should be called to change block size. */ - if (fault_status == FSC_PERM && vma_pagesize == fault_granule) + if (fault_status == ESR_ELx_FSC_PERM && vma_pagesize == fault_granule) ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot); else ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize, @@ -1441,7 +1443,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) fault_ipa = kvm_vcpu_get_fault_ipa(vcpu); is_iabt = kvm_vcpu_trap_is_iabt(vcpu); - if (fault_status == FSC_FAULT) { + if (fault_status == ESR_ELx_FSC_FAULT) { /* Beyond sanitised PARange (which is the IPA limit) */ if (fault_ipa >= BIT_ULL(get_kvm_ipa_limit())) { kvm_inject_size_fault(vcpu); @@ -1476,8 +1478,9 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) kvm_vcpu_get_hfar(vcpu), fault_ipa); /* Check the stage-2 fault is trans. fault or write fault */ - if (fault_status != FSC_FAULT && fault_status != FSC_PERM && - fault_status != FSC_ACCESS) { + if (fault_status != ESR_ELx_FSC_FAULT && + fault_status != ESR_ELx_FSC_PERM && + fault_status != ESR_ELx_FSC_ACCESS) { kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n", kvm_vcpu_trap_get_class(vcpu), (unsigned long)kvm_vcpu_trap_get_fault(vcpu), @@ -1539,7 +1542,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) /* Userspace should not be able to register out-of-bounds IPAs */ VM_BUG_ON(fault_ipa >= kvm_phys_size(vcpu->kvm)); - if (fault_status == FSC_ACCESS) { + if (fault_status == ESR_ELx_FSC_ACCESS) { handle_access_fault(vcpu, fault_ipa); ret = 1; goto out_unlock; diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index d5ee52d6bf73..c6cbfe6b854b 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -646,7 +646,7 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) return; /* Only preserve PMCR_EL0.N, and reset the rest to 0 */ - pmcr = read_sysreg(pmcr_el0) & ARMV8_PMU_PMCR_N_MASK; + pmcr = read_sysreg(pmcr_el0) & (ARMV8_PMU_PMCR_N_MASK << ARMV8_PMU_PMCR_N_SHIFT); if (!kvm_supports_32bit_el0()) pmcr |= ARMV8_PMU_PMCR_LC; diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index 826ff6f2a4e7..2074521d4a8c 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -616,6 +616,8 @@ static const struct midr_range broken_seis[] = { MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_PRO), MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM_MAX), MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_MAX), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE), {}, }; diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 35e9a468d13e..95364e8bdc19 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -559,3 +559,24 @@ bool __init arch_hugetlb_valid_size(unsigned long size) { return __hugetlb_valid_size(size); } + +pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) +{ + if (IS_ENABLED(CONFIG_ARM64_ERRATUM_2645198) && + cpus_have_const_cap(ARM64_WORKAROUND_2645198)) { + /* + * Break-before-make (BBM) is required for all user space mappings + * when the permission changes from executable to non-executable + * in cases where cpu is affected with errata #2645198. + */ + if (pte_user_exec(READ_ONCE(*ptep))) + return huge_ptep_clear_flush(vma, addr, ptep); + } + return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); +} + +void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, + pte_t old_pte, pte_t pte) +{ + set_huge_pte_at(vma->vm_mm, addr, ptep, pte); +} diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 14c87e8d69d8..d77c9f56b7b4 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1630,3 +1630,24 @@ static int __init prevent_bootmem_remove_init(void) } early_initcall(prevent_bootmem_remove_init); #endif + +pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) +{ + if (IS_ENABLED(CONFIG_ARM64_ERRATUM_2645198) && + cpus_have_const_cap(ARM64_WORKAROUND_2645198)) { + /* + * Break-before-make (BBM) is required for all user space mappings + * when the permission changes from executable to non-executable + * in cases where cpu is affected with errata #2645198. + */ + if (pte_user_exec(READ_ONCE(*ptep))) + return ptep_clear_flush(vma, addr, ptep); + } + return ptep_get_and_clear(vma->vm_mm, addr, ptep); +} + +void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, + pte_t old_pte, pte_t pte) +{ + set_pte_at(vma->vm_mm, addr, ptep, pte); +} diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index a86ee376920a..dfeb2c51e257 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -71,6 +71,7 @@ WORKAROUND_2038923 WORKAROUND_2064142 WORKAROUND_2077057 WORKAROUND_2457168 +WORKAROUND_2645198 WORKAROUND_2658417 WORKAROUND_TRBE_OVERWRITE_FILL_MODE WORKAROUND_TSB_FLUSH_FAILURE diff --git a/arch/ia64/kernel/elfcore.c b/arch/ia64/kernel/elfcore.c index 94680521fbf9..8895df121540 100644 --- a/arch/ia64/kernel/elfcore.c +++ b/arch/ia64/kernel/elfcore.c @@ -7,7 +7,7 @@ #include <asm/elf.h> -Elf64_Half elf_core_extra_phdrs(void) +Elf64_Half elf_core_extra_phdrs(struct coredump_params *cprm) { return GATE_EHDR->e_phnum; } @@ -60,7 +60,7 @@ int elf_core_write_extra_data(struct coredump_params *cprm) return 1; } -size_t elf_core_extra_data_size(void) +size_t elf_core_extra_data_size(struct coredump_params *cprm) { const struct elf_phdr *const gate_phdrs = (const struct elf_phdr *) (GATE_ADDR + GATE_EHDR->e_phoff); diff --git a/arch/mips/ralink/of.c b/arch/mips/ralink/of.c index 01c132bc33d5..4d06de77d92a 100644 --- a/arch/mips/ralink/of.c +++ b/arch/mips/ralink/of.c @@ -64,7 +64,7 @@ void __init plat_mem_setup(void) dtb = get_fdt(); __dt_setup_arch(dtb); - if (!early_init_dt_scan_memory()) + if (early_init_dt_scan_memory()) return; if (soc_info.mem_detect) diff --git a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi index 74e17e134387..27714dc2f04a 100644 --- a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi @@ -659,3 +659,19 @@ interrupts = <16 2 1 9>; }; }; + +&fman0_rx_0x08 { + /delete-property/ fsl,fman-10g-port; +}; + +&fman0_tx_0x28 { + /delete-property/ fsl,fman-10g-port; +}; + +&fman0_rx_0x09 { + /delete-property/ fsl,fman-10g-port; +}; + +&fman0_tx_0x29 { + /delete-property/ fsl,fman-10g-port; +}; diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper index af04cea82b94..352d7de24018 100755 --- a/arch/powerpc/boot/wrapper +++ b/arch/powerpc/boot/wrapper @@ -210,6 +210,10 @@ ld_version() gsub(".*version ", ""); gsub("-.*", ""); split($1,a, "."); + if( length(a[3]) == "8" ) + # a[3] is probably a date of format yyyymmdd used for release snapshots. We + # can assume it to be zero as it does not signify a new version as such. + a[3] = 0; print a[1]*100000000 + a[2]*1000000 + a[3]*10000; exit }' diff --git a/arch/powerpc/include/asm/imc-pmu.h b/arch/powerpc/include/asm/imc-pmu.h index 4f897993b710..699a88584ae1 100644 --- a/arch/powerpc/include/asm/imc-pmu.h +++ b/arch/powerpc/include/asm/imc-pmu.h @@ -137,7 +137,7 @@ struct imc_pmu { * are inited. */ struct imc_pmu_ref { - struct mutex lock; + spinlock_t lock; unsigned int id; int refc; }; diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 8c3862b4c259..958e77a24f85 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -8,6 +8,7 @@ #define BSS_FIRST_SECTIONS *(.bss.prominit) #define EMITS_PT_NOTE #define RO_EXCEPTION_TABLE_ALIGN 0 +#define RUNTIME_DISCARD_EXIT #define SOFT_MASK_TABLE(align) \ . = ALIGN(align); \ @@ -410,9 +411,12 @@ SECTIONS DISCARDS /DISCARD/ : { *(*.EMB.apuinfo) - *(.glink .iplt .plt .rela* .comment) + *(.glink .iplt .plt) *(.gnu.version*) *(.gnu.attributes) *(.eh_frame) +#ifndef CONFIG_RELOCATABLE + *(.rela*) +#endif } } diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index 80a148c57de8..44a35ed4f686 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -1012,7 +1012,7 @@ static void __init hash_init_partition_table(phys_addr_t hash_table, void hpt_clear_stress(void); static struct timer_list stress_hpt_timer; -void stress_hpt_timer_fn(struct timer_list *timer) +static void stress_hpt_timer_fn(struct timer_list *timer) { int next_cpu; diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index d517aba94d1b..100e97daf76b 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -14,6 +14,7 @@ #include <asm/cputhreads.h> #include <asm/smp.h> #include <linux/string.h> +#include <linux/spinlock.h> /* Nest IMC data structures and variables */ @@ -21,7 +22,7 @@ * Used to avoid races in counting the nest-pmu units during hotplug * register and unregister */ -static DEFINE_MUTEX(nest_init_lock); +static DEFINE_SPINLOCK(nest_init_lock); static DEFINE_PER_CPU(struct imc_pmu_ref *, local_nest_imc_refc); static struct imc_pmu **per_nest_pmu_arr; static cpumask_t nest_imc_cpumask; @@ -50,7 +51,7 @@ static int trace_imc_mem_size; * core and trace-imc */ static struct imc_pmu_ref imc_global_refc = { - .lock = __MUTEX_INITIALIZER(imc_global_refc.lock), + .lock = __SPIN_LOCK_INITIALIZER(imc_global_refc.lock), .id = 0, .refc = 0, }; @@ -400,7 +401,7 @@ static int ppc_nest_imc_cpu_offline(unsigned int cpu) get_hard_smp_processor_id(cpu)); /* * If this is the last cpu in this chip then, skip the reference - * count mutex lock and make the reference count on this chip zero. + * count lock and make the reference count on this chip zero. */ ref = get_nest_pmu_ref(cpu); if (!ref) @@ -462,15 +463,15 @@ static void nest_imc_counters_release(struct perf_event *event) /* * See if we need to disable the nest PMU. * If no events are currently in use, then we have to take a - * mutex to ensure that we don't race with another task doing + * lock to ensure that we don't race with another task doing * enable or disable the nest counters. */ ref = get_nest_pmu_ref(event->cpu); if (!ref) return; - /* Take the mutex lock for this node and then decrement the reference count */ - mutex_lock(&ref->lock); + /* Take the lock for this node and then decrement the reference count */ + spin_lock(&ref->lock); if (ref->refc == 0) { /* * The scenario where this is true is, when perf session is @@ -482,7 +483,7 @@ static void nest_imc_counters_release(struct perf_event *event) * an OPAL call to disable the engine in that node. * */ - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); return; } ref->refc--; @@ -490,7 +491,7 @@ static void nest_imc_counters_release(struct perf_event *event) rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_NEST, get_hard_smp_processor_id(event->cpu)); if (rc) { - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); pr_err("nest-imc: Unable to stop the counters for core %d\n", node_id); return; } @@ -498,7 +499,7 @@ static void nest_imc_counters_release(struct perf_event *event) WARN(1, "nest-imc: Invalid event reference count\n"); ref->refc = 0; } - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); } static int nest_imc_event_init(struct perf_event *event) @@ -557,26 +558,25 @@ static int nest_imc_event_init(struct perf_event *event) /* * Get the imc_pmu_ref struct for this node. - * Take the mutex lock and then increment the count of nest pmu events - * inited. + * Take the lock and then increment the count of nest pmu events inited. */ ref = get_nest_pmu_ref(event->cpu); if (!ref) return -EINVAL; - mutex_lock(&ref->lock); + spin_lock(&ref->lock); if (ref->refc == 0) { rc = opal_imc_counters_start(OPAL_IMC_COUNTERS_NEST, get_hard_smp_processor_id(event->cpu)); if (rc) { - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); pr_err("nest-imc: Unable to start the counters for node %d\n", node_id); return rc; } } ++ref->refc; - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); event->destroy = nest_imc_counters_release; return 0; @@ -612,9 +612,8 @@ static int core_imc_mem_init(int cpu, int size) return -ENOMEM; mem_info->vbase = page_address(page); - /* Init the mutex */ core_imc_refc[core_id].id = core_id; - mutex_init(&core_imc_refc[core_id].lock); + spin_lock_init(&core_imc_refc[core_id].lock); rc = opal_imc_counters_init(OPAL_IMC_COUNTERS_CORE, __pa((void *)mem_info->vbase), @@ -703,9 +702,8 @@ static int ppc_core_imc_cpu_offline(unsigned int cpu) perf_pmu_migrate_context(&core_imc_pmu->pmu, cpu, ncpu); } else { /* - * If this is the last cpu in this core then, skip taking refernce - * count mutex lock for this core and directly zero "refc" for - * this core. + * If this is the last cpu in this core then skip taking reference + * count lock for this core and directly zero "refc" for this core. */ opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE, get_hard_smp_processor_id(cpu)); @@ -720,11 +718,11 @@ static int ppc_core_imc_cpu_offline(unsigned int cpu) * last cpu in this core and core-imc event running * in this cpu. */ - mutex_lock(&imc_global_refc.lock); + spin_lock(&imc_global_refc.lock); if (imc_global_refc.id == IMC_DOMAIN_CORE) imc_global_refc.refc--; - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); } return 0; } @@ -739,7 +737,7 @@ static int core_imc_pmu_cpumask_init(void) static void reset_global_refc(struct perf_event *event) { - mutex_lock(&imc_global_refc.lock); + spin_lock(&imc_global_refc.lock); imc_global_refc.refc--; /* @@ -751,7 +749,7 @@ static void reset_global_refc(struct perf_event *event) imc_global_refc.refc = 0; imc_global_refc.id = 0; } - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); } static void core_imc_counters_release(struct perf_event *event) @@ -764,17 +762,17 @@ static void core_imc_counters_release(struct perf_event *event) /* * See if we need to disable the IMC PMU. * If no events are currently in use, then we have to take a - * mutex to ensure that we don't race with another task doing + * lock to ensure that we don't race with another task doing * enable or disable the core counters. */ core_id = event->cpu / threads_per_core; - /* Take the mutex lock and decrement the refernce count for this core */ + /* Take the lock and decrement the refernce count for this core */ ref = &core_imc_refc[core_id]; if (!ref) return; - mutex_lock(&ref->lock); + spin_lock(&ref->lock); if (ref->refc == 0) { /* * The scenario where this is true is, when perf session is @@ -786,7 +784,7 @@ static void core_imc_counters_release(struct perf_event *event) * an OPAL call to disable the engine in that core. * */ - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); return; } ref->refc--; @@ -794,7 +792,7 @@ static void core_imc_counters_release(struct perf_event *event) rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE, get_hard_smp_processor_id(event->cpu)); if (rc) { - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); pr_err("IMC: Unable to stop the counters for core %d\n", core_id); return; } @@ -802,7 +800,7 @@ static void core_imc_counters_release(struct perf_event *event) WARN(1, "core-imc: Invalid event reference count\n"); ref->refc = 0; } - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); reset_global_refc(event); } @@ -840,7 +838,6 @@ static int core_imc_event_init(struct perf_event *event) if ((!pcmi->vbase)) return -ENODEV; - /* Get the core_imc mutex for this core */ ref = &core_imc_refc[core_id]; if (!ref) return -EINVAL; @@ -848,22 +845,22 @@ static int core_imc_event_init(struct perf_event *event) /* * Core pmu units are enabled only when it is used. * See if this is triggered for the first time. - * If yes, take the mutex lock and enable the core counters. + * If yes, take the lock and enable the core counters. * If not, just increment the count in core_imc_refc struct. */ - mutex_lock(&ref->lock); + spin_lock(&ref->lock); if (ref->refc == 0) { rc = opal_imc_counters_start(OPAL_IMC_COUNTERS_CORE, get_hard_smp_processor_id(event->cpu)); if (rc) { - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); pr_err("core-imc: Unable to start the counters for core %d\n", core_id); return rc; } } ++ref->refc; - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); /* * Since the system can run either in accumulation or trace-mode @@ -874,7 +871,7 @@ static int core_imc_event_init(struct perf_event *event) * to know whether any other trace/thread imc * events are running. */ - mutex_lock(&imc_global_refc.lock); + spin_lock(&imc_global_refc.lock); if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_CORE) { /* * No other trace/thread imc events are running in @@ -883,10 +880,10 @@ static int core_imc_event_init(struct perf_event *event) imc_global_refc.id = IMC_DOMAIN_CORE; imc_global_refc.refc++; } else { - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); return -EBUSY; } - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); event->hw.event_base = (u64)pcmi->vbase + (config & IMC_EVENT_OFFSET_MASK); event->destroy = core_imc_counters_release; @@ -958,10 +955,10 @@ static int ppc_thread_imc_cpu_offline(unsigned int cpu) mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63)))); /* Reduce the refc if thread-imc event running on this cpu */ - mutex_lock(&imc_global_refc.lock); + spin_lock(&imc_global_refc.lock); if (imc_global_refc.id == IMC_DOMAIN_THREAD) imc_global_refc.refc--; - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); return 0; } @@ -1001,7 +998,7 @@ static int thread_imc_event_init(struct perf_event *event) if (!target) return -EINVAL; - mutex_lock(&imc_global_refc.lock); + spin_lock(&imc_global_refc.lock); /* * Check if any other trace/core imc events are running in the * system, if not set the global id to thread-imc. @@ -1010,10 +1007,10 @@ static int thread_imc_event_init(struct perf_event *event) imc_global_refc.id = IMC_DOMAIN_THREAD; imc_global_refc.refc++; } else { - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); return -EBUSY; } - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); event->pmu->task_ctx_nr = perf_sw_context; event->destroy = reset_global_refc; @@ -1135,25 +1132,25 @@ static int thread_imc_event_add(struct perf_event *event, int flags) /* * imc pmus are enabled only when it is used. * See if this is triggered for the first time. - * If yes, take the mutex lock and enable the counters. + * If yes, take the lock and enable the counters. * If not, just increment the count in ref count struct. */ ref = &core_imc_refc[core_id]; if (!ref) return -EINVAL; - mutex_lock(&ref->lock); + spin_lock(&ref->lock); if (ref->refc == 0) { if (opal_imc_counters_start(OPAL_IMC_COUNTERS_CORE, get_hard_smp_processor_id(smp_processor_id()))) { - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); pr_err("thread-imc: Unable to start the counter\ for core %d\n", core_id); return -EINVAL; } } ++ref->refc; - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); return 0; } @@ -1170,12 +1167,12 @@ static void thread_imc_event_del(struct perf_event *event, int flags) return; } - mutex_lock(&ref->lock); + spin_lock(&ref->lock); ref->refc--; if (ref->refc == 0) { if (opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE, get_hard_smp_processor_id(smp_processor_id()))) { - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); pr_err("thread-imc: Unable to stop the counters\ for core %d\n", core_id); return; @@ -1183,7 +1180,7 @@ static void thread_imc_event_del(struct perf_event *event, int flags) } else if (ref->refc < 0) { ref->refc = 0; } - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); /* Set bit 0 of LDBAR to zero, to stop posting updates to memory */ mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63)))); @@ -1224,9 +1221,8 @@ static int trace_imc_mem_alloc(int cpu_id, int size) } } - /* Init the mutex, if not already */ trace_imc_refc[core_id].id = core_id; - mutex_init(&trace_imc_refc[core_id].lock); + spin_lock_init(&trace_imc_refc[core_id].lock); mtspr(SPRN_LDBAR, 0); return 0; @@ -1246,10 +1242,10 @@ static int ppc_trace_imc_cpu_offline(unsigned int cpu) * Reduce the refc if any trace-imc event running * on this cpu. */ - mutex_lock(&imc_global_refc.lock); + spin_lock(&imc_global_refc.lock); if (imc_global_refc.id == IMC_DOMAIN_TRACE) imc_global_refc.refc--; - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); return 0; } @@ -1371,17 +1367,17 @@ static int trace_imc_event_add(struct perf_event *event, int flags) } mtspr(SPRN_LDBAR, ldbar_value); - mutex_lock(&ref->lock); + spin_lock(&ref->lock); if (ref->refc == 0) { if (opal_imc_counters_start(OPAL_IMC_COUNTERS_TRACE, get_hard_smp_processor_id(smp_processor_id()))) { - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); pr_err("trace-imc: Unable to start the counters for core %d\n", core_id); return -EINVAL; } } ++ref->refc; - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); return 0; } @@ -1414,19 +1410,19 @@ static void trace_imc_event_del(struct perf_event *event, int flags) return; } - mutex_lock(&ref->lock); + spin_lock(&ref->lock); ref->refc--; if (ref->refc == 0) { if (opal_imc_counters_stop(OPAL_IMC_COUNTERS_TRACE, get_hard_smp_processor_id(smp_processor_id()))) { - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); pr_err("trace-imc: Unable to stop the counters for core %d\n", core_id); return; } } else if (ref->refc < 0) { ref->refc = 0; } - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); trace_imc_event_stop(event, flags); } @@ -1448,7 +1444,7 @@ static int trace_imc_event_init(struct perf_event *event) * no other thread is running any core/thread imc * events */ - mutex_lock(&imc_global_refc.lock); + spin_lock(&imc_global_refc.lock); if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_TRACE) { /* * No core/thread imc events are running in the @@ -1457,10 +1453,10 @@ static int trace_imc_event_init(struct perf_event *event) imc_global_refc.id = IMC_DOMAIN_TRACE; imc_global_refc.refc++; } else { - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); return -EBUSY; } - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); event->hw.idx = -1; @@ -1533,10 +1529,10 @@ static int init_nest_pmu_ref(void) i = 0; for_each_node(nid) { /* - * Mutex lock to avoid races while tracking the number of + * Take the lock to avoid races while tracking the number of * sessions using the chip's nest pmu units. */ - mutex_init(&nest_imc_refc[i].lock); + spin_lock_init(&nest_imc_refc[i].lock); /* * Loop to init the "id" with the node_id. Variable "i" initialized to @@ -1633,7 +1629,7 @@ static void imc_common_mem_free(struct imc_pmu *pmu_ptr) static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr) { if (pmu_ptr->domain == IMC_DOMAIN_NEST) { - mutex_lock(&nest_init_lock); + spin_lock(&nest_init_lock); if (nest_pmus == 1) { cpuhp_remove_state(CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE); kfree(nest_imc_refc); @@ -1643,7 +1639,7 @@ static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr) if (nest_pmus > 0) nest_pmus--; - mutex_unlock(&nest_init_lock); + spin_unlock(&nest_init_lock); } /* Free core_imc memory */ @@ -1800,11 +1796,11 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id * rest. To handle the cpuhotplug callback unregister, we track * the number of nest pmus in "nest_pmus". */ - mutex_lock(&nest_init_lock); + spin_lock(&nest_init_lock); if (nest_pmus == 0) { ret = init_nest_pmu_ref(); if (ret) { - mutex_unlock(&nest_init_lock); + spin_unlock(&nest_init_lock); kfree(per_nest_pmu_arr); per_nest_pmu_arr = NULL; goto err_free_mem; @@ -1812,7 +1808,7 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id /* Register for cpu hotplug notification. */ ret = nest_pmu_cpumask_init(); if (ret) { - mutex_unlock(&nest_init_lock); + spin_unlock(&nest_init_lock); kfree(nest_imc_refc); kfree(per_nest_pmu_arr); per_nest_pmu_arr = NULL; @@ -1820,7 +1816,7 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id } } nest_pmus++; - mutex_unlock(&nest_init_lock); + spin_unlock(&nest_init_lock); break; case IMC_DOMAIN_CORE: ret = core_imc_pmu_cpumask_init(); diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h index 855450bed9f5..ec0cab9fbddd 100644 --- a/arch/riscv/include/asm/uaccess.h +++ b/arch/riscv/include/asm/uaccess.h @@ -165,7 +165,7 @@ do { \ might_fault(); \ access_ok(__p, sizeof(*__p)) ? \ __get_user((x), __p) : \ - ((x) = 0, -EFAULT); \ + ((x) = (__force __typeof__(x))0, -EFAULT); \ }) #define __put_user_asm(insn, x, ptr, err) \ diff --git a/arch/riscv/kernel/probes/simulate-insn.h b/arch/riscv/kernel/probes/simulate-insn.h index cb6ff7dccb92..de8474146a9b 100644 --- a/arch/riscv/kernel/probes/simulate-insn.h +++ b/arch/riscv/kernel/probes/simulate-insn.h @@ -31,9 +31,9 @@ __RISCV_INSN_FUNCS(fence, 0x7f, 0x0f); } while (0) __RISCV_INSN_FUNCS(c_j, 0xe003, 0xa001); -__RISCV_INSN_FUNCS(c_jr, 0xf007, 0x8002); +__RISCV_INSN_FUNCS(c_jr, 0xf07f, 0x8002); __RISCV_INSN_FUNCS(c_jal, 0xe003, 0x2001); -__RISCV_INSN_FUNCS(c_jalr, 0xf007, 0x9002); +__RISCV_INSN_FUNCS(c_jalr, 0xf07f, 0x9002); __RISCV_INSN_FUNCS(c_beqz, 0xe003, 0xc001); __RISCV_INSN_FUNCS(c_bnez, 0xe003, 0xe001); __RISCV_INSN_FUNCS(c_ebreak, 0xffff, 0x9002); diff --git a/arch/s390/boot/decompressor.c b/arch/s390/boot/decompressor.c index e27c2140d620..8dcd7af2911a 100644 --- a/arch/s390/boot/decompressor.c +++ b/arch/s390/boot/decompressor.c @@ -23,9 +23,9 @@ #define memmove memmove #define memzero(s, n) memset((s), 0, (n)) -#ifdef CONFIG_KERNEL_BZIP2 +#if defined(CONFIG_KERNEL_BZIP2) #define BOOT_HEAP_SIZE 0x400000 -#elif CONFIG_KERNEL_ZSTD +#elif defined(CONFIG_KERNEL_ZSTD) #define BOOT_HEAP_SIZE 0x30000 #else #define BOOT_HEAP_SIZE 0x10000 diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index a7b4e1d82758..74b35ec2ad28 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -190,7 +190,6 @@ CONFIG_NFT_CT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_NAT=m -CONFIG_NFT_OBJREF=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m @@ -569,6 +568,7 @@ CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set CONFIG_LEGACY_PTY_COUNT=0 +# CONFIG_LEGACY_TIOCSTI is not set CONFIG_VIRTIO_CONSOLE=m CONFIG_HW_RANDOM_VIRTIO=m CONFIG_HANGCHECK_TIMER=m @@ -660,6 +660,7 @@ CONFIG_CONFIGFS_FS=m CONFIG_ECRYPT_FS=m CONFIG_CRAMFS=m CONFIG_SQUASHFS=m +CONFIG_SQUASHFS_CHOICE_DECOMP_BY_MOUNT=y CONFIG_SQUASHFS_XATTR=y CONFIG_SQUASHFS_LZ4=y CONFIG_SQUASHFS_LZO=y @@ -705,6 +706,7 @@ CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y CONFIG_SECURITY_LANDLOCK=y CONFIG_INTEGRITY_SIGNATURE=y CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y +CONFIG_INTEGRITY_PLATFORM_KEYRING=y CONFIG_IMA=y CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y @@ -781,6 +783,7 @@ CONFIG_ZCRYPT=m CONFIG_PKEY=m CONFIG_CRYPTO_PAES_S390=m CONFIG_CRYPTO_DEV_VIRTIO=m +CONFIG_SYSTEM_BLACKLIST_KEYRING=y CONFIG_CORDIC=m CONFIG_CRYPTO_LIB_CURVE25519=m CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m @@ -848,7 +851,6 @@ CONFIG_PREEMPT_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_BLK_DEV_IO_TRACE=y -CONFIG_BPF_KPROBE_OVERRIDE=y CONFIG_HIST_TRIGGERS=y CONFIG_FTRACE_STARTUP_TEST=y # CONFIG_EVENT_TRACE_STARTUP_TEST is not set @@ -870,7 +872,6 @@ CONFIG_FAIL_MAKE_REQUEST=y CONFIG_FAIL_IO_TIMEOUT=y CONFIG_FAIL_FUTEX=y CONFIG_FAULT_INJECTION_DEBUG_FS=y -CONFIG_FAIL_FUNCTION=y CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y CONFIG_LKDTM=m CONFIG_TEST_MIN_HEAP=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 2bc2d0fe5774..cec71268e3bc 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -181,7 +181,6 @@ CONFIG_NFT_CT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_NAT=m -CONFIG_NFT_OBJREF=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m @@ -559,6 +558,7 @@ CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set CONFIG_LEGACY_PTY_COUNT=0 +# CONFIG_LEGACY_TIOCSTI is not set CONFIG_VIRTIO_CONSOLE=m CONFIG_HW_RANDOM_VIRTIO=m CONFIG_HANGCHECK_TIMER=m @@ -645,6 +645,7 @@ CONFIG_CONFIGFS_FS=m CONFIG_ECRYPT_FS=m CONFIG_CRAMFS=m CONFIG_SQUASHFS=m +CONFIG_SQUASHFS_CHOICE_DECOMP_BY_MOUNT=y CONFIG_SQUASHFS_XATTR=y CONFIG_SQUASHFS_LZ4=y CONFIG_SQUASHFS_LZO=y @@ -688,6 +689,7 @@ CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y CONFIG_SECURITY_LANDLOCK=y CONFIG_INTEGRITY_SIGNATURE=y CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y +CONFIG_INTEGRITY_PLATFORM_KEYRING=y CONFIG_IMA=y CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y @@ -766,6 +768,7 @@ CONFIG_ZCRYPT=m CONFIG_PKEY=m CONFIG_CRYPTO_PAES_S390=m CONFIG_CRYPTO_DEV_VIRTIO=m +CONFIG_SYSTEM_BLACKLIST_KEYRING=y CONFIG_CORDIC=m CONFIG_PRIME_NUMBERS=m CONFIG_CRYPTO_LIB_CURVE25519=m @@ -798,7 +801,6 @@ CONFIG_STACK_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_BLK_DEV_IO_TRACE=y -CONFIG_BPF_KPROBE_OVERRIDE=y CONFIG_HIST_TRIGGERS=y CONFIG_SAMPLES=y CONFIG_SAMPLE_TRACE_PRINTK=m diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index ae14ab0b864d..a9c0c81d1de9 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -13,7 +13,6 @@ CONFIG_TUNE_ZEC12=y # CONFIG_COMPAT is not set CONFIG_NR_CPUS=2 CONFIG_HZ_100=y -# CONFIG_RELOCATABLE is not set # CONFIG_CHSC_SCH is not set # CONFIG_SCM_BUS is not set CONFIG_CRASH_DUMP=y @@ -50,6 +49,7 @@ CONFIG_ZFCP=y # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set +# CONFIG_LEGACY_TIOCSTI is not set # CONFIG_HVC_IUCV is not set # CONFIG_HW_RANDOM_S390 is not set # CONFIG_HMC_DRV is not set diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h index feaba12dbecb..efa103b52a1a 100644 --- a/arch/s390/include/asm/cpu_mf.h +++ b/arch/s390/include/asm/cpu_mf.h @@ -131,19 +131,21 @@ struct hws_combined_entry { struct hws_diag_entry diag; /* Diagnostic-sampling data entry */ } __packed; -struct hws_trailer_entry { - union { - struct { - unsigned int f:1; /* 0 - Block Full Indicator */ - unsigned int a:1; /* 1 - Alert request control */ - unsigned int t:1; /* 2 - Timestamp format */ - unsigned int :29; /* 3 - 31: Reserved */ - unsigned int bsdes:16; /* 32-47: size of basic SDE */ - unsigned int dsdes:16; /* 48-63: size of diagnostic SDE */ - }; - unsigned long long flags; /* 0 - 63: All indicators */ +union hws_trailer_header { + struct { + unsigned int f:1; /* 0 - Block Full Indicator */ + unsigned int a:1; /* 1 - Alert request control */ + unsigned int t:1; /* 2 - Timestamp format */ + unsigned int :29; /* 3 - 31: Reserved */ + unsigned int bsdes:16; /* 32-47: size of basic SDE */ + unsigned int dsdes:16; /* 48-63: size of diagnostic SDE */ + unsigned long long overflow; /* 64 - Overflow Count */ }; - unsigned long long overflow; /* 64 - sample Overflow count */ + __uint128_t val; +}; + +struct hws_trailer_entry { + union hws_trailer_header header; /* 0 - 15 Flags + Overflow Count */ unsigned char timestamp[16]; /* 16 - 31 timestamp */ unsigned long long reserved1; /* 32 -Reserved */ unsigned long long reserved2; /* */ @@ -290,14 +292,11 @@ static inline unsigned long sample_rate_to_freq(struct hws_qsi_info_block *qsi, return USEC_PER_SEC * qsi->cpu_speed / rate; } -#define SDB_TE_ALERT_REQ_MASK 0x4000000000000000UL -#define SDB_TE_BUFFER_FULL_MASK 0x8000000000000000UL - /* Return TOD timestamp contained in an trailer entry */ static inline unsigned long long trailer_timestamp(struct hws_trailer_entry *te) { /* TOD in STCKE format */ - if (te->t) + if (te->header.t) return *((unsigned long long *) &te->timestamp[1]); /* TOD in STCK format */ diff --git a/arch/s390/include/asm/debug.h b/arch/s390/include/asm/debug.h index 77f24262c25c..ac665b9670c5 100644 --- a/arch/s390/include/asm/debug.h +++ b/arch/s390/include/asm/debug.h @@ -4,8 +4,8 @@ * * Copyright IBM Corp. 1999, 2020 */ -#ifndef DEBUG_H -#define DEBUG_H +#ifndef _ASM_S390_DEBUG_H +#define _ASM_S390_DEBUG_H #include <linux/string.h> #include <linux/spinlock.h> @@ -487,4 +487,4 @@ void debug_register_static(debug_info_t *id, int pages_per_area, int nr_areas); #endif /* MODULE */ -#endif /* DEBUG_H */ +#endif /* _ASM_S390_DEBUG_H */ diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h index cb5fc0690435..081837b391e3 100644 --- a/arch/s390/include/asm/percpu.h +++ b/arch/s390/include/asm/percpu.h @@ -31,7 +31,7 @@ pcp_op_T__ *ptr__; \ preempt_disable_notrace(); \ ptr__ = raw_cpu_ptr(&(pcp)); \ - prev__ = *ptr__; \ + prev__ = READ_ONCE(*ptr__); \ do { \ old__ = prev__; \ new__ = old__ op (val); \ diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c index fc6d5f58debe..2df94d32140c 100644 --- a/arch/s390/kernel/machine_kexec_file.c +++ b/arch/s390/kernel/machine_kexec_file.c @@ -187,8 +187,6 @@ static int kexec_file_add_ipl_report(struct kimage *image, data->memsz = ALIGN(data->memsz, PAGE_SIZE); buf.mem = data->memsz; - if (image->type == KEXEC_TYPE_CRASH) - buf.mem += crashk_res.start; ptr = (void *)ipl_cert_list_addr; end = ptr + ipl_cert_list_size; @@ -225,6 +223,9 @@ static int kexec_file_add_ipl_report(struct kimage *image, data->kernel_buf + offsetof(struct lowcore, ipl_parmblock_ptr); *lc_ipl_parmblock_ptr = (__u32)buf.mem; + if (image->type == KEXEC_TYPE_CRASH) + buf.mem += crashk_res.start; + ret = kexec_add_buffer(&buf); out: return ret; diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 332a49965130..ce886a03545a 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -163,14 +163,15 @@ static void free_sampling_buffer(struct sf_buffer *sfb) static int alloc_sample_data_block(unsigned long *sdbt, gfp_t gfp_flags) { - unsigned long sdb, *trailer; + struct hws_trailer_entry *te; + unsigned long sdb; /* Allocate and initialize sample-data-block */ sdb = get_zeroed_page(gfp_flags); if (!sdb) return -ENOMEM; - trailer = trailer_entry_ptr(sdb); - *trailer = SDB_TE_ALERT_REQ_MASK; + te = (struct hws_trailer_entry *)trailer_entry_ptr(sdb); + te->header.a = 1; /* Link SDB into the sample-data-block-table */ *sdbt = sdb; @@ -1206,7 +1207,7 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt, "%s: Found unknown" " sampling data entry: te->f %i" " basic.def %#4x (%p)\n", __func__, - te->f, sample->def, sample); + te->header.f, sample->def, sample); /* Sample slot is not yet written or other record. * * This condition can occur if the buffer was reused @@ -1217,7 +1218,7 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt, * that are not full. Stop processing if the first * invalid format was detected. */ - if (!te->f) + if (!te->header.f) break; } @@ -1227,6 +1228,16 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt, } } +static inline __uint128_t __cdsg(__uint128_t *ptr, __uint128_t old, __uint128_t new) +{ + asm volatile( + " cdsg %[old],%[new],%[ptr]\n" + : [old] "+d" (old), [ptr] "+QS" (*ptr) + : [new] "d" (new) + : "memory", "cc"); + return old; +} + /* hw_perf_event_update() - Process sampling buffer * @event: The perf event * @flush_all: Flag to also flush partially filled sample-data-blocks @@ -1243,10 +1254,11 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt, */ static void hw_perf_event_update(struct perf_event *event, int flush_all) { + unsigned long long event_overflow, sampl_overflow, num_sdb; + union hws_trailer_header old, prev, new; struct hw_perf_event *hwc = &event->hw; struct hws_trailer_entry *te; unsigned long *sdbt; - unsigned long long event_overflow, sampl_overflow, num_sdb, te_flags; int done; /* @@ -1266,25 +1278,25 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all) te = (struct hws_trailer_entry *) trailer_entry_ptr(*sdbt); /* Leave loop if no more work to do (block full indicator) */ - if (!te->f) { + if (!te->header.f) { done = 1; if (!flush_all) break; } /* Check the sample overflow count */ - if (te->overflow) + if (te->header.overflow) /* Account sample overflows and, if a particular limit * is reached, extend the sampling buffer. * For details, see sfb_account_overflows(). */ - sampl_overflow += te->overflow; + sampl_overflow += te->header.overflow; /* Timestamps are valid for full sample-data-blocks only */ debug_sprintf_event(sfdbg, 6, "%s: sdbt %#lx " "overflow %llu timestamp %#llx\n", - __func__, (unsigned long)sdbt, te->overflow, - (te->f) ? trailer_timestamp(te) : 0ULL); + __func__, (unsigned long)sdbt, te->header.overflow, + (te->header.f) ? trailer_timestamp(te) : 0ULL); /* Collect all samples from a single sample-data-block and * flag if an (perf) event overflow happened. If so, the PMU @@ -1294,12 +1306,16 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all) num_sdb++; /* Reset trailer (using compare-double-and-swap) */ + /* READ_ONCE() 16 byte header */ + prev.val = __cdsg(&te->header.val, 0, 0); do { - te_flags = te->flags & ~SDB_TE_BUFFER_FULL_MASK; - te_flags |= SDB_TE_ALERT_REQ_MASK; - } while (!cmpxchg_double(&te->flags, &te->overflow, - te->flags, te->overflow, - te_flags, 0ULL)); + old.val = prev.val; + new.val = prev.val; + new.f = 0; + new.a = 1; + new.overflow = 0; + prev.val = __cdsg(&te->header.val, old.val, new.val); + } while (prev.val != old.val); /* Advance to next sample-data-block */ sdbt++; @@ -1384,7 +1400,7 @@ static void aux_output_end(struct perf_output_handle *handle) range_scan = AUX_SDB_NUM_ALERT(aux); for (i = 0, idx = aux->head; i < range_scan; i++, idx++) { te = aux_sdb_trailer(aux, idx); - if (!(te->flags & SDB_TE_BUFFER_FULL_MASK)) + if (!te->header.f) break; } /* i is num of SDBs which are full */ @@ -1392,7 +1408,7 @@ static void aux_output_end(struct perf_output_handle *handle) /* Remove alert indicators in the buffer */ te = aux_sdb_trailer(aux, aux->alert_mark); - te->flags &= ~SDB_TE_ALERT_REQ_MASK; + te->header.a = 0; debug_sprintf_event(sfdbg, 6, "%s: SDBs %ld range %ld head %ld\n", __func__, i, range_scan, aux->head); @@ -1437,9 +1453,9 @@ static int aux_output_begin(struct perf_output_handle *handle, idx = aux->empty_mark + 1; for (i = 0; i < range_scan; i++, idx++) { te = aux_sdb_trailer(aux, idx); - te->flags &= ~(SDB_TE_BUFFER_FULL_MASK | - SDB_TE_ALERT_REQ_MASK); - te->overflow = 0; + te->header.f = 0; + te->header.a = 0; + te->header.overflow = 0; } /* Save the position of empty SDBs */ aux->empty_mark = aux->head + range - 1; @@ -1448,7 +1464,7 @@ static int aux_output_begin(struct perf_output_handle *handle, /* Set alert indicator */ aux->alert_mark = aux->head + range/2 - 1; te = aux_sdb_trailer(aux, aux->alert_mark); - te->flags = te->flags | SDB_TE_ALERT_REQ_MASK; + te->header.a = 1; /* Reset hardware buffer head */ head = AUX_SDB_INDEX(aux, aux->head); @@ -1475,14 +1491,17 @@ static int aux_output_begin(struct perf_output_handle *handle, static bool aux_set_alert(struct aux_buffer *aux, unsigned long alert_index, unsigned long long *overflow) { - unsigned long long orig_overflow, orig_flags, new_flags; + union hws_trailer_header old, prev, new; struct hws_trailer_entry *te; te = aux_sdb_trailer(aux, alert_index); + /* READ_ONCE() 16 byte header */ + prev.val = __cdsg(&te->header.val, 0, 0); do { - orig_flags = te->flags; - *overflow = orig_overflow = te->overflow; - if (orig_flags & SDB_TE_BUFFER_FULL_MASK) { + old.val = prev.val; + new.val = prev.val; + *overflow = old.overflow; + if (old.f) { /* * SDB is already set by hardware. * Abort and try to set somewhere @@ -1490,10 +1509,10 @@ static bool aux_set_alert(struct aux_buffer *aux, unsigned long alert_index, */ return false; } - new_flags = orig_flags | SDB_TE_ALERT_REQ_MASK; - } while (!cmpxchg_double(&te->flags, &te->overflow, - orig_flags, orig_overflow, - new_flags, 0ULL)); + new.a = 1; + new.overflow = 0; + prev.val = __cdsg(&te->header.val, old.val, new.val); + } while (prev.val != old.val); return true; } @@ -1522,8 +1541,9 @@ static bool aux_set_alert(struct aux_buffer *aux, unsigned long alert_index, static bool aux_reset_buffer(struct aux_buffer *aux, unsigned long range, unsigned long long *overflow) { - unsigned long long orig_overflow, orig_flags, new_flags; unsigned long i, range_scan, idx, idx_old; + union hws_trailer_header old, prev, new; + unsigned long long orig_overflow; struct hws_trailer_entry *te; debug_sprintf_event(sfdbg, 6, "%s: range %ld head %ld alert %ld " @@ -1554,17 +1574,20 @@ static bool aux_reset_buffer(struct aux_buffer *aux, unsigned long range, idx_old = idx = aux->empty_mark + 1; for (i = 0; i < range_scan; i++, idx++) { te = aux_sdb_trailer(aux, idx); + /* READ_ONCE() 16 byte header */ + prev.val = __cdsg(&te->header.val, 0, 0); do { - orig_flags = te->flags; - orig_overflow = te->overflow; - new_flags = orig_flags & ~SDB_TE_BUFFER_FULL_MASK; + old.val = prev.val; + new.val = prev.val; + orig_overflow = old.overflow; + new.f = 0; + new.overflow = 0; if (idx == aux->alert_mark) - new_flags |= SDB_TE_ALERT_REQ_MASK; + new.a = 1; else - new_flags &= ~SDB_TE_ALERT_REQ_MASK; - } while (!cmpxchg_double(&te->flags, &te->overflow, - orig_flags, orig_overflow, - new_flags, 0ULL)); + new.a = 0; + prev.val = __cdsg(&te->header.val, old.val, new.val); + } while (prev.val != old.val); *overflow += orig_overflow; } diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 5ea3830af0cc..cbf9c1b0beda 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -17,6 +17,8 @@ /* Handle ro_after_init data on our own. */ #define RO_AFTER_INIT_DATA +#define RUNTIME_DISCARD_EXIT + #define EMITS_PT_NOTE #include <asm-generic/vmlinux.lds.h> @@ -79,6 +81,7 @@ SECTIONS _end_amode31_refs = .; } + . = ALIGN(PAGE_SIZE); _edata = .; /* End of data section */ /* will be freed after init */ @@ -193,6 +196,7 @@ SECTIONS BSS_SECTION(PAGE_SIZE, 4 * PAGE_SIZE, PAGE_SIZE) + . = ALIGN(PAGE_SIZE); _end = . ; /* diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 1dae78deddf2..ab26aa53ee37 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -83,8 +83,9 @@ static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id) struct esca_block *sca = vcpu->kvm->arch.sca; union esca_sigp_ctrl *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl); - union esca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl; + union esca_sigp_ctrl new_val = {0}, old_val; + old_val = READ_ONCE(*sigp_ctrl); new_val.scn = src_id; new_val.c = 1; old_val.c = 0; @@ -95,8 +96,9 @@ static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id) struct bsca_block *sca = vcpu->kvm->arch.sca; union bsca_sigp_ctrl *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl); - union bsca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl; + union bsca_sigp_ctrl new_val = {0}, old_val; + old_val = READ_ONCE(*sigp_ctrl); new_val.scn = src_id; new_val.c = 1; old_val.c = 0; @@ -126,16 +128,18 @@ static void sca_clear_ext_call(struct kvm_vcpu *vcpu) struct esca_block *sca = vcpu->kvm->arch.sca; union esca_sigp_ctrl *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl); - union esca_sigp_ctrl old = *sigp_ctrl; + union esca_sigp_ctrl old; + old = READ_ONCE(*sigp_ctrl); expect = old.value; rc = cmpxchg(&sigp_ctrl->value, old.value, 0); } else { struct bsca_block *sca = vcpu->kvm->arch.sca; union bsca_sigp_ctrl *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl); - union bsca_sigp_ctrl old = *sigp_ctrl; + union bsca_sigp_ctrl old; + old = READ_ONCE(*sigp_ctrl); expect = old.value; rc = cmpxchg(&sigp_ctrl->value, old.value, 0); } diff --git a/arch/sh/include/asm/pgtable-3level.h b/arch/sh/include/asm/pgtable-3level.h index a889a3a938ba..d1ce73f3bd85 100644 --- a/arch/sh/include/asm/pgtable-3level.h +++ b/arch/sh/include/asm/pgtable-3level.h @@ -28,7 +28,7 @@ #define pmd_ERROR(e) \ printk("%s:%d: bad pmd %016llx.\n", __FILE__, __LINE__, pmd_val(e)) -typedef struct { +typedef union { struct { unsigned long pmd_low; unsigned long pmd_high; diff --git a/arch/x86/boot/bioscall.S b/arch/x86/boot/bioscall.S index 5521ea12f44e..aa9b96457584 100644 --- a/arch/x86/boot/bioscall.S +++ b/arch/x86/boot/bioscall.S @@ -32,7 +32,7 @@ intcall: movw %dx, %si movw %sp, %di movw $11, %cx - rep; movsd + rep; movsl /* Pop full state from the stack */ popal @@ -67,7 +67,7 @@ intcall: jz 4f movw %sp, %si movw $11, %cx - rep; movsd + rep; movsl 4: addw $44, %sp /* Restore state and return */ diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c index cfd4c95b9f04..669d9e4f2901 100644 --- a/arch/x86/coco/tdx/tdx.c +++ b/arch/x86/coco/tdx/tdx.c @@ -386,8 +386,8 @@ static int handle_mmio(struct pt_regs *regs, struct ve_info *ve) { unsigned long *reg, val, vaddr; char buffer[MAX_INSN_SIZE]; + enum insn_mmio_type mmio; struct insn insn = {}; - enum mmio_type mmio; int size, extend_size; u8 extend_val = 0; @@ -402,10 +402,10 @@ static int handle_mmio(struct pt_regs *regs, struct ve_info *ve) return -EINVAL; mmio = insn_decode_mmio(&insn, &size); - if (WARN_ON_ONCE(mmio == MMIO_DECODE_FAILED)) + if (WARN_ON_ONCE(mmio == INSN_MMIO_DECODE_FAILED)) return -EINVAL; - if (mmio != MMIO_WRITE_IMM && mmio != MMIO_MOVS) { + if (mmio != INSN_MMIO_WRITE_IMM && mmio != INSN_MMIO_MOVS) { reg = insn_get_modrm_reg_ptr(&insn, regs); if (!reg) return -EINVAL; @@ -426,23 +426,23 @@ static int handle_mmio(struct pt_regs *regs, struct ve_info *ve) /* Handle writes first */ switch (mmio) { - case MMIO_WRITE: + case INSN_MMIO_WRITE: memcpy(&val, reg, size); if (!mmio_write(size, ve->gpa, val)) return -EIO; return insn.length; - case MMIO_WRITE_IMM: + case INSN_MMIO_WRITE_IMM: val = insn.immediate.value; if (!mmio_write(size, ve->gpa, val)) return -EIO; return insn.length; - case MMIO_READ: - case MMIO_READ_ZERO_EXTEND: - case MMIO_READ_SIGN_EXTEND: + case INSN_MMIO_READ: + case INSN_MMIO_READ_ZERO_EXTEND: + case INSN_MMIO_READ_SIGN_EXTEND: /* Reads are handled below */ break; - case MMIO_MOVS: - case MMIO_DECODE_FAILED: + case INSN_MMIO_MOVS: + case INSN_MMIO_DECODE_FAILED: /* * MMIO was accessed with an instruction that could not be * decoded or handled properly. It was likely not using io.h @@ -459,15 +459,15 @@ static int handle_mmio(struct pt_regs *regs, struct ve_info *ve) return -EIO; switch (mmio) { - case MMIO_READ: + case INSN_MMIO_READ: /* Zero-extend for 32-bit operation */ extend_size = size == 4 ? sizeof(*reg) : 0; break; - case MMIO_READ_ZERO_EXTEND: + case INSN_MMIO_READ_ZERO_EXTEND: /* Zero extend based on operand size */ extend_size = insn.opnd_bytes; break; - case MMIO_READ_SIGN_EXTEND: + case INSN_MMIO_READ_SIGN_EXTEND: /* Sign extend based on operand size */ extend_size = insn.opnd_bytes; if (size == 1 && val & BIT(7)) diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index d6f3703e4119..4386b10682ce 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -1387,7 +1387,7 @@ static int __init amd_core_pmu_init(void) * numbered counter following it. */ for (i = 0; i < x86_pmu.num_counters - 1; i += 2) - even_ctr_mask |= 1 << i; + even_ctr_mask |= BIT_ULL(i); pair_constraint = (struct event_constraint) __EVENT_CONSTRAINT(0, even_ctr_mask, 0, diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 6f1ccc57a692..459b1aafd4d4 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1833,6 +1833,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &adl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &adl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &spr_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &spr_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &snr_uncore_init), {}, }; diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index 074150d28fa8..c65d8906cbcf 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -69,6 +69,7 @@ static bool test_intel(int idx, void *data) case INTEL_FAM6_BROADWELL_G: case INTEL_FAM6_BROADWELL_X: case INTEL_FAM6_SAPPHIRERAPIDS_X: + case INTEL_FAM6_EMERALDRAPIDS_X: case INTEL_FAM6_ATOM_SILVERMONT: case INTEL_FAM6_ATOM_SILVERMONT_D: diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index a829492bca4c..52e6e7ed4f78 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -800,13 +800,18 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &model_hsx), X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE, &model_skl), + X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &model_skl), + X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &model_spr), + X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &model_spr), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &model_skl), + X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE, &model_skl), + X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, &model_skl), {}, }; MODULE_DEVICE_TABLE(x86cpu, rapl_model_match); diff --git a/arch/x86/include/asm/insn-eval.h b/arch/x86/include/asm/insn-eval.h index f07faa61c7f3..54368a43abf6 100644 --- a/arch/x86/include/asm/insn-eval.h +++ b/arch/x86/include/asm/insn-eval.h @@ -32,16 +32,16 @@ int insn_fetch_from_user_inatomic(struct pt_regs *regs, bool insn_decode_from_regs(struct insn *insn, struct pt_regs *regs, unsigned char buf[MAX_INSN_SIZE], int buf_size); -enum mmio_type { - MMIO_DECODE_FAILED, - MMIO_WRITE, - MMIO_WRITE_IMM, - MMIO_READ, - MMIO_READ_ZERO_EXTEND, - MMIO_READ_SIGN_EXTEND, - MMIO_MOVS, +enum insn_mmio_type { + INSN_MMIO_DECODE_FAILED, + INSN_MMIO_WRITE, + INSN_MMIO_WRITE_IMM, + INSN_MMIO_READ, + INSN_MMIO_READ_ZERO_EXTEND, + INSN_MMIO_READ_SIGN_EXTEND, + INSN_MMIO_MOVS, }; -enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes); +enum insn_mmio_type insn_decode_mmio(struct insn *insn, int *bytes); #endif /* _ASM_X86_INSN_EVAL_H */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index f35f1ff4427b..6aaae18f1854 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1111,6 +1111,7 @@ struct msr_bitmap_range { /* Xen emulation context */ struct kvm_xen { + struct mutex xen_lock; u32 xen_version; bool long_mode; bool runstate_update_flag; diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c index 7d2c75ec9a8c..ffea98f9064b 100644 --- a/arch/x86/kernel/callthunks.c +++ b/arch/x86/kernel/callthunks.c @@ -119,7 +119,7 @@ static bool is_coretext(const struct core_text *ct, void *addr) return within_module_coretext(addr); } -static __init_or_module bool skip_addr(void *dest) +static bool skip_addr(void *dest) { if (dest == error_entry) return true; @@ -181,7 +181,7 @@ static const u8 nops[] = { 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, }; -static __init_or_module void *patch_dest(void *dest, bool direct) +static void *patch_dest(void *dest, bool direct) { unsigned int tsize = SKL_TMPL_SIZE; u8 *pad = dest - tsize; diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index d970ddb0cc65..bca0bd8f4846 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1981,6 +1981,8 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl) if (ctrl == PR_SPEC_FORCE_DISABLE) task_set_spec_ib_force_disable(task); task_update_spec_tif(task); + if (task == current) + indirect_branch_prediction_barrier(); break; default: return -ERANGE; diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index efe0c30d3a12..77538abeb72a 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -146,6 +146,30 @@ static inline struct rmid_entry *__rmid_entry(u32 rmid) return entry; } +static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val) +{ + u64 msr_val; + + /* + * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured + * with a valid event code for supported resource type and the bits + * IA32_QM_EVTSEL.RMID (bits 41:32) are configured with valid RMID, + * IA32_QM_CTR.data (bits 61:0) reports the monitored data. + * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62) + * are error bits. + */ + wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid); + rdmsrl(MSR_IA32_QM_CTR, msr_val); + + if (msr_val & RMID_VAL_ERROR) + return -EIO; + if (msr_val & RMID_VAL_UNAVAIL) + return -EINVAL; + + *val = msr_val; + return 0; +} + static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom, u32 rmid, enum resctrl_event_id eventid) @@ -172,8 +196,12 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d, struct arch_mbm_state *am; am = get_arch_mbm_state(hw_dom, rmid, eventid); - if (am) + if (am) { memset(am, 0, sizeof(*am)); + + /* Record any initial, non-zero count value. */ + __rmid_read(rmid, eventid, &am->prev_msr); + } } static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width) @@ -191,25 +219,14 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d, struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); struct arch_mbm_state *am; u64 msr_val, chunks; + int ret; if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask)) return -EINVAL; - /* - * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured - * with a valid event code for supported resource type and the bits - * IA32_QM_EVTSEL.RMID (bits 41:32) are configured with valid RMID, - * IA32_QM_CTR.data (bits 61:0) reports the monitored data. - * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62) - * are error bits. - */ - wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid); - rdmsrl(MSR_IA32_QM_CTR, msr_val); - - if (msr_val & RMID_VAL_ERROR) - return -EIO; - if (msr_val & RMID_VAL_UNAVAIL) - return -EINVAL; + ret = __rmid_read(rmid, eventid, &msr_val); + if (ret) + return ret; am = get_arch_mbm_state(hw_dom, rmid, eventid); if (am) { diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index e5a48f05e787..5993da21d822 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -580,8 +580,10 @@ static int __rdtgroup_move_task(struct task_struct *tsk, /* * Ensure the task's closid and rmid are written before determining if * the task is current that will decide if it will be interrupted. + * This pairs with the full barrier between the rq->curr update and + * resctrl_sched_in() during context switch. */ - barrier(); + smp_mb(); /* * By now, the task's closid and rmid are set. If the task is current @@ -2402,6 +2404,14 @@ static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to, WRITE_ONCE(t->rmid, to->mon.rmid); /* + * Order the closid/rmid stores above before the loads + * in task_curr(). This pairs with the full barrier + * between the rq->curr update and resctrl_sched_in() + * during context switch. + */ + smp_mb(); + + /* * If the task is on a CPU, set the CPU in the mask. * The detection is inaccurate as tasks might move or * schedule before the smp function call takes place. diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 9730c88530fc..305514431f26 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -401,10 +401,8 @@ int crash_load_segments(struct kimage *image) kbuf.buf_align = ELF_CORE_HEADER_ALIGN; kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; ret = kexec_add_buffer(&kbuf); - if (ret) { - vfree((void *)image->elf_headers); + if (ret) return ret; - } image->elf_load_addr = kbuf.mem; pr_debug("Loaded ELF headers at 0x%lx bufsz=0x%lx memsz=0x%lx\n", image->elf_load_addr, kbuf.bufsz, kbuf.memsz); diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index fd0420a3e72e..cd529aed2e7b 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -37,6 +37,7 @@ #include <linux/extable.h> #include <linux/kdebug.h> #include <linux/kallsyms.h> +#include <linux/kgdb.h> #include <linux/ftrace.h> #include <linux/kasan.h> #include <linux/moduleloader.h> @@ -281,12 +282,15 @@ static int can_probe(unsigned long paddr) if (ret < 0) return 0; +#ifdef CONFIG_KGDB /* - * Another debugging subsystem might insert this breakpoint. - * In that case, we can't recover it. + * If there is a dynamically installed kgdb sw breakpoint, + * this function should not be probed. */ - if (insn.opcode.bytes[0] == INT3_INSN_OPCODE) + if (insn.opcode.bytes[0] == INT3_INSN_OPCODE && + kgdb_has_hit_break(addr)) return 0; +#endif addr += insn.length; } diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index e6b8c5362b94..e57e07b0edb6 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -15,6 +15,7 @@ #include <linux/extable.h> #include <linux/kdebug.h> #include <linux/kallsyms.h> +#include <linux/kgdb.h> #include <linux/ftrace.h> #include <linux/objtool.h> #include <linux/pgtable.h> @@ -279,19 +280,6 @@ static int insn_is_indirect_jump(struct insn *insn) return ret; } -static bool is_padding_int3(unsigned long addr, unsigned long eaddr) -{ - unsigned char ops; - - for (; addr < eaddr; addr++) { - if (get_kernel_nofault(ops, (void *)addr) < 0 || - ops != INT3_INSN_OPCODE) - return false; - } - - return true; -} - /* Decode whole function to ensure any instructions don't jump into target */ static int can_optimize(unsigned long paddr) { @@ -334,15 +322,15 @@ static int can_optimize(unsigned long paddr) ret = insn_decode_kernel(&insn, (void *)recovered_insn); if (ret < 0) return 0; - +#ifdef CONFIG_KGDB /* - * In the case of detecting unknown breakpoint, this could be - * a padding INT3 between functions. Let's check that all the - * rest of the bytes are also INT3. + * If there is a dynamically installed kgdb sw breakpoint, + * this function should not be probed. */ - if (insn.opcode.bytes[0] == INT3_INSN_OPCODE) - return is_padding_int3(addr, paddr - offset + size) ? 1 : 0; - + if (insn.opcode.bytes[0] == INT3_INSN_OPCODE && + kgdb_has_hit_break(addr)) + return 0; +#endif /* Recover address */ insn.kaddr = (void *)addr; insn.next_byte = (void *)(addr + insn.length); diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index a428c62330d3..679026a640ef 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -1536,32 +1536,32 @@ static enum es_result vc_handle_mmio_movs(struct es_em_ctxt *ctxt, static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) { struct insn *insn = &ctxt->insn; + enum insn_mmio_type mmio; unsigned int bytes = 0; - enum mmio_type mmio; enum es_result ret; u8 sign_byte; long *reg_data; mmio = insn_decode_mmio(insn, &bytes); - if (mmio == MMIO_DECODE_FAILED) + if (mmio == INSN_MMIO_DECODE_FAILED) return ES_DECODE_FAILED; - if (mmio != MMIO_WRITE_IMM && mmio != MMIO_MOVS) { + if (mmio != INSN_MMIO_WRITE_IMM && mmio != INSN_MMIO_MOVS) { reg_data = insn_get_modrm_reg_ptr(insn, ctxt->regs); if (!reg_data) return ES_DECODE_FAILED; } switch (mmio) { - case MMIO_WRITE: + case INSN_MMIO_WRITE: memcpy(ghcb->shared_buffer, reg_data, bytes); ret = vc_do_mmio(ghcb, ctxt, bytes, false); break; - case MMIO_WRITE_IMM: + case INSN_MMIO_WRITE_IMM: memcpy(ghcb->shared_buffer, insn->immediate1.bytes, bytes); ret = vc_do_mmio(ghcb, ctxt, bytes, false); break; - case MMIO_READ: + case INSN_MMIO_READ: ret = vc_do_mmio(ghcb, ctxt, bytes, true); if (ret) break; @@ -1572,7 +1572,7 @@ static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) memcpy(reg_data, ghcb->shared_buffer, bytes); break; - case MMIO_READ_ZERO_EXTEND: + case INSN_MMIO_READ_ZERO_EXTEND: ret = vc_do_mmio(ghcb, ctxt, bytes, true); if (ret) break; @@ -1581,7 +1581,7 @@ static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) memset(reg_data, 0, insn->opnd_bytes); memcpy(reg_data, ghcb->shared_buffer, bytes); break; - case MMIO_READ_SIGN_EXTEND: + case INSN_MMIO_READ_SIGN_EXTEND: ret = vc_do_mmio(ghcb, ctxt, bytes, true); if (ret) break; @@ -1600,7 +1600,7 @@ static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) memset(reg_data, sign_byte, insn->opnd_bytes); memcpy(reg_data, ghcb->shared_buffer, bytes); break; - case MMIO_MOVS: + case INSN_MMIO_MOVS: ret = vc_handle_mmio_movs(ctxt, bytes); break; default: diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index b14653b61470..596061c1610e 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -770,16 +770,22 @@ struct kvm_cpuid_array { int nent; }; +static struct kvm_cpuid_entry2 *get_next_cpuid(struct kvm_cpuid_array *array) +{ + if (array->nent >= array->maxnent) + return NULL; + + return &array->entries[array->nent++]; +} + static struct kvm_cpuid_entry2 *do_host_cpuid(struct kvm_cpuid_array *array, u32 function, u32 index) { - struct kvm_cpuid_entry2 *entry; + struct kvm_cpuid_entry2 *entry = get_next_cpuid(array); - if (array->nent >= array->maxnent) + if (!entry) return NULL; - entry = &array->entries[array->nent++]; - memset(entry, 0, sizeof(*entry)); entry->function = function; entry->index = index; @@ -956,22 +962,13 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->edx = edx.full; break; } - /* - * Per Intel's SDM, the 0x1f is a superset of 0xb, - * thus they can be handled by common code. - */ case 0x1f: case 0xb: /* - * Populate entries until the level type (ECX[15:8]) of the - * previous entry is zero. Note, CPUID EAX.{0x1f,0xb}.0 is - * the starting entry, filled by the primary do_host_cpuid(). + * No topology; a valid topology is indicated by the presence + * of subleaf 1. */ - for (i = 1; entry->ecx & 0xff00; ++i) { - entry = do_host_cpuid(array, function, i); - if (!entry) - goto out; - } + entry->eax = entry->ebx = entry->ecx = 0; break; case 0xd: { u64 permitted_xcr0 = kvm_caps.supported_xcr0 & xstate_get_guest_group_perm(); @@ -1202,6 +1199,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->ebx = entry->ecx = entry->edx = 0; break; case 0x8000001e: + /* Do not return host topology information. */ + entry->eax = entry->ebx = entry->ecx = 0; + entry->edx = 0; /* reserved */ break; case 0x8000001F: if (!kvm_cpu_cap_has(X86_FEATURE_SEV)) { diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 2c7f2a26421e..e8296942a868 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1769,6 +1769,7 @@ static bool hv_is_vp_in_sparse_set(u32 vp_id, u64 valid_bank_mask, u64 sparse_ba } struct kvm_hv_hcall { + /* Hypercall input data */ u64 param; u64 ingpa; u64 outgpa; @@ -1779,12 +1780,21 @@ struct kvm_hv_hcall { bool fast; bool rep; sse128_t xmm[HV_HYPERCALL_MAX_XMM_REGISTERS]; + + /* + * Current read offset when KVM reads hypercall input data gradually, + * either offset in bytes from 'ingpa' for regular hypercalls or the + * number of already consumed 'XMM halves' for 'fast' hypercalls. + */ + union { + gpa_t data_offset; + int consumed_xmm_halves; + }; }; static int kvm_hv_get_hc_data(struct kvm *kvm, struct kvm_hv_hcall *hc, - u16 orig_cnt, u16 cnt_cap, u64 *data, - int consumed_xmm_halves, gpa_t offset) + u16 orig_cnt, u16 cnt_cap, u64 *data) { /* * Preserve the original count when ignoring entries via a "cap", KVM @@ -1799,11 +1809,11 @@ static int kvm_hv_get_hc_data(struct kvm *kvm, struct kvm_hv_hcall *hc, * Each XMM holds two sparse banks, but do not count halves that * have already been consumed for hypercall parameters. */ - if (orig_cnt > 2 * HV_HYPERCALL_MAX_XMM_REGISTERS - consumed_xmm_halves) + if (orig_cnt > 2 * HV_HYPERCALL_MAX_XMM_REGISTERS - hc->consumed_xmm_halves) return HV_STATUS_INVALID_HYPERCALL_INPUT; for (i = 0; i < cnt; i++) { - j = i + consumed_xmm_halves; + j = i + hc->consumed_xmm_halves; if (j % 2) data[i] = sse128_hi(hc->xmm[j / 2]); else @@ -1812,27 +1822,24 @@ static int kvm_hv_get_hc_data(struct kvm *kvm, struct kvm_hv_hcall *hc, return 0; } - return kvm_read_guest(kvm, hc->ingpa + offset, data, + return kvm_read_guest(kvm, hc->ingpa + hc->data_offset, data, cnt * sizeof(*data)); } static u64 kvm_get_sparse_vp_set(struct kvm *kvm, struct kvm_hv_hcall *hc, - u64 *sparse_banks, int consumed_xmm_halves, - gpa_t offset) + u64 *sparse_banks) { if (hc->var_cnt > HV_MAX_SPARSE_VCPU_BANKS) return -EINVAL; /* Cap var_cnt to ignore banks that cannot contain a legal VP index. */ return kvm_hv_get_hc_data(kvm, hc, hc->var_cnt, KVM_HV_MAX_SPARSE_VCPU_SET_BITS, - sparse_banks, consumed_xmm_halves, offset); + sparse_banks); } -static int kvm_hv_get_tlb_flush_entries(struct kvm *kvm, struct kvm_hv_hcall *hc, u64 entries[], - int consumed_xmm_halves, gpa_t offset) +static int kvm_hv_get_tlb_flush_entries(struct kvm *kvm, struct kvm_hv_hcall *hc, u64 entries[]) { - return kvm_hv_get_hc_data(kvm, hc, hc->rep_cnt, hc->rep_cnt, - entries, consumed_xmm_halves, offset); + return kvm_hv_get_hc_data(kvm, hc, hc->rep_cnt, hc->rep_cnt, entries); } static void hv_tlb_flush_enqueue(struct kvm_vcpu *vcpu, @@ -1926,8 +1933,6 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) struct kvm_vcpu *v; unsigned long i; bool all_cpus; - int consumed_xmm_halves = 0; - gpa_t data_offset; /* * The Hyper-V TLFS doesn't allow more than HV_MAX_SPARSE_VCPU_BANKS @@ -1955,12 +1960,12 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) flush.address_space = hc->ingpa; flush.flags = hc->outgpa; flush.processor_mask = sse128_lo(hc->xmm[0]); - consumed_xmm_halves = 1; + hc->consumed_xmm_halves = 1; } else { if (unlikely(kvm_read_guest(kvm, hc->ingpa, &flush, sizeof(flush)))) return HV_STATUS_INVALID_HYPERCALL_INPUT; - data_offset = sizeof(flush); + hc->data_offset = sizeof(flush); } trace_kvm_hv_flush_tlb(flush.processor_mask, @@ -1985,12 +1990,12 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) flush_ex.flags = hc->outgpa; memcpy(&flush_ex.hv_vp_set, &hc->xmm[0], sizeof(hc->xmm[0])); - consumed_xmm_halves = 2; + hc->consumed_xmm_halves = 2; } else { if (unlikely(kvm_read_guest(kvm, hc->ingpa, &flush_ex, sizeof(flush_ex)))) return HV_STATUS_INVALID_HYPERCALL_INPUT; - data_offset = sizeof(flush_ex); + hc->data_offset = sizeof(flush_ex); } trace_kvm_hv_flush_tlb_ex(flush_ex.hv_vp_set.valid_bank_mask, @@ -2009,8 +2014,7 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) if (!hc->var_cnt) goto ret_success; - if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks, - consumed_xmm_halves, data_offset)) + if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks)) return HV_STATUS_INVALID_HYPERCALL_INPUT; } @@ -2021,8 +2025,10 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) * consumed_xmm_halves to make sure TLB flush entries are read * from the correct offset. */ - data_offset += hc->var_cnt * sizeof(sparse_banks[0]); - consumed_xmm_halves += hc->var_cnt; + if (hc->fast) + hc->consumed_xmm_halves += hc->var_cnt; + else + hc->data_offset += hc->var_cnt * sizeof(sparse_banks[0]); } if (hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE || @@ -2030,8 +2036,7 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) hc->rep_cnt > ARRAY_SIZE(__tlb_flush_entries)) { tlb_flush_entries = NULL; } else { - if (kvm_hv_get_tlb_flush_entries(kvm, hc, __tlb_flush_entries, - consumed_xmm_halves, data_offset)) + if (kvm_hv_get_tlb_flush_entries(kvm, hc, __tlb_flush_entries)) return HV_STATUS_INVALID_HYPERCALL_INPUT; tlb_flush_entries = __tlb_flush_entries; } @@ -2180,9 +2185,13 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) if (!hc->var_cnt) goto ret_success; - if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks, 1, - offsetof(struct hv_send_ipi_ex, - vp_set.bank_contents))) + if (!hc->fast) + hc->data_offset = offsetof(struct hv_send_ipi_ex, + vp_set.bank_contents); + else + hc->consumed_xmm_halves = 1; + + if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks)) return HV_STATUS_INVALID_HYPERCALL_INPUT; } diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 0687162c4f22..3742d9adacfc 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -426,8 +426,9 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, kvm_set_msi_irq(vcpu->kvm, entry, &irq); if (irq.trig_mode && - kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT, - irq.dest_id, irq.dest_mode)) + (kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT, + irq.dest_id, irq.dest_mode) || + kvm_apic_pending_eoi(vcpu, irq.vector))) __set_bit(irq.vector, ioapic_handled_vectors); } } diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 28e3769066e2..58c3242fcc7a 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -188,11 +188,11 @@ static inline bool lapic_in_kernel(struct kvm_vcpu *vcpu) extern struct static_key_false_deferred apic_hw_disabled; -static inline int kvm_apic_hw_enabled(struct kvm_lapic *apic) +static inline bool kvm_apic_hw_enabled(struct kvm_lapic *apic) { if (static_branch_unlikely(&apic_hw_disabled.key)) return apic->vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE; - return MSR_IA32_APICBASE_ENABLE; + return true; } extern struct static_key_false_deferred apic_sw_disabled; diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index 1f03701b943a..6f54dc9409c9 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -363,7 +363,7 @@ static __always_inline bool is_rsvd_spte(struct rsvd_bits_validate *rsvd_check, * A shadow-present leaf SPTE may be non-writable for 4 possible reasons: * * 1. To intercept writes for dirty logging. KVM write-protects huge pages - * so that they can be split be split down into the dirty logging + * so that they can be split down into the dirty logging * granularity (4KiB) whenever the guest writes to them. KVM also * write-protects 4KiB pages so that writes can be recorded in the dirty log * (e.g. if not using PML). SPTEs are write-protected for dirty logging diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 771210ce5181..d6df38d371a0 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -1074,7 +1074,9 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, int ret = RET_PF_FIXED; bool wrprot = false; - WARN_ON(sp->role.level != fault->goal_level); + if (WARN_ON_ONCE(sp->role.level != fault->goal_level)) + return RET_PF_RETRY; + if (unlikely(!fault->slot)) new_spte = make_mmio_spte(vcpu, iter->gfn, ACC_ALL); else @@ -1173,9 +1175,6 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) if (fault->nx_huge_page_workaround_enabled) disallowed_hugepage_adjust(fault, iter.old_spte, iter.level); - if (iter.level == fault->goal_level) - break; - /* * If SPTE has been frozen by another thread, just give up and * retry, avoiding unnecessary page table allocation and free. @@ -1183,6 +1182,9 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) if (is_removed_spte(iter.old_spte)) goto retry; + if (iter.level == fault->goal_level) + goto map_target_level; + /* Step down into the lower level page table if it exists. */ if (is_shadow_present_pte(iter.old_spte) && !is_large_pte(iter.old_spte)) @@ -1203,8 +1205,8 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) r = tdp_mmu_link_sp(kvm, &iter, sp, true); /* - * Also force the guest to retry the access if the upper level SPTEs - * aren't in place. + * Force the guest to retry if installing an upper level SPTE + * failed, e.g. because a different task modified the SPTE. */ if (r) { tdp_mmu_free_sp(sp); @@ -1214,11 +1216,20 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) if (fault->huge_page_disallowed && fault->req_level >= iter.level) { spin_lock(&kvm->arch.tdp_mmu_pages_lock); - track_possible_nx_huge_page(kvm, sp); + if (sp->nx_huge_page_disallowed) + track_possible_nx_huge_page(kvm, sp); spin_unlock(&kvm->arch.tdp_mmu_pages_lock); } } + /* + * The walk aborted before reaching the target level, e.g. because the + * iterator detected an upper level SPTE was frozen during traversal. + */ + WARN_ON_ONCE(iter.level == fault->goal_level); + goto retry; + +map_target_level: ret = tdp_mmu_map_handle_target_level(vcpu, fault, &iter); retry: diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 684393c22105..eb594620dd75 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -238,7 +238,8 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc) return false; /* recalibrate sample period and check if it's accepted by perf core */ - if (perf_event_period(pmc->perf_event, + if (is_sampling_event(pmc->perf_event) && + perf_event_period(pmc->perf_event, get_sample_period(pmc, pmc->counter))) return false; diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 85ff3c0588ba..cdb91009701d 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -140,7 +140,8 @@ static inline u64 get_sample_period(struct kvm_pmc *pmc, u64 counter_value) static inline void pmc_update_sample_period(struct kvm_pmc *pmc) { - if (!pmc->perf_event || pmc->is_paused) + if (!pmc->perf_event || pmc->is_paused || + !is_sampling_event(pmc->perf_event)) return; perf_event_period(pmc->perf_event, diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index bc9cd7086fa9..add65dd59756 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -138,15 +138,13 @@ void recalc_intercepts(struct vcpu_svm *svm) c->intercepts[i] = h->intercepts[i]; if (g->int_ctl & V_INTR_MASKING_MASK) { - /* We only want the cr8 intercept bits of L1 */ - vmcb_clr_intercept(c, INTERCEPT_CR8_READ); - vmcb_clr_intercept(c, INTERCEPT_CR8_WRITE); - /* - * Once running L2 with HF_VINTR_MASK, EFLAGS.IF does not - * affect any interrupt we may want to inject; therefore, - * interrupt window vmexits are irrelevant to L0. + * Once running L2 with HF_VINTR_MASK, EFLAGS.IF and CR8 + * does not affect any interrupt we may want to inject; + * therefore, writes to CR8 are irrelevant to L0, as are + * interrupt window vmexits. */ + vmcb_clr_intercept(c, INTERCEPT_CR8_WRITE); vmcb_clr_intercept(c, INTERCEPT_VINTR); } diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index b6f4411b613e..d93c715cda6a 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -5296,10 +5296,19 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) if (vmptr == vmx->nested.current_vmptr) nested_release_vmcs12(vcpu); - kvm_vcpu_write_guest(vcpu, - vmptr + offsetof(struct vmcs12, - launch_state), - &zero, sizeof(zero)); + /* + * Silently ignore memory errors on VMCLEAR, Intel's pseudocode + * for VMCLEAR includes a "ensure that data for VMCS referenced + * by the operand is in memory" clause that guards writes to + * memory, i.e. doing nothing for I/O is architecturally valid. + * + * FIXME: Suppress failures if and only if no memslot is found, + * i.e. exit to userspace if __copy_to_user() fails. + */ + (void)kvm_vcpu_write_guest(vcpu, + vmptr + offsetof(struct vmcs12, + launch_state), + &zero, sizeof(zero)); } else if (vmx->nested.hv_evmcs && vmptr == vmx->nested.hv_evmcs_vmptr) { nested_release_evmcs(vcpu); } @@ -6873,7 +6882,8 @@ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) SECONDARY_EXEC_ENABLE_INVPCID | SECONDARY_EXEC_RDSEED_EXITING | SECONDARY_EXEC_XSAVES | - SECONDARY_EXEC_TSC_SCALING; + SECONDARY_EXEC_TSC_SCALING | + SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE; /* * We can emulate "VMCS shadowing," even if the hardware diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index fe5615fd8295..fc9008dbed33 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -4459,6 +4459,13 @@ vmx_adjust_secondary_exec_control(struct vcpu_vmx *vmx, u32 *exec_control, * controls for features that are/aren't exposed to the guest. */ if (nested) { + /* + * All features that can be added or removed to VMX MSRs must + * be supported in the first place for nested virtualization. + */ + if (WARN_ON_ONCE(!(vmcs_config.nested.secondary_ctls_high & control))) + enabled = false; + if (enabled) vmx->nested.msrs.secondary_ctls_high |= control; else diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 312aea1854ae..da4bbd043a7b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -13132,6 +13132,9 @@ int kvm_handle_memory_failure(struct kvm_vcpu *vcpu, int r, struct x86_exception *e) { if (r == X86EMUL_PROPAGATE_FAULT) { + if (KVM_BUG_ON(!e, vcpu->kvm)) + return -EIO; + kvm_inject_emulated_page_fault(vcpu, e); return 1; } diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index d7af40240248..8fd41f5deae3 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -41,7 +41,7 @@ static int kvm_xen_shared_info_init(struct kvm *kvm, gfn_t gfn) int ret = 0; int idx = srcu_read_lock(&kvm->srcu); - if (gfn == GPA_INVALID) { + if (gfn == KVM_XEN_INVALID_GFN) { kvm_gpc_deactivate(gpc); goto out; } @@ -271,7 +271,15 @@ static void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, bool atomic) * Attempt to obtain the GPC lock on *both* (if there are two) * gfn_to_pfn caches that cover the region. */ - read_lock_irqsave(&gpc1->lock, flags); + if (atomic) { + local_irq_save(flags); + if (!read_trylock(&gpc1->lock)) { + local_irq_restore(flags); + return; + } + } else { + read_lock_irqsave(&gpc1->lock, flags); + } while (!kvm_gpc_check(gpc1, user_len1)) { read_unlock_irqrestore(&gpc1->lock, flags); @@ -304,9 +312,18 @@ static void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, bool atomic) * The guest's runstate_info is split across two pages and we * need to hold and validate both GPCs simultaneously. We can * declare a lock ordering GPC1 > GPC2 because nothing else - * takes them more than one at a time. + * takes them more than one at a time. Set a subclass on the + * gpc1 lock to make lockdep shut up about it. */ - read_lock(&gpc2->lock); + lock_set_subclass(&gpc1->lock.dep_map, 1, _THIS_IP_); + if (atomic) { + if (!read_trylock(&gpc2->lock)) { + read_unlock_irqrestore(&gpc1->lock, flags); + return; + } + } else { + read_lock(&gpc2->lock); + } if (!kvm_gpc_check(gpc2, user_len2)) { read_unlock(&gpc2->lock); @@ -590,26 +607,26 @@ int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) if (!IS_ENABLED(CONFIG_64BIT) && data->u.long_mode) { r = -EINVAL; } else { - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.xen.xen_lock); kvm->arch.xen.long_mode = !!data->u.long_mode; - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); r = 0; } break; case KVM_XEN_ATTR_TYPE_SHARED_INFO: - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.xen.xen_lock); r = kvm_xen_shared_info_init(kvm, data->u.shared_info.gfn); - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); break; case KVM_XEN_ATTR_TYPE_UPCALL_VECTOR: if (data->u.vector && data->u.vector < 0x10) r = -EINVAL; else { - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.xen.xen_lock); kvm->arch.xen.upcall_vector = data->u.vector; - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); r = 0; } break; @@ -619,9 +636,9 @@ int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) break; case KVM_XEN_ATTR_TYPE_XEN_VERSION: - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.xen.xen_lock); kvm->arch.xen.xen_version = data->u.xen_version; - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); r = 0; break; @@ -630,9 +647,9 @@ int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) r = -EOPNOTSUPP; break; } - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.xen.xen_lock); kvm->arch.xen.runstate_update_flag = !!data->u.runstate_update_flag; - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); r = 0; break; @@ -647,7 +664,7 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) { int r = -ENOENT; - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.xen.xen_lock); switch (data->type) { case KVM_XEN_ATTR_TYPE_LONG_MODE: @@ -659,7 +676,7 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) if (kvm->arch.xen.shinfo_cache.active) data->u.shared_info.gfn = gpa_to_gfn(kvm->arch.xen.shinfo_cache.gpa); else - data->u.shared_info.gfn = GPA_INVALID; + data->u.shared_info.gfn = KVM_XEN_INVALID_GFN; r = 0; break; @@ -686,7 +703,7 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) break; } - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); return r; } @@ -694,7 +711,7 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) { int idx, r = -ENOENT; - mutex_lock(&vcpu->kvm->lock); + mutex_lock(&vcpu->kvm->arch.xen.xen_lock); idx = srcu_read_lock(&vcpu->kvm->srcu); switch (data->type) { @@ -705,7 +722,7 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) BUILD_BUG_ON(offsetof(struct vcpu_info, time) != offsetof(struct compat_vcpu_info, time)); - if (data->u.gpa == GPA_INVALID) { + if (data->u.gpa == KVM_XEN_INVALID_GPA) { kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_info_cache); r = 0; break; @@ -719,7 +736,7 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) break; case KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO: - if (data->u.gpa == GPA_INVALID) { + if (data->u.gpa == KVM_XEN_INVALID_GPA) { kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_time_info_cache); r = 0; break; @@ -739,7 +756,7 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) r = -EOPNOTSUPP; break; } - if (data->u.gpa == GPA_INVALID) { + if (data->u.gpa == KVM_XEN_INVALID_GPA) { r = 0; deactivate_out: kvm_gpc_deactivate(&vcpu->arch.xen.runstate_cache); @@ -922,7 +939,7 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) } srcu_read_unlock(&vcpu->kvm->srcu, idx); - mutex_unlock(&vcpu->kvm->lock); + mutex_unlock(&vcpu->kvm->arch.xen.xen_lock); return r; } @@ -930,14 +947,14 @@ int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) { int r = -ENOENT; - mutex_lock(&vcpu->kvm->lock); + mutex_lock(&vcpu->kvm->arch.xen.xen_lock); switch (data->type) { case KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO: if (vcpu->arch.xen.vcpu_info_cache.active) data->u.gpa = vcpu->arch.xen.vcpu_info_cache.gpa; else - data->u.gpa = GPA_INVALID; + data->u.gpa = KVM_XEN_INVALID_GPA; r = 0; break; @@ -945,7 +962,7 @@ int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) if (vcpu->arch.xen.vcpu_time_info_cache.active) data->u.gpa = vcpu->arch.xen.vcpu_time_info_cache.gpa; else - data->u.gpa = GPA_INVALID; + data->u.gpa = KVM_XEN_INVALID_GPA; r = 0; break; @@ -1013,7 +1030,7 @@ int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) break; } - mutex_unlock(&vcpu->kvm->lock); + mutex_unlock(&vcpu->kvm->arch.xen.xen_lock); return r; } @@ -1069,6 +1086,7 @@ int kvm_xen_write_hypercall_page(struct kvm_vcpu *vcpu, u64 data) u8 blob_size = lm ? kvm->arch.xen_hvm_config.blob_size_64 : kvm->arch.xen_hvm_config.blob_size_32; u8 *page; + int ret; if (page_num >= blob_size) return 1; @@ -1079,10 +1097,10 @@ int kvm_xen_write_hypercall_page(struct kvm_vcpu *vcpu, u64 data) if (IS_ERR(page)) return PTR_ERR(page); - if (kvm_vcpu_write_guest(vcpu, page_addr, page, PAGE_SIZE)) { - kfree(page); + ret = kvm_vcpu_write_guest(vcpu, page_addr, page, PAGE_SIZE); + kfree(page); + if (ret) return 1; - } } return 0; } @@ -1105,7 +1123,7 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc) xhc->blob_size_32 || xhc->blob_size_64)) return -EINVAL; - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.xen.xen_lock); if (xhc->msr && !kvm->arch.xen_hvm_config.msr) static_branch_inc(&kvm_xen_enabled.key); @@ -1114,7 +1132,7 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc) memcpy(&kvm->arch.xen_hvm_config, xhc, sizeof(*xhc)); - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); return 0; } @@ -1183,30 +1201,22 @@ static bool wait_pending_event(struct kvm_vcpu *vcpu, int nr_ports, static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode, u64 param, u64 *r) { - int idx, i; struct sched_poll sched_poll; evtchn_port_t port, *ports; - gpa_t gpa; + struct x86_exception e; + int i; if (!lapic_in_kernel(vcpu) || !(vcpu->kvm->arch.xen_hvm_config.flags & KVM_XEN_HVM_CONFIG_EVTCHN_SEND)) return false; - idx = srcu_read_lock(&vcpu->kvm->srcu); - gpa = kvm_mmu_gva_to_gpa_system(vcpu, param, NULL); - srcu_read_unlock(&vcpu->kvm->srcu, idx); - if (!gpa) { - *r = -EFAULT; - return true; - } - if (IS_ENABLED(CONFIG_64BIT) && !longmode) { struct compat_sched_poll sp32; /* Sanity check that the compat struct definition is correct */ BUILD_BUG_ON(sizeof(sp32) != 16); - if (kvm_vcpu_read_guest(vcpu, gpa, &sp32, sizeof(sp32))) { + if (kvm_read_guest_virt(vcpu, param, &sp32, sizeof(sp32), &e)) { *r = -EFAULT; return true; } @@ -1220,8 +1230,8 @@ static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode, sched_poll.nr_ports = sp32.nr_ports; sched_poll.timeout = sp32.timeout; } else { - if (kvm_vcpu_read_guest(vcpu, gpa, &sched_poll, - sizeof(sched_poll))) { + if (kvm_read_guest_virt(vcpu, param, &sched_poll, + sizeof(sched_poll), &e)) { *r = -EFAULT; return true; } @@ -1243,18 +1253,13 @@ static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode, } else ports = &port; + if (kvm_read_guest_virt(vcpu, (gva_t)sched_poll.ports, ports, + sched_poll.nr_ports * sizeof(*ports), &e)) { + *r = -EFAULT; + return true; + } + for (i = 0; i < sched_poll.nr_ports; i++) { - idx = srcu_read_lock(&vcpu->kvm->srcu); - gpa = kvm_mmu_gva_to_gpa_system(vcpu, - (gva_t)(sched_poll.ports + i), - NULL); - srcu_read_unlock(&vcpu->kvm->srcu, idx); - - if (!gpa || kvm_vcpu_read_guest(vcpu, gpa, - &ports[i], sizeof(port))) { - *r = -EFAULT; - goto out; - } if (ports[i] >= max_evtchn_port(vcpu->kvm)) { *r = -EINVAL; goto out; @@ -1330,9 +1335,8 @@ static bool kvm_xen_hcall_vcpu_op(struct kvm_vcpu *vcpu, bool longmode, int cmd, int vcpu_id, u64 param, u64 *r) { struct vcpu_set_singleshot_timer oneshot; + struct x86_exception e; s64 delta; - gpa_t gpa; - int idx; if (!kvm_xen_timer_enabled(vcpu)) return false; @@ -1343,9 +1347,6 @@ static bool kvm_xen_hcall_vcpu_op(struct kvm_vcpu *vcpu, bool longmode, int cmd, *r = -EINVAL; return true; } - idx = srcu_read_lock(&vcpu->kvm->srcu); - gpa = kvm_mmu_gva_to_gpa_system(vcpu, param, NULL); - srcu_read_unlock(&vcpu->kvm->srcu, idx); /* * The only difference for 32-bit compat is the 4 bytes of @@ -1363,9 +1364,8 @@ static bool kvm_xen_hcall_vcpu_op(struct kvm_vcpu *vcpu, bool longmode, int cmd, BUILD_BUG_ON(sizeof_field(struct compat_vcpu_set_singleshot_timer, flags) != sizeof_field(struct vcpu_set_singleshot_timer, flags)); - if (!gpa || - kvm_vcpu_read_guest(vcpu, gpa, &oneshot, longmode ? sizeof(oneshot) : - sizeof(struct compat_vcpu_set_singleshot_timer))) { + if (kvm_read_guest_virt(vcpu, param, &oneshot, longmode ? sizeof(oneshot) : + sizeof(struct compat_vcpu_set_singleshot_timer), &e)) { *r = -EFAULT; return true; } @@ -1675,15 +1675,7 @@ static int kvm_xen_set_evtchn(struct kvm_xen_evtchn *xe, struct kvm *kvm) mm_borrowed = true; } - /* - * For the irqfd workqueue, using the main kvm->lock mutex is - * fine since this function is invoked from kvm_set_irq() with - * no other lock held, no srcu. In future if it will be called - * directly from a vCPU thread (e.g. on hypercall for an IPI) - * then it may need to switch to using a leaf-node mutex for - * serializing the shared_info mapping. - */ - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.xen.xen_lock); /* * It is theoretically possible for the page to be unmapped @@ -1712,7 +1704,7 @@ static int kvm_xen_set_evtchn(struct kvm_xen_evtchn *xe, struct kvm *kvm) srcu_read_unlock(&kvm->srcu, idx); } while(!rc); - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); if (mm_borrowed) kthread_unuse_mm(kvm->mm); @@ -1825,20 +1817,20 @@ static int kvm_xen_eventfd_update(struct kvm *kvm, { u32 port = data->u.evtchn.send_port; struct evtchnfd *evtchnfd; + int ret; - if (!port || port >= max_evtchn_port(kvm)) - return -EINVAL; - - mutex_lock(&kvm->lock); + /* Protect writes to evtchnfd as well as the idr lookup. */ + mutex_lock(&kvm->arch.xen.xen_lock); evtchnfd = idr_find(&kvm->arch.xen.evtchn_ports, port); - mutex_unlock(&kvm->lock); + ret = -ENOENT; if (!evtchnfd) - return -ENOENT; + goto out_unlock; /* For an UPDATE, nothing may change except the priority/vcpu */ + ret = -EINVAL; if (evtchnfd->type != data->u.evtchn.type) - return -EINVAL; + goto out_unlock; /* * Port cannot change, and if it's zero that was an eventfd @@ -1846,20 +1838,21 @@ static int kvm_xen_eventfd_update(struct kvm *kvm, */ if (!evtchnfd->deliver.port.port || evtchnfd->deliver.port.port != data->u.evtchn.deliver.port.port) - return -EINVAL; + goto out_unlock; /* We only support 2 level event channels for now */ if (data->u.evtchn.deliver.port.priority != KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL) - return -EINVAL; + goto out_unlock; - mutex_lock(&kvm->lock); evtchnfd->deliver.port.priority = data->u.evtchn.deliver.port.priority; if (evtchnfd->deliver.port.vcpu_id != data->u.evtchn.deliver.port.vcpu) { evtchnfd->deliver.port.vcpu_id = data->u.evtchn.deliver.port.vcpu; evtchnfd->deliver.port.vcpu_idx = -1; } - mutex_unlock(&kvm->lock); - return 0; + ret = 0; +out_unlock: + mutex_unlock(&kvm->arch.xen.xen_lock); + return ret; } /* @@ -1871,12 +1864,9 @@ static int kvm_xen_eventfd_assign(struct kvm *kvm, { u32 port = data->u.evtchn.send_port; struct eventfd_ctx *eventfd = NULL; - struct evtchnfd *evtchnfd = NULL; + struct evtchnfd *evtchnfd; int ret = -EINVAL; - if (!port || port >= max_evtchn_port(kvm)) - return -EINVAL; - evtchnfd = kzalloc(sizeof(struct evtchnfd), GFP_KERNEL); if (!evtchnfd) return -ENOMEM; @@ -1924,10 +1914,10 @@ static int kvm_xen_eventfd_assign(struct kvm *kvm, evtchnfd->deliver.port.priority = data->u.evtchn.deliver.port.priority; } - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.xen.xen_lock); ret = idr_alloc(&kvm->arch.xen.evtchn_ports, evtchnfd, port, port + 1, GFP_KERNEL); - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); if (ret >= 0) return 0; @@ -1945,15 +1935,14 @@ static int kvm_xen_eventfd_deassign(struct kvm *kvm, u32 port) { struct evtchnfd *evtchnfd; - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.xen.xen_lock); evtchnfd = idr_remove(&kvm->arch.xen.evtchn_ports, port); - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); if (!evtchnfd) return -ENOENT; - if (kvm) - synchronize_srcu(&kvm->srcu); + synchronize_srcu(&kvm->srcu); if (!evtchnfd->deliver.port.port) eventfd_ctx_put(evtchnfd->deliver.eventfd.ctx); kfree(evtchnfd); @@ -1962,18 +1951,42 @@ static int kvm_xen_eventfd_deassign(struct kvm *kvm, u32 port) static int kvm_xen_eventfd_reset(struct kvm *kvm) { - struct evtchnfd *evtchnfd; + struct evtchnfd *evtchnfd, **all_evtchnfds; int i; + int n = 0; + + mutex_lock(&kvm->arch.xen.xen_lock); - mutex_lock(&kvm->lock); + /* + * Because synchronize_srcu() cannot be called inside the + * critical section, first collect all the evtchnfd objects + * in an array as they are removed from evtchn_ports. + */ + idr_for_each_entry(&kvm->arch.xen.evtchn_ports, evtchnfd, i) + n++; + + all_evtchnfds = kmalloc_array(n, sizeof(struct evtchnfd *), GFP_KERNEL); + if (!all_evtchnfds) { + mutex_unlock(&kvm->arch.xen.xen_lock); + return -ENOMEM; + } + + n = 0; idr_for_each_entry(&kvm->arch.xen.evtchn_ports, evtchnfd, i) { + all_evtchnfds[n++] = evtchnfd; idr_remove(&kvm->arch.xen.evtchn_ports, evtchnfd->send_port); - synchronize_srcu(&kvm->srcu); + } + mutex_unlock(&kvm->arch.xen.xen_lock); + + synchronize_srcu(&kvm->srcu); + + while (n--) { + evtchnfd = all_evtchnfds[n]; if (!evtchnfd->deliver.port.port) eventfd_ctx_put(evtchnfd->deliver.eventfd.ctx); kfree(evtchnfd); } - mutex_unlock(&kvm->lock); + kfree(all_evtchnfds); return 0; } @@ -2002,20 +2015,22 @@ static bool kvm_xen_hcall_evtchn_send(struct kvm_vcpu *vcpu, u64 param, u64 *r) { struct evtchnfd *evtchnfd; struct evtchn_send send; - gpa_t gpa; - int idx; + struct x86_exception e; - idx = srcu_read_lock(&vcpu->kvm->srcu); - gpa = kvm_mmu_gva_to_gpa_system(vcpu, param, NULL); - srcu_read_unlock(&vcpu->kvm->srcu, idx); - - if (!gpa || kvm_vcpu_read_guest(vcpu, gpa, &send, sizeof(send))) { + /* Sanity check: this structure is the same for 32-bit and 64-bit */ + BUILD_BUG_ON(sizeof(send) != 4); + if (kvm_read_guest_virt(vcpu, param, &send, sizeof(send), &e)) { *r = -EFAULT; return true; } - /* The evtchn_ports idr is protected by vcpu->kvm->srcu */ + /* + * evtchnfd is protected by kvm->srcu; the idr lookup instead + * is protected by RCU. + */ + rcu_read_lock(); evtchnfd = idr_find(&vcpu->kvm->arch.xen.evtchn_ports, send.port); + rcu_read_unlock(); if (!evtchnfd) return false; @@ -2063,6 +2078,7 @@ void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu) void kvm_xen_init_vm(struct kvm *kvm) { + mutex_init(&kvm->arch.xen.xen_lock); idr_init(&kvm->arch.xen.evtchn_ports); kvm_gpc_init(&kvm->arch.xen.shinfo_cache, kvm, NULL, KVM_HOST_USES_PFN); } diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c index 21104c41cba0..558a605929db 100644 --- a/arch/x86/lib/insn-eval.c +++ b/arch/x86/lib/insn-eval.c @@ -1595,16 +1595,16 @@ bool insn_decode_from_regs(struct insn *insn, struct pt_regs *regs, * Returns: * * Type of the instruction. Size of the memory operand is stored in - * @bytes. If decode failed, MMIO_DECODE_FAILED returned. + * @bytes. If decode failed, INSN_MMIO_DECODE_FAILED returned. */ -enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes) +enum insn_mmio_type insn_decode_mmio(struct insn *insn, int *bytes) { - enum mmio_type type = MMIO_DECODE_FAILED; + enum insn_mmio_type type = INSN_MMIO_DECODE_FAILED; *bytes = 0; if (insn_get_opcode(insn)) - return MMIO_DECODE_FAILED; + return INSN_MMIO_DECODE_FAILED; switch (insn->opcode.bytes[0]) { case 0x88: /* MOV m8,r8 */ @@ -1613,7 +1613,7 @@ enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes) case 0x89: /* MOV m16/m32/m64, r16/m32/m64 */ if (!*bytes) *bytes = insn->opnd_bytes; - type = MMIO_WRITE; + type = INSN_MMIO_WRITE; break; case 0xc6: /* MOV m8, imm8 */ @@ -1622,7 +1622,7 @@ enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes) case 0xc7: /* MOV m16/m32/m64, imm16/imm32/imm64 */ if (!*bytes) *bytes = insn->opnd_bytes; - type = MMIO_WRITE_IMM; + type = INSN_MMIO_WRITE_IMM; break; case 0x8a: /* MOV r8, m8 */ @@ -1631,7 +1631,7 @@ enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes) case 0x8b: /* MOV r16/r32/r64, m16/m32/m64 */ if (!*bytes) *bytes = insn->opnd_bytes; - type = MMIO_READ; + type = INSN_MMIO_READ; break; case 0xa4: /* MOVS m8, m8 */ @@ -1640,7 +1640,7 @@ enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes) case 0xa5: /* MOVS m16/m32/m64, m16/m32/m64 */ if (!*bytes) *bytes = insn->opnd_bytes; - type = MMIO_MOVS; + type = INSN_MMIO_MOVS; break; case 0x0f: /* Two-byte instruction */ @@ -1651,7 +1651,7 @@ enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes) case 0xb7: /* MOVZX r32/r64, m16 */ if (!*bytes) *bytes = 2; - type = MMIO_READ_ZERO_EXTEND; + type = INSN_MMIO_READ_ZERO_EXTEND; break; case 0xbe: /* MOVSX r16/r32/r64, m8 */ @@ -1660,7 +1660,7 @@ enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes) case 0xbf: /* MOVSX r32/r64, m16 */ if (!*bytes) *bytes = 2; - type = MMIO_READ_SIGN_EXTEND; + type = INSN_MMIO_READ_SIGN_EXTEND; break; } break; diff --git a/arch/x86/lib/iomap_copy_64.S b/arch/x86/lib/iomap_copy_64.S index a1f9416bf67a..6ff2f56cb0f7 100644 --- a/arch/x86/lib/iomap_copy_64.S +++ b/arch/x86/lib/iomap_copy_64.S @@ -10,6 +10,6 @@ */ SYM_FUNC_START(__iowrite32_copy) movl %edx,%ecx - rep movsd + rep movsl RET SYM_FUNC_END(__iowrite32_copy) diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index d3987359d441..cb258f58fdc8 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -26,6 +26,7 @@ #include <asm/pti.h> #include <asm/text-patching.h> #include <asm/memtype.h> +#include <asm/paravirt.h> /* * We need to define the tracepoints somewhere, and tlb.c @@ -804,6 +805,9 @@ void __init poking_init(void) poking_mm = mm_alloc(); BUG_ON(!poking_mm); + /* Xen PV guests need the PGD to be pinned. */ + paravirt_arch_dup_mmap(NULL, poking_mm); + /* * Randomize the poking address, but make sure that the following page * will be mapped at the same PMD. We need 2 pages, so find space for 3, diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index 46de9cf5c91d..fb4b1b5e0dea 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -387,7 +387,8 @@ static unsigned long pat_x_mtrr_type(u64 start, u64 end, u8 mtrr_type, uniform; mtrr_type = mtrr_type_lookup(start, end, &uniform); - if (mtrr_type != MTRR_TYPE_WRBACK) + if (mtrr_type != MTRR_TYPE_WRBACK && + mtrr_type != MTRR_TYPE_INVALID) return _PAGE_CACHE_MODE_UC_MINUS; return _PAGE_CACHE_MODE_WB; diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index 758cbfe55daa..4b3efaa82ab7 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -12,6 +12,7 @@ */ #include <linux/acpi.h> +#include <linux/efi.h> #include <linux/pci.h> #include <linux/init.h> #include <linux/bitmap.h> @@ -442,17 +443,42 @@ static bool is_acpi_reserved(u64 start, u64 end, enum e820_type not_used) return mcfg_res.flags; } +static bool is_efi_mmio(u64 start, u64 end, enum e820_type not_used) +{ +#ifdef CONFIG_EFI + efi_memory_desc_t *md; + u64 size, mmio_start, mmio_end; + + for_each_efi_memory_desc(md) { + if (md->type == EFI_MEMORY_MAPPED_IO) { + size = md->num_pages << EFI_PAGE_SHIFT; + mmio_start = md->phys_addr; + mmio_end = mmio_start + size; + + /* + * N.B. Caller supplies (start, start + size), + * so to match, mmio_end is the first address + * *past* the EFI_MEMORY_MAPPED_IO area. + */ + if (mmio_start <= start && end <= mmio_end) + return true; + } + } +#endif + + return false; +} + typedef bool (*check_reserved_t)(u64 start, u64 end, enum e820_type type); static bool __ref is_mmconf_reserved(check_reserved_t is_reserved, struct pci_mmcfg_region *cfg, - struct device *dev, int with_e820) + struct device *dev, const char *method) { u64 addr = cfg->res.start; u64 size = resource_size(&cfg->res); u64 old_size = size; int num_buses; - char *method = with_e820 ? "E820" : "ACPI motherboard resources"; while (!is_reserved(addr, addr + size, E820_TYPE_RESERVED)) { size >>= 1; @@ -464,10 +490,10 @@ static bool __ref is_mmconf_reserved(check_reserved_t is_reserved, return false; if (dev) - dev_info(dev, "MMCONFIG at %pR reserved in %s\n", + dev_info(dev, "MMCONFIG at %pR reserved as %s\n", &cfg->res, method); else - pr_info(PREFIX "MMCONFIG at %pR reserved in %s\n", + pr_info(PREFIX "MMCONFIG at %pR reserved as %s\n", &cfg->res, method); if (old_size != size) { @@ -500,7 +526,8 @@ static bool __ref pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int early) { if (!early && !acpi_disabled) { - if (is_mmconf_reserved(is_acpi_reserved, cfg, dev, 0)) + if (is_mmconf_reserved(is_acpi_reserved, cfg, dev, + "ACPI motherboard resource")) return true; if (dev) @@ -513,6 +540,10 @@ pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int e "MMCONFIG at %pR not reserved in " "ACPI motherboard resources\n", &cfg->res); + + if (is_mmconf_reserved(is_efi_mmio, cfg, dev, + "EfiMemoryMappedIO")) + return true; } /* @@ -527,7 +558,8 @@ pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int e /* Don't try to do this check unless configuration type 1 is available. how about type 2 ?*/ if (raw_pci_ops) - return is_mmconf_reserved(e820__mapped_all, cfg, dev, 1); + return is_mmconf_reserved(e820__mapped_all, cfg, dev, + "E820 entry"); return false; } diff --git a/arch/x86/um/elfcore.c b/arch/x86/um/elfcore.c index 48a3eb09d951..650cdbbdaf45 100644 --- a/arch/x86/um/elfcore.c +++ b/arch/x86/um/elfcore.c @@ -7,7 +7,7 @@ #include <asm/elf.h> -Elf32_Half elf_core_extra_phdrs(void) +Elf32_Half elf_core_extra_phdrs(struct coredump_params *cprm) { return vsyscall_ehdr ? (((struct elfhdr *)vsyscall_ehdr)->e_phnum) : 0; } @@ -60,7 +60,7 @@ int elf_core_write_extra_data(struct coredump_params *cprm) return 1; } -size_t elf_core_extra_data_size(void) +size_t elf_core_extra_data_size(struct coredump_params *cprm) { if ( vsyscall_ehdr ) { const struct elfhdr *const ehdrp = diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 58db86f7b384..9bdc3b656b2c 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -134,11 +134,6 @@ static inline unsigned p2m_mid_index(unsigned long pfn) return (pfn / P2M_PER_PAGE) % P2M_MID_PER_PAGE; } -static inline unsigned p2m_index(unsigned long pfn) -{ - return pfn % P2M_PER_PAGE; -} - static void p2m_top_mfn_init(unsigned long *top) { unsigned i; diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h index 228e4dff5fb2..a6d09fe04831 100644 --- a/arch/xtensa/include/asm/processor.h +++ b/arch/xtensa/include/asm/processor.h @@ -154,11 +154,6 @@ struct thread_struct { unsigned long ra; /* kernel's a0: return address and window call size */ unsigned long sp; /* kernel's a1: stack pointer */ - /* struct xtensa_cpuinfo info; */ - - unsigned long bad_vaddr; /* last user fault */ - unsigned long bad_uaddr; /* last kernel fault accessing user space */ - unsigned long error_code; #ifdef CONFIG_HAVE_HW_BREAKPOINT struct perf_event *ptrace_bp[XCHAL_NUM_IBREAK]; struct perf_event *ptrace_wp[XCHAL_NUM_DBREAK]; @@ -176,10 +171,6 @@ struct thread_struct { { \ ra: 0, \ sp: sizeof(init_stack) + (long) &init_stack, \ - /*info: {0}, */ \ - bad_vaddr: 0, \ - bad_uaddr: 0, \ - error_code: 0, \ } diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c index 0c25e035ff10..cd98366a9b23 100644 --- a/arch/xtensa/kernel/traps.c +++ b/arch/xtensa/kernel/traps.c @@ -362,8 +362,6 @@ static void do_unaligned_user(struct pt_regs *regs) __die_if_kernel("Unhandled unaligned exception in kernel", regs, SIGKILL); - current->thread.bad_vaddr = regs->excvaddr; - current->thread.error_code = -3; pr_info_ratelimited("Unaligned memory access to %08lx in '%s' " "(pid = %d, pc = %#010lx)\n", regs->excvaddr, current->comm, diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index 8c781b05c0bd..faf7cf35a0ee 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -206,8 +206,6 @@ good_area: bad_area: mmap_read_unlock(mm); if (user_mode(regs)) { - current->thread.bad_vaddr = address; - current->thread.error_code = is_write; force_sig_fault(SIGSEGV, code, (void *) address); return; } @@ -232,7 +230,6 @@ do_sigbus: /* Send a sigbus, regardless of whether we were in kernel * or user mode. */ - current->thread.bad_vaddr = address; force_sig_fault(SIGBUS, BUS_ADRERR, (void *) address); /* Kernel mode? Handle exceptions or die */ @@ -252,7 +249,6 @@ bad_page_fault(struct pt_regs *regs, unsigned long address, int sig) if ((entry = search_exception_tables(regs->pc)) != NULL) { pr_debug("%s: Exception at pc=%#010lx (%lx)\n", current->comm, regs->pc, entry->fixup); - current->thread.bad_uaddr = address; regs->pc = entry->fixup; return; } |