diff options
Diffstat (limited to 'arch')
-rw-r--r-- | arch/arm64/Kconfig | 14 | ||||
-rw-r--r-- | arch/arm64/include/asm/assembler.h | 40 | ||||
-rw-r--r-- | arch/arm64/include/asm/cputype.h | 2 | ||||
-rw-r--r-- | arch/arm64/mm/proc.S | 5 | ||||
-rw-r--r-- | arch/powerpc/kvm/book3s_64_mmu_radix.c | 72 | ||||
-rw-r--r-- | arch/powerpc/kvm/book3s_hv.c | 17 | ||||
-rw-r--r-- | arch/powerpc/kvm/book3s_hv_rmhandlers.S | 8 | ||||
-rw-r--r-- | arch/x86/events/core.c | 8 | ||||
-rw-r--r-- | arch/x86/events/intel/cstate.c | 2 | ||||
-rw-r--r-- | arch/x86/events/msr.c | 9 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.c | 37 |
11 files changed, 156 insertions, 58 deletions
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 7e08c4fd1ae0..f1c20cfca4ab 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -444,6 +444,20 @@ config ARM64_ERRATUM_843419 If unsure, say Y. +config ARM64_ERRATUM_1024718 + bool "Cortex-A55: 1024718: Update of DBM/AP bits without break before make might result in incorrect update" + default y + help + This option adds work around for Arm Cortex-A55 Erratum 1024718. + + Affected Cortex-A55 cores (r0p0, r0p1, r1p0) could cause incorrect + update of the hardware dirty bit when the DBM/AP bits are updated + without a break-before-make. The work around is to disable the usage + of hardware DBM locally on the affected cores. CPUs not affected by + erratum will continue to use the feature. + + If unsure, say Y. + config CAVIUM_ERRATUM_22375 bool "Cavium erratum 22375, 24313" default y diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 463619dcadd4..25b2a4161c7a 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -25,6 +25,7 @@ #include <asm/asm-offsets.h> #include <asm/cpufeature.h> +#include <asm/cputype.h> #include <asm/page.h> #include <asm/pgtable-hwdef.h> #include <asm/ptrace.h> @@ -495,4 +496,43 @@ alternative_endif and \phys, \pte, #(((1 << (48 - PAGE_SHIFT)) - 1) << PAGE_SHIFT) .endm +/* + * Check the MIDR_EL1 of the current CPU for a given model and a range of + * variant/revision. See asm/cputype.h for the macros used below. + * + * model: MIDR_CPU_MODEL of CPU + * rv_min: Minimum of MIDR_CPU_VAR_REV() + * rv_max: Maximum of MIDR_CPU_VAR_REV() + * res: Result register. + * tmp1, tmp2, tmp3: Temporary registers + * + * Corrupts: res, tmp1, tmp2, tmp3 + * Returns: 0, if the CPU id doesn't match. Non-zero otherwise + */ + .macro cpu_midr_match model, rv_min, rv_max, res, tmp1, tmp2, tmp3 + mrs \res, midr_el1 + mov_q \tmp1, (MIDR_REVISION_MASK | MIDR_VARIANT_MASK) + mov_q \tmp2, MIDR_CPU_MODEL_MASK + and \tmp3, \res, \tmp2 // Extract model + and \tmp1, \res, \tmp1 // rev & variant + mov_q \tmp2, \model + cmp \tmp3, \tmp2 + cset \res, eq + cbz \res, .Ldone\@ // Model matches ? + + .if (\rv_min != 0) // Skip min check if rv_min == 0 + mov_q \tmp3, \rv_min + cmp \tmp1, \tmp3 + cset \res, ge + .endif // \rv_min != 0 + /* Skip rv_max check if rv_min == rv_max && rv_min != 0 */ + .if ((\rv_min != \rv_max) || \rv_min == 0) + mov_q \tmp2, \rv_max + cmp \tmp1, \tmp2 + cset \tmp2, le + and \res, \res, \tmp2 + .endif +.Ldone\@: + .endm + #endif /* __ASM_ASSEMBLER_H */ diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index be7bd19c87ec..30da0918d046 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -78,6 +78,7 @@ #define ARM_CPU_PART_AEM_V8 0xD0F #define ARM_CPU_PART_FOUNDATION 0xD00 +#define ARM_CPU_PART_CORTEX_A55 0xD05 #define ARM_CPU_PART_CORTEX_A57 0xD07 #define ARM_CPU_PART_CORTEX_A72 0xD08 #define ARM_CPU_PART_CORTEX_A53 0xD03 @@ -98,6 +99,7 @@ #define QCOM_CPU_PART_KRYO 0x200 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) +#define MIDR_CORTEX_A55 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A55) #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) #define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72) #define MIDR_CORTEX_A73 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A73) diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 139320a7f7a2..e338165000e6 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -438,6 +438,11 @@ ENTRY(__cpu_setup) cbz x9, 2f cmp x9, #2 b.lt 1f +#ifdef CONFIG_ARM64_ERRATUM_1024718 + /* Disable hardware DBM on Cortex-A55 r0p0, r0p1 & r1p0 */ + cpu_midr_match MIDR_CORTEX_A55, MIDR_CPU_VAR_REV(0, 0), MIDR_CPU_VAR_REV(1, 0), x1, x2, x3, x4 + cbnz x1, 1f +#endif orr x10, x10, #TCR_HD // hardware Dirty flag update 1: orr x10, x10, #TCR_HA // hardware Access flag update 2: diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index c5d7435455f1..27a41695fcfd 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -19,6 +19,9 @@ #include <asm/pgalloc.h> #include <asm/pte-walk.h> +static void mark_pages_dirty(struct kvm *kvm, struct kvm_memory_slot *memslot, + unsigned long gfn, unsigned int order); + /* * Supported radix tree geometry. * Like p9, we support either 5 or 9 bits at the first (lowest) level, @@ -195,6 +198,12 @@ static void kvmppc_pte_free(pte_t *ptep) kmem_cache_free(kvm_pte_cache, ptep); } +/* Like pmd_huge() and pmd_large(), but works regardless of config options */ +static inline int pmd_is_leaf(pmd_t pmd) +{ + return !!(pmd_val(pmd) & _PAGE_PTE); +} + static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa, unsigned int level, unsigned long mmu_seq) { @@ -219,7 +228,7 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa, else new_pmd = pmd_alloc_one(kvm->mm, gpa); - if (level == 0 && !(pmd && pmd_present(*pmd))) + if (level == 0 && !(pmd && pmd_present(*pmd) && !pmd_is_leaf(*pmd))) new_ptep = kvmppc_pte_alloc(); /* Check if we might have been invalidated; let the guest retry if so */ @@ -244,12 +253,30 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa, new_pmd = NULL; } pmd = pmd_offset(pud, gpa); - if (pmd_large(*pmd)) { - /* Someone else has instantiated a large page here; retry */ - ret = -EAGAIN; - goto out_unlock; - } - if (level == 1 && !pmd_none(*pmd)) { + if (pmd_is_leaf(*pmd)) { + unsigned long lgpa = gpa & PMD_MASK; + + /* + * If we raced with another CPU which has just put + * a 2MB pte in after we saw a pte page, try again. + */ + if (level == 0 && !new_ptep) { + ret = -EAGAIN; + goto out_unlock; + } + /* Valid 2MB page here already, remove it */ + old = kvmppc_radix_update_pte(kvm, pmdp_ptep(pmd), + ~0UL, 0, lgpa, PMD_SHIFT); + kvmppc_radix_tlbie_page(kvm, lgpa, PMD_SHIFT); + if (old & _PAGE_DIRTY) { + unsigned long gfn = lgpa >> PAGE_SHIFT; + struct kvm_memory_slot *memslot; + memslot = gfn_to_memslot(kvm, gfn); + if (memslot) + mark_pages_dirty(kvm, memslot, gfn, + PMD_SHIFT - PAGE_SHIFT); + } + } else if (level == 1 && !pmd_none(*pmd)) { /* * There's a page table page here, but we wanted * to install a large page. Tell the caller and let @@ -412,28 +439,24 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, } else { page = pages[0]; pfn = page_to_pfn(page); - if (PageHuge(page)) { - page = compound_head(page); - pte_size <<= compound_order(page); + if (PageCompound(page)) { + pte_size <<= compound_order(compound_head(page)); /* See if we can insert a 2MB large-page PTE here */ if (pte_size >= PMD_SIZE && - (gpa & PMD_MASK & PAGE_MASK) == - (hva & PMD_MASK & PAGE_MASK)) { + (gpa & (PMD_SIZE - PAGE_SIZE)) == + (hva & (PMD_SIZE - PAGE_SIZE))) { level = 1; pfn &= ~((PMD_SIZE >> PAGE_SHIFT) - 1); } } /* See if we can provide write access */ if (writing) { - /* - * We assume gup_fast has set dirty on the host PTE. - */ pgflags |= _PAGE_WRITE; } else { local_irq_save(flags); ptep = find_current_mm_pte(current->mm->pgd, hva, NULL, NULL); - if (ptep && pte_write(*ptep) && pte_dirty(*ptep)) + if (ptep && pte_write(*ptep)) pgflags |= _PAGE_WRITE; local_irq_restore(flags); } @@ -459,18 +482,15 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, pte = pfn_pte(pfn, __pgprot(pgflags)); ret = kvmppc_create_pte(kvm, pte, gpa, level, mmu_seq); } - if (ret == 0 || ret == -EAGAIN) - ret = RESUME_GUEST; if (page) { - /* - * We drop pages[0] here, not page because page might - * have been set to the head page of a compound, but - * we have to drop the reference on the correct tail - * page to match the get inside gup() - */ - put_page(pages[0]); + if (!ret && (pgflags & _PAGE_WRITE)) + set_page_dirty_lock(page); + put_page(page); } + + if (ret == 0 || ret == -EAGAIN) + ret = RESUME_GUEST; return ret; } @@ -676,7 +696,7 @@ void kvmppc_free_radix(struct kvm *kvm) continue; pmd = pmd_offset(pud, 0); for (im = 0; im < PTRS_PER_PMD; ++im, ++pmd) { - if (pmd_huge(*pmd)) { + if (pmd_is_leaf(*pmd)) { pmd_clear(pmd); continue; } diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index e094dc90ff1b..377d1420bd02 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -2847,7 +2847,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) */ trace_hardirqs_on(); - guest_enter(); + guest_enter_irqoff(); srcu_idx = srcu_read_lock(&vc->kvm->srcu); @@ -2855,8 +2855,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) srcu_read_unlock(&vc->kvm->srcu, srcu_idx); - guest_exit(); - trace_hardirqs_off(); set_irq_happened(trap); @@ -2890,6 +2888,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) kvmppc_set_host_core(pcpu); local_irq_enable(); + guest_exit(); /* Let secondaries go back to the offline loop */ for (i = 0; i < controlled_threads; ++i) { @@ -3619,15 +3618,17 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) goto up_out; psize = vma_kernel_pagesize(vma); - porder = __ilog2(psize); up_read(¤t->mm->mmap_sem); /* We can handle 4k, 64k or 16M pages in the VRMA */ - err = -EINVAL; - if (!(psize == 0x1000 || psize == 0x10000 || - psize == 0x1000000)) - goto out_srcu; + if (psize >= 0x1000000) + psize = 0x1000000; + else if (psize >= 0x10000) + psize = 0x10000; + else + psize = 0x1000; + porder = __ilog2(psize); senc = slb_pgsize_encoding(psize); kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T | diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 2b3194b9608f..663a398449b7 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -308,7 +308,6 @@ kvm_novcpu_exit: stw r12, STACK_SLOT_TRAP(r1) bl kvmhv_commence_exit nop - lwz r12, STACK_SLOT_TRAP(r1) b kvmhv_switch_to_host /* @@ -1136,6 +1135,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) secondary_too_late: li r12, 0 + stw r12, STACK_SLOT_TRAP(r1) cmpdi r4, 0 beq 11f stw r12, VCPU_TRAP(r4) @@ -1445,12 +1445,12 @@ mc_cont: 1: #endif /* CONFIG_KVM_XICS */ + stw r12, STACK_SLOT_TRAP(r1) mr r3, r12 /* Increment exit count, poke other threads to exit */ bl kvmhv_commence_exit nop ld r9, HSTATE_KVM_VCPU(r13) - lwz r12, VCPU_TRAP(r9) /* Stop others sending VCPU interrupts to this physical CPU */ li r0, -1 @@ -1816,6 +1816,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_POWER9_DD1) * POWER7/POWER8 guest -> host partition switch code. * We don't have to lock against tlbies but we do * have to coordinate the hardware threads. + * Here STACK_SLOT_TRAP(r1) contains the trap number. */ kvmhv_switch_to_host: /* Secondary threads wait for primary to do partition switch */ @@ -1868,11 +1869,11 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) /* If HMI, call kvmppc_realmode_hmi_handler() */ + lwz r12, STACK_SLOT_TRAP(r1) cmpwi r12, BOOK3S_INTERRUPT_HMI bne 27f bl kvmppc_realmode_hmi_handler nop - li r12, BOOK3S_INTERRUPT_HMI /* * At this point kvmppc_realmode_hmi_handler would have resync-ed * the TB. Hence it is not required to subtract guest timebase @@ -1950,6 +1951,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX) li r0, KVM_GUEST_MODE_NONE stb r0, HSTATE_IN_GUEST(r13) + lwz r12, STACK_SLOT_TRAP(r1) /* return trap # in r12 */ ld r0, SFS+PPC_LR_STKOFF(r1) addi r1, r1, SFS mtlr r0 diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 589af1eec7c1..011a47b4587c 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -27,6 +27,7 @@ #include <linux/cpu.h> #include <linux/bitops.h> #include <linux/device.h> +#include <linux/nospec.h> #include <asm/apic.h> #include <asm/stacktrace.h> @@ -304,17 +305,20 @@ set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event *event) config = attr->config; - cache_type = (config >> 0) & 0xff; + cache_type = (config >> 0) & 0xff; if (cache_type >= PERF_COUNT_HW_CACHE_MAX) return -EINVAL; + cache_type = array_index_nospec(cache_type, PERF_COUNT_HW_CACHE_MAX); cache_op = (config >> 8) & 0xff; if (cache_op >= PERF_COUNT_HW_CACHE_OP_MAX) return -EINVAL; + cache_op = array_index_nospec(cache_op, PERF_COUNT_HW_CACHE_OP_MAX); cache_result = (config >> 16) & 0xff; if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX) return -EINVAL; + cache_result = array_index_nospec(cache_result, PERF_COUNT_HW_CACHE_RESULT_MAX); val = hw_cache_event_ids[cache_type][cache_op][cache_result]; @@ -421,6 +425,8 @@ int x86_setup_perfctr(struct perf_event *event) if (attr->config >= x86_pmu.max_events) return -EINVAL; + attr->config = array_index_nospec((unsigned long)attr->config, x86_pmu.max_events); + /* * The generic map: */ diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 72db0664a53d..357e82dc0e2a 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -91,6 +91,7 @@ #include <linux/module.h> #include <linux/slab.h> #include <linux/perf_event.h> +#include <linux/nospec.h> #include <asm/cpu_device_id.h> #include <asm/intel-family.h> #include "../perf_event.h" @@ -301,6 +302,7 @@ static int cstate_pmu_event_init(struct perf_event *event) } else if (event->pmu == &cstate_pkg_pmu) { if (cfg >= PERF_CSTATE_PKG_EVENT_MAX) return -EINVAL; + cfg = array_index_nospec((unsigned long)cfg, PERF_CSTATE_PKG_EVENT_MAX); if (!pkg_msr[cfg].attr) return -EINVAL; event->hw.event_base = pkg_msr[cfg].msr; diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index 14efaa0e8684..81dd57280441 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/perf_event.h> +#include <linux/nospec.h> #include <asm/intel-family.h> enum perf_msr_id { @@ -145,9 +146,6 @@ static int msr_event_init(struct perf_event *event) if (event->attr.type != event->pmu->type) return -ENOENT; - if (cfg >= PERF_MSR_EVENT_MAX) - return -EINVAL; - /* unsupported modes and filters */ if (event->attr.exclude_user || event->attr.exclude_kernel || @@ -158,6 +156,11 @@ static int msr_event_init(struct perf_event *event) event->attr.sample_period) /* no sampling */ return -EINVAL; + if (cfg >= PERF_MSR_EVENT_MAX) + return -EINVAL; + + cfg = array_index_nospec((unsigned long)cfg, PERF_MSR_EVENT_MAX); + if (!msr[cfg].attr) return -EINVAL; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 6866c863318d..ddd83fb65da5 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1418,23 +1418,6 @@ static void start_sw_tscdeadline(struct kvm_lapic *apic) local_irq_restore(flags); } -static void start_sw_period(struct kvm_lapic *apic) -{ - if (!apic->lapic_timer.period) - return; - - if (apic_lvtt_oneshot(apic) && - ktime_after(ktime_get(), - apic->lapic_timer.target_expiration)) { - apic_timer_expired(apic); - return; - } - - hrtimer_start(&apic->lapic_timer.timer, - apic->lapic_timer.target_expiration, - HRTIMER_MODE_ABS_PINNED); -} - static bool set_target_expiration(struct kvm_lapic *apic) { ktime_t now; @@ -1491,6 +1474,26 @@ static void advance_periodic_target_expiration(struct kvm_lapic *apic) apic->lapic_timer.period); } +static void start_sw_period(struct kvm_lapic *apic) +{ + if (!apic->lapic_timer.period) + return; + + if (ktime_after(ktime_get(), + apic->lapic_timer.target_expiration)) { + apic_timer_expired(apic); + + if (apic_lvtt_oneshot(apic)) + return; + + advance_periodic_target_expiration(apic); + } + + hrtimer_start(&apic->lapic_timer.timer, + apic->lapic_timer.target_expiration, + HRTIMER_MODE_ABS_PINNED); +} + bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu) { if (!lapic_in_kernel(vcpu)) |