diff options
Diffstat (limited to 'arch')
32 files changed, 327 insertions, 85 deletions
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index 8073625371f5..07060e5b5864 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -59,6 +59,9 @@ struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata; static __read_mostly unsigned int xen_events_irq; +uint32_t xen_start_flags; +EXPORT_SYMBOL(xen_start_flags); + int xen_remap_domain_gfn_array(struct vm_area_struct *vma, unsigned long addr, xen_pfn_t *gfn, int nr, @@ -293,9 +296,7 @@ void __init xen_early_init(void) xen_setup_features(); if (xen_feature(XENFEAT_dom0)) - xen_start_info->flags |= SIF_INITDOMAIN|SIF_PRIVILEGED; - else - xen_start_info->flags &= ~(SIF_INITDOMAIN|SIF_PRIVILEGED); + xen_start_flags |= SIF_INITDOMAIN|SIF_PRIVILEGED; if (!console_set_on_cmdline && !xen_initial_domain()) add_preferred_console("hvc", 0, NULL); diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c index 253188fb8cb0..e3e50950a863 100644 --- a/arch/arm64/crypto/aes-glue.c +++ b/arch/arm64/crypto/aes-glue.c @@ -223,8 +223,8 @@ static int ctr_encrypt(struct skcipher_request *req) kernel_neon_begin(); aes_ctr_encrypt(walk.dst.virt.addr, walk.src.virt.addr, (u8 *)ctx->key_enc, rounds, blocks, walk.iv); - err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE); kernel_neon_end(); + err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE); } if (walk.nbytes) { u8 __aligned(8) tail[AES_BLOCK_SIZE]; diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index fda9a8ca48be..fe8777b12f86 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -306,6 +306,7 @@ struct kvm_vcpu_arch { #define KVM_ARM64_FP_ENABLED (1 << 1) /* guest FP regs loaded */ #define KVM_ARM64_FP_HOST (1 << 2) /* host FP regs loaded */ #define KVM_ARM64_HOST_SVE_IN_USE (1 << 3) /* backup for host TIF_SVE */ +#define KVM_ARM64_HOST_SVE_ENABLED (1 << 4) /* SVE enabled for EL0 */ #define vcpu_gp_regs(v) (&(v)->arch.ctxt.gp_regs) diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 6171178075dc..a8f84812c6e8 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -728,6 +728,17 @@ asm( asm volatile("msr_s " __stringify(r) ", %x0" : : "rZ" (__val)); \ } while (0) +/* + * Modify bits in a sysreg. Bits in the clear mask are zeroed, then bits in the + * set mask are set. Other bits are left as-is. + */ +#define sysreg_clear_set(sysreg, clear, set) do { \ + u64 __scs_val = read_sysreg(sysreg); \ + u64 __scs_new = (__scs_val & ~(u64)(clear)) | (set); \ + if (__scs_new != __scs_val) \ + write_sysreg(__scs_new, sysreg); \ +} while (0) + static inline void config_sctlr_el1(u32 clear, u32 set) { u32 val; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index d2856b129097..f24892a40d2c 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -937,7 +937,7 @@ static int __init parse_kpti(char *str) __kpti_forced = enabled ? 1 : -1; return 0; } -__setup("kpti=", parse_kpti); +early_param("kpti", parse_kpti); #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */ #ifdef CONFIG_ARM64_HW_AFDBM diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index f3e2e3aec0b0..2faa9863d2e5 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -179,7 +179,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) * This is the secondary CPU boot entry. We're using this CPUs * idle thread stack, but a set of temporary page tables. */ -asmlinkage void secondary_start_kernel(void) +asmlinkage notrace void secondary_start_kernel(void) { u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK; struct mm_struct *mm = &init_mm; diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index dc6ecfa5a2d2..aac7808ce216 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -5,13 +5,14 @@ * Copyright 2018 Arm Limited * Author: Dave Martin <Dave.Martin@arm.com> */ -#include <linux/bottom_half.h> +#include <linux/irqflags.h> #include <linux/sched.h> #include <linux/thread_info.h> #include <linux/kvm_host.h> #include <asm/kvm_asm.h> #include <asm/kvm_host.h> #include <asm/kvm_mmu.h> +#include <asm/sysreg.h> /* * Called on entry to KVM_RUN unless this vcpu previously ran at least @@ -61,10 +62,16 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) { BUG_ON(!current->mm); - vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED | KVM_ARM64_HOST_SVE_IN_USE); + vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED | + KVM_ARM64_HOST_SVE_IN_USE | + KVM_ARM64_HOST_SVE_ENABLED); vcpu->arch.flags |= KVM_ARM64_FP_HOST; + if (test_thread_flag(TIF_SVE)) vcpu->arch.flags |= KVM_ARM64_HOST_SVE_IN_USE; + + if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN) + vcpu->arch.flags |= KVM_ARM64_HOST_SVE_ENABLED; } /* @@ -92,19 +99,30 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu) */ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) { - local_bh_disable(); + unsigned long flags; - update_thread_flag(TIF_SVE, - vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE); + local_irq_save(flags); if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) { /* Clean guest FP state to memory and invalidate cpu view */ fpsimd_save(); fpsimd_flush_cpu_state(); - } else if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) { - /* Ensure user trap controls are correctly restored */ - fpsimd_bind_task_to_cpu(); + } else if (system_supports_sve()) { + /* + * The FPSIMD/SVE state in the CPU has not been touched, and we + * have SVE (and VHE): CPACR_EL1 (alias CPTR_EL2) has been + * reset to CPACR_EL1_DEFAULT by the Hyp code, disabling SVE + * for EL0. To avoid spurious traps, restore the trap state + * seen by kvm_arch_vcpu_load_fp(): + */ + if (vcpu->arch.flags & KVM_ARM64_HOST_SVE_ENABLED) + sysreg_clear_set(CPACR_EL1, 0, CPACR_EL1_ZEN_EL0EN); + else + sysreg_clear_set(CPACR_EL1, CPACR_EL1_ZEN_EL0EN, 0); } - local_bh_enable(); + update_thread_flag(TIF_SVE, + vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE); + + local_irq_restore(flags); } diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 49e217ac7e1e..61e93f0b5482 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -583,13 +583,14 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, size >> PAGE_SHIFT); return NULL; } - if (!coherent) - __dma_flush_area(page_to_virt(page), iosize); - addr = dma_common_contiguous_remap(page, size, VM_USERMAP, prot, __builtin_return_address(0)); - if (!addr) { + if (addr) { + memset(addr, 0, size); + if (!coherent) + __dma_flush_area(page_to_virt(page), iosize); + } else { iommu_dma_unmap_page(dev, *handle, iosize, 0, attrs); dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT); diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 5f9a73a4452c..03646e6a2ef4 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -217,8 +217,9 @@ ENDPROC(idmap_cpu_replace_ttbr1) .macro __idmap_kpti_put_pgtable_ent_ng, type orr \type, \type, #PTE_NG // Same bit for blocks and pages - str \type, [cur_\()\type\()p] // Update the entry and ensure it - dc civac, cur_\()\type\()p // is visible to all CPUs. + str \type, [cur_\()\type\()p] // Update the entry and ensure + dmb sy // that it is visible to all + dc civac, cur_\()\type\()p // CPUs. .endm /* diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index bd06a3ccda31..2ea575cb3401 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -244,6 +244,7 @@ cpu-as-$(CONFIG_4xx) += -Wa,-m405 cpu-as-$(CONFIG_ALTIVEC) += $(call as-option,-Wa$(comma)-maltivec) cpu-as-$(CONFIG_E200) += -Wa,-me200 cpu-as-$(CONFIG_PPC_BOOK3S_64) += -Wa,-mpower4 +cpu-as-$(CONFIG_PPC_E500MC) += $(call as-option,-Wa$(comma)-me500mc) KBUILD_AFLAGS += $(cpu-as-y) KBUILD_CFLAGS += $(cpu-as-y) diff --git a/arch/powerpc/include/asm/book3s/32/pgalloc.h b/arch/powerpc/include/asm/book3s/32/pgalloc.h index 6a6673907e45..e4633803fe43 100644 --- a/arch/powerpc/include/asm/book3s/32/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/32/pgalloc.h @@ -108,6 +108,7 @@ static inline void pgtable_free(void *table, unsigned index_size) } #define check_pgt_cache() do { } while (0) +#define get_hugepd_cache_index(x) (x) #ifdef CONFIG_SMP static inline void pgtable_free_tlb(struct mmu_gather *tlb, diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-4k.h b/arch/powerpc/include/asm/book3s/64/pgtable-4k.h index af5f2baac80f..a069dfcac9a9 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable-4k.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable-4k.h @@ -49,6 +49,27 @@ static inline int hugepd_ok(hugepd_t hpd) } #define is_hugepd(hpd) (hugepd_ok(hpd)) +/* + * 16M and 16G huge page directory tables are allocated from slab cache + * + */ +#define H_16M_CACHE_INDEX (PAGE_SHIFT + H_PTE_INDEX_SIZE + H_PMD_INDEX_SIZE - 24) +#define H_16G_CACHE_INDEX \ + (PAGE_SHIFT + H_PTE_INDEX_SIZE + H_PMD_INDEX_SIZE + H_PUD_INDEX_SIZE - 34) + +static inline int get_hugepd_cache_index(int index) +{ + switch (index) { + case H_16M_CACHE_INDEX: + return HTLB_16M_INDEX; + case H_16G_CACHE_INDEX: + return HTLB_16G_INDEX; + default: + BUG(); + } + /* should not reach */ +} + #else /* !CONFIG_HUGETLB_PAGE */ static inline int pmd_huge(pmd_t pmd) { return 0; } static inline int pud_huge(pud_t pud) { return 0; } diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h index fb4b3ba52339..d7ee249d6890 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h @@ -45,8 +45,17 @@ static inline int hugepd_ok(hugepd_t hpd) { return 0; } + #define is_hugepd(pdep) 0 +/* + * This should never get called + */ +static inline int get_hugepd_cache_index(int index) +{ + BUG(); +} + #else /* !CONFIG_HUGETLB_PAGE */ static inline int pmd_huge(pmd_t pmd) { return 0; } static inline int pud_huge(pud_t pud) { return 0; } diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 63cee159022b..42aafba7a308 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -287,6 +287,11 @@ enum pgtable_index { PMD_INDEX, PUD_INDEX, PGD_INDEX, + /* + * Below are used with 4k page size and hugetlb + */ + HTLB_16M_INDEX, + HTLB_16G_INDEX, }; extern unsigned long __vmalloc_start; diff --git a/arch/powerpc/include/asm/nmi.h b/arch/powerpc/include/asm/nmi.h index 0f571e0ebca1..bd9ba8defd72 100644 --- a/arch/powerpc/include/asm/nmi.h +++ b/arch/powerpc/include/asm/nmi.h @@ -8,7 +8,7 @@ extern void arch_touch_nmi_watchdog(void); static inline void arch_touch_nmi_watchdog(void) {} #endif -#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_STACKTRACE) +#if defined(CONFIG_NMI_IPI) && defined(CONFIG_STACKTRACE) extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self); #define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace diff --git a/arch/powerpc/include/asm/nohash/32/pgalloc.h b/arch/powerpc/include/asm/nohash/32/pgalloc.h index 1707781d2f20..9de40eb614da 100644 --- a/arch/powerpc/include/asm/nohash/32/pgalloc.h +++ b/arch/powerpc/include/asm/nohash/32/pgalloc.h @@ -109,6 +109,7 @@ static inline void pgtable_free(void *table, unsigned index_size) } #define check_pgt_cache() do { } while (0) +#define get_hugepd_cache_index(x) (x) #ifdef CONFIG_SMP static inline void pgtable_free_tlb(struct mmu_gather *tlb, diff --git a/arch/powerpc/include/asm/nohash/64/pgalloc.h b/arch/powerpc/include/asm/nohash/64/pgalloc.h index 0e693f322cb2..e2d62d033708 100644 --- a/arch/powerpc/include/asm/nohash/64/pgalloc.h +++ b/arch/powerpc/include/asm/nohash/64/pgalloc.h @@ -141,6 +141,7 @@ static inline void pgtable_free(void *table, int shift) } } +#define get_hugepd_cache_index(x) (x) #ifdef CONFIG_SMP static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift) { diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 4be1c0de9406..96dd3d871986 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -711,7 +711,8 @@ static __init void cpufeatures_cpu_quirks(void) cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_HV_ASSIST; cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_XER_SO_BUG; cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1; - } else /* DD2.1 and up have DD2_1 */ + } else if ((version & 0xffff0000) == 0x004e0000) + /* DD2.1 and up have DD2_1 */ cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1; if ((version & 0xffff0000) == 0x004e0000) { diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 62b1a40d8957..40b44bb53a4e 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -701,11 +701,18 @@ static int ppc_panic_event(struct notifier_block *this, unsigned long event, void *ptr) { /* + * panic does a local_irq_disable, but we really + * want interrupts to be hard disabled. + */ + hard_irq_disable(); + + /* * If firmware-assisted dump has been registered then trigger * firmware-assisted dump and let firmware handle everything else. */ crash_fadump(NULL, ptr); - ppc_md.panic(ptr); /* May not return */ + if (ppc_md.panic) + ppc_md.panic(ptr); /* May not return */ return NOTIFY_DONE; } @@ -716,7 +723,8 @@ static struct notifier_block ppc_panic_block = { void __init setup_panic(void) { - if (!ppc_md.panic) + /* PPC64 always does a hard irq disable in its panic handler */ + if (!IS_ENABLED(CONFIG_PPC64) && !ppc_md.panic) return; atomic_notifier_chain_register(&panic_notifier_list, &ppc_panic_block); } diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 7a7ce8ad455e..225bc5f91049 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -387,6 +387,14 @@ void early_setup_secondary(void) #endif /* CONFIG_SMP */ +void panic_smp_self_stop(void) +{ + hard_irq_disable(); + spin_begin(); + while (1) + spin_cpu_relax(); +} + #if defined(CONFIG_SMP) || defined(CONFIG_KEXEC_CORE) static bool use_spinloop(void) { diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 5eadfffabe35..4794d6b4f4d2 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -600,9 +600,6 @@ static void nmi_stop_this_cpu(struct pt_regs *regs) nmi_ipi_busy_count--; nmi_ipi_unlock(); - /* Remove this CPU */ - set_cpu_online(smp_processor_id(), false); - spin_begin(); while (1) spin_cpu_relax(); @@ -617,9 +614,6 @@ void smp_send_stop(void) static void stop_this_cpu(void *dummy) { - /* Remove this CPU */ - set_cpu_online(smp_processor_id(), false); - hard_irq_disable(); spin_begin(); while (1) diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c index 07e97f289c52..e2c50b55138f 100644 --- a/arch/powerpc/kernel/stacktrace.c +++ b/arch/powerpc/kernel/stacktrace.c @@ -196,7 +196,7 @@ save_stack_trace_tsk_reliable(struct task_struct *tsk, EXPORT_SYMBOL_GPL(save_stack_trace_tsk_reliable); #endif /* CONFIG_HAVE_RELIABLE_STACKTRACE */ -#ifdef CONFIG_PPC_BOOK3S_64 +#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_NMI_IPI) static void handle_backtrace_ipi(struct pt_regs *regs) { nmi_cpu_backtrace(regs); @@ -242,4 +242,4 @@ void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self) { nmi_trigger_cpumask_backtrace(mask, exclude_self, raise_backtrace_ipi); } -#endif /* CONFIG_PPC64 */ +#endif /* defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_NMI_IPI) */ diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 7c5f479c5c00..8a9a49c13865 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -337,7 +337,8 @@ static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshif if (shift >= pdshift) hugepd_free(tlb, hugepte); else - pgtable_free_tlb(tlb, hugepte, pdshift - shift); + pgtable_free_tlb(tlb, hugepte, + get_hugepd_cache_index(pdshift - shift)); } static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud, diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c index c1f4ca45c93a..4afbfbb64bfd 100644 --- a/arch/powerpc/mm/pgtable-book3s64.c +++ b/arch/powerpc/mm/pgtable-book3s64.c @@ -409,6 +409,18 @@ static inline void pgtable_free(void *table, int index) case PUD_INDEX: kmem_cache_free(PGT_CACHE(PUD_CACHE_INDEX), table); break; +#if defined(CONFIG_PPC_4K_PAGES) && defined(CONFIG_HUGETLB_PAGE) + /* 16M hugepd directory at pud level */ + case HTLB_16M_INDEX: + BUILD_BUG_ON(H_16M_CACHE_INDEX <= 0); + kmem_cache_free(PGT_CACHE(H_16M_CACHE_INDEX), table); + break; + /* 16G hugepd directory at the pgd level */ + case HTLB_16G_INDEX: + BUILD_BUG_ON(H_16G_CACHE_INDEX <= 0); + kmem_cache_free(PGT_CACHE(H_16G_CACHE_INDEX), table); + break; +#endif /* We don't free pgd table via RCU callback */ default: BUG(); diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c index 67a6e86d3e7e..1135b43a597c 100644 --- a/arch/powerpc/mm/tlb-radix.c +++ b/arch/powerpc/mm/tlb-radix.c @@ -689,22 +689,17 @@ EXPORT_SYMBOL(radix__flush_tlb_kernel_range); static unsigned long tlb_single_page_flush_ceiling __read_mostly = 33; static unsigned long tlb_local_single_page_flush_ceiling __read_mostly = POWER9_TLB_SETS_RADIX * 2; -void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start, - unsigned long end) +static inline void __radix__flush_tlb_range(struct mm_struct *mm, + unsigned long start, unsigned long end, + bool flush_all_sizes) { - struct mm_struct *mm = vma->vm_mm; unsigned long pid; unsigned int page_shift = mmu_psize_defs[mmu_virtual_psize].shift; unsigned long page_size = 1UL << page_shift; unsigned long nr_pages = (end - start) >> page_shift; bool local, full; -#ifdef CONFIG_HUGETLB_PAGE - if (is_vm_hugetlb_page(vma)) - return radix__flush_hugetlb_tlb_range(vma, start, end); -#endif - pid = mm->context.id; if (unlikely(pid == MMU_NO_CONTEXT)) return; @@ -738,37 +733,64 @@ is_local: _tlbie_pid(pid, RIC_FLUSH_TLB); } } else { - bool hflush = false; + bool hflush = flush_all_sizes; + bool gflush = flush_all_sizes; unsigned long hstart, hend; + unsigned long gstart, gend; -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - hstart = (start + HPAGE_PMD_SIZE - 1) >> HPAGE_PMD_SHIFT; - hend = end >> HPAGE_PMD_SHIFT; - if (hstart < hend) { - hstart <<= HPAGE_PMD_SHIFT; - hend <<= HPAGE_PMD_SHIFT; + if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) hflush = true; + + if (hflush) { + hstart = (start + PMD_SIZE - 1) & PMD_MASK; + hend = end & PMD_MASK; + if (hstart == hend) + hflush = false; + } + + if (gflush) { + gstart = (start + PUD_SIZE - 1) & PUD_MASK; + gend = end & PUD_MASK; + if (gstart == gend) + gflush = false; } -#endif asm volatile("ptesync": : :"memory"); if (local) { __tlbiel_va_range(start, end, pid, page_size, mmu_virtual_psize); if (hflush) __tlbiel_va_range(hstart, hend, pid, - HPAGE_PMD_SIZE, MMU_PAGE_2M); + PMD_SIZE, MMU_PAGE_2M); + if (gflush) + __tlbiel_va_range(gstart, gend, pid, + PUD_SIZE, MMU_PAGE_1G); asm volatile("ptesync": : :"memory"); } else { __tlbie_va_range(start, end, pid, page_size, mmu_virtual_psize); if (hflush) __tlbie_va_range(hstart, hend, pid, - HPAGE_PMD_SIZE, MMU_PAGE_2M); + PMD_SIZE, MMU_PAGE_2M); + if (gflush) + __tlbie_va_range(gstart, gend, pid, + PUD_SIZE, MMU_PAGE_1G); fixup_tlbie(); asm volatile("eieio; tlbsync; ptesync": : :"memory"); } } preempt_enable(); } + +void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end) + +{ +#ifdef CONFIG_HUGETLB_PAGE + if (is_vm_hugetlb_page(vma)) + return radix__flush_hugetlb_tlb_range(vma, start, end); +#endif + + __radix__flush_tlb_range(vma->vm_mm, start, end, false); +} EXPORT_SYMBOL(radix__flush_tlb_range); static int radix_get_mmu_psize(int page_size) @@ -837,6 +859,8 @@ void radix__tlb_flush(struct mmu_gather *tlb) int psize = 0; struct mm_struct *mm = tlb->mm; int page_size = tlb->page_size; + unsigned long start = tlb->start; + unsigned long end = tlb->end; /* * if page size is not something we understand, do a full mm flush @@ -847,15 +871,45 @@ void radix__tlb_flush(struct mmu_gather *tlb) */ if (tlb->fullmm) { __flush_all_mm(mm, true); +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE) + } else if (mm_tlb_flush_nested(mm)) { + /* + * If there is a concurrent invalidation that is clearing ptes, + * then it's possible this invalidation will miss one of those + * cleared ptes and miss flushing the TLB. If this invalidate + * returns before the other one flushes TLBs, that can result + * in it returning while there are still valid TLBs inside the + * range to be invalidated. + * + * See mm/memory.c:tlb_finish_mmu() for more details. + * + * The solution to this is ensure the entire range is always + * flushed here. The problem for powerpc is that the flushes + * are page size specific, so this "forced flush" would not + * do the right thing if there are a mix of page sizes in + * the range to be invalidated. So use __flush_tlb_range + * which invalidates all possible page sizes in the range. + * + * PWC flush probably is not be required because the core code + * shouldn't free page tables in this path, but accounting + * for the possibility makes us a bit more robust. + * + * need_flush_all is an uncommon case because page table + * teardown should be done with exclusive locks held (but + * after locks are dropped another invalidate could come + * in), it could be optimized further if necessary. + */ + if (!tlb->need_flush_all) + __radix__flush_tlb_range(mm, start, end, true); + else + radix__flush_all_mm(mm); +#endif } else if ( (psize = radix_get_mmu_psize(page_size)) == -1) { if (!tlb->need_flush_all) radix__flush_tlb_mm(mm); else radix__flush_all_mm(mm); } else { - unsigned long start = tlb->start; - unsigned long end = tlb->end; - if (!tlb->need_flush_all) radix__flush_tlb_range_psize(mm, start, end, psize); else @@ -1043,6 +1097,8 @@ extern void radix_kvm_prefetch_workaround(struct mm_struct *mm) for (; sib <= cpu_last_thread_sibling(cpu) && !flush; sib++) { if (sib == cpu) continue; + if (!cpu_possible(sib)) + continue; if (paca_ptrs[sib]->kvm_hstate.kvm_vcpu) flush = true; } diff --git a/arch/s390/include/asm/css_chars.h b/arch/s390/include/asm/css_chars.h index 0563fd3e8458..480bb02ccacd 100644 --- a/arch/s390/include/asm/css_chars.h +++ b/arch/s390/include/asm/css_chars.h @@ -6,36 +6,38 @@ struct css_general_char { u64 : 12; - u32 dynio : 1; /* bit 12 */ - u32 : 4; - u32 eadm : 1; /* bit 17 */ - u32 : 23; - u32 aif : 1; /* bit 41 */ - u32 : 3; - u32 mcss : 1; /* bit 45 */ - u32 fcs : 1; /* bit 46 */ - u32 : 1; - u32 ext_mb : 1; /* bit 48 */ - u32 : 7; - u32 aif_tdd : 1; /* bit 56 */ - u32 : 1; - u32 qebsm : 1; /* bit 58 */ - u32 : 2; - u32 aiv : 1; /* bit 61 */ - u32 : 5; - u32 aif_osa : 1; /* bit 67 */ - u32 : 12; - u32 eadm_rf : 1; /* bit 80 */ - u32 : 1; - u32 cib : 1; /* bit 82 */ - u32 : 5; - u32 fcx : 1; /* bit 88 */ - u32 : 19; - u32 alt_ssi : 1; /* bit 108 */ - u32 : 1; - u32 narf : 1; /* bit 110 */ - u32 : 12; - u32 util_str : 1;/* bit 123 */ + u64 dynio : 1; /* bit 12 */ + u64 : 4; + u64 eadm : 1; /* bit 17 */ + u64 : 23; + u64 aif : 1; /* bit 41 */ + u64 : 3; + u64 mcss : 1; /* bit 45 */ + u64 fcs : 1; /* bit 46 */ + u64 : 1; + u64 ext_mb : 1; /* bit 48 */ + u64 : 7; + u64 aif_tdd : 1; /* bit 56 */ + u64 : 1; + u64 qebsm : 1; /* bit 58 */ + u64 : 2; + u64 aiv : 1; /* bit 61 */ + u64 : 2; + + u64 : 3; + u64 aif_osa : 1; /* bit 67 */ + u64 : 12; + u64 eadm_rf : 1; /* bit 80 */ + u64 : 1; + u64 cib : 1; /* bit 82 */ + u64 : 5; + u64 fcx : 1; /* bit 88 */ + u64 : 19; + u64 alt_ssi : 1; /* bit 108 */ + u64 : 1; + u64 narf : 1; /* bit 110 */ + u64 : 12; + u64 util_str : 1;/* bit 123 */ } __packed; extern struct css_general_char css_general_characteristics; diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 425e6b8b9547..6aa8499e1f62 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -114,6 +114,7 @@ #define VMX_MISC_PREEMPTION_TIMER_RATE_MASK 0x0000001f #define VMX_MISC_SAVE_EFER_LMA 0x00000020 #define VMX_MISC_ACTIVITY_HLT 0x00000040 +#define VMX_MISC_ZERO_LEN_INS 0x40000000 /* VMFUNC functions */ #define VMX_VMFUNC_EPTP_SWITCHING 0x00000001 @@ -351,11 +352,13 @@ enum vmcs_field { #define VECTORING_INFO_VALID_MASK INTR_INFO_VALID_MASK #define INTR_TYPE_EXT_INTR (0 << 8) /* external interrupt */ +#define INTR_TYPE_RESERVED (1 << 8) /* reserved */ #define INTR_TYPE_NMI_INTR (2 << 8) /* NMI */ #define INTR_TYPE_HARD_EXCEPTION (3 << 8) /* processor exception */ #define INTR_TYPE_SOFT_INTR (4 << 8) /* software interrupt */ #define INTR_TYPE_PRIV_SW_EXCEPTION (5 << 8) /* ICE breakpoint - undocumented */ #define INTR_TYPE_SOFT_EXCEPTION (6 << 8) /* software exception */ +#define INTR_TYPE_OTHER_EVENT (7 << 8) /* other event */ /* GUEST_INTERRUPTIBILITY_INFO flags. */ #define GUEST_INTR_STATE_STI 0x00000001 diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 559a12b6184d..1689f433f3a0 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1705,6 +1705,17 @@ static inline bool nested_cpu_has_vmwrite_any_field(struct kvm_vcpu *vcpu) MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS; } +static inline bool nested_cpu_has_zero_length_injection(struct kvm_vcpu *vcpu) +{ + return to_vmx(vcpu)->nested.msrs.misc_low & VMX_MISC_ZERO_LEN_INS; +} + +static inline bool nested_cpu_supports_monitor_trap_flag(struct kvm_vcpu *vcpu) +{ + return to_vmx(vcpu)->nested.msrs.procbased_ctls_high & + CPU_BASED_MONITOR_TRAP_FLAG; +} + static inline bool nested_cpu_has(struct vmcs12 *vmcs12, u32 bit) { return vmcs12->cpu_based_vm_exec_control & bit; @@ -11620,6 +11631,62 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) !nested_cr3_valid(vcpu, vmcs12->host_cr3)) return VMXERR_ENTRY_INVALID_HOST_STATE_FIELD; + /* + * From the Intel SDM, volume 3: + * Fields relevant to VM-entry event injection must be set properly. + * These fields are the VM-entry interruption-information field, the + * VM-entry exception error code, and the VM-entry instruction length. + */ + if (vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK) { + u32 intr_info = vmcs12->vm_entry_intr_info_field; + u8 vector = intr_info & INTR_INFO_VECTOR_MASK; + u32 intr_type = intr_info & INTR_INFO_INTR_TYPE_MASK; + bool has_error_code = intr_info & INTR_INFO_DELIVER_CODE_MASK; + bool should_have_error_code; + bool urg = nested_cpu_has2(vmcs12, + SECONDARY_EXEC_UNRESTRICTED_GUEST); + bool prot_mode = !urg || vmcs12->guest_cr0 & X86_CR0_PE; + + /* VM-entry interruption-info field: interruption type */ + if (intr_type == INTR_TYPE_RESERVED || + (intr_type == INTR_TYPE_OTHER_EVENT && + !nested_cpu_supports_monitor_trap_flag(vcpu))) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + + /* VM-entry interruption-info field: vector */ + if ((intr_type == INTR_TYPE_NMI_INTR && vector != NMI_VECTOR) || + (intr_type == INTR_TYPE_HARD_EXCEPTION && vector > 31) || + (intr_type == INTR_TYPE_OTHER_EVENT && vector != 0)) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + + /* VM-entry interruption-info field: deliver error code */ + should_have_error_code = + intr_type == INTR_TYPE_HARD_EXCEPTION && prot_mode && + x86_exception_has_error_code(vector); + if (has_error_code != should_have_error_code) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + + /* VM-entry exception error code */ + if (has_error_code && + vmcs12->vm_entry_exception_error_code & GENMASK(31, 15)) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + + /* VM-entry interruption-info field: reserved bits */ + if (intr_info & INTR_INFO_RESVD_BITS_MASK) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + + /* VM-entry instruction length */ + switch (intr_type) { + case INTR_TYPE_SOFT_EXCEPTION: + case INTR_TYPE_SOFT_INTR: + case INTR_TYPE_PRIV_SW_EXCEPTION: + if ((vmcs12->vm_entry_instruction_len > 15) || + (vmcs12->vm_entry_instruction_len == 0 && + !nested_cpu_has_zero_length_injection(vcpu))) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + } + } + return 0; } diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 331993c49dae..257f27620bc2 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -110,6 +110,15 @@ static inline bool is_la57_mode(struct kvm_vcpu *vcpu) #endif } +static inline bool x86_exception_has_error_code(unsigned int vector) +{ + static u32 exception_has_error_code = BIT(DF_VECTOR) | BIT(TS_VECTOR) | + BIT(NP_VECTOR) | BIT(SS_VECTOR) | BIT(GP_VECTOR) | + BIT(PF_VECTOR) | BIT(AC_VECTOR); + + return (1U << vector) & exception_has_error_code; +} + static inline bool mmu_is_nested(struct kvm_vcpu *vcpu) { return vcpu->arch.walk_mmu == &vcpu->arch.nested_mmu; diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index c9081c6671f0..3b5318505c69 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -65,6 +65,13 @@ __read_mostly int xen_have_vector_callback; EXPORT_SYMBOL_GPL(xen_have_vector_callback); /* + * NB: needs to live in .data because it's used by xen_prepare_pvh which runs + * before clearing the bss. + */ +uint32_t xen_start_flags __attribute__((section(".data"))) = 0; +EXPORT_SYMBOL(xen_start_flags); + +/* * Point at some empty memory to start with. We map the real shared_info * page as soon as fixmap is up and running. */ diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 357969a3697c..8d4e2e1ae60b 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -1203,6 +1203,7 @@ asmlinkage __visible void __init xen_start_kernel(void) return; xen_domain_type = XEN_PV_DOMAIN; + xen_start_flags = xen_start_info->flags; xen_setup_features(); diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index aa1c6a6831a9..c85d1a88f476 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -97,6 +97,7 @@ void __init xen_prepare_pvh(void) } xen_pvh = 1; + xen_start_flags = pvh_start_info.flags; msr = cpuid_ebx(xen_cpuid_base() + 2); pfn = __pa(hypercall_page); |