diff options
Diffstat (limited to 'arch/x86/kvm/x86.c')
| -rw-r--r-- | arch/x86/kvm/x86.c | 1112 |
1 files changed, 795 insertions, 317 deletions
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 6eda2834fc05..17468d983fbd 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -58,6 +58,7 @@ #include <linux/sched/isolation.h> #include <linux/mem_encrypt.h> #include <linux/entry-kvm.h> +#include <linux/suspend.h> #include <trace/events/kvm.h> @@ -102,6 +103,8 @@ static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE); static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS; +#define KVM_EXIT_HYPERCALL_VALID_MASK (1 << KVM_HC_MAP_GPA_RANGE) + #define KVM_X2APIC_API_VALID_FLAGS (KVM_X2APIC_API_USE_32BIT_IDS | \ KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK) @@ -113,6 +116,9 @@ static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); static void store_regs(struct kvm_vcpu *vcpu); static int sync_regs(struct kvm_vcpu *vcpu); +static int __set_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2); +static void __get_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2); + struct kvm_x86_ops kvm_x86_ops __read_mostly; EXPORT_SYMBOL_GPL(kvm_x86_ops); @@ -184,11 +190,6 @@ module_param(pi_inject_timer, bint, S_IRUGO | S_IWUSR); */ #define KVM_MAX_NR_USER_RETURN_MSRS 16 -struct kvm_user_return_msrs_global { - int nr; - u32 msrs[KVM_MAX_NR_USER_RETURN_MSRS]; -}; - struct kvm_user_return_msrs { struct user_return_notifier urn; bool registered; @@ -198,7 +199,9 @@ struct kvm_user_return_msrs { } values[KVM_MAX_NR_USER_RETURN_MSRS]; }; -static struct kvm_user_return_msrs_global __read_mostly user_return_msrs_global; +u32 __read_mostly kvm_nr_uret_msrs; +EXPORT_SYMBOL_GPL(kvm_nr_uret_msrs); +static u32 __read_mostly kvm_uret_msrs_list[KVM_MAX_NR_USER_RETURN_MSRS]; static struct kvm_user_return_msrs __percpu *user_return_msrs; #define KVM_SUPPORTED_XCR0 (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \ @@ -212,55 +215,78 @@ EXPORT_SYMBOL_GPL(host_efer); bool __read_mostly allow_smaller_maxphyaddr = 0; EXPORT_SYMBOL_GPL(allow_smaller_maxphyaddr); +bool __read_mostly enable_apicv = true; +EXPORT_SYMBOL_GPL(enable_apicv); + u64 __read_mostly host_xss; EXPORT_SYMBOL_GPL(host_xss); u64 __read_mostly supported_xss; EXPORT_SYMBOL_GPL(supported_xss); -struct kvm_stats_debugfs_item debugfs_entries[] = { - VCPU_STAT("pf_fixed", pf_fixed), - VCPU_STAT("pf_guest", pf_guest), - VCPU_STAT("tlb_flush", tlb_flush), - VCPU_STAT("invlpg", invlpg), - VCPU_STAT("exits", exits), - VCPU_STAT("io_exits", io_exits), - VCPU_STAT("mmio_exits", mmio_exits), - VCPU_STAT("signal_exits", signal_exits), - VCPU_STAT("irq_window", irq_window_exits), - VCPU_STAT("nmi_window", nmi_window_exits), - VCPU_STAT("halt_exits", halt_exits), - VCPU_STAT("halt_successful_poll", halt_successful_poll), - VCPU_STAT("halt_attempted_poll", halt_attempted_poll), - VCPU_STAT("halt_poll_invalid", halt_poll_invalid), - VCPU_STAT("halt_wakeup", halt_wakeup), - VCPU_STAT("hypercalls", hypercalls), - VCPU_STAT("request_irq", request_irq_exits), - VCPU_STAT("irq_exits", irq_exits), - VCPU_STAT("host_state_reload", host_state_reload), - VCPU_STAT("fpu_reload", fpu_reload), - VCPU_STAT("insn_emulation", insn_emulation), - VCPU_STAT("insn_emulation_fail", insn_emulation_fail), - VCPU_STAT("irq_injections", irq_injections), - VCPU_STAT("nmi_injections", nmi_injections), - VCPU_STAT("req_event", req_event), - VCPU_STAT("l1d_flush", l1d_flush), - VCPU_STAT("halt_poll_success_ns", halt_poll_success_ns), - VCPU_STAT("halt_poll_fail_ns", halt_poll_fail_ns), - VCPU_STAT("nested_run", nested_run), - VCPU_STAT("directed_yield_attempted", directed_yield_attempted), - VCPU_STAT("directed_yield_successful", directed_yield_successful), - VM_STAT("mmu_shadow_zapped", mmu_shadow_zapped), - VM_STAT("mmu_pte_write", mmu_pte_write), - VM_STAT("mmu_pde_zapped", mmu_pde_zapped), - VM_STAT("mmu_flooded", mmu_flooded), - VM_STAT("mmu_recycled", mmu_recycled), - VM_STAT("mmu_cache_miss", mmu_cache_miss), - VM_STAT("mmu_unsync", mmu_unsync), - VM_STAT("remote_tlb_flush", remote_tlb_flush), - VM_STAT("largepages", lpages, .mode = 0444), - VM_STAT("nx_largepages_splitted", nx_lpage_splits, .mode = 0444), - VM_STAT("max_mmu_page_hash_collisions", max_mmu_page_hash_collisions), - { NULL } +const struct _kvm_stats_desc kvm_vm_stats_desc[] = { + KVM_GENERIC_VM_STATS(), + STATS_DESC_COUNTER(VM, mmu_shadow_zapped), + STATS_DESC_COUNTER(VM, mmu_pte_write), + STATS_DESC_COUNTER(VM, mmu_pde_zapped), + STATS_DESC_COUNTER(VM, mmu_flooded), + STATS_DESC_COUNTER(VM, mmu_recycled), + STATS_DESC_COUNTER(VM, mmu_cache_miss), + STATS_DESC_ICOUNTER(VM, mmu_unsync), + STATS_DESC_ICOUNTER(VM, lpages), + STATS_DESC_ICOUNTER(VM, nx_lpage_splits), + STATS_DESC_PCOUNTER(VM, max_mmu_page_hash_collisions) +}; +static_assert(ARRAY_SIZE(kvm_vm_stats_desc) == + sizeof(struct kvm_vm_stat) / sizeof(u64)); + +const struct kvm_stats_header kvm_vm_stats_header = { + .name_size = KVM_STATS_NAME_SIZE, + .num_desc = ARRAY_SIZE(kvm_vm_stats_desc), + .id_offset = sizeof(struct kvm_stats_header), + .desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE, + .data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE + + sizeof(kvm_vm_stats_desc), +}; + +const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { + KVM_GENERIC_VCPU_STATS(), + STATS_DESC_COUNTER(VCPU, pf_fixed), + STATS_DESC_COUNTER(VCPU, pf_guest), + STATS_DESC_COUNTER(VCPU, tlb_flush), + STATS_DESC_COUNTER(VCPU, invlpg), + STATS_DESC_COUNTER(VCPU, exits), + STATS_DESC_COUNTER(VCPU, io_exits), + STATS_DESC_COUNTER(VCPU, mmio_exits), + STATS_DESC_COUNTER(VCPU, signal_exits), + STATS_DESC_COUNTER(VCPU, irq_window_exits), + STATS_DESC_COUNTER(VCPU, nmi_window_exits), + STATS_DESC_COUNTER(VCPU, l1d_flush), + STATS_DESC_COUNTER(VCPU, halt_exits), + STATS_DESC_COUNTER(VCPU, request_irq_exits), + STATS_DESC_COUNTER(VCPU, irq_exits), + STATS_DESC_COUNTER(VCPU, host_state_reload), + STATS_DESC_COUNTER(VCPU, fpu_reload), + STATS_DESC_COUNTER(VCPU, insn_emulation), + STATS_DESC_COUNTER(VCPU, insn_emulation_fail), + STATS_DESC_COUNTER(VCPU, hypercalls), + STATS_DESC_COUNTER(VCPU, irq_injections), + STATS_DESC_COUNTER(VCPU, nmi_injections), + STATS_DESC_COUNTER(VCPU, req_event), + STATS_DESC_COUNTER(VCPU, nested_run), + STATS_DESC_COUNTER(VCPU, directed_yield_attempted), + STATS_DESC_COUNTER(VCPU, directed_yield_successful), + STATS_DESC_ICOUNTER(VCPU, guest_mode) +}; +static_assert(ARRAY_SIZE(kvm_vcpu_stats_desc) == + sizeof(struct kvm_vcpu_stat) / sizeof(u64)); + +const struct kvm_stats_header kvm_vcpu_stats_header = { + .name_size = KVM_STATS_NAME_SIZE, + .num_desc = ARRAY_SIZE(kvm_vcpu_stats_desc), + .id_offset = sizeof(struct kvm_stats_header), + .desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE, + .data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE + + sizeof(kvm_vcpu_stats_desc), }; u64 __read_mostly host_xcr0; @@ -330,23 +356,53 @@ static void kvm_on_user_return(struct user_return_notifier *urn) user_return_notifier_unregister(urn); } local_irq_restore(flags); - for (slot = 0; slot < user_return_msrs_global.nr; ++slot) { + for (slot = 0; slot < kvm_nr_uret_msrs; ++slot) { values = &msrs->values[slot]; if (values->host != values->curr) { - wrmsrl(user_return_msrs_global.msrs[slot], values->host); + wrmsrl(kvm_uret_msrs_list[slot], values->host); values->curr = values->host; } } } -void kvm_define_user_return_msr(unsigned slot, u32 msr) +static int kvm_probe_user_return_msr(u32 msr) +{ + u64 val; + int ret; + + preempt_disable(); + ret = rdmsrl_safe(msr, &val); + if (ret) + goto out; + ret = wrmsrl_safe(msr, val); +out: + preempt_enable(); + return ret; +} + +int kvm_add_user_return_msr(u32 msr) { - BUG_ON(slot >= KVM_MAX_NR_USER_RETURN_MSRS); - user_return_msrs_global.msrs[slot] = msr; - if (slot >= user_return_msrs_global.nr) - user_return_msrs_global.nr = slot + 1; + BUG_ON(kvm_nr_uret_msrs >= KVM_MAX_NR_USER_RETURN_MSRS); + + if (kvm_probe_user_return_msr(msr)) + return -1; + + kvm_uret_msrs_list[kvm_nr_uret_msrs] = msr; + return kvm_nr_uret_msrs++; } -EXPORT_SYMBOL_GPL(kvm_define_user_return_msr); +EXPORT_SYMBOL_GPL(kvm_add_user_return_msr); + +int kvm_find_user_return_msr(u32 msr) +{ + int i; + + for (i = 0; i < kvm_nr_uret_msrs; ++i) { + if (kvm_uret_msrs_list[i] == msr) + return i; + } + return -1; +} +EXPORT_SYMBOL_GPL(kvm_find_user_return_msr); static void kvm_user_return_msr_cpu_online(void) { @@ -355,8 +411,8 @@ static void kvm_user_return_msr_cpu_online(void) u64 value; int i; - for (i = 0; i < user_return_msrs_global.nr; ++i) { - rdmsrl_safe(user_return_msrs_global.msrs[i], &value); + for (i = 0; i < kvm_nr_uret_msrs; ++i) { + rdmsrl_safe(kvm_uret_msrs_list[i], &value); msrs->values[i].host = value; msrs->values[i].curr = value; } @@ -371,7 +427,7 @@ int kvm_set_user_return_msr(unsigned slot, u64 value, u64 mask) value = (value & mask) | (msrs->values[slot].host & ~mask); if (value == msrs->values[slot].curr) return 0; - err = wrmsrl_safe(user_return_msrs_global.msrs[slot], value); + err = wrmsrl_safe(kvm_uret_msrs_list[slot], value); if (err) return 1; @@ -751,13 +807,6 @@ int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, } EXPORT_SYMBOL_GPL(kvm_read_guest_page_mmu); -static int kvm_read_nested_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, - void *data, int offset, int len, u32 access) -{ - return kvm_read_guest_page_mmu(vcpu, vcpu->arch.walk_mmu, gfn, - data, offset, len, access); -} - static inline u64 pdptr_rsvd_bits(struct kvm_vcpu *vcpu) { return vcpu->arch.reserved_gpa_bits | rsvd_bits(5, 8) | rsvd_bits(1, 2); @@ -792,6 +841,7 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) memcpy(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs)); kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); + vcpu->arch.pdptrs_from_userspace = false; out: @@ -799,40 +849,14 @@ out: } EXPORT_SYMBOL_GPL(load_pdptrs); -bool pdptrs_changed(struct kvm_vcpu *vcpu) -{ - u64 pdpte[ARRAY_SIZE(vcpu->arch.walk_mmu->pdptrs)]; - int offset; - gfn_t gfn; - int r; - - if (!is_pae_paging(vcpu)) - return false; - - if (!kvm_register_is_available(vcpu, VCPU_EXREG_PDPTR)) - return true; - - gfn = (kvm_read_cr3(vcpu) & 0xffffffe0ul) >> PAGE_SHIFT; - offset = (kvm_read_cr3(vcpu) & 0xffffffe0ul) & (PAGE_SIZE - 1); - r = kvm_read_nested_guest_page(vcpu, gfn, pdpte, offset, sizeof(pdpte), - PFERR_USER_MASK | PFERR_WRITE_MASK); - if (r < 0) - return true; - - return memcmp(pdpte, vcpu->arch.walk_mmu->pdptrs, sizeof(pdpte)) != 0; -} -EXPORT_SYMBOL_GPL(pdptrs_changed); - void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned long cr0) { - unsigned long update_bits = X86_CR0_PG | X86_CR0_WP; - if ((cr0 ^ old_cr0) & X86_CR0_PG) { kvm_clear_async_pf_completion_queue(vcpu); kvm_async_pf_hash_reset(vcpu); } - if ((cr0 ^ old_cr0) & update_bits) + if ((cr0 ^ old_cr0) & KVM_MMU_CR0_ROLE_BITS) kvm_mmu_reset_context(vcpu); if (((cr0 ^ old_cr0) & X86_CR0_CD) && @@ -1011,10 +1035,7 @@ EXPORT_SYMBOL_GPL(kvm_is_valid_cr4); void kvm_post_set_cr4(struct kvm_vcpu *vcpu, unsigned long old_cr4, unsigned long cr4) { - unsigned long mmu_role_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | - X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE; - - if (((cr4 ^ old_cr4) & mmu_role_bits) || + if (((cr4 ^ old_cr4) & KVM_MMU_CR4_ROLE_BITS) || (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE))) kvm_mmu_reset_context(vcpu); } @@ -1057,25 +1078,46 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) } EXPORT_SYMBOL_GPL(kvm_set_cr4); +static void kvm_invalidate_pcid(struct kvm_vcpu *vcpu, unsigned long pcid) +{ + struct kvm_mmu *mmu = vcpu->arch.mmu; + unsigned long roots_to_free = 0; + int i; + + /* + * If neither the current CR3 nor any of the prev_roots use the given + * PCID, then nothing needs to be done here because a resync will + * happen anyway before switching to any other CR3. + */ + if (kvm_get_active_pcid(vcpu) == pcid) { + kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); + } + + for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) + if (kvm_get_pcid(vcpu, mmu->prev_roots[i].pgd) == pcid) + roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i); + + kvm_mmu_free_roots(vcpu, mmu, roots_to_free); +} + int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) { bool skip_tlb_flush = false; + unsigned long pcid = 0; #ifdef CONFIG_X86_64 bool pcid_enabled = kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE); if (pcid_enabled) { skip_tlb_flush = cr3 & X86_CR3_PCID_NOFLUSH; cr3 &= ~X86_CR3_PCID_NOFLUSH; + pcid = cr3 & X86_CR3_PCID_MASK; } #endif - if (cr3 == kvm_read_cr3(vcpu) && !pdptrs_changed(vcpu)) { - if (!skip_tlb_flush) { - kvm_mmu_sync_roots(vcpu); - kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); - } - return 0; - } + /* PDPTRs are always reloaded for PAE paging. */ + if (cr3 == kvm_read_cr3(vcpu) && !is_pae_paging(vcpu)) + goto handle_tlb_flush; /* * Do not condition the GPA check on long mode, this helper is used to @@ -1088,10 +1130,23 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) return 1; - kvm_mmu_new_pgd(vcpu, cr3, skip_tlb_flush, skip_tlb_flush); + if (cr3 != kvm_read_cr3(vcpu)) + kvm_mmu_new_pgd(vcpu, cr3); + vcpu->arch.cr3 = cr3; kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); +handle_tlb_flush: + /* + * A load of CR3 that flushes the TLB flushes only the current PCID, + * even if PCID is disabled, in which case PCID=0 is flushed. It's a + * moot point in the end because _disabling_ PCID will flush all PCIDs, + * and it's impossible to use a non-zero PCID when PCID is disabled, + * i.e. only PCID=0 can be relevant. + */ + if (!skip_tlb_flush) + kvm_invalidate_pcid(vcpu, pcid); + return 0; } EXPORT_SYMBOL_GPL(kvm_set_cr3); @@ -1149,6 +1204,9 @@ static u64 kvm_dr6_fixed(struct kvm_vcpu *vcpu) if (!guest_cpuid_has(vcpu, X86_FEATURE_RTM)) fixed |= DR6_RTM; + + if (!guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT)) + fixed |= DR6_BUS_LOCK; return fixed; } @@ -1615,6 +1673,30 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, * invokes 64-bit SYSENTER. */ data = get_canonical(data, vcpu_virt_addr_bits(vcpu)); + break; + case MSR_TSC_AUX: + if (!kvm_is_supported_user_return_msr(MSR_TSC_AUX)) + return 1; + + if (!host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) && + !guest_cpuid_has(vcpu, X86_FEATURE_RDPID)) + return 1; + + /* + * Per Intel's SDM, bits 63:32 are reserved, but AMD's APM has + * incomplete and conflicting architectural behavior. Current + * AMD CPUs completely ignore bits 63:32, i.e. they aren't + * reserved and always read as zeros. Enforce Intel's reserved + * bits check if and only if the guest CPU is Intel, and clear + * the bits in all other cases. This ensures cross-vendor + * migration will provide consistent behavior for the guest. + */ + if (guest_cpuid_is_intel(vcpu) && (data >> 32) != 0) + return 1; + + data = (u32)data; + break; } msr.data = data; @@ -1651,6 +1733,18 @@ int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ)) return KVM_MSR_RET_FILTERED; + switch (index) { + case MSR_TSC_AUX: + if (!kvm_is_supported_user_return_msr(MSR_TSC_AUX)) + return 1; + + if (!host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) && + !guest_cpuid_has(vcpu, X86_FEATURE_RDPID)) + return 1; + break; + } + msr.index = index; msr.host_initiated = host_initiated; @@ -2113,13 +2207,15 @@ static u32 adjust_tsc_khz(u32 khz, s32 ppm) return v; } +static void kvm_vcpu_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 l1_multiplier); + static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) { u64 ratio; /* Guest TSC same frequency as host TSC? */ if (!scale) { - vcpu->arch.tsc_scaling_ratio = kvm_default_tsc_scaling_ratio; + kvm_vcpu_write_tsc_multiplier(vcpu, kvm_default_tsc_scaling_ratio); return 0; } @@ -2145,7 +2241,7 @@ static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) return -1; } - vcpu->arch.tsc_scaling_ratio = ratio; + kvm_vcpu_write_tsc_multiplier(vcpu, ratio); return 0; } @@ -2157,7 +2253,7 @@ static int kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz) /* tsc_khz can be zero if TSC calibration fails */ if (user_tsc_khz == 0) { /* set tsc_scaling_ratio to a safe value */ - vcpu->arch.tsc_scaling_ratio = kvm_default_tsc_scaling_ratio; + kvm_vcpu_write_tsc_multiplier(vcpu, kvm_default_tsc_scaling_ratio); return -1; } @@ -2239,10 +2335,9 @@ static inline u64 __scale_tsc(u64 ratio, u64 tsc) return mul_u64_u64_shr(tsc, ratio, kvm_tsc_scaling_ratio_frac_bits); } -u64 kvm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc) +u64 kvm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc, u64 ratio) { u64 _tsc = tsc; - u64 ratio = vcpu->arch.tsc_scaling_ratio; if (ratio != kvm_default_tsc_scaling_ratio) _tsc = __scale_tsc(ratio, tsc); @@ -2251,25 +2346,86 @@ u64 kvm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc) } EXPORT_SYMBOL_GPL(kvm_scale_tsc); -static u64 kvm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) +static u64 kvm_compute_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) { u64 tsc; - tsc = kvm_scale_tsc(vcpu, rdtsc()); + tsc = kvm_scale_tsc(vcpu, rdtsc(), vcpu->arch.l1_tsc_scaling_ratio); return target_tsc - tsc; } u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) { - return vcpu->arch.l1_tsc_offset + kvm_scale_tsc(vcpu, host_tsc); + return vcpu->arch.l1_tsc_offset + + kvm_scale_tsc(vcpu, host_tsc, vcpu->arch.l1_tsc_scaling_ratio); } EXPORT_SYMBOL_GPL(kvm_read_l1_tsc); -static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) +u64 kvm_calc_nested_tsc_offset(u64 l1_offset, u64 l2_offset, u64 l2_multiplier) +{ + u64 nested_offset; + + if (l2_multiplier == kvm_default_tsc_scaling_ratio) + nested_offset = l1_offset; + else + nested_offset = mul_s64_u64_shr((s64) l1_offset, l2_multiplier, + kvm_tsc_scaling_ratio_frac_bits); + + nested_offset += l2_offset; + return nested_offset; +} +EXPORT_SYMBOL_GPL(kvm_calc_nested_tsc_offset); + +u64 kvm_calc_nested_tsc_multiplier(u64 l1_multiplier, u64 l2_multiplier) { - vcpu->arch.l1_tsc_offset = offset; - vcpu->arch.tsc_offset = static_call(kvm_x86_write_l1_tsc_offset)(vcpu, offset); + if (l2_multiplier != kvm_default_tsc_scaling_ratio) + return mul_u64_u64_shr(l1_multiplier, l2_multiplier, + kvm_tsc_scaling_ratio_frac_bits); + + return l1_multiplier; +} +EXPORT_SYMBOL_GPL(kvm_calc_nested_tsc_multiplier); + +static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 l1_offset) +{ + trace_kvm_write_tsc_offset(vcpu->vcpu_id, + vcpu->arch.l1_tsc_offset, + l1_offset); + + vcpu->arch.l1_tsc_offset = l1_offset; + + /* + * If we are here because L1 chose not to trap WRMSR to TSC then + * according to the spec this should set L1's TSC (as opposed to + * setting L1's offset for L2). + */ + if (is_guest_mode(vcpu)) + vcpu->arch.tsc_offset = kvm_calc_nested_tsc_offset( + l1_offset, + static_call(kvm_x86_get_l2_tsc_offset)(vcpu), + static_call(kvm_x86_get_l2_tsc_multiplier)(vcpu)); + else + vcpu->arch.tsc_offset = l1_offset; + + static_call(kvm_x86_write_tsc_offset)(vcpu, vcpu->arch.tsc_offset); +} + +static void kvm_vcpu_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 l1_multiplier) +{ + vcpu->arch.l1_tsc_scaling_ratio = l1_multiplier; + + /* Userspace is changing the multiplier while L2 is active */ + if (is_guest_mode(vcpu)) + vcpu->arch.tsc_scaling_ratio = kvm_calc_nested_tsc_multiplier( + l1_multiplier, + static_call(kvm_x86_get_l2_tsc_multiplier)(vcpu)); + else + vcpu->arch.tsc_scaling_ratio = l1_multiplier; + + if (kvm_has_tsc_control) + static_call(kvm_x86_write_tsc_multiplier)( + vcpu, vcpu->arch.tsc_scaling_ratio); } static inline bool kvm_check_tsc_unstable(void) @@ -2295,7 +2451,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data) bool synchronizing = false; raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags); - offset = kvm_compute_tsc_offset(vcpu, data); + offset = kvm_compute_l1_tsc_offset(vcpu, data); ns = get_kvmclock_base_ns(); elapsed = ns - kvm->arch.last_tsc_nsec; @@ -2334,7 +2490,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data) } else { u64 delta = nsec_to_cycles(vcpu, elapsed); data += delta; - offset = kvm_compute_tsc_offset(vcpu, data); + offset = kvm_compute_l1_tsc_offset(vcpu, data); } matched = true; already_matched = (vcpu->arch.this_tsc_generation == kvm->arch.cur_tsc_generation); @@ -2393,9 +2549,10 @@ static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment) { - if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio) + if (vcpu->arch.l1_tsc_scaling_ratio != kvm_default_tsc_scaling_ratio) WARN_ON(adjustment < 0); - adjustment = kvm_scale_tsc(vcpu, (u64) adjustment); + adjustment = kvm_scale_tsc(vcpu, (u64) adjustment, + vcpu->arch.l1_tsc_scaling_ratio); adjust_tsc_offset_guest(vcpu, adjustment); } @@ -2778,7 +2935,8 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) /* With all the info we got, fill in the values */ if (kvm_has_tsc_control) - tgt_tsc_khz = kvm_scale_tsc(v, tgt_tsc_khz); + tgt_tsc_khz = kvm_scale_tsc(v, tgt_tsc_khz, + v->arch.l1_tsc_scaling_ratio); if (unlikely(vcpu->hw_tsc_khz != tgt_tsc_khz)) { kvm_get_time_scale(NSEC_PER_SEC, tgt_tsc_khz * 1000LL, @@ -3006,6 +3164,19 @@ static void kvm_vcpu_flush_tlb_all(struct kvm_vcpu *vcpu) static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu) { ++vcpu->stat.tlb_flush; + + if (!tdp_enabled) { + /* + * A TLB flush on behalf of the guest is equivalent to + * INVPCID(all), toggling CR4.PGE, etc., which requires + * a forced sync of the shadow page tables. Unload the + * entire MMU here and the subsequent load will sync the + * shadow page tables, and also flush the TLB. + */ + kvm_mmu_unload(vcpu); + return; + } + static_call(kvm_x86_tlb_flush_guest)(vcpu); } @@ -3035,10 +3206,14 @@ static void record_steal_time(struct kvm_vcpu *vcpu) * expensive IPIs. */ if (guest_pv_has(vcpu, KVM_FEATURE_PV_TLB_FLUSH)) { + u8 st_preempted = xchg(&st->preempted, 0); + trace_kvm_pv_tlb_flush(vcpu->vcpu_id, - st->preempted & KVM_VCPU_FLUSH_TLB); - if (xchg(&st->preempted, 0) & KVM_VCPU_FLUSH_TLB) + st_preempted & KVM_VCPU_FLUSH_TLB); + if (st_preempted & KVM_VCPU_FLUSH_TLB) kvm_vcpu_flush_tlb_guest(vcpu); + } else { + st->preempted = 0; } vcpu->arch.st.preempted = 0; @@ -3167,7 +3342,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (msr_info->host_initiated) { kvm_synchronize_tsc(vcpu, data); } else { - u64 adj = kvm_compute_tsc_offset(vcpu, data) - vcpu->arch.l1_tsc_offset; + u64 adj = kvm_compute_l1_tsc_offset(vcpu, data) - vcpu->arch.l1_tsc_offset; adjust_tsc_offset_guest(vcpu, adj); vcpu->arch.ia32_tsc_adjust_msr += adj; } @@ -3402,7 +3577,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_LASTBRANCHTOIP: case MSR_IA32_LASTINTFROMIP: case MSR_IA32_LASTINTTOIP: - case MSR_K8_SYSCFG: + case MSR_AMD64_SYSCFG: case MSR_K8_TSEG_ADDR: case MSR_K8_TSEG_MASK: case MSR_VM_HSAVE_PA: @@ -3469,10 +3644,17 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) * return L1's TSC value to ensure backwards-compatible * behavior for migration. */ - u64 tsc_offset = msr_info->host_initiated ? vcpu->arch.l1_tsc_offset : - vcpu->arch.tsc_offset; + u64 offset, ratio; - msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + tsc_offset; + if (msr_info->host_initiated) { + offset = vcpu->arch.l1_tsc_offset; + ratio = vcpu->arch.l1_tsc_scaling_ratio; + } else { + offset = vcpu->arch.tsc_offset; + ratio = vcpu->arch.tsc_scaling_ratio; + } + + msr_info->data = kvm_scale_tsc(vcpu, rdtsc(), ratio) + offset; break; } case MSR_MTRRcap: @@ -3796,6 +3978,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_HYPERV_TLBFLUSH: case KVM_CAP_HYPERV_SEND_IPI: case KVM_CAP_HYPERV_CPUID: + case KVM_CAP_HYPERV_ENFORCE_CPUID: case KVM_CAP_SYS_HYPERV_CPUID: case KVM_CAP_PCI_SEGMENT: case KVM_CAP_DEBUGREGS: @@ -3826,8 +4009,13 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SGX_ATTRIBUTE: #endif case KVM_CAP_VM_COPY_ENC_CONTEXT_FROM: + case KVM_CAP_SREGS2: + case KVM_CAP_EXIT_ON_EMULATION_FAILURE: r = 1; break; + case KVM_CAP_EXIT_HYPERCALL: + r = KVM_EXIT_HYPERCALL_VALID_MASK; + break; case KVM_CAP_SET_GUEST_DEBUG2: return KVM_GUESTDBG_VALID_MASK; #ifdef CONFIG_KVM_XEN @@ -4055,7 +4243,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) mark_tsc_unstable("KVM discovered backwards TSC"); if (kvm_check_tsc_unstable()) { - u64 offset = kvm_compute_tsc_offset(vcpu, + u64 offset = kvm_compute_l1_tsc_offset(vcpu, vcpu->arch.last_guest_tsc); kvm_vcpu_write_tsc_offset(vcpu, offset); vcpu->arch.tsc_catchup = 1; @@ -4374,7 +4562,7 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, memset(&events->reserved, 0, sizeof(events->reserved)); } -static void kvm_smm_changed(struct kvm_vcpu *vcpu); +static void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm); static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) @@ -4434,13 +4622,8 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.apic->sipi_vector = events->sipi_vector; if (events->flags & KVM_VCPUEVENT_VALID_SMM) { - if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) { - if (events->smi.smm) - vcpu->arch.hflags |= HF_SMM_MASK; - else - vcpu->arch.hflags &= ~HF_SMM_MASK; - kvm_smm_changed(vcpu); - } + if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) + kvm_smm_changed(vcpu, events->smi.smm); vcpu->arch.smi_pending = events->smi.pending; @@ -4724,6 +4907,9 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, return static_call(kvm_x86_enable_direct_tlbflush)(vcpu); + case KVM_CAP_HYPERV_ENFORCE_CPUID: + return kvm_hv_set_enforce_cpuid(vcpu, cap->args[0]); + case KVM_CAP_ENFORCE_PV_FEATURE_CPUID: vcpu->arch.pv_cpuid.enforce = cap->args[0]; if (vcpu->arch.pv_cpuid.enforce) @@ -4742,6 +4928,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, void __user *argp = (void __user *)arg; int r; union { + struct kvm_sregs2 *sregs2; struct kvm_lapic_state *lapic; struct kvm_xsave *xsave; struct kvm_xcrs *xcrs; @@ -5114,6 +5301,28 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } #endif + case KVM_GET_SREGS2: { + u.sregs2 = kzalloc(sizeof(struct kvm_sregs2), GFP_KERNEL); + r = -ENOMEM; + if (!u.sregs2) + goto out; + __get_sregs2(vcpu, u.sregs2); + r = -EFAULT; + if (copy_to_user(argp, u.sregs2, sizeof(struct kvm_sregs2))) + goto out; + r = 0; + break; + } + case KVM_SET_SREGS2: { + u.sregs2 = memdup_user(argp, sizeof(struct kvm_sregs2)); + if (IS_ERR(u.sregs2)) { + r = PTR_ERR(u.sregs2); + u.sregs2 = NULL; + goto out; + } + r = __set_sregs2(vcpu, u.sregs2); + break; + } default: r = -EINVAL; } @@ -5433,6 +5642,21 @@ split_irqchip_unlock: if (kvm_x86_ops.vm_copy_enc_context_from) r = kvm_x86_ops.vm_copy_enc_context_from(kvm, cap->args[0]); return r; + case KVM_CAP_EXIT_HYPERCALL: + if (cap->args[0] & ~KVM_EXIT_HYPERCALL_VALID_MASK) { + r = -EINVAL; + break; + } + kvm->arch.hypercall_exit_enabled = cap->args[0]; + r = 0; + break; + case KVM_CAP_EXIT_ON_EMULATION_FAILURE: + r = -EINVAL; + if (cap->args[0] & ~1) + break; + kvm->arch.exit_on_emulation_error = cap->args[0]; + r = 0; + break; default: r = -EINVAL; break; @@ -5468,14 +5692,18 @@ static void kvm_free_msr_filter(struct kvm_x86_msr_filter *msr_filter) static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter, struct kvm_msr_filter_range *user_range) { - struct msr_bitmap_range range; unsigned long *bitmap = NULL; size_t bitmap_size; - int r; if (!user_range->nmsrs) return 0; + if (user_range->flags & ~(KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE)) + return -EINVAL; + + if (!user_range->flags) + return -EINVAL; + bitmap_size = BITS_TO_LONGS(user_range->nmsrs) * sizeof(long); if (!bitmap_size || bitmap_size > KVM_MSR_FILTER_MAX_BITMAP_SIZE) return -EINVAL; @@ -5484,31 +5712,15 @@ static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter, if (IS_ERR(bitmap)) return PTR_ERR(bitmap); - range = (struct msr_bitmap_range) { + msr_filter->ranges[msr_filter->count] = (struct msr_bitmap_range) { .flags = user_range->flags, .base = user_range->base, .nmsrs = user_range->nmsrs, .bitmap = bitmap, }; - if (range.flags & ~(KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE)) { - r = -EINVAL; - goto err; - } - - if (!range.flags) { - r = -EINVAL; - goto err; - } - - /* Everything ok, add this range identifier. */ - msr_filter->ranges[msr_filter->count] = range; msr_filter->count++; - return 0; -err: - kfree(bitmap); - return r; } static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) @@ -5559,6 +5771,41 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) return 0; } +#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER +static int kvm_arch_suspend_notifier(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu; + int i, ret = 0; + + mutex_lock(&kvm->lock); + kvm_for_each_vcpu(i, vcpu, kvm) { + if (!vcpu->arch.pv_time_enabled) + continue; + + ret = kvm_set_guest_paused(vcpu); + if (ret) { + kvm_err("Failed to pause guest VCPU%d: %d\n", + vcpu->vcpu_id, ret); + break; + } + } + mutex_unlock(&kvm->lock); + + return ret ? NOTIFY_BAD : NOTIFY_DONE; +} + +int kvm_arch_pm_notifier(struct kvm *kvm, unsigned long state) +{ + switch (state) { + case PM_HIBERNATION_PREPARE: + case PM_SUSPEND_PREPARE: + return kvm_arch_suspend_notifier(kvm); + } + + return NOTIFY_DONE; +} +#endif /* CONFIG_HAVE_KVM_PM_NOTIFIER */ + long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -5937,7 +6184,8 @@ static void kvm_init_msr_list(void) continue; break; case MSR_TSC_AUX: - if (!kvm_cpu_cap_has(X86_FEATURE_RDTSCP)) + if (!kvm_cpu_cap_has(X86_FEATURE_RDTSCP) && + !kvm_cpu_cap_has(X86_FEATURE_RDPID)) continue; break; case MSR_IA32_UMWAIT_CONTROL: @@ -7032,20 +7280,22 @@ static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt) return emul_to_vcpu(ctxt)->arch.hflags; } -static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_flags) +static void emulator_exiting_smm(struct x86_emulate_ctxt *ctxt) { - emul_to_vcpu(ctxt)->arch.hflags = emul_flags; + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + + kvm_smm_changed(vcpu, false); } -static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt, +static int emulator_leave_smm(struct x86_emulate_ctxt *ctxt, const char *smstate) { - return static_call(kvm_x86_pre_leave_smm)(emul_to_vcpu(ctxt), smstate); + return static_call(kvm_x86_leave_smm)(emul_to_vcpu(ctxt), smstate); } -static void emulator_post_leave_smm(struct x86_emulate_ctxt *ctxt) +static void emulator_triple_fault(struct x86_emulate_ctxt *ctxt) { - kvm_smm_changed(emul_to_vcpu(ctxt)); + kvm_make_request(KVM_REQ_TRIPLE_FAULT, emul_to_vcpu(ctxt)); } static int emulator_set_xcr(struct x86_emulate_ctxt *ctxt, u32 index, u64 xcr) @@ -7094,9 +7344,9 @@ static const struct x86_emulate_ops emulate_ops = { .guest_has_fxsr = emulator_guest_has_fxsr, .set_nmi_mask = emulator_set_nmi_mask, .get_hflags = emulator_get_hflags, - .set_hflags = emulator_set_hflags, - .pre_leave_smm = emulator_pre_leave_smm, - .post_leave_smm = emulator_post_leave_smm, + .exiting_smm = emulator_exiting_smm, + .leave_smm = emulator_leave_smm, + .triple_fault = emulator_triple_fault, .set_xcr = emulator_set_xcr, }; @@ -7171,6 +7421,11 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu) BUILD_BUG_ON(HF_SMM_MASK != X86EMUL_SMM_MASK); BUILD_BUG_ON(HF_SMM_INSIDE_NMI_MASK != X86EMUL_SMM_INSIDE_NMI_MASK); + ctxt->interruptibility = 0; + ctxt->have_exception = false; + ctxt->exception.vector = -1; + ctxt->perm_ok = false; + init_decode_cache(ctxt); vcpu->arch.emulate_regs_need_sync_from_vcpu = false; } @@ -7197,8 +7452,33 @@ void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip) } EXPORT_SYMBOL_GPL(kvm_inject_realmode_interrupt); +static void prepare_emulation_failure_exit(struct kvm_vcpu *vcpu) +{ + struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; + u32 insn_size = ctxt->fetch.end - ctxt->fetch.data; + struct kvm_run *run = vcpu->run; + + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + run->emulation_failure.suberror = KVM_INTERNAL_ERROR_EMULATION; + run->emulation_failure.ndata = 0; + run->emulation_failure.flags = 0; + + if (insn_size) { + run->emulation_failure.ndata = 3; + run->emulation_failure.flags |= + KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES; + run->emulation_failure.insn_size = insn_size; + memset(run->emulation_failure.insn_bytes, 0x90, + sizeof(run->emulation_failure.insn_bytes)); + memcpy(run->emulation_failure.insn_bytes, + ctxt->fetch.data, insn_size); + } +} + static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) { + struct kvm *kvm = vcpu->kvm; + ++vcpu->stat.insn_emulation_fail; trace_kvm_emulate_insn_failed(vcpu); @@ -7207,10 +7487,9 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) return 1; } - if (emulation_type & EMULTYPE_SKIP) { - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; - vcpu->run->internal.ndata = 0; + if (kvm->arch.exit_on_emulation_error || + (emulation_type & EMULTYPE_SKIP)) { + prepare_emulation_failure_exit(vcpu); return 0; } @@ -7352,11 +7631,14 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt, static int complete_emulated_mmio(struct kvm_vcpu *vcpu); static int complete_emulated_pio(struct kvm_vcpu *vcpu); -static void kvm_smm_changed(struct kvm_vcpu *vcpu) +static void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm) { - if (!(vcpu->arch.hflags & HF_SMM_MASK)) { - /* This is a good place to trace that we are exiting SMM. */ - trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, false); + trace_kvm_smm_transition(vcpu->vcpu_id, vcpu->arch.smbase, entering_smm); + + if (entering_smm) { + vcpu->arch.hflags |= HF_SMM_MASK; + } else { + vcpu->arch.hflags &= ~(HF_SMM_MASK | HF_SMM_INSIDE_NMI_MASK); /* Process a latched INIT or SMI, if any. */ kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -7506,14 +7788,7 @@ int x86_decode_emulated_instruction(struct kvm_vcpu *vcpu, int emulation_type, kvm_vcpu_check_breakpoint(vcpu, &r)) return r; - ctxt->interruptibility = 0; - ctxt->have_exception = false; - ctxt->exception.vector = -1; - ctxt->perm_ok = false; - - ctxt->ud = emulation_type & EMULTYPE_TRAP_UD; - - r = x86_decode_insn(ctxt, insn, insn_len); + r = x86_decode_insn(ctxt, insn, insn_len, emulation_type); trace_kvm_emulate_insn_start(vcpu); ++vcpu->stat.insn_emulation; @@ -8040,6 +8315,18 @@ static void pvclock_gtod_update_fn(struct work_struct *work) static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn); /* + * Indirection to move queue_work() out of the tk_core.seq write held + * region to prevent possible deadlocks against time accessors which + * are invoked with work related locks held. + */ +static void pvclock_irq_work_fn(struct irq_work *w) +{ + queue_work(system_long_wq, &pvclock_gtod_work); +} + +static DEFINE_IRQ_WORK(pvclock_irq_work, pvclock_irq_work_fn); + +/* * Notification about pvclock gtod data update. */ static int pvclock_gtod_notify(struct notifier_block *nb, unsigned long unused, @@ -8050,13 +8337,14 @@ static int pvclock_gtod_notify(struct notifier_block *nb, unsigned long unused, update_pvclock_gtod(tk); - /* disable master clock if host does not trust, or does not - * use, TSC based clocksource. + /* + * Disable master clock if host does not trust, or does not use, + * TSC based clocksource. Delegate queue_work() to irq_work as + * this is invoked with tk_core.seq write held. */ if (!gtod_is_based_on_tsc(gtod->clock.vclock_mode) && atomic_read(&kvm_guest_has_master_clock) != 0) - queue_work(system_long_wq, &pvclock_gtod_work); - + irq_work_queue(&pvclock_irq_work); return 0; } @@ -8118,6 +8406,7 @@ int kvm_arch_init(void *opaque) printk(KERN_ERR "kvm: failed to allocate percpu kvm_user_return_msrs\n"); goto out_free_x86_emulator_cache; } + kvm_nr_uret_msrs = 0; r = kvm_mmu_module_init(); if (r) @@ -8168,10 +8457,13 @@ void kvm_arch_exit(void) cpuhp_remove_state_nocalls(CPUHP_AP_X86_KVM_CLK_ONLINE); #ifdef CONFIG_X86_64 pvclock_gtod_unregister_notifier(&pvclock_gtod_notifier); + irq_work_sync(&pvclock_irq_work); + cancel_work_sync(&pvclock_gtod_work); #endif kvm_x86_ops.hardware_enable = NULL; kvm_mmu_module_exit(); free_percpu(user_return_msrs); + kmem_cache_destroy(x86_emulator_cache); kmem_cache_destroy(x86_fpu_cache); #ifdef CONFIG_KVM_XEN static_key_deferred_flush(&kvm_xen_enabled); @@ -8271,16 +8563,15 @@ bool kvm_apicv_activated(struct kvm *kvm) } EXPORT_SYMBOL_GPL(kvm_apicv_activated); -void kvm_apicv_init(struct kvm *kvm, bool enable) +static void kvm_apicv_init(struct kvm *kvm) { - if (enable) + if (enable_apicv) clear_bit(APICV_INHIBIT_REASON_DISABLE, &kvm->arch.apicv_inhibit_reasons); else set_bit(APICV_INHIBIT_REASON_DISABLE, &kvm->arch.apicv_inhibit_reasons); } -EXPORT_SYMBOL_GPL(kvm_apicv_init); static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id) { @@ -8289,6 +8580,9 @@ static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id) vcpu->stat.directed_yield_attempted++; + if (single_task_running()) + goto no_yield; + rcu_read_lock(); map = rcu_dereference(vcpu->kvm->arch.apic_map); @@ -8313,6 +8607,17 @@ no_yield: return; } +static int complete_hypercall_exit(struct kvm_vcpu *vcpu) +{ + u64 ret = vcpu->run->hypercall.ret; + + if (!is_64_bit_mode(vcpu)) + ret = (u32)ret; + kvm_rax_write(vcpu, ret); + ++vcpu->stat.hypercalls; + return kvm_skip_emulated_instruction(vcpu); +} + int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) { unsigned long nr, a0, a1, a2, a3, ret; @@ -8378,6 +8683,28 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) kvm_sched_yield(vcpu, a0); ret = 0; break; + case KVM_HC_MAP_GPA_RANGE: { + u64 gpa = a0, npages = a1, attrs = a2; + + ret = -KVM_ENOSYS; + if (!(vcpu->kvm->arch.hypercall_exit_enabled & (1 << KVM_HC_MAP_GPA_RANGE))) + break; + + if (!PAGE_ALIGNED(gpa) || !npages || + gpa_to_gfn(gpa) + npages <= gpa_to_gfn(gpa)) { + ret = -KVM_EINVAL; + break; + } + + vcpu->run->exit_reason = KVM_EXIT_HYPERCALL; + vcpu->run->hypercall.nr = KVM_HC_MAP_GPA_RANGE; + vcpu->run->hypercall.args[0] = gpa; + vcpu->run->hypercall.args[1] = npages; + vcpu->run->hypercall.args[2] = attrs; + vcpu->run->hypercall.longmode = op_64_bit; + vcpu->arch.complete_userspace_io = complete_hypercall_exit; + return 0; + } default: ret = -KVM_ENOSYS; break; @@ -8461,9 +8788,6 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) int kvm_check_nested_events(struct kvm_vcpu *vcpu) { - if (WARN_ON_ONCE(!is_guest_mode(vcpu))) - return -EIO; - if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { kvm_x86_ops.nested_ops->triple_fault(vcpu); return 1; @@ -8479,7 +8803,7 @@ static void kvm_inject_exception(struct kvm_vcpu *vcpu) static_call(kvm_x86_queue_exception)(vcpu); } -static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit) +static int inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit) { int r; bool can_inject = true; @@ -8526,7 +8850,7 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit if (is_guest_mode(vcpu)) { r = kvm_check_nested_events(vcpu); if (r < 0) - goto busy; + goto out; } /* try to inject new event if pending */ @@ -8568,7 +8892,7 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit if (vcpu->arch.smi_pending) { r = can_inject ? static_call(kvm_x86_smi_allowed)(vcpu, true) : -EBUSY; if (r < 0) - goto busy; + goto out; if (r) { vcpu->arch.smi_pending = false; ++vcpu->arch.smi_count; @@ -8581,7 +8905,7 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit if (vcpu->arch.nmi_pending) { r = can_inject ? static_call(kvm_x86_nmi_allowed)(vcpu, true) : -EBUSY; if (r < 0) - goto busy; + goto out; if (r) { --vcpu->arch.nmi_pending; vcpu->arch.nmi_injected = true; @@ -8596,7 +8920,7 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit if (kvm_cpu_has_injectable_intr(vcpu)) { r = can_inject ? static_call(kvm_x86_interrupt_allowed)(vcpu, true) : -EBUSY; if (r < 0) - goto busy; + goto out; if (r) { kvm_queue_interrupt(vcpu, kvm_cpu_get_interrupt(vcpu), false); static_call(kvm_x86_set_irq)(vcpu); @@ -8612,11 +8936,14 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit *req_immediate_exit = true; WARN_ON(vcpu->arch.exception.pending); - return; + return 0; -busy: - *req_immediate_exit = true; - return; +out: + if (r == -EBUSY) { + *req_immediate_exit = true; + r = 0; + } + return r; } static void process_nmi(struct kvm_vcpu *vcpu) @@ -8795,10 +9122,9 @@ static void enter_smm(struct kvm_vcpu *vcpu) { struct kvm_segment cs, ds; struct desc_ptr dt; + unsigned long cr0; char buf[512]; - u32 cr0; - trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, true); memset(buf, 0, 512); #ifdef CONFIG_X86_64 if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) @@ -8808,13 +9134,13 @@ static void enter_smm(struct kvm_vcpu *vcpu) enter_smm_save_state_32(vcpu, buf); /* - * Give pre_enter_smm() a chance to make ISA-specific changes to the - * vCPU state (e.g. leave guest mode) after we've saved the state into - * the SMM state-save area. + * Give enter_smm() a chance to make ISA-specific changes to the vCPU + * state (e.g. leave guest mode) after we've saved the state into the + * SMM state-save area. */ - static_call(kvm_x86_pre_enter_smm)(vcpu, buf); + static_call(kvm_x86_enter_smm)(vcpu, buf); - vcpu->arch.hflags |= HF_SMM_MASK; + kvm_smm_changed(vcpu, true); kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, buf, sizeof(buf)); if (static_call(kvm_x86_get_nmi_mask)(vcpu)) @@ -8903,6 +9229,15 @@ void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) vcpu->arch.apicv_active = kvm_apicv_activated(vcpu->kvm); kvm_apic_update_apicv(vcpu); static_call(kvm_x86_refresh_apicv_exec_ctrl)(vcpu); + + /* + * When APICv gets disabled, we may still have injected interrupts + * pending. At the same time, KVM_REQ_EVENT may not be set as APICv was + * still active when the interrupt got accepted. Make sure + * inject_pending_event() is called to check for that. + */ + if (!vcpu->arch.apicv_active) + kvm_make_request(KVM_REQ_EVENT, vcpu); } EXPORT_SYMBOL_GPL(kvm_vcpu_update_apicv); @@ -9078,7 +9413,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) } if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) kvm_vcpu_flush_tlb_current(vcpu); - if (kvm_check_request(KVM_REQ_HV_TLB_FLUSH, vcpu)) + if (kvm_check_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu)) kvm_vcpu_flush_tlb_guest(vcpu); if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) { @@ -9171,13 +9506,21 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win || kvm_xen_has_interrupt(vcpu)) { ++vcpu->stat.req_event; - kvm_apic_accept_events(vcpu); + r = kvm_apic_accept_events(vcpu); + if (r < 0) { + r = 0; + goto out; + } if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) { r = 1; goto out; } - inject_pending_event(vcpu, &req_immediate_exit); + r = inject_pending_event(vcpu, &req_immediate_exit); + if (r < 0) { + r = 0; + goto out; + } if (req_int_win) static_call(kvm_x86_enable_irq_window)(vcpu); @@ -9379,7 +9722,8 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) return 1; } - kvm_apic_accept_events(vcpu); + if (kvm_apic_accept_events(vcpu) < 0) + return 0; switch(vcpu->arch.mp_state) { case KVM_MP_STATE_HALTED: case KVM_MP_STATE_AP_RESET_HOLD: @@ -9425,7 +9769,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu) if (r <= 0) break; - kvm_clear_request(KVM_REQ_PENDING_TIMER, vcpu); + kvm_clear_request(KVM_REQ_UNBLOCK, vcpu); if (kvm_cpu_has_pending_timer(vcpu)) kvm_inject_pending_timer_irqs(vcpu); @@ -9603,7 +9947,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) goto out; } kvm_vcpu_block(vcpu); - kvm_apic_accept_events(vcpu); + if (kvm_apic_accept_events(vcpu) < 0) { + r = 0; + goto out; + } kvm_clear_request(KVM_REQ_UNHALT, vcpu); r = -EAGAIN; if (signal_pending(current)) { @@ -9752,7 +10099,7 @@ void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) } EXPORT_SYMBOL_GPL(kvm_get_cs_db_l_bits); -static void __get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +static void __get_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { struct desc_ptr dt; @@ -9785,14 +10132,36 @@ skip_protected_regs: sregs->cr8 = kvm_get_cr8(vcpu); sregs->efer = vcpu->arch.efer; sregs->apic_base = kvm_get_apic_base(vcpu); +} - memset(sregs->interrupt_bitmap, 0, sizeof(sregs->interrupt_bitmap)); +static void __get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +{ + __get_sregs_common(vcpu, sregs); + + if (vcpu->arch.guest_state_protected) + return; if (vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft) set_bit(vcpu->arch.interrupt.nr, (unsigned long *)sregs->interrupt_bitmap); } +static void __get_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2) +{ + int i; + + __get_sregs_common(vcpu, (struct kvm_sregs *)sregs2); + + if (vcpu->arch.guest_state_protected) + return; + + if (is_pae_paging(vcpu)) { + for (i = 0 ; i < 4 ; i++) + sregs2->pdptrs[i] = kvm_pdptr_read(vcpu, i); + sregs2->flags |= KVM_SREGS2_FLAGS_PDPTRS_VALID; + } +} + int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { @@ -9805,11 +10174,17 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { + int r; + vcpu_load(vcpu); if (kvm_mpx_supported()) kvm_load_guest_fpu(vcpu); - kvm_apic_accept_events(vcpu); + r = kvm_apic_accept_events(vcpu); + if (r < 0) + goto out; + r = 0; + if ((vcpu->arch.mp_state == KVM_MP_STATE_HALTED || vcpu->arch.mp_state == KVM_MP_STATE_AP_RESET_HOLD) && vcpu->arch.pv.pv_unhalted) @@ -9817,10 +10192,11 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, else mp_state->mp_state = vcpu->arch.mp_state; +out: if (kvm_mpx_supported()) kvm_put_guest_fpu(vcpu); vcpu_put(vcpu); - return 0; + return r; } int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, @@ -9904,24 +10280,23 @@ static bool kvm_is_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) return kvm_is_valid_cr4(vcpu, sregs->cr4); } -static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +static int __set_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs, + int *mmu_reset_needed, bool update_pdptrs) { struct msr_data apic_base_msr; - int mmu_reset_needed = 0; - int pending_vec, max_bits, idx; + int idx; struct desc_ptr dt; - int ret = -EINVAL; if (!kvm_is_valid_sregs(vcpu, sregs)) - goto out; + return -EINVAL; apic_base_msr.data = sregs->apic_base; apic_base_msr.host_initiated = true; if (kvm_set_apic_base(vcpu, &apic_base_msr)) - goto out; + return -EINVAL; if (vcpu->arch.guest_state_protected) - goto skip_protected_regs; + return 0; dt.size = sregs->idt.limit; dt.address = sregs->idt.base; @@ -9931,31 +10306,30 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) static_call(kvm_x86_set_gdt)(vcpu, &dt); vcpu->arch.cr2 = sregs->cr2; - mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3; + *mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3; vcpu->arch.cr3 = sregs->cr3; kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); kvm_set_cr8(vcpu, sregs->cr8); - mmu_reset_needed |= vcpu->arch.efer != sregs->efer; + *mmu_reset_needed |= vcpu->arch.efer != sregs->efer; static_call(kvm_x86_set_efer)(vcpu, sregs->efer); - mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0; + *mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0; static_call(kvm_x86_set_cr0)(vcpu, sregs->cr0); vcpu->arch.cr0 = sregs->cr0; - mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4; + *mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4; static_call(kvm_x86_set_cr4)(vcpu, sregs->cr4); - idx = srcu_read_lock(&vcpu->kvm->srcu); - if (is_pae_paging(vcpu)) { - load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); - mmu_reset_needed = 1; + if (update_pdptrs) { + idx = srcu_read_lock(&vcpu->kvm->srcu); + if (is_pae_paging(vcpu)) { + load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); + *mmu_reset_needed = 1; + } + srcu_read_unlock(&vcpu->kvm->srcu, idx); } - srcu_read_unlock(&vcpu->kvm->srcu, idx); - - if (mmu_reset_needed) - kvm_mmu_reset_context(vcpu); kvm_set_segment(vcpu, &sregs->cs, VCPU_SREG_CS); kvm_set_segment(vcpu, &sregs->ds, VCPU_SREG_DS); @@ -9975,20 +10349,63 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) !is_protmode(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; -skip_protected_regs: + return 0; +} + +static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +{ + int pending_vec, max_bits; + int mmu_reset_needed = 0; + int ret = __set_sregs_common(vcpu, sregs, &mmu_reset_needed, true); + + if (ret) + return ret; + + if (mmu_reset_needed) + kvm_mmu_reset_context(vcpu); + max_bits = KVM_NR_INTERRUPTS; pending_vec = find_first_bit( (const unsigned long *)sregs->interrupt_bitmap, max_bits); + if (pending_vec < max_bits) { kvm_queue_interrupt(vcpu, pending_vec, false); pr_debug("Set back pending irq %d\n", pending_vec); + kvm_make_request(KVM_REQ_EVENT, vcpu); } + return 0; +} - kvm_make_request(KVM_REQ_EVENT, vcpu); +static int __set_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2) +{ + int mmu_reset_needed = 0; + bool valid_pdptrs = sregs2->flags & KVM_SREGS2_FLAGS_PDPTRS_VALID; + bool pae = (sregs2->cr0 & X86_CR0_PG) && (sregs2->cr4 & X86_CR4_PAE) && + !(sregs2->efer & EFER_LMA); + int i, ret; - ret = 0; -out: - return ret; + if (sregs2->flags & ~KVM_SREGS2_FLAGS_PDPTRS_VALID) + return -EINVAL; + + if (valid_pdptrs && (!pae || vcpu->arch.guest_state_protected)) + return -EINVAL; + + ret = __set_sregs_common(vcpu, (struct kvm_sregs *)sregs2, + &mmu_reset_needed, !valid_pdptrs); + if (ret) + return ret; + + if (valid_pdptrs) { + for (i = 0; i < 4 ; i++) + kvm_pdptr_write(vcpu, i, sregs2->pdptrs[i]); + + kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); + mmu_reset_needed = 1; + vcpu->arch.pdptrs_from_userspace = true; + } + if (mmu_reset_needed) + kvm_mmu_reset_context(vcpu); + return 0; } int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, @@ -10044,8 +10461,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, kvm_update_dr7(vcpu); if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) - vcpu->arch.singlestep_rip = kvm_rip_read(vcpu) + - get_segment_base(vcpu, VCPU_SREG_CS); + vcpu->arch.singlestep_rip = kvm_get_linear_rip(vcpu); /* * Trigger an rflags update that will inject or remove the trace @@ -10213,13 +10629,13 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) struct page *page; int r; + vcpu->arch.last_vmentry_cpu = -1; + if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; else vcpu->arch.mp_state = KVM_MP_STATE_UNINITIALIZED; - kvm_set_tsc_khz(vcpu, max_tsc_khz); - r = kvm_mmu_create(vcpu); if (r < 0) return r; @@ -10279,6 +10695,10 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) vcpu->arch.pending_external_vector = -1; vcpu->arch.preempted_in_kernel = false; +#if IS_ENABLED(CONFIG_HYPERV) + vcpu->arch.hv_root_tdp = INVALID_PAGE; +#endif + r = static_call(kvm_x86_vcpu_create)(vcpu); if (r) goto free_guest_fpu; @@ -10287,8 +10707,9 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) vcpu->arch.msr_platform_info = MSR_PLATFORM_INFO_CPUID_FAULT; kvm_vcpu_mtrr_init(vcpu); vcpu_load(vcpu); + kvm_set_tsc_khz(vcpu, max_tsc_khz); kvm_vcpu_reset(vcpu, false); - kvm_init_mmu(vcpu, false); + kvm_init_mmu(vcpu); vcpu_put(vcpu); return 0; @@ -10362,6 +10783,8 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { + unsigned long old_cr0 = kvm_read_cr0(vcpu); + kvm_lapic_reset(vcpu, init_event); vcpu->arch.hflags = 0; @@ -10430,6 +10853,17 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vcpu->arch.ia32_xss = 0; static_call(kvm_x86_vcpu_reset)(vcpu, init_event); + + /* + * Reset the MMU context if paging was enabled prior to INIT (which is + * implied if CR0.PG=1 as CR0 will be '0' prior to RESET). Unlike the + * standard CR0/CR4/EFER modification paths, only CR0.PG needs to be + * checked because it is unconditionally cleared on INIT and all other + * paging related bits are ignored if paging is disabled, i.e. CR0.WP, + * CR4, and EFER changes are all irrelevant if CR0.PG was '0'. + */ + if (old_cr0 & X86_CR0_PG) + kvm_mmu_reset_context(vcpu); } void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) @@ -10547,6 +10981,9 @@ int kvm_arch_hardware_setup(void *opaque) int r; rdmsrl_safe(MSR_EFER, &host_efer); + if (WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_NX) && + !(host_efer & EFER_NX))) + return -EIO; if (boot_cpu_has(X86_FEATURE_XSAVES)) rdmsrl(MSR_IA32_XSS, host_xss); @@ -10662,9 +11099,15 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm->arch.guest_can_read_msr_platform_info = true; +#if IS_ENABLED(CONFIG_HYPERV) + spin_lock_init(&kvm->arch.hv_root_tdp_lock); + kvm->arch.hv_root_tdp = INVALID_PAGE; +#endif + INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn); INIT_DELAYED_WORK(&kvm->arch.kvmclock_sync_work, kvmclock_sync_fn); + kvm_apicv_init(kvm); kvm_hv_init_vm(kvm); kvm_page_track_init(kvm); kvm_mmu_init_vm(kvm); @@ -10825,17 +11268,23 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kvm_hv_destroy_vm(kvm); } -void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) +static void memslot_rmap_free(struct kvm_memory_slot *slot) { int i; for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { kvfree(slot->arch.rmap[i]); slot->arch.rmap[i] = NULL; + } +} - if (i == 0) - continue; +void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) +{ + int i; + + memslot_rmap_free(slot); + for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) { kvfree(slot->arch.lpage_info[i - 1]); slot->arch.lpage_info[i - 1] = NULL; } @@ -10843,11 +11292,79 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) kvm_page_track_free_memslot(slot); } -static int kvm_alloc_memslot_metadata(struct kvm_memory_slot *slot, - unsigned long npages) +static int memslot_rmap_alloc(struct kvm_memory_slot *slot, + unsigned long npages) { + const int sz = sizeof(*slot->arch.rmap[0]); int i; + for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { + int level = i + 1; + int lpages = gfn_to_index(slot->base_gfn + npages - 1, + slot->base_gfn, level) + 1; + + WARN_ON(slot->arch.rmap[i]); + + slot->arch.rmap[i] = kvcalloc(lpages, sz, GFP_KERNEL_ACCOUNT); + if (!slot->arch.rmap[i]) { + memslot_rmap_free(slot); + return -ENOMEM; + } + } + + return 0; +} + +int alloc_all_memslots_rmaps(struct kvm *kvm) +{ + struct kvm_memslots *slots; + struct kvm_memory_slot *slot; + int r, i; + + /* + * Check if memslots alreday have rmaps early before acquiring + * the slots_arch_lock below. + */ + if (kvm_memslots_have_rmaps(kvm)) + return 0; + + mutex_lock(&kvm->slots_arch_lock); + + /* + * Read memslots_have_rmaps again, under the slots arch lock, + * before allocating the rmaps + */ + if (kvm_memslots_have_rmaps(kvm)) { + mutex_unlock(&kvm->slots_arch_lock); + return 0; + } + + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + slots = __kvm_memslots(kvm, i); + kvm_for_each_memslot(slot, slots) { + r = memslot_rmap_alloc(slot, slot->npages); + if (r) { + mutex_unlock(&kvm->slots_arch_lock); + return r; + } + } + } + + /* + * Ensure that memslots_have_rmaps becomes true strictly after + * all the rmap pointers are set. + */ + smp_store_release(&kvm->arch.memslots_have_rmaps, true); + mutex_unlock(&kvm->slots_arch_lock); + return 0; +} + +static int kvm_alloc_memslot_metadata(struct kvm *kvm, + struct kvm_memory_slot *slot, + unsigned long npages) +{ + int i, r; + /* * Clear out the previous array pointers for the KVM_MR_MOVE case. The * old arrays will be freed by __kvm_set_memory_region() if installing @@ -10855,7 +11372,13 @@ static int kvm_alloc_memslot_metadata(struct kvm_memory_slot *slot, */ memset(&slot->arch, 0, sizeof(slot->arch)); - for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { + if (kvm_memslots_have_rmaps(kvm)) { + r = memslot_rmap_alloc(slot, npages); + if (r) + return r; + } + + for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) { struct kvm_lpage_info *linfo; unsigned long ugfn; int lpages; @@ -10864,14 +11387,6 @@ static int kvm_alloc_memslot_metadata(struct kvm_memory_slot *slot, lpages = gfn_to_index(slot->base_gfn + npages - 1, slot->base_gfn, level) + 1; - slot->arch.rmap[i] = - kvcalloc(lpages, sizeof(*slot->arch.rmap[i]), - GFP_KERNEL_ACCOUNT); - if (!slot->arch.rmap[i]) - goto out_free; - if (i == 0) - continue; - linfo = kvcalloc(lpages, sizeof(*linfo), GFP_KERNEL_ACCOUNT); if (!linfo) goto out_free; @@ -10901,12 +11416,9 @@ static int kvm_alloc_memslot_metadata(struct kvm_memory_slot *slot, return 0; out_free: - for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { - kvfree(slot->arch.rmap[i]); - slot->arch.rmap[i] = NULL; - if (i == 0) - continue; + memslot_rmap_free(slot); + for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) { kvfree(slot->arch.lpage_info[i - 1]); slot->arch.lpage_info[i - 1] = NULL; } @@ -10935,7 +11447,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, enum kvm_mr_change change) { if (change == KVM_MR_CREATE || change == KVM_MR_MOVE) - return kvm_alloc_memslot_metadata(memslot, + return kvm_alloc_memslot_metadata(kvm, memslot, mem->memory_size >> PAGE_SHIFT); return 0; } @@ -11011,36 +11523,19 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, */ kvm_mmu_zap_collapsible_sptes(kvm, new); } else { - /* By default, write-protect everything to log writes. */ - int level = PG_LEVEL_4K; + /* + * Initially-all-set does not require write protecting any page, + * because they're all assumed to be dirty. + */ + if (kvm_dirty_log_manual_protect_and_init_set(kvm)) + return; if (kvm_x86_ops.cpu_dirty_log_size) { - /* - * Clear all dirty bits, unless pages are treated as - * dirty from the get-go. - */ - if (!kvm_dirty_log_manual_protect_and_init_set(kvm)) - kvm_mmu_slot_leaf_clear_dirty(kvm, new); - - /* - * Write-protect large pages on write so that dirty - * logging happens at 4k granularity. No need to - * write-protect small SPTEs since write accesses are - * logged by the CPU via dirty bits. - */ - level = PG_LEVEL_2M; - } else if (kvm_dirty_log_manual_protect_and_init_set(kvm)) { - /* - * If we're with initial-all-set, we don't need - * to write protect any small page because - * they're reported as dirty already. However - * we still need to write-protect huge pages - * so that the page split can happen lazily on - * the first write to the huge page. - */ - level = PG_LEVEL_2M; + kvm_mmu_slot_leaf_clear_dirty(kvm, new); + kvm_mmu_slot_remove_write_access(kvm, new, PG_LEVEL_2M); + } else { + kvm_mmu_slot_remove_write_access(kvm, new, PG_LEVEL_4K); } - kvm_mmu_slot_remove_write_access(kvm, new, level); } } @@ -11428,7 +11923,8 @@ bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu) void kvm_arch_start_assignment(struct kvm *kvm) { - atomic_inc(&kvm->arch.assigned_device_count); + if (atomic_inc_return(&kvm->arch.assigned_device_count) == 1) + static_call_cond(kvm_x86_start_assignment)(kvm); } EXPORT_SYMBOL_GPL(kvm_arch_start_assignment); @@ -11608,8 +12104,6 @@ int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva) { bool pcid_enabled; struct x86_exception e; - unsigned i; - unsigned long roots_to_free = 0; struct { u64 pcid; u64 gla; @@ -11643,23 +12137,7 @@ int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva) return 1; } - if (kvm_get_active_pcid(vcpu) == operand.pcid) { - kvm_mmu_sync_roots(vcpu); - kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); - } - - for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) - if (kvm_get_pcid(vcpu, vcpu->arch.mmu->prev_roots[i].pgd) - == operand.pcid) - roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i); - - kvm_mmu_free_roots(vcpu, vcpu->arch.mmu, roots_to_free); - /* - * If neither the current cr3 nor any of the prev_roots use the - * given PCID, then nothing needs to be done here because a - * resync will happen anyway before switching to any other CR3. - */ - + kvm_invalidate_pcid(vcpu, operand.pcid); return kvm_skip_emulated_instruction(vcpu); case INVPCID_TYPE_ALL_NON_GLOBAL: @@ -11672,7 +12150,7 @@ int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva) fallthrough; case INVPCID_TYPE_ALL_INCL_GLOBAL: - kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); return kvm_skip_emulated_instruction(vcpu); default: |