diff options
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r-- | arch/x86/kvm/Kconfig | 11 | ||||
-rw-r--r-- | arch/x86/kvm/cpuid.c | 18 | ||||
-rw-r--r-- | arch/x86/kvm/cpuid.h | 3 | ||||
-rw-r--r-- | arch/x86/kvm/hyperv.c | 10 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.c | 38 | ||||
-rw-r--r-- | arch/x86/kvm/mmu.h | 7 | ||||
-rw-r--r-- | arch/x86/kvm/mmu/mmu.c | 58 | ||||
-rw-r--r-- | arch/x86/kvm/mmu/mmu_internal.h | 15 | ||||
-rw-r--r-- | arch/x86/kvm/mmu/tdp_mmu.c | 152 | ||||
-rw-r--r-- | arch/x86/kvm/mmu/tdp_mmu.h | 5 | ||||
-rw-r--r-- | arch/x86/kvm/mtrr.c | 2 | ||||
-rw-r--r-- | arch/x86/kvm/pmu.c | 27 | ||||
-rw-r--r-- | arch/x86/kvm/pmu.h | 6 | ||||
-rw-r--r-- | arch/x86/kvm/smm.c | 1 | ||||
-rw-r--r-- | arch/x86/kvm/svm/avic.c | 5 | ||||
-rw-r--r-- | arch/x86/kvm/svm/nested.c | 3 | ||||
-rw-r--r-- | arch/x86/kvm/svm/pmu.c | 2 | ||||
-rw-r--r-- | arch/x86/kvm/svm/sev.c | 34 | ||||
-rw-r--r-- | arch/x86/kvm/svm/svm.c | 106 | ||||
-rw-r--r-- | arch/x86/kvm/svm/svm.h | 1 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/pmu_intel.c | 4 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/vmx.c | 45 | ||||
-rw-r--r-- | arch/x86/kvm/x86.c | 293 | ||||
-rw-r--r-- | arch/x86/kvm/x86.h | 1 | ||||
-rw-r--r-- | arch/x86/kvm/xen.c | 59 |
25 files changed, 560 insertions, 346 deletions
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index ed90f148140d..950c12868d30 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -154,4 +154,15 @@ config KVM_PROVE_MMU config KVM_EXTERNAL_WRITE_TRACKING bool +config KVM_MAX_NR_VCPUS + int "Maximum number of vCPUs per KVM guest" + depends on KVM + range 1024 4096 + default 4096 if MAXSMP + default 1024 + help + Set the maximum number of vCPUs per KVM guest. Larger values will increase + the memory footprint of each KVM guest, regardless of how many vCPUs are + created for a given VM. + endif # VIRTUALIZATION diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 0544e30b4946..dda6fc4cfae8 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -360,14 +360,6 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vcpu->arch.guest_supported_xcr0 = cpuid_get_supported_xcr0(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent); - /* - * FP+SSE can always be saved/restored via KVM_{G,S}ET_XSAVE, even if - * XSAVE/XCRO are not exposed to the guest, and even if XSAVE isn't - * supported by the host. - */ - vcpu->arch.guest_fpu.fpstate->user_xfeatures = vcpu->arch.guest_supported_xcr0 | - XFEATURE_MASK_FPSSE; - kvm_update_pv_runtime(vcpu); vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); @@ -456,7 +448,9 @@ static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, vcpu->arch.cpuid_nent = nent; vcpu->arch.kvm_cpuid = kvm_get_hypervisor_cpuid(vcpu, KVM_SIGNATURE); +#ifdef CONFIG_KVM_XEN vcpu->arch.xen.cpuid = kvm_get_hypervisor_cpuid(vcpu, XEN_SIGNATURE); +#endif kvm_vcpu_after_set_cpuid(vcpu); return 0; @@ -761,11 +755,13 @@ void kvm_set_cpu_caps(void) kvm_cpu_cap_mask(CPUID_8000_0021_EAX, F(NO_NESTED_DATA_BP) | F(LFENCE_RDTSC) | 0 /* SmmPgCfgLock */ | - F(NULL_SEL_CLR_BASE) | F(AUTOIBRS) | 0 /* PrefetchCtlMsr */ + F(NULL_SEL_CLR_BASE) | F(AUTOIBRS) | 0 /* PrefetchCtlMsr */ | + F(WRMSR_XX_BASE_NS) ); - if (cpu_feature_enabled(X86_FEATURE_SRSO_NO)) - kvm_cpu_cap_set(X86_FEATURE_SRSO_NO); + kvm_cpu_cap_check_and_set(X86_FEATURE_SBPB); + kvm_cpu_cap_check_and_set(X86_FEATURE_IBPB_BRTYPE); + kvm_cpu_cap_check_and_set(X86_FEATURE_SRSO_NO); kvm_cpu_cap_init_kvm_defined(CPUID_8000_0022_EAX, F(PERFMON_V2) diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 284fa4704553..0b90532b6e26 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -174,7 +174,8 @@ static inline bool guest_has_spec_ctrl_msr(struct kvm_vcpu *vcpu) static inline bool guest_has_pred_cmd_msr(struct kvm_vcpu *vcpu) { return (guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) || - guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBPB)); + guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBPB) || + guest_cpuid_has(vcpu, X86_FEATURE_SBPB)); } static inline bool supports_cpuid_fault(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 7c2dac6824e2..238afd7335e4 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -727,10 +727,12 @@ static int stimer_set_count(struct kvm_vcpu_hv_stimer *stimer, u64 count, stimer_cleanup(stimer); stimer->count = count; - if (stimer->count == 0) - stimer->config.enable = 0; - else if (stimer->config.auto_enable) - stimer->config.enable = 1; + if (!host) { + if (stimer->count == 0) + stimer->config.enable = 0; + else if (stimer->config.auto_enable) + stimer->config.enable = 1; + } if (stimer->config.enable) stimer_mark_pending(stimer, false); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index dcd60b39e794..245b20973cae 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2444,22 +2444,22 @@ EXPORT_SYMBOL_GPL(kvm_lapic_set_eoi); void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset) { struct kvm_lapic *apic = vcpu->arch.apic; - u64 val; /* - * ICR is a single 64-bit register when x2APIC is enabled. For legacy - * xAPIC, ICR writes need to go down the common (slightly slower) path - * to get the upper half from ICR2. + * ICR is a single 64-bit register when x2APIC is enabled, all others + * registers hold 32-bit values. For legacy xAPIC, ICR writes need to + * go down the common path to get the upper half from ICR2. + * + * Note, using the write helpers may incur an unnecessary write to the + * virtual APIC state, but KVM needs to conditionally modify the value + * in certain cases, e.g. to clear the ICR busy bit. The cost of extra + * conditional branches is likely a wash relative to the cost of the + * maybe-unecessary write, and both are in the noise anyways. */ - if (apic_x2apic_mode(apic) && offset == APIC_ICR) { - val = kvm_lapic_get_reg64(apic, APIC_ICR); - kvm_apic_send_ipi(apic, (u32)val, (u32)(val >> 32)); - trace_kvm_apic_write(APIC_ICR, val); - } else { - /* TODO: optimize to just emulate side effect w/o one more write */ - val = kvm_lapic_get_reg(apic, offset); - kvm_lapic_reg_write(apic, offset, (u32)val); - } + if (apic_x2apic_mode(apic) && offset == APIC_ICR) + kvm_x2apic_icr_write(apic, kvm_lapic_get_reg64(apic, APIC_ICR)); + else + kvm_lapic_reg_write(apic, offset, kvm_lapic_get_reg(apic, offset)); } EXPORT_SYMBOL_GPL(kvm_apic_write_nodecode); @@ -2670,6 +2670,8 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) u64 msr_val; int i; + static_call_cond(kvm_x86_apicv_pre_state_restore)(vcpu); + if (!init_event) { msr_val = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE; if (kvm_vcpu_is_reset_bsp(vcpu)) @@ -2759,13 +2761,17 @@ int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type) { u32 reg = kvm_lapic_get_reg(apic, lvt_type); int vector, mode, trig_mode; + int r; if (kvm_apic_hw_enabled(apic) && !(reg & APIC_LVT_MASKED)) { vector = reg & APIC_VECTOR_MASK; mode = reg & APIC_MODE_MASK; trig_mode = reg & APIC_LVT_LEVEL_TRIGGER; - return __apic_accept_irq(apic, mode, vector, 1, trig_mode, - NULL); + + r = __apic_accept_irq(apic, mode, vector, 1, trig_mode, NULL); + if (r && lvt_type == APIC_LVTPC) + kvm_lapic_set_reg(apic, APIC_LVTPC, reg | APIC_LVT_MASKED); + return r; } return 0; } @@ -2977,6 +2983,8 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) struct kvm_lapic *apic = vcpu->arch.apic; int r; + static_call_cond(kvm_x86_apicv_pre_state_restore)(vcpu); + kvm_lapic_set_base(vcpu, vcpu->arch.apic_base); /* set SPIV separately to get count of SW disabled APICs right */ apic_set_spiv(apic, *((u32 *)(s->regs + APIC_SPIV))); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 253fb2093d5d..bb8c86eefac0 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -237,6 +237,13 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, return -(u32)fault & errcode; } +bool __kvm_mmu_honors_guest_mtrrs(bool vm_has_noncoherent_dma); + +static inline bool kvm_mmu_honors_guest_mtrrs(struct kvm *kvm) +{ + return __kvm_mmu_honors_guest_mtrrs(kvm_arch_has_noncoherent_dma(kvm)); +} + void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end); int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index e1d011c67cc6..b0f01d605617 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3425,8 +3425,8 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { struct kvm_mmu_page *sp; int ret = RET_PF_INVALID; - u64 spte = 0ull; - u64 *sptep = NULL; + u64 spte; + u64 *sptep; uint retry_count = 0; if (!page_fault_can_be_fast(fault)) @@ -3442,6 +3442,14 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) else sptep = fast_pf_get_last_sptep(vcpu, fault->addr, &spte); + /* + * It's entirely possible for the mapping to have been zapped + * by a different task, but the root page should always be + * available as the vCPU holds a reference to its root(s). + */ + if (WARN_ON_ONCE(!sptep)) + spte = REMOVED_SPTE; + if (!is_shadow_present_pte(spte)) break; @@ -4479,21 +4487,28 @@ out_unlock: } #endif -int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) +bool __kvm_mmu_honors_guest_mtrrs(bool vm_has_noncoherent_dma) { /* - * If the guest's MTRRs may be used to compute the "real" memtype, - * restrict the mapping level to ensure KVM uses a consistent memtype - * across the entire mapping. If the host MTRRs are ignored by TDP - * (shadow_memtype_mask is non-zero), and the VM has non-coherent DMA - * (DMA doesn't snoop CPU caches), KVM's ABI is to honor the memtype - * from the guest's MTRRs so that guest accesses to memory that is - * DMA'd aren't cached against the guest's wishes. + * If host MTRRs are ignored (shadow_memtype_mask is non-zero), and the + * VM has non-coherent DMA (DMA doesn't snoop CPU caches), KVM's ABI is + * to honor the memtype from the guest's MTRRs so that guest accesses + * to memory that is DMA'd aren't cached against the guest's wishes. * * Note, KVM may still ultimately ignore guest MTRRs for certain PFNs, * e.g. KVM will force UC memtype for host MMIO. */ - if (shadow_memtype_mask && kvm_arch_has_noncoherent_dma(vcpu->kvm)) { + return vm_has_noncoherent_dma && shadow_memtype_mask; +} + +int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) +{ + /* + * If the guest's MTRRs may be used to compute the "real" memtype, + * restrict the mapping level to ensure KVM uses a consistent memtype + * across the entire mapping. + */ + if (kvm_mmu_honors_guest_mtrrs(vcpu->kvm)) { for ( ; fault->max_level > PG_LEVEL_4K; --fault->max_level) { int page_num = KVM_PAGES_PER_HPAGE(fault->max_level); gfn_t base = gfn_round_for_level(fault->gfn, @@ -6167,20 +6182,15 @@ static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm) return unlikely(!list_empty_careful(&kvm->arch.zapped_obsolete_pages)); } -int kvm_mmu_init_vm(struct kvm *kvm) +void kvm_mmu_init_vm(struct kvm *kvm) { - int r; - INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages); INIT_LIST_HEAD(&kvm->arch.possible_nx_huge_pages); spin_lock_init(&kvm->arch.mmu_unsync_pages_lock); - if (tdp_mmu_enabled) { - r = kvm_mmu_init_tdp_mmu(kvm); - if (r < 0) - return r; - } + if (tdp_mmu_enabled) + kvm_mmu_init_tdp_mmu(kvm); kvm->arch.split_page_header_cache.kmem_cache = mmu_page_header_cache; kvm->arch.split_page_header_cache.gfp_zero = __GFP_ZERO; @@ -6189,8 +6199,6 @@ int kvm_mmu_init_vm(struct kvm *kvm) kvm->arch.split_desc_cache.kmem_cache = pte_list_desc_cache; kvm->arch.split_desc_cache.gfp_zero = __GFP_ZERO; - - return 0; } static void mmu_free_vm_memory_caches(struct kvm *kvm) @@ -6246,7 +6254,6 @@ static bool kvm_rmap_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_e void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) { bool flush; - int i; if (WARN_ON_ONCE(gfn_end <= gfn_start)) return; @@ -6257,11 +6264,8 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) flush = kvm_rmap_zap_gfn_range(kvm, gfn_start, gfn_end); - if (tdp_mmu_enabled) { - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) - flush = kvm_tdp_mmu_zap_leafs(kvm, i, gfn_start, - gfn_end, true, flush); - } + if (tdp_mmu_enabled) + flush = kvm_tdp_mmu_zap_leafs(kvm, gfn_start, gfn_end, flush); if (flush) kvm_flush_remote_tlbs_range(kvm, gfn_start, gfn_end - gfn_start); diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index b102014e2c60..decc1f153669 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -58,7 +58,12 @@ struct kvm_mmu_page { bool tdp_mmu_page; bool unsync; - u8 mmu_valid_gen; + union { + u8 mmu_valid_gen; + + /* Only accessed under slots_lock. */ + bool tdp_mmu_scheduled_root_to_zap; + }; /* * The shadow page can't be replaced by an equivalent huge page @@ -100,13 +105,7 @@ struct kvm_mmu_page { struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */ tdp_ptep_t ptep; }; - union { - DECLARE_BITMAP(unsync_child_bitmap, 512); - struct { - struct work_struct tdp_mmu_async_work; - void *tdp_mmu_async_data; - }; - }; + DECLARE_BITMAP(unsync_child_bitmap, 512); /* * Tracks shadow pages that, if zapped, would allow KVM to create an NX diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 6c63f2d1675f..6cd4dd631a2f 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -12,18 +12,10 @@ #include <trace/events/kvm.h> /* Initializes the TDP MMU for the VM, if enabled. */ -int kvm_mmu_init_tdp_mmu(struct kvm *kvm) +void kvm_mmu_init_tdp_mmu(struct kvm *kvm) { - struct workqueue_struct *wq; - - wq = alloc_workqueue("kvm", WQ_UNBOUND|WQ_MEM_RECLAIM|WQ_CPU_INTENSIVE, 0); - if (!wq) - return -ENOMEM; - INIT_LIST_HEAD(&kvm->arch.tdp_mmu_roots); spin_lock_init(&kvm->arch.tdp_mmu_pages_lock); - kvm->arch.tdp_mmu_zap_wq = wq; - return 1; } /* Arbitrarily returns true so that this may be used in if statements. */ @@ -46,20 +38,15 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) * ultimately frees all roots. */ kvm_tdp_mmu_invalidate_all_roots(kvm); - - /* - * Destroying a workqueue also first flushes the workqueue, i.e. no - * need to invoke kvm_tdp_mmu_zap_invalidated_roots(). - */ - destroy_workqueue(kvm->arch.tdp_mmu_zap_wq); + kvm_tdp_mmu_zap_invalidated_roots(kvm); WARN_ON(atomic64_read(&kvm->arch.tdp_mmu_pages)); WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots)); /* * Ensure that all the outstanding RCU callbacks to free shadow pages - * can run before the VM is torn down. Work items on tdp_mmu_zap_wq - * can call kvm_tdp_mmu_put_root and create new callbacks. + * can run before the VM is torn down. Putting the last reference to + * zapped roots will create new callbacks. */ rcu_barrier(); } @@ -86,46 +73,6 @@ static void tdp_mmu_free_sp_rcu_callback(struct rcu_head *head) tdp_mmu_free_sp(sp); } -static void tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root, - bool shared); - -static void tdp_mmu_zap_root_work(struct work_struct *work) -{ - struct kvm_mmu_page *root = container_of(work, struct kvm_mmu_page, - tdp_mmu_async_work); - struct kvm *kvm = root->tdp_mmu_async_data; - - read_lock(&kvm->mmu_lock); - - /* - * A TLB flush is not necessary as KVM performs a local TLB flush when - * allocating a new root (see kvm_mmu_load()), and when migrating vCPU - * to a different pCPU. Note, the local TLB flush on reuse also - * invalidates any paging-structure-cache entries, i.e. TLB entries for - * intermediate paging structures, that may be zapped, as such entries - * are associated with the ASID on both VMX and SVM. - */ - tdp_mmu_zap_root(kvm, root, true); - - /* - * Drop the refcount using kvm_tdp_mmu_put_root() to test its logic for - * avoiding an infinite loop. By design, the root is reachable while - * it's being asynchronously zapped, thus a different task can put its - * last reference, i.e. flowing through kvm_tdp_mmu_put_root() for an - * asynchronously zapped root is unavoidable. - */ - kvm_tdp_mmu_put_root(kvm, root, true); - - read_unlock(&kvm->mmu_lock); -} - -static void tdp_mmu_schedule_zap_root(struct kvm *kvm, struct kvm_mmu_page *root) -{ - root->tdp_mmu_async_data = kvm; - INIT_WORK(&root->tdp_mmu_async_work, tdp_mmu_zap_root_work); - queue_work(kvm->arch.tdp_mmu_zap_wq, &root->tdp_mmu_async_work); -} - void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, bool shared) { @@ -211,8 +158,12 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, #define for_each_valid_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared) \ __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared, true) -#define for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id) \ - __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, false, false) +#define for_each_tdp_mmu_root_yield_safe(_kvm, _root, _shared) \ + for (_root = tdp_mmu_next_root(_kvm, NULL, _shared, false); \ + _root; \ + _root = tdp_mmu_next_root(_kvm, _root, _shared, false)) \ + if (!kvm_lockdep_assert_mmu_lock_held(_kvm, _shared)) { \ + } else /* * Iterate over all TDP MMU roots. Requires that mmu_lock be held for write, @@ -292,7 +243,7 @@ hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu) * by a memslot update or by the destruction of the VM. Initialize the * refcount to two; one reference for the vCPU, and one reference for * the TDP MMU itself, which is held until the root is invalidated and - * is ultimately put by tdp_mmu_zap_root_work(). + * is ultimately put by kvm_tdp_mmu_zap_invalidated_roots(). */ refcount_set(&root->tdp_mmu_root_count, 2); @@ -877,13 +828,12 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root, * true if a TLB flush is needed before releasing the MMU lock, i.e. if one or * more SPTEs were zapped since the MMU lock was last acquired. */ -bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, gfn_t end, - bool can_yield, bool flush) +bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush) { struct kvm_mmu_page *root; - for_each_tdp_mmu_root_yield_safe(kvm, root, as_id) - flush = tdp_mmu_zap_leafs(kvm, root, start, end, can_yield, flush); + for_each_tdp_mmu_root_yield_safe(kvm, root, false) + flush = tdp_mmu_zap_leafs(kvm, root, start, end, true, flush); return flush; } @@ -891,7 +841,6 @@ bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, gfn_t end, void kvm_tdp_mmu_zap_all(struct kvm *kvm) { struct kvm_mmu_page *root; - int i; /* * Zap all roots, including invalid roots, as all SPTEs must be dropped @@ -905,10 +854,8 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm) * is being destroyed or the userspace VMM has exited. In both cases, * KVM_RUN is unreachable, i.e. no vCPUs will ever service the request. */ - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { - for_each_tdp_mmu_root_yield_safe(kvm, root, i) - tdp_mmu_zap_root(kvm, root, false); - } + for_each_tdp_mmu_root_yield_safe(kvm, root, false) + tdp_mmu_zap_root(kvm, root, false); } /* @@ -917,18 +864,47 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm) */ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) { - flush_workqueue(kvm->arch.tdp_mmu_zap_wq); + struct kvm_mmu_page *root; + + read_lock(&kvm->mmu_lock); + + for_each_tdp_mmu_root_yield_safe(kvm, root, true) { + if (!root->tdp_mmu_scheduled_root_to_zap) + continue; + + root->tdp_mmu_scheduled_root_to_zap = false; + KVM_BUG_ON(!root->role.invalid, kvm); + + /* + * A TLB flush is not necessary as KVM performs a local TLB + * flush when allocating a new root (see kvm_mmu_load()), and + * when migrating a vCPU to a different pCPU. Note, the local + * TLB flush on reuse also invalidates paging-structure-cache + * entries, i.e. TLB entries for intermediate paging structures, + * that may be zapped, as such entries are associated with the + * ASID on both VMX and SVM. + */ + tdp_mmu_zap_root(kvm, root, true); + + /* + * The referenced needs to be put *after* zapping the root, as + * the root must be reachable by mmu_notifiers while it's being + * zapped + */ + kvm_tdp_mmu_put_root(kvm, root, true); + } + + read_unlock(&kvm->mmu_lock); } /* * Mark each TDP MMU root as invalid to prevent vCPUs from reusing a root that * is about to be zapped, e.g. in response to a memslots update. The actual - * zapping is performed asynchronously. Using a separate workqueue makes it - * easy to ensure that the destruction is performed before the "fast zap" - * completes, without keeping a separate list of invalidated roots; the list is - * effectively the list of work items in the workqueue. + * zapping is done separately so that it happens with mmu_lock with read, + * whereas invalidating roots must be done with mmu_lock held for write (unless + * the VM is being destroyed). * - * Note, the asynchronous worker is gifted the TDP MMU's reference. + * Note, kvm_tdp_mmu_zap_invalidated_roots() is gifted the TDP MMU's reference. * See kvm_tdp_mmu_get_vcpu_root_hpa(). */ void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm) @@ -953,19 +929,20 @@ void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm) /* * As above, mmu_lock isn't held when destroying the VM! There can't * be other references to @kvm, i.e. nothing else can invalidate roots - * or be consuming roots, but walking the list of roots does need to be - * guarded against roots being deleted by the asynchronous zap worker. + * or get/put references to roots. */ - rcu_read_lock(); - - list_for_each_entry_rcu(root, &kvm->arch.tdp_mmu_roots, link) { + list_for_each_entry(root, &kvm->arch.tdp_mmu_roots, link) { + /* + * Note, invalid roots can outlive a memslot update! Invalid + * roots must be *zapped* before the memslot update completes, + * but a different task can acquire a reference and keep the + * root alive after its been zapped. + */ if (!root->role.invalid) { + root->tdp_mmu_scheduled_root_to_zap = true; root->role.invalid = true; - tdp_mmu_schedule_zap_root(kvm, root); } } - - rcu_read_unlock(); } /* @@ -1146,8 +1123,13 @@ retry: bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range, bool flush) { - return kvm_tdp_mmu_zap_leafs(kvm, range->slot->as_id, range->start, - range->end, range->may_block, flush); + struct kvm_mmu_page *root; + + __for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false, false) + flush = tdp_mmu_zap_leafs(kvm, root, range->start, range->end, + range->may_block, flush); + + return flush; } typedef bool (*tdp_handler_t)(struct kvm *kvm, struct tdp_iter *iter, diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index 0a63b1afabd3..733a3aef3a96 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -7,7 +7,7 @@ #include "spte.h" -int kvm_mmu_init_tdp_mmu(struct kvm *kvm); +void kvm_mmu_init_tdp_mmu(struct kvm *kvm); void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm); hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu); @@ -20,8 +20,7 @@ __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root) void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, bool shared); -bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, - gfn_t end, bool can_yield, bool flush); +bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush); bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp); void kvm_tdp_mmu_zap_all(struct kvm *kvm); void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm); diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index 3eb6e7f47e96..a67c28a56417 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -320,7 +320,7 @@ static void update_mtrr(struct kvm_vcpu *vcpu, u32 msr) struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state; gfn_t start, end; - if (!tdp_enabled || !kvm_arch_has_noncoherent_dma(vcpu->kvm)) + if (!kvm_mmu_honors_guest_mtrrs(vcpu->kvm)) return; if (!mtrr_is_enabled(mtrr_state) && msr != MSR_MTRRdefType) diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index edb89b51b383..9ae07db6f0f6 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -93,14 +93,6 @@ void kvm_pmu_ops_update(const struct kvm_pmu_ops *pmu_ops) #undef __KVM_X86_PMU_OP } -static void kvm_pmi_trigger_fn(struct irq_work *irq_work) -{ - struct kvm_pmu *pmu = container_of(irq_work, struct kvm_pmu, irq_work); - struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu); - - kvm_pmu_deliver_pmi(vcpu); -} - static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi) { struct kvm_pmu *pmu = pmc_to_pmu(pmc); @@ -124,20 +116,7 @@ static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi) __set_bit(pmc->idx, (unsigned long *)&pmu->global_status); } - if (!pmc->intr || skip_pmi) - return; - - /* - * Inject PMI. If vcpu was in a guest mode during NMI PMI - * can be ejected on a guest mode re-entry. Otherwise we can't - * be sure that vcpu wasn't executing hlt instruction at the - * time of vmexit and is not going to re-enter guest mode until - * woken up. So we should wake it, but this is impossible from - * NMI context. Do it from irq work instead. - */ - if (in_pmi && !kvm_handling_nmi_from_guest(pmc->vcpu)) - irq_work_queue(&pmc_to_pmu(pmc)->irq_work); - else + if (pmc->intr && !skip_pmi) kvm_make_request(KVM_REQ_PMI, pmc->vcpu); } @@ -675,9 +654,6 @@ void kvm_pmu_refresh(struct kvm_vcpu *vcpu) void kvm_pmu_reset(struct kvm_vcpu *vcpu) { - struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - - irq_work_sync(&pmu->irq_work); static_call(kvm_x86_pmu_reset)(vcpu); } @@ -687,7 +663,6 @@ void kvm_pmu_init(struct kvm_vcpu *vcpu) memset(pmu, 0, sizeof(*pmu)); static_call(kvm_x86_pmu_init)(vcpu); - init_irq_work(&pmu->irq_work, kvm_pmi_trigger_fn); pmu->event_count = 0; pmu->need_cleanup = false; kvm_pmu_refresh(vcpu); diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 7d9ba301c090..1d64113de488 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -74,6 +74,12 @@ static inline u64 pmc_read_counter(struct kvm_pmc *pmc) return counter & pmc_bitmask(pmc); } +static inline void pmc_write_counter(struct kvm_pmc *pmc, u64 val) +{ + pmc->counter += val - pmc_read_counter(pmc); + pmc->counter &= pmc_bitmask(pmc); +} + static inline void pmc_release_perf_event(struct kvm_pmc *pmc) { if (pmc->perf_event) { diff --git a/arch/x86/kvm/smm.c b/arch/x86/kvm/smm.c index b42111a24cc2..dc3d95fdca7d 100644 --- a/arch/x86/kvm/smm.c +++ b/arch/x86/kvm/smm.c @@ -324,7 +324,6 @@ void enter_smm(struct kvm_vcpu *vcpu) cr0 = vcpu->arch.cr0 & ~(X86_CR0_PE | X86_CR0_EM | X86_CR0_TS | X86_CR0_PG); static_call(kvm_x86_set_cr0)(vcpu, cr0); - vcpu->arch.cr0 = cr0; static_call(kvm_x86_set_cr4)(vcpu, 0); diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 2092db892d7d..4b74ea91f4e6 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -529,8 +529,11 @@ int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu) case AVIC_IPI_FAILURE_INVALID_BACKING_PAGE: WARN_ONCE(1, "Invalid backing page\n"); break; + case AVIC_IPI_FAILURE_INVALID_IPI_VECTOR: + /* Invalid IPI with vector < 16 */ + break; default: - pr_err("Unknown IPI interception\n"); + vcpu_unimpl(vcpu, "Unknown avic incomplete IPI interception\n"); } return 1; diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index dd496c9e5f91..3fea8c47679e 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -1253,6 +1253,9 @@ void svm_leave_nested(struct kvm_vcpu *vcpu) nested_svm_uninit_mmu_context(vcpu); vmcb_mark_all_dirty(svm->vmcb); + + if (kvm_apicv_activated(vcpu->kvm)) + kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); } kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index cef5a3d0abd0..373ff6a6687b 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -160,7 +160,7 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) /* MSR_PERFCTRn */ pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER); if (pmc) { - pmc->counter += data - pmc_read_counter(pmc); + pmc_write_counter(pmc, data); pmc_update_sample_period(pmc); return 0; } diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index b9a0a939d59f..4900c078045a 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2962,6 +2962,32 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) count, in); } +static void sev_es_vcpu_after_set_cpuid(struct vcpu_svm *svm) +{ + struct kvm_vcpu *vcpu = &svm->vcpu; + + if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) { + bool v_tsc_aux = guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) || + guest_cpuid_has(vcpu, X86_FEATURE_RDPID); + + set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, v_tsc_aux, v_tsc_aux); + } +} + +void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm) +{ + struct kvm_vcpu *vcpu = &svm->vcpu; + struct kvm_cpuid_entry2 *best; + + /* For sev guests, the memory encryption bit is not reserved in CR3. */ + best = kvm_find_cpuid_entry(vcpu, 0x8000001F); + if (best) + vcpu->arch.reserved_gpa_bits &= ~(1UL << (best->ebx & 0x3f)); + + if (sev_es_guest(svm->vcpu.kvm)) + sev_es_vcpu_after_set_cpuid(svm); +} + static void sev_es_init_vmcb(struct vcpu_svm *svm) { struct vmcb *vmcb = svm->vmcb01.ptr; @@ -3024,14 +3050,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm) set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1); - - if (boot_cpu_has(X86_FEATURE_V_TSC_AUX) && - (guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDTSCP) || - guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDPID))) { - set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, 1, 1); - if (guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDTSCP)) - svm_clr_intercept(svm, INTERCEPT_RDTSCP); - } } void sev_init_vmcb(struct vcpu_svm *svm) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index f283eb47f6ac..712146312358 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -199,7 +199,7 @@ module_param_named(npt, npt_enabled, bool, 0444); /* allow nested virtualization in KVM/SVM */ static int nested = true; -module_param(nested, int, S_IRUGO); +module_param(nested, int, 0444); /* enable/disable Next RIP Save */ int nrips = true; @@ -364,8 +364,6 @@ static void svm_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask) svm->vmcb->control.int_state |= SVM_INTERRUPT_SHADOW_MASK; } -static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, - void *insn, int insn_len); static int __svm_skip_emulated_instruction(struct kvm_vcpu *vcpu, bool commit_side_effects) @@ -386,14 +384,6 @@ static int __svm_skip_emulated_instruction(struct kvm_vcpu *vcpu, } if (!svm->next_rip) { - /* - * FIXME: Drop this when kvm_emulate_instruction() does the - * right thing and treats "can't emulate" as outright failure - * for EMULTYPE_SKIP. - */ - if (!svm_can_emulate_instruction(vcpu, EMULTYPE_SKIP, NULL, 0)) - return 0; - if (unlikely(!commit_side_effects)) old_rflags = svm->vmcb->save.rflags; @@ -531,8 +521,6 @@ static bool __kvm_is_svm_supported(void) int cpu = smp_processor_id(); struct cpuinfo_x86 *c = &cpu_data(cpu); - u64 vm_cr; - if (c->x86_vendor != X86_VENDOR_AMD && c->x86_vendor != X86_VENDOR_HYGON) { pr_err("CPU %d isn't AMD or Hygon\n", cpu); @@ -549,12 +537,6 @@ static bool __kvm_is_svm_supported(void) return false; } - rdmsrl(MSR_VM_CR, vm_cr); - if (vm_cr & (1 << SVM_VM_CR_SVM_DISABLE)) { - pr_err("SVM disabled (by BIOS) in MSR_VM_CR on CPU %d\n", cpu); - return false; - } - return true; } @@ -683,6 +665,21 @@ static int svm_hardware_enable(void) amd_pmu_enable_virt(); + /* + * If TSC_AUX virtualization is supported, TSC_AUX becomes a swap type + * "B" field (see sev_es_prepare_switch_to_guest()) for SEV-ES guests. + * Since Linux does not change the value of TSC_AUX once set, prime the + * TSC_AUX field now to avoid a RDMSR on every vCPU run. + */ + if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) { + struct sev_es_save_area *hostsa; + u32 __maybe_unused msr_hi; + + hostsa = (struct sev_es_save_area *)(page_address(sd->save_area) + 0x400); + + rdmsr(MSR_TSC_AUX, hostsa->tsc_aux, msr_hi); + } + return 0; } @@ -898,8 +895,7 @@ void svm_set_x2apic_msr_interception(struct vcpu_svm *svm, bool intercept) if (intercept == svm->x2avic_msrs_intercepted) return; - if (!x2avic_enabled || - !apic_x2apic_mode(svm->vcpu.arch.apic)) + if (!x2avic_enabled) return; for (i = 0; i < MAX_DIRECT_ACCESS_MSRS; i++) { @@ -1532,7 +1528,14 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) if (tsc_scaling) __svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio); - if (likely(tsc_aux_uret_slot >= 0)) + /* + * TSC_AUX is always virtualized for SEV-ES guests when the feature is + * available. The user return MSR support is not required in this case + * because TSC_AUX is restored on #VMEXIT from the host save area + * (which has been initialized in svm_hardware_enable()). + */ + if (likely(tsc_aux_uret_slot >= 0) && + (!boot_cpu_has(X86_FEATURE_V_TSC_AUX) || !sev_es_guest(vcpu->kvm))) kvm_set_user_return_msr(tsc_aux_uret_slot, svm->tsc_aux, -1ull); svm->guest_state_loaded = true; @@ -2181,12 +2184,6 @@ static int shutdown_interception(struct kvm_vcpu *vcpu) struct kvm_run *kvm_run = vcpu->run; struct vcpu_svm *svm = to_svm(vcpu); - /* - * The VM save area has already been encrypted so it - * cannot be reinitialized - just terminate. - */ - if (sev_es_guest(vcpu->kvm)) - return -EINVAL; /* * VMCB is undefined after a SHUTDOWN intercept. INIT the vCPU to put @@ -2195,9 +2192,14 @@ static int shutdown_interception(struct kvm_vcpu *vcpu) * userspace. At a platform view, INIT is acceptable behavior as * there exist bare metal platforms that automatically INIT the CPU * in response to shutdown. + * + * The VM save area for SEV-ES guests has already been encrypted so it + * cannot be reinitialized, i.e. synthesizing INIT is futile. */ - clear_page(svm->vmcb); - kvm_vcpu_reset(vcpu, true); + if (!sev_es_guest(vcpu->kvm)) { + clear_page(svm->vmcb); + kvm_vcpu_reset(vcpu, true); + } kvm_run->exit_reason = KVM_EXIT_SHUTDOWN; return 0; @@ -3087,6 +3089,16 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) break; case MSR_TSC_AUX: /* + * TSC_AUX is always virtualized for SEV-ES guests when the + * feature is available. The user return MSR support is not + * required in this case because TSC_AUX is restored on #VMEXIT + * from the host save area (which has been initialized in + * svm_hardware_enable()). + */ + if (boot_cpu_has(X86_FEATURE_V_TSC_AUX) && sev_es_guest(vcpu->kvm)) + break; + + /* * TSC_AUX is usually changed only during boot and never read * directly. Intercept TSC_AUX instead of exposing it to the * guest via direct_access_msrs, and switch it via user return. @@ -4284,7 +4296,6 @@ static bool svm_has_emulated_msr(struct kvm *kvm, u32 index) static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - struct kvm_cpuid_entry2 *best; /* * SVM doesn't provide a way to disable just XSAVES in the guest, KVM @@ -4328,12 +4339,8 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) set_msr_interception(vcpu, svm->msrpm, MSR_IA32_FLUSH_CMD, 0, !!guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D)); - /* For sev guests, the memory encryption bit is not reserved in CR3. */ - if (sev_guest(vcpu->kvm)) { - best = kvm_find_cpuid_entry(vcpu, 0x8000001F); - if (best) - vcpu->arch.reserved_gpa_bits &= ~(1UL << (best->ebx & 0x3f)); - } + if (sev_guest(vcpu->kvm)) + sev_vcpu_after_set_cpuid(svm); init_vmcb_after_set_cpuid(vcpu); } @@ -4701,15 +4708,15 @@ static void svm_enable_smi_window(struct kvm_vcpu *vcpu) } #endif -static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, - void *insn, int insn_len) +static int svm_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len) { bool smep, smap, is_user; u64 error_code; /* Emulation is always possible when KVM has access to all guest state. */ if (!sev_guest(vcpu->kvm)) - return true; + return X86EMUL_CONTINUE; /* #UD and #GP should never be intercepted for SEV guests. */ WARN_ON_ONCE(emul_type & (EMULTYPE_TRAP_UD | @@ -4721,14 +4728,14 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, * to guest register state. */ if (sev_es_guest(vcpu->kvm)) - return false; + return X86EMUL_RETRY_INSTR; /* * Emulation is possible if the instruction is already decoded, e.g. * when completing I/O after returning from userspace. */ if (emul_type & EMULTYPE_NO_DECODE) - return true; + return X86EMUL_CONTINUE; /* * Emulation is possible for SEV guests if and only if a prefilled @@ -4754,9 +4761,11 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, * success (and in practice it will work the vast majority of the time). */ if (unlikely(!insn)) { - if (!(emul_type & EMULTYPE_SKIP)) - kvm_queue_exception(vcpu, UD_VECTOR); - return false; + if (emul_type & EMULTYPE_SKIP) + return X86EMUL_UNHANDLEABLE; + + kvm_queue_exception(vcpu, UD_VECTOR); + return X86EMUL_PROPAGATE_FAULT; } /* @@ -4767,7 +4776,7 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, * table used to translate CS:RIP resides in emulated MMIO. */ if (likely(insn_len)) - return true; + return X86EMUL_CONTINUE; /* * Detect and workaround Errata 1096 Fam_17h_00_0Fh. @@ -4825,6 +4834,7 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, kvm_inject_gp(vcpu, 0); else kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); + return X86EMUL_PROPAGATE_FAULT; } resume_guest: @@ -4842,7 +4852,7 @@ resume_guest: * doesn't explicitly define "ignored", i.e. doing nothing and letting * the guest spin is technically "ignoring" the access. */ - return false; + return X86EMUL_RETRY_INSTR; } static bool svm_apic_init_signal_blocked(struct kvm_vcpu *vcpu) @@ -5002,7 +5012,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .vm_copy_enc_context_from = sev_vm_copy_enc_context_from, .vm_move_enc_context_from = sev_vm_move_enc_context_from, - .can_emulate_instruction = svm_can_emulate_instruction, + .check_emulate_instruction = svm_check_emulate_instruction, .apic_init_signal_blocked = svm_apic_init_signal_blocked, diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index f41253958357..be67ab7fdd10 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -684,6 +684,7 @@ void __init sev_hardware_setup(void); void sev_hardware_unsetup(void); int sev_cpu_init(struct svm_cpu_data *sd); void sev_init_vmcb(struct vcpu_svm *svm); +void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm); void sev_free_vcpu(struct kvm_vcpu *vcpu); int sev_handle_vmgexit(struct kvm_vcpu *vcpu); int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in); diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index f2efa0bf7ae8..820d3e1f6b4f 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -436,11 +436,11 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!msr_info->host_initiated && !(msr & MSR_PMC_FULL_WIDTH_BIT)) data = (s64)(s32)data; - pmc->counter += data - pmc_read_counter(pmc); + pmc_write_counter(pmc, data); pmc_update_sample_period(pmc); break; } else if ((pmc = get_fixed_pmc(pmu, msr))) { - pmc->counter += data - pmc_read_counter(pmc); + pmc_write_counter(pmc, data); pmc_update_sample_period(pmc); break; } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 72e3943f3693..be20a60047b1 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -82,28 +82,28 @@ bool __read_mostly enable_vpid = 1; module_param_named(vpid, enable_vpid, bool, 0444); static bool __read_mostly enable_vnmi = 1; -module_param_named(vnmi, enable_vnmi, bool, S_IRUGO); +module_param_named(vnmi, enable_vnmi, bool, 0444); bool __read_mostly flexpriority_enabled = 1; -module_param_named(flexpriority, flexpriority_enabled, bool, S_IRUGO); +module_param_named(flexpriority, flexpriority_enabled, bool, 0444); bool __read_mostly enable_ept = 1; -module_param_named(ept, enable_ept, bool, S_IRUGO); +module_param_named(ept, enable_ept, bool, 0444); bool __read_mostly enable_unrestricted_guest = 1; module_param_named(unrestricted_guest, - enable_unrestricted_guest, bool, S_IRUGO); + enable_unrestricted_guest, bool, 0444); bool __read_mostly enable_ept_ad_bits = 1; -module_param_named(eptad, enable_ept_ad_bits, bool, S_IRUGO); +module_param_named(eptad, enable_ept_ad_bits, bool, 0444); static bool __read_mostly emulate_invalid_guest_state = true; -module_param(emulate_invalid_guest_state, bool, S_IRUGO); +module_param(emulate_invalid_guest_state, bool, 0444); static bool __read_mostly fasteoi = 1; -module_param(fasteoi, bool, S_IRUGO); +module_param(fasteoi, bool, 0444); -module_param(enable_apicv, bool, S_IRUGO); +module_param(enable_apicv, bool, 0444); bool __read_mostly enable_ipiv = true; module_param(enable_ipiv, bool, 0444); @@ -114,10 +114,10 @@ module_param(enable_ipiv, bool, 0444); * use VMX instructions. */ static bool __read_mostly nested = 1; -module_param(nested, bool, S_IRUGO); +module_param(nested, bool, 0444); bool __read_mostly enable_pml = 1; -module_param_named(pml, enable_pml, bool, S_IRUGO); +module_param_named(pml, enable_pml, bool, 0444); static bool __read_mostly error_on_inconsistent_vmcs_config = true; module_param(error_on_inconsistent_vmcs_config, bool, 0444); @@ -1657,8 +1657,8 @@ static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data) return 0; } -static bool vmx_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, - void *insn, int insn_len) +static int vmx_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len) { /* * Emulation of instructions in SGX enclaves is impossible as RIP does @@ -1669,9 +1669,9 @@ static bool vmx_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, */ if (to_vmx(vcpu)->exit_reason.enclave_mode) { kvm_queue_exception(vcpu, UD_VECTOR); - return false; + return X86EMUL_PROPAGATE_FAULT; } - return true; + return X86EMUL_CONTINUE; } static int skip_emulated_instruction(struct kvm_vcpu *vcpu) @@ -5792,7 +5792,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) { gpa_t gpa; - if (!vmx_can_emulate_instruction(vcpu, EMULTYPE_PF, NULL, 0)) + if (vmx_check_emulate_instruction(vcpu, EMULTYPE_PF, NULL, 0)) return 1; /* @@ -6912,7 +6912,7 @@ static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) vmcs_write64(EOI_EXIT_BITMAP3, eoi_exit_bitmap[3]); } -static void vmx_apicv_post_state_restore(struct kvm_vcpu *vcpu) +static void vmx_apicv_pre_state_restore(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -7579,8 +7579,6 @@ static int vmx_vm_init(struct kvm *kvm) static u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) { - u8 cache; - /* We wanted to honor guest CD/MTRR/PAT, but doing so could result in * memory aliases with conflicting memory types and sometimes MCEs. * We have to be careful as to what are honored and when. @@ -7607,11 +7605,10 @@ static u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) if (kvm_read_cr0_bits(vcpu, X86_CR0_CD)) { if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) - cache = MTRR_TYPE_WRBACK; + return MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT; else - cache = MTRR_TYPE_UNCACHABLE; - - return (cache << VMX_EPT_MT_EPTE_SHIFT) | VMX_EPT_IPAT_BIT; + return (MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT) | + VMX_EPT_IPAT_BIT; } return kvm_mtrr_get_guest_memory_type(vcpu, gfn) << VMX_EPT_MT_EPTE_SHIFT; @@ -8286,7 +8283,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .set_apic_access_page_addr = vmx_set_apic_access_page_addr, .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, .load_eoi_exitmap = vmx_load_eoi_exitmap, - .apicv_post_state_restore = vmx_apicv_post_state_restore, + .apicv_pre_state_restore = vmx_apicv_pre_state_restore, .required_apicv_inhibits = VMX_REQUIRED_APICV_INHIBITS, .hwapic_irr_update = vmx_hwapic_irr_update, .hwapic_isr_update = vmx_hwapic_isr_update, @@ -8341,7 +8338,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .enable_smi_window = vmx_enable_smi_window, #endif - .can_emulate_instruction = vmx_can_emulate_instruction, + .check_emulate_instruction = vmx_check_emulate_instruction, .apic_init_signal_blocked = vmx_apic_init_signal_blocked, .migrate_timers = vmx_migrate_timers, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 6c9c81e82e65..2c924075f6f1 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -145,21 +145,21 @@ EXPORT_STATIC_CALL_GPL(kvm_x86_get_cs_db_l_bits); EXPORT_STATIC_CALL_GPL(kvm_x86_cache_reg); static bool __read_mostly ignore_msrs = 0; -module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR); +module_param(ignore_msrs, bool, 0644); bool __read_mostly report_ignored_msrs = true; -module_param(report_ignored_msrs, bool, S_IRUGO | S_IWUSR); +module_param(report_ignored_msrs, bool, 0644); EXPORT_SYMBOL_GPL(report_ignored_msrs); unsigned int min_timer_period_us = 200; -module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR); +module_param(min_timer_period_us, uint, 0644); static bool __read_mostly kvmclock_periodic_sync = true; -module_param(kvmclock_periodic_sync, bool, S_IRUGO); +module_param(kvmclock_periodic_sync, bool, 0444); /* tsc tolerance in parts per million - default to 1/2 of the NTP threshold */ static u32 __read_mostly tsc_tolerance_ppm = 250; -module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR); +module_param(tsc_tolerance_ppm, uint, 0644); /* * lapic timer advance (tscdeadline mode only) in nanoseconds. '-1' enables @@ -168,13 +168,13 @@ module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR); * tuning, i.e. allows privileged userspace to set an exact advancement time. */ static int __read_mostly lapic_timer_advance_ns = -1; -module_param(lapic_timer_advance_ns, int, S_IRUGO | S_IWUSR); +module_param(lapic_timer_advance_ns, int, 0644); static bool __read_mostly vector_hashing = true; -module_param(vector_hashing, bool, S_IRUGO); +module_param(vector_hashing, bool, 0444); bool __read_mostly enable_vmware_backdoor = false; -module_param(enable_vmware_backdoor, bool, S_IRUGO); +module_param(enable_vmware_backdoor, bool, 0444); EXPORT_SYMBOL_GPL(enable_vmware_backdoor); /* @@ -186,7 +186,7 @@ static int __read_mostly force_emulation_prefix; module_param(force_emulation_prefix, int, 0644); int __read_mostly pi_inject_timer = -1; -module_param(pi_inject_timer, bint, S_IRUGO | S_IWUSR); +module_param(pi_inject_timer, bint, 0644); /* Enable/disable PMU virtualization */ bool __read_mostly enable_pmu = true; @@ -962,7 +962,7 @@ void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned lon kvm_mmu_reset_context(vcpu); if (((cr0 ^ old_cr0) & X86_CR0_CD) && - kvm_arch_has_noncoherent_dma(vcpu->kvm) && + kvm_mmu_honors_guest_mtrrs(vcpu->kvm) && !kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) kvm_zap_gfn_range(vcpu->kvm, 0, ~0ULL); } @@ -2331,14 +2331,9 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock, int sec_hi_o if (kvm_write_guest(kvm, wall_clock, &version, sizeof(version))) return; - /* - * The guest calculates current wall clock time by adding - * system time (updated by kvm_guest_time_update below) to the - * wall clock specified here. We do the reverse here. - */ - wall_nsec = ktime_get_real_ns() - get_kvmclock_ns(kvm); + wall_nsec = kvm_get_wall_clock_epoch(kvm); - wc.nsec = do_div(wall_nsec, 1000000000); + wc.nsec = do_div(wall_nsec, NSEC_PER_SEC); wc.sec = (u32)wall_nsec; /* overflow in 2106 guest time */ wc.version = version; @@ -2714,8 +2709,9 @@ static void __kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 offset, u64 tsc, kvm_track_tsc_matching(vcpu); } -static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data) +static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 *user_value) { + u64 data = user_value ? *user_value : 0; struct kvm *kvm = vcpu->kvm; u64 offset, ns, elapsed; unsigned long flags; @@ -2730,25 +2726,37 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data) if (vcpu->arch.virtual_tsc_khz) { if (data == 0) { /* - * detection of vcpu initialization -- need to sync - * with other vCPUs. This particularly helps to keep - * kvm_clock stable after CPU hotplug + * Force synchronization when creating a vCPU, or when + * userspace explicitly writes a zero value. */ synchronizing = true; - } else { + } else if (kvm->arch.user_set_tsc) { u64 tsc_exp = kvm->arch.last_tsc_write + nsec_to_cycles(vcpu, elapsed); u64 tsc_hz = vcpu->arch.virtual_tsc_khz * 1000LL; /* - * Special case: TSC write with a small delta (1 second) - * of virtual cycle time against real time is - * interpreted as an attempt to synchronize the CPU. + * Here lies UAPI baggage: when a user-initiated TSC write has + * a small delta (1 second) of virtual cycle time against the + * previously set vCPU, we assume that they were intended to be + * in sync and the delta was only due to the racy nature of the + * legacy API. + * + * This trick falls down when restoring a guest which genuinely + * has been running for less time than the 1 second of imprecision + * which we allow for in the legacy API. In this case, the first + * value written by userspace (on any vCPU) should not be subject + * to this 'correction' to make it sync up with values that only + * come from the kernel's default vCPU creation. Make the 1-second + * slop hack only trigger if the user_set_tsc flag is already set. */ synchronizing = data < tsc_exp + tsc_hz && data + tsc_hz > tsc_exp; } } + if (user_value) + kvm->arch.user_set_tsc = true; + /* * For a reliable TSC, we can match TSC offsets, and for an unstable * TSC, we add elapsed time in this computation. We could let the @@ -3232,16 +3240,94 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) if (vcpu->pv_time.active) kvm_setup_guest_pvclock(v, &vcpu->pv_time, 0); +#ifdef CONFIG_KVM_XEN if (vcpu->xen.vcpu_info_cache.active) kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_info_cache, offsetof(struct compat_vcpu_info, time)); if (vcpu->xen.vcpu_time_info_cache.active) kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_time_info_cache, 0); +#endif kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock); return 0; } /* + * The pvclock_wall_clock ABI tells the guest the wall clock time at + * which it started (i.e. its epoch, when its kvmclock was zero). + * + * In fact those clocks are subtly different; wall clock frequency is + * adjusted by NTP and has leap seconds, while the kvmclock is a + * simple function of the TSC without any such adjustment. + * + * Perhaps the ABI should have exposed CLOCK_TAI and a ratio between + * that and kvmclock, but even that would be subject to change over + * time. + * + * Attempt to calculate the epoch at a given moment using the *same* + * TSC reading via kvm_get_walltime_and_clockread() to obtain both + * wallclock and kvmclock times, and subtracting one from the other. + * + * Fall back to using their values at slightly different moments by + * calling ktime_get_real_ns() and get_kvmclock_ns() separately. + */ +uint64_t kvm_get_wall_clock_epoch(struct kvm *kvm) +{ +#ifdef CONFIG_X86_64 + struct pvclock_vcpu_time_info hv_clock; + struct kvm_arch *ka = &kvm->arch; + unsigned long seq, local_tsc_khz; + struct timespec64 ts; + uint64_t host_tsc; + + do { + seq = read_seqcount_begin(&ka->pvclock_sc); + + local_tsc_khz = 0; + if (!ka->use_master_clock) + break; + + /* + * The TSC read and the call to get_cpu_tsc_khz() must happen + * on the same CPU. + */ + get_cpu(); + + local_tsc_khz = get_cpu_tsc_khz(); + + if (local_tsc_khz && + !kvm_get_walltime_and_clockread(&ts, &host_tsc)) + local_tsc_khz = 0; /* Fall back to old method */ + + put_cpu(); + + /* + * These values must be snapshotted within the seqcount loop. + * After that, it's just mathematics which can happen on any + * CPU at any time. + */ + hv_clock.tsc_timestamp = ka->master_cycle_now; + hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset; + + } while (read_seqcount_retry(&ka->pvclock_sc, seq)); + + /* + * If the conditions were right, and obtaining the wallclock+TSC was + * successful, calculate the KVM clock at the corresponding time and + * subtract one from the other to get the guest's epoch in nanoseconds + * since 1970-01-01. + */ + if (local_tsc_khz) { + kvm_get_time_scale(NSEC_PER_SEC, local_tsc_khz * NSEC_PER_USEC, + &hv_clock.tsc_shift, + &hv_clock.tsc_to_system_mul); + return ts.tv_nsec + NSEC_PER_SEC * ts.tv_sec - + __pvclock_read_cycles(&hv_clock, host_tsc); + } +#endif + return ktime_get_real_ns() - get_kvmclock_ns(kvm); +} + +/* * kvmclock updates which are isolated to a given vcpu, such as * vcpu->cpu migration, should not allow system_timestamp from * the rest of the vcpus to remain static. Otherwise ntp frequency @@ -3290,9 +3376,6 @@ static void kvmclock_sync_fn(struct work_struct *work) kvmclock_sync_work); struct kvm *kvm = container_of(ka, struct kvm, arch); - if (!kvmclock_periodic_sync) - return; - schedule_delayed_work(&kvm->arch.kvmclock_update_work, 0); schedule_delayed_work(&kvm->arch.kvmclock_sync_work, KVMCLOCK_SYNC_PERIOD); @@ -3641,6 +3724,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_AMD64_PATCH_LOADER: case MSR_AMD64_BU_CFG2: case MSR_AMD64_DC_CFG: + case MSR_AMD64_TW_CFG: case MSR_F15H_EX_CFG: break; @@ -3670,17 +3754,36 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vcpu->arch.perf_capabilities = data; kvm_pmu_refresh(vcpu); break; - case MSR_IA32_PRED_CMD: - if (!msr_info->host_initiated && !guest_has_pred_cmd_msr(vcpu)) - return 1; + case MSR_IA32_PRED_CMD: { + u64 reserved_bits = ~(PRED_CMD_IBPB | PRED_CMD_SBPB); + + if (!msr_info->host_initiated) { + if ((!guest_has_pred_cmd_msr(vcpu))) + return 1; + + if (!guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) && + !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBPB)) + reserved_bits |= PRED_CMD_IBPB; + + if (!guest_cpuid_has(vcpu, X86_FEATURE_SBPB)) + reserved_bits |= PRED_CMD_SBPB; + } + + if (!boot_cpu_has(X86_FEATURE_IBPB)) + reserved_bits |= PRED_CMD_IBPB; - if (!boot_cpu_has(X86_FEATURE_IBPB) || (data & ~PRED_CMD_IBPB)) + if (!boot_cpu_has(X86_FEATURE_SBPB)) + reserved_bits |= PRED_CMD_SBPB; + + if (data & reserved_bits) return 1; + if (!data) break; - wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); + wrmsrl(MSR_IA32_PRED_CMD, data); break; + } case MSR_IA32_FLUSH_CMD: if (!msr_info->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D)) @@ -3700,13 +3803,16 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) data &= ~(u64)0x100; /* ignore ignne emulation enable */ data &= ~(u64)0x8; /* ignore TLB cache disable */ - /* Handle McStatusWrEn */ - if (data == BIT_ULL(18)) { - vcpu->arch.msr_hwcr = data; - } else if (data != 0) { + /* + * Allow McStatusWrEn and TscFreqSel. (Linux guests from v3.2 + * through at least v6.6 whine if TscFreqSel is clear, + * depending on F/M/S. + */ + if (data & ~(BIT_ULL(18) | BIT_ULL(24))) { kvm_pr_unimpl_wrmsr(vcpu, msr, data); return 1; } + vcpu->arch.msr_hwcr = data; break; case MSR_FAM10H_MMIO_CONF_BASE: if (data != 0) { @@ -3777,7 +3883,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_TSC: if (msr_info->host_initiated) { - kvm_synchronize_tsc(vcpu, data); + kvm_synchronize_tsc(vcpu, &data); } else { u64 adj = kvm_compute_l1_tsc_offset(vcpu, data) - vcpu->arch.l1_tsc_offset; adjust_tsc_offset_guest(vcpu, adj); @@ -4065,6 +4171,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_AMD64_BU_CFG2: case MSR_IA32_PERF_CTL: case MSR_AMD64_DC_CFG: + case MSR_AMD64_TW_CFG: case MSR_F15H_EX_CFG: /* * Intel Sandy Bridge CPUs must support the RAPL (running average power @@ -5382,26 +5489,37 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, return 0; } -static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, - struct kvm_xsave *guest_xsave) -{ - if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) - return; - - fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, - guest_xsave->region, - sizeof(guest_xsave->region), - vcpu->arch.pkru); -} static void kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu, u8 *state, unsigned int size) { + /* + * Only copy state for features that are enabled for the guest. The + * state itself isn't problematic, but setting bits in the header for + * features that are supported in *this* host but not exposed to the + * guest can result in KVM_SET_XSAVE failing when live migrating to a + * compatible host without the features that are NOT exposed to the + * guest. + * + * FP+SSE can always be saved/restored via KVM_{G,S}ET_XSAVE, even if + * XSAVE/XCRO are not exposed to the guest, and even if XSAVE isn't + * supported by the host. + */ + u64 supported_xcr0 = vcpu->arch.guest_supported_xcr0 | + XFEATURE_MASK_FPSSE; + if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) return; - fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, - state, size, vcpu->arch.pkru); + fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, state, size, + supported_xcr0, vcpu->arch.pkru); +} + +static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, + struct kvm_xsave *guest_xsave) +{ + return kvm_vcpu_ioctl_x86_get_xsave2(vcpu, (void *)guest_xsave->region, + sizeof(guest_xsave->region)); } static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, @@ -5536,6 +5654,7 @@ static int kvm_arch_tsc_set_attr(struct kvm_vcpu *vcpu, tsc = kvm_scale_tsc(rdtsc(), vcpu->arch.l1_tsc_scaling_ratio) + offset; ns = get_kvmclock_base_ns(); + kvm->arch.user_set_tsc = true; __kvm_synchronize_tsc(vcpu, offset, tsc, ns, matched); raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); @@ -6248,6 +6367,9 @@ void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) struct kvm_vcpu *vcpu; unsigned long i; + if (!kvm_x86_ops.cpu_dirty_log_size) + return; + kvm_for_each_vcpu(i, vcpu, kvm) kvm_vcpu_kick(vcpu); } @@ -7474,11 +7596,11 @@ int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu, gva_t addr, void *val, } EXPORT_SYMBOL_GPL(kvm_write_guest_virt_system); -static int kvm_can_emulate_insn(struct kvm_vcpu *vcpu, int emul_type, - void *insn, int insn_len) +static int kvm_check_emulate_insn(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len) { - return static_call(kvm_x86_can_emulate_instruction)(vcpu, emul_type, - insn, insn_len); + return static_call(kvm_x86_check_emulate_instruction)(vcpu, emul_type, + insn, insn_len); } int handle_ud(struct kvm_vcpu *vcpu) @@ -7488,8 +7610,10 @@ int handle_ud(struct kvm_vcpu *vcpu) int emul_type = EMULTYPE_TRAP_UD; char sig[5]; /* ud2; .ascii "kvm" */ struct x86_exception e; + int r; - if (unlikely(!kvm_can_emulate_insn(vcpu, emul_type, NULL, 0))) + r = kvm_check_emulate_insn(vcpu, emul_type, NULL, 0); + if (r != X86EMUL_CONTINUE) return 1; if (fep_flags && @@ -8871,8 +8995,14 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; bool writeback = true; - if (unlikely(!kvm_can_emulate_insn(vcpu, emulation_type, insn, insn_len))) - return 1; + r = kvm_check_emulate_insn(vcpu, emulation_type, insn, insn_len); + if (r != X86EMUL_CONTINUE) { + if (r == X86EMUL_RETRY_INSTR || r == X86EMUL_PROPAGATE_FAULT) + return 1; + + WARN_ON_ONCE(r != X86EMUL_UNHANDLEABLE); + return handle_emulation_failure(vcpu, emulation_type); + } vcpu->arch.l1tf_flush_l1d = true; @@ -10576,16 +10706,16 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) } if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu)) record_steal_time(vcpu); + if (kvm_check_request(KVM_REQ_PMU, vcpu)) + kvm_pmu_handle_event(vcpu); + if (kvm_check_request(KVM_REQ_PMI, vcpu)) + kvm_pmu_deliver_pmi(vcpu); #ifdef CONFIG_KVM_SMM if (kvm_check_request(KVM_REQ_SMI, vcpu)) process_smi(vcpu); #endif if (kvm_check_request(KVM_REQ_NMI, vcpu)) process_nmi(vcpu); - if (kvm_check_request(KVM_REQ_PMU, vcpu)) - kvm_pmu_handle_event(vcpu); - if (kvm_check_request(KVM_REQ_PMI, vcpu)) - kvm_pmu_deliver_pmi(vcpu); if (kvm_check_request(KVM_REQ_IOAPIC_EOI_EXIT, vcpu)) { BUG_ON(vcpu->arch.pending_ioapic_eoi > 255); if (test_bit(vcpu->arch.pending_ioapic_eoi, @@ -11521,7 +11651,6 @@ static int __set_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs, *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; static_call(kvm_x86_set_cr4)(vcpu, sregs->cr4); @@ -11565,8 +11694,10 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) if (ret) return ret; - if (mmu_reset_needed) + if (mmu_reset_needed) { kvm_mmu_reset_context(vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); + } max_bits = KVM_NR_INTERRUPTS; pending_vec = find_first_bit( @@ -11607,8 +11738,10 @@ static int __set_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2) mmu_reset_needed = 1; vcpu->arch.pdptrs_from_userspace = true; } - if (mmu_reset_needed) + if (mmu_reset_needed) { kvm_mmu_reset_context(vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); + } return 0; } @@ -11959,7 +12092,7 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) if (mutex_lock_killable(&vcpu->mutex)) return; vcpu_load(vcpu); - kvm_synchronize_tsc(vcpu, 0); + kvm_synchronize_tsc(vcpu, NULL); vcpu_put(vcpu); /* poll control enabled by default */ @@ -12308,16 +12441,13 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) if (ret) goto out; - ret = kvm_mmu_init_vm(kvm); - if (ret) - goto out_page_track; + kvm_mmu_init_vm(kvm); ret = static_call(kvm_x86_vm_init)(kvm); if (ret) goto out_uninit_mmu; INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list); - INIT_LIST_HEAD(&kvm->arch.assigned_dev_head); atomic_set(&kvm->arch.noncoherent_dma_count, 0); /* Reserve bit 0 of irq_sources_bitmap for userspace irq source */ @@ -12355,7 +12485,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) out_uninit_mmu: kvm_mmu_uninit_vm(kvm); -out_page_track: kvm_page_track_cleanup(kvm); out: return ret; @@ -12846,6 +12975,9 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) return true; #endif + if (kvm_test_request(KVM_REQ_PMI, vcpu)) + return true; + if (kvm_arch_interrupt_allowed(vcpu) && (kvm_cpu_has_interrupt(vcpu) || kvm_guest_apic_has_interrupt(vcpu))) @@ -13191,15 +13323,30 @@ bool noinstr kvm_arch_has_assigned_device(struct kvm *kvm) } EXPORT_SYMBOL_GPL(kvm_arch_has_assigned_device); +static void kvm_noncoherent_dma_assignment_start_or_stop(struct kvm *kvm) +{ + /* + * Non-coherent DMA assignment and de-assignment will affect + * whether KVM honors guest MTRRs and cause changes in memtypes + * in TDP. + * So, pass %true unconditionally to indicate non-coherent DMA was, + * or will be involved, and that zapping SPTEs might be necessary. + */ + if (__kvm_mmu_honors_guest_mtrrs(true)) + kvm_zap_gfn_range(kvm, gpa_to_gfn(0), gpa_to_gfn(~0ULL)); +} + void kvm_arch_register_noncoherent_dma(struct kvm *kvm) { - atomic_inc(&kvm->arch.noncoherent_dma_count); + if (atomic_inc_return(&kvm->arch.noncoherent_dma_count) == 1) + kvm_noncoherent_dma_assignment_start_or_stop(kvm); } EXPORT_SYMBOL_GPL(kvm_arch_register_noncoherent_dma); void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm) { - atomic_dec(&kvm->arch.noncoherent_dma_count); + if (!atomic_dec_return(&kvm->arch.noncoherent_dma_count)) + kvm_noncoherent_dma_assignment_start_or_stop(kvm); } EXPORT_SYMBOL_GPL(kvm_arch_unregister_noncoherent_dma); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 1e7be1f6ab29..5184fde1dc54 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -293,6 +293,7 @@ static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk) void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip); u64 get_kvmclock_ns(struct kvm *kvm); +uint64_t kvm_get_wall_clock_epoch(struct kvm *kvm); int kvm_read_guest_virt(struct kvm_vcpu *vcpu, gva_t addr, void *val, unsigned int bytes, diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 40edf4d1974c..e53fad915a62 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -59,7 +59,7 @@ static int kvm_xen_shared_info_init(struct kvm *kvm, gfn_t gfn) * This code mirrors kvm_write_wall_clock() except that it writes * directly through the pfn cache and doesn't mark the page dirty. */ - wall_nsec = ktime_get_real_ns() - get_kvmclock_ns(kvm); + wall_nsec = kvm_get_wall_clock_epoch(kvm); /* It could be invalid again already, so we need to check */ read_lock_irq(&gpc->lock); @@ -98,7 +98,7 @@ static int kvm_xen_shared_info_init(struct kvm *kvm, gfn_t gfn) wc_version = wc->version = (wc->version + 1) | 1; smp_wmb(); - wc->nsec = do_div(wall_nsec, 1000000000); + wc->nsec = do_div(wall_nsec, NSEC_PER_SEC); wc->sec = (u32)wall_nsec; *wc_sec_hi = wall_nsec >> 32; smp_wmb(); @@ -134,9 +134,23 @@ static enum hrtimer_restart xen_timer_callback(struct hrtimer *timer) { struct kvm_vcpu *vcpu = container_of(timer, struct kvm_vcpu, arch.xen.timer); + struct kvm_xen_evtchn e; + int rc; + if (atomic_read(&vcpu->arch.xen.timer_pending)) return HRTIMER_NORESTART; + e.vcpu_id = vcpu->vcpu_id; + e.vcpu_idx = vcpu->vcpu_idx; + e.port = vcpu->arch.xen.timer_virq; + e.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL; + + rc = kvm_xen_set_evtchn_fast(&e, vcpu->kvm); + if (rc != -EWOULDBLOCK) { + vcpu->arch.xen.timer_expires = 0; + return HRTIMER_NORESTART; + } + atomic_inc(&vcpu->arch.xen.timer_pending); kvm_make_request(KVM_REQ_UNBLOCK, vcpu); kvm_vcpu_kick(vcpu); @@ -146,6 +160,14 @@ static enum hrtimer_restart xen_timer_callback(struct hrtimer *timer) static void kvm_xen_start_timer(struct kvm_vcpu *vcpu, u64 guest_abs, s64 delta_ns) { + /* + * Avoid races with the old timer firing. Checking timer_expires + * to avoid calling hrtimer_cancel() will only have false positives + * so is fine. + */ + if (vcpu->arch.xen.timer_expires) + hrtimer_cancel(&vcpu->arch.xen.timer); + atomic_set(&vcpu->arch.xen.timer_pending, 0); vcpu->arch.xen.timer_expires = guest_abs; @@ -1019,9 +1041,36 @@ int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) break; case KVM_XEN_VCPU_ATTR_TYPE_TIMER: + /* + * Ensure a consistent snapshot of state is captured, with a + * timer either being pending, or the event channel delivered + * to the corresponding bit in the shared_info. Not still + * lurking in the timer_pending flag for deferred delivery. + * Purely as an optimisation, if the timer_expires field is + * zero, that means the timer isn't active (or even in the + * timer_pending flag) and there is no need to cancel it. + */ + if (vcpu->arch.xen.timer_expires) { + hrtimer_cancel(&vcpu->arch.xen.timer); + kvm_xen_inject_timer_irqs(vcpu); + } + data->u.timer.port = vcpu->arch.xen.timer_virq; data->u.timer.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL; data->u.timer.expires_ns = vcpu->arch.xen.timer_expires; + + /* + * The hrtimer may trigger and raise the IRQ immediately, + * while the returned state causes it to be set up and + * raised again on the destination system after migration. + * That's fine, as the guest won't even have had a chance + * to run and handle the interrupt. Asserting an already + * pending event channel is idempotent. + */ + if (vcpu->arch.xen.timer_expires) + hrtimer_start_expires(&vcpu->arch.xen.timer, + HRTIMER_MODE_ABS_HARD); + r = 0; break; @@ -1374,12 +1423,8 @@ static bool kvm_xen_hcall_vcpu_op(struct kvm_vcpu *vcpu, bool longmode, int cmd, return true; } + /* A delta <= 0 results in an immediate callback, which is what we want */ delta = oneshot.timeout_abs_ns - get_kvmclock_ns(vcpu->kvm); - if ((oneshot.flags & VCPU_SSHOTTMR_future) && delta < 0) { - *r = -ETIME; - return true; - } - kvm_xen_start_timer(vcpu, oneshot.timeout_abs_ns, delta); *r = 0; return true; |