diff options
Diffstat (limited to 'arch/x86/kvm/x86.c')
| -rw-r--r-- | arch/x86/kvm/x86.c | 460 |
1 files changed, 324 insertions, 136 deletions
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 04c5d96b1d67..ccbd45ecd41a 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -54,6 +54,8 @@ #include <linux/pvclock_gtod.h> #include <linux/kvm_irqfd.h> #include <linux/irqbypass.h> +#include <linux/sched/stat.h> + #include <trace/events/kvm.h> #include <asm/debugreg.h> @@ -180,6 +182,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "insn_emulation_fail", VCPU_STAT(insn_emulation_fail) }, { "irq_injections", VCPU_STAT(irq_injections) }, { "nmi_injections", VCPU_STAT(nmi_injections) }, + { "req_event", VCPU_STAT(req_event) }, { "mmu_shadow_zapped", VM_STAT(mmu_shadow_zapped) }, { "mmu_pte_write", VM_STAT(mmu_pte_write) }, { "mmu_pte_updated", VM_STAT(mmu_pte_updated) }, @@ -190,6 +193,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "mmu_unsync", VM_STAT(mmu_unsync) }, { "remote_tlb_flush", VM_STAT(remote_tlb_flush) }, { "largepages", VM_STAT(lpages) }, + { "max_mmu_page_hash_collisions", + VM_STAT(max_mmu_page_hash_collisions) }, { NULL } }; @@ -434,12 +439,14 @@ void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr) } EXPORT_SYMBOL_GPL(kvm_requeue_exception); -void kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err) +int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err) { if (err) kvm_inject_gp(vcpu, 0); else - kvm_x86_ops->skip_emulated_instruction(vcpu); + return kvm_skip_emulated_instruction(vcpu); + + return 1; } EXPORT_SYMBOL_GPL(kvm_complete_insn_gp); @@ -573,7 +580,7 @@ out: } EXPORT_SYMBOL_GPL(load_pdptrs); -static bool pdptrs_changed(struct kvm_vcpu *vcpu) +bool pdptrs_changed(struct kvm_vcpu *vcpu) { u64 pdpte[ARRAY_SIZE(vcpu->arch.walk_mmu->pdptrs)]; bool changed = true; @@ -599,6 +606,7 @@ out: return changed; } +EXPORT_SYMBOL_GPL(pdptrs_changed); int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { @@ -1128,14 +1136,15 @@ struct pvclock_gtod_data { struct { /* extract of a clocksource struct */ int vclock_mode; - cycle_t cycle_last; - cycle_t mask; + u64 cycle_last; + u64 mask; u32 mult; u32 shift; } clock; u64 boot_ns; u64 nsec_base; + u64 wall_time_sec; }; static struct pvclock_gtod_data pvclock_gtod_data; @@ -1159,6 +1168,8 @@ static void update_pvclock_gtod(struct timekeeper *tk) vdata->boot_ns = boot_ns; vdata->nsec_base = tk->tkr_mono.xtime_nsec; + vdata->wall_time_sec = tk->xtime_sec; + write_seqcount_end(&vdata->seq); } #endif @@ -1569,9 +1580,9 @@ static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment) #ifdef CONFIG_X86_64 -static cycle_t read_tsc(void) +static u64 read_tsc(void) { - cycle_t ret = (cycle_t)rdtsc_ordered(); + u64 ret = (u64)rdtsc_ordered(); u64 last = pvclock_gtod_data.clock.cycle_last; if (likely(ret >= last)) @@ -1589,7 +1600,7 @@ static cycle_t read_tsc(void) return last; } -static inline u64 vgettsc(cycle_t *cycle_now) +static inline u64 vgettsc(u64 *cycle_now) { long v; struct pvclock_gtod_data *gtod = &pvclock_gtod_data; @@ -1600,7 +1611,7 @@ static inline u64 vgettsc(cycle_t *cycle_now) return v * gtod->clock.mult; } -static int do_monotonic_boot(s64 *t, cycle_t *cycle_now) +static int do_monotonic_boot(s64 *t, u64 *cycle_now) { struct pvclock_gtod_data *gtod = &pvclock_gtod_data; unsigned long seq; @@ -1620,8 +1631,30 @@ static int do_monotonic_boot(s64 *t, cycle_t *cycle_now) return mode; } +static int do_realtime(struct timespec *ts, u64 *cycle_now) +{ + struct pvclock_gtod_data *gtod = &pvclock_gtod_data; + unsigned long seq; + int mode; + u64 ns; + + do { + seq = read_seqcount_begin(>od->seq); + mode = gtod->clock.vclock_mode; + ts->tv_sec = gtod->wall_time_sec; + ns = gtod->nsec_base; + ns += vgettsc(cycle_now); + ns >>= gtod->clock.shift; + } while (unlikely(read_seqcount_retry(>od->seq, seq))); + + ts->tv_sec += __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns); + ts->tv_nsec = ns; + + return mode; +} + /* returns true if host is using tsc clocksource */ -static bool kvm_get_time_and_clockread(s64 *kernel_ns, cycle_t *cycle_now) +static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *cycle_now) { /* checked again under seqlock below */ if (pvclock_gtod_data.clock.vclock_mode != VCLOCK_TSC) @@ -1629,6 +1662,17 @@ static bool kvm_get_time_and_clockread(s64 *kernel_ns, cycle_t *cycle_now) return do_monotonic_boot(kernel_ns, cycle_now) == VCLOCK_TSC; } + +/* returns true if host is using tsc clocksource */ +static bool kvm_get_walltime_and_clockread(struct timespec *ts, + u64 *cycle_now) +{ + /* checked again under seqlock below */ + if (pvclock_gtod_data.clock.vclock_mode != VCLOCK_TSC) + return false; + + return do_realtime(ts, cycle_now) == VCLOCK_TSC; +} #endif /* @@ -1769,7 +1813,7 @@ static void kvm_setup_pvclock_page(struct kvm_vcpu *v) struct kvm_vcpu_arch *vcpu = &v->arch; struct pvclock_vcpu_time_info guest_hv_clock; - if (unlikely(kvm_read_guest_cached(v->kvm, &vcpu->pv_time, + if (unlikely(kvm_vcpu_read_guest_cached(v, &vcpu->pv_time, &guest_hv_clock, sizeof(guest_hv_clock)))) return; @@ -1790,9 +1834,9 @@ static void kvm_setup_pvclock_page(struct kvm_vcpu *v) BUILD_BUG_ON(offsetof(struct pvclock_vcpu_time_info, version) != 0); vcpu->hv_clock.version = guest_hv_clock.version + 1; - kvm_write_guest_cached(v->kvm, &vcpu->pv_time, - &vcpu->hv_clock, - sizeof(vcpu->hv_clock.version)); + kvm_vcpu_write_guest_cached(v, &vcpu->pv_time, + &vcpu->hv_clock, + sizeof(vcpu->hv_clock.version)); smp_wmb(); @@ -1806,16 +1850,16 @@ static void kvm_setup_pvclock_page(struct kvm_vcpu *v) trace_kvm_pvclock_update(v->vcpu_id, &vcpu->hv_clock); - kvm_write_guest_cached(v->kvm, &vcpu->pv_time, - &vcpu->hv_clock, - sizeof(vcpu->hv_clock)); + kvm_vcpu_write_guest_cached(v, &vcpu->pv_time, + &vcpu->hv_clock, + sizeof(vcpu->hv_clock)); smp_wmb(); vcpu->hv_clock.version++; - kvm_write_guest_cached(v->kvm, &vcpu->pv_time, - &vcpu->hv_clock, - sizeof(vcpu->hv_clock.version)); + kvm_vcpu_write_guest_cached(v, &vcpu->pv_time, + &vcpu->hv_clock, + sizeof(vcpu->hv_clock.version)); } static int kvm_guest_time_update(struct kvm_vcpu *v) @@ -2048,7 +2092,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) return 0; } - if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa, + if (kvm_vcpu_gfn_to_hva_cache_init(vcpu, &vcpu->arch.apf.data, gpa, sizeof(u32))) return 1; @@ -2067,16 +2111,18 @@ static void record_steal_time(struct kvm_vcpu *vcpu) if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; - if (unlikely(kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, + if (unlikely(kvm_vcpu_read_guest_cached(vcpu, &vcpu->arch.st.stime, &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)))) return; + vcpu->arch.st.steal.preempted = 0; + if (vcpu->arch.st.steal.version & 1) vcpu->arch.st.steal.version += 1; /* first time write, random junk */ vcpu->arch.st.steal.version += 1; - kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, + kvm_vcpu_write_guest_cached(vcpu, &vcpu->arch.st.stime, &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)); smp_wmb(); @@ -2085,14 +2131,14 @@ static void record_steal_time(struct kvm_vcpu *vcpu) vcpu->arch.st.last_steal; vcpu->arch.st.last_steal = current->sched_info.run_delay; - kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, + kvm_vcpu_write_guest_cached(vcpu, &vcpu->arch.st.stime, &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)); smp_wmb(); vcpu->arch.st.steal.version += 1; - kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, + kvm_vcpu_write_guest_cached(vcpu, &vcpu->arch.st.stime, &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)); } @@ -2176,7 +2222,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_KVM_SYSTEM_TIME_NEW: case MSR_KVM_SYSTEM_TIME: { - u64 gpa_offset; struct kvm_arch *ka = &vcpu->kvm->arch; kvmclock_reset(vcpu); @@ -2198,9 +2243,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!(data & 1)) break; - gpa_offset = data & ~(PAGE_MASK | 1); - - if (kvm_gfn_to_hva_cache_init(vcpu->kvm, + if (kvm_vcpu_gfn_to_hva_cache_init(vcpu, &vcpu->arch.pv_time, data & ~1ULL, sizeof(struct pvclock_vcpu_time_info))) vcpu->arch.pv_time_enabled = false; @@ -2221,7 +2264,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (data & KVM_STEAL_RESERVED_MASK) return 1; - if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.st.stime, + if (kvm_vcpu_gfn_to_hva_cache_init(vcpu, &vcpu->arch.st.stime, data & KVM_STEAL_VALID_BITS, sizeof(struct kvm_steal_time))) return 1; @@ -2294,7 +2337,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (kvm_pmu_is_valid_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr_info); if (!ignore_msrs) { - vcpu_unimpl(vcpu, "unhandled wrmsr: 0x%x data 0x%llx\n", + vcpu_debug_ratelimited(vcpu, "unhandled wrmsr: 0x%x data 0x%llx\n", msr, data); return 1; } else { @@ -2506,7 +2549,8 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (kvm_pmu_is_valid_msr(vcpu, msr_info->index)) return kvm_pmu_get_msr(vcpu, msr_info->index, &msr_info->data); if (!ignore_msrs) { - vcpu_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr_info->index); + vcpu_debug_ratelimited(vcpu, "unhandled rdmsr: 0x%x\n", + msr_info->index); return 1; } else { vcpu_unimpl(vcpu, "ignored rdmsr: 0x%x\n", msr_info->index); @@ -2630,6 +2674,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_DISABLE_QUIRKS: case KVM_CAP_SET_BOOT_CPU_ID: case KVM_CAP_SPLIT_IRQCHIP: + case KVM_CAP_IMMEDIATE_EXIT: #ifdef CONFIG_KVM_DEVICE_ASSIGNMENT case KVM_CAP_ASSIGN_DEV_IRQ: case KVM_CAP_PCI_2_3: @@ -2810,7 +2855,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) } if (kvm_lapic_hv_timer_in_use(vcpu) && kvm_x86_ops->set_hv_timer(vcpu, - kvm_get_lapic_tscdeadline_msr(vcpu))) + kvm_get_lapic_target_expiration_tsc(vcpu))) kvm_lapic_switch_to_sw_timer(vcpu); /* * On a host with synchronized TSC, there is no need to update @@ -2826,8 +2871,39 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); } +static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) +{ + if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) + return; + + vcpu->arch.st.steal.preempted = 1; + + kvm_vcpu_write_guest_offset_cached(vcpu, &vcpu->arch.st.stime, + &vcpu->arch.st.steal.preempted, + offsetof(struct kvm_steal_time, preempted), + sizeof(vcpu->arch.st.steal.preempted)); +} + void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { + int idx; + /* + * Disable page faults because we're in atomic context here. + * kvm_write_guest_offset_cached() would call might_fault() + * that relies on pagefault_disable() to tell if there's a + * bug. NOTE: the write to guest memory may not go through if + * during postcopy live migration or if there's heavy guest + * paging. + */ + pagefault_disable(); + /* + * kvm_memslots() will be called by + * kvm_write_guest_offset_cached() so take the srcu lock. + */ + idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_steal_time_set_preempted(vcpu); + srcu_read_unlock(&vcpu->kvm->srcu, idx); + pagefault_enable(); kvm_x86_ops->vcpu_put(vcpu); kvm_put_guest_fpu(vcpu); vcpu->arch.last_host_tsc = rdtsc(); @@ -2836,7 +2912,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { - if (vcpu->arch.apicv_active) + if (kvm_x86_ops->sync_pir_to_irr && vcpu->arch.apicv_active) kvm_x86_ops->sync_pir_to_irr(vcpu); return kvm_apic_get_state(vcpu, s); @@ -3036,6 +3112,8 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, memset(&events->reserved, 0, sizeof(events->reserved)); } +static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags); + static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) { @@ -3072,10 +3150,13 @@ 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) { + u32 hflags = vcpu->arch.hflags; if (events->smi.smm) - vcpu->arch.hflags |= HF_SMM_MASK; + hflags |= HF_SMM_MASK; else - vcpu->arch.hflags &= ~HF_SMM_MASK; + hflags &= ~HF_SMM_MASK; + kvm_set_hflags(vcpu, hflags); + vcpu->arch.smi_pending = events->smi.pending; if (events->smi.smm_inside_nmi) vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK; @@ -3143,6 +3224,7 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu) memcpy(dest, xsave, XSAVE_HDR_OFFSET); /* Set XSTATE_BV */ + xstate_bv &= vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FPSSE; *(u64 *)(dest + XSAVE_HDR_OFFSET) = xstate_bv; /* @@ -3303,6 +3385,8 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, switch (cap->cap) { case KVM_CAP_HYPERV_SYNIC: + if (!irqchip_in_kernel(vcpu->kvm)) + return -EINVAL; return kvm_hv_activate_synic(vcpu); default: return -EINVAL; @@ -3855,7 +3939,7 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, goto split_irqchip_unlock; /* Pairs with irqchip_in_kernel. */ smp_wmb(); - kvm->arch.irqchip_split = true; + kvm->arch.irqchip_mode = KVM_IRQCHIP_SPLIT; kvm->arch.nr_reserved_ioapic_pins = cap->args[0]; r = 0; split_irqchip_unlock: @@ -3918,40 +4002,41 @@ long kvm_arch_vm_ioctl(struct file *filp, r = kvm_vm_ioctl_get_nr_mmu_pages(kvm); break; case KVM_CREATE_IRQCHIP: { - struct kvm_pic *vpic; - mutex_lock(&kvm->lock); + r = -EEXIST; - if (kvm->arch.vpic) + if (irqchip_in_kernel(kvm)) goto create_irqchip_unlock; + r = -EINVAL; if (kvm->created_vcpus) goto create_irqchip_unlock; - r = -ENOMEM; - vpic = kvm_create_pic(kvm); - if (vpic) { - r = kvm_ioapic_init(kvm); - if (r) { - mutex_lock(&kvm->slots_lock); - kvm_destroy_pic(vpic); - mutex_unlock(&kvm->slots_lock); - goto create_irqchip_unlock; - } - } else + + r = kvm_pic_init(kvm); + if (r) goto create_irqchip_unlock; + + r = kvm_ioapic_init(kvm); + if (r) { + mutex_lock(&kvm->slots_lock); + kvm_pic_destroy(kvm); + mutex_unlock(&kvm->slots_lock); + goto create_irqchip_unlock; + } + r = kvm_setup_default_irq_routing(kvm); if (r) { mutex_lock(&kvm->slots_lock); mutex_lock(&kvm->irq_lock); kvm_ioapic_destroy(kvm); - kvm_destroy_pic(vpic); + kvm_pic_destroy(kvm); mutex_unlock(&kvm->irq_lock); mutex_unlock(&kvm->slots_lock); goto create_irqchip_unlock; } - /* Write kvm->irq_routing before kvm->arch.vpic. */ + /* Write kvm->irq_routing before enabling irqchip_in_kernel. */ smp_wmb(); - kvm->arch.vpic = vpic; + kvm->arch.irqchip_mode = KVM_IRQCHIP_KERNEL; create_irqchip_unlock: mutex_unlock(&kvm->lock); break; @@ -3987,7 +4072,7 @@ long kvm_arch_vm_ioctl(struct file *filp, } r = -ENXIO; - if (!irqchip_in_kernel(kvm) || irqchip_split(kvm)) + if (!irqchip_kernel(kvm)) goto get_irqchip_out; r = kvm_vm_ioctl_get_irqchip(kvm, chip); if (r) @@ -4011,7 +4096,7 @@ long kvm_arch_vm_ioctl(struct file *filp, } r = -ENXIO; - if (!irqchip_in_kernel(kvm) || irqchip_split(kvm)) + if (!irqchip_kernel(kvm)) goto set_irqchip_out; r = kvm_vm_ioctl_set_irqchip(kvm, chip); if (r) @@ -4420,6 +4505,21 @@ out: } EXPORT_SYMBOL_GPL(kvm_write_guest_virt_system); +static int vcpu_is_mmio_gpa(struct kvm_vcpu *vcpu, unsigned long gva, + gpa_t gpa, bool write) +{ + /* For APIC access vmexit */ + if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) + return 1; + + if (vcpu_match_mmio_gpa(vcpu, gpa)) { + trace_vcpu_match_mmio(gva, gpa, write, true); + return 1; + } + + return 0; +} + static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, gpa_t *gpa, struct x86_exception *exception, bool write) @@ -4446,16 +4546,7 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, if (*gpa == UNMAPPED_GVA) return -1; - /* For APIC access vmexit */ - if ((*gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) - return 1; - - if (vcpu_match_mmio_gpa(vcpu, *gpa)) { - trace_vcpu_match_mmio(gva, *gpa, write, true); - return 1; - } - - return 0; + return vcpu_is_mmio_gpa(vcpu, gva, *gpa, write); } int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, @@ -4552,6 +4643,22 @@ static int emulator_read_write_onepage(unsigned long addr, void *val, int handled, ret; bool write = ops->write; struct kvm_mmio_fragment *frag; + struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + + /* + * If the exit was due to a NPF we may already have a GPA. + * If the GPA is present, use it to avoid the GVA to GPA table walk. + * Note, this cannot be used on string operations since string + * operation using rep will only have the initial GPA from the NPF + * occurred. + */ + if (vcpu->arch.gpa_available && + emulator_can_use_gpa(ctxt) && + vcpu_is_mmio_gpa(vcpu, addr, exception->address, write) && + (addr & ~PAGE_MASK) == (exception->address & ~PAGE_MASK)) { + gpa = exception->address; + goto mmio; + } ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, write); @@ -4816,7 +4923,7 @@ static void emulator_invlpg(struct x86_emulate_ctxt *ctxt, ulong address) kvm_mmu_invlpg(emul_to_vcpu(ctxt), address); } -int kvm_emulate_wbinvd_noskip(struct kvm_vcpu *vcpu) +static int kvm_emulate_wbinvd_noskip(struct kvm_vcpu *vcpu) { if (!need_emulate_wbinvd(vcpu)) return X86EMUL_CONTINUE; @@ -4836,8 +4943,8 @@ int kvm_emulate_wbinvd_noskip(struct kvm_vcpu *vcpu) int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu) { - kvm_x86_ops->skip_emulated_instruction(vcpu); - return kvm_emulate_wbinvd_noskip(vcpu); + kvm_emulate_wbinvd_noskip(vcpu); + return kvm_skip_emulated_instruction(vcpu); } EXPORT_SYMBOL_GPL(kvm_emulate_wbinvd); @@ -5081,11 +5188,6 @@ static void emulator_get_fpu(struct x86_emulate_ctxt *ctxt) { preempt_disable(); kvm_load_guest_fpu(emul_to_vcpu(ctxt)); - /* - * CR0.TS may reference the host fpu state, not the guest fpu state, - * so it may be clear at this point. - */ - clts(); } static void emulator_put_fpu(struct x86_emulate_ctxt *ctxt) @@ -5440,7 +5542,6 @@ static void kvm_vcpu_check_singlestep(struct kvm_vcpu *vcpu, unsigned long rflag kvm_run->exit_reason = KVM_EXIT_DEBUG; *r = EMULATE_USER_EXIT; } else { - vcpu->arch.emulate_ctxt.eflags &= ~X86_EFLAGS_TF; /* * "Certain debug exceptions may clear bit 0-3. The * remaining contents of the DR6 register are never @@ -5453,6 +5554,17 @@ static void kvm_vcpu_check_singlestep(struct kvm_vcpu *vcpu, unsigned long rflag } } +int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu) +{ + unsigned long rflags = kvm_x86_ops->get_rflags(vcpu); + int r = EMULATE_DONE; + + kvm_x86_ops->skip_emulated_instruction(vcpu); + kvm_vcpu_check_singlestep(vcpu, rflags, &r); + return r == EMULATE_DONE; +} +EXPORT_SYMBOL_GPL(kvm_skip_emulated_instruction); + static bool kvm_vcpu_check_breakpoint(struct kvm_vcpu *vcpu, int *r) { if (unlikely(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) && @@ -5563,6 +5675,9 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, } restart: + /* Save the faulting GPA (cr2) in the address field */ + ctxt->exception.address = cr2; + r = x86_emulate_insn(ctxt); if (r == EMULATION_INTERCEPTED) @@ -5638,6 +5753,49 @@ int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port) } EXPORT_SYMBOL_GPL(kvm_fast_pio_out); +static int complete_fast_pio_in(struct kvm_vcpu *vcpu) +{ + unsigned long val; + + /* We should only ever be called with arch.pio.count equal to 1 */ + BUG_ON(vcpu->arch.pio.count != 1); + + /* For size less than 4 we merge, else we zero extend */ + val = (vcpu->arch.pio.size < 4) ? kvm_register_read(vcpu, VCPU_REGS_RAX) + : 0; + + /* + * Since vcpu->arch.pio.count == 1 let emulator_pio_in_emulated perform + * the copy and tracing + */ + emulator_pio_in_emulated(&vcpu->arch.emulate_ctxt, vcpu->arch.pio.size, + vcpu->arch.pio.port, &val, 1); + kvm_register_write(vcpu, VCPU_REGS_RAX, val); + + return 1; +} + +int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size, unsigned short port) +{ + unsigned long val; + int ret; + + /* For size less than 4 we merge, else we zero extend */ + val = (size < 4) ? kvm_register_read(vcpu, VCPU_REGS_RAX) : 0; + + ret = emulator_pio_in_emulated(&vcpu->arch.emulate_ctxt, size, port, + &val, 1); + if (ret) { + kvm_register_write(vcpu, VCPU_REGS_RAX, val); + return ret; + } + + vcpu->arch.complete_userspace_io = complete_fast_pio_in; + + return 0; +} +EXPORT_SYMBOL_GPL(kvm_fast_pio_in); + static int kvmclock_cpu_down_prep(unsigned int cpu) { __this_cpu_write(cpu_tsc_khz, 0); @@ -5773,7 +5931,7 @@ static void kvm_timer_init(void) } pr_debug("kvm: max_tsc_khz = %ld\n", max_tsc_khz); - cpuhp_setup_state(CPUHP_AP_X86_KVM_CLK_ONLINE, "AP_X86_KVM_CLK_ONLINE", + cpuhp_setup_state(CPUHP_AP_X86_KVM_CLK_ONLINE, "x86/kvm/clk:online", kvmclock_cpu_online, kvmclock_cpu_down_prep); } @@ -5834,9 +5992,6 @@ static void kvm_set_mmio_spte_mask(void) /* Mask the reserved physical address bits. */ mask = rsvd_bits(maxphyaddr, 51); - /* Bit 62 is always reserved for 32bit host. */ - mask |= 0x3ull << 62; - /* Set the present bit. */ mask |= 1ull; @@ -5935,7 +6090,7 @@ int kvm_arch_init(void *opaque) kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK, PT_DIRTY_MASK, PT64_NX_MASK, 0, - PT_PRESENT_MASK); + PT_PRESENT_MASK, 0); kvm_timer_init(); perf_register_guest_info_callbacks(&kvm_guest_cbs); @@ -5958,6 +6113,7 @@ out: void kvm_arch_exit(void) { + kvm_lapic_exit(); perf_unregister_guest_info_callbacks(&kvm_guest_cbs); if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) @@ -5987,11 +6143,44 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_halt); int kvm_emulate_halt(struct kvm_vcpu *vcpu) { - kvm_x86_ops->skip_emulated_instruction(vcpu); - return kvm_vcpu_halt(vcpu); + int ret = kvm_skip_emulated_instruction(vcpu); + /* + * TODO: we might be squashing a GUESTDBG_SINGLESTEP-triggered + * KVM_EXIT_DEBUG here. + */ + return kvm_vcpu_halt(vcpu) && ret; } EXPORT_SYMBOL_GPL(kvm_emulate_halt); +#ifdef CONFIG_X86_64 +static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr, + unsigned long clock_type) +{ + struct kvm_clock_pairing clock_pairing; + struct timespec ts; + u64 cycle; + int ret; + + if (clock_type != KVM_CLOCK_PAIRING_WALLCLOCK) + return -KVM_EOPNOTSUPP; + + if (kvm_get_walltime_and_clockread(&ts, &cycle) == false) + return -KVM_EOPNOTSUPP; + + clock_pairing.sec = ts.tv_sec; + clock_pairing.nsec = ts.tv_nsec; + clock_pairing.tsc = kvm_read_l1_tsc(vcpu, cycle); + clock_pairing.flags = 0; + + ret = 0; + if (kvm_write_guest(vcpu->kvm, paddr, &clock_pairing, + sizeof(struct kvm_clock_pairing))) + ret = -KVM_EFAULT; + + return ret; +} +#endif + /* * kvm_pv_kick_cpu_op: Kick a vcpu. * @@ -6019,9 +6208,9 @@ void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu) int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) { unsigned long nr, a0, a1, a2, a3, ret; - int op_64_bit, r = 1; + int op_64_bit, r; - kvm_x86_ops->skip_emulated_instruction(vcpu); + r = kvm_skip_emulated_instruction(vcpu); if (kvm_hv_hypercall_enabled(vcpu->kvm)) return kvm_hv_hypercall(vcpu); @@ -6056,6 +6245,11 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) kvm_pv_kick_cpu_op(vcpu->kvm, a0, a1); ret = 0; break; +#ifdef CONFIG_X86_64 + case KVM_HC_CLOCK_PAIRING: + ret = kvm_pv_clock_pairing(vcpu, a0, a1); + break; +#endif default: ret = -KVM_ENOSYS; break; @@ -6077,7 +6271,8 @@ static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt) kvm_x86_ops->patch_hypercall(vcpu, instruction); - return emulator_write_emulated(ctxt, rip, instruction, 3, NULL); + return emulator_write_emulated(ctxt, rip, instruction, 3, + &ctxt->exception); } static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu) @@ -6468,7 +6663,7 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) if (irqchip_split(vcpu->kvm)) kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors); else { - if (vcpu->arch.apicv_active) + if (kvm_x86_ops->sync_pir_to_irr && vcpu->arch.apicv_active) kvm_x86_ops->sync_pir_to_irr(vcpu); kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); } @@ -6559,10 +6754,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) r = 0; goto out; } - if (kvm_check_request(KVM_REQ_DEACTIVATE_FPU, vcpu)) { - vcpu->fpu_active = 0; - kvm_x86_ops->fpu_deactivate(vcpu); - } if (kvm_check_request(KVM_REQ_APF_HALT, vcpu)) { /* Page is swapped out. Do synthetic halt */ vcpu->arch.apf.halted = true; @@ -6622,21 +6813,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_hv_process_stimers(vcpu); } - /* - * KVM_REQ_EVENT is not set when posted interrupts are set by - * VT-d hardware, so we have to update RVI unconditionally. - */ - if (kvm_lapic_enabled(vcpu)) { - /* - * Update architecture specific hints for APIC - * virtual interrupt delivery. - */ - if (vcpu->arch.apicv_active) - kvm_x86_ops->hwapic_irr_update(vcpu, - kvm_lapic_find_highest_irr(vcpu)); - } - if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) { + ++vcpu->stat.req_event; kvm_apic_accept_events(vcpu); if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) { r = 1; @@ -6677,22 +6855,40 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) preempt_disable(); kvm_x86_ops->prepare_guest_switch(vcpu); - if (vcpu->fpu_active) - kvm_load_guest_fpu(vcpu); + kvm_load_guest_fpu(vcpu); + + /* + * Disable IRQs before setting IN_GUEST_MODE. Posted interrupt + * IPI are then delayed after guest entry, which ensures that they + * result in virtual interrupt delivery. + */ + local_irq_disable(); vcpu->mode = IN_GUEST_MODE; srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); /* - * We should set ->mode before check ->requests, - * Please see the comment in kvm_make_all_cpus_request. - * This also orders the write to mode from any reads - * to the page tables done while the VCPU is running. - * Please see the comment in kvm_flush_remote_tlbs. + * 1) We should set ->mode before checking ->requests. Please see + * the comment in kvm_make_all_cpus_request. + * + * 2) For APICv, we should set ->mode before checking PIR.ON. This + * pairs with the memory barrier implicit in pi_test_and_set_on + * (see vmx_deliver_posted_interrupt). + * + * 3) This also orders the write to mode from any reads to the page + * tables done while the VCPU is running. Please see the comment + * in kvm_flush_remote_tlbs. */ smp_mb__after_srcu_read_unlock(); - local_irq_disable(); + /* + * This handles the case where a posted interrupt was + * notified with kvm_vcpu_kick. + */ + if (kvm_lapic_enabled(vcpu)) { + if (kvm_x86_ops->sync_pir_to_irr && vcpu->arch.apicv_active) + kvm_x86_ops->sync_pir_to_irr(vcpu); + } if (vcpu->mode == EXITING_GUEST_MODE || vcpu->requests || need_resched() || signal_pending(current)) { @@ -6831,6 +7027,9 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu) { + if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) + kvm_x86_ops->check_nested_events(vcpu, false); + return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && !vcpu->arch.apf.halted); } @@ -7002,7 +7201,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } else WARN_ON(vcpu->arch.pio.count || vcpu->mmio_needed); - r = vcpu_run(vcpu); + if (kvm_run->immediate_exit) + r = -EINTR; + else + r = vcpu_run(vcpu); out: post_kvm_run_save(vcpu); @@ -7407,25 +7609,13 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) { - if (!vcpu->guest_fpu_loaded) { - vcpu->fpu_counter = 0; + if (!vcpu->guest_fpu_loaded) return; - } vcpu->guest_fpu_loaded = 0; copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu); __kernel_fpu_end(); ++vcpu->stat.fpu_reload; - /* - * If using eager FPU mode, or if the guest is a frequent user - * of the FPU, just leave the FPU active for next time. - * Every 255 times fpu_counter rolls over to 0; a guest that uses - * the FPU in bursts will revert to loading it on demand. - */ - if (!use_eager_fpu()) { - if (++vcpu->fpu_counter < 5) - kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu); - } trace_kvm_fpu(0); } @@ -7824,6 +8014,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) raw_spin_lock_init(&kvm->arch.tsc_write_lock); mutex_init(&kvm->arch.apic_map_lock); + mutex_init(&kvm->arch.hyperv.hv_lock); spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock); kvm->arch.kvmclock_offset = -ktime_get_boot_ns(); @@ -7962,11 +8153,12 @@ void kvm_arch_destroy_vm(struct kvm *kvm) if (kvm_x86_ops->vm_destroy) kvm_x86_ops->vm_destroy(kvm); kvm_iommu_unmap_guest(kvm); - kfree(kvm->arch.vpic); - kfree(kvm->arch.vioapic); + kvm_pic_destroy(kvm); + kvm_ioapic_destroy(kvm); kvm_free_vcpus(kvm); kvfree(rcu_dereference_check(kvm->arch.apic_map, 1)); kvm_mmu_uninit_vm(kvm); + kvm_page_track_cleanup(kvm); } void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, @@ -8176,7 +8368,7 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm) void kvm_arch_flush_shadow_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { - kvm_mmu_invalidate_zap_all_pages(kvm); + kvm_page_track_flush_slot(kvm, slot); } static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) @@ -8208,9 +8400,6 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) { - if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) - kvm_x86_ops->check_nested_events(vcpu, false); - return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu); } @@ -8347,9 +8536,8 @@ static void kvm_del_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn) static int apf_put_user(struct kvm_vcpu *vcpu, u32 val) { - - return kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.apf.data, &val, - sizeof(val)); + return kvm_vcpu_write_guest_cached(vcpu, &vcpu->arch.apf.data, &val, + sizeof(val)); } void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, @@ -8379,11 +8567,11 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, { struct x86_exception fault; - trace_kvm_async_pf_ready(work->arch.token, work->gva); if (work->wakeup_all) work->arch.token = ~0; /* broadcast wakeup */ else kvm_del_async_pf_gfn(vcpu, work->arch.gfn); + trace_kvm_async_pf_ready(work->arch.token, work->gva); if ((vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) && !apf_put_user(vcpu, KVM_PV_REASON_PAGE_READY)) { |