Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:
 "4.11 is going to be a relatively large release for KVM, with a little
  over 200 commits and noteworthy changes for most architectures.

  ARM:
   - GICv3 save/restore
   - cache flushing fixes
   - working MSI injection for GICv3 ITS
   - physical timer emulation

  MIPS:
   - various improvements under the hood
   - support for SMP guests
   - a large rewrite of MMU emulation. KVM MIPS can now use MMU
     notifiers to support copy-on-write, KSM, idle page tracking,
     swapping, ballooning and everything else. KVM_CAP_READONLY_MEM is
     also supported, so that writes to some memory regions can be
     treated as MMIO. The new MMU also paves the way for hardware
     virtualization support.

  PPC:
   - support for POWER9 using the radix-tree MMU for host and guest
   - resizable hashed page table
   - bugfixes.

  s390:
   - expose more features to the guest
   - more SIMD extensions
   - instruction execution protection
   - ESOP2

  x86:
   - improved hashing in the MMU
   - faster PageLRU tracking for Intel CPUs without EPT A/D bits
   - some refactoring of nested VMX entry/exit code, preparing for live
     migration support of nested hypervisors
   - expose yet another AVX512 CPUID bit
   - host-to-guest PTP support
   - refactoring of interrupt injection, with some optimizations thrown
     in and some duct tape removed.
   - remove lazy FPU handling
   - optimizations of user-mode exits
   - optimizations of vcpu_is_preempted() for KVM guests

  generic:
   - alternative signaling mechanism that doesn't pound on
     tsk->sighand->siglock"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (195 commits)
  x86/kvm: Provide optimized version of vcpu_is_preempted() for x86-64
  x86/paravirt: Change vcp_is_preempted() arg type to long
  KVM: VMX: use correct vmcs_read/write for guest segment selector/base
  x86/kvm/vmx: Defer TR reload after VM exit
  x86/asm/64: Drop __cacheline_aligned from struct x86_hw_tss
  x86/kvm/vmx: Simplify segment_base()
  x86/kvm/vmx: Get rid of segment_base() on 64-bit kernels
  x86/kvm/vmx: Don't fetch the TSS base from the GDT
  x86/asm: Define the kernel TSS limit in a macro
  kvm: fix page struct leak in handle_vmon
  KVM: PPC: Book3S HV: Disable HPT resizing on POWER9 for now
  KVM: Return an error code only as a constant in kvm_get_dirty_log()
  KVM: Return an error code only as a constant in kvm_get_dirty_log_protect()
  KVM: Return directly after a failed copy_from_user() in kvm_vm_compat_ioctl()
  KVM: x86: remove code for lazy FPU handling
  KVM: race-free exit from KVM_RUN without POSIX signals
  KVM: PPC: Book3S HV: Turn "KVM guest htab" message into a debug message
  KVM: PPC: Book3S PR: Ratelimit copy data failure error messages
  KVM: Support vCPU-based gfn->hva cache
  KVM: use separate generations for each address space
  ...

1 files changed, 187 insertions, 87 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e52c9088660f..b2a4b11274b0 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -180,6 +180,7 @@ 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 +191,8 @@ 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 }
 };
 
@@ -1139,6 +1142,7 @@ struct pvclock_gtod_data {
 
 	u64		boot_ns;
 	u64		nsec_base;
+	u64		wall_time_sec;
 };
 
 static struct pvclock_gtod_data pvclock_gtod_data;
@@ -1162,6 +1166,8 @@ 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
@@ -1623,6 +1629,28 @@ static int do_monotonic_boot(s64 *t, u64 *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(&gtod->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(&gtod->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, u64 *cycle_now)
 {
@@ -1632,6 +1660,17 @@ static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *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
 
 /*
@@ -1772,7 +1811,7 @@ 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;
 
@@ -1793,9 +1832,9 @@ 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();
 
@@ -1809,16 +1848,16 @@ 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)
@@ -2051,7 +2090,7 @@ 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;
 
@@ -2070,7 +2109,7 @@ 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;
 
@@ -2081,7 +2120,7 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
 
 	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();
@@ -2090,14 +2129,14 @@ 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));
 }
 
@@ -2202,7 +2241,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (!(data & 1))
 			break;
 
-		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;
@@ -2223,7 +2262,7 @@ 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;
@@ -2633,6 +2672,7 @@ 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:
@@ -2836,7 +2876,7 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu)
 
 	vcpu->arch.st.steal.preempted = 1;
 
-	kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.st.stime,
+	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));
@@ -2870,7 +2910,7 @@ 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);
@@ -3897,7 +3937,7 @@ 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:
@@ -3960,40 +4000,41 @@ 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;
@@ -4029,7 +4070,7 @@ 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)
@@ -4053,7 +4094,7 @@ 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)
@@ -4462,6 +4503,21 @@ 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)
@@ -4488,16 +4544,7 @@ 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,
@@ -4594,6 +4641,22 @@ 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);
 
@@ -5610,6 +5673,9 @@ 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)
@@ -5924,9 +5990,6 @@ 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;
 
@@ -6025,7 +6088,7 @@ 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);
@@ -6087,6 +6150,35 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu)
 }
 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.
  *
@@ -6151,6 +6243,11 @@ 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;
@@ -6564,7 +6661,7 @@ 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);
 	}
@@ -6655,10 +6752,6 @@ 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;
@@ -6718,21 +6811,8 @@ 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;
@@ -6773,22 +6853,40 @@ 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)) {
@@ -6927,6 +7025,9 @@ 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);
 }
@@ -7098,7 +7199,10 @@ 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);
@@ -8293,9 +8397,6 @@ 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);
 }
 
@@ -8432,9 +8533,8 @@ 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,