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

Pull KVM updates from Paolo Bonzini: "First batch of KVM changes for 4.4. s390: A bunch of fixes and optimizations for interrupt and time handling. PPC: Mostly bug fixes. ARM: No big features, but many small fixes and prerequisites including: - a number of fixes for the arch-timer - introducing proper level-triggered semantics for the arch-timers - a series of patches to synchronously halt a guest (prerequisite for IRQ forwarding) - some tracepoint improvements - a tweak for the EL2 panic handlers - some more VGIC cleanups getting rid of redundant state x86: Quite a few changes: - support for VT-d posted interrupts (i.e. PCI devices can inject interrupts directly into vCPUs). This introduces a new component (in virt/lib/) that connects VFIO and KVM together. The same infrastructure will be used for ARM interrupt forwarding as well. - more Hyper-V features, though the main one Hyper-V synthetic interrupt controller will have to wait for 4.5. These will let KVM expose Hyper-V devices. - nested virtualization now supports VPID (same as PCID but for vCPUs) which makes it quite a bit faster - for future hardware that supports NVDIMM, there is support for clflushopt, clwb, pcommit - support for "split irqchip", i.e. LAPIC in kernel + IOAPIC/PIC/PIT in userspace, which reduces the attack surface of the hypervisor - obligatory smattering of SMM fixes - on the guest side, stable scheduler clock support was rewritten to not require help from the hypervisor" * tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (123 commits) KVM: VMX: Fix commit which broke PML KVM: x86: obey KVM_X86_QUIRK_CD_NW_CLEARED in kvm_set_cr0() KVM: x86: allow RSM from 64-bit mode KVM: VMX: fix SMEP and SMAP without EPT KVM: x86: move kvm_set_irq_inatomic to legacy device assignment KVM: device assignment: remove pointless #ifdefs KVM: x86: merge kvm_arch_set_irq with kvm_set_msi_inatomic KVM: x86: zero apic_arb_prio on reset drivers/hv: share Hyper-V SynIC constants with userspace KVM: x86: handle SMBASE as physical address in RSM KVM: x86: add read_phys to x86_emulate_ops KVM: x86: removing unused variable KVM: don't pointlessly leave KVM_COMPAT=y in non-KVM configs KVM: arm/arm64: Merge vgic_set_lr() and vgic_sync_lr_elrsr() KVM: arm/arm64: Clean up vgic_retire_lr() and surroundings KVM: arm/arm64: Optimize away redundant LR tracking KVM: s390: use simple switch statement as multiplexer KVM: s390: drop useless newline in debugging data KVM: s390: SCA must not cross page boundaries KVM: arm: Do not indent the arguments of DECLARE_BITMAP ...
author: Linus Torvalds <torvalds@linux-foundation.org> 2015-11-05 16:26:26 -0800
committer: Linus Torvalds <torvalds@linux-foundation.org> 2015-11-05 16:26:26 -0800
commit: 933425fb0010bd02bd459b41e63082756818ffce (patch)
tree: 1cbc6c2035b9dcff8cb265c9ac562cbee7c6bb82 /arch/x86
parent: Merge tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi (diff)
parent: KVM: VMX: Fix commit which broke PML (diff)
download: linux-dev-933425fb0010bd02bd459b41e63082756818ffce.tar.xz
linux-dev-933425fb0010bd02bd459b41e63082756818ffce.zip
27 files changed, 1445 insertions, 441 deletions
diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h
index 046c7fb1ca43..a210eba2727c 100644
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -33,6 +33,11 @@ enum irq_remap_cap {
 	IRQ_POSTING_CAP = 0,
 };
 
+struct vcpu_data {
+	u64 pi_desc_addr;	/* Physical address of PI Descriptor */
+	u32 vector;		/* Guest vector of the interrupt */
+};
+
 #ifdef CONFIG_IRQ_REMAP
 
 extern bool irq_remapping_cap(enum irq_remap_cap cap);
@@ -58,11 +63,6 @@ static inline struct irq_domain *arch_get_ir_parent_domain(void)
 	return x86_vector_domain;
 }
 
-struct vcpu_data {
-	u64 pi_desc_addr;	/* Physical address of PI Descriptor */
-	u32 vector;		/* Guest vector of the interrupt */
-};
-
 #else  /* CONFIG_IRQ_REMAP */
 
 static inline bool irq_remapping_cap(enum irq_remap_cap cap) { return 0; }
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index e16466ec473c..e9cd7befcb76 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -112,6 +112,16 @@ struct x86_emulate_ops {
 			struct x86_exception *fault);
 
 	/*
+	 * read_phys: Read bytes of standard (non-emulated/special) memory.
+	 *            Used for descriptor reading.
+	 *  @addr:  [IN ] Physical address from which to read.
+	 *  @val:   [OUT] Value read from memory.
+	 *  @bytes: [IN ] Number of bytes to read from memory.
+	 */
+	int (*read_phys)(struct x86_emulate_ctxt *ctxt, unsigned long addr,
+			void *val, unsigned int bytes);
+
+	/*
 	 * write_std: Write bytes of standard (non-emulated/special) memory.
 	 *            Used for descriptor writing.
 	 *  @addr:  [IN ] Linear address to which to write.
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 3a36ee704c30..9265196e877f 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -24,6 +24,7 @@
 #include <linux/perf_event.h>
 #include <linux/pvclock_gtod.h>
 #include <linux/clocksource.h>
+#include <linux/irqbypass.h>
 
 #include <asm/pvclock-abi.h>
 #include <asm/desc.h>
@@ -176,6 +177,8 @@ enum {
  */
 #define KVM_APIC_PV_EOI_PENDING	1
 
+struct kvm_kernel_irq_routing_entry;
+
 /*
  * We don't want allocation failures within the mmu code, so we preallocate
  * enough memory for a single page fault in a cache.
@@ -374,6 +377,7 @@ struct kvm_mtrr {
 /* Hyper-V per vcpu emulation context */
 struct kvm_vcpu_hv {
 	u64 hv_vapic;
+	s64 runtime_offset;
 };
 
 struct kvm_vcpu_arch {
@@ -396,6 +400,7 @@ struct kvm_vcpu_arch {
 	u64 efer;
 	u64 apic_base;
 	struct kvm_lapic *apic;    /* kernel irqchip context */
+	u64 eoi_exit_bitmap[4];
 	unsigned long apic_attention;
 	int32_t apic_arb_prio;
 	int mp_state;
@@ -573,6 +578,9 @@ struct kvm_vcpu_arch {
 	struct {
 		bool pv_unhalted;
 	} pv;
+
+	int pending_ioapic_eoi;
+	int pending_external_vector;
 };
 
 struct kvm_lpage_info {
@@ -683,6 +691,9 @@ struct kvm_arch {
 	u32 bsp_vcpu_id;
 
 	u64 disabled_quirks;
+
+	bool irqchip_split;
+	u8 nr_reserved_ioapic_pins;
 };
 
 struct kvm_vm_stat {
@@ -819,10 +830,10 @@ struct kvm_x86_ops {
 	void (*enable_nmi_window)(struct kvm_vcpu *vcpu);
 	void (*enable_irq_window)(struct kvm_vcpu *vcpu);
 	void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr);
-	int (*vm_has_apicv)(struct kvm *kvm);
+	int (*cpu_uses_apicv)(struct kvm_vcpu *vcpu);
 	void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr);
 	void (*hwapic_isr_update)(struct kvm *kvm, int isr);
-	void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
+	void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu);
 	void (*set_virtual_x2apic_mode)(struct kvm_vcpu *vcpu, bool set);
 	void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa);
 	void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector);
@@ -887,6 +898,20 @@ struct kvm_x86_ops {
 					   gfn_t offset, unsigned long mask);
 	/* pmu operations of sub-arch */
 	const struct kvm_pmu_ops *pmu_ops;
+
+	/*
+	 * Architecture specific hooks for vCPU blocking due to
+	 * HLT instruction.
+	 * Returns for .pre_block():
+	 *    - 0 means continue to block the vCPU.
+	 *    - 1 means we cannot block the vCPU since some event
+	 *        happens during this period, such as, 'ON' bit in
+	 *        posted-interrupts descriptor is set.
+	 */
+	int (*pre_block)(struct kvm_vcpu *vcpu);
+	void (*post_block)(struct kvm_vcpu *vcpu);
+	int (*update_pi_irte)(struct kvm *kvm, unsigned int host_irq,
+			      uint32_t guest_irq, bool set);
 };
 
 struct kvm_arch_async_pf {
@@ -1231,4 +1256,13 @@ int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size);
 bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu);
 bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu);
 
+bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq,
+			     struct kvm_vcpu **dest_vcpu);
+
+void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e,
+		     struct kvm_lapic_irq *irq);
+
+static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
+
 #endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 448b7ca61aee..aa336ff3e03e 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -72,7 +72,7 @@
 #define SECONDARY_EXEC_SHADOW_VMCS              0x00004000
 #define SECONDARY_EXEC_ENABLE_PML               0x00020000
 #define SECONDARY_EXEC_XSAVES			0x00100000
-
+#define SECONDARY_EXEC_PCOMMIT			0x00200000
 
 #define PIN_BASED_EXT_INTR_MASK                 0x00000001
 #define PIN_BASED_NMI_EXITING                   0x00000008
@@ -416,6 +416,7 @@ enum vmcs_field {
 #define VMX_EPT_EXTENT_CONTEXT_BIT		(1ull << 25)
 #define VMX_EPT_EXTENT_GLOBAL_BIT		(1ull << 26)
 
+#define VMX_VPID_INVVPID_BIT                    (1ull << 0) /* (32 - 32) */
 #define VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT      (1ull << 9) /* (41 - 32) */
 #define VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT      (1ull << 10) /* (42 - 32) */
 
diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h
index f0412c50c47b..040d4083c24f 100644
--- a/arch/x86/include/uapi/asm/hyperv.h
+++ b/arch/x86/include/uapi/asm/hyperv.h
@@ -153,6 +153,12 @@
 /* MSR used to provide vcpu index */
 #define HV_X64_MSR_VP_INDEX			0x40000002
 
+/* MSR used to reset the guest OS. */
+#define HV_X64_MSR_RESET			0x40000003
+
+/* MSR used to provide vcpu runtime in 100ns units */
+#define HV_X64_MSR_VP_RUNTIME			0x40000010
+
 /* MSR used to read the per-partition time reference counter */
 #define HV_X64_MSR_TIME_REF_COUNT		0x40000020
 
@@ -251,4 +257,16 @@ typedef struct _HV_REFERENCE_TSC_PAGE {
 	__s64 tsc_offset;
 } HV_REFERENCE_TSC_PAGE, *PHV_REFERENCE_TSC_PAGE;
 
+/* Define the number of synthetic interrupt sources. */
+#define HV_SYNIC_SINT_COUNT		(16)
+/* Define the expected SynIC version. */
+#define HV_SYNIC_VERSION_1		(0x1)
+
+#define HV_SYNIC_CONTROL_ENABLE		(1ULL << 0)
+#define HV_SYNIC_SIMP_ENABLE		(1ULL << 0)
+#define HV_SYNIC_SIEFP_ENABLE		(1ULL << 0)
+#define HV_SYNIC_SINT_MASKED		(1ULL << 16)
+#define HV_SYNIC_SINT_AUTO_EOI		(1ULL << 17)
+#define HV_SYNIC_SINT_VECTOR_MASK	(0xFF)
+
 #endif
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index 37fee272618f..5b15d94a33f8 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -78,6 +78,7 @@
 #define EXIT_REASON_PML_FULL            62
 #define EXIT_REASON_XSAVES              63
 #define EXIT_REASON_XRSTORS             64
+#define EXIT_REASON_PCOMMIT             65
 
 #define VMX_EXIT_REASONS \
 	{ EXIT_REASON_EXCEPTION_NMI,         "EXCEPTION_NMI" }, \
@@ -126,7 +127,8 @@
 	{ EXIT_REASON_INVVPID,               "INVVPID" }, \
 	{ EXIT_REASON_INVPCID,               "INVPCID" }, \
 	{ EXIT_REASON_XSAVES,                "XSAVES" }, \
-	{ EXIT_REASON_XRSTORS,               "XRSTORS" }
+	{ EXIT_REASON_XRSTORS,               "XRSTORS" }, \
+	{ EXIT_REASON_PCOMMIT,               "PCOMMIT" }
 
 #define VMX_ABORT_SAVE_GUEST_MSR_FAIL        1
 #define VMX_ABORT_LOAD_HOST_MSR_FAIL         4
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 2c7aafa70702..2bd81e302427 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -32,6 +32,7 @@
 static int kvmclock = 1;
 static int msr_kvm_system_time = MSR_KVM_SYSTEM_TIME;
 static int msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK;
+static cycle_t kvm_sched_clock_offset;
 
 static int parse_no_kvmclock(char *arg)
 {
@@ -92,6 +93,29 @@ static cycle_t kvm_clock_get_cycles(struct clocksource *cs)
 	return kvm_clock_read();
 }
 
+static cycle_t kvm_sched_clock_read(void)
+{
+	return kvm_clock_read() - kvm_sched_clock_offset;
+}
+
+static inline void kvm_sched_clock_init(bool stable)
+{
+	if (!stable) {
+		pv_time_ops.sched_clock = kvm_clock_read;
+		return;
+	}
+
+	kvm_sched_clock_offset = kvm_clock_read();
+	pv_time_ops.sched_clock = kvm_sched_clock_read;
+	set_sched_clock_stable();
+
+	printk(KERN_INFO "kvm-clock: using sched offset of %llu cycles\n",
+			kvm_sched_clock_offset);
+
+	BUILD_BUG_ON(sizeof(kvm_sched_clock_offset) >
+	         sizeof(((struct pvclock_vcpu_time_info *)NULL)->system_time));
+}
+
 /*
  * If we don't do that, there is the possibility that the guest
  * will calibrate under heavy load - thus, getting a lower lpj -
@@ -248,7 +272,17 @@ void __init kvmclock_init(void)
 		memblock_free(mem, size);
 		return;
 	}
-	pv_time_ops.sched_clock = kvm_clock_read;
+
+	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))
+		pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT);
+
+	cpu = get_cpu();
+	vcpu_time = &hv_clock[cpu].pvti;
+	flags = pvclock_read_flags(vcpu_time);
+
+	kvm_sched_clock_init(flags & PVCLOCK_TSC_STABLE_BIT);
+	put_cpu();
+
 	x86_platform.calibrate_tsc = kvm_get_tsc_khz;
 	x86_platform.get_wallclock = kvm_get_wallclock;
 	x86_platform.set_wallclock = kvm_set_wallclock;
@@ -265,16 +299,6 @@ void __init kvmclock_init(void)
 	kvm_get_preset_lpj();
 	clocksource_register_hz(&kvm_clock, NSEC_PER_SEC);
 	pv_info.name = "KVM";
-
-	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))
-		pvclock_set_flags(~0);
-
-	cpu = get_cpu();
-	vcpu_time = &hv_clock[cpu].pvti;
-	flags = pvclock_read_flags(vcpu_time);
-	if (flags & PVCLOCK_COUNTS_FROM_ZERO)
-		set_sched_clock_stable();
-	put_cpu();
 }
 
 int __init kvm_setup_vsyscall_timeinfo(void)
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index d8a1d56276e1..639a6e34500c 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -28,6 +28,8 @@ config KVM
 	select ANON_INODES
 	select HAVE_KVM_IRQCHIP
 	select HAVE_KVM_IRQFD
+	select IRQ_BYPASS_MANAGER
+	select HAVE_KVM_IRQ_BYPASS
 	select HAVE_KVM_IRQ_ROUTING
 	select HAVE_KVM_EVENTFD
 	select KVM_APIC_ARCHITECTURE
diff --git a/arch/x86/kvm/assigned-dev.c b/arch/x86/kvm/assigned-dev.c
index d090ecf08809..9dc091acd5fb 100644
--- a/arch/x86/kvm/assigned-dev.c
+++ b/arch/x86/kvm/assigned-dev.c
@@ -21,6 +21,7 @@
 #include <linux/fs.h>
 #include "irq.h"
 #include "assigned-dev.h"
+#include "trace/events/kvm.h"
 
 struct kvm_assigned_dev_kernel {
 	struct kvm_irq_ack_notifier ack_notifier;
@@ -131,7 +132,42 @@ static irqreturn_t kvm_assigned_dev_thread_intx(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-#ifdef __KVM_HAVE_MSI
+/*
+ * Deliver an IRQ in an atomic context if we can, or return a failure,
+ * user can retry in a process context.
+ * Return value:
+ *  -EWOULDBLOCK - Can't deliver in atomic context: retry in a process context.
+ *  Other values - No need to retry.
+ */
+static int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq,
+				int level)
+{
+	struct kvm_kernel_irq_routing_entry entries[KVM_NR_IRQCHIPS];
+	struct kvm_kernel_irq_routing_entry *e;
+	int ret = -EINVAL;
+	int idx;
+
+	trace_kvm_set_irq(irq, level, irq_source_id);
+
+	/*
+	 * Injection into either PIC or IOAPIC might need to scan all CPUs,
+	 * which would need to be retried from thread context;  when same GSI
+	 * is connected to both PIC and IOAPIC, we'd have to report a
+	 * partial failure here.
+	 * Since there's no easy way to do this, we only support injecting MSI
+	 * which is limited to 1:1 GSI mapping.
+	 */
+	idx = srcu_read_lock(&kvm->irq_srcu);
+	if (kvm_irq_map_gsi(kvm, entries, irq) > 0) {
+		e = &entries[0];
+		ret = kvm_arch_set_irq_inatomic(e, kvm, irq_source_id,
+						irq, level);
+	}
+	srcu_read_unlock(&kvm->irq_srcu, idx);
+	return ret;
+}
+
+
 static irqreturn_t kvm_assigned_dev_msi(int irq, void *dev_id)
 {
 	struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
@@ -150,9 +186,7 @@ static irqreturn_t kvm_assigned_dev_thread_msi(int irq, void *dev_id)
 
 	return IRQ_HANDLED;
 }
-#endif
 
-#ifdef __KVM_HAVE_MSIX
 static irqreturn_t kvm_assigned_dev_msix(int irq, void *dev_id)
 {
 	struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
@@ -183,7 +217,6 @@ static irqreturn_t kvm_assigned_dev_thread_msix(int irq, void *dev_id)
 
 	return IRQ_HANDLED;
 }
-#endif
 
 /* Ack the irq line for an assigned device */
 static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian)
@@ -386,7 +419,6 @@ static int assigned_device_enable_host_intx(struct kvm *kvm,
 	return 0;
 }
 
-#ifdef __KVM_HAVE_MSI
 static int assigned_device_enable_host_msi(struct kvm *kvm,
 					   struct kvm_assigned_dev_kernel *dev)
 {
@@ -408,9 +440,7 @@ static int assigned_device_enable_host_msi(struct kvm *kvm,
 
 	return 0;
 }
-#endif
 
-#ifdef __KVM_HAVE_MSIX
 static int assigned_device_enable_host_msix(struct kvm *kvm,
 					    struct kvm_assigned_dev_kernel *dev)
 {
@@ -443,8 +473,6 @@ err:
 	return r;
 }
 
-#endif
-
 static int assigned_device_enable_guest_intx(struct kvm *kvm,
 				struct kvm_assigned_dev_kernel *dev,
 				struct kvm_assigned_irq *irq)
@@ -454,7 +482,6 @@ static int assigned_device_enable_guest_intx(struct kvm *kvm,
 	return 0;
 }
 
-#ifdef __KVM_HAVE_MSI
 static int assigned_device_enable_guest_msi(struct kvm *kvm,
 			struct kvm_assigned_dev_kernel *dev,
 			struct kvm_assigned_irq *irq)
@@ -463,9 +490,7 @@ static int assigned_device_enable_guest_msi(struct kvm *kvm,
 	dev->ack_notifier.gsi = -1;
 	return 0;
 }
-#endif
 
-#ifdef __KVM_HAVE_MSIX
 static int assigned_device_enable_guest_msix(struct kvm *kvm,
 			struct kvm_assigned_dev_kernel *dev,
 			struct kvm_assigned_irq *irq)
@@ -474,7 +499,6 @@ static int assigned_device_enable_guest_msix(struct kvm *kvm,
 	dev->ack_notifier.gsi = -1;
 	return 0;
 }
-#endif
 
 static int assign_host_irq(struct kvm *kvm,
 			   struct kvm_assigned_dev_kernel *dev,
@@ -492,16 +516,12 @@ static int assign_host_irq(struct kvm *kvm,
 	case KVM_DEV_IRQ_HOST_INTX:
 		r = assigned_device_enable_host_intx(kvm, dev);
 		break;
-#ifdef __KVM_HAVE_MSI
 	case KVM_DEV_IRQ_HOST_MSI:
 		r = assigned_device_enable_host_msi(kvm, dev);
 		break;
-#endif
-#ifdef __KVM_HAVE_MSIX
 	case KVM_DEV_IRQ_HOST_MSIX:
 		r = assigned_device_enable_host_msix(kvm, dev);
 		break;
-#endif
 	default:
 		r = -EINVAL;
 	}
@@ -534,16 +554,12 @@ static int assign_guest_irq(struct kvm *kvm,
 	case KVM_DEV_IRQ_GUEST_INTX:
 		r = assigned_device_enable_guest_intx(kvm, dev, irq);
 		break;
-#ifdef __KVM_HAVE_MSI
 	case KVM_DEV_IRQ_GUEST_MSI:
 		r = assigned_device_enable_guest_msi(kvm, dev, irq);
 		break;
-#endif
-#ifdef __KVM_HAVE_MSIX
 	case KVM_DEV_IRQ_GUEST_MSIX:
 		r = assigned_device_enable_guest_msix(kvm, dev, irq);
 		break;
-#endif
 	default:
 		r = -EINVAL;
 	}
@@ -826,7 +842,6 @@ out:
 }
 
 
-#ifdef __KVM_HAVE_MSIX
 static int kvm_vm_ioctl_set_msix_nr(struct kvm *kvm,
 				    struct kvm_assigned_msix_nr *entry_nr)
 {
@@ -906,7 +921,6 @@ msix_entry_out:
 
 	return r;
 }
-#endif
 
 static int kvm_vm_ioctl_set_pci_irq_mask(struct kvm *kvm,
 		struct kvm_assigned_pci_dev *assigned_dev)
@@ -1012,7 +1026,6 @@ long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
 			goto out;
 		break;
 	}
-#ifdef __KVM_HAVE_MSIX
 	case KVM_ASSIGN_SET_MSIX_NR: {
 		struct kvm_assigned_msix_nr entry_nr;
 		r = -EFAULT;
@@ -1033,7 +1046,6 @@ long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
 			goto out;
 		break;
 	}
-#endif
 	case KVM_ASSIGN_SET_INTX_MASK: {
 		struct kvm_assigned_pci_dev assigned_dev;
 
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 156441bcaac8..6525e926f566 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -348,7 +348,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		F(FSGSBASE) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) |
 		F(BMI2) | F(ERMS) | f_invpcid | F(RTM) | f_mpx | F(RDSEED) |
 		F(ADX) | F(SMAP) | F(AVX512F) | F(AVX512PF) | F(AVX512ER) |
-		F(AVX512CD);
+		F(AVX512CD) | F(CLFLUSHOPT) | F(CLWB) | F(PCOMMIT);
 
 	/* cpuid 0xD.1.eax */
 	const u32 kvm_supported_word10_x86_features =
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index dd05b9cef6ae..06332cb7e7d1 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -133,4 +133,41 @@ static inline bool guest_cpuid_has_mpx(struct kvm_vcpu *vcpu)
 	best = kvm_find_cpuid_entry(vcpu, 7, 0);
 	return best && (best->ebx & bit(X86_FEATURE_MPX));
 }
+
+static inline bool guest_cpuid_has_pcommit(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 7, 0);
+	return best && (best->ebx & bit(X86_FEATURE_PCOMMIT));
+}
+
+static inline bool guest_cpuid_has_rdtscp(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
+	return best && (best->edx & bit(X86_FEATURE_RDTSCP));
+}
+
+/*
+ * NRIPS is provided through cpuidfn 0x8000000a.edx bit 3
+ */
+#define BIT_NRIPS	3
+
+static inline bool guest_cpuid_has_nrips(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 0x8000000a, 0);
+
+	/*
+	 * NRIPS is a scattered cpuid feature, so we can't use
+	 * X86_FEATURE_NRIPS here (X86_FEATURE_NRIPS would be bit
+	 * position 8, not 3).
+	 */
+	return best && (best->edx & bit(BIT_NRIPS));
+}
+#undef BIT_NRIPS
+
 #endif
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 9da95b9daf8d..1505587d06e9 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2272,8 +2272,8 @@ static int emulator_has_longmode(struct x86_emulate_ctxt *ctxt)
 #define GET_SMSTATE(type, smbase, offset)				  \
 	({								  \
 	 type __val;							  \
-	 int r = ctxt->ops->read_std(ctxt, smbase + offset, &__val,       \
-				     sizeof(__val), NULL);		  \
+	 int r = ctxt->ops->read_phys(ctxt, smbase + offset, &__val,      \
+				      sizeof(__val));			  \
 	 if (r != X86EMUL_CONTINUE)					  \
 		 return X86EMUL_UNHANDLEABLE;				  \
 	 __val;								  \
@@ -2484,17 +2484,36 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt)
 
 	/*
 	 * Get back to real mode, to prepare a safe state in which to load
-	 * CR0/CR3/CR4/EFER.  Also this will ensure that addresses passed
-	 * to read_std/write_std are not virtual.
-	 *
-	 * CR4.PCIDE must be zero, because it is a 64-bit mode only feature.
+	 * CR0/CR3/CR4/EFER.  It's all a bit more complicated if the vCPU
+	 * supports long mode.
 	 */
+	cr4 = ctxt->ops->get_cr(ctxt, 4);
+	if (emulator_has_longmode(ctxt)) {
+		struct desc_struct cs_desc;
+
+		/* Zero CR4.PCIDE before CR0.PG.  */
+		if (cr4 & X86_CR4_PCIDE) {
+			ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE);
+			cr4 &= ~X86_CR4_PCIDE;
+		}
+
+		/* A 32-bit code segment is required to clear EFER.LMA.  */
+		memset(&cs_desc, 0, sizeof(cs_desc));
+		cs_desc.type = 0xb;
+		cs_desc.s = cs_desc.g = cs_desc.p = 1;
+		ctxt->ops->set_segment(ctxt, 0, &cs_desc, 0, VCPU_SREG_CS);
+	}
+
+	/* For the 64-bit case, this will clear EFER.LMA.  */
 	cr0 = ctxt->ops->get_cr(ctxt, 0);
 	if (cr0 & X86_CR0_PE)
 		ctxt->ops->set_cr(ctxt, 0, cr0 & ~(X86_CR0_PG | X86_CR0_PE));
-	cr4 = ctxt->ops->get_cr(ctxt, 4);
+
+	/* Now clear CR4.PAE (which must be done before clearing EFER.LME).  */
 	if (cr4 & X86_CR4_PAE)
 		ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE);
+
+	/* And finally go back to 32-bit mode.  */
 	efer = 0;
 	ctxt->ops->set_msr(ctxt, MSR_EFER, efer);
 
@@ -4455,7 +4474,7 @@ static const struct opcode twobyte_table[256] = {
 	F(DstMem | SrcReg | Src2CL | ModRM, em_shld), N, N,
 	/* 0xA8 - 0xAF */
 	I(Stack | Src2GS, em_push_sreg), I(Stack | Src2GS, em_pop_sreg),
-	II(No64 | EmulateOnUD | ImplicitOps, em_rsm, rsm),
+	II(EmulateOnUD | ImplicitOps, em_rsm, rsm),
 	F(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_bts),
 	F(DstMem | SrcReg | Src2ImmByte | ModRM, em_shrd),
 	F(DstMem | SrcReg | Src2CL | ModRM, em_shrd),
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index a8160d2ae362..62cf8c915e95 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -41,6 +41,7 @@ static bool kvm_hv_msr_partition_wide(u32 msr)
 	case HV_X64_MSR_TIME_REF_COUNT:
 	case HV_X64_MSR_CRASH_CTL:
 	case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
+	case HV_X64_MSR_RESET:
 		r = true;
 		break;
 	}
@@ -163,6 +164,12 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
 						 data);
 	case HV_X64_MSR_CRASH_CTL:
 		return kvm_hv_msr_set_crash_ctl(vcpu, data, host);
+	case HV_X64_MSR_RESET:
+		if (data == 1) {
+			vcpu_debug(vcpu, "hyper-v reset requested\n");
+			kvm_make_request(KVM_REQ_HV_RESET, vcpu);
+		}
+		break;
 	default:
 		vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n",
 			    msr, data);
@@ -171,7 +178,16 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
 	return 0;
 }
 
-static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
+/* Calculate cpu time spent by current task in 100ns units */
+static u64 current_task_runtime_100ns(void)
+{
+	cputime_t utime, stime;
+
+	task_cputime_adjusted(current, &utime, &stime);
+	return div_u64(cputime_to_nsecs(utime + stime), 100);
+}
+
+static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
 {
 	struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv;
 
@@ -205,6 +221,11 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		return kvm_hv_vapic_msr_write(vcpu, APIC_ICR, data);
 	case HV_X64_MSR_TPR:
 		return kvm_hv_vapic_msr_write(vcpu, APIC_TASKPRI, data);
+	case HV_X64_MSR_VP_RUNTIME:
+		if (!host)
+			return 1;
+		hv->runtime_offset = data - current_task_runtime_100ns();
+		break;
 	default:
 		vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n",
 			    msr, data);
@@ -241,6 +262,9 @@ static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 						 pdata);
 	case HV_X64_MSR_CRASH_CTL:
 		return kvm_hv_msr_get_crash_ctl(vcpu, pdata);
+	case HV_X64_MSR_RESET:
+		data = 0;
+		break;
 	default:
 		vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
 		return 1;
@@ -277,6 +301,9 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case HV_X64_MSR_APIC_ASSIST_PAGE:
 		data = hv->hv_vapic;
 		break;
+	case HV_X64_MSR_VP_RUNTIME:
+		data = current_task_runtime_100ns() + hv->runtime_offset;
+		break;
 	default:
 		vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
 		return 1;
@@ -295,7 +322,7 @@ int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
 		mutex_unlock(&vcpu->kvm->lock);
 		return r;
 	} else
-		return kvm_hv_set_msr(vcpu, msr, data);
+		return kvm_hv_set_msr(vcpu, msr, data, host);
 }
 
 int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index f90952f64e79..08116ff227cc 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -35,6 +35,7 @@
 #include <linux/kvm_host.h>
 #include <linux/slab.h>
 
+#include "ioapic.h"
 #include "irq.h"
 #include "i8254.h"
 #include "x86.h"
@@ -333,7 +334,8 @@ static void create_pit_timer(struct kvm *kvm, u32 val, int is_period)
 	struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state;
 	s64 interval;
 
-	if (!irqchip_in_kernel(kvm) || ps->flags & KVM_PIT_FLAGS_HPET_LEGACY)
+	if (!ioapic_in_kernel(kvm) ||
+	    ps->flags & KVM_PIT_FLAGS_HPET_LEGACY)
 		return;
 
 	interval = muldiv64(val, NSEC_PER_SEC, KVM_PIT_FREQ);
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 856f79105bb5..88d0a92d3f94 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -233,21 +233,7 @@ static void kvm_ioapic_inject_all(struct kvm_ioapic *ioapic, unsigned long irr)
 }
 
 
-static void update_handled_vectors(struct kvm_ioapic *ioapic)
-{
-	DECLARE_BITMAP(handled_vectors, 256);
-	int i;
-
-	memset(handled_vectors, 0, sizeof(handled_vectors));
-	for (i = 0; i < IOAPIC_NUM_PINS; ++i)
-		__set_bit(ioapic->redirtbl[i].fields.vector, handled_vectors);
-	memcpy(ioapic->handled_vectors, handled_vectors,
-	       sizeof(handled_vectors));
-	smp_wmb();
-}
-
-void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap,
-			u32 *tmr)
+void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
 {
 	struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic;
 	union kvm_ioapic_redirect_entry *e;
@@ -260,13 +246,11 @@ void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap,
 		    kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index) ||
 		    index == RTC_GSI) {
 			if (kvm_apic_match_dest(vcpu, NULL, 0,
-				e->fields.dest_id, e->fields.dest_mode)) {
+			             e->fields.dest_id, e->fields.dest_mode) ||
+			    (e->fields.trig_mode == IOAPIC_EDGE_TRIG &&
+			     kvm_apic_pending_eoi(vcpu, e->fields.vector)))
 				__set_bit(e->fields.vector,
 					(unsigned long *)eoi_exit_bitmap);
-				if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG)
-					__set_bit(e->fields.vector,
-						(unsigned long *)tmr);
-			}
 		}
 	}
 	spin_unlock(&ioapic->lock);
@@ -315,7 +299,6 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 			e->bits |= (u32) val;
 			e->fields.remote_irr = 0;
 		}
-		update_handled_vectors(ioapic);
 		mask_after = e->fields.mask;
 		if (mask_before != mask_after)
 			kvm_fire_mask_notifiers(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index, mask_after);
@@ -599,7 +582,6 @@ static void kvm_ioapic_reset(struct kvm_ioapic *ioapic)
 	ioapic->id = 0;
 	memset(ioapic->irq_eoi, 0x00, IOAPIC_NUM_PINS);
 	rtc_irq_eoi_tracking_reset(ioapic);
-	update_handled_vectors(ioapic);
 }
 
 static const struct kvm_io_device_ops ioapic_mmio_ops = {
@@ -628,8 +610,10 @@ int kvm_ioapic_init(struct kvm *kvm)
 	if (ret < 0) {
 		kvm->arch.vioapic = NULL;
 		kfree(ioapic);
+		return ret;
 	}
 
+	kvm_vcpu_request_scan_ioapic(kvm);
 	return ret;
 }
 
@@ -666,7 +650,6 @@ int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state)
 	memcpy(ioapic, state, sizeof(struct kvm_ioapic_state));
 	ioapic->irr = 0;
 	ioapic->irr_delivered = 0;
-	update_handled_vectors(ioapic);
 	kvm_vcpu_request_scan_ioapic(kvm);
 	kvm_ioapic_inject_all(ioapic, state->irr);
 	spin_unlock(&ioapic->lock);
diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h
index ca0b0b4e6256..084617d37c74 100644
--- a/arch/x86/kvm/ioapic.h
+++ b/arch/x86/kvm/ioapic.h
@@ -9,6 +9,7 @@ struct kvm;
 struct kvm_vcpu;
 
 #define IOAPIC_NUM_PINS  KVM_IOAPIC_NUM_PINS
+#define MAX_NR_RESERVED_IOAPIC_PINS KVM_MAX_IRQ_ROUTES
 #define IOAPIC_VERSION_ID 0x11	/* IOAPIC version */
 #define IOAPIC_EDGE_TRIG  0
 #define IOAPIC_LEVEL_TRIG 1
@@ -73,7 +74,6 @@ struct kvm_ioapic {
 	struct kvm *kvm;
 	void (*ack_notifier)(void *opaque, int irq);
 	spinlock_t lock;
-	DECLARE_BITMAP(handled_vectors, 256);
 	struct rtc_status rtc_status;
 	struct delayed_work eoi_inject;
 	u32 irq_eoi[IOAPIC_NUM_PINS];
@@ -98,11 +98,12 @@ static inline struct kvm_ioapic *ioapic_irqchip(struct kvm *kvm)
 	return kvm->arch.vioapic;
 }
 
-static inline bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector)
+static inline int ioapic_in_kernel(struct kvm *kvm)
 {
-	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
-	smp_rmb();
-	return test_bit(vector, ioapic->handled_vectors);
+	int ret;
+
+	ret = (ioapic_irqchip(kvm) != NULL);
+	return ret;
 }
 
 void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu);
@@ -120,7 +121,7 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 		struct kvm_lapic_irq *irq, unsigned long *dest_map);
 int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state);
 int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state);
-void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap,
-			u32 *tmr);
+void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
+void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
 
 #endif
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index a1ec6a50a05a..097060e33bd6 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -38,14 +38,27 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 EXPORT_SYMBOL(kvm_cpu_has_pending_timer);
 
 /*
+ * check if there is a pending userspace external interrupt
+ */
+static int pending_userspace_extint(struct kvm_vcpu *v)
+{
+	return v->arch.pending_external_vector != -1;
+}
+
+/*
  * check if there is pending interrupt from
  * non-APIC source without intack.
  */
 static int kvm_cpu_has_extint(struct kvm_vcpu *v)
 {
-	if (kvm_apic_accept_pic_intr(v))
-		return pic_irqchip(v->kvm)->output;	/* PIC */
-	else
+	u8 accept = kvm_apic_accept_pic_intr(v);
+
+	if (accept) {
+		if (irqchip_split(v->kvm))
+			return pending_userspace_extint(v);
+		else
+			return pic_irqchip(v->kvm)->output;
+	} else
 		return 0;
 }
 
@@ -57,13 +70,13 @@ static int kvm_cpu_has_extint(struct kvm_vcpu *v)
  */
 int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v)
 {
-	if (!irqchip_in_kernel(v->kvm))
+	if (!lapic_in_kernel(v))
 		return v->arch.interrupt.pending;
 
 	if (kvm_cpu_has_extint(v))
 		return 1;
 
-	if (kvm_apic_vid_enabled(v->kvm))
+	if (kvm_vcpu_apic_vid_enabled(v))
 		return 0;
 
 	return kvm_apic_has_interrupt(v) != -1; /* LAPIC */
@@ -75,7 +88,7 @@ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v)
  */
 int kvm_cpu_has_interrupt(struct kvm_vcpu *v)
 {
-	if (!irqchip_in_kernel(v->kvm))
+	if (!lapic_in_kernel(v))
 		return v->arch.interrupt.pending;
 
 	if (kvm_cpu_has_extint(v))
@@ -91,9 +104,16 @@ EXPORT_SYMBOL_GPL(kvm_cpu_has_interrupt);
  */
 static int kvm_cpu_get_extint(struct kvm_vcpu *v)
 {
-	if (kvm_cpu_has_extint(v))
-		return kvm_pic_read_irq(v->kvm); /* PIC */
-	return -1;
+	if (kvm_cpu_has_extint(v)) {
+		if (irqchip_split(v->kvm)) {
+			int vector = v->arch.pending_external_vector;
+
+			v->arch.pending_external_vector = -1;
+			return vector;
+		} else
+			return kvm_pic_read_irq(v->kvm); /* PIC */
+	} else
+		return -1;
 }
 
 /*
@@ -103,7 +123,7 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v)
 {
 	int vector;
 
-	if (!irqchip_in_kernel(v->kvm))
+	if (!lapic_in_kernel(v))
 		return v->arch.interrupt.nr;
 
 	vector = kvm_cpu_get_extint(v);
diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index 3d782a2c336a..ae5c78f2337d 100644
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -83,13 +83,38 @@ static inline struct kvm_pic *pic_irqchip(struct kvm *kvm)
 	return kvm->arch.vpic;
 }
 
+static inline int pic_in_kernel(struct kvm *kvm)
+{
+	int ret;
+
+	ret = (pic_irqchip(kvm) != NULL);
+	return ret;
+}
+
+static inline int irqchip_split(struct kvm *kvm)
+{
+	return kvm->arch.irqchip_split;
+}
+
 static inline int irqchip_in_kernel(struct kvm *kvm)
 {
 	struct kvm_pic *vpic = pic_irqchip(kvm);
+	bool ret;
+
+	ret = (vpic != NULL);
+	ret |= irqchip_split(kvm);
 
 	/* Read vpic before kvm->irq_routing.  */
 	smp_rmb();
-	return vpic != NULL;
+	return ret;
+}
+
+static inline int lapic_in_kernel(struct kvm_vcpu *vcpu)
+{
+	/* Same as irqchip_in_kernel(vcpu->kvm), but with less
+	 * pointer chasing and no unnecessary memory barriers.
+	 */
+	return vcpu->arch.apic != NULL;
 }
 
 void kvm_pic_reset(struct kvm_kpic_state *s);
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index 9efff9e5b58c..84b96d319909 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -91,8 +91,8 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 	return r;
 }
 
-static inline void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e,
-				   struct kvm_lapic_irq *irq)
+void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e,
+		     struct kvm_lapic_irq *irq)
 {
 	trace_kvm_msi_set_irq(e->msi.address_lo, e->msi.data);
 
@@ -108,6 +108,7 @@ static inline void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e,
 	irq->level = 1;
 	irq->shorthand = 0;
 }
+EXPORT_SYMBOL_GPL(kvm_set_msi_irq);
 
 int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 		struct kvm *kvm, int irq_source_id, int level, bool line_status)
@@ -123,12 +124,16 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 }
 
 
-static int kvm_set_msi_inatomic(struct kvm_kernel_irq_routing_entry *e,
-			 struct kvm *kvm)
+int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
+			      struct kvm *kvm, int irq_source_id, int level,
+			      bool line_status)
 {
 	struct kvm_lapic_irq irq;
 	int r;
 
+	if (unlikely(e->type != KVM_IRQ_ROUTING_MSI))
+		return -EWOULDBLOCK;
+
 	kvm_set_msi_irq(e, &irq);
 
 	if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL))
@@ -137,42 +142,6 @@ static int kvm_set_msi_inatomic(struct kvm_kernel_irq_routing_entry *e,
 		return -EWOULDBLOCK;
 }
 
-/*
- * Deliver an IRQ in an atomic context if we can, or return a failure,
- * user can retry in a process context.
- * Return value:
- *  -EWOULDBLOCK - Can't deliver in atomic context: retry in a process context.
- *  Other values - No need to retry.
- */
-int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level)
-{
-	struct kvm_kernel_irq_routing_entry entries[KVM_NR_IRQCHIPS];
-	struct kvm_kernel_irq_routing_entry *e;
-	int ret = -EINVAL;
-	int idx;
-
-	trace_kvm_set_irq(irq, level, irq_source_id);
-
-	/*
-	 * Injection into either PIC or IOAPIC might need to scan all CPUs,
-	 * which would need to be retried from thread context;  when same GSI
-	 * is connected to both PIC and IOAPIC, we'd have to report a
-	 * partial failure here.
-	 * Since there's no easy way to do this, we only support injecting MSI
-	 * which is limited to 1:1 GSI mapping.
-	 */
-	idx = srcu_read_lock(&kvm->irq_srcu);
-	if (kvm_irq_map_gsi(kvm, entries, irq) > 0) {
-		e = &entries[0];
-		if (likely(e->type == KVM_IRQ_ROUTING_MSI))
-			ret = kvm_set_msi_inatomic(e, kvm);
-		else
-			ret = -EWOULDBLOCK;
-	}
-	srcu_read_unlock(&kvm->irq_srcu, idx);
-	return ret;
-}
-
 int kvm_request_irq_source_id(struct kvm *kvm)
 {
 	unsigned long *bitmap = &kvm->arch.irq_sources_bitmap;
@@ -208,7 +177,7 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id)
 		goto unlock;
 	}
 	clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap);
-	if (!irqchip_in_kernel(kvm))
+	if (!ioapic_in_kernel(kvm))
 		goto unlock;
 
 	kvm_ioapic_clear_all(kvm->arch.vioapic, irq_source_id);
@@ -297,6 +266,33 @@ out:
 	return r;
 }
 
+bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq,
+			     struct kvm_vcpu **dest_vcpu)
+{
+	int i, r = 0;
+	struct kvm_vcpu *vcpu;
+
+	if (kvm_intr_is_single_vcpu_fast(kvm, irq, dest_vcpu))
+		return true;
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (!kvm_apic_present(vcpu))
+			continue;
+
+		if (!kvm_apic_match_dest(vcpu, NULL, irq->shorthand,
+					irq->dest_id, irq->dest_mode))
+			continue;
+
+		if (++r == 2)
+			return false;
+
+		*dest_vcpu = vcpu;
+	}
+
+	return r == 1;
+}
+EXPORT_SYMBOL_GPL(kvm_intr_is_single_vcpu);
+
 #define IOAPIC_ROUTING_ENTRY(irq) \
 	{ .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP,	\
 	  .u.irqchip = { .irqchip = KVM_IRQCHIP_IOAPIC, .pin = (irq) } }
@@ -328,3 +324,54 @@ int kvm_setup_default_irq_routing(struct kvm *kvm)
 	return kvm_set_irq_routing(kvm, default_routing,
 				   ARRAY_SIZE(default_routing), 0);
 }
+
+static const struct kvm_irq_routing_entry empty_routing[] = {};
+
+int kvm_setup_empty_irq_routing(struct kvm *kvm)
+{
+	return kvm_set_irq_routing(kvm, empty_routing, 0, 0);
+}
+
+void kvm_arch_irq_routing_update(struct kvm *kvm)
+{
+	if (ioapic_in_kernel(kvm) || !irqchip_in_kernel(kvm))
+		return;
+	kvm_make_scan_ioapic_request(kvm);
+}
+
+void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_kernel_irq_routing_entry *entry;
+	struct kvm_irq_routing_table *table;
+	u32 i, nr_ioapic_pins;
+	int idx;
+
+	/* kvm->irq_routing must be read after clearing
+	 * KVM_SCAN_IOAPIC. */
+	smp_mb();
+	idx = srcu_read_lock(&kvm->irq_srcu);
+	table = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
+	nr_ioapic_pins = min_t(u32, table->nr_rt_entries,
+			       kvm->arch.nr_reserved_ioapic_pins);
+	for (i = 0; i < nr_ioapic_pins; ++i) {
+		hlist_for_each_entry(entry, &table->map[i], link) {
+			u32 dest_id, dest_mode;
+			bool level;
+
+			if (entry->type != KVM_IRQ_ROUTING_MSI)
+				continue;
+			dest_id = (entry->msi.address_lo >> 12) & 0xff;
+			dest_mode = (entry->msi.address_lo >> 2) & 0x1;
+			level = entry->msi.data & MSI_DATA_TRIGGER_LEVEL;
+			if (level && kvm_apic_match_dest(vcpu, NULL, 0,
+						dest_id, dest_mode)) {
+				u32 vector = entry->msi.data & 0xff;
+
+				__set_bit(vector,
+					  (unsigned long *) eoi_exit_bitmap);
+			}
+		}
+	}
+	srcu_read_unlock(&kvm->irq_srcu, idx);
+}
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 8d9013c5e1ee..ecd4ea1d28a8 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -209,7 +209,7 @@ out:
 	if (old)
 		kfree_rcu(old, rcu);
 
-	kvm_vcpu_request_scan_ioapic(kvm);
+	kvm_make_scan_ioapic_request(kvm);
 }
 
 static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val)
@@ -348,6 +348,8 @@ void kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir)
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
 	__kvm_apic_update_irr(pir, apic->regs);
+
+	kvm_make_request(KVM_REQ_EVENT, vcpu);
 }
 EXPORT_SYMBOL_GPL(kvm_apic_update_irr);
 
@@ -390,7 +392,7 @@ static inline void apic_clear_irr(int vec, struct kvm_lapic *apic)
 
 	vcpu = apic->vcpu;
 
-	if (unlikely(kvm_apic_vid_enabled(vcpu->kvm))) {
+	if (unlikely(kvm_vcpu_apic_vid_enabled(vcpu))) {
 		/* try to update RVI */
 		apic_clear_vector(vec, apic->regs + APIC_IRR);
 		kvm_make_request(KVM_REQ_EVENT, vcpu);
@@ -551,15 +553,6 @@ static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu)
 	__clear_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention);
 }
 
-void kvm_apic_update_tmr(struct kvm_vcpu *vcpu, u32 *tmr)
-{
-	struct kvm_lapic *apic = vcpu->arch.apic;
-	int i;
-
-	for (i = 0; i < 8; i++)
-		apic_set_reg(apic, APIC_TMR + 0x10 * i, tmr[i]);
-}
-
 static void apic_update_ppr(struct kvm_lapic *apic)
 {
 	u32 tpr, isrv, ppr, old_ppr;
@@ -764,6 +757,65 @@ out:
 	return ret;
 }
 
+bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq,
+			struct kvm_vcpu **dest_vcpu)
+{
+	struct kvm_apic_map *map;
+	bool ret = false;
+	struct kvm_lapic *dst = NULL;
+
+	if (irq->shorthand)
+		return false;
+
+	rcu_read_lock();
+	map = rcu_dereference(kvm->arch.apic_map);
+
+	if (!map)
+		goto out;
+
+	if (irq->dest_mode == APIC_DEST_PHYSICAL) {
+		if (irq->dest_id == 0xFF)
+			goto out;
+
+		if (irq->dest_id >= ARRAY_SIZE(map->phys_map))
+			goto out;
+
+		dst = map->phys_map[irq->dest_id];
+		if (dst && kvm_apic_present(dst->vcpu))
+			*dest_vcpu = dst->vcpu;
+		else
+			goto out;
+	} else {
+		u16 cid;
+		unsigned long bitmap = 1;
+		int i, r = 0;
+
+		if (!kvm_apic_logical_map_valid(map))
+			goto out;
+
+		apic_logical_id(map, irq->dest_id, &cid, (u16 *)&bitmap);
+
+		if (cid >= ARRAY_SIZE(map->logical_map))
+			goto out;
+
+		for_each_set_bit(i, &bitmap, 16) {
+			dst = map->logical_map[cid][i];
+			if (++r == 2)
+				goto out;
+		}
+
+		if (dst && kvm_apic_present(dst->vcpu))
+			*dest_vcpu = dst->vcpu;
+		else
+			goto out;
+	}
+
+	ret = true;
+out:
+	rcu_read_unlock();
+	return ret;
+}
+
 /*
  * Add a pending IRQ into lapic.
  * Return 1 if successfully added and 0 if discarded.
@@ -781,6 +833,9 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 	case APIC_DM_LOWEST:
 		vcpu->arch.apic_arb_prio++;
 	case APIC_DM_FIXED:
+		if (unlikely(trig_mode && !level))
+			break;
+
 		/* FIXME add logic for vcpu on reset */
 		if (unlikely(!apic_enabled(apic)))
 			break;
@@ -790,6 +845,13 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 		if (dest_map)
 			__set_bit(vcpu->vcpu_id, dest_map);
 
+		if (apic_test_vector(vector, apic->regs + APIC_TMR) != !!trig_mode) {
+			if (trig_mode)
+				apic_set_vector(vector, apic->regs + APIC_TMR);
+			else
+				apic_clear_vector(vector, apic->regs + APIC_TMR);
+		}
+
 		if (kvm_x86_ops->deliver_posted_interrupt)
 			kvm_x86_ops->deliver_posted_interrupt(vcpu, vector);
 		else {
@@ -868,16 +930,32 @@ int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2)
 	return vcpu1->arch.apic_arb_prio - vcpu2->arch.apic_arb_prio;
 }
 
+static bool kvm_ioapic_handles_vector(struct kvm_lapic *apic, int vector)
+{
+	return test_bit(vector, (ulong *)apic->vcpu->arch.eoi_exit_bitmap);
+}
+
 static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector)
 {
-	if (kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) {
-		int trigger_mode;
-		if (apic_test_vector(vector, apic->regs + APIC_TMR))
-			trigger_mode = IOAPIC_LEVEL_TRIG;
-		else
-			trigger_mode = IOAPIC_EDGE_TRIG;
-		kvm_ioapic_update_eoi(apic->vcpu, vector, trigger_mode);
+	int trigger_mode;
+
+	/* Eoi the ioapic only if the ioapic doesn't own the vector. */
+	if (!kvm_ioapic_handles_vector(apic, vector))
+		return;
+
+	/* Request a KVM exit to inform the userspace IOAPIC. */
+	if (irqchip_split(apic->vcpu->kvm)) {
+		apic->vcpu->arch.pending_ioapic_eoi = vector;
+		kvm_make_request(KVM_REQ_IOAPIC_EOI_EXIT, apic->vcpu);
+		return;
 	}
+
+	if (apic_test_vector(vector, apic->regs + APIC_TMR))
+		trigger_mode = IOAPIC_LEVEL_TRIG;
+	else
+		trigger_mode = IOAPIC_EDGE_TRIG;
+
+	kvm_ioapic_update_eoi(apic->vcpu, vector, trigger_mode);
 }
 
 static int apic_set_eoi(struct kvm_lapic *apic)
@@ -1615,7 +1693,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
 		apic_set_reg(apic, APIC_ISR + 0x10 * i, 0);
 		apic_set_reg(apic, APIC_TMR + 0x10 * i, 0);
 	}
-	apic->irr_pending = kvm_apic_vid_enabled(vcpu->kvm);
+	apic->irr_pending = kvm_vcpu_apic_vid_enabled(vcpu);
 	apic->isr_count = kvm_x86_ops->hwapic_isr_update ? 1 : 0;
 	apic->highest_isr_cache = -1;
 	update_divide_count(apic);
@@ -1838,7 +1916,10 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu,
 		kvm_x86_ops->hwapic_isr_update(vcpu->kvm,
 				apic_find_highest_isr(apic));
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
-	kvm_rtc_eoi_tracking_restore_one(vcpu);
+	if (ioapic_in_kernel(vcpu->kvm))
+		kvm_rtc_eoi_tracking_restore_one(vcpu);
+
+	vcpu->arch.apic_arb_prio = 0;
 }
 
 void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu)
@@ -1922,7 +2003,7 @@ static void apic_sync_pv_eoi_to_guest(struct kvm_vcpu *vcpu,
 	    /* Cache not set: could be safe but we don't bother. */
 	    apic->highest_isr_cache == -1 ||
 	    /* Need EOI to update ioapic. */
-	    kvm_ioapic_handles_vector(vcpu->kvm, apic->highest_isr_cache)) {
+	    kvm_ioapic_handles_vector(apic, apic->highest_isr_cache)) {
 		/*
 		 * PV EOI was disabled by apic_sync_pv_eoi_from_guest
 		 * so we need not do anything here.
@@ -1978,7 +2059,7 @@ int kvm_x2apic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	u32 reg = (msr - APIC_BASE_MSR) << 4;
 
-	if (!irqchip_in_kernel(vcpu->kvm) || !apic_x2apic_mode(apic))
+	if (!lapic_in_kernel(vcpu) || !apic_x2apic_mode(apic))
 		return 1;
 
 	if (reg == APIC_ICR2)
@@ -1995,7 +2076,7 @@ int kvm_x2apic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	u32 reg = (msr - APIC_BASE_MSR) << 4, low, high = 0;
 
-	if (!irqchip_in_kernel(vcpu->kvm) || !apic_x2apic_mode(apic))
+	if (!lapic_in_kernel(vcpu) || !apic_x2apic_mode(apic))
 		return 1;
 
 	if (reg == APIC_DFR || reg == APIC_ICR2) {
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 764037991d26..fde8e35d5850 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -57,7 +57,6 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value);
 u64 kvm_lapic_get_base(struct kvm_vcpu *vcpu);
 void kvm_apic_set_version(struct kvm_vcpu *vcpu);
 
-void kvm_apic_update_tmr(struct kvm_vcpu *vcpu, u32 *tmr);
 void __kvm_apic_update_irr(u32 *pir, void *regs);
 void kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir);
 int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq,
@@ -144,9 +143,9 @@ static inline int apic_x2apic_mode(struct kvm_lapic *apic)
 	return apic->vcpu->arch.apic_base & X2APIC_ENABLE;
 }
 
-static inline bool kvm_apic_vid_enabled(struct kvm *kvm)
+static inline bool kvm_vcpu_apic_vid_enabled(struct kvm_vcpu *vcpu)
 {
-	return kvm_x86_ops->vm_has_apicv(kvm);
+	return kvm_x86_ops->cpu_uses_apicv(vcpu);
 }
 
 static inline bool kvm_apic_has_events(struct kvm_vcpu *vcpu)
@@ -169,4 +168,6 @@ bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector);
 
 void wait_lapic_expire(struct kvm_vcpu *vcpu);
 
+bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq,
+			struct kvm_vcpu **dest_vcpu);
 #endif
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index ff606f507913..7d85bcae3332 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -818,14 +818,11 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 	kvm->arch.indirect_shadow_pages--;
 }
 
-static int has_wrprotected_page(struct kvm_vcpu *vcpu,
-				gfn_t gfn,
-				int level)
+static int __has_wrprotected_page(gfn_t gfn, int level,
+				  struct kvm_memory_slot *slot)
 {
-	struct kvm_memory_slot *slot;
 	struct kvm_lpage_info *linfo;
 
-	slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
 	if (slot) {
 		linfo = lpage_info_slot(gfn, slot, level);
 		return linfo->write_count;
@@ -834,6 +831,14 @@ static int has_wrprotected_page(struct kvm_vcpu *vcpu,
 	return 1;
 }
 
+static int has_wrprotected_page(struct kvm_vcpu *vcpu, gfn_t gfn, int level)
+{
+	struct kvm_memory_slot *slot;
+
+	slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
+	return __has_wrprotected_page(gfn, level, slot);
+}
+
 static int host_mapping_level(struct kvm *kvm, gfn_t gfn)
 {
 	unsigned long page_size;
@@ -851,6 +856,17 @@ static int host_mapping_level(struct kvm *kvm, gfn_t gfn)
 	return ret;
 }
 
+static inline bool memslot_valid_for_gpte(struct kvm_memory_slot *slot,
+					  bool no_dirty_log)
+{
+	if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
+		return false;
+	if (no_dirty_log && slot->dirty_bitmap)
+		return false;
+
+	return true;
+}
+
 static struct kvm_memory_slot *
 gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn,
 			    bool no_dirty_log)
@@ -858,21 +874,25 @@ gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn,
 	struct kvm_memory_slot *slot;
 
 	slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
-	if (!slot || slot->flags & KVM_MEMSLOT_INVALID ||
-	      (no_dirty_log && slot->dirty_bitmap))
+	if (!memslot_valid_for_gpte(slot, no_dirty_log))
 		slot = NULL;
 
 	return slot;
 }
 
-static bool mapping_level_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t large_gfn)
-{
-	return !gfn_to_memslot_dirty_bitmap(vcpu, large_gfn, true);
-}
-
-static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn)
+static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn,
+			 bool *force_pt_level)
 {
 	int host_level, level, max_level;
+	struct kvm_memory_slot *slot;
+
+	if (unlikely(*force_pt_level))
+		return PT_PAGE_TABLE_LEVEL;
+
+	slot = kvm_vcpu_gfn_to_memslot(vcpu, large_gfn);
+	*force_pt_level = !memslot_valid_for_gpte(slot, true);
+	if (unlikely(*force_pt_level))
+		return PT_PAGE_TABLE_LEVEL;
 
 	host_level = host_mapping_level(vcpu->kvm, large_gfn);
 
@@ -882,7 +902,7 @@ static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn)
 	max_level = min(kvm_x86_ops->get_lpage_level(), host_level);
 
 	for (level = PT_DIRECTORY_LEVEL; level <= max_level; ++level)
-		if (has_wrprotected_page(vcpu, large_gfn, level))
+		if (__has_wrprotected_page(large_gfn, level, slot))
 			break;
 
 	return level - 1;
@@ -2962,14 +2982,13 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
 {
 	int r;
 	int level;
-	int force_pt_level;
+	bool force_pt_level = false;
 	pfn_t pfn;
 	unsigned long mmu_seq;
 	bool map_writable, write = error_code & PFERR_WRITE_MASK;
 
-	force_pt_level = mapping_level_dirty_bitmap(vcpu, gfn);
+	level = mapping_level(vcpu, gfn, &force_pt_level);
 	if (likely(!force_pt_level)) {
-		level = mapping_level(vcpu, gfn);
 		/*
 		 * This path builds a PAE pagetable - so we can map
 		 * 2mb pages at maximum. Therefore check if the level
@@ -2979,8 +2998,7 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
 			level = PT_DIRECTORY_LEVEL;
 
 		gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1);
-	} else
-		level = PT_PAGE_TABLE_LEVEL;
+	}
 
 	if (fast_page_fault(vcpu, v, level, error_code))
 		return 0;
@@ -3427,7 +3445,7 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
 
 static bool can_do_async_pf(struct kvm_vcpu *vcpu)
 {
-	if (unlikely(!irqchip_in_kernel(vcpu->kvm) ||
+	if (unlikely(!lapic_in_kernel(vcpu) ||
 		     kvm_event_needs_reinjection(vcpu)))
 		return false;
 
@@ -3476,7 +3494,7 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
 	pfn_t pfn;
 	int r;
 	int level;
-	int force_pt_level;
+	bool force_pt_level;
 	gfn_t gfn = gpa >> PAGE_SHIFT;
 	unsigned long mmu_seq;
 	int write = error_code & PFERR_WRITE_MASK;
@@ -3495,20 +3513,15 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
 	if (r)
 		return r;
 
-	if (mapping_level_dirty_bitmap(vcpu, gfn) ||
-	    !check_hugepage_cache_consistency(vcpu, gfn, PT_DIRECTORY_LEVEL))
-		force_pt_level = 1;
-	else
-		force_pt_level = 0;
-
+	force_pt_level = !check_hugepage_cache_consistency(vcpu, gfn,
+							   PT_DIRECTORY_LEVEL);
+	level = mapping_level(vcpu, gfn, &force_pt_level);
 	if (likely(!force_pt_level)) {
-		level = mapping_level(vcpu, gfn);
 		if (level > PT_DIRECTORY_LEVEL &&
 		    !check_hugepage_cache_consistency(vcpu, gfn, level))
 			level = PT_DIRECTORY_LEVEL;
 		gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1);
-	} else
-		level = PT_PAGE_TABLE_LEVEL;
+	}
 
 	if (fast_page_fault(vcpu, gpa, level, error_code))
 		return 0;
@@ -3706,7 +3719,7 @@ static void
 __reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check,
 			    int maxphyaddr, bool execonly)
 {
-	int pte;
+	u64 bad_mt_xwr;
 
 	rsvd_check->rsvd_bits_mask[0][3] =
 		rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 7);
@@ -3724,14 +3737,16 @@ __reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check,
 		rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 20);
 	rsvd_check->rsvd_bits_mask[1][0] = rsvd_check->rsvd_bits_mask[0][0];
 
-	for (pte = 0; pte < 64; pte++) {
-		int rwx_bits = pte & 7;
-		int mt = pte >> 3;
-		if (mt == 0x2 || mt == 0x3 || mt == 0x7 ||
-				rwx_bits == 0x2 || rwx_bits == 0x6 ||
-				(rwx_bits == 0x4 && !execonly))
-			rsvd_check->bad_mt_xwr |= (1ull << pte);
+	bad_mt_xwr = 0xFFull << (2 * 8);	/* bits 3..5 must not be 2 */
+	bad_mt_xwr |= 0xFFull << (3 * 8);	/* bits 3..5 must not be 3 */
+	bad_mt_xwr |= 0xFFull << (7 * 8);	/* bits 3..5 must not be 7 */
+	bad_mt_xwr |= REPEAT_BYTE(1ull << 2);	/* bits 0..2 must not be 010 */
+	bad_mt_xwr |= REPEAT_BYTE(1ull << 6);	/* bits 0..2 must not be 110 */
+	if (!execonly) {
+		/* bits 0..2 must not be 100 unless VMX capabilities allow it */
+		bad_mt_xwr |= REPEAT_BYTE(1ull << 4);
 	}
+	rsvd_check->bad_mt_xwr = bad_mt_xwr;
 }
 
 static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 736e6ab8784d..b41faa91a6f9 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -698,7 +698,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 	int r;
 	pfn_t pfn;
 	int level = PT_PAGE_TABLE_LEVEL;
-	int force_pt_level;
+	bool force_pt_level = false;
 	unsigned long mmu_seq;
 	bool map_writable, is_self_change_mapping;
 
@@ -743,15 +743,14 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 	is_self_change_mapping = FNAME(is_self_change_mapping)(vcpu,
 	      &walker, user_fault, &vcpu->arch.write_fault_to_shadow_pgtable);
 
-	if (walker.level >= PT_DIRECTORY_LEVEL)
-		force_pt_level = mapping_level_dirty_bitmap(vcpu, walker.gfn)
-		   || is_self_change_mapping;
-	else
-		force_pt_level = 1;
-	if (!force_pt_level) {
-		level = min(walker.level, mapping_level(vcpu, walker.gfn));
-		walker.gfn = walker.gfn & ~(KVM_PAGES_PER_HPAGE(level) - 1);
-	}
+	if (walker.level >= PT_DIRECTORY_LEVEL && !is_self_change_mapping) {
+		level = mapping_level(vcpu, walker.gfn, &force_pt_level);
+		if (likely(!force_pt_level)) {
+			level = min(walker.level, level);
+			walker.gfn = walker.gfn & ~(KVM_PAGES_PER_HPAGE(level) - 1);
+		}
+	} else
+		force_pt_level = true;
 
 	mmu_seq = vcpu->kvm->mmu_notifier_seq;
 	smp_rmb();
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 2f9ed1ff0632..f2c8e4917688 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -159,6 +159,9 @@ struct vcpu_svm {
 	u32 apf_reason;
 
 	u64  tsc_ratio;
+
+	/* cached guest cpuid flags for faster access */
+	bool nrips_enabled	: 1;
 };
 
 static DEFINE_PER_CPU(u64, current_tsc_ratio);
@@ -1086,7 +1089,7 @@ static u64 svm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
 	return target_tsc - tsc;
 }
 
-static void init_vmcb(struct vcpu_svm *svm, bool init_event)
+static void init_vmcb(struct vcpu_svm *svm)
 {
 	struct vmcb_control_area *control = &svm->vmcb->control;
 	struct vmcb_save_area *save = &svm->vmcb->save;
@@ -1157,8 +1160,7 @@ static void init_vmcb(struct vcpu_svm *svm, bool init_event)
 	init_sys_seg(&save->ldtr, SEG_TYPE_LDT);
 	init_sys_seg(&save->tr, SEG_TYPE_BUSY_TSS16);
 
-	if (!init_event)
-		svm_set_efer(&svm->vcpu, 0);
+	svm_set_efer(&svm->vcpu, 0);
 	save->dr6 = 0xffff0ff0;
 	kvm_set_rflags(&svm->vcpu, 2);
 	save->rip = 0x0000fff0;
@@ -1212,7 +1214,7 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 		if (kvm_vcpu_is_reset_bsp(&svm->vcpu))
 			svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP;
 	}
-	init_vmcb(svm, init_event);
+	init_vmcb(svm);
 
 	kvm_cpuid(vcpu, &eax, &dummy, &dummy, &dummy);
 	kvm_register_write(vcpu, VCPU_REGS_RDX, eax);
@@ -1268,7 +1270,7 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 	clear_page(svm->vmcb);
 	svm->vmcb_pa = page_to_pfn(page) << PAGE_SHIFT;
 	svm->asid_generation = 0;
-	init_vmcb(svm, false);
+	init_vmcb(svm);
 
 	svm_init_osvw(&svm->vcpu);
 
@@ -1890,7 +1892,7 @@ static int shutdown_interception(struct vcpu_svm *svm)
 	 * so reinitialize it.
 	 */
 	clear_page(svm->vmcb);
-	init_vmcb(svm, false);
+	init_vmcb(svm);
 
 	kvm_run->exit_reason = KVM_EXIT_SHUTDOWN;
 	return 0;
@@ -2365,7 +2367,9 @@ static int nested_svm_vmexit(struct vcpu_svm *svm)
 	nested_vmcb->control.exit_info_2       = vmcb->control.exit_info_2;
 	nested_vmcb->control.exit_int_info     = vmcb->control.exit_int_info;
 	nested_vmcb->control.exit_int_info_err = vmcb->control.exit_int_info_err;
-	nested_vmcb->control.next_rip          = vmcb->control.next_rip;
+
+	if (svm->nrips_enabled)
+		nested_vmcb->control.next_rip  = vmcb->control.next_rip;
 
 	/*
 	 * If we emulate a VMRUN/#VMEXIT in the same host #vmexit cycle we have
@@ -3060,7 +3064,7 @@ static int cr8_write_interception(struct vcpu_svm *svm)
 	u8 cr8_prev = kvm_get_cr8(&svm->vcpu);
 	/* instruction emulation calls kvm_set_cr8() */
 	r = cr_interception(svm);
-	if (irqchip_in_kernel(svm->vcpu.kvm))
+	if (lapic_in_kernel(&svm->vcpu))
 		return r;
 	if (cr8_prev <= kvm_get_cr8(&svm->vcpu))
 		return r;
@@ -3294,24 +3298,11 @@ static int msr_interception(struct vcpu_svm *svm)
 
 static int interrupt_window_interception(struct vcpu_svm *svm)
 {
-	struct kvm_run *kvm_run = svm->vcpu.run;
-
 	kvm_make_request(KVM_REQ_EVENT, &svm->vcpu);
 	svm_clear_vintr(svm);
 	svm->vmcb->control.int_ctl &= ~V_IRQ_MASK;
 	mark_dirty(svm->vmcb, VMCB_INTR);
 	++svm->vcpu.stat.irq_window_exits;
-	/*
-	 * If the user space waits to inject interrupts, exit as soon as
-	 * possible
-	 */
-	if (!irqchip_in_kernel(svm->vcpu.kvm) &&
-	    kvm_run->request_interrupt_window &&
-	    !kvm_cpu_has_interrupt(&svm->vcpu)) {
-		kvm_run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN;
-		return 0;
-	}
-
 	return 1;
 }
 
@@ -3659,12 +3650,12 @@ static void svm_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
 	return;
 }
 
-static int svm_vm_has_apicv(struct kvm *kvm)
+static int svm_cpu_uses_apicv(struct kvm_vcpu *vcpu)
 {
 	return 0;
 }
 
-static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
+static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu)
 {
 	return;
 }
@@ -4098,6 +4089,10 @@ static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
 
 static void svm_cpuid_update(struct kvm_vcpu *vcpu)
 {
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	/* Update nrips enabled cache */
+	svm->nrips_enabled = !!guest_cpuid_has_nrips(&svm->vcpu);
 }
 
 static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
@@ -4425,7 +4420,7 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.enable_irq_window = enable_irq_window,
 	.update_cr8_intercept = update_cr8_intercept,
 	.set_virtual_x2apic_mode = svm_set_virtual_x2apic_mode,
-	.vm_has_apicv = svm_vm_has_apicv,
+	.cpu_uses_apicv = svm_cpu_uses_apicv,
 	.load_eoi_exitmap = svm_load_eoi_exitmap,
 	.sync_pir_to_irr = svm_sync_pir_to_irr,
 
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 4eae7c35ddf5..120302511802 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -129,6 +129,24 @@ TRACE_EVENT(kvm_pio,
 );
 
 /*
+ * Tracepoint for fast mmio.
+ */
+TRACE_EVENT(kvm_fast_mmio,
+	TP_PROTO(u64 gpa),
+	TP_ARGS(gpa),
+
+	TP_STRUCT__entry(
+		__field(u64,	gpa)
+	),
+
+	TP_fast_assign(
+		__entry->gpa		= gpa;
+	),
+
+	TP_printk("fast mmio at gpa 0x%llx", __entry->gpa)
+);
+
+/*
  * Tracepoint for cpuid.
  */
 TRACE_EVENT(kvm_cpuid,
@@ -974,6 +992,39 @@ TRACE_EVENT(kvm_enter_smm,
 		  __entry->smbase)
 );
 
+/*
+ * Tracepoint for VT-d posted-interrupts.
+ */
+TRACE_EVENT(kvm_pi_irte_update,
+	TP_PROTO(unsigned int vcpu_id, unsigned int gsi,
+		 unsigned int gvec, u64 pi_desc_addr, bool set),
+	TP_ARGS(vcpu_id, gsi, gvec, pi_desc_addr, set),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	vcpu_id		)
+		__field(	unsigned int,	gsi		)
+		__field(	unsigned int,	gvec		)
+		__field(	u64,		pi_desc_addr	)
+		__field(	bool,		set		)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_id	= vcpu_id;
+		__entry->gsi		= gsi;
+		__entry->gvec		= gvec;
+		__entry->pi_desc_addr	= pi_desc_addr;
+		__entry->set		= set;
+	),
+
+	TP_printk("VT-d PI is %s for this irq, vcpu %u, gsi: 0x%x, "
+		  "gvec: 0x%x, pi_desc_addr: 0x%llx",
+		  __entry->set ? "enabled and being updated" : "disabled",
+		  __entry->vcpu_id,
+		  __entry->gsi,
+		  __entry->gvec,
+		  __entry->pi_desc_addr)
+);
+
 #endif /* _TRACE_KVM_H */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 6a8bc64566ab..5eb56ed77c1f 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -35,6 +35,7 @@
 #include "kvm_cache_regs.h"
 #include "x86.h"
 
+#include <asm/cpu.h>
 #include <asm/io.h>
 #include <asm/desc.h>
 #include <asm/vmx.h>
@@ -45,6 +46,7 @@
 #include <asm/debugreg.h>
 #include <asm/kexec.h>
 #include <asm/apic.h>
+#include <asm/irq_remapping.h>
 
 #include "trace.h"
 #include "pmu.h"
@@ -424,6 +426,9 @@ struct nested_vmx {
 	/* to migrate it to L2 if VM_ENTRY_LOAD_DEBUG_CONTROLS is off */
 	u64 vmcs01_debugctl;
 
+	u16 vpid02;
+	u16 last_vpid;
+
 	u32 nested_vmx_procbased_ctls_low;
 	u32 nested_vmx_procbased_ctls_high;
 	u32 nested_vmx_true_procbased_ctls_low;
@@ -440,14 +445,33 @@ struct nested_vmx {
 	u32 nested_vmx_misc_low;
 	u32 nested_vmx_misc_high;
 	u32 nested_vmx_ept_caps;
+	u32 nested_vmx_vpid_caps;
 };
 
 #define POSTED_INTR_ON  0
+#define POSTED_INTR_SN  1
+
 /* Posted-Interrupt Descriptor */
 struct pi_desc {
 	u32 pir[8];     /* Posted interrupt requested */
-	u32 control;	/* bit 0 of control is outstanding notification bit */
-	u32 rsvd[7];
+	union {
+		struct {
+				/* bit 256 - Outstanding Notification */
+			u16	on	: 1,
+				/* bit 257 - Suppress Notification */
+				sn	: 1,
+				/* bit 271:258 - Reserved */
+				rsvd_1	: 14;
+				/* bit 279:272 - Notification Vector */
+			u8	nv;
+				/* bit 287:280 - Reserved */
+			u8	rsvd_2;
+				/* bit 319:288 - Notification Destination */
+			u32	ndst;
+		};
+		u64 control;
+	};
+	u32 rsvd[6];
 } __aligned(64);
 
 static bool pi_test_and_set_on(struct pi_desc *pi_desc)
@@ -467,6 +491,30 @@ static int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc)
 	return test_and_set_bit(vector, (unsigned long *)pi_desc->pir);
 }
 
+static inline void pi_clear_sn(struct pi_desc *pi_desc)
+{
+	return clear_bit(POSTED_INTR_SN,
+			(unsigned long *)&pi_desc->control);
+}
+
+static inline void pi_set_sn(struct pi_desc *pi_desc)
+{
+	return set_bit(POSTED_INTR_SN,
+			(unsigned long *)&pi_desc->control);
+}
+
+static inline int pi_test_on(struct pi_desc *pi_desc)
+{
+	return test_bit(POSTED_INTR_ON,
+			(unsigned long *)&pi_desc->control);
+}
+
+static inline int pi_test_sn(struct pi_desc *pi_desc)
+{
+	return test_bit(POSTED_INTR_SN,
+			(unsigned long *)&pi_desc->control);
+}
+
 struct vcpu_vmx {
 	struct kvm_vcpu       vcpu;
 	unsigned long         host_rsp;
@@ -532,8 +580,6 @@ struct vcpu_vmx {
 	s64 vnmi_blocked_time;
 	u32 exit_reason;
 
-	bool rdtscp_enabled;
-
 	/* Posted interrupt descriptor */
 	struct pi_desc pi_desc;
 
@@ -563,6 +609,11 @@ static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)
 	return container_of(vcpu, struct vcpu_vmx, vcpu);
 }
 
+static struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu)
+{
+	return &(to_vmx(vcpu)->pi_desc);
+}
+
 #define VMCS12_OFFSET(x) offsetof(struct vmcs12, x)
 #define FIELD(number, name)	[number] = VMCS12_OFFSET(name)
 #define FIELD64(number, name)	[number] = VMCS12_OFFSET(name), \
@@ -809,7 +860,7 @@ static void kvm_cpu_vmxon(u64 addr);
 static void kvm_cpu_vmxoff(void);
 static bool vmx_mpx_supported(void);
 static bool vmx_xsaves_supported(void);
-static int vmx_vm_has_apicv(struct kvm *kvm);
+static int vmx_cpu_uses_apicv(struct kvm_vcpu *vcpu);
 static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr);
 static void vmx_set_segment(struct kvm_vcpu *vcpu,
 			    struct kvm_segment *var, int seg);
@@ -831,6 +882,13 @@ static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
 static DEFINE_PER_CPU(struct list_head, loaded_vmcss_on_cpu);
 static DEFINE_PER_CPU(struct desc_ptr, host_gdt);
 
+/*
+ * We maintian a per-CPU linked-list of vCPU, so in wakeup_handler() we
+ * can find which vCPU should be waken up.
+ */
+static DEFINE_PER_CPU(struct list_head, blocked_vcpu_on_cpu);
+static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock);
+
 static unsigned long *vmx_io_bitmap_a;
 static unsigned long *vmx_io_bitmap_b;
 static unsigned long *vmx_msr_bitmap_legacy;
@@ -946,9 +1004,9 @@ static inline bool cpu_has_vmx_tpr_shadow(void)
 	return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW;
 }
 
-static inline bool vm_need_tpr_shadow(struct kvm *kvm)
+static inline bool cpu_need_tpr_shadow(struct kvm_vcpu *vcpu)
 {
-	return (cpu_has_vmx_tpr_shadow()) && (irqchip_in_kernel(kvm));
+	return cpu_has_vmx_tpr_shadow() && lapic_in_kernel(vcpu);
 }
 
 static inline bool cpu_has_secondary_exec_ctrls(void)
@@ -983,7 +1041,8 @@ static inline bool cpu_has_vmx_virtual_intr_delivery(void)
 
 static inline bool cpu_has_vmx_posted_intr(void)
 {
-	return vmcs_config.pin_based_exec_ctrl & PIN_BASED_POSTED_INTR;
+	return IS_ENABLED(CONFIG_X86_LOCAL_APIC) &&
+		vmcs_config.pin_based_exec_ctrl & PIN_BASED_POSTED_INTR;
 }
 
 static inline bool cpu_has_vmx_apicv(void)
@@ -1062,9 +1121,9 @@ static inline bool cpu_has_vmx_ple(void)
 		SECONDARY_EXEC_PAUSE_LOOP_EXITING;
 }
 
-static inline bool vm_need_virtualize_apic_accesses(struct kvm *kvm)
+static inline bool cpu_need_virtualize_apic_accesses(struct kvm_vcpu *vcpu)
 {
-	return flexpriority_enabled && irqchip_in_kernel(kvm);
+	return flexpriority_enabled && lapic_in_kernel(vcpu);
 }
 
 static inline bool cpu_has_vmx_vpid(void)
@@ -1157,6 +1216,11 @@ static inline bool nested_cpu_has_virt_x2apic_mode(struct vmcs12 *vmcs12)
 	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE);
 }
 
+static inline bool nested_cpu_has_vpid(struct vmcs12 *vmcs12)
+{
+	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_VPID);
+}
+
 static inline bool nested_cpu_has_apic_reg_virt(struct vmcs12 *vmcs12)
 {
 	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_APIC_REGISTER_VIRT);
@@ -1337,13 +1401,13 @@ static void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs)
 			 __loaded_vmcs_clear, loaded_vmcs, 1);
 }
 
-static inline void vpid_sync_vcpu_single(struct vcpu_vmx *vmx)
+static inline void vpid_sync_vcpu_single(int vpid)
 {
-	if (vmx->vpid == 0)
+	if (vpid == 0)
 		return;
 
 	if (cpu_has_vmx_invvpid_single())
-		__invvpid(VMX_VPID_EXTENT_SINGLE_CONTEXT, vmx->vpid, 0);
+		__invvpid(VMX_VPID_EXTENT_SINGLE_CONTEXT, vpid, 0);
 }
 
 static inline void vpid_sync_vcpu_global(void)
@@ -1352,10 +1416,10 @@ static inline void vpid_sync_vcpu_global(void)
 		__invvpid(VMX_VPID_EXTENT_ALL_CONTEXT, 0, 0);
 }
 
-static inline void vpid_sync_context(struct vcpu_vmx *vmx)
+static inline void vpid_sync_context(int vpid)
 {
 	if (cpu_has_vmx_invvpid_single())
-		vpid_sync_vcpu_single(vmx);
+		vpid_sync_vcpu_single(vpid);
 	else
 		vpid_sync_vcpu_global();
 }
@@ -1895,6 +1959,52 @@ static void vmx_load_host_state(struct vcpu_vmx *vmx)
 	preempt_enable();
 }
 
+static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
+{
+	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+	struct pi_desc old, new;
+	unsigned int dest;
+
+	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
+		!irq_remapping_cap(IRQ_POSTING_CAP))
+		return;
+
+	do {
+		old.control = new.control = pi_desc->control;
+
+		/*
+		 * If 'nv' field is POSTED_INTR_WAKEUP_VECTOR, there
+		 * are two possible cases:
+		 * 1. After running 'pre_block', context switch
+		 *    happened. For this case, 'sn' was set in
+		 *    vmx_vcpu_put(), so we need to clear it here.
+		 * 2. After running 'pre_block', we were blocked,
+		 *    and woken up by some other guy. For this case,
+		 *    we don't need to do anything, 'pi_post_block'
+		 *    will do everything for us. However, we cannot
+		 *    check whether it is case #1 or case #2 here
+		 *    (maybe, not needed), so we also clear sn here,
+		 *    I think it is not a big deal.
+		 */
+		if (pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR) {
+			if (vcpu->cpu != cpu) {
+				dest = cpu_physical_id(cpu);
+
+				if (x2apic_enabled())
+					new.ndst = dest;
+				else
+					new.ndst = (dest << 8) & 0xFF00;
+			}
+
+			/* set 'NV' to 'notification vector' */
+			new.nv = POSTED_INTR_VECTOR;
+		}
+
+		/* Allow posting non-urgent interrupts */
+		new.sn = 0;
+	} while (cmpxchg(&pi_desc->control, old.control,
+			new.control) != old.control);
+}
 /*
  * Switches to specified vcpu, until a matching vcpu_put(), but assumes
  * vcpu mutex is already taken.
@@ -1945,10 +2055,27 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */
 		vmx->loaded_vmcs->cpu = cpu;
 	}
+
+	vmx_vcpu_pi_load(vcpu, cpu);
+}
+
+static void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu)
+{
+	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+
+	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
+		!irq_remapping_cap(IRQ_POSTING_CAP))
+		return;
+
+	/* Set SN when the vCPU is preempted */
+	if (vcpu->preempted)
+		pi_set_sn(pi_desc);
 }
 
 static void vmx_vcpu_put(struct kvm_vcpu *vcpu)
 {
+	vmx_vcpu_pi_put(vcpu);
+
 	__vmx_load_host_state(to_vmx(vcpu));
 	if (!vmm_exclusive) {
 		__loaded_vmcs_clear(to_vmx(vcpu)->loaded_vmcs);
@@ -2207,7 +2334,7 @@ static void setup_msrs(struct vcpu_vmx *vmx)
 		if (index >= 0)
 			move_msr_up(vmx, index, save_nmsrs++);
 		index = __find_msr_index(vmx, MSR_TSC_AUX);
-		if (index >= 0 && vmx->rdtscp_enabled)
+		if (index >= 0 && guest_cpuid_has_rdtscp(&vmx->vcpu))
 			move_msr_up(vmx, index, save_nmsrs++);
 		/*
 		 * MSR_STAR is only needed on long mode guests, and only
@@ -2377,7 +2504,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 	vmx->nested.nested_vmx_pinbased_ctls_high |=
 		PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR |
 		PIN_BASED_VMX_PREEMPTION_TIMER;
-	if (vmx_vm_has_apicv(vmx->vcpu.kvm))
+	if (vmx_cpu_uses_apicv(&vmx->vcpu))
 		vmx->nested.nested_vmx_pinbased_ctls_high |=
 			PIN_BASED_POSTED_INTR;
 
@@ -2471,10 +2598,12 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 		SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
 		SECONDARY_EXEC_RDTSCP |
 		SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
+		SECONDARY_EXEC_ENABLE_VPID |
 		SECONDARY_EXEC_APIC_REGISTER_VIRT |
 		SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
 		SECONDARY_EXEC_WBINVD_EXITING |
-		SECONDARY_EXEC_XSAVES;
+		SECONDARY_EXEC_XSAVES |
+		SECONDARY_EXEC_PCOMMIT;
 
 	if (enable_ept) {
 		/* nested EPT: emulate EPT also to L1 */
@@ -2493,6 +2622,12 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 	} else
 		vmx->nested.nested_vmx_ept_caps = 0;
 
+	if (enable_vpid)
+		vmx->nested.nested_vmx_vpid_caps = VMX_VPID_INVVPID_BIT |
+				VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT;
+	else
+		vmx->nested.nested_vmx_vpid_caps = 0;
+
 	if (enable_unrestricted_guest)
 		vmx->nested.nested_vmx_secondary_ctls_high |=
 			SECONDARY_EXEC_UNRESTRICTED_GUEST;
@@ -2608,7 +2743,8 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
 		break;
 	case MSR_IA32_VMX_EPT_VPID_CAP:
 		/* Currently, no nested vpid support */
-		*pdata = vmx->nested.nested_vmx_ept_caps;
+		*pdata = vmx->nested.nested_vmx_ept_caps |
+			((u64)vmx->nested.nested_vmx_vpid_caps << 32);
 		break;
 	default:
 		return 1;
@@ -2673,7 +2809,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		msr_info->data = vcpu->arch.ia32_xss;
 		break;
 	case MSR_TSC_AUX:
-		if (!to_vmx(vcpu)->rdtscp_enabled)
+		if (!guest_cpuid_has_rdtscp(vcpu))
 			return 1;
 		/* Otherwise falls through */
 	default:
@@ -2779,7 +2915,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			clear_atomic_switch_msr(vmx, MSR_IA32_XSS);
 		break;
 	case MSR_TSC_AUX:
-		if (!vmx->rdtscp_enabled)
+		if (!guest_cpuid_has_rdtscp(vcpu))
 			return 1;
 		/* Check reserved bit, higher 32 bits should be zero */
 		if ((data >> 32) != 0)
@@ -2874,6 +3010,8 @@ static int hardware_enable(void)
 		return -EBUSY;
 
 	INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu));
+	INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu));
+	spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
 
 	/*
 	 * Now we can enable the vmclear operation in kdump
@@ -3015,7 +3153,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
 			SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
 			SECONDARY_EXEC_SHADOW_VMCS |
 			SECONDARY_EXEC_XSAVES |
-			SECONDARY_EXEC_ENABLE_PML;
+			SECONDARY_EXEC_ENABLE_PML |
+			SECONDARY_EXEC_PCOMMIT;
 		if (adjust_vmx_controls(min2, opt2,
 					MSR_IA32_VMX_PROCBASED_CTLS2,
 					&_cpu_based_2nd_exec_control) < 0)
@@ -3441,9 +3580,9 @@ static void exit_lmode(struct kvm_vcpu *vcpu)
 
 #endif
 
-static void vmx_flush_tlb(struct kvm_vcpu *vcpu)
+static inline void __vmx_flush_tlb(struct kvm_vcpu *vcpu, int vpid)
 {
-	vpid_sync_context(to_vmx(vcpu));
+	vpid_sync_context(vpid);
 	if (enable_ept) {
 		if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
 			return;
@@ -3451,6 +3590,11 @@ static void vmx_flush_tlb(struct kvm_vcpu *vcpu)
 	}
 }
 
+static void vmx_flush_tlb(struct kvm_vcpu *vcpu)
+{
+	__vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid);
+}
+
 static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
 {
 	ulong cr0_guest_owned_bits = vcpu->arch.cr0_guest_owned_bits;
@@ -3644,20 +3788,21 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 		if (!is_paging(vcpu)) {
 			hw_cr4 &= ~X86_CR4_PAE;
 			hw_cr4 |= X86_CR4_PSE;
-			/*
-			 * SMEP/SMAP is disabled if CPU is in non-paging mode
-			 * in hardware. However KVM always uses paging mode to
-			 * emulate guest non-paging mode with TDP.
-			 * To emulate this behavior, SMEP/SMAP needs to be
-			 * manually disabled when guest switches to non-paging
-			 * mode.
-			 */
-			hw_cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP);
 		} else if (!(cr4 & X86_CR4_PAE)) {
 			hw_cr4 &= ~X86_CR4_PAE;
 		}
 	}
 
+	if (!enable_unrestricted_guest && !is_paging(vcpu))
+		/*
+		 * SMEP/SMAP is disabled if CPU is in non-paging mode in
+		 * hardware.  However KVM always uses paging mode without
+		 * unrestricted guest.
+		 * To emulate this behavior, SMEP/SMAP needs to be manually
+		 * disabled when guest switches to non-paging mode.
+		 */
+		hw_cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP);
+
 	vmcs_writel(CR4_READ_SHADOW, cr4);
 	vmcs_writel(GUEST_CR4, hw_cr4);
 	return 0;
@@ -4146,29 +4291,28 @@ static int alloc_identity_pagetable(struct kvm *kvm)
 	return r;
 }
 
-static void allocate_vpid(struct vcpu_vmx *vmx)
+static int allocate_vpid(void)
 {
 	int vpid;
 
-	vmx->vpid = 0;
 	if (!enable_vpid)
-		return;
+		return 0;
 	spin_lock(&vmx_vpid_lock);
 	vpid = find_first_zero_bit(vmx_vpid_bitmap, VMX_NR_VPIDS);
-	if (vpid < VMX_NR_VPIDS) {
-		vmx->vpid = vpid;
+	if (vpid < VMX_NR_VPIDS)
 		__set_bit(vpid, vmx_vpid_bitmap);
-	}
+	else
+		vpid = 0;
 	spin_unlock(&vmx_vpid_lock);
+	return vpid;
 }
 
-static void free_vpid(struct vcpu_vmx *vmx)
+static void free_vpid(int vpid)
 {
-	if (!enable_vpid)
+	if (!enable_vpid || vpid == 0)
 		return;
 	spin_lock(&vmx_vpid_lock);
-	if (vmx->vpid != 0)
-		__clear_bit(vmx->vpid, vmx_vpid_bitmap);
+	__clear_bit(vpid, vmx_vpid_bitmap);
 	spin_unlock(&vmx_vpid_lock);
 }
 
@@ -4323,9 +4467,9 @@ static void vmx_disable_intercept_msr_write_x2apic(u32 msr)
 			msr, MSR_TYPE_W);
 }
 
-static int vmx_vm_has_apicv(struct kvm *kvm)
+static int vmx_cpu_uses_apicv(struct kvm_vcpu *vcpu)
 {
-	return enable_apicv && irqchip_in_kernel(kvm);
+	return enable_apicv && lapic_in_kernel(vcpu);
 }
 
 static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
@@ -4369,6 +4513,22 @@ static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu)
 {
 #ifdef CONFIG_SMP
 	if (vcpu->mode == IN_GUEST_MODE) {
+		struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+		/*
+		 * Currently, we don't support urgent interrupt,
+		 * all interrupts are recognized as non-urgent
+		 * interrupt, so we cannot post interrupts when
+		 * 'SN' is set.
+		 *
+		 * If the vcpu is in guest mode, it means it is
+		 * running instead of being scheduled out and
+		 * waiting in the run queue, and that's the only
+		 * case when 'SN' is set currently, warning if
+		 * 'SN' is set.
+		 */
+		WARN_ON_ONCE(pi_test_sn(&vmx->pi_desc));
+
 		apic->send_IPI_mask(get_cpu_mask(vcpu->cpu),
 				POSTED_INTR_VECTOR);
 		return true;
@@ -4505,7 +4665,7 @@ static u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx)
 {
 	u32 pin_based_exec_ctrl = vmcs_config.pin_based_exec_ctrl;
 
-	if (!vmx_vm_has_apicv(vmx->vcpu.kvm))
+	if (!vmx_cpu_uses_apicv(&vmx->vcpu))
 		pin_based_exec_ctrl &= ~PIN_BASED_POSTED_INTR;
 	return pin_based_exec_ctrl;
 }
@@ -4517,7 +4677,7 @@ static u32 vmx_exec_control(struct vcpu_vmx *vmx)
 	if (vmx->vcpu.arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)
 		exec_control &= ~CPU_BASED_MOV_DR_EXITING;
 
-	if (!vm_need_tpr_shadow(vmx->vcpu.kvm)) {
+	if (!cpu_need_tpr_shadow(&vmx->vcpu)) {
 		exec_control &= ~CPU_BASED_TPR_SHADOW;
 #ifdef CONFIG_X86_64
 		exec_control |= CPU_BASED_CR8_STORE_EXITING |
@@ -4534,7 +4694,7 @@ static u32 vmx_exec_control(struct vcpu_vmx *vmx)
 static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx)
 {
 	u32 exec_control = vmcs_config.cpu_based_2nd_exec_ctrl;
-	if (!vm_need_virtualize_apic_accesses(vmx->vcpu.kvm))
+	if (!cpu_need_virtualize_apic_accesses(&vmx->vcpu))
 		exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
 	if (vmx->vpid == 0)
 		exec_control &= ~SECONDARY_EXEC_ENABLE_VPID;
@@ -4548,7 +4708,7 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx)
 		exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST;
 	if (!ple_gap)
 		exec_control &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING;
-	if (!vmx_vm_has_apicv(vmx->vcpu.kvm))
+	if (!vmx_cpu_uses_apicv(&vmx->vcpu))
 		exec_control &= ~(SECONDARY_EXEC_APIC_REGISTER_VIRT |
 				  SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
 	exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
@@ -4558,8 +4718,12 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx)
 	   a current VMCS12
 	*/
 	exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS;
-	/* PML is enabled/disabled in creating/destorying vcpu */
-	exec_control &= ~SECONDARY_EXEC_ENABLE_PML;
+
+	if (!enable_pml)
+		exec_control &= ~SECONDARY_EXEC_ENABLE_PML;
+
+	/* Currently, we allow L1 guest to directly run pcommit instruction. */
+	exec_control &= ~SECONDARY_EXEC_PCOMMIT;
 
 	return exec_control;
 }
@@ -4604,12 +4768,11 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 
 	vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, vmx_exec_control(vmx));
 
-	if (cpu_has_secondary_exec_ctrls()) {
+	if (cpu_has_secondary_exec_ctrls())
 		vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
 				vmx_secondary_exec_control(vmx));
-	}
 
-	if (vmx_vm_has_apicv(vmx->vcpu.kvm)) {
+	if (vmx_cpu_uses_apicv(&vmx->vcpu)) {
 		vmcs_write64(EOI_EXIT_BITMAP0, 0);
 		vmcs_write64(EOI_EXIT_BITMAP1, 0);
 		vmcs_write64(EOI_EXIT_BITMAP2, 0);
@@ -4753,7 +4916,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 
 	if (cpu_has_vmx_tpr_shadow() && !init_event) {
 		vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0);
-		if (vm_need_tpr_shadow(vcpu->kvm))
+		if (cpu_need_tpr_shadow(vcpu))
 			vmcs_write64(VIRTUAL_APIC_PAGE_ADDR,
 				     __pa(vcpu->arch.apic->regs));
 		vmcs_write32(TPR_THRESHOLD, 0);
@@ -4761,7 +4924,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 
 	kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);
 
-	if (vmx_vm_has_apicv(vcpu->kvm))
+	if (vmx_cpu_uses_apicv(vcpu))
 		memset(&vmx->pi_desc, 0, sizeof(struct pi_desc));
 
 	if (vmx->vpid != 0)
@@ -4771,12 +4934,11 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	vmx_set_cr0(vcpu, cr0); /* enter rmode */
 	vmx->vcpu.arch.cr0 = cr0;
 	vmx_set_cr4(vcpu, 0);
-	if (!init_event)
-		vmx_set_efer(vcpu, 0);
+	vmx_set_efer(vcpu, 0);
 	vmx_fpu_activate(vcpu);
 	update_exception_bitmap(vcpu);
 
-	vpid_sync_context(vmx);
+	vpid_sync_context(vmx->vpid);
 }
 
 /*
@@ -5296,7 +5458,7 @@ static int handle_cr(struct kvm_vcpu *vcpu)
 				u8 cr8 = (u8)val;
 				err = kvm_set_cr8(vcpu, cr8);
 				kvm_complete_insn_gp(vcpu, err);
-				if (irqchip_in_kernel(vcpu->kvm))
+				if (lapic_in_kernel(vcpu))
 					return 1;
 				if (cr8_prev <= cr8)
 					return 1;
@@ -5510,17 +5672,6 @@ static int handle_interrupt_window(struct kvm_vcpu *vcpu)
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 
 	++vcpu->stat.irq_window_exits;
-
-	/*
-	 * If the user space waits to inject interrupts, exit as soon as
-	 * possible
-	 */
-	if (!irqchip_in_kernel(vcpu->kvm) &&
-	    vcpu->run->request_interrupt_window &&
-	    !kvm_cpu_has_interrupt(vcpu)) {
-		vcpu->run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN;
-		return 0;
-	}
 	return 1;
 }
 
@@ -5753,6 +5904,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
 	gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
 	if (!kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) {
 		skip_emulated_instruction(vcpu);
+		trace_kvm_fast_mmio(gpa);
 		return 1;
 	}
 
@@ -5910,6 +6062,25 @@ static void update_ple_window_actual_max(void)
 			                    ple_window_grow, INT_MIN);
 }
 
+/*
+ * Handler for POSTED_INTERRUPT_WAKEUP_VECTOR.
+ */
+static void wakeup_handler(void)
+{
+	struct kvm_vcpu *vcpu;
+	int cpu = smp_processor_id();
+
+	spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
+	list_for_each_entry(vcpu, &per_cpu(blocked_vcpu_on_cpu, cpu),
+			blocked_vcpu_list) {
+		struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+
+		if (pi_test_on(pi_desc) == 1)
+			kvm_vcpu_kick(vcpu);
+	}
+	spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
+}
+
 static __init int hardware_setup(void)
 {
 	int r = -ENOMEM, i, msr;
@@ -6096,6 +6267,8 @@ static __init int hardware_setup(void)
 		kvm_x86_ops->enable_log_dirty_pt_masked = NULL;
 	}
 
+	kvm_set_posted_intr_wakeup_handler(wakeup_handler);
+
 	return alloc_kvm_area();
 
 out8:
@@ -6627,7 +6800,6 @@ static int nested_vmx_check_permission(struct kvm_vcpu *vcpu)
 
 static inline void nested_release_vmcs12(struct vcpu_vmx *vmx)
 {
-	u32 exec_control;
 	if (vmx->nested.current_vmptr == -1ull)
 		return;
 
@@ -6640,9 +6812,8 @@ static inline void nested_release_vmcs12(struct vcpu_vmx *vmx)
 		   they were modified */
 		copy_shadow_to_vmcs12(vmx);
 		vmx->nested.sync_shadow_vmcs = false;
-		exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
-		exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS;
-		vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control);
+		vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
+				SECONDARY_EXEC_SHADOW_VMCS);
 		vmcs_write64(VMCS_LINK_POINTER, -1ull);
 	}
 	vmx->nested.posted_intr_nv = -1;
@@ -6662,6 +6833,7 @@ static void free_nested(struct vcpu_vmx *vmx)
 		return;
 
 	vmx->nested.vmxon = false;
+	free_vpid(vmx->nested.vpid02);
 	nested_release_vmcs12(vmx);
 	if (enable_shadow_vmcs)
 		free_vmcs(vmx->nested.current_shadow_vmcs);
@@ -7038,7 +7210,6 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	gpa_t vmptr;
-	u32 exec_control;
 
 	if (!nested_vmx_check_permission(vcpu))
 		return 1;
@@ -7070,9 +7241,8 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 		vmx->nested.current_vmcs12 = new_vmcs12;
 		vmx->nested.current_vmcs12_page = page;
 		if (enable_shadow_vmcs) {
-			exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
-			exec_control |= SECONDARY_EXEC_SHADOW_VMCS;
-			vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control);
+			vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
+				      SECONDARY_EXEC_SHADOW_VMCS);
 			vmcs_write64(VMCS_LINK_POINTER,
 				     __pa(vmx->nested.current_shadow_vmcs));
 			vmx->nested.sync_shadow_vmcs = true;
@@ -7178,7 +7348,63 @@ static int handle_invept(struct kvm_vcpu *vcpu)
 
 static int handle_invvpid(struct kvm_vcpu *vcpu)
 {
-	kvm_queue_exception(vcpu, UD_VECTOR);
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	u32 vmx_instruction_info;
+	unsigned long type, types;
+	gva_t gva;
+	struct x86_exception e;
+	int vpid;
+
+	if (!(vmx->nested.nested_vmx_secondary_ctls_high &
+	      SECONDARY_EXEC_ENABLE_VPID) ||
+			!(vmx->nested.nested_vmx_vpid_caps & VMX_VPID_INVVPID_BIT)) {
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return 1;
+	}
+
+	if (!nested_vmx_check_permission(vcpu))
+		return 1;
+
+	vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
+	type = kvm_register_readl(vcpu, (vmx_instruction_info >> 28) & 0xf);
+
+	types = (vmx->nested.nested_vmx_vpid_caps >> 8) & 0x7;
+
+	if (!(types & (1UL << type))) {
+		nested_vmx_failValid(vcpu,
+			VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
+		return 1;
+	}
+
+	/* according to the intel vmx instruction reference, the memory
+	 * operand is read even if it isn't needed (e.g., for type==global)
+	 */
+	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
+			vmx_instruction_info, false, &gva))
+		return 1;
+	if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vpid,
+				sizeof(u32), &e)) {
+		kvm_inject_page_fault(vcpu, &e);
+		return 1;
+	}
+
+	switch (type) {
+	case VMX_VPID_EXTENT_ALL_CONTEXT:
+		if (get_vmcs12(vcpu)->virtual_processor_id == 0) {
+			nested_vmx_failValid(vcpu,
+				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
+			return 1;
+		}
+		__vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02);
+		nested_vmx_succeed(vcpu);
+		break;
+	default:
+		/* Trap single context invalidation invvpid calls */
+		BUG_ON(1);
+		break;
+	}
+
+	skip_emulated_instruction(vcpu);
 	return 1;
 }
 
@@ -7207,6 +7433,13 @@ static int handle_pml_full(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+static int handle_pcommit(struct kvm_vcpu *vcpu)
+{
+	/* we never catch pcommit instruct for L1 guest. */
+	WARN_ON(1);
+	return 1;
+}
+
 /*
  * The exit handlers return 1 if the exit was handled fully and guest execution
  * may resume.  Otherwise they set the kvm_run parameter to indicate what needs
@@ -7257,6 +7490,7 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[EXIT_REASON_XSAVES]                  = handle_xsaves,
 	[EXIT_REASON_XRSTORS]                 = handle_xrstors,
 	[EXIT_REASON_PML_FULL]		      = handle_pml_full,
+	[EXIT_REASON_PCOMMIT]                 = handle_pcommit,
 };
 
 static const int kvm_vmx_max_exit_handlers =
@@ -7558,6 +7792,8 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 		 * the XSS exit bitmap in vmcs12.
 		 */
 		return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES);
+	case EXIT_REASON_PCOMMIT:
+		return nested_cpu_has2(vmcs12, SECONDARY_EXEC_PCOMMIT);
 	default:
 		return true;
 	}
@@ -7569,10 +7805,9 @@ static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2)
 	*info2 = vmcs_read32(VM_EXIT_INTR_INFO);
 }
 
-static int vmx_enable_pml(struct vcpu_vmx *vmx)
+static int vmx_create_pml_buffer(struct vcpu_vmx *vmx)
 {
 	struct page *pml_pg;
-	u32 exec_control;
 
 	pml_pg = alloc_page(GFP_KERNEL | __GFP_ZERO);
 	if (!pml_pg)
@@ -7583,24 +7818,15 @@ static int vmx_enable_pml(struct vcpu_vmx *vmx)
 	vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
 	vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
 
-	exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
-	exec_control |= SECONDARY_EXEC_ENABLE_PML;
-	vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control);
-
 	return 0;
 }
 
-static void vmx_disable_pml(struct vcpu_vmx *vmx)
+static void vmx_destroy_pml_buffer(struct vcpu_vmx *vmx)
 {
-	u32 exec_control;
-
-	ASSERT(vmx->pml_pg);
-	__free_page(vmx->pml_pg);
-	vmx->pml_pg = NULL;
-
-	exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
-	exec_control &= ~SECONDARY_EXEC_ENABLE_PML;
-	vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control);
+	if (vmx->pml_pg) {
+		__free_page(vmx->pml_pg);
+		vmx->pml_pg = NULL;
+	}
 }
 
 static void vmx_flush_pml_buffer(struct kvm_vcpu *vcpu)
@@ -7924,10 +8150,10 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
 	 * apicv
 	 */
 	if (!cpu_has_vmx_virtualize_x2apic_mode() ||
-				!vmx_vm_has_apicv(vcpu->kvm))
+				!vmx_cpu_uses_apicv(vcpu))
 		return;
 
-	if (!vm_need_tpr_shadow(vcpu->kvm))
+	if (!cpu_need_tpr_shadow(vcpu))
 		return;
 
 	sec_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
@@ -8029,9 +8255,10 @@ static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr)
 	}
 }
 
-static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
+static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu)
 {
-	if (!vmx_vm_has_apicv(vcpu->kvm))
+	u64 *eoi_exit_bitmap = vcpu->arch.eoi_exit_bitmap;
+	if (!vmx_cpu_uses_apicv(vcpu))
 		return;
 
 	vmcs_write64(EOI_EXIT_BITMAP0, eoi_exit_bitmap[0]);
@@ -8477,8 +8704,8 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
 	if (enable_pml)
-		vmx_disable_pml(vmx);
-	free_vpid(vmx);
+		vmx_destroy_pml_buffer(vmx);
+	free_vpid(vmx->vpid);
 	leave_guest_mode(vcpu);
 	vmx_load_vmcs01(vcpu);
 	free_nested(vmx);
@@ -8497,7 +8724,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	if (!vmx)
 		return ERR_PTR(-ENOMEM);
 
-	allocate_vpid(vmx);
+	vmx->vpid = allocate_vpid();
 
 	err = kvm_vcpu_init(&vmx->vcpu, kvm, id);
 	if (err)
@@ -8530,7 +8757,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	put_cpu();
 	if (err)
 		goto free_vmcs;
-	if (vm_need_virtualize_apic_accesses(kvm)) {
+	if (cpu_need_virtualize_apic_accesses(&vmx->vcpu)) {
 		err = alloc_apic_access_page(kvm);
 		if (err)
 			goto free_vmcs;
@@ -8545,8 +8772,10 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 			goto free_vmcs;
 	}
 
-	if (nested)
+	if (nested) {
 		nested_vmx_setup_ctls_msrs(vmx);
+		vmx->nested.vpid02 = allocate_vpid();
+	}
 
 	vmx->nested.posted_intr_nv = -1;
 	vmx->nested.current_vmptr = -1ull;
@@ -8559,7 +8788,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	 * for the guest, etc.
 	 */
 	if (enable_pml) {
-		err = vmx_enable_pml(vmx);
+		err = vmx_create_pml_buffer(vmx);
 		if (err)
 			goto free_vmcs;
 	}
@@ -8567,13 +8796,14 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	return &vmx->vcpu;
 
 free_vmcs:
+	free_vpid(vmx->nested.vpid02);
 	free_loaded_vmcs(vmx->loaded_vmcs);
 free_msrs:
 	kfree(vmx->guest_msrs);
 uninit_vcpu:
 	kvm_vcpu_uninit(&vmx->vcpu);
 free_vcpu:
-	free_vpid(vmx);
+	free_vpid(vmx->vpid);
 	kmem_cache_free(kvm_vcpu_cache, vmx);
 	return ERR_PTR(err);
 }
@@ -8648,49 +8878,67 @@ static int vmx_get_lpage_level(void)
 		return PT_PDPE_LEVEL;
 }
 
+static void vmcs_set_secondary_exec_control(u32 new_ctl)
+{
+	/*
+	 * These bits in the secondary execution controls field
+	 * are dynamic, the others are mostly based on the hypervisor
+	 * architecture and the guest's CPUID.  Do not touch the
+	 * dynamic bits.
+	 */
+	u32 mask =
+		SECONDARY_EXEC_SHADOW_VMCS |
+		SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
+		SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+
+	u32 cur_ctl = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
+
+	vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
+		     (new_ctl & ~mask) | (cur_ctl & mask));
+}
+
 static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	u32 exec_control;
+	u32 secondary_exec_ctl = vmx_secondary_exec_control(vmx);
 
-	vmx->rdtscp_enabled = false;
 	if (vmx_rdtscp_supported()) {
-		exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
-		if (exec_control & SECONDARY_EXEC_RDTSCP) {
-			best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
-			if (best && (best->edx & bit(X86_FEATURE_RDTSCP)))
-				vmx->rdtscp_enabled = true;
-			else {
-				exec_control &= ~SECONDARY_EXEC_RDTSCP;
-				vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
-						exec_control);
-			}
+		bool rdtscp_enabled = guest_cpuid_has_rdtscp(vcpu);
+		if (!rdtscp_enabled)
+			secondary_exec_ctl &= ~SECONDARY_EXEC_RDTSCP;
+
+		if (nested) {
+			if (rdtscp_enabled)
+				vmx->nested.nested_vmx_secondary_ctls_high |=
+					SECONDARY_EXEC_RDTSCP;
+			else
+				vmx->nested.nested_vmx_secondary_ctls_high &=
+					~SECONDARY_EXEC_RDTSCP;
 		}
-		if (nested && !vmx->rdtscp_enabled)
-			vmx->nested.nested_vmx_secondary_ctls_high &=
-				~SECONDARY_EXEC_RDTSCP;
 	}
 
 	/* Exposing INVPCID only when PCID is exposed */
 	best = kvm_find_cpuid_entry(vcpu, 0x7, 0);
 	if (vmx_invpcid_supported() &&
-	    best && (best->ebx & bit(X86_FEATURE_INVPCID)) &&
-	    guest_cpuid_has_pcid(vcpu)) {
-		exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
-		exec_control |= SECONDARY_EXEC_ENABLE_INVPCID;
-		vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
-			     exec_control);
-	} else {
-		if (cpu_has_secondary_exec_ctrls()) {
-			exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
-			exec_control &= ~SECONDARY_EXEC_ENABLE_INVPCID;
-			vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
-				     exec_control);
-		}
+	    (!best || !(best->ebx & bit(X86_FEATURE_INVPCID)) ||
+	    !guest_cpuid_has_pcid(vcpu))) {
+		secondary_exec_ctl &= ~SECONDARY_EXEC_ENABLE_INVPCID;
+
 		if (best)
 			best->ebx &= ~bit(X86_FEATURE_INVPCID);
 	}
+
+	vmcs_set_secondary_exec_control(secondary_exec_ctl);
+
+	if (static_cpu_has(X86_FEATURE_PCOMMIT) && nested) {
+		if (guest_cpuid_has_pcommit(vcpu))
+			vmx->nested.nested_vmx_secondary_ctls_high |=
+				SECONDARY_EXEC_PCOMMIT;
+		else
+			vmx->nested.nested_vmx_secondary_ctls_high &=
+				~SECONDARY_EXEC_PCOMMIT;
+	}
 }
 
 static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
@@ -9298,13 +9546,13 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 
 	if (cpu_has_secondary_exec_ctrls()) {
 		exec_control = vmx_secondary_exec_control(vmx);
-		if (!vmx->rdtscp_enabled)
-			exec_control &= ~SECONDARY_EXEC_RDTSCP;
+
 		/* Take the following fields only from vmcs12 */
 		exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
 				  SECONDARY_EXEC_RDTSCP |
 				  SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
-				  SECONDARY_EXEC_APIC_REGISTER_VIRT);
+				  SECONDARY_EXEC_APIC_REGISTER_VIRT |
+				  SECONDARY_EXEC_PCOMMIT);
 		if (nested_cpu_has(vmcs12,
 				CPU_BASED_ACTIVATE_SECONDARY_CONTROLS))
 			exec_control |= vmcs12->secondary_vm_exec_control;
@@ -9323,7 +9571,7 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 				vmcs_write64(APIC_ACCESS_ADDR,
 				  page_to_phys(vmx->nested.apic_access_page));
 		} else if (!(nested_cpu_has_virt_x2apic_mode(vmcs12)) &&
-			    (vm_need_virtualize_apic_accesses(vmx->vcpu.kvm))) {
+			    cpu_need_virtualize_apic_accesses(&vmx->vcpu)) {
 			exec_control |=
 				SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
 			kvm_vcpu_reload_apic_access_page(vcpu);
@@ -9433,12 +9681,24 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 
 	if (enable_vpid) {
 		/*
-		 * Trivially support vpid by letting L2s share their parent
-		 * L1's vpid. TODO: move to a more elaborate solution, giving
-		 * each L2 its own vpid and exposing the vpid feature to L1.
+		 * There is no direct mapping between vpid02 and vpid12, the
+		 * vpid02 is per-vCPU for L0 and reused while the value of
+		 * vpid12 is changed w/ one invvpid during nested vmentry.
+		 * The vpid12 is allocated by L1 for L2, so it will not
+		 * influence global bitmap(for vpid01 and vpid02 allocation)
+		 * even if spawn a lot of nested vCPUs.
 		 */
-		vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
-		vmx_flush_tlb(vcpu);
+		if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02) {
+			vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->nested.vpid02);
+			if (vmcs12->virtual_processor_id != vmx->nested.last_vpid) {
+				vmx->nested.last_vpid = vmcs12->virtual_processor_id;
+				__vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02);
+			}
+		} else {
+			vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
+			vmx_flush_tlb(vcpu);
+		}
+
 	}
 
 	if (nested_cpu_has_ept(vmcs12)) {
@@ -10278,6 +10538,201 @@ static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm,
 	kvm_mmu_clear_dirty_pt_masked(kvm, memslot, offset, mask);
 }
 
+/*
+ * This routine does the following things for vCPU which is going
+ * to be blocked if VT-d PI is enabled.
+ * - Store the vCPU to the wakeup list, so when interrupts happen
+ *   we can find the right vCPU to wake up.
+ * - Change the Posted-interrupt descriptor as below:
+ *      'NDST' <-- vcpu->pre_pcpu
+ *      'NV' <-- POSTED_INTR_WAKEUP_VECTOR
+ * - If 'ON' is set during this process, which means at least one
+ *   interrupt is posted for this vCPU, we cannot block it, in
+ *   this case, return 1, otherwise, return 0.
+ *
+ */
+static int vmx_pre_block(struct kvm_vcpu *vcpu)
+{
+	unsigned long flags;
+	unsigned int dest;
+	struct pi_desc old, new;
+	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+
+	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
+		!irq_remapping_cap(IRQ_POSTING_CAP))
+		return 0;
+
+	vcpu->pre_pcpu = vcpu->cpu;
+	spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock,
+			  vcpu->pre_pcpu), flags);
+	list_add_tail(&vcpu->blocked_vcpu_list,
+		      &per_cpu(blocked_vcpu_on_cpu,
+		      vcpu->pre_pcpu));
+	spin_unlock_irqrestore(&per_cpu(blocked_vcpu_on_cpu_lock,
+			       vcpu->pre_pcpu), flags);
+
+	do {
+		old.control = new.control = pi_desc->control;
+
+		/*
+		 * We should not block the vCPU if
+		 * an interrupt is posted for it.
+		 */
+		if (pi_test_on(pi_desc) == 1) {
+			spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock,
+					  vcpu->pre_pcpu), flags);
+			list_del(&vcpu->blocked_vcpu_list);
+			spin_unlock_irqrestore(
+					&per_cpu(blocked_vcpu_on_cpu_lock,
+					vcpu->pre_pcpu), flags);
+			vcpu->pre_pcpu = -1;
+
+			return 1;
+		}
+
+		WARN((pi_desc->sn == 1),
+		     "Warning: SN field of posted-interrupts "
+		     "is set before blocking\n");
+
+		/*
+		 * Since vCPU can be preempted during this process,
+		 * vcpu->cpu could be different with pre_pcpu, we
+		 * need to set pre_pcpu as the destination of wakeup
+		 * notification event, then we can find the right vCPU
+		 * to wakeup in wakeup handler if interrupts happen
+		 * when the vCPU is in blocked state.
+		 */
+		dest = cpu_physical_id(vcpu->pre_pcpu);
+
+		if (x2apic_enabled())
+			new.ndst = dest;
+		else
+			new.ndst = (dest << 8) & 0xFF00;
+
+		/* set 'NV' to 'wakeup vector' */
+		new.nv = POSTED_INTR_WAKEUP_VECTOR;
+	} while (cmpxchg(&pi_desc->control, old.control,
+			new.control) != old.control);
+
+	return 0;
+}
+
+static void vmx_post_block(struct kvm_vcpu *vcpu)
+{
+	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+	struct pi_desc old, new;
+	unsigned int dest;
+	unsigned long flags;
+
+	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
+		!irq_remapping_cap(IRQ_POSTING_CAP))
+		return;
+
+	do {
+		old.control = new.control = pi_desc->control;
+
+		dest = cpu_physical_id(vcpu->cpu);
+
+		if (x2apic_enabled())
+			new.ndst = dest;
+		else
+			new.ndst = (dest << 8) & 0xFF00;
+
+		/* Allow posting non-urgent interrupts */
+		new.sn = 0;
+
+		/* set 'NV' to 'notification vector' */
+		new.nv = POSTED_INTR_VECTOR;
+	} while (cmpxchg(&pi_desc->control, old.control,
+			new.control) != old.control);
+
+	if(vcpu->pre_pcpu != -1) {
+		spin_lock_irqsave(
+			&per_cpu(blocked_vcpu_on_cpu_lock,
+			vcpu->pre_pcpu), flags);
+		list_del(&vcpu->blocked_vcpu_list);
+		spin_unlock_irqrestore(
+			&per_cpu(blocked_vcpu_on_cpu_lock,
+			vcpu->pre_pcpu), flags);
+		vcpu->pre_pcpu = -1;
+	}
+}
+
+/*
+ * vmx_update_pi_irte - set IRTE for Posted-Interrupts
+ *
+ * @kvm: kvm
+ * @host_irq: host irq of the interrupt
+ * @guest_irq: gsi of the interrupt
+ * @set: set or unset PI
+ * returns 0 on success, < 0 on failure
+ */
+static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
+			      uint32_t guest_irq, bool set)
+{
+	struct kvm_kernel_irq_routing_entry *e;
+	struct kvm_irq_routing_table *irq_rt;
+	struct kvm_lapic_irq irq;
+	struct kvm_vcpu *vcpu;
+	struct vcpu_data vcpu_info;
+	int idx, ret = -EINVAL;
+
+	if (!kvm_arch_has_assigned_device(kvm) ||
+		!irq_remapping_cap(IRQ_POSTING_CAP))
+		return 0;
+
+	idx = srcu_read_lock(&kvm->irq_srcu);
+	irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
+	BUG_ON(guest_irq >= irq_rt->nr_rt_entries);
+
+	hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) {
+		if (e->type != KVM_IRQ_ROUTING_MSI)
+			continue;
+		/*
+		 * VT-d PI cannot support posting multicast/broadcast
+		 * interrupts to a vCPU, we still use interrupt remapping
+		 * for these kind of interrupts.
+		 *
+		 * For lowest-priority interrupts, we only support
+		 * those with single CPU as the destination, e.g. user
+		 * configures the interrupts via /proc/irq or uses
+		 * irqbalance to make the interrupts single-CPU.
+		 *
+		 * We will support full lowest-priority interrupt later.
+		 */
+
+		kvm_set_msi_irq(e, &irq);
+		if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu))
+			continue;
+
+		vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu));
+		vcpu_info.vector = irq.vector;
+
+		trace_kvm_pi_irte_update(vcpu->vcpu_id, e->gsi,
+				vcpu_info.vector, vcpu_info.pi_desc_addr, set);
+
+		if (set)
+			ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
+		else {
+			/* suppress notification event before unposting */
+			pi_set_sn(vcpu_to_pi_desc(vcpu));
+			ret = irq_set_vcpu_affinity(host_irq, NULL);
+			pi_clear_sn(vcpu_to_pi_desc(vcpu));
+		}
+
+		if (ret < 0) {
+			printk(KERN_INFO "%s: failed to update PI IRTE\n",
+					__func__);
+			goto out;
+		}
+	}
+
+	ret = 0;
+out:
+	srcu_read_unlock(&kvm->irq_srcu, idx);
+	return ret;
+}
+
 static struct kvm_x86_ops vmx_x86_ops = {
 	.cpu_has_kvm_support = cpu_has_kvm_support,
 	.disabled_by_bios = vmx_disabled_by_bios,
@@ -10347,7 +10802,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.update_cr8_intercept = update_cr8_intercept,
 	.set_virtual_x2apic_mode = vmx_set_virtual_x2apic_mode,
 	.set_apic_access_page_addr = vmx_set_apic_access_page_addr,
-	.vm_has_apicv = vmx_vm_has_apicv,
+	.cpu_uses_apicv = vmx_cpu_uses_apicv,
 	.load_eoi_exitmap = vmx_load_eoi_exitmap,
 	.hwapic_irr_update = vmx_hwapic_irr_update,
 	.hwapic_isr_update = vmx_hwapic_isr_update,
@@ -10394,7 +10849,12 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.flush_log_dirty = vmx_flush_log_dirty,
 	.enable_log_dirty_pt_masked = vmx_enable_log_dirty_pt_masked,
 
+	.pre_block = vmx_pre_block,
+	.post_block = vmx_post_block,
+
 	.pmu_ops = &intel_pmu_ops,
+
+	.update_pi_irte = vmx_update_pi_irte,
 };
 
 static int __init vmx_init(void)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index bda65690788e..4a6eff166fc6 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -51,6 +51,8 @@
 #include <linux/pci.h>
 #include <linux/timekeeper_internal.h>
 #include <linux/pvclock_gtod.h>
+#include <linux/kvm_irqfd.h>
+#include <linux/irqbypass.h>
 #include <trace/events/kvm.h>
 
 #define CREATE_TRACE_POINTS
@@ -64,6 +66,7 @@
 #include <asm/fpu/internal.h> /* Ugh! */
 #include <asm/pvclock.h>
 #include <asm/div64.h>
+#include <asm/irq_remapping.h>
 
 #define MAX_IO_MSRS 256
 #define KVM_MAX_MCE_BANKS 32
@@ -622,7 +625,9 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	if ((cr0 ^ old_cr0) & update_bits)
 		kvm_mmu_reset_context(vcpu);
 
-	if ((cr0 ^ old_cr0) & X86_CR0_CD)
+	if (((cr0 ^ old_cr0) & X86_CR0_CD) &&
+	    kvm_arch_has_noncoherent_dma(vcpu->kvm) &&
+	    !kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED))
 		kvm_zap_gfn_range(vcpu->kvm, 0, ~0ULL);
 
 	return 0;
@@ -789,7 +794,7 @@ int kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8)
 {
 	if (cr8 & CR8_RESERVED_BITS)
 		return 1;
-	if (irqchip_in_kernel(vcpu->kvm))
+	if (lapic_in_kernel(vcpu))
 		kvm_lapic_set_tpr(vcpu, cr8);
 	else
 		vcpu->arch.cr8 = cr8;
@@ -799,7 +804,7 @@ EXPORT_SYMBOL_GPL(kvm_set_cr8);
 
 unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu)
 {
-	if (irqchip_in_kernel(vcpu->kvm))
+	if (lapic_in_kernel(vcpu))
 		return kvm_lapic_get_cr8(vcpu);
 	else
 		return vcpu->arch.cr8;
@@ -953,6 +958,9 @@ static u32 emulated_msrs[] = {
 	HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC,
 	HV_X64_MSR_CRASH_P0, HV_X64_MSR_CRASH_P1, HV_X64_MSR_CRASH_P2,
 	HV_X64_MSR_CRASH_P3, HV_X64_MSR_CRASH_P4, HV_X64_MSR_CRASH_CTL,
+	HV_X64_MSR_RESET,
+	HV_X64_MSR_VP_INDEX,
+	HV_X64_MSR_VP_RUNTIME,
 	HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME,
 	MSR_KVM_PV_EOI_EN,
 
@@ -1898,6 +1906,8 @@ static void accumulate_steal_time(struct kvm_vcpu *vcpu)
 
 static void record_steal_time(struct kvm_vcpu *vcpu)
 {
+	accumulate_steal_time(vcpu);
+
 	if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
 		return;
 
@@ -2048,12 +2058,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (!(data & KVM_MSR_ENABLED))
 			break;
 
-		vcpu->arch.st.last_steal = current->sched_info.run_delay;
-
-		preempt_disable();
-		accumulate_steal_time(vcpu);
-		preempt_enable();
-
 		kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
 
 		break;
@@ -2449,6 +2453,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_ENABLE_CAP_VM:
 	case KVM_CAP_DISABLE_QUIRKS:
 	case KVM_CAP_SET_BOOT_CPU_ID:
+ 	case KVM_CAP_SPLIT_IRQCHIP:
 #ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
 	case KVM_CAP_ASSIGN_DEV_IRQ:
 	case KVM_CAP_PCI_2_3:
@@ -2628,7 +2633,6 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		vcpu->cpu = cpu;
 	}
 
-	accumulate_steal_time(vcpu);
 	kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
 }
 
@@ -2662,12 +2666,24 @@ static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
 {
 	if (irq->irq >= KVM_NR_INTERRUPTS)
 		return -EINVAL;
-	if (irqchip_in_kernel(vcpu->kvm))
+
+	if (!irqchip_in_kernel(vcpu->kvm)) {
+		kvm_queue_interrupt(vcpu, irq->irq, false);
+		kvm_make_request(KVM_REQ_EVENT, vcpu);
+		return 0;
+	}
+
+	/*
+	 * With in-kernel LAPIC, we only use this to inject EXTINT, so
+	 * fail for in-kernel 8259.
+	 */
+	if (pic_in_kernel(vcpu->kvm))
 		return -ENXIO;
 
-	kvm_queue_interrupt(vcpu, irq->irq, false);
-	kvm_make_request(KVM_REQ_EVENT, vcpu);
+	if (vcpu->arch.pending_external_vector != -1)
+		return -EEXIST;
 
+	vcpu->arch.pending_external_vector = irq->irq;
 	return 0;
 }
 
@@ -3176,7 +3192,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		struct kvm_vapic_addr va;
 
 		r = -EINVAL;
-		if (!irqchip_in_kernel(vcpu->kvm))
+		if (!lapic_in_kernel(vcpu))
 			goto out;
 		r = -EFAULT;
 		if (copy_from_user(&va, argp, sizeof va))
@@ -3425,41 +3441,35 @@ static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
 
 static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps)
 {
-	int r = 0;
-
 	mutex_lock(&kvm->arch.vpit->pit_state.lock);
 	memcpy(ps, &kvm->arch.vpit->pit_state, sizeof(struct kvm_pit_state));
 	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
-	return r;
+	return 0;
 }
 
 static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps)
 {
-	int r = 0;
-
 	mutex_lock(&kvm->arch.vpit->pit_state.lock);
 	memcpy(&kvm->arch.vpit->pit_state, ps, sizeof(struct kvm_pit_state));
 	kvm_pit_load_count(kvm, 0, ps->channels[0].count, 0);
 	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
-	return r;
+	return 0;
 }
 
 static int kvm_vm_ioctl_get_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps)
 {
-	int r = 0;
-
 	mutex_lock(&kvm->arch.vpit->pit_state.lock);
 	memcpy(ps->channels, &kvm->arch.vpit->pit_state.channels,
 		sizeof(ps->channels));
 	ps->flags = kvm->arch.vpit->pit_state.flags;
 	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
 	memset(&ps->reserved, 0, sizeof(ps->reserved));
-	return r;
+	return 0;
 }
 
 static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps)
 {
-	int r = 0, start = 0;
+	int start = 0;
 	u32 prev_legacy, cur_legacy;
 	mutex_lock(&kvm->arch.vpit->pit_state.lock);
 	prev_legacy = kvm->arch.vpit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY;
@@ -3471,7 +3481,7 @@ static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps)
 	kvm->arch.vpit->pit_state.flags = ps->flags;
 	kvm_pit_load_count(kvm, 0, kvm->arch.vpit->pit_state.channels[0].count, start);
 	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
-	return r;
+	return 0;
 }
 
 static int kvm_vm_ioctl_reinject(struct kvm *kvm,
@@ -3556,6 +3566,28 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 		kvm->arch.disabled_quirks = cap->args[0];
 		r = 0;
 		break;
+	case KVM_CAP_SPLIT_IRQCHIP: {
+		mutex_lock(&kvm->lock);
+		r = -EINVAL;
+		if (cap->args[0] > MAX_NR_RESERVED_IOAPIC_PINS)
+			goto split_irqchip_unlock;
+		r = -EEXIST;
+		if (irqchip_in_kernel(kvm))
+			goto split_irqchip_unlock;
+		if (atomic_read(&kvm->online_vcpus))
+			goto split_irqchip_unlock;
+		r = kvm_setup_empty_irq_routing(kvm);
+		if (r)
+			goto split_irqchip_unlock;
+		/* Pairs with irqchip_in_kernel. */
+		smp_wmb();
+		kvm->arch.irqchip_split = true;
+		kvm->arch.nr_reserved_ioapic_pins = cap->args[0];
+		r = 0;
+split_irqchip_unlock:
+		mutex_unlock(&kvm->lock);
+		break;
+	}
 	default:
 		r = -EINVAL;
 		break;
@@ -3669,7 +3701,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		}
 
 		r = -ENXIO;
-		if (!irqchip_in_kernel(kvm))
+		if (!irqchip_in_kernel(kvm) || irqchip_split(kvm))
 			goto get_irqchip_out;
 		r = kvm_vm_ioctl_get_irqchip(kvm, chip);
 		if (r)
@@ -3693,7 +3725,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		}
 
 		r = -ENXIO;
-		if (!irqchip_in_kernel(kvm))
+		if (!irqchip_in_kernel(kvm) || irqchip_split(kvm))
 			goto set_irqchip_out;
 		r = kvm_vm_ioctl_set_irqchip(kvm, chip);
 		if (r)
@@ -4060,6 +4092,15 @@ static int kvm_read_guest_virt_system(struct x86_emulate_ctxt *ctxt,
 	return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, 0, exception);
 }
 
+static int kvm_read_guest_phys_system(struct x86_emulate_ctxt *ctxt,
+		unsigned long addr, void *val, unsigned int bytes)
+{
+	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
+	int r = kvm_vcpu_read_guest(vcpu, addr, val, bytes);
+
+	return r < 0 ? X86EMUL_IO_NEEDED : X86EMUL_CONTINUE;
+}
+
 int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt,
 				       gva_t addr, void *val,
 				       unsigned int bytes,
@@ -4795,6 +4836,7 @@ static const struct x86_emulate_ops emulate_ops = {
 	.write_gpr           = emulator_write_gpr,
 	.read_std            = kvm_read_guest_virt_system,
 	.write_std           = kvm_write_guest_virt_system,
+	.read_phys           = kvm_read_guest_phys_system,
 	.fetch               = kvm_fetch_guest_virt,
 	.read_emulated       = emulator_read_emulated,
 	.write_emulated      = emulator_write_emulated,
@@ -5667,7 +5709,7 @@ void kvm_arch_exit(void)
 int kvm_vcpu_halt(struct kvm_vcpu *vcpu)
 {
 	++vcpu->stat.halt_exits;
-	if (irqchip_in_kernel(vcpu->kvm)) {
+	if (lapic_in_kernel(vcpu)) {
 		vcpu->arch.mp_state = KVM_MP_STATE_HALTED;
 		return 1;
 	} else {
@@ -5774,9 +5816,15 @@ static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt)
  */
 static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu)
 {
-	return (!irqchip_in_kernel(vcpu->kvm) && !kvm_cpu_has_interrupt(vcpu) &&
-		vcpu->run->request_interrupt_window &&
-		kvm_arch_interrupt_allowed(vcpu));
+	if (!vcpu->run->request_interrupt_window || pic_in_kernel(vcpu->kvm))
+		return false;
+
+	if (kvm_cpu_has_interrupt(vcpu))
+		return false;
+
+	return (irqchip_split(vcpu->kvm)
+		? kvm_apic_accept_pic_intr(vcpu)
+		: kvm_arch_interrupt_allowed(vcpu));
 }
 
 static void post_kvm_run_save(struct kvm_vcpu *vcpu)
@@ -5787,13 +5835,17 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu)
 	kvm_run->flags = is_smm(vcpu) ? KVM_RUN_X86_SMM : 0;
 	kvm_run->cr8 = kvm_get_cr8(vcpu);
 	kvm_run->apic_base = kvm_get_apic_base(vcpu);
-	if (irqchip_in_kernel(vcpu->kvm))
-		kvm_run->ready_for_interrupt_injection = 1;
-	else
+	if (!irqchip_in_kernel(vcpu->kvm))
 		kvm_run->ready_for_interrupt_injection =
 			kvm_arch_interrupt_allowed(vcpu) &&
 			!kvm_cpu_has_interrupt(vcpu) &&
 			!kvm_event_needs_reinjection(vcpu);
+	else if (!pic_in_kernel(vcpu->kvm))
+		kvm_run->ready_for_interrupt_injection =
+			kvm_apic_accept_pic_intr(vcpu) &&
+			!kvm_cpu_has_interrupt(vcpu);
+	else
+		kvm_run->ready_for_interrupt_injection = 1;
 }
 
 static void update_cr8_intercept(struct kvm_vcpu *vcpu)
@@ -6144,18 +6196,18 @@ static void process_smi(struct kvm_vcpu *vcpu)
 
 static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
 {
-	u64 eoi_exit_bitmap[4];
-	u32 tmr[8];
-
 	if (!kvm_apic_hw_enabled(vcpu->arch.apic))
 		return;
 
-	memset(eoi_exit_bitmap, 0, 32);
-	memset(tmr, 0, 32);
+	memset(vcpu->arch.eoi_exit_bitmap, 0, 256 / 8);
 
-	kvm_ioapic_scan_entry(vcpu, eoi_exit_bitmap, tmr);
-	kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap);
-	kvm_apic_update_tmr(vcpu, tmr);
+	if (irqchip_split(vcpu->kvm))
+		kvm_scan_ioapic_routes(vcpu, vcpu->arch.eoi_exit_bitmap);
+	else {
+		kvm_x86_ops->sync_pir_to_irr(vcpu);
+		kvm_ioapic_scan_entry(vcpu, vcpu->arch.eoi_exit_bitmap);
+	}
+	kvm_x86_ops->load_eoi_exitmap(vcpu);
 }
 
 static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
@@ -6168,7 +6220,7 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
 {
 	struct page *page = NULL;
 
-	if (!irqchip_in_kernel(vcpu->kvm))
+	if (!lapic_in_kernel(vcpu))
 		return;
 
 	if (!kvm_x86_ops->set_apic_access_page_addr)
@@ -6206,7 +6258,7 @@ void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
 static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 {
 	int r;
-	bool req_int_win = !irqchip_in_kernel(vcpu->kvm) &&
+	bool req_int_win = !lapic_in_kernel(vcpu) &&
 		vcpu->run->request_interrupt_window;
 	bool req_immediate_exit = false;
 
@@ -6258,6 +6310,17 @@ static int vcpu_enter_guest(struct kvm_vcpu *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,
+				     (void *) vcpu->arch.eoi_exit_bitmap)) {
+				vcpu->run->exit_reason = KVM_EXIT_IOAPIC_EOI;
+				vcpu->run->eoi.vector =
+						vcpu->arch.pending_ioapic_eoi;
+				r = 0;
+				goto out;
+			}
+		}
 		if (kvm_check_request(KVM_REQ_SCAN_IOAPIC, vcpu))
 			vcpu_scan_ioapic(vcpu);
 		if (kvm_check_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu))
@@ -6268,6 +6331,26 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			r = 0;
 			goto out;
 		}
+		if (kvm_check_request(KVM_REQ_HV_RESET, vcpu)) {
+			vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
+			vcpu->run->system_event.type = KVM_SYSTEM_EVENT_RESET;
+			r = 0;
+			goto out;
+		}
+	}
+
+	/*
+	 * 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 (kvm_x86_ops->hwapic_irr_update)
+			kvm_x86_ops->hwapic_irr_update(vcpu,
+				kvm_lapic_find_highest_irr(vcpu));
 	}
 
 	if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) {
@@ -6286,13 +6369,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			kvm_x86_ops->enable_irq_window(vcpu);
 
 		if (kvm_lapic_enabled(vcpu)) {
-			/*
-			 * Update architecture specific hints for APIC
-			 * virtual interrupt delivery.
-			 */
-			if (kvm_x86_ops->hwapic_irr_update)
-				kvm_x86_ops->hwapic_irr_update(vcpu,
-					kvm_lapic_find_highest_irr(vcpu));
 			update_cr8_intercept(vcpu);
 			kvm_lapic_sync_to_vapic(vcpu);
 		}
@@ -6428,10 +6504,15 @@ out:
 
 static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu)
 {
-	if (!kvm_arch_vcpu_runnable(vcpu)) {
+	if (!kvm_arch_vcpu_runnable(vcpu) &&
+	    (!kvm_x86_ops->pre_block || kvm_x86_ops->pre_block(vcpu) == 0)) {
 		srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
 		kvm_vcpu_block(vcpu);
 		vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
+
+		if (kvm_x86_ops->post_block)
+			kvm_x86_ops->post_block(vcpu);
+
 		if (!kvm_check_request(KVM_REQ_UNHALT, vcpu))
 			return 1;
 	}
@@ -6468,10 +6549,12 @@ static int vcpu_run(struct kvm_vcpu *vcpu)
 	vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
 
 	for (;;) {
-		if (kvm_vcpu_running(vcpu))
+		if (kvm_vcpu_running(vcpu)) {
 			r = vcpu_enter_guest(vcpu);
-		else
+		} else {
 			r = vcpu_block(kvm, vcpu);
+		}
+
 		if (r <= 0)
 			break;
 
@@ -6480,8 +6563,8 @@ static int vcpu_run(struct kvm_vcpu *vcpu)
 			kvm_inject_pending_timer_irqs(vcpu);
 
 		if (dm_request_for_irq_injection(vcpu)) {
-			r = -EINTR;
-			vcpu->run->exit_reason = KVM_EXIT_INTR;
+			r = 0;
+			vcpu->run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN;
 			++vcpu->stat.request_irq_exits;
 			break;
 		}
@@ -6608,7 +6691,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	}
 
 	/* re-sync apic's tpr */
-	if (!irqchip_in_kernel(vcpu->kvm)) {
+	if (!lapic_in_kernel(vcpu)) {
 		if (kvm_set_cr8(vcpu, kvm_run->cr8) != 0) {
 			r = -EINVAL;
 			goto out;
@@ -7308,7 +7391,7 @@ bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu)
 
 bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu)
 {
-	return irqchip_in_kernel(vcpu->kvm) == (vcpu->arch.apic != NULL);
+	return irqchip_in_kernel(vcpu->kvm) == lapic_in_kernel(vcpu);
 }
 
 struct static_key kvm_no_apic_vcpu __read_mostly;
@@ -7377,6 +7460,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	kvm_async_pf_hash_reset(vcpu);
 	kvm_pmu_init(vcpu);
 
+	vcpu->arch.pending_external_vector = -1;
+
 	return 0;
 
 fail_free_mce_banks:
@@ -7402,7 +7487,7 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 	kvm_mmu_destroy(vcpu);
 	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 	free_page((unsigned long)vcpu->arch.pio_data);
-	if (!irqchip_in_kernel(vcpu->kvm))
+	if (!lapic_in_kernel(vcpu))
 		static_key_slow_dec(&kvm_no_apic_vcpu);
 }
 
@@ -8029,7 +8114,59 @@ bool kvm_arch_has_noncoherent_dma(struct kvm *kvm)
 }
 EXPORT_SYMBOL_GPL(kvm_arch_has_noncoherent_dma);
 
+int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
+				      struct irq_bypass_producer *prod)
+{
+	struct kvm_kernel_irqfd *irqfd =
+		container_of(cons, struct kvm_kernel_irqfd, consumer);
+
+	if (kvm_x86_ops->update_pi_irte) {
+		irqfd->producer = prod;
+		return kvm_x86_ops->update_pi_irte(irqfd->kvm,
+				prod->irq, irqfd->gsi, 1);
+	}
+
+	return -EINVAL;
+}
+
+void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
+				      struct irq_bypass_producer *prod)
+{
+	int ret;
+	struct kvm_kernel_irqfd *irqfd =
+		container_of(cons, struct kvm_kernel_irqfd, consumer);
+
+	if (!kvm_x86_ops->update_pi_irte) {
+		WARN_ON(irqfd->producer != NULL);
+		return;
+	}
+
+	WARN_ON(irqfd->producer != prod);
+	irqfd->producer = NULL;
+
+	/*
+	 * When producer of consumer is unregistered, we change back to
+	 * remapped mode, so we can re-use the current implementation
+	 * when the irq is masked/disabed or the consumer side (KVM
+	 * int this case doesn't want to receive the interrupts.
+	*/
+	ret = kvm_x86_ops->update_pi_irte(irqfd->kvm, prod->irq, irqfd->gsi, 0);
+	if (ret)
+		printk(KERN_INFO "irq bypass consumer (token %p) unregistration"
+		       " fails: %d\n", irqfd->consumer.token, ret);
+}
+
+int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq,
+				   uint32_t guest_irq, bool set)
+{
+	if (!kvm_x86_ops->update_pi_irte)
+		return -EINVAL;
+
+	return kvm_x86_ops->update_pi_irte(kvm, host_irq, guest_irq, set);
+}
+
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_msr);
@@ -8044,3 +8181,4 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intercepts);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_write_tsc_offset);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_ple_window);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pml_full);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pi_irte_update);
author	Linus Torvalds <torvalds@linux-foundation.org>	2015-11-05 16:26:26 -0800
committer	Linus Torvalds <torvalds@linux-foundation.org>	2015-11-05 16:26:26 -0800
commit	933425fb0010bd02bd459b41e63082756818ffce (patch)
tree	1cbc6c2035b9dcff8cb265c9ac562cbee7c6bb82 /arch/x86
parent	Merge tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi (diff)
parent	KVM: VMX: Fix commit which broke PML (diff)
download	linux-dev-933425fb0010bd02bd459b41e63082756818ffce.tar.xz linux-dev-933425fb0010bd02bd459b41e63082756818ffce.zip