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

Pull KVM updates from Paolo Bonzini:
 "PPC changes will come next week.

   - s390: Support for runtime instrumentation within guests, support of
     248 VCPUs.

   - ARM: rewrite of the arm64 world switch in C, support for 16-bit VM
     identifiers.  Performance counter virtualization missed the boat.

   - x86: Support for more Hyper-V features (synthetic interrupt
     controller), MMU cleanups"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (115 commits)
  kvm: x86: Fix vmwrite to SECONDARY_VM_EXEC_CONTROL
  kvm/x86: Hyper-V SynIC timers tracepoints
  kvm/x86: Hyper-V SynIC tracepoints
  kvm/x86: Update SynIC timers on guest entry only
  kvm/x86: Skip SynIC vector check for QEMU side
  kvm/x86: Hyper-V fix SynIC timer disabling condition
  kvm/x86: Reorg stimer_expiration() to better control timer restart
  kvm/x86: Hyper-V unify stimer_start() and stimer_restart()
  kvm/x86: Drop stimer_stop() function
  kvm/x86: Hyper-V timers fix incorrect logical operation
  KVM: move architecture-dependent requests to arch/
  KVM: renumber vcpu->request bits
  KVM: document which architecture uses each request bit
  KVM: Remove unused KVM_REQ_KICK to save a bit in vcpu->requests
  kvm: x86: Check kvm_write_guest return value in kvm_write_wall_clock
  KVM: s390: implement the RI support of guest
  kvm/s390: drop unpaired smp_mb
  kvm: x86: fix comment about {mmu,nested_mmu}.gva_to_gpa
  KVM: x86: MMU: Use clear_page() instead of init_shadow_page_table()
  arm/arm64: KVM: Detect vGIC presence at runtime
  ...

17 files changed, 1719 insertions, 360 deletions

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 30cfd64295a0..44adbb819041 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -25,6 +25,7 @@
 #include <linux/pvclock_gtod.h>
 #include <linux/clocksource.h>
 #include <linux/irqbypass.h>
+#include <linux/hyperv.h>
 
 #include <asm/pvclock-abi.h>
 #include <asm/desc.h>
@@ -45,6 +46,31 @@
 
 #define KVM_IRQCHIP_NUM_PINS  KVM_IOAPIC_NUM_PINS
 
+/* x86-specific vcpu->requests bit members */
+#define KVM_REQ_MIGRATE_TIMER      8
+#define KVM_REQ_REPORT_TPR_ACCESS  9
+#define KVM_REQ_TRIPLE_FAULT      10
+#define KVM_REQ_MMU_SYNC          11
+#define KVM_REQ_CLOCK_UPDATE      12
+#define KVM_REQ_DEACTIVATE_FPU    13
+#define KVM_REQ_EVENT             14
+#define KVM_REQ_APF_HALT          15
+#define KVM_REQ_STEAL_UPDATE      16
+#define KVM_REQ_NMI               17
+#define KVM_REQ_PMU               18
+#define KVM_REQ_PMI               19
+#define KVM_REQ_SMI               20
+#define KVM_REQ_MASTERCLOCK_UPDATE 21
+#define KVM_REQ_MCLOCK_INPROGRESS 22
+#define KVM_REQ_SCAN_IOAPIC       23
+#define KVM_REQ_GLOBAL_CLOCK_UPDATE 24
+#define KVM_REQ_APIC_PAGE_RELOAD  25
+#define KVM_REQ_HV_CRASH          26
+#define KVM_REQ_IOAPIC_EOI_EXIT   27
+#define KVM_REQ_HV_RESET          28
+#define KVM_REQ_HV_EXIT           29
+#define KVM_REQ_HV_STIMER         30
+
 #define CR0_RESERVED_BITS                                               \
 	(~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \
 			  | X86_CR0_ET | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM \
@@ -213,6 +239,10 @@ union kvm_mmu_page_role {
 	};
 };
 
+struct kvm_rmap_head {
+	unsigned long val;
+};
+
 struct kvm_mmu_page {
 	struct list_head link;
 	struct hlist_node hash_link;
@@ -230,7 +260,7 @@ struct kvm_mmu_page {
 	bool unsync;
 	int root_count;          /* Currently serving as active root */
 	unsigned int unsync_children;
-	unsigned long parent_ptes;	/* Reverse mapping for parent_pte */
+	struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */
 
 	/* The page is obsolete if mmu_valid_gen != kvm->arch.mmu_valid_gen.  */
 	unsigned long mmu_valid_gen;
@@ -374,10 +404,38 @@ struct kvm_mtrr {
 	struct list_head head;
 };
 
+/* Hyper-V SynIC timer */
+struct kvm_vcpu_hv_stimer {
+	struct hrtimer timer;
+	int index;
+	u64 config;
+	u64 count;
+	u64 exp_time;
+	struct hv_message msg;
+	bool msg_pending;
+};
+
+/* Hyper-V synthetic interrupt controller (SynIC)*/
+struct kvm_vcpu_hv_synic {
+	u64 version;
+	u64 control;
+	u64 msg_page;
+	u64 evt_page;
+	atomic64_t sint[HV_SYNIC_SINT_COUNT];
+	atomic_t sint_to_gsi[HV_SYNIC_SINT_COUNT];
+	DECLARE_BITMAP(auto_eoi_bitmap, 256);
+	DECLARE_BITMAP(vec_bitmap, 256);
+	bool active;
+};
+
 /* Hyper-V per vcpu emulation context */
 struct kvm_vcpu_hv {
 	u64 hv_vapic;
 	s64 runtime_offset;
+	struct kvm_vcpu_hv_synic synic;
+	struct kvm_hyperv_exit exit;
+	struct kvm_vcpu_hv_stimer stimer[HV_SYNIC_STIMER_COUNT];
+	DECLARE_BITMAP(stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT);
 };
 
 struct kvm_vcpu_arch {
@@ -400,7 +458,8 @@ struct kvm_vcpu_arch {
 	u64 efer;
 	u64 apic_base;
 	struct kvm_lapic *apic;    /* kernel irqchip context */
-	u64 eoi_exit_bitmap[4];
+	bool apicv_active;
+	DECLARE_BITMAP(ioapic_handled_vectors, 256);
 	unsigned long apic_attention;
 	int32_t apic_arb_prio;
 	int mp_state;
@@ -589,7 +648,7 @@ struct kvm_lpage_info {
 };
 
 struct kvm_arch_memory_slot {
-	unsigned long *rmap[KVM_NR_PAGE_SIZES];
+	struct kvm_rmap_head *rmap[KVM_NR_PAGE_SIZES];
 	struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1];
 };
 
@@ -831,10 +890,11 @@ 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 (*cpu_uses_apicv)(struct kvm_vcpu *vcpu);
+	bool (*get_enable_apicv)(void);
+	void (*refresh_apicv_exec_ctrl)(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);
+	void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
 	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);
@@ -1086,6 +1146,8 @@ gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva,
 gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva,
 				struct x86_exception *exception);
 
+void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu);
+
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
 
 int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code,
@@ -1231,6 +1293,9 @@ u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc);
 unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu);
 bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip);
 
+void kvm_make_mclock_inprogress_request(struct kvm *kvm);
+void kvm_make_scan_ioapic_request(struct kvm *kvm);
+
 void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
 				     struct kvm_async_pf *work);
 void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h
index 040d4083c24f..7956412d09bd 100644
--- a/arch/x86/include/uapi/asm/hyperv.h
+++ b/arch/x86/include/uapi/asm/hyperv.h
@@ -269,4 +269,96 @@ typedef struct _HV_REFERENCE_TSC_PAGE {
 #define HV_SYNIC_SINT_AUTO_EOI		(1ULL << 17)
 #define HV_SYNIC_SINT_VECTOR_MASK	(0xFF)
 
+#define HV_SYNIC_STIMER_COUNT		(4)
+
+/* Define synthetic interrupt controller message constants. */
+#define HV_MESSAGE_SIZE			(256)
+#define HV_MESSAGE_PAYLOAD_BYTE_COUNT	(240)
+#define HV_MESSAGE_PAYLOAD_QWORD_COUNT	(30)
+
+/* Define hypervisor message types. */
+enum hv_message_type {
+	HVMSG_NONE			= 0x00000000,
+
+	/* Memory access messages. */
+	HVMSG_UNMAPPED_GPA		= 0x80000000,
+	HVMSG_GPA_INTERCEPT		= 0x80000001,
+
+	/* Timer notification messages. */
+	HVMSG_TIMER_EXPIRED			= 0x80000010,
+
+	/* Error messages. */
+	HVMSG_INVALID_VP_REGISTER_VALUE	= 0x80000020,
+	HVMSG_UNRECOVERABLE_EXCEPTION	= 0x80000021,
+	HVMSG_UNSUPPORTED_FEATURE		= 0x80000022,
+
+	/* Trace buffer complete messages. */
+	HVMSG_EVENTLOG_BUFFERCOMPLETE	= 0x80000040,
+
+	/* Platform-specific processor intercept messages. */
+	HVMSG_X64_IOPORT_INTERCEPT		= 0x80010000,
+	HVMSG_X64_MSR_INTERCEPT		= 0x80010001,
+	HVMSG_X64_CPUID_INTERCEPT		= 0x80010002,
+	HVMSG_X64_EXCEPTION_INTERCEPT	= 0x80010003,
+	HVMSG_X64_APIC_EOI			= 0x80010004,
+	HVMSG_X64_LEGACY_FP_ERROR		= 0x80010005
+};
+
+/* Define synthetic interrupt controller message flags. */
+union hv_message_flags {
+	__u8 asu8;
+	struct {
+		__u8 msg_pending:1;
+		__u8 reserved:7;
+	};
+};
+
+/* Define port identifier type. */
+union hv_port_id {
+	__u32 asu32;
+	struct {
+		__u32 id:24;
+		__u32 reserved:8;
+	} u;
+};
+
+/* Define synthetic interrupt controller message header. */
+struct hv_message_header {
+	__u32 message_type;
+	__u8 payload_size;
+	union hv_message_flags message_flags;
+	__u8 reserved[2];
+	union {
+		__u64 sender;
+		union hv_port_id port;
+	};
+};
+
+/* Define synthetic interrupt controller message format. */
+struct hv_message {
+	struct hv_message_header header;
+	union {
+		__u64 payload[HV_MESSAGE_PAYLOAD_QWORD_COUNT];
+	} u;
+};
+
+/* Define the synthetic interrupt message page layout. */
+struct hv_message_page {
+	struct hv_message sint_message[HV_SYNIC_SINT_COUNT];
+};
+
+/* Define timer message payload structure. */
+struct hv_timer_message_payload {
+	__u32 timer_index;
+	__u32 reserved;
+	__u64 expiration_time;	/* When the timer expired */
+	__u64 delivery_time;	/* When the message was delivered */
+};
+
+#define HV_STIMER_ENABLE		(1ULL << 0)
+#define HV_STIMER_PERIODIC		(1ULL << 1)
+#define HV_STIMER_LAZY			(1ULL << 2)
+#define HV_STIMER_AUTOENABLE		(1ULL << 3)
+#define HV_STIMER_SINT(config)		(__u8)(((config) >> 16) & 0x0F)
+
 #endif
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 62cf8c915e95..c58ba67175ac 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -23,13 +23,665 @@
 
 #include "x86.h"
 #include "lapic.h"
+#include "ioapic.h"
 #include "hyperv.h"
 
 #include <linux/kvm_host.h>
+#include <linux/highmem.h>
+#include <asm/apicdef.h>
 #include <trace/events/kvm.h>
 
 #include "trace.h"
 
+static inline u64 synic_read_sint(struct kvm_vcpu_hv_synic *synic, int sint)
+{
+	return atomic64_read(&synic->sint[sint]);
+}
+
+static inline int synic_get_sint_vector(u64 sint_value)
+{
+	if (sint_value & HV_SYNIC_SINT_MASKED)
+		return -1;
+	return sint_value & HV_SYNIC_SINT_VECTOR_MASK;
+}
+
+static bool synic_has_vector_connected(struct kvm_vcpu_hv_synic *synic,
+				      int vector)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(synic->sint); i++) {
+		if (synic_get_sint_vector(synic_read_sint(synic, i)) == vector)
+			return true;
+	}
+	return false;
+}
+
+static bool synic_has_vector_auto_eoi(struct kvm_vcpu_hv_synic *synic,
+				     int vector)
+{
+	int i;
+	u64 sint_value;
+
+	for (i = 0; i < ARRAY_SIZE(synic->sint); i++) {
+		sint_value = synic_read_sint(synic, i);
+		if (synic_get_sint_vector(sint_value) == vector &&
+		    sint_value & HV_SYNIC_SINT_AUTO_EOI)
+			return true;
+	}
+	return false;
+}
+
+static int synic_set_sint(struct kvm_vcpu_hv_synic *synic, int sint,
+			  u64 data, bool host)
+{
+	int vector;
+
+	vector = data & HV_SYNIC_SINT_VECTOR_MASK;
+	if (vector < 16 && !host)
+		return 1;
+	/*
+	 * Guest may configure multiple SINTs to use the same vector, so
+	 * we maintain a bitmap of vectors handled by synic, and a
+	 * bitmap of vectors with auto-eoi behavior.  The bitmaps are
+	 * updated here, and atomically queried on fast paths.
+	 */
+
+	atomic64_set(&synic->sint[sint], data);
+
+	if (synic_has_vector_connected(synic, vector))
+		__set_bit(vector, synic->vec_bitmap);
+	else
+		__clear_bit(vector, synic->vec_bitmap);
+
+	if (synic_has_vector_auto_eoi(synic, vector))
+		__set_bit(vector, synic->auto_eoi_bitmap);
+	else
+		__clear_bit(vector, synic->auto_eoi_bitmap);
+
+	/* Load SynIC vectors into EOI exit bitmap */
+	kvm_make_request(KVM_REQ_SCAN_IOAPIC, synic_to_vcpu(synic));
+	return 0;
+}
+
+static struct kvm_vcpu_hv_synic *synic_get(struct kvm *kvm, u32 vcpu_id)
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vcpu_hv_synic *synic;
+
+	if (vcpu_id >= atomic_read(&kvm->online_vcpus))
+		return NULL;
+	vcpu = kvm_get_vcpu(kvm, vcpu_id);
+	if (!vcpu)
+		return NULL;
+	synic = vcpu_to_synic(vcpu);
+	return (synic->active) ? synic : NULL;
+}
+
+static void synic_clear_sint_msg_pending(struct kvm_vcpu_hv_synic *synic,
+					u32 sint)
+{
+	struct kvm_vcpu *vcpu = synic_to_vcpu(synic);
+	struct page *page;
+	gpa_t gpa;
+	struct hv_message *msg;
+	struct hv_message_page *msg_page;
+
+	gpa = synic->msg_page & PAGE_MASK;
+	page = kvm_vcpu_gfn_to_page(vcpu, gpa >> PAGE_SHIFT);
+	if (is_error_page(page)) {
+		vcpu_err(vcpu, "Hyper-V SynIC can't get msg page, gpa 0x%llx\n",
+			 gpa);
+		return;
+	}
+	msg_page = kmap_atomic(page);
+
+	msg = &msg_page->sint_message[sint];
+	msg->header.message_flags.msg_pending = 0;
+
+	kunmap_atomic(msg_page);
+	kvm_release_page_dirty(page);
+	kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT);
+}
+
+static void kvm_hv_notify_acked_sint(struct kvm_vcpu *vcpu, u32 sint)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_vcpu_hv_synic *synic = vcpu_to_synic(vcpu);
+	struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu);
+	struct kvm_vcpu_hv_stimer *stimer;
+	int gsi, idx, stimers_pending;
+
+	trace_kvm_hv_notify_acked_sint(vcpu->vcpu_id, sint);
+
+	if (synic->msg_page & HV_SYNIC_SIMP_ENABLE)
+		synic_clear_sint_msg_pending(synic, sint);
+
+	/* Try to deliver pending Hyper-V SynIC timers messages */
+	stimers_pending = 0;
+	for (idx = 0; idx < ARRAY_SIZE(hv_vcpu->stimer); idx++) {
+		stimer = &hv_vcpu->stimer[idx];
+		if (stimer->msg_pending &&
+		    (stimer->config & HV_STIMER_ENABLE) &&
+		    HV_STIMER_SINT(stimer->config) == sint) {
+			set_bit(stimer->index,
+				hv_vcpu->stimer_pending_bitmap);
+			stimers_pending++;
+		}
+	}
+	if (stimers_pending)
+		kvm_make_request(KVM_REQ_HV_STIMER, vcpu);
+
+	idx = srcu_read_lock(&kvm->irq_srcu);
+	gsi = atomic_read(&synic->sint_to_gsi[sint]);
+	if (gsi != -1)
+		kvm_notify_acked_gsi(kvm, gsi);
+	srcu_read_unlock(&kvm->irq_srcu, idx);
+}
+
+static void synic_exit(struct kvm_vcpu_hv_synic *synic, u32 msr)
+{
+	struct kvm_vcpu *vcpu = synic_to_vcpu(synic);
+	struct kvm_vcpu_hv *hv_vcpu = &vcpu->arch.hyperv;
+
+	hv_vcpu->exit.type = KVM_EXIT_HYPERV_SYNIC;
+	hv_vcpu->exit.u.synic.msr = msr;
+	hv_vcpu->exit.u.synic.control = synic->control;
+	hv_vcpu->exit.u.synic.evt_page = synic->evt_page;
+	hv_vcpu->exit.u.synic.msg_page = synic->msg_page;
+
+	kvm_make_request(KVM_REQ_HV_EXIT, vcpu);
+}
+
+static int synic_set_msr(struct kvm_vcpu_hv_synic *synic,
+			 u32 msr, u64 data, bool host)
+{
+	struct kvm_vcpu *vcpu = synic_to_vcpu(synic);
+	int ret;
+
+	if (!synic->active)
+		return 1;
+
+	trace_kvm_hv_synic_set_msr(vcpu->vcpu_id, msr, data, host);
+
+	ret = 0;
+	switch (msr) {
+	case HV_X64_MSR_SCONTROL:
+		synic->control = data;
+		if (!host)
+			synic_exit(synic, msr);
+		break;
+	case HV_X64_MSR_SVERSION:
+		if (!host) {
+			ret = 1;
+			break;
+		}
+		synic->version = data;
+		break;
+	case HV_X64_MSR_SIEFP:
+		if (data & HV_SYNIC_SIEFP_ENABLE)
+			if (kvm_clear_guest(vcpu->kvm,
+					    data & PAGE_MASK, PAGE_SIZE)) {
+				ret = 1;
+				break;
+			}
+		synic->evt_page = data;
+		if (!host)
+			synic_exit(synic, msr);
+		break;
+	case HV_X64_MSR_SIMP:
+		if (data & HV_SYNIC_SIMP_ENABLE)
+			if (kvm_clear_guest(vcpu->kvm,
+					    data & PAGE_MASK, PAGE_SIZE)) {
+				ret = 1;
+				break;
+			}
+		synic->msg_page = data;
+		if (!host)
+			synic_exit(synic, msr);
+		break;
+	case HV_X64_MSR_EOM: {
+		int i;
+
+		for (i = 0; i < ARRAY_SIZE(synic->sint); i++)
+			kvm_hv_notify_acked_sint(vcpu, i);
+		break;
+	}
+	case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15:
+		ret = synic_set_sint(synic, msr - HV_X64_MSR_SINT0, data, host);
+		break;
+	default:
+		ret = 1;
+		break;
+	}
+	return ret;
+}
+
+static int synic_get_msr(struct kvm_vcpu_hv_synic *synic, u32 msr, u64 *pdata)
+{
+	int ret;
+
+	if (!synic->active)
+		return 1;
+
+	ret = 0;
+	switch (msr) {
+	case HV_X64_MSR_SCONTROL:
+		*pdata = synic->control;
+		break;
+	case HV_X64_MSR_SVERSION:
+		*pdata = synic->version;
+		break;
+	case HV_X64_MSR_SIEFP:
+		*pdata = synic->evt_page;
+		break;
+	case HV_X64_MSR_SIMP:
+		*pdata = synic->msg_page;
+		break;
+	case HV_X64_MSR_EOM:
+		*pdata = 0;
+		break;
+	case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15:
+		*pdata = atomic64_read(&synic->sint[msr - HV_X64_MSR_SINT0]);
+		break;
+	default:
+		ret = 1;
+		break;
+	}
+	return ret;
+}
+
+int synic_set_irq(struct kvm_vcpu_hv_synic *synic, u32 sint)
+{
+	struct kvm_vcpu *vcpu = synic_to_vcpu(synic);
+	struct kvm_lapic_irq irq;
+	int ret, vector;
+
+	if (sint >= ARRAY_SIZE(synic->sint))
+		return -EINVAL;
+
+	vector = synic_get_sint_vector(synic_read_sint(synic, sint));
+	if (vector < 0)
+		return -ENOENT;
+
+	memset(&irq, 0, sizeof(irq));
+	irq.dest_id = kvm_apic_id(vcpu->arch.apic);
+	irq.dest_mode = APIC_DEST_PHYSICAL;
+	irq.delivery_mode = APIC_DM_FIXED;
+	irq.vector = vector;
+	irq.level = 1;
+
+	ret = kvm_irq_delivery_to_apic(vcpu->kvm, NULL, &irq, NULL);
+	trace_kvm_hv_synic_set_irq(vcpu->vcpu_id, sint, irq.vector, ret);
+	return ret;
+}
+
+int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vcpu_id, u32 sint)
+{
+	struct kvm_vcpu_hv_synic *synic;
+
+	synic = synic_get(kvm, vcpu_id);
+	if (!synic)
+		return -EINVAL;
+
+	return synic_set_irq(synic, sint);
+}
+
+void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector)
+{
+	struct kvm_vcpu_hv_synic *synic = vcpu_to_synic(vcpu);
+	int i;
+
+	trace_kvm_hv_synic_send_eoi(vcpu->vcpu_id, vector);
+
+	for (i = 0; i < ARRAY_SIZE(synic->sint); i++)
+		if (synic_get_sint_vector(synic_read_sint(synic, i)) == vector)
+			kvm_hv_notify_acked_sint(vcpu, i);
+}
+
+static int kvm_hv_set_sint_gsi(struct kvm *kvm, u32 vcpu_id, u32 sint, int gsi)
+{
+	struct kvm_vcpu_hv_synic *synic;
+
+	synic = synic_get(kvm, vcpu_id);
+	if (!synic)
+		return -EINVAL;
+
+	if (sint >= ARRAY_SIZE(synic->sint_to_gsi))
+		return -EINVAL;
+
+	atomic_set(&synic->sint_to_gsi[sint], gsi);
+	return 0;
+}
+
+void kvm_hv_irq_routing_update(struct kvm *kvm)
+{
+	struct kvm_irq_routing_table *irq_rt;
+	struct kvm_kernel_irq_routing_entry *e;
+	u32 gsi;
+
+	irq_rt = srcu_dereference_check(kvm->irq_routing, &kvm->irq_srcu,
+					lockdep_is_held(&kvm->irq_lock));
+
+	for (gsi = 0; gsi < irq_rt->nr_rt_entries; gsi++) {
+		hlist_for_each_entry(e, &irq_rt->map[gsi], link) {
+			if (e->type == KVM_IRQ_ROUTING_HV_SINT)
+				kvm_hv_set_sint_gsi(kvm, e->hv_sint.vcpu,
+						    e->hv_sint.sint, gsi);
+		}
+	}
+}
+
+static void synic_init(struct kvm_vcpu_hv_synic *synic)
+{
+	int i;
+
+	memset(synic, 0, sizeof(*synic));
+	synic->version = HV_SYNIC_VERSION_1;
+	for (i = 0; i < ARRAY_SIZE(synic->sint); i++) {
+		atomic64_set(&synic->sint[i], HV_SYNIC_SINT_MASKED);
+		atomic_set(&synic->sint_to_gsi[i], -1);
+	}
+}
+
+static u64 get_time_ref_counter(struct kvm *kvm)
+{
+	return div_u64(get_kernel_ns() + kvm->arch.kvmclock_offset, 100);
+}
+
+static void stimer_mark_pending(struct kvm_vcpu_hv_stimer *stimer,
+				bool vcpu_kick)
+{
+	struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer);
+
+	set_bit(stimer->index,
+		vcpu_to_hv_vcpu(vcpu)->stimer_pending_bitmap);
+	kvm_make_request(KVM_REQ_HV_STIMER, vcpu);
+	if (vcpu_kick)
+		kvm_vcpu_kick(vcpu);
+}
+
+static void stimer_cleanup(struct kvm_vcpu_hv_stimer *stimer)
+{
+	struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer);
+
+	trace_kvm_hv_stimer_cleanup(stimer_to_vcpu(stimer)->vcpu_id,
+				    stimer->index);
+
+	hrtimer_cancel(&stimer->timer);
+	clear_bit(stimer->index,
+		  vcpu_to_hv_vcpu(vcpu)->stimer_pending_bitmap);
+	stimer->msg_pending = false;
+	stimer->exp_time = 0;
+}
+
+static enum hrtimer_restart stimer_timer_callback(struct hrtimer *timer)
+{
+	struct kvm_vcpu_hv_stimer *stimer;
+
+	stimer = container_of(timer, struct kvm_vcpu_hv_stimer, timer);
+	trace_kvm_hv_stimer_callback(stimer_to_vcpu(stimer)->vcpu_id,
+				     stimer->index);
+	stimer_mark_pending(stimer, true);
+
+	return HRTIMER_NORESTART;
+}
+
+/*
+ * stimer_start() assumptions:
+ * a) stimer->count is not equal to 0
+ * b) stimer->config has HV_STIMER_ENABLE flag
+ */
+static int stimer_start(struct kvm_vcpu_hv_stimer *stimer)
+{
+	u64 time_now;
+	ktime_t ktime_now;
+
+	time_now = get_time_ref_counter(stimer_to_vcpu(stimer)->kvm);
+	ktime_now = ktime_get();
+
+	if (stimer->config & HV_STIMER_PERIODIC) {
+		if (stimer->exp_time) {
+			if (time_now >= stimer->exp_time) {
+				u64 remainder;
+
+				div64_u64_rem(time_now - stimer->exp_time,
+					      stimer->count, &remainder);
+				stimer->exp_time =
+					time_now + (stimer->count - remainder);
+			}
+		} else
+			stimer->exp_time = time_now + stimer->count;
+
+		trace_kvm_hv_stimer_start_periodic(
+					stimer_to_vcpu(stimer)->vcpu_id,
+					stimer->index,
+					time_now, stimer->exp_time);
+
+		hrtimer_start(&stimer->timer,
+			      ktime_add_ns(ktime_now,
+					   100 * (stimer->exp_time - time_now)),
+			      HRTIMER_MODE_ABS);
+		return 0;
+	}
+	stimer->exp_time = stimer->count;
+	if (time_now >= stimer->count) {
+		/*
+		 * Expire timer according to Hypervisor Top-Level Functional
+		 * specification v4(15.3.1):
+		 * "If a one shot is enabled and the specified count is in
+		 * the past, it will expire immediately."
+		 */
+		stimer_mark_pending(stimer, false);
+		return 0;
+	}
+
+	trace_kvm_hv_stimer_start_one_shot(stimer_to_vcpu(stimer)->vcpu_id,
+					   stimer->index,
+					   time_now, stimer->count);
+
+	hrtimer_start(&stimer->timer,
+		      ktime_add_ns(ktime_now, 100 * (stimer->count - time_now)),
+		      HRTIMER_MODE_ABS);
+	return 0;
+}
+
+static int stimer_set_config(struct kvm_vcpu_hv_stimer *stimer, u64 config,
+			     bool host)
+{
+	trace_kvm_hv_stimer_set_config(stimer_to_vcpu(stimer)->vcpu_id,
+				       stimer->index, config, host);
+
+	stimer_cleanup(stimer);
+	if ((stimer->config & HV_STIMER_ENABLE) && HV_STIMER_SINT(config) == 0)
+		config &= ~HV_STIMER_ENABLE;
+	stimer->config = config;
+	stimer_mark_pending(stimer, false);
+	return 0;
+}
+
+static int stimer_set_count(struct kvm_vcpu_hv_stimer *stimer, u64 count,
+			    bool host)
+{
+	trace_kvm_hv_stimer_set_count(stimer_to_vcpu(stimer)->vcpu_id,
+				      stimer->index, count, host);
+
+	stimer_cleanup(stimer);
+	stimer->count = count;
+	if (stimer->count == 0)
+		stimer->config &= ~HV_STIMER_ENABLE;
+	else if (stimer->config & HV_STIMER_AUTOENABLE)
+		stimer->config |= HV_STIMER_ENABLE;
+	stimer_mark_pending(stimer, false);
+	return 0;
+}
+
+static int stimer_get_config(struct kvm_vcpu_hv_stimer *stimer, u64 *pconfig)
+{
+	*pconfig = stimer->config;
+	return 0;
+}
+
+static int stimer_get_count(struct kvm_vcpu_hv_stimer *stimer, u64 *pcount)
+{
+	*pcount = stimer->count;
+	return 0;
+}
+
+static int synic_deliver_msg(struct kvm_vcpu_hv_synic *synic, u32 sint,
+			     struct hv_message *src_msg)
+{
+	struct kvm_vcpu *vcpu = synic_to_vcpu(synic);
+	struct page *page;
+	gpa_t gpa;
+	struct hv_message *dst_msg;
+	int r;
+	struct hv_message_page *msg_page;
+
+	if (!(synic->msg_page & HV_SYNIC_SIMP_ENABLE))
+		return -ENOENT;
+
+	gpa = synic->msg_page & PAGE_MASK;
+	page = kvm_vcpu_gfn_to_page(vcpu, gpa >> PAGE_SHIFT);
+	if (is_error_page(page))
+		return -EFAULT;
+
+	msg_page = kmap_atomic(page);
+	dst_msg = &msg_page->sint_message[sint];
+	if (sync_cmpxchg(&dst_msg->header.message_type, HVMSG_NONE,
+			 src_msg->header.message_type) != HVMSG_NONE) {
+		dst_msg->header.message_flags.msg_pending = 1;
+		r = -EAGAIN;
+	} else {
+		memcpy(&dst_msg->u.payload, &src_msg->u.payload,
+		       src_msg->header.payload_size);
+		dst_msg->header.message_type = src_msg->header.message_type;
+		dst_msg->header.payload_size = src_msg->header.payload_size;
+		r = synic_set_irq(synic, sint);
+		if (r >= 1)
+			r = 0;
+		else if (r == 0)
+			r = -EFAULT;
+	}
+	kunmap_atomic(msg_page);
+	kvm_release_page_dirty(page);
+	kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT);
+	return r;
+}
+
+static int stimer_send_msg(struct kvm_vcpu_hv_stimer *stimer)
+{
+	struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer);
+	struct hv_message *msg = &stimer->msg;
+	struct hv_timer_message_payload *payload =
+			(struct hv_timer_message_payload *)&msg->u.payload;
+
+	payload->expiration_time = stimer->exp_time;
+	payload->delivery_time = get_time_ref_counter(vcpu->kvm);
+	return synic_deliver_msg(vcpu_to_synic(vcpu),
+				 HV_STIMER_SINT(stimer->config), msg);
+}
+
+static void stimer_expiration(struct kvm_vcpu_hv_stimer *stimer)
+{
+	int r;
+
+	stimer->msg_pending = true;
+	r = stimer_send_msg(stimer);
+	trace_kvm_hv_stimer_expiration(stimer_to_vcpu(stimer)->vcpu_id,
+				       stimer->index, r);
+	if (!r) {
+		stimer->msg_pending = false;
+		if (!(stimer->config & HV_STIMER_PERIODIC))
+			stimer->config &= ~HV_STIMER_ENABLE;
+	}
+}
+
+void kvm_hv_process_stimers(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu);
+	struct kvm_vcpu_hv_stimer *stimer;
+	u64 time_now, exp_time;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++)
+		if (test_and_clear_bit(i, hv_vcpu->stimer_pending_bitmap)) {
+			stimer = &hv_vcpu->stimer[i];
+			if (stimer->config & HV_STIMER_ENABLE) {
+				exp_time = stimer->exp_time;
+
+				if (exp_time) {
+					time_now =
+						get_time_ref_counter(vcpu->kvm);
+					if (time_now >= exp_time)
+						stimer_expiration(stimer);
+				}
+
+				if ((stimer->config & HV_STIMER_ENABLE) &&
+				    stimer->count)
+					stimer_start(stimer);
+				else
+					stimer_cleanup(stimer);
+			}
+		}
+}
+
+void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu);
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++)
+		stimer_cleanup(&hv_vcpu->stimer[i]);
+}
+
+static void stimer_prepare_msg(struct kvm_vcpu_hv_stimer *stimer)
+{
+	struct hv_message *msg = &stimer->msg;
+	struct hv_timer_message_payload *payload =
+			(struct hv_timer_message_payload *)&msg->u.payload;
+
+	memset(&msg->header, 0, sizeof(msg->header));
+	msg->header.message_type = HVMSG_TIMER_EXPIRED;
+	msg->header.payload_size = sizeof(*payload);
+
+	payload->timer_index = stimer->index;
+	payload->expiration_time = 0;
+	payload->delivery_time = 0;
+}
+
+static void stimer_init(struct kvm_vcpu_hv_stimer *stimer, int timer_index)
+{
+	memset(stimer, 0, sizeof(*stimer));
+	stimer->index = timer_index;
+	hrtimer_init(&stimer->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	stimer->timer.function = stimer_timer_callback;
+	stimer_prepare_msg(stimer);
+}
+
+void kvm_hv_vcpu_init(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu);
+	int i;
+
+	synic_init(&hv_vcpu->synic);
+
+	bitmap_zero(hv_vcpu->stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT);
+	for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++)
+		stimer_init(&hv_vcpu->stimer[i], i);
+}
+
+int kvm_hv_activate_synic(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * Hyper-V SynIC auto EOI SINT's are
+	 * not compatible with APICV, so deactivate APICV
+	 */
+	kvm_vcpu_deactivate_apicv(vcpu);
+	vcpu_to_synic(vcpu)->active = true;
+	return 0;
+}
+
 static bool kvm_hv_msr_partition_wide(u32 msr)
 {
 	bool r = false;
@@ -226,6 +878,31 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
 			return 1;
 		hv->runtime_offset = data - current_task_runtime_100ns();
 		break;
+	case HV_X64_MSR_SCONTROL:
+	case HV_X64_MSR_SVERSION:
+	case HV_X64_MSR_SIEFP:
+	case HV_X64_MSR_SIMP:
+	case HV_X64_MSR_EOM:
+	case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15:
+		return synic_set_msr(vcpu_to_synic(vcpu), msr, data, host);
+	case HV_X64_MSR_STIMER0_CONFIG:
+	case HV_X64_MSR_STIMER1_CONFIG:
+	case HV_X64_MSR_STIMER2_CONFIG:
+	case HV_X64_MSR_STIMER3_CONFIG: {
+		int timer_index = (msr - HV_X64_MSR_STIMER0_CONFIG)/2;
+
+		return stimer_set_config(vcpu_to_stimer(vcpu, timer_index),
+					 data, host);
+	}
+	case HV_X64_MSR_STIMER0_COUNT:
+	case HV_X64_MSR_STIMER1_COUNT:
+	case HV_X64_MSR_STIMER2_COUNT:
+	case HV_X64_MSR_STIMER3_COUNT: {
+		int timer_index = (msr - HV_X64_MSR_STIMER0_COUNT)/2;
+
+		return stimer_set_count(vcpu_to_stimer(vcpu, timer_index),
+					data, host);
+	}
 	default:
 		vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n",
 			    msr, data);
@@ -248,11 +925,9 @@ static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case HV_X64_MSR_HYPERCALL:
 		data = hv->hv_hypercall;
 		break;
-	case HV_X64_MSR_TIME_REF_COUNT: {
-		data =
-		     div_u64(get_kernel_ns() + kvm->arch.kvmclock_offset, 100);
+	case HV_X64_MSR_TIME_REF_COUNT:
+		data = get_time_ref_counter(kvm);
 		break;
-	}
 	case HV_X64_MSR_REFERENCE_TSC:
 		data = hv->hv_tsc_page;
 		break;
@@ -304,6 +979,31 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case HV_X64_MSR_VP_RUNTIME:
 		data = current_task_runtime_100ns() + hv->runtime_offset;
 		break;
+	case HV_X64_MSR_SCONTROL:
+	case HV_X64_MSR_SVERSION:
+	case HV_X64_MSR_SIEFP:
+	case HV_X64_MSR_SIMP:
+	case HV_X64_MSR_EOM:
+	case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15:
+		return synic_get_msr(vcpu_to_synic(vcpu), msr, pdata);
+	case HV_X64_MSR_STIMER0_CONFIG:
+	case HV_X64_MSR_STIMER1_CONFIG:
+	case HV_X64_MSR_STIMER2_CONFIG:
+	case HV_X64_MSR_STIMER3_CONFIG: {
+		int timer_index = (msr - HV_X64_MSR_STIMER0_CONFIG)/2;
+
+		return stimer_get_config(vc