[Qemu-devel] [PATCH v4 0/12] HyperV equivalent of pvpanic driver

[Qemu-devel] [PATCH v4 0/12] HyperV equivalent of pvpanic driver

[Denis V. Lunev]

ndows 2012 guests can notify hypervisor about occurred guest crash
(Windows bugcheck(BSOD)) by writing specific Hyper-V msrs. This patch does
handling of this MSR's by KVM and sending notification to user space that
allows to gather Windows guest crash dump by QEMU/LIBVIRT.

The idea is to provide functionality equal to pvpanic device without
QEMU guest agent for Windows.

The idea is borrowed from Linux HyperV bus driver and validated against
Windows 2k12.

Changes from v3:
* remove unused HV_X64_MSR_CRASH_CTL_NOTIFY
* added documentation section about KVM_SYSTEM_EVENT_CRASH
* allow only supported values inside crash ctl msr
* qemu: split patch into generic crash handling patches and hyperv specific
* qemu: skip migration of crash ctl msr value

Changes from v2:
* forbid modification crash ctl msr by guest
* qemu_system_guest_panicked usage in pvpanic and s390x
* hyper-v crash handler move from generic kvm to i386
* hyper-v crash handler: skip fetching crash msrs just mark crash occured
* sync with linux-next 20150629
* patch 11 squashed to patch 10
* patch 9 squashed to patch 7

Changes from v1:
* hyperv code move to hyperv.c
* added read handlers of crash data msrs
* added per vm and per cpu hyperv context structures
* added saving crash msrs inside qemu cpu state
* added qemu fetch and update of crash msrs
* added qemu crash msrs store in cpu state and it's migration

Signed-off-by: Andrey Smetanin <asmetanin@virtuozzo.com>
Signed-off-by: Denis V. Lunev <den@openvz.org>
CC: Gleb Natapov <gleb@kernel.org>
CC: Paolo Bonzini <pbonzini@redhat.com>

[Qemu-devel] [PATCH 1/12] kvm/x86: move Hyper-V MSR's/hypercall code into hyperv.c file

[Denis V. Lunev]

From: Andrey Smetanin <asmetanin@virtuozzo.com>

This patch introduce Hyper-V related source code file - hyperv.c and
per vm and per vcpu hyperv context structures.
All Hyper-V MSR's and hypercall code moved into hyperv.c.
All Hyper-V kvm/vcpu fields moved into appropriate hyperv context
structures. Copyrights and authors information copied from x86.c
to hyperv.c.

Signed-off-by: Andrey Smetanin <asmetanin@virtuozzo.com>
Signed-off-by: Denis V. Lunev <den@openvz.org>
Reviewed-by: Peter Hornyack <peterhornyack@google.com>
CC: Paolo Bonzini <pbonzini@redhat.com>
CC: Gleb Natapov <gleb@kernel.org>
---
 arch/x86/include/asm/kvm_host.h |  20 ++-
 arch/x86/kvm/Makefile           |   4 +-
 arch/x86/kvm/hyperv.c           | 307 ++++++++++++++++++++++++++++++++++++++++
 arch/x86/kvm/hyperv.h           |  32 +++++
 arch/x86/kvm/lapic.h            |   2 +-
 arch/x86/kvm/x86.c              | 265 +---------------------------------
 arch/x86/kvm/x86.h              |   5 +
 7 files changed, 366 insertions(+), 269 deletions(-)
 create mode 100644 arch/x86/kvm/hyperv.c
 create mode 100644 arch/x86/kvm/hyperv.h

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index c7fa57b..78616aa 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -358,6 +358,11 @@ struct kvm_mtrr {
 	struct list_head head;
 };
 
+/* Hyper-V per vcpu emulation context */
+struct kvm_vcpu_hv {
+	u64 hv_vapic;
+};
+
 struct kvm_vcpu_arch {
 	/*
 	 * rip and regs accesses must go through
@@ -514,8 +519,7 @@ struct kvm_vcpu_arch {
 	/* used for guest single stepping over the given code position */
 	unsigned long singlestep_rip;
 
-	/* fields used by HYPER-V emulation */
-	u64 hv_vapic;
+	struct kvm_vcpu_hv hyperv;
 
 	cpumask_var_t wbinvd_dirty_mask;
 
@@ -586,6 +590,13 @@ struct kvm_apic_map {
 	struct kvm_lapic *logical_map[16][16];
 };
 
+/* Hyper-V emulation context */
+struct kvm_hv {
+	u64 hv_guest_os_id;
+	u64 hv_hypercall;
+	u64 hv_tsc_page;
+};
+
 struct kvm_arch {
 	unsigned int n_used_mmu_pages;
 	unsigned int n_requested_mmu_pages;
@@ -643,10 +654,7 @@ struct kvm_arch {
 	/* reads protected by irq_srcu, writes by irq_lock */
 	struct hlist_head mask_notifier_list;
 
-	/* fields used by HYPER-V emulation */
-	u64 hv_guest_os_id;
-	u64 hv_hypercall;
-	u64 hv_tsc_page;
+	struct kvm_hv hyperv;
 
 	#ifdef CONFIG_KVM_MMU_AUDIT
 	int audit_point;
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index 67d215c..a1ff508 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -12,7 +12,9 @@ kvm-y			+= $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \
 kvm-$(CONFIG_KVM_ASYNC_PF)	+= $(KVM)/async_pf.o
 
 kvm-y			+= x86.o mmu.o emulate.o i8259.o irq.o lapic.o \
-			   i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o
+			   i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \
+			   hyperv.o
+
 kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT)	+= assigned-dev.o iommu.o
 kvm-intel-y		+= vmx.o pmu_intel.o
 kvm-amd-y		+= svm.o pmu_amd.o
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
new file mode 100644
index 0000000..2b49f10
--- /dev/null
+++ b/arch/x86/kvm/hyperv.c
@@ -0,0 +1,307 @@
+/*
+ * KVM Microsoft Hyper-V emulation
+ *
+ * derived from arch/x86/kvm/x86.c
+ *
+ * Copyright (C) 2006 Qumranet, Inc.
+ * Copyright (C) 2008 Qumranet, Inc.
+ * Copyright IBM Corporation, 2008
+ * Copyright 2010 Red Hat, Inc. and/or its affiliates.
+ * Copyright (C) 2015 Andrey Smetanin <asmetanin@virtuozzo.com>
+ *
+ * Authors:
+ *   Avi Kivity   <avi@qumranet.com>
+ *   Yaniv Kamay  <yaniv@qumranet.com>
+ *   Amit Shah    <amit.shah@qumranet.com>
+ *   Ben-Ami Yassour <benami@il.ibm.com>
+ *   Andrey Smetanin <asmetanin@virtuozzo.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#include "x86.h"
+#include "lapic.h"
+#include "hyperv.h"
+
+#include <linux/kvm_host.h>
+#include <trace/events/kvm.h>
+
+#include "trace.h"
+
+static bool kvm_hv_msr_partition_wide(u32 msr)
+{
+	bool r = false;
+
+	switch (msr) {
+	case HV_X64_MSR_GUEST_OS_ID:
+	case HV_X64_MSR_HYPERCALL:
+	case HV_X64_MSR_REFERENCE_TSC:
+	case HV_X64_MSR_TIME_REF_COUNT:
+		r = true;
+		break;
+	}
+
+	return r;
+}
+
+static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_hv *hv = &kvm->arch.hyperv;
+
+	switch (msr) {
+	case HV_X64_MSR_GUEST_OS_ID:
+		hv->hv_guest_os_id = data;
+		/* setting guest os id to zero disables hypercall page */
+		if (!hv->hv_guest_os_id)
+			hv->hv_hypercall &= ~HV_X64_MSR_HYPERCALL_ENABLE;
+		break;
+	case HV_X64_MSR_HYPERCALL: {
+		u64 gfn;
+		unsigned long addr;
+		u8 instructions[4];
+
+		/* if guest os id is not set hypercall should remain disabled */
+		if (!hv->hv_guest_os_id)
+			break;
+		if (!(data & HV_X64_MSR_HYPERCALL_ENABLE)) {
+			hv->hv_hypercall = data;
+			break;
+		}
+		gfn = data >> HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT;
+		addr = gfn_to_hva(kvm, gfn);
+		if (kvm_is_error_hva(addr))
+			return 1;
+		kvm_x86_ops->patch_hypercall(vcpu, instructions);
+		((unsigned char *)instructions)[3] = 0xc3; /* ret */
+		if (__copy_to_user((void __user *)addr, instructions, 4))
+			return 1;
+		hv->hv_hypercall = data;
+		mark_page_dirty(kvm, gfn);
+		break;
+	}
+	case HV_X64_MSR_REFERENCE_TSC: {
+		u64 gfn;
+		HV_REFERENCE_TSC_PAGE tsc_ref;
+
+		memset(&tsc_ref, 0, sizeof(tsc_ref));
+		hv->hv_tsc_page = data;
+		if (!(data & HV_X64_MSR_TSC_REFERENCE_ENABLE))
+			break;
+		gfn = data >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT;
+		if (kvm_write_guest(
+				kvm,
+				gfn << HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT,
+				&tsc_ref, sizeof(tsc_ref)))
+			return 1;
+		mark_page_dirty(kvm, gfn);
+		break;
+	}
+	default:
+		vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n",
+			    msr, data);
+		return 1;
+	}
+	return 0;
+}
+
+static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
+{
+	struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv;
+
+	switch (msr) {
+	case HV_X64_MSR_APIC_ASSIST_PAGE: {
+		u64 gfn;
+		unsigned long addr;
+
+		if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) {
+			hv->hv_vapic = data;
+			if (kvm_lapic_enable_pv_eoi(vcpu, 0))
+				return 1;
+			break;
+		}
+		gfn = data >> HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT;
+		addr = kvm_vcpu_gfn_to_hva(vcpu, gfn);
+		if (kvm_is_error_hva(addr))
+			return 1;
+		if (__clear_user((void __user *)addr, PAGE_SIZE))
+			return 1;
+		hv->hv_vapic = data;
+		kvm_vcpu_mark_page_dirty(vcpu, gfn);
+		if (kvm_lapic_enable_pv_eoi(vcpu,
+					    gfn_to_gpa(gfn) | KVM_MSR_ENABLED))
+			return 1;
+		break;
+	}
+	case HV_X64_MSR_EOI:
+		return kvm_hv_vapic_msr_write(vcpu, APIC_EOI, data);
+	case HV_X64_MSR_ICR:
+		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);
+	default:
+		vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n",
+			    msr, data);
+		return 1;
+	}
+
+	return 0;
+}
+
+static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
+{
+	u64 data = 0;
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_hv *hv = &kvm->arch.hyperv;
+
+	switch (msr) {
+	case HV_X64_MSR_GUEST_OS_ID:
+		data = hv->hv_guest_os_id;
+		break;
+	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);
+		break;
+	}
+	case HV_X64_MSR_REFERENCE_TSC:
+		data = hv->hv_tsc_page;
+		break;
+	default:
+		vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
+		return 1;
+	}
+
+	*pdata = data;
+	return 0;
+}
+
+static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
+{
+	u64 data = 0;
+	struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv;
+
+	switch (msr) {
+	case HV_X64_MSR_VP_INDEX: {
+		int r;
+		struct kvm_vcpu *v;
+
+		kvm_for_each_vcpu(r, v, vcpu->kvm) {
+			if (v == vcpu) {
+				data = r;
+				break;
+			}
+		}
+		break;
+	}
+	case HV_X64_MSR_EOI:
+		return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata);
+	case HV_X64_MSR_ICR:
+		return kvm_hv_vapic_msr_read(vcpu, APIC_ICR, pdata);
+	case HV_X64_MSR_TPR:
+		return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata);
+	case HV_X64_MSR_APIC_ASSIST_PAGE:
+		data = hv->hv_vapic;
+		break;
+	default:
+		vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
+		return 1;
+	}
+	*pdata = data;
+	return 0;
+}
+
+int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
+{
+	if (kvm_hv_msr_partition_wide(msr)) {
+		int r;
+
+		mutex_lock(&vcpu->kvm->lock);
+		r = kvm_hv_set_msr_pw(vcpu, msr, data);
+		mutex_unlock(&vcpu->kvm->lock);
+		return r;
+	} else
+		return kvm_hv_set_msr(vcpu, msr, data);
+}
+
+int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
+{
+	if (kvm_hv_msr_partition_wide(msr)) {
+		int r;
+
+		mutex_lock(&vcpu->kvm->lock);
+		r = kvm_hv_get_msr_pw(vcpu, msr, pdata);
+		mutex_unlock(&vcpu->kvm->lock);
+		return r;
+	} else
+		return kvm_hv_get_msr(vcpu, msr, pdata);
+}
+
+bool kvm_hv_hypercall_enabled(struct kvm *kvm)
+{
+	return kvm->arch.hyperv.hv_hypercall & HV_X64_MSR_HYPERCALL_ENABLE;
+}
+
+int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
+{
+	u64 param, ingpa, outgpa, ret;
+	uint16_t code, rep_idx, rep_cnt, res = HV_STATUS_SUCCESS, rep_done = 0;
+	bool fast, longmode;
+
+	/*
+	 * hypercall generates UD from non zero cpl and real mode
+	 * per HYPER-V spec
+	 */
+	if (kvm_x86_ops->get_cpl(vcpu) != 0 || !is_protmode(vcpu)) {
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return 0;
+	}
+
+	longmode = is_64_bit_mode(vcpu);
+
+	if (!longmode) {
+		param = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDX) << 32) |
+			(kvm_register_read(vcpu, VCPU_REGS_RAX) & 0xffffffff);
+		ingpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RBX) << 32) |
+			(kvm_register_read(vcpu, VCPU_REGS_RCX) & 0xffffffff);
+		outgpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDI) << 32) |
+			(kvm_register_read(vcpu, VCPU_REGS_RSI) & 0xffffffff);
+	}
+#ifdef CONFIG_X86_64
+	else {
+		param = kvm_register_read(vcpu, VCPU_REGS_RCX);
+		ingpa = kvm_register_read(vcpu, VCPU_REGS_RDX);
+		outgpa = kvm_register_read(vcpu, VCPU_REGS_R8);
+	}
+#endif
+
+	code = param & 0xffff;
+	fast = (param >> 16) & 0x1;
+	rep_cnt = (param >> 32) & 0xfff;
+	rep_idx = (param >> 48) & 0xfff;
+
+	trace_kvm_hv_hypercall(code, fast, rep_cnt, rep_idx, ingpa, outgpa);
+
+	switch (code) {
+	case HV_X64_HV_NOTIFY_LONG_SPIN_WAIT:
+		kvm_vcpu_on_spin(vcpu);
+		break;
+	default:
+		res = HV_STATUS_INVALID_HYPERCALL_CODE;
+		break;
+	}
+
+	ret = res | (((u64)rep_done & 0xfff) << 32);
+	if (longmode) {
+		kvm_register_write(vcpu, VCPU_REGS_RAX, ret);
+	} else {
+		kvm_register_write(vcpu, VCPU_REGS_RDX, ret >> 32);
+		kvm_register_write(vcpu, VCPU_REGS_RAX, ret & 0xffffffff);
+	}
+
+	return 1;
+}
diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
new file mode 100644
index 0000000..115c738
--- /dev/null
+++ b/arch/x86/kvm/hyperv.h
@@ -0,0 +1,32 @@
+/*
+ * KVM Microsoft Hyper-V emulation
+ *
+ * derived from arch/x86/kvm/x86.c
+ *
+ * Copyright (C) 2006 Qumranet, Inc.
+ * Copyright (C) 2008 Qumranet, Inc.
+ * Copyright IBM Corporation, 2008
+ * Copyright 2010 Red Hat, Inc. and/or its affiliates.
+ * Copyright (C) 2015 Andrey Smetanin <asmetanin@virtuozzo.com>
+ *
+ * Authors:
+ *   Avi Kivity   <avi@qumranet.com>
+ *   Yaniv Kamay  <yaniv@qumranet.com>
+ *   Amit Shah    <amit.shah@qumranet.com>
+ *   Ben-Ami Yassour <benami@il.ibm.com>
+ *   Andrey Smetanin <asmetanin@virtuozzo.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef __ARCH_X86_KVM_HYPERV_H__
+#define __ARCH_X86_KVM_HYPERV_H__
+
+int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data);
+int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata);
+bool kvm_hv_hypercall_enabled(struct kvm *kvm);
+int kvm_hv_hypercall(struct kvm_vcpu *vcpu);
+
+#endif
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index f2f4e10..26f7817 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -90,7 +90,7 @@ int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
 
 static inline bool kvm_hv_vapic_assist_page_enabled(struct kvm_vcpu *vcpu)
 {
-	return vcpu->arch.hv_vapic & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE;
+	return vcpu->arch.hyperv.hv_vapic & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE;
 }
 
 int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index ac165c2..301ee01 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -29,6 +29,7 @@
 #include "cpuid.h"
 #include "assigned-dev.h"
 #include "pmu.h"
+#include "hyperv.h"
 
 #include <linux/clocksource.h>
 #include <linux/interrupt.h>
@@ -1217,11 +1218,6 @@ static void kvm_get_time_scale(uint32_t scaled_khz, uint32_t base_khz,
 		 __func__, base_khz, scaled_khz, shift, *pmultiplier);
 }
 
-static inline u64 get_kernel_ns(void)
-{
-	return ktime_get_boot_ns();
-}
-
 #ifdef CONFIG_X86_64
 static atomic_t kvm_guest_has_master_clock = ATOMIC_INIT(0);
 #endif
@@ -1869,123 +1865,6 @@ out:
 	return r;
 }
 
-static bool kvm_hv_hypercall_enabled(struct kvm *kvm)
-{
-	return kvm->arch.hv_hypercall & HV_X64_MSR_HYPERCALL_ENABLE;
-}
-
-static bool kvm_hv_msr_partition_wide(u32 msr)
-{
-	bool r = false;
-	switch (msr) {
-	case HV_X64_MSR_GUEST_OS_ID:
-	case HV_X64_MSR_HYPERCALL:
-	case HV_X64_MSR_REFERENCE_TSC:
-	case HV_X64_MSR_TIME_REF_COUNT:
-		r = true;
-		break;
-	}
-
-	return r;
-}
-
-static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data)
-{
-	struct kvm *kvm = vcpu->kvm;
-
-	switch (msr) {
-	case HV_X64_MSR_GUEST_OS_ID:
-		kvm->arch.hv_guest_os_id = data;
-		/* setting guest os id to zero disables hypercall page */
-		if (!kvm->arch.hv_guest_os_id)
-			kvm->arch.hv_hypercall &= ~HV_X64_MSR_HYPERCALL_ENABLE;
-		break;
-	case HV_X64_MSR_HYPERCALL: {
-		u64 gfn;
-		unsigned long addr;
-		u8 instructions[4];
-
-		/* if guest os id is not set hypercall should remain disabled */
-		if (!kvm->arch.hv_guest_os_id)
-			break;
-		if (!(data & HV_X64_MSR_HYPERCALL_ENABLE)) {
-			kvm->arch.hv_hypercall = data;
-			break;
-		}
-		gfn = data >> HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT;
-		addr = gfn_to_hva(kvm, gfn);
-		if (kvm_is_error_hva(addr))
-			return 1;
-		kvm_x86_ops->patch_hypercall(vcpu, instructions);
-		((unsigned char *)instructions)[3] = 0xc3; /* ret */
-		if (__copy_to_user((void __user *)addr, instructions, 4))
-			return 1;
-		kvm->arch.hv_hypercall = data;
-		mark_page_dirty(kvm, gfn);
-		break;
-	}
-	case HV_X64_MSR_REFERENCE_TSC: {
-		u64 gfn;
-		HV_REFERENCE_TSC_PAGE tsc_ref;
-		memset(&tsc_ref, 0, sizeof(tsc_ref));
-		kvm->arch.hv_tsc_page = data;
-		if (!(data & HV_X64_MSR_TSC_REFERENCE_ENABLE))
-			break;
-		gfn = data >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT;
-		if (kvm_write_guest(kvm, gfn << HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT,
-			&tsc_ref, sizeof(tsc_ref)))
-			return 1;
-		mark_page_dirty(kvm, gfn);
-		break;
-	}
-	default:
-		vcpu_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x "
-			    "data 0x%llx\n", msr, data);
-		return 1;
-	}
-	return 0;
-}
-
-static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data)
-{
-	switch (msr) {
-	case HV_X64_MSR_APIC_ASSIST_PAGE: {
-		u64 gfn;
-		unsigned long addr;
-
-		if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) {
-			vcpu->arch.hv_vapic = data;
-			if (kvm_lapic_enable_pv_eoi(vcpu, 0))
-				return 1;
-			break;
-		}
-		gfn = data >> HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT;
-		addr = kvm_vcpu_gfn_to_hva(vcpu, gfn);
-		if (kvm_is_error_hva(addr))
-			return 1;
-		if (__clear_user((void __user *)addr, PAGE_SIZE))
-			return 1;
-		vcpu->arch.hv_vapic = data;
-		kvm_vcpu_mark_page_dirty(vcpu, gfn);
-		if (kvm_lapic_enable_pv_eoi(vcpu, gfn_to_gpa(gfn) | KVM_MSR_ENABLED))
-			return 1;
-		break;
-	}
-	case HV_X64_MSR_EOI:
-		return kvm_hv_vapic_msr_write(vcpu, APIC_EOI, data);
-	case HV_X64_MSR_ICR:
-		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);
-	default:
-		vcpu_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x "
-			    "data 0x%llx\n", msr, data);
-		return 1;
-	}
-
-	return 0;
-}
-
 static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 {
 	gpa_t gpa = data & ~0x3f;
@@ -2224,15 +2103,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		 */
 		break;
 	case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
-		if (kvm_hv_msr_partition_wide(msr)) {
-			int r;
-			mutex_lock(&vcpu->kvm->lock);
-			r = set_msr_hyperv_pw(vcpu, msr, data);
-			mutex_unlock(&vcpu->kvm->lock);
-			return r;
-		} else
-			return set_msr_hyperv(vcpu, msr, data);
-		break;
+		return kvm_hv_set_msr_common(vcpu, msr, data);
 	case MSR_IA32_BBL_CR_CTL3:
 		/* Drop writes to this legacy MSR -- see rdmsr
 		 * counterpart for further detail.
@@ -2315,68 +2186,6 @@ static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	return 0;
 }
 
-static int get_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
-{
-	u64 data = 0;
-	struct kvm *kvm = vcpu->kvm;
-
-	switch (msr) {
-	case HV_X64_MSR_GUEST_OS_ID:
-		data = kvm->arch.hv_guest_os_id;
-		break;
-	case HV_X64_MSR_HYPERCALL:
-		data = kvm->arch.hv_hypercall;
-		break;
-	case HV_X64_MSR_TIME_REF_COUNT: {
-		data =
-		     div_u64(get_kernel_ns() + kvm->arch.kvmclock_offset, 100);
-		break;
-	}
-	case HV_X64_MSR_REFERENCE_TSC:
-		data = kvm->arch.hv_tsc_page;
-		break;
-	default:
-		vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
-		return 1;
-	}
-
-	*pdata = data;
-	return 0;
-}
-
-static int get_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
-{
-	u64 data = 0;
-
-	switch (msr) {
-	case HV_X64_MSR_VP_INDEX: {
-		int r;
-		struct kvm_vcpu *v;
-		kvm_for_each_vcpu(r, v, vcpu->kvm) {
-			if (v == vcpu) {
-				data = r;
-				break;
-			}
-		}
-		break;
-	}
-	case HV_X64_MSR_EOI:
-		return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata);
-	case HV_X64_MSR_ICR:
-		return kvm_hv_vapic_msr_read(vcpu, APIC_ICR, pdata);
-	case HV_X64_MSR_TPR:
-		return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata);
-	case HV_X64_MSR_APIC_ASSIST_PAGE:
-		data = vcpu->arch.hv_vapic;
-		break;
-	default:
-		vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
-		return 1;
-	}
-	*pdata = data;
-	return 0;
-}
-
 int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
 	u64 data;
@@ -2495,14 +2304,8 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		msr_info->data = 0x20000000;
 		break;
 	case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
-		if (kvm_hv_msr_partition_wide(msr_info->index)) {
-			int r;
-			mutex_lock(&vcpu->kvm->lock);
-			r = get_msr_hyperv_pw(vcpu, msr_info->index, &msr_info->data);
-			mutex_unlock(&vcpu->kvm->lock);
-			return r;
-		} else
-			return get_msr_hyperv(vcpu, msr_info->index, &msr_info->data);
+		return kvm_hv_get_msr_common(vcpu,
+					     msr_info->index, &msr_info->data);
 		break;
 	case MSR_IA32_BBL_CR_CTL3:
 		/* This legacy MSR exists but isn't fully documented in current
@@ -5885,66 +5688,6 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_halt);
 
-int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
-{
-	u64 param, ingpa, outgpa, ret;
-	uint16_t code, rep_idx, rep_cnt, res = HV_STATUS_SUCCESS, rep_done = 0;
-	bool fast, longmode;
-
-	/*
-	 * hypercall generates UD from non zero cpl and real mode
-	 * per HYPER-V spec
-	 */
-	if (kvm_x86_ops->get_cpl(vcpu) != 0 || !is_protmode(vcpu)) {
-		kvm_queue_exception(vcpu, UD_VECTOR);
-		return 0;
-	}
-
-	longmode = is_64_bit_mode(vcpu);
-
-	if (!longmode) {
-		param = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDX) << 32) |
-			(kvm_register_read(vcpu, VCPU_REGS_RAX) & 0xffffffff);
-		ingpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RBX) << 32) |
-			(kvm_register_read(vcpu, VCPU_REGS_RCX) & 0xffffffff);
-		outgpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDI) << 32) |
-			(kvm_register_read(vcpu, VCPU_REGS_RSI) & 0xffffffff);
-	}
-#ifdef CONFIG_X86_64
-	else {
-		param = kvm_register_read(vcpu, VCPU_REGS_RCX);
-		ingpa = kvm_register_read(vcpu, VCPU_REGS_RDX);
-		outgpa = kvm_register_read(vcpu, VCPU_REGS_R8);
-	}
-#endif
-
-	code = param & 0xffff;
-	fast = (param >> 16) & 0x1;
-	rep_cnt = (param >> 32) & 0xfff;
-	rep_idx = (param >> 48) & 0xfff;
-
-	trace_kvm_hv_hypercall(code, fast, rep_cnt, rep_idx, ingpa, outgpa);
-
-	switch (code) {
-	case HV_X64_HV_NOTIFY_LONG_SPIN_WAIT:
-		kvm_vcpu_on_spin(vcpu);
-		break;
-	default:
-		res = HV_STATUS_INVALID_HYPERCALL_CODE;
-		break;
-	}
-
-	ret = res | (((u64)rep_done & 0xfff) << 32);
-	if (longmode) {
-		kvm_register_write(vcpu, VCPU_REGS_RAX, ret);
-	} else {
-		kvm_register_write(vcpu, VCPU_REGS_RDX, ret >> 32);
-		kvm_register_write(vcpu, VCPU_REGS_RAX, ret & 0xffffffff);
-	}
-
-	return 1;
-}
-
 /*
  * kvm_pv_kick_cpu_op:  Kick a vcpu.
  *
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index edc8cdc..c04b56b 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -147,6 +147,11 @@ static inline void kvm_register_writel(struct kvm_vcpu *vcpu,
 	return kvm_register_write(vcpu, reg, val);
 }
 
+static inline u64 get_kernel_ns(void)
+{
+	return ktime_get_boot_ns();
+}
+
 void kvm_before_handle_nmi(struct kvm_vcpu *vcpu);
 void kvm_after_handle_nmi(struct kvm_vcpu *vcpu);
 void kvm_set_pending_timer(struct kvm_vcpu *vcpu);
-- 
2.1.4

[Qemu-devel] [PATCH 2/12] kvm: introduce vcpu_debug = kvm_debug + vcpu context

[Denis V. Lunev]

From: Andrey Smetanin <asmetanin@virtuozzo.com>

vcpu_debug is useful macro like kvm_debug but additionally
includes vcpu context inside output.

Signed-off-by: Andrey Smetanin <asmetanin@virtuozzo.com>
Signed-off-by: Denis V. Lunev <den@openvz.org>
Reviewed-by: Peter Hornyack <peterhornyack@google.com>
CC: Paolo Bonzini <pbonzini@redhat.com>
CC: Gleb Natapov <gleb@kernel.org>
---
 include/linux/kvm_host.h | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 9564fd7..2b2edf1 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -424,6 +424,9 @@ struct kvm {
 #define vcpu_unimpl(vcpu, fmt, ...)					\
 	kvm_pr_unimpl("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__)
 
+#define vcpu_debug(vcpu, fmt, ...)					\
+	kvm_debug("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__)
+
 static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i)
 {
 	smp_rmb();
-- 
2.1.4

[Qemu-devel] [PATCH 3/12] kvm: add hyper-v crash msrs values

[Denis V. Lunev]

From: Andrey Smetanin <asmetanin@virtuozzo.com>

Added Hyper-V crash msrs values - HV_X64_MSR_CRASH*.

Signed-off-by: Andrey Smetanin <asmetanin@virtuozzo.com>
Signed-off-by: Denis V. Lunev <den@openvz.org>
Reviewed-by: Peter Hornyack <peterhornyack@google.com>
CC: Paolo Bonzini <pbonzini@redhat.com>
CC: Gleb Natapov <gleb@kernel.org>
---
 arch/x86/include/uapi/asm/hyperv.h | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h
index ce6068d..8fba544 100644
--- a/arch/x86/include/uapi/asm/hyperv.h
+++ b/arch/x86/include/uapi/asm/hyperv.h
@@ -199,6 +199,17 @@
 #define HV_X64_MSR_STIMER3_CONFIG		0x400000B6
 #define HV_X64_MSR_STIMER3_COUNT		0x400000B7
 
+/* Hyper-V guest crash notification MSR's */
+#define HV_X64_MSR_CRASH_P0			0x40000100
+#define HV_X64_MSR_CRASH_P1			0x40000101
+#define HV_X64_MSR_CRASH_P2			0x40000102
+#define HV_X64_MSR_CRASH_P3			0x40000103
+#define HV_X64_MSR_CRASH_P4			0x40000104
+#define HV_X64_MSR_CRASH_CTL			0x40000105
+#define HV_X64_MSR_CRASH_CTL_NOTIFY		(1ULL << 63)
+#define HV_X64_MSR_CRASH_PARAMS		\
+		(1 + (HV_X64_MSR_CRASH_P4 - HV_X64_MSR_CRASH_P0))
+
 #define HV_X64_MSR_HYPERCALL_ENABLE		0x00000001
 #define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT	12
 #define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_MASK	\
-- 
2.1.4

[Qemu-devel] [PATCH 4/12] kvm/x86: added hyper-v crash msrs into kvm hyperv context

[Denis V. Lunev]

From: Andrey Smetanin <asmetanin@virtuozzo.com>

Added kvm Hyper-V context hv crash variables as storage
of Hyper-V crash msrs.

Signed-off-by: Andrey Smetanin <asmetanin@virtuozzo.com>
Signed-off-by: Denis V. Lunev <den@openvz.org>
Reviewed-by: Peter Hornyack <peterhornyack@google.com>
CC: Paolo Bonzini <pbonzini@redhat.com>
CC: Gleb Natapov <gleb@kernel.org>
---
 arch/x86/include/asm/kvm_host.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 78616aa..697c1f3 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -595,6 +595,10 @@ struct kvm_hv {
 	u64 hv_guest_os_id;
 	u64 hv_hypercall;
 	u64 hv_tsc_page;
+
+	/* Hyper-v based guest crash (NT kernel bugcheck) parameters */
+	u64 hv_crash_param[HV_X64_MSR_CRASH_PARAMS];
+	u64 hv_crash_ctl;
 };
 
 struct kvm_arch {
-- 
2.1.4

[Qemu-devel] [PATCH 5/12] kvm: added KVM_REQ_HV_CRASH value to notify qemu about hyper-v crash

[Denis V. Lunev]

From: Andrey Smetanin <asmetanin@virtuozzo.com>

Added KVM_REQ_HV_CRASH - vcpu request used for notify user space(QEMU)
about Hyper-V crash.

Signed-off-by: Andrey Smetanin <asmetanin@virtuozzo.com>
Signed-off-by: Denis V. Lunev <den@openvz.org>
Reviewed-by: Peter Hornyack <peterhornyack@google.com>
CC: Paolo Bonzini <pbonzini@redhat.com>
CC: Gleb Natapov <gleb@kernel.org>
---
 include/linux/kvm_host.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 2b2edf1..a377e00 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -139,6 +139,7 @@ static inline bool is_error_page(struct page *page)
 #define KVM_REQ_DISABLE_IBS       24
 #define KVM_REQ_APIC_PAGE_RELOAD  25
 #define KVM_REQ_SMI               26
+#define KVM_REQ_HV_CRASH          27
 
 #define KVM_USERSPACE_IRQ_SOURCE_ID		0
 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID	1
-- 
2.1.4

[Qemu-devel] [PATCH 6/12] kvm/x86: mark hyper-v crash msrs as partition wide

[Denis V. Lunev]

From: Andrey Smetanin <asmetanin@virtuozzo.com>

Hyper-V crash msr's are per vm, aren't per vcpu, so mark them
as partition wide.

Signed-off-by: Andrey Smetanin <asmetanin@virtuozzo.com>
Signed-off-by: Denis V. Lunev <den@openvz.org>
Reviewed-by: Peter Hornyack <peterhornyack@google.com>
CC: Paolo Bonzini <pbonzini@redhat.com>
CC: Gleb Natapov <gleb@kernel.org>
---
 arch/x86/kvm/hyperv.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 2b49f10..af83c96 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -39,6 +39,8 @@ static bool kvm_hv_msr_partition_wide(u32 msr)
 	case HV_X64_MSR_HYPERCALL:
 	case HV_X64_MSR_REFERENCE_TSC:
 	case HV_X64_MSR_TIME_REF_COUNT:
+	case HV_X64_MSR_CRASH_CTL:
+	case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
 		r = true;
 		break;
 	}
-- 
2.1.4

[Qemu-devel] [PATCH 7/12] kvm/x86: added hyper-v crash data and ctl msr's get/set'ers

[Denis V. Lunev]

From: Andrey Smetanin <asmetanin@virtuozzo.com>

Added hyper-v crash msr's(HV_X64_MSR_CRASH*) data and control
geters and setters. Userspace should check that such msr's
available by check of KVM_CAP_HYPERV_MSR_CRASH capability.

User space allowed to setup Hyper-V crash ctl msr.
This msr should be setup to HV_X64_MSR_CRASH_CTL_NOTIFY
value so Hyper-V guest knows it can send crash data to host.
But Hyper-V guest notifies about crash event by writing
the same HV_X64_MSR_CRASH_CTL_NOTIFY value into crash ctl msr.
So both user space and guest writes inside ctl msr the same value
and this patch distingiush the moment of actual guest crash
by checking host initiated value from msr info. Also patch
prevents modification of crash ctl msr by guest.

Signed-off-by: Andrey Smetanin <asmetanin@virtuozzo.com>
Signed-off-by: Denis V. Lunev <den@openvz.org>
Reviewed-by: Peter Hornyack <peterhornyack@google.com>
CC: Paolo Bonzini <pbonzini@redhat.com>
CC: Gleb Natapov <gleb@kernel.org>
---
 arch/x86/kvm/hyperv.c    | 74 ++++++++++++++++++++++++++++++++++++++++++++++--
 arch/x86/kvm/hyperv.h    |  2 +-
 arch/x86/kvm/x86.c       |  8 +++++-
 include/uapi/linux/kvm.h |  1 +
 4 files changed, 80 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index af83c96..a8160d2 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -48,7 +48,63 @@ static bool kvm_hv_msr_partition_wide(u32 msr)
 	return r;
 }
 
-static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data)
+static int kvm_hv_msr_get_crash_data(struct kvm_vcpu *vcpu,
+				     u32 index, u64 *pdata)
+{
+	struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;
+
+	if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param)))
+		return -EINVAL;
+
+	*pdata = hv->hv_crash_param[index];
+	return 0;
+}
+
+static int kvm_hv_msr_get_crash_ctl(struct kvm_vcpu *vcpu, u64 *pdata)
+{
+	struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;
+
+	*pdata = hv->hv_crash_ctl;
+	return 0;
+}
+
+static int kvm_hv_msr_set_crash_ctl(struct kvm_vcpu *vcpu, u64 data, bool host)
+{
+	struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;
+
+	if (host)
+		hv->hv_crash_ctl = data & HV_X64_MSR_CRASH_CTL_NOTIFY;
+
+	if (!host && (data & HV_X64_MSR_CRASH_CTL_NOTIFY)) {
+
+		vcpu_debug(vcpu, "hv crash (0x%llx 0x%llx 0x%llx 0x%llx 0x%llx)\n",
+			  hv->hv_crash_param[0],
+			  hv->hv_crash_param[1],
+			  hv->hv_crash_param[2],
+			  hv->hv_crash_param[3],
+			  hv->hv_crash_param[4]);
+
+		/* Send notification about crash to user space */
+		kvm_make_request(KVM_REQ_HV_CRASH, vcpu);
+	}
+
+	return 0;
+}
+
+static int kvm_hv_msr_set_crash_data(struct kvm_vcpu *vcpu,
+				     u32 index, u64 data)
+{
+	struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;
+
+	if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param)))
+		return -EINVAL;
+
+	hv->hv_crash_param[index] = data;
+	return 0;
+}
+
+static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
+			     bool host)
 {
 	struct kvm *kvm = vcpu->kvm;
 	struct kvm_hv *hv = &kvm->arch.hyperv;
@@ -101,6 +157,12 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		mark_page_dirty(kvm, gfn);
 		break;
 	}
+	case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
+		return kvm_hv_msr_set_crash_data(vcpu,
+						 msr - HV_X64_MSR_CRASH_P0,
+						 data);
+	case HV_X64_MSR_CRASH_CTL:
+		return kvm_hv_msr_set_crash_ctl(vcpu, data, host);
 	default:
 		vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n",
 			    msr, data);
@@ -173,6 +235,12 @@ static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case HV_X64_MSR_REFERENCE_TSC:
 		data = hv->hv_tsc_page;
 		break;
+	case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
+		return kvm_hv_msr_get_crash_data(vcpu,
+						 msr - HV_X64_MSR_CRASH_P0,
+						 pdata);
+	case HV_X64_MSR_CRASH_CTL:
+		return kvm_hv_msr_get_crash_ctl(vcpu, pdata);
 	default:
 		vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
 		return 1;
@@ -217,13 +285,13 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	return 0;
 }
 
-int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
+int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
 {
 	if (kvm_hv_msr_partition_wide(msr)) {
 		int r;
 
 		mutex_lock(&vcpu->kvm->lock);
-		r = kvm_hv_set_msr_pw(vcpu, msr, data);
+		r = kvm_hv_set_msr_pw(vcpu, msr, data, host);
 		mutex_unlock(&vcpu->kvm->lock);
 		return r;
 	} else
diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
index 115c738..c7bce55 100644
--- a/arch/x86/kvm/hyperv.h
+++ b/arch/x86/kvm/hyperv.h
@@ -24,7 +24,7 @@
 #ifndef __ARCH_X86_KVM_HYPERV_H__
 #define __ARCH_X86_KVM_HYPERV_H__
 
-int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data);
+int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host);
 int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata);
 bool kvm_hv_hypercall_enabled(struct kvm *kvm);
 int kvm_hv_hypercall(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 301ee01..b4c2767 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2103,7 +2103,10 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		 */
 		break;
 	case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
-		return kvm_hv_set_msr_common(vcpu, msr, data);
+	case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
+	case HV_X64_MSR_CRASH_CTL:
+		return kvm_hv_set_msr_common(vcpu, msr, data,
+					     msr_info->host_initiated);
 	case MSR_IA32_BBL_CR_CTL3:
 		/* Drop writes to this legacy MSR -- see rdmsr
 		 * counterpart for further detail.
@@ -2304,6 +2307,8 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		msr_info->data = 0x20000000;
 		break;
 	case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
+	case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
+	case HV_X64_MSR_CRASH_CTL:
 		return kvm_hv_get_msr_common(vcpu,
 					     msr_info->index, &msr_info->data);
 		break;
@@ -2456,6 +2461,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_TSC_DEADLINE_TIMER:
 	case KVM_CAP_ENABLE_CAP_VM:
 	case KVM_CAP_DISABLE_QUIRKS:
+	case KVM_CAP_HYPERV_MSR_CRASH:
 #ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
 	case KVM_CAP_ASSIGN_DEV_IRQ:
 	case KVM_CAP_PCI_2_3:
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 716ad4a..5da4ca3 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -817,6 +817,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_DISABLE_QUIRKS 116
 #define KVM_CAP_X86_SMM 117
 #define KVM_CAP_MULTI_ADDRESS_SPACE 118
+#define KVM_CAP_HYPERV_MSR_CRASH 119
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
-- 
2.1.4

[Qemu-devel] [PATCH 8/12] kvm/x86: add sending hyper-v crash notification to user space

[Denis V. Lunev]

From: Andrey Smetanin <asmetanin@virtuozzo.com>

Sending of notification is done by exiting vcpu to user space
if KVM_REQ_HV_CRASH is enabled for vcpu. At exit to user space
the kvm_run structure contains system_event with type
KVM_SYSTEM_EVENT_CRASH to notify about guest crash occured.

Signed-off-by: Andrey Smetanin <asmetanin@virtuozzo.com>
Signed-off-by: Denis V. Lunev <den@openvz.org>
Reviewed-by: Peter Hornyack <peterhornyack@google.com>
CC: Paolo Bonzini <pbonzini@redhat.com>
CC: Gleb Natapov <gleb@kernel.org>
---
 Documentation/virtual/kvm/api.txt | 5 +++++
 arch/x86/kvm/x86.c                | 6 ++++++
 include/uapi/linux/kvm.h          | 1 +
 3 files changed, 12 insertions(+)

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index a7926a9..a4ebcb7 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -3277,6 +3277,7 @@ should put the acknowledged interrupt vector into the 'epr' field.
 		struct {
 #define KVM_SYSTEM_EVENT_SHUTDOWN       1
 #define KVM_SYSTEM_EVENT_RESET          2
+#define KVM_SYSTEM_EVENT_CRASH          3
 			__u32 type;
 			__u64 flags;
 		} system_event;
@@ -3296,6 +3297,10 @@ Valid values for 'type' are:
   KVM_SYSTEM_EVENT_RESET -- the guest has requested a reset of the VM.
    As with SHUTDOWN, userspace can choose to ignore the request, or
    to schedule the reset to occur in the future and may call KVM_RUN again.
+  KVM_SYSTEM_EVENT_CRASH -- the guest crash occurred and the guest
+   has requested a crash condition maintenance. Userspace can choose
+   to ignore the request, or to gather VM memory core dump and/or
+   reset/shutdown of the VM.
 
 		/* Fix the size of the union. */
 		char padding[256];
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b4c2767..28e79c0 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6265,6 +6265,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			vcpu_scan_ioapic(vcpu);
 		if (kvm_check_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu))
 			kvm_vcpu_reload_apic_access_page(vcpu);
+		if (kvm_check_request(KVM_REQ_HV_CRASH, vcpu)) {
+			vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
+			vcpu->run->system_event.type = KVM_SYSTEM_EVENT_CRASH;
+			r = 0;
+			goto out;
+		}
 	}
 
 	if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) {
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 5da4ca3..c8c6b8b 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -317,6 +317,7 @@ struct kvm_run {
 		struct {
 #define KVM_SYSTEM_EVENT_SHUTDOWN       1
 #define KVM_SYSTEM_EVENT_RESET          2
+#define KVM_SYSTEM_EVENT_CRASH          3
 			__u32 type;
 			__u64 flags;
 		} system_event;
-- 
2.1.4

[Qemu-devel] [PATCH 6/12] kvm/x86: mark hyper-v crash msrs as partition wide

[Denis V. Lunev]

From: Andrey Smetanin <asmetanin@virtuozzo.com>

Hyper-V crash msr's are per vm, aren't per vcpu, so mark them
as partition wide.

Signed-off-by: Andrey Smetanin <asmetanin@virtuozzo.com>
Signed-off-by: Denis V. Lunev <den@openvz.org>
Reviewed-by: Peter Hornyack <peterhornyack@google.com>
CC: Paolo Bonzini <pbonzini@redhat.com>
CC: Gleb Natapov <gleb@kernel.org>
---
 arch/x86/kvm/hyperv.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 2b49f10..af83c96 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -39,6 +39,8 @@ static bool kvm_hv_msr_partition_wide(u32 msr)
 	case HV_X64_MSR_HYPERCALL:
 	case HV_X64_MSR_REFERENCE_TSC:
 	case HV_X64_MSR_TIME_REF_COUNT:
+	case HV_X64_MSR_CRASH_CTL:
+	case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
 		r = true;
 		break;
 	}
-- 
2.1.4