From 448fa4a9c5dbc6941dd19ed09692c588d815bb06 Mon Sep 17 00:00:00 2001
From: Jan Kiszka <jan.kiszka@siemens.com>
Date: Fri, 26 Sep 2008 09:30:48 +0200
Subject: KVM: x86: Reset pending/inject NMI state on CPU reset

CPU reset invalidates pending or already injected NMIs, therefore reset
the related state variables.

Based on original patch by Gleb Natapov.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/x86/kvm/x86.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'arch/x86/kvm/x86.c')

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f1f8ff2f1fa2..1a71f6735593 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3925,6 +3925,9 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 
 int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu)
 {
+	vcpu->arch.nmi_pending = false;
+	vcpu->arch.nmi_injected = false;
+
 	return kvm_x86_ops->vcpu_reset(vcpu);
 }
 
-- 
cgit v1.2.3


From 0496fbb973ccc9477082e859ed0faab5acb805ba Mon Sep 17 00:00:00 2001
From: Jan Kiszka <jan.kiszka@siemens.com>
Date: Fri, 26 Sep 2008 09:30:53 +0200
Subject: KVM: x86: VCPU with pending NMI is runnabled

Ensure that a VCPU with pending NMIs is considered runnable.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/x86/kvm/x86.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'arch/x86/kvm/x86.c')

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1a71f6735593..1fa9a6db633d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4130,7 +4130,8 @@ void kvm_arch_flush_shadow(struct kvm *kvm)
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE
-	       || vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED;
+	       || vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED
+	       || vcpu->arch.nmi_pending;
 }
 
 static void vcpu_kick_intr(void *info)
-- 
cgit v1.2.3


From c4abb7c9cde24b7351a47328ef866e6a2bbb1ad0 Mon Sep 17 00:00:00 2001
From: Jan Kiszka <jan.kiszka@siemens.com>
Date: Fri, 26 Sep 2008 09:30:55 +0200
Subject: KVM: x86: Support for user space injected NMIs

Introduces the KVM_NMI IOCTL to the generic x86 part of KVM for
injecting NMIs from user space and also extends the statistic report
accordingly.

Based on the original patch by Sheng Yang.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Sheng Yang <sheng.yang@intel.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/x86/include/asm/kvm_host.h |  2 ++
 arch/x86/kvm/x86.c              | 46 +++++++++++++++++++++++++++++++++++++++--
 include/linux/kvm.h             | 11 ++++++++--
 3 files changed, 55 insertions(+), 4 deletions(-)

(limited to 'arch/x86/kvm/x86.c')

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index bfbbdea869bf..a40fa8478920 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -398,6 +398,7 @@ struct kvm_vcpu_stat {
 	u32 halt_exits;
 	u32 halt_wakeup;
 	u32 request_irq_exits;
+	u32 request_nmi_exits;
 	u32 irq_exits;
 	u32 host_state_reload;
 	u32 efer_reload;
@@ -406,6 +407,7 @@ struct kvm_vcpu_stat {
 	u32 insn_emulation_fail;
 	u32 hypercalls;
 	u32 irq_injections;
+	u32 nmi_injections;
 };
 
 struct descriptor_table {
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1fa9a6db633d..07971451b947 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -86,6 +86,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
 	{ "hypercalls", VCPU_STAT(hypercalls) },
 	{ "request_irq", VCPU_STAT(request_irq_exits) },
+	{ "request_nmi", VCPU_STAT(request_nmi_exits) },
 	{ "irq_exits", VCPU_STAT(irq_exits) },
 	{ "host_state_reload", VCPU_STAT(host_state_reload) },
 	{ "efer_reload", VCPU_STAT(efer_reload) },
@@ -93,6 +94,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "insn_emulation", VCPU_STAT(insn_emulation) },
 	{ "insn_emulation_fail", VCPU_STAT(insn_emulation_fail) },
 	{ "irq_injections", VCPU_STAT(irq_injections) },
+	{ "nmi_injections", VCPU_STAT(nmi_injections) },
 	{ "mmu_shadow_zapped", VM_STAT(mmu_shadow_zapped) },
 	{ "mmu_pte_write", VM_STAT(mmu_pte_write) },
 	{ "mmu_pte_updated", VM_STAT(mmu_pte_updated) },
@@ -1318,6 +1320,15 @@ static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+static int kvm_vcpu_ioctl_nmi(struct kvm_vcpu *vcpu)
+{
+	vcpu_load(vcpu);
+	kvm_inject_nmi(vcpu);
+	vcpu_put(vcpu);
+
+	return 0;
+}
+
 static int vcpu_ioctl_tpr_access_reporting(struct kvm_vcpu *vcpu,
 					   struct kvm_tpr_access_ctl *tac)
 {
@@ -1377,6 +1388,13 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = 0;
 		break;
 	}
+	case KVM_NMI: {
+		r = kvm_vcpu_ioctl_nmi(vcpu);
+		if (r)
+			goto out;
+		r = 0;
+		break;
+	}
 	case KVM_SET_CPUID: {
 		struct kvm_cpuid __user *cpuid_arg = argp;
 		struct kvm_cpuid cpuid;
@@ -2812,18 +2830,37 @@ static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu,
 		(kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_IF));
 }
 
+/*
+ * Check if userspace requested a NMI window, and that the NMI window
+ * is open.
+ *
+ * No need to exit to userspace if we already have a NMI queued.
+ */
+static int dm_request_for_nmi_injection(struct kvm_vcpu *vcpu,
+					struct kvm_run *kvm_run)
+{
+	return (!vcpu->arch.nmi_pending &&
+		kvm_run->request_nmi_window &&
+		vcpu->arch.nmi_window_open);
+}
+
 static void post_kvm_run_save(struct kvm_vcpu *vcpu,
 			      struct kvm_run *kvm_run)
 {
 	kvm_run->if_flag = (kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_IF) != 0;
 	kvm_run->cr8 = kvm_get_cr8(vcpu);
 	kvm_run->apic_base = kvm_get_apic_base(vcpu);
-	if (irqchip_in_kernel(vcpu->kvm))
+	if (irqchip_in_kernel(vcpu->kvm)) {
 		kvm_run->ready_for_interrupt_injection = 1;
-	else
+		kvm_run->ready_for_nmi_injection = 1;
+	} else {
 		kvm_run->ready_for_interrupt_injection =
 					(vcpu->arch.interrupt_window_open &&
 					 vcpu->arch.irq_summary == 0);
+		kvm_run->ready_for_nmi_injection =
+					(vcpu->arch.nmi_window_open &&
+					 vcpu->arch.nmi_pending == 0);
+	}
 }
 
 static void vapic_enter(struct kvm_vcpu *vcpu)
@@ -2999,6 +3036,11 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		}
 
 		if (r > 0) {
+			if (dm_request_for_nmi_injection(vcpu, kvm_run)) {
+				r = -EINTR;
+				kvm_run->exit_reason = KVM_EXIT_NMI;
+				++vcpu->stat.request_nmi_exits;
+			}
 			if (dm_request_for_irq_injection(vcpu, kvm_run)) {
 				r = -EINTR;
 				kvm_run->exit_reason = KVM_EXIT_INTR;
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index f18b86fa8655..44fd7fa0af2b 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -83,18 +83,22 @@ struct kvm_irqchip {
 #define KVM_EXIT_S390_SIEIC       13
 #define KVM_EXIT_S390_RESET       14
 #define KVM_EXIT_DCR              15
+#define KVM_EXIT_NMI              16
+#define KVM_EXIT_NMI_WINDOW_OPEN  17
 
 /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */
 struct kvm_run {
 	/* in */
 	__u8 request_interrupt_window;
-	__u8 padding1[7];
+	__u8 request_nmi_window;
+	__u8 padding1[6];
 
 	/* out */
 	__u32 exit_reason;
 	__u8 ready_for_interrupt_injection;
 	__u8 if_flag;
-	__u8 padding2[2];
+	__u8 ready_for_nmi_injection;
+	__u8 padding2;
 
 	/* in (pre_kvm_run), out (post_kvm_run) */
 	__u64 cr8;
@@ -387,6 +391,7 @@ struct kvm_trace_rec {
 #define KVM_CAP_DEVICE_ASSIGNMENT 17
 #endif
 #define KVM_CAP_IOMMU 18
+#define KVM_CAP_NMI 19
 
 /*
  * ioctls for VM fds
@@ -458,6 +463,8 @@ struct kvm_trace_rec {
 #define KVM_S390_INITIAL_RESET    _IO(KVMIO,  0x97)
 #define KVM_GET_MP_STATE          _IOR(KVMIO,  0x98, struct kvm_mp_state)
 #define KVM_SET_MP_STATE          _IOW(KVMIO,  0x99, struct kvm_mp_state)
+/* Available with KVM_CAP_NMI */
+#define KVM_NMI                   _IO(KVMIO,  0x9a)
 
 #define KVM_TRC_INJ_VIRQ         (KVM_TRC_HANDLER + 0x02)
 #define KVM_TRC_REDELIVER_EVT    (KVM_TRC_HANDLER + 0x03)
-- 
cgit v1.2.3


From 5f179287fa02723215eecf681d812b303c243973 Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Tue, 7 Oct 2008 15:42:33 +0200
Subject: KVM: call kvm_arch_vcpu_reset() instead of the kvm_x86_ops callback

Call kvm_arch_vcpu_reset() instead of directly using arch callback.
The function does additional things.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/x86/kvm/x86.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86/kvm/x86.c')

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 07971451b947..a2c4b5594555 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3010,7 +3010,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		pr_debug("vcpu %d received sipi with vector # %x\n",
 			 vcpu->vcpu_id, vcpu->arch.sipi_vector);
 		kvm_lapic_reset(vcpu);
-		r = kvm_x86_ops->vcpu_reset(vcpu);
+		r = kvm_arch_vcpu_reset(vcpu);
 		if (r)
 			return r;
 		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
-- 
cgit v1.2.3


From 0bed3b568b68e5835ef5da888a372b9beabf7544 Mon Sep 17 00:00:00 2001
From: Sheng Yang <sheng@linux.intel.com>
Date: Thu, 9 Oct 2008 16:01:54 +0800
Subject: KVM: Improve MTRR structure

As well as reset mmu context when set MTRR.

Signed-off-by: Sheng Yang <sheng@linux.intel.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/x86/include/asm/kvm_host.h |  5 +++-
 arch/x86/kvm/x86.c              | 61 +++++++++++++++++++++++++++++++++++++++--
 2 files changed, 63 insertions(+), 3 deletions(-)

(limited to 'arch/x86/kvm/x86.c')

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index a40fa8478920..8082e87f628d 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -21,6 +21,7 @@
 
 #include <asm/pvclock-abi.h>
 #include <asm/desc.h>
+#include <asm/mtrr.h>
 
 #define KVM_MAX_VCPUS 16
 #define KVM_MEMORY_SLOTS 32
@@ -86,6 +87,7 @@
 #define KVM_MIN_FREE_MMU_PAGES 5
 #define KVM_REFILL_PAGES 25
 #define KVM_MAX_CPUID_ENTRIES 40
+#define KVM_NR_FIXED_MTRR_REGION 88
 #define KVM_NR_VAR_MTRR 8
 
 extern spinlock_t kvm_lock;
@@ -329,7 +331,8 @@ struct kvm_vcpu_arch {
 	bool nmi_injected;
 	bool nmi_window_open;
 
-	u64 mtrr[0x100];
+	struct mtrr_state_type mtrr_state;
+	u32 pat;
 };
 
 struct kvm_mem_alias {
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a2c4b5594555..f5b2334c6bda 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -39,6 +39,7 @@
 #include <asm/uaccess.h>
 #include <asm/msr.h>
 #include <asm/desc.h>
+#include <asm/mtrr.h>
 
 #define MAX_IO_MSRS 256
 #define CR0_RESERVED_BITS						\
@@ -650,10 +651,38 @@ static bool msr_mtrr_valid(unsigned msr)
 
 static int set_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 {
+	u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges;
+
 	if (!msr_mtrr_valid(msr))
 		return 1;
 
-	vcpu->arch.mtrr[msr - 0x200] = data;
+	if (msr == MSR_MTRRdefType) {
+		vcpu->arch.mtrr_state.def_type = data;
+		vcpu->arch.mtrr_state.enabled = (data & 0xc00) >> 10;
+	} else if (msr == MSR_MTRRfix64K_00000)
+		p[0] = data;
+	else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000)
+		p[1 + msr - MSR_MTRRfix16K_80000] = data;
+	else if (msr >= MSR_MTRRfix4K_C0000 && msr <= MSR_MTRRfix4K_F8000)
+		p[3 + msr - MSR_MTRRfix4K_C0000] = data;
+	else if (msr == MSR_IA32_CR_PAT)
+		vcpu->arch.pat = data;
+	else {	/* Variable MTRRs */
+		int idx, is_mtrr_mask;
+		u64 *pt;
+
+		idx = (msr - 0x200) / 2;
+		is_mtrr_mask = msr - 0x200 - 2 * idx;
+		if (!is_mtrr_mask)
+			pt =
+			  (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].base_lo;
+		else
+			pt =
+			  (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].mask_lo;
+		*pt = data;
+	}
+
+	kvm_mmu_reset_context(vcpu);
 	return 0;
 }
 
@@ -749,10 +778,37 @@ int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
 
 static int get_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 {
+	u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges;
+
 	if (!msr_mtrr_valid(msr))
 		return 1;
 
-	*pdata = vcpu->arch.mtrr[msr - 0x200];
+	if (msr == MSR_MTRRdefType)
+		*pdata = vcpu->arch.mtrr_state.def_type +
+			 (vcpu->arch.mtrr_state.enabled << 10);
+	else if (msr == MSR_MTRRfix64K_00000)
+		*pdata = p[0];
+	else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000)
+		*pdata = p[1 + msr - MSR_MTRRfix16K_80000];
+	else if (msr >= MSR_MTRRfix4K_C0000 && msr <= MSR_MTRRfix4K_F8000)
+		*pdata = p[3 + msr - MSR_MTRRfix4K_C0000];
+	else if (msr == MSR_IA32_CR_PAT)
+		*pdata = vcpu->arch.pat;
+	else {	/* Variable MTRRs */
+		int idx, is_mtrr_mask;
+		u64 *pt;
+
+		idx = (msr - 0x200) / 2;
+		is_mtrr_mask = msr - 0x200 - 2 * idx;
+		if (!is_mtrr_mask)
+			pt =
+			  (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].base_lo;
+		else
+			pt =
+			  (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].mask_lo;
+		*pdata = *pt;
+	}
+
 	return 0;
 }
 
@@ -3942,6 +3998,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	/* We do fxsave: this must be aligned. */
 	BUG_ON((unsigned long)&vcpu->arch.host_fx_image & 0xF);
 
+	vcpu->arch.mtrr_state.have_fixed = 1;
 	vcpu_load(vcpu);
 	r = kvm_arch_vcpu_reset(vcpu);
 	if (r == 0)
-- 
cgit v1.2.3


From 468d472f3f65100d5fb88c8d45043c85b874c294 Mon Sep 17 00:00:00 2001
From: Sheng Yang <sheng@linux.intel.com>
Date: Thu, 9 Oct 2008 16:01:55 +0800
Subject: KVM: VMX: Add PAT support for EPT

GUEST_PAT support is a new feature introduced by Intel Core i7 architecture.
With this, cpu would save/load guest and host PAT automatically, for EPT memory
type in guest depends on MSR_IA32_CR_PAT.

Also add save/restore for MSR_IA32_CR_PAT.

Signed-off-by: Sheng Yang <sheng@linux.intel.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/x86/kvm/vmx.c | 29 ++++++++++++++++++++++++++---
 arch/x86/kvm/vmx.h |  7 +++++++
 arch/x86/kvm/x86.c |  2 +-
 3 files changed, 34 insertions(+), 4 deletions(-)

(limited to 'arch/x86/kvm/x86.c')

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 2180109d794c..b4c95a501cca 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -962,6 +962,13 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
 		pr_unimpl(vcpu, "unimplemented perfctr wrmsr: 0x%x data 0x%llx\n", msr_index, data);
 
 		break;
+	case MSR_IA32_CR_PAT:
+		if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) {
+			vmcs_write64(GUEST_IA32_PAT, data);
+			vcpu->arch.pat = data;
+			break;
+		}
+		/* Otherwise falls through to kvm_set_msr_common */
 	default:
 		vmx_load_host_state(vmx);
 		msr = find_msr_entry(vmx, msr_index);
@@ -1181,12 +1188,13 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
 #ifdef CONFIG_X86_64
 	min |= VM_EXIT_HOST_ADDR_SPACE_SIZE;
 #endif
-	opt = 0;
+	opt = VM_EXIT_SAVE_IA32_PAT | VM_EXIT_LOAD_IA32_PAT;
 	if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_EXIT_CTLS,
 				&_vmexit_control) < 0)
 		return -EIO;
 
-	min = opt = 0;
+	min = 0;
+	opt = VM_ENTRY_LOAD_IA32_PAT;
 	if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_ENTRY_CTLS,
 				&_vmentry_control) < 0)
 		return -EIO;
@@ -2092,8 +2100,9 @@ static void vmx_disable_intercept_for_msr(struct page *msr_bitmap, u32 msr)
  */
 static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 {
-	u32 host_sysenter_cs;
+	u32 host_sysenter_cs, msr_low, msr_high;
 	u32 junk;
+	u64 host_pat;
 	unsigned long a;
 	struct descriptor_table dt;
 	int i;
@@ -2181,6 +2190,20 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 	rdmsrl(MSR_IA32_SYSENTER_EIP, a);
 	vmcs_writel(HOST_IA32_SYSENTER_EIP, a);   /* 22.2.3 */
 
+	if (vmcs_config.vmexit_ctrl & VM_EXIT_LOAD_IA32_PAT) {
+		rdmsr(MSR_IA32_CR_PAT, msr_low, msr_high);
+		host_pat = msr_low | ((u64) msr_high << 32);
+		vmcs_write64(HOST_IA32_PAT, host_pat);
+	}
+	if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) {
+		rdmsr(MSR_IA32_CR_PAT, msr_low, msr_high);
+		host_pat = msr_low | ((u64) msr_high << 32);
+		/* Write the default value follow host pat */
+		vmcs_write64(GUEST_IA32_PAT, host_pat);
+		/* Keep arch.pat sync with GUEST_IA32_PAT */
+		vmx->vcpu.arch.pat = host_pat;
+	}
+
 	for (i = 0; i < NR_VMX_MSR; ++i) {
 		u32 index = vmx_msr_index[i];
 		u32 data_low, data_high;
diff --git a/arch/x86/kvm/vmx.h b/arch/x86/kvm/vmx.h
index ec5edc339da6..18598afe52eb 100644
--- a/arch/x86/kvm/vmx.h
+++ b/arch/x86/kvm/vmx.h
@@ -63,10 +63,13 @@
 
 #define VM_EXIT_HOST_ADDR_SPACE_SIZE            0x00000200
 #define VM_EXIT_ACK_INTR_ON_EXIT                0x00008000
+#define VM_EXIT_SAVE_IA32_PAT			0x00040000
+#define VM_EXIT_LOAD_IA32_PAT			0x00080000
 
 #define VM_ENTRY_IA32E_MODE                     0x00000200
 #define VM_ENTRY_SMM                            0x00000400
 #define VM_ENTRY_DEACT_DUAL_MONITOR             0x00000800
+#define VM_ENTRY_LOAD_IA32_PAT			0x00004000
 
 /* VMCS Encodings */
 enum vmcs_field {
@@ -112,6 +115,8 @@ enum vmcs_field {
 	VMCS_LINK_POINTER_HIGH          = 0x00002801,
 	GUEST_IA32_DEBUGCTL             = 0x00002802,
 	GUEST_IA32_DEBUGCTL_HIGH        = 0x00002803,
+	GUEST_IA32_PAT			= 0x00002804,
+	GUEST_IA32_PAT_HIGH		= 0x00002805,
 	GUEST_PDPTR0                    = 0x0000280a,
 	GUEST_PDPTR0_HIGH               = 0x0000280b,
 	GUEST_PDPTR1                    = 0x0000280c,
@@ -120,6 +125,8 @@ enum vmcs_field {
 	GUEST_PDPTR2_HIGH               = 0x0000280f,
 	GUEST_PDPTR3                    = 0x00002810,
 	GUEST_PDPTR3_HIGH               = 0x00002811,
+	HOST_IA32_PAT			= 0x00002c00,
+	HOST_IA32_PAT_HIGH		= 0x00002c01,
 	PIN_BASED_VM_EXEC_CONTROL       = 0x00004000,
 	CPU_BASED_VM_EXEC_CONTROL       = 0x00004002,
 	EXCEPTION_BITMAP                = 0x00004004,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f5b2334c6bda..0edf75339f3a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -452,7 +452,7 @@ static u32 msrs_to_save[] = {
 	MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR,
 #endif
 	MSR_IA32_TIME_STAMP_COUNTER, MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
-	MSR_IA32_PERF_STATUS,
+	MSR_IA32_PERF_STATUS, MSR_IA32_CR_PAT
 };
 
 static unsigned num_msrs_to_save;
-- 
cgit v1.2.3


From 64d4d521757117aa5c1cfe79d3baa6cf57703f81 Mon Sep 17 00:00:00 2001
From: Sheng Yang <sheng@linux.intel.com>
Date: Thu, 9 Oct 2008 16:01:57 +0800
Subject: KVM: Enable MTRR for EPT

The effective memory type of EPT is the mixture of MSR_IA32_CR_PAT and memory
type field of EPT entry.

Signed-off-by: Sheng Yang <sheng@linux.intel.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/x86/include/asm/kvm_host.h |  3 ++-
 arch/x86/kvm/mmu.c              | 11 ++++++++++-
 arch/x86/kvm/svm.c              |  6 ++++++
 arch/x86/kvm/vmx.c              | 10 ++++++++--
 arch/x86/kvm/x86.c              |  2 +-
 5 files changed, 27 insertions(+), 5 deletions(-)

(limited to 'arch/x86/kvm/x86.c')

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 8082e87f628d..93040b5eed96 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -483,6 +483,7 @@ struct kvm_x86_ops {
 
 	int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
 	int (*get_tdp_level)(void);
+	int (*get_mt_mask_shift)(void);
 };
 
 extern struct kvm_x86_ops *kvm_x86_ops;
@@ -496,7 +497,7 @@ int kvm_mmu_setup(struct kvm_vcpu *vcpu);
 void kvm_mmu_set_nonpresent_ptes(u64 trap_pte, u64 notrap_pte);
 void kvm_mmu_set_base_ptes(u64 base_pte);
 void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
-		u64 dirty_mask, u64 nx_mask, u64 x_mask);
+		u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 mt_mask);
 
 int kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
 void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index ac2304fd173e..09d05f57bf66 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -168,6 +168,7 @@ static u64 __read_mostly shadow_x_mask;	/* mutual exclusive with nx_mask */
 static u64 __read_mostly shadow_user_mask;
 static u64 __read_mostly shadow_accessed_mask;
 static u64 __read_mostly shadow_dirty_mask;
+static u64 __read_mostly shadow_mt_mask;
 
 void kvm_mmu_set_nonpresent_ptes(u64 trap_pte, u64 notrap_pte)
 {
@@ -183,13 +184,14 @@ void kvm_mmu_set_base_ptes(u64 base_pte)
 EXPORT_SYMBOL_GPL(kvm_mmu_set_base_ptes);
 
 void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
-		u64 dirty_mask, u64 nx_mask, u64 x_mask)
+		u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 mt_mask)
 {
 	shadow_user_mask = user_mask;
 	shadow_accessed_mask = accessed_mask;
 	shadow_dirty_mask = dirty_mask;
 	shadow_nx_mask = nx_mask;
 	shadow_x_mask = x_mask;
+	shadow_mt_mask = mt_mask;
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
 
@@ -1546,6 +1548,8 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
 {
 	u64 spte;
 	int ret = 0;
+	u64 mt_mask = shadow_mt_mask;
+
 	/*
 	 * We don't set the accessed bit, since we sometimes want to see
 	 * whether the guest actually used the pte (in order to detect
@@ -1564,6 +1568,11 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
 		spte |= shadow_user_mask;
 	if (largepage)
 		spte |= PT_PAGE_SIZE_MASK;
+	if (mt_mask) {
+		mt_mask = get_memory_type(vcpu, gfn) <<
+			  kvm_x86_ops->get_mt_mask_shift();
+		spte |= mt_mask;
+	}
 
 	spte |= (u64)pfn << PAGE_SHIFT;
 
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 9c4ce657d963..05efc4ef75a6 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1912,6 +1912,11 @@ static int get_npt_level(void)
 #endif
 }
 
+static int svm_get_mt_mask_shift(void)
+{
+	return 0;
+}
+
 static struct kvm_x86_ops svm_x86_ops = {
 	.cpu_has_kvm_support = has_svm,
 	.disabled_by_bios = is_disabled,
@@ -1967,6 +1972,7 @@ static struct kvm_x86_ops svm_x86_ops = {
 
 	.set_tss_addr = svm_set_tss_addr,
 	.get_tdp_level = get_npt_level,
+	.get_mt_mask_shift = svm_get_mt_mask_shift,
 };
 
 static int __init svm_init(void)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index b4c95a501cca..dae134fa09e7 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3574,6 +3574,11 @@ static int get_ept_level(void)
 	return VMX_EPT_DEFAULT_GAW + 1;
 }
 
+static int vmx_get_mt_mask_shift(void)
+{
+	return VMX_EPT_MT_EPTE_SHIFT;
+}
+
 static struct kvm_x86_ops vmx_x86_ops = {
 	.cpu_has_kvm_support = cpu_has_kvm_support,
 	.disabled_by_bios = vmx_disabled_by_bios,
@@ -3629,6 +3634,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
 
 	.set_tss_addr = vmx_set_tss_addr,
 	.get_tdp_level = get_ept_level,
+	.get_mt_mask_shift = vmx_get_mt_mask_shift,
 };
 
 static int __init vmx_init(void)
@@ -3685,10 +3691,10 @@ static int __init vmx_init(void)
 		bypass_guest_pf = 0;
 		kvm_mmu_set_base_ptes(VMX_EPT_READABLE_MASK |
 			VMX_EPT_WRITABLE_MASK |
-			VMX_EPT_DEFAULT_MT << VMX_EPT_MT_EPTE_SHIFT |
 			VMX_EPT_IGMT_BIT);
 		kvm_mmu_set_mask_ptes(0ull, 0ull, 0ull, 0ull,
-				VMX_EPT_EXECUTABLE_MASK);
+				VMX_EPT_EXECUTABLE_MASK,
+				VMX_EPT_DEFAULT_MT << VMX_EPT_MT_EPTE_SHIFT);
 		kvm_enable_tdp();
 	} else
 		kvm_disable_tdp();
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0edf75339f3a..f175b796c2a6 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2615,7 +2615,7 @@ int kvm_arch_init(void *opaque)
 	kvm_mmu_set_nonpresent_ptes(0ull, 0ull);
 	kvm_mmu_set_base_ptes(PT_PRESENT_MASK);
 	kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK,
-			PT_DIRTY_MASK, PT64_NX_MASK, 0);
+			PT_DIRTY_MASK, PT64_NX_MASK, 0, 0);
 	return 0;
 
 out:
-- 
cgit v1.2.3


From b8222ad2e52fd2c0c4e5e1c53e65d131f911b767 Mon Sep 17 00:00:00 2001
From: Amit Shah <amit.shah@redhat.com>
Date: Wed, 22 Oct 2008 16:39:47 +0530
Subject: KVM: x86: Fix typo in function name

get_segment_descritptor_dtable() contains an obvious type.

Signed-off-by: Amit Shah <amit.shah@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/x86/kvm/x86.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'arch/x86/kvm/x86.c')

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f175b796c2a6..ceeac8897143 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3373,9 +3373,9 @@ static void seg_desct_to_kvm_desct(struct desc_struct *seg_desc, u16 selector,
 	kvm_desct->padding = 0;
 }
 
-static void get_segment_descritptor_dtable(struct kvm_vcpu *vcpu,
-					   u16 selector,
-					   struct descriptor_table *dtable)
+static void get_segment_descriptor_dtable(struct kvm_vcpu *vcpu,
+					  u16 selector,
+					  struct descriptor_table *dtable)
 {
 	if (selector & 1 << 2) {
 		struct kvm_segment kvm_seg;
@@ -3400,7 +3400,7 @@ static int load_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
 	struct descriptor_table dtable;
 	u16 index = selector >> 3;
 
-	get_segment_descritptor_dtable(vcpu, selector, &dtable);
+	get_segment_descriptor_dtable(vcpu, selector, &dtable);
 
 	if (dtable.limit < index * 8 + 7) {
 		kvm_queue_exception_e(vcpu, GP_VECTOR, selector & 0xfffc);
@@ -3419,7 +3419,7 @@ static int save_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
 	struct descriptor_table dtable;
 	u16 index = selector >> 3;
 
-	get_segment_descritptor_dtable(vcpu, selector, &dtable);
+	get_segment_descriptor_dtable(vcpu, selector, &dtable);
 
 	if (dtable.limit < index * 8 + 7)
 		return 1;
-- 
cgit v1.2.3


From e93f36bcfaa9e899c595e1c446c784a69021854a Mon Sep 17 00:00:00 2001
From: Guillaume Thouvenin <guillaume.thouvenin@ext.bull.net>
Date: Tue, 28 Oct 2008 10:51:30 +0100
Subject: KVM: allow emulator to adjust rip for emulated pio instructions

If we call the emulator we shouldn't call skip_emulated_instruction()
in the first place, since the emulator already computes the next rip
for us. Thus we move ->skip_emulated_instruction() out of
kvm_emulate_pio() and into handle_io() (and the svm equivalent). We
also replaced "return 0" by "break" in the "do_io:" case because now
the shadow register state needs to be committed. Otherwise eip will never
be updated.

Signed-off-by: Guillaume Thouvenin <guillaume.thouvenin@ext.bull.net>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/x86/kvm/svm.c         | 1 +
 arch/x86/kvm/vmx.c         | 1 +
 arch/x86/kvm/x86.c         | 2 --
 arch/x86/kvm/x86_emulate.c | 2 +-
 4 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'arch/x86/kvm/x86.c')

diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 743aebd7bfcc..f0ad4d4217e4 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1115,6 +1115,7 @@ static int io_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	rep = (io_info & SVM_IOIO_REP_MASK) != 0;
 	down = (svm->vmcb->save.rflags & X86_EFLAGS_DF) != 0;
 
+	skip_emulated_instruction(&svm->vcpu);
 	return kvm_emulate_pio(&svm->vcpu, kvm_run, in, size, port);
 }
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 7623eb7b68d5..816d23185fb8 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2687,6 +2687,7 @@ static int handle_io(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	rep = (exit_qualification & 32) != 0;
 	port = exit_qualification >> 16;
 
+	skip_emulated_instruction(vcpu);
 	return kvm_emulate_pio(vcpu, kvm_run, in, size, port);
 }
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index ceeac8897143..38f79b6aaf1e 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2478,8 +2478,6 @@ int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
 	val = kvm_register_read(vcpu, VCPU_REGS_RAX);
 	memcpy(vcpu->arch.pio_data, &val, 4);
 
-	kvm_x86_ops->skip_emulated_instruction(vcpu);
-
 	pio_dev = vcpu_find_pio_dev(vcpu, port, size, !in);
 	if (pio_dev) {
 		kernel_pio(pio_dev, vcpu, vcpu->arch.pio_data);
diff --git a/arch/x86/kvm/x86_emulate.c b/arch/x86/kvm/x86_emulate.c
index 57d7cc45be44..8f60ace13874 100644
--- a/arch/x86/kvm/x86_emulate.c
+++ b/arch/x86/kvm/x86_emulate.c
@@ -1772,7 +1772,7 @@ special_insn:
 			c->eip = saved_eip;
 			goto cannot_emulate;
 		}
-		return 0;
+		break;
 	case 0xf4:              /* hlt */
 		ctxt->vcpu->arch.halt_request = 1;
 		break;
-- 
cgit v1.2.3


From 6eb55818c043b097c83828da8430fcb9a02fdb89 Mon Sep 17 00:00:00 2001
From: Sheng Yang <sheng@linux.intel.com>
Date: Fri, 31 Oct 2008 12:37:41 +0800
Subject: KVM: Enable Function Level Reset for assigned device

Ideally, every assigned device should in a clear condition before and after
assignment, so that the former state of device won't affect later work.
Some devices provide a mechanism named Function Level Reset, which is
defined in PCI/PCI-e document. We should execute it before and after device
assignment.

(But sadly, the feature is new, and most device on the market now don't
support it. We are considering using D0/D3hot transmit to emulate it later,
but not that elegant and reliable as FLR itself.)

[Update: Reminded by Xiantao, execute FLR after we ensure that the device can
be assigned to the guest.]

Signed-off-by: Sheng Yang <sheng@linux.intel.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/x86/kvm/x86.c  | 2 +-
 virt/kvm/kvm_main.c | 5 +++++
 2 files changed, 6 insertions(+), 1 deletion(-)

(limited to 'arch/x86/kvm/x86.c')

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 38f79b6aaf1e..9a4a39cfe6ef 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4148,8 +4148,8 @@ static void kvm_free_vcpus(struct kvm *kvm)
 
 void kvm_arch_destroy_vm(struct kvm *kvm)
 {
-	kvm_iommu_unmap_guest(kvm);
 	kvm_free_all_assigned_devices(kvm);
+	kvm_iommu_unmap_guest(kvm);
 	kvm_free_pit(kvm);
 	kfree(kvm->arch.vpic);
 	kfree(kvm->arch.vioapic);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 4f43abe198e4..1838052f3c9e 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -152,6 +152,8 @@ static void kvm_free_assigned_device(struct kvm *kvm,
 		 */
 		kvm_put_kvm(kvm);
 
+	pci_reset_function(assigned_dev->dev);
+
 	pci_release_regions(assigned_dev->dev);
 	pci_disable_device(assigned_dev->dev);
 	pci_dev_put(assigned_dev->dev);
@@ -283,6 +285,9 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
 		       __func__);
 		goto out_disable;
 	}
+
+	pci_reset_function(dev);
+
 	match->assigned_dev_id = assigned_dev->assigned_dev_id;
 	match->host_busnr = assigned_dev->busnr;
 	match->host_devfn = assigned_dev->devfn;
-- 
cgit v1.2.3


From 0853d2c1d849ef69884d2447d90d04007590b72b Mon Sep 17 00:00:00 2001
From: Nitin A Kamble <nitin.a.kamble@intel.com>
Date: Wed, 5 Nov 2008 15:37:36 -0800
Subject: KVM: Fix cpuid leaf 0xb loop termination

For cpuid leaf 0xb the bits 8-15 in ECX register define the end of counting
leaf.      The previous code was using bits 0-7 for this purpose, which is
a bug.

Signed-off-by: Nitin A Kamble <nitin.a.kamble@intel.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/x86/kvm/x86.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86/kvm/x86.c')

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9a4a39cfe6ef..2889a0f359ea 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1276,7 +1276,7 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
 		/* read more entries until level_type is zero */
 		for (i = 1; *nent < maxnent; ++i) {
-			level_type = entry[i - 1].ecx & 0xff;
+			level_type = entry[i - 1].ecx & 0xff00;
 			if (!level_type)
 				break;
 			do_cpuid_1_ent(&entry[i], function, i);
-- 
cgit v1.2.3


From 0fdf8e59faa5c60e9d77c8e14abe3a0f8bfcf586 Mon Sep 17 00:00:00 2001
From: Nitin A Kamble <nitin.a.kamble@intel.com>
Date: Wed, 5 Nov 2008 15:56:21 -0800
Subject: KVM: Fix cpuid iteration on multiple leaves per eac

The code to traverse the cpuid data array list for counting type of leaves is
currently broken.

This patches fixes the 2 things in it.

 1. Set the 1st counting entry's flag KVM_CPUID_FLAG_STATE_READ_NEXT. Without
    it the code will never find a valid entry.

 2. Also the stop condition in the for loop while looking for the next unflaged
    entry is broken. It needs to stop when it find one matching entry;
    and in the case of count of 1, it will be the same entry found in this
    iteration.

Signed-Off-By: Nitin A Kamble <nitin.a.kamble@intel.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/x86/kvm/x86.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'arch/x86/kvm/x86.c')

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2889a0f359ea..7a2aeba0bfbd 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1246,6 +1246,7 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		int t, times = entry->eax & 0xff;
 
 		entry->flags |= KVM_CPUID_FLAG_STATEFUL_FUNC;
+		entry->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
 		for (t = 1; t < times && *nent < maxnent; ++t) {
 			do_cpuid_1_ent(&entry[t], function, 0);
 			entry[t].flags |= KVM_CPUID_FLAG_STATEFUL_FUNC;
@@ -2801,7 +2802,7 @@ static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i)
 
 	e->flags &= ~KVM_CPUID_FLAG_STATE_READ_NEXT;
 	/* when no next entry is found, the current entry[i] is reselected */
-	for (j = i + 1; j == i; j = (j + 1) % nent) {
+	for (j = i + 1; ; j = (j + 1) % nent) {
 		struct kvm_cpuid_entry2 *ej = &vcpu->arch.cpuid_entries[j];
 		if (ej->function == e->function) {
 			ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
-- 
cgit v1.2.3


From 6cffe8ca4a2adf1ac5003d9cad08fe4434d6eee0 Mon Sep 17 00:00:00 2001
From: Marcelo Tosatti <mtosatti@redhat.com>
Date: Mon, 1 Dec 2008 22:32:04 -0200
Subject: KVM: MMU: skip global pgtables on sync due to cr3 switch

Skip syncing global pages on cr3 switch (but not on cr4/cr0). This is
important for Linux 32-bit guests with PAE, where the kmap page is
marked as global.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/x86/include/asm/kvm_host.h |  6 +++++
 arch/x86/kvm/mmu.c              | 53 ++++++++++++++++++++++++++++++++++++-----
 arch/x86/kvm/paging_tmpl.h      | 10 ++++----
 arch/x86/kvm/x86.c              |  4 ++++
 4 files changed, 63 insertions(+), 10 deletions(-)

(limited to 'arch/x86/kvm/x86.c')

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 93d0aed35880..65b1ed295698 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -182,6 +182,8 @@ struct kvm_mmu_page {
 	struct list_head link;
 	struct hlist_node hash_link;
 
+	struct list_head oos_link;
+
 	/*
 	 * The following two entries are used to key the shadow page in the
 	 * hash table.
@@ -200,6 +202,7 @@ struct kvm_mmu_page {
 	int multimapped;         /* More than one parent_pte? */
 	int root_count;          /* Currently serving as active root */
 	bool unsync;
+	bool global;
 	unsigned int unsync_children;
 	union {
 		u64 *parent_pte;               /* !multimapped */
@@ -356,6 +359,7 @@ struct kvm_arch{
 	 */
 	struct list_head active_mmu_pages;
 	struct list_head assigned_dev_head;
+	struct list_head oos_global_pages;
 	struct dmar_domain *intel_iommu_domain;
 	struct kvm_pic *vpic;
 	struct kvm_ioapic *vioapic;
@@ -385,6 +389,7 @@ struct kvm_vm_stat {
 	u32 mmu_recycled;
 	u32 mmu_cache_miss;
 	u32 mmu_unsync;
+	u32 mmu_unsync_global;
 	u32 remote_tlb_flush;
 	u32 lpages;
 };
@@ -603,6 +608,7 @@ void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
 int kvm_mmu_load(struct kvm_vcpu *vcpu);
 void kvm_mmu_unload(struct kvm_vcpu *vcpu);
 void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu);
+void kvm_mmu_sync_global(struct kvm_vcpu *vcpu);
 
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
 
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 58c35dead321..cbac9e4b156f 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -793,9 +793,11 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu,
 	sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache, PAGE_SIZE);
 	set_page_private(virt_to_page(sp->spt), (unsigned long)sp);
 	list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages);
+	INIT_LIST_HEAD(&sp->oos_link);
 	ASSERT(is_empty_shadow_page(sp->spt));
 	bitmap_zero(sp->slot_bitmap, KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS);
 	sp->multimapped = 0;
+	sp->global = 1;
 	sp->parent_pte = parent_pte;
 	--vcpu->kvm->arch.n_free_mmu_pages;
 	return sp;
@@ -1066,10 +1068,18 @@ static struct kvm_mmu_page *kvm_mmu_lookup_page(struct kvm *kvm, gfn_t gfn)
 	return NULL;
 }
 
+static void kvm_unlink_unsync_global(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+	list_del(&sp->oos_link);
+	--kvm->stat.mmu_unsync_global;
+}
+
 static void kvm_unlink_unsync_page(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
 	WARN_ON(!sp->unsync);
 	sp->unsync = 0;
+	if (sp->global)
+		kvm_unlink_unsync_global(kvm, sp);
 	--kvm->stat.mmu_unsync;
 }
 
@@ -1615,9 +1625,15 @@ static int kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 		if (s->role.word != sp->role.word)
 			return 1;
 	}
-	kvm_mmu_mark_parents_unsync(vcpu, sp);
 	++vcpu->kvm->stat.mmu_unsync;
 	sp->unsync = 1;
+
+	if (sp->global) {
+		list_add(&sp->oos_link, &vcpu->kvm->arch.oos_global_pages);
+		++vcpu->kvm->stat.mmu_unsync_global;
+	} else
+		kvm_mmu_mark_parents_unsync(vcpu, sp);
+
 	mmu_convert_notrap(sp);
 	return 0;
 }
@@ -1643,12 +1659,21 @@ static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
 static int set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
 		    unsigned pte_access, int user_fault,
 		    int write_fault, int dirty, int largepage,
-		    gfn_t gfn, pfn_t pfn, bool speculative,
+		    int global, gfn_t gfn, pfn_t pfn, bool speculative,
 		    bool can_unsync)
 {
 	u64 spte;
 	int ret = 0;
 	u64 mt_mask = shadow_mt_mask;
+	struct kvm_mmu_page *sp = page_header(__pa(shadow_pte));
+
+	if (!global && sp->global) {
+		sp->global = 0;
+		if (sp->unsync) {
+			kvm_unlink_unsync_global(vcpu->kvm, sp);
+			kvm_mmu_mark_parents_unsync(vcpu, sp);
+		}
+	}
 
 	/*
 	 * We don't set the accessed bit, since we sometimes want to see
@@ -1717,8 +1742,8 @@ set_pte:
 static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
 			 unsigned pt_access, unsigned pte_access,
 			 int user_fault, int write_fault, int dirty,
-			 int *ptwrite, int largepage, gfn_t gfn,
-			 pfn_t pfn, bool speculative)
+			 int *ptwrite, int largepage, int global,
+			 gfn_t gfn, pfn_t pfn, bool speculative)
 {
 	int was_rmapped = 0;
 	int was_writeble = is_writeble_pte(*shadow_pte);
@@ -1751,7 +1776,7 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
 		}
 	}
 	if (set_spte(vcpu, shadow_pte, pte_access, user_fault, write_fault,
-		      dirty, largepage, gfn, pfn, speculative, true)) {
+		      dirty, largepage, global, gfn, pfn, speculative, true)) {
 		if (write_fault)
 			*ptwrite = 1;
 		kvm_x86_ops->tlb_flush(vcpu);
@@ -1808,7 +1833,7 @@ static int direct_map_entry(struct kvm_shadow_walk *_walk,
 	    || (walk->largepage && level == PT_DIRECTORY_LEVEL)) {
 		mmu_set_spte(vcpu, sptep, ACC_ALL, ACC_ALL,
 			     0, walk->write, 1, &walk->pt_write,
-			     walk->largepage, gfn, walk->pfn, false);
+			     walk->largepage, 0, gfn, walk->pfn, false);
 		++vcpu->stat.pf_fixed;
 		return 1;
 	}
@@ -1995,6 +2020,15 @@ static void mmu_sync_roots(struct kvm_vcpu *vcpu)
 	}
 }
 
+static void mmu_sync_global(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_mmu_page *sp, *n;
+
+	list_for_each_entry_safe(sp, n, &kvm->arch.oos_global_pages, oos_link)
+		kvm_sync_page(vcpu, sp);
+}
+
 void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
 {
 	spin_lock(&vcpu->kvm->mmu_lock);
@@ -2002,6 +2036,13 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
 	spin_unlock(&vcpu->kvm->mmu_lock);
 }
 
+void kvm_mmu_sync_global(struct kvm_vcpu *vcpu)
+{
+	spin_lock(&vcpu->kvm->mmu_lock);
+	mmu_sync_global(vcpu);
+	spin_unlock(&vcpu->kvm->mmu_lock);
+}
+
 static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr)
 {
 	return vaddr;
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 84eee43bbe74..e644d81979b6 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -274,7 +274,8 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page,
 		return;
 	kvm_get_pfn(pfn);
 	mmu_set_spte(vcpu, spte, page->role.access, pte_access, 0, 0,
-		     gpte & PT_DIRTY_MASK, NULL, largepage, gpte_to_gfn(gpte),
+		     gpte & PT_DIRTY_MASK, NULL, largepage,
+		     gpte & PT_GLOBAL_MASK, gpte_to_gfn(gpte),
 		     pfn, true);
 }
 
@@ -301,8 +302,9 @@ static int FNAME(shadow_walk_entry)(struct kvm_shadow_walk *_sw,
 		mmu_set_spte(vcpu, sptep, access, gw->pte_access & access,
 			     sw->user_fault, sw->write_fault,
 			     gw->ptes[gw->level-1] & PT_DIRTY_MASK,
-			     sw->ptwrite, sw->largepage, gw->gfn, sw->pfn,
-			     false);
+			     sw->ptwrite, sw->largepage,
+			     gw->ptes[gw->level-1] & PT_GLOBAL_MASK,
+			     gw->gfn, sw->pfn, false);
 		sw->sptep = sptep;
 		return 1;
 	}
@@ -580,7 +582,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 		nr_present++;
 		pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte);
 		set_spte(vcpu, &sp->spt[i], pte_access, 0, 0,
-			 is_dirty_pte(gpte), 0, gfn,
+			 is_dirty_pte(gpte), 0, gpte & PT_GLOBAL_MASK, gfn,
 			 spte_to_pfn(sp->spt[i]), true, false);
 	}
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 7a2aeba0bfbd..774db00d2db6 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -104,6 +104,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "mmu_recycled", VM_STAT(mmu_recycled) },
 	{ "mmu_cache_miss", VM_STAT(mmu_cache_miss) },
 	{ "mmu_unsync", VM_STAT(mmu_unsync) },
+	{ "mmu_unsync_global", VM_STAT(mmu_unsync_global) },
 	{ "remote_tlb_flush", VM_STAT(remote_tlb_flush) },
 	{ "largepages", VM_STAT(lpages) },
 	{ NULL }
@@ -315,6 +316,7 @@ void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	kvm_x86_ops->set_cr0(vcpu, cr0);
 	vcpu->arch.cr0 = cr0;
 
+	kvm_mmu_sync_global(vcpu);
 	kvm_mmu_reset_context(vcpu);
 	return;
 }
@@ -358,6 +360,7 @@ void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	}
 	kvm_x86_ops->set_cr4(vcpu, cr4);
 	vcpu->arch.cr4 = cr4;
+	kvm_mmu_sync_global(vcpu);
 	kvm_mmu_reset_context(vcpu);
 }
 EXPORT_SYMBOL_GPL(kvm_set_cr4);
@@ -4113,6 +4116,7 @@ struct  kvm *kvm_arch_create_vm(void)
 		return ERR_PTR(-ENOMEM);
 
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
+	INIT_LIST_HEAD(&kvm->arch.oos_global_pages);
 	INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);
 
 	/* Reserve bit 0 of irq_sources_bitmap for userspace irq source */
-- 
cgit v1.2.3


From ad218f85e388e8ca816ff09d91c246cd014c53a8 Mon Sep 17 00:00:00 2001
From: Marcelo Tosatti <mtosatti@redhat.com>
Date: Mon, 1 Dec 2008 22:32:05 -0200
Subject: KVM: MMU: prepopulate the shadow on invlpg

If the guest executes invlpg, peek into the pagetable and attempt to
prepopulate the shadow entry.

Also stop dirty fault updates from interfering with the fork detector.

2% improvement on RHEL3/AIM7.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/x86/include/asm/kvm_host.h |  3 ++-
 arch/x86/kvm/mmu.c              | 25 +++++++++++++------------
 arch/x86/kvm/paging_tmpl.h      | 25 ++++++++++++++++++++++++-
 arch/x86/kvm/x86.c              |  2 +-
 4 files changed, 40 insertions(+), 15 deletions(-)

(limited to 'arch/x86/kvm/x86.c')

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 65b1ed295698..97215a458e5f 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -602,7 +602,8 @@ unsigned long segment_base(u16 selector);
 
 void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu);
 void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
-		       const u8 *new, int bytes);
+		       const u8 *new, int bytes,
+		       bool guest_initiated);
 int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva);
 void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
 int kvm_mmu_load(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index cbac9e4b156f..863baf70506e 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2441,7 +2441,8 @@ static void kvm_mmu_access_page(struct kvm_vcpu *vcpu, gfn_t gfn)
 }
 
 void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
-		       const u8 *new, int bytes)
+		       const u8 *new, int bytes,
+		       bool guest_initiated)
 {
 	gfn_t gfn = gpa >> PAGE_SHIFT;
 	struct kvm_mmu_page *sp;
@@ -2467,15 +2468,17 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	kvm_mmu_free_some_pages(vcpu);
 	++vcpu->kvm->stat.mmu_pte_write;
 	kvm_mmu_audit(vcpu, "pre pte write");
-	if (gfn == vcpu->arch.last_pt_write_gfn
-	    && !last_updated_pte_accessed(vcpu)) {
-		++vcpu->arch.last_pt_write_count;
-		if (vcpu->arch.last_pt_write_count >= 3)
-			flooded = 1;
-	} else {
-		vcpu->arch.last_pt_write_gfn = gfn;
-		vcpu->arch.last_pt_write_count = 1;
-		vcpu->arch.last_pte_updated = NULL;
+	if (guest_initiated) {
+		if (gfn == vcpu->arch.last_pt_write_gfn
+		    && !last_updated_pte_accessed(vcpu)) {
+			++vcpu->arch.last_pt_write_count;
+			if (vcpu->arch.last_pt_write_count >= 3)
+				flooded = 1;
+		} else {
+			vcpu->arch.last_pt_write_gfn = gfn;
+			vcpu->arch.last_pt_write_count = 1;
+			vcpu->arch.last_pte_updated = NULL;
+		}
 	}
 	index = kvm_page_table_hashfn(gfn);
 	bucket = &vcpu->kvm->arch.mmu_page_hash[index];
@@ -2615,9 +2618,7 @@ EXPORT_SYMBOL_GPL(kvm_mmu_page_fault);
 
 void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva)
 {
-	spin_lock(&vcpu->kvm->mmu_lock);
 	vcpu->arch.mmu.invlpg(vcpu, gva);
-	spin_unlock(&vcpu->kvm->mmu_lock);
 	kvm_mmu_flush_tlb(vcpu);
 	++vcpu->stat.invlpg;
 }
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index e644d81979b6..d20640154216 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -82,6 +82,7 @@ struct shadow_walker {
 	int *ptwrite;
 	pfn_t pfn;
 	u64 *sptep;
+	gpa_t pte_gpa;
 };
 
 static gfn_t gpte_to_gfn(pt_element_t gpte)
@@ -222,7 +223,7 @@ walk:
 		if (ret)
 			goto walk;
 		pte |= PT_DIRTY_MASK;
-		kvm_mmu_pte_write(vcpu, pte_gpa, (u8 *)&pte, sizeof(pte));
+		kvm_mmu_pte_write(vcpu, pte_gpa, (u8 *)&pte, sizeof(pte), 0);
 		walker->ptes[walker->level - 1] = pte;
 	}
 
@@ -468,8 +469,15 @@ static int FNAME(shadow_invlpg_entry)(struct kvm_shadow_walk *_sw,
 				      struct kvm_vcpu *vcpu, u64 addr,
 				      u64 *sptep, int level)
 {
+	struct shadow_walker *sw =
+		container_of(_sw, struct shadow_walker, walker);
 
 	if (level == PT_PAGE_TABLE_LEVEL) {
+		struct kvm_mmu_page *sp = page_header(__pa(sptep));
+
+		sw->pte_gpa = (sp->gfn << PAGE_SHIFT);
+		sw->pte_gpa += (sptep - sp->spt) * sizeof(pt_element_t);
+
 		if (is_shadow_present_pte(*sptep))
 			rmap_remove(vcpu->kvm, sptep);
 		set_shadow_pte(sptep, shadow_trap_nonpresent_pte);
@@ -482,11 +490,26 @@ static int FNAME(shadow_invlpg_entry)(struct kvm_shadow_walk *_sw,
 
 static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
 {
+	pt_element_t gpte;
 	struct shadow_walker walker = {
 		.walker = { .entry = FNAME(shadow_invlpg_entry), },
+		.pte_gpa = -1,
 	};
 
+	spin_lock(&vcpu->kvm->mmu_lock);
 	walk_shadow(&walker.walker, vcpu, gva);
+	spin_unlock(&vcpu->kvm->mmu_lock);
+	if (walker.pte_gpa == -1)
+		return;
+	if (kvm_read_guest_atomic(vcpu->kvm, walker.pte_gpa, &gpte,
+				  sizeof(pt_element_t)))
+		return;
+	if (is_present_pte(gpte) && (gpte & PT_ACCESSED_MASK)) {
+		if (mmu_topup_memory_caches(vcpu))
+			return;
+		kvm_mmu_pte_write(vcpu, walker.pte_gpa, (const u8 *)&gpte,
+				  sizeof(pt_element_t), 0);
+	}
 }
 
 static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 774db00d2db6..ba102879de33 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2046,7 +2046,7 @@ int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
 	ret = kvm_write_guest(vcpu->kvm, gpa, val, bytes);
 	if (ret < 0)
 		return 0;
-	kvm_mmu_pte_write(vcpu, gpa, val, bytes);
+	kvm_mmu_pte_write(vcpu, gpa, val, bytes, 1);
 	return 1;
 }
 
-- 
cgit v1.2.3


From ca9edaee1aea34ebd9adb48910aba0b3d64b1b22 Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi@redhat.com>
Date: Mon, 8 Dec 2008 18:29:29 +0200
Subject: KVM: Consolidate userspace memory capability reporting into common
 code

Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/ia64/kvm/kvm-ia64.c   | 1 -
 arch/powerpc/kvm/powerpc.c | 3 ---
 arch/s390/kvm/kvm-s390.c   | 2 --
 arch/x86/kvm/x86.c         | 1 -
 virt/kvm/kvm_main.c        | 1 +
 5 files changed, 1 insertion(+), 7 deletions(-)

(limited to 'arch/x86/kvm/x86.c')

diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index b4d24e2cce40..d2eb9691d61d 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -180,7 +180,6 @@ int kvm_dev_ioctl_check_extension(long ext)
 
 	switch (ext) {
 	case KVM_CAP_IRQCHIP:
-	case KVM_CAP_USER_MEMORY:
 	case KVM_CAP_MP_STATE:
 
 		r = 1;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 1deda37cb771..2822c8ccfaaf 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -137,9 +137,6 @@ int kvm_dev_ioctl_check_extension(long ext)
 	int r;
 
 	switch (ext) {
-	case KVM_CAP_USER_MEMORY:
-		r = 1;
-		break;
 	case KVM_CAP_COALESCED_MMIO:
 		r = KVM_COALESCED_MMIO_PAGE_OFFSET;
 		break;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 76f05ddaef10..be8497186b96 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -113,8 +113,6 @@ long kvm_arch_dev_ioctl(struct file *filp,
 int kvm_dev_ioctl_check_extension(long ext)
 {
 	switch (ext) {
-	case KVM_CAP_USER_MEMORY:
-		return 1;
 	default:
 		return 0;
 	}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index ba102879de33..10302d3bd415 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -964,7 +964,6 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_IRQCHIP:
 	case KVM_CAP_HLT:
 	case KVM_CAP_MMU_SHADOW_CACHE_CONTROL:
-	case KVM_CAP_USER_MEMORY:
 	case KVM_CAP_SET_TSS_ADDR:
 	case KVM_CAP_EXT_CPUID:
 	case KVM_CAP_CLOCKSOURCE:
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index e066eb125e55..eb70ca6c7145 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1908,6 +1908,7 @@ static int kvm_dev_ioctl_create_vm(void)
 static long kvm_dev_ioctl_check_extension_generic(long arg)
 {
 	switch (arg) {
+	case KVM_CAP_USER_MEMORY:
 	case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
 		return 1;
 	default:
-- 
cgit v1.2.3


From 4531220b71f0399e71cda0c4cf749e7281a7416a Mon Sep 17 00:00:00 2001
From: Jan Kiszka <jan.kiszka@siemens.com>
Date: Thu, 11 Dec 2008 16:54:54 +0100
Subject: KVM: x86: Rework user space NMI injection as KVM_CAP_USER_NMI

There is no point in doing the ready_for_nmi_injection/
request_nmi_window dance with user space. First, we don't do this for
in-kernel irqchip anyway, while the code path is the same as for user
space irqchip mode. And second, there is nothing to loose if a pending
NMI is overwritten by another one (in contrast to IRQs where we have to
save the number). Actually, there is even the risk of raising spurious
NMIs this way because the reason for the held-back NMI might already be
handled while processing the first one.

Therefore this patch creates a simplified user space NMI injection
interface, exporting it under KVM_CAP_USER_NMI and dropping the old
KVM_CAP_NMI capability. And this time we also take care to provide the
interface only on archs supporting NMIs via KVM (right now only x86).

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/x86/kvm/vmx.c  | 24 ++----------------------
 arch/x86/kvm/x86.c  | 28 ++--------------------------
 include/linux/kvm.h | 11 +++++------
 3 files changed, 9 insertions(+), 54 deletions(-)

(limited to 'arch/x86/kvm/x86.c')

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 487e1dcdce33..6259d7467648 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2498,15 +2498,13 @@ static void do_interrupt_requests(struct kvm_vcpu *vcpu,
 	}
 	if (vcpu->arch.nmi_injected) {
 		vmx_inject_nmi(vcpu);
-		if (vcpu->arch.nmi_pending || kvm_run->request_nmi_window)
+		if (vcpu->arch.nmi_pending)
 			enable_nmi_window(vcpu);
 		else if (vcpu->arch.irq_summary
 			 || kvm_run->request_interrupt_window)
 			enable_irq_window(vcpu);
 		return;
 	}
-	if (!vcpu->arch.nmi_window_open || kvm_run->request_nmi_window)
-		enable_nmi_window(vcpu);
 
 	if (vcpu->arch.interrupt_window_open) {
 		if (vcpu->arch.irq_summary && !vcpu->arch.interrupt.pending)
@@ -3040,14 +3038,6 @@ static int handle_nmi_window(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
 	++vcpu->stat.nmi_window_exits;
 
-	/*
-	 * If the user space waits to inject a NMI, exit as soon as possible
-	 */
-	if (kvm_run->request_nmi_window && !vcpu->arch.nmi_pending) {
-		kvm_run->exit_reason = KVM_EXIT_NMI_WINDOW_OPEN;
-		return 0;
-	}
-
 	return 1;
 }
 
@@ -3162,7 +3152,7 @@ static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 			vmx->soft_vnmi_blocked = 0;
 			vcpu->arch.nmi_window_open = 1;
 		} else if (vmx->vnmi_blocked_time > 1000000000LL &&
-		    (kvm_run->request_nmi_window || vcpu->arch.nmi_pending)) {
+			   vcpu->arch.nmi_pending) {
 			/*
 			 * This CPU don't support us in finding the end of an
 			 * NMI-blocked window if the guest runs with IRQs
@@ -3175,16 +3165,6 @@ static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 			vmx->soft_vnmi_blocked = 0;
 			vmx->vcpu.arch.nmi_window_open = 1;
 		}
-
-		/*
-		 * If the user space waits to inject an NNI, exit ASAP
-		 */
-		if (vcpu->arch.nmi_window_open && kvm_run->request_nmi_window
-		    && !vcpu->arch.nmi_pending) {
-			kvm_run->exit_reason = KVM_EXIT_NMI_WINDOW_OPEN;
-			++vcpu->stat.nmi_window_exits;
-			return 0;
-		}
 	}
 
 	if (exit_reason < kvm_vmx_max_exit_handlers
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 10302d3bd415..0e6aa8141dcd 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2887,37 +2887,18 @@ static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu,
 		(kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_IF));
 }
 
-/*
- * Check if userspace requested a NMI window, and that the NMI window
- * is open.
- *
- * No need to exit to userspace if we already have a NMI queued.
- */
-static int dm_request_for_nmi_injection(struct kvm_vcpu *vcpu,
-					struct kvm_run *kvm_run)
-{
-	return (!vcpu->arch.nmi_pending &&
-		kvm_run->request_nmi_window &&
-		vcpu->arch.nmi_window_open);
-}
-
 static void post_kvm_run_save(struct kvm_vcpu *vcpu,
 			      struct kvm_run *kvm_run)
 {
 	kvm_run->if_flag = (kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_IF) != 0;
 	kvm_run->cr8 = kvm_get_cr8(vcpu);
 	kvm_run->apic_base = kvm_get_apic_base(vcpu);
-	if (irqchip_in_kernel(vcpu->kvm)) {
+	if (irqchip_in_kernel(vcpu->kvm))
 		kvm_run->ready_for_interrupt_injection = 1;
-		kvm_run->ready_for_nmi_injection = 1;
-	} else {
+	else
 		kvm_run->ready_for_interrupt_injection =
 					(vcpu->arch.interrupt_window_open &&
 					 vcpu->arch.irq_summary == 0);
-		kvm_run->ready_for_nmi_injection =
-					(vcpu->arch.nmi_window_open &&
-					 vcpu->arch.nmi_pending == 0);
-	}
 }
 
 static void vapic_enter(struct kvm_vcpu *vcpu)
@@ -3093,11 +3074,6 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		}
 
 		if (r > 0) {
-			if (dm_request_for_nmi_injection(vcpu, kvm_run)) {
-				r = -EINTR;
-				kvm_run->exit_reason = KVM_EXIT_NMI;
-				++vcpu->stat.request_nmi_exits;
-			}
 			if (dm_request_for_irq_injection(vcpu, kvm_run)) {
 				r = -EINTR;
 				kvm_run->exit_reason = KVM_EXIT_INTR;
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 48807767e726..35525ac63337 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -84,21 +84,18 @@ struct kvm_irqchip {
 #define KVM_EXIT_S390_RESET       14
 #define KVM_EXIT_DCR              15
 #define KVM_EXIT_NMI              16
-#define KVM_EXIT_NMI_WINDOW_OPEN  17
 
 /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */
 struct kvm_run {
 	/* in */
 	__u8 request_interrupt_window;
-	__u8 request_nmi_window;
-	__u8 padding1[6];
+	__u8 padding1[7];
 
 	/* out */
 	__u32 exit_reason;
 	__u8 ready_for_interrupt_injection;
 	__u8 if_flag;
-	__u8 ready_for_nmi_injection;
-	__u8 padding2;
+	__u8 padding2[2];
 
 	/* in (pre_kvm_run), out (post_kvm_run) */
 	__u64 cr8;
@@ -391,12 +388,14 @@ struct kvm_trace_rec {
 #define KVM_CAP_DEVICE_ASSIGNMENT 17
 #endif
 #define KVM_CAP_IOMMU 18
-#define KVM_CAP_NMI 19
 #if defined(CONFIG_X86)
 #define KVM_CAP_DEVICE_MSI 20
 #endif
 /* Bug in KVM_SET_USER_MEMORY_REGION fixed: */
 #define KVM_CAP_DESTROY_MEMORY_REGION_WORKS 21
+#if defined(CONFIG_X86)
+#define KVM_CAP_USER_NMI 22
+#endif
 
 /*
  * ioctls for VM fds
-- 
cgit v1.2.3