From e9196cebbe41559d2c485f004b3db869ba34ba29 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Thu, 18 May 2017 10:39:53 +0300
Subject: KVM: Tidy the whitespace in nested_svm_check_permissions()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

I moved the || to the line before.  Also I replaced some spaces with a
tab on the "return 0;" line.  It looks OK in the diff but originally
that line was only indented 7 spaces.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
---
 arch/x86/kvm/svm.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index ba9891ac5c56..6e3095d1bad4 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -2369,8 +2369,8 @@ static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu)
 
 static int nested_svm_check_permissions(struct vcpu_svm *svm)
 {
-	if (!(svm->vcpu.arch.efer & EFER_SVME)
-	    || !is_paging(&svm->vcpu)) {
+	if (!(svm->vcpu.arch.efer & EFER_SVME) ||
+	    !is_paging(&svm->vcpu)) {
 		kvm_queue_exception(&svm->vcpu, UD_VECTOR);
 		return 1;
 	}
@@ -2380,7 +2380,7 @@ static int nested_svm_check_permissions(struct vcpu_svm *svm)
 		return 1;
 	}
 
-       return 0;
+	return 0;
 }
 
 static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
-- 
cgit v1.2.3


From 7461fbc46e9078d3143d396e2ad1c0c5bfd07b6f Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Thu, 18 May 2017 10:41:15 +0300
Subject: KVM: white space cleanup in nested_vmx_setup_ctls_msrs()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This should have been indented one more character over and it should use
tabs.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
---
 arch/x86/kvm/vmx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 9b4b5d6dcd34..60fa010d3fa1 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2769,7 +2769,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 		if (enable_ept_ad_bits) {
 			vmx->nested.nested_vmx_secondary_ctls_high |=
 				SECONDARY_EXEC_ENABLE_PML;
-		       vmx->nested.nested_vmx_ept_caps |= VMX_EPT_AD_BIT;
+			vmx->nested.nested_vmx_ept_caps |= VMX_EPT_AD_BIT;
 		}
 	} else
 		vmx->nested.nested_vmx_ept_caps = 0;
-- 
cgit v1.2.3


From 9d643f63128bcec2b845fd0719a6b971b68c59cc Mon Sep 17 00:00:00 2001
From: Nick Desaulniers <nick.desaulniers@gmail.com>
Date: Tue, 30 May 2017 20:08:38 -0700
Subject: KVM: x86: avoid large stack allocations in em_fxrstor

em_fxstor previously called fxstor_fixup.  Both created instances of
struct fxregs_state on the stack, which triggered the warning:

arch/x86/kvm/emulate.c:4018:12: warning: stack frame size of 1080 bytes
in function
      'em_fxrstor' [-Wframe-larger-than=]
static int em_fxrstor(struct x86_emulate_ctxt *ctxt)
           ^
with CONFIG_FRAME_WARN set to 1024.

This patch does the fixup in em_fxstor now, avoiding one additional
struct fxregs_state, and now fxstor_fixup can be removed as it has no
other call sites.

Further, the calculation for offsets into xmm_space can be shared
between em_fxstor and em_fxsave.

Signed-off-by: Nick Desaulniers <nick.desaulniers@gmail.com>
[Clean up calculation of offsets and fix it for 64-bit mode. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/emulate.c | 82 +++++++++++++++++++++++---------------------------
 1 file changed, 37 insertions(+), 45 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 0816ab2e8adc..0f0815c824de 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -3940,6 +3940,25 @@ static int check_fxsr(struct x86_emulate_ctxt *ctxt)
 	return X86EMUL_CONTINUE;
 }
 
+/*
+ * Hardware doesn't save and restore XMM 0-7 without CR4.OSFXSR, but does save
+ * and restore MXCSR.
+ */
+static size_t __fxstate_size(int nregs)
+{
+	return offsetof(struct fxregs_state, xmm_space[0]) + nregs * 16;
+}
+
+static inline size_t fxstate_size(struct x86_emulate_ctxt *ctxt)
+{
+	bool cr4_osfxsr;
+	if (ctxt->mode == X86EMUL_MODE_PROT64)
+		return __fxstate_size(16);
+
+	cr4_osfxsr = ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR;
+	return __fxstate_size(cr4_osfxsr ? 8 : 0);
+}
+
 /*
  * FXSAVE and FXRSTOR have 4 different formats depending on execution mode,
  *  1) 16 bit mode
@@ -3961,7 +3980,6 @@ static int check_fxsr(struct x86_emulate_ctxt *ctxt)
 static int em_fxsave(struct x86_emulate_ctxt *ctxt)
 {
 	struct fxregs_state fx_state;
-	size_t size;
 	int rc;
 
 	rc = check_fxsr(ctxt);
@@ -3977,68 +3995,42 @@ static int em_fxsave(struct x86_emulate_ctxt *ctxt)
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
-	if (ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR)
-		size = offsetof(struct fxregs_state, xmm_space[8 * 16/4]);
-	else
-		size = offsetof(struct fxregs_state, xmm_space[0]);
-
-	return segmented_write_std(ctxt, ctxt->memop.addr.mem, &fx_state, size);
-}
-
-static int fxrstor_fixup(struct x86_emulate_ctxt *ctxt,
-		struct fxregs_state *new)
-{
-	int rc = X86EMUL_CONTINUE;
-	struct fxregs_state old;
-
-	rc = asm_safe("fxsave %[fx]", , [fx] "+m"(old));
-	if (rc != X86EMUL_CONTINUE)
-		return rc;
-
-	/*
-	 * 64 bit host will restore XMM 8-15, which is not correct on non-64
-	 * bit guests.  Load the current values in order to preserve 64 bit
-	 * XMMs after fxrstor.
-	 */
-#ifdef CONFIG_X86_64
-	/* XXX: accessing XMM 8-15 very awkwardly */
-	memcpy(&new->xmm_space[8 * 16/4], &old.xmm_space[8 * 16/4], 8 * 16);
-#endif
-
-	/*
-	 * Hardware doesn't save and restore XMM 0-7 without CR4.OSFXSR, but
-	 * does save and restore MXCSR.
-	 */
-	if (!(ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR))
-		memcpy(new->xmm_space, old.xmm_space, 8 * 16);
-
-	return rc;
+	return segmented_write_std(ctxt, ctxt->memop.addr.mem, &fx_state,
+		                   fxstate_size(ctxt));
 }
 
 static int em_fxrstor(struct x86_emulate_ctxt *ctxt)
 {
 	struct fxregs_state fx_state;
 	int rc;
+	size_t size;
 
 	rc = check_fxsr(ctxt);
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
-	rc = segmented_read_std(ctxt, ctxt->memop.addr.mem, &fx_state, 512);
-	if (rc != X86EMUL_CONTINUE)
-		return rc;
+	ctxt->ops->get_fpu(ctxt);
 
-	if (fx_state.mxcsr >> 16)
-		return emulate_gp(ctxt, 0);
+	size = fxstate_size(ctxt);
+	if (size < __fxstate_size(16)) {
+		rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state));
+		if (rc != X86EMUL_CONTINUE)
+			goto out;
+	}
 
-	ctxt->ops->get_fpu(ctxt);
+	rc = segmented_read_std(ctxt, ctxt->memop.addr.mem, &fx_state, size);
+	if (rc != X86EMUL_CONTINUE)
+		goto out;
 
-	if (ctxt->mode < X86EMUL_MODE_PROT64)
-		rc = fxrstor_fixup(ctxt, &fx_state);
+	if (fx_state.mxcsr >> 16) {
+		rc = emulate_gp(ctxt, 0);
+		goto out;
+	}
 
 	if (rc == X86EMUL_CONTINUE)
 		rc = asm_safe("fxrstor %[fx]", : [fx] "m"(fx_state));
 
+out:
 	ctxt->ops->put_fpu(ctxt);
 
 	return rc;
-- 
cgit v1.2.3


From 2387149eade25f32dcf1398811b3d0293181d005 Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Sun, 4 Jun 2017 14:43:51 +0200
Subject: KVM: improve arch vcpu request defining

Marc Zyngier suggested that we define the arch specific VCPU request
base, rather than requiring each arch to remember to start from 8.
That suggestion, along with Radim Krcmar's recent VCPU request flag
addition, snowballed into defining something of an arch VCPU request
defining API.

No functional change.

(Looks like x86 is running out of arch VCPU request bits.  Maybe
 someday we'll need to extend to 64.)

Signed-off-by: Andrew Jones <drjones@redhat.com>
Acked-by: Christoffer Dall <cdall@linaro.org>
Signed-off-by: Christoffer Dall <cdall@linaro.org>
---
 arch/arm/include/asm/kvm_host.h     |  3 ++-
 arch/arm64/include/asm/kvm_host.h   |  3 ++-
 arch/powerpc/include/asm/kvm_host.h |  4 ++--
 arch/s390/include/asm/kvm_host.h    |  6 ++---
 arch/x86/include/asm/kvm_host.h     | 47 ++++++++++++++++++++-----------------
 include/linux/kvm_host.h            |  7 ++++++
 6 files changed, 41 insertions(+), 29 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index 12274d46df70..c556babe467c 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -44,7 +44,8 @@
 #define KVM_MAX_VCPUS VGIC_V2_MAX_CPUS
 #endif
 
-#define KVM_REQ_VCPU_EXIT	(8 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
+#define KVM_REQ_VCPU_EXIT \
+	KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 
 u32 *kvm_vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num, u32 mode);
 int __attribute_const__ kvm_target_cpu(void);
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 32cbe8a3bb0d..0ff991c9c66e 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -41,7 +41,8 @@
 
 #define KVM_VCPU_MAX_FEATURES 4
 
-#define KVM_REQ_VCPU_EXIT	(8 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
+#define KVM_REQ_VCPU_EXIT \
+	KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 
 int __attribute_const__ kvm_target_cpu(void);
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 9c51ac4b8f36..50e0bc9723cc 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -52,8 +52,8 @@
 #define KVM_IRQCHIP_NUM_PINS     256
 
 /* PPC-specific vcpu->requests bit members */
-#define KVM_REQ_WATCHDOG           8
-#define KVM_REQ_EPR_EXIT           9
+#define KVM_REQ_WATCHDOG	KVM_ARCH_REQ(0)
+#define KVM_REQ_EPR_EXIT	KVM_ARCH_REQ(1)
 
 #include <linux/mmu_notifier.h>
 
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 426614a882a9..9c3bd94204ac 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -42,9 +42,9 @@
 #define KVM_HALT_POLL_NS_DEFAULT 80000
 
 /* s390-specific vcpu->requests bit members */
-#define KVM_REQ_ENABLE_IBS         8
-#define KVM_REQ_DISABLE_IBS        9
-#define KVM_REQ_ICPT_OPEREXC       10
+#define KVM_REQ_ENABLE_IBS	KVM_ARCH_REQ(0)
+#define KVM_REQ_DISABLE_IBS	KVM_ARCH_REQ(1)
+#define KVM_REQ_ICPT_OPEREXC	KVM_ARCH_REQ(2)
 
 #define SIGP_CTRL_C		0x80
 #define SIGP_CTRL_SCN_MASK	0x3f
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 9c761fea0c98..563979976fab 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -48,28 +48,31 @@
 #define KVM_IRQCHIP_NUM_PINS  KVM_IOAPIC_NUM_PINS
 
 /* x86-specific vcpu->requests bit members */
-#define KVM_REQ_MIGRATE_TIMER      8
-#define KVM_REQ_REPORT_TPR_ACCESS  9
-#define KVM_REQ_TRIPLE_FAULT      10
-#define KVM_REQ_MMU_SYNC          11
-#define KVM_REQ_CLOCK_UPDATE      12
-#define KVM_REQ_EVENT             14
-#define KVM_REQ_APF_HALT          15
-#define KVM_REQ_STEAL_UPDATE      16
-#define KVM_REQ_NMI               17
-#define KVM_REQ_PMU               18
-#define KVM_REQ_PMI               19
-#define KVM_REQ_SMI               20
-#define KVM_REQ_MASTERCLOCK_UPDATE 21
-#define KVM_REQ_MCLOCK_INPROGRESS (22 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
-#define KVM_REQ_SCAN_IOAPIC       (23 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
-#define KVM_REQ_GLOBAL_CLOCK_UPDATE 24
-#define KVM_REQ_APIC_PAGE_RELOAD  (25 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
-#define KVM_REQ_HV_CRASH          26
-#define KVM_REQ_IOAPIC_EOI_EXIT   27
-#define KVM_REQ_HV_RESET          28
-#define KVM_REQ_HV_EXIT           29
-#define KVM_REQ_HV_STIMER         30
+#define KVM_REQ_MIGRATE_TIMER		KVM_ARCH_REQ(0)
+#define KVM_REQ_REPORT_TPR_ACCESS	KVM_ARCH_REQ(1)
+#define KVM_REQ_TRIPLE_FAULT		KVM_ARCH_REQ(2)
+#define KVM_REQ_MMU_SYNC		KVM_ARCH_REQ(3)
+#define KVM_REQ_CLOCK_UPDATE		KVM_ARCH_REQ(4)
+#define KVM_REQ_EVENT			KVM_ARCH_REQ(6)
+#define KVM_REQ_APF_HALT		KVM_ARCH_REQ(7)
+#define KVM_REQ_STEAL_UPDATE		KVM_ARCH_REQ(8)
+#define KVM_REQ_NMI			KVM_ARCH_REQ(9)
+#define KVM_REQ_PMU			KVM_ARCH_REQ(10)
+#define KVM_REQ_PMI			KVM_ARCH_REQ(11)
+#define KVM_REQ_SMI			KVM_ARCH_REQ(12)
+#define KVM_REQ_MASTERCLOCK_UPDATE	KVM_ARCH_REQ(13)
+#define KVM_REQ_MCLOCK_INPROGRESS \
+	KVM_ARCH_REQ_FLAGS(14, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
+#define KVM_REQ_SCAN_IOAPIC \
+	KVM_ARCH_REQ_FLAGS(15, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
+#define KVM_REQ_GLOBAL_CLOCK_UPDATE	KVM_ARCH_REQ(16)
+#define KVM_REQ_APIC_PAGE_RELOAD \
+	KVM_ARCH_REQ_FLAGS(17, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
+#define KVM_REQ_HV_CRASH		KVM_ARCH_REQ(18)
+#define KVM_REQ_IOAPIC_EOI_EXIT		KVM_ARCH_REQ(19)
+#define KVM_REQ_HV_RESET		KVM_ARCH_REQ(20)
+#define KVM_REQ_HV_EXIT			KVM_ARCH_REQ(21)
+#define KVM_REQ_HV_STIMER		KVM_ARCH_REQ(22)
 
 #define CR0_RESERVED_BITS                                               \
 	(~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 8c0664309815..3724b51aab64 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -126,6 +126,13 @@ static inline bool is_error_page(struct page *page)
 #define KVM_REQ_MMU_RELOAD        (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_PENDING_TIMER     2
 #define KVM_REQ_UNHALT            3
+#define KVM_REQUEST_ARCH_BASE     8
+
+#define KVM_ARCH_REQ_FLAGS(nr, flags) ({ \
+	BUILD_BUG_ON((unsigned)(nr) >= 32 - KVM_REQUEST_ARCH_BASE); \
+	(unsigned)(((nr) + KVM_REQUEST_ARCH_BASE) | (flags)); \
+})
+#define KVM_ARCH_REQ(nr)           KVM_ARCH_REQ_FLAGS(nr, 0)
 
 #define KVM_USERSPACE_IRQ_SOURCE_ID		0
 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID	1
-- 
cgit v1.2.3


From 2fa6e1e12a024b48b2c7ea39f50205246e027da7 Mon Sep 17 00:00:00 2001
From: Radim Krčmář <rkrcmar@redhat.com>
Date: Sun, 4 Jun 2017 14:43:52 +0200
Subject: KVM: add kvm_request_pending
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

A first step in vcpu->requests encapsulation.  Additionally, we now
use READ_ONCE() when accessing vcpu->requests, which ensures we
always load vcpu->requests when it's accessed.  This is important as
other threads can change it any time.  Also, READ_ONCE() documents
that vcpu->requests is used with other threads, likely requiring
memory barriers, which it does.

Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
[ Documented the new use of READ_ONCE() and converted another check
  in arch/mips/kvm/vz.c ]
Signed-off-by: Andrew Jones <drjones@redhat.com>
Acked-by: Christoffer Dall <cdall@linaro.org>
Signed-off-by: Christoffer Dall <cdall@linaro.org>
---
 arch/mips/kvm/trap_emul.c  | 2 +-
 arch/mips/kvm/vz.c         | 2 +-
 arch/powerpc/kvm/booke.c   | 2 +-
 arch/powerpc/kvm/powerpc.c | 5 ++---
 arch/s390/kvm/kvm-s390.c   | 2 +-
 arch/x86/kvm/x86.c         | 4 ++--
 include/linux/kvm_host.h   | 5 +++++
 7 files changed, 13 insertions(+), 9 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/mips/kvm/trap_emul.c b/arch/mips/kvm/trap_emul.c
index a563759fd142..6a0d7040d882 100644
--- a/arch/mips/kvm/trap_emul.c
+++ b/arch/mips/kvm/trap_emul.c
@@ -1094,7 +1094,7 @@ static void kvm_trap_emul_check_requests(struct kvm_vcpu *vcpu, int cpu,
 	struct mm_struct *mm;
 	int i;
 
-	if (likely(!vcpu->requests))
+	if (likely(!kvm_request_pending(vcpu)))
 		return;
 
 	if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) {
diff --git a/arch/mips/kvm/vz.c b/arch/mips/kvm/vz.c
index 71d8856ade64..74805035edc8 100644
--- a/arch/mips/kvm/vz.c
+++ b/arch/mips/kvm/vz.c
@@ -2337,7 +2337,7 @@ static int kvm_vz_check_requests(struct kvm_vcpu *vcpu, int cpu)
 	int ret = 0;
 	int i;
 
-	if (!vcpu->requests)
+	if (!kvm_request_pending(vcpu))
 		return 0;
 
 	if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) {
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 3eaac3809977..071b87ee682f 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -687,7 +687,7 @@ int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu)
 
 	kvmppc_core_check_exceptions(vcpu);
 
-	if (vcpu->requests) {
+	if (kvm_request_pending(vcpu)) {
 		/* Exception delivery raised request; start over */
 		return 1;
 	}
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index f7cf2cd564ef..fd64f087737c 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -55,8 +55,7 @@ EXPORT_SYMBOL_GPL(kvmppc_pr_ops);
 
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
 {
-	return !!(v->arch.pending_exceptions) ||
-	       v->requests;
+	return !!(v->arch.pending_exceptions) || kvm_request_pending(v);
 }
 
 int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
@@ -108,7 +107,7 @@ int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu)
 		 */
 		smp_mb();
 
-		if (vcpu->requests) {
+		if (kvm_request_pending(vcpu)) {
 			/* Make sure we process requests preemptable */
 			local_irq_enable();
 			trace_kvm_check_requests(vcpu);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 689ac48361c6..ad41e0fa3a21 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -2440,7 +2440,7 @@ static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu)
 {
 retry:
 	kvm_s390_vcpu_request_handled(vcpu);
-	if (!vcpu->requests)
+	if (!kvm_request_pending(vcpu))
 		return 0;
 	/*
 	 * We use MMU_RELOAD just to re-arm the ipte notifier for the
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 464da936c53d..f81060518635 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6710,7 +6710,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 	bool req_immediate_exit = false;
 
-	if (vcpu->requests) {
+	if (kvm_request_pending(vcpu)) {
 		if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu))
 			kvm_mmu_unload(vcpu);
 		if (kvm_check_request(KVM_REQ_MIGRATE_TIMER, vcpu))
@@ -6874,7 +6874,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			kvm_x86_ops->sync_pir_to_irr(vcpu);
 	}
 
-	if (vcpu->mode == EXITING_GUEST_MODE || vcpu->requests
+	if (vcpu->mode == EXITING_GUEST_MODE || kvm_request_pending(vcpu)
 	    || need_resched() || signal_pending(current)) {
 		vcpu->mode = OUTSIDE_GUEST_MODE;
 		smp_wmb();
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 3724b51aab64..0b50e7b35ed4 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1105,6 +1105,11 @@ static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu)
 	set_bit(req & KVM_REQUEST_MASK, &vcpu->requests);
 }
 
+static inline bool kvm_request_pending(struct kvm_vcpu *vcpu)
+{
+	return READ_ONCE(vcpu->requests);
+}
+
 static inline bool kvm_test_request(int req, struct kvm_vcpu *vcpu)
 {
 	return test_bit(req & KVM_REQUEST_MASK, &vcpu->requests);
-- 
cgit v1.2.3


From a8b6fda38f80e75afa3b125c9e7f2550b579454b Mon Sep 17 00:00:00 2001
From: Jim Mattson <jmattson@google.com>
Date: Tue, 23 May 2017 11:52:52 -0700
Subject: kvm: vmx: Do not disable intercepts for BNDCFGS
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The MSR permission bitmaps are shared by all VMs. However, some VMs
may not be configured to support MPX, even when the host does. If the
host supports VMX and the guest does not, we should intercept accesses
to the BNDCFGS MSR, so that we can synthesize a #GP
fault. Furthermore, if the host does not support MPX and the
"ignore_msrs" kvm kernel parameter is set, then we should intercept
accesses to the BNDCFGS MSR, so that we can skip over the rdmsr/wrmsr
without raising a #GP fault.

Fixes: da8999d31818fdc8 ("KVM: x86: Intel MPX vmx and msr handle")
Signed-off-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
---
 arch/x86/kvm/vmx.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 60fa010d3fa1..577bb1d75e1e 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6547,7 +6547,6 @@ static __init int hardware_setup(void)
 	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false);
 	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false);
 	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false);
-	vmx_disable_intercept_for_msr(MSR_IA32_BNDCFGS, true);
 
 	memcpy(vmx_msr_bitmap_legacy_x2apic_apicv,
 			vmx_msr_bitmap_legacy, PAGE_SIZE);
-- 
cgit v1.2.3


From 4439af9f911ae0243ffe4e2dfc12bace49605d8b Mon Sep 17 00:00:00 2001
From: Jim Mattson <jmattson@google.com>
Date: Wed, 24 May 2017 10:49:25 -0700
Subject: kvm: x86: Guest BNDCFGS requires guest MPX support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The BNDCFGS MSR should only be exposed to the guest if the guest
supports MPX. (cf. the TSC_AUX MSR and RDTSCP.)

Fixes: 0dd376e709975779 ("KVM: x86: add MSR_IA32_BNDCFGS to msrs_to_save")
Change-Id: I3ad7c01bda616715137ceac878f3fa7e66b6b387
Signed-off-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
---
 arch/x86/kvm/cpuid.h | 8 ++++++++
 arch/x86/kvm/vmx.c   | 4 ++--
 2 files changed, 10 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index a6fd40aade7c..da6728383052 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -144,6 +144,14 @@ static inline bool guest_cpuid_has_rtm(struct kvm_vcpu *vcpu)
 	return best && (best->ebx & bit(X86_FEATURE_RTM));
 }
 
+static inline bool guest_cpuid_has_mpx(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 7, 0);
+	return best && (best->ebx & bit(X86_FEATURE_MPX));
+}
+
 static inline bool guest_cpuid_has_rdtscp(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 577bb1d75e1e..a339e97e26a3 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3195,7 +3195,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		msr_info->data = vmcs_readl(GUEST_SYSENTER_ESP);
 		break;
 	case MSR_IA32_BNDCFGS:
-		if (!kvm_mpx_supported())
+		if (!kvm_mpx_supported() || !guest_cpuid_has_mpx(vcpu))
 			return 1;
 		msr_info->data = vmcs_read64(GUEST_BNDCFGS);
 		break;
@@ -3277,7 +3277,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		vmcs_writel(GUEST_SYSENTER_ESP, data);
 		break;
 	case MSR_IA32_BNDCFGS:
-		if (!kvm_mpx_supported())
+		if (!kvm_mpx_supported() || !guest_cpuid_has_mpx(vcpu))
 			return 1;
 		vmcs_write64(GUEST_BNDCFGS, data);
 		break;
-- 
cgit v1.2.3


From 4531662d1abf6c1f0e5c2b86ddb60e61509786c8 Mon Sep 17 00:00:00 2001
From: Jim Mattson <jmattson@google.com>
Date: Tue, 23 May 2017 11:52:54 -0700
Subject: kvm: vmx: Check value written to IA32_BNDCFGS
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Bits 11:2 must be zero and the linear addess in bits 63:12 must be
canonical. Otherwise, WRMSR(BNDCFGS) should raise #GP.

Fixes: 0dd376e709975779 ("KVM: x86: add MSR_IA32_BNDCFGS to msrs_to_save")
Signed-off-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
---
 arch/x86/include/asm/msr-index.h | 2 ++
 arch/x86/kvm/vmx.c               | 3 +++
 2 files changed, 5 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 673f9ac50f6d..dbf266b0d14a 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -420,6 +420,8 @@
 #define MSR_IA32_TSC_ADJUST             0x0000003b
 #define MSR_IA32_BNDCFGS		0x00000d90
 
+#define MSR_IA32_BNDCFGS_RSVD		0x00000ffc
+
 #define MSR_IA32_XSS			0x00000da0
 
 #define FEATURE_CONTROL_LOCKED				(1<<0)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index a339e97e26a3..39301297352a 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3279,6 +3279,9 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_BNDCFGS:
 		if (!kvm_mpx_supported() || !guest_cpuid_has_mpx(vcpu))
 			return 1;
+		if (is_noncanonical_address(data & PAGE_MASK) ||
+		    (data & MSR_IA32_BNDCFGS_RSVD))
+			return 1;
 		vmcs_write64(GUEST_BNDCFGS, data);
 		break;
 	case MSR_IA32_TSC:
-- 
cgit v1.2.3


From d923fcf6361da3b8b25b13ce6c1e427e759f125a Mon Sep 17 00:00:00 2001
From: Jim Mattson <jmattson@google.com>
Date: Thu, 1 Jun 2017 12:43:37 -0700
Subject: KVM: nVMX: Don't update vmcs12->xss_exit_bitmap on nested VM-exit
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The XSS-exiting bitmap is a VMCS control field that does not change
while the CPU is in non-root mode. Transferring the unchanged value
from vmcs02 to vmcs12 is unnecessary.

Signed-off-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
---
 arch/x86/kvm/vmx.c | 2 --
 1 file changed, 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 39301297352a..fbc18085b599 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -10738,8 +10738,6 @@ static void sync_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	vmcs12->guest_sysenter_eip = vmcs_readl(GUEST_SYSENTER_EIP);
 	if (kvm_mpx_supported())
 		vmcs12->guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS);
-	if (nested_cpu_has_xsaves(vmcs12))
-		vmcs12->xss_exit_bitmap = vmcs_read64(XSS_EXIT_BITMAP);
 }
 
 /*
-- 
cgit v1.2.3


From d281e13b0bfe745a21061a194e386a949784393f Mon Sep 17 00:00:00 2001
From: Jim Mattson <jmattson@google.com>
Date: Thu, 1 Jun 2017 12:44:46 -0700
Subject: KVM: nVMX: Update vmcs12->guest_linear_address on nested VM-exit
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The guest-linear address field is set for VM exits due to attempts to
execute LMSW with a memory operand and VM exits due to attempts to
execute INS or OUTS for which the relevant segment is usable,
regardless of whether or not EPT is in use.

Fixes: 119a9c01a5922 ("KVM: nVMX: pass valid guest linear-address to the L1")
Signed-off-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
---
 arch/x86/kvm/vmx.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index fbc18085b599..c6dec552b28f 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -10712,8 +10712,7 @@ static void sync_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 		vmcs12->guest_pdptr3 = vmcs_read64(GUEST_PDPTR3);
 	}
 
-	if (nested_cpu_has_ept(vmcs12))
-		vmcs12->guest_linear_address = vmcs_readl(GUEST_LINEAR_ADDRESS);
+	vmcs12->guest_linear_address = vmcs_readl(GUEST_LINEAR_ADDRESS);
 
 	if (nested_cpu_has_vid(vmcs12))
 		vmcs12->guest_intr_status = vmcs_read16(GUEST_INTR_STATUS);
-- 
cgit v1.2.3


From 4aebd0e9ca3776368813239018287021002b8973 Mon Sep 17 00:00:00 2001
From: Ladi Prosek <lprosek@redhat.com>
Date: Wed, 21 Jun 2017 09:06:57 +0200
Subject: KVM: SVM: introduce disable_nmi_singlestep helper

Just moving the code to a new helper in preparation for following
commits.

Signed-off-by: Ladi Prosek <lprosek@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 6e3095d1bad4..7dda9c4ee485 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -963,6 +963,14 @@ static void svm_disable_lbrv(struct vcpu_svm *svm)
 	set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0);
 }
 
+static void disable_nmi_singlestep(struct vcpu_svm *svm)
+{
+	svm->nmi_singlestep = false;
+	if (!(svm->vcpu.guest_debug & KVM_GUESTDBG_SINGLESTEP))
+		svm->vmcb->save.rflags &=
+			~(X86_EFLAGS_TF | X86_EFLAGS_RF);
+}
+
 /* Note:
  * This hash table is used to map VM_ID to a struct kvm_arch,
  * when handling AMD IOMMU GALOG notification to schedule in
@@ -2111,10 +2119,7 @@ static int db_interception(struct vcpu_svm *svm)
 	}
 
 	if (svm->nmi_singlestep) {
-		svm->nmi_singlestep = false;
-		if (!(svm->vcpu.guest_debug & KVM_GUESTDBG_SINGLESTEP))
-			svm->vmcb->save.rflags &=
-				~(X86_EFLAGS_TF | X86_EFLAGS_RF);
+		disable_nmi_singlestep(svm);
 	}
 
 	if (svm->vcpu.guest_debug &
-- 
cgit v1.2.3


From ab2f4d73ebc33487930e7adf1dd8ed671c72827c Mon Sep 17 00:00:00 2001
From: Ladi Prosek <lprosek@redhat.com>
Date: Wed, 21 Jun 2017 09:06:58 +0200
Subject: KVM: nSVM: do not forward NMI window singlestep VM exits to L1

Nested hypervisor should not see singlestep VM exits if singlestepping
was enabled internally by KVM. Windows is particularly sensitive to this
and known to bluescreen on unexpected VM exits.

Signed-off-by: Ladi Prosek <lprosek@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm.c | 45 ++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 40 insertions(+), 5 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 7dda9c4ee485..1a854ce6025e 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -189,6 +189,7 @@ struct vcpu_svm {
 	struct nested_state nested;
 
 	bool nmi_singlestep;
+	u64 nmi_singlestep_guest_rflags;
 
 	unsigned int3_injected;
 	unsigned long int3_rip;
@@ -966,9 +967,13 @@ static void svm_disable_lbrv(struct vcpu_svm *svm)
 static void disable_nmi_singlestep(struct vcpu_svm *svm)
 {
 	svm->nmi_singlestep = false;
-	if (!(svm->vcpu.guest_debug & KVM_GUESTDBG_SINGLESTEP))
-		svm->vmcb->save.rflags &=
-			~(X86_EFLAGS_TF | X86_EFLAGS_RF);
+	if (!(svm->vcpu.guest_debug & KVM_GUESTDBG_SINGLESTEP)) {
+		/* Clear our flags if they were not set by the guest */
+		if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_TF))
+			svm->vmcb->save.rflags &= ~X86_EFLAGS_TF;
+		if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_RF))
+			svm->vmcb->save.rflags &= ~X86_EFLAGS_RF;
+	}
 }
 
 /* Note:
@@ -2538,6 +2543,31 @@ static int nested_svm_exit_handled_msr(struct vcpu_svm *svm)
 	return (value & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST;
 }
 
+/* DB exceptions for our internal use must not cause vmexit */
+static int nested_svm_intercept_db(struct vcpu_svm *svm)
+{
+	unsigned long dr6;
+
+	/* if we're not singlestepping, it's not ours */
+	if (!svm->nmi_singlestep)
+		return NESTED_EXIT_DONE;
+
+	/* if it's not a singlestep exception, it's not ours */
+	if (kvm_get_dr(&svm->vcpu, 6, &dr6))
+		return NESTED_EXIT_DONE;
+	if (!(dr6 & DR6_BS))
+		return NESTED_EXIT_DONE;
+
+	/* if the guest is singlestepping, it should get the vmexit */
+	if (svm->nmi_singlestep_guest_rflags & X86_EFLAGS_TF) {
+		disable_nmi_singlestep(svm);
+		return NESTED_EXIT_DONE;
+	}
+
+	/* it's ours, the nested hypervisor must not see this one */
+	return NESTED_EXIT_HOST;
+}
+
 static int nested_svm_exit_special(struct vcpu_svm *svm)
 {
 	u32 exit_code = svm->vmcb->control.exit_code;
@@ -2593,8 +2623,12 @@ static int nested_svm_intercept(struct vcpu_svm *svm)
 	}
 	case SVM_EXIT_EXCP_BASE ... SVM_EXIT_EXCP_BASE + 0x1f: {
 		u32 excp_bits = 1 << (exit_code - SVM_EXIT_EXCP_BASE);
-		if (svm->nested.intercept_exceptions & excp_bits)
-			vmexit = NESTED_EXIT_DONE;
+		if (svm->nested.intercept_exceptions & excp_bits) {
+			if (exit_code == SVM_EXIT_EXCP_BASE + DB_VECTOR)
+				vmexit = nested_svm_intercept_db(svm);
+			else
+				vmexit = NESTED_EXIT_DONE;
+		}
 		/* async page fault always cause vmexit */
 		else if ((exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR) &&
 			 svm->apf_reason != 0)
@@ -4635,6 +4669,7 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu)
 	 * Something prevents NMI from been injected. Single step over possible
 	 * problem (IRET or exception injection or interrupt shadow)
 	 */
+	svm->nmi_singlestep_guest_rflags = svm_get_rflags(vcpu);
 	svm->nmi_singlestep = true;
 	svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF);
 }
-- 
cgit v1.2.3


From 9b61174793f2aae1ef5ef843ef1cdbe52c2e36e8 Mon Sep 17 00:00:00 2001
From: Ladi Prosek <lprosek@redhat.com>
Date: Wed, 21 Jun 2017 09:06:59 +0200
Subject: KVM: SVM: hide TF/RF flags used by NMI singlestep

These flags are used internally by SVM so it's cleaner to not leak
them to callers of svm_get_rflags. This is similar to how the TF
flag is handled on KVM_GUESTDBG_SINGLESTEP by kvm_get_rflags and
kvm_set_rflags.

Without this change, the flags may propagate from host VMCB to nested
VMCB or vice versa while singlestepping over a nested VM enter/exit,
and then get stuck in inappropriate places.

Example: NMI singlestepping is enabled while running L1 guest. The
instruction to step over is VMRUN and nested vmrun emulation stashes
rflags to hsave->save.rflags. Then if singlestepping is disabled
while still in L2, TF/RF will be cleared from the nested VMCB but the
next nested VM exit will restore them from hsave->save.rflags and
cause an unexpected DB exception.

Signed-off-by: Ladi Prosek <lprosek@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 1a854ce6025e..6ac9bcd7f6f0 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1725,11 +1725,24 @@ static void svm_vcpu_unblocking(struct kvm_vcpu *vcpu)
 
 static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu)
 {
-	return to_svm(vcpu)->vmcb->save.rflags;
+	struct vcpu_svm *svm = to_svm(vcpu);
+	unsigned long rflags = svm->vmcb->save.rflags;
+
+	if (svm->nmi_singlestep) {
+		/* Hide our flags if they were not set by the guest */
+		if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_TF))
+			rflags &= ~X86_EFLAGS_TF;
+		if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_RF))
+			rflags &= ~X86_EFLAGS_RF;
+	}
+	return rflags;
 }
 
 static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 {
+	if (to_svm(vcpu)->nmi_singlestep)
+		rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF);
+
        /*
         * Any change of EFLAGS.VM is accompanied by a reload of SS
         * (caused by either a task switch or an inter-privilege IRET),
-- 
cgit v1.2.3


From a12713c25b36cbbc1a3204b2a49a72f7bc8a8847 Mon Sep 17 00:00:00 2001
From: Ladi Prosek <lprosek@redhat.com>
Date: Wed, 21 Jun 2017 09:07:00 +0200
Subject: KVM: SVM: don't NMI singlestep over event injection

Singlestepping is enabled by setting the TF flag and care must be
taken to not let the guest see (and reuse at an inconvenient time)
the modified rflag value. One such case is event injection, as part
of which flags are pushed on the stack and restored later on iret.

This commit disables singlestepping when we're about to inject an
event and forces an immediate exit for us to re-evaluate the NMI
related state.

Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Ladi Prosek <lprosek@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 6ac9bcd7f6f0..597337987a16 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -4823,6 +4823,22 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 	if (unlikely(svm->nested.exit_required))
 		return;
 
+	/*
+	 * Disable singlestep if we're injecting an interrupt/exception.
+	 * We don't want our modified rflags to be pushed on the stack where
+	 * we might not be able to easily reset them if we disabled NMI
+	 * singlestep later.
+	 */
+	if (svm->nmi_singlestep && svm->vmcb->control.event_inj) {
+		/*
+		 * Event injection happens before external interrupts cause a
+		 * vmexit and interrupts are disabled here, so smp_send_reschedule
+		 * is enough to force an immediate vmexit.
+		 */
+		disable_nmi_singlestep(svm);
+		smp_send_reschedule(vcpu->cpu);
+	}
+
 	pre_svm_run(svm);
 
 	sync_lapic_to_cr8(vcpu);
-- 
cgit v1.2.3


From 1a5e1852941d0d8ae98a4b5c769ec998e3708158 Mon Sep 17 00:00:00 2001
From: Ladi Prosek <lprosek@redhat.com>
Date: Wed, 21 Jun 2017 09:07:01 +0200
Subject: KVM: SVM: suppress unnecessary NMI singlestep on GIF=0 and nested
 exit

enable_nmi_window is supposed to be a no-op if we know that we'll see
a VM exit by the time the NMI window opens. This commit adds two more
cases:

* We intercept stgi so we don't need to singlestep on GIF=0.

* We emulate nested vmexit so we don't need to singlestep when nested
  VM exit is required.

Signed-off-by: Ladi Prosek <lprosek@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm.c | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 597337987a16..03df7c1da581 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -4678,6 +4678,12 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu)
 	    == HF_NMI_MASK)
 		return; /* IRET will cause a vm exit */
 
+	if ((svm->vcpu.arch.hflags & HF_GIF_MASK) == 0)
+		return; /* STGI will cause a vm exit */
+
+	if (svm->nested.exit_required)
+		return; /* we're not going to run the guest yet */
+
 	/*
 	 * Something prevents NMI from been injected. Single step over possible
 	 * problem (IRET or exception injection or interrupt shadow)
-- 
cgit v1.2.3


From 403526054a38073137458f6c5c8c765ec27e015d Mon Sep 17 00:00:00 2001
From: Jim Mattson <jmattson@google.com>
Date: Wed, 28 Jun 2017 09:37:37 -0700
Subject: kvm: nVMX: Check memory operand to INVVPID

The memory operand fetched for INVVPID is 128 bits. Bits 63:16 are
reserved and must be zero.  Otherwise, the instruction fails with
VMfail(Invalid operand to INVEPT/INVVPID).  If the INVVPID_TYPE is 0
(individual address invalidation), then bits 127:64 must be in
canonical form, or the instruction fails with VMfail(Invalid operand
to INVEPT/INVVPID).

Signed-off-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/vmx.c | 22 ++++++++++++++++++----
 1 file changed, 18 insertions(+), 4 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c6dec552b28f..e8b61ad84a8e 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -7653,7 +7653,10 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 	unsigned long type, types;
 	gva_t gva;
 	struct x86_exception e;
-	int vpid;
+	struct {
+		u64 vpid;
+		u64 gla;
+	} operand;
 
 	if (!(vmx->nested.nested_vmx_secondary_ctls_high &
 	      SECONDARY_EXEC_ENABLE_VPID) ||
@@ -7683,17 +7686,28 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
 			vmx_instruction_info, false, &gva))
 		return 1;
-	if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vpid,
-				sizeof(u32), &e)) {
+	if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &operand,
+				sizeof(operand), &e)) {
 		kvm_inject_page_fault(vcpu, &e);
 		return 1;
 	}
+	if (operand.vpid >> 16) {
+		nested_vmx_failValid(vcpu,
+			VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
+		return kvm_skip_emulated_instruction(vcpu);
+	}
 
 	switch (type) {
 	case VMX_VPID_EXTENT_INDIVIDUAL_ADDR:
+		if (is_noncanonical_address(operand.gla)) {
+			nested_vmx_failValid(vcpu,
+				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
+			return kvm_skip_emulated_instruction(vcpu);
+		}
+		/* fall through */
 	case VMX_VPID_EXTENT_SINGLE_CONTEXT:
 	case VMX_VPID_EXTENT_SINGLE_NON_GLOBAL:
-		if (!vpid) {
+		if (!operand.vpid) {
 			nested_vmx_failValid(vcpu,
 				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
 			return kvm_skip_emulated_instruction(vcpu);
-- 
cgit v1.2.3


From 35ee9e48b9df6c7751e8f759a4deec5aed1463c3 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Thu, 29 Jun 2017 17:14:50 +0200
Subject: KVM: lapic: reorganize start_hv_timer

There are many cases in which the hv timer must be canceled.  Split out
a new function to avoid duplication.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/lapic.c | 40 +++++++++++++++++++++++++++-------------
 1 file changed, 27 insertions(+), 13 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index d24c8742d9b0..b6689dcae1da 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1501,24 +1501,38 @@ static void cancel_hv_timer(struct kvm_lapic *apic)
 	preempt_enable();
 }
 
-static bool start_hv_timer(struct kvm_lapic *apic)
+static bool __start_hv_timer(struct kvm_lapic *apic)
 {
-	u64 tscdeadline = apic->lapic_timer.tscdeadline;
+	struct kvm_timer *ktimer = &apic->lapic_timer;
+	int r;
 
-	if ((atomic_read(&apic->lapic_timer.pending) &&
-		!apic_lvtt_period(apic)) ||
-		kvm_x86_ops->set_hv_timer(apic->vcpu, tscdeadline)) {
-		if (apic->lapic_timer.hv_timer_in_use)
-			cancel_hv_timer(apic);
-	} else {
-		apic->lapic_timer.hv_timer_in_use = true;
-		hrtimer_cancel(&apic->lapic_timer.timer);
+	if (!apic_lvtt_period(apic) && atomic_read(&ktimer->pending))
+		return false;
+
+	r = kvm_x86_ops->set_hv_timer(apic->vcpu, ktimer->tscdeadline);
+	if (r < 0)
+		return false;
+
+	ktimer->hv_timer_in_use = true;
+	hrtimer_cancel(&ktimer->timer);
 
-		/* In case the sw timer triggered in the window */
-		if (atomic_read(&apic->lapic_timer.pending) &&
-			!apic_lvtt_period(apic))
+	/*
+	 * Also recheck ktimer->pending, in case the sw timer triggered in
+	 * the window.  For periodic timer, leave the hv timer running for
+	 * simplicity, and the deadline will be recomputed on the next vmexit.
+	 */
+	if (!apic_lvtt_period(apic) && atomic_read(&ktimer->pending))
+		return false;
+	return true;
+}
+
+static bool start_hv_timer(struct kvm_lapic *apic)
+{
+	if (!__start_hv_timer(apic)) {
+		if (apic->lapic_timer.hv_timer_in_use)
 			cancel_hv_timer(apic);
 	}
+
 	trace_kvm_hv_timer_state(apic->vcpu->vcpu_id,
 			apic->lapic_timer.hv_timer_in_use);
 	return apic->lapic_timer.hv_timer_in_use;
-- 
cgit v1.2.3


From a749e247f745f609fd1106f1400ea063fe9b18ba Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Thu, 29 Jun 2017 17:14:50 +0200
Subject: KVM: lapic: reorganize restart_apic_timer

Move the code to cancel the hv timer into the caller, just before
it starts the hrtimer.  Check availability of the hv timer in
start_hv_timer.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/lapic.c | 85 +++++++++++++++++++++++++---------------------------
 arch/x86/kvm/lapic.h |  2 +-
 arch/x86/kvm/x86.c   |  8 ++---
 3 files changed, 45 insertions(+), 50 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index b6689dcae1da..a80e5a5d6f2f 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1495,17 +1495,21 @@ EXPORT_SYMBOL_GPL(kvm_lapic_hv_timer_in_use);
 
 static void cancel_hv_timer(struct kvm_lapic *apic)
 {
+	WARN_ON(!apic->lapic_timer.hv_timer_in_use);
 	preempt_disable();
 	kvm_x86_ops->cancel_hv_timer(apic->vcpu);
 	apic->lapic_timer.hv_timer_in_use = false;
 	preempt_enable();
 }
 
-static bool __start_hv_timer(struct kvm_lapic *apic)
+static bool start_hv_timer(struct kvm_lapic *apic)
 {
 	struct kvm_timer *ktimer = &apic->lapic_timer;
 	int r;
 
+	if (!kvm_x86_ops->set_hv_timer)
+		return false;
+
 	if (!apic_lvtt_period(apic) && atomic_read(&ktimer->pending))
 		return false;
 
@@ -1523,19 +1527,30 @@ static bool __start_hv_timer(struct kvm_lapic *apic)
 	 */
 	if (!apic_lvtt_period(apic) && atomic_read(&ktimer->pending))
 		return false;
+
+	trace_kvm_hv_timer_state(apic->vcpu->vcpu_id, true);
 	return true;
 }
 
-static bool start_hv_timer(struct kvm_lapic *apic)
+static void start_sw_timer(struct kvm_lapic *apic)
 {
-	if (!__start_hv_timer(apic)) {
-		if (apic->lapic_timer.hv_timer_in_use)
-			cancel_hv_timer(apic);
-	}
+	struct kvm_timer *ktimer = &apic->lapic_timer;
+	if (apic->lapic_timer.hv_timer_in_use)
+		cancel_hv_timer(apic);
+	if (!apic_lvtt_period(apic) && atomic_read(&ktimer->pending))
+		return;
+
+	if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic))
+		start_sw_period(apic);
+	else if (apic_lvtt_tscdeadline(apic))
+		start_sw_tscdeadline(apic);
+	trace_kvm_hv_timer_state(apic->vcpu->vcpu_id, false);
+}
 
-	trace_kvm_hv_timer_state(apic->vcpu->vcpu_id,
-			apic->lapic_timer.hv_timer_in_use);
-	return apic->lapic_timer.hv_timer_in_use;
+static void restart_apic_timer(struct kvm_lapic *apic)
+{
+	if (!start_hv_timer(apic))
+		start_sw_timer(apic);
 }
 
 void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu)
@@ -1549,19 +1564,14 @@ void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu)
 
 	if (apic_lvtt_period(apic) && apic->lapic_timer.period) {
 		advance_periodic_target_expiration(apic);
-		if (!start_hv_timer(apic))
-			start_sw_period(apic);
+		restart_apic_timer(apic);
 	}
 }
 EXPORT_SYMBOL_GPL(kvm_lapic_expired_hv_timer);
 
 void kvm_lapic_switch_to_hv_timer(struct kvm_vcpu *vcpu)
 {
-	struct kvm_lapic *apic = vcpu->arch.apic;
-
-	WARN_ON(apic->lapic_timer.hv_timer_in_use);
-
-	start_hv_timer(apic);
+	restart_apic_timer(vcpu->arch.apic);
 }
 EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_hv_timer);
 
@@ -1570,33 +1580,28 @@ void kvm_lapic_switch_to_sw_timer(struct kvm_vcpu *vcpu)
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
 	/* Possibly the TSC deadline timer is not enabled yet */
-	if (!apic->lapic_timer.hv_timer_in_use)
-		return;
-
-	cancel_hv_timer(apic);
+	if (apic->lapic_timer.hv_timer_in_use)
+		start_sw_timer(apic);
+}
+EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_sw_timer);
 
-	if (atomic_read(&apic->lapic_timer.pending))
-		return;
+void kvm_lapic_restart_hv_timer(struct kvm_vcpu *vcpu)
+{
+	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic))
-		start_sw_period(apic);
-	else if (apic_lvtt_tscdeadline(apic))
-		start_sw_tscdeadline(apic);
+	WARN_ON(!apic->lapic_timer.hv_timer_in_use);
+	restart_apic_timer(apic);
 }
-EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_sw_timer);
 
 static void start_apic_timer(struct kvm_lapic *apic)
 {
 	atomic_set(&apic->lapic_timer.pending, 0);
 
-	if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) {
-		if (set_target_expiration(apic) &&
-			!(kvm_x86_ops->set_hv_timer && start_hv_timer(apic)))
-			start_sw_period(apic);
-	} else if (apic_lvtt_tscdeadline(apic)) {
-		if (!(kvm_x86_ops->set_hv_timer && start_hv_timer(apic)))
-			start_sw_tscdeadline(apic);
-	}
+	if ((apic_lvtt_period(apic) || apic_lvtt_oneshot(apic))
+	    && !set_target_expiration(apic))
+		return;
+
+	restart_apic_timer(apic);
 }
 
 static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val)
@@ -1827,16 +1832,6 @@ void kvm_free_lapic(struct kvm_vcpu *vcpu)
  * LAPIC interface
  *----------------------------------------------------------------------
  */
-u64 kvm_get_lapic_target_expiration_tsc(struct kvm_vcpu *vcpu)
-{
-	struct kvm_lapic *apic = vcpu->arch.apic;
-
-	if (!lapic_in_kernel(vcpu))
-		return 0;
-
-	return apic->lapic_timer.tscdeadline;
-}
-
 u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index bcbe811f3b97..29caa2c3dff9 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -87,7 +87,6 @@ int kvm_apic_get_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s);
 int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s);
 int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu);
 
-u64 kvm_get_lapic_target_expiration_tsc(struct kvm_vcpu *vcpu);
 u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu);
 void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data);
 
@@ -216,4 +215,5 @@ void kvm_lapic_switch_to_sw_timer(struct kvm_vcpu *vcpu);
 void kvm_lapic_switch_to_hv_timer(struct kvm_vcpu *vcpu);
 void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu);
 bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu);
+void kvm_lapic_restart_hv_timer(struct kvm_vcpu *vcpu);
 #endif
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a2cd0997343c..81aa9c321be3 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2841,10 +2841,10 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 			kvm_vcpu_write_tsc_offset(vcpu, offset);
 			vcpu->arch.tsc_catchup = 1;
 		}
-		if (kvm_lapic_hv_timer_in_use(vcpu) &&
-				kvm_x86_ops->set_hv_timer(vcpu,
-					kvm_get_lapic_target_expiration_tsc(vcpu)))
-			kvm_lapic_switch_to_sw_timer(vcpu);
+
+		if (kvm_lapic_hv_timer_in_use(vcpu))
+			kvm_lapic_restart_hv_timer(vcpu);
+
 		/*
 		 * On a host with synchronized TSC, there is no need to update
 		 * kvmclock on vcpu->cpu migration
-- 
cgit v1.2.3


From c853354429f7ec88f9cdde4e46e69a2c0e3c8310 Mon Sep 17 00:00:00 2001
From: Wanpeng Li <wanpeng.li@hotmail.com>
Date: Thu, 29 Jun 2017 06:28:09 -0700
Subject: KVM: LAPIC: Fix lapic timer injection delay
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If the TSC deadline timer is programmed really close to the deadline or
even in the past, the computation in vmx_set_hv_timer will program the
absolute target tsc value to vmcs preemption timer field w/ delta == 0,
then plays a vmentry and an upcoming vmx preemption timer fire vmexit
dance, the lapic timer injection is delayed due to this duration. Actually
the lapic timer which is emulated by hrtimer can handle this correctly.

This patch fixes it by firing the lapic timer and injecting a timer interrupt
immediately during the next vmentry if the TSC deadline timer is programmed
really close to the deadline or even in the past. This saves ~300 cycles on
the tsc_deadline_timer test of apic.flat.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/lapic.c | 5 ++++-
 arch/x86/kvm/vmx.c   | 3 ++-
 2 files changed, 6 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index a80e5a5d6f2f..2819d4c123eb 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1525,8 +1525,11 @@ static bool start_hv_timer(struct kvm_lapic *apic)
 	 * the window.  For periodic timer, leave the hv timer running for
 	 * simplicity, and the deadline will be recomputed on the next vmexit.
 	 */
-	if (!apic_lvtt_period(apic) && atomic_read(&ktimer->pending))
+	if (!apic_lvtt_period(apic) && (r || atomic_read(&ktimer->pending))) {
+		if (r)
+			apic_timer_expired(apic);
 		return false;
+	}
 
 	trace_kvm_hv_timer_state(apic->vcpu->vcpu_id, true);
 	return true;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index e8b61ad84a8e..92ddea08f999 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -11147,7 +11147,8 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc)
 	vmx->hv_deadline_tsc = tscl + delta_tsc;
 	vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL,
 			PIN_BASED_VMX_PREEMPTION_TIMER);
-	return 0;
+
+	return delta_tsc == 0;
 }
 
 static void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu)
-- 
cgit v1.2.3


From 8616abc253793345a245d026c7a0cc11fbc3abd8 Mon Sep 17 00:00:00 2001
From: Nick Desaulniers <nick.desaulniers@gmail.com>
Date: Tue, 27 Jun 2017 19:37:14 -0700
Subject: KVM: x86: remove ignored type attribute

The macro insn_fetch marks the 'type' argument as having a specified
alignment.  Type attributes can only be applied to structs, unions, or
enums, but insn_fetch is only ever invoked with integral types, so Clang
produces 19 -Wignored-attributes warnings for this source file.

Signed-off-by: Nick Desaulniers <nick.desaulniers@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/emulate.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 0f0815c824de..4a38b9656391 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -900,7 +900,7 @@ static __always_inline int do_insn_fetch_bytes(struct x86_emulate_ctxt *ctxt,
 	if (rc != X86EMUL_CONTINUE)					\
 		goto done;						\
 	ctxt->_eip += sizeof(_type);					\
-	_x = *(_type __aligned(1) *) ctxt->fetch.ptr;			\
+	memcpy(&_x, ctxt->fetch.ptr, sizeof(_type));			\
 	ctxt->fetch.ptr += sizeof(_type);				\
 	_x;								\
 })
-- 
cgit v1.2.3


From ce00053b1cfca312c22e2a6465451f1862561eab Mon Sep 17 00:00:00 2001
From: Peter Feiner <pfeiner@google.com>
Date: Fri, 30 Jun 2017 17:26:29 -0700
Subject: x86: kvm: mmu: dead code thanks to access tracking

The MMU always has hardware A bits or access tracking support, thus
it's unnecessary to handle the scenario where we have neither.

Signed-off-by: Peter Feiner <pfeiner@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu.c | 30 +++++++++---------------------
 1 file changed, 9 insertions(+), 21 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 5d3376f67794..dfd4cd67e5a6 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -315,12 +315,21 @@ static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte)
 	return likely(kvm_gen == spte_gen);
 }
 
+/*
+ * Sets the shadow PTE masks used by the MMU.
+ *
+ * Assumptions:
+ *  - Setting either @accessed_mask or @dirty_mask requires setting both
+ *  - At least one of @accessed_mask or @acc_track_mask must be set
+ */
 void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
 		u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask,
 		u64 acc_track_mask)
 {
 	if (acc_track_mask != 0)
 		acc_track_mask |= SPTE_SPECIAL_MASK;
+	BUG_ON(!dirty_mask != !accessed_mask);
+	BUG_ON(!accessed_mask && !acc_track_mask);
 
 	shadow_user_mask = user_mask;
 	shadow_accessed_mask = accessed_mask;
@@ -1766,18 +1775,9 @@ static int kvm_test_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
 	u64 *sptep;
 	struct rmap_iterator iter;
 
-	/*
-	 * If there's no access bit in the secondary pte set by the hardware and
-	 * fast access tracking is also not enabled, it's up to gup-fast/gup to
-	 * set the access bit in the primary pte or in the page structure.
-	 */
-	if (!shadow_accessed_mask && !shadow_acc_track_mask)
-		goto out;
-
 	for_each_rmap_spte(rmap_head, &iter, sptep)
 		if (is_accessed_spte(*sptep))
 			return 1;
-out:
 	return 0;
 }
 
@@ -1798,18 +1798,6 @@ static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
 
 int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
 {
-	/*
-	 * In case of absence of EPT Access and Dirty Bits supports,
-	 * emulate the accessed bit for EPT, by checking if this page has
-	 * an EPT mapping, and clearing it if it does. On the next access,
-	 * a new EPT mapping will be established.
-	 * This has some overhead, but not as much as the cost of swapping
-	 * out actively used pages or breaking up actively used hugepages.
-	 */
-	if (!shadow_accessed_mask && !shadow_acc_track_mask)
-		return kvm_handle_hva_range(kvm, start, end, 0,
-					    kvm_unmap_rmapp);
-
 	return kvm_handle_hva_range(kvm, start, end, 0, kvm_age_rmapp);
 }
 
-- 
cgit v1.2.3


From dcdca5fed5f6ef2521f927ba3b5cd6b328054be1 Mon Sep 17 00:00:00 2001
From: Peter Feiner <pfeiner@google.com>
Date: Fri, 30 Jun 2017 17:26:30 -0700
Subject: x86: kvm: mmu: make spte mmio mask more explicit

Specify both a mask (i.e., bits to consider) and a value (i.e.,
pattern of bits that indicates a special PTE) for mmio SPTEs. On
Intel, this lets us pack even more information into the
(SPTE_SPECIAL_MASK | EPT_VMX_RWX_MASK) mask we use for access
tracking liberating all (SPTE_SPECIAL_MASK | (non-misconfigured-RWX))
values.

Signed-off-by: Peter Feiner <pfeiner@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu.c | 9 ++++++---
 arch/x86/kvm/mmu.h | 2 +-
 arch/x86/kvm/vmx.c | 3 ++-
 arch/x86/kvm/x86.c | 2 +-
 4 files changed, 10 insertions(+), 6 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index dfd4cd67e5a6..10b3cfc7b411 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -183,6 +183,7 @@ 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_mmio_mask;
+static u64 __read_mostly shadow_mmio_value;
 static u64 __read_mostly shadow_present_mask;
 
 /*
@@ -207,8 +208,10 @@ static const u64 shadow_acc_track_saved_bits_shift = PT64_SECOND_AVAIL_BITS_SHIF
 static void mmu_spte_set(u64 *sptep, u64 spte);
 static void mmu_free_roots(struct kvm_vcpu *vcpu);
 
-void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask)
+void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value)
 {
+	BUG_ON((mmio_mask & mmio_value) != mmio_value);
+	shadow_mmio_value = mmio_value | SPTE_SPECIAL_MASK;
 	shadow_mmio_mask = mmio_mask | SPTE_SPECIAL_MASK;
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask);
@@ -270,7 +273,7 @@ static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn,
 	u64 mask = generation_mmio_spte_mask(gen);
 
 	access &= ACC_WRITE_MASK | ACC_USER_MASK;
-	mask |= shadow_mmio_mask | access | gfn << PAGE_SHIFT;
+	mask |= shadow_mmio_value | access | gfn << PAGE_SHIFT;
 
 	trace_mark_mmio_spte(sptep, gfn, access, gen);
 	mmu_spte_set(sptep, mask);
@@ -278,7 +281,7 @@ static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn,
 
 static bool is_mmio_spte(u64 spte)
 {
-	return (spte & shadow_mmio_mask) == shadow_mmio_mask;
+	return (spte & shadow_mmio_mask) == shadow_mmio_value;
 }
 
 static gfn_t get_mmio_spte_gfn(u64 spte)
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 27975807cc64..41d362e95681 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -51,7 +51,7 @@ static inline u64 rsvd_bits(int s, int e)
 	return ((1ULL << (e - s + 1)) - 1) << s;
 }
 
-void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask);
+void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value);
 
 void
 reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 92ddea08f999..b102a864e61f 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -5163,7 +5163,8 @@ static void ept_set_mmio_spte_mask(void)
 	 * EPT Misconfigurations can be generated if the value of bits 2:0
 	 * of an EPT paging-structure entry is 110b (write/execute).
 	 */
-	kvm_mmu_set_mmio_spte_mask(VMX_EPT_MISCONFIG_WX_VALUE);
+	kvm_mmu_set_mmio_spte_mask(VMX_EPT_RWX_MASK,
+				   VMX_EPT_MISCONFIG_WX_VALUE);
 }
 
 #define VMX_XSS_EXIT_BITMAP 0
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f2bd155883dd..3a12b879f542 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6009,7 +6009,7 @@ static void kvm_set_mmio_spte_mask(void)
 		mask &= ~1ull;
 #endif
 
-	kvm_mmu_set_mmio_spte_mask(mask);
+	kvm_mmu_set_mmio_spte_mask(mask, mask);
 }
 
 #ifdef CONFIG_X86_64
-- 
cgit v1.2.3


From ac8d57e5734389da18633d4e8cc030fe10843da7 Mon Sep 17 00:00:00 2001
From: Peter Feiner <pfeiner@google.com>
Date: Fri, 30 Jun 2017 17:26:31 -0700
Subject: kvm: x86: mmu: allow A/D bits to be disabled in an mmu

Adds the plumbing to disable A/D bits in the MMU based on a new role
bit, ad_disabled. When A/D is disabled, the MMU operates as though A/D
aren't available (i.e., using access tracking faults instead).

To avoid SP -> kvm_mmu_page.role.ad_disabled lookups all over the
place, A/D disablement is now stored in the SPTE. This state is stored
in the SPTE by tweaking the use of SPTE_SPECIAL_MASK for access
tracking. Rather than just setting SPTE_SPECIAL_MASK when an
access-tracking SPTE is non-present, we now always set
SPTE_SPECIAL_MASK for access-tracking SPTEs.

Signed-off-by: Peter Feiner <pfeiner@google.com>
[Use role.ad_disabled even for direct (non-shadow) EPT page tables.  Add
 documentation and a few MMU_WARN_ONs. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virtual/kvm/mmu.txt |   4 ++
 arch/x86/include/asm/kvm_host.h   |   3 +-
 arch/x86/kvm/mmu.c                | 115 ++++++++++++++++++++++++++++----------
 arch/x86/kvm/mmutrace.h           |   6 +-
 4 files changed, 95 insertions(+), 33 deletions(-)

(limited to 'arch/x86')

diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt
index 481b6a9c25d5..f50d45b1e967 100644
--- a/Documentation/virtual/kvm/mmu.txt
+++ b/Documentation/virtual/kvm/mmu.txt
@@ -179,6 +179,10 @@ Shadow pages contain the following information:
     shadow page; it is also used to go back from a struct kvm_mmu_page
     to a memslot, through the kvm_memslots_for_spte_role macro and
     __gfn_to_memslot.
+  role.ad_disabled:
+    Is 1 if the MMU instance cannot use A/D bits.  EPT did not have A/D
+    bits before Haswell; shadow EPT page tables also cannot use A/D bits
+    if the L1 hypervisor does not enable them.
   gfn:
     Either the guest page table containing the translations shadowed by this
     page, or the base page frame for linear translations.  See role.direct.
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 9be890893885..1588e9e3dc01 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -257,7 +257,8 @@ union kvm_mmu_page_role {
 		unsigned cr0_wp:1;
 		unsigned smep_andnot_wp:1;
 		unsigned smap_andnot_wp:1;
-		unsigned :8;
+		unsigned ad_disabled:1;
+		unsigned :7;
 
 		/*
 		 * This is left at the top of the word so that
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 10b3cfc7b411..48d8e7e60163 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -187,10 +187,9 @@ static u64 __read_mostly shadow_mmio_value;
 static u64 __read_mostly shadow_present_mask;
 
 /*
- * The mask/value to distinguish a PTE that has been marked not-present for
- * access tracking purposes.
- * The mask would be either 0 if access tracking is disabled, or
- * SPTE_SPECIAL_MASK|VMX_EPT_RWX_MASK if access tracking is enabled.
+ * SPTEs used by MMUs without A/D bits are marked with shadow_acc_track_value.
+ * Non-present SPTEs with shadow_acc_track_value set are in place for access
+ * tracking.
  */
 static u64 __read_mostly shadow_acc_track_mask;
 static const u64 shadow_acc_track_value = SPTE_SPECIAL_MASK;
@@ -216,10 +215,32 @@ void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value)
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask);
 
+static inline bool sp_ad_disabled(struct kvm_mmu_page *sp)
+{
+	return sp->role.ad_disabled;
+}
+
+static inline bool spte_ad_enabled(u64 spte)
+{
+	MMU_WARN_ON((spte & shadow_mmio_mask) == shadow_mmio_value);
+	return !(spte & shadow_acc_track_value);
+}
+
+static inline u64 spte_shadow_accessed_mask(u64 spte)
+{
+	MMU_WARN_ON((spte & shadow_mmio_mask) == shadow_mmio_value);
+	return spte_ad_enabled(spte) ? shadow_accessed_mask : 0;
+}
+
+static inline u64 spte_shadow_dirty_mask(u64 spte)
+{
+	MMU_WARN_ON((spte & shadow_mmio_mask) == shadow_mmio_value);
+	return spte_ad_enabled(spte) ? shadow_dirty_mask : 0;
+}
+
 static inline bool is_access_track_spte(u64 spte)
 {
-	/* Always false if shadow_acc_track_mask is zero.  */
-	return (spte & shadow_acc_track_mask) == shadow_acc_track_value;
+	return !spte_ad_enabled(spte) && (spte & shadow_acc_track_mask) == 0;
 }
 
 /*
@@ -329,10 +350,9 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
 		u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask,
 		u64 acc_track_mask)
 {
-	if (acc_track_mask != 0)
-		acc_track_mask |= SPTE_SPECIAL_MASK;
 	BUG_ON(!dirty_mask != !accessed_mask);
 	BUG_ON(!accessed_mask && !acc_track_mask);
+	BUG_ON(acc_track_mask & shadow_acc_track_value);
 
 	shadow_user_mask = user_mask;
 	shadow_accessed_mask = accessed_mask;
@@ -341,7 +361,6 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
 	shadow_x_mask = x_mask;
 	shadow_present_mask = p_mask;
 	shadow_acc_track_mask = acc_track_mask;
-	WARN_ON(shadow_accessed_mask != 0 && shadow_acc_track_mask != 0);
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
 
@@ -561,7 +580,7 @@ static bool spte_has_volatile_bits(u64 spte)
 	    is_access_track_spte(spte))
 		return true;
 
-	if (shadow_accessed_mask) {
+	if (spte_ad_enabled(spte)) {
 		if ((spte & shadow_accessed_mask) == 0 ||
 	    	    (is_writable_pte(spte) && (spte & shadow_dirty_mask) == 0))
 			return true;
@@ -572,14 +591,17 @@ static bool spte_has_volatile_bits(u64 spte)
 
 static bool is_accessed_spte(u64 spte)
 {
-	return shadow_accessed_mask ? spte & shadow_accessed_mask
-				    : !is_access_track_spte(spte);
+	u64 accessed_mask = spte_shadow_accessed_mask(spte);
+
+	return accessed_mask ? spte & accessed_mask
+			     : !is_access_track_spte(spte);
 }
 
 static bool is_dirty_spte(u64 spte)
 {
-	return shadow_dirty_mask ? spte & shadow_dirty_mask
-				 : spte & PT_WRITABLE_MASK;
+	u64 dirty_mask = spte_shadow_dirty_mask(spte);
+
+	return dirty_mask ? spte & dirty_mask : spte & PT_WRITABLE_MASK;
 }
 
 /* Rules for using mmu_spte_set:
@@ -719,10 +741,10 @@ static u64 mmu_spte_get_lockless(u64 *sptep)
 
 static u64 mark_spte_for_access_track(u64 spte)
 {
-	if (shadow_accessed_mask != 0)
+	if (spte_ad_enabled(spte))
 		return spte & ~shadow_accessed_mask;
 
-	if (shadow_acc_track_mask == 0 || is_access_track_spte(spte))
+	if (is_access_track_spte(spte))
 		return spte;
 
 	/*
@@ -741,7 +763,6 @@ static u64 mark_spte_for_access_track(u64 spte)
 	spte |= (spte & shadow_acc_track_saved_bits_mask) <<
 		shadow_acc_track_saved_bits_shift;
 	spte &= ~shadow_acc_track_mask;
-	spte |= shadow_acc_track_value;
 
 	return spte;
 }
@@ -753,6 +774,7 @@ static u64 restore_acc_track_spte(u64 spte)
 	u64 saved_bits = (spte >> shadow_acc_track_saved_bits_shift)
 			 & shadow_acc_track_saved_bits_mask;
 
+	WARN_ON_ONCE(spte_ad_enabled(spte));
 	WARN_ON_ONCE(!is_access_track_spte(spte));
 
 	new_spte &= ~shadow_acc_track_mask;
@@ -771,7 +793,7 @@ static bool mmu_spte_age(u64 *sptep)
 	if (!is_accessed_spte(spte))
 		return false;
 
-	if (shadow_accessed_mask) {
+	if (spte_ad_enabled(spte)) {
 		clear_bit((ffs(shadow_accessed_mask) - 1),
 			  (unsigned long *)sptep);
 	} else {
@@ -1402,6 +1424,22 @@ static bool spte_clear_dirty(u64 *sptep)
 	return mmu_spte_update(sptep, spte);
 }
 
+static bool wrprot_ad_disabled_spte(u64 *sptep)
+{
+	bool was_writable = test_and_clear_bit(PT_WRITABLE_SHIFT,
+					       (unsigned long *)sptep);
+	if (was_writable)
+		kvm_set_pfn_dirty(spte_to_pfn(*sptep));
+
+	return was_writable;
+}
+
+/*
+ * Gets the GFN ready for another round of dirty logging by clearing the
+ *	- D bit on ad-enabled SPTEs, and
+ *	- W bit on ad-disabled SPTEs.
+ * Returns true iff any D or W bits were cleared.
+ */
 static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head)
 {
 	u64 *sptep;
@@ -1409,7 +1447,10 @@ static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head)
 	bool flush = false;
 
 	for_each_rmap_spte(rmap_head, &iter, sptep)
-		flush |= spte_clear_dirty(sptep);
+		if (spte_ad_enabled(*sptep))
+			flush |= spte_clear_dirty(sptep);
+		else
+			flush |= wrprot_ad_disabled_spte(sptep);
 
 	return flush;
 }
@@ -1432,7 +1473,8 @@ static bool __rmap_set_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head)
 	bool flush = false;
 
 	for_each_rmap_spte(rmap_head, &iter, sptep)
-		flush |= spte_set_dirty(sptep);
+		if (spte_ad_enabled(*sptep))
+			flush |= spte_set_dirty(sptep);
 
 	return flush;
 }
@@ -1464,7 +1506,8 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
 }
 
 /**
- * kvm_mmu_clear_dirty_pt_masked - clear MMU D-bit for PT level pages
+ * kvm_mmu_clear_dirty_pt_masked - clear MMU D-bit for PT level pages, or write
+ * protect the page if the D-bit isn't supported.
  * @kvm: kvm instance
  * @slot: slot to clear D-bit
  * @gfn_offset: start of the BITS_PER_LONG pages we care about
@@ -2389,7 +2432,12 @@ static void link_shadow_page(struct kvm_vcpu *vcpu, u64 *sptep,
 	BUILD_BUG_ON(VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK);
 
 	spte = __pa(sp->spt) | shadow_present_mask | PT_WRITABLE_MASK |
-	       shadow_user_mask | shadow_x_mask | shadow_accessed_mask;
+	       shadow_user_mask | shadow_x_mask;
+
+	if (sp_ad_disabled(sp))
+		spte |= shadow_acc_track_value;
+	else
+		spte |= shadow_accessed_mask;
 
 	mmu_spte_set(sptep, spte);
 
@@ -2657,10 +2705,15 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 {
 	u64 spte = 0;
 	int ret = 0;
+	struct kvm_mmu_page *sp;
 
 	if (set_mmio_spte(vcpu, sptep, gfn, pfn, pte_access))
 		return 0;
 
+	sp = page_header(__pa(sptep));
+	if (sp_ad_disabled(sp))
+		spte |= shadow_acc_track_value;
+
 	/*
 	 * For the EPT case, shadow_present_mask is 0 if hardware
 	 * supports exec-only page table entries.  In that case,
@@ -2669,7 +2722,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 	 */
 	spte |= shadow_present_mask;
 	if (!speculative)
-		spte |= shadow_accessed_mask;
+		spte |= spte_shadow_accessed_mask(spte);
 
 	if (pte_access & ACC_EXEC_MASK)
 		spte |= shadow_x_mask;
@@ -2726,7 +2779,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 
 	if (pte_access & ACC_WRITE_MASK) {
 		kvm_vcpu_mark_page_dirty(vcpu, gfn);
-		spte |= shadow_dirty_mask;
+		spte |= spte_shadow_dirty_mask(spte);
 	}
 
 	if (speculative)
@@ -2868,16 +2921,16 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep)
 {
 	struct kvm_mmu_page *sp;
 
+	sp = page_header(__pa(sptep));
+
 	/*
-	 * Since it's no accessed bit on EPT, it's no way to
-	 * distinguish between actually accessed translations
-	 * and prefetched, so disable pte prefetch if EPT is
-	 * enabled.
+	 * Without accessed bits, there's no way to distinguish between
+	 * actually accessed translations and prefetched, so disable pte
+	 * prefetch if accessed bits aren't available.
 	 */
-	if (!shadow_accessed_mask)
+	if (sp_ad_disabled(sp))
 		return;
 
-	sp = page_header(__pa(sptep));
 	if (sp->role.level > PT_PAGE_TABLE_LEVEL)
 		return;
 
@@ -4278,6 +4331,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
 
 	context->base_role.word = 0;
 	context->base_role.smm = is_smm(vcpu);
+	context->base_role.ad_disabled = (shadow_accessed_mask == 0);
 	context->page_fault = tdp_page_fault;
 	context->sync_page = nonpaging_sync_page;
 	context->invlpg = nonpaging_invlpg;
@@ -4624,6 +4678,7 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	mask.smep_andnot_wp = 1;
 	mask.smap_andnot_wp = 1;
 	mask.smm = 1;
+	mask.ad_disabled = 1;
 
 	/*
 	 * If we don't have indirect shadow pages, it means no page is
diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h
index 5a24b846a1cb..8b97a6cba8d1 100644
--- a/arch/x86/kvm/mmutrace.h
+++ b/arch/x86/kvm/mmutrace.h
@@ -30,8 +30,9 @@
 								        \
 	role.word = __entry->role;					\
 									\
-	trace_seq_printf(p, "sp gen %lx gfn %llx %u%s q%u%s %s%s"	\
-			 " %snxe root %u %s%c",	__entry->mmu_valid_gen,	\
+	trace_seq_printf(p, "sp gen %lx gfn %llx l%u%s q%u%s %s%s"	\
+			 " %snxe %sad root %u %s%c",			\
+			 __entry->mmu_valid_gen,			\
 			 __entry->gfn, role.level,			\
 			 role.cr4_pae ? " pae" : "",			\
 			 role.quadrant,					\
@@ -39,6 +40,7 @@
 			 access_str[role.access],			\
 			 role.invalid ? " invalid" : "",		\
 			 role.nxe ? "" : "!",				\
+			 role.ad_disabled ? "!" : "",			\
 			 __entry->root_count,				\
 			 __entry->unsync ? "unsync" : "sync", 0);	\
 	saved_ptr;							\
-- 
cgit v1.2.3


From 995f00a619584e65e53eff372d9b73b121a7bad5 Mon Sep 17 00:00:00 2001
From: Peter Feiner <pfeiner@google.com>
Date: Fri, 30 Jun 2017 17:26:32 -0700
Subject: x86: kvm: mmu: use ept a/d in vmcs02 iff used in vmcs12

EPT A/D was enabled in the vmcs02 EPTP regardless of the vmcs12's EPTP
value. The problem is that enabling A/D changes the behavior of L2's
x86 page table walks as seen by L1. With A/D enabled, x86 page table
walks are always treated as EPT writes.

Commit ae1e2d1082ae ("kvm: nVMX: support EPT accessed/dirty bits",
2017-03-30) tried to work around this problem by clearing the write
bit in the exit qualification for EPT violations triggered by page
walks.  However, that fixup introduced the opposite bug: page-table walks
that actually set x86 A/D bits were *missing* the write bit in the exit
qualification.

This patch fixes the problem by disabling EPT A/D in the shadow MMU
when EPT A/D is disabled in vmcs12's EPTP.

Signed-off-by: Peter Feiner <pfeiner@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu.c |  1 +
 arch/x86/kvm/vmx.c | 38 +++++++++++++++++---------------------
 2 files changed, 18 insertions(+), 21 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 48d8e7e60163..3ba600d09dea 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -4419,6 +4419,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
 	context->root_level = context->shadow_root_level;
 	context->root_hpa = INVALID_PAGE;
 	context->direct_map = false;
+	context->base_role.ad_disabled = !accessed_dirty;
 
 	update_permission_bitmask(vcpu, context, true);
 	update_pkru_bitmask(vcpu, context, true);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index b102a864e61f..fb0471268a14 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -910,8 +910,9 @@ static void nested_release_page_clean(struct page *page)
 	kvm_release_page_clean(page);
 }
 
+static bool nested_ept_ad_enabled(struct kvm_vcpu *vcpu);
 static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu);
-static u64 construct_eptp(unsigned long root_hpa);
+static u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa);
 static bool vmx_xsaves_supported(void);
 static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr);
 static void vmx_set_segment(struct kvm_vcpu *vcpu,
@@ -4013,7 +4014,7 @@ static inline void __vmx_flush_tlb(struct kvm_vcpu *vcpu, int vpid)
 	if (enable_ept) {
 		if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
 			return;
-		ept_sync_context(construct_eptp(vcpu->arch.mmu.root_hpa));
+		ept_sync_context(construct_eptp(vcpu, vcpu->arch.mmu.root_hpa));
 	} else {
 		vpid_sync_context(vpid);
 	}
@@ -4188,14 +4189,15 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	vmx->emulation_required = emulation_required(vcpu);
 }
 
-static u64 construct_eptp(unsigned long root_hpa)
+static u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa)
 {
 	u64 eptp;
 
 	/* TODO write the value reading from MSR */
 	eptp = VMX_EPT_DEFAULT_MT |
 		VMX_EPT_DEFAULT_GAW << VMX_EPT_GAW_EPTP_SHIFT;
-	if (enable_ept_ad_bits)
+	if (enable_ept_ad_bits &&
+	    (!is_guest_mode(vcpu) || nested_ept_ad_enabled(vcpu)))
 		eptp |= VMX_EPT_AD_ENABLE_BIT;
 	eptp |= (root_hpa & PAGE_MASK);
 
@@ -4209,7 +4211,7 @@ static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 
 	guest_cr3 = cr3;
 	if (enable_ept) {
-		eptp = construct_eptp(cr3);
+		eptp = construct_eptp(vcpu, cr3);
 		vmcs_write64(EPT_POINTER, eptp);
 		if (is_paging(vcpu) || is_guest_mode(vcpu))
 			guest_cr3 = kvm_read_cr3(vcpu);
@@ -6214,17 +6216,6 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
 
 	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
 
-	if (is_guest_mode(vcpu)
-	    && !(exit_qualification & EPT_VIOLATION_GVA_TRANSLATED)) {
-		/*
-		 * Fix up exit_qualification according to whether guest
-		 * page table accesses are reads or writes.
-		 */
-		u64 eptp = nested_ept_get_cr3(vcpu);
-		if (!(eptp & VMX_EPT_AD_ENABLE_BIT))
-			exit_qualification &= ~EPT_VIOLATION_ACC_WRITE;
-	}
-
 	/*
 	 * EPT violation happened while executing iret from NMI,
 	 * "blocked by NMI" bit has to be set before next VM entry.
@@ -6447,7 +6438,7 @@ void vmx_enable_tdp(void)
 		enable_ept_ad_bits ? VMX_EPT_DIRTY_BIT : 0ull,
 		0ull, VMX_EPT_EXECUTABLE_MASK,
 		cpu_has_vmx_ept_execute_only() ? 0ull : VMX_EPT_READABLE_MASK,
-		enable_ept_ad_bits ? 0ull : VMX_EPT_RWX_MASK);
+		VMX_EPT_RWX_MASK);
 
 	ept_set_mmio_spte_mask();
 	kvm_enable_tdp();
@@ -9393,6 +9384,11 @@ static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu,
 	vmcs12->guest_physical_address = fault->address;
 }
 
+static bool nested_ept_ad_enabled(struct kvm_vcpu *vcpu)
+{
+	return nested_ept_get_cr3(vcpu) & VMX_EPT_AD_ENABLE_BIT;
+}
+
 /* Callbacks for nested_ept_init_mmu_context: */
 
 static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu)
@@ -9403,18 +9399,18 @@ static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu)
 
 static int nested_ept_init_mmu_context(struct kvm_vcpu *vcpu)
 {
-	u64 eptp;
+	bool wants_ad;
 
 	WARN_ON(mmu_is_nested(vcpu));
-	eptp = nested_ept_get_cr3(vcpu);
-	if ((eptp & VMX_EPT_AD_ENABLE_BIT) && !enable_ept_ad_bits)
+	wants_ad = nested_ept_ad_enabled(vcpu);
+	if (wants_ad && !enable_ept_ad_bits)
 		return 1;
 
 	kvm_mmu_unload(vcpu);
 	kvm_init_shadow_ept_mmu(vcpu,
 			to_vmx(vcpu)->nested.nested_vmx_ept_caps &
 			VMX_EPT_EXECUTE_ONLY_BIT,
-			eptp & VMX_EPT_AD_ENABLE_BIT);
+			wants_ad);
 	vcpu->arch.mmu.set_cr3           = vmx_set_cr3;
 	vcpu->arch.mmu.get_cr3           = nested_ept_get_cr3;
 	vcpu->arch.mmu.inject_page_fault = nested_ept_inject_page_fault;
-- 
cgit v1.2.3


From 691bd4340bef49cf7e5855d06cf24444b5bf2d85 Mon Sep 17 00:00:00 2001
From: Haozhong Zhang <haozhong.zhang@intel.com>
Date: Tue, 4 Jul 2017 10:27:41 +0800
Subject: kvm: vmx: allow host to access guest MSR_IA32_BNDCFGS

It's easier for host applications, such as QEMU, if they can always
access guest MSR_IA32_BNDCFGS in VMCS, even though MPX is disabled in
guest cpuid.

Cc: stable@vger.kernel.org
Signed-off-by: Haozhong Zhang <haozhong.zhang@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/vmx.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index fb0471268a14..b4cfdcfdc1c1 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3196,7 +3196,8 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		msr_info->data = vmcs_readl(GUEST_SYSENTER_ESP);
 		break;
 	case MSR_IA32_BNDCFGS:
-		if (!kvm_mpx_supported() || !guest_cpuid_has_mpx(vcpu))
+		if (!kvm_mpx_supported() ||
+		    (!msr_info->host_initiated && !guest_cpuid_has_mpx(vcpu)))
 			return 1;
 		msr_info->data = vmcs_read64(GUEST_BNDCFGS);
 		break;
@@ -3278,7 +3279,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		vmcs_writel(GUEST_SYSENTER_ESP, data);
 		break;
 	case MSR_IA32_BNDCFGS:
-		if (!kvm_mpx_supported() || !guest_cpuid_has_mpx(vcpu))
+		if (!kvm_mpx_supported() ||
+		    (!msr_info->host_initiated && !guest_cpuid_has_mpx(vcpu)))
 			return 1;
 		if (is_noncanonical_address(data & PAGE_MASK) ||
 		    (data & MSR_IA32_BNDCFGS_RSVD))
-- 
cgit v1.2.3