1 files changed, 66 insertions, 100 deletions

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index b4ee5e9f9e20..b213ca966d41 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -525,67 +525,19 @@ static int nested_vmx_check_tpr_shadow_controls(struct kvm_vcpu *vcpu,
 }
 
 /*
- * Check if MSR is intercepted for L01 MSR bitmap.
+ * For x2APIC MSRs, ignore the vmcs01 bitmap.  L1 can enable x2APIC without L1
+ * itself utilizing x2APIC.  All MSRs were previously set to be intercepted,
+ * only the "disable intercept" case needs to be handled.
  */
-static bool msr_write_intercepted_l01(struct kvm_vcpu *vcpu, u32 msr)
+static void nested_vmx_disable_intercept_for_x2apic_msr(unsigned long *msr_bitmap_l1,
+							unsigned long *msr_bitmap_l0,
+							u32 msr, int type)
 {
-	unsigned long *msr_bitmap;
-	int f = sizeof(unsigned long);
+	if (type & MSR_TYPE_R && !vmx_test_msr_bitmap_read(msr_bitmap_l1, msr))
+		vmx_clear_msr_bitmap_read(msr_bitmap_l0, msr);
 
-	if (!cpu_has_vmx_msr_bitmap())
-		return true;
-
-	msr_bitmap = to_vmx(vcpu)->vmcs01.msr_bitmap;
-
-	if (msr <= 0x1fff) {
-		return !!test_bit(msr, msr_bitmap + 0x800 / f);
-	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
-		msr &= 0x1fff;
-		return !!test_bit(msr, msr_bitmap + 0xc00 / f);
-	}
-
-	return true;
-}
-
-/*
- * If a msr is allowed by L0, we should check whether it is allowed by L1.
- * The corresponding bit will be cleared unless both of L0 and L1 allow it.
- */
-static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1,
-					       unsigned long *msr_bitmap_nested,
-					       u32 msr, int type)
-{
-	int f = sizeof(unsigned long);
-
-	/*
-	 * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals
-	 * have the write-low and read-high bitmap offsets the wrong way round.
-	 * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff.
-	 */
-	if (msr <= 0x1fff) {
-		if (type & MSR_TYPE_R &&
-		   !test_bit(msr, msr_bitmap_l1 + 0x000 / f))
-			/* read-low */
-			__clear_bit(msr, msr_bitmap_nested + 0x000 / f);
-
-		if (type & MSR_TYPE_W &&
-		   !test_bit(msr, msr_bitmap_l1 + 0x800 / f))
-			/* write-low */
-			__clear_bit(msr, msr_bitmap_nested + 0x800 / f);
-
-	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
-		msr &= 0x1fff;
-		if (type & MSR_TYPE_R &&
-		   !test_bit(msr, msr_bitmap_l1 + 0x400 / f))
-			/* read-high */
-			__clear_bit(msr, msr_bitmap_nested + 0x400 / f);
-
-		if (type & MSR_TYPE_W &&
-		   !test_bit(msr, msr_bitmap_l1 + 0xc00 / f))
-			/* write-high */
-			__clear_bit(msr, msr_bitmap_nested + 0xc00 / f);
-
-	}
+	if (type & MSR_TYPE_W && !vmx_test_msr_bitmap_write(msr_bitmap_l1, msr))
+		vmx_clear_msr_bitmap_write(msr_bitmap_l0, msr);
 }
 
 static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap)
@@ -600,6 +552,34 @@ static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap)
 	}
 }
 
+#define BUILD_NVMX_MSR_INTERCEPT_HELPER(rw)					\
+static inline									\
+void nested_vmx_set_msr_##rw##_intercept(struct vcpu_vmx *vmx,			\
+					 unsigned long *msr_bitmap_l1,		\
+					 unsigned long *msr_bitmap_l0, u32 msr)	\
+{										\
+	if (vmx_test_msr_bitmap_##rw(vmx->vmcs01.msr_bitmap, msr) ||		\
+	    vmx_test_msr_bitmap_##rw(msr_bitmap_l1, msr))			\
+		vmx_set_msr_bitmap_##rw(msr_bitmap_l0, msr);			\
+	else									\
+		vmx_clear_msr_bitmap_##rw(msr_bitmap_l0, msr);			\
+}
+BUILD_NVMX_MSR_INTERCEPT_HELPER(read)
+BUILD_NVMX_MSR_INTERCEPT_HELPER(write)
+
+static inline void nested_vmx_set_intercept_for_msr(struct vcpu_vmx *vmx,
+						    unsigned long *msr_bitmap_l1,
+						    unsigned long *msr_bitmap_l0,
+						    u32 msr, int types)
+{
+	if (types & MSR_TYPE_R)
+		nested_vmx_set_msr_read_intercept(vmx, msr_bitmap_l1,
+						  msr_bitmap_l0, msr);
+	if (types & MSR_TYPE_W)
+		nested_vmx_set_msr_write_intercept(vmx, msr_bitmap_l1,
+						   msr_bitmap_l0, msr);
+}
+
 /*
  * Merge L0's and L1's MSR bitmap, return false to indicate that
  * we do not use the hardware.
@@ -607,10 +587,11 @@ static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap)
 static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 						 struct vmcs12 *vmcs12)
 {
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	int msr;
 	unsigned long *msr_bitmap_l1;
-	unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.vmcs02.msr_bitmap;
-	struct kvm_host_map *map = &to_vmx(vcpu)->nested.msr_bitmap_map;
+	unsigned long *msr_bitmap_l0 = vmx->nested.vmcs02.msr_bitmap;
+	struct kvm_host_map *map = &vmx->nested.msr_bitmap_map;
 
 	/* Nothing to do if the MSR bitmap is not in use.  */
 	if (!cpu_has_vmx_msr_bitmap() ||
@@ -625,7 +606,7 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 	/*
 	 * To keep the control flow simple, pay eight 8-byte writes (sixteen
 	 * 4-byte writes on 32-bit systems) up front to enable intercepts for
-	 * the x2APIC MSR range and selectively disable them below.
+	 * the x2APIC MSR range and selectively toggle those relevant to L2.
 	 */
 	enable_x2apic_msr_intercepts(msr_bitmap_l0);
 
@@ -644,61 +625,44 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 			}
 		}
 
-		nested_vmx_disable_intercept_for_msr(
+		nested_vmx_disable_intercept_for_x2apic_msr(
 			msr_bitmap_l1, msr_bitmap_l0,
 			X2APIC_MSR(APIC_TASKPRI),
 			MSR_TYPE_R | MSR_TYPE_W);
 
 		if (nested_cpu_has_vid(vmcs12)) {
-			nested_vmx_disable_intercept_for_msr(
+			nested_vmx_disable_intercept_for_x2apic_msr(
 				msr_bitmap_l1, msr_bitmap_l0,
 				X2APIC_MSR(APIC_EOI),
 				MSR_TYPE_W);
-			nested_vmx_disable_intercept_for_msr(
+			nested_vmx_disable_intercept_for_x2apic_msr(
 				msr_bitmap_l1, msr_bitmap_l0,
 				X2APIC_MSR(APIC_SELF_IPI),
 				MSR_TYPE_W);
 		}
 	}
 
-	/* KVM unconditionally exposes the FS/GS base MSRs to L1. */
+	/*
+	 * Always check vmcs01's bitmap to honor userspace MSR filters and any
+	 * other runtime changes to vmcs01's bitmap, e.g. dynamic pass-through.
+	 */
 #ifdef CONFIG_X86_64
-	nested_vmx_disable_intercept_for_msr(msr_bitmap_l1, msr_bitmap_l0,
-					     MSR_FS_BASE, MSR_TYPE_RW);
+	nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
+					 MSR_FS_BASE, MSR_TYPE_RW);
 
-	nested_vmx_disable_intercept_for_msr(msr_bitmap_l1, msr_bitmap_l0,
-					     MSR_GS_BASE, MSR_TYPE_RW);
+	nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
+					 MSR_GS_BASE, MSR_TYPE_RW);
 
-	nested_vmx_disable_intercept_for_msr(msr_bitmap_l1, msr_bitmap_l0,
-					     MSR_KERNEL_GS_BASE, MSR_TYPE_RW);
+	nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
+					 MSR_KERNEL_GS_BASE, MSR_TYPE_RW);
 #endif
+	nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
+					 MSR_IA32_SPEC_CTRL, MSR_TYPE_RW);
 
-	/*
-	 * Checking the L0->L1 bitmap is trying to verify two things:
-	 *
-	 * 1. L0 gave a permission to L1 to actually passthrough the MSR. This
-	 *    ensures that we do not accidentally generate an L02 MSR bitmap
-	 *    from the L12 MSR bitmap that is too permissive.
-	 * 2. That L1 or L2s have actually used the MSR. This avoids
-	 *    unnecessarily merging of the bitmap if the MSR is unused. This
-	 *    works properly because we only update the L01 MSR bitmap lazily.
-	 *    So even if L0 should pass L1 these MSRs, the L01 bitmap is only
-	 *    updated to reflect this when L1 (or its L2s) actually write to
-	 *    the MSR.
-	 */
-	if (!msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL))
-		nested_vmx_disable_intercept_for_msr(
-					msr_bitmap_l1, msr_bitmap_l0,
-					MSR_IA32_SPEC_CTRL,
-					MSR_TYPE_R | MSR_TYPE_W);
-
-	if (!msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD))
-		nested_vmx_disable_intercept_for_msr(
-					msr_bitmap_l1, msr_bitmap_l0,
-					MSR_IA32_PRED_CMD,
-					MSR_TYPE_W);
+	nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
+					 MSR_IA32_PRED_CMD, MSR_TYPE_W);
 
-	kvm_vcpu_unmap(vcpu, &to_vmx(vcpu)->nested.msr_bitmap_map, false);
+	kvm_vcpu_unmap(vcpu, &vmx->nested.msr_bitmap_map, false);
 
 	return true;
 }
@@ -5379,7 +5343,7 @@ static int handle_invept(struct kvm_vcpu *vcpu)
 	struct {
 		u64 eptp, gpa;
 	} operand;
-	int i, r;
+	int i, r, gpr_index;
 
 	if (!(vmx->nested.msrs.secondary_ctls_high &
 	      SECONDARY_EXEC_ENABLE_EPT) ||
@@ -5392,7 +5356,8 @@ static int handle_invept(struct kvm_vcpu *vcpu)
 		return 1;
 
 	vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
-	type = kvm_register_read(vcpu, (vmx_instruction_info >> 28) & 0xf);
+	gpr_index = vmx_get_instr_info_reg2(vmx_instruction_info);
+	type = kvm_register_read(vcpu, gpr_index);
 
 	types = (vmx->nested.msrs.ept_caps >> VMX_EPT_EXTENT_SHIFT) & 6;
 
@@ -5459,7 +5424,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 		u64 gla;
 	} operand;
 	u16 vpid02;
-	int r;
+	int r, gpr_index;
 
 	if (!(vmx->nested.msrs.secondary_ctls_high &
 	      SECONDARY_EXEC_ENABLE_VPID) ||
@@ -5472,7 +5437,8 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 		return 1;
 
 	vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
-	type = kvm_register_read(vcpu, (vmx_instruction_info >> 28) & 0xf);
+	gpr_index = vmx_get_instr_info_reg2(vmx_instruction_info);
+	type = kvm_register_read(vcpu, gpr_index);
 
 	types = (vmx->nested.msrs.vpid_caps &
 			VMX_VPID_EXTENT_SUPPORTED_MASK) >> 8;