KVM: x86: Prepare MSR bitmaps for userspace tracked MSRs

Prepare vmx and svm for a subsequent change that ensures the MSR permission
bitmap is set to allow an MSR that userspace is tracking to force a vmx_vmexit
in the guest.
Signed-off-by: Aaron Lewis <aaronlewis@google.com>
Reviewed-by: Oliver Upton <oupton@google.com>
[agraf: rebase, adapt SVM scheme to nested changes that came in between]
Signed-off-by: Alexander Graf <graf@amazon.com>
Message-Id: <20200925143422.21718-5-graf@amazon.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/kvm/svm/svm.c

@@ -564,7 +564,7 @@ static bool valid_msr_intercept(u32 index)
 	return false;
 }
 
-static bool msr_write_intercepted(struct kvm_vcpu *vcpu, unsigned msr)
+static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr)
 {
 	u8 bit_write;
 	unsigned long tmp;
@@ -583,7 +583,7 @@ static bool msr_write_intercepted(struct kvm_vcpu *vcpu, unsigned msr)
 	return !!test_bit(bit_write,  &tmp);
 }
 
-static void set_msr_interception(u32 *msrpm, unsigned msr,
+static void set_msr_interception(struct kvm_vcpu *vcpu, u32 *msrpm, u32 msr,
 				 int read, int write)
 {
 	u8 bit_read, bit_write;
@@ -609,11 +609,10 @@ static void set_msr_interception(u32 *msrpm, unsigned msr,
 	msrpm[offset] = tmp;
 }
 
-static u32 *svm_vcpu_init_msrpm(void)
+static u32 *svm_vcpu_alloc_msrpm(void)
 {
-	int i;
-	u32 *msrpm;
 	struct page *pages = alloc_pages(GFP_KERNEL_ACCOUNT, MSRPM_ALLOC_ORDER);
+	u32 *msrpm;
 
 	if (!pages)
 		return NULL;
@@ -621,12 +620,18 @@ static u32 *svm_vcpu_init_msrpm(void)
 	msrpm = page_address(pages);
 	memset(msrpm, 0xff, PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER));
 
+	return msrpm;
+}
+
+static void svm_vcpu_init_msrpm(struct kvm_vcpu *vcpu, u32 *msrpm)
+{
+	int i;
+
 	for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) {
 		if (!direct_access_msrs[i].always)
 			continue;
-		set_msr_interception(msrpm, direct_access_msrs[i].index, 1, 1);
+		set_msr_interception(vcpu, msrpm, direct_access_msrs[i].index, 1, 1);
 	}
-	return msrpm;
 }
 
 static void svm_vcpu_free_msrpm(u32 *msrpm)
@@ -677,26 +682,26 @@ static void init_msrpm_offsets(void)
 	}
 }
 
-static void svm_enable_lbrv(struct vcpu_svm *svm)
+static void svm_enable_lbrv(struct kvm_vcpu *vcpu)
 {
-	u32 *msrpm = svm->msrpm;
+	struct vcpu_svm *svm = to_svm(vcpu);
 
 	svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK;
-	set_msr_interception(msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1);
-	set_msr_interception(msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1);
-	set_msr_interception(msrpm, MSR_IA32_LASTINTFROMIP, 1, 1);
-	set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 1, 1);
+	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1);
+	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1);
+	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1);
+	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1);
 }
 
-static void svm_disable_lbrv(struct vcpu_svm *svm)
+static void svm_disable_lbrv(struct kvm_vcpu *vcpu)
 {
-	u32 *msrpm = svm->msrpm;
+	struct vcpu_svm *svm = to_svm(vcpu);
 
 	svm->vmcb->control.virt_ext &= ~LBR_CTL_ENABLE_MASK;
-	set_msr_interception(msrpm, MSR_IA32_LASTBRANCHFROMIP, 0, 0);
-	set_msr_interception(msrpm, MSR_IA32_LASTBRANCHTOIP, 0, 0);
-	set_msr_interception(msrpm, MSR_IA32_LASTINTFROMIP, 0, 0);
-	set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0);
+	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 0, 0);
+	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 0, 0);
+	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 0, 0);
+	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 0, 0);
 }
 
 void disable_nmi_singlestep(struct vcpu_svm *svm)
@@ -1230,14 +1235,19 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu)
 
 	svm->nested.hsave = page_address(hsave_page);
 
-	svm->msrpm = svm_vcpu_init_msrpm();
+	svm->msrpm = svm_vcpu_alloc_msrpm();
 	if (!svm->msrpm)
 		goto error_free_hsave_page;
 
-	svm->nested.msrpm = svm_vcpu_init_msrpm();
+	svm_vcpu_init_msrpm(vcpu, svm->msrpm);
+
+	svm->nested.msrpm = svm_vcpu_alloc_msrpm();
 	if (!svm->nested.msrpm)
 		goto error_free_msrpm;
 
+	/* We only need the L1 pass-through MSR state, so leave vcpu as NULL */
+	svm_vcpu_init_msrpm(vcpu, svm->nested.msrpm);
+
 	svm->vmcb = page_address(vmcb_page);
 	svm->vmcb_pa = __sme_set(page_to_pfn(vmcb_page) << PAGE_SHIFT);
 	svm->asid_generation = 0;
@@ -2574,7 +2584,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		 * We update the L1 MSR bit as well since it will end up
 		 * touching the MSR anyway now.
 		 */
-		set_msr_interception(svm->msrpm, MSR_IA32_SPEC_CTRL, 1, 1);
+		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SPEC_CTRL, 1, 1);
 		break;
 	case MSR_IA32_PRED_CMD:
 		if (!msr->host_initiated &&
@@ -2589,7 +2599,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 			break;
 
 		wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB);
-		set_msr_interception(svm->msrpm, MSR_IA32_PRED_CMD, 0, 1);
+		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_PRED_CMD, 0, 1);
 		break;
 	case MSR_AMD64_VIRT_SPEC_CTRL:
 		if (!msr->host_initiated &&
@@ -2653,9 +2663,9 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		svm->vmcb->save.dbgctl = data;
 		vmcb_mark_dirty(svm->vmcb, VMCB_LBR);
 		if (data & (1ULL<<0))
-			svm_enable_lbrv(svm);
+			svm_enable_lbrv(vcpu);
 		else
-			svm_disable_lbrv(svm);
+			svm_disable_lbrv(vcpu);
 		break;
 	case MSR_VM_HSAVE_PA:
 		svm->nested.hsave_msr = data;

arch/x86/kvm/vmx/nested.c

@@ -4776,7 +4776,7 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu)
 
 	if (vmx_pt_mode_is_host_guest()) {
 		vmx->pt_desc.guest.ctl = 0;
-		pt_update_intercept_for_msr(vmx);
+		pt_update_intercept_for_msr(vcpu);
 	}
 
 	return 0;

arch/x86/kvm/vmx/vmx.c

@@ -338,7 +338,7 @@ static const struct kernel_param_ops vmentry_l1d_flush_ops = {
 module_param_cb(vmentry_l1d_flush, &vmentry_l1d_flush_ops, NULL, 0644);
 
 static u32 vmx_segment_access_rights(struct kvm_segment *var);
-static __always_inline void vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
+static __always_inline void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu,
 							  u32 msr, int type);
 
 void vmx_vmexit(void);
@@ -1980,7 +1980,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		 * in the merging. We update the vmcs01 here for L1 as well
 		 * since it will end up touching the MSR anyway now.
 		 */
-		vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap,
+		vmx_disable_intercept_for_msr(vcpu,
 					      MSR_IA32_SPEC_CTRL,
 					      MSR_TYPE_RW);
 		break;
@@ -2016,8 +2016,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		 * vmcs02.msr_bitmap here since it gets completely overwritten
 		 * in the merging.
 		 */
-		vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, MSR_IA32_PRED_CMD,
-					      MSR_TYPE_W);
+		vmx_disable_intercept_for_msr(vcpu, MSR_IA32_PRED_CMD, MSR_TYPE_W);
 		break;
 	case MSR_IA32_CR_PAT:
 		if (!kvm_pat_valid(data))
@@ -2067,7 +2066,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 1;
 		vmcs_write64(GUEST_IA32_RTIT_CTL, data);
 		vmx->pt_desc.guest.ctl = data;
-		pt_update_intercept_for_msr(vmx);
+		pt_update_intercept_for_msr(vcpu);
 		break;
 	case MSR_IA32_RTIT_STATUS:
 		if (!pt_can_write_msr(vmx))
@@ -3584,9 +3583,11 @@ void free_vpid(int vpid)
 	spin_unlock(&vmx_vpid_lock);
 }
 
-static __always_inline void vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
+static __always_inline void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu,
 							  u32 msr, int type)
 {
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap;
 	int f = sizeof(unsigned long);
 
 	if (!cpu_has_vmx_msr_bitmap())
@@ -3622,9 +3623,11 @@ static __always_inline void vmx_disable_intercept_for_msr(unsigned long *msr_bit
 	}
 }
 
-static __always_inline void vmx_enable_intercept_for_msr(unsigned long *msr_bitmap,
+static __always_inline void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu,
 							 u32 msr, int type)
 {
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap;
 	int f = sizeof(unsigned long);
 
 	if (!cpu_has_vmx_msr_bitmap())
@@ -3660,13 +3663,13 @@ static __always_inline void vmx_enable_intercept_for_msr(unsigned long *msr_bitm
 	}
 }
 
-static __always_inline void vmx_set_intercept_for_msr(unsigned long *msr_bitmap,
-			     			      u32 msr, int type, bool value)
+static __always_inline void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu,
+						      u32 msr, int type, bool value)
 {
 	if (value)
-		vmx_enable_intercept_for_msr(msr_bitmap, msr, type);
+		vmx_enable_intercept_for_msr(vcpu, msr, type);
 	else
-		vmx_disable_intercept_for_msr(msr_bitmap, msr, type);
+		vmx_disable_intercept_for_msr(vcpu, msr, type);
 }
 
 static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu)
@@ -3684,8 +3687,8 @@ static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu)
 	return mode;
 }
 
-static void vmx_update_msr_bitmap_x2apic(unsigned long *msr_bitmap,
-					 u8 mode)
+static void vmx_update_msr_bitmap_x2apic(struct kvm_vcpu *vcpu,
+					 unsigned long *msr_bitmap, u8 mode)
 {
 	int msr;
 
@@ -3700,11 +3703,11 @@ static void vmx_update_msr_bitmap_x2apic(unsigned long *msr_bitmap,
 		 * TPR reads and writes can be virtualized even if virtual interrupt
 		 * delivery is not in use.
 		 */
-		vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_RW);
+		vmx_disable_intercept_for_msr(vcpu, X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_RW);
 		if (mode & MSR_BITMAP_MODE_X2APIC_APICV) {
-			vmx_enable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TMCCT), MSR_TYPE_R);
-			vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_EOI), MSR_TYPE_W);
-			vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_SELF_IPI), MSR_TYPE_W);
+			vmx_enable_intercept_for_msr(vcpu, X2APIC_MSR(APIC_TMCCT), MSR_TYPE_RW);
+			vmx_disable_intercept_for_msr(vcpu, X2APIC_MSR(APIC_EOI), MSR_TYPE_W);
+			vmx_disable_intercept_for_msr(vcpu, X2APIC_MSR(APIC_SELF_IPI), MSR_TYPE_W);
 		}
 	}
 }
@@ -3720,30 +3723,24 @@ void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu)
 		return;
 
 	if (changed & (MSR_BITMAP_MODE_X2APIC | MSR_BITMAP_MODE_X2APIC_APICV))
-		vmx_update_msr_bitmap_x2apic(msr_bitmap, mode);
+		vmx_update_msr_bitmap_x2apic(vcpu, msr_bitmap, mode);
 
 	vmx->msr_bitmap_mode = mode;
 }
 
-void pt_update_intercept_for_msr(struct vcpu_vmx *vmx)
+void pt_update_intercept_for_msr(struct kvm_vcpu *vcpu)
 {
-	unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap;
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	bool flag = !(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN);
 	u32 i;
 
-	vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_STATUS,
-							MSR_TYPE_RW, flag);
-	vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_OUTPUT_BASE,
-							MSR_TYPE_RW, flag);
-	vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_OUTPUT_MASK,
-							MSR_TYPE_RW, flag);
-	vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_CR3_MATCH,
-							MSR_TYPE_RW, flag);
+	vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_STATUS, MSR_TYPE_RW, flag);
+	vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_OUTPUT_BASE, MSR_TYPE_RW, flag);
+	vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_OUTPUT_MASK, MSR_TYPE_RW, flag);
+	vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_CR3_MATCH, MSR_TYPE_RW, flag);
 	for (i = 0; i < vmx->pt_desc.addr_range; i++) {
-		vmx_set_intercept_for_msr(msr_bitmap,
-			MSR_IA32_RTIT_ADDR0_A + i * 2, MSR_TYPE_RW, flag);
-		vmx_set_intercept_for_msr(msr_bitmap,
-			MSR_IA32_RTIT_ADDR0_B + i * 2, MSR_TYPE_RW, flag);
+		vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_ADDR0_A + i * 2, MSR_TYPE_RW, flag);
+		vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_ADDR0_B + i * 2, MSR_TYPE_RW, flag);
 	}
 }
 
@@ -6753,18 +6750,18 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
 		goto free_pml;
 
 	msr_bitmap = vmx->vmcs01.msr_bitmap;
-	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_TSC, MSR_TYPE_R);
-	vmx_disable_intercept_for_msr(msr_bitmap, MSR_FS_BASE, MSR_TYPE_RW);
-	vmx_disable_intercept_for_msr(msr_bitmap, MSR_GS_BASE, MSR_TYPE_RW);
-	vmx_disable_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW);
-	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW);
-	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW);
-	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW);
+	vmx_disable_intercept_for_msr(vcpu, MSR_IA32_TSC, MSR_TYPE_R);
+	vmx_disable_intercept_for_msr(vcpu, MSR_FS_BASE, MSR_TYPE_RW);
+	vmx_disable_intercept_for_msr(vcpu, MSR_GS_BASE, MSR_TYPE_RW);
+	vmx_disable_intercept_for_msr(vcpu, MSR_KERNEL_GS_BASE, MSR_TYPE_RW);
+	vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW);
+	vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW);
+	vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW);
 	if (kvm_cstate_in_guest(vcpu->kvm)) {
-		vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C1_RES, MSR_TYPE_R);
-		vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C3_RESIDENCY, MSR_TYPE_R);
-		vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C6_RESIDENCY, MSR_TYPE_R);
-		vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C7_RESIDENCY, MSR_TYPE_R);
+		vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C1_RES, MSR_TYPE_R);
+		vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C3_RESIDENCY, MSR_TYPE_R);
+		vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C6_RESIDENCY, MSR_TYPE_R);
+		vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C7_RESIDENCY, MSR_TYPE_R);
 	}
 	vmx->msr_bitmap_mode = 0;
 

arch/x86/kvm/vmx/vmx.h

@@ -330,7 +330,7 @@ bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu);
 void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked);
 void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu);
 struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr);
-void pt_update_intercept_for_msr(struct vcpu_vmx *vmx);
+void pt_update_intercept_for_msr(struct kvm_vcpu *vcpu);
 void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp);
 int vmx_find_loadstore_msr_slot(struct vmx_msrs *m, u32 msr);
 void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu);