Merge tag 'v6.1-rc7' into iommufd.git for-next

Resolve conflicts in drivers/vfio/vfio_main.c by using the iommfd version.
The rc fix was done a different way when iommufd patches reworked this
code.

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

1 files changed, 58 insertions, 28 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9cf1ba865562..2835bd796639 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -628,6 +628,12 @@ static void kvm_queue_exception_vmexit(struct kvm_vcpu *vcpu, unsigned int vecto
 	ex->payload = payload;
 }
 
+/* Forcibly leave the nested mode in cases like a vCPU reset */
+static void kvm_leave_nested(struct kvm_vcpu *vcpu)
+{
+	kvm_x86_ops.nested_ops->leave_nested(vcpu);
+}
+
 static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
 		unsigned nr, bool has_error, u32 error_code,
 	        bool has_payload, unsigned long payload, bool reinject)
@@ -1438,32 +1444,27 @@ static const u32 msrs_to_save_all[] = {
 	MSR_ARCH_PERFMON_FIXED_CTR0 + 2,
 	MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS,
 	MSR_CORE_PERF_GLOBAL_CTRL, MSR_CORE_PERF_GLOBAL_OVF_CTRL,
+	MSR_IA32_PEBS_ENABLE, MSR_IA32_DS_AREA, MSR_PEBS_DATA_CFG,
+
+	/* This part of MSRs should match KVM_INTEL_PMC_MAX_GENERIC. */
 	MSR_ARCH_PERFMON_PERFCTR0, MSR_ARCH_PERFMON_PERFCTR1,
 	MSR_ARCH_PERFMON_PERFCTR0 + 2, MSR_ARCH_PERFMON_PERFCTR0 + 3,
 	MSR_ARCH_PERFMON_PERFCTR0 + 4, MSR_ARCH_PERFMON_PERFCTR0 + 5,
 	MSR_ARCH_PERFMON_PERFCTR0 + 6, MSR_ARCH_PERFMON_PERFCTR0 + 7,
-	MSR_ARCH_PERFMON_PERFCTR0 + 8, MSR_ARCH_PERFMON_PERFCTR0 + 9,
-	MSR_ARCH_PERFMON_PERFCTR0 + 10, MSR_ARCH_PERFMON_PERFCTR0 + 11,
-	MSR_ARCH_PERFMON_PERFCTR0 + 12, MSR_ARCH_PERFMON_PERFCTR0 + 13,
-	MSR_ARCH_PERFMON_PERFCTR0 + 14, MSR_ARCH_PERFMON_PERFCTR0 + 15,
-	MSR_ARCH_PERFMON_PERFCTR0 + 16, MSR_ARCH_PERFMON_PERFCTR0 + 17,
 	MSR_ARCH_PERFMON_EVENTSEL0, MSR_ARCH_PERFMON_EVENTSEL1,
 	MSR_ARCH_PERFMON_EVENTSEL0 + 2, MSR_ARCH_PERFMON_EVENTSEL0 + 3,
 	MSR_ARCH_PERFMON_EVENTSEL0 + 4, MSR_ARCH_PERFMON_EVENTSEL0 + 5,
 	MSR_ARCH_PERFMON_EVENTSEL0 + 6, MSR_ARCH_PERFMON_EVENTSEL0 + 7,
-	MSR_ARCH_PERFMON_EVENTSEL0 + 8, MSR_ARCH_PERFMON_EVENTSEL0 + 9,
-	MSR_ARCH_PERFMON_EVENTSEL0 + 10, MSR_ARCH_PERFMON_EVENTSEL0 + 11,
-	MSR_ARCH_PERFMON_EVENTSEL0 + 12, MSR_ARCH_PERFMON_EVENTSEL0 + 13,
-	MSR_ARCH_PERFMON_EVENTSEL0 + 14, MSR_ARCH_PERFMON_EVENTSEL0 + 15,
-	MSR_ARCH_PERFMON_EVENTSEL0 + 16, MSR_ARCH_PERFMON_EVENTSEL0 + 17,
-	MSR_IA32_PEBS_ENABLE, MSR_IA32_DS_AREA, MSR_PEBS_DATA_CFG,
 
 	MSR_K7_EVNTSEL0, MSR_K7_EVNTSEL1, MSR_K7_EVNTSEL2, MSR_K7_EVNTSEL3,
 	MSR_K7_PERFCTR0, MSR_K7_PERFCTR1, MSR_K7_PERFCTR2, MSR_K7_PERFCTR3,
+
+	/* This part of MSRs should match KVM_AMD_PMC_MAX_GENERIC. */
 	MSR_F15H_PERF_CTL0, MSR_F15H_PERF_CTL1, MSR_F15H_PERF_CTL2,
 	MSR_F15H_PERF_CTL3, MSR_F15H_PERF_CTL4, MSR_F15H_PERF_CTL5,
 	MSR_F15H_PERF_CTR0, MSR_F15H_PERF_CTR1, MSR_F15H_PERF_CTR2,
 	MSR_F15H_PERF_CTR3, MSR_F15H_PERF_CTR4, MSR_F15H_PERF_CTR5,
+
 	MSR_IA32_XFD, MSR_IA32_XFD_ERR,
 };
 
@@ -1562,7 +1563,7 @@ static const u32 msr_based_features_all[] = {
 	MSR_IA32_VMX_EPT_VPID_CAP,
 	MSR_IA32_VMX_VMFUNC,
 
-	MSR_F10H_DECFG,
+	MSR_AMD64_DE_CFG,
 	MSR_IA32_UCODE_REV,
 	MSR_IA32_ARCH_CAPABILITIES,
 	MSR_IA32_PERF_CAPABILITIES,
@@ -2315,11 +2316,11 @@ static void kvm_write_system_time(struct kvm_vcpu *vcpu, gpa_t system_time,
 
 	/* we verify if the enable bit is set... */
 	if (system_time & 1) {
-		kvm_gfn_to_pfn_cache_init(vcpu->kvm, &vcpu->arch.pv_time, vcpu,
-					  KVM_HOST_USES_PFN, system_time & ~1ULL,
-					  sizeof(struct pvclock_vcpu_time_info));
+		kvm_gpc_activate(vcpu->kvm, &vcpu->arch.pv_time, vcpu,
+				 KVM_HOST_USES_PFN, system_time & ~1ULL,
+				 sizeof(struct pvclock_vcpu_time_info));
 	} else {
-		kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, &vcpu->arch.pv_time);
+		kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.pv_time);
 	}
 
 	return;
@@ -3388,7 +3389,7 @@ static int kvm_pv_enable_async_pf_int(struct kvm_vcpu *vcpu, u64 data)
 
 static void kvmclock_reset(struct kvm_vcpu *vcpu)
 {
-	kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, &vcpu->arch.pv_time);
+	kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.pv_time);
 	vcpu->arch.time = 0;
 }
 
@@ -5200,7 +5201,7 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 
 	if (events->flags & KVM_VCPUEVENT_VALID_SMM) {
 		if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) {
-			kvm_x86_ops.nested_ops->leave_nested(vcpu);
+			kvm_leave_nested(vcpu);
 			kvm_smm_changed(vcpu, events->smi.smm);
 		}
 
@@ -7041,14 +7042,14 @@ static void kvm_init_msr_list(void)
 				intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2)
 				continue;
 			break;
-		case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR0 + 17:
+		case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR_MAX:
 			if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_PERFCTR0 >=
-			    min(INTEL_PMC_MAX_GENERIC, kvm_pmu_cap.num_counters_gp))
+			    min(KVM_INTEL_PMC_MAX_GENERIC, kvm_pmu_cap.num_counters_gp))
 				continue;
 			break;
-		case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL0 + 17:
+		case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL_MAX:
 			if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_EVENTSEL0 >=
-			    min(INTEL_PMC_MAX_GENERIC, kvm_pmu_cap.num_counters_gp))
+			    min(KVM_INTEL_PMC_MAX_GENERIC, kvm_pmu_cap.num_counters_gp))
 				continue;
 			break;
 		case MSR_IA32_XFD:
@@ -9810,7 +9811,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu)
 
 int kvm_check_nested_events(struct kvm_vcpu *vcpu)
 {
-	if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
+	if (kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
 		kvm_x86_ops.nested_ops->triple_fault(vcpu);
 		return 1;
 	}
@@ -10044,7 +10045,20 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu,
 	    kvm_x86_ops.nested_ops->has_events(vcpu))
 		*req_immediate_exit = true;
 
-	WARN_ON(kvm_is_exception_pending(vcpu));
+	/*
+	 * KVM must never queue a new exception while injecting an event; KVM
+	 * is done emulating and should only propagate the to-be-injected event
+	 * to the VMCS/VMCB.  Queueing a new exception can put the vCPU into an
+	 * infinite loop as KVM will bail from VM-Enter to inject the pending
+	 * exception and start the cycle all over.
+	 *
+	 * Exempt triple faults as they have special handling and won't put the
+	 * vCPU into an infinite loop.  Triple fault can be queued when running
+	 * VMX without unrestricted guest, as that requires KVM to emulate Real
+	 * Mode events (see kvm_inject_realmode_interrupt()).
+	 */
+	WARN_ON_ONCE(vcpu->arch.exception.pending ||
+		     vcpu->arch.exception_vmexit.pending);
 	return 0;
 
 out:
@@ -10391,7 +10405,10 @@ void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm,
 		kvm->arch.apicv_inhibit_reasons = new;
 		if (new) {
 			unsigned long gfn = gpa_to_gfn(APIC_DEFAULT_PHYS_BASE);
+			int idx = srcu_read_lock(&kvm->srcu);
+
 			kvm_zap_gfn_range(kvm, gfn, gfn+1);
+			srcu_read_unlock(&kvm->srcu, idx);
 		}
 	} else {
 		kvm->arch.apicv_inhibit_reasons = new;
@@ -10549,15 +10566,16 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			r = 0;
 			goto out;
 		}
-		if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
-			if (is_guest_mode(vcpu)) {
+		if (kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
+			if (is_guest_mode(vcpu))
 				kvm_x86_ops.nested_ops->triple_fault(vcpu);
-			} else {
+
+			if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
 				vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN;
 				vcpu->mmio_needed = 0;
 				r = 0;
-				goto out;
 			}
+			goto out;
 		}
 		if (kvm_check_request(KVM_REQ_APF_HALT, vcpu)) {
 			/* Page is swapped out. Do synthetic halt */
@@ -11816,6 +11834,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	vcpu->arch.regs_avail = ~0;
 	vcpu->arch.regs_dirty = ~0;
 
+	kvm_gpc_init(&vcpu->arch.pv_time);
+
 	if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu))
 		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 	else
@@ -11984,8 +12004,18 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	WARN_ON_ONCE(!init_event &&
 		     (old_cr0 || kvm_read_cr3(vcpu) || kvm_read_cr4(vcpu)));
 
+	/*
+	 * SVM doesn't unconditionally VM-Exit on INIT and SHUTDOWN, thus it's
+	 * possible to INIT the vCPU while L2 is active.  Force the vCPU back
+	 * into L1 as EFER.SVME is cleared on INIT (along with all other EFER
+	 * bits), i.e. virtualization is disabled.
+	 */
+	if (is_guest_mode(vcpu))
+		kvm_leave_nested(vcpu);
+
 	kvm_lapic_reset(vcpu, init_event);
 
+	WARN_ON_ONCE(is_guest_mode(vcpu) || is_smm(vcpu));
 	vcpu->arch.hflags = 0;
 
 	vcpu->arch.smi_pending = 0;