kvm: x86: Add "last CPU" to some KVM_EXIT information

More often than not, a failed VM-entry in an x86 production
environment is induced by a defective CPU. To help identify the bad
hardware, include the id of the last logical CPU to run a vCPU in the
information provided to userspace on a KVM exit for failed VM-entry or
for KVM internal errors not associated with emulation. The presence of
this additional information is indicated by a new capability,
KVM_CAP_LAST_CPU.

Signed-off-by: Jim Mattson <jmattson@google.com>
Reviewed-by: Oliver Upton <oupton@google.com>
Reviewed-by: Peter Shier <pshier@google.com>
Message-Id: <20200603235623.245638-5-jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Documentation/virt/kvm/api.rst

@@ -4794,6 +4794,7 @@ hardware_exit_reason.
 		/* KVM_EXIT_FAIL_ENTRY */
 		struct {
 			__u64 hardware_entry_failure_reason;
+			__u32 cpu; /* if KVM_LAST_CPU */
 		} fail_entry;
 
 If exit_reason is KVM_EXIT_FAIL_ENTRY, the vcpu could not be run due

arch/x86/kvm/svm/svm.c

@@ -2947,6 +2947,7 @@ static int handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 		kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
 		kvm_run->fail_entry.hardware_entry_failure_reason
 			= svm->vmcb->control.exit_code;
+		kvm_run->fail_entry.cpu = svm->last_cpu;
 		dump_vmcb(vcpu);
 		return 0;
 	}
@@ -2970,8 +2971,9 @@ static int handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror =
 			KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON;
-		vcpu->run->internal.ndata = 1;
+		vcpu->run->internal.ndata = 2;
 		vcpu->run->internal.data[0] = exit_code;
+		vcpu->run->internal.data[1] = svm->last_cpu;
 		return 0;
 	}
 

arch/x86/kvm/vmx/vmx.c

@@ -4781,10 +4781,11 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
 	    !(is_page_fault(intr_info) && !(error_code & PFERR_RSVD_MASK))) {
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_SIMUL_EX;
-		vcpu->run->internal.ndata = 3;
+		vcpu->run->internal.ndata = 4;
 		vcpu->run->internal.data[0] = vect_info;
 		vcpu->run->internal.data[1] = intr_info;
 		vcpu->run->internal.data[2] = error_code;
+		vcpu->run->internal.data[3] = vmx->last_cpu;
 		return 0;
 	}
 
@@ -6006,6 +6007,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 		vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY;
 		vcpu->run->fail_entry.hardware_entry_failure_reason
 			= exit_reason;
+		vcpu->run->fail_entry.cpu = vmx->last_cpu;
 		return 0;
 	}
 
@@ -6014,6 +6016,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 		vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY;
 		vcpu->run->fail_entry.hardware_entry_failure_reason
 			= vmcs_read32(VM_INSTRUCTION_ERROR);
+		vcpu->run->fail_entry.cpu = vmx->last_cpu;
 		return 0;
 	}
 
@@ -6040,6 +6043,8 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 			vcpu->run->internal.data[3] =
 				vmcs_read64(GUEST_PHYSICAL_ADDRESS);
 		}
+		vcpu->run->internal.data[vcpu->run->internal.ndata++] =
+			vmx->last_cpu;
 		return 0;
 	}
 
@@ -6095,8 +6100,9 @@ unexpected_vmexit:
 	vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 	vcpu->run->internal.suberror =
 			KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON;
-	vcpu->run->internal.ndata = 1;
+	vcpu->run->internal.ndata = 2;
 	vcpu->run->internal.data[0] = exit_reason;
+	vcpu->run->internal.data[1] = vmx->last_cpu;
 	return 0;
 }
 

arch/x86/kvm/x86.c

@@ -3510,6 +3510,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_MSR_PLATFORM_INFO:
 	case KVM_CAP_EXCEPTION_PAYLOAD:
 	case KVM_CAP_SET_GUEST_DEBUG:
+	case KVM_CAP_LAST_CPU:
 		r = 1;
 		break;
 	case KVM_CAP_SYNC_REGS:

include/uapi/linux/kvm.h

@@ -289,6 +289,7 @@ struct kvm_run {
 		/* KVM_EXIT_FAIL_ENTRY */
 		struct {
 			__u64 hardware_entry_failure_reason;
+			__u32 cpu;
 		} fail_entry;
 		/* KVM_EXIT_EXCEPTION */
 		struct {
@@ -1031,6 +1032,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_PPC_SECURE_GUEST 181
 #define KVM_CAP_HALT_POLL 182
 #define KVM_CAP_ASYNC_PF_INT 183
+#define KVM_CAP_LAST_CPU 184
 
 #ifdef KVM_CAP_IRQ_ROUTING