[PATCH v4 3/4] KVM: x86: On emulation failure, convey the exit reason, etc. to userspace

[David Edmondson]

Should instruction emulation fail, include the VM exit reason, etc. in
the emulation_failure data passed to userspace, in order that the VMM
can report it as a debugging aid when describing the failure.

Suggested-by: Joao Martins <joao.m.martins@xxxxxxxxxx>
Signed-off-by: David Edmondson <david.edmondson@xxxxxxxxxx>
---
 arch/x86/include/asm/kvm_host.h |  3 ++
 arch/x86/kvm/vmx/vmx.c          |  5 +--
 arch/x86/kvm/x86.c              | 73 ++++++++++++++++++++++++++-------
 include/uapi/linux/kvm.h        |  7 ++++
 4 files changed, 70 insertions(+), 18 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index e3c0788bcdc2..da2d8f3a2019 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1630,6 +1630,9 @@ extern u64 kvm_mce_cap_supported;
 int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type);
 int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu,
 					void *insn, int insn_len);
+void __kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu,
+					  u64 *data, u8 ndata);
+void kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu);
 
 void kvm_enable_efer_bits(u64);
 bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 6e5706ecce0b..9d14f68651f1 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -5367,10 +5367,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
 
 		if (vmx->emulation_required && !vmx->rmode.vm86_active &&
 		    vcpu->arch.exception.pending) {
-			vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-			vcpu->run->internal.suberror =
-						KVM_INTERNAL_ERROR_EMULATION;
-			vcpu->run->internal.ndata = 0;
+			kvm_prepare_emulation_failure_exit(vcpu);
 			return 0;
 		}
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e5d5c5ed7dd4..35639391de7b 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7465,29 +7465,78 @@ void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip)
 }
 EXPORT_SYMBOL_GPL(kvm_inject_realmode_interrupt);
 
-static void prepare_emulation_failure_exit(struct kvm_vcpu *vcpu)
+static void prepare_emulation_failure_exit(struct kvm_vcpu *vcpu, u64 *data,
+					   u8 ndata, u8 *insn_bytes, u8 insn_size)
 {
-	struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt;
-	u32 insn_size = ctxt->fetch.end - ctxt->fetch.data;
 	struct kvm_run *run = vcpu->run;
+	u8 ndata_start;
+	u64 info[5];
+
+	/*
+	 * Zero the whole array used to retrieve the exit info, casting to u32
+	 * for select entries will leave some chunks uninitialized.
+	 */
+	memset(&info, 0, sizeof(info));
+
+	static_call(kvm_x86_get_exit_info)(vcpu, (u32 *)&info[0], &info[1],
+					   &info[2], (u32 *)&info[3],
+					   (u32 *)&info[4]);
 
 	run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 	run->emulation_failure.suberror = KVM_INTERNAL_ERROR_EMULATION;
-	run->emulation_failure.ndata = 0;
+
+	/*
+	 * There's currently space for 13 entries, but 5 are used for the exit
+	 * reason and info.  Restrict to 4 to reduce the maintenance burden
+	 * when expanding kvm_run.emulation_failure in the future.
+	 */
+	if (WARN_ON_ONCE(ndata > 4))
+		ndata = 4;
+
+	/* Always include the flags as a 'data' entry. */
+	ndata_start = 1;
 	run->emulation_failure.flags = 0;
 
 	if (insn_size) {
-		run->emulation_failure.ndata = 3;
+		ndata_start += (sizeof(run->emulation_failure.insn_size) +
+				sizeof(run->emulation_failure.insn_bytes)) /
+			sizeof(u64);
 		run->emulation_failure.flags |=
 			KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES;
 		run->emulation_failure.insn_size = insn_size;
 		memset(run->emulation_failure.insn_bytes, 0x90,
 		       sizeof(run->emulation_failure.insn_bytes));
-		memcpy(run->emulation_failure.insn_bytes,
-		       ctxt->fetch.data, insn_size);
+		memcpy(run->emulation_failure.insn_bytes, insn_bytes, insn_size);
 	}
+
+	memcpy(&run->internal.data[ndata_start], info, sizeof(info));
+	memcpy(&run->internal.data[ndata_start + ARRAY_SIZE(info)], data,
+	       ndata * sizeof(u64));
+
+	run->emulation_failure.ndata = ndata_start + ARRAY_SIZE(info) + ndata;
 }
 
+static void prepare_emulation_ctxt_failure_exit(struct kvm_vcpu *vcpu)
+{
+	struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt;
+
+	prepare_emulation_failure_exit(vcpu, NULL, 0, ctxt->fetch.data,
+				       ctxt->fetch.end - ctxt->fetch.data);
+}
+
+void __kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu, u64 *data,
+					  u8 ndata)
+{
+	prepare_emulation_failure_exit(vcpu, data, ndata, NULL, 0);
+}
+EXPORT_SYMBOL_GPL(__kvm_prepare_emulation_failure_exit);
+
+void kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu)
+{
+	__kvm_prepare_emulation_failure_exit(vcpu, NULL, 0);
+}
+EXPORT_SYMBOL_GPL(kvm_prepare_emulation_failure_exit);
+
 static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type)
 {
 	struct kvm *kvm = vcpu->kvm;
@@ -7502,16 +7551,14 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type)
 
 	if (kvm->arch.exit_on_emulation_error ||
 	    (emulation_type & EMULTYPE_SKIP)) {
-		prepare_emulation_failure_exit(vcpu);
+		prepare_emulation_ctxt_failure_exit(vcpu);
 		return 0;
 	}
 
 	kvm_queue_exception(vcpu, UD_VECTOR);
 
 	if (!is_guest_mode(vcpu) && static_call(kvm_x86_get_cpl)(vcpu) == 0) {
-		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
-		vcpu->run->internal.ndata = 0;
+		prepare_emulation_ctxt_failure_exit(vcpu);
 		return 0;
 	}
 
@@ -12104,9 +12151,7 @@ int kvm_handle_memory_failure(struct kvm_vcpu *vcpu, int r,
 	 * doesn't seem to be a real use-case behind such requests, just return
 	 * KVM_EXIT_INTERNAL_ERROR for now.
 	 */
-	vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-	vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
-	vcpu->run->internal.ndata = 0;
+	kvm_prepare_emulation_failure_exit(vcpu);
 
 	return 0;
 }
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 6c79c1ce3703..e86cc2de7b5c 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -397,6 +397,12 @@ struct kvm_run {
 		 * "ndata" is correct, that new fields are enumerated in "flags",
 		 * and that each flag enumerates fields that are 64-bit aligned
 		 * and sized (so that ndata+internal.data[] is valid/accurate).
+		 *
+		 * Space beyond the defined fields may be used to
+		 * store arbitrary debug information relating to the
+		 * emulation failure. It is accounted for in "ndata"
+		 * but otherwise unspecified and is not represented in
+		 * "flags".
 		 */
 		struct {
 			__u32 suberror;
@@ -408,6 +414,7 @@ struct kvm_run {
 					__u8  insn_bytes[15];
 				};
 			};
+			/* Arbitrary debug data may follow. */
 		} emulation_failure;
 		/* KVM_EXIT_OSI */
 		struct {
-- 
2.30.2