Add a fallback mechanism to the in-kernel instruction emulator that
allows userspace the opportunity to process an instruction the emulator
was unable to. When the in-kernel instruction emulator fails to process
an instruction it will either inject a #UD into the guest or exit to
userspace with exit reason KVM_INTERNAL_ERROR. This is because it does
not know how to proceed in an appropriate manner. This feature lets
userspace get involved to see if it can figure out a better path
forward.
Signed-off-by: Aaron Lewis <aaronlewis@xxxxxxxxxx>
Change-Id: If9876bc73d26f6c3ff9a8bce177c2fc6f160e629
---
Documentation/virt/kvm/api.rst | 16 ++++++++++++++++
arch/x86/include/asm/kvm_host.h | 6 ++++++
arch/x86/kvm/x86.c | 33 +++++++++++++++++++++++++++++----
include/uapi/linux/kvm.h | 20 ++++++++++++++++++++
tools/include/uapi/linux/kvm.h | 20 ++++++++++++++++++++
5 files changed, 91 insertions(+), 4 deletions(-)
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 307f2fcf1b02..f8278e893fbe 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6233,6 +6233,22 @@ KVM_RUN_BUS_LOCK flag is used to distinguish between them.
This capability can be used to check / enable 2nd DAWR feature provided
by POWER10 processor.
+7.24 KVM_CAP_EXIT_ON_EMULATION_FAILURE
+--------------------------------------
+
+:Architectures: x86
+:Parameters: args[0] whether the feature should be enabled or not
+
+With this capability enabled, the in-kernel instruction emulator packs the exit
+struct of KVM_INTERNAL_ERROR with the instruction length and instruction bytes
+when an error occurs while emulating an instruction. This allows userspace to
+then take a look at the instruction and see if it is able to handle it more
+gracefully than the in-kernel emulator.
+
+When this capability is enabled use the emulation_failure struct instead of the
+internal struct for the exit struct. They have the same layout, but the
+emulation_failure struct matches the content better.
+
8. Other capabilities.
======================
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 3768819693e5..07235d08e976 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1049,6 +1049,12 @@ struct kvm_arch {
bool exception_payload_enabled;
bool bus_lock_detection_enabled;
+ /*
+ * If exit_on_emulation_error is set, and the in-kernel instruction
+ * emulator fails to emulate an instruction, allow userspace
+ * the opportunity to look at it.
+ */
+ bool exit_on_emulation_error;
/* Deflect RDMSR and WRMSR to user space when they trigger a #GP */
u32 user_space_msr_mask;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index eca63625aee4..f9a207f815fb 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3771,6 +3771,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_X86_USER_SPACE_MSR:
case KVM_CAP_X86_MSR_FILTER:
case KVM_CAP_ENFORCE_PV_FEATURE_CPUID:
+ case KVM_CAP_EXIT_ON_EMULATION_FAILURE:
r = 1;
break;
#ifdef CONFIG_KVM_XEN
@@ -5357,6 +5358,10 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
kvm->arch.bus_lock_detection_enabled = true;
r = 0;
break;
+ case KVM_CAP_EXIT_ON_EMULATION_FAILURE:
+ kvm->arch.exit_on_emulation_error = cap->args[0];
+ r = 0;
+ break;
default:
r = -EINVAL;
break;
@@ -7119,8 +7124,29 @@ 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)
+{
+ struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt;
+ u64 insn_size = ctxt->fetch.end - ctxt->fetch.data;
+ struct kvm *kvm = vcpu->kvm;
+
+ vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+ vcpu->run->emulation_failure.suberror = KVM_INTERNAL_ERROR_EMULATION;
+ vcpu->run->emulation_failure.ndata = 0;
+ if (kvm->arch.exit_on_emulation_error && insn_size > 0) {
+ vcpu->run->emulation_failure.ndata = 3;
+ vcpu->run->emulation_failure.flags =
+ KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES;
+ vcpu->run->emulation_failure.insn_size = insn_size;
+ memcpy(vcpu->run->emulation_failure.insn_bytes,
+ ctxt->fetch.data, sizeof(ctxt->fetch.data));
+ }
+}
+
static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type)
{
+ struct kvm *kvm = vcpu->kvm;
+
++vcpu->stat.insn_emulation_fail;
trace_kvm_emulate_insn_failed(vcpu);
@@ -7129,10 +7155,9 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type)
return 1;
}
- if (emulation_type & EMULTYPE_SKIP) {
- vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
- vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
- vcpu->run->internal.ndata = 0;
+ if (kvm->arch.exit_on_emulation_error ||
+ (emulation_type & EMULTYPE_SKIP)) {
+ prepare_emulation_failure_exit(vcpu);
return 0;
}
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index f6afee209620..7c77099235b2 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -279,6 +279,17 @@ struct kvm_xen_exit {
/* Encounter unexpected vm-exit reason */
#define KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON 4
+/*
+ * When using the suberror KVM_INTERNAL_ERROR_EMULATION, these flags are used
+ * to describe what is contained in the exit struct. The flags are used to
+ * describe it's contents, and the contents should be in ascending numerical
+ * order of the flag values. For example, if the flag
+ * KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES is set, the instruction
+ * length and instruction bytes would be expected to show up first because this
+ * flag has the lowest numerical value (1) of all the other flags.
+ */
+#define KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES (1ULL << 0)
+
/* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */
struct kvm_run {
/* in */
@@ -382,6 +393,14 @@ struct kvm_run {
__u32 ndata;
__u64 data[16];
} internal;
+ /* KVM_EXIT_INTERNAL_ERROR, too (not 2) */
+ struct {
+ __u32 suberror;
+ __u32 ndata;
+ __u64 flags;
+ __u8 insn_size;
+ __u8 insn_bytes[15];
+ } emulation_failure;
/* KVM_EXIT_OSI */
struct {
__u64 gprs[32];
@@ -1078,6 +1097,7 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_DIRTY_LOG_RING 192
#define KVM_CAP_X86_BUS_LOCK_EXIT 193
#define KVM_CAP_PPC_DAWR1 194
+#define KVM_CAP_EXIT_ON_EMULATION_FAILURE 195
#ifdef KVM_CAP_IRQ_ROUTING
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index f6afee209620..7c77099235b2 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -279,6 +279,17 @@ struct kvm_xen_exit {
/* Encounter unexpected vm-exit reason */
#define KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON 4
+/*
+ * When using the suberror KVM_INTERNAL_ERROR_EMULATION, these flags are used
+ * to describe what is contained in the exit struct. The flags are used to
+ * describe it's contents, and the contents should be in ascending numerical
+ * order of the flag values. For example, if the flag
+ * KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES is set, the instruction
+ * length and instruction bytes would be expected to show up first because this
+ * flag has the lowest numerical value (1) of all the other flags.
+ */
+#define KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES (1ULL << 0)
+
/* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */
struct kvm_run {
/* in */
@@ -382,6 +393,14 @@ struct kvm_run {
__u32 ndata;
__u64 data[16];
} internal;
+ /* KVM_EXIT_INTERNAL_ERROR, too (not 2) */
+ struct {
+ __u32 suberror;
+ __u32 ndata;
+ __u64 flags;
+ __u8 insn_size;
+ __u8 insn_bytes[15];
+ } emulation_failure;
/* KVM_EXIT_OSI */
struct {
__u64 gprs[32];
@@ -1078,6 +1097,7 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_DIRTY_LOG_RING 192
#define KVM_CAP_X86_BUS_LOCK_EXIT 193
#define KVM_CAP_PPC_DAWR1 194
+#define KVM_CAP_EXIT_ON_EMULATION_FAILURE 195
#ifdef KVM_CAP_IRQ_ROUTING
--
2.31.1.368.gbe11c130af-goog
