[PATCH v3 1/2] kvm: x86: Allow userspace to handle emulation errors

[PATCH v3 1/2] kvm: x86: Allow userspace to handle emulation errors

[Aaron Lewis]

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@google.com>
---
 Documentation/virt/kvm/api.rst  | 18 +++++++++++++++++
 arch/x86/include/asm/kvm_host.h |  6 ++++++
 arch/x86/kvm/x86.c              | 35 +++++++++++++++++++++++++++++----
 include/uapi/linux/kvm.h        | 23 ++++++++++++++++++++++
 tools/include/uapi/linux/kvm.h  | 23 ++++++++++++++++++++++
 5 files changed, 101 insertions(+), 4 deletions(-)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 307f2fcf1b02..6ae57fdf3a56 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6233,6 +6233,24 @@ 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
+
+When this capability is enabled the in-kernel instruction emulator packs
+the exit struct of KVM_INTERNAL_ERROR with the instrution length and
+instruction bytes when an error occurs while emulating an instruction.  This
+will also happen when the emulation type is set to EMULTYPE_SKIP, but with this
+capability enabled this becomes the default behavior regarless of how the
+emulation type is set unless it is a VMware #GP; in that case a #GP is injected
+and KVM does not exit to userspace.
+
+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..c0d4f077d3fc 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 +7124,31 @@ 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_run *run = vcpu->run;
+
+	run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+	run->emulation_failure.suberror = KVM_INTERNAL_ERROR_EMULATION;
+	run->emulation_failure.ndata = 0;
+	run->emulation_failure.flags = 0;
+
+	if (insn_size) {
+		run->emulation_failure.ndata = 3;
+		run->emulation_failure.flags |=
+			KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES;
+		run->emulation_failure.insn_size = insn_size;
+		memcpy(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 +7157,9 @@ 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..87009222c20c 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -279,6 +279,9 @@ struct kvm_xen_exit {
 /* Encounter unexpected vm-exit reason */
 #define KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON	4
 
+/* Flags that describe what fields in emulation_failure hold valid data. */
+#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 +385,25 @@ struct kvm_run {
 			__u32 ndata;
 			__u64 data[16];
 		} internal;
+		/*
+		 * KVM_INTERNAL_ERROR_EMULATION
+		 *
+		 * "struct emulation_failure" is an overlay of "struct internal"
+		 * that is used for the KVM_INTERNAL_ERROR_EMULATION sub-type of
+		 * KVM_EXIT_INTERNAL_ERROR.  Note, unlike other internal error
+		 * sub-types, this struct is ABI!  It also needs to be backwards
+		 * compabile with "struct internal".  Take special care that
+		 * "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).
+		 */
+		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 +1100,7 @@ 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..87009222c20c 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -279,6 +279,9 @@ struct kvm_xen_exit {
 /* Encounter unexpected vm-exit reason */
 #define KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON	4
 
+/* Flags that describe what fields in emulation_failure hold valid data. */
+#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 +385,25 @@ struct kvm_run {
 			__u32 ndata;
 			__u64 data[16];
 		} internal;
+		/*
+		 * KVM_INTERNAL_ERROR_EMULATION
+		 *
+		 * "struct emulation_failure" is an overlay of "struct internal"
+		 * that is used for the KVM_INTERNAL_ERROR_EMULATION sub-type of
+		 * KVM_EXIT_INTERNAL_ERROR.  Note, unlike other internal error
+		 * sub-types, this struct is ABI!  It also needs to be backwards
+		 * compabile with "struct internal".  Take special care that
+		 * "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).
+		 */
+		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 +1100,7 @@ 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
 
-- 
2.31.1.498.g6c1eba8ee3d-goog

[PATCH v3 2/2] selftests: kvm: Allows userspace to handle emulation errors.

[Aaron Lewis]

This test exercises the feature KVM_CAP_EXIT_ON_EMULATION_FAILURE.  When
enabled, errors in the in-kernel instruction emulator are forwarded to
userspace with the instruction bytes stored in the exit struct for
KVM_EXIT_INTERNAL_ERROR.  So, when the guest attempts to emulate an
'flds' instruction, which isn't able to be emulated in KVM, instead
of failing, KVM sends the instruction to userspace to handle.

For this test to work properly the module parameter
'allow_smaller_maxphyaddr' has to be set.

Signed-off-by: Aaron Lewis <aaronlewis@google.com>
---
 tools/testing/selftests/kvm/.gitignore        |   1 +
 tools/testing/selftests/kvm/Makefile          |   1 +
 .../selftests/kvm/include/x86_64/processor.h  |   3 +
 .../selftests/kvm/lib/x86_64/processor.c      |  58 +++++
 .../kvm/x86_64/emulator_error_test.c          | 209 ++++++++++++++++++
 5 files changed, 272 insertions(+)
 create mode 100644 tools/testing/selftests/kvm/x86_64/emulator_error_test.c

diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 7bd7e776c266..ec9e20a2f752 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -7,6 +7,7 @@
 /x86_64/cr4_cpuid_sync_test
 /x86_64/debug_regs
 /x86_64/evmcs_test
+/x86_64/emulator_error_test
 /x86_64/get_cpuid_test
 /x86_64/get_msr_index_features
 /x86_64/kvm_pv_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 67eebb53235f..5ff705d92d02 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -41,6 +41,7 @@ LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_ha
 TEST_GEN_PROGS_x86_64 = x86_64/cr4_cpuid_sync_test
 TEST_GEN_PROGS_x86_64 += x86_64/get_msr_index_features
 TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test
+TEST_GEN_PROGS_x86_64 += x86_64/emulator_error_test
 TEST_GEN_PROGS_x86_64 += x86_64/get_cpuid_test
 TEST_GEN_PROGS_x86_64 += x86_64/hyperv_clock
 TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index 0b30b4e15c38..40f70f91e6a2 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -394,6 +394,9 @@ void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid);
 void vm_handle_exception(struct kvm_vm *vm, int vector,
 			void (*handler)(struct ex_regs *));
 
+uint64_t vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr);
+void vm_set_page_table_entry(struct kvm_vm *vm, uint64_t vaddr, uint64_t mask);
+
 /*
  * set_cpuid() - overwrites a matching cpuid entry with the provided value.
  *		 matches based on ent->function && ent->index. returns true
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index a8906e60a108..1aa4fc5e84c6 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -292,6 +292,64 @@ void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 	pte[index[0]].present = 1;
 }
 
+static struct pageTableEntry *_vm_get_page_table_entry(struct kvm_vm *vm,
+						       uint64_t vaddr)
+{
+	uint16_t index[4];
+	struct pageMapL4Entry *pml4e;
+	struct pageDirectoryPointerEntry *pdpe;
+	struct pageDirectoryEntry *pde;
+	struct pageTableEntry *pte;
+
+	TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
+		"unknown or unsupported guest mode, mode: 0x%x", vm->mode);
+	TEST_ASSERT((vaddr % vm->page_size) == 0,
+		"Virtual address not on page boundary,\n"
+		"  vaddr: 0x%lx vm->page_size: 0x%x",
+		vaddr, vm->page_size);
+	TEST_ASSERT(sparsebit_is_set(vm->vpages_valid,
+		(vaddr >> vm->page_shift)),
+		"Invalid virtual address, vaddr: 0x%lx",
+		vaddr);
+
+	index[0] = (vaddr >> 12) & 0x1ffu;
+	index[1] = (vaddr >> 21) & 0x1ffu;
+	index[2] = (vaddr >> 30) & 0x1ffu;
+	index[3] = (vaddr >> 39) & 0x1ffu;
+
+	pml4e = addr_gpa2hva(vm, vm->pgd);
+	TEST_ASSERT(pml4e[index[3]].present,
+		"Expected pml4e to be present for gva: 0x%08lx", vaddr);
+
+	pdpe = addr_gpa2hva(vm, pml4e[index[3]].address * vm->page_size);
+	TEST_ASSERT(pdpe[index[2]].present,
+		"Expected pdpe to be present for gva: 0x%08lx", vaddr);
+
+	pde = addr_gpa2hva(vm, pdpe[index[2]].address * vm->page_size);
+	TEST_ASSERT(pde[index[1]].present,
+		"Expected pde to be present for gva: 0x%08lx", vaddr);
+
+	pte = addr_gpa2hva(vm, pde[index[1]].address * vm->page_size);
+	TEST_ASSERT(pte[index[0]].present,
+		"Expected pte to be present for gva: 0x%08lx", vaddr);
+
+	return &pte[index[0]];
+}
+
+uint64_t vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr)
+{
+	struct pageTableEntry *pte = _vm_get_page_table_entry(vm, vaddr);
+
+	return *(uint64_t *)pte;
+}
+
+void vm_set_page_table_entry(struct kvm_vm *vm, uint64_t vaddr, uint64_t mask)
+{
+	struct pageTableEntry *pte = _vm_get_page_table_entry(vm, vaddr);
+
+	*(uint64_t *)pte |= mask;
+}
+
 void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
 {
 	struct pageMapL4Entry *pml4e, *pml4e_start;
diff --git a/tools/testing/selftests/kvm/x86_64/emulator_error_test.c b/tools/testing/selftests/kvm/x86_64/emulator_error_test.c
new file mode 100644
index 000000000000..825da57ad791
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/emulator_error_test.c
@@ -0,0 +1,209 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020, Google LLC.
+ *
+ * Tests for KVM_CAP_EXIT_ON_EMULATION_FAILURE capability.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_short_name */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "vmx.h"
+
+#define VCPU_ID	   1
+#define PAGE_SIZE  4096
+#define MAXPHYADDR 36
+
+#define MEM_REGION_GVA	0x0000123456789000
+#define MEM_REGION_GPA	0x0000000700000000
+#define MEM_REGION_SLOT	10
+#define MEM_REGION_SIZE PAGE_SIZE
+
+extern char fld_start, fld_end;
+
+static void guest_code(void)
+{
+	__asm__ __volatile__("fld_start: flds (%[addr]); fld_end:"
+			     :: [addr]"r"(MEM_REGION_GVA));
+
+	GUEST_DONE();
+}
+
+static void run_guest(struct kvm_vm *vm)
+{
+	int rc;
+
+	rc = _vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(rc == 0, "vcpu_run failed: %d\n", rc);
+}
+
+/*
+ * Accessors to get R/M, REG, and Mod bits described in the SDM vol 2,
+ * figure 2-2 "Table Interpretation of ModR/M Byte (C8H)".
+ */
+#define GET_RM(insn_byte) (insn_byte & 0x7)
+#define GET_REG(insn_byte) ((insn_byte & 0x38) >> 3)
+#define GET_MOD(insn_byte) ((insn_byte & 0xc) >> 6)
+
+bool is_flds(uint8_t *insn_bytes, uint8_t insn_size)
+{
+	return insn_size >= 2 &&
+	       insn_bytes[0] == 0xd9 &&
+	       GET_REG(insn_bytes[1]) == 0x0;
+}
+
+static void process_exit_on_emulation_error(struct kvm_vm *vm)
+{
+	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+	struct kvm_regs regs;
+	uint8_t *insn_bytes;
+	uint8_t insn_size;
+	uint64_t flags;
+
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_INTERNAL_ERROR,
+		    "Unexpected exit reason: %u (%s)",
+		    run->exit_reason,
+		    exit_reason_str(run->exit_reason));
+
+	TEST_ASSERT(run->emulation_failure.suberror == KVM_INTERNAL_ERROR_EMULATION,
+		    "Unexpected suberror: %u",
+		    run->emulation_failure.suberror);
+
+	if (run->emulation_failure.ndata >= 1) {
+		flags = run->emulation_failure.flags;
+		if ((flags & KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES) &&
+		    run->emulation_failure.ndata >= 3) {
+			insn_size = run->emulation_failure.insn_size;
+			insn_bytes = run->emulation_failure.insn_bytes;
+
+			TEST_ASSERT(insn_size <= 15 && insn_size > 0,
+				    "Unexpected instruction size: %u",
+				    insn_size);
+
+			TEST_ASSERT(is_flds(insn_bytes, insn_size),
+				    "Unexpected instruction.  Expected 'flds' (0xd9 /0), encountered (0x%x /%u)",
+				    insn_bytes[0], (insn_size >= 2) ? GET_REG(insn_bytes[1]) : 0);
+
+			vcpu_regs_get(vm, VCPU_ID, &regs);
+			regs.rip += (uintptr_t)(&fld_end) - (uintptr_t)(&fld_start);
+			vcpu_regs_set(vm, VCPU_ID, &regs);
+		}
+	}
+}
+
+static void do_guest_assert(struct kvm_vm *vm, struct ucall *uc)
+{
+	TEST_FAIL("%s at %s:%ld", (const char *)uc->args[0], __FILE__,
+		  uc->args[1]);
+}
+
+static void check_for_guest_assert(struct kvm_vm *vm)
+{
+	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+	struct ucall uc;
+
+	if (run->exit_reason == KVM_EXIT_IO &&
+	    get_ucall(vm, VCPU_ID, &uc) == UCALL_ABORT) {
+		do_guest_assert(vm, &uc);
+	}
+}
+
+static void process_ucall_done(struct kvm_vm *vm)
+{
+	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+	struct ucall uc;
+
+	check_for_guest_assert(vm);
+
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+		    "Unexpected exit reason: %u (%s)",
+		    run->exit_reason,
+		    exit_reason_str(run->exit_reason));
+
+	TEST_ASSERT(get_ucall(vm, VCPU_ID, &uc) == UCALL_DONE,
+		    "Unexpected ucall command: %lu, expected UCALL_DONE (%d)",
+		    uc.cmd, UCALL_DONE);
+}
+
+static uint64_t process_ucall(struct kvm_vm *vm)
+{
+	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+	struct ucall uc;
+
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+		    "Unexpected exit reason: %u (%s)",
+		    run->exit_reason,
+		    exit_reason_str(run->exit_reason));
+
+	switch (get_ucall(vm, VCPU_ID, &uc)) {
+	case UCALL_SYNC:
+		break;
+	case UCALL_ABORT:
+		do_guest_assert(vm, &uc);
+		break;
+	case UCALL_DONE:
+		process_ucall_done(vm);
+		break;
+	default:
+		TEST_ASSERT(false, "Unexpected ucall");
+	}
+
+	return uc.cmd;
+}
+
+int main(int argc, char *argv[])
+{
+	struct kvm_enable_cap emul_failure_cap = {
+		.cap = KVM_CAP_EXIT_ON_EMULATION_FAILURE,
+		.args[0] = 1,
+	};
+	struct kvm_cpuid_entry2 *entry;
+	struct kvm_cpuid2 *cpuid;
+	struct kvm_vm *vm;
+	uint64_t *hva;
+	uint64_t gpa;
+	int rc;
+
+	/* Tell stdout not to buffer its content */
+	setbuf(stdout, NULL);
+
+	vm = vm_create_default(VCPU_ID, 0, guest_code);
+
+	cpuid = kvm_get_supported_cpuid();
+
+	entry = kvm_get_supported_cpuid_index(0x80000008, 0);
+	if (entry) {
+		entry->eax = (entry->eax & 0xffffff00) | MAXPHYADDR;
+		set_cpuid(cpuid, entry);
+	}
+
+	vcpu_set_cpuid(vm, VCPU_ID, cpuid);
+
+	entry = kvm_get_supported_cpuid_index(0x80000008, 0);
+
+	rc = kvm_check_cap(KVM_CAP_EXIT_ON_EMULATION_FAILURE);
+	TEST_ASSERT(rc, "KVM_CAP_EXIT_ON_EMULATION_FAILURE is unavailable");
+	vm_enable_cap(vm, &emul_failure_cap);
+
+	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+				    MEM_REGION_GPA, MEM_REGION_SLOT,
+				    MEM_REGION_SIZE / PAGE_SIZE, 0);
+	gpa = vm_phy_pages_alloc(vm, MEM_REGION_SIZE / PAGE_SIZE,
+				 MEM_REGION_GPA, MEM_REGION_SLOT);
+	TEST_ASSERT(gpa == MEM_REGION_GPA, "Failed vm_phy_pages_alloc\n");
+	virt_map(vm, MEM_REGION_GVA, MEM_REGION_GPA, 1, 0);
+	hva = addr_gpa2hva(vm, MEM_REGION_GPA);
+	memset(hva, 0, PAGE_SIZE);
+	vm_set_page_table_entry(vm, MEM_REGION_GVA, 1ull << 36);
+
+	run_guest(vm);
+	process_exit_on_emulation_error(vm);
+	run_guest(vm);
+
+	TEST_ASSERT(process_ucall(vm) == UCALL_DONE, "Expected UCALL_DONE");
+
+	kvm_vm_free(vm);
+
+	return 0;
+}
-- 
2.31.1.498.g6c1eba8ee3d-goog

Re: [PATCH v3 1/2] kvm: x86: Allow userspace to handle emulation errors

[Sean Christopherson]

Please wait at least a day between versions to give everyone a chance to review
the latest information and digest other folks' comments.  Even a single day is
a bit too frequent in most cases, especially for a series where people are
actively commenting on the changes, as is the case here.  I.e. give the current
conversation a chance to run its course before spawning a new thread.  Exceptions
are few and far between, e.g. if you completely botched something and there's no
point in having people review the current versions.

Also, please include a cover letter with a synopsis of the delta between versions.
Without that, reviewers have no idea what's different in v1 vs. v2 vs. v3 vs. vN,
which increases the burden on reviewers.  The delta information is especially
helpful if other reviewers join the conversation at a later point.

On Wed, Apr 21, 2021, Aaron Lewis wrote:
> 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@google.com>

Re: [PATCH v3 2/2] selftests: kvm: Allows userspace to handle emulation errors.

[Jim Mattson]

On Wed, Apr 21, 2021 at 9:23 AM Aaron Lewis <aaronlewis@google.com> wrote:
>
> This test exercises the feature KVM_CAP_EXIT_ON_EMULATION_FAILURE.  When
> enabled, errors in the in-kernel instruction emulator are forwarded to
> userspace with the instruction bytes stored in the exit struct for
> KVM_EXIT_INTERNAL_ERROR.  So, when the guest attempts to emulate an
> 'flds' instruction, which isn't able to be emulated in KVM, instead
> of failing, KVM sends the instruction to userspace to handle.
>
> For this test to work properly the module parameter
> 'allow_smaller_maxphyaddr' has to be set.

Can you at least test for this?

> Signed-off-by: Aaron Lewis <aaronlewis@google.com>
> ---
>  tools/testing/selftests/kvm/.gitignore        |   1 +
>  tools/testing/selftests/kvm/Makefile          |   1 +
>  .../selftests/kvm/include/x86_64/processor.h  |   3 +
>  .../selftests/kvm/lib/x86_64/processor.c      |  58 +++++
>  .../kvm/x86_64/emulator_error_test.c          | 209 ++++++++++++++++++
>  5 files changed, 272 insertions(+)
>  create mode 100644 tools/testing/selftests/kvm/x86_64/emulator_error_test.c
>
> diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
> index 7bd7e776c266..ec9e20a2f752 100644
> --- a/tools/testing/selftests/kvm/.gitignore
> +++ b/tools/testing/selftests/kvm/.gitignore
> @@ -7,6 +7,7 @@
>  /x86_64/cr4_cpuid_sync_test
>  /x86_64/debug_regs
>  /x86_64/evmcs_test
> +/x86_64/emulator_error_test
>  /x86_64/get_cpuid_test
>  /x86_64/get_msr_index_features
>  /x86_64/kvm_pv_test
> diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
> index 67eebb53235f..5ff705d92d02 100644
> --- a/tools/testing/selftests/kvm/Makefile
> +++ b/tools/testing/selftests/kvm/Makefile
> @@ -41,6 +41,7 @@ LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_ha
>  TEST_GEN_PROGS_x86_64 = x86_64/cr4_cpuid_sync_test
>  TEST_GEN_PROGS_x86_64 += x86_64/get_msr_index_features
>  TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test
> +TEST_GEN_PROGS_x86_64 += x86_64/emulator_error_test
>  TEST_GEN_PROGS_x86_64 += x86_64/get_cpuid_test
>  TEST_GEN_PROGS_x86_64 += x86_64/hyperv_clock
>  TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid
> diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
> index 0b30b4e15c38..40f70f91e6a2 100644
> --- a/tools/testing/selftests/kvm/include/x86_64/processor.h
> +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
> @@ -394,6 +394,9 @@ void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid);
>  void vm_handle_exception(struct kvm_vm *vm, int vector,
>                         void (*handler)(struct ex_regs *));
>
> +uint64_t vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr);
> +void vm_set_page_table_entry(struct kvm_vm *vm, uint64_t vaddr, uint64_t mask);
> +
>  /*
>   * set_cpuid() - overwrites a matching cpuid entry with the provided value.
>   *              matches based on ent->function && ent->index. returns true
> diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
> index a8906e60a108..1aa4fc5e84c6 100644
> --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
> +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
> @@ -292,6 +292,64 @@ void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
>         pte[index[0]].present = 1;
>  }
>
> +static struct pageTableEntry *_vm_get_page_table_entry(struct kvm_vm *vm,
> +                                                      uint64_t vaddr)
> +{
> +       uint16_t index[4];
> +       struct pageMapL4Entry *pml4e;
> +       struct pageDirectoryPointerEntry *pdpe;
> +       struct pageDirectoryEntry *pde;
> +       struct pageTableEntry *pte;
> +
> +       TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
> +               "unknown or unsupported guest mode, mode: 0x%x", vm->mode);
> +       TEST_ASSERT((vaddr % vm->page_size) == 0,
> +               "Virtual address not on page boundary,\n"
> +               "  vaddr: 0x%lx vm->page_size: 0x%x",
> +               vaddr, vm->page_size);

Why not allow the caller to query the PTE for *any* (valid) virtual address?
Speaking of valid virtual addresses, should there be a canonical check here?

> +       TEST_ASSERT(sparsebit_is_set(vm->vpages_valid,
> +               (vaddr >> vm->page_shift)),
> +               "Invalid virtual address, vaddr: 0x%lx",
> +               vaddr);
> +
> +       index[0] = (vaddr >> 12) & 0x1ffu;
> +       index[1] = (vaddr >> 21) & 0x1ffu;
> +       index[2] = (vaddr >> 30) & 0x1ffu;
> +       index[3] = (vaddr >> 39) & 0x1ffu;
> +
> +       pml4e = addr_gpa2hva(vm, vm->pgd);
> +       TEST_ASSERT(pml4e[index[3]].present,
> +               "Expected pml4e to be present for gva: 0x%08lx", vaddr);

Should we verify that no reserved bits are set before continuing the walk?

> +       pdpe = addr_gpa2hva(vm, pml4e[index[3]].address * vm->page_size);
> +       TEST_ASSERT(pdpe[index[2]].present,
> +               "Expected pdpe to be present for gva: 0x%08lx", vaddr);

Should we verify that no reserved bits are set (and that the superpage
bit is clear) before continuing the walk?

> +       pde = addr_gpa2hva(vm, pdpe[index[2]].address * vm->page_size);
> +       TEST_ASSERT(pde[index[1]].present,
> +               "Expected pde to be present for gva: 0x%08lx", vaddr);

Should we verify that no reserved bits are set (and that the superpage
bit is clear) before continuing the walk?

> +       pte = addr_gpa2hva(vm, pde[index[1]].address * vm->page_size);
> +       TEST_ASSERT(pte[index[0]].present,
> +               "Expected pte to be present for gva: 0x%08lx", vaddr);

As long as we're checking for present before returning the PTE
pointer, should we also check for reserved bits?

> +       return &pte[index[0]];
> +}
> +
> +uint64_t vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr)
> +{
> +       struct pageTableEntry *pte = _vm_get_page_table_entry(vm, vaddr);
> +
> +       return *(uint64_t *)pte;
> +}
> +
> +void vm_set_page_table_entry(struct kvm_vm *vm, uint64_t vaddr, uint64_t mask)
> +{
> +       struct pageTableEntry *pte = _vm_get_page_table_entry(vm, vaddr);
> +
> +       *(uint64_t *)pte |= mask;
> +}

I'm not sure this is the best API. What if we want to clear bits, or
change the PFN? Why not have the caller construct the desired PTE and
pass that in?

>  void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
>  {
>         struct pageMapL4Entry *pml4e, *pml4e_start;
> diff --git a/tools/testing/selftests/kvm/x86_64/emulator_error_test.c b/tools/testing/selftests/kvm/x86_64/emulator_error_test.c
> new file mode 100644
> index 000000000000..825da57ad791
> --- /dev/null
> +++ b/tools/testing/selftests/kvm/x86_64/emulator_error_test.c
> @@ -0,0 +1,209 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/*
> + * Copyright (C) 2020, Google LLC.
> + *
> + * Tests for KVM_CAP_EXIT_ON_EMULATION_FAILURE capability.
> + */
> +
> +#define _GNU_SOURCE /* for program_invocation_short_name */
> +
> +#include "test_util.h"
> +#include "kvm_util.h"
> +#include "vmx.h"
> +
> +#define VCPU_ID           1
> +#define PAGE_SIZE  4096
> +#define MAXPHYADDR 36
> +
> +#define MEM_REGION_GVA 0x0000123456789000
> +#define MEM_REGION_GPA 0x0000000700000000
> +#define MEM_REGION_SLOT        10
> +#define MEM_REGION_SIZE PAGE_SIZE
> +
> +extern char fld_start, fld_end;
> +
> +static void guest_code(void)
> +{
> +       __asm__ __volatile__("fld_start: flds (%[addr]); fld_end:"
> +                            :: [addr]"r"(MEM_REGION_GVA));
> +
> +       GUEST_DONE();
> +}
> +
> +static void run_guest(struct kvm_vm *vm)
> +{
> +       int rc;
> +
> +       rc = _vcpu_run(vm, VCPU_ID);
> +       TEST_ASSERT(rc == 0, "vcpu_run failed: %d\n", rc);
> +}
> +
> +/*
> + * Accessors to get R/M, REG, and Mod bits described in the SDM vol 2,
> + * figure 2-2 "Table Interpretation of ModR/M Byte (C8H)".
> + */
> +#define GET_RM(insn_byte) (insn_byte & 0x7)
> +#define GET_REG(insn_byte) ((insn_byte & 0x38) >> 3)
> +#define GET_MOD(insn_byte) ((insn_byte & 0xc) >> 6)
> +
> +bool is_flds(uint8_t *insn_bytes, uint8_t insn_size)
> +{
> +       return insn_size >= 2 &&
> +              insn_bytes[0] == 0xd9 &&
> +              GET_REG(insn_bytes[1]) == 0x0;
> +}
> +
> +static void process_exit_on_emulation_error(struct kvm_vm *vm)
> +{
> +       struct kvm_run *run = vcpu_state(vm, VCPU_ID);
> +       struct kvm_regs regs;
> +       uint8_t *insn_bytes;
> +       uint8_t insn_size;
> +       uint64_t flags;
> +
> +       TEST_ASSERT(run->exit_reason == KVM_EXIT_INTERNAL_ERROR,
> +                   "Unexpected exit reason: %u (%s)",
> +                   run->exit_reason,
> +                   exit_reason_str(run->exit_reason));
> +
> +       TEST_ASSERT(run->emulation_failure.suberror == KVM_INTERNAL_ERROR_EMULATION,
> +                   "Unexpected suberror: %u",
> +                   run->emulation_failure.suberror);
> +
> +       if (run->emulation_failure.ndata >= 1) {
> +               flags = run->emulation_failure.flags;
> +               if ((flags & KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES) &&
> +                   run->emulation_failure.ndata >= 3) {
> +                       insn_size = run->emulation_failure.insn_size;
> +                       insn_bytes = run->emulation_failure.insn_bytes;
> +
> +                       TEST_ASSERT(insn_size <= 15 && insn_size > 0,
> +                                   "Unexpected instruction size: %u",
> +                                   insn_size);
> +
> +                       TEST_ASSERT(is_flds(insn_bytes, insn_size),
> +                                   "Unexpected instruction.  Expected 'flds' (0xd9 /0), encountered (0x%x /%u)",
> +                                   insn_bytes[0], (insn_size >= 2) ? GET_REG(insn_bytes[1]) : 0);

If you don't get 'flds', you shouldn't assume that the second byte is
the modr/m byte. Even if it is, the reg field may not be part of the
opcode.

> +                       vcpu_regs_get(vm, VCPU_ID, &regs);
> +                       regs.rip += (uintptr_t)(&fld_end) - (uintptr_t)(&fld_start);

A general purpose hypervisor wouldn't normally have access to these
labels, so you should really determine the length of the instruction
by decoding, *and* ensure that kvm gave you sufficient instruction
bytes. For instance, if the addressing mode involves a SIB byte and a
32-bit displacement, you would need kvm to give you at least 7 bytes.
Speaking of sufficient bytes, it would be nice to see your test
exercise the case where kvm's in-kernel emulator can't actually fetch
the full 15 bytes.

Can you comment on what else would have to be done to actually emulate
this instruction in userspace?

> +                       vcpu_regs_set(vm, VCPU_ID, &regs);
> +               }
> +       }
> +}
> +
> +static void do_guest_assert(struct kvm_vm *vm, struct ucall *uc)
> +{
> +       TEST_FAIL("%s at %s:%ld", (const char *)uc->args[0], __FILE__,
> +                 uc->args[1]);
> +}
> +
> +static void check_for_guest_assert(struct kvm_vm *vm)
> +{
> +       struct kvm_run *run = vcpu_state(vm, VCPU_ID);
> +       struct ucall uc;
> +
> +       if (run->exit_reason == KVM_EXIT_IO &&
> +           get_ucall(vm, VCPU_ID, &uc) == UCALL_ABORT) {
> +               do_guest_assert(vm, &uc);
> +       }
> +}
> +
> +static void process_ucall_done(struct kvm_vm *vm)
> +{
> +       struct kvm_run *run = vcpu_state(vm, VCPU_ID);
> +       struct ucall uc;
> +
> +       check_for_guest_assert(vm);
> +
> +       TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
> +                   "Unexpected exit reason: %u (%s)",
> +                   run->exit_reason,
> +                   exit_reason_str(run->exit_reason));
> +
> +       TEST_ASSERT(get_ucall(vm, VCPU_ID, &uc) == UCALL_DONE,
> +                   "Unexpected ucall command: %lu, expected UCALL_DONE (%d)",
> +                   uc.cmd, UCALL_DONE);
> +}
> +
> +static uint64_t process_ucall(struct kvm_vm *vm)
> +{
> +       struct kvm_run *run = vcpu_state(vm, VCPU_ID);
> +       struct ucall uc;
> +
> +       TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
> +                   "Unexpected exit reason: %u (%s)",
> +                   run->exit_reason,
> +                   exit_reason_str(run->exit_reason));
> +
> +       switch (get_ucall(vm, VCPU_ID, &uc)) {
> +       case UCALL_SYNC:
> +               break;
> +       case UCALL_ABORT:
> +               do_guest_assert(vm, &uc);
> +               break;
> +       case UCALL_DONE:
> +               process_ucall_done(vm);
> +               break;
> +       default:
> +               TEST_ASSERT(false, "Unexpected ucall");
> +       }
> +
> +       return uc.cmd;
> +}
> +
> +int main(int argc, char *argv[])
> +{
> +       struct kvm_enable_cap emul_failure_cap = {
> +               .cap = KVM_CAP_EXIT_ON_EMULATION_FAILURE,
> +               .args[0] = 1,
> +       };
> +       struct kvm_cpuid_entry2 *entry;
> +       struct kvm_cpuid2 *cpuid;
> +       struct kvm_vm *vm;
> +       uint64_t *hva;
> +       uint64_t gpa;
> +       int rc;
> +
> +       /* Tell stdout not to buffer its content */
> +       setbuf(stdout, NULL);
> +
> +       vm = vm_create_default(VCPU_ID, 0, guest_code);
> +
> +       cpuid = kvm_get_supported_cpuid();
> +
> +       entry = kvm_get_supported_cpuid_index(0x80000008, 0);
> +       if (entry) {
> +               entry->eax = (entry->eax & 0xffffff00) | MAXPHYADDR;
> +               set_cpuid(cpuid, entry);
> +       }
> +
> +       vcpu_set_cpuid(vm, VCPU_ID, cpuid);
> +
> +       entry = kvm_get_supported_cpuid_index(0x80000008, 0);
> +
> +       rc = kvm_check_cap(KVM_CAP_EXIT_ON_EMULATION_FAILURE);
> +       TEST_ASSERT(rc, "KVM_CAP_EXIT_ON_EMULATION_FAILURE is unavailable");
> +       vm_enable_cap(vm, &emul_failure_cap);
> +
> +       vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
> +                                   MEM_REGION_GPA, MEM_REGION_SLOT,
> +                                   MEM_REGION_SIZE / PAGE_SIZE, 0);
> +       gpa = vm_phy_pages_alloc(vm, MEM_REGION_SIZE / PAGE_SIZE,
> +                                MEM_REGION_GPA, MEM_REGION_SLOT);
> +       TEST_ASSERT(gpa == MEM_REGION_GPA, "Failed vm_phy_pages_alloc\n");
> +       virt_map(vm, MEM_REGION_GVA, MEM_REGION_GPA, 1, 0);
> +       hva = addr_gpa2hva(vm, MEM_REGION_GPA);
> +       memset(hva, 0, PAGE_SIZE);
> +       vm_set_page_table_entry(vm, MEM_REGION_GVA, 1ull << 36);
> +
> +       run_guest(vm);
> +       process_exit_on_emulation_error(vm);
> +       run_guest(vm);
> +
> +       TEST_ASSERT(process_ucall(vm) == UCALL_DONE, "Expected UCALL_DONE");
> +
> +       kvm_vm_free(vm);
> +
> +       return 0;
> +}
> --
> 2.31.1.498.g6c1eba8ee3d-goog
>

Re: [PATCH v3 2/2] selftests: kvm: Allows userspace to handle emulation errors.

[Aaron Lewis]

> > +static void process_exit_on_emulation_error(struct kvm_vm *vm)
> > +{
> > +       struct kvm_run *run = vcpu_state(vm, VCPU_ID);
> > +       struct kvm_regs regs;
> > +       uint8_t *insn_bytes;
> > +       uint8_t insn_size;
> > +       uint64_t flags;
> > +
> > +       TEST_ASSERT(run->exit_reason == KVM_EXIT_INTERNAL_ERROR,
> > +                   "Unexpected exit reason: %u (%s)",
> > +                   run->exit_reason,
> > +                   exit_reason_str(run->exit_reason));
> > +
> > +       TEST_ASSERT(run->emulation_failure.suberror == KVM_INTERNAL_ERROR_EMULATION,
> > +                   "Unexpected suberror: %u",
> > +                   run->emulation_failure.suberror);
> > +
> > +       if (run->emulation_failure.ndata >= 1) {
> > +               flags = run->emulation_failure.flags;
> > +               if ((flags & KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES) &&
> > +                   run->emulation_failure.ndata >= 3) {
> > +                       insn_size = run->emulation_failure.insn_size;
> > +                       insn_bytes = run->emulation_failure.insn_bytes;
> > +
> > +                       TEST_ASSERT(insn_size <= 15 && insn_size > 0,
> > +                                   "Unexpected instruction size: %u",
> > +                                   insn_size);
> > +
> > +                       TEST_ASSERT(is_flds(insn_bytes, insn_size),
> > +                                   "Unexpected instruction.  Expected 'flds' (0xd9 /0), encountered (0x%x /%u)",
> > +                                   insn_bytes[0], (insn_size >= 2) ? GET_REG(insn_bytes[1]) : 0);
>
> If you don't get 'flds', you shouldn't assume that the second byte is
> the modr/m byte. Even if it is, the reg field may not be part of the
> opcode.
>
> > +                       vcpu_regs_get(vm, VCPU_ID, &regs);
> > +                       regs.rip += (uintptr_t)(&fld_end) - (uintptr_t)(&fld_start);
>
> A general purpose hypervisor wouldn't normally have access to these
> labels, so you should really determine the length of the instruction
> by decoding, *and* ensure that kvm gave you sufficient instruction
> bytes. For instance, if the addressing mode involves a SIB byte and a
> 32-bit displacement, you would need kvm to give you at least 7 bytes.
> Speaking of sufficient bytes, it would be nice to see your test
> exercise the case where kvm's in-kernel emulator can't actually fetch
> the full 15 bytes.
>
> Can you comment on what else would have to be done to actually emulate
> this instruction in userspace?
>

Along with doing a more thorough job decoding this instruction we
should really have a way to convert the effective address to a linear
address.  This can be tricky to do, so I'd suggest letting the kernel
do it (because it already knows how).  I could create an ioctl that
resolves the effective address and returns either the corresponding
linear address or an exception in the event it fails to linearize the
address.  In the case we have here in this test I'd expect an
exception in the form of a #PF(RSVD).  I was thinking this could be
done as a followup to this change.

> > +                       vcpu_regs_set(vm, VCPU_ID, &regs);
> > +               }
> > +       }
> > +}
> > +
> > +static void do_guest_assert(struct kvm_vm *vm, struct ucall *uc)
> > +{
> > +       TEST_FAIL("%s at %s:%ld", (const char *)uc->args[0], __FILE__,
> > +                 uc->args[1]);
> > +}
> > +