Add a helper to detect VMRUN failures so that KVM can guard against its
own long-standing bug, where KVM neglects to set exitcode[63:32] when
synthesizing a nested VMFAIL_INVALID VM-Exit.  This will allow fixing
KVM's mess of treating exitcode as two separate 32-bit values without
breaking KVM-on-KVM when running on an older, unfixed KVM.

Cc: Jim Mattson <jmattson@google.com>
Cc: Yosry Ahmed <yosry.ahmed@linux.dev>
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/nested.c | 16 +++++++---------
 arch/x86/kvm/svm/svm.c    |  4 ++--
 arch/x86/kvm/svm/svm.h    |  5 +++++
 3 files changed, 14 insertions(+), 11 deletions(-)

diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index ba0f11c68372..f5bde972a2b1 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -1134,7 +1134,7 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 	vmcb12->control.exit_info_1       = vmcb02->control.exit_info_1;
 	vmcb12->control.exit_info_2       = vmcb02->control.exit_info_2;
 
-	if (vmcb12->control.exit_code != SVM_EXIT_ERR)
+	if (!svm_is_vmrun_failure(vmcb12->control.exit_code))
 		nested_save_pending_event_to_vmcb12(svm, vmcb12);
 
 	if (guest_cpu_cap_has(vcpu, X86_FEATURE_NRIPS))
@@ -1425,6 +1425,9 @@ static int nested_svm_intercept(struct vcpu_svm *svm)
 	u32 exit_code = svm->vmcb->control.exit_code;
 	int vmexit = NESTED_EXIT_HOST;
 
+	if (svm_is_vmrun_failure(exit_code))
+		return NESTED_EXIT_DONE;
+
 	switch (exit_code) {
 	case SVM_EXIT_MSR:
 		vmexit = nested_svm_exit_handled_msr(svm);
@@ -1432,7 +1435,7 @@ static int nested_svm_intercept(struct vcpu_svm *svm)
 	case SVM_EXIT_IOIO:
 		vmexit = nested_svm_intercept_ioio(svm);
 		break;
-	case SVM_EXIT_EXCP_BASE ... SVM_EXIT_EXCP_BASE + 0x1f: {
+	case SVM_EXIT_EXCP_BASE ... SVM_EXIT_EXCP_BASE + 0x1f:
 		/*
 		 * Host-intercepted exceptions have been checked already in
 		 * nested_svm_exit_special.  There is nothing to do here,
@@ -1440,15 +1443,10 @@ static int nested_svm_intercept(struct vcpu_svm *svm)
 		 */
 		vmexit = NESTED_EXIT_DONE;
 		break;
-	}
-	case SVM_EXIT_ERR: {
-		vmexit = NESTED_EXIT_DONE;
-		break;
-	}
-	default: {
+	default:
 		if (vmcb12_is_intercept(&svm->nested.ctl, exit_code))
 			vmexit = NESTED_EXIT_DONE;
-	}
+		break;
 	}
 
 	return vmexit;
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 24d59ccfa40d..c2ddf2e0aa1a 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3540,7 +3540,7 @@ static int svm_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 			return 1;
 	}
 
-	if (svm->vmcb->control.exit_code == SVM_EXIT_ERR) {
+	if (svm_is_vmrun_failure(svm->vmcb->control.exit_code)) {
 		kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
 		kvm_run->fail_entry.hardware_entry_failure_reason
 			= svm->vmcb->control.exit_code;
@@ -4311,7 +4311,7 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags)
 
 		/* Track VMRUNs that have made past consistency checking */
 		if (svm->nested.nested_run_pending &&
-		    svm->vmcb->control.exit_code != SVM_EXIT_ERR)
+		    !svm_is_vmrun_failure(svm->vmcb->control.exit_code))
                         ++vcpu->stat.nested_run;
 
 		svm->nested.nested_run_pending = 0;
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 01be93a53d07..0f006793f973 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -424,6 +424,11 @@ static __always_inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu)
 	return container_of(vcpu, struct vcpu_svm, vcpu);
 }
 
+static inline bool svm_is_vmrun_failure(u64 exit_code)
+{
+	return (u32)exit_code == (u32)SVM_EXIT_ERR;
+}
+
 /*
  * Only the PDPTRs are loaded on demand into the shadow MMU.  All other
  * fields are synchronized on VM-Exit, because accessing the VMCB is cheap.
-- 
2.52.0.351.gbe84eed79e-goog

Fold svm_check_exit_valid() and svm_handle_invalid_exit() into their sole
caller, svm_invoke_exit_handler(), as having tiny single-use helpers makes
the code unncessarily difficult to follow.  This will also allow for
additional cleanups in svm_invoke_exit_handler().

No functional change intended.

Suggested-by: Yosry Ahmed <yosry.ahmed@linux.dev>
Reviewed-by: Yosry Ahmed <yosry.ahmed@linux.dev>
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/svm.c | 25 ++++++++++---------------
 1 file changed, 10 insertions(+), 15 deletions(-)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index c2ddf2e0aa1a..a523011f0923 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3443,23 +3443,13 @@ static void dump_vmcb(struct kvm_vcpu *vcpu)
 		sev_free_decrypted_vmsa(vcpu, save);
 }
 
-static bool svm_check_exit_valid(u64 exit_code)
-{
-	return (exit_code < ARRAY_SIZE(svm_exit_handlers) &&
-		svm_exit_handlers[exit_code]);
-}
-
-static int svm_handle_invalid_exit(struct kvm_vcpu *vcpu, u64 exit_code)
-{
-	dump_vmcb(vcpu);
-	kvm_prepare_unexpected_reason_exit(vcpu, exit_code);
-	return 0;
-}
-
 int svm_invoke_exit_handler(struct kvm_vcpu *vcpu, u64 exit_code)
 {
-	if (!svm_check_exit_valid(exit_code))
-		return svm_handle_invalid_exit(vcpu, exit_code);
+	if (exit_code >= ARRAY_SIZE(svm_exit_handlers))
+		goto unexpected_vmexit;
+
+	if (!svm_exit_handlers[exit_code])
+		goto unexpected_vmexit;
 
 #ifdef CONFIG_MITIGATION_RETPOLINE
 	if (exit_code == SVM_EXIT_MSR)
@@ -3478,6 +3468,11 @@ int svm_invoke_exit_handler(struct kvm_vcpu *vcpu, u64 exit_code)
 #endif
 #endif
 	return svm_exit_handlers[exit_code](vcpu);
+
+unexpected_vmexit:
+	dump_vmcb(vcpu);
+	kvm_prepare_unexpected_reason_exit(vcpu, exit_code);
+	return 0;
 }
 
 static void svm_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason,
-- 
2.52.0.351.gbe84eed79e-goog

Check for an unexpected/unhandled VM-Exit after the manual RETPOLINE=y
handling.  The entire point of the RETPOLINE checks is to optimize for
common VM-Exits, i.e. checking for the rare case of an unsupported
VM-Exit is counter-productive.  This also aligns SVM and VMX exit handling.

No functional change intended.

Reviewed-by: Yosry Ahmed <yosry.ahmed@linux.dev>
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/svm.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index a523011f0923..e24bedf1fc81 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3445,12 +3445,6 @@ static void dump_vmcb(struct kvm_vcpu *vcpu)
 
 int svm_invoke_exit_handler(struct kvm_vcpu *vcpu, u64 exit_code)
 {
-	if (exit_code >= ARRAY_SIZE(svm_exit_handlers))
-		goto unexpected_vmexit;
-
-	if (!svm_exit_handlers[exit_code])
-		goto unexpected_vmexit;
-
 #ifdef CONFIG_MITIGATION_RETPOLINE
 	if (exit_code == SVM_EXIT_MSR)
 		return msr_interception(vcpu);
@@ -3467,6 +3461,12 @@ int svm_invoke_exit_handler(struct kvm_vcpu *vcpu, u64 exit_code)
 		return sev_handle_vmgexit(vcpu);
 #endif
 #endif
+	if (exit_code >= ARRAY_SIZE(svm_exit_handlers))
+		goto unexpected_vmexit;
+
+	if (!svm_exit_handlers[exit_code])
+		goto unexpected_vmexit;
+
 	return svm_exit_handlers[exit_code](vcpu);
 
 unexpected_vmexit:
-- 
2.52.0.351.gbe84eed79e-goog

Explicitly filter out 64-bit exit codes when invoking exit handlers, as
svm_exit_handlers[] will never be sized with entries that use bits 63:32.

Processing the non-failing exit code as a 32-bit value will allow tracking
exit_code as a single 64-bit value (which it is, architecturally).  This
will also allow hardening KVM against Spectre-like attacks without needing
to do silly things to avoid build failures on 32-bit kernels
(array_index_nospec() rightly asserts that the index fits in an "unsigned
long").

Omit the check when running as a VM, as KVM has historically failed to set
bits 63:32 appropriately when synthesizing VM-Exits, i.e. KVM could get
false positives when running as a VM on an older, broken KVM/kernel.  From
a functional perspective, omitting the check is "fine", as any unwanted
collision between e.g. VMEXIT_INVALID and a 32-bit exit code will be
fatal to KVM-on-KVM regardless of what KVM-as-L1 does.

Reviewed-by: Yosry Ahmed <yosry.ahmed@linux.dev>
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/svm.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index e24bedf1fc81..1ffe922e95fd 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3443,8 +3443,22 @@ static void dump_vmcb(struct kvm_vcpu *vcpu)
 		sev_free_decrypted_vmsa(vcpu, save);
 }
 
-int svm_invoke_exit_handler(struct kvm_vcpu *vcpu, u64 exit_code)
+int svm_invoke_exit_handler(struct kvm_vcpu *vcpu, u64 __exit_code)
 {
+	u32 exit_code = __exit_code;
+
+	/*
+	 * SVM uses negative values, i.e. 64-bit values, to indicate that VMRUN
+	 * failed.  Report all such errors to userspace (note, VMEXIT_INVALID,
+	 * a.k.a. SVM_EXIT_ERR, is special cased by svm_handle_exit()).  Skip
+	 * the check when running as a VM, as KVM has historically left garbage
+	 * in bits 63:32, i.e. running KVM-on-KVM would hit false positives if
+	 * the underlying kernel is buggy.
+	 */
+	if (!cpu_feature_enabled(X86_FEATURE_HYPERVISOR) &&
+	    (u64)exit_code != __exit_code)
+		goto unexpected_vmexit;
+
 #ifdef CONFIG_MITIGATION_RETPOLINE
 	if (exit_code == SVM_EXIT_MSR)
 		return msr_interception(vcpu);
@@ -3471,7 +3485,7 @@ int svm_invoke_exit_handler(struct kvm_vcpu *vcpu, u64 exit_code)
 
 unexpected_vmexit:
 	dump_vmcb(vcpu);
-	kvm_prepare_unexpected_reason_exit(vcpu, exit_code);
+	kvm_prepare_unexpected_reason_exit(vcpu, __exit_code);
 	return 0;
 }
 
-- 
2.52.0.351.gbe84eed79e-goog

Fix KVM's long-standing buggy handling of SVM's exit_code as a 32-bit
value.  Per the APM and Xen commit d1bd157fbc ("Big merge the HVM
full-virtualisation abstractions.") (which is arguably more trustworthy
than KVM), offset 0x70 is a single 64-bit value:

  070h 63:0 EXITCODE

Track exit_code as a single u64 to prevent reintroducing bugs where KVM
neglects to correctly set bits 63:32.

Fixes: 6aa8b732ca01 ("[PATCH] kvm: userspace interface")
Cc: Jim Mattson <jmattson@google.com>
Cc: Yosry Ahmed <yosry.ahmed@linux.dev>
Reviewed-by: Yosry Ahmed <yosry.ahmed@linux.dev>
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/svm.h                    |  3 +-
 arch/x86/include/uapi/asm/svm.h               | 32 ++++++++---------
 arch/x86/kvm/svm/hyperv.c                     |  1 -
 arch/x86/kvm/svm/nested.c                     | 13 ++-----
 arch/x86/kvm/svm/sev.c                        | 36 +++++++------------
 arch/x86/kvm/svm/svm.c                        |  7 ++--
 arch/x86/kvm/svm/svm.h                        |  4 +--
 arch/x86/kvm/trace.h                          |  6 ++--
 include/hyperv/hvgdk.h                        |  2 +-
 tools/testing/selftests/kvm/include/x86/svm.h |  3 +-
 .../kvm/x86/svm_nested_soft_inject_test.c     |  4 +--
 11 files changed, 42 insertions(+), 69 deletions(-)

diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 56aa99503dc4..ba28ff531b60 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -136,8 +136,7 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
 	u32 int_vector;
 	u32 int_state;
 	u8 reserved_3[4];
-	u32 exit_code;
-	u32 exit_code_hi;
+	u64 exit_code;
 	u64 exit_info_1;
 	u64 exit_info_2;
 	u32 exit_int_info;
diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h
index 650e3256ea7d..010a45c9f614 100644
--- a/arch/x86/include/uapi/asm/svm.h
+++ b/arch/x86/include/uapi/asm/svm.h
@@ -103,38 +103,38 @@
 #define SVM_EXIT_VMGEXIT       0x403
 
 /* SEV-ES software-defined VMGEXIT events */
-#define SVM_VMGEXIT_MMIO_READ			0x80000001
-#define SVM_VMGEXIT_MMIO_WRITE			0x80000002
-#define SVM_VMGEXIT_NMI_COMPLETE		0x80000003
-#define SVM_VMGEXIT_AP_HLT_LOOP			0x80000004
-#define SVM_VMGEXIT_AP_JUMP_TABLE		0x80000005
+#define SVM_VMGEXIT_MMIO_READ			0x80000001ull
+#define SVM_VMGEXIT_MMIO_WRITE			0x80000002ull
+#define SVM_VMGEXIT_NMI_COMPLETE		0x80000003ull
+#define SVM_VMGEXIT_AP_HLT_LOOP			0x80000004ull
+#define SVM_VMGEXIT_AP_JUMP_TABLE		0x80000005ull
 #define SVM_VMGEXIT_SET_AP_JUMP_TABLE		0
 #define SVM_VMGEXIT_GET_AP_JUMP_TABLE		1
-#define SVM_VMGEXIT_PSC				0x80000010
-#define SVM_VMGEXIT_GUEST_REQUEST		0x80000011
-#define SVM_VMGEXIT_EXT_GUEST_REQUEST		0x80000012
-#define SVM_VMGEXIT_AP_CREATION			0x80000013
+#define SVM_VMGEXIT_PSC				0x80000010ull
+#define SVM_VMGEXIT_GUEST_REQUEST		0x80000011ull
+#define SVM_VMGEXIT_EXT_GUEST_REQUEST		0x80000012ull
+#define SVM_VMGEXIT_AP_CREATION			0x80000013ull
 #define SVM_VMGEXIT_AP_CREATE_ON_INIT		0
 #define SVM_VMGEXIT_AP_CREATE			1
 #define SVM_VMGEXIT_AP_DESTROY			2
-#define SVM_VMGEXIT_SNP_RUN_VMPL		0x80000018
-#define SVM_VMGEXIT_SAVIC			0x8000001a
+#define SVM_VMGEXIT_SNP_RUN_VMPL		0x80000018ull
+#define SVM_VMGEXIT_SAVIC			0x8000001aull
 #define SVM_VMGEXIT_SAVIC_REGISTER_GPA		0
 #define SVM_VMGEXIT_SAVIC_UNREGISTER_GPA	1
 #define SVM_VMGEXIT_SAVIC_SELF_GPA		~0ULL
-#define SVM_VMGEXIT_HV_FEATURES			0x8000fffd
-#define SVM_VMGEXIT_TERM_REQUEST		0x8000fffe
+#define SVM_VMGEXIT_HV_FEATURES			0x8000fffdull
+#define SVM_VMGEXIT_TERM_REQUEST		0x8000fffeull
 #define SVM_VMGEXIT_TERM_REASON(reason_set, reason_code)	\
 	/* SW_EXITINFO1[3:0] */					\
 	(((((u64)reason_set) & 0xf)) |				\
 	/* SW_EXITINFO1[11:4] */				\
 	((((u64)reason_code) & 0xff) << 4))
-#define SVM_VMGEXIT_UNSUPPORTED_EVENT		0x8000ffff
+#define SVM_VMGEXIT_UNSUPPORTED_EVENT		0x8000ffffull
 
 /* Exit code reserved for hypervisor/software use */
-#define SVM_EXIT_SW				0xf0000000
+#define SVM_EXIT_SW				0xf0000000ull
 
-#define SVM_EXIT_ERR           -1
+#define SVM_EXIT_ERR           -1ull
 
 #define SVM_EXIT_REASONS \
 	{ SVM_EXIT_READ_CR0,    "read_cr0" }, \
diff --git a/arch/x86/kvm/svm/hyperv.c b/arch/x86/kvm/svm/hyperv.c
index 088f6429b24c..3ec580d687f5 100644
--- a/arch/x86/kvm/svm/hyperv.c
+++ b/arch/x86/kvm/svm/hyperv.c
@@ -11,7 +11,6 @@ void svm_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu)
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	svm->vmcb->control.exit_code = HV_SVM_EXITCODE_ENL;
-	svm->vmcb->control.exit_code_hi = 0;
 	svm->vmcb->control.exit_info_1 = HV_SVM_ENL_EXITCODE_TRAP_AFTER_FLUSH;
 	svm->vmcb->control.exit_info_2 = 0;
 	nested_svm_vmexit(svm);
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index f5bde972a2b1..18b656508de9 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -45,7 +45,6 @@ static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu,
 		 * correctly fill in the high bits of exit_info_1.
 		 */
 		vmcb->control.exit_code = SVM_EXIT_NPF;
-		vmcb->control.exit_code_hi = 0;
 		vmcb->control.exit_info_1 = (1ULL << 32);
 		vmcb->control.exit_info_2 = fault->address;
 	}
@@ -421,7 +420,6 @@ void __nested_copy_vmcb_control_to_cache(struct kvm_vcpu *vcpu,
 	to->int_vector          = from->int_vector;
 	to->int_state           = from->int_state;
 	to->exit_code           = from->exit_code;
-	to->exit_code_hi        = from->exit_code_hi;
 	to->exit_info_1         = from->exit_info_1;
 	to->exit_info_2         = from->exit_info_2;
 	to->exit_int_info       = from->exit_int_info;
@@ -727,8 +725,8 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm,
 	enter_guest_mode(vcpu);
 
 	/*
-	 * Filled at exit: exit_code, exit_code_hi, exit_info_1, exit_info_2,
-	 * exit_int_info, exit_int_info_err, next_rip, insn_len, insn_bytes.
+	 * Filled at exit: exit_code, exit_info_1, exit_info_2, exit_int_info,
+	 * exit_int_info_err, next_rip, insn_len, insn_bytes.
 	 */
 
 	if (guest_cpu_cap_has(vcpu, X86_FEATURE_VGIF) &&
@@ -985,7 +983,6 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu)
 	if (!nested_vmcb_check_save(vcpu) ||
 	    !nested_vmcb_check_controls(vcpu)) {
 		vmcb12->control.exit_code    = SVM_EXIT_ERR;
-		vmcb12->control.exit_code_hi = -1u;
 		vmcb12->control.exit_info_1  = 0;
 		vmcb12->control.exit_info_2  = 0;
 		goto out;
@@ -1018,7 +1015,6 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu)
 	svm->soft_int_injected = false;
 
 	svm->vmcb->control.exit_code    = SVM_EXIT_ERR;
-	svm->vmcb->control.exit_code_hi = -1u;
 	svm->vmcb->control.exit_info_1  = 0;
 	svm->vmcb->control.exit_info_2  = 0;
 
@@ -1130,7 +1126,6 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 
 	vmcb12->control.int_state         = vmcb02->control.int_state;
 	vmcb12->control.exit_code         = vmcb02->control.exit_code;
-	vmcb12->control.exit_code_hi      = vmcb02->control.exit_code_hi;
 	vmcb12->control.exit_info_1       = vmcb02->control.exit_info_1;
 	vmcb12->control.exit_info_2       = vmcb02->control.exit_info_2;
 
@@ -1422,7 +1417,7 @@ static int nested_svm_intercept_ioio(struct vcpu_svm *svm)
 
 static int nested_svm_intercept(struct vcpu_svm *svm)
 {
-	u32 exit_code = svm->vmcb->control.exit_code;
+	u64 exit_code = svm->vmcb->control.exit_code;
 	int vmexit = NESTED_EXIT_HOST;
 
 	if (svm_is_vmrun_failure(exit_code))
@@ -1494,7 +1489,6 @@ static void nested_svm_inject_exception_vmexit(struct kvm_vcpu *vcpu)
 	struct vmcb *vmcb = svm->vmcb;
 
 	vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + ex->vector;
-	vmcb->control.exit_code_hi = 0;
 
 	if (ex->has_error_code)
 		vmcb->control.exit_info_1 = ex->error_code;
@@ -1669,7 +1663,6 @@ static void nested_copy_vmcb_cache_to_control(struct vmcb_control_area *dst,
 	dst->int_vector           = from->int_vector;
 	dst->int_state            = from->int_state;
 	dst->exit_code            = from->exit_code;
-	dst->exit_code_hi         = from->exit_code_hi;
 	dst->exit_info_1          = from->exit_info_1;
 	dst->exit_info_2          = from->exit_info_2;
 	dst->exit_int_info        = from->exit_int_info;
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index f59c65abe3cf..794640bebb62 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -3275,11 +3275,6 @@ void sev_free_vcpu(struct kvm_vcpu *vcpu)
 		kvfree(svm->sev_es.ghcb_sa);
 }
 
-static u64 kvm_get_cached_sw_exit_code(struct vmcb_control_area *control)
-{
-	return (((u64)control->exit_code_hi) << 32) | control->exit_code;
-}
-
 static void dump_ghcb(struct vcpu_svm *svm)
 {
 	struct vmcb_control_area *control = &svm->vmcb->control;
@@ -3301,7 +3296,7 @@ static void dump_ghcb(struct vcpu_svm *svm)
 	 */
 	pr_err("GHCB (GPA=%016llx) snapshot:\n", svm->vmcb->control.ghcb_gpa);
 	pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_code",
-	       kvm_get_cached_sw_exit_code(control), kvm_ghcb_sw_exit_code_is_valid(svm));
+	       control->exit_code, kvm_ghcb_sw_exit_code_is_valid(svm));
 	pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_info_1",
 	       control->exit_info_1, kvm_ghcb_sw_exit_info_1_is_valid(svm));
 	pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_info_2",
@@ -3335,7 +3330,6 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm)
 	struct vmcb_control_area *control = &svm->vmcb->control;
 	struct kvm_vcpu *vcpu = &svm->vcpu;
 	struct ghcb *ghcb = svm->sev_es.ghcb;
-	u64 exit_code;
 
 	/*
 	 * The GHCB protocol so far allows for the following data
@@ -3369,9 +3363,7 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm)
 		__kvm_emulate_msr_write(vcpu, MSR_IA32_XSS, kvm_ghcb_get_xss(svm));
 
 	/* Copy the GHCB exit information into the VMCB fields */
-	exit_code = kvm_ghcb_get_sw_exit_code(svm);
-	control->exit_code = lower_32_bits(exit_code);
-	control->exit_code_hi = upper_32_bits(exit_code);
+	control->exit_code = kvm_ghcb_get_sw_exit_code(svm);
 	control->exit_info_1 = kvm_ghcb_get_sw_exit_info_1(svm);
 	control->exit_info_2 = kvm_ghcb_get_sw_exit_info_2(svm);
 	svm->sev_es.sw_scratch = kvm_ghcb_get_sw_scratch_if_valid(svm);
@@ -3384,15 +3376,8 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
 {
 	struct vmcb_control_area *control = &svm->vmcb->control;
 	struct kvm_vcpu *vcpu = &svm->vcpu;
-	u64 exit_code;
 	u64 reason;
 
-	/*
-	 * Retrieve the exit code now even though it may not be marked valid
-	 * as it could help with debugging.
-	 */
-	exit_code = kvm_get_cached_sw_exit_code(control);
-
 	/* Only GHCB Usage code 0 is supported */
 	if (svm->sev_es.ghcb->ghcb_usage) {
 		reason = GHCB_ERR_INVALID_USAGE;
@@ -3406,7 +3391,7 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
 	    !kvm_ghcb_sw_exit_info_2_is_valid(svm))
 		goto vmgexit_err;
 
-	switch (exit_code) {
+	switch (control->exit_code) {
 	case SVM_EXIT_READ_DR7:
 		break;
 	case SVM_EXIT_WRITE_DR7:
@@ -3507,15 +3492,19 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
 	return 0;
 
 vmgexit_err:
+	/*
+	 * Print the exit code even though it may not be marked valid as it
+	 * could help with debugging.
+	 */
 	if (reason == GHCB_ERR_INVALID_USAGE) {
 		vcpu_unimpl(vcpu, "vmgexit: ghcb usage %#x is not valid\n",
 			    svm->sev_es.ghcb->ghcb_usage);
 	} else if (reason == GHCB_ERR_INVALID_EVENT) {
 		vcpu_unimpl(vcpu, "vmgexit: exit code %#llx is not valid\n",
-			    exit_code);
+			    control->exit_code);
 	} else {
 		vcpu_unimpl(vcpu, "vmgexit: exit code %#llx input is not valid\n",
-			    exit_code);
+			    control->exit_code);
 		dump_ghcb(svm);
 	}
 
@@ -4354,7 +4343,7 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	struct vmcb_control_area *control = &svm->vmcb->control;
-	u64 ghcb_gpa, exit_code;
+	u64 ghcb_gpa;
 	int ret;
 
 	/* Validate the GHCB */
@@ -4396,8 +4385,7 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 
 	svm_vmgexit_success(svm, 0);
 
-	exit_code = kvm_get_cached_sw_exit_code(control);
-	switch (exit_code) {
+	switch (control->exit_code) {
 	case SVM_VMGEXIT_MMIO_READ:
 		ret = setup_vmgexit_scratch(svm, true, control->exit_info_2);
 		if (ret)
@@ -4489,7 +4477,7 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 		ret = -EINVAL;
 		break;
 	default:
-		ret = svm_invoke_exit_handler(vcpu, exit_code);
+		ret = svm_invoke_exit_handler(vcpu, control->exit_code);
 	}
 
 	return ret;
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 1ffe922e95fd..b97e6763839b 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -2443,7 +2443,6 @@ static bool check_selective_cr0_intercepted(struct kvm_vcpu *vcpu,
 
 	if (cr0 ^ val) {
 		svm->vmcb->control.exit_code = SVM_EXIT_CR0_SEL_WRITE;
-		svm->vmcb->control.exit_code_hi = 0;
 		ret = (nested_svm_exit_handled(svm) == NESTED_EXIT_DONE);
 	}
 
@@ -3275,7 +3274,7 @@ static void dump_vmcb(struct kvm_vcpu *vcpu)
 	pr_err("%-20s%08x\n", "int_ctl:", control->int_ctl);
 	pr_err("%-20s%08x\n", "int_vector:", control->int_vector);
 	pr_err("%-20s%08x\n", "int_state:", control->int_state);
-	pr_err("%-20s%08x\n", "exit_code:", control->exit_code);
+	pr_err("%-20s%016llx\n", "exit_code:", control->exit_code);
 	pr_err("%-20s%016llx\n", "exit_info1:", control->exit_info_1);
 	pr_err("%-20s%016llx\n", "exit_info2:", control->exit_info_2);
 	pr_err("%-20s%08x\n", "exit_int_info:", control->exit_int_info);
@@ -3525,7 +3524,6 @@ static int svm_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	struct kvm_run *kvm_run = vcpu->run;
-	u32 exit_code = svm->vmcb->control.exit_code;
 
 	/* SEV-ES guests must use the CR write traps to track CR registers. */
 	if (!sev_es_guest(vcpu->kvm)) {
@@ -3561,7 +3559,7 @@ static int svm_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 	if (exit_fastpath != EXIT_FASTPATH_NONE)
 		return 1;
 
-	return svm_invoke_exit_handler(vcpu, exit_code);
+	return svm_invoke_exit_handler(vcpu, svm->vmcb->control.exit_code);
 }
 
 static int pre_svm_run(struct kvm_vcpu *vcpu)
@@ -4627,7 +4625,6 @@ static int svm_check_intercept(struct kvm_vcpu *vcpu,
 	if (static_cpu_has(X86_FEATURE_NRIPS))
 		vmcb->control.next_rip  = info->next_rip;
 	vmcb->control.exit_code = icpt_info.exit_code;
-	vmcb->control.exit_code_hi = 0;
 	vmexit = nested_svm_exit_handled(svm);
 
 	ret = (vmexit == NESTED_EXIT_DONE) ? X86EMUL_INTERCEPTED
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 0f006793f973..105f1394026e 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -159,8 +159,7 @@ struct vmcb_ctrl_area_cached {
 	u32 int_ctl;
 	u32 int_vector;
 	u32 int_state;
-	u32 exit_code;
-	u32 exit_code_hi;
+	u64 exit_code;
 	u64 exit_info_1;
 	u64 exit_info_2;
 	u32 exit_int_info;
@@ -767,7 +766,6 @@ int nested_svm_vmexit(struct vcpu_svm *svm);
 static inline int nested_svm_simple_vmexit(struct vcpu_svm *svm, u32 exit_code)
 {
 	svm->vmcb->control.exit_code	= exit_code;
-	svm->vmcb->control.exit_code_hi	= 0;
 	svm->vmcb->control.exit_info_1	= 0;
 	svm->vmcb->control.exit_info_2	= 0;
 	return nested_svm_vmexit(svm);
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index e79bc9cb7162..e7fdbe9efc90 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -383,10 +383,10 @@ TRACE_EVENT(kvm_apic,
 #define kvm_print_exit_reason(exit_reason, isa)				\
 	(isa == KVM_ISA_VMX) ?						\
 	__print_symbolic(exit_reason & 0xffff, VMX_EXIT_REASONS) :	\
-	__print_symbolic(exit_reason, SVM_EXIT_REASONS),		\
+	__print_symbolic_u64(exit_reason, SVM_EXIT_REASONS),		\
 	(isa == KVM_ISA_VMX && exit_reason & ~0xffff) ? " " : "",	\
 	(isa == KVM_ISA_VMX) ?						\
-	__print_flags(exit_reason & ~0xffff, " ", VMX_EXIT_REASON_FLAGS) : ""
+	__print_flags_u64(exit_reason & ~0xffff, " ", VMX_EXIT_REASON_FLAGS) : ""
 
 #define TRACE_EVENT_KVM_EXIT(name)					     \
 TRACE_EVENT(name,							     \
@@ -781,7 +781,7 @@ TRACE_EVENT_KVM_EXIT(kvm_nested_vmexit);
  * Tracepoint for #VMEXIT reinjected to the guest
  */
 TRACE_EVENT(kvm_nested_vmexit_inject,
-	    TP_PROTO(__u32 exit_code,
+	    TP_PROTO(__u64 exit_code,
 		     __u64 exit_info1, __u64 exit_info2,
 		     __u32 exit_int_info, __u32 exit_int_info_err, __u32 isa),
 	    TP_ARGS(exit_code, exit_info1, exit_info2,
diff --git a/include/hyperv/hvgdk.h b/include/hyperv/hvgdk.h
index dd6d4939ea29..384c3f3ff4a5 100644
--- a/include/hyperv/hvgdk.h
+++ b/include/hyperv/hvgdk.h
@@ -281,7 +281,7 @@ struct hv_vmcb_enlightenments {
 #define HV_VMCB_NESTED_ENLIGHTENMENTS		31
 
 /* Synthetic VM-Exit */
-#define HV_SVM_EXITCODE_ENL			0xf0000000
+#define HV_SVM_EXITCODE_ENL			0xf0000000ull
 #define HV_SVM_ENL_EXITCODE_TRAP_AFTER_FLUSH	(1)
 
 /* VM_PARTITION_ASSIST_PAGE */
diff --git a/tools/testing/selftests/kvm/include/x86/svm.h b/tools/testing/selftests/kvm/include/x86/svm.h
index 29cffd0a9181..10b30b38bb3f 100644
--- a/tools/testing/selftests/kvm/include/x86/svm.h
+++ b/tools/testing/selftests/kvm/include/x86/svm.h
@@ -92,8 +92,7 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
 	u32 int_vector;
 	u32 int_state;
 	u8 reserved_3[4];
-	u32 exit_code;
-	u32 exit_code_hi;
+	u64 exit_code;
 	u64 exit_info_1;
 	u64 exit_info_2;
 	u32 exit_int_info;
diff --git a/tools/testing/selftests/kvm/x86/svm_nested_soft_inject_test.c b/tools/testing/selftests/kvm/x86/svm_nested_soft_inject_test.c
index 7b6481d6c0d3..4bd1655f9e6d 100644
--- a/tools/testing/selftests/kvm/x86/svm_nested_soft_inject_test.c
+++ b/tools/testing/selftests/kvm/x86/svm_nested_soft_inject_test.c
@@ -103,7 +103,7 @@ static void l1_guest_code(struct svm_test_data *svm, uint64_t is_nmi, uint64_t i
 
 	run_guest(vmcb, svm->vmcb_gpa);
 	__GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL,
-		       "Expected VMMCAL #VMEXIT, got '0x%x', info1 = '0x%lx, info2 = '0x%lx'",
+		       "Expected VMMCAL #VMEXIT, got '0x%lx', info1 = '0x%lx, info2 = '0x%lx'",
 		       vmcb->control.exit_code,
 		       vmcb->control.exit_info_1, vmcb->control.exit_info_2);
 
@@ -133,7 +133,7 @@ static void l1_guest_code(struct svm_test_data *svm, uint64_t is_nmi, uint64_t i
 
 	run_guest(vmcb, svm->vmcb_gpa);
 	__GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_HLT,
-		       "Expected HLT #VMEXIT, got '0x%x', info1 = '0x%lx, info2 = '0x%lx'",
+		       "Expected HLT #VMEXIT, got '0x%lx', info1 = '0x%lx, info2 = '0x%lx'",
 		       vmcb->control.exit_code,
 		       vmcb->control.exit_info_1, vmcb->control.exit_info_2);
 
-- 
2.52.0.351.gbe84eed79e-goog

Limit KVM's incorrect check for VMXEXIT_INVALID, a.k.a. SVM_EXIT_ERR, to
running as a VM, as detected by X86_FEATURE_HYPERVISOR.  The exit_code and
all failure codes, e.g. VMXEXIT_INVALID, are 64-bit values, and so checking
only bits 31:0 could result in false positives when running on non-broken
hardware, e.g. in the extremely unlikely scenario exit code 0xffffffffull
is ever generated by hardware.

Keep the 32-bit check to play nice with running on broken KVM (for years,
KVM has not set bits 63:32 when synthesizing nested SVM VM-Exits).

Reviewed-by: Yosry Ahmed <yosry.ahmed@linux.dev>
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/svm.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 105f1394026e..f938679c0231 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -425,7 +425,10 @@ static __always_inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu)
 
 static inline bool svm_is_vmrun_failure(u64 exit_code)
 {
-	return (u32)exit_code == (u32)SVM_EXIT_ERR;
+	if (cpu_feature_enabled(X86_FEATURE_HYPERVISOR))
+		return (u32)exit_code == (u32)SVM_EXIT_ERR;
+
+	return exit_code == SVM_EXIT_ERR;
 }
 
 /*
-- 
2.52.0.351.gbe84eed79e-goog

Explicitly clamp the exit code used to index KVM's exit handlers to guard
against Spectre-like attacks, mainly to provide consistency between VMX
and SVM (VMX was given the same treatment by commit c926f2f7230b ("KVM:
x86: Protect exit_reason from being used in Spectre-v1/L1TF attacks").

For normal VMs, it's _extremely_ unlikely the exit code could be used to
exploit a speculation vulnerability, as the exit code is set by hardware
and unexpected/unknown exit codes should be quite well bounded (as is/was
the case with VMX).  But with SEV-ES+, the exit code is guest-controlled
as it comes from the GHCB, not from hardware, i.e. an attack from the
guest is at least somewhat plausible.

Irrespective of SEV-ES+, hardening KVM is easy and inexpensive, and such
an attack is theoretically possible.

Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/svm.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index b97e6763839b..a75cd832e194 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3477,6 +3477,7 @@ int svm_invoke_exit_handler(struct kvm_vcpu *vcpu, u64 __exit_code)
 	if (exit_code >= ARRAY_SIZE(svm_exit_handlers))
 		goto unexpected_vmexit;
 
+	exit_code = array_index_nospec(exit_code, ARRAY_SIZE(svm_exit_handlers));
 	if (!svm_exit_handlers[exit_code])
 		goto unexpected_vmexit;
 
-- 
2.52.0.351.gbe84eed79e-goog

Add a build-time assertiont that Hyper-V's "enlightened" exit code is that,
same as the AMD-defined "Reserved for Host" exit code, mostly to help
readers connect the dots and understand why synthesizing a software-defined
exit code is safe/ok.

Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/hyperv.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/arch/x86/kvm/svm/hyperv.c b/arch/x86/kvm/svm/hyperv.c
index 3ec580d687f5..4f24dcb45116 100644
--- a/arch/x86/kvm/svm/hyperv.c
+++ b/arch/x86/kvm/svm/hyperv.c
@@ -10,6 +10,12 @@ void svm_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	/*
+	 * The exit code used by Hyper-V for software-defined exits is reserved
+	 * by AMD specifically for such use cases.
+	 */
+	BUILD_BUG_ON(HV_SVM_EXITCODE_ENL != SVM_EXIT_SW);
+
 	svm->vmcb->control.exit_code = HV_SVM_EXITCODE_ENL;
 	svm->vmcb->control.exit_info_1 = HV_SVM_ENL_EXITCODE_TRAP_AFTER_FLUSH;
 	svm->vmcb->control.exit_info_2 = 0;
-- 
2.52.0.351.gbe84eed79e-goog