FAILED: patch "[PATCH] KVM: x86: Fill kvm_run exit fields in common" failed to apply to 6.18-stable tree

PATCH In review [email protected] 3 participants 6 messages Sep 29 – Oct 7

Subsystems (3)

Stable branch x86 KVM x86

lore

Share & tools

lore

[email protected]

author maintainer

2026-09-29 11:38 UTC #0 lore raw

The patch below does not apply to the 6.18-stable tree.
If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <[email protected]>.

To reproduce the conflict and resubmit, you may use the following commands:

git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.18.y
git checkout FETCH_HEAD
git cherry-pick -x c1214f293d77c6e425a379f90d09bdb4815993a8
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<[email protected]>' --in-reply-to '2026092938-celibate-sarcastic-e56f@gregkh' --subject-prefix 'PATCH 6.18.y' 'HEAD^..'

Possible dependencies:

thanks,

greg k-h

------------------ original commit in Linus's tree ------------------

From c1214f293d77c6e425a379f90d09bdb4815993a8 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <[email protected]>
Date: Mon, 21 Sep 2026 14:16:08 -0700
Subject: [PATCH] KVM: x86: Fill kvm_run exit fields in common
get_nested_state_pages() error paths

Fill kvm_run with "internal error, emulation" in the common error handling paths for getting nested state pages, as requiring each check to manually fill kvm_run is error prone and requires a non-trivial amount of copy+paste.

Specifically, both SVM and VMX fail to fill kvm_run if load_pdptrs() fails, and SVM fails to fill kvm_run if kvm_hv_verify_vp_assist() fails. If those flows fail, the *best* case scenario is that KVM will exit to userspace with KVM_EXIT_UNKNOWN. The worst case scenario is that KVM exits with a stale exit_reason and confuses userspace.

Note, SVM never exits to userspace if something goes sideways when dealing with vmcb12 assets while emulating VMRUN, i.e. lack of SVM-specific code is not a bug.

Fixes 0f85722341b0 ("KVM: nVMX: delay loading of PDPTRs to KVM_REQ_GET_NESTED_STATE_PAGES")

Fixes 232f75d3b4b5 ("KVM: nSVM: call nested_svm_load_cr3 on nested state load")

Fixes 3f4a812edf5c ("KVM: nSVM: hyper-v: Enable L2 TLB flush")

Cc [email protected]

Reported-by Jinwoo Lee <[email protected]>

Closes https://lore.kernel.org/all/[email protected] open here

Reported-by Stefan Teodorescu <[email protected]>

Link https://patch.msgid.link/[email protected] open here

Signed-off-by Sean Christopherson <[email protected]>

arch/x86/kvm/svm/nested.c +1 -6

index 73f37b050d0a..f9090b601efa 100644
@@ -2125,13 +2125,8 @@ static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu)
 			return false;
 	}
 
-	if (!nested_svm_merge_msrpm(vcpu)) {
-		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-		vcpu->run->internal.suberror =
-			KVM_INTERNAL_ERROR_EMULATION;
-		vcpu->run->internal.ndata = 0;
+	if (!nested_svm_merge_msrpm(vcpu))
 		return false;
-	}
 
 	if (kvm_hv_verify_vp_assist(vcpu))
 		return false;

arch/x86/kvm/vmx/nested.c +5 ~~-10~~

index 151873407abd..40c1a5f6fa8a 100644
@@ -3465,10 +3465,6 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
 		} else {
 			pr_debug_ratelimited("%s: no backing for APIC-access address in vmcs12\n",
 					     __func__);
-			vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-			vcpu->run->internal.suberror =
-				KVM_INTERNAL_ERROR_EMULATION;
-			vcpu->run->internal.ndata = 0;
 			return false;
 		}
 	}

@@ -3539,11 +3535,6 @@ static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu)
 	if (!nested_get_evmcs_page(vcpu)) {
 		pr_debug_ratelimited("%s: enlightened vmptrld failed\n",
 				     __func__);
-		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-		vcpu->run->internal.suberror =
-			KVM_INTERNAL_ERROR_EMULATION;
-		vcpu->run->internal.ndata = 0;
-
 		return false;
 	}
 #endif

@@ -3915,8 +3906,12 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 
 vmentry_failed:
 	vcpu->arch.nested_run_pending = 0;
-	if (status == NVMX_VMENTRY_KVM_INTERNAL_ERROR)
+	if (status == NVMX_VMENTRY_KVM_INTERNAL_ERROR) {
+		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+		vcpu->run->internal.ndata = 0;
 		return 0;
+	}
 	if (status == NVMX_VMENTRY_VMEXIT)
 		return 1;
 	WARN_ON_ONCE(status != NVMX_VMENTRY_VMFAIL);

arch/x86/kvm/x86.c +3 -0

index 4ec17aaff413..aad065d035fb 100644
@@ -8072,6 +8072,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 		if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) {
 			if (unlikely(!kvm_nested_call(get_nested_state_pages)(vcpu))) {
+				vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+				vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+				vcpu->run->internal.ndata = 0;
 				kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
 				r = 0;
 				goto out;

Sasha Levin

maintainer

2026-09-30 15:39 UTC #1 lore raw

PATCH 1/4 KVM: move TSS constants from kvm_host.h to tss.h

From: Paolo Bonzini <[email protected]>

[ Upstream commit 35fdfa632e7cf8271189c7ae6f97e7c4b55f7f80 ]

Suggested-by Kai Huang <[email protected]>

Signed-off-by Paolo Bonzini <[email protected]>

Stable-dep-of: c1214f293d77 ("KVM: x86: Fill kvm_run exit fields in common get_nested_state_pages() error paths")

Signed-off-by Sasha Levin <[email protected]>

---
 arch/x86/include/asm/kvm_host.h | 7 -------
 arch/x86/kvm/tss.h              | 7 +++++++
 arch/x86/kvm/vmx/vmx.c          | 1 +
 3 files changed, 8 insertions(+), 7 deletions(-)

arch/x86/include/asm/kvm_host.h +0 -7

index 03866683ac336..0008a3c4fc452 100644
@@ -2350,13 +2350,6 @@ static inline void kvm_inject_gp(struct kvm_vcpu *vcpu, u32 error_code)
 	kvm_queue_exception_e(vcpu, GP_VECTOR, error_code);
 }
 
-#define TSS_IOPB_BASE_OFFSET 0x66
-#define TSS_BASE_SIZE 0x68
-#define TSS_IOPB_SIZE (65536 / 8)
-#define TSS_REDIRECTION_SIZE (256 / 8)
-#define RMODE_TSS_SIZE							\
-	(TSS_BASE_SIZE + TSS_REDIRECTION_SIZE + TSS_IOPB_SIZE + 1)
-
 enum {
 	TASK_SWITCH_CALL = 0,
 	TASK_SWITCH_IRET = 1,

arch/x86/kvm/tss.h +7 -0

index 3f9150125e701..117bf8bec07dc 100644
@@ -57,4 +57,11 @@ struct tss_segment_16 {
 	u16 ldt;
 };
 
+#define TSS_IOPB_BASE_OFFSET 0x66
+#define TSS_BASE_SIZE 0x68
+#define TSS_IOPB_SIZE (65536 / 8)
+#define TSS_REDIRECTION_SIZE (256 / 8)
+#define RMODE_TSS_SIZE							\
+	(TSS_BASE_SIZE + TSS_REDIRECTION_SIZE + TSS_IOPB_SIZE + 1)
+
 #endif

arch/x86/kvm/vmx/vmx.c +1 -0

index f65081330c8a4..6b51f352d2826 100644
@@ -71,6 +71,7 @@
 #include "x86.h"
 #include "x86_ops.h"
 #include "smm.h"
+#include "tss.h"
 #include "vmx_onhyperv.h"
 #include "posted_intr.h"

Signature · 1 line

2.53.0

Sasha Levin

maintainer

2026-09-30 15:39 UTC #2 lore raw

PATCH 2/4 KVM: x86: Reject nested CAP enablement if nested virtualization is disabled

From: Sean Christopherson <[email protected]>

[ Upstream commit b65699be2c606d2687593516d93e66d16a713b61 ]

Add a flag to explicitly track if nested virtualization is enabled, and use it enumerate that various nested CAPs are unsupported, and to reject enablement of said CAPs. When the nested ops hooks were moved to their own structure, KVM's NULL-by-default behavior was deliberately dropped, with the changelog asserting that all was well. That wasn't quite true; there is no danger to KVM, but now KVM is over-reporting support for KVM_CAP_NESTED_STATE and KVM_CAP_HYPERV_ENLIGHTENED_VMCS.

Fixes 33b22172452f ("KVM: x86: move nested-related kvm_x86_ops to a separate struct")

Reviewed-by Vitaly Kuznetsov <[email protected]>

Link https://patch.msgid.link/[email protected] open here

Signed-off-by Sean Christopherson <[email protected]>

Stable-dep-of: c1214f293d77 ("KVM: x86: Fill kvm_run exit fields in common get_nested_state_pages() error paths")

Signed-off-by Sasha Levin <[email protected]>

---
 arch/x86/include/asm/kvm_host.h |  2 ++
 arch/x86/kvm/hyperv.c           |  3 ++-
 arch/x86/kvm/svm/svm.c          |  1 +
 arch/x86/kvm/vmx/vmx.c          |  1 +
 arch/x86/kvm/x86.c              | 12 +++++++-----
 5 files changed, 13 insertions(+), 6 deletions(-)

arch/x86/include/asm/kvm_host.h +2 -0

index 0008a3c4fc452..5202b0a708807 100644
@@ -1954,6 +1954,8 @@ struct kvm_x86_ops {
 };
 
 struct kvm_x86_nested_ops {
+	bool enabled;
+
 	void (*leave_nested)(struct kvm_vcpu *vcpu);
 	bool (*is_exception_vmexit)(struct kvm_vcpu *vcpu, u8 vector,
 				    u32 error_code);

arch/x86/kvm/hyperv.c +2 -1

index 380a211f56f00..4753d084e2567 100644
@@ -2799,7 +2799,8 @@ int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
 	};
 	int i, nent = ARRAY_SIZE(cpuid_entries);
 
-	if (kvm_x86_ops.nested_ops->get_evmcs_version)
+	if (kvm_x86_ops.nested_ops->enabled &&
+	    kvm_x86_ops.nested_ops->get_evmcs_version)
 		evmcs_ver = kvm_x86_ops.nested_ops->get_evmcs_version(vcpu);
 
 	if (cpuid->nent < nent)

arch/x86/kvm/svm/svm.c +1 -0

index a24a6871b6936..e3daa6e57192d 100644
@@ -5461,6 +5461,7 @@ static __init int svm_hardware_setup(void)
 		if (r)
 			return r;
 	}
+	svm_nested_ops.enabled = nested;
 
 	/*
 	 * KVM's MMU doesn't support using 2-level paging for itself, and thus

arch/x86/kvm/vmx/vmx.c +1 -0

index 6b51f352d2826..5bae3d5ce6eec 100644
@@ -8642,6 +8642,7 @@ __init int vmx_hardware_setup(void)
 		if (r)
 			return r;
 	}
+	vmx_nested_ops.enabled = nested;
 
 	r = alloc_kvm_area();
 	if (r && nested)

arch/x86/kvm/x86.c +7 -5

index f08a34d3ff3d9..91d38d709d8a7 100644
@@ -4604,7 +4604,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 			r &= ~KVM_X2APIC_ENABLE_SUPPRESS_EOI_BROADCAST;
 		break;
 	case KVM_CAP_NESTED_STATE:
-		r = kvm_x86_ops.nested_ops->get_state ?
+		r = kvm_x86_ops.nested_ops->enabled ?
 			kvm_x86_ops.nested_ops->get_state(NULL, NULL, 0) : 0;
 		break;
 #ifdef CONFIG_KVM_HYPERV

@@ -4612,7 +4612,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = kvm_x86_ops.enable_l2_tlb_flush != NULL;
 		break;
 	case KVM_CAP_HYPERV_ENLIGHTENED_VMCS:
-		r = kvm_x86_ops.nested_ops->enable_evmcs != NULL;
+		r = kvm_x86_ops.nested_ops->enabled &&
+		    kvm_x86_ops.nested_ops->enable_evmcs != NULL;
 		break;
 #endif
 	case KVM_CAP_SMALLER_MAXPHYADDR:

@@ -5650,7 +5651,8 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 			uint16_t vmcs_version;
 			void __user *user_ptr;
 
-			if (!kvm_x86_ops.nested_ops->enable_evmcs)
+			if (!kvm_x86_ops.nested_ops->enabled ||
+			    !kvm_x86_ops.nested_ops->enable_evmcs)
 				return -ENOTTY;
 			r = kvm_x86_ops.nested_ops->enable_evmcs(vcpu, &vmcs_version);
 			if (!r) {

@@ -6150,7 +6152,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		u32 user_data_size;
 
 		r = -EINVAL;
-		if (!kvm_x86_ops.nested_ops->get_state)
+		if (!kvm_x86_ops.nested_ops->enabled)
 			break;
 
 		BUILD_BUG_ON(sizeof(user_data_size) != sizeof(user_kvm_nested_state->size));

@@ -6180,7 +6182,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		int idx;
 
 		r = -EINVAL;
-		if (!kvm_x86_ops.nested_ops->set_state)
+		if (!kvm_x86_ops.nested_ops->enabled)
 			break;
 
 		r = -EFAULT;

Signature · 1 line

2.53.0

Sasha Levin

maintainer

2026-09-30 15:39 UTC #3 lore raw

PATCH 3/4 KVM: x86: Add static calls for nested virtualization ops

In reply to Sasha Levin

From: Sean Christopherson <[email protected]>

[ Upstream commit 4b9819a50674dd40d176033f9ea2e23a70889dc6 ]

Use static calls to invoke nested virtualization ops, as many of the calls are in relatively hot paths when L2 is active, e.g. checking for events, and because there's no reason not use static calls these days.

Opportunistically use a RET0 static call for get_evmcs_version() instead of manually checking for a non-NULL vendor hook.

Link https://patch.msgid.link/[email protected] open here

Signed-off-by Sean Christopherson <[email protected]>

Backport to 6.18 as a dependency of c1214f293d77:

- Preserve the vendor init/exit declarations and the direct nested GPA translation path. This tree has no translate_nested_gpa nested op.
- Initialize nested static calls inside the existing kvm_ops_update(), avoiding new helper functions and the unrelated EFER setup refactoring.
- Fold in the boolean nested_run_pending relocation from 3d4470d71fbf7, preserving the stable SVM control and error paths. The target expects this flag in kvm_vcpu_arch in its VMX entry-failure hunk.
- Fold in the request requeue from 10180a2775493, which is context for the target's common error path and prevents retrying L2 with stale pages.
- Brace the existing SVM PDPTR reload condition to match target context.

These preparations let the unmodified target apply cleanly without adding functions or importing unrelated upstream refactoring.

[ sashal: Reduced backport -- upstream 4b9819a50674d touches 7 file(s), this
backport carries 12. Not backported here:
arch/x86/kvm/mmu.h
This note is generated from the file lists only; see the resolution record for the reasoning. ]

Stable-dep-of: c1214f293d77 ("KVM: x86: Fill kvm_run exit fields in common get_nested_state_pages() error paths")

Signed-off-by Sasha Levin <[email protected]>

---
 arch/x86/include/asm/kvm-x86-nested-ops.h | 35 ++++++++++++++++
 arch/x86/include/asm/kvm_host.h           | 17 ++++++++
 arch/x86/kvm/hyperv.c                     |  7 ++--
 arch/x86/kvm/mmu/paging_tmpl.h            |  2 +-
 arch/x86/kvm/svm/nested.c                 | 21 +++++-----
 arch/x86/kvm/svm/svm.c                    | 16 +++----
 arch/x86/kvm/svm/svm.h                    |  4 --
 arch/x86/kvm/vmx/nested.c                 | 46 ++++++++++----------
 arch/x86/kvm/vmx/vmx.c                    | 16 +++----
 arch/x86/kvm/vmx/vmx.h                    |  3 --
 arch/x86/kvm/x86.c                        | 51 +++++++++++++++--------
 arch/x86/kvm/x86.h                        |  2 +-
 12 files changed, 140 insertions(+), 80 deletions(-)
 create mode 100644 arch/x86/include/asm/kvm-x86-nested-ops.h

arch/x86/include/asm/kvm-x86-nested-ops.h new file +35 -0

new file mode 100644
index 0000000000000..66360aa440c4b
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#if !defined(KVM_X86_NESTED_OP) || \
+    !defined(KVM_X86_NESTED_OP_OPTIONAL) || \
+    !defined(KVM_X86_NESTED_OP_OPTIONAL_RET0)
+#error Missing one or more KVM_X86_NESTED_OP #defines
+#else
+/*
+ * KVM_X86_NESTED_OP() and KVM_X86_NESTED_OP_OPTIONAL() are used to help
+ * generate both DECLARE/DEFINE_STATIC_CALL() invocations and
+ * "static_call_update()" calls.
+ *
+ * KVM_X86_NESTED_OP_OPTIONAL() can be used for those functions that can have
+ * a NULL definition.  KVM_X86_NESTED_OP_OPTIONAL_RET0() can be used likewise
+ * to make a definition optional, but in this case the default will
+ * be __static_call_return0.
+ */
+KVM_X86_NESTED_OP(leave_nested)
+KVM_X86_NESTED_OP(is_exception_vmexit)
+KVM_X86_NESTED_OP(check_events)
+KVM_X86_NESTED_OP_OPTIONAL_RET0(has_events)
+KVM_X86_NESTED_OP(triple_fault)
+KVM_X86_NESTED_OP(get_state)
+KVM_X86_NESTED_OP(set_state)
+KVM_X86_NESTED_OP(get_nested_state_pages)
+KVM_X86_NESTED_OP_OPTIONAL_RET0(write_log_dirty)
+#ifdef CONFIG_KVM_HYPERV
+KVM_X86_NESTED_OP_OPTIONAL(enable_evmcs)
+KVM_X86_NESTED_OP_OPTIONAL_RET0(get_evmcs_version)
+KVM_X86_NESTED_OP(hv_inject_synthetic_vmexit_post_tlb_flush)
+#endif
+#endif
+
+#undef KVM_X86_NESTED_OP
+#undef KVM_X86_NESTED_OP_OPTIONAL
+#undef KVM_X86_NESTED_OP_OPTIONAL_RET0

arch/x86/include/asm/kvm_host.h +17 -0

index 5202b0a708807..77d1984581033 100644
@@ -1089,6 +1089,15 @@ struct kvm_vcpu_arch {
 	 */
 	bool pdptrs_from_userspace;
 
+	/*
+	 * Set if an emulated nested VM-Enter to L2 is pending completion.  KVM
+	 * must not synthesize a VM-Exit to L1 before entering L2, as VM-Exits
+	 * can only occur at instruction boundaries.  The only exception is
+	 * VMX's "notify" exits, which exist in large part to break the CPU out
+	 * of infinite ucode loops, but can corrupt vCPU state in the process!
+	 */
+	bool nested_run_pending;
+
 #if IS_ENABLED(CONFIG_HYPERV)
 	hpa_t hv_root_tdp;
 #endif

@@ -2009,6 +2018,14 @@ extern struct kvm_x86_ops kvm_x86_ops;
 #define KVM_X86_OP_OPTIONAL_RET0 KVM_X86_OP
 #include <asm/kvm-x86-ops.h>
 
+#define kvm_nested_call(func) static_call(kvm_x86_nested_##func)
+
+#define KVM_X86_NESTED_OP(func) \
+	DECLARE_STATIC_CALL(kvm_x86_nested_##func, *(((struct kvm_x86_nested_ops *)0)->func));
+#define KVM_X86_NESTED_OP_OPTIONAL KVM_X86_NESTED_OP
+#define KVM_X86_NESTED_OP_OPTIONAL_RET0 KVM_X86_NESTED_OP
+#include <asm/kvm-x86-nested-ops.h>
+
 int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops);
 void kvm_x86_vendor_exit(void);

arch/x86/kvm/hyperv.c +3 -4

index 4753d084e2567..56325ba9ef367 100644
@@ -2415,7 +2415,7 @@ static int kvm_hv_hypercall_complete(struct kvm_vcpu *vcpu, u64 result)
 	ret = kvm_skip_emulated_instruction(vcpu);
 
 	if (tlb_lock_count)
-		kvm_x86_ops.nested_ops->hv_inject_synthetic_vmexit_post_tlb_flush(vcpu);
+		kvm_nested_call(hv_inject_synthetic_vmexit_post_tlb_flush)(vcpu);
 
 	return ret;
 }

@@ -2799,9 +2799,8 @@ int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
 	};
 	int i, nent = ARRAY_SIZE(cpuid_entries);
 
-	if (kvm_x86_ops.nested_ops->enabled &&
-	    kvm_x86_ops.nested_ops->get_evmcs_version)
-		evmcs_ver = kvm_x86_ops.nested_ops->get_evmcs_version(vcpu);
+	if (kvm_x86_ops.nested_ops->enabled)
+		evmcs_ver = kvm_nested_call(get_evmcs_version)(vcpu);
 
 	if (cpuid->nent < nent)
 		return -E2BIG;

arch/x86/kvm/mmu/paging_tmpl.h +1 -1

index af220c9c8ab8d..6e2ce54a13b31 100644
@@ -222,7 +222,7 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
 				!(pte & PT_GUEST_DIRTY_MASK)) {
 			trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte));
 #if PTTYPE == PTTYPE_EPT
-			if (kvm_x86_ops.nested_ops->write_log_dirty(vcpu, addr))
+			if (kvm_nested_call(write_log_dirty)(vcpu, addr))
 				return -EINVAL;
 #endif
 			pte |= PT_GUEST_DIRTY_MASK;

arch/x86/kvm/svm/nested.c +11 ~~-10~~

index 66b8955a1658e..c765ea1dff69c 100644
@@ -838,7 +838,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm)
 	 * the CPU and/or KVM and should be used regardless of L1's support.
 	 */
 	if (guest_cpu_cap_has(vcpu, X86_FEATURE_NRIPS) ||
-	    !svm->nested.nested_run_pending)
+	    !vcpu->arch.nested_run_pending)
 		vmcb02->control.next_rip = svm->nested.ctl.next_rip;
 
 	svm->nmi_l1_to_l2 = is_evtinj_nmi(vmcb02->control.event_inj);

@@ -850,7 +850,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm)
 	if (is_evtinj_soft(vmcb02->control.event_inj)) {
 		svm->soft_int_injected = true;
 		if (guest_cpu_cap_has(vcpu, X86_FEATURE_NRIPS) ||
-		    !svm->nested.nested_run_pending)
+		    !vcpu->arch.nested_run_pending)
 			svm->soft_int_next_rip = svm->nested.ctl.next_rip;
 	}

@@ -1023,7 +1023,7 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu)
 	if (!npt_enabled)
 		vmcb01->save.cr3 = kvm_read_cr3(vcpu);
 
-	svm->nested.nested_run_pending = 1;
+	vcpu->arch.nested_run_pending = 1;
 
 	if (enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, true))
 		goto out_exit_err;

@@ -1032,7 +1032,7 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu)
 		goto out;
 
 out_exit_err:
-	svm->nested.nested_run_pending = 0;
+	vcpu->arch.nested_run_pending = 0;
 
 	svm->vmcb->control.exit_code    = SVM_EXIT_ERR;
 	svm->vmcb->control.exit_code_hi = -1u;

@@ -1177,7 +1177,7 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 	/* Exit Guest-Mode */
 	leave_guest_mode(vcpu);
 	svm->nested.vmcb12_gpa = 0;
-	WARN_ON_ONCE(svm->nested.nested_run_pending);
+	WARN_ON_ONCE(vcpu->arch.nested_run_pending);
 
 	kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);

@@ -1387,7 +1387,7 @@ void svm_leave_nested(struct kvm_vcpu *vcpu)
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	if (is_guest_mode(vcpu)) {
-		svm->nested.nested_run_pending = 0;
+		vcpu->arch.nested_run_pending = 0;
 		svm->nested.vmcb12_gpa = INVALID_GPA;
 
 		leave_guest_mode(vcpu);

@@ -1583,7 +1583,7 @@ static int svm_check_nested_events(struct kvm_vcpu *vcpu)
 	 * previously injected event, the pending exception occurred while said
 	 * event was being delivered and thus needs to be handled.
 	 */
-	bool block_nested_exceptions = svm->nested.nested_run_pending;
+	bool block_nested_exceptions = vcpu->arch.nested_run_pending;
 	/*
 	 * New events (not exceptions) are only recognized at instruction
 	 * boundaries.  If an event needs reinjection, then KVM is handling a

@@ -1758,7 +1758,7 @@ static int svm_get_nested_state(struct kvm_vcpu *vcpu,
 		kvm_state.size += KVM_STATE_NESTED_SVM_VMCB_SIZE;
 		kvm_state.flags |= KVM_STATE_NESTED_GUEST_MODE;
 
-		if (svm->nested.nested_run_pending)
+		if (vcpu->arch.nested_run_pending)
 			kvm_state.flags |= KVM_STATE_NESTED_RUN_PENDING;
 	}

@@ -1895,7 +1895,7 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu,
 
 	svm_set_gif(svm, !!(kvm_state->flags & KVM_STATE_NESTED_GIF_SET));
 
-	svm->nested.nested_run_pending =
+	vcpu->arch.nested_run_pending =
 		!!(kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING);
 
 	svm->nested.vmcb12_gpa = kvm_state->hdr.svm.vmcb_pa;

@@ -1943,7 +1943,7 @@ static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu)
 		return true;
 
 	if (!vcpu->arch.pdptrs_from_userspace &&
-	    !nested_npt_enabled(to_svm(vcpu)) && is_pae_paging(vcpu))
+	    !nested_npt_enabled(to_svm(vcpu)) && is_pae_paging(vcpu)) {
 		/*
 		 * Reload the guest's PDPTRs since after a migration
 		 * the guest CR3 might be restored prior to setting the nested

@@ -1951,6 +1951,7 @@ static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu)
 		 */
 		if (CC(!load_pdptrs(vcpu, vcpu->arch.cr3)))
 			return false;
+	}
 
 	if (!nested_svm_merge_msrpm(vcpu)) {
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;

arch/x86/kvm/svm/svm.c +8 -8

index e3daa6e57192d..f687df75f775c 100644
@@ -3721,7 +3721,7 @@ static void svm_fixup_nested_rips(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	if (!is_guest_mode(vcpu) || !svm->nested.nested_run_pending)
+	if (!is_guest_mode(vcpu) || !vcpu->arch.nested_run_pending)
 		return;
 
 	/*

@@ -3869,7 +3869,7 @@ bool svm_nmi_blocked(struct kvm_vcpu *vcpu)
 static int svm_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
-	if (svm->nested.nested_run_pending)
+	if (vcpu->arch.nested_run_pending)
 		return -EBUSY;
 
 	if (svm_nmi_blocked(vcpu))

@@ -3911,7 +3911,7 @@ static int svm_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	if (svm->nested.nested_run_pending)
+	if (vcpu->arch.nested_run_pending)
 		return -EBUSY;
 
 	if (svm_interrupt_blocked(vcpu))

@@ -4116,7 +4116,7 @@ static void svm_complete_soft_interrupt(struct kvm_vcpu *vcpu, u8 vector,
 	 * the soft int and will reinject it via the standard injection flow,
 	 * and so KVM needs to grab the state from the pending nested VMRUN.
 	 */
-	if (is_guest_mode(vcpu) && svm->nested.nested_run_pending)
+	if (is_guest_mode(vcpu) && vcpu->arch.nested_run_pending)
 		svm_set_nested_run_soft_int_state(vcpu);
 
 	/*

@@ -4417,11 +4417,11 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags)
 		nested_sync_control_from_vmcb02(svm);
 
 		/* Track VMRUNs that have made past consistency checking */
-		if (svm->nested.nested_run_pending &&
+		if (vcpu->arch.nested_run_pending &&
 		    svm->vmcb->control.exit_code != SVM_EXIT_ERR)
                         ++vcpu->stat.nested_run;
 
-		svm->nested.nested_run_pending = 0;
+		vcpu->arch.nested_run_pending = 0;
 	}
 
 	svm->vmcb->control.tlb_ctl = TLB_CONTROL_DO_NOTHING;

@@ -4780,7 +4780,7 @@ bool svm_smi_blocked(struct kvm_vcpu *vcpu)
 static int svm_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
-	if (svm->nested.nested_run_pending)
+	if (vcpu->arch.nested_run_pending)
 		return -EBUSY;
 
 	if (svm_smi_blocked(vcpu))

@@ -4902,7 +4902,7 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram)
 	if (ret)
 		goto unmap_save;
 
-	svm->nested.nested_run_pending = 1;
+	vcpu->arch.nested_run_pending = 1;
 
 unmap_save:
 	kvm_vcpu_unmap(vcpu, &map_save);

arch/x86/kvm/svm/svm.h +0 -4

index 85f64d9ebe59a..a213aae517b28 100644
@@ -199,10 +199,6 @@ struct svm_nested_state {
 	 */
 	void *msrpm;
 
-	/* A VMRUN has started but has not yet been performed, so
-	 * we cannot inject a nested vmexit yet.  */
-	bool nested_run_pending;
-
 	/* cache for control fields of the guest */
 	struct vmcb_ctrl_area_cached ctl;

arch/x86/kvm/vmx/nested.c +23 ~~-23~~

175 lines not on this page · raw message

arch/x86/kvm/vmx/vmx.c +8 -8

index 5bae3d5ce6eec..c36c0589cbca1 100644
@@ -5038,7 +5038,7 @@ bool vmx_nmi_blocked(struct kvm_vcpu *vcpu)
 
 int vmx_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
 {
-	if (to_vmx(vcpu)->nested.nested_run_pending)
+	if (vcpu->arch.nested_run_pending)
 		return -EBUSY;
 
 	/* An NMI must not be injected into L2 if it's supposed to VM-Exit.  */

@@ -5065,7 +5065,7 @@ bool vmx_interrupt_blocked(struct kvm_vcpu *vcpu)
 
 int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection)
 {
-	if (to_vmx(vcpu)->nested.nested_run_pending)
+	if (vcpu->arch.nested_run_pending)
 		return -EBUSY;
 
 	/*

@@ -5830,7 +5830,7 @@ static bool vmx_unhandleable_emulation_required(struct kvm_vcpu *vcpu)
 	 * only reachable if userspace modifies L2 guest state after KVM has
 	 * performed the nested VM-Enter consistency checks.
 	 */
-	if (vmx->nested.nested_run_pending)
+	if (vcpu->arch.nested_run_pending)
 		return true;
 
 	/*

@@ -6508,7 +6508,7 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 	 * invalid guest state should never happen as that means KVM knowingly
 	 * allowed a nested VM-Enter with an invalid vmcs12.  More below.
 	 */
-	if (KVM_BUG_ON(vmx->nested.nested_run_pending, vcpu->kvm))
+	if (KVM_BUG_ON(vcpu->arch.nested_run_pending, vcpu->kvm))
 		return -EIO;
 
 	if (is_guest_mode(vcpu)) {

@@ -7500,11 +7500,11 @@ fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags)
 		 * Track VMLAUNCH/VMRESUME that have made past guest state
 		 * checking.
 		 */
-		if (vmx->nested.nested_run_pending &&
+		if (vcpu->arch.nested_run_pending &&
 		    !vmx_get_exit_reason(vcpu).failed_vmentry)
 			++vcpu->stat.nested_run;
 
-		vmx->nested.nested_run_pending = 0;
+		vcpu->arch.nested_run_pending = 0;
 	}
 
 	if (unlikely(vmx->fail))

@@ -8263,7 +8263,7 @@ void vmx_setup_mce(struct kvm_vcpu *vcpu)
 int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
 {
 	/* we need a nested vmexit to enter SMM, postpone if run is pending */
-	if (to_vmx(vcpu)->nested.nested_run_pending)
+	if (vcpu->arch.nested_run_pending)
 		return -EBUSY;
 	return !is_smm(vcpu);
 }

@@ -8304,7 +8304,7 @@ int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram)
 		if (ret)
 			return ret;
 
-		vmx->nested.nested_run_pending = 1;
+		vcpu->arch.nested_run_pending = 1;
 		vmx->nested.smm.guest_mode = false;
 	}
 	return 0;

arch/x86/kvm/vmx/vmx.h +0 -3

index ea93121029f91..a6b0be1afdc37 100644
@@ -144,9 +144,6 @@ struct nested_vmx {
 	 */
 	bool enlightened_vmcs_enabled;
 
-	/* L2 must run next, and mustn't decide to exit to L1. */
-	bool nested_run_pending;
-
 	/* Pending MTF VM-exit into L1.  */
 	bool mtf_pending;

arch/x86/kvm/x86.c +33 ~~-18~~

138 lines not on this page · raw message

arch/x86/kvm/x86.h +1 -1

index f4cd73a074903..6eddad77ab7ce 100644
@@ -165,7 +165,7 @@ int kvm_check_nested_events(struct kvm_vcpu *vcpu);
 /* Forcibly leave the nested mode in cases like a vCPU reset */
 static inline void kvm_leave_nested(struct kvm_vcpu *vcpu)
 {
-	kvm_x86_ops.nested_ops->leave_nested(vcpu);
+	kvm_nested_call(leave_nested)(vcpu);
 }
 
 /*

Signature · 1 line

2.53.0

Sasha Levin

maintainer

2026-09-30 15:39 UTC #4 lore raw

PATCH 4/4 KVM: x86: Fill kvm_run exit fields in common get_nested_state_pages() error paths

In reply to Sasha Levin

From: Sean Christopherson <[email protected]>

[ Upstream commit c1214f293d77c6e425a379f90d09bdb4815993a8 ]

Note, SVM never exits to userspace if something goes sideways when dealing with vmcb12 assets while emulating VMRUN, i.e. lack of SVM-specific code is not a bug.

Fixes 0f85722341b0 ("KVM: nVMX: delay loading of PDPTRs to KVM_REQ_GET_NESTED_STATE_PAGES")

Fixes 232f75d3b4b5 ("KVM: nSVM: call nested_svm_load_cr3 on nested state load")

Fixes 3f4a812edf5c ("KVM: nSVM: hyper-v: Enable L2 TLB flush")

Cc [email protected]

Reported-by Jinwoo Lee <[email protected]>

Closes https://lore.kernel.org/all/[email protected] open here

Reported-by Stefan Teodorescu <[email protected]>

Link https://patch.msgid.link/[email protected] open here

Signed-off-by Sean Christopherson <[email protected]>

Signed-off-by Sasha Levin <[email protected]>

---
 arch/x86/kvm/svm/nested.c |  7 +------
 arch/x86/kvm/vmx/nested.c | 15 +++++----------
 arch/x86/kvm/x86.c        |  3 +++
 3 files changed, 9 insertions(+), 16 deletions(-)

arch/x86/kvm/svm/nested.c +1 -6

index c765ea1dff69c..a6b92819318b8 100644
@@ -1953,13 +1953,8 @@ static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu)
 			return false;
 	}
 
-	if (!nested_svm_merge_msrpm(vcpu)) {
-		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-		vcpu->run->internal.suberror =
-			KVM_INTERNAL_ERROR_EMULATION;
-		vcpu->run->internal.ndata = 0;
+	if (!nested_svm_merge_msrpm(vcpu))
 		return false;
-	}
 
 	if (kvm_hv_verify_vp_assist(vcpu))
 		return false;

arch/x86/kvm/vmx/nested.c +5 ~~-10~~

index cb44ae23728b3..890ee82af35d6 100644
@@ -3492,10 +3492,6 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
 		} else {
 			pr_debug_ratelimited("%s: no backing for APIC-access address in vmcs12\n",
 					     __func__);
-			vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-			vcpu->run->internal.suberror =
-				KVM_INTERNAL_ERROR_EMULATION;
-			vcpu->run->internal.ndata = 0;
 			return false;
 		}
 	}

@@ -3566,11 +3562,6 @@ static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu)
 	if (!nested_get_evmcs_page(vcpu)) {
 		pr_debug_ratelimited("%s: enlightened vmptrld failed\n",
 				     __func__);
-		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-		vcpu->run->internal.suberror =
-			KVM_INTERNAL_ERROR_EMULATION;
-		vcpu->run->internal.ndata = 0;
-
 		return false;
 	}
 #endif

@@ -3956,8 +3947,12 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 
 vmentry_failed:
 	vcpu->arch.nested_run_pending = 0;
-	if (status == NVMX_VMENTRY_KVM_INTERNAL_ERROR)
+	if (status == NVMX_VMENTRY_KVM_INTERNAL_ERROR) {
+		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+		vcpu->run->internal.ndata = 0;
 		return 0;
+	}
 	if (status == NVMX_VMENTRY_VMEXIT)
 		return 1;
 	WARN_ON_ONCE(status != NVMX_VMENTRY_VMFAIL);

arch/x86/kvm/x86.c +3 -0

index 69d48df5d1d89..c86b828ca578a 100644
@@ -10708,6 +10708,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 		if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) {
 			if (unlikely(!kvm_nested_call(get_nested_state_pages)(vcpu))) {
+				vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+				vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+				vcpu->run->internal.ndata = 0;
 				kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
 				r = 0;
 				goto out;

Signature · 1 line

2.53.0

Greg KH

2026-10-07 06:42 UTC #5 lore raw

Re: [PATCH 6.18.y 4/4] KVM: x86: Fill kvm_run exit fields in common get_nested_state_pages() error paths

Quoted 112 lines · Sasha Levin

From: Sean Christopherson <[email protected]>
[ Upstream commit c1214f293d77c6e425a379f90d09bdb4815993a8 ]
Fill kvm_run with "internal error, emulation" in the common error handling paths for getting nested state pages, as requiring each check to manually fill kvm_run is error prone and requires a non-trivial amount of copy+paste.
Specifically, both SVM and VMX fail to fill kvm_run if load_pdptrs() fails, and SVM fails to fill kvm_run if kvm_hv_verify_vp_assist() fails. If those flows fail, the *best* case scenario is that KVM will exit to userspace with KVM_EXIT_UNKNOWN. The worst case scenario is that KVM exits with a stale exit_reason and confuses userspace.
Note, SVM never exits to userspace if something goes sideways when dealing with vmcb12 assets while emulating VMRUN, i.e. lack of SVM-specific code is not a bug.
Fixes 0f85722341b0 ("KVM: nVMX: delay loading of PDPTRs to KVM_REQ_GET_NESTED_STATE_PAGES")
Fixes 232f75d3b4b5 ("KVM: nSVM: call nested_svm_load_cr3 on nested state load")
Fixes 3f4a812edf5c ("KVM: nSVM: hyper-v: Enable L2 TLB flush")
Cc [email protected]
Reported-by Jinwoo Lee <[email protected]>
Closes https://lore.kernel.org/all/[email protected] open here
Reported-by Stefan Teodorescu <[email protected]>
Link https://patch.msgid.link/[email protected] open here
Signed-off-by Sean Christopherson <[email protected]>
Signed-off-by Sasha Levin <[email protected]>
---
 arch/x86/kvm/svm/nested.c |  7 +------
 arch/x86/kvm/vmx/nested.c | 15 +++++----------
 arch/x86/kvm/x86.c        |  3 +++
 3 files changed, 9 insertions(+), 16 deletions(-)
arch/x86/kvm/svm/nested.c +1 -6
index c765ea1dff69c..a6b92819318b8 100644
@@ -1953,13 +1953,8 @@ static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu)
 			return false;
 	}
 
-	if (!nested_svm_merge_msrpm(vcpu)) {
-		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-		vcpu->run->internal.suberror =
-			KVM_INTERNAL_ERROR_EMULATION;
-		vcpu->run->internal.ndata = 0;
+	if (!nested_svm_merge_msrpm(vcpu))
 		return false;
-	}
 
 	if (kvm_hv_verify_vp_assist(vcpu))
 		return false;
arch/x86/kvm/vmx/nested.c +5 ~~-10~~
index cb44ae23728b3..890ee82af35d6 100644
@@ -3492,10 +3492,6 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
 		} else {
 			pr_debug_ratelimited("%s: no backing for APIC-access address in vmcs12\n",
 					     __func__);
-			vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-			vcpu->run->internal.suberror =
-				KVM_INTERNAL_ERROR_EMULATION;
-			vcpu->run->internal.ndata = 0;
 			return false;
 		}
 	}
@@ -3566,11 +3562,6 @@ static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu)
 	if (!nested_get_evmcs_page(vcpu)) {
 		pr_debug_ratelimited("%s: enlightened vmptrld failed\n",
 				     __func__);
-		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-		vcpu->run->internal.suberror =
-			KVM_INTERNAL_ERROR_EMULATION;
-		vcpu->run->internal.ndata = 0;
-
 		return false;
 	}
 #endif
@@ -3956,8 +3947,12 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 
 vmentry_failed:
 	vcpu->arch.nested_run_pending = 0;
-	if (status == NVMX_VMENTRY_KVM_INTERNAL_ERROR)
+	if (status == NVMX_VMENTRY_KVM_INTERNAL_ERROR) {
+		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+		vcpu->run->internal.ndata = 0;
 		return 0;
+	}
 	if (status == NVMX_VMENTRY_VMEXIT)
 		return 1;
 	WARN_ON_ONCE(status != NVMX_VMENTRY_VMFAIL);
arch/x86/kvm/x86.c +3 -0
index 69d48df5d1d89..c86b828ca578a 100644
@@ -10708,6 +10708,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 		if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) {
 			if (unlikely(!kvm_nested_call(get_nested_state_pages)(vcpu))) {
+				vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+				vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+				vcpu->run->internal.ndata = 0;
 				kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
 				r = 0;
 				goto out;
Signature · 1 line
2.53.0

Did not apply :(