[PATCH 6.12.y 0/7] KVM: x86: Backports for 6.12.y

[PATCH 6.12.y 0/7] KVM: x86: Backports for 6.12.y

[Sean Christopherson]

More KVM backports, this time for 6.12.y (and with far fewer dependencies).

Same note/caveat about Sasha already posting[1][2] many/most of these:

  KVM: VMX: Allow guest to set DEBUGCTL.RTM_DEBUG if RTM is supported
  KVM: VMX: Extract checking of guest's DEBUGCTL into helper
  KVM: nVMX: Check vmcs12->guest_ia32_debugctl on nested VM-Enter
  KVM: VMX: Wrap all accesses to IA32_DEBUGCTL with getter/setter APIs

I'm including them here to hopefully make life easier for y'all, and because
the order they are presented here is the preferred ordering, i.e. should be
the same ordering as the original upstream patches.

But, if you end up grabbing Sasha's patches first, it's not a big deal as the
only true dependencies is that the DEBUGCTL.RTM_DEBUG patch needs to land
before "Check vmcs12->guest_ia32_debugctl on nested VM-Enter".

[1] https://lore.kernel.org/all/20250813182455.2068642-1-sashal@kernel.org
[2] https://lore.kernel.org/all/20250814125614.2090890-1-sashal@kernel.org

Maxim Levitsky (3):
  KVM: nVMX: Check vmcs12->guest_ia32_debugctl on nested VM-Enter
  KVM: VMX: Wrap all accesses to IA32_DEBUGCTL with getter/setter APIs
  KVM: VMX: Preserve host's DEBUGCTLMSR_FREEZE_IN_SMM while running the
    guest

Sean Christopherson (4):
  KVM: x86: Convert vcpu_run()'s immediate exit param into a generic
    bitmap
  KVM: x86: Drop kvm_x86_ops.set_dr6() in favor of a new KVM_RUN flag
  KVM: VMX: Allow guest to set DEBUGCTL.RTM_DEBUG if RTM is supported
  KVM: VMX: Extract checking of guest's DEBUGCTL into helper

 arch/x86/include/asm/kvm-x86-ops.h |  1 -
 arch/x86/include/asm/kvm_host.h    | 15 ++++++--
 arch/x86/include/asm/msr-index.h   |  1 +
 arch/x86/kvm/svm/svm.c             | 14 ++++----
 arch/x86/kvm/vmx/main.c            |  3 +-
 arch/x86/kvm/vmx/nested.c          | 21 ++++++++---
 arch/x86/kvm/vmx/pmu_intel.c       |  8 ++---
 arch/x86/kvm/vmx/vmx.c             | 57 ++++++++++++++++++------------
 arch/x86/kvm/vmx/vmx.h             | 26 ++++++++++++++
 arch/x86/kvm/vmx/x86_ops.h         |  2 +-
 arch/x86/kvm/x86.c                 | 25 ++++++++++---
 11 files changed, 125 insertions(+), 48 deletions(-)


base-commit: 8f5ff9784f3262e6e85c68d86f8b7931827f2983
-- 
2.51.0.rc1.163.g2494970778-goog

[PATCH 6.12.y 1/7] KVM: x86: Convert vcpu_run()'s immediate exit param into a generic bitmap

[Sean Christopherson]

[ Upstream commit 2478b1b220c49d25cb1c3f061ec4f9b351d9a131 ]

Convert kvm_x86_ops.vcpu_run()'s "force_immediate_exit" boolean parameter
into an a generic bitmap so that similar "take action" information can be
passed to vendor code without creating a pile of boolean parameters.

This will allow dropping kvm_x86_ops.set_dr6() in favor of a new flag, and
will also allow for adding similar functionality for re-loading debugctl
in the active VMCS.

Opportunistically massage the TDX WARN and comment to prepare for adding
more run_flags, all of which are expected to be mutually exclusive with
TDX, i.e. should be WARNed on.

No functional change intended.

Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250610232010.162191-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
[sean: drop TDX changes]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/kvm_host.h |  6 +++++-
 arch/x86/kvm/svm/svm.c          |  4 ++--
 arch/x86/kvm/vmx/vmx.c          |  3 ++-
 arch/x86/kvm/vmx/x86_ops.h      |  2 +-
 arch/x86/kvm/x86.c              | 11 ++++++++---
 5 files changed, 18 insertions(+), 8 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 0caa3293f6db..cccc8cbe72db 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1627,6 +1627,10 @@ static inline u16 kvm_lapic_irq_dest_mode(bool dest_mode_logical)
 	return dest_mode_logical ? APIC_DEST_LOGICAL : APIC_DEST_PHYSICAL;
 }
 
+enum kvm_x86_run_flags {
+	KVM_RUN_FORCE_IMMEDIATE_EXIT	= BIT(0),
+};
+
 struct kvm_x86_ops {
 	const char *name;
 
@@ -1706,7 +1710,7 @@ struct kvm_x86_ops {
 
 	int (*vcpu_pre_run)(struct kvm_vcpu *vcpu);
 	enum exit_fastpath_completion (*vcpu_run)(struct kvm_vcpu *vcpu,
-						  bool force_immediate_exit);
+						  u64 run_flags);
 	int (*handle_exit)(struct kvm_vcpu *vcpu,
 		enum exit_fastpath_completion exit_fastpath);
 	int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 1f42a71b15c0..7d1b871cfc02 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4226,9 +4226,9 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_in
 	guest_state_exit_irqoff();
 }
 
-static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu,
-					  bool force_immediate_exit)
+static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags)
 {
+	bool force_immediate_exit = run_flags & KVM_RUN_FORCE_IMMEDIATE_EXIT;
 	struct vcpu_svm *svm = to_svm(vcpu);
 	bool spec_ctrl_intercepted = msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL);
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 9a4ebf3dfbfc..2a977cdfcd0c 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -7353,8 +7353,9 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
 	guest_state_exit_irqoff();
 }
 
-fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
+fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags)
 {
+	bool force_immediate_exit = run_flags & KVM_RUN_FORCE_IMMEDIATE_EXIT;
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	unsigned long cr3, cr4;
 
diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
index 4aba200f435d..5e4ce13ab305 100644
--- a/arch/x86/kvm/vmx/x86_ops.h
+++ b/arch/x86/kvm/vmx/x86_ops.h
@@ -21,7 +21,7 @@ void vmx_vm_destroy(struct kvm *kvm);
 int vmx_vcpu_precreate(struct kvm *kvm);
 int vmx_vcpu_create(struct kvm_vcpu *vcpu);
 int vmx_vcpu_pre_run(struct kvm_vcpu *vcpu);
-fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit);
+fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags);
 void vmx_vcpu_free(struct kvm_vcpu *vcpu);
 void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event);
 void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 213af0fda768..44ab46f2a2d2 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -10711,6 +10711,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		dm_request_for_irq_injection(vcpu) &&
 		kvm_cpu_accept_dm_intr(vcpu);
 	fastpath_t exit_fastpath;
+	u64 run_flags;
 
 	bool req_immediate_exit = false;
 
@@ -10955,8 +10956,11 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		goto cancel_injection;
 	}
 
-	if (req_immediate_exit)
+	run_flags = 0;
+	if (req_immediate_exit) {
+		run_flags |= KVM_RUN_FORCE_IMMEDIATE_EXIT;
 		kvm_make_request(KVM_REQ_EVENT, vcpu);
+	}
 
 	fpregs_assert_state_consistent();
 	if (test_thread_flag(TIF_NEED_FPU_LOAD))
@@ -10992,8 +10996,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		WARN_ON_ONCE((kvm_vcpu_apicv_activated(vcpu) != kvm_vcpu_apicv_active(vcpu)) &&
 			     (kvm_get_apic_mode(vcpu) != LAPIC_MODE_DISABLED));
 
-		exit_fastpath = kvm_x86_call(vcpu_run)(vcpu,
-						       req_immediate_exit);
+		exit_fastpath = kvm_x86_call(vcpu_run)(vcpu, run_flags);
 		if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST))
 			break;
 
@@ -11005,6 +11008,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			break;
 		}
 
+		run_flags = 0;
+
 		/* Note, VM-Exits that go down the "slow" path are accounted below. */
 		++vcpu->stat.exits;
 	}
-- 
2.51.0.rc1.163.g2494970778-goog

[PATCH 6.12.y 2/7] KVM: x86: Drop kvm_x86_ops.set_dr6() in favor of a new KVM_RUN flag

[Sean Christopherson]

[ Upstream commit 80c64c7afea1da6a93ebe88d3d29d8a60377ef80 ]

Instruct vendor code to load the guest's DR6 into hardware via a new
KVM_RUN flag, and remove kvm_x86_ops.set_dr6(), whose sole purpose was to
load vcpu->arch.dr6 into hardware when DR6 can be read/written directly
by the guest.

Note, TDX already WARNs on any run_flag being set, i.e. will yell if KVM
thinks DR6 needs to be reloaded.  TDX vCPUs force KVM_DEBUGREG_AUTO_SWITCH
and never clear the flag, i.e. should never observe KVM_RUN_LOAD_GUEST_DR6.

Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250610232010.162191-4-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
[sean: drop TDX changes]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/kvm-x86-ops.h |  1 -
 arch/x86/include/asm/kvm_host.h    |  2 +-
 arch/x86/kvm/svm/svm.c             | 10 ++++++----
 arch/x86/kvm/vmx/main.c            |  1 -
 arch/x86/kvm/vmx/vmx.c             |  9 +++------
 arch/x86/kvm/x86.c                 |  2 +-
 6 files changed, 11 insertions(+), 14 deletions(-)

diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index cfb22f8c451a..861d080ed4c6 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -47,7 +47,6 @@ KVM_X86_OP(set_idt)
 KVM_X86_OP(get_gdt)
 KVM_X86_OP(set_gdt)
 KVM_X86_OP(sync_dirty_debug_regs)
-KVM_X86_OP(set_dr6)
 KVM_X86_OP(set_dr7)
 KVM_X86_OP(cache_reg)
 KVM_X86_OP(get_rflags)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index cccc8cbe72db..2ed05925d9d5 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1629,6 +1629,7 @@ static inline u16 kvm_lapic_irq_dest_mode(bool dest_mode_logical)
 
 enum kvm_x86_run_flags {
 	KVM_RUN_FORCE_IMMEDIATE_EXIT	= BIT(0),
+	KVM_RUN_LOAD_GUEST_DR6		= BIT(1),
 };
 
 struct kvm_x86_ops {
@@ -1679,7 +1680,6 @@ struct kvm_x86_ops {
 	void (*get_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
 	void (*set_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
 	void (*sync_dirty_debug_regs)(struct kvm_vcpu *vcpu);
-	void (*set_dr6)(struct kvm_vcpu *vcpu, unsigned long value);
 	void (*set_dr7)(struct kvm_vcpu *vcpu, unsigned long value);
 	void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg);
 	unsigned long (*get_rflags)(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 7d1b871cfc02..800f781475c0 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4270,10 +4270,13 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags)
 	svm_hv_update_vp_id(svm->vmcb, vcpu);
 
 	/*
-	 * Run with all-zero DR6 unless needed, so that we can get the exact cause
-	 * of a #DB.
+	 * Run with all-zero DR6 unless the guest can write DR6 freely, so that
+	 * KVM can get the exact cause of a #DB.  Note, loading guest DR6 from
+	 * KVM's snapshot is only necessary when DR accesses won't exit.
 	 */
-	if (likely(!(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)))
+	if (unlikely(run_flags & KVM_RUN_LOAD_GUEST_DR6))
+		svm_set_dr6(vcpu, vcpu->arch.dr6);
+	else if (likely(!(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)))
 		svm_set_dr6(vcpu, DR6_ACTIVE_LOW);
 
 	clgi();
@@ -5084,7 +5087,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.set_idt = svm_set_idt,
 	.get_gdt = svm_get_gdt,
 	.set_gdt = svm_set_gdt,
-	.set_dr6 = svm_set_dr6,
 	.set_dr7 = svm_set_dr7,
 	.sync_dirty_debug_regs = svm_sync_dirty_debug_regs,
 	.cache_reg = svm_cache_reg,
diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
index 47476fcc179a..7668e2fb8043 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -60,7 +60,6 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.set_idt = vmx_set_idt,
 	.get_gdt = vmx_get_gdt,
 	.set_gdt = vmx_set_gdt,
-	.set_dr6 = vmx_set_dr6,
 	.set_dr7 = vmx_set_dr7,
 	.sync_dirty_debug_regs = vmx_sync_dirty_debug_regs,
 	.cache_reg = vmx_cache_reg,
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 2a977cdfcd0c..b9c7940feac6 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -5630,12 +5630,6 @@ void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
 	set_debugreg(DR6_RESERVED, 6);
 }
 
-void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val)
-{
-	lockdep_assert_irqs_disabled();
-	set_debugreg(vcpu->arch.dr6, 6);
-}
-
 void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val)
 {
 	vmcs_writel(GUEST_DR7, val);
@@ -7400,6 +7394,9 @@ fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags)
 		vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
 	vcpu->arch.regs_dirty = 0;
 
+	if (run_flags & KVM_RUN_LOAD_GUEST_DR6)
+		set_debugreg(vcpu->arch.dr6, 6);
+
 	/*
 	 * Refresh vmcs.HOST_CR3 if necessary.  This must be done immediately
 	 * prior to VM-Enter, as the kernel may load a new ASID (PCID) any time
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 44ab46f2a2d2..7beea8fb6ea6 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -10977,7 +10977,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		set_debugreg(vcpu->arch.eff_db[3], 3);
 		/* When KVM_DEBUGREG_WONT_EXIT, dr6 is accessible in guest. */
 		if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT))
-			kvm_x86_call(set_dr6)(vcpu, vcpu->arch.dr6);
+			run_flags |= KVM_RUN_LOAD_GUEST_DR6;
 	} else if (unlikely(hw_breakpoint_active())) {
 		set_debugreg(DR7_FIXED_1, 7);
 	}
-- 
2.51.0.rc1.163.g2494970778-goog

[PATCH 6.12.y 3/7] KVM: VMX: Allow guest to set DEBUGCTL.RTM_DEBUG if RTM is supported

[Sean Christopherson]

[ Upstream commit 17ec2f965344ee3fd6620bef7ef68792f4ac3af0 ]

Let the guest set DEBUGCTL.RTM_DEBUG if RTM is supported according to the
guest CPUID model, as debug support is supposed to be available if RTM is
supported, and there are no known downsides to letting the guest debug RTM
aborts.

Note, there are no known bug reports related to RTM_DEBUG, the primary
motivation is to reduce the probability of breaking existing guests when a
future change adds a missing consistency check on vmcs12.GUEST_DEBUGCTL
(KVM currently lets L2 run with whatever hardware supports; whoops).

Note #2, KVM already emulates DR6.RTM, and doesn't restrict access to
DR7.RTM.

Fixes: 83c529151ab0 ("KVM: x86: expose Intel cpu new features (HLE, RTM) to guest")
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250610232010.162191-5-seanjc@google.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/msr-index.h | 1 +
 arch/x86/kvm/vmx/vmx.c           | 4 ++++
 2 files changed, 5 insertions(+)

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 7ebe76f69417..2b6e3127ef4e 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -417,6 +417,7 @@
 #define DEBUGCTLMSR_FREEZE_PERFMON_ON_PMI	(1UL << 12)
 #define DEBUGCTLMSR_FREEZE_IN_SMM_BIT	14
 #define DEBUGCTLMSR_FREEZE_IN_SMM	(1UL << DEBUGCTLMSR_FREEZE_IN_SMM_BIT)
+#define DEBUGCTLMSR_RTM_DEBUG		BIT(15)
 
 #define MSR_PEBS_FRONTEND		0x000003f7
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index b9c7940feac6..529a10bba056 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2185,6 +2185,10 @@ static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated
 	    (host_initiated || intel_pmu_lbr_is_enabled(vcpu)))
 		debugctl |= DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI;
 
+	if (boot_cpu_has(X86_FEATURE_RTM) &&
+	    (host_initiated || guest_cpuid_has(vcpu, X86_FEATURE_RTM)))
+		debugctl |= DEBUGCTLMSR_RTM_DEBUG;
+
 	return debugctl;
 }
 
-- 
2.51.0.rc1.163.g2494970778-goog

[PATCH 6.12.y 4/7] KVM: VMX: Extract checking of guest's DEBUGCTL into helper

[Sean Christopherson]

[ Upstream commit 8a4351ac302cd8c19729ba2636acfd0467c22ae8 ]

Move VMX's logic to check DEBUGCTL values into a standalone helper so that
the code can be used by nested VM-Enter to apply the same logic to the
value being loaded from vmcs12.

KVM needs to explicitly check vmcs12->guest_ia32_debugctl on nested
VM-Enter, as hardware may support features that KVM does not, i.e. relying
on hardware to detect invalid guest state will result in false negatives.
Unfortunately, that means applying KVM's funky suppression of BTF and LBR
to vmcs12 so as not to break existing guests.

No functional change intended.

Reviewed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Link: https://lore.kernel.org/r/20250610232010.162191-6-seanjc@google.com
Stable-dep-of: 7d0cce6cbe71 ("KVM: VMX: Wrap all accesses to IA32_DEBUGCTL with getter/setter APIs")
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/vmx/vmx.c | 29 +++++++++++++++++------------
 1 file changed, 17 insertions(+), 12 deletions(-)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 529a10bba056..ff61093e9af7 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2192,6 +2192,19 @@ static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated
 	return debugctl;
 }
 
+static bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data,
+				  bool host_initiated)
+{
+	u64 invalid;
+
+	invalid = data & ~vmx_get_supported_debugctl(vcpu, host_initiated);
+	if (invalid & (DEBUGCTLMSR_BTF | DEBUGCTLMSR_LBR)) {
+		kvm_pr_unimpl_wrmsr(vcpu, MSR_IA32_DEBUGCTLMSR, data);
+		invalid &= ~(DEBUGCTLMSR_BTF | DEBUGCTLMSR_LBR);
+	}
+	return !invalid;
+}
+
 /*
  * Writes msr value into the appropriate "register".
  * Returns 0 on success, non-0 otherwise.
@@ -2260,19 +2273,12 @@ int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		}
 		vmcs_writel(GUEST_SYSENTER_ESP, data);
 		break;
-	case MSR_IA32_DEBUGCTLMSR: {
-		u64 invalid;
-
-		invalid = data & ~vmx_get_supported_debugctl(vcpu, msr_info->host_initiated);
-		if (invalid & (DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR)) {
-			kvm_pr_unimpl_wrmsr(vcpu, msr_index, data);
-			data &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR);
-			invalid &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR);
-		}
-
-		if (invalid)
+	case MSR_IA32_DEBUGCTLMSR:
+		if (!vmx_is_valid_debugctl(vcpu, data, msr_info->host_initiated))
 			return 1;
 
+		data &= vmx_get_supported_debugctl(vcpu, msr_info->host_initiated);
+
 		if (is_guest_mode(vcpu) && get_vmcs12(vcpu)->vm_exit_controls &
 						VM_EXIT_SAVE_DEBUG_CONTROLS)
 			get_vmcs12(vcpu)->guest_ia32_debugctl = data;
@@ -2282,7 +2288,6 @@ int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		    (data & DEBUGCTLMSR_LBR))
 			intel_pmu_create_guest_lbr_event(vcpu);
 		return 0;
-	}
 	case MSR_IA32_BNDCFGS:
 		if (!kvm_mpx_supported() ||
 		    (!msr_info->host_initiated &&
-- 
2.51.0.rc1.163.g2494970778-goog

[PATCH 6.12.y 5/7] KVM: nVMX: Check vmcs12->guest_ia32_debugctl on nested VM-Enter

[Sean Christopherson]

From: Maxim Levitsky <mlevitsk@redhat.com>

[ Upstream commit 095686e6fcb4150f0a55b1a25987fad3d8af58d6 ]

Add a consistency check for L2's guest_ia32_debugctl, as KVM only supports
a subset of hardware functionality, i.e. KVM can't rely on hardware to
detect illegal/unsupported values.  Failure to check the vmcs12 value
would allow the guest to load any harware-supported value while running L2.

Take care to exempt BTF and LBR from the validity check in order to match
KVM's behavior for writes via WRMSR, but without clobbering vmcs12.  Even
if VM_EXIT_SAVE_DEBUG_CONTROLS is set in vmcs12, L1 can reasonably expect
that vmcs12->guest_ia32_debugctl will not be modified if writes to the MSR
are being intercepted.

Arguably, KVM _should_ update vmcs12 if VM_EXIT_SAVE_DEBUG_CONTROLS is set
*and* writes to MSR_IA32_DEBUGCTLMSR are not being intercepted by L1, but
that would incur non-trivial complexity and wouldn't change the fact that
KVM's handling of DEBUGCTL is blatantly broken.  I.e. the extra complexity
is not worth carrying.

Cc: stable@vger.kernel.org
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/r/20250610232010.162191-7-seanjc@google.com
Stable-dep-of: 7d0cce6cbe71 ("KVM: VMX: Wrap all accesses to IA32_DEBUGCTL with getter/setter APIs")
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/vmx/nested.c | 12 ++++++++++--
 arch/x86/kvm/vmx/vmx.c    |  5 ++---
 arch/x86/kvm/vmx/vmx.h    |  3 +++
 3 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 903e874041ac..1e0b9f92ff18 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2653,7 +2653,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	if (vmx->nested.nested_run_pending &&
 	    (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) {
 		kvm_set_dr(vcpu, 7, vmcs12->guest_dr7);
-		vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl);
+		vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl &
+						  vmx_get_supported_debugctl(vcpu, false));
 	} else {
 		kvm_set_dr(vcpu, 7, vcpu->arch.dr7);
 		vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.pre_vmenter_debugctl);
@@ -3135,7 +3136,8 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 
 	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) &&
-	    CC(!kvm_dr7_valid(vmcs12->guest_dr7)))
+	    (CC(!kvm_dr7_valid(vmcs12->guest_dr7)) ||
+	     CC(!vmx_is_valid_debugctl(vcpu, vmcs12->guest_ia32_debugctl, false))))
 		return -EINVAL;
 
 	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) &&
@@ -4576,6 +4578,12 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 		(vmcs12->vm_entry_controls & ~VM_ENTRY_IA32E_MODE) |
 		(vm_entry_controls_get(to_vmx(vcpu)) & VM_ENTRY_IA32E_MODE);
 
+	/*
+	 * Note!  Save DR7, but intentionally don't grab DEBUGCTL from vmcs02.
+	 * Writes to DEBUGCTL that aren't intercepted by L1 are immediately
+	 * propagated to vmcs12 (see vmx_set_msr()), as the value loaded into
+	 * vmcs02 doesn't strictly track vmcs12.
+	 */
 	if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS)
 		vmcs12->guest_dr7 = vcpu->arch.dr7;
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index ff61093e9af7..50d45c18fce9 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2173,7 +2173,7 @@ static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu,
 	return (unsigned long)data;
 }
 
-static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated)
+u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated)
 {
 	u64 debugctl = 0;
 
@@ -2192,8 +2192,7 @@ static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated
 	return debugctl;
 }
 
-static bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data,
-				  bool host_initiated)
+bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated)
 {
 	u64 invalid;
 
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index cf57fbf12104..ee330d14089d 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -435,6 +435,9 @@ static inline void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr,
 
 void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu);
 
+u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated);
+bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated);
+
 /*
  * Note, early Intel manuals have the write-low and read-high bitmap offsets
  * the wrong way round.  The bitmaps control MSRs 0x00000000-0x00001fff and
-- 
2.51.0.rc1.163.g2494970778-goog

[PATCH 6.12.y 6/7] KVM: VMX: Wrap all accesses to IA32_DEBUGCTL with getter/setter APIs

[Sean Christopherson]

From: Maxim Levitsky <mlevitsk@redhat.com>

[ Upstream commit 7d0cce6cbe71af6e9c1831bff101a2b9c249c4a2 ]

Introduce vmx_guest_debugctl_{read,write}() to handle all accesses to
vmcs.GUEST_IA32_DEBUGCTL. This will allow stuffing FREEZE_IN_SMM into
GUEST_IA32_DEBUGCTL based on the host setting without bleeding the state
into the guest, and without needing to copy+paste the FREEZE_IN_SMM
logic into every patch that accesses GUEST_IA32_DEBUGCTL.

No functional change intended.

Cc: stable@vger.kernel.org
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
[sean: massage changelog, make inline, use in all prepare_vmcs02() cases]
Reviewed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Link: https://lore.kernel.org/r/20250610232010.162191-8-seanjc@google.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/vmx/nested.c    | 10 +++++-----
 arch/x86/kvm/vmx/pmu_intel.c |  8 ++++----
 arch/x86/kvm/vmx/vmx.c       |  8 +++++---
 arch/x86/kvm/vmx/vmx.h       | 10 ++++++++++
 4 files changed, 24 insertions(+), 12 deletions(-)

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 1e0b9f92ff18..9a336f661fc6 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2653,11 +2653,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	if (vmx->nested.nested_run_pending &&
 	    (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) {
 		kvm_set_dr(vcpu, 7, vmcs12->guest_dr7);
-		vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl &
-						  vmx_get_supported_debugctl(vcpu, false));
+		vmx_guest_debugctl_write(vcpu, vmcs12->guest_ia32_debugctl &
+					       vmx_get_supported_debugctl(vcpu, false));
 	} else {
 		kvm_set_dr(vcpu, 7, vcpu->arch.dr7);
-		vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.pre_vmenter_debugctl);
+		vmx_guest_debugctl_write(vcpu, vmx->nested.pre_vmenter_debugctl);
 	}
 	if (kvm_mpx_supported() && (!vmx->nested.nested_run_pending ||
 	    !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)))
@@ -3527,7 +3527,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
 
 	if (!vmx->nested.nested_run_pending ||
 	    !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS))
-		vmx->nested.pre_vmenter_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);
+		vmx->nested.pre_vmenter_debugctl = vmx_guest_debugctl_read();
 	if (kvm_mpx_supported() &&
 	    (!vmx->nested.nested_run_pending ||
 	     !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)))
@@ -4774,7 +4774,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 	__vmx_set_segment(vcpu, &seg, VCPU_SREG_LDTR);
 
 	kvm_set_dr(vcpu, 7, 0x400);
-	vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
+	vmx_guest_debugctl_write(vcpu, 0);
 
 	if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr,
 				vmcs12->vm_exit_msr_load_count))
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 9c9d4a336166..a5edc623166a 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -605,11 +605,11 @@ static void intel_pmu_reset(struct kvm_vcpu *vcpu)
  */
 static void intel_pmu_legacy_freezing_lbrs_on_pmi(struct kvm_vcpu *vcpu)
 {
-	u64 data = vmcs_read64(GUEST_IA32_DEBUGCTL);
+	u64 data = vmx_guest_debugctl_read();
 
 	if (data & DEBUGCTLMSR_FREEZE_LBRS_ON_PMI) {
 		data &= ~DEBUGCTLMSR_LBR;
-		vmcs_write64(GUEST_IA32_DEBUGCTL, data);
+		vmx_guest_debugctl_write(vcpu, data);
 	}
 }
 
@@ -679,7 +679,7 @@ void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu)
 
 	if (!lbr_desc->event) {
 		vmx_disable_lbr_msrs_passthrough(vcpu);
-		if (vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR)
+		if (vmx_guest_debugctl_read() & DEBUGCTLMSR_LBR)
 			goto warn;
 		if (test_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use))
 			goto warn;
@@ -701,7 +701,7 @@ void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu)
 
 static void intel_pmu_cleanup(struct kvm_vcpu *vcpu)
 {
-	if (!(vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR))
+	if (!(vmx_guest_debugctl_read() & DEBUGCTLMSR_LBR))
 		intel_pmu_release_guest_lbr_event(vcpu);
 }
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 50d45c18fce9..4bb25519e7ce 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2148,7 +2148,7 @@ int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			msr_info->data = vmx->pt_desc.guest.addr_a[index / 2];
 		break;
 	case MSR_IA32_DEBUGCTLMSR:
-		msr_info->data = vmcs_read64(GUEST_IA32_DEBUGCTL);
+		msr_info->data = vmx_guest_debugctl_read();
 		break;
 	default:
 	find_uret_msr:
@@ -2282,7 +2282,8 @@ int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 						VM_EXIT_SAVE_DEBUG_CONTROLS)
 			get_vmcs12(vcpu)->guest_ia32_debugctl = data;
 
-		vmcs_write64(GUEST_IA32_DEBUGCTL, data);
+		vmx_guest_debugctl_write(vcpu, data);
+
 		if (intel_pmu_lbr_is_enabled(vcpu) && !to_vmx(vcpu)->lbr_desc.event &&
 		    (data & DEBUGCTLMSR_LBR))
 			intel_pmu_create_guest_lbr_event(vcpu);
@@ -4831,7 +4832,8 @@ static void init_vmcs(struct vcpu_vmx *vmx)
 	vmcs_write32(GUEST_SYSENTER_CS, 0);
 	vmcs_writel(GUEST_SYSENTER_ESP, 0);
 	vmcs_writel(GUEST_SYSENTER_EIP, 0);
-	vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
+
+	vmx_guest_debugctl_write(&vmx->vcpu, 0);
 
 	if (cpu_has_vmx_tpr_shadow()) {
 		vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0);
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index ee330d14089d..5b2c5cb5e32e 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -438,6 +438,16 @@ void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu);
 u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated);
 bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated);
 
+static inline void vmx_guest_debugctl_write(struct kvm_vcpu *vcpu, u64 val)
+{
+	vmcs_write64(GUEST_IA32_DEBUGCTL, val);
+}
+
+static inline u64 vmx_guest_debugctl_read(void)
+{
+	return vmcs_read64(GUEST_IA32_DEBUGCTL);
+}
+
 /*
  * Note, early Intel manuals have the write-low and read-high bitmap offsets
  * the wrong way round.  The bitmaps control MSRs 0x00000000-0x00001fff and
-- 
2.51.0.rc1.163.g2494970778-goog

[PATCH 6.12.y 7/7] KVM: VMX: Preserve host's DEBUGCTLMSR_FREEZE_IN_SMM while running the guest

[Sean Christopherson]

From: Maxim Levitsky <mlevitsk@redhat.com>

[ Upstream commit 6b1dd26544d045f6a79e8c73572c0c0db3ef3c1a ]

Set/clear DEBUGCTLMSR_FREEZE_IN_SMM in GUEST_IA32_DEBUGCTL based on the
host's pre-VM-Enter value, i.e. preserve the host's FREEZE_IN_SMM setting
while running the guest.  When running with the "default treatment of SMIs"
in effect (the only mode KVM supports), SMIs do not generate a VM-Exit that
is visible to host (non-SMM) software, and instead transitions directly
from VMX non-root to SMM.  And critically, DEBUGCTL isn't context switched
by hardware on SMI or RSM, i.e. SMM will run with whatever value was
resident in hardware at the time of the SMI.

Failure to preserve FREEZE_IN_SMM results in the PMU unexpectedly counting
events while the CPU is executing in SMM, which can pollute profiling and
potentially leak information into the guest.

Check for changes in FREEZE_IN_SMM prior to every entry into KVM's inner
run loop, as the bit can be toggled in IRQ context via IPI callback (SMP
function call), by way of /sys/devices/cpu/freeze_on_smi.

Add a field in kvm_x86_ops to communicate which DEBUGCTL bits need to be
preserved, as FREEZE_IN_SMM is only supported and defined for Intel CPUs,
i.e. explicitly checking FREEZE_IN_SMM in common x86 is at best weird, and
at worst could lead to undesirable behavior in the future if AMD CPUs ever
happened to pick up a collision with the bit.

Exempt TDX vCPUs, i.e. protected guests, from the check, as the TDX Module
owns and controls GUEST_IA32_DEBUGCTL.

WARN in SVM if KVM_RUN_LOAD_DEBUGCTL is set, mostly to document that the
lack of handling isn't a KVM bug (TDX already WARNs on any run_flag).

Lastly, explicitly reload GUEST_IA32_DEBUGCTL on a VM-Fail that is missed
by KVM but detected by hardware, i.e. in nested_vmx_restore_host_state().
Doing so avoids the need to track host_debugctl on a per-VMCS basis, as
GUEST_IA32_DEBUGCTL is unconditionally written by prepare_vmcs02() and
load_vmcs12_host_state().  For the VM-Fail case, even though KVM won't
have actually entered the guest, vcpu_enter_guest() will have run with
vmcs02 active and thus could result in vmcs01 being run with a stale value.

Cc: stable@vger.kernel.org
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/r/20250610232010.162191-9-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
[sean: resolve syntactic conflict in vt_x86_ops definition]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/kvm_host.h |  7 +++++++
 arch/x86/kvm/vmx/main.c         |  2 ++
 arch/x86/kvm/vmx/nested.c       |  3 +++
 arch/x86/kvm/vmx/vmx.c          |  3 +++
 arch/x86/kvm/vmx/vmx.h          | 15 ++++++++++++++-
 arch/x86/kvm/x86.c              | 14 ++++++++++++--
 6 files changed, 41 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 2ed05925d9d5..d27df86aa62c 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1630,6 +1630,7 @@ static inline u16 kvm_lapic_irq_dest_mode(bool dest_mode_logical)
 enum kvm_x86_run_flags {
 	KVM_RUN_FORCE_IMMEDIATE_EXIT	= BIT(0),
 	KVM_RUN_LOAD_GUEST_DR6		= BIT(1),
+	KVM_RUN_LOAD_DEBUGCTL		= BIT(2),
 };
 
 struct kvm_x86_ops {
@@ -1659,6 +1660,12 @@ struct kvm_x86_ops {
 	void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu);
 	void (*vcpu_put)(struct kvm_vcpu *vcpu);
 
+	/*
+	 * Mask of DEBUGCTL bits that are owned by the host, i.e. that need to
+	 * match the host's value even while the guest is active.
+	 */
+	const u64 HOST_OWNED_DEBUGCTL;
+
 	void (*update_exception_bitmap)(struct kvm_vcpu *vcpu);
 	int (*get_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr);
 	int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr);
diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
index 7668e2fb8043..3f83e36a657b 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -42,6 +42,8 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.vcpu_load = vmx_vcpu_load,
 	.vcpu_put = vmx_vcpu_put,
 
+	.HOST_OWNED_DEBUGCTL = DEBUGCTLMSR_FREEZE_IN_SMM,
+
 	.update_exception_bitmap = vmx_update_exception_bitmap,
 	.get_feature_msr = vmx_get_feature_msr,
 	.get_msr = vmx_get_msr,
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 9a336f661fc6..60bd2791d933 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -4829,6 +4829,9 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu)
 			WARN_ON(kvm_set_dr(vcpu, 7, vmcs_readl(GUEST_DR7)));
 	}
 
+	/* Reload DEBUGCTL to ensure vmcs01 has a fresh FREEZE_IN_SMM value. */
+	vmx_reload_guest_debugctl(vcpu);
+
 	/*
 	 * Note that calling vmx_set_{efer,cr0,cr4} is important as they
 	 * handle a variety of side effects to KVM's software model.
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 4bb25519e7ce..6c185a260c5b 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -7407,6 +7407,9 @@ fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags)
 	if (run_flags & KVM_RUN_LOAD_GUEST_DR6)
 		set_debugreg(vcpu->arch.dr6, 6);
 
+	if (run_flags & KVM_RUN_LOAD_DEBUGCTL)
+		vmx_reload_guest_debugctl(vcpu);
+
 	/*
 	 * Refresh vmcs.HOST_CR3 if necessary.  This must be done immediately
 	 * prior to VM-Enter, as the kernel may load a new ASID (PCID) any time
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 5b2c5cb5e32e..a7e2de50d27f 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -440,12 +440,25 @@ bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated)
 
 static inline void vmx_guest_debugctl_write(struct kvm_vcpu *vcpu, u64 val)
 {
+	WARN_ON_ONCE(val & DEBUGCTLMSR_FREEZE_IN_SMM);
+
+	val |= vcpu->arch.host_debugctl & DEBUGCTLMSR_FREEZE_IN_SMM;
 	vmcs_write64(GUEST_IA32_DEBUGCTL, val);
 }
 
 static inline u64 vmx_guest_debugctl_read(void)
 {
-	return vmcs_read64(GUEST_IA32_DEBUGCTL);
+	return vmcs_read64(GUEST_IA32_DEBUGCTL) & ~DEBUGCTLMSR_FREEZE_IN_SMM;
+}
+
+static inline void vmx_reload_guest_debugctl(struct kvm_vcpu *vcpu)
+{
+	u64 val = vmcs_read64(GUEST_IA32_DEBUGCTL);
+
+	if (!((val ^ vcpu->arch.host_debugctl) & DEBUGCTLMSR_FREEZE_IN_SMM))
+		return;
+
+	vmx_guest_debugctl_write(vcpu, val & ~DEBUGCTLMSR_FREEZE_IN_SMM);
 }
 
 /*
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 7beea8fb6ea6..dbd295ef3eba 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -10711,7 +10711,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		dm_request_for_irq_injection(vcpu) &&
 		kvm_cpu_accept_dm_intr(vcpu);
 	fastpath_t exit_fastpath;
-	u64 run_flags;
+	u64 run_flags, debug_ctl;
 
 	bool req_immediate_exit = false;
 
@@ -10982,7 +10982,17 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		set_debugreg(DR7_FIXED_1, 7);
 	}
 
-	vcpu->arch.host_debugctl = get_debugctlmsr();
+	/*
+	 * Refresh the host DEBUGCTL snapshot after disabling IRQs, as DEBUGCTL
+	 * can be modified in IRQ context, e.g. via SMP function calls.  Inform
+	 * vendor code if any host-owned bits were changed, e.g. so that the
+	 * value loaded into hardware while running the guest can be updated.
+	 */
+	debug_ctl = get_debugctlmsr();
+	if ((debug_ctl ^ vcpu->arch.host_debugctl) & kvm_x86_ops.HOST_OWNED_DEBUGCTL &&
+	    !vcpu->arch.guest_state_protected)
+		run_flags |= KVM_RUN_LOAD_DEBUGCTL;
+	vcpu->arch.host_debugctl = debug_ctl;
 
 	guest_timing_enter_irqoff();
 
-- 
2.51.0.rc1.163.g2494970778-goog

Re: [PATCH 6.12.y 0/7] KVM: x86: Backports for 6.12.y

[Sasha Levin]

On Thu, Aug 14, 2025 at 05:57:18PM -0700, Sean Christopherson wrote:
>More KVM backports, this time for 6.12.y (and with far fewer dependencies).
>
>Same note/caveat about Sasha already posting[1][2] many/most of these:

I've queued your backports up, thanks :)