[ 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; }

[ 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; }

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

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();