Re: CPU Lockups in KVM with deferred hrtimer rearming

[Sean Christopherson <seanjc@google.com>]

On Tue, Apr 21, 2026, Peter Zijlstra wrote:
> On Tue, Apr 21, 2026 at 08:57:24PM +0000, Sean Christopherson wrote:
> > This as delta? (I had typed this all up before Peter posted a new verison, so
> > dammit I'm sending it!)
> 
> :-)
> 
> I'll go stare at it in the morning, I'm about to go crash out.

New delta against your effective v2, builds all of my configs (which isn't _that_
many, but I think they cover most of the weirder ways to include KVM (or not)).

I'll start testing the full thing to try and get early signal on the health.

diff --git arch/x86/entry/common.c arch/x86/entry/common.c
index 8de94a590b26..0532c1b65dd9 100644
--- arch/x86/entry/common.c
+++ arch/x86/entry/common.c
@@ -6,6 +6,15 @@
 #include <asm/fred.h>
 #include <asm/desc.h>
 
+#if IS_ENABLED(CONFIG_KVM_INTEL)
+/*
+ * On VMX, NMIs and IRQs (as configured by KVM) are acknowledge by hardware as
+ * part of the VM-Exit, i.e. the event itself is consumed as part the VM-Exit.
+ * x86_entry_from_kvm() is invoked by KVM to effectively forward NMIs and IRQs
+ * to the kernel for servicing.  On SVM, a.k.a. AMD, the NMI/IRQ VM-Exit is
+ * purely a signal that an NMI/IRQ is pending, i.e. the event that triggered
+ * the VM-Exit is held pending until it's unblocked in the host.
+ */
 noinstr void x86_entry_from_kvm(unsigned int event_type, unsigned int vector)
 {
 #ifdef CONFIG_X86_64
@@ -20,3 +29,4 @@ noinstr void x86_entry_from_kvm(unsigned int event_type, unsigned int vector)
        }
 }
 EXPORT_SYMBOL_FOR_KVM(x86_entry_from_kvm);
+#endif
diff --git arch/x86/include/asm/fred.h arch/x86/include/asm/fred.h
index 2bb65677c079..18a2f811c358 100644
--- arch/x86/include/asm/fred.h
+++ arch/x86/include/asm/fred.h
@@ -110,7 +110,6 @@ static __always_inline unsigned long fred_event_data(struct pt_regs *regs) { ret
 static inline void cpu_init_fred_exceptions(void) { }
 static inline void cpu_init_fred_rsps(void) { }
 static inline void fred_complete_exception_setup(void) { }
-static inline void fred_entry_from_kvm(unsigned int type, unsigned int vector) { }
 static inline void fred_sync_rsp0(unsigned long rsp0) { }
 static inline void fred_update_rsp0(void) { }
 #endif /* CONFIG_X86_FRED */
diff --git arch/x86/kernel/idt.c arch/x86/kernel/idt.c
index d95d8d196cd4..d69d27846424 100644
--- arch/x86/kernel/idt.c
+++ arch/x86/kernel/idt.c
@@ -267,7 +267,7 @@ void __init idt_setup_early_pf(void)
                             ARRAY_SIZE(early_pf_idts), true);
 }
 #else
-void idt_entry_from_kvm(unsigned int vector)
+noinstr void idt_entry_from_kvm(unsigned int vector)
 {
        if (vector == NMI_VECTOR)
                idt_do_nmi_irqoff();
diff --git arch/x86/kvm/vmx/vmx.c arch/x86/kvm/vmx/vmx.c
index f6f5c124ed3b..753f0dbb9cf8 100644
--- arch/x86/kvm/vmx/vmx.c
+++ arch/x86/kvm/vmx/vmx.c
@@ -7083,9 +7083,6 @@ void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
        vmcs_write64(EOI_EXIT_BITMAP3, eoi_exit_bitmap[3]);
 }
 
-void vmx_do_interrupt_irqoff(unsigned long entry);
-void vmx_do_nmi_irqoff(void);
-
 static void handle_nm_fault_irqoff(struct kvm_vcpu *vcpu)
 {
        /*