[PATCH v3 53/62] KVM: x86: Decouple device assignment from IRQ bypass
From: Sean Christopherson <seanjc@google.com>
Date: 2025-06-11 22:48:28
Also in:
kvm, kvmarm, linux-iommu, lkml
Subsystem:
kernel virtual machine for x86 (kvm/x86), the rest, x86 architecture (32-bit and 64-bit) · Maintainers:
Sean Christopherson, Paolo Bonzini, Linus Torvalds, Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen
Use a dedicated counter to track the number of IRQs that can utilize IRQ
bypass instead of piggybacking the assigned device count. As evidenced by
commit 2edd9cb79fb3 ("kvm: detect assigned device via irqbypass manager"),
it's possible for a device to be able to post IRQs to a vCPU without said
device being assigned to a VM.
Leave the calls to kvm_arch_{start,end}_assignment() alone for the moment
to avoid regressing the MMIO stale data mitigation. KVM is abusing the
assigned device count when applying mmio_stale_data_clear, and it's not at
all clear if vDPA devices rely on this behavior. This will hopefully be
cleaned up in the future, as the number of assigned devices is a terrible
heuristic for detecting if a VM has access to host MMIO.
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
arch/x86/include/asm/kvm-x86-ops.h | 2 +-
arch/x86/include/asm/kvm_host.h | 4 +++-
arch/x86/kvm/irq.c | 9 ++++++++-
arch/x86/kvm/vmx/main.c | 2 +-
arch/x86/kvm/vmx/posted_intr.c | 16 ++++++++++------
arch/x86/kvm/vmx/posted_intr.h | 2 +-
arch/x86/kvm/x86.c | 3 +--
7 files changed, 25 insertions(+), 13 deletions(-)
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 8d50e3e0a19b..8897f509860c 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h@@ -112,7 +112,7 @@ KVM_X86_OP_OPTIONAL(update_cpu_dirty_logging) KVM_X86_OP_OPTIONAL(vcpu_blocking) KVM_X86_OP_OPTIONAL(vcpu_unblocking) KVM_X86_OP_OPTIONAL(pi_update_irte) -KVM_X86_OP_OPTIONAL(pi_start_assignment) +KVM_X86_OP_OPTIONAL(pi_start_bypass) KVM_X86_OP_OPTIONAL(apicv_pre_state_restore) KVM_X86_OP_OPTIONAL(apicv_post_state_restore) KVM_X86_OP_OPTIONAL_RET0(dy_apicv_has_pending_interrupt)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index c722adfedd96..01edcefbd937 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h@@ -1382,6 +1382,8 @@ struct kvm_arch { atomic_t noncoherent_dma_count; #define __KVM_HAVE_ARCH_ASSIGNED_DEVICE atomic_t assigned_device_count; + unsigned long nr_possible_bypass_irqs; + #ifdef CONFIG_KVM_IOAPIC struct kvm_pic *vpic; struct kvm_ioapic *vioapic;
@@ -1855,7 +1857,7 @@ struct kvm_x86_ops { int (*pi_update_irte)(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, struct kvm_vcpu *vcpu, u32 vector); - void (*pi_start_assignment)(struct kvm *kvm); + void (*pi_start_bypass)(struct kvm *kvm); void (*apicv_pre_state_restore)(struct kvm_vcpu *vcpu); void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu); bool (*dy_apicv_has_pending_interrupt)(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index 02efa7162252..3e4338c6a712 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c@@ -570,10 +570,15 @@ int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons, spin_lock_irq(&kvm->irqfds.lock); irqfd->producer = prod; + if (!kvm->arch.nr_possible_bypass_irqs++) + kvm_x86_call(pi_start_bypass)(kvm); + if (irqfd->irq_entry.type == KVM_IRQ_ROUTING_MSI) { ret = kvm_pi_update_irte(irqfd, &irqfd->irq_entry); - if (ret) + if (ret) { + kvm->arch.nr_possible_bypass_irqs--; kvm_arch_end_assignment(irqfd->kvm); + } } spin_unlock_irq(&kvm->irqfds.lock);
@@ -606,6 +611,8 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, } irqfd->producer = NULL; + kvm->arch.nr_possible_bypass_irqs--; + spin_unlock_irq(&kvm->irqfds.lock);
diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
index d1e02e567b57..a986fc45145e 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c@@ -1014,7 +1014,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .nested_ops = &vmx_nested_ops, .pi_update_irte = vmx_pi_update_irte, - .pi_start_assignment = vmx_pi_start_assignment, + .pi_start_bypass = vmx_pi_start_bypass, #ifdef CONFIG_X86_64 .set_hv_timer = vt_op(set_hv_timer),
diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c
index 3a23c30f73cb..5671d59a6b6d 100644
--- a/arch/x86/kvm/vmx/posted_intr.c
+++ b/arch/x86/kvm/vmx/posted_intr.c@@ -146,8 +146,13 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) static bool vmx_can_use_vtd_pi(struct kvm *kvm) { + /* + * Note, reading the number of possible bypass IRQs can race with a + * bypass IRQ being attached to the VM. vmx_pi_start_bypass() ensures + * blockng vCPUs will see an elevated count or get KVM_REQ_UNBLOCK. + */ return irqchip_in_kernel(kvm) && kvm_arch_has_irq_bypass() && - kvm_arch_has_assigned_device(kvm); + READ_ONCE(kvm->arch.nr_possible_bypass_irqs); } /*
@@ -285,12 +290,11 @@ bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu) /* - * Bail out of the block loop if the VM has an assigned - * device, but the blocking vCPU didn't reconfigure the - * PI.NV to the wakeup vector, i.e. the assigned device - * came along after the initial check in vmx_vcpu_pi_put(). + * Kick all vCPUs when the first possible bypass IRQ is attached to a VM, as + * blocking vCPUs may scheduled out without reconfiguring PID.NV to the wakeup + * vector, i.e. if the bypass IRQ came along after vmx_vcpu_pi_put(). */ -void vmx_pi_start_assignment(struct kvm *kvm) +void vmx_pi_start_bypass(struct kvm *kvm) { if (!kvm_arch_has_irq_bypass()) return;
diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h
index 94ed66ea6249..a4af39948cf0 100644
--- a/arch/x86/kvm/vmx/posted_intr.h
+++ b/arch/x86/kvm/vmx/posted_intr.h@@ -17,7 +17,7 @@ bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu); int vmx_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, struct kvm_vcpu *vcpu, u32 vector); -void vmx_pi_start_assignment(struct kvm *kvm); +void vmx_pi_start_bypass(struct kvm *kvm); static inline int pi_find_highest_vector(struct pi_desc *pi_desc) {
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index d3571c484790..59391cb56674 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c@@ -13440,8 +13440,7 @@ bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu) void kvm_arch_start_assignment(struct kvm *kvm) { - if (atomic_inc_return(&kvm->arch.assigned_device_count) == 1) - kvm_x86_call(pi_start_assignment)(kvm); + atomic_inc(&kvm->arch.assigned_device_count); } EXPORT_SYMBOL_GPL(kvm_arch_start_assignment);
--
2.50.0.rc1.591.g9c95f17f64-goog