[PATCH v3 03/62] KVM: Pass new routing entries and irqfd when updating IRTEs
From: Sean Christopherson <seanjc@google.com>
Date: 2025-06-11 22:47:01
Also in:
kvm, kvmarm, linux-iommu, lkml
Subsystem:
arm64 port (aarch64 architecture), kernel virtual machine (kvm), kernel virtual machine for arm64 (kvm/arm64), kernel virtual machine for x86 (kvm/x86), the rest, x86 architecture (32-bit and 64-bit) · Maintainers:
Catalin Marinas, Will Deacon, Paolo Bonzini, Marc Zyngier, Oliver Upton, Sean Christopherson, Linus Torvalds, Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen
When updating IRTEs in response to a GSI routing or IRQ bypass change, pass the new/current routing information along with the associated irqfd. This will allow KVM x86 to harden, simplify, and deduplicate its code. Since adding/removing a bypass producer is now conveniently protected with irqfds.lock, i.e. can't run concurrently with kvm_irq_routing_update(), use the routing information cached in the irqfd instead of looking up the information in the current GSI routing tables. Opportunistically convert an existing printk() to pr_info() and put its string onto a single line (old code that strictly adhered to 80 chars). Signed-off-by: Sean Christopherson <seanjc@google.com> --- arch/arm64/kvm/arm.c | 7 ++++--- arch/x86/include/asm/kvm_host.h | 6 ++++-- arch/x86/kvm/svm/avic.c | 18 +++++++---------- arch/x86/kvm/svm/svm.h | 5 +++-- arch/x86/kvm/vmx/posted_intr.c | 19 ++++++++--------- arch/x86/kvm/vmx/posted_intr.h | 8 ++++++-- arch/x86/kvm/x86.c | 36 ++++++++++++++++++--------------- include/linux/kvm_host.h | 7 +++++-- virt/kvm/eventfd.c | 11 +++++----- 9 files changed, 62 insertions(+), 55 deletions(-)
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 38a91bb5d4c7..a9a39e0375f7 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c@@ -2771,8 +2771,9 @@ bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *old, return memcmp(&old->msi, &new->msi, sizeof(new->msi)); } -int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, - uint32_t guest_irq, bool set) +int kvm_arch_update_irqfd_routing(struct kvm_kernel_irqfd *irqfd, + struct kvm_kernel_irq_routing_entry *old, + struct kvm_kernel_irq_routing_entry *new) { /* * Remapping the vLPI requires taking the its_lock mutex to resolve
@@ -2781,7 +2782,7 @@ int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, * * Unmap the vLPI and fall back to software LPI injection. */ - return kvm_vgic_v4_unset_forwarding(kvm, host_irq); + return kvm_vgic_v4_unset_forwarding(irqfd->kvm, irqfd->producer->irq); } void kvm_arch_irq_bypass_stop(struct irq_bypass_consumer *cons)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 21ccb122ab76..2a6ef1398da7 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h@@ -296,6 +296,7 @@ enum x86_intercept_stage; */ #define KVM_APIC_PV_EOI_PENDING 1 +struct kvm_kernel_irqfd; struct kvm_kernel_irq_routing_entry; /*
@@ -1844,8 +1845,9 @@ struct kvm_x86_ops { void (*vcpu_blocking)(struct kvm_vcpu *vcpu); void (*vcpu_unblocking)(struct kvm_vcpu *vcpu); - int (*pi_update_irte)(struct kvm *kvm, unsigned int host_irq, - uint32_t guest_irq, bool set); + int (*pi_update_irte)(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm, + unsigned int host_irq, uint32_t guest_irq, + struct kvm_kernel_irq_routing_entry *new); void (*pi_start_assignment)(struct kvm *kvm); void (*apicv_pre_state_restore)(struct kvm_vcpu *vcpu); void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 7338879d1c0c..adacf00d6664 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c@@ -18,6 +18,7 @@ #include <linux/hashtable.h> #include <linux/amd-iommu.h> #include <linux/kvm_host.h> +#include <linux/kvm_irqfd.h> #include <asm/irq_remapping.h>
@@ -885,21 +886,14 @@ get_pi_vcpu_info(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, return 0; } -/* - * avic_pi_update_irte - set IRTE for Posted-Interrupts - * - * @kvm: kvm - * @host_irq: host irq of the interrupt - * @guest_irq: gsi of the interrupt - * @set: set or unset PI - * returns 0 on success, < 0 on failure - */ -int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq, - uint32_t guest_irq, bool set) +int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm, + unsigned int host_irq, uint32_t guest_irq, + struct kvm_kernel_irq_routing_entry *new) { struct kvm_kernel_irq_routing_entry *e; struct kvm_irq_routing_table *irq_rt; bool enable_remapped_mode = true; + bool set = !!new; int idx, ret = 0; if (!kvm_arch_has_assigned_device(kvm) || !kvm_arch_has_irq_bypass())
@@ -925,6 +919,8 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq, if (e->type != KVM_IRQ_ROUTING_MSI) continue; + WARN_ON_ONCE(new && memcmp(e, new, sizeof(*new))); + /** * Here, we setup with legacy mode in the following cases: * 1. When cannot target interrupt to a specific vcpu.
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index e6f3c6a153a0..b35fce30d923 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h@@ -736,8 +736,9 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu); void avic_vcpu_put(struct kvm_vcpu *vcpu); void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu); void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu); -int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq, - uint32_t guest_irq, bool set); +int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm, + unsigned int host_irq, uint32_t guest_irq, + struct kvm_kernel_irq_routing_entry *new); void avic_vcpu_blocking(struct kvm_vcpu *vcpu); void avic_vcpu_unblocking(struct kvm_vcpu *vcpu); void avic_ring_doorbell(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c
index 5c615e5845bf..110fb19848ab 100644
--- a/arch/x86/kvm/vmx/posted_intr.c
+++ b/arch/x86/kvm/vmx/posted_intr.c@@ -2,6 +2,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> +#include <linux/kvm_irqfd.h> #include <asm/irq_remapping.h> #include <asm/cpu.h>
@@ -294,17 +295,9 @@ void vmx_pi_start_assignment(struct kvm *kvm) kvm_make_all_cpus_request(kvm, KVM_REQ_UNBLOCK); } -/* - * vmx_pi_update_irte - set IRTE for Posted-Interrupts - * - * @kvm: kvm - * @host_irq: host irq of the interrupt - * @guest_irq: gsi of the interrupt - * @set: set or unset PI - * returns 0 on success, < 0 on failure - */ -int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq, - uint32_t guest_irq, bool set) +int vmx_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm, + unsigned int host_irq, uint32_t guest_irq, + struct kvm_kernel_irq_routing_entry *new) { struct kvm_kernel_irq_routing_entry *e; struct kvm_irq_routing_table *irq_rt;
@@ -312,6 +305,7 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq, struct kvm_lapic_irq irq; struct kvm_vcpu *vcpu; struct vcpu_data vcpu_info; + bool set = !!new; int idx, ret = 0; if (!vmx_can_use_vtd_pi(kvm))
@@ -329,6 +323,9 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq, hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) { if (e->type != KVM_IRQ_ROUTING_MSI) continue; + + WARN_ON_ONCE(new && memcmp(e, new, sizeof(*new))); + /* * VT-d PI cannot support posting multicast/broadcast * interrupts to a vCPU, we still use interrupt remapping
diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h
index 80499ea0e674..a94afcb55f7f 100644
--- a/arch/x86/kvm/vmx/posted_intr.h
+++ b/arch/x86/kvm/vmx/posted_intr.h@@ -3,6 +3,9 @@ #define __KVM_X86_VMX_POSTED_INTR_H #include <linux/bitmap.h> +#include <linux/find.h> +#include <linux/kvm_host.h> + #include <asm/posted_intr.h> void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu);
@@ -11,8 +14,9 @@ void pi_wakeup_handler(void); void __init pi_init_cpu(int cpu); void pi_apicv_pre_state_restore(struct kvm_vcpu *vcpu); bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu); -int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq, - uint32_t guest_irq, bool set); +int vmx_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm, + unsigned int host_irq, uint32_t guest_irq, + struct kvm_kernel_irq_routing_entry *new); void vmx_pi_start_assignment(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 28a20f0aa3dd..93711a5ef272 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c@@ -13507,31 +13507,31 @@ int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons, struct kvm_kernel_irqfd *irqfd = container_of(cons, struct kvm_kernel_irqfd, consumer); struct kvm *kvm = irqfd->kvm; - int ret; + int ret = 0; kvm_arch_start_assignment(irqfd->kvm); spin_lock_irq(&kvm->irqfds.lock); irqfd->producer = prod; - ret = kvm_x86_call(pi_update_irte)(irqfd->kvm, - prod->irq, irqfd->gsi, 1); - if (ret) - kvm_arch_end_assignment(irqfd->kvm); - + if (irqfd->irq_entry.type == KVM_IRQ_ROUTING_MSI) { + ret = kvm_x86_call(pi_update_irte)(irqfd, irqfd->kvm, prod->irq, + irqfd->gsi, &irqfd->irq_entry); + if (ret) + kvm_arch_end_assignment(irqfd->kvm); + } spin_unlock_irq(&kvm->irqfds.lock); - return ret; } void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, struct irq_bypass_producer *prod) { - int ret; struct kvm_kernel_irqfd *irqfd = container_of(cons, struct kvm_kernel_irqfd, consumer); struct kvm *kvm = irqfd->kvm; + int ret; WARN_ON(irqfd->producer != prod);
@@ -13544,11 +13544,13 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, spin_lock_irq(&kvm->irqfds.lock); irqfd->producer = NULL; - ret = kvm_x86_call(pi_update_irte)(irqfd->kvm, - prod->irq, irqfd->gsi, 0); - if (ret) - printk(KERN_INFO "irq bypass consumer (token %p) unregistration" - " fails: %d\n", irqfd->consumer.token, ret); + if (irqfd->irq_entry.type == KVM_IRQ_ROUTING_MSI) { + ret = kvm_x86_call(pi_update_irte)(irqfd, irqfd->kvm, prod->irq, + irqfd->gsi, NULL); + if (ret) + pr_info("irq bypass consumer (token %p) unregistration fails: %d\n", + irqfd->consumer.token, ret); + } spin_unlock_irq(&kvm->irqfds.lock);
@@ -13556,10 +13558,12 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, kvm_arch_end_assignment(irqfd->kvm); } -int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, - uint32_t guest_irq, bool set) +int kvm_arch_update_irqfd_routing(struct kvm_kernel_irqfd *irqfd, + struct kvm_kernel_irq_routing_entry *old, + struct kvm_kernel_irq_routing_entry *new) { - return kvm_x86_call(pi_update_irte)(kvm, host_irq, guest_irq, set); + return kvm_x86_call(pi_update_irte)(irqfd, irqfd->kvm, irqfd->producer->irq, + irqfd->gsi, new); } bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *old,
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 3b5575d0b574..a4160c1c0c6b 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h@@ -2401,6 +2401,8 @@ struct kvm_vcpu *kvm_get_running_vcpu(void); struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void); #if IS_ENABLED(CONFIG_HAVE_KVM_IRQ_BYPASS) +struct kvm_kernel_irqfd; + bool kvm_arch_has_irq_bypass(void); int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *, struct irq_bypass_producer *);
@@ -2408,8 +2410,9 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *, struct irq_bypass_producer *); void kvm_arch_irq_bypass_stop(struct irq_bypass_consumer *); void kvm_arch_irq_bypass_start(struct irq_bypass_consumer *); -int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, - uint32_t guest_irq, bool set); +int kvm_arch_update_irqfd_routing(struct kvm_kernel_irqfd *irqfd, + struct kvm_kernel_irq_routing_entry *old, + struct kvm_kernel_irq_routing_entry *new); bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *, struct kvm_kernel_irq_routing_entry *); #endif /* CONFIG_HAVE_KVM_IRQ_BYPASS */
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 11e5d1e3f12e..85581550dc8d 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c@@ -285,9 +285,9 @@ void __attribute__((weak)) kvm_arch_irq_bypass_start( { } -int __attribute__((weak)) kvm_arch_update_irqfd_routing( - struct kvm *kvm, unsigned int host_irq, - uint32_t guest_irq, bool set) +int __weak kvm_arch_update_irqfd_routing(struct kvm_kernel_irqfd *irqfd, + struct kvm_kernel_irq_routing_entry *old, + struct kvm_kernel_irq_routing_entry *new) { return 0; }
@@ -619,9 +619,8 @@ void kvm_irq_routing_update(struct kvm *kvm) #if IS_ENABLED(CONFIG_HAVE_KVM_IRQ_BYPASS) if (irqfd->producer && kvm_arch_irqfd_route_changed(&old, &irqfd->irq_entry)) { - int ret = kvm_arch_update_irqfd_routing( - irqfd->kvm, irqfd->producer->irq, - irqfd->gsi, 1); + int ret = kvm_arch_update_irqfd_routing(irqfd, &old, &irqfd->irq_entry); + WARN_ON(ret); } #endif
--
2.50.0.rc1.591.g9c95f17f64-goog