Merge tag 'kvm-x86-irqs-6.17' of https://github.com/kvm-x86/linux into HEAD

KVM IRQ changes for 6.17

 - Rework irqbypass to track/match producers and consumers via an xarray
   instead of a linked list.  Using a linked list leads to O(n^2) insertion
   times, which is hugely problematic for use cases that create large numbers
   of VMs.  Such use cases typically don't actually use irqbypass, but
   eliminating the pointless registration is a future problem to solve as it
   likely requires new uAPI.

 - Track irqbypass's "token" as "struct eventfd_ctx *" instead of a "void *",
   to avoid making a simple concept unnecessarily difficult to understand.

 - Add CONFIG_KVM_IOAPIC for x86 to allow disabling support for I/O APIC, PIC,
   and PIT emulation at compile time.

 - Drop x86's irq_comm.c, and move a pile of IRQ related code into irq.c.

 - Fix a variety of flaws and bugs in the AVIC device posted IRQ code.

 - Inhibited AVIC if a vCPU's ID is too big (relative to what hardware
   supports) instead of rejecting vCPU creation.

 - Extend enable_ipiv module param support to SVM, by simply leaving IsRunning
   clear in the vCPU's physical ID table entry.

 - Disable IPI virtualization, via enable_ipiv, if the CPU is affected by
   erratum #1235, to allow (safely) enabling AVIC on such CPUs.

 - Dedup x86's device posted IRQ code, as the vast majority of functionality
   can be shared verbatime between SVM and VMX.

 - Harden the device posted IRQ code against bugs and runtime errors.

 - Use vcpu_idx, not vcpu_id, for GA log tag/metadata, to make lookups O(1)
   instead of O(n).

 - Generate GA Log interrupts if and only if the target vCPU is blocking, i.e.
   only if KVM needs a notification in order to wake the vCPU.

 - Decouple device posted IRQs from VFIO device assignment, as binding a VM to
   a VFIO group is not a requirement for enabling device posted IRQs.

 - Clean up and document/comment the irqfd assignment code.

 - Disallow binding multiple irqfds to an eventfd with a priority waiter, i.e.
   ensure an eventfd is bound to at most one irqfd through the entire host,
   and add a selftest to verify eventfd:irqfd bindings are globally unique.

1 files changed, 25 insertions, 229 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 93636f77c42d..ac961153a736 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -226,6 +226,9 @@ EXPORT_SYMBOL_GPL(allow_smaller_maxphyaddr);
 bool __read_mostly enable_apicv = true;
 EXPORT_SYMBOL_GPL(enable_apicv);
 
+bool __read_mostly enable_ipiv = true;
+EXPORT_SYMBOL_GPL(enable_ipiv);
+
 bool __read_mostly enable_device_posted_irqs = true;
 EXPORT_SYMBOL_GPL(enable_device_posted_irqs);
 
@@ -4634,17 +4637,20 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_EXT_CPUID:
 	case KVM_CAP_EXT_EMUL_CPUID:
 	case KVM_CAP_CLOCKSOURCE:
+#ifdef CONFIG_KVM_IOAPIC
 	case KVM_CAP_PIT:
+	case KVM_CAP_PIT2:
+	case KVM_CAP_PIT_STATE2:
+	case KVM_CAP_REINJECT_CONTROL:
+#endif
 	case KVM_CAP_NOP_IO_DELAY:
 	case KVM_CAP_MP_STATE:
 	case KVM_CAP_SYNC_MMU:
 	case KVM_CAP_USER_NMI:
-	case KVM_CAP_REINJECT_CONTROL:
 	case KVM_CAP_IRQ_INJECT_STATUS:
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_IOEVENTFD_NO_LENGTH:
-	case KVM_CAP_PIT2:
-	case KVM_CAP_PIT_STATE2:
+
 	case KVM_CAP_SET_IDENTITY_MAP_ADDR:
 	case KVM_CAP_VCPU_EVENTS:
 #ifdef CONFIG_KVM_HYPERV
@@ -6401,135 +6407,6 @@ static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm,
 	return 0;
 }
 
-static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
-{
-	struct kvm_pic *pic = kvm->arch.vpic;
-	int r;
-
-	r = 0;
-	switch (chip->chip_id) {
-	case KVM_IRQCHIP_PIC_MASTER:
-		memcpy(&chip->chip.pic, &pic->pics[0],
-			sizeof(struct kvm_pic_state));
-		break;
-	case KVM_IRQCHIP_PIC_SLAVE:
-		memcpy(&chip->chip.pic, &pic->pics[1],
-			sizeof(struct kvm_pic_state));
-		break;
-	case KVM_IRQCHIP_IOAPIC:
-		kvm_get_ioapic(kvm, &chip->chip.ioapic);
-		break;
-	default:
-		r = -EINVAL;
-		break;
-	}
-	return r;
-}
-
-static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
-{
-	struct kvm_pic *pic = kvm->arch.vpic;
-	int r;
-
-	r = 0;
-	switch (chip->chip_id) {
-	case KVM_IRQCHIP_PIC_MASTER:
-		spin_lock(&pic->lock);
-		memcpy(&pic->pics[0], &chip->chip.pic,
-			sizeof(struct kvm_pic_state));
-		spin_unlock(&pic->lock);
-		break;
-	case KVM_IRQCHIP_PIC_SLAVE:
-		spin_lock(&pic->lock);
-		memcpy(&pic->pics[1], &chip->chip.pic,
-			sizeof(struct kvm_pic_state));
-		spin_unlock(&pic->lock);
-		break;
-	case KVM_IRQCHIP_IOAPIC:
-		kvm_set_ioapic(kvm, &chip->chip.ioapic);
-		break;
-	default:
-		r = -EINVAL;
-		break;
-	}
-	kvm_pic_update_irq(pic);
-	return r;
-}
-
-static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps)
-{
-	struct kvm_kpit_state *kps = &kvm->arch.vpit->pit_state;
-
-	BUILD_BUG_ON(sizeof(*ps) != sizeof(kps->channels));
-
-	mutex_lock(&kps->lock);
-	memcpy(ps, &kps->channels, sizeof(*ps));
-	mutex_unlock(&kps->lock);
-	return 0;
-}
-
-static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps)
-{
-	int i;
-	struct kvm_pit *pit = kvm->arch.vpit;
-
-	mutex_lock(&pit->pit_state.lock);
-	memcpy(&pit->pit_state.channels, ps, sizeof(*ps));
-	for (i = 0; i < 3; i++)
-		kvm_pit_load_count(pit, i, ps->channels[i].count, 0);
-	mutex_unlock(&pit->pit_state.lock);
-	return 0;
-}
-
-static int kvm_vm_ioctl_get_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps)
-{
-	mutex_lock(&kvm->arch.vpit->pit_state.lock);
-	memcpy(ps->channels, &kvm->arch.vpit->pit_state.channels,
-		sizeof(ps->channels));
-	ps->flags = kvm->arch.vpit->pit_state.flags;
-	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
-	memset(&ps->reserved, 0, sizeof(ps->reserved));
-	return 0;
-}
-
-static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps)
-{
-	int start = 0;
-	int i;
-	u32 prev_legacy, cur_legacy;
-	struct kvm_pit *pit = kvm->arch.vpit;
-
-	mutex_lock(&pit->pit_state.lock);
-	prev_legacy = pit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY;
-	cur_legacy = ps->flags & KVM_PIT_FLAGS_HPET_LEGACY;
-	if (!prev_legacy && cur_legacy)
-		start = 1;
-	memcpy(&pit->pit_state.channels, &ps->channels,
-	       sizeof(pit->pit_state.channels));
-	pit->pit_state.flags = ps->flags;
-	for (i = 0; i < 3; i++)
-		kvm_pit_load_count(pit, i, pit->pit_state.channels[i].count,
-				   start && i == 0);
-	mutex_unlock(&pit->pit_state.lock);
-	return 0;
-}
-
-static int kvm_vm_ioctl_reinject(struct kvm *kvm,
-				 struct kvm_reinject_control *control)
-{
-	struct kvm_pit *pit = kvm->arch.vpit;
-
-	/* pit->pit_state.lock was overloaded to prevent userspace from getting
-	 * an inconsistent state after running multiple KVM_REINJECT_CONTROL
-	 * ioctls in parallel.  Use a separate lock if that ioctl isn't rare.
-	 */
-	mutex_lock(&pit->pit_state.lock);
-	kvm_pit_set_reinject(pit, control->pit_reinject);
-	mutex_unlock(&pit->pit_state.lock);
-
-	return 0;
-}
-
 void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
 {
 
@@ -6549,18 +6426,6 @@ void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
 		kvm_vcpu_kick(vcpu);
 }
 
-int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event,
-			bool line_status)
-{
-	if (!irqchip_in_kernel(kvm))
-		return -ENXIO;
-
-	irq_event->status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
-					irq_event->irq, irq_event->level,
-					line_status);
-	return 0;
-}
-
 int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 			    struct kvm_enable_cap *cap)
 {
@@ -7072,9 +6937,11 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
 	struct kvm *kvm = filp->private_data;
 	void __user *argp = (void __user *)arg;
 	int r = -ENOTTY;
+
+#ifdef CONFIG_KVM_IOAPIC
 	/*
 	 * This union makes it completely explicit to gcc-3.x
-	 * that these two variables' stack usage should be
+	 * that these three variables' stack usage should be
 	 * combined, not added together.
 	 */
 	union {
@@ -7082,6 +6949,7 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
 		struct kvm_pit_state2 ps2;
 		struct kvm_pit_config pit_config;
 	} u;
+#endif
 
 	switch (ioctl) {
 	case KVM_SET_TSS_ADDR:
@@ -7105,6 +6973,7 @@ set_identity_unlock:
 	case KVM_SET_NR_MMU_PAGES:
 		r = kvm_vm_ioctl_set_nr_mmu_pages(kvm, arg);
 		break;
+#ifdef CONFIG_KVM_IOAPIC
 	case KVM_CREATE_IRQCHIP: {
 		mutex_lock(&kvm->lock);
 
@@ -7126,7 +6995,7 @@ set_identity_unlock:
 			goto create_irqchip_unlock;
 		}
 
-		r = kvm_setup_default_irq_routing(kvm);
+		r = kvm_setup_default_ioapic_and_pic_routing(kvm);
 		if (r) {
 			kvm_ioapic_destroy(kvm);
 			kvm_pic_destroy(kvm);
@@ -7174,7 +7043,7 @@ set_identity_unlock:
 		}
 
 		r = -ENXIO;
-		if (!irqchip_kernel(kvm))
+		if (!irqchip_full(kvm))
 			goto get_irqchip_out;
 		r = kvm_vm_ioctl_get_irqchip(kvm, chip);
 		if (r)
@@ -7198,7 +7067,7 @@ set_identity_unlock:
 		}
 
 		r = -ENXIO;
-		if (!irqchip_kernel(kvm))
+		if (!irqchip_full(kvm))
 			goto set_irqchip_out;
 		r = kvm_vm_ioctl_set_irqchip(kvm, chip);
 	set_irqchip_out:
@@ -7271,6 +7140,7 @@ set_pit2_out:
 		r = kvm_vm_ioctl_reinject(kvm, &control);
 		break;
 	}
+#endif
 	case KVM_SET_BOOT_CPU_ID:
 		r = 0;
 		mutex_lock(&kvm->lock);
@@ -10730,8 +10600,10 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
 
 	if (irqchip_split(vcpu->kvm))
 		kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors);
+#ifdef CONFIG_KVM_IOAPIC
 	else if (ioapic_in_kernel(vcpu->kvm))
 		kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors);
+#endif
 
 	if (is_guest_mode(vcpu))
 		vcpu->arch.load_eoi_exitmap_pending = true;
@@ -12801,15 +12673,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	if (ret)
 		goto out_uninit_mmu;
 
-	INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list);
 	atomic_set(&kvm->arch.noncoherent_dma_count, 0);
 
-	/* Reserve bit 0 of irq_sources_bitmap for userspace irq source */
-	set_bit(KVM_USERSPACE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap);
-	/* Reserve bit 1 of irq_sources_bitmap for irqfd-resampler */
-	set_bit(KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
-		&kvm->arch.irq_sources_bitmap);
-
 	raw_spin_lock_init(&kvm->arch.tsc_write_lock);
 	mutex_init(&kvm->arch.apic_map_lock);
 	seqcount_raw_spinlock_init(&kvm->arch.pvclock_sc, &kvm->arch.tsc_write_lock);
@@ -12940,7 +12805,9 @@ void kvm_arch_pre_destroy_vm(struct kvm *kvm)
 	cancel_delayed_work_sync(&kvm->arch.kvmclock_sync_work);
 	cancel_delayed_work_sync(&kvm->arch.kvmclock_update_work);
 
+#ifdef CONFIG_KVM_IOAPIC
 	kvm_free_pit(kvm);
+#endif
 
 	kvm_mmu_pre_destroy_vm(kvm);
 	static_call_cond(kvm_x86_vm_pre_destroy)(kvm);
@@ -12964,8 +12831,10 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	}
 	kvm_destroy_vcpus(kvm);
 	kvm_free_msr_filter(srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1));
+#ifdef CONFIG_KVM_IOAPIC
 	kvm_pic_destroy(kvm);
 	kvm_ioapic_destroy(kvm);
+#endif
 	kvfree(rcu_dereference_check(kvm->arch.apic_map, 1));
 	kfree(srcu_dereference_check(kvm->arch.pmu_event_filter, &kvm->srcu, 1));
 	kvm_mmu_uninit_vm(kvm);
@@ -13577,8 +13446,7 @@ 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);
 
@@ -13629,77 +13497,6 @@ bool kvm_arch_has_noncoherent_dma(struct kvm *kvm)
 }
 EXPORT_SYMBOL_GPL(kvm_arch_has_noncoherent_dma);
 
-int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
-				      struct irq_bypass_producer *prod)
-{
-	struct kvm_kernel_irqfd *irqfd =
-		container_of(cons, struct kvm_kernel_irqfd, consumer);
-	struct kvm *kvm = irqfd->kvm;
-	int ret;
-
-	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);
-
-	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;
-
-	WARN_ON(irqfd->producer != prod);
-
-	/*
-	 * When producer of consumer is unregistered, we change back to
-	 * remapped mode, so we can re-use the current implementation
-	 * when the irq is masked/disabled or the consumer side (KVM
-	 * int this case doesn't want to receive the interrupts.
-	*/
-	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);
-
-	spin_unlock_irq(&kvm->irqfds.lock);
-
-
-	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)
-{
-	return kvm_x86_call(pi_update_irte)(kvm, host_irq, guest_irq, set);
-}
-
-bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *old,
-				  struct kvm_kernel_irq_routing_entry *new)
-{
-	if (old->type != KVM_IRQ_ROUTING_MSI ||
-	    new->type != KVM_IRQ_ROUTING_MSI)
-		return true;
-
-	return !!memcmp(&old->msi, &new->msi, sizeof(new->msi));
-}
-
 bool kvm_vector_hashing_enabled(void)
 {
 	return vector_hashing;
@@ -14099,7 +13896,6 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intercepts);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_write_tsc_offset);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_ple_window_update);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pml_full);
-EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pi_irte_update);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_unaccelerated_access);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_incomplete_ipi);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_ga_log);