From patchwork Thu Jun 4 18:08:24 2009 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Marcelo Tosatti X-Patchwork-Id: 27991 Received: from vger.kernel.org (vger.kernel.org [209.132.176.167]) by demeter.kernel.org (8.14.2/8.14.2) with ESMTP id n54IFsnX002204 for ; Thu, 4 Jun 2009 18:15:55 GMT Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753234AbZFDSM5 (ORCPT ); Thu, 4 Jun 2009 14:12:57 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752517AbZFDSM5 (ORCPT ); Thu, 4 Jun 2009 14:12:57 -0400 Received: from mx2.redhat.com ([66.187.237.31]:50797 "EHLO mx2.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753460AbZFDSMt (ORCPT ); Thu, 4 Jun 2009 14:12:49 -0400 Received: from int-mx2.corp.redhat.com (int-mx2.corp.redhat.com [172.16.27.26]) by mx2.redhat.com (8.13.8/8.13.8) with ESMTP id n54ICqd6019383 for ; Thu, 4 Jun 2009 14:12:52 -0400 Received: from ns3.rdu.redhat.com (ns3.rdu.redhat.com [10.11.255.199]) by int-mx2.corp.redhat.com (8.13.1/8.13.1) with ESMTP id n54ICpg8002659; Thu, 4 Jun 2009 14:12:51 -0400 Received: from amt.cnet (vpn-10-27.str.redhat.com [10.32.10.27]) by ns3.rdu.redhat.com (8.13.8/8.13.8) with ESMTP id n54IClcI006171; Thu, 4 Jun 2009 14:12:48 -0400 Received: from amt.cnet (amt.cnet [127.0.0.1]) by amt.cnet (Postfix) with ESMTP id 5CF58680268; Thu, 4 Jun 2009 15:11:50 -0300 (BRT) Received: (from marcelo@localhost) by amt.cnet (8.14.3/8.14.3/Submit) id n54IBoaC014198; Thu, 4 Jun 2009 15:11:50 -0300 Message-Id: <20090604180939.194890957@localhost.localdomain> References: <20090604180820.644455695@localhost.localdomain> User-Agent: quilt/0.46-1 Date: Thu, 04 Jun 2009 15:08:24 -0300 From: Marcelo Tosatti To: avi@redhat.com, kvm@vger.kernel.org Cc: Marcelo Tosatti Subject: [patch 4/4] KVM: switch irq injection/acking data structures to irq_lock Content-Disposition: inline; filename=irqlock X-Scanned-By: MIMEDefang 2.58 on 172.16.27.26 Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org Protect irq injection/acking data structures with a separate irq_lock mutex. This fixes the following deadlock: CPU A CPU B kvm_vm_ioctl_deassign_dev_irq() mutex_lock(&kvm->lock); worker_thread() -> kvm_deassign_irq() -> kvm_assigned_dev_interrupt_work_handler() -> deassign_host_irq() mutex_lock(&kvm->lock); -> cancel_work_sync() [blocked] Reported-by: Alex Williamson Signed-off-by: Marcelo Tosatti Index: kvm/arch/x86/kvm/i8254.c =================================================================== --- kvm.orig/arch/x86/kvm/i8254.c +++ kvm/arch/x86/kvm/i8254.c @@ -651,10 +651,10 @@ static void __inject_pit_timer_intr(stru struct kvm_vcpu *vcpu; int i; - mutex_lock(&kvm->lock); + mutex_lock(&kvm->irq_lock); kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 1); kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 0); - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->irq_lock); /* * Provides NMI watchdog support via Virtual Wire mode. Index: kvm/arch/x86/kvm/x86.c =================================================================== --- kvm.orig/arch/x86/kvm/x86.c +++ kvm/arch/x86/kvm/x86.c @@ -2099,10 +2099,10 @@ long kvm_arch_vm_ioctl(struct file *filp goto out; if (irqchip_in_kernel(kvm)) { __s32 status; - mutex_lock(&kvm->lock); + mutex_lock(&kvm->irq_lock); status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irq_event.irq, irq_event.level); - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->irq_lock); if (ioctl == KVM_IRQ_LINE_STATUS) { irq_event.status = status; if (copy_to_user(argp, &irq_event, @@ -2348,12 +2348,11 @@ mmio: */ mutex_lock(&vcpu->kvm->lock); mmio_dev = vcpu_find_mmio_dev(vcpu, gpa, bytes, 0); + mutex_unlock(&vcpu->kvm->lock); if (mmio_dev) { kvm_iodevice_read(mmio_dev, gpa, bytes, val); - mutex_unlock(&vcpu->kvm->lock); return X86EMUL_CONTINUE; } - mutex_unlock(&vcpu->kvm->lock); vcpu->mmio_needed = 1; vcpu->mmio_phys_addr = gpa; @@ -2403,12 +2402,11 @@ mmio: */ mutex_lock(&vcpu->kvm->lock); mmio_dev = vcpu_find_mmio_dev(vcpu, gpa, bytes, 1); + mutex_unlock(&vcpu->kvm->lock); if (mmio_dev) { kvm_iodevice_write(mmio_dev, gpa, bytes, val); - mutex_unlock(&vcpu->kvm->lock); return X86EMUL_CONTINUE; } - mutex_unlock(&vcpu->kvm->lock); vcpu->mmio_needed = 1; vcpu->mmio_phys_addr = gpa; @@ -2731,7 +2729,6 @@ static void kernel_pio(struct kvm_io_dev { /* TODO: String I/O for in kernel device */ - mutex_lock(&vcpu->kvm->lock); if (vcpu->arch.pio.in) kvm_iodevice_read(pio_dev, vcpu->arch.pio.port, vcpu->arch.pio.size, @@ -2740,7 +2737,6 @@ static void kernel_pio(struct kvm_io_dev kvm_iodevice_write(pio_dev, vcpu->arch.pio.port, vcpu->arch.pio.size, pd); - mutex_unlock(&vcpu->kvm->lock); } static void pio_string_write(struct kvm_io_device *pio_dev, @@ -2750,14 +2746,12 @@ static void pio_string_write(struct kvm_ void *pd = vcpu->arch.pio_data; int i; - mutex_lock(&vcpu->kvm->lock); for (i = 0; i < io->cur_count; i++) { kvm_iodevice_write(pio_dev, io->port, io->size, pd); pd += io->size; } - mutex_unlock(&vcpu->kvm->lock); } static struct kvm_io_device *vcpu_find_pio_dev(struct kvm_vcpu *vcpu, @@ -2794,7 +2788,9 @@ int kvm_emulate_pio(struct kvm_vcpu *vcp val = kvm_register_read(vcpu, VCPU_REGS_RAX); memcpy(vcpu->arch.pio_data, &val, 4); + mutex_lock(&vcpu->kvm->lock); pio_dev = vcpu_find_pio_dev(vcpu, port, size, !in); + mutex_unlock(&vcpu->kvm->lock); if (pio_dev) { kernel_pio(pio_dev, vcpu, vcpu->arch.pio_data); complete_pio(vcpu); @@ -2858,9 +2854,12 @@ int kvm_emulate_pio_string(struct kvm_vc vcpu->arch.pio.guest_gva = address; + mutex_lock(&vcpu->kvm->lock); pio_dev = vcpu_find_pio_dev(vcpu, port, vcpu->arch.pio.cur_count, !vcpu->arch.pio.in); + mutex_unlock(&vcpu->kvm->lock); + if (!vcpu->arch.pio.in) { /* string PIO write */ ret = pio_copy_data(vcpu); Index: kvm/virt/kvm/kvm_main.c =================================================================== --- kvm.orig/virt/kvm/kvm_main.c +++ kvm/virt/kvm/kvm_main.c @@ -62,6 +62,12 @@ MODULE_AUTHOR("Qumranet"); MODULE_LICENSE("GPL"); +/* + * Ordering of locks: + * + * kvm->lock --> kvm->irq_lock + */ + DEFINE_SPINLOCK(kvm_lock); LIST_HEAD(vm_list); @@ -126,11 +132,7 @@ static void kvm_assigned_dev_interrupt_w interrupt_work); kvm = assigned_dev->kvm; - /* This is taken to safely inject irq inside the guest. When - * the interrupt injection (or the ioapic code) uses a - * finer-grained lock, update this - */ - mutex_lock(&kvm->lock); + mutex_lock(&kvm->irq_lock); spin_lock_irq(&assigned_dev->assigned_dev_lock); if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) { struct kvm_guest_msix_entry *guest_entries = @@ -149,7 +151,7 @@ static void kvm_assigned_dev_interrupt_w assigned_dev->guest_irq, 1); spin_unlock_irq(&assigned_dev->assigned_dev_lock); - mutex_unlock(&assigned_dev->kvm->lock); + mutex_unlock(&assigned_dev->kvm->irq_lock); } static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id) @@ -207,7 +209,7 @@ static void kvm_assigned_dev_ack_irq(str static void deassign_guest_irq(struct kvm *kvm, struct kvm_assigned_dev_kernel *assigned_dev) { - kvm_unregister_irq_ack_notifier(&assigned_dev->ack_notifier); + kvm_unregister_irq_ack_notifier(kvm, &assigned_dev->ack_notifier); assigned_dev->ack_notifier.gsi = -1; if (assigned_dev->irq_source_id != -1) Index: kvm/virt/kvm/irq_comm.c =================================================================== --- kvm.orig/virt/kvm/irq_comm.c +++ kvm/virt/kvm/irq_comm.c @@ -62,6 +62,8 @@ int kvm_irq_delivery_to_apic(struct kvm int i, r = -1; struct kvm_vcpu *vcpu, *lowest = NULL; + WARN_ON(!mutex_is_locked(&kvm->irq_lock)); + if (irq->dest_mode == 0 && irq->dest_id == 0xff && kvm_is_dm_lowest_prio(irq)) printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n"); @@ -113,7 +115,7 @@ static int kvm_set_msi(struct kvm_kernel return kvm_irq_delivery_to_apic(kvm, NULL, &irq); } -/* This should be called with the kvm->lock mutex held +/* This should be called with the kvm->irq_lock mutex held * Return value: * < 0 Interrupt was ignored (masked or not delivered for other reasons) * = 0 Interrupt was coalesced (previous irq is still pending) @@ -125,6 +127,8 @@ int kvm_set_irq(struct kvm *kvm, int irq unsigned long *irq_state, sig_level; int ret = -1; + WARN_ON(!mutex_is_locked(&kvm->irq_lock)); + if (irq < KVM_IOAPIC_NUM_PINS) { irq_state = (unsigned long *)&kvm->arch.irq_states[irq]; @@ -174,19 +178,26 @@ void kvm_notify_acked_irq(struct kvm *kv void kvm_register_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian) { + mutex_lock(&kvm->irq_lock); hlist_add_head(&kian->link, &kvm->arch.irq_ack_notifier_list); + mutex_unlock(&kvm->irq_lock); } -void kvm_unregister_irq_ack_notifier(struct kvm_irq_ack_notifier *kian) +void kvm_unregister_irq_ack_notifier(struct kvm *kvm, + struct kvm_irq_ack_notifier *kian) { + mutex_lock(&kvm->irq_lock); hlist_del_init(&kian->link); + mutex_unlock(&kvm->irq_lock); } -/* The caller must hold kvm->lock mutex */ int kvm_request_irq_source_id(struct kvm *kvm) { unsigned long *bitmap = &kvm->arch.irq_sources_bitmap; - int irq_source_id = find_first_zero_bit(bitmap, + int irq_source_id; + + mutex_lock(&kvm->irq_lock); + irq_source_id = find_first_zero_bit(bitmap, sizeof(kvm->arch.irq_sources_bitmap)); if (irq_source_id >= sizeof(kvm->arch.irq_sources_bitmap)) { @@ -196,6 +207,7 @@ int kvm_request_irq_source_id(struct kvm ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID); set_bit(irq_source_id, bitmap); + mutex_unlock(&kvm->irq_lock); return irq_source_id; } @@ -206,6 +218,7 @@ void kvm_free_irq_source_id(struct kvm * ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID); + mutex_lock(&kvm->irq_lock); if (irq_source_id < 0 || irq_source_id >= sizeof(kvm->arch.irq_sources_bitmap)) { printk(KERN_ERR "kvm: IRQ source ID out of range!\n"); @@ -214,19 +227,24 @@ void kvm_free_irq_source_id(struct kvm * for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++) clear_bit(irq_source_id, &kvm->arch.irq_states[i]); clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap); + mutex_unlock(&kvm->irq_lock); } void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq, struct kvm_irq_mask_notifier *kimn) { + mutex_lock(&kvm->irq_lock); kimn->irq = irq; hlist_add_head(&kimn->link, &kvm->mask_notifier_list); + mutex_unlock(&kvm->irq_lock); } void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq, struct kvm_irq_mask_notifier *kimn) { + mutex_lock(&kvm->irq_lock); hlist_del(&kimn->link); + mutex_unlock(&kvm->irq_lock); } void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask) @@ -234,6 +252,8 @@ void kvm_fire_mask_notifiers(struct kvm struct kvm_irq_mask_notifier *kimn; struct hlist_node *n; + WARN_ON(!mutex_is_locked(&kvm->irq_lock)); + hlist_for_each_entry(kimn, n, &kvm->mask_notifier_list, link) if (kimn->irq == irq) kimn->func(kimn, mask); @@ -249,7 +269,9 @@ static void __kvm_free_irq_routing(struc void kvm_free_irq_routing(struct kvm *kvm) { + mutex_lock(&kvm->irq_lock); __kvm_free_irq_routing(&kvm->irq_routing); + mutex_unlock(&kvm->irq_lock); } static int setup_routing_entry(struct kvm_kernel_irq_routing_entry *e, @@ -323,13 +345,13 @@ int kvm_set_irq_routing(struct kvm *kvm, e = NULL; } - mutex_lock(&kvm->lock); + mutex_lock(&kvm->irq_lock); list_splice(&kvm->irq_routing, &tmp); INIT_LIST_HEAD(&kvm->irq_routing); list_splice(&irq_list, &kvm->irq_routing); INIT_LIST_HEAD(&irq_list); list_splice(&tmp, &irq_list); - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->irq_lock); r = 0; Index: kvm/arch/x86/kvm/lapic.c =================================================================== --- kvm.orig/arch/x86/kvm/lapic.c +++ kvm/arch/x86/kvm/lapic.c @@ -425,7 +425,9 @@ static void apic_set_eoi(struct kvm_lapi trigger_mode = IOAPIC_LEVEL_TRIG; else trigger_mode = IOAPIC_EDGE_TRIG; + mutex_lock(&apic->vcpu->kvm->irq_lock); kvm_ioapic_update_eoi(apic->vcpu->kvm, vector, trigger_mode); + mutex_unlock(&apic->vcpu->kvm->irq_lock); } static void apic_send_ipi(struct kvm_lapic *apic) @@ -449,7 +451,9 @@ static void apic_send_ipi(struct kvm_lap irq.trig_mode, irq.level, irq.dest_mode, irq.delivery_mode, irq.vector); + mutex_lock(&apic->vcpu->kvm->irq_lock); kvm_irq_delivery_to_apic(apic->vcpu->kvm, apic, &irq); + mutex_unlock(&apic->vcpu->kvm->irq_lock); } static u32 apic_get_tmcct(struct kvm_lapic *apic) Index: kvm/include/linux/kvm_host.h =================================================================== --- kvm.orig/include/linux/kvm_host.h +++ kvm/include/linux/kvm_host.h @@ -371,7 +371,8 @@ int kvm_set_irq(struct kvm *kvm, int irq void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin); void kvm_register_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian); -void kvm_unregister_irq_ack_notifier(struct kvm_irq_ack_notifier *kian); +void kvm_unregister_irq_ack_notifier(struct kvm *kvm, + struct kvm_irq_ack_notifier *kian); int kvm_request_irq_source_id(struct kvm *kvm); void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id); Index: kvm/virt/kvm/eventfd.c =================================================================== --- kvm.orig/virt/kvm/eventfd.c +++ kvm/virt/kvm/eventfd.c @@ -59,10 +59,10 @@ irqfd_inject(struct work_struct *work) kvm = rcu_dereference(irqfd->kvm); if (kvm) { - mutex_lock(&kvm->lock); + mutex_lock(&kvm->irq_lock); kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 1); kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 0); - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->irq_lock); } srcu_read_unlock(&irqfd->srcu, idx);