KVM: switch irq injection/acking data structures to irq_lock

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]

[gleb: fix ia64 path]

Reported-by: Alex Williamson <alex.williamson@hp.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>

4 files changed, 17 insertions, 14 deletions

diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index 319922137fdd..8dde36953af3 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -1000,10 +1000,10 @@ 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,
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 977af7ab8193..3837db65d33e 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -654,10 +654,10 @@ static void __inject_pit_timer_intr(struct kvm *kvm)
 	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.
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index a23f42e550af..44f20cdb5709 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -424,7 +424,9 @@ static void apic_set_eoi(struct kvm_lapic *apic)
 		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)
@@ -448,7 +450,9 @@ static void apic_send_ipi(struct kvm_lapic *apic)
 		   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)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2ad8c97f58cc..05cbe83c74e2 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2136,10 +2136,10 @@ 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,
@@ -2385,12 +2385,11 @@ 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;
@@ -2440,12 +2439,11 @@ 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;
@@ -2768,7 +2766,6 @@ static void kernel_pio(struct kvm_io_device *pio_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,
@@ -2777,7 +2774,6 @@ static void kernel_pio(struct kvm_io_device *pio_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,
@@ -2787,14 +2783,12 @@ static void pio_string_write(struct kvm_io_device *pio_dev,
 	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,
@@ -2831,7 +2825,9 @@ int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
 	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);
@@ -2895,9 +2891,12 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
 
 	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);