KVM: Fix guest shared interrupt with in-kernel irqchip

Every call of kvm_set_irq() should offer an irq_source_id, which is
allocated by kvm_request_irq_source_id(). Based on irq_source_id, we
identify the irq source and implement logical OR for shared level
interrupts.

The allocated irq_source_id can be freed by kvm_free_irq_source_id().

Currently, we support at most sizeof(unsigned long) different irq sources.

[Amit: - rebase to kvm.git HEAD
       - move definition of KVM_USERSPACE_IRQ_SOURCE_ID to common file
       - move kvm_request_irq_source_id to the update_irq ioctl]

[Xiantao: - Add kvm/ia64 stuff and make it work for kvm/ia64 guests]

Signed-off-by: Sheng Yang <[email protected]>
Signed-off-by: Amit Shah <[email protected]>
Signed-off-by: Xiantao Zhang <[email protected]>
Signed-off-by: Avi Kivity <[email protected]>

virt/kvm/irq_comm.c

@@ -25,15 +25,23 @@
 #include "ioapic.h"
 
 /* This should be called with the kvm->lock mutex held */
-void kvm_set_irq(struct kvm *kvm, int irq, int level)
+void kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level)
 {
+	unsigned long *irq_state = (unsigned long *)&kvm->arch.irq_states[irq];
+
+	/* Logical OR for level trig interrupt */
+	if (level)
+		set_bit(irq_source_id, irq_state);
+	else
+		clear_bit(irq_source_id, irq_state);
+
 	/* Not possible to detect if the guest uses the PIC or the
 	 * IOAPIC.  So set the bit in both. The guest will ignore
 	 * writes to the unused one.
 	 */
-	kvm_ioapic_set_irq(kvm->arch.vioapic, irq, level);
+	kvm_ioapic_set_irq(kvm->arch.vioapic, irq, !!(*irq_state));
 #ifdef CONFIG_X86
-	kvm_pic_set_irq(pic_irqchip(kvm), irq, level);
+	kvm_pic_set_irq(pic_irqchip(kvm), irq, !!(*irq_state));
 #endif
 }
 
@@ -58,3 +66,31 @@ void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
 {
 	hlist_del(&kian->link);
 }
+
+/* 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,
+				sizeof(kvm->arch.irq_sources_bitmap));
+	if (irq_source_id >= sizeof(kvm->arch.irq_sources_bitmap)) {
+		printk(KERN_WARNING "kvm: exhaust allocatable IRQ sources!\n");
+		irq_source_id = -EFAULT;
+	} else
+		set_bit(irq_source_id, bitmap);
+	return irq_source_id;
+}
+
+void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id)
+{
+	int i;
+
+	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");
+		return;
+	}
+	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);
+}

virt/kvm/kvm_main.c

@@ -105,14 +105,12 @@ static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work)
 	 */
 	mutex_lock(&assigned_dev->kvm->lock);
 	kvm_set_irq(assigned_dev->kvm,
+		    assigned_dev->irq_source_id,
 		    assigned_dev->guest_irq, 1);
 	mutex_unlock(&assigned_dev->kvm->lock);
 	kvm_put_kvm(assigned_dev->kvm);
 }
 
-/* FIXME: Implement the OR logic needed to make shared interrupts on
- * this line behave properly
- */
 static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id)
 {
 	struct kvm_assigned_dev_kernel *assigned_dev =
@@ -134,7 +132,7 @@ static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian)
 
 	dev = container_of(kian, struct kvm_assigned_dev_kernel,
 			   ack_notifier);
-	kvm_set_irq(dev->kvm, dev->guest_irq, 0);
+	kvm_set_irq(dev->kvm, dev->irq_source_id, dev->guest_irq, 0);
 	enable_irq(dev->host_irq);
 }
 
@@ -146,6 +144,7 @@ static void kvm_free_assigned_device(struct kvm *kvm,
 		free_irq(assigned_dev->host_irq, (void *)assigned_dev);
 
 	kvm_unregister_irq_ack_notifier(kvm, &assigned_dev->ack_notifier);
+	kvm_free_irq_source_id(kvm, assigned_dev->irq_source_id);
 
 	if (cancel_work_sync(&assigned_dev->interrupt_work))
 		/* We had pending work. That means we will have to take
@@ -215,6 +214,11 @@ static int kvm_vm_ioctl_assign_irq(struct kvm *kvm,
 		match->ack_notifier.gsi = assigned_irq->guest_irq;
 		match->ack_notifier.irq_acked = kvm_assigned_dev_ack_irq;
 		kvm_register_irq_ack_notifier(kvm, &match->ack_notifier);
+		r = kvm_request_irq_source_id(kvm);
+		if (r < 0)
+			goto out_release;
+		else
+			match->irq_source_id = r;
 
 		/* Even though this is PCI, we don't want to use shared
 		 * interrupts. Sharing host devices with guest-assigned devices