[PATCH 2/3] KVM: Add gsi_msg_pending_bitmap for MSI-X

[Sheng Yang <sheng@linux.intel.com>]

We have to handle more than one interrupt with one handler for MSI-X. So we
need a bitmap to track the triggered interrupts.

Signed-off-by: Sheng Yang <sheng@linux.intel.com>
---
 include/linux/kvm_host.h |    5 +-
 virt/kvm/kvm_main.c      |  102 ++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 102 insertions(+), 5 deletions(-)

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index b105ada..6e354af 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -145,6 +145,8 @@ struct kvm {
 #ifdef CONFIG_HAVE_KVM_IRQCHIP
 	struct list_head irq_routing; /* of kvm_kernel_irq_routing_entry */
 	struct hlist_head mask_notifier_list;
+#define KVM_MAX_IRQ_ROUTES 1024
+	DECLARE_BITMAP(irq_routes_pending_bitmap, KVM_MAX_IRQ_ROUTES);
 #endif
 
 #ifdef KVM_ARCH_WANT_MMU_NOTIFIER
@@ -336,6 +338,7 @@ struct kvm_assigned_dev_kernel {
 #define KVM_ASSIGNED_DEV_GUEST_MSI	(1 << 1)
 #define KVM_ASSIGNED_DEV_HOST_INTX	(1 << 8)
 #define KVM_ASSIGNED_DEV_HOST_MSI	(1 << 9)
+#define KVM_ASSIGNED_DEV_MSIX		((1 << 2) | (1 << 10))
 	unsigned long irq_requested_type;
 	int irq_source_id;
 	int flags;
@@ -503,8 +506,6 @@ static inline int mmu_notifier_retry(struct kvm_vcpu *vcpu, unsigned long mmu_se
 
 #ifdef CONFIG_HAVE_KVM_IRQCHIP
 
-#define KVM_MAX_IRQ_ROUTES 1024
-
 int kvm_setup_default_irq_routing(struct kvm *kvm);
 int kvm_set_irq_routing(struct kvm *kvm,
 			const struct kvm_irq_routing_entry *entries,
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index bb4aa73..4010802 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -95,25 +95,113 @@ static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *h
 	return NULL;
 }
 
+static int find_host_irq_from_gsi(struct kvm_assigned_dev_kernel *assigned_dev,
+				  u32 gsi)
+{
+	int i, entry, irq;
+	struct msix_entry *host_msix_entries, *guest_msix_entries;
+
+	host_msix_entries = assigned_dev->host_msix_entries;
+	guest_msix_entries = assigned_dev->guest_msix_entries;
+
+	entry = -1;
+	irq = 0;
+	for (i = 0; i < assigned_dev->entries_nr; i++)
+		if (gsi == (guest_msix_entries + i)->vector) {
+			entry = (guest_msix_entries + i)->entry;
+			break;
+		}
+	if (entry < 0) {
+		printk(KERN_WARNING "Fail to find correlated MSI-X entry!\n");
+		return 0;
+	}
+	for (i = 0; i < assigned_dev->entries_nr; i++)
+		if (entry == (host_msix_entries + i)->entry) {
+			irq = (host_msix_entries + i)->vector;
+			break;
+		}
+	if (irq == 0) {
+		printk(KERN_WARNING "Fail to find correlated MSI-X irq!\n");
+		return 0;
+	}
+
+	return irq;
+}
+
+static int find_gsi_from_host_irq(struct kvm_assigned_dev_kernel *assigned_dev,
+				  int irq)
+{
+	int i, entry, gsi;
+	struct msix_entry *host_msix_entries, *guest_msix_entries;
+
+	host_msix_entries = assigned_dev->host_msix_entries;
+	guest_msix_entries = assigned_dev->guest_msix_entries;
+
+	entry = -1;
+	gsi = -1;
+	for (i = 0; i < assigned_dev->entries_nr; i++)
+		if (irq == (host_msix_entries + i)->vector) {
+			entry = (host_msix_entries + i)->entry;
+			break;
+		}
+	if (entry < 0) {
+		printk(KERN_WARNING "Fail to find correlated MSI-X entry!\n");
+		return 0;
+	}
+	for (i = 0; i < assigned_dev->entries_nr; i++)
+		if (entry == (guest_msix_entries + i)->entry) {
+			gsi = (guest_msix_entries + i)->vector;
+			break;
+		}
+	if (gsi < 0) {
+		printk(KERN_WARNING "Fail to find correlated MSI-X gsi!\n");
+		return 0;
+	}
+
+	return gsi;
+}
+
 static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work)
 {
 	struct kvm_assigned_dev_kernel *assigned_dev;
+	struct kvm *kvm;
+	u32 gsi;
+	int irq;
 
 	assigned_dev = container_of(work, struct kvm_assigned_dev_kernel,
 				    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(&assigned_dev->kvm->lock);
-	kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
-		    assigned_dev->guest_irq, 1);
+	mutex_lock(&kvm->lock);
+handle_irq:
+	if (assigned_dev->irq_requested_type & KVM_ASSIGNED_DEV_MSIX) {
+		gsi = find_first_bit(kvm->irq_routes_pending_bitmap,
+				     KVM_MAX_IRQ_ROUTES);
+		BUG_ON(gsi >= KVM_MAX_IRQ_ROUTES);
+		clear_bit(gsi, kvm->irq_routes_pending_bitmap);
+	} else
+		gsi = assigned_dev->guest_irq;
+
+	kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id, gsi, 1);
 
 	if (assigned_dev->irq_requested_type & KVM_ASSIGNED_DEV_GUEST_MSI) {
 		enable_irq(assigned_dev->host_irq);
 		assigned_dev->host_irq_disabled = false;
+	} else if (assigned_dev->irq_requested_type & KVM_ASSIGNED_DEV_MSIX) {
+		irq = find_host_irq_from_gsi(assigned_dev, gsi);
+		if (irq != 0)
+			enable_irq(irq);
+		assigned_dev->host_irq_disabled = false;
+		gsi = find_first_bit(kvm->irq_routes_pending_bitmap,
+				KVM_MAX_IRQ_ROUTES);
+		if (gsi < KVM_MAX_IRQ_ROUTES)
+			goto handle_irq;
 	}
+
 	mutex_unlock(&assigned_dev->kvm->lock);
 }
 
@@ -121,6 +209,14 @@ static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id)
 {
 	struct kvm_assigned_dev_kernel *assigned_dev =
 		(struct kvm_assigned_dev_kernel *) dev_id;
+	struct kvm *kvm = assigned_dev->kvm;
+
+	if (assigned_dev->irq_requested_type == KVM_ASSIGNED_DEV_MSIX) {
+		int gsi = find_gsi_from_host_irq(assigned_dev, irq);
+		if (gsi < 0)
+			return IRQ_HANDLED;
+		set_bit(gsi, kvm->irq_routes_pending_bitmap);
+	}
 
 	schedule_work(&assigned_dev->interrupt_work);
 
-- 
1.5.4.5