virtio-pci: speedup MSI-X masking and unmasking

This patch tries to speed up the MSI-X masking and unmasking through
the mapping between vector and queues. With this patch it will there's
no need to go through all possible virtqueues, which may help to
reduce the time spent when doing MSI-X masking/unmasking a single
vector when more than hundreds or even thousands of virtqueues were
supported.

Tested with 80 queue pairs virito-net-pci by changing the smp affinity
in the background and doing netperf in the same time:

Before the patch:
5711.70 Gbits/sec
After the patch:
6830.98 Gbits/sec

About 19.6% improvements in throughput.

Cc: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: NJason Wang <jasowang@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

hw/virtio/virtio-pci.c

@@ -630,28 +630,30 @@ static int virtio_pci_vector_unmask(PCIDevice *dev, unsigned vector,
 {
     VirtIOPCIProxy *proxy = container_of(dev, VirtIOPCIProxy, pci_dev);
     VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
-    int ret, queue_no;
+    VirtQueue *vq = virtio_vector_first_queue(vdev, vector);
+    int ret, index, unmasked = 0;
 
-    for (queue_no = 0; queue_no < proxy->nvqs_with_notifiers; queue_no++) {
-        if (!virtio_queue_get_num(vdev, queue_no)) {
+    while (vq) {
+        index = virtio_get_queue_index(vq);
+        if (!virtio_queue_get_num(vdev, index)) {
             break;
         }
-        if (virtio_queue_vector(vdev, queue_no) != vector) {
-            continue;
-        }
-        ret = virtio_pci_vq_vector_unmask(proxy, queue_no, vector, msg);
+        ret = virtio_pci_vq_vector_unmask(proxy, index, vector, msg);
         if (ret < 0) {
             goto undo;
         }
+        vq = virtio_vector_next_queue(vq);
+        ++unmasked;
     }
+
     return 0;
 
 undo:
-    while (--queue_no >= 0) {
-        if (virtio_queue_vector(vdev, queue_no) != vector) {
-            continue;
-        }
-        virtio_pci_vq_vector_mask(proxy, queue_no, vector);
+    vq = virtio_vector_first_queue(vdev, vector);
+    while (vq && --unmasked >= 0) {
+        index = virtio_get_queue_index(vq);
+        virtio_pci_vq_vector_mask(proxy, index, vector);
+        vq = virtio_vector_next_queue(vq);
     }
     return ret;
 }
@@ -660,16 +662,16 @@ static void virtio_pci_vector_mask(PCIDevice *dev, unsigned vector)
 {
     VirtIOPCIProxy *proxy = container_of(dev, VirtIOPCIProxy, pci_dev);
     VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
-    int queue_no;
+    VirtQueue *vq = virtio_vector_first_queue(vdev, vector);
+    int index;
 
-    for (queue_no = 0; queue_no < proxy->nvqs_with_notifiers; queue_no++) {
-        if (!virtio_queue_get_num(vdev, queue_no)) {
+    while (vq) {
+        index = virtio_get_queue_index(vq);
+        if (!virtio_queue_get_num(vdev, index)) {
             break;
         }
-        if (virtio_queue_vector(vdev, queue_no) != vector) {
-            continue;
-        }
-        virtio_pci_vq_vector_mask(proxy, queue_no, vector);
+        virtio_pci_vq_vector_mask(proxy, index, vector);
+        vq = virtio_vector_next_queue(vq);
     }
 }