virtio: introduce an API to set affinity for a virtqueue

Sometimes, virtio device need to configure irq affinity hint to maximize the
performance. Instead of just exposing the irq of a virtqueue, this patch
introduce an API to set the affinity for a virtqueue.

The api is best-effort, the affinity hint may not be set as expected due to
platform support, irq sharing or irq type. Currently, only pci method were
implemented and we set the affinity according to:

- if device uses INTX, we just ignore the request
- if device has per vq vector, we force the affinity hint
- if the virtqueues share MSI, make the affinity OR over all affinities
  requested

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>

diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c
index d902464b89ce2af4f8da695d8c002d529a55f2f4..f5dfe6bdb9598c7ac4b5ef4553cee62190d83732 100644 (file)
--- a/drivers/virtio/virtio_pci.c
+++ b/drivers/virtio/virtio_pci.c
@@ -48,6 +48,7 @@ struct virtio_pci_device
        int msix_enabled;
        int intx_enabled;
        struct msix_entry *msix_entries;
+       cpumask_var_t *msix_affinity_masks;
        /* Name strings for interrupts. This size should be enough,
         * and I'm too lazy to allocate each name separately. */
        char (*msix_names)[256];
@@ -276,6 +277,10 @@ static void vp_free_vectors(struct virtio_device *vdev)
        for (i = 0; i < vp_dev->msix_used_vectors; ++i)
                free_irq(vp_dev->msix_entries[i].vector, vp_dev);
 
+       for (i = 0; i < vp_dev->msix_vectors; i++)
+               if (vp_dev->msix_affinity_masks[i])
+                       free_cpumask_var(vp_dev->msix_affinity_masks[i]);
+
        if (vp_dev->msix_enabled) {
                /* Disable the vector used for configuration */
                iowrite16(VIRTIO_MSI_NO_VECTOR,
@@ -293,6 +298,8 @@ static void vp_free_vectors(struct virtio_device *vdev)
        vp_dev->msix_names = NULL;
        kfree(vp_dev->msix_entries);
        vp_dev->msix_entries = NULL;
+       kfree(vp_dev->msix_affinity_masks);
+       vp_dev->msix_affinity_masks = NULL;
 }
 
 static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors,
@@ -311,6 +318,15 @@ static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors,
                                     GFP_KERNEL);
        if (!vp_dev->msix_names)
                goto error;
+       vp_dev->msix_affinity_masks
+               = kzalloc(nvectors * sizeof *vp_dev->msix_affinity_masks,
+                         GFP_KERNEL);
+       if (!vp_dev->msix_affinity_masks)
+               goto error;
+       for (i = 0; i < nvectors; ++i)
+               if (!alloc_cpumask_var(&vp_dev->msix_affinity_masks[i],
+                                       GFP_KERNEL))
+                       goto error;
 
        for (i = 0; i < nvectors; ++i)
                vp_dev->msix_entries[i].entry = i;
@@ -606,6 +622,35 @@ static const char *vp_bus_name(struct virtio_device *vdev)
        return pci_name(vp_dev->pci_dev);
 }
 
+/* Setup the affinity for a virtqueue:
+ * - force the affinity for per vq vector
+ * - OR over all affinities for shared MSI
+ * - ignore the affinity request if we're using INTX
+ */
+static int vp_set_vq_affinity(struct virtqueue *vq, int cpu)
+{
+       struct virtio_device *vdev = vq->vdev;
+       struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+       struct virtio_pci_vq_info *info = vq->priv;
+       struct cpumask *mask;
+       unsigned int irq;
+
+       if (!vq->callback)
+               return -EINVAL;
+
+       if (vp_dev->msix_enabled) {
+               mask = vp_dev->msix_affinity_masks[info->msix_vector];
+               irq = vp_dev->msix_entries[info->msix_vector].vector;
+               if (cpu == -1)
+                       irq_set_affinity_hint(irq, NULL);
+               else {
+                       cpumask_set_cpu(cpu, mask);
+                       irq_set_affinity_hint(irq, mask);
+               }
+       }
+       return 0;
+}
+
 static struct virtio_config_ops virtio_pci_config_ops = {
        .get            = vp_get,
        .set            = vp_set,
@@ -617,6 +662,7 @@ static struct virtio_config_ops virtio_pci_config_ops = {
        .get_features   = vp_get_features,
        .finalize_features = vp_finalize_features,
        .bus_name       = vp_bus_name,
+       .set_vq_affinity = vp_set_vq_affinity,
 };
 
 static void virtio_pci_release_dev(struct device *_d)

diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index fc457f452f648722a1dc2850bc681e78576403d3..2c4a9895379d7b046f039c5d1d9400af622318db 100644 (file)
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -98,6 +98,7 @@
  *     vdev: the virtio_device
  *      This returns a pointer to the bus name a la pci_name from which
  *      the caller can then copy.
+ * @set_vq_affinity: set the affinity for a virtqueue.
  */
 typedef void vq_callback_t(struct virtqueue *);
 struct virtio_config_ops {
@@ -116,6 +117,7 @@ struct virtio_config_ops {
        u32 (*get_features)(struct virtio_device *vdev);
        void (*finalize_features)(struct virtio_device *vdev);
        const char *(*bus_name)(struct virtio_device *vdev);
+       int (*set_vq_affinity)(struct virtqueue *vq, int cpu);
 };
 
 /* If driver didn't advertise the feature, it will never appear. */
@@ -190,5 +192,24 @@ const char *virtio_bus_name(struct virtio_device *vdev)
        return vdev->config->bus_name(vdev);
 }
 
+/**
+ * virtqueue_set_affinity - setting affinity for a virtqueue
+ * @vq: the virtqueue
+ * @cpu: the cpu no.
+ *
+ * Pay attention the function are best-effort: the affinity hint may not be set
+ * due to config support, irq type and sharing.
+ *
+ */
+static inline
+int virtqueue_set_affinity(struct virtqueue *vq, int cpu)
+{
+       struct virtio_device *vdev = vq->vdev;
+       if (vdev->config->set_vq_affinity)
+               return vdev->config->set_vq_affinity(vq, cpu);
+       return 0;
+}
+
+
 #endif /* __KERNEL__ */
 #endif /* _LINUX_VIRTIO_CONFIG_H */