vhost: do not GSO when no header is present

[dpdk.git] / lib / librte_vhost / vhost_user.c

diff --git a/lib/librte_vhost/vhost_user.c b/lib/librte_vhost/vhost_user.c
index e651912..ab7f3fc 100644 (file)
--- a/lib/librte_vhost/vhost_user.c
+++ b/lib/librte_vhost/vhost_user.c
@@ -180,7 +180,32 @@ static int
 vhost_user_set_vring_num(struct virtio_net *dev,
                         struct vhost_vring_state *state)
 {
-       dev->virtqueue[state->index]->size = state->num;
+       struct vhost_virtqueue *vq = dev->virtqueue[state->index];
+
+       vq->size = state->num;
+
+       if (dev->dequeue_zero_copy) {
+               vq->nr_zmbuf = 0;
+               vq->last_zmbuf_idx = 0;
+               vq->zmbuf_size = vq->size;
+               vq->zmbufs = rte_zmalloc(NULL, vq->zmbuf_size *
+                                        sizeof(struct zcopy_mbuf), 0);
+               if (vq->zmbufs == NULL) {
+                       RTE_LOG(WARNING, VHOST_CONFIG,
+                               "failed to allocate mem for zero copy; "
+                               "zero copy is force disabled\n");
+                       dev->dequeue_zero_copy = 0;
+               }
+       }
+
+       vq->shadow_used_ring = rte_malloc(NULL,
+                               vq->size * sizeof(struct vring_used_elem),
+                               RTE_CACHE_LINE_SIZE);
+       if (!vq->shadow_used_ring) {
+               RTE_LOG(ERR, VHOST_CONFIG,
+                       "failed to allocate memory for shadow used ring.\n");
+               return -1;
+       }
 
        return 0;
 }
@@ -343,7 +368,8 @@ vhost_user_set_vring_addr(struct virtio_net *dev, struct vhost_vring_addr *addr)
                        "last_used_idx (%u) and vq->used->idx (%u) mismatches; "
                        "some packets maybe resent for Tx and dropped for Rx\n",
                        vq->last_used_idx, vq->used->idx);
-               vq->last_used_idx     = vq->used->idx;
+               vq->last_used_idx  = vq->used->idx;
+               vq->last_avail_idx = vq->used->idx;
        }
 
        vq->log_guest_addr = addr->log_guest_addr;
@@ -367,7 +393,8 @@ static int
 vhost_user_set_vring_base(struct virtio_net *dev,
                          struct vhost_vring_state *state)
 {
-       dev->virtqueue[state->index]->last_used_idx = state->num;
+       dev->virtqueue[state->index]->last_used_idx  = state->num;
+       dev->virtqueue[state->index]->last_avail_idx = state->num;
 
        return 0;
 }
@@ -420,14 +447,14 @@ add_guest_pages(struct virtio_net *dev, struct virtio_memory_region *reg,
        reg_size -= size;
 
        while (reg_size > 0) {
+               size = RTE_MIN(reg_size, page_size);
                host_phys_addr = rte_mem_virt2phy((void *)(uintptr_t)
                                                  host_user_addr);
-               add_one_guest_page(dev, guest_phys_addr, host_phys_addr,
-                                  page_size);
+               add_one_guest_page(dev, guest_phys_addr, host_phys_addr, size);
 
-               host_user_addr  += page_size;
-               guest_phys_addr += page_size;
-               reg_size -= page_size;
+               host_user_addr  += size;
+               guest_phys_addr += size;
+               reg_size -= size;
        }
 }
 
@@ -540,7 +567,8 @@ vhost_user_set_mem_table(struct virtio_net *dev, struct VhostUserMsg *pmsg)
                reg->host_user_addr = (uint64_t)(uintptr_t)mmap_addr +
                                      mmap_offset;
 
-               add_guest_pages(dev, reg, alignment);
+               if (dev->dequeue_zero_copy)
+                       add_guest_pages(dev, reg, alignment);
 
                RTE_LOG(INFO, VHOST_CONFIG,
                        "guest memory region %u, size: 0x%" PRIx64 "\n"
@@ -660,11 +688,32 @@ vhost_user_set_vring_kick(struct virtio_net *dev, struct VhostUserMsg *pmsg)
        vq->kickfd = file.fd;
 
        if (virtio_is_ready(dev) && !(dev->flags & VIRTIO_DEV_RUNNING)) {
+               if (dev->dequeue_zero_copy) {
+                       RTE_LOG(INFO, VHOST_CONFIG,
+                               "dequeue zero copy is enabled\n");
+               }
+
                if (notify_ops->new_device(dev->vid) == 0)
                        dev->flags |= VIRTIO_DEV_RUNNING;
        }
 }
 
+static void
+free_zmbufs(struct vhost_virtqueue *vq)
+{
+       struct zcopy_mbuf *zmbuf, *next;
+
+       for (zmbuf = TAILQ_FIRST(&vq->zmbuf_list);
+            zmbuf != NULL; zmbuf = next) {
+               next = TAILQ_NEXT(zmbuf, next);
+
+               rte_pktmbuf_free(zmbuf->mbuf);
+               TAILQ_REMOVE(&vq->zmbuf_list, zmbuf, next);
+       }
+
+       rte_free(vq->zmbufs);
+}
+
 /*
  * when virtio is stopped, qemu will send us the GET_VRING_BASE message.
  */
@@ -672,6 +721,8 @@ static int
 vhost_user_get_vring_base(struct virtio_net *dev,
                          struct vhost_vring_state *state)
 {
+       struct vhost_virtqueue *vq = dev->virtqueue[state->index];
+
        /* We have to stop the queue (virtio) if it is running. */
        if (dev->flags & VIRTIO_DEV_RUNNING) {
                dev->flags &= ~VIRTIO_DEV_RUNNING;
@@ -679,7 +730,7 @@ vhost_user_get_vring_base(struct virtio_net *dev,
        }
 
        /* Here we are safe to get the last used index */
-       state->num = dev->virtqueue[state->index]->last_used_idx;
+       state->num = vq->last_used_idx;
 
        RTE_LOG(INFO, VHOST_CONFIG,
                "vring base idx:%d file:%d\n", state->index, state->num);
@@ -688,10 +739,15 @@ vhost_user_get_vring_base(struct virtio_net *dev,
         * sent and only sent in vhost_vring_stop.
         * TODO: cleanup the vring, it isn't usable since here.
         */
-       if (dev->virtqueue[state->index]->kickfd >= 0)
-               close(dev->virtqueue[state->index]->kickfd);
+       if (vq->kickfd >= 0)
+               close(vq->kickfd);
+
+       vq->kickfd = VIRTIO_UNINITIALIZED_EVENTFD;
 
-       dev->virtqueue[state->index]->kickfd = VIRTIO_UNINITIALIZED_EVENTFD;
+       if (dev->dequeue_zero_copy)
+               free_zmbufs(vq);
+       rte_free(vq->shadow_used_ring);
+       vq->shadow_used_ring = NULL;
 
        return 0;
 }
@@ -848,6 +904,7 @@ send_vhost_message(int sockfd, struct VhostUserMsg *msg)
                return 0;
 
        msg->flags &= ~VHOST_USER_VERSION_MASK;
+       msg->flags &= ~VHOST_USER_NEED_REPLY;
        msg->flags |= VHOST_USER_VERSION;
        msg->flags |= VHOST_USER_REPLY_MASK;
 
@@ -883,6 +940,7 @@ vhost_user_msg_handler(int vid, int fd)
                return -1;
        }
 
+       ret = 0;
        RTE_LOG(INFO, VHOST_CONFIG, "read message %s\n",
                vhost_message_str[msg.request]);
        switch (msg.request) {
@@ -912,7 +970,7 @@ vhost_user_msg_handler(int vid, int fd)
                break;
 
        case VHOST_USER_SET_MEM_TABLE:
-               vhost_user_set_mem_table(dev, &msg);
+               ret = vhost_user_set_mem_table(dev, &msg);
                break;
 
        case VHOST_USER_SET_LOG_BASE:
@@ -970,9 +1028,16 @@ vhost_user_msg_handler(int vid, int fd)
                break;
 
        default:
+               ret = -1;
                break;
 
        }
 
+       if (msg.flags & VHOST_USER_NEED_REPLY) {
+               msg.payload.u64 = !!ret;
+               msg.size = sizeof(msg.payload.u64);
+               send_vhost_message(fd, &msg);
+       }
+
        return 0;
 }