X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Flibrte_vhost%2Fvhost_user.c;h=d20c8c57ad203f24834421e0de89a8809e19960f;hb=e2a94f9ad3ef949c0df3e63699bd4e381b5003d9;hp=4ca872842b6ea7e5c6178fc09b1c92399a4beb33;hpb=d0fcc38f5fa41778968b6f39777a61edb3aef813;p=dpdk.git

diff --git a/lib/librte_vhost/vhost_user.c b/lib/librte_vhost/vhost_user.c
index 4ca872842b..d20c8c57ad 100644
--- a/lib/librte_vhost/vhost_user.c
+++ b/lib/librte_vhost/vhost_user.c
@@ -87,6 +87,8 @@ static const char *vhost_message_str[VHOST_USER_MAX] = {
 	[VHOST_USER_POSTCOPY_END]  = "VHOST_USER_POSTCOPY_END",
 	[VHOST_USER_GET_INFLIGHT_FD] = "VHOST_USER_GET_INFLIGHT_FD",
 	[VHOST_USER_SET_INFLIGHT_FD] = "VHOST_USER_SET_INFLIGHT_FD",
+	[VHOST_USER_SET_STATUS] = "VHOST_USER_SET_STATUS",
+	[VHOST_USER_GET_STATUS] = "VHOST_USER_GET_STATUS",
 };
 
 static int send_vhost_reply(int sockfd, struct VhostUserMsg *msg);
@@ -132,47 +134,15 @@ get_blk_size(int fd)
 	return ret == -1 ? (uint64_t)-1 : (uint64_t)stat.st_blksize;
 }
 
-/*
- * Reclaim all the outstanding zmbufs for a virtqueue.
- */
-static void
-drain_zmbuf_list(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);
-
-		while (!mbuf_is_consumed(zmbuf->mbuf))
-			usleep(1000);
-
-		TAILQ_REMOVE(&vq->zmbuf_list, zmbuf, next);
-		restore_mbuf(zmbuf->mbuf);
-		rte_pktmbuf_free(zmbuf->mbuf);
-		put_zmbuf(zmbuf);
-		vq->nr_zmbuf -= 1;
-	}
-}
-
 static void
 free_mem_region(struct virtio_net *dev)
 {
 	uint32_t i;
 	struct rte_vhost_mem_region *reg;
-	struct vhost_virtqueue *vq;
 
 	if (!dev || !dev->mem)
 		return;
 
-	if (dev->dequeue_zero_copy) {
-		for (i = 0; i < dev->nr_vring; i++) {
-			vq = dev->virtqueue[i];
-			if (vq)
-				drain_zmbuf_list(vq);
-		}
-	}
-
 	for (i = 0; i < dev->mem->nregions; i++) {
 		reg = &dev->mem->regions[i];
 		if (reg->host_user_addr) {
@@ -233,6 +203,11 @@ vhost_user_notify_queue_state(struct virtio_net *dev, uint16_t index,
 			      int enable)
 {
 	struct rte_vdpa_device *vdpa_dev = dev->vdpa_dev;
+	struct vhost_virtqueue *vq = dev->virtqueue[index];
+
+	/* Configure guest notifications on enable */
+	if (enable && vq->notif_enable != VIRTIO_UNINITIALIZED_NOTIF)
+		vhost_enable_guest_notification(dev, vq, vq->notif_enable);
 
 	if (vdpa_dev && vdpa_dev->ops->set_vring_state)
 		vdpa_dev->ops->set_vring_state(dev->vid, index, enable);
@@ -338,6 +313,9 @@ vhost_user_set_features(struct virtio_net **pdev, struct VhostUserMsg *msg,
 		VHOST_LOG_CONFIG(ERR,
 			"(%d) received invalid negotiated features.\n",
 			dev->vid);
+		dev->flags |= VIRTIO_DEV_FEATURES_FAILED;
+		dev->status &= ~VIRTIO_DEVICE_STATUS_FEATURES_OK;
+
 		return RTE_VHOST_MSG_RESULT_ERR;
 	}
 
@@ -363,7 +341,9 @@ vhost_user_set_features(struct virtio_net **pdev, struct VhostUserMsg *msg,
 
 	dev->features = features;
 	if (dev->features &
-		((1 << VIRTIO_NET_F_MRG_RXBUF) | (1ULL << VIRTIO_F_VERSION_1))) {
+		((1ULL << VIRTIO_NET_F_MRG_RXBUF) |
+		 (1ULL << VIRTIO_F_VERSION_1) |
+		 (1ULL << VIRTIO_F_RING_PACKED))) {
 		dev->vhost_hlen = sizeof(struct virtio_net_hdr_mrg_rxbuf);
 	} else {
 		dev->vhost_hlen = sizeof(struct virtio_net_hdr);
@@ -398,9 +378,10 @@ vhost_user_set_features(struct virtio_net **pdev, struct VhostUserMsg *msg,
 	}
 
 	vdpa_dev = dev->vdpa_dev;
-	if (vdpa_dev && vdpa_dev->ops->set_features)
+	if (vdpa_dev)
 		vdpa_dev->ops->set_features(dev->vid);
 
+	dev->flags &= ~VIRTIO_DEV_FEATURES_FAILED;
 	return RTE_VHOST_MSG_RESULT_OK;
 }
 
@@ -443,23 +424,6 @@ vhost_user_set_vring_num(struct virtio_net **pdev,
 		return RTE_VHOST_MSG_RESULT_ERR;
 	}
 
-	if (dev->dequeue_zero_copy) {
-		vq->nr_zmbuf = 0;
-		vq->last_zmbuf_idx = 0;
-		vq->zmbuf_size = vq->size;
-		if (vq->zmbufs)
-			rte_free(vq->zmbufs);
-		vq->zmbufs = rte_zmalloc(NULL, vq->zmbuf_size *
-					 sizeof(struct zcopy_mbuf), 0);
-		if (vq->zmbufs == NULL) {
-			VHOST_LOG_CONFIG(WARNING,
-				"failed to allocate mem for zero copy; "
-				"zero copy is force disabled\n");
-			dev->dequeue_zero_copy = 0;
-		}
-		TAILQ_INIT(&vq->zmbuf_list);
-	}
-
 	if (vq_is_packed(dev)) {
 		if (vq->shadow_used_packed)
 			rte_free(vq->shadow_used_packed);
@@ -476,12 +440,14 @@ vhost_user_set_vring_num(struct virtio_net **pdev,
 	} else {
 		if (vq->shadow_used_split)
 			rte_free(vq->shadow_used_split);
+
 		vq->shadow_used_split = rte_malloc(NULL,
 				vq->size * sizeof(struct vring_used_elem),
 				RTE_CACHE_LINE_SIZE);
+
 		if (!vq->shadow_used_split) {
 			VHOST_LOG_CONFIG(ERR,
-					"failed to allocate memory for shadow used ring.\n");
+					"failed to allocate memory for vq internal data.\n");
 			return RTE_VHOST_MSG_RESULT_ERR;
 		}
 	}
@@ -511,7 +477,6 @@ numa_realloc(struct virtio_net *dev, int index)
 	int oldnode, newnode;
 	struct virtio_net *old_dev;
 	struct vhost_virtqueue *old_vq, *vq;
-	struct zcopy_mbuf *new_zmbuf;
 	struct vring_used_elem *new_shadow_used_split;
 	struct vring_used_elem_packed *new_shadow_used_packed;
 	struct batch_copy_elem *new_batch_copy_elems;
@@ -542,16 +507,6 @@ numa_realloc(struct virtio_net *dev, int index)
 			return dev;
 
 		memcpy(vq, old_vq, sizeof(*vq));
-		TAILQ_INIT(&vq->zmbuf_list);
-
-		if (dev->dequeue_zero_copy) {
-			new_zmbuf = rte_malloc_socket(NULL, vq->zmbuf_size *
-					sizeof(struct zcopy_mbuf), 0, newnode);
-			if (new_zmbuf) {
-				rte_free(vq->zmbufs);
-				vq->zmbufs = new_zmbuf;
-			}
-		}
 
 		if (vq_is_packed(dev)) {
 			new_shadow_used_packed = rte_malloc_socket(NULL,
@@ -1070,6 +1025,13 @@ vhost_user_set_mem_table(struct virtio_net **pdev, struct VhostUserMsg *msg,
 	}
 
 	if (dev->mem) {
+		if (dev->flags & VIRTIO_DEV_VDPA_CONFIGURED) {
+			struct rte_vdpa_device *vdpa_dev = dev->vdpa_dev;
+
+			if (vdpa_dev && vdpa_dev->ops->dev_close)
+				vdpa_dev->ops->dev_close(dev->vid);
+			dev->flags &= ~VIRTIO_DEV_VDPA_CONFIGURED;
+		}
 		free_mem_region(dev);
 		rte_free(dev->mem);
 		dev->mem = NULL;
@@ -1159,7 +1121,7 @@ vhost_user_set_mem_table(struct virtio_net **pdev, struct VhostUserMsg *msg,
 			goto err_mmap;
 		}
 
-		populate = (dev->dequeue_zero_copy) ? MAP_POPULATE : 0;
+		populate = dev->async_copy ? MAP_POPULATE : 0;
 		mmap_addr = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE,
 				 MAP_SHARED | populate, fd, 0);
 
@@ -1174,7 +1136,7 @@ vhost_user_set_mem_table(struct virtio_net **pdev, struct VhostUserMsg *msg,
 		reg->host_user_addr = (uint64_t)(uintptr_t)mmap_addr +
 				      mmap_offset;
 
-		if (dev->dequeue_zero_copy)
+		if (dev->async_copy)
 			if (add_guest_pages(dev, reg, alignment) < 0) {
 				VHOST_LOG_CONFIG(ERR,
 					"adding guest pages to region %u failed.\n",
@@ -1322,24 +1284,41 @@ vq_is_ready(struct virtio_net *dev, struct vhost_virtqueue *vq)
 	       vq->enabled;
 }
 
-#define VIRTIO_DEV_NUM_VQS_TO_BE_READY 2u
+#define VIRTIO_BUILTIN_NUM_VQS_TO_BE_READY 2u
 
 static int
 virtio_is_ready(struct virtio_net *dev)
 {
 	struct vhost_virtqueue *vq;
-	uint32_t i;
+	uint32_t i, nr_vring = dev->nr_vring;
+
+	if (dev->flags & VIRTIO_DEV_READY)
+		return 1;
 
-	if (dev->nr_vring < VIRTIO_DEV_NUM_VQS_TO_BE_READY)
+	if (!dev->nr_vring)
 		return 0;
 
-	for (i = 0; i < VIRTIO_DEV_NUM_VQS_TO_BE_READY; i++) {
+	if (dev->flags & VIRTIO_DEV_BUILTIN_VIRTIO_NET) {
+		nr_vring = VIRTIO_BUILTIN_NUM_VQS_TO_BE_READY;
+
+		if (dev->nr_vring < nr_vring)
+			return 0;
+	}
+
+	for (i = 0; i < nr_vring; i++) {
 		vq = dev->virtqueue[i];
 
 		if (!vq_is_ready(dev, vq))
 			return 0;
 	}
 
+	/* If supported, ensure the frontend is really done with config */
+	if (dev->protocol_features & (1ULL << VHOST_USER_PROTOCOL_F_STATUS))
+		if (!(dev->status & VIRTIO_DEVICE_STATUS_DRIVER_OK))
+			return 0;
+
+	dev->flags |= VIRTIO_DEV_READY;
+
 	if (!(dev->flags & VIRTIO_DEV_RUNNING))
 		VHOST_LOG_CONFIG(INFO,
 			"virtio is now ready for processing.\n");
@@ -1612,6 +1591,12 @@ vhost_user_set_vring_call(struct virtio_net **pdev, struct VhostUserMsg *msg,
 		"vring call idx:%d file:%d\n", file.index, file.fd);
 
 	vq = dev->virtqueue[file.index];
+
+	if (vq->ready) {
+		vq->ready = 0;
+		vhost_user_notify_queue_state(dev, file.index, 0);
+	}
+
 	if (vq->callfd >= 0)
 		close(vq->callfd);
 
@@ -1870,6 +1855,11 @@ vhost_user_set_vring_kick(struct virtio_net **pdev, struct VhostUserMsg *msg,
 				dev->vid, file.index, 1);
 	}
 
+	if (vq->ready) {
+		vq->ready = 0;
+		vhost_user_notify_queue_state(dev, file.index, 0);
+	}
+
 	if (vq->kickfd >= 0)
 		close(vq->kickfd);
 	vq->kickfd = file.fd;
@@ -1891,14 +1881,6 @@ vhost_user_set_vring_kick(struct virtio_net **pdev, struct VhostUserMsg *msg,
 	return RTE_VHOST_MSG_RESULT_OK;
 }
 
-static void
-free_zmbufs(struct vhost_virtqueue *vq)
-{
-	drain_zmbuf_list(vq);
-
-	rte_free(vq->zmbufs);
-}
-
 /*
  * when virtio is stopped, qemu will send us the GET_VRING_BASE message.
  */
@@ -1953,14 +1935,18 @@ vhost_user_get_vring_base(struct virtio_net **pdev,
 
 	vq->signalled_used_valid = false;
 
-	if (dev->dequeue_zero_copy)
-		free_zmbufs(vq);
 	if (vq_is_packed(dev)) {
 		rte_free(vq->shadow_used_packed);
 		vq->shadow_used_packed = NULL;
 	} else {
 		rte_free(vq->shadow_used_split);
 		vq->shadow_used_split = NULL;
+		if (vq->async_pkts_pending)
+			rte_free(vq->async_pkts_pending);
+		if (vq->async_pkts_info)
+			rte_free(vq->async_pkts_info);
+		vq->async_pkts_pending = NULL;
+		vq->async_pkts_info = NULL;
 	}
 
 	rte_free(vq->batch_copy_elems);
@@ -1994,9 +1980,13 @@ vhost_user_set_vring_enable(struct virtio_net **pdev,
 		"set queue enable: %d to qp idx: %d\n",
 		enable, index);
 
-	/* On disable, rings have to be stopped being processed. */
-	if (!enable && dev->dequeue_zero_copy)
-		drain_zmbuf_list(dev->virtqueue[index]);
+	if (enable && dev->virtqueue[index]->async_registered) {
+		if (dev->virtqueue[index]->async_pkts_inflight_n) {
+			VHOST_LOG_CONFIG(ERR, "failed to enable vring. "
+			"async inflight packets must be completed first\n");
+			return RTE_VHOST_MSG_RESULT_ERR;
+		}
+	}
 
 	dev->virtqueue[index]->enabled = enable;
 
@@ -2429,6 +2419,70 @@ vhost_user_postcopy_end(struct virtio_net **pdev, struct VhostUserMsg *msg,
 	return RTE_VHOST_MSG_RESULT_REPLY;
 }
 
+static int
+vhost_user_get_status(struct virtio_net **pdev, struct VhostUserMsg *msg,
+		      int main_fd __rte_unused)
+{
+	struct virtio_net *dev = *pdev;
+
+	if (validate_msg_fds(msg, 0) != 0)
+		return RTE_VHOST_MSG_RESULT_ERR;
+
+	msg->payload.u64 = dev->status;
+	msg->size = sizeof(msg->payload.u64);
+	msg->fd_num = 0;
+
+	return RTE_VHOST_MSG_RESULT_REPLY;
+}
+
+static int
+vhost_user_set_status(struct virtio_net **pdev, struct VhostUserMsg *msg,
+			int main_fd __rte_unused)
+{
+	struct virtio_net *dev = *pdev;
+
+	if (validate_msg_fds(msg, 0) != 0)
+		return RTE_VHOST_MSG_RESULT_ERR;
+
+	/* As per Virtio specification, the device status is 8bits long */
+	if (msg->payload.u64 > UINT8_MAX) {
+		VHOST_LOG_CONFIG(ERR, "Invalid VHOST_USER_SET_STATUS payload 0x%" PRIx64 "\n",
+				msg->payload.u64);
+		return RTE_VHOST_MSG_RESULT_ERR;
+	}
+
+	dev->status = msg->payload.u64;
+
+	if ((dev->status & VIRTIO_DEVICE_STATUS_FEATURES_OK) &&
+	    (dev->flags & VIRTIO_DEV_FEATURES_FAILED)) {
+		VHOST_LOG_CONFIG(ERR, "FEATURES_OK bit is set but feature negotiation failed\n");
+		/*
+		 * Clear the bit to let the driver know about the feature
+		 * negotiation failure
+		 */
+		dev->status &= ~VIRTIO_DEVICE_STATUS_FEATURES_OK;
+	}
+
+	VHOST_LOG_CONFIG(INFO, "New device status(0x%08x):\n"
+			"\t-RESET: %u\n"
+			"\t-ACKNOWLEDGE: %u\n"
+			"\t-DRIVER: %u\n"
+			"\t-FEATURES_OK: %u\n"
+			"\t-DRIVER_OK: %u\n"
+			"\t-DEVICE_NEED_RESET: %u\n"
+			"\t-FAILED: %u\n",
+			dev->status,
+			(dev->status == VIRTIO_DEVICE_STATUS_RESET),
+			!!(dev->status & VIRTIO_DEVICE_STATUS_ACK),
+			!!(dev->status & VIRTIO_DEVICE_STATUS_DRIVER),
+			!!(dev->status & VIRTIO_DEVICE_STATUS_FEATURES_OK),
+			!!(dev->status & VIRTIO_DEVICE_STATUS_DRIVER_OK),
+			!!(dev->status & VIRTIO_DEVICE_STATUS_DEV_NEED_RESET),
+			!!(dev->status & VIRTIO_DEVICE_STATUS_FAILED));
+
+	return RTE_VHOST_MSG_RESULT_OK;
+}
+
 typedef int (*vhost_message_handler_t)(struct virtio_net **pdev,
 					struct VhostUserMsg *msg,
 					int main_fd);
@@ -2461,6 +2515,8 @@ static vhost_message_handler_t vhost_message_handlers[VHOST_USER_MAX] = {
 	[VHOST_USER_POSTCOPY_END] = vhost_user_postcopy_end,
 	[VHOST_USER_GET_INFLIGHT_FD] = vhost_user_get_inflight_fd,
 	[VHOST_USER_SET_INFLIGHT_FD] = vhost_user_set_inflight_fd,
+	[VHOST_USER_SET_STATUS] = vhost_user_set_status,
+	[VHOST_USER_GET_STATUS] = vhost_user_get_status,
 };
 
 /* return bytes# of read on success or negative val on failure. */
@@ -2801,34 +2857,39 @@ skip_to_post_handle:
 		bool cur_ready = vq_is_ready(dev, vq);
 
 		if (cur_ready != (vq && vq->ready)) {
-			vhost_user_notify_queue_state(dev, i, cur_ready);
 			vq->ready = cur_ready;
+			vhost_user_notify_queue_state(dev, i, cur_ready);
 		}
 	}
 
 
-	if (!(dev->flags & VIRTIO_DEV_RUNNING) && virtio_is_ready(dev)) {
-		dev->flags |= VIRTIO_DEV_READY;
+	if (!virtio_is_ready(dev))
+		goto out;
 
-		if (!(dev->flags & VIRTIO_DEV_RUNNING)) {
-			if (dev->dequeue_zero_copy) {
-				VHOST_LOG_CONFIG(INFO,
-						"dequeue zero copy is enabled\n");
-			}
+	/*
+	 * Virtio is now ready. If not done already, it is time
+	 * to notify the application it can process the rings and
+	 * configure the vDPA device if present.
+	 */
 
-			if (dev->notify_ops->new_device(dev->vid) == 0)
-				dev->flags |= VIRTIO_DEV_RUNNING;
-		}
+	if (!(dev->flags & VIRTIO_DEV_RUNNING)) {
+		if (dev->notify_ops->new_device(dev->vid) == 0)
+			dev->flags |= VIRTIO_DEV_RUNNING;
 	}
 
 	vdpa_dev = dev->vdpa_dev;
-	if (vdpa_dev && virtio_is_ready(dev) &&
-	    !(dev->flags & VIRTIO_DEV_VDPA_CONFIGURED)) {
-		if (vdpa_dev->ops->dev_conf)
-			vdpa_dev->ops->dev_conf(dev->vid);
-		dev->flags |= VIRTIO_DEV_VDPA_CONFIGURED;
+	if (!vdpa_dev)
+		goto out;
+
+	if (!(dev->flags & VIRTIO_DEV_VDPA_CONFIGURED)) {
+		if (vdpa_dev->ops->dev_conf(dev->vid))
+			VHOST_LOG_CONFIG(ERR,
+					 "Failed to configure vDPA device\n");
+		else
+			dev->flags |= VIRTIO_DEV_VDPA_CONFIGURED;
 	}
 
+out:
 	return 0;
 }