Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Pull virtio updates from Michael Tsirkin:

 - A huge patchset supporting vq resize using the new vq reset
   capability

 - Features, fixes, and cleanups all over the place

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (88 commits)
  vdpa/mlx5: Fix possible uninitialized return value
  vdpa_sim_blk: add support for discard and write-zeroes
  vdpa_sim_blk: add support for VIRTIO_BLK_T_FLUSH
  vdpa_sim_blk: make vdpasim_blk_check_range usable by other requests
  vdpa_sim_blk: check if sector is 0 for commands other than read or write
  vdpa_sim: Implement suspend vdpa op
  vhost-vdpa: uAPI to suspend the device
  vhost-vdpa: introduce SUSPEND backend feature bit
  vdpa: Add suspend operation
  virtio-blk: Avoid use-after-free on suspend/resume
  virtio_vdpa: support the arg sizes of find_vqs()
  vhost-vdpa: Call ida_simple_remove() when failed
  vDPA: fix 'cast to restricted le16' warnings in vdpa.c
  vDPA: !FEATURES_OK should not block querying device config space
  vDPA/ifcvf: support userspace to query features and MQ of a management device
  vDPA/ifcvf: get_config_size should return a value no greater than dev implementation
  vhost scsi: Allow user to control num virtqueues
  vhost-scsi: Fix max number of virtqueues
  vdpa/mlx5: Support different address spaces for control and data
  vdpa/mlx5: Implement susupend virtqueue callback
  ...

1 files changed, 286 insertions, 39 deletions

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 3b3eebad3977..d934774e9733 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -135,6 +135,9 @@ struct send_queue {
 	struct virtnet_sq_stats stats;
 
 	struct napi_struct napi;
+
+	/* Record whether sq is in reset state. */
+	bool reset;
 };
 
 /* Internal representation of a receive virtqueue */
@@ -267,6 +270,12 @@ struct virtnet_info {
 	u8 duplex;
 	u32 speed;
 
+	/* Interrupt coalescing settings */
+	u32 tx_usecs;
+	u32 rx_usecs;
+	u32 tx_max_packets;
+	u32 rx_max_packets;
+
 	unsigned long guest_offloads;
 	unsigned long guest_offloads_capable;
 
@@ -284,6 +293,9 @@ struct padded_vnet_hdr {
 	char padding[12];
 };
 
+static void virtnet_rq_free_unused_buf(struct virtqueue *vq, void *buf);
+static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf);
+
 static bool is_xdp_frame(void *ptr)
 {
 	return (unsigned long)ptr & VIRTIO_XDP_FLAG;
@@ -1628,6 +1640,11 @@ static void virtnet_poll_cleantx(struct receive_queue *rq)
 		return;
 
 	if (__netif_tx_trylock(txq)) {
+		if (sq->reset) {
+			__netif_tx_unlock(txq);
+			return;
+		}
+
 		do {
 			virtqueue_disable_cb(sq->vq);
 			free_old_xmit_skbs(sq, true);
@@ -1875,6 +1892,70 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 	return NETDEV_TX_OK;
 }
 
+static int virtnet_rx_resize(struct virtnet_info *vi,
+			     struct receive_queue *rq, u32 ring_num)
+{
+	bool running = netif_running(vi->dev);
+	int err, qindex;
+
+	qindex = rq - vi->rq;
+
+	if (running)
+		napi_disable(&rq->napi);
+
+	err = virtqueue_resize(rq->vq, ring_num, virtnet_rq_free_unused_buf);
+	if (err)
+		netdev_err(vi->dev, "resize rx fail: rx queue index: %d err: %d\n", qindex, err);
+
+	if (!try_fill_recv(vi, rq, GFP_KERNEL))
+		schedule_delayed_work(&vi->refill, 0);
+
+	if (running)
+		virtnet_napi_enable(rq->vq, &rq->napi);
+	return err;
+}
+
+static int virtnet_tx_resize(struct virtnet_info *vi,
+			     struct send_queue *sq, u32 ring_num)
+{
+	bool running = netif_running(vi->dev);
+	struct netdev_queue *txq;
+	int err, qindex;
+
+	qindex = sq - vi->sq;
+
+	if (running)
+		virtnet_napi_tx_disable(&sq->napi);
+
+	txq = netdev_get_tx_queue(vi->dev, qindex);
+
+	/* 1. wait all ximt complete
+	 * 2. fix the race of netif_stop_subqueue() vs netif_start_subqueue()
+	 */
+	__netif_tx_lock_bh(txq);
+
+	/* Prevent rx poll from accessing sq. */
+	sq->reset = true;
+
+	/* Prevent the upper layer from trying to send packets. */
+	netif_stop_subqueue(vi->dev, qindex);
+
+	__netif_tx_unlock_bh(txq);
+
+	err = virtqueue_resize(sq->vq, ring_num, virtnet_sq_free_unused_buf);
+	if (err)
+		netdev_err(vi->dev, "resize tx fail: tx queue index: %d err: %d\n", qindex, err);
+
+	__netif_tx_lock_bh(txq);
+	sq->reset = false;
+	netif_tx_wake_queue(txq);
+	__netif_tx_unlock_bh(txq);
+
+	if (running)
+		virtnet_napi_tx_enable(vi, sq->vq, &sq->napi);
+	return err;
+}
+
 /*
  * Send command via the control virtqueue and check status.  Commands
  * supported by the hypervisor, as indicated by feature bits, should
@@ -2285,10 +2366,57 @@ static void virtnet_get_ringparam(struct net_device *dev,
 {
 	struct virtnet_info *vi = netdev_priv(dev);
 
-	ring->rx_max_pending = virtqueue_get_vring_size(vi->rq[0].vq);
-	ring->tx_max_pending = virtqueue_get_vring_size(vi->sq[0].vq);
-	ring->rx_pending = ring->rx_max_pending;
-	ring->tx_pending = ring->tx_max_pending;
+	ring->rx_max_pending = vi->rq[0].vq->num_max;
+	ring->tx_max_pending = vi->sq[0].vq->num_max;
+	ring->rx_pending = virtqueue_get_vring_size(vi->rq[0].vq);
+	ring->tx_pending = virtqueue_get_vring_size(vi->sq[0].vq);
+}
+
+static int virtnet_set_ringparam(struct net_device *dev,
+				 struct ethtool_ringparam *ring,
+				 struct kernel_ethtool_ringparam *kernel_ring,
+				 struct netlink_ext_ack *extack)
+{
+	struct virtnet_info *vi = netdev_priv(dev);
+	u32 rx_pending, tx_pending;
+	struct receive_queue *rq;
+	struct send_queue *sq;
+	int i, err;
+
+	if (ring->rx_mini_pending || ring->rx_jumbo_pending)
+		return -EINVAL;
+
+	rx_pending = virtqueue_get_vring_size(vi->rq[0].vq);
+	tx_pending = virtqueue_get_vring_size(vi->sq[0].vq);
+
+	if (ring->rx_pending == rx_pending &&
+	    ring->tx_pending == tx_pending)
+		return 0;
+
+	if (ring->rx_pending > vi->rq[0].vq->num_max)
+		return -EINVAL;
+
+	if (ring->tx_pending > vi->sq[0].vq->num_max)
+		return -EINVAL;
+
+	for (i = 0; i < vi->max_queue_pairs; i++) {
+		rq = vi->rq + i;
+		sq = vi->sq + i;
+
+		if (ring->tx_pending != tx_pending) {
+			err = virtnet_tx_resize(vi, sq, ring->tx_pending);
+			if (err)
+				return err;
+		}
+
+		if (ring->rx_pending != rx_pending) {
+			err = virtnet_rx_resize(vi, rq, ring->rx_pending);
+			if (err)
+				return err;
+		}
+	}
+
+	return 0;
 }
 
 static bool virtnet_commit_rss_command(struct virtnet_info *vi)
@@ -2618,27 +2746,89 @@ static int virtnet_get_link_ksettings(struct net_device *dev,
 	return 0;
 }
 
+static int virtnet_send_notf_coal_cmds(struct virtnet_info *vi,
+				       struct ethtool_coalesce *ec)
+{
+	struct scatterlist sgs_tx, sgs_rx;
+	struct virtio_net_ctrl_coal_tx coal_tx;
+	struct virtio_net_ctrl_coal_rx coal_rx;
+
+	coal_tx.tx_usecs = cpu_to_le32(ec->tx_coalesce_usecs);
+	coal_tx.tx_max_packets = cpu_to_le32(ec->tx_max_coalesced_frames);
+	sg_init_one(&sgs_tx, &coal_tx, sizeof(coal_tx));
+
+	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL,
+				  VIRTIO_NET_CTRL_NOTF_COAL_TX_SET,
+				  &sgs_tx))
+		return -EINVAL;
+
+	/* Save parameters */
+	vi->tx_usecs = ec->tx_coalesce_usecs;
+	vi->tx_max_packets = ec->tx_max_coalesced_frames;
+
+	coal_rx.rx_usecs = cpu_to_le32(ec->rx_coalesce_usecs);
+	coal_rx.rx_max_packets = cpu_to_le32(ec->rx_max_coalesced_frames);
+	sg_init_one(&sgs_rx, &coal_rx, sizeof(coal_rx));
+
+	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL,
+				  VIRTIO_NET_CTRL_NOTF_COAL_RX_SET,
+				  &sgs_rx))
+		return -EINVAL;
+
+	/* Save parameters */
+	vi->rx_usecs = ec->rx_coalesce_usecs;
+	vi->rx_max_packets = ec->rx_max_coalesced_frames;
+
+	return 0;
+}
+
+static int virtnet_coal_params_supported(struct ethtool_coalesce *ec)
+{
+	/* usecs coalescing is supported only if VIRTIO_NET_F_NOTF_COAL
+	 * feature is negotiated.
+	 */
+	if (ec->rx_coalesce_usecs || ec->tx_coalesce_usecs)
+		return -EOPNOTSUPP;
+
+	if (ec->tx_max_coalesced_frames > 1 ||
+	    ec->rx_max_coalesced_frames != 1)
+		return -EINVAL;
+
+	return 0;
+}
+
 static int virtnet_set_coalesce(struct net_device *dev,
 				struct ethtool_coalesce *ec,
 				struct kernel_ethtool_coalesce *kernel_coal,
 				struct netlink_ext_ack *extack)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
-	int i, napi_weight;
-
-	if (ec->tx_max_coalesced_frames > 1 ||
-	    ec->rx_max_coalesced_frames != 1)
-		return -EINVAL;
+	int ret, i, napi_weight;
+	bool update_napi = false;
 
+	/* Can't change NAPI weight if the link is up */
 	napi_weight = ec->tx_max_coalesced_frames ? NAPI_POLL_WEIGHT : 0;
 	if (napi_weight ^ vi->sq[0].napi.weight) {
 		if (dev->flags & IFF_UP)
 			return -EBUSY;
+		else
+			update_napi = true;
+	}
+
+	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_NOTF_COAL))
+		ret = virtnet_send_notf_coal_cmds(vi, ec);
+	else
+		ret = virtnet_coal_params_supported(ec);
+
+	if (ret)
+		return ret;
+
+	if (update_napi) {
 		for (i = 0; i < vi->max_queue_pairs; i++)
 			vi->sq[i].napi.weight = napi_weight;
 	}
 
-	return 0;
+	return ret;
 }
 
 static int virtnet_get_coalesce(struct net_device *dev,
@@ -2646,16 +2836,19 @@ static int virtnet_get_coalesce(struct net_device *dev,
 				struct kernel_ethtool_coalesce *kernel_coal,
 				struct netlink_ext_ack *extack)
 {
-	struct ethtool_coalesce ec_default = {
-		.cmd = ETHTOOL_GCOALESCE,
-		.rx_max_coalesced_frames = 1,
-	};
 	struct virtnet_info *vi = netdev_priv(dev);
 
-	memcpy(ec, &ec_default, sizeof(ec_default));
+	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_NOTF_COAL)) {
+		ec->rx_coalesce_usecs = vi->rx_usecs;
+		ec->tx_coalesce_usecs = vi->tx_usecs;
+		ec->tx_max_coalesced_frames = vi->tx_max_packets;
+		ec->rx_max_coalesced_frames = vi->rx_max_packets;
+	} else {
+		ec->rx_max_coalesced_frames = 1;
 
-	if (vi->sq[0].napi.weight)
-		ec->tx_max_coalesced_frames = 1;
+		if (vi->sq[0].napi.weight)
+			ec->tx_max_coalesced_frames = 1;
+	}
 
 	return 0;
 }
@@ -2774,10 +2967,12 @@ static int virtnet_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info)
 }
 
 static const struct ethtool_ops virtnet_ethtool_ops = {
-	.supported_coalesce_params = ETHTOOL_COALESCE_MAX_FRAMES,
+	.supported_coalesce_params = ETHTOOL_COALESCE_MAX_FRAMES |
+		ETHTOOL_COALESCE_USECS,
 	.get_drvinfo = virtnet_get_drvinfo,
 	.get_link = ethtool_op_get_link,
 	.get_ringparam = virtnet_get_ringparam,
+	.set_ringparam = virtnet_set_ringparam,
 	.get_strings = virtnet_get_strings,
 	.get_sset_count = virtnet_get_sset_count,
 	.get_ethtool_stats = virtnet_get_ethtool_stats,
@@ -3171,6 +3366,27 @@ static void free_receive_page_frags(struct virtnet_info *vi)
 			put_page(vi->rq[i].alloc_frag.page);
 }
 
+static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf)
+{
+	if (!is_xdp_frame(buf))
+		dev_kfree_skb(buf);
+	else
+		xdp_return_frame(ptr_to_xdp(buf));
+}
+
+static void virtnet_rq_free_unused_buf(struct virtqueue *vq, void *buf)
+{
+	struct virtnet_info *vi = vq->vdev->priv;
+	int i = vq2rxq(vq);
+
+	if (vi->mergeable_rx_bufs)
+		put_page(virt_to_head_page(buf));
+	else if (vi->big_packets)
+		give_pages(&vi->rq[i], buf);
+	else
+		put_page(virt_to_head_page(buf));
+}
+
 static void free_unused_bufs(struct virtnet_info *vi)
 {
 	void *buf;
@@ -3178,26 +3394,14 @@ static void free_unused_bufs(struct virtnet_info *vi)
 
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		struct virtqueue *vq = vi->sq[i].vq;
-		while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) {
-			if (!is_xdp_frame(buf))
-				dev_kfree_skb(buf);
-			else
-				xdp_return_frame(ptr_to_xdp(buf));
-		}
+		while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
+			virtnet_sq_free_unused_buf(vq, buf);
 	}
 
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		struct virtqueue *vq = vi->rq[i].vq;
-
-		while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) {
-			if (vi->mergeable_rx_bufs) {
-				put_page(virt_to_head_page(buf));
-			} else if (vi->big_packets) {
-				give_pages(&vi->rq[i], buf);
-			} else {
-				put_page(virt_to_head_page(buf));
-			}
-		}
+		while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
+			virtnet_rq_free_unused_buf(vq, buf);
 	}
 }
 
@@ -3228,6 +3432,29 @@ static unsigned int mergeable_min_buf_len(struct virtnet_info *vi, struct virtqu
 		   (unsigned int)GOOD_PACKET_LEN);
 }
 
+static void virtnet_config_sizes(struct virtnet_info *vi, u32 *sizes)
+{
+	u32 i, rx_size, tx_size;
+
+	if (vi->speed == SPEED_UNKNOWN || vi->speed < SPEED_10000) {
+		rx_size = 1024;
+		tx_size = 1024;
+
+	} else if (vi->speed < SPEED_40000) {
+		rx_size = 1024 * 4;
+		tx_size = 1024 * 4;
+
+	} else {
+		rx_size = 1024 * 8;
+		tx_size = 1024 * 8;
+	}
+
+	for (i = 0; i < vi->max_queue_pairs; i++) {
+		sizes[rxq2vq(i)] = rx_size;
+		sizes[txq2vq(i)] = tx_size;
+	}
+}
+
 static int virtnet_find_vqs(struct virtnet_info *vi)
 {
 	vq_callback_t **callbacks;
@@ -3235,6 +3462,7 @@ static int virtnet_find_vqs(struct virtnet_info *vi)
 	int ret = -ENOMEM;
 	int i, total_vqs;
 	const char **names;
+	u32 *sizes;
 	bool *ctx;
 
 	/* We expect 1 RX virtqueue followed by 1 TX virtqueue, followed by
@@ -3262,10 +3490,15 @@ static int virtnet_find_vqs(struct virtnet_info *vi)
 		ctx = NULL;
 	}
 
+	sizes = kmalloc_array(total_vqs, sizeof(*sizes), GFP_KERNEL);
+	if (!sizes)
+		goto err_sizes;
+
 	/* Parameters for control virtqueue, if any */
 	if (vi->has_cvq) {
 		callbacks[total_vqs - 1] = NULL;
 		names[total_vqs - 1] = "control";
+		sizes[total_vqs - 1] = 64;
 	}
 
 	/* Allocate/initialize parameters for send/receive virtqueues */
@@ -3280,8 +3513,10 @@ static int virtnet_find_vqs(struct virtnet_info *vi)
 			ctx[rxq2vq(i)] = true;
 	}
 
-	ret = virtio_find_vqs_ctx(vi->vdev, total_vqs, vqs, callbacks,
-				  names, ctx, NULL);
+	virtnet_config_sizes(vi, sizes);
+
+	ret = virtio_find_vqs_ctx_size(vi->vdev, total_vqs, vqs, callbacks,
+				       names, sizes, ctx, NULL);
 	if (ret)
 		goto err_find;
 
@@ -3301,6 +3536,8 @@ static int virtnet_find_vqs(struct virtnet_info *vi)
 
 
 err_find:
+	kfree(sizes);
+err_sizes:
 	kfree(ctx);
 err_ctx:
 	kfree(names);
@@ -3444,6 +3681,8 @@ static bool virtnet_validate_features(struct virtio_device *vdev)
 	     VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_RSS,
 			     "VIRTIO_NET_F_CTRL_VQ") ||
 	     VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_HASH_REPORT,
+			     "VIRTIO_NET_F_CTRL_VQ") ||
+	     VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_NOTF_COAL,
 			     "VIRTIO_NET_F_CTRL_VQ"))) {
 		return false;
 	}
@@ -3580,6 +3819,13 @@ static int virtnet_probe(struct virtio_device *vdev)
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF))
 		vi->mergeable_rx_bufs = true;
 
+	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_NOTF_COAL)) {
+		vi->rx_usecs = 0;
+		vi->tx_usecs = 0;
+		vi->tx_max_packets = 0;
+		vi->rx_max_packets = 0;
+	}
+
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_HASH_REPORT))
 		vi->has_rss_hash_report = true;
 
@@ -3651,6 +3897,9 @@ static int virtnet_probe(struct virtio_device *vdev)
 		vi->curr_queue_pairs = num_online_cpus();
 	vi->max_queue_pairs = max_queue_pairs;
 
+	virtnet_init_settings(dev);
+	virtnet_update_settings(vi);
+
 	/* Allocate/initialize the rx/tx queues, and invoke find_vqs */
 	err = init_vqs(vi);
 	if (err)
@@ -3663,8 +3912,6 @@ static int virtnet_probe(struct virtio_device *vdev)
 	netif_set_real_num_tx_queues(dev, vi->curr_queue_pairs);
 	netif_set_real_num_rx_queues(dev, vi->curr_queue_pairs);
 
-	virtnet_init_settings(dev);
-
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_STANDBY)) {
 		vi->failover = net_failover_create(vi->dev);
 		if (IS_ERR(vi->failover)) {
@@ -3814,7 +4061,7 @@ static struct virtio_device_id id_table[] = {
 	VIRTIO_NET_F_CTRL_MAC_ADDR, \
 	VIRTIO_NET_F_MTU, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS, \
 	VIRTIO_NET_F_SPEED_DUPLEX, VIRTIO_NET_F_STANDBY, \
-	VIRTIO_NET_F_RSS, VIRTIO_NET_F_HASH_REPORT
+	VIRTIO_NET_F_RSS, VIRTIO_NET_F_HASH_REPORT, VIRTIO_NET_F_NOTF_COAL
 
 static unsigned int features[] = {
 	VIRTNET_FEATURES,