1 files changed, 129 insertions, 56 deletions

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index ec14bf2a9a..290bec2926 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -80,6 +80,11 @@ struct virtnet_stat_desc {
 	size_t offset;
 };
 
+struct virtnet_sq_free_stats {
+	u64 packets;
+	u64 bytes;
+};
+
 struct virtnet_sq_stats {
 	struct u64_stats_sync syncp;
 	u64_stats_t packets;
@@ -304,6 +309,12 @@ struct virtnet_info {
 	/* Work struct for config space updates */
 	struct work_struct config_work;
 
+	/* Work struct for setting rx mode */
+	struct work_struct rx_mode_work;
+
+	/* OK to queue work setting RX mode? */
+	bool rx_mode_work_enabled;
+
 	/* Does the affinity hint is set for virtqueues? */
 	bool affinity_hint_set;
 
@@ -366,6 +377,31 @@ static struct xdp_frame *ptr_to_xdp(void *ptr)
 	return (struct xdp_frame *)((unsigned long)ptr & ~VIRTIO_XDP_FLAG);
 }
 
+static void __free_old_xmit(struct send_queue *sq, bool in_napi,
+			    struct virtnet_sq_free_stats *stats)
+{
+	unsigned int len;
+	void *ptr;
+
+	while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) {
+		++stats->packets;
+
+		if (!is_xdp_frame(ptr)) {
+			struct sk_buff *skb = ptr;
+
+			pr_debug("Sent skb %p\n", skb);
+
+			stats->bytes += skb->len;
+			napi_consume_skb(skb, in_napi);
+		} else {
+			struct xdp_frame *frame = ptr_to_xdp(ptr);
+
+			stats->bytes += xdp_get_frame_len(frame);
+			xdp_return_frame(frame);
+		}
+	}
+}
+
 /* Converting between virtqueue no. and kernel tx/rx queue no.
  * 0:rx0 1:tx0 2:rx1 3:tx1 ... 2N:rxN 2N+1:txN 2N+2:cvq
  */
@@ -447,6 +483,20 @@ static void disable_delayed_refill(struct virtnet_info *vi)
 	spin_unlock_bh(&vi->refill_lock);
 }
 
+static void enable_rx_mode_work(struct virtnet_info *vi)
+{
+	rtnl_lock();
+	vi->rx_mode_work_enabled = true;
+	rtnl_unlock();
+}
+
+static void disable_rx_mode_work(struct virtnet_info *vi)
+{
+	rtnl_lock();
+	vi->rx_mode_work_enabled = false;
+	rtnl_unlock();
+}
+
 static void virtqueue_napi_schedule(struct napi_struct *napi,
 				    struct virtqueue *vq)
 {
@@ -776,39 +826,21 @@ static void virtnet_rq_unmap_free_buf(struct virtqueue *vq, void *buf)
 	virtnet_rq_free_buf(vi, rq, buf);
 }
 
-static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi)
+static void free_old_xmit(struct send_queue *sq, bool in_napi)
 {
-	unsigned int len;
-	unsigned int packets = 0;
-	unsigned int bytes = 0;
-	void *ptr;
-
-	while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) {
-		if (likely(!is_xdp_frame(ptr))) {
-			struct sk_buff *skb = ptr;
+	struct virtnet_sq_free_stats stats = {0};
 
-			pr_debug("Sent skb %p\n", skb);
-
-			bytes += skb->len;
-			napi_consume_skb(skb, in_napi);
-		} else {
-			struct xdp_frame *frame = ptr_to_xdp(ptr);
-
-			bytes += xdp_get_frame_len(frame);
-			xdp_return_frame(frame);
-		}
-		packets++;
-	}
+	__free_old_xmit(sq, in_napi, &stats);
 
 	/* Avoid overhead when no packets have been processed
 	 * happens when called speculatively from start_xmit.
 	 */
-	if (!packets)
+	if (!stats.packets)
 		return;
 
 	u64_stats_update_begin(&sq->stats.syncp);
-	u64_stats_add(&sq->stats.bytes, bytes);
-	u64_stats_add(&sq->stats.packets, packets);
+	u64_stats_add(&sq->stats.bytes, stats.bytes);
+	u64_stats_add(&sq->stats.packets, stats.packets);
 	u64_stats_update_end(&sq->stats.syncp);
 }
 
@@ -848,7 +880,7 @@ static void check_sq_full_and_disable(struct virtnet_info *vi,
 				virtqueue_napi_schedule(&sq->napi, sq->vq);
 		} else if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) {
 			/* More just got used, free them then recheck. */
-			free_old_xmit_skbs(sq, false);
+			free_old_xmit(sq, false);
 			if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) {
 				netif_start_subqueue(dev, qnum);
 				virtqueue_disable_cb(sq->vq);
@@ -947,15 +979,12 @@ static int virtnet_xdp_xmit(struct net_device *dev,
 			    int n, struct xdp_frame **frames, u32 flags)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
+	struct virtnet_sq_free_stats stats = {0};
 	struct receive_queue *rq = vi->rq;
 	struct bpf_prog *xdp_prog;
 	struct send_queue *sq;
-	unsigned int len;
-	int packets = 0;
-	int bytes = 0;
 	int nxmit = 0;
 	int kicks = 0;
-	void *ptr;
 	int ret;
 	int i;
 
@@ -974,20 +1003,7 @@ static int virtnet_xdp_xmit(struct net_device *dev,
 	}
 
 	/* Free up any pending old buffers before queueing new ones. */
-	while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) {
-		if (likely(is_xdp_frame(ptr))) {
-			struct xdp_frame *frame = ptr_to_xdp(ptr);
-
-			bytes += xdp_get_frame_len(frame);
-			xdp_return_frame(frame);
-		} else {
-			struct sk_buff *skb = ptr;
-
-			bytes += skb->len;
-			napi_consume_skb(skb, false);
-		}
-		packets++;
-	}
+	__free_old_xmit(sq, false, &stats);
 
 	for (i = 0; i < n; i++) {
 		struct xdp_frame *xdpf = frames[i];
@@ -1007,8 +1023,8 @@ static int virtnet_xdp_xmit(struct net_device *dev,
 	}
 out:
 	u64_stats_update_begin(&sq->stats.syncp);
-	u64_stats_add(&sq->stats.bytes, bytes);
-	u64_stats_add(&sq->stats.packets, packets);
+	u64_stats_add(&sq->stats.bytes, stats.bytes);
+	u64_stats_add(&sq->stats.packets, stats.packets);
 	u64_stats_add(&sq->stats.xdp_tx, n);
 	u64_stats_add(&sq->stats.xdp_tx_drops, n - nxmit);
 	u64_stats_add(&sq->stats.kicks, kicks);
@@ -1209,6 +1225,10 @@ static struct sk_buff *receive_small_xdp(struct net_device *dev,
 	if (unlikely(hdr->hdr.gso_type))
 		goto err_xdp;
 
+	/* Partially checksummed packets must be dropped. */
+	if (unlikely(hdr->hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM))
+		goto err_xdp;
+
 	buflen = SKB_DATA_ALIGN(GOOD_PACKET_LEN + headroom) +
 		SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
@@ -1526,6 +1546,10 @@ static void *mergeable_xdp_get_buf(struct virtnet_info *vi,
 	if (unlikely(hdr->hdr.gso_type))
 		return NULL;
 
+	/* Partially checksummed packets must be dropped. */
+	if (unlikely(hdr->hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM))
+		return NULL;
+
 	/* Now XDP core assumes frag size is PAGE_SIZE, but buffers
 	 * with headroom may add hole in truesize, which
 	 * make their length exceed PAGE_SIZE. So we disabled the
@@ -1792,6 +1816,7 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
 	struct net_device *dev = vi->dev;
 	struct sk_buff *skb;
 	struct virtio_net_common_hdr *hdr;
+	u8 flags;
 
 	if (unlikely(len < vi->hdr_len + ETH_HLEN)) {
 		pr_debug("%s: short packet %i\n", dev->name, len);
@@ -1800,6 +1825,15 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
 		return;
 	}
 
+	/* 1. Save the flags early, as the XDP program might overwrite them.
+	 * These flags ensure packets marked as VIRTIO_NET_HDR_F_DATA_VALID
+	 * stay valid after XDP processing.
+	 * 2. XDP doesn't work with partially checksummed packets (refer to
+	 * virtnet_xdp_set()), so packets marked as
+	 * VIRTIO_NET_HDR_F_NEEDS_CSUM get dropped during XDP processing.
+	 */
+	flags = ((struct virtio_net_common_hdr *)buf)->hdr.flags;
+
 	if (vi->mergeable_rx_bufs)
 		skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit,
 					stats);
@@ -1815,7 +1849,7 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
 	if (dev->features & NETIF_F_RXHASH && vi->has_rss_hash_report)
 		virtio_skb_set_hash(&hdr->hash_v1_hdr, skb);
 
-	if (hdr->hdr.flags & VIRTIO_NET_HDR_F_DATA_VALID)
+	if (flags & VIRTIO_NET_HDR_F_DATA_VALID)
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
 
 	if (virtio_net_hdr_to_skb(skb, &hdr->hdr,
@@ -2160,7 +2194,7 @@ static void virtnet_poll_cleantx(struct receive_queue *rq)
 
 		do {
 			virtqueue_disable_cb(sq->vq);
-			free_old_xmit_skbs(sq, true);
+			free_old_xmit(sq, true);
 		} while (unlikely(!virtqueue_enable_cb_delayed(sq->vq)));
 
 		if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS)
@@ -2308,7 +2342,7 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget)
 	txq = netdev_get_tx_queue(vi->dev, index);
 	__netif_tx_lock(txq, raw_smp_processor_id());
 	virtqueue_disable_cb(sq->vq);
-	free_old_xmit_skbs(sq, true);
+	free_old_xmit(sq, true);
 
 	if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS)
 		netif_tx_wake_queue(txq);
@@ -2398,7 +2432,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 		if (use_napi)
 			virtqueue_disable_cb(sq->vq);
 
-		free_old_xmit_skbs(sq, false);
+		free_old_xmit(sq, false);
 
 	} while (use_napi && kick &&
 	       unlikely(!virtqueue_enable_cb_delayed(sq->vq)));
@@ -2550,8 +2584,10 @@ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd,
 	 * into the hypervisor, so the request should be handled immediately.
 	 */
 	while (!virtqueue_get_buf(vi->cvq, &tmp) &&
-	       !virtqueue_is_broken(vi->cvq))
+	       !virtqueue_is_broken(vi->cvq)) {
+		cond_resched();
 		cpu_relax();
+	}
 
 	return vi->ctrl->status == VIRTIO_NET_OK;
 }
@@ -2706,9 +2742,11 @@ static int virtnet_close(struct net_device *dev)
 	return 0;
 }
 
-static void virtnet_set_rx_mode(struct net_device *dev)
+static void virtnet_rx_mode_work(struct work_struct *work)
 {
-	struct virtnet_info *vi = netdev_priv(dev);
+	struct virtnet_info *vi =
+		container_of(work, struct virtnet_info, rx_mode_work);
+	struct net_device *dev = vi->dev;
 	struct scatterlist sg[2];
 	struct virtio_net_ctrl_mac *mac_data;
 	struct netdev_hw_addr *ha;
@@ -2721,6 +2759,8 @@ static void virtnet_set_rx_mode(struct net_device *dev)
 	if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_RX))
 		return;
 
+	rtnl_lock();
+
 	vi->ctrl->promisc = ((dev->flags & IFF_PROMISC) != 0);
 	vi->ctrl->allmulti = ((dev->flags & IFF_ALLMULTI) != 0);
 
@@ -2738,14 +2778,19 @@ static void virtnet_set_rx_mode(struct net_device *dev)
 		dev_warn(&dev->dev, "Failed to %sable allmulti mode.\n",
 			 vi->ctrl->allmulti ? "en" : "dis");
 
+	netif_addr_lock_bh(dev);
+
 	uc_count = netdev_uc_count(dev);
 	mc_count = netdev_mc_count(dev);
 	/* MAC filter - use one buffer for both lists */
 	buf = kzalloc(((uc_count + mc_count) * ETH_ALEN) +
 		      (2 * sizeof(mac_data->entries)), GFP_ATOMIC);
 	mac_data = buf;
-	if (!buf)
+	if (!buf) {
+		netif_addr_unlock_bh(dev);
+		rtnl_unlock();
 		return;
+	}
 
 	sg_init_table(sg, 2);
 
@@ -2766,6 +2811,8 @@ static void virtnet_set_rx_mode(struct net_device *dev)
 	netdev_for_each_mc_addr(ha, dev)
 		memcpy(&mac_data->macs[i++][0], ha->addr, ETH_ALEN);
 
+	netif_addr_unlock_bh(dev);
+
 	sg_set_buf(&sg[1], mac_data,
 		   sizeof(mac_data->entries) + (mc_count * ETH_ALEN));
 
@@ -2773,9 +2820,19 @@ static void virtnet_set_rx_mode(struct net_device *dev)
 				  VIRTIO_NET_CTRL_MAC_TABLE_SET, sg))
 		dev_warn(&dev->dev, "Failed to set MAC filter table.\n");
 
+	rtnl_unlock();
+
 	kfree(buf);
 }
 
+static void virtnet_set_rx_mode(struct net_device *dev)
+{
+	struct virtnet_info *vi = netdev_priv(dev);
+
+	if (vi->rx_mode_work_enabled)
+		schedule_work(&vi->rx_mode_work);
+}
+
 static int virtnet_vlan_rx_add_vid(struct net_device *dev,
 				   __be16 proto, u16 vid)
 {
@@ -3550,10 +3607,10 @@ static void virtnet_rx_dim_work(struct work_struct *work)
 			if (err)
 				pr_debug("%s: Failed to send dim parameters on rxq%d\n",
 					 dev->name, qnum);
-			dim->state = DIM_START_MEASURE;
 		}
 	}
 
+	dim->state = DIM_START_MEASURE;
 	rtnl_unlock();
 }
 
@@ -3872,6 +3929,8 @@ static void virtnet_freeze_down(struct virtio_device *vdev)
 
 	/* Make sure no work handler is accessing the device */
 	flush_work(&vi->config_work);
+	disable_rx_mode_work(vi);
+	flush_work(&vi->rx_mode_work);
 
 	netif_tx_lock_bh(vi->dev);
 	netif_device_detach(vi->dev);
@@ -3894,6 +3953,7 @@ static int virtnet_restore_up(struct virtio_device *vdev)
 	virtio_device_ready(vdev);
 
 	enable_delayed_refill(vi);
+	enable_rx_mode_work(vi);
 
 	if (netif_running(vi->dev)) {
 		err = virtnet_open(vi->dev);
@@ -4656,8 +4716,16 @@ static int virtnet_probe(struct virtio_device *vdev)
 			dev->features |= dev->hw_features & NETIF_F_ALL_TSO;
 		/* (!csum && gso) case will be fixed by register_netdev() */
 	}
-	if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_CSUM))
-		dev->features |= NETIF_F_RXCSUM;
+
+	/* 1. With VIRTIO_NET_F_GUEST_CSUM negotiation, the driver doesn't
+	 * need to calculate checksums for partially checksummed packets,
+	 * as they're considered valid by the upper layer.
+	 * 2. Without VIRTIO_NET_F_GUEST_CSUM negotiation, the driver only
+	 * receives fully checksummed packets. The device may assist in
+	 * validating these packets' checksums, so the driver won't have to.
+	 */
+	dev->features |= NETIF_F_RXCSUM;
+
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) ||
 	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO6))
 		dev->features |= NETIF_F_GRO_HW;
@@ -4692,6 +4760,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 	vdev->priv = vi;
 
 	INIT_WORK(&vi->config_work, virtnet_config_changed_work);
+	INIT_WORK(&vi->rx_mode_work, virtnet_rx_mode_work);
 	spin_lock_init(&vi->refill_lock);
 
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF)) {
@@ -4816,6 +4885,8 @@ static int virtnet_probe(struct virtio_device *vdev)
 	if (vi->has_rss || vi->has_rss_hash_report)
 		virtnet_init_default_rss(vi);
 
+	enable_rx_mode_work(vi);
+
 	/* serialize netdev register + virtio_device_ready() with ndo_open() */
 	rtnl_lock();
 
@@ -4913,6 +4984,8 @@ static void virtnet_remove(struct virtio_device *vdev)
 
 	/* Make sure no work handler is accessing the device. */
 	flush_work(&vi->config_work);
+	disable_rx_mode_work(vi);
+	flush_work(&vi->rx_mode_work);
 
 	unregister_netdev(vi->dev);