1 files changed, 136 insertions, 36 deletions

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 61a57d134544..0b4747e81464 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -47,7 +47,8 @@ module_param(napi_tx, bool, 0644);
 #define VIRTIO_XDP_TX		BIT(0)
 #define VIRTIO_XDP_REDIR	BIT(1)
 
-#define VIRTIO_XDP_FLAG	BIT(0)
+#define VIRTIO_XDP_FLAG		BIT(0)
+#define VIRTIO_ORPHAN_FLAG	BIT(1)
 
 /* RX packet size EWMA. The average packet size is used to determine the packet
  * buffer size when refilling RX rings. As the entire RX ring may be refilled
@@ -85,6 +86,8 @@ struct virtnet_stat_desc {
 struct virtnet_sq_free_stats {
 	u64 packets;
 	u64 bytes;
+	u64 napi_packets;
+	u64 napi_bytes;
 };
 
 struct virtnet_sq_stats {
@@ -506,29 +509,50 @@ 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)
+static bool is_orphan_skb(void *ptr)
+{
+	return (unsigned long)ptr & VIRTIO_ORPHAN_FLAG;
+}
+
+static void *skb_to_ptr(struct sk_buff *skb, bool orphan)
+{
+	return (void *)((unsigned long)skb | (orphan ? VIRTIO_ORPHAN_FLAG : 0));
+}
+
+static struct sk_buff *ptr_to_skb(void *ptr)
+{
+	return (struct sk_buff *)((unsigned long)ptr & ~VIRTIO_ORPHAN_FLAG);
+}
+
+static void __free_old_xmit(struct send_queue *sq, struct netdev_queue *txq,
+			    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;
+			struct sk_buff *skb = ptr_to_skb(ptr);
 
 			pr_debug("Sent skb %p\n", skb);
 
-			stats->bytes += skb->len;
+			if (is_orphan_skb(ptr)) {
+				stats->packets++;
+				stats->bytes += skb->len;
+			} else {
+				stats->napi_packets++;
+				stats->napi_bytes += skb->len;
+			}
 			napi_consume_skb(skb, in_napi);
 		} else {
 			struct xdp_frame *frame = ptr_to_xdp(ptr);
 
+			stats->packets++;
 			stats->bytes += xdp_get_frame_len(frame);
 			xdp_return_frame(frame);
 		}
 	}
+	netdev_tx_completed_queue(txq, stats->napi_packets, stats->napi_bytes);
 }
 
 /* Converting between virtqueue no. and kernel tx/rx queue no.
@@ -955,21 +979,22 @@ static void virtnet_rq_unmap_free_buf(struct virtqueue *vq, void *buf)
 	virtnet_rq_free_buf(vi, rq, buf);
 }
 
-static void free_old_xmit(struct send_queue *sq, bool in_napi)
+static void free_old_xmit(struct send_queue *sq, struct netdev_queue *txq,
+			  bool in_napi)
 {
 	struct virtnet_sq_free_stats stats = {0};
 
-	__free_old_xmit(sq, in_napi, &stats);
+	__free_old_xmit(sq, txq, in_napi, &stats);
 
 	/* Avoid overhead when no packets have been processed
 	 * happens when called speculatively from start_xmit.
 	 */
-	if (!stats.packets)
+	if (!stats.packets && !stats.napi_packets)
 		return;
 
 	u64_stats_update_begin(&sq->stats.syncp);
-	u64_stats_add(&sq->stats.bytes, stats.bytes);
-	u64_stats_add(&sq->stats.packets, stats.packets);
+	u64_stats_add(&sq->stats.bytes, stats.bytes + stats.napi_bytes);
+	u64_stats_add(&sq->stats.packets, stats.packets + stats.napi_packets);
 	u64_stats_update_end(&sq->stats.syncp);
 }
 
@@ -1003,7 +1028,9 @@ static void check_sq_full_and_disable(struct virtnet_info *vi,
 	 * early means 16 slots are typically wasted.
 	 */
 	if (sq->vq->num_free < 2+MAX_SKB_FRAGS) {
-		netif_stop_subqueue(dev, qnum);
+		struct netdev_queue *txq = netdev_get_tx_queue(dev, qnum);
+
+		netif_tx_stop_queue(txq);
 		u64_stats_update_begin(&sq->stats.syncp);
 		u64_stats_inc(&sq->stats.stop);
 		u64_stats_update_end(&sq->stats.syncp);
@@ -1012,7 +1039,7 @@ 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(sq, false);
+			free_old_xmit(sq, txq, false);
 			if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) {
 				netif_start_subqueue(dev, qnum);
 				u64_stats_update_begin(&sq->stats.syncp);
@@ -1138,7 +1165,8 @@ static int virtnet_xdp_xmit(struct net_device *dev,
 	}
 
 	/* Free up any pending old buffers before queueing new ones. */
-	__free_old_xmit(sq, false, &stats);
+	__free_old_xmit(sq, netdev_get_tx_queue(dev, sq - vi->sq),
+			false, &stats);
 
 	for (i = 0; i < n; i++) {
 		struct xdp_frame *xdpf = frames[i];
@@ -1360,6 +1388,10 @@ 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));
 
@@ -1677,6 +1709,10 @@ 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
@@ -1943,6 +1979,7 @@ 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);
@@ -1951,6 +1988,15 @@ 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);
@@ -1966,7 +2012,7 @@ 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,
@@ -2313,7 +2359,7 @@ static void virtnet_poll_cleantx(struct receive_queue *rq)
 
 		do {
 			virtqueue_disable_cb(sq->vq);
-			free_old_xmit(sq, true);
+			free_old_xmit(sq, txq, true);
 		} while (unlikely(!virtqueue_enable_cb_delayed(sq->vq)));
 
 		if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS) {
@@ -2336,12 +2382,13 @@ static void virtnet_rx_dim_update(struct virtnet_info *vi, struct receive_queue
 	if (!rq->packets_in_napi)
 		return;
 
-	u64_stats_update_begin(&rq->stats.syncp);
+	/* Don't need protection when fetching stats, since fetcher and
+	 * updater of the stats are in same context
+	 */
 	dim_update_sample(rq->calls,
 			  u64_stats_read(&rq->stats.packets),
 			  u64_stats_read(&rq->stats.bytes),
 			  &cur_sample);
-	u64_stats_update_end(&rq->stats.syncp);
 
 	net_dim(&rq->dim, cur_sample);
 	rq->packets_in_napi = 0;
@@ -2412,6 +2459,7 @@ static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index)
 		goto err_xdp_reg_mem_model;
 
 	virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi);
+	netdev_tx_reset_queue(netdev_get_tx_queue(vi->dev, qp_index));
 	virtnet_napi_tx_enable(vi, vi->sq[qp_index].vq, &vi->sq[qp_index].napi);
 
 	return 0;
@@ -2421,6 +2469,13 @@ err_xdp_reg_mem_model:
 	return err;
 }
 
+static void virtnet_cancel_dim(struct virtnet_info *vi, struct dim *dim)
+{
+	if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL))
+		return;
+	net_dim_work_cancel(dim);
+}
+
 static int virtnet_open(struct net_device *dev)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
@@ -2447,7 +2502,7 @@ err_enable_qp:
 
 	for (i--; i >= 0; i--) {
 		virtnet_disable_queue_pair(vi, i);
-		cancel_work_sync(&vi->rq[i].dim.work);
+		virtnet_cancel_dim(vi, &vi->rq[i].dim);
 	}
 
 	return err;
@@ -2471,7 +2526,7 @@ 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(sq, true);
+	free_old_xmit(sq, txq, true);
 
 	if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS) {
 		if (netif_tx_queue_stopped(txq)) {
@@ -2505,7 +2560,7 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget)
 	return 0;
 }
 
-static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
+static int xmit_skb(struct send_queue *sq, struct sk_buff *skb, bool orphan)
 {
 	struct virtio_net_hdr_mrg_rxbuf *hdr;
 	const unsigned char *dest = ((struct ethhdr *)skb->data)->h_dest;
@@ -2549,7 +2604,8 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
 			return num_sg;
 		num_sg++;
 	}
-	return virtqueue_add_outbuf(sq->vq, sq->sg, num_sg, skb, GFP_ATOMIC);
+	return virtqueue_add_outbuf(sq->vq, sq->sg, num_sg,
+				    skb_to_ptr(skb, orphan), GFP_ATOMIC);
 }
 
 static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
@@ -2559,24 +2615,25 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct send_queue *sq = &vi->sq[qnum];
 	int err;
 	struct netdev_queue *txq = netdev_get_tx_queue(dev, qnum);
-	bool kick = !netdev_xmit_more();
+	bool xmit_more = netdev_xmit_more();
 	bool use_napi = sq->napi.weight;
+	bool kick;
 
 	/* Free up any pending old buffers before queueing new ones. */
 	do {
 		if (use_napi)
 			virtqueue_disable_cb(sq->vq);
 
-		free_old_xmit(sq, false);
+		free_old_xmit(sq, txq, false);
 
-	} while (use_napi && kick &&
+	} while (use_napi && !xmit_more &&
 	       unlikely(!virtqueue_enable_cb_delayed(sq->vq)));
 
 	/* timestamp packet in software */
 	skb_tx_timestamp(skb);
 
 	/* Try to transmit */
-	err = xmit_skb(sq, skb);
+	err = xmit_skb(sq, skb, !use_napi);
 
 	/* This should not happen! */
 	if (unlikely(err)) {
@@ -2598,7 +2655,9 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	check_sq_full_and_disable(vi, dev, sq);
 
-	if (kick || netif_xmit_stopped(txq)) {
+	kick = use_napi ? __netdev_tx_sent_queue(txq, skb->len, xmit_more) :
+			  !xmit_more || netif_xmit_stopped(txq);
+	if (kick) {
 		if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) {
 			u64_stats_update_begin(&sq->stats.syncp);
 			u64_stats_inc(&sq->stats.kicks);
@@ -2619,7 +2678,7 @@ static int virtnet_rx_resize(struct virtnet_info *vi,
 
 	if (running) {
 		napi_disable(&rq->napi);
-		cancel_work_sync(&rq->dim.work);
+		virtnet_cancel_dim(vi, &rq->dim);
 	}
 
 	err = virtqueue_resize(rq->vq, ring_num, virtnet_rq_unmap_free_buf);
@@ -2880,7 +2939,7 @@ static int virtnet_close(struct net_device *dev)
 
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		virtnet_disable_queue_pair(vi, i);
-		cancel_work_sync(&vi->rq[i].dim.work);
+		virtnet_cancel_dim(vi, &vi->rq[i].dim);
 	}
 
 	return 0;
@@ -4406,7 +4465,7 @@ static void virtnet_rx_dim_work(struct work_struct *work)
 	if (!rq->dim_enabled)
 		goto out;
 
-	update_moder = net_dim_get_rx_moderation(dim->mode, dim->profile_ix);
+	update_moder = net_dim_get_rx_irq_moder(dev, dim);
 	if (update_moder.usec != rq->intr_coal.max_usecs ||
 	    update_moder.pkts != rq->intr_coal.max_packets) {
 		err = virtnet_send_rx_ctrl_coal_vq_cmd(vi, qnum,
@@ -5106,6 +5165,36 @@ static void virtnet_tx_timeout(struct net_device *dev, unsigned int txqueue)
 		   jiffies_to_usecs(jiffies - READ_ONCE(txq->trans_start)));
 }
 
+static int virtnet_init_irq_moder(struct virtnet_info *vi)
+{
+	u8 profile_flags = 0, coal_flags = 0;
+	int ret, i;
+
+	profile_flags |= DIM_PROFILE_RX;
+	coal_flags |= DIM_COALESCE_USEC | DIM_COALESCE_PKTS;
+	ret = net_dim_init_irq_moder(vi->dev, profile_flags, coal_flags,
+				     DIM_CQ_PERIOD_MODE_START_FROM_EQE,
+				     0, virtnet_rx_dim_work, NULL);
+
+	if (ret)
+		return ret;
+
+	for (i = 0; i < vi->max_queue_pairs; i++)
+		net_dim_setting(vi->dev, &vi->rq[i].dim, false);
+
+	return 0;
+}
+
+static void virtnet_free_irq_moder(struct virtnet_info *vi)
+{
+	if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL))
+		return;
+
+	rtnl_lock();
+	net_dim_free_irq_moder(vi->dev);
+	rtnl_unlock();
+}
+
 static const struct net_device_ops virtnet_netdev = {
 	.ndo_open            = virtnet_open,
 	.ndo_stop   	     = virtnet_close,
@@ -5385,9 +5474,6 @@ static int virtnet_alloc_queues(struct virtnet_info *vi)
 					 virtnet_poll_tx,
 					 napi_tx ? napi_weight : 0);
 
-		INIT_WORK(&vi->rq[i].dim.work, virtnet_rx_dim_work);
-		vi->rq[i].dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
-
 		sg_init_table(vi->rq[i].sg, ARRAY_SIZE(vi->rq[i].sg));
 		ewma_pkt_len_init(&vi->rq[i].mrg_avg_pkt_len);
 		sg_init_table(vi->sq[i].sg, ARRAY_SIZE(vi->sq[i].sg));
@@ -5666,8 +5752,16 @@ 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;
@@ -5808,6 +5902,10 @@ static int virtnet_probe(struct virtio_device *vdev)
 		for (i = 0; i < vi->max_queue_pairs; i++)
 			if (vi->sq[i].napi.weight)
 				vi->sq[i].intr_coal.max_packets = 1;
+
+		err = virtnet_init_irq_moder(vi);
+		if (err)
+			goto free;
 	}
 
 #ifdef CONFIG_SYSFS
@@ -5959,6 +6057,8 @@ static void virtnet_remove(struct virtio_device *vdev)
 	disable_rx_mode_work(vi);
 	flush_work(&vi->rx_mode_work);
 
+	virtnet_free_irq_moder(vi);
+
 	unregister_netdev(vi->dev);
 
 	net_failover_destroy(vi->failover);