1 files changed, 140 insertions, 69 deletions

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 030d30603c29..f4c03518d7d2 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -63,6 +63,11 @@ static const unsigned long guest_offloads[] = {
 	VIRTIO_NET_F_GUEST_CSUM
 };
 
+#define GUEST_OFFLOAD_GRO_HW_MASK ((1ULL << VIRTIO_NET_F_GUEST_TSO4) | \
+				(1ULL << VIRTIO_NET_F_GUEST_TSO6) | \
+				(1ULL << VIRTIO_NET_F_GUEST_ECN)  | \
+				(1ULL << VIRTIO_NET_F_GUEST_UFO))
+
 struct virtnet_stat_desc {
 	char desc[ETH_GSTRING_LEN];
 	size_t offset;
@@ -190,6 +195,9 @@ struct virtnet_info {
 	/* # of XDP queue pairs currently used by the driver */
 	u16 xdp_queue_pairs;
 
+	/* xdp_queue_pairs may be 0, when xdp is already loaded. So add this. */
+	bool xdp_enabled;
+
 	/* I like... big packets and I cannot lie! */
 	bool big_packets;
 
@@ -371,7 +379,7 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 				   struct receive_queue *rq,
 				   struct page *page, unsigned int offset,
 				   unsigned int len, unsigned int truesize,
-				   bool hdr_valid)
+				   bool hdr_valid, unsigned int metasize)
 {
 	struct sk_buff *skb;
 	struct virtio_net_hdr_mrg_rxbuf *hdr;
@@ -393,6 +401,7 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 	else
 		hdr_padded_len = sizeof(struct padded_vnet_hdr);
 
+	/* hdr_valid means no XDP, so we can copy the vnet header */
 	if (hdr_valid)
 		memcpy(hdr, p, hdr_len);
 
@@ -400,11 +409,20 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 	offset += hdr_padded_len;
 	p += hdr_padded_len;
 
-	copy = len;
-	if (copy > skb_tailroom(skb))
-		copy = skb_tailroom(skb);
+	/* Copy all frame if it fits skb->head, otherwise
+	 * we let virtio_net_hdr_to_skb() and GRO pull headers as needed.
+	 */
+	if (len <= skb_tailroom(skb))
+		copy = len;
+	else
+		copy = ETH_HLEN + metasize;
 	skb_put_data(skb, p, copy);
 
+	if (metasize) {
+		__skb_pull(skb, metasize);
+		skb_metadata_set(skb, metasize);
+	}
+
 	len -= copy;
 	offset += copy;
 
@@ -450,10 +468,6 @@ static int __virtnet_xdp_xmit_one(struct virtnet_info *vi,
 	struct virtio_net_hdr_mrg_rxbuf *hdr;
 	int err;
 
-	/* virtqueue want to use data area in-front of packet */
-	if (unlikely(xdpf->metasize > 0))
-		return -EOPNOTSUPP;
-
 	if (unlikely(xdpf->headroom < vi->hdr_len))
 		return -EOVERFLOW;
 
@@ -474,12 +488,41 @@ static int __virtnet_xdp_xmit_one(struct virtnet_info *vi,
 	return 0;
 }
 
-static struct send_queue *virtnet_xdp_sq(struct virtnet_info *vi)
-{
-	unsigned int qp;
-
-	qp = vi->curr_queue_pairs - vi->xdp_queue_pairs + smp_processor_id();
-	return &vi->sq[qp];
+/* when vi->curr_queue_pairs > nr_cpu_ids, the txq/sq is only used for xdp tx on
+ * the current cpu, so it does not need to be locked.
+ *
+ * Here we use marco instead of inline functions because we have to deal with
+ * three issues at the same time: 1. the choice of sq. 2. judge and execute the
+ * lock/unlock of txq 3. make sparse happy. It is difficult for two inline
+ * functions to perfectly solve these three problems at the same time.
+ */
+#define virtnet_xdp_get_sq(vi) ({                                       \
+	struct netdev_queue *txq;                                       \
+	typeof(vi) v = (vi);                                            \
+	unsigned int qp;                                                \
+									\
+	if (v->curr_queue_pairs > nr_cpu_ids) {                         \
+		qp = v->curr_queue_pairs - v->xdp_queue_pairs;          \
+		qp += smp_processor_id();                               \
+		txq = netdev_get_tx_queue(v->dev, qp);                  \
+		__netif_tx_acquire(txq);                                \
+	} else {                                                        \
+		qp = smp_processor_id() % v->curr_queue_pairs;          \
+		txq = netdev_get_tx_queue(v->dev, qp);                  \
+		__netif_tx_lock(txq, raw_smp_processor_id());           \
+	}                                                               \
+	v->sq + qp;                                                     \
+})
+
+#define virtnet_xdp_put_sq(vi, q) {                                     \
+	struct netdev_queue *txq;                                       \
+	typeof(vi) v = (vi);                                            \
+									\
+	txq = netdev_get_tx_queue(v->dev, (q) - v->sq);                 \
+	if (v->curr_queue_pairs > nr_cpu_ids)                           \
+		__netif_tx_release(txq);                                \
+	else                                                            \
+		__netif_tx_unlock(txq);                                 \
 }
 
 static int virtnet_xdp_xmit(struct net_device *dev,
@@ -505,7 +548,7 @@ static int virtnet_xdp_xmit(struct net_device *dev,
 	if (!xdp_prog)
 		return -ENXIO;
 
-	sq = virtnet_xdp_sq(vi);
+	sq = virtnet_xdp_get_sq(vi);
 
 	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) {
 		ret = -EINVAL;
@@ -553,12 +596,13 @@ out:
 	sq->stats.kicks += kicks;
 	u64_stats_update_end(&sq->stats.syncp);
 
+	virtnet_xdp_put_sq(vi, sq);
 	return ret;
 }
 
 static unsigned int virtnet_get_headroom(struct virtnet_info *vi)
 {
-	return vi->xdp_queue_pairs ? VIRTIO_XDP_HEADROOM : 0;
+	return vi->xdp_enabled ? VIRTIO_XDP_HEADROOM : 0;
 }
 
 /* We copy the packet for XDP in the following cases:
@@ -644,6 +688,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 	unsigned int delta = 0;
 	struct page *xdp_page;
 	int err;
+	unsigned int metasize = 0;
 
 	len -= vi->hdr_len;
 	stats->bytes += len;
@@ -683,8 +728,8 @@ static struct sk_buff *receive_small(struct net_device *dev,
 
 		xdp.data_hard_start = buf + VIRTNET_RX_PAD + vi->hdr_len;
 		xdp.data = xdp.data_hard_start + xdp_headroom;
-		xdp_set_data_meta_invalid(&xdp);
 		xdp.data_end = xdp.data + len;
+		xdp.data_meta = xdp.data;
 		xdp.rxq = &rq->xdp_rxq;
 		orig_data = xdp.data;
 		act = bpf_prog_run_xdp(xdp_prog, &xdp);
@@ -695,6 +740,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 			/* Recalculate length in case bpf program changed it */
 			delta = orig_data - xdp.data;
 			len = xdp.data_end - xdp.data;
+			metasize = xdp.data - xdp.data_meta;
 			break;
 		case XDP_TX:
 			stats->xdp_tx++;
@@ -740,6 +786,9 @@ static struct sk_buff *receive_small(struct net_device *dev,
 		memcpy(skb_vnet_hdr(skb), buf, vi->hdr_len);
 	} /* keep zeroed vnet hdr since packet was changed by bpf */
 
+	if (metasize)
+		skb_metadata_set(skb, metasize);
+
 err:
 	return skb;
 
@@ -760,8 +809,8 @@ static struct sk_buff *receive_big(struct net_device *dev,
 				   struct virtnet_rq_stats *stats)
 {
 	struct page *page = buf;
-	struct sk_buff *skb = page_to_skb(vi, rq, page, 0, len,
-					  PAGE_SIZE, true);
+	struct sk_buff *skb =
+		page_to_skb(vi, rq, page, 0, len, PAGE_SIZE, true, 0);
 
 	stats->bytes += len - vi->hdr_len;
 	if (unlikely(!skb))
@@ -793,6 +842,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 	unsigned int truesize;
 	unsigned int headroom = mergeable_ctx_to_headroom(ctx);
 	int err;
+	unsigned int metasize = 0;
 
 	head_skb = NULL;
 	stats->bytes += len - vi->hdr_len;
@@ -839,8 +889,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 		data = page_address(xdp_page) + offset;
 		xdp.data_hard_start = data - VIRTIO_XDP_HEADROOM + vi->hdr_len;
 		xdp.data = data + vi->hdr_len;
-		xdp_set_data_meta_invalid(&xdp);
 		xdp.data_end = xdp.data + (len - vi->hdr_len);
+		xdp.data_meta = xdp.data;
 		xdp.rxq = &rq->xdp_rxq;
 
 		act = bpf_prog_run_xdp(xdp_prog, &xdp);
@@ -848,24 +898,27 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 
 		switch (act) {
 		case XDP_PASS:
+			metasize = xdp.data - xdp.data_meta;
+
 			/* recalculate offset to account for any header
-			 * adjustments. Note other cases do not build an
-			 * skb and avoid using offset
+			 * adjustments and minus the metasize to copy the
+			 * metadata in page_to_skb(). Note other cases do not
+			 * build an skb and avoid using offset
 			 */
-			offset = xdp.data -
-					page_address(xdp_page) - vi->hdr_len;
+			offset = xdp.data - page_address(xdp_page) -
+				 vi->hdr_len - metasize;
 
-			/* recalculate len if xdp.data or xdp.data_end were
-			 * adjusted
+			/* recalculate len if xdp.data, xdp.data_end or
+			 * xdp.data_meta were adjusted
 			 */
-			len = xdp.data_end - xdp.data + vi->hdr_len;
+			len = xdp.data_end - xdp.data + vi->hdr_len + metasize;
 			/* We can only create skb based on xdp_page. */
 			if (unlikely(xdp_page != page)) {
 				rcu_read_unlock();
 				put_page(page);
-				head_skb = page_to_skb(vi, rq, xdp_page,
-						       offset, len,
-						       PAGE_SIZE, false);
+				head_skb = page_to_skb(vi, rq, xdp_page, offset,
+						       len, PAGE_SIZE, false,
+						       metasize);
 				return head_skb;
 			}
 			break;
@@ -921,7 +974,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 		goto err_skb;
 	}
 
-	head_skb = page_to_skb(vi, rq, page, offset, len, truesize, !xdp_prog);
+	head_skb = page_to_skb(vi, rq, page, offset, len, truesize, !xdp_prog,
+			       metasize);
 	curr_skb = head_skb;
 
 	if (unlikely(!curr_skb))
@@ -1437,12 +1491,13 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
 		xdp_do_flush_map();
 
 	if (xdp_xmit & VIRTIO_XDP_TX) {
-		sq = virtnet_xdp_sq(vi);
+		sq = virtnet_xdp_get_sq(vi);
 		if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) {
 			u64_stats_update_begin(&sq->stats.syncp);
 			sq->stats.kicks++;
 			u64_stats_update_end(&sq->stats.syncp);
 		}
+		virtnet_xdp_put_sq(vi, sq);
 	}
 
 	return received;
@@ -1483,6 +1538,8 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget)
 	struct virtnet_info *vi = sq->vq->vdev->priv;
 	unsigned int index = vq2txq(sq->vq);
 	struct netdev_queue *txq;
+	int opaque;
+	bool done;
 
 	if (unlikely(is_xdp_raw_buffer_queue(vi, index))) {
 		/* We don't need to enable cb for XDP */
@@ -1492,10 +1549,28 @@ 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);
+
+	opaque = virtqueue_enable_cb_prepare(sq->vq);
+
+	done = napi_complete_done(napi, 0);
+
+	if (!done)
+		virtqueue_disable_cb(sq->vq);
+
 	__netif_tx_unlock(txq);
 
-	virtqueue_napi_complete(napi, sq->vq, 0);
+	if (done) {
+		if (unlikely(virtqueue_poll(sq->vq, opaque))) {
+			if (napi_schedule_prep(napi)) {
+				__netif_tx_lock(txq, raw_smp_processor_id());
+				virtqueue_disable_cb(sq->vq);
+				__netif_tx_unlock(txq);
+				__napi_schedule(napi);
+			}
+		}
+	}
 
 	if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS)
 		netif_tx_wake_queue(txq);
@@ -1527,7 +1602,7 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
 	if (virtio_net_hdr_from_skb(skb, &hdr->hdr,
 				    virtio_is_little_endian(vi->vdev), false,
 				    0))
-		BUG();
+		return -EPROTO;
 
 	if (vi->mergeable_rx_bufs)
 		hdr->num_buffers = 0;
@@ -2067,14 +2142,16 @@ static int virtnet_set_channels(struct net_device *dev,
 
 	get_online_cpus();
 	err = _virtnet_set_queues(vi, queue_pairs);
-	if (!err) {
-		netif_set_real_num_tx_queues(dev, queue_pairs);
-		netif_set_real_num_rx_queues(dev, queue_pairs);
-
-		virtnet_set_affinity(vi);
+	if (err) {
+		put_online_cpus();
+		goto err;
 	}
+	virtnet_set_affinity(vi);
 	put_online_cpus();
 
+	netif_set_real_num_tx_queues(dev, queue_pairs);
+	netif_set_real_num_rx_queues(dev, queue_pairs);
+ err:
 	return err;
 }
 
@@ -2316,7 +2393,6 @@ static const struct ethtool_ops virtnet_ethtool_ops = {
 static void virtnet_freeze_down(struct virtio_device *vdev)
 {
 	struct virtnet_info *vi = vdev->priv;
-	int i;
 
 	/* Make sure no work handler is accessing the device */
 	flush_work(&vi->config_work);
@@ -2324,14 +2400,8 @@ static void virtnet_freeze_down(struct virtio_device *vdev)
 	netif_tx_lock_bh(vi->dev);
 	netif_device_detach(vi->dev);
 	netif_tx_unlock_bh(vi->dev);
-	cancel_delayed_work_sync(&vi->refill);
-
-	if (netif_running(vi->dev)) {
-		for (i = 0; i < vi->max_queue_pairs; i++) {
-			napi_disable(&vi->rq[i].napi);
-			virtnet_napi_tx_disable(&vi->sq[i].napi);
-		}
-	}
+	if (netif_running(vi->dev))
+		virtnet_close(vi->dev);
 }
 
 static int init_vqs(struct virtnet_info *vi);
@@ -2339,7 +2409,7 @@ static int init_vqs(struct virtnet_info *vi);
 static int virtnet_restore_up(struct virtio_device *vdev)
 {
 	struct virtnet_info *vi = vdev->priv;
-	int err, i;
+	int err;
 
 	err = init_vqs(vi);
 	if (err)
@@ -2348,15 +2418,9 @@ static int virtnet_restore_up(struct virtio_device *vdev)
 	virtio_device_ready(vdev);
 
 	if (netif_running(vi->dev)) {
-		for (i = 0; i < vi->curr_queue_pairs; i++)
-			if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL))
-				schedule_delayed_work(&vi->refill, 0);
-
-		for (i = 0; i < vi->max_queue_pairs; i++) {
-			virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
-			virtnet_napi_tx_enable(vi, vi->sq[i].vq,
-					       &vi->sq[i].napi);
-		}
+		err = virtnet_open(vi->dev);
+		if (err)
+			return err;
 	}
 
 	netif_tx_lock_bh(vi->dev);
@@ -2416,7 +2480,7 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 	        virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_ECN) ||
 		virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_UFO) ||
 		virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_CSUM))) {
-		NL_SET_ERR_MSG_MOD(extack, "Can't set XDP while host is implementing LRO/CSUM, disable LRO/CSUM first");
+		NL_SET_ERR_MSG_MOD(extack, "Can't set XDP while host is implementing GRO_HW/CSUM, disable GRO_HW/CSUM first");
 		return -EOPNOTSUPP;
 	}
 
@@ -2437,10 +2501,9 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 
 	/* XDP requires extra queues for XDP_TX */
 	if (curr_qp + xdp_qp > vi->max_queue_pairs) {
-		NL_SET_ERR_MSG_MOD(extack, "Too few free TX rings available");
-		netdev_warn(dev, "request %i queues but max is %i\n",
+		netdev_warn(dev, "XDP request %i queues but max is %i. XDP_TX and XDP_REDIRECT will operate in a slower locked tx mode.\n",
 			    curr_qp + xdp_qp, vi->max_queue_pairs);
-		return -ENOMEM;
+		xdp_qp = 0;
 	}
 
 	old_prog = rtnl_dereference(vi->rq[0].xdp_prog);
@@ -2477,11 +2540,14 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 	vi->xdp_queue_pairs = xdp_qp;
 
 	if (prog) {
+		vi->xdp_enabled = true;
 		for (i = 0; i < vi->max_queue_pairs; i++) {
 			rcu_assign_pointer(vi->rq[i].xdp_prog, prog);
 			if (i == 0 && !old_prog)
 				virtnet_clear_guest_offloads(vi);
 		}
+	} else {
+		vi->xdp_enabled = false;
 	}
 
 	for (i = 0; i < vi->max_queue_pairs; i++) {
@@ -2565,14 +2631,15 @@ static int virtnet_set_features(struct net_device *dev,
 	u64 offloads;
 	int err;
 
-	if ((dev->features ^ features) & NETIF_F_LRO) {
-		if (vi->xdp_queue_pairs)
+	if ((dev->features ^ features) & NETIF_F_GRO_HW) {
+		if (vi->xdp_enabled)
 			return -EBUSY;
 
-		if (features & NETIF_F_LRO)
+		if (features & NETIF_F_GRO_HW)
 			offloads = vi->guest_offloads_capable;
 		else
-			offloads = 0;
+			offloads = vi->guest_offloads_capable &
+				   ~GUEST_OFFLOAD_GRO_HW_MASK;
 
 		err = virtnet_set_guest_offloads(vi, offloads);
 		if (err)
@@ -3048,9 +3115,9 @@ static int virtnet_probe(struct virtio_device *vdev)
 		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_LRO;
+		dev->features |= NETIF_F_GRO_HW;
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS))
-		dev->hw_features |= NETIF_F_LRO;
+		dev->hw_features |= NETIF_F_GRO_HW;
 
 	dev->vlan_features = dev->features;
 
@@ -3108,6 +3175,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 			dev_err(&vdev->dev,
 				"device MTU appears to have changed it is now %d < %d",
 				mtu, dev->min_mtu);
+			err = -EINVAL;
 			goto free;
 		}
 
@@ -3257,8 +3325,11 @@ static __maybe_unused int virtnet_restore(struct virtio_device *vdev)
 	virtnet_set_queues(vi, vi->curr_queue_pairs);
 
 	err = virtnet_cpu_notif_add(vi);
-	if (err)
+	if (err) {
+		virtnet_freeze_down(vdev);
+		remove_vq_common(vi);
 		return err;
+	}
 
 	return 0;
 }