1 files changed, 376 insertions, 199 deletions

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 61e33e4dd0cd..2396c28c0122 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -134,7 +134,7 @@ struct send_queue {
 	struct scatterlist sg[MAX_SKB_FRAGS + 2];
 
 	/* Name of the send queue: output.$index */
-	char name[40];
+	char name[16];
 
 	struct virtnet_sq_stats stats;
 
@@ -171,7 +171,7 @@ struct receive_queue {
 	unsigned int min_buf_len;
 
 	/* Name of this receive queue: input.$index */
-	char name[40];
+	char name[16];
 
 	struct xdp_rxq_info xdp_rxq;
 };
@@ -447,7 +447,6 @@ 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, unsigned int metasize,
 				   unsigned int headroom)
 {
 	struct sk_buff *skb;
@@ -466,21 +465,11 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 	else
 		hdr_padded_len = sizeof(struct padded_vnet_hdr);
 
-	/* If headroom is not 0, there is an offset between the beginning of the
-	 * data and the allocated space, otherwise the data and the allocated
-	 * space are aligned.
-	 *
-	 * Buffers with headroom use PAGE_SIZE as alloc size, see
-	 * add_recvbuf_mergeable() + get_mergeable_buf_len()
-	 */
-	truesize = headroom ? PAGE_SIZE : truesize;
-	tailroom = truesize - headroom;
 	buf = p - headroom;
-
 	len -= hdr_len;
 	offset += hdr_padded_len;
 	p += hdr_padded_len;
-	tailroom -= hdr_padded_len + len;
+	tailroom = truesize - headroom  - hdr_padded_len - len;
 
 	shinfo_size = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
@@ -510,7 +499,7 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 	if (len <= skb_tailroom(skb))
 		copy = len;
 	else
-		copy = ETH_HLEN + metasize;
+		copy = ETH_HLEN;
 	skb_put_data(skb, p, copy);
 
 	len -= copy;
@@ -549,20 +538,93 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 		give_pages(rq, page);
 
 ok:
-	/* hdr_valid means no XDP, so we can copy the vnet header */
-	if (hdr_valid) {
-		hdr = skb_vnet_hdr(skb);
-		memcpy(hdr, hdr_p, hdr_len);
-	}
+	hdr = skb_vnet_hdr(skb);
+	memcpy(hdr, hdr_p, hdr_len);
 	if (page_to_free)
 		put_page(page_to_free);
 
-	if (metasize) {
-		__skb_pull(skb, metasize);
-		skb_metadata_set(skb, metasize);
+	return skb;
+}
+
+static void free_old_xmit_skbs(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;
+
+			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++;
 	}
 
-	return skb;
+	/* Avoid overhead when no packets have been processed
+	 * happens when called speculatively from start_xmit.
+	 */
+	if (!packets)
+		return;
+
+	u64_stats_update_begin(&sq->stats.syncp);
+	sq->stats.bytes += bytes;
+	sq->stats.packets += packets;
+	u64_stats_update_end(&sq->stats.syncp);
+}
+
+static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q)
+{
+	if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs))
+		return false;
+	else if (q < vi->curr_queue_pairs)
+		return true;
+	else
+		return false;
+}
+
+static void check_sq_full_and_disable(struct virtnet_info *vi,
+				      struct net_device *dev,
+				      struct send_queue *sq)
+{
+	bool use_napi = sq->napi.weight;
+	int qnum;
+
+	qnum = sq - vi->sq;
+
+	/* If running out of space, stop queue to avoid getting packets that we
+	 * are then unable to transmit.
+	 * An alternative would be to force queuing layer to requeue the skb by
+	 * returning NETDEV_TX_BUSY. However, NETDEV_TX_BUSY should not be
+	 * returned in a normal path of operation: it means that driver is not
+	 * maintaining the TX queue stop/start state properly, and causes
+	 * the stack to do a non-trivial amount of useless work.
+	 * Since most packets only take 1 or 2 ring slots, stopping the queue
+	 * early means 16 slots are typically wasted.
+	 */
+	if (sq->vq->num_free < 2+MAX_SKB_FRAGS) {
+		netif_stop_subqueue(dev, qnum);
+		if (use_napi) {
+			if (unlikely(!virtqueue_enable_cb_delayed(sq->vq)))
+				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);
+			if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) {
+				netif_start_subqueue(dev, qnum);
+				virtqueue_disable_cb(sq->vq);
+			}
+		}
+	}
 }
 
 static int __virtnet_xdp_xmit_one(struct virtnet_info *vi,
@@ -570,22 +632,43 @@ static int __virtnet_xdp_xmit_one(struct virtnet_info *vi,
 				   struct xdp_frame *xdpf)
 {
 	struct virtio_net_hdr_mrg_rxbuf *hdr;
-	int err;
+	struct skb_shared_info *shinfo;
+	u8 nr_frags = 0;
+	int err, i;
 
 	if (unlikely(xdpf->headroom < vi->hdr_len))
 		return -EOVERFLOW;
 
-	/* Make room for virtqueue hdr (also change xdpf->headroom?) */
+	if (unlikely(xdp_frame_has_frags(xdpf))) {
+		shinfo = xdp_get_shared_info_from_frame(xdpf);
+		nr_frags = shinfo->nr_frags;
+	}
+
+	/* In wrapping function virtnet_xdp_xmit(), we need to free
+	 * up the pending old buffers, where we need to calculate the
+	 * position of skb_shared_info in xdp_get_frame_len() and
+	 * xdp_return_frame(), which will involve to xdpf->data and
+	 * xdpf->headroom. Therefore, we need to update the value of
+	 * headroom synchronously here.
+	 */
+	xdpf->headroom -= vi->hdr_len;
 	xdpf->data -= vi->hdr_len;
 	/* Zero header and leave csum up to XDP layers */
 	hdr = xdpf->data;
 	memset(hdr, 0, vi->hdr_len);
 	xdpf->len   += vi->hdr_len;
 
-	sg_init_one(sq->sg, xdpf->data, xdpf->len);
+	sg_init_table(sq->sg, nr_frags + 1);
+	sg_set_buf(sq->sg, xdpf->data, xdpf->len);
+	for (i = 0; i < nr_frags; i++) {
+		skb_frag_t *frag = &shinfo->frags[i];
+
+		sg_set_page(&sq->sg[i + 1], skb_frag_page(frag),
+			    skb_frag_size(frag), skb_frag_off(frag));
+	}
 
-	err = virtqueue_add_outbuf(sq->vq, sq->sg, 1, xdp_to_ptr(xdpf),
-				   GFP_ATOMIC);
+	err = virtqueue_add_outbuf(sq->vq, sq->sg, nr_frags + 1,
+				   xdp_to_ptr(xdpf), GFP_ATOMIC);
 	if (unlikely(err))
 		return -ENOSPC; /* Caller handle free/refcnt */
 
@@ -665,7 +748,7 @@ static int virtnet_xdp_xmit(struct net_device *dev,
 		if (likely(is_xdp_frame(ptr))) {
 			struct xdp_frame *frame = ptr_to_xdp(ptr);
 
-			bytes += frame->len;
+			bytes += xdp_get_frame_len(frame);
 			xdp_return_frame(frame);
 		} else {
 			struct sk_buff *skb = ptr;
@@ -685,6 +768,9 @@ static int virtnet_xdp_xmit(struct net_device *dev,
 	}
 	ret = nxmit;
 
+	if (!is_xdp_raw_buffer_queue(vi, sq - vi->sq))
+		check_sq_full_and_disable(vi, dev, sq);
+
 	if (flags & XDP_XMIT_FLUSH) {
 		if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq))
 			kicks = 1;
@@ -722,7 +808,7 @@ static unsigned int virtnet_get_headroom(struct virtnet_info *vi)
  * have enough headroom.
  */
 static struct page *xdp_linearize_page(struct receive_queue *rq,
-				       u16 *num_buf,
+				       int *num_buf,
 				       struct page *p,
 				       int offset,
 				       int page_off,
@@ -822,7 +908,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 		if (unlikely(xdp_headroom < virtnet_get_headroom(vi))) {
 			int offset = buf - page_address(page) + header_offset;
 			unsigned int tlen = len + vi->hdr_len;
-			u16 num_buf = 1;
+			int num_buf = 1;
 
 			xdp_headroom = virtnet_get_headroom(vi);
 			header_offset = VIRTNET_RX_PAD + xdp_headroom;
@@ -924,7 +1010,7 @@ static struct sk_buff *receive_big(struct net_device *dev,
 {
 	struct page *page = buf;
 	struct sk_buff *skb =
-		page_to_skb(vi, rq, page, 0, len, PAGE_SIZE, true, 0, 0);
+		page_to_skb(vi, rq, page, 0, len, PAGE_SIZE, 0);
 
 	stats->bytes += len - vi->hdr_len;
 	if (unlikely(!skb))
@@ -938,6 +1024,143 @@ err:
 	return NULL;
 }
 
+/* Why not use xdp_build_skb_from_frame() ?
+ * XDP core assumes that xdp frags are PAGE_SIZE in length, while in
+ * virtio-net there are 2 points that do not match its requirements:
+ *  1. The size of the prefilled buffer is not fixed before xdp is set.
+ *  2. xdp_build_skb_from_frame() does more checks that we don't need,
+ *     like eth_type_trans() (which virtio-net does in receive_buf()).
+ */
+static struct sk_buff *build_skb_from_xdp_buff(struct net_device *dev,
+					       struct virtnet_info *vi,
+					       struct xdp_buff *xdp,
+					       unsigned int xdp_frags_truesz)
+{
+	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
+	unsigned int headroom, data_len;
+	struct sk_buff *skb;
+	int metasize;
+	u8 nr_frags;
+
+	if (unlikely(xdp->data_end > xdp_data_hard_end(xdp))) {
+		pr_debug("Error building skb as missing reserved tailroom for xdp");
+		return NULL;
+	}
+
+	if (unlikely(xdp_buff_has_frags(xdp)))
+		nr_frags = sinfo->nr_frags;
+
+	skb = build_skb(xdp->data_hard_start, xdp->frame_sz);
+	if (unlikely(!skb))
+		return NULL;
+
+	headroom = xdp->data - xdp->data_hard_start;
+	data_len = xdp->data_end - xdp->data;
+	skb_reserve(skb, headroom);
+	__skb_put(skb, data_len);
+
+	metasize = xdp->data - xdp->data_meta;
+	metasize = metasize > 0 ? metasize : 0;
+	if (metasize)
+		skb_metadata_set(skb, metasize);
+
+	if (unlikely(xdp_buff_has_frags(xdp)))
+		xdp_update_skb_shared_info(skb, nr_frags,
+					   sinfo->xdp_frags_size,
+					   xdp_frags_truesz,
+					   xdp_buff_is_frag_pfmemalloc(xdp));
+
+	return skb;
+}
+
+/* TODO: build xdp in big mode */
+static int virtnet_build_xdp_buff_mrg(struct net_device *dev,
+				      struct virtnet_info *vi,
+				      struct receive_queue *rq,
+				      struct xdp_buff *xdp,
+				      void *buf,
+				      unsigned int len,
+				      unsigned int frame_sz,
+				      int *num_buf,
+				      unsigned int *xdp_frags_truesize,
+				      struct virtnet_rq_stats *stats)
+{
+	struct virtio_net_hdr_mrg_rxbuf *hdr = buf;
+	unsigned int headroom, tailroom, room;
+	unsigned int truesize, cur_frag_size;
+	struct skb_shared_info *shinfo;
+	unsigned int xdp_frags_truesz = 0;
+	struct page *page;
+	skb_frag_t *frag;
+	int offset;
+	void *ctx;
+
+	xdp_init_buff(xdp, frame_sz, &rq->xdp_rxq);
+	xdp_prepare_buff(xdp, buf - VIRTIO_XDP_HEADROOM,
+			 VIRTIO_XDP_HEADROOM + vi->hdr_len, len - vi->hdr_len, true);
+
+	if (!*num_buf)
+		return 0;
+
+	if (*num_buf > 1) {
+		/* If we want to build multi-buffer xdp, we need
+		 * to specify that the flags of xdp_buff have the
+		 * XDP_FLAGS_HAS_FRAG bit.
+		 */
+		if (!xdp_buff_has_frags(xdp))
+			xdp_buff_set_frags_flag(xdp);
+
+		shinfo = xdp_get_shared_info_from_buff(xdp);
+		shinfo->nr_frags = 0;
+		shinfo->xdp_frags_size = 0;
+	}
+
+	if (*num_buf > MAX_SKB_FRAGS + 1)
+		return -EINVAL;
+
+	while (--*num_buf > 0) {
+		buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx);
+		if (unlikely(!buf)) {
+			pr_debug("%s: rx error: %d buffers out of %d missing\n",
+				 dev->name, *num_buf,
+				 virtio16_to_cpu(vi->vdev, hdr->num_buffers));
+			dev->stats.rx_length_errors++;
+			return -EINVAL;
+		}
+
+		stats->bytes += len;
+		page = virt_to_head_page(buf);
+		offset = buf - page_address(page);
+
+		truesize = mergeable_ctx_to_truesize(ctx);
+		headroom = mergeable_ctx_to_headroom(ctx);
+		tailroom = headroom ? sizeof(struct skb_shared_info) : 0;
+		room = SKB_DATA_ALIGN(headroom + tailroom);
+
+		cur_frag_size = truesize;
+		xdp_frags_truesz += cur_frag_size;
+		if (unlikely(len > truesize - room || cur_frag_size > PAGE_SIZE)) {
+			put_page(page);
+			pr_debug("%s: rx error: len %u exceeds truesize %lu\n",
+				 dev->name, len, (unsigned long)(truesize - room));
+			dev->stats.rx_length_errors++;
+			return -EINVAL;
+		}
+
+		frag = &shinfo->frags[shinfo->nr_frags++];
+		__skb_frag_set_page(frag, page);
+		skb_frag_off_set(frag, offset);
+		skb_frag_size_set(frag, len);
+		if (page_is_pfmemalloc(page))
+			xdp_buff_set_frag_pfmemalloc(xdp);
+
+		shinfo->xdp_frags_size += len;
+	}
+
+	*xdp_frags_truesize = xdp_frags_truesz;
+	return 0;
+}
+
 static struct sk_buff *receive_mergeable(struct net_device *dev,
 					 struct virtnet_info *vi,
 					 struct receive_queue *rq,
@@ -948,23 +1171,24 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 					 struct virtnet_rq_stats *stats)
 {
 	struct virtio_net_hdr_mrg_rxbuf *hdr = buf;
-	u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers);
+	int num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers);
 	struct page *page = virt_to_head_page(buf);
 	int offset = buf - page_address(page);
 	struct sk_buff *head_skb, *curr_skb;
 	struct bpf_prog *xdp_prog;
 	unsigned int truesize = mergeable_ctx_to_truesize(ctx);
 	unsigned int headroom = mergeable_ctx_to_headroom(ctx);
-	unsigned int metasize = 0;
-	unsigned int frame_sz;
+	unsigned int tailroom = headroom ? sizeof(struct skb_shared_info) : 0;
+	unsigned int room = SKB_DATA_ALIGN(headroom + tailroom);
+	unsigned int frame_sz, xdp_room;
 	int err;
 
 	head_skb = NULL;
 	stats->bytes += len - vi->hdr_len;
 
-	if (unlikely(len > truesize)) {
+	if (unlikely(len > truesize - room)) {
 		pr_debug("%s: rx error: len %u exceeds truesize %lu\n",
-			 dev->name, len, (unsigned long)ctx);
+			 dev->name, len, (unsigned long)(truesize - room));
 		dev->stats.rx_length_errors++;
 		goto err_skb;
 	}
@@ -977,11 +1201,14 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(rq->xdp_prog);
 	if (xdp_prog) {
+		unsigned int xdp_frags_truesz = 0;
+		struct skb_shared_info *shinfo;
 		struct xdp_frame *xdpf;
 		struct page *xdp_page;
 		struct xdp_buff xdp;
 		void *data;
 		u32 act;
+		int i;
 
 		/* Transient failure which in theory could occur if
 		 * in-flight packets from before XDP was enabled reach
@@ -990,19 +1217,23 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 		if (unlikely(hdr->hdr.gso_type))
 			goto err_xdp;
 
-		/* Buffers with headroom use PAGE_SIZE as alloc size,
-		 * see add_recvbuf_mergeable() + get_mergeable_buf_len()
+		/* 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
+		 * hole mechanism for xdp. See add_recvbuf_mergeable().
 		 */
-		frame_sz = headroom ? PAGE_SIZE : truesize;
-
-		/* This happens when rx buffer size is underestimated
-		 * or headroom is not enough because of the buffer
-		 * was refilled before XDP is set. This should only
-		 * happen for the first several packets, so we don't
-		 * care much about its performance.
+		frame_sz = truesize;
+
+		/* This happens when headroom is not enough because
+		 * of the buffer was prefilled before XDP is set.
+		 * This should only happen for the first several packets.
+		 * In fact, vq reset can be used here to help us clean up
+		 * the prefilled buffers, but many existing devices do not
+		 * support it, and we don't want to bother users who are
+		 * using xdp normally.
 		 */
-		if (unlikely(num_buf > 1 ||
-			     headroom < virtnet_get_headroom(vi))) {
+		if (!xdp_prog->aux->xdp_has_frags &&
+		    (num_buf > 1 || headroom < virtnet_get_headroom(vi))) {
 			/* linearize data for XDP */
 			xdp_page = xdp_linearize_page(rq, &num_buf,
 						      page, offset,
@@ -1013,82 +1244,56 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			if (!xdp_page)
 				goto err_xdp;
 			offset = VIRTIO_XDP_HEADROOM;
+		} else if (unlikely(headroom < virtnet_get_headroom(vi))) {
+			xdp_room = SKB_DATA_ALIGN(VIRTIO_XDP_HEADROOM +
+						  sizeof(struct skb_shared_info));
+			if (len + xdp_room > PAGE_SIZE)
+				goto err_xdp;
+
+			xdp_page = alloc_page(GFP_ATOMIC);
+			if (!xdp_page)
+				goto err_xdp;
+
+			memcpy(page_address(xdp_page) + VIRTIO_XDP_HEADROOM,
+			       page_address(page) + offset, len);
+			frame_sz = PAGE_SIZE;
+			offset = VIRTIO_XDP_HEADROOM;
 		} else {
 			xdp_page = page;
 		}
 
-		/* Allow consuming headroom but reserve enough space to push
-		 * the descriptor on if we get an XDP_TX return code.
-		 */
 		data = page_address(xdp_page) + offset;
-		xdp_init_buff(&xdp, frame_sz - vi->hdr_len, &rq->xdp_rxq);
-		xdp_prepare_buff(&xdp, data - VIRTIO_XDP_HEADROOM + vi->hdr_len,
-				 VIRTIO_XDP_HEADROOM, len - vi->hdr_len, true);
+		err = virtnet_build_xdp_buff_mrg(dev, vi, rq, &xdp, data, len, frame_sz,
+						 &num_buf, &xdp_frags_truesz, stats);
+		if (unlikely(err))
+			goto err_xdp_frags;
 
 		act = bpf_prog_run_xdp(xdp_prog, &xdp);
 		stats->xdp_packets++;
 
 		switch (act) {
 		case XDP_PASS:
-			metasize = xdp.data - xdp.data_meta;
-
-			/* recalculate offset to account for any header
-			 * 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 - metasize;
+			head_skb = build_skb_from_xdp_buff(dev, vi, &xdp, xdp_frags_truesz);
+			if (unlikely(!head_skb))
+				goto err_xdp_frags;
 
-			/* recalculate len if xdp.data, xdp.data_end or
-			 * xdp.data_meta were adjusted
-			 */
-			len = xdp.data_end - xdp.data + vi->hdr_len + metasize;
-
-			/* recalculate headroom if xdp.data or xdp_data_meta
-			 * were adjusted, note that offset should always point
-			 * to the start of the reserved bytes for virtio_net
-			 * header which are followed by xdp.data, that means
-			 * that offset is equal to the headroom (when buf is
-			 * starting at the beginning of the page, otherwise
-			 * there is a base offset inside the page) but it's used
-			 * with a different starting point (buf start) than
-			 * xdp.data (buf start + vnet hdr size). If xdp.data or
-			 * data_meta were adjusted by the xdp prog then the
-			 * headroom size has changed and so has the offset, we
-			 * can use data_hard_start, which points at buf start +
-			 * vnet hdr size, to calculate the new headroom and use
-			 * it later to compute buf start in page_to_skb()
-			 */
-			headroom = xdp.data - xdp.data_hard_start - metasize;
-
-			/* We can only create skb based on xdp_page. */
-			if (unlikely(xdp_page != page)) {
-				rcu_read_unlock();
+			if (unlikely(xdp_page != page))
 				put_page(page);
-				head_skb = page_to_skb(vi, rq, xdp_page, offset,
-						       len, PAGE_SIZE, false,
-						       metasize,
-						       headroom);
-				return head_skb;
-			}
-			break;
+			rcu_read_unlock();
+			return head_skb;
 		case XDP_TX:
 			stats->xdp_tx++;
 			xdpf = xdp_convert_buff_to_frame(&xdp);
 			if (unlikely(!xdpf)) {
-				if (unlikely(xdp_page != page))
-					put_page(xdp_page);
-				goto err_xdp;
+				netdev_dbg(dev, "convert buff to frame failed for xdp\n");
+				goto err_xdp_frags;
 			}
 			err = virtnet_xdp_xmit(dev, 1, &xdpf, 0);
 			if (unlikely(!err)) {
 				xdp_return_frame_rx_napi(xdpf);
 			} else if (unlikely(err < 0)) {
 				trace_xdp_exception(vi->dev, xdp_prog, act);
-				if (unlikely(xdp_page != page))
-					put_page(xdp_page);
-				goto err_xdp;
+				goto err_xdp_frags;
 			}
 			*xdp_xmit |= VIRTIO_XDP_TX;
 			if (unlikely(xdp_page != page))
@@ -1098,11 +1303,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 		case XDP_REDIRECT:
 			stats->xdp_redirects++;
 			err = xdp_do_redirect(dev, &xdp, xdp_prog);
-			if (err) {
-				if (unlikely(xdp_page != page))
-					put_page(xdp_page);
-				goto err_xdp;
-			}
+			if (err)
+				goto err_xdp_frags;
 			*xdp_xmit |= VIRTIO_XDP_REDIR;
 			if (unlikely(xdp_page != page))
 				put_page(page);
@@ -1115,16 +1317,26 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			trace_xdp_exception(vi->dev, xdp_prog, act);
 			fallthrough;
 		case XDP_DROP:
-			if (unlikely(xdp_page != page))
-				__free_pages(xdp_page, 0);
-			goto err_xdp;
+			goto err_xdp_frags;
+		}
+err_xdp_frags:
+		if (unlikely(xdp_page != page))
+			__free_pages(xdp_page, 0);
+
+		if (xdp_buff_has_frags(&xdp)) {
+			shinfo = xdp_get_shared_info_from_buff(&xdp);
+			for (i = 0; i < shinfo->nr_frags; i++) {
+				xdp_page = skb_frag_page(&shinfo->frags[i]);
+				put_page(xdp_page);
+			}
 		}
+
+		goto err_xdp;
 	}
 	rcu_read_unlock();
 
 skip_xdp:
-	head_skb = page_to_skb(vi, rq, page, offset, len, truesize, !xdp_prog,
-			       metasize, headroom);
+	head_skb = page_to_skb(vi, rq, page, offset, len, truesize, headroom);
 	curr_skb = head_skb;
 
 	if (unlikely(!curr_skb))
@@ -1146,9 +1358,12 @@ skip_xdp:
 		page = virt_to_head_page(buf);
 
 		truesize = mergeable_ctx_to_truesize(ctx);
-		if (unlikely(len > truesize)) {
+		headroom = mergeable_ctx_to_headroom(ctx);
+		tailroom = headroom ? sizeof(struct skb_shared_info) : 0;
+		room = SKB_DATA_ALIGN(headroom + tailroom);
+		if (unlikely(len > truesize - room)) {
 			pr_debug("%s: rx error: len %u exceeds truesize %lu\n",
-				 dev->name, len, (unsigned long)ctx);
+				 dev->name, len, (unsigned long)(truesize - room));
 			dev->stats.rx_length_errors++;
 			goto err_skb;
 		}
@@ -1251,13 +1466,7 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
 	if (unlikely(len < vi->hdr_len + ETH_HLEN)) {
 		pr_debug("%s: short packet %i\n", dev->name, len);
 		dev->stats.rx_length_errors++;
-		if (vi->mergeable_rx_bufs) {
-			put_page(virt_to_head_page(buf));
-		} else if (vi->big_packets) {
-			give_pages(rq, buf);
-		} else {
-			put_page(virt_to_head_page(buf));
-		}
+		virtnet_rq_free_unused_buf(rq->vq, buf);
 		return;
 	}
 
@@ -1426,13 +1635,16 @@ static int add_recvbuf_mergeable(struct virtnet_info *vi,
 		/* To avoid internal fragmentation, if there is very likely not
 		 * enough space for another buffer, add the remaining space to
 		 * the current buffer.
+		 * XDP core assumes that frame_size of xdp_buff and the length
+		 * of the frag are PAGE_SIZE, so we disable the hole mechanism.
 		 */
-		len += hole;
+		if (!headroom)
+			len += hole;
 		alloc_frag->offset += hole;
 	}
 
 	sg_init_one(rq->sg, buf, len);
-	ctx = mergeable_len_to_ctx(len, headroom);
+	ctx = mergeable_len_to_ctx(len + room, headroom);
 	err = virtqueue_add_inbuf_ctx(rq->vq, rq->sg, 1, buf, ctx, gfp);
 	if (err < 0)
 		put_page(virt_to_head_page(buf));
@@ -1590,52 +1802,6 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
 	return stats.packets;
 }
 
-static void free_old_xmit_skbs(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;
-
-			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 += frame->len;
-			xdp_return_frame(frame);
-		}
-		packets++;
-	}
-
-	/* Avoid overhead when no packets have been processed
-	 * happens when called speculatively from start_xmit.
-	 */
-	if (!packets)
-		return;
-
-	u64_stats_update_begin(&sq->stats.syncp);
-	sq->stats.bytes += bytes;
-	sq->stats.packets += packets;
-	u64_stats_update_end(&sq->stats.syncp);
-}
-
-static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q)
-{
-	if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs))
-		return false;
-	else if (q < vi->curr_queue_pairs)
-		return true;
-	else
-		return false;
-}
-
 static void virtnet_poll_cleantx(struct receive_queue *rq)
 {
 	struct virtnet_info *vi = rq->vq->vdev->priv;
@@ -1865,30 +2031,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 		nf_reset_ct(skb);
 	}
 
-	/* If running out of space, stop queue to avoid getting packets that we
-	 * are then unable to transmit.
-	 * An alternative would be to force queuing layer to requeue the skb by
-	 * returning NETDEV_TX_BUSY. However, NETDEV_TX_BUSY should not be
-	 * returned in a normal path of operation: it means that driver is not
-	 * maintaining the TX queue stop/start state properly, and causes
-	 * the stack to do a non-trivial amount of useless work.
-	 * Since most packets only take 1 or 2 ring slots, stopping the queue
-	 * early means 16 slots are typically wasted.
-	 */
-	if (sq->vq->num_free < 2+MAX_SKB_FRAGS) {
-		netif_stop_subqueue(dev, qnum);
-		if (use_napi) {
-			if (unlikely(!virtqueue_enable_cb_delayed(sq->vq)))
-				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);
-			if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) {
-				netif_start_subqueue(dev, qnum);
-				virtqueue_disable_cb(sq->vq);
-			}
-		}
-	}
+	check_sq_full_and_disable(vi, dev, sq);
 
 	if (kick || netif_xmit_stopped(txq)) {
 		if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) {
@@ -2158,9 +2301,9 @@ static int virtnet_close(struct net_device *dev)
 	cancel_delayed_work_sync(&vi->refill);
 
 	for (i = 0; i < vi->max_queue_pairs; i++) {
+		virtnet_napi_tx_disable(&vi->sq[i].napi);
 		napi_disable(&vi->rq[i].napi);
 		xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq);
-		virtnet_napi_tx_disable(&vi->sq[i].napi);
 	}
 
 	return 0;
@@ -3080,7 +3223,9 @@ static int virtnet_restore_guest_offloads(struct virtnet_info *vi)
 static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 			   struct netlink_ext_ack *extack)
 {
-	unsigned long int max_sz = PAGE_SIZE - sizeof(struct padded_vnet_hdr);
+	unsigned int room = SKB_DATA_ALIGN(VIRTIO_XDP_HEADROOM +
+					   sizeof(struct skb_shared_info));
+	unsigned int max_sz = PAGE_SIZE - room - ETH_HLEN;
 	struct virtnet_info *vi = netdev_priv(dev);
 	struct bpf_prog *old_prog;
 	u16 xdp_qp = 0, curr_qp;
@@ -3103,9 +3248,9 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 		return -EINVAL;
 	}
 
-	if (dev->mtu > max_sz) {
-		NL_SET_ERR_MSG_MOD(extack, "MTU too large to enable XDP");
-		netdev_warn(dev, "XDP requires MTU less than %lu\n", max_sz);
+	if (prog && !prog->aux->xdp_has_frags && dev->mtu > max_sz) {
+		NL_SET_ERR_MSG_MOD(extack, "MTU too large to enable XDP without frags");
+		netdev_warn(dev, "single-buffer XDP requires MTU less than %u\n", max_sz);
 		return -EINVAL;
 	}
 
@@ -3157,7 +3302,10 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 			if (i == 0 && !old_prog)
 				virtnet_clear_guest_offloads(vi);
 		}
+		if (!old_prog)
+			xdp_features_set_redirect_target(dev, true);
 	} else {
+		xdp_features_clear_redirect_target(dev);
 		vi->xdp_enabled = false;
 	}
 
@@ -3690,6 +3838,12 @@ static int virtnet_validate(struct virtio_device *vdev)
 			__virtio_clear_bit(vdev, VIRTIO_NET_F_MTU);
 	}
 
+	if (virtio_has_feature(vdev, VIRTIO_NET_F_STANDBY) &&
+	    !virtio_has_feature(vdev, VIRTIO_NET_F_MAC)) {
+		dev_warn(&vdev->dev, "device advertises feature VIRTIO_NET_F_STANDBY but not VIRTIO_NET_F_MAC, disabling standby");
+		__virtio_clear_bit(vdev, VIRTIO_NET_F_STANDBY);
+	}
+
 	return 0;
 }
 
@@ -3787,6 +3941,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 		dev->hw_features |= NETIF_F_GRO_HW;
 
 	dev->vlan_features = dev->features;
+	dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT;
 
 	/* MTU range: 68 - 65535 */
 	dev->min_mtu = MIN_MTU;
@@ -3802,6 +3957,8 @@ static int virtnet_probe(struct virtio_device *vdev)
 		eth_hw_addr_set(dev, addr);
 	} else {
 		eth_hw_addr_random(dev);
+		dev_info(&vdev->dev, "Assigned random MAC address %pM\n",
+			 dev->dev_addr);
 	}
 
 	/* Set up our device-specific information */
@@ -3813,8 +3970,10 @@ static int virtnet_probe(struct virtio_device *vdev)
 	INIT_WORK(&vi->config_work, virtnet_config_changed_work);
 	spin_lock_init(&vi->refill_lock);
 
-	if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF))
+	if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF)) {
 		vi->mergeable_rx_bufs = true;
+		dev->xdp_features |= NETDEV_XDP_ACT_RX_SG;
+	}
 
 	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_NOTF_COAL)) {
 		vi->rx_usecs = 0;
@@ -3929,6 +4088,24 @@ static int virtnet_probe(struct virtio_device *vdev)
 
 	virtio_device_ready(vdev);
 
+	/* a random MAC address has been assigned, notify the device.
+	 * We don't fail probe if VIRTIO_NET_F_CTRL_MAC_ADDR is not there
+	 * because many devices work fine without getting MAC explicitly
+	 */
+	if (!virtio_has_feature(vdev, VIRTIO_NET_F_MAC) &&
+	    virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_MAC_ADDR)) {
+		struct scatterlist sg;
+
+		sg_init_one(&sg, dev->dev_addr, dev->addr_len);
+		if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MAC,
+					  VIRTIO_NET_CTRL_MAC_ADDR_SET, &sg)) {
+			pr_debug("virtio_net: setting MAC address failed\n");
+			rtnl_unlock();
+			err = -EINVAL;
+			goto free_unregister_netdev;
+		}
+	}
+
 	rtnl_unlock();
 
 	err = virtnet_cpu_notif_add(vi);