bpf.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
To: netdev@vger.kernel.org
Cc: "David S. Miller" <davem@davemloft.net>,
	Eric Dumazet <edumazet@google.com>,
	Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
	"Michael S. Tsirkin" <mst@redhat.com>,
	Jason Wang <jasowang@redhat.com>,
	Xuan Zhuo <xuanzhuo@linux.alibaba.com>,
	Alexei Starovoitov <ast@kernel.org>,
	Daniel Borkmann <daniel@iogearbox.net>,
	Jesper Dangaard Brouer <hawk@kernel.org>,
	John Fastabend <john.fastabend@gmail.com>,
	virtualization@lists.linux-foundation.org, bpf@vger.kernel.org
Subject: [PATCH net-next v1 16/19] virtio_net: xsk: rx: introduce receive_xsk() to recv xsk buffer
Date: Mon, 16 Oct 2023 20:00:30 +0800	[thread overview]
Message-ID: <20231016120033.26933-17-xuanzhuo@linux.alibaba.com> (raw)
In-Reply-To: <20231016120033.26933-1-xuanzhuo@linux.alibaba.com>

Implementing the logic of xsk rx. If this packet is not for XSK
determined in XDP, then we need to copy once to generate a SKB.
If it is for XSK, it is a zerocopy receive packet process.

Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
---
 drivers/net/virtio/main.c       |  14 ++--
 drivers/net/virtio/virtio_net.h |   4 ++
 drivers/net/virtio/xsk.c        | 120 ++++++++++++++++++++++++++++++++
 drivers/net/virtio/xsk.h        |   4 ++
 4 files changed, 137 insertions(+), 5 deletions(-)

diff --git a/drivers/net/virtio/main.c b/drivers/net/virtio/main.c
index 0e740447b142..003dd67ab707 100644
--- a/drivers/net/virtio/main.c
+++ b/drivers/net/virtio/main.c
@@ -822,10 +822,10 @@ static void put_xdp_frags(struct xdp_buff *xdp)
 	}
 }
 
-static int virtnet_xdp_handler(struct bpf_prog *xdp_prog, struct xdp_buff *xdp,
-			       struct net_device *dev,
-			       unsigned int *xdp_xmit,
-			       struct virtnet_rq_stats *stats)
+int virtnet_xdp_handler(struct bpf_prog *xdp_prog, struct xdp_buff *xdp,
+			struct net_device *dev,
+			unsigned int *xdp_xmit,
+			struct virtnet_rq_stats *stats)
 {
 	struct xdp_frame *xdpf;
 	int err;
@@ -1589,13 +1589,17 @@ static void receive_buf(struct virtnet_info *vi, struct virtnet_rq *rq,
 		return;
 	}
 
-	if (vi->mergeable_rx_bufs)
+	rcu_read_lock();
+	if (rcu_dereference(rq->xsk.pool))
+		skb = virtnet_receive_xsk(dev, vi, rq, buf, len, xdp_xmit, stats);
+	else if (vi->mergeable_rx_bufs)
 		skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit,
 					stats);
 	else if (vi->big_packets)
 		skb = receive_big(dev, vi, rq, buf, len, stats);
 	else
 		skb = receive_small(dev, vi, rq, buf, ctx, len, xdp_xmit, stats);
+	rcu_read_unlock();
 
 	if (unlikely(!skb))
 		return;
diff --git a/drivers/net/virtio/virtio_net.h b/drivers/net/virtio/virtio_net.h
index 6e71622fca45..fd7f34703c9b 100644
--- a/drivers/net/virtio/virtio_net.h
+++ b/drivers/net/virtio/virtio_net.h
@@ -346,6 +346,10 @@ static inline bool virtnet_is_xdp_raw_buffer_queue(struct virtnet_info *vi, int
 		return false;
 }
 
+int virtnet_xdp_handler(struct bpf_prog *xdp_prog, struct xdp_buff *xdp,
+			struct net_device *dev,
+			unsigned int *xdp_xmit,
+			struct virtnet_rq_stats *stats);
 void virtnet_rx_pause(struct virtnet_info *vi, struct virtnet_rq *rq);
 void virtnet_rx_resume(struct virtnet_info *vi, struct virtnet_rq *rq);
 void virtnet_tx_pause(struct virtnet_info *vi, struct virtnet_sq *sq);
diff --git a/drivers/net/virtio/xsk.c b/drivers/net/virtio/xsk.c
index 841fb078882a..f1c64414fac9 100644
--- a/drivers/net/virtio/xsk.c
+++ b/drivers/net/virtio/xsk.c
@@ -13,6 +13,18 @@ static void sg_fill_dma(struct scatterlist *sg, dma_addr_t addr, u32 len)
 	sg->length = len;
 }
 
+static unsigned int virtnet_receive_buf_num(struct virtnet_info *vi, char *buf)
+{
+	struct virtio_net_hdr_mrg_rxbuf *hdr;
+
+	if (vi->mergeable_rx_bufs) {
+		hdr = (struct virtio_net_hdr_mrg_rxbuf *)buf;
+		return virtio16_to_cpu(vi->vdev, hdr->num_buffers);
+	}
+
+	return 1;
+}
+
 static void virtnet_xsk_check_queue(struct virtnet_sq *sq)
 {
 	struct virtnet_info *vi = sq->vq->vdev->priv;
@@ -37,6 +49,114 @@ static void virtnet_xsk_check_queue(struct virtnet_sq *sq)
 		netif_stop_subqueue(dev, qnum);
 }
 
+static void merge_drop_follow_xdp(struct net_device *dev,
+				  struct virtnet_rq *rq,
+				  u32 num_buf,
+				  struct virtnet_rq_stats *stats)
+{
+	struct xdp_buff *xdp;
+	u32 len;
+
+	while (num_buf-- > 1) {
+		xdp = virtqueue_get_buf(rq->vq, &len);
+		if (unlikely(!xdp)) {
+			pr_debug("%s: rx error: %d buffers missing\n",
+				 dev->name, num_buf);
+			dev->stats.rx_length_errors++;
+			break;
+		}
+		stats->bytes += len;
+		xsk_buff_free(xdp);
+	}
+}
+
+static struct sk_buff *construct_skb(struct virtnet_rq *rq,
+				     struct xdp_buff *xdp)
+{
+	unsigned int metasize = xdp->data - xdp->data_meta;
+	struct sk_buff *skb;
+	unsigned int size;
+
+	size = xdp->data_end - xdp->data_hard_start;
+	skb = napi_alloc_skb(&rq->napi, size);
+	if (unlikely(!skb))
+		return NULL;
+
+	skb_reserve(skb, xdp->data_meta - xdp->data_hard_start);
+
+	size = xdp->data_end - xdp->data_meta;
+	memcpy(__skb_put(skb, size), xdp->data_meta, size);
+
+	if (metasize) {
+		__skb_pull(skb, metasize);
+		skb_metadata_set(skb, metasize);
+	}
+
+	return skb;
+}
+
+struct sk_buff *virtnet_receive_xsk(struct net_device *dev, struct virtnet_info *vi,
+				    struct virtnet_rq *rq, void *buf,
+				    unsigned int len, unsigned int *xdp_xmit,
+				    struct virtnet_rq_stats *stats)
+{
+	struct virtio_net_hdr_mrg_rxbuf *hdr;
+	struct sk_buff *skb = NULL;
+	u32 ret, headroom, num_buf;
+	struct bpf_prog *prog;
+	struct xdp_buff *xdp;
+
+	len -= vi->hdr_len;
+
+	xdp = (struct xdp_buff *)buf;
+
+	xsk_buff_set_size(xdp, len);
+
+	hdr = xdp->data - vi->hdr_len;
+
+	num_buf = virtnet_receive_buf_num(vi, (char *)hdr);
+	if (num_buf > 1)
+		goto drop;
+
+	headroom = xdp->data - xdp->data_hard_start;
+
+	xdp_prepare_buff(xdp, xdp->data_hard_start, headroom, len, true);
+	xsk_buff_dma_sync_for_cpu(xdp, rq->xsk.pool);
+
+	ret = XDP_PASS;
+	rcu_read_lock();
+	prog = rcu_dereference(rq->xdp_prog);
+	if (prog)
+		ret = virtnet_xdp_handler(prog, xdp, dev, xdp_xmit, stats);
+	rcu_read_unlock();
+
+	switch (ret) {
+	case XDP_PASS:
+		skb = construct_skb(rq, xdp);
+		xsk_buff_free(xdp);
+		break;
+
+	case XDP_TX:
+	case XDP_REDIRECT:
+		goto consumed;
+
+	default:
+		goto drop;
+	}
+
+	return skb;
+
+drop:
+	stats->drops++;
+
+	xsk_buff_free(xdp);
+
+	if (num_buf > 1)
+		merge_drop_follow_xdp(dev, rq, num_buf, stats);
+consumed:
+	return NULL;
+}
+
 static int virtnet_add_recvbuf_batch(struct virtnet_info *vi, struct virtnet_rq *rq,
 				     struct xsk_buff_pool *pool, gfp_t gfp)
 {
diff --git a/drivers/net/virtio/xsk.h b/drivers/net/virtio/xsk.h
index bef41a3f954e..dbd2839a5f61 100644
--- a/drivers/net/virtio/xsk.h
+++ b/drivers/net/virtio/xsk.h
@@ -25,4 +25,8 @@ bool virtnet_xsk_xmit(struct virtnet_sq *sq, struct xsk_buff_pool *pool,
 int virtnet_xsk_wakeup(struct net_device *dev, u32 qid, u32 flag);
 int virtnet_add_recvbuf_xsk(struct virtnet_info *vi, struct virtnet_rq *rq,
 			    struct xsk_buff_pool *pool, gfp_t gfp);
+struct sk_buff *virtnet_receive_xsk(struct net_device *dev, struct virtnet_info *vi,
+				    struct virtnet_rq *rq, void *buf,
+				    unsigned int len, unsigned int *xdp_xmit,
+				    struct virtnet_rq_stats *stats);
 #endif
-- 
2.32.0.3.g01195cf9f


  parent reply	other threads:[~2023-10-16 12:01 UTC|newest]

Thread overview: 66+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-10-16 12:00 [PATCH net-next v1 00/19] virtio-net: support AF_XDP zero copy Xuan Zhuo
2023-10-16 12:00 ` [PATCH net-next v1 01/19] virtio_net: rename free_old_xmit_skbs to free_old_xmit Xuan Zhuo
2023-10-19  4:17   ` Jason Wang
2023-10-16 12:00 ` [PATCH net-next v1 02/19] virtio_net: unify the code for recycling the xmit ptr Xuan Zhuo
2023-10-19  4:23   ` Jason Wang
2023-10-16 12:00 ` [PATCH net-next v1 03/19] virtio_net: independent directory Xuan Zhuo
2023-10-19  6:10   ` Jason Wang
2023-10-16 12:00 ` [PATCH net-next v1 04/19] virtio_net: move to virtio_net.h Xuan Zhuo
2023-10-19  6:12   ` Jason Wang
2023-10-19  7:16     ` Xuan Zhuo
2023-10-20  6:59       ` Jason Wang
2023-10-16 12:00 ` [PATCH net-next v1 05/19] virtio_net: add prefix virtnet to all struct/api inside virtio_net.h Xuan Zhuo
2023-10-19  6:14   ` Jason Wang
2023-10-19  6:36     ` Michael S. Tsirkin
2023-10-16 12:00 ` [PATCH net-next v1 06/19] virtio_net: separate virtnet_rx_resize() Xuan Zhuo
2023-10-19  6:17   ` Jason Wang
2023-10-16 12:00 ` [PATCH net-next v1 07/19] virtio_net: separate virtnet_tx_resize() Xuan Zhuo
2023-10-19  6:18   ` Jason Wang
2023-10-16 12:00 ` [PATCH net-next v1 08/19] virtio_net: sq support premapped mode Xuan Zhuo
2023-10-20  6:50   ` Jason Wang
2023-10-20  7:16     ` Xuan Zhuo
2023-10-16 12:00 ` [PATCH net-next v1 09/19] virtio_net: xsk: bind/unbind xsk Xuan Zhuo
2023-10-20  6:51   ` Jason Wang
2023-10-20  7:28     ` Xuan Zhuo
2023-10-16 12:00 ` [PATCH net-next v1 10/19] virtio_net: xsk: prevent disable tx napi Xuan Zhuo
2023-10-20  6:51   ` Jason Wang
2023-10-16 12:00 ` [PATCH net-next v1 11/19] virtio_net: xsk: tx: support tx Xuan Zhuo
2023-10-20  6:52   ` Jason Wang
2023-10-20  8:06     ` Xuan Zhuo
2023-10-16 12:00 ` [PATCH net-next v1 12/19] virtio_net: xsk: tx: support wakeup Xuan Zhuo
2023-10-20  6:52   ` Jason Wang
2023-10-20  8:09     ` Xuan Zhuo
2023-10-16 12:00 ` [PATCH net-next v1 13/19] virtio_net: xsk: tx: virtnet_free_old_xmit() distinguishes xsk buffer Xuan Zhuo
2023-10-16 23:44   ` Jakub Kicinski
2023-10-17  2:02     ` Xuan Zhuo
2023-10-19  6:38       ` Michael S. Tsirkin
2023-10-19  7:13         ` Xuan Zhuo
2023-10-19  8:42           ` Michael S. Tsirkin
2023-10-16 12:00 ` [PATCH net-next v1 14/19] virtio_net: xsk: tx: virtnet_sq_free_unused_buf() check " Xuan Zhuo
2023-10-20  6:53   ` Jason Wang
2023-10-16 12:00 ` [PATCH net-next v1 15/19] virtio_net: xsk: rx: introduce add_recvbuf_xsk() Xuan Zhuo
2023-10-20  6:56   ` Jason Wang
2023-10-23  6:56     ` Xuan Zhuo
2023-10-16 12:00 ` Xuan Zhuo [this message]
2023-10-20  6:57   ` [PATCH net-next v1 16/19] virtio_net: xsk: rx: introduce receive_xsk() to recv xsk buffer Jason Wang
2023-10-23  2:39     ` Xuan Zhuo
2023-11-15  2:35     ` Xuan Zhuo
2023-10-16 12:00 ` [PATCH net-next v1 17/19] virtio_net: xsk: rx: virtnet_rq_free_unused_buf() check " Xuan Zhuo
2023-10-16 12:00 ` [PATCH net-next v1 18/19] virtio_net: update tx timeout record Xuan Zhuo
2023-10-20  6:57   ` Jason Wang
2023-10-16 12:00 ` [PATCH net-next v1 19/19] virtio_net: xdp_features add NETDEV_XDP_ACT_XSK_ZEROCOPY Xuan Zhuo
2023-10-17  2:53 ` [PATCH net-next v1 00/19] virtio-net: support AF_XDP zero copy Jason Wang
2023-10-17  3:02   ` Xuan Zhuo
2023-10-17  3:20     ` Jason Wang
2023-10-17  3:22       ` Xuan Zhuo
2023-10-17  3:28         ` Jason Wang
2023-10-17  5:27           ` Jason Wang
2023-10-17  6:06             ` Xuan Zhuo
2023-10-17  6:26               ` Jason Wang
2023-10-17  6:43                 ` Xuan Zhuo
2023-10-17 11:19                   ` Xuan Zhuo
2023-10-18  2:46                     ` Jason Wang
2023-10-18  2:56                       ` Xuan Zhuo
2023-10-18  3:32                     ` Xuan Zhuo
2023-10-18  3:40                       ` Jason Wang
2023-10-18  1:02                   ` Jason Wang

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20231016120033.26933-17-xuanzhuo@linux.alibaba.com \
    --to=xuanzhuo@linux.alibaba.com \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=hawk@kernel.org \
    --cc=jasowang@redhat.com \
    --cc=john.fastabend@gmail.com \
    --cc=kuba@kernel.org \
    --cc=mst@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=virtualization@lists.linux-foundation.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).