| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Mon, 13 Nov 2023 17:11:04 +0100
From: Maciej Fijalkowski <maciej.fijalkowski@...el.com>
To: Xuan Zhuo <xuanzhuo@...ux.alibaba.com>
CC: <netdev@...r.kernel.org>, "David S. Miller" <davem@...emloft.net>, "Eric
Dumazet" <edumazet@...gle.com>, Jakub Kicinski <kuba@...nel.org>, Paolo Abeni
<pabeni@...hat.com>, "Michael S. Tsirkin" <mst@...hat.com>, Jason Wang
<jasowang@...hat.com>, Alexei Starovoitov <ast@...nel.org>, Daniel Borkmann
<daniel@...earbox.net>, Jesper Dangaard Brouer <hawk@...nel.org>, "John
Fastabend" <john.fastabend@...il.com>,
<virtualization@...ts.linux-foundation.org>, <bpf@...r.kernel.org>
Subject: Re: [PATCH net-next v2 18/21] virtio_net: xsk: rx: introduce
receive_xsk() to recv xsk buffer
On Tue, Nov 07, 2023 at 11:12:24AM +0800, Xuan Zhuo wrote:
> The virtnet_xdp_handler() is re-used. But
>
> 1. We need to copy data to create skb for XDP_PASS.
> 2. We need to call xsk_buff_free() to release the buffer.
> 3. The handle for xdp_buff is difference.
>
> If we pushed this logic into existing receive handle(merge and small),
> we would have to maintain code scattered inside merge and small (and big).
> So I think it is a good choice for us to put the xsk code into an
> independent function.
>
> Signed-off-by: Xuan Zhuo <xuanzhuo@...ux.alibaba.com>
> ---
> drivers/net/virtio/main.c | 12 ++--
> drivers/net/virtio/virtio_net.h | 4 ++
> drivers/net/virtio/xsk.c | 120 ++++++++++++++++++++++++++++++++
> drivers/net/virtio/xsk.h | 4 ++
> 4 files changed, 135 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/net/virtio/main.c b/drivers/net/virtio/main.c
> index a318b2533b94..095f4acb0577 100644
> --- a/drivers/net/virtio/main.c
> +++ b/drivers/net/virtio/main.c
> @@ -831,10 +831,10 @@ 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;
> @@ -1598,7 +1598,9 @@ static void receive_buf(struct virtnet_info *vi, struct virtnet_rq *rq,
> return;
> }
>
> - if (vi->mergeable_rx_bufs)
> + if (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)
> diff --git a/drivers/net/virtio/virtio_net.h b/drivers/net/virtio/virtio_net.h
> index 2005d0cd22e2..f520fec06662 100644
> --- a/drivers/net/virtio/virtio_net.h
> +++ b/drivers/net/virtio/virtio_net.h
> @@ -339,4 +339,8 @@ void virtnet_tx_pause(struct virtnet_info *vi, struct virtnet_sq *sq);
> void virtnet_tx_resume(struct virtnet_info *vi, struct virtnet_sq *sq);
> void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf);
> void virtnet_rq_free_unused_buf(struct virtqueue *vq, void *buf);
> +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);
> #endif
> diff --git a/drivers/net/virtio/xsk.c b/drivers/net/virtio/xsk.c
> index b09c473c29fb..5c7eb19ab04b 100644
> --- a/drivers/net/virtio/xsk.c
> +++ b/drivers/net/virtio/xsk.c
> @@ -14,6 +14,18 @@ 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;
> @@ -38,6 +50,114 @@ 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;
> + }
> + u64_stats_add(&stats->bytes, len);
> + xsk_buff_free(xdp);
> + }
> +}
> +
> +static struct sk_buff *construct_skb(struct virtnet_rq *rq,
could you name this to virtnet_construct_skb_zc
> + 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);
Please don't.
xsk_buff_pool has ::data_hard_start initialized and you already
initialized ::data and ::data_end within xsk_buff_set_size().
> + xsk_buff_dma_sync_for_cpu(xdp, rq->xsk.pool);
> +
> + ret = XDP_PASS;
> + rcu_read_lock();
We don't need RCU sections for running XDP progs anymore.
> + prog = rcu_dereference(rq->xdp_prog);
> + if (prog)
Prog is always !NULL for ZC case. Just dereference it at the beginning of
rx processing instead of doing it for each buf.
> + 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:
> + u64_stats_inc(&stats->drops);
> +
> + xsk_buff_free(xdp);
> +
> + if (num_buf > 1)
> + merge_drop_follow_xdp(dev, rq, num_buf, stats);
> +consumed:
> + return NULL;
> +}
> +
> int virtnet_add_recvbuf_xsk(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
>
>
Powered by blists - more mailing lists