| 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
| ||
|
Message-Id: <20221220141449.115918-6-hengqi@linux.alibaba.com>
Date: Tue, 20 Dec 2022 22:14:45 +0800
From: Heng Qi <hengqi@...ux.alibaba.com>
To: netdev@...r.kernel.org, bpf@...r.kernel.org
Cc: Jason Wang <jasowang@...hat.com>,
"Michael S . Tsirkin" <mst@...hat.com>,
Paolo Abeni <pabeni@...hat.com>,
Jakub Kicinski <kuba@...nel.org>,
John Fastabend <john.fastabend@...il.com>,
"David S . Miller" <davem@...emloft.net>,
Daniel Borkmann <daniel@...earbox.net>,
Alexei Starovoitov <ast@...nel.org>,
Eric Dumazet <edumazet@...gle.com>,
Xuan Zhuo <xuanzhuo@...ux.alibaba.com>
Subject: [PATCH v2 5/9] virtio_net: construct multi-buffer xdp in mergeable
Build multi-buffer xdp using virtnet_build_xdp_buff_mrg().
For the prefilled buffer before xdp is set, we will probably use
vq reset in the future. At the same time, virtio net currently
uses comp pages, and bpf_xdp_frags_increase_tail() needs to calculate
the tailroom of the last frag, which will involve the offset of the
corresponding page and cause a negative value, so we disable tail
increase by not setting xdp_rxq->frag_size.
Signed-off-by: Heng Qi <hengqi@...ux.alibaba.com>
Reviewed-by: Xuan Zhuo <xuanzhuo@...ux.alibaba.com>
---
drivers/net/virtio_net.c | 60 +++++++++++++++++++++++++++++-----------
1 file changed, 44 insertions(+), 16 deletions(-)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 8fc3b1841d92..40bc58fa57f5 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1018,6 +1018,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
unsigned int *xdp_xmit,
struct virtnet_rq_stats *stats)
{
+ unsigned int tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
struct virtio_net_hdr_mrg_rxbuf *hdr = buf;
u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers);
struct page *page = virt_to_head_page(buf);
@@ -1048,11 +1049,14 @@ 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
@@ -1061,19 +1065,23 @@ 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.
+ /* 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,
@@ -1084,17 +1092,26 @@ 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))) {
+ if ((VIRTIO_XDP_HEADROOM + len + tailroom) > 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++;
@@ -1190,6 +1207,17 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
__free_pages(xdp_page, 0);
goto err_xdp;
}
+err_xdp_frags:
+ shinfo = xdp_get_shared_info_from_buff(&xdp);
+
+ if (unlikely(xdp_page != page))
+ __free_pages(xdp_page, 0);
+
+ 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();
--
2.19.1.6.gb485710b
Powered by blists - more mailing lists