netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jason Xing <kerneljasonxing@gmail.com>
To: davem@davemloft.net, edumazet@google.com, kuba@kernel.org,
	pabeni@redhat.com, bjorn@kernel.org, magnus.karlsson@intel.com,
	maciej.fijalkowski@intel.com, jonathan.lemon@gmail.com,
	sdf@fomichev.me, ast@kernel.org, daniel@iogearbox.net,
	hawk@kernel.org, john.fastabend@gmail.com, horms@kernel.org,
	andrew+netdev@lunn.ch
Cc: bpf@vger.kernel.org, netdev@vger.kernel.org,
	Jason Xing <kernelxing@tencent.com>
Subject: [PATCH net-next v2 8/9] xsk: support generic batch xmit in copy mode
Date: Mon, 25 Aug 2025 21:53:41 +0800	[thread overview]
Message-ID: <20250825135342.53110-9-kerneljasonxing@gmail.com> (raw)
In-Reply-To: <20250825135342.53110-1-kerneljasonxing@gmail.com>

From: Jason Xing <kernelxing@tencent.com>

- Move xs->mutex into xsk_generic_xmit to prevent race condition when
  application manipulates generic_xmit_batch simultaneously.
- Enable batch xmit eventually.

Make the whole feature work eventually.

Signed-off-by: Jason Xing <kernelxing@tencent.com>
---
 net/xdp/xsk.c | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 90089a6e78b2..34fd54ad4768 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -803,8 +803,6 @@ static int __xsk_generic_xmit_batch(struct xdp_sock *xs)
 	u32 max_batch, expected;
 	int err = 0;
 
-	mutex_lock(&xs->mutex);
-
 	/* Since we dropped the RCU read lock, the socket state might have changed. */
 	if (unlikely(!xsk_is_bound(xs))) {
 		err = -ENXIO;
@@ -902,21 +900,17 @@ static int __xsk_generic_xmit_batch(struct xdp_sock *xs)
 	if (sent_frame)
 		__xsk_tx_release(xs);
 
-	mutex_unlock(&xs->mutex);
 	return err;
 }
 
-static int __xsk_generic_xmit(struct sock *sk)
+static int __xsk_generic_xmit(struct xdp_sock *xs)
 {
-	struct xdp_sock *xs = xdp_sk(sk);
 	bool sent_frame = false;
 	struct xdp_desc desc;
 	struct sk_buff *skb;
 	u32 max_batch;
 	int err = 0;
 
-	mutex_lock(&xs->mutex);
-
 	/* Since we dropped the RCU read lock, the socket state might have changed. */
 	if (unlikely(!xsk_is_bound(xs))) {
 		err = -ENXIO;
@@ -991,17 +985,22 @@ static int __xsk_generic_xmit(struct sock *sk)
 	if (sent_frame)
 		__xsk_tx_release(xs);
 
-	mutex_unlock(&xs->mutex);
 	return err;
 }
 
 static int xsk_generic_xmit(struct sock *sk)
 {
+	struct xdp_sock *xs = xdp_sk(sk);
 	int ret;
 
 	/* Drop the RCU lock since the SKB path might sleep. */
 	rcu_read_unlock();
-	ret = __xsk_generic_xmit(sk);
+	mutex_lock(&xs->mutex);
+	if (xs->generic_xmit_batch)
+		ret = __xsk_generic_xmit_batch(xs);
+	else
+		ret = __xsk_generic_xmit(xs);
+	mutex_unlock(&xs->mutex);
 	/* Reaquire RCU lock before going into common code. */
 	rcu_read_lock();
 
-- 
2.41.3


  parent reply	other threads:[~2025-08-25 13:54 UTC|newest]

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-08-25 13:53 [PATCH net-next v2 0/9] xsk: improvement performance in copy mode Jason Xing
2025-08-25 13:53 ` [PATCH net-next v2 1/9] xsk: introduce XDP_GENERIC_XMIT_BATCH setsockopt Jason Xing
2025-08-25 13:53 ` [PATCH net-next v2 2/9] xsk: add descs parameter in xskq_cons_read_desc_batch() Jason Xing
2025-08-25 21:18   ` Maciej Fijalkowski
2025-08-26  0:10     ` Jason Xing
2025-08-25 13:53 ` [PATCH net-next v2 3/9] xsk: introduce locked version of xskq_prod_write_addr_batch Jason Xing
2025-08-25 21:42   ` Maciej Fijalkowski
2025-08-26  0:13     ` Jason Xing
2025-08-25 13:53 ` [PATCH net-next v2 4/9] xsk: extend xsk_build_skb() to support passing an already allocated skb Jason Xing
2025-08-25 21:49   ` Maciej Fijalkowski
2025-08-26  0:26     ` Jason Xing
2025-08-25 13:53 ` [PATCH net-next v2 5/9] xsk: add xsk_alloc_batch_skb() to build skbs in batch Jason Xing
2025-08-25 16:56   ` kernel test robot
2025-08-27 14:32   ` Alexander Lobakin
2025-08-28  0:38     ` Jason Xing
2025-08-28 15:28       ` Alexander Lobakin
2025-08-29  0:31         ` Jason Xing
2025-08-25 13:53 ` [PATCH net-next v2 6/9] xsk: add direct xmit in batch function Jason Xing
2025-08-25 17:34   ` Stanislav Fomichev
2025-08-26  0:27     ` Jason Xing
2025-08-25 13:53 ` [PATCH net-next v2 7/9] xsk: support batch xmit main logic Jason Xing
2025-08-25 13:53 ` Jason Xing [this message]
2025-08-25 13:53 ` [PATCH net-next v2 9/9] xsk: support dynamic xmit.more control for batch xmit Jason Xing
2025-08-25 17:44 ` [PATCH net-next v2 0/9] xsk: improvement performance in copy mode Jakub Kicinski
2025-08-26  0:01   ` Jason Xing
2025-08-26  0:29     ` Jakub Kicinski
2025-08-26  0:51       ` Jason Xing
2025-08-26  1:15         ` Jakub Kicinski
2025-08-26  1:49           ` Jason Xing
2025-08-25 21:15 ` Maciej Fijalkowski
2025-08-26  0:06   ` Jason Xing

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=20250825135342.53110-9-kerneljasonxing@gmail.com \
    --to=kerneljasonxing@gmail.com \
    --cc=andrew+netdev@lunn.ch \
    --cc=ast@kernel.org \
    --cc=bjorn@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=hawk@kernel.org \
    --cc=horms@kernel.org \
    --cc=john.fastabend@gmail.com \
    --cc=jonathan.lemon@gmail.com \
    --cc=kernelxing@tencent.com \
    --cc=kuba@kernel.org \
    --cc=maciej.fijalkowski@intel.com \
    --cc=magnus.karlsson@intel.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=sdf@fomichev.me \
    /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).