diff mbox series

[net,v3,2/4] tcp: fix tcp_cleanup_rbuf() for tcp_read_skb()

Message ID 20220817195445.151609-3-xiyou.wangcong@gmail.com (mailing list archive)
State Accepted
Commit c457985aaa92e1fda2ce837cabf90bf687b92dcb
Delegated to: Netdev Maintainers
Headers show
Series tcp: some bug fixes for tcp_read_skb() | expand

Checks

Context Check Description
netdev/tree_selection success Clearly marked for net
netdev/fixes_present success Fixes tag present in non-next series
netdev/subject_prefix success Link
netdev/cover_letter success Series has a cover letter
netdev/patch_count success Link
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 342 this patch: 342
netdev/cc_maintainers fail 1 blamed authors not CCed: daniel@iogearbox.net; 6 maintainers not CCed: yoshfuji@linux-ipv6.org davem@davemloft.net daniel@iogearbox.net dsahern@kernel.org kuba@kernel.org pabeni@redhat.com
netdev/build_clang success Errors and warnings before: 5 this patch: 5
netdev/module_param success Was 0 now: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success Fixes tag looks correct
netdev/build_allmodconfig_warn success Errors and warnings before: 342 this patch: 342
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 57 lines checked
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0

Commit Message

Cong Wang Aug. 17, 2022, 7:54 p.m. UTC 
From: Cong Wang <cong.wang@bytedance.com>

tcp_cleanup_rbuf() retrieves the skb from sk_receive_queue, it
assumes the skb is not yet dequeued. This is no longer true for
tcp_read_skb() case where we dequeue the skb first.

Fix this by introducing a helper __tcp_cleanup_rbuf() which does
not require any skb and calling it in tcp_read_skb().

Fixes: 04919bed948d ("tcp: Introduce tcp_read_skb()")
Cc: Eric Dumazet <edumazet@google.com>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
---
 net/ipv4/tcp.c | 24 ++++++++++++++----------
 1 file changed, 14 insertions(+), 10 deletions(-)

Comments

Jakub Sitnicki Aug. 25, 2022, 8:31 a.m. UTC | #1 
On Wed, Aug 17, 2022 at 12:54 PM -07, Cong Wang wrote:
> From: Cong Wang <cong.wang@bytedance.com>
>
> tcp_cleanup_rbuf() retrieves the skb from sk_receive_queue, it
> assumes the skb is not yet dequeued. This is no longer true for
> tcp_read_skb() case where we dequeue the skb first.
>
> Fix this by introducing a helper __tcp_cleanup_rbuf() which does
> not require any skb and calling it in tcp_read_skb().
>
> Fixes: 04919bed948d ("tcp: Introduce tcp_read_skb()")
> Cc: Eric Dumazet <edumazet@google.com>
> Cc: John Fastabend <john.fastabend@gmail.com>
> Cc: Jakub Sitnicki <jakub@cloudflare.com>
> Signed-off-by: Cong Wang <cong.wang@bytedance.com>
> ---
>  net/ipv4/tcp.c | 24 ++++++++++++++----------
>  1 file changed, 14 insertions(+), 10 deletions(-)
>
> diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
> index 05da5cac080b..181a0d350123 100644
> --- a/net/ipv4/tcp.c
> +++ b/net/ipv4/tcp.c
> @@ -1567,17 +1567,11 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len)
>   * calculation of whether or not we must ACK for the sake of
>   * a window update.
>   */
> -void tcp_cleanup_rbuf(struct sock *sk, int copied)
> +static void __tcp_cleanup_rbuf(struct sock *sk, int copied)
>  {
>  	struct tcp_sock *tp = tcp_sk(sk);
>  	bool time_to_ack = false;
>  
> -	struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
> -
> -	WARN(skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq),
> -	     "cleanup rbuf bug: copied %X seq %X rcvnxt %X\n",
> -	     tp->copied_seq, TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt);
> -
>  	if (inet_csk_ack_scheduled(sk)) {
>  		const struct inet_connection_sock *icsk = inet_csk(sk);
>  
> @@ -1623,6 +1617,17 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied)
>  		tcp_send_ack(sk);
>  }
>  
> +void tcp_cleanup_rbuf(struct sock *sk, int copied)
> +{
> +	struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
> +	struct tcp_sock *tp = tcp_sk(sk);
> +
> +	WARN(skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq),
> +	     "cleanup rbuf bug: copied %X seq %X rcvnxt %X\n",
> +	     tp->copied_seq, TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt);
> +	__tcp_cleanup_rbuf(sk, copied);
> +}
> +
>  static void tcp_eat_recv_skb(struct sock *sk, struct sk_buff *skb)
>  {
>  	__skb_unlink(skb, &sk->sk_receive_queue);
> @@ -1771,20 +1776,19 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
>  		copied += used;
>  
>  		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) {
> -			consume_skb(skb);
>  			++seq;
>  			break;
>  		}
> -		consume_skb(skb);
>  		break;
>  	}
> +	consume_skb(skb);
>  	WRITE_ONCE(tp->copied_seq, seq);
>  
>  	tcp_rcv_space_adjust(sk);
>  
>  	/* Clean up data we have read: This will do ACK frames. */
>  	if (copied > 0)
> -		tcp_cleanup_rbuf(sk, copied);
> +		__tcp_cleanup_rbuf(sk, copied);
>  
>  	return copied;
>  }

This seems to be fixing 2 different problems, but the commit description
mentions just one.

consume_skb() got pulled out of the `while' body. And thanks to that we
are not leaving a dangling skb ref if recv_actor, sk_psock_verdict_recv
in this case, returns 0.
diff mbox series

Patch

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 05da5cac080b..181a0d350123 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1567,17 +1567,11 @@  static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len)
  * calculation of whether or not we must ACK for the sake of
  * a window update.
  */
-void tcp_cleanup_rbuf(struct sock *sk, int copied)
+static void __tcp_cleanup_rbuf(struct sock *sk, int copied)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	bool time_to_ack = false;
 
-	struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
-
-	WARN(skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq),
-	     "cleanup rbuf bug: copied %X seq %X rcvnxt %X\n",
-	     tp->copied_seq, TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt);
-
 	if (inet_csk_ack_scheduled(sk)) {
 		const struct inet_connection_sock *icsk = inet_csk(sk);
 
@@ -1623,6 +1617,17 @@  void tcp_cleanup_rbuf(struct sock *sk, int copied)
 		tcp_send_ack(sk);
 }
 
+void tcp_cleanup_rbuf(struct sock *sk, int copied)
+{
+	struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	WARN(skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq),
+	     "cleanup rbuf bug: copied %X seq %X rcvnxt %X\n",
+	     tp->copied_seq, TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt);
+	__tcp_cleanup_rbuf(sk, copied);
+}
+
 static void tcp_eat_recv_skb(struct sock *sk, struct sk_buff *skb)
 {
 	__skb_unlink(skb, &sk->sk_receive_queue);
@@ -1771,20 +1776,19 @@  int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 		copied += used;
 
 		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) {
-			consume_skb(skb);
 			++seq;
 			break;
 		}
-		consume_skb(skb);
 		break;
 	}
+	consume_skb(skb);
 	WRITE_ONCE(tp->copied_seq, seq);
 
 	tcp_rcv_space_adjust(sk);
 
 	/* Clean up data we have read: This will do ACK frames. */
 	if (copied > 0)
-		tcp_cleanup_rbuf(sk, copied);
+		__tcp_cleanup_rbuf(sk, copied);
 
 	return copied;
 }