From: Eric Dumazet <edumazet@kernel.org>
To: "David S . Miller" <davem@davemloft.net>,
Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
Kuniyuki Iwashima <kuniyu@google.com>,
Neal Cardwell <ncardwell@google.com>
Cc: Simon Horman <horms@kernel.org>,
netdev@vger.kernel.org, Eric Dumazet <edumazet@kernel.org>
Subject: [PATCH net-next 3/5] tcp: use SKB_DROP_REASON_SOCKET_RCVBUFF when over sk_rcvbuf
Date: Sat, 14 Nov 2026 16:51:48 +0100 [thread overview]
Message-ID: <20261114155150.235743-4-edumazet@kernel.org> (raw)
In-Reply-To: <20261114155150.235743-1-edumazet@kernel.org>
tcp_data_queue() and tcp_data_queue_ofo() use SKB_DROP_REASON_PROTO_MEM
for all packets that can not be queued, whether the socket is over its
receive buffer, or the protocol memory limits (tcp_mem) are reached.
Make tcp_try_rmem_schedule() return a drop reason:
- SKB_DROP_REASON_SOCKET_RCVBUFF when the socket is over sk_rcvbuf,
as already used by UDP and sock_queue_rcv_skb().
- SKB_DROP_REASON_PROTO_MEM when sk_rmem_schedule() fails.
This helps to identify peers repeatedly sending segments that can not
be queued, with tools like drop monitor or perf.
Signed-off-by: Eric Dumazet <edumazet@kernel.org>
---
net/ipv4/tcp_input.c | 39 ++++++++++++++++++++++++---------------
1 file changed, 24 insertions(+), 15 deletions(-)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 80f8f262bc44..2d8f224f9bf0 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5400,21 +5400,28 @@ static bool tcp_can_ingest(const struct sock *sk, const struct sk_buff *skb)
return rmem <= sk->sk_rcvbuf;
}
-static int tcp_try_rmem_schedule(struct sock *sk, const struct sk_buff *skb,
- unsigned int size)
+/* Return SKB_NOT_DROPPED_YET if @skb can be queued, or the drop reason. */
+static enum skb_drop_reason
+tcp_try_rmem_schedule(struct sock *sk, const struct sk_buff *skb,
+ unsigned int size)
{
- if (!tcp_can_ingest(sk, skb) ||
- !sk_rmem_schedule(sk, skb, size)) {
+ enum skb_drop_reason reason;
- if (tcp_prune_queue(sk, skb) < 0)
- return -1;
+ if (!tcp_can_ingest(sk, skb))
+ reason = SKB_DROP_REASON_SOCKET_RCVBUFF;
+ else if (!sk_rmem_schedule(sk, skb, size))
+ reason = SKB_DROP_REASON_PROTO_MEM;
+ else
+ return SKB_NOT_DROPPED_YET;
- while (!sk_rmem_schedule(sk, skb, size)) {
- if (!tcp_prune_ofo_queue(sk, skb))
- return -1;
- }
+ if (tcp_prune_queue(sk, skb) < 0)
+ return reason;
+
+ while (!sk_rmem_schedule(sk, skb, size)) {
+ if (!tcp_prune_ofo_queue(sk, skb))
+ return SKB_DROP_REASON_PROTO_MEM;
}
- return 0;
+ return SKB_NOT_DROPPED_YET;
}
/* Credit the memory added to the receive queues since @rmem was sampled
@@ -5434,6 +5441,7 @@ static void tcp_collapse_credit_add(struct sock *sk, int rmem)
static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
+ enum skb_drop_reason reason;
struct rb_node **p, *parent;
struct sk_buff *skb1;
u32 seq, end_seq;
@@ -5443,10 +5451,11 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
tcp_save_lrcv_flowlabel(sk, skb);
tcp_data_ecn_check(sk, skb);
- if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) {
+ reason = tcp_try_rmem_schedule(sk, skb, skb->truesize);
+ if (unlikely(reason)) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFODROP);
READ_ONCE(sk->sk_data_ready)(sk);
- tcp_drop_reason(sk, skb, SKB_DROP_REASON_PROTO_MEM);
+ tcp_drop_reason(sk, skb, reason);
return;
}
/* Sampled after tcp_try_rmem_schedule(), which can prune. */
@@ -5716,7 +5725,8 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
/* Ok. In sequence. In window. */
queue_and_out:
- if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) {
+ reason = tcp_try_rmem_schedule(sk, skb, skb->truesize);
+ if (reason) {
/* TODO: maybe ratelimit these WIN 0 ACK ? */
inet_csk(sk)->icsk_ack.pending |=
(ICSK_ACK_NOMEM | ICSK_ACK_NOW);
@@ -5724,7 +5734,6 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
READ_ONCE(sk->sk_data_ready)(sk);
if (skb_queue_len(&sk->sk_receive_queue) && skb->len) {
- reason = SKB_DROP_REASON_PROTO_MEM;
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP);
goto drop;
}
--
2.53.0
next prev parent reply other threads:[~2026-11-14 15:52 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-14 15:51 [PATCH net-next 0/5] tcp: better visibility when receive queues are full Eric Dumazet
2026-11-14 15:51 ` [PATCH net-next 1/5] tcp: add TCPRcvCollapseSkipped counter Eric Dumazet
2026-11-14 16:28 ` Kuniyuki Iwashima
2026-11-14 15:51 ` [PATCH net-next 2/5] selftests/net: packetdrill: add tcp_rcv_collapse_ratelimit.pkt Eric Dumazet
2026-11-14 16:34 ` Kuniyuki Iwashima
2026-11-14 15:51 ` Eric Dumazet [this message]
2026-11-14 16:36 ` [PATCH net-next 3/5] tcp: use SKB_DROP_REASON_SOCKET_RCVBUFF when over sk_rcvbuf Kuniyuki Iwashima
2026-11-14 15:51 ` [PATCH net-next 4/5] net: add SKB_DROP_REASON_MEMCG Eric Dumazet
2026-11-14 16:43 ` Kuniyuki Iwashima
2026-11-14 15:51 ` [PATCH net-next 5/5] selftests/net: packetdrill: add tcp_rcv_collapse.pkt Eric Dumazet
2026-11-14 16:49 ` Kuniyuki Iwashima
2026-11-17 3:17 ` [PATCH net-next 0/5] tcp: better visibility when receive queues are full Jakub Kicinski
2026-11-17 9:21 ` Eric Dumazet
2026-11-17 3:20 ` patchwork-bot+netdevbpf
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=20261114155150.235743-4-edumazet@kernel.org \
--to=edumazet@kernel.org \
--cc=davem@davemloft.net \
--cc=horms@kernel.org \
--cc=kuba@kernel.org \
--cc=kuniyu@google.com \
--cc=ncardwell@google.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.