Netdev List
 help / color / mirror / Atom feed
From: Mahanta Jambigi <mjambigi@linux.ibm.com>
To: andrew+netdev@lunn.ch, davem@davemloft.net, edumazet@google.com,
	kuba@kernel.org, pabeni@redhat.com, alibuda@linux.alibaba.com,
	dust.li@linux.alibaba.com, sidraya@linux.ibm.com
Cc: hidayath@linux.ibm.com, pasic@linux.ibm.com, horms@kernel.org,
	tonylu@linux.alibaba.com, guwen@linux.alibaba.com,
	stable@vger.kernel.org, netdev@vger.kernel.org,
	linux-s390@vger.kernel.org, linux-rdma@vger.kernel.org,
	Mahanta Jambigi <mjambigi@linux.ibm.com>
Subject: [PATCH net] net/smc: fix handshake abort on a terminating link group
Date: Tue,  3 Nov 2026 13:39:55 +0100	[thread overview]
Message-ID: <20261103123955.47454-1-mjambigi@linux.ibm.com> (raw)

The handshake abort path can leave a connection that smc_conn_free()
already freed in lgr->conns_all: when a received first-contact CLC
DECLINE has already scheduled the link group termination and emptied
lgr->list, smc_conn_free() skips the unregister. The handshake thread
then calls smc_lgr_cleanup_early() on a link group that is already being
terminated, and __smc_lgr_terminate() hangs on the socket lock that
thread already holds; if the termination work wins the race instead, it
later kills the freed connection and aborts the clcsock of a socket that
has fallen back to TCP.

Do not terminate a link group that another context has already removed
from the link group list, and drop an already freed connection in
smc_conn_kill() without running the connection and socket teardown.

Fixes: 2a0674fffb6b ("net/smc: improve abnormal termination of link groups")
Fixes: f9aab6f2ce57 ("net/smc: immediate freeing in smc_lgr_cleanup_early()")
Cc: stable@vger.kernel.org
Signed-off-by: Mahanta Jambigi <mjambigi@linux.ibm.com>
---
 net/smc/smc_core.c | 21 +++++++++++++++++++--
 1 file changed, 19 insertions(+), 2 deletions(-)

diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 6021322253e9..df2ab2da2793 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -688,9 +688,15 @@ void smc_lgr_cleanup_early(struct smc_link_group *lgr)

 	smc_lgr_list_head(lgr, &lgr_lock);
 	spin_lock_bh(lgr_lock);
+	if (list_empty(&lgr->list)) {
+		/* another context already removed the link group from the
+		 * list and will terminate it
+		 */
+		spin_unlock_bh(lgr_lock);
+		return;
+	}
 	/* do not use this link group for new connections */
-	if (!list_empty(&lgr->list))
-		list_del_init(&lgr->list);
+	list_del_init(&lgr->list);
 	spin_unlock_bh(lgr_lock);
 	__smc_lgr_terminate(lgr, true);
 }
@@ -1519,6 +1525,17 @@ static void smc_conn_kill(struct smc_connection *conn, bool soft)
 {
 	struct smc_sock *smc = container_of(conn, struct smc_sock, conn);

+	if (conn->freed) {
+		/* connection was already freed, e.g. by an aborted
+		 * handshake, but kept its entry because smc_conn_free() skips
+		 * the unregister for a link group that is no longer on the lgr
+		 * list. Remove the stale entry, but do not kill a socket that
+		 * may be an established fallback connection.
+		 */
+		smc_lgr_unregister_conn(conn);
+		return;
+	}
+
 	if (conn->lgr->is_smcd && conn->lgr->peer_shutdown)
 		conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1;
 	else

             reply	other threads:[~2026-11-03 12:40 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-03 12:39 Mahanta Jambigi [this message]
2026-11-03 12:44 ` [PATCH net] net/smc: fix handshake abort on a terminating link group netdev-bot+sinfo
2026-11-06  0:40 ` netdev-bot+sashiko
2026-11-06 13:06   ` Mahanta Jambigi

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=20261103123955.47454-1-mjambigi@linux.ibm.com \
    --to=mjambigi@linux.ibm.com \
    --cc=alibuda@linux.alibaba.com \
    --cc=andrew+netdev@lunn.ch \
    --cc=davem@davemloft.net \
    --cc=dust.li@linux.alibaba.com \
    --cc=edumazet@google.com \
    --cc=guwen@linux.alibaba.com \
    --cc=hidayath@linux.ibm.com \
    --cc=horms@kernel.org \
    --cc=kuba@kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=linux-s390@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=pasic@linux.ibm.com \
    --cc=sidraya@linux.ibm.com \
    --cc=stable@vger.kernel.org \
    --cc=tonylu@linux.alibaba.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox