mptcp: drop bogus optimization in __mptcp_check_push()

commit 27b0e701d3872ba59c5b579a9e8a02ea49ad3d3b upstream.

Accessing the transmit queue without owning the msk socket lock is
inherently racy, hence __mptcp_check_push() could actually quit early
even when there is pending data.

That in turn could cause unexpected tx lock and timeout.

Dropping the early check avoids the race, implicitly relaying on later
tests under the relevant lock. With such change, all the other
mptcp_send_head() call sites are now under the msk socket lock and we
can additionally drop the now unneeded annotation on the transmit head
pointer accesses.

Fixes: 6e628cd3a8f7 ("mptcp: use mptcp release_cb for delayed tasks")
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Geliang Tang <geliang@kernel.org>
Tested-by: Geliang Tang <geliang@kernel.org>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20251028-net-mptcp-send-timeout-v1-1-38ffff5a9ec8@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 5e497a83e9675b5217052299463c1dfc58de947c..9801cb077293429a373335ddf57dcb5722daa924 100644 (file)
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -965,7 +965,7 @@ static void __mptcp_clean_una(struct sock *sk)
                        if (WARN_ON_ONCE(!msk->recovery))
                                break;
 
-                       WRITE_ONCE(msk->first_pending, mptcp_send_next(sk));
+                       msk->first_pending = mptcp_send_next(sk);
                }
 
                dfrag_clear(sk, dfrag);
@@ -1510,7 +1510,7 @@ static int __subflow_push_pending(struct sock *sk, struct sock *ssk,
 
                        mptcp_update_post_push(msk, dfrag, ret);
                }
-               WRITE_ONCE(msk->first_pending, mptcp_send_next(sk));
+               msk->first_pending = mptcp_send_next(sk);
 
                if (msk->snd_burst <= 0 ||
                    !sk_stream_memory_free(ssk) ||
@@ -1854,7 +1854,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
                        get_page(dfrag->page);
                        list_add_tail(&dfrag->list, &msk->rtx_queue);
                        if (!msk->first_pending)
-                               WRITE_ONCE(msk->first_pending, dfrag);
+                               msk->first_pending = dfrag;
                }
                pr_debug("msk=%p dfrag at seq=%llu len=%u sent=%u new=%d\n", msk,
                         dfrag->data_seq, dfrag->data_len, dfrag->already_sent,
@@ -2854,7 +2854,7 @@ static void __mptcp_clear_xmit(struct sock *sk)
        struct mptcp_sock *msk = mptcp_sk(sk);
        struct mptcp_data_frag *dtmp, *dfrag;
 
-       WRITE_ONCE(msk->first_pending, NULL);
+       msk->first_pending = NULL;
        list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list)
                dfrag_clear(sk, dfrag);
 }
@@ -3394,9 +3394,6 @@ void __mptcp_data_acked(struct sock *sk)
 
 void __mptcp_check_push(struct sock *sk, struct sock *ssk)
 {
-       if (!mptcp_send_head(sk))
-               return;
-
        if (!sock_owned_by_user(sk))
                __mptcp_subflow_push_pending(sk, ssk, false);
        else

diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 245428e23161960c366fc5784c5c49ea8bc44010..f96f1ccde93e3cbecc9775c102eed854374a3b1a 100644 (file)
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -414,7 +414,7 @@ static inline struct mptcp_data_frag *mptcp_send_head(const struct sock *sk)
 {
        const struct mptcp_sock *msk = mptcp_sk(sk);
 
-       return READ_ONCE(msk->first_pending);
+       return msk->first_pending;
 }
 
 static inline struct mptcp_data_frag *mptcp_send_next(struct sock *sk)