From: Paolo Abeni pabeni@redhat.com
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 --- net/mptcp/protocol.c | 11 ++++------- net/mptcp/protocol.h | 2 +- 2 files changed, 5 insertions(+), 8 deletions(-)
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 0292162a14ee..bf2c9e4f3ba9 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -998,7 +998,7 @@ 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); @@ -1543,7 +1543,7 @@ 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) || @@ -1903,7 +1903,7 @@ 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, @@ -2874,7 +2874,7 @@ 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); } @@ -3414,9 +3414,6 @@ 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 52f9cfa4ce95..379a88e14e8d 100644 --- 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)