diff options
Diffstat (limited to 'net/mptcp/protocol.c')
-rw-r--r-- | net/mptcp/protocol.c | 67 |
1 files changed, 47 insertions, 20 deletions
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 88f2a7a0ccb8..eaa61e227492 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -466,6 +466,18 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, struct tcp_sock *tp; u32 old_copied_seq; bool done = false; + int sk_rbuf; + + sk_rbuf = READ_ONCE(sk->sk_rcvbuf); + + if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { + int ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf); + + if (unlikely(ssk_rbuf > sk_rbuf)) { + WRITE_ONCE(sk->sk_rcvbuf, ssk_rbuf); + sk_rbuf = ssk_rbuf; + } + } pr_debug("msk=%p ssk=%p", msk, ssk); tp = tcp_sk(ssk); @@ -528,7 +540,7 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, WRITE_ONCE(tp->copied_seq, seq); more_data_avail = mptcp_subflow_data_available(ssk); - if (atomic_read(&sk->sk_rmem_alloc) > READ_ONCE(sk->sk_rcvbuf)) { + if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf) { done = true; break; } @@ -622,6 +634,7 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct mptcp_sock *msk = mptcp_sk(sk); + int sk_rbuf, ssk_rbuf; bool wake; /* move_skbs_to_msk below can legitly clear the data_avail flag, @@ -632,12 +645,16 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) if (wake) set_bit(MPTCP_DATA_READY, &msk->flags); - if (atomic_read(&sk->sk_rmem_alloc) < READ_ONCE(sk->sk_rcvbuf) && - move_skbs_to_msk(msk, ssk)) + ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf); + sk_rbuf = READ_ONCE(sk->sk_rcvbuf); + if (unlikely(ssk_rbuf > sk_rbuf)) + sk_rbuf = ssk_rbuf; + + /* over limit? can't append more skbs to msk */ + if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf) goto wake; - /* don't schedule if mptcp sk is (still) over limit */ - if (atomic_read(&sk->sk_rmem_alloc) > READ_ONCE(sk->sk_rcvbuf)) + if (move_skbs_to_msk(msk, ssk)) goto wake; /* mptcp socket is owned, release_cb should retry */ @@ -754,8 +771,11 @@ static bool mptcp_skb_can_collapse_to(u64 write_seq, if (!tcp_skb_can_collapse_to(skb)) return false; - /* can collapse only if MPTCP level sequence is in order */ - return mpext && mpext->data_seq + mpext->data_len == write_seq; + /* can collapse only if MPTCP level sequence is in order and this + * mapping has not been xmitted yet + */ + return mpext && mpext->data_seq + mpext->data_len == write_seq && + !mpext->frozen; } static bool mptcp_frag_can_collapse_to(const struct mptcp_sock *msk, @@ -833,19 +853,25 @@ static void mptcp_clean_una(struct sock *sk) } out: - if (cleaned) { + if (cleaned) sk_mem_reclaim_partial(sk); +} - /* Only wake up writers if a subflow is ready */ - if (mptcp_is_writeable(msk)) { - set_bit(MPTCP_SEND_SPACE, &mptcp_sk(sk)->flags); - smp_mb__after_atomic(); +static void mptcp_clean_una_wakeup(struct sock *sk) +{ + struct mptcp_sock *msk = mptcp_sk(sk); - /* set SEND_SPACE before sk_stream_write_space clears - * NOSPACE - */ - sk_stream_write_space(sk); - } + mptcp_clean_una(sk); + + /* Only wake up writers if a subflow is ready */ + if (mptcp_is_writeable(msk)) { + set_bit(MPTCP_SEND_SPACE, &msk->flags); + smp_mb__after_atomic(); + + /* set SEND_SPACE before sk_stream_write_space clears + * NOSPACE + */ + sk_stream_write_space(sk); } } @@ -1476,13 +1502,14 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk) __mptcp_flush_join_list(msk); do { struct sock *ssk = mptcp_subflow_recv_lookup(msk); + bool slowpath; if (!ssk) break; - lock_sock(ssk); + slowpath = lock_sock_fast(ssk); done = __mptcp_move_skbs_from_subflow(msk, ssk, &moved); - release_sock(ssk); + unlock_sock_fast(ssk, slowpath); } while (!done); if (mptcp_ofo_queue(msk) || moved > 0) { @@ -1748,7 +1775,7 @@ static void mptcp_worker(struct work_struct *work) long timeo = 0; lock_sock(sk); - mptcp_clean_una(sk); + mptcp_clean_una_wakeup(sk); mptcp_check_data_fin_ack(sk); __mptcp_flush_join_list(msk); if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) |