diff options
author | Xin Long <lucien.xin@gmail.com> | 2018-10-17 03:07:51 +0800 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2018-10-18 11:23:47 -0700 |
commit | cd305c74b0f8b49748a79a8f67fc8e5e3e0c4794 (patch) | |
tree | 5e3af28184fb65447c9aaeffa51bfb95f473667a /net | |
parent | 605c0ac182c34867bda71bfbcc74958aabbe2fe0 (diff) |
sctp: use sk_wmem_queued to check for writable space
sk->sk_wmem_queued is used to count the size of chunks in out queue
while sk->sk_wmem_alloc is for counting the size of chunks has been
sent. sctp is increasing both of them before enqueuing the chunks,
and using sk->sk_wmem_alloc to check for writable space.
However, sk_wmem_alloc is also increased by 1 for the skb allocked
for sending in sctp_packet_transmit() but it will not wake up the
waiters when sk_wmem_alloc is decreased in this skb's destructor.
If msg size is equal to sk_sndbuf and sendmsg is waiting for sndbuf,
the check 'msg_len <= sctp_wspace(asoc)' in sctp_wait_for_sndbuf()
will keep waiting if there's a skb allocked in sctp_packet_transmit,
and later even if this skb got freed, the waiting thread will never
get waked up.
This issue has been there since very beginning, so we change to use
sk->sk_wmem_queued to check for writable space as sk_wmem_queued is
not increased for the skb allocked for sending, also as TCP does.
SOCK_SNDBUF_LOCK check is also removed here as it's for tx buf auto
tuning which I will add in another patch.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
-rw-r--r-- | net/sctp/socket.c | 38 |
1 files changed, 9 insertions, 29 deletions
diff --git a/net/sctp/socket.c b/net/sctp/socket.c index c6f29505c34d..111ebd89f0ab 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -83,7 +83,7 @@ #include <net/sctp/stream_sched.h> /* Forward declarations for internal helper functions. */ -static int sctp_writeable(struct sock *sk); +static bool sctp_writeable(struct sock *sk); static void sctp_wfree(struct sk_buff *skb); static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, size_t msg_len); @@ -119,25 +119,10 @@ static void sctp_enter_memory_pressure(struct sock *sk) /* Get the sndbuf space available at the time on the association. */ static inline int sctp_wspace(struct sctp_association *asoc) { - int amt; + struct sock *sk = asoc->base.sk; - if (asoc->ep->sndbuf_policy) - amt = asoc->sndbuf_used; - else - amt = sk_wmem_alloc_get(asoc->base.sk); - - if (amt >= asoc->base.sk->sk_sndbuf) { - if (asoc->base.sk->sk_userlocks & SOCK_SNDBUF_LOCK) - amt = 0; - else { - amt = sk_stream_wspace(asoc->base.sk); - if (amt < 0) - amt = 0; - } - } else { - amt = asoc->base.sk->sk_sndbuf - amt; - } - return amt; + return asoc->ep->sndbuf_policy ? sk->sk_sndbuf - asoc->sndbuf_used + : sk_stream_wspace(sk); } /* Increment the used sndbuf space count of the corresponding association by @@ -1925,10 +1910,10 @@ static int sctp_sendmsg_to_asoc(struct sctp_association *asoc, asoc->pmtu_pending = 0; } - if (sctp_wspace(asoc) < msg_len) + if (sctp_wspace(asoc) < (int)msg_len) sctp_prsctp_prune(asoc, sinfo, msg_len - sctp_wspace(asoc)); - if (!sctp_wspace(asoc)) { + if (sctp_wspace(asoc) <= 0) { timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len); if (err) @@ -8535,7 +8520,7 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, goto do_error; if (signal_pending(current)) goto do_interrupted; - if (msg_len <= sctp_wspace(asoc)) + if ((int)msg_len <= sctp_wspace(asoc)) break; /* Let another process have a go. Since we are going @@ -8610,14 +8595,9 @@ void sctp_write_space(struct sock *sk) * UDP-style sockets or TCP-style sockets, this code should work. * - Daisy */ -static int sctp_writeable(struct sock *sk) +static bool sctp_writeable(struct sock *sk) { - int amt = 0; - - amt = sk->sk_sndbuf - sk_wmem_alloc_get(sk); - if (amt < 0) - amt = 0; - return amt; + return sk->sk_sndbuf > sk->sk_wmem_queued; } /* Wait for an association to go into ESTABLISHED state. If timeout is 0, |