Messages in this thread Patch in this message | | | Date | Fri, 22 Oct 2010 11:35:09 -0700 | From | Greg KH <> | Subject | [42/66] tcp: Fix race in tcp_poll |
| |
2.6.32-stable review patch. If anyone has any objections, please let us know.
------------------
From: Tom Marshall <tdm.code@gmail.com>
[ Upstream commit a4d258036ed9b2a1811c3670c6099203a0f284a0 ]
If a RST comes in immediately after checking sk->sk_err, tcp_poll will return POLLIN but not POLLOUT. Fix this by checking sk->sk_err at the end of tcp_poll. Additionally, ensure the correct order of operations on SMP machines with memory barriers.
Signed-off-by: Tom Marshall <tdm.code@gmail.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de> --- net/ipv4/tcp.c | 7 +++++-- net/ipv4/tcp_input.c | 2 ++ 2 files changed, 7 insertions(+), 2 deletions(-)
--- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -386,8 +386,6 @@ unsigned int tcp_poll(struct file *file, */ mask = 0; - if (sk->sk_err) - mask = POLLERR; /* * POLLHUP is certainly not done right. But poll() doesn't @@ -457,6 +455,11 @@ unsigned int tcp_poll(struct file *file, if (tp->urg_data & TCP_URG_VALID) mask |= POLLPRI; } + /* This barrier is coupled with smp_wmb() in tcp_reset() */ + smp_rmb(); + if (sk->sk_err) + mask |= POLLERR; + return mask; } --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3969,6 +3969,8 @@ static void tcp_reset(struct sock *sk) default: sk->sk_err = ECONNRESET; } + /* This barrier is coupled with smp_rmb() in tcp_poll() */ + smp_wmb(); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_error_report(sk);
| |