summaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2008-06-12 23:31:35 (GMT)
committerDavid S. Miller <davem@davemloft.net>2008-06-12 23:34:35 (GMT)
commitec0a196626bd12e0ba108d7daa6d95a4fb25c2c5 (patch)
tree68d9c2923765e12853368e8edb27b241142e0c48 /include
parentf23d60de719e639690b2dc5c2d0e4243ff614b7a (diff)
downloadlinux-ec0a196626bd12e0ba108d7daa6d95a4fb25c2c5.tar.xz
tcp: Revert 'process defer accept as established' changes.
This reverts two changesets, ec3c0982a2dd1e671bad8e9d26c28dcba0039d87 ("[TCP]: TCP_DEFER_ACCEPT updates - process as established") and the follow-on bug fix 9ae27e0adbf471c7a6b80102e38e1d5a346b3b38 ("tcp: Fix slab corruption with ipv6 and tcp6fuzz"). This change causes several problems, first reported by Ingo Molnar as a distcc-over-loopback regression where connections were getting stuck. Ilpo Järvinen first spotted the locking problems. The new function added by this code, tcp_defer_accept_check(), only has the child socket locked, yet it is modifying state of the parent listening socket. Fixing that is non-trivial at best, because we can't simply just grab the parent listening socket lock at this point, because it would create an ABBA deadlock. The normal ordering is parent listening socket --> child socket, but this code path would require the reverse lock ordering. Next is a problem noticed by Vitaliy Gusev, he noted: ---------------------------------------- >--- a/net/ipv4/tcp_timer.c >+++ b/net/ipv4/tcp_timer.c >@@ -481,6 +481,11 @@ static void tcp_keepalive_timer (unsigned long data) > goto death; > } > >+ if (tp->defer_tcp_accept.request && sk->sk_state == TCP_ESTABLISHED) { >+ tcp_send_active_reset(sk, GFP_ATOMIC); >+ goto death; Here socket sk is not attached to listening socket's request queue. tcp_done() will not call inet_csk_destroy_sock() (and tcp_v4_destroy_sock() which should release this sk) as socket is not DEAD. Therefore socket sk will be lost for freeing. ---------------------------------------- Finally, Alexey Kuznetsov argues that there might not even be any real value or advantage to these new semantics even if we fix all of the bugs: ---------------------------------------- Hiding from accept() sockets with only out-of-order data only is the only thing which is impossible with old approach. Is this really so valuable? My opinion: no, this is nothing but a new loophole to consume memory without control. ---------------------------------------- So revert this thing for now. Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'include')
-rw-r--r--include/linux/tcp.h7
-rw-r--r--include/net/request_sock.h4
-rw-r--r--include/net/tcp.h1
3 files changed, 2 insertions, 10 deletions
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 18e62e3..b31b6b7 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -239,11 +239,6 @@ static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req)
return (struct tcp_request_sock *)req;
}
-struct tcp_deferred_accept_info {
- struct sock *listen_sk;
- struct request_sock *request;
-};
-
struct tcp_sock {
/* inet_connection_sock has to be the first member of tcp_sock */
struct inet_connection_sock inet_conn;
@@ -379,8 +374,6 @@ struct tcp_sock {
unsigned int keepalive_intvl; /* time interval between keep alive probes */
int linger2;
- struct tcp_deferred_accept_info defer_tcp_accept;
-
unsigned long last_synq_overflow;
u32 tso_deferred;
diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index b220b5f..0c96e7b 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -115,8 +115,8 @@ struct request_sock_queue {
struct request_sock *rskq_accept_head;
struct request_sock *rskq_accept_tail;
rwlock_t syn_wait_lock;
- u16 rskq_defer_accept;
- /* 2 bytes hole, try to pack */
+ u8 rskq_defer_accept;
+ /* 3 bytes hole, try to pack */
struct listen_sock *listen_opt;
};
diff --git a/include/net/tcp.h b/include/net/tcp.h
index d448310..cf54034 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -139,7 +139,6 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
#define MAX_TCP_KEEPINTVL 32767
#define MAX_TCP_KEEPCNT 127
#define MAX_TCP_SYNCNT 127
-#define MAX_TCP_ACCEPT_DEFERRED 65535
#define TCP_SYNQ_INTERVAL (HZ/5) /* Period of SYNACK timer */