diff options
| author | Joanne Koong <joannelkoong@gmail.com> | 2022-05-19 17:18:33 -0700 |
|---|---|---|
| committer | Jakub Kicinski <kuba@kernel.org> | 2022-05-20 18:16:24 -0700 |
| commit | d5a42de8bdbe25081f07b801d8b35f4d75a791f4 (patch) | |
| tree | 7bc53e45ea3628a75c25931f9f1d5c7f64d63cd5 /include/net/inet_connection_sock.h | |
| parent | eac67d83bf2553f98cfddd42cfbcfd6f9ccfc287 (diff) | |
| download | lwn-d5a42de8bdbe25081f07b801d8b35f4d75a791f4.tar.gz lwn-d5a42de8bdbe25081f07b801d8b35f4d75a791f4.zip | |
net: Add a second bind table hashed by port and address
We currently have one tcp bind table (bhash) which hashes by port
number only. In the socket bind path, we check for bind conflicts by
traversing the specified port's inet_bind2_bucket while holding the
bucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()).
In instances where there are tons of sockets hashed to the same port
at different addresses, checking for a bind conflict is time-intensive
and can cause softirq cpu lockups, as well as stops new tcp connections
since __inet_inherit_port() also contests for the spinlock.
This patch proposes adding a second bind table, bhash2, that hashes by
port and ip address. Searching the bhash2 table leads to significantly
faster conflict resolution and less time holding the spinlock.
Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'include/net/inet_connection_sock.h')
| -rw-r--r-- | include/net/inet_connection_sock.h | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 85cd695e7fd1..077cd730ce2f 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -25,6 +25,7 @@ #undef INET_CSK_CLEAR_TIMERS struct inet_bind_bucket; +struct inet_bind2_bucket; struct tcp_congestion_ops; /* @@ -57,6 +58,7 @@ struct inet_connection_sock_af_ops { * * @icsk_accept_queue: FIFO of established children * @icsk_bind_hash: Bind node + * @icsk_bind2_hash: Bind node in the bhash2 table * @icsk_timeout: Timeout * @icsk_retransmit_timer: Resend (no ack) * @icsk_rto: Retransmit timeout @@ -83,6 +85,7 @@ struct inet_connection_sock { struct inet_sock icsk_inet; struct request_sock_queue icsk_accept_queue; struct inet_bind_bucket *icsk_bind_hash; + struct inet_bind2_bucket *icsk_bind2_hash; unsigned long icsk_timeout; struct timer_list icsk_retransmit_timer; struct timer_list icsk_delack_timer; |