Eric Dumazet
22a0e18eac
net: properly release sk_frag.page
...
I mistakenly added the code to release sk->sk_frag in
sk_common_release() instead of sk_destruct()
TCP sockets using sk->sk_allocation == GFP_ATOMIC do no call
sk_common_release() at close time, thus leaking one (order-3) page.
iSCSI is using such sockets.
Fixes: 5640f76858 ("net: use a per task frag allocator")
Signed-off-by: Eric Dumazet <edumazet@google.com >
Signed-off-by: David S. Miller <davem@davemloft.net >
2017-03-15 15:37:45 -07:00
..
2017-02-07 11:19:00 -05:00
2014-11-18 15:26:32 -05:00
2014-11-18 15:27:32 -05:00
2017-03-14 11:33:44 -07:00
2017-02-10 14:43:00 -05:00
2017-01-03 11:09:44 -05:00
2016-03-18 17:45:08 -04:00
2017-02-07 13:07:47 -05:00
2017-03-02 08:42:32 +01:00
2016-11-09 13:28:10 -05:00
2017-02-23 13:53:42 -05:00
2017-01-16 13:48:48 -05:00
2016-12-12 19:25:04 -08:00
2016-12-24 11:46:01 -08:00
2016-12-05 15:21:59 -05:00
2017-02-08 14:38:18 -05:00
2016-05-25 12:35:09 -07:00
2015-04-02 14:04:59 -04:00
2017-01-30 15:14:22 -05:00
2017-01-30 15:14:22 -05:00
2017-02-08 14:38:18 -05:00
2017-02-15 12:38:43 -05:00
2017-03-02 08:42:38 +01:00
2016-04-26 15:53:05 -04:00
2017-03-13 16:02:27 -07:00
2014-01-05 20:27:54 -05:00
2015-11-22 11:54:10 -05:00
2017-03-02 08:42:38 +01:00
2015-05-31 00:03:21 -07:00
2016-11-16 18:32:02 -05:00
2017-03-02 08:42:38 +01:00
2017-01-08 20:58:52 -05:00
2015-11-03 11:08:22 -05:00
2016-12-29 11:38:31 -05:00
2017-02-21 12:17:43 -05:00
2017-03-02 08:42:29 +01:00
2017-01-12 15:57:10 -05:00
2017-03-07 14:06:15 -08:00
2016-04-26 12:00:48 -04:00
2016-10-18 14:18:23 -04:00
2017-03-15 15:37:45 -07:00
2017-03-02 08:42:29 +01:00
2017-02-17 13:40:05 -05:00
2015-07-09 14:17:15 -07:00
2015-10-26 22:24:22 -07:00
2016-12-24 11:46:01 -08:00