diff options
| author | Eric Dumazet <eric.dumazet@gmail.com> | 2010-05-31 16:41:35 +0200 |
|---|---|---|
| committer | Patrick McHardy <kaber@trash.net> | 2010-05-31 16:41:35 +0200 |
| commit | 7489aec8eed4f2f1eb3b4d35763bd3ea30b32ef5 (patch) | |
| tree | fe2450679dc217183421e606b3912641545596bd /include | |
| parent | c936e8bd1de2fa50c49e3df6fa5036bf07870b67 (diff) | |
netfilter: xtables: stackptr should be percpu
commit f3c5c1bfd4 (netfilter: xtables: make ip_tables reentrant)
introduced a performance regression, because stackptr array is shared by
all cpus, adding cache line ping pongs. (16 cpus share a 64 bytes cache
line)
Fix this using alloc_percpu()
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Acked-By: Jan Engelhardt <jengelh@medozas.de>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Diffstat (limited to 'include')
| -rw-r--r-- | include/linux/netfilter/x_tables.h | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index c00cc0c4d0b..24e5d01d27d 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -397,7 +397,7 @@ struct xt_table_info { * @stacksize jumps (number of user chains) can possibly be made. */ unsigned int stacksize; - unsigned int *stackptr; + unsigned int __percpu *stackptr; void ***jumpstack; /* ipt_entry tables: one per CPU */ /* Note : this field MUST be the last one, see XT_TABLE_INFO_SZ */ |