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>

1 files changed, 1 insertions, 1 deletions

diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index c00cc0c4d0b7..24e5d01d27d0 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 */