From 7489aec8eed4f2f1eb3b4d35763bd3ea30b32ef5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Mon, 31 May 2010 16:41:35 +0200
Subject: 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>
---
 include/linux/netfilter/x_tables.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

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 */
-- 
cgit v1.2.2


From b1faf5666438090a4dc4fceac8502edc7788b7e3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Mon, 31 May 2010 23:44:05 -0700
Subject: net: sock_queue_err_skb() dont mess with sk_forward_alloc

Correct sk_forward_alloc handling for error_queue would need to use a
backlog of frames that softirq handler could not deliver because socket
is owned by user thread. Or extend backlog processing to be able to
process normal and error packets.

Another possibility is to not use mem charge for error queue, this is
what I implemented in this patch.

Note: this reverts commit 29030374
(net: fix sk_forward_alloc corruptions), since we dont need to lock
socket anymore.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 15 +--------------
 1 file changed, 1 insertion(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index ca241ea14875..731150d52799 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1524,20 +1524,7 @@ extern void sk_stop_timer(struct sock *sk, struct timer_list* timer);
 
 extern int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
 
-static inline int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
-{
-	/* Cast skb->rcvbuf to unsigned... It's pointless, but reduces
-	   number of warnings when compiling with -W --ANK
-	 */
-	if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
-	    (unsigned)sk->sk_rcvbuf)
-		return -ENOMEM;
-	skb_set_owner_r(skb, sk);
-	skb_queue_tail(&sk->sk_error_queue, skb);
-	if (!sock_flag(sk, SOCK_DEAD))
-		sk->sk_data_ready(sk, skb->len);
-	return 0;
-}
+extern int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb);
 
 /*
  *	Recover an error report and clear atomically
-- 
cgit v1.2.2


From 8764ab2ca7ab5055e1ca80f9cfa4970c34acb804 Mon Sep 17 00:00:00 2001
From: Steffen Klassert <steffen.klassert@secunet.com>
Date: Fri, 4 Jun 2010 01:57:38 +0000
Subject: net: check for refcount if pop a stacked dst_entry

xfrm triggers a warning if dst_pop() drops a refcount
on a noref dst. This patch changes dst_pop() to
skb_dst_pop(). skb_dst_pop() drops the refcnt only
on a refcounted dst. Also we don't clone the child
dst_entry, so it is not refcounted and we can use
skb_dst_set_noref() in xfrm_output_one().

Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/dst.h b/include/net/dst.h
index 612069beda73..81d1413a8701 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -250,11 +250,11 @@ static inline void skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev)
  * Linux networking.  Thus, destinations are stackable.
  */
 
-static inline struct dst_entry *dst_pop(struct dst_entry *dst)
+static inline struct dst_entry *skb_dst_pop(struct sk_buff *skb)
 {
-	struct dst_entry *child = dst_clone(dst->child);
+	struct dst_entry *child = skb_dst(skb)->child;
 
-	dst_release(dst);
+	skb_dst_drop(skb);
 	return child;
 }
 
-- 
cgit v1.2.2