ipsec: Fix xfrm_state_walk race

As discovered by Timo Teräs, the currently xfrm_state_walk scheme
is racy because if a second dump finishes before the first, we
may free xfrm states that the first dump would walk over later.

This patch fixes this by storing the dumps in a list in order
to calculate the correct completion counter which cures this
problem.

I've expanded netlink_cb in order to accomodate the extra state
related to this.  It shouldn't be a big deal since netlink_cb
is kmalloced for each dump and we're just increasing it by 4 or
8 bytes.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 3 insertions, 7 deletions

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 4bb94992b5fa..48630b266593 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1246,6 +1246,8 @@ struct xfrm6_tunnel {
 };
 
 struct xfrm_state_walk {
+	struct list_head list;
+	unsigned long genid;
 	struct xfrm_state *state;
 	int count;
 	u8 proto;
@@ -1281,13 +1283,7 @@ static inline void xfrm6_fini(void)
 extern int xfrm_proc_init(void);
 #endif
 
-static inline void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto)
-{
-	walk->proto = proto;
-	walk->state = NULL;
-	walk->count = 0;
-}
-
+extern void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto);
 extern int xfrm_state_walk(struct xfrm_state_walk *walk,
 			   int (*func)(struct xfrm_state *, int, void*), void *);
 extern void xfrm_state_walk_done(struct xfrm_state_walk *walk);