ipv4: Restore old dst_free() behavior.

commit 404e0a8b6a55 (net: ipv4: fix RCU races on dst refcounts) tried
to solve a race but added a problem at device/fib dismantle time :

We really want to call dst_free() as soon as possible, even if sockets
still have dst in their cache.
dst_release() calls in free_fib_info_rcu() are not welcomed.

Root of the problem was that now we also cache output routes (in
nh_rth_output), we must use call_rcu() instead of call_rcu_bh() in
rt_free(), because output route lookups are done in process context.

Based on feedback and initial patch from David Miller (adding another
call_rcu_bh() call in fib, but it appears it was not the right fix)

I left the inet_sk_rx_dst_set() helper and added __rcu attributes
to nh_rth_output and nh_rth_input to better document what is going on in
this code.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 5 insertions, 21 deletions

diff --git a/net/core/dst.c b/net/core/dst.c
index d9e33ebe..069d51d 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -258,15 +258,6 @@ again:
 }
 EXPORT_SYMBOL(dst_destroy);
 
-static void dst_rcu_destroy(struct rcu_head *head)
-{
-	struct dst_entry *dst = container_of(head, struct dst_entry, rcu_head);
-
-	dst = dst_destroy(dst);
-	if (dst)
-		__dst_free(dst);
-}
-
 void dst_release(struct dst_entry *dst)
 {
 	if (dst) {
@@ -274,14 +265,10 @@ void dst_release(struct dst_entry *dst)
 
 		newrefcnt = atomic_dec_return(&dst->__refcnt);
 		WARN_ON(newrefcnt < 0);
-		if (unlikely(dst->flags & (DST_NOCACHE | DST_RCU_FREE)) && !newrefcnt) {
-			if (dst->flags & DST_RCU_FREE) {
-				call_rcu_bh(&dst->rcu_head, dst_rcu_destroy);
-			} else {
-				dst = dst_destroy(dst);
-				if (dst)
-					__dst_free(dst);
-			}
+		if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt) {
+			dst = dst_destroy(dst);
+			if (dst)
+				__dst_free(dst);
 		}
 	}
 }
@@ -333,14 +320,11 @@ EXPORT_SYMBOL(__dst_destroy_metrics_generic);
  */
 void skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst)
 {
-	bool hold;
-
 	WARN_ON(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
 	/* If dst not in cache, we must take a reference, because
 	 * dst_release() will destroy dst as soon as its refcount becomes zero
 	 */
-	hold = (dst->flags & (DST_NOCACHE | DST_RCU_FREE)) == DST_NOCACHE;
-	if (unlikely(hold)) {
+	if (unlikely(dst->flags & DST_NOCACHE)) {
 		dst_hold(dst);
 		skb_dst_set(skb, dst);
 	} else {