dst: no need to take reference on DST_NOCACHE dsts

Since commit f8864972126899 ("ipv4: fix dst race in sk_dst_get()")
DST_NOCACHE dst_entries get freed by RCU. So there is no need to get a
reference on them when we are in rcu protected sections.

Cc: Eric Dumazet <edumazet@google.com>
Cc: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Reviewed-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index e9281b5b7f597f4401dac640ed73e7618c90e281..ef64cec42804d8bde1dd081825908f119ba347c9 100644 (file)
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -717,9 +717,6 @@ static inline void skb_dst_set(struct sk_buff *skb, struct dst_entry *dst)
        skb->_skb_refdst = (unsigned long)dst;
 }
 
-void __skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst,
-                        bool force);
-
 /**
  * skb_dst_set_noref - sets skb dst, hopefully, without taking reference
  * @skb: buffer
@@ -732,24 +729,8 @@ void __skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst,
  */
 static inline void skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst)
 {
-       __skb_dst_set_noref(skb, dst, false);
-}
-
-/**
- * skb_dst_set_noref_force - sets skb dst, without taking reference
- * @skb: buffer
- * @dst: dst entry
- *
- * Sets skb dst, assuming a reference was not taken on dst.
- * No reference is taken and no dst_release will be called. While for
- * cached dsts deferred reclaim is a basic feature, for entries that are
- * not cached it is caller's job to guarantee that last dst_release for
- * provided dst happens when nobody uses it, eg. after a RCU grace period.
- */
-static inline void skb_dst_set_noref_force(struct sk_buff *skb,
-                                          struct dst_entry *dst)
-{
-       __skb_dst_set_noref(skb, dst, true);
+       WARN_ON(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
+       skb->_skb_refdst = (unsigned long)dst | SKB_DST_NOREF;
 }
 
 /**

diff --git a/net/core/dst.c b/net/core/dst.c
index a028409ee438c27d738deb1b065269a441a0f5f3..e956ce6d13782f2da0a229cabafef663665159eb 100644 (file)
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -327,30 +327,6 @@ void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old)
 }
 EXPORT_SYMBOL(__dst_destroy_metrics_generic);
 
-/**
- * __skb_dst_set_noref - sets skb dst, without a reference
- * @skb: buffer
- * @dst: dst entry
- * @force: if force is set, use noref version even for DST_NOCACHE entries
- *
- * Sets skb dst, assuming a reference was not taken on dst
- * skb_dst_drop() should not dst_release() this dst
- */
-void __skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst, bool force)
-{
-       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
-        */
-       if (unlikely((dst->flags & DST_NOCACHE) && !force)) {
-               dst_hold(dst);
-               skb_dst_set(skb, dst);
-       } else {
-               skb->_skb_refdst = (unsigned long)dst | SKB_DST_NOREF;
-       }
-}
-EXPORT_SYMBOL(__skb_dst_set_noref);
-
 /* Dirty hack. We did it in 2.2 (in __dst_free),
  * we have _very_ good reasons not to repeat
  * this mistake in 2.3, but we have no choice

diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 1f933136155a321b9f082eb8837eb1b79ef44c03..3aedbda7658a4fbbbd54fcc683a09f089ffe6de5 100644 (file)
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -343,7 +343,7 @@ __ip_vs_get_out_rt(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
        skb_dst_drop(skb);
        if (noref) {
                if (!local)
-                       skb_dst_set_noref_force(skb, &rt->dst);
+                       skb_dst_set_noref(skb, &rt->dst);
                else
                        skb_dst_set(skb, dst_clone(&rt->dst));
        } else
@@ -487,7 +487,7 @@ __ip_vs_get_out_rt_v6(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
        skb_dst_drop(skb);
        if (noref) {
                if (!local)
-                       skb_dst_set_noref_force(skb, &rt->dst);
+                       skb_dst_set_noref(skb, &rt->dst);
                else
                        skb_dst_set(skb, dst_clone(&rt->dst));
        } else