summaryrefslogtreecommitdiffstats
path: root/net/core/dst.c
diff options
context:
space:
mode:
authorEric Dumazet <eric.dumazet@gmail.com>2010-10-15 05:44:11 +0000
committerDavid S. Miller <davem@davemloft.net>2010-10-20 03:02:23 -0700
commit27b75c95f10d249574d9c4cb9dab878107faede8 (patch)
tree466656d86aaa395951e12b50903e730203c5f86f /net/core/dst.c
parente6484930d7c73d324bccda7d43d131088da697b9 (diff)
downloadop-kernel-dev-27b75c95f10d249574d9c4cb9dab878107faede8.zip
op-kernel-dev-27b75c95f10d249574d9c4cb9dab878107faede8.tar.gz
net: avoid RCU for NOCACHE dst
There is no point using RCU for dst we allocate for a very short time (used once). Change dst_release() to take DST_NOCACHE into account, but also change skb_dst_set_noref() to force a refcount increment for such dst. This is a _huge_ gain, because we dont waste memory to store xx thousand of dsts. Instead of queueing them to RCU, we can free them instantly. CPU caches can stay hot, re-using same memory blocks to hold temporary dsts. Note : remove unneeded smp_mb__before_atomic_dec(); in dst_release(), since atomic_dec_return() implies a full memory barrier. Stress test, 160.000.000 udp frames sent, IP route cache disabled (DDOS). Before: real 0m38.091s user 0m13.189s sys 7m53.018s After: real 0m29.946s user 0m12.157s sys 7m40.605s For reference, if IP route cache was enabled : real 0m32.030s user 0m10.521s sys 8m15.243s Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/core/dst.c')
-rw-r--r--net/core/dst.c29
1 files changed, 28 insertions, 1 deletions
diff --git a/net/core/dst.c b/net/core/dst.c
index 32e542d..8abe628 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -271,13 +271,40 @@ void dst_release(struct dst_entry *dst)
if (dst) {
int newrefcnt;
- smp_mb__before_atomic_dec();
newrefcnt = atomic_dec_return(&dst->__refcnt);
WARN_ON(newrefcnt < 0);
+ if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt) {
+ dst = dst_destroy(dst);
+ if (dst)
+ __dst_free(dst);
+ }
}
}
EXPORT_SYMBOL(dst_release);
+/**
+ * skb_dst_set_noref - sets skb dst, without a reference
+ * @skb: buffer
+ * @dst: dst entry
+ *
+ * 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)
+{
+ 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)) {
+ 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
OpenPOWER on IntegriCloud