diff options
| author | Eric Dumazet <edumazet@google.com> | 2012-07-29 23:20:37 +0000 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2012-07-30 14:53:22 -0700 |
| commit | 404e0a8b6a55d5e1cd138c6deb1bca9abdf75d8c (patch) | |
| tree | 38e9748d38c415cc97b973fecb9279cd43f76393 /net/decnet | |
| parent | cca32e4bf999a34ac08d959f351f2b30bcd02460 (diff) | |
| download | linux-404e0a8b6a55d5e1cd138c6deb1bca9abdf75d8c.tar.bz2 | |
net: ipv4: fix RCU races on dst refcounts
commit c6cffba4ffa2 (ipv4: Fix input route performance regression.)
added various fatal races with dst refcounts.
crashes happen on tcp workloads if routes are added/deleted at the same
time.
The dst_free() calls from free_fib_info_rcu() are clearly racy.
We need instead regular dst refcounting (dst_release()) and make
sure dst_release() is aware of RCU grace periods :
Add DST_RCU_FREE flag so that dst_release() respects an RCU grace period
before dst destruction for cached dst
Introduce a new inet_sk_rx_dst_set() helper, using atomic_inc_not_zero()
to make sure we dont increase a zero refcount (On a dst currently
waiting an rcu grace period before destruction)
rt_cache_route() must take a reference on the new cached route, and
release it if was not able to install it.
With this patch, my machines survive various benchmarks.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/decnet')
| -rw-r--r-- | net/decnet/dn_route.c | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 85a3604c87c8..26719779ad8e 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -184,6 +184,12 @@ static __inline__ unsigned int dn_hash(__le16 src, __le16 dst) return dn_rt_hash_mask & (unsigned int)tmp; } +static inline void dst_rcu_free(struct rcu_head *head) +{ + struct dst_entry *dst = container_of(head, struct dst_entry, rcu_head); + dst_free(dst); +} + static inline void dnrt_free(struct dn_route *rt) { call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free); |