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 /include/net | |
| 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 'include/net')
| -rw-r--r-- | include/net/dst.h | 7 | ||||
| -rw-r--r-- | include/net/inet_sock.h | 13 |
2 files changed, 14 insertions, 6 deletions
diff --git a/include/net/dst.h b/include/net/dst.h index baf597890064..31a9fd39edb6 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -61,6 +61,7 @@ struct dst_entry { #define DST_NOPEER 0x0040 #define DST_FAKE_RTABLE 0x0080 #define DST_XFRM_TUNNEL 0x0100 +#define DST_RCU_FREE 0x0200 unsigned short pending_confirm; @@ -382,12 +383,6 @@ static inline void dst_free(struct dst_entry *dst) __dst_free(dst); } -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 dst_confirm(struct dst_entry *dst) { dst->pending_confirm = 1; diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 613cfa401672..e3fd34c83ac9 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -249,4 +249,17 @@ static inline __u8 inet_sk_flowi_flags(const struct sock *sk) return flags; } +static inline void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + + if (atomic_inc_not_zero(&dst->__refcnt)) { + if (!(dst->flags & DST_RCU_FREE)) + dst->flags |= DST_RCU_FREE; + + sk->sk_rx_dst = dst; + inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; + } +} + #endif /* _INET_SOCK_H */ |