diff options
author | Su, Xuemin <suxm@chinanetcenter.com> | 2016-06-13 06:02:50 +0300 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2016-06-15 00:23:09 +0300 |
commit | d1e37288c9146dccff830e3253e403af8705b51f (patch) | |
tree | 573ea16d2781cf3754df56de05a306f8fff17c88 /net/ipv4/udp.c | |
parent | 6c0d54f1897d229748d4f41ef919078db6db2123 (diff) | |
download | linux-d1e37288c9146dccff830e3253e403af8705b51f.tar.xz |
udp reuseport: fix packet of same flow hashed to different socket
There is a corner case in which udp packets belonging to a same
flow are hashed to different socket when hslot->count changes from 10
to 11:
1) When hslot->count <= 10, __udp_lib_lookup() searches udp_table->hash,
and always passes 'daddr' to udp_ehashfn().
2) When hslot->count > 10, __udp_lib_lookup() searches udp_table->hash2,
but may pass 'INADDR_ANY' to udp_ehashfn() if the sockets are bound to
INADDR_ANY instead of some specific addr.
That means when hslot->count changes from 10 to 11, the hash calculated by
udp_ehashfn() is also changed, and the udp packets belonging to a same
flow will be hashed to different socket.
This is easily reproduced:
1) Create 10 udp sockets and bind all of them to 0.0.0.0:40000.
2) From the same host send udp packets to 127.0.0.1:40000, record the
socket index which receives the packets.
3) Create 1 more udp socket and bind it to 0.0.0.0:44096. The number 44096
is 40000 + UDP_HASH_SIZE(4096), this makes the new socket put into the
same hslot as the aformentioned 10 sockets, and makes the hslot->count
change from 10 to 11.
4) From the same host send udp packets to 127.0.0.1:40000, and the socket
index which receives the packets will be different from the one received
in step 2.
This should not happen as the socket bound to 0.0.0.0:44096 should not
change the behavior of the sockets bound to 0.0.0.0:40000.
It's the same case for IPv6, and this patch also fixes that.
Signed-off-by: Su, Xuemin <suxm@chinanetcenter.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv4/udp.c')
-rw-r--r-- | net/ipv4/udp.c | 73 |
1 files changed, 16 insertions, 57 deletions
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index ba0d8b8b7690..ca5e8ea29538 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -391,9 +391,9 @@ int udp_v4_get_port(struct sock *sk, unsigned short snum) return udp_lib_get_port(sk, snum, ipv4_rcv_saddr_equal, hash2_nulladdr); } -static inline int compute_score(struct sock *sk, struct net *net, - __be32 saddr, unsigned short hnum, __be16 sport, - __be32 daddr, __be16 dport, int dif) +static int compute_score(struct sock *sk, struct net *net, + __be32 saddr, __be16 sport, + __be32 daddr, unsigned short hnum, int dif) { int score; struct inet_sock *inet; @@ -434,52 +434,6 @@ static inline int compute_score(struct sock *sk, struct net *net, return score; } -/* - * In this second variant, we check (daddr, dport) matches (inet_rcv_sadd, inet_num) - */ -static inline int compute_score2(struct sock *sk, struct net *net, - __be32 saddr, __be16 sport, - __be32 daddr, unsigned int hnum, int dif) -{ - int score; - struct inet_sock *inet; - - if (!net_eq(sock_net(sk), net) || - ipv6_only_sock(sk)) - return -1; - - inet = inet_sk(sk); - - if (inet->inet_rcv_saddr != daddr || - inet->inet_num != hnum) - return -1; - - score = (sk->sk_family == PF_INET) ? 2 : 1; - - if (inet->inet_daddr) { - if (inet->inet_daddr != saddr) - return -1; - score += 4; - } - - if (inet->inet_dport) { - if (inet->inet_dport != sport) - return -1; - score += 4; - } - - if (sk->sk_bound_dev_if) { - if (sk->sk_bound_dev_if != dif) - return -1; - score += 4; - } - - if (sk->sk_incoming_cpu == raw_smp_processor_id()) - score++; - - return score; -} - static u32 udp_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport, const __be32 faddr, const __be16 fport) @@ -492,11 +446,11 @@ static u32 udp_ehashfn(const struct net *net, const __be32 laddr, udp_ehash_secret + net_hash_mix(net)); } -/* called with read_rcu_lock() */ +/* called with rcu_read_lock() */ static struct sock *udp4_lib_lookup2(struct net *net, __be32 saddr, __be16 sport, __be32 daddr, unsigned int hnum, int dif, - struct udp_hslot *hslot2, unsigned int slot2, + struct udp_hslot *hslot2, struct sk_buff *skb) { struct sock *sk, *result; @@ -506,7 +460,7 @@ static struct sock *udp4_lib_lookup2(struct net *net, result = NULL; badness = 0; udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) { - score = compute_score2(sk, net, saddr, sport, + score = compute_score(sk, net, saddr, sport, daddr, hnum, dif); if (score > badness) { reuseport = sk->sk_reuseport; @@ -554,17 +508,22 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, result = udp4_lib_lookup2(net, saddr, sport, daddr, hnum, dif, - hslot2, slot2, skb); + hslot2, skb); if (!result) { + unsigned int old_slot2 = slot2; hash2 = udp4_portaddr_hash(net, htonl(INADDR_ANY), hnum); slot2 = hash2 & udptable->mask; + /* avoid searching the same slot again. */ + if (unlikely(slot2 == old_slot2)) + return result; + hslot2 = &udptable->hash2[slot2]; if (hslot->count < hslot2->count) goto begin; result = udp4_lib_lookup2(net, saddr, sport, - htonl(INADDR_ANY), hnum, dif, - hslot2, slot2, skb); + daddr, hnum, dif, + hslot2, skb); } return result; } @@ -572,8 +531,8 @@ begin: result = NULL; badness = 0; sk_for_each_rcu(sk, &hslot->head) { - score = compute_score(sk, net, saddr, hnum, sport, - daddr, dport, dif); + score = compute_score(sk, net, saddr, sport, + daddr, hnum, dif); if (score > badness) { reuseport = sk->sk_reuseport; if (reuseport) { |