From ad1af0fedba14f82b240a03fe20eb9b2fdbd0357 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 25 Aug 2010 02:27:49 -0700 Subject: tcp: Combat per-cpu skew in orphan tests. As reported by Anton Blanchard when we use percpu_counter_read_positive() to make our orphan socket limit checks, the check can be off by up to num_cpus_online() * batch (which is 32 by default) which on a 128 cpu machine can be as large as the default orphan limit itself. Fix this by doing the full expensive sum check if the optimized check triggers. Reported-by: Anton Blanchard Signed-off-by: David S. Miller Acked-by: Eric Dumazet --- include/net/tcp.h | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index df6a2eb20193..eaa9582779d0 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -268,11 +268,21 @@ static inline int between(__u32 seq1, __u32 seq2, __u32 seq3) return seq3 - seq2 >= seq1 - seq2; } -static inline int tcp_too_many_orphans(struct sock *sk, int num) +static inline bool tcp_too_many_orphans(struct sock *sk, int shift) { - return (num > sysctl_tcp_max_orphans) || - (sk->sk_wmem_queued > SOCK_MIN_SNDBUF && - atomic_read(&tcp_memory_allocated) > sysctl_tcp_mem[2]); + struct percpu_counter *ocp = sk->sk_prot->orphan_count; + int orphans = percpu_counter_read_positive(ocp); + + if (orphans << shift > sysctl_tcp_max_orphans) { + orphans = percpu_counter_sum_positive(ocp); + if (orphans << shift > sysctl_tcp_max_orphans) + return true; + } + + if (sk->sk_wmem_queued > SOCK_MIN_SNDBUF && + atomic_read(&tcp_memory_allocated) > sysctl_tcp_mem[2]) + return true; + return false; } /* syncookies: remember time of last synqueue overflow */ -- cgit v1.2.3 From 3fb5a991916091a908d53608a5899240039fb51e Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Thu, 2 Sep 2010 15:42:43 +0000 Subject: cls_cgroup: Fix rcu lockdep warning Dave reported an rcu lockdep warning on 2.6.35.4 kernel task->cgroups and task->cgroups->subsys[i] are protected by RCU. So we avoid accessing invalid pointers here. This might happen, for example, when you are deref-ing those pointers while someone move @task from one cgroup to another. Reported-by: Dave Jones Signed-off-by: Li Zefan Signed-off-by: David S. Miller --- include/net/cls_cgroup.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/cls_cgroup.h b/include/net/cls_cgroup.h index 726cc3536409..ef6c24a529e1 100644 --- a/include/net/cls_cgroup.h +++ b/include/net/cls_cgroup.h @@ -27,11 +27,17 @@ struct cgroup_cls_state #ifdef CONFIG_NET_CLS_CGROUP static inline u32 task_cls_classid(struct task_struct *p) { + int classid; + if (in_interrupt()) return 0; - return container_of(task_subsys_state(p, net_cls_subsys_id), - struct cgroup_cls_state, css)->classid; + rcu_read_lock(); + classid = container_of(task_subsys_state(p, net_cls_subsys_id), + struct cgroup_cls_state, css)->classid; + rcu_read_unlock(); + + return classid; } #else extern int net_cls_subsys_id; -- cgit v1.2.3 From 6523ce1525e88c598c75a1a6b8c4edddfa9defe8 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Sun, 5 Sep 2010 18:02:29 +0000 Subject: ipvs: fix active FTP - Do not create expectation when forwarding the PORT command to avoid blocking the connection. The problem is that nf_conntrack_ftp.c:help() tries to create the same expectation later in POST_ROUTING and drops the packet with "dropping packet" message after failure in nf_ct_expect_related. - Change ip_vs_update_conntrack to alter the conntrack for related connections from real server. If we do not alter the reply in this direction the next packet from client sent to vport 20 comes as NEW connection. We alter it but may be some collision happens for both conntracks and the second conntrack gets destroyed immediately. The connection stucks too. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- include/net/ip_vs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/net') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index a4747a0f7303..f976885f686f 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -955,6 +955,9 @@ static inline __wsum ip_vs_check_diff2(__be16 old, __be16 new, __wsum oldsum) return csum_partial(diff, sizeof(diff), oldsum); } +extern void ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp, + int outin); + #endif /* __KERNEL__ */ #endif /* _NET_IP_VS_H */ -- cgit v1.2.3 From 719f835853a92f6090258114a72ffe41f09155cd Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 8 Sep 2010 05:08:44 +0000 Subject: udp: add rehash on connect() commit 30fff923 introduced in linux-2.6.33 (udp: bind() optimisation) added a secondary hash on UDP, hashed on (local addr, local port). Problem is that following sequence : fd = socket(...) connect(fd, &remote, ...) not only selects remote end point (address and port), but also sets local address, while UDP stack stored in secondary hash table the socket while its local address was INADDR_ANY (or ipv6 equivalent) Sequence is : - autobind() : choose a random local port, insert socket in hash tables [while local address is INADDR_ANY] - connect() : set remote address and port, change local address to IP given by a route lookup. When an incoming UDP frame comes, if more than 10 sockets are found in primary hash table, we switch to secondary table, and fail to find socket because its local address changed. One solution to this problem is to rehash datagram socket if needed. We add a new rehash(struct socket *) method in "struct proto", and implement this method for UDP v4 & v6, using a common helper. This rehashing only takes care of secondary hash table, since primary hash (based on local port only) is not changed. Reported-by: Krzysztof Piotr Oledzki Signed-off-by: Eric Dumazet Tested-by: Krzysztof Piotr Oledzki Signed-off-by: David S. Miller --- include/net/sock.h | 1 + include/net/udp.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index ac53bfbdfe16..adab9dc58183 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -752,6 +752,7 @@ struct proto { /* Keeping track of sk's, looking them up, and port selection methods. */ void (*hash)(struct sock *sk); void (*unhash)(struct sock *sk); + void (*rehash)(struct sock *sk); int (*get_port)(struct sock *sk, unsigned short snum); /* Keeping track of sockets in use */ diff --git a/include/net/udp.h b/include/net/udp.h index 7abdf305da50..a184d3496b13 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -151,6 +151,7 @@ static inline void udp_lib_hash(struct sock *sk) } extern void udp_lib_unhash(struct sock *sk); +extern void udp_lib_rehash(struct sock *sk, u16 new_hash); static inline void udp_lib_close(struct sock *sk, long timeout) { -- cgit v1.2.3