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') diff --git a/include/net/cls_cgroup.h b/include/net/cls_cgroup.h index 726cc353640..ef6c24a529e 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 v1.2.3-70-g09d2 From 73457f0f836956747e0394320be2163c050e96ef Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 6 Aug 2010 01:59:14 +0300 Subject: cgroups: fix API thinko cgroup_attach_task_current_cg API that have upstream is backwards: we really need an API to attach to the cgroups from another process A to the current one. In our case (vhost), a priveledged user wants to attach it's task to cgroups from a less priveledged one, the API makes us run it in the other task's context, and this fails. So let's make the API generic and just pass in 'from' and 'to' tasks. Add an inline wrapper for cgroup_attach_task_current_cg to avoid breaking bisect. Signed-off-by: Michael S. Tsirkin Acked-by: Li Zefan Acked-by: Paul Menage --- include/linux/cgroup.h | 11 ++++++++++- kernel/cgroup.c | 9 +++++---- 2 files changed, 15 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index ed3e92e41c6..5a53d8f039a 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -578,7 +578,11 @@ struct task_struct *cgroup_iter_next(struct cgroup *cgrp, void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it); int cgroup_scan_tasks(struct cgroup_scanner *scan); int cgroup_attach_task(struct cgroup *, struct task_struct *); -int cgroup_attach_task_current_cg(struct task_struct *); +int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); +static inline int cgroup_attach_task_current_cg(struct task_struct *tsk) +{ + return cgroup_attach_task_all(current, tsk); +} /* * CSS ID is ID for cgroup_subsys_state structs under subsys. This only works @@ -636,6 +640,11 @@ static inline int cgroupstats_build(struct cgroupstats *stats, } /* No cgroups - nothing to do */ +static inline int cgroup_attach_task_all(struct task_struct *from, + struct task_struct *t) +{ + return 0; +} static inline int cgroup_attach_task_current_cg(struct task_struct *t) { return 0; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index a8ce0995440..9d90c08f3bd 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1789,10 +1789,11 @@ out: } /** - * cgroup_attach_task_current_cg - attach task 'tsk' to current task's cgroup + * cgroup_attach_task_all - attach task 'tsk' to all cgroups of task 'from' + * @from: attach to all cgroups of a given task * @tsk: the task to be attached */ -int cgroup_attach_task_current_cg(struct task_struct *tsk) +int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) { struct cgroupfs_root *root; struct cgroup *cur_cg; @@ -1800,7 +1801,7 @@ int cgroup_attach_task_current_cg(struct task_struct *tsk) cgroup_lock(); for_each_active_root(root) { - cur_cg = task_cgroup_from_root(current, root); + cur_cg = task_cgroup_from_root(from, root); retval = cgroup_attach_task(cur_cg, tsk); if (retval) break; @@ -1809,7 +1810,7 @@ int cgroup_attach_task_current_cg(struct task_struct *tsk) return retval; } -EXPORT_SYMBOL_GPL(cgroup_attach_task_current_cg); +EXPORT_SYMBOL_GPL(cgroup_attach_task_all); /* * Attach task with pid 'pid' to cgroup 'cgrp'. Call with cgroup_mutex -- cgit v1.2.3-70-g09d2 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 +++ net/netfilter/ipvs/ip_vs_core.c | 1 + net/netfilter/ipvs/ip_vs_ftp.c | 6 ------ net/netfilter/ipvs/ip_vs_xmit.c | 18 ++++++++++++------ 4 files changed, 16 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index a4747a0f730..f976885f686 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 */ diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 4f8ddba4801..4c2f89df5cc 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -924,6 +924,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, ip_vs_out_stats(cp, skb); ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pp); + ip_vs_update_conntrack(skb, cp, 0); ip_vs_conn_put(cp); skb->ipvs_property = 1; diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index 33b329bfc2d..7e9af5b76d9 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -410,7 +410,6 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, union nf_inet_addr to; __be16 port; struct ip_vs_conn *n_cp; - struct nf_conn *ct; #ifdef CONFIG_IP_VS_IPV6 /* This application helper doesn't work with IPv6 yet, @@ -497,11 +496,6 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, ip_vs_control_add(n_cp, cp); } - ct = (struct nf_conn *)skb->nfct; - if (ct && ct != &nf_conntrack_untracked) - ip_vs_expect_related(skb, ct, n_cp, - IPPROTO_TCP, &n_cp->dport, 1); - /* * Move tunnel to listen state */ diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 21e1a5e9b9d..49df6bea6a2 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -349,8 +349,8 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, } #endif -static void -ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp) +void +ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp, int outin) { struct nf_conn *ct = (struct nf_conn *)skb->nfct; struct nf_conntrack_tuple new_tuple; @@ -365,11 +365,17 @@ ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp) * real-server we will see RIP->DIP. */ new_tuple = ct->tuplehash[IP_CT_DIR_REPLY].tuple; - new_tuple.src.u3 = cp->daddr; + if (outin) + new_tuple.src.u3 = cp->daddr; + else + new_tuple.dst.u3 = cp->vaddr; /* * This will also take care of UDP and other protocols. */ - new_tuple.src.u.tcp.port = cp->dport; + if (outin) + new_tuple.src.u.tcp.port = cp->dport; + else + new_tuple.dst.u.tcp.port = cp->vport; nf_conntrack_alter_reply(ct, &new_tuple); } @@ -428,7 +434,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, IP_VS_DBG_PKT(10, pp, skb, 0, "After DNAT"); - ip_vs_update_conntrack(skb, cp); + ip_vs_update_conntrack(skb, cp, 1); /* FIXME: when application helper enlarges the packet and the length is larger than the MTU of outgoing device, there will be still @@ -506,7 +512,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, IP_VS_DBG_PKT(10, pp, skb, 0, "After DNAT"); - ip_vs_update_conntrack(skb, cp); + ip_vs_update_conntrack(skb, cp, 1); /* FIXME: when application helper enlarges the packet and the length is larger than the MTU of outgoing device, there will be still -- cgit v1.2.3-70-g09d2 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 + net/ipv4/datagram.c | 5 ++++- net/ipv4/udp.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ net/ipv6/datagram.c | 7 ++++++- net/ipv6/udp.c | 10 ++++++++++ 6 files changed, 66 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index ac53bfbdfe1..adab9dc5818 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 7abdf305da5..a184d3496b1 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) { diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index f0550941df7..721a8a37b45 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -62,8 +62,11 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) } if (!inet->inet_saddr) inet->inet_saddr = rt->rt_src; /* Update source address */ - if (!inet->inet_rcv_saddr) + if (!inet->inet_rcv_saddr) { inet->inet_rcv_saddr = rt->rt_src; + if (sk->sk_prot->rehash) + sk->sk_prot->rehash(sk); + } inet->inet_daddr = rt->rt_dst; inet->inet_dport = usin->sin_port; sk->sk_state = TCP_ESTABLISHED; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 32e0bef60d0..fb23c2e63b5 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1260,6 +1260,49 @@ void udp_lib_unhash(struct sock *sk) } EXPORT_SYMBOL(udp_lib_unhash); +/* + * inet_rcv_saddr was changed, we must rehash secondary hash + */ +void udp_lib_rehash(struct sock *sk, u16 newhash) +{ + if (sk_hashed(sk)) { + struct udp_table *udptable = sk->sk_prot->h.udp_table; + struct udp_hslot *hslot, *hslot2, *nhslot2; + + hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); + nhslot2 = udp_hashslot2(udptable, newhash); + udp_sk(sk)->udp_portaddr_hash = newhash; + if (hslot2 != nhslot2) { + hslot = udp_hashslot(udptable, sock_net(sk), + udp_sk(sk)->udp_port_hash); + /* we must lock primary chain too */ + spin_lock_bh(&hslot->lock); + + spin_lock(&hslot2->lock); + hlist_nulls_del_init_rcu(&udp_sk(sk)->udp_portaddr_node); + hslot2->count--; + spin_unlock(&hslot2->lock); + + spin_lock(&nhslot2->lock); + hlist_nulls_add_head_rcu(&udp_sk(sk)->udp_portaddr_node, + &nhslot2->head); + nhslot2->count++; + spin_unlock(&nhslot2->lock); + + spin_unlock_bh(&hslot->lock); + } + } +} +EXPORT_SYMBOL(udp_lib_rehash); + +static void udp_v4_rehash(struct sock *sk) +{ + u16 new_hash = udp4_portaddr_hash(sock_net(sk), + inet_sk(sk)->inet_rcv_saddr, + inet_sk(sk)->inet_num); + udp_lib_rehash(sk, new_hash); +} + static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { int rc; @@ -1843,6 +1886,7 @@ struct proto udp_prot = { .backlog_rcv = __udp_queue_rcv_skb, .hash = udp_lib_hash, .unhash = udp_lib_unhash, + .rehash = udp_v4_rehash, .get_port = udp_v4_get_port, .memory_allocated = &udp_memory_allocated, .sysctl_mem = sysctl_udp_mem, diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 7d929a22cbc..ef371aa01ac 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -105,9 +105,12 @@ ipv4_connected: if (ipv6_addr_any(&np->saddr)) ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); - if (ipv6_addr_any(&np->rcv_saddr)) + if (ipv6_addr_any(&np->rcv_saddr)) { ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, &np->rcv_saddr); + if (sk->sk_prot->rehash) + sk->sk_prot->rehash(sk); + } goto out; } @@ -181,6 +184,8 @@ ipv4_connected: if (ipv6_addr_any(&np->rcv_saddr)) { ipv6_addr_copy(&np->rcv_saddr, &fl.fl6_src); inet->inet_rcv_saddr = LOOPBACK4_IPV6; + if (sk->sk_prot->rehash) + sk->sk_prot->rehash(sk); } ip6_dst_store(sk, dst, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 1dd1affdead..5acb3560ff1 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -111,6 +111,15 @@ int udp_v6_get_port(struct sock *sk, unsigned short snum) return udp_lib_get_port(sk, snum, ipv6_rcv_saddr_equal, hash2_nulladdr); } +static void udp_v6_rehash(struct sock *sk) +{ + u16 new_hash = udp6_portaddr_hash(sock_net(sk), + &inet6_sk(sk)->rcv_saddr, + inet_sk(sk)->inet_num); + + udp_lib_rehash(sk, new_hash); +} + static inline int compute_score(struct sock *sk, struct net *net, unsigned short hnum, struct in6_addr *saddr, __be16 sport, @@ -1447,6 +1456,7 @@ struct proto udpv6_prot = { .backlog_rcv = udpv6_queue_rcv_skb, .hash = udp_lib_hash, .unhash = udp_lib_unhash, + .rehash = udp_v6_rehash, .get_port = udp_v6_get_port, .memory_allocated = &udp_memory_allocated, .sysctl_mem = sysctl_udp_mem, -- cgit v1.2.3-70-g09d2