From 6f86b325189e0a53c97bf86cff0c8b02ff624934 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 6 Sep 2010 22:36:19 -0700 Subject: ipv4: Fix reverse path filtering with multipath routing. Actually iterate over the next-hops to make sure we have a device match. Otherwise RP filtering is always elided when the route matched has multiple next-hops. Reported-by: Igor M Podlesny Signed-off-by: David S. Miller --- net/ipv4/fib_frontend.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index a43968918350..7d02a9f999fa 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -246,6 +246,7 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, struct fib_result res; int no_addr, rpf, accept_local; + bool dev_match; int ret; struct net *net; @@ -273,12 +274,22 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, } *spec_dst = FIB_RES_PREFSRC(res); fib_combine_itag(itag, &res); + dev_match = false; + #ifdef CONFIG_IP_ROUTE_MULTIPATH - if (FIB_RES_DEV(res) == dev || res.fi->fib_nhs > 1) + for (ret = 0; ret < res.fi->fib_nhs; ret++) { + struct fib_nh *nh = &res.fi->fib_nh[ret]; + + if (nh->nh_dev == dev) { + dev_match = true; + break; + } + } #else if (FIB_RES_DEV(res) == dev) + dev_match = true; #endif - { + if (dev_match) { ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST; fib_res_put(&res); return ret; -- cgit v1.2.3-59-g8ed1b From f6b085b69d1cbbd62f49f34e71a3d58cb6d34b7e Mon Sep 17 00:00:00 2001 From: Jarek Poplawski Date: Tue, 7 Sep 2010 07:51:17 +0000 Subject: ipv4: Suppress lockdep-RCU false positive in FIB trie (3) Hi, Here is one more of these warnings and a patch below: Sep 5 23:52:33 del kernel: [46044.244833] =================================================== Sep 5 23:52:33 del kernel: [46044.269681] [ INFO: suspicious rcu_dereference_check() usage. ] Sep 5 23:52:33 del kernel: [46044.277000] --------------------------------------------------- Sep 5 23:52:33 del kernel: [46044.285185] net/ipv4/fib_trie.c:1756 invoked rcu_dereference_check() without protection! Sep 5 23:52:33 del kernel: [46044.293627] Sep 5 23:52:33 del kernel: [46044.293632] other info that might help us debug this: Sep 5 23:52:33 del kernel: [46044.293634] Sep 5 23:52:33 del kernel: [46044.325333] Sep 5 23:52:33 del kernel: [46044.325335] rcu_scheduler_active = 1, debug_locks = 0 Sep 5 23:52:33 del kernel: [46044.348013] 1 lock held by pppd/1717: Sep 5 23:52:33 del kernel: [46044.357548] #0: (rtnl_mutex){+.+.+.}, at: [] rtnl_lock+0xf/0x20 Sep 5 23:52:33 del kernel: [46044.367647] Sep 5 23:52:33 del kernel: [46044.367652] stack backtrace: Sep 5 23:52:33 del kernel: [46044.387429] Pid: 1717, comm: pppd Not tainted 2.6.35.4.4a #3 Sep 5 23:52:33 del kernel: [46044.398764] Call Trace: Sep 5 23:52:33 del kernel: [46044.409596] [] ? printk+0x18/0x1e Sep 5 23:52:33 del kernel: [46044.420761] [] lockdep_rcu_dereference+0xa9/0xb0 Sep 5 23:52:33 del kernel: [46044.432229] [] trie_firstleaf+0x65/0x70 Sep 5 23:52:33 del kernel: [46044.443941] [] fib_table_flush+0x14/0x170 Sep 5 23:52:33 del kernel: [46044.455823] [] ? local_bh_enable_ip+0x62/0xd0 Sep 5 23:52:33 del kernel: [46044.467995] [] ? _raw_spin_unlock_bh+0x2f/0x40 Sep 5 23:52:33 del kernel: [46044.480404] [] ? fib_sync_down_dev+0x120/0x180 Sep 5 23:52:33 del kernel: [46044.493025] [] fib_flush+0x2d/0x60 Sep 5 23:52:33 del kernel: [46044.505796] [] fib_disable_ip+0x25/0x50 Sep 5 23:52:33 del kernel: [46044.518772] [] fib_netdev_event+0x73/0xd0 Sep 5 23:52:33 del kernel: [46044.531918] [] notifier_call_chain+0x2d/0x70 Sep 5 23:52:33 del kernel: [46044.545358] [] raw_notifier_call_chain+0x1a/0x20 Sep 5 23:52:33 del kernel: [46044.559092] [] call_netdevice_notifiers+0x27/0x60 Sep 5 23:52:33 del kernel: [46044.573037] [] __dev_notify_flags+0x5c/0x80 Sep 5 23:52:33 del kernel: [46044.586489] [] dev_change_flags+0x37/0x60 Sep 5 23:52:33 del kernel: [46044.599394] [] devinet_ioctl+0x54d/0x630 Sep 5 23:52:33 del kernel: [46044.612277] [] inet_ioctl+0x97/0xc0 Sep 5 23:52:34 del kernel: [46044.625208] [] sock_ioctl+0x6f/0x270 Sep 5 23:52:34 del kernel: [46044.638046] [] ? handle_mm_fault+0x420/0x6c0 Sep 5 23:52:34 del kernel: [46044.650968] [] ? sock_ioctl+0x0/0x270 Sep 5 23:52:34 del kernel: [46044.663865] [] vfs_ioctl+0x28/0xa0 Sep 5 23:52:34 del kernel: [46044.676556] [] do_vfs_ioctl+0x6a/0x5c0 Sep 5 23:52:34 del kernel: [46044.688989] [] ? up_read+0x16/0x30 Sep 5 23:52:34 del kernel: [46044.701411] [] ? do_page_fault+0x1d6/0x3a0 Sep 5 23:52:34 del kernel: [46044.714223] [] ? fget_light+0xf8/0x2f0 Sep 5 23:52:34 del kernel: [46044.726601] [] ? sys_socketcall+0x208/0x2c0 Sep 5 23:52:34 del kernel: [46044.739140] [] sys_ioctl+0x63/0x70 Sep 5 23:52:34 del kernel: [46044.751967] [] syscall_call+0x7/0xb Sep 5 23:52:34 del kernel: [46044.764734] [] ? cookie_v6_check+0x3d0/0x630 --------------> This patch fixes the warning: =================================================== [ INFO: suspicious rcu_dereference_check() usage. ] --------------------------------------------------- net/ipv4/fib_trie.c:1756 invoked rcu_dereference_check() without protection! other info that might help us debug this: rcu_scheduler_active = 1, debug_locks = 0 1 lock held by pppd/1717: #0: (rtnl_mutex){+.+.+.}, at: [] rtnl_lock+0xf/0x20 stack backtrace: Pid: 1717, comm: pppd Not tainted 2.6.35.4a #3 Call Trace: [] ? printk+0x18/0x1e [] lockdep_rcu_dereference+0xa9/0xb0 [] trie_firstleaf+0x65/0x70 [] fib_table_flush+0x14/0x170 ... Allow trie_firstleaf() to be called either under rcu_read_lock() protection or with RTNL held. The same annotation is added to node_parent_rcu() to prevent a similar warning a bit later. Followup of commits 634a4b20 and 4eaa0e3c. Signed-off-by: Jarek Poplawski Signed-off-by: David S. Miller --- net/ipv4/fib_trie.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 79d057a939ba..4a8e370862bc 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -186,7 +186,9 @@ static inline struct tnode *node_parent_rcu(struct node *node) { struct tnode *ret = node_parent(node); - return rcu_dereference(ret); + return rcu_dereference_check(ret, + rcu_read_lock_held() || + lockdep_rtnl_is_held()); } /* Same as rcu_assign_pointer @@ -1753,7 +1755,9 @@ static struct leaf *leaf_walk_rcu(struct tnode *p, struct node *c) static struct leaf *trie_firstleaf(struct trie *t) { - struct tnode *n = (struct tnode *) rcu_dereference(t->trie); + struct tnode *n = (struct tnode *) rcu_dereference_check(t->trie, + rcu_read_lock_held() || + lockdep_rtnl_is_held()); if (!n) return NULL; -- cgit v1.2.3-59-g8ed1b From ae2688d59b5f861dc70a091d003773975d2ae7fb Mon Sep 17 00:00:00 2001 From: Jianzhao Wang Date: Wed, 8 Sep 2010 14:35:43 -0700 Subject: net: blackhole route should always be recalculated Blackhole routes are used when xfrm_lookup() returns -EREMOTE (error triggered by IKE for example), hence this kind of route is always temporary and so we should check if a better route exists for next packets. Bug has been introduced by commit d11a4dc18bf41719c9f0d7ed494d295dd2973b92. Signed-off-by: Jianzhao Wang Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- net/ipv4/route.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'net/ipv4') diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 3f56b6e6c6aa..6298f75d5e93 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2738,6 +2738,11 @@ slow_output: } EXPORT_SYMBOL_GPL(__ip_route_output_key); +static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie) +{ + return NULL; +} + static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) { } @@ -2746,7 +2751,7 @@ static struct dst_ops ipv4_dst_blackhole_ops = { .family = AF_INET, .protocol = cpu_to_be16(ETH_P_IP), .destroy = ipv4_dst_destroy, - .check = ipv4_dst_check, + .check = ipv4_blackhole_dst_check, .update_pmtu = ipv4_rt_blackhole_update_pmtu, .entries = ATOMIC_INIT(0), }; -- cgit v1.2.3-59-g8ed1b 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 'net/ipv4') 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) { diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index f0550941df7b..721a8a37b45c 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 32e0bef60d0a..fb23c2e63b52 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 7d929a22cbc2..ef371aa01ac5 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 1dd1affdead2..5acb3560ff15 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 v1.2.3-59-g8ed1b