From 4eaa0e3c869acd5dbc7c2e3818a9ae9cbf221d27 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 14 Apr 2010 16:13:29 -0700 Subject: fib: suppress lockdep-RCU false positive in FIB trie. Followup of commit 634a4b20 Allow tnode_get_child_rcu() to be called either under rcu_read_lock() protection or with RTNL held. Signed-off-by: Eric Dumazet Signed-off-by: Paul E. McKenney Signed-off-by: David S. Miller --- net/ipv4/fib_trie.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 59a8387..c98f115 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -209,7 +209,9 @@ static inline struct node *tnode_get_child_rcu(struct tnode *tn, unsigned int i) { struct node *ret = tnode_get_child(tn, i); - return rcu_dereference(ret); + return rcu_dereference_check(ret, + rcu_read_lock_held() || + lockdep_rtnl_is_held()); } static inline int tnode_child_length(const struct tnode *tn) -- cgit v1.1 From 8728c544a9cbdcb0034aa5c45706c5f953f030ee Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 11 Apr 2010 21:18:17 +0000 Subject: net: dev_pick_tx() fix When dev_pick_tx() caches tx queue_index on a socket, we must check socket dst_entry matches skb one, or risk a crash later, as reported by Denys Fedorysychenko, if old packets are in flight during a route change, involving devices with different number of queues. Bug introduced by commit a4ee3ce3 (net: Use sk_tx_queue_mapping for connected sockets) Reported-by: Denys Fedorysychenko Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/dev.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/core/dev.c b/net/core/dev.c index 1c8a0ce..92584bf 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1989,8 +1989,12 @@ static struct netdev_queue *dev_pick_tx(struct net_device *dev, if (dev->real_num_tx_queues > 1) queue_index = skb_tx_hash(dev, skb); - if (sk && sk->sk_dst_cache) - sk_tx_queue_set(sk, queue_index); + if (sk) { + struct dst_entry *dst = rcu_dereference(sk->sk_dst_cache); + + if (dst && skb_dst(skb) == dst) + sk_tx_queue_set(sk, queue_index); + } } } -- cgit v1.1 From e30b38c298b55e09456d3ccbc1df2f3e2e8dc6e9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 15 Apr 2010 09:13:03 +0000 Subject: ip: Fix ip_dev_loopback_xmit() Eric Paris got following trace with a linux-next kernel [ 14.203970] BUG: using smp_processor_id() in preemptible [00000000] code: avahi-daemon/2093 [ 14.204025] caller is netif_rx+0xfa/0x110 [ 14.204035] Call Trace: [ 14.204064] [] debug_smp_processor_id+0x105/0x110 [ 14.204070] [] netif_rx+0xfa/0x110 [ 14.204090] [] ip_dev_loopback_xmit+0x71/0xa0 [ 14.204095] [] ip_mc_output+0x192/0x2c0 [ 14.204099] [] ip_local_out+0x20/0x30 [ 14.204105] [] ip_push_pending_frames+0x28d/0x3d0 [ 14.204119] [] udp_push_pending_frames+0x14c/0x400 [ 14.204125] [] udp_sendmsg+0x39c/0x790 [ 14.204137] [] inet_sendmsg+0x45/0x80 [ 14.204149] [] sock_sendmsg+0xf1/0x110 [ 14.204189] [] sys_sendmsg+0x20c/0x380 [ 14.204233] [] system_call_fastpath+0x16/0x1b While current linux-2.6 kernel doesnt emit this warning, bug is latent and might cause unexpected failures. ip_dev_loopback_xmit() runs in process context, preemption enabled, so must call netif_rx_ni() instead of netif_rx(), to make sure that we process pending software interrupt. Same change for ip6_dev_loopback_xmit() Reported-by: Eric Paris Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/ip_output.c | 2 +- net/ipv6/ip6_output.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index c65f18e..d1bcc9f 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -120,7 +120,7 @@ static int ip_dev_loopback_xmit(struct sk_buff *newskb) newskb->pkt_type = PACKET_LOOPBACK; newskb->ip_summed = CHECKSUM_UNNECESSARY; WARN_ON(!skb_dst(newskb)); - netif_rx(newskb); + netif_rx_ni(newskb); return 0; } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 16c4391..65f9c37 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -108,7 +108,7 @@ static int ip6_dev_loopback_xmit(struct sk_buff *newskb) newskb->ip_summed = CHECKSUM_UNNECESSARY; WARN_ON(!skb_dst(newskb)); - netif_rx(newskb); + netif_rx_ni(newskb); return 0; } -- cgit v1.1 From 1c4f0197323254e463b642abf2c8361e2a924859 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 14 Apr 2010 23:11:14 +0000 Subject: packet : remove init_net restriction The af_packet protocol is used by Perl to do ioctls as reported by Stephane Riviere: "Net::RawIP relies on SIOCGIFADDR et SIOCGIFHWADDR to get the IP and MAC addresses of the network interface." But in a new network namespace these ioctl fail because it is disabled for a namespace different from the init_net_ns. These two lines should not be there as af_inet and af_packet are namespace aware since a long time now. I suppose we forget to remove these lines because we sent the af_packet first, before af_inet was supported. Signed-off-by: Daniel Lezcano Reported-by: Stephane Riviere Signed-off-by: David S. Miller --- net/packet/af_packet.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'net') diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index cc90363..243946d 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2169,8 +2169,6 @@ static int packet_ioctl(struct socket *sock, unsigned int cmd, case SIOCGIFDSTADDR: case SIOCSIFDSTADDR: case SIOCSIFFLAGS: - if (!net_eq(sock_net(sk), &init_net)) - return -ENOIOCTLCMD; return inet_dgram_ops.ioctl(sock, cmd, arg); #endif -- cgit v1.1