From bade732a2848e640482c1e99629a90e085d574dd Mon Sep 17 00:00:00 2001 From: Tom Tucker Date: Sat, 3 Apr 2010 08:27:29 -0500 Subject: svcrdma: RDMA support not yet compatible with RPC6 RPC6 requires that it be possible to create endpoints that listen exclusively for IPv4 or IPv6 connection requests. This is not currently supported by the RDMA API. This fixes a server RDMA regression introduced by 37498292a "NFSD: Create PF_INET6 listener in write_ports". Signed-off-by: Tom Tucker Tested-by: Steve Wise Reviewed-by: Chuck Lever Signed-off-by: J. Bruce Fields --- net/sunrpc/xprtrdma/svc_rdma_transport.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 3fa5751af0ec..4e6bbf91a570 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -678,7 +678,10 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv, int ret; dprintk("svcrdma: Creating RDMA socket\n"); - + if (sa->sa_family != AF_INET) { + dprintk("svcrdma: Address family %d is not supported.\n", sa->sa_family); + return ERR_PTR(-EAFNOSUPPORT); + } cma_xprt = rdma_create_xprt(serv, 1); if (!cma_xprt) return ERR_PTR(-ENOMEM); -- cgit v1.2.1 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 59a838795e3e..c98f115fb0fd 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 v1.2.1 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 1c8a0ce473a8..92584bfef09b 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 v1.2.1 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 c65f18e0936e..d1bcc9f21d4f 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 16c4391f952b..65f9c379df38 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 v1.2.1 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 cc90363d7e7a..243946d4809d 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 v1.2.1 From b4bb5c3fd9333024044362df67e23e96158489ed Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 19 Apr 2010 10:48:38 +0200 Subject: mac80211: remove bogus TX agg state assignment When the addba timer expires but has no work to do, it should not affect the state machine. If it does, TX will not see the successfully established and we can also crash trying to re-establish the session. Cc: stable@kernel.org [2.6.32, 2.6.33] Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- net/mac80211/agg-tx.c | 1 - 1 file changed, 1 deletion(-) (limited to 'net') diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 5538e1b4a697..944a8a92207b 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -183,7 +183,6 @@ static void sta_addba_resp_timer_expired(unsigned long data) HT_AGG_STATE_REQ_STOP_BA_MSK)) != HT_ADDBA_REQUESTED_MSK) { spin_unlock_bh(&sta->lock); - *state = HT_AGG_STATE_IDLE; #ifdef CONFIG_MAC80211_HT_DEBUG printk(KERN_DEBUG "timer expired on tid %d but we are not " "(or no longer) expecting addBA response there", -- cgit v1.2.1 From fe6f212ce12341df18ef9b890bea739b4547157b Mon Sep 17 00:00:00 2001 From: Reinette Chatre Date: Mon, 19 Apr 2010 10:46:31 -0700 Subject: mac80211: pass HT changes to driver when off channel Since "mac80211: make off-channel work generic" drivers have not been notified of configuration changes after association or authentication. This caused more dependence on current state to ensure driver will be notified when configuration changes occur. One such problem arises if off-channel is in progress when HT information changes. Since HT is only enabled on the "oper_channel" the driver will never be notified of this change. Usually the driver is notified soon after of a BSS information change (BSS_CHANGED_HT) ... but since the driver did not get a notification that this is a HT channel the new BSS information does not make sense. Fix this by also changing the off-channel information when HT is enabled and thus cause driver to be notified correctly. This fixes a problem in 4965 when associated with 5GHz 40MHz channel. Without this patch the system can associate but is unable to transfer any data, not even ping. See http://bugzilla.intellinuxwireless.org/show_bug.cgi?id=2158 Signed-off-by: Reinette Chatre Signed-off-by: John W. Linville --- net/mac80211/mlme.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net') diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index be5f723d643a..8a9650343f26 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -167,6 +167,8 @@ static u32 ieee80211_enable_ht(struct ieee80211_sub_if_data *sdata, ht_changed = conf_is_ht(&local->hw.conf) != enable_ht || channel_type != local->hw.conf.channel_type; + if (local->tmp_channel) + local->tmp_channel_type = channel_type; local->oper_channel_type = channel_type; if (ht_changed) { -- cgit v1.2.1 From 8eabf95cb17253a3ac72b1a62ce8a80b3efecd62 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 20 Apr 2010 03:20:05 +0000 Subject: bridge: add a missing ntohs() grec_nsrcs is in network order, we should convert to host horder in br_multicast_igmp3_report() Signed-off-by: Eric Dumazet Acked-by: Herbert Xu Signed-off-by: David S. Miller --- net/bridge/br_multicast.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index f29ada827a6a..386c15369d91 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -727,7 +727,7 @@ static int br_multicast_igmp3_report(struct net_bridge *br, group = grec->grec_mca; type = grec->grec_type; - len += grec->grec_nsrcs * 4; + len += ntohs(grec->grec_nsrcs) * 4; if (!pskb_may_pull(skb, len)) return -EINVAL; -- cgit v1.2.1 From 6651ffc8e8bdd5fb4b7d1867c6cfebb4f309512c Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 21 Apr 2010 00:47:15 -0700 Subject: ipv6: Fix tcp_v6_send_response transport header setting. My recent patch to remove the open-coded checksum sequence in tcp_v6_send_response broke it as we did not set the transport header pointer on the new packet. Actually, there is code there trying to set the transport header properly, but it sets it for the wrong skb ('skb' instead of 'buff'). This bug was introduced by commit a8fdf2b331b38d61fb5f11f3aec4a4f9fb2dedcb ("ipv6: Fix tcp_v6_send_response(): it didn't set skb transport header") Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- net/ipv6/tcp_ipv6.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index c92ebe8f80d5..075f540ec197 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1015,7 +1015,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, skb_reserve(buff, MAX_HEADER + sizeof(struct ipv6hdr) + tot_len); t1 = (struct tcphdr *) skb_push(buff, tot_len); - skb_reset_transport_header(skb); + skb_reset_transport_header(buff); /* Swap the send and the receive. */ memset(t1, 0, sizeof(*t1)); -- cgit v1.2.1 From 05d17608a69b3ae653ea5c9857283bef3439c733 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 20 Apr 2010 00:25:58 +0000 Subject: net: Fix an RCU warning in dev_pick_tx() Fix the following RCU warning in dev_pick_tx(): =================================================== [ INFO: suspicious rcu_dereference_check() usage. ] --------------------------------------------------- net/core/dev.c:1993 invoked rcu_dereference_check() without protection! other info that might help us debug this: rcu_scheduler_active = 1, debug_locks = 0 2 locks held by swapper/0: #0: (&idev->mc_ifc_timer){+.-...}, at: [] run_timer_softirq+0x17b/0x278 #1: (rcu_read_lock_bh){.+....}, at: [] dev_queue_xmit+0x14e/0x4dc stack backtrace: Pid: 0, comm: swapper Not tainted 2.6.34-rc5-cachefs #4 Call Trace: [] lockdep_rcu_dereference+0xaa/0xb2 [] dev_queue_xmit+0x259/0x4dc [] ? dev_queue_xmit+0x14e/0x4dc [] ? trace_hardirqs_on+0xd/0xf [] ? local_bh_enable_ip+0xbc/0xc1 [] neigh_resolve_output+0x24b/0x27c [] ip6_output_finish+0x7c/0xb4 [] ip6_output2+0x256/0x261 [] ? trace_hardirqs_on+0xd/0xf [] ip6_output+0xbbc/0xbcb [] ? fib6_force_start_gc+0x2b/0x2d [] mld_sendpack+0x273/0x39d [] ? mld_sendpack+0x0/0x39d [] ? mark_held_locks+0x52/0x70 [] mld_ifc_timer_expire+0x24f/0x288 [] run_timer_softirq+0x1ec/0x278 [] ? run_timer_softirq+0x17b/0x278 [] ? mld_ifc_timer_expire+0x0/0x288 [] ? __do_softirq+0x69/0x140 [] __do_softirq+0xa2/0x140 [] call_softirq+0x1c/0x28 [] do_softirq+0x38/0x80 [] irq_exit+0x45/0x47 [] smp_apic_timer_interrupt+0x88/0x96 [] apic_timer_interrupt+0x13/0x20 [] ? __atomic_notifier_call_chain+0x0/0x86 [] ? mwait_idle+0x6e/0x78 [] ? mwait_idle+0x65/0x78 [] cpu_idle+0x4d/0x83 [] rest_init+0xb9/0xc0 [] ? rest_init+0x0/0xc0 [] start_kernel+0x392/0x39d [] x86_64_start_reservations+0xb3/0xb7 [] x86_64_start_kernel+0xe4/0xeb An rcu_dereference() should be an rcu_dereference_bh(). Signed-off-by: David Howells Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/core/dev.c b/net/core/dev.c index 92584bfef09b..f769098774b7 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1990,7 +1990,7 @@ static struct netdev_queue *dev_pick_tx(struct net_device *dev, queue_index = skb_tx_hash(dev, skb); if (sk) { - struct dst_entry *dst = rcu_dereference(sk->sk_dst_cache); + struct dst_entry *dst = rcu_dereference_bh(sk->sk_dst_cache); if (dst && skb_dst(skb) == dst) sk_tx_queue_set(sk, queue_index); -- cgit v1.2.1