From 9be6dd6510fde5cfa2ab73f238754d38ee6797bc Mon Sep 17 00:00:00 2001 From: Andrei Warkentin Date: Fri, 5 Aug 2011 11:04:10 +0000 Subject: Bridge: Always send NETDEV_CHANGEADDR up on br MAC change. This ensures the neighbor entries associated with the bridge dev are flushed, also invalidating the associated cached L2 headers. This means we br_add_if/br_del_if ports to implement hand-over and not wind up with bridge packets going out with stale MAC. This means we can also change MAC of port device and also not wind up with bridge packets going out with stale MAC. This builds on Stephen Hemminger's patch, also handling the br_del_if case and the port MAC change case. Cc: Stephen Hemminger Signed-off-by: Andrei Warkentin Acked-by: Stephen Hemminger Signed-off-by: David S. Miller --- net/bridge/br_if.c | 6 +++++- net/bridge/br_notify.c | 7 ++++++- 2 files changed, 11 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 3176e2e13d9b..2cdf0070419f 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -417,6 +417,7 @@ put_back: int br_del_if(struct net_bridge *br, struct net_device *dev) { struct net_bridge_port *p; + bool changed_addr; p = br_port_get_rtnl(dev); if (!p || p->br != br) @@ -425,9 +426,12 @@ int br_del_if(struct net_bridge *br, struct net_device *dev) del_nbp(p); spin_lock_bh(&br->lock); - br_stp_recalculate_bridge_id(br); + changed_addr = br_stp_recalculate_bridge_id(br); spin_unlock_bh(&br->lock); + if (changed_addr) + call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev); + netdev_update_features(br->dev); return 0; diff --git a/net/bridge/br_notify.c b/net/bridge/br_notify.c index 6545ee9591d1..a76b62135558 100644 --- a/net/bridge/br_notify.c +++ b/net/bridge/br_notify.c @@ -34,6 +34,7 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v struct net_device *dev = ptr; struct net_bridge_port *p; struct net_bridge *br; + bool changed_addr; int err; /* register of bridge completed, add sysfs entries */ @@ -57,8 +58,12 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v case NETDEV_CHANGEADDR: spin_lock_bh(&br->lock); br_fdb_changeaddr(p, dev->dev_addr); - br_stp_recalculate_bridge_id(br); + changed_addr = br_stp_recalculate_bridge_id(br); spin_unlock_bh(&br->lock); + + if (changed_addr) + call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev); + break; case NETDEV_CHANGE: -- cgit v1.2.3 From 3557619f0f6f7496ed453d4825e24958ab1884e0 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 9 Aug 2011 02:04:43 +0000 Subject: net_sched: prio: use qdisc_dequeue_peeked commit 07bd8df5df4369487812bf85a237322ff3569b77 (sch_sfq: fix peek() implementation) changed sfq to use generic peek helper. This makes HFSC complain about a non-work-conserving child qdisc, if prio with sfq child is used within hfsc: hfsc peeks into prio qdisc, which will then peek into sfq. returned skb is stashed in sch->gso_skb. Next, hfsc tries to dequeue from prio, but prio will call sfq dequeue directly, which may return NULL instead of previously peeked-at skb. Have prio call qdisc_dequeue_peeked, so sfq->dequeue() is not called in this case. Cc: Eric Dumazet Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- net/sched/sch_prio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 2a318f2dc3e5..b5d56a22b1d2 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -112,7 +112,7 @@ static struct sk_buff *prio_dequeue(struct Qdisc *sch) for (prio = 0; prio < q->bands; prio++) { struct Qdisc *qdisc = q->queues[prio]; - struct sk_buff *skb = qdisc->dequeue(qdisc); + struct sk_buff *skb = qdisc_dequeue_peeked(qdisc); if (skb) { qdisc_bstats_update(sch, skb); sch->q.qlen--; -- cgit v1.2.3 From f0e3d0689da401f7d1981c2777a714ba295ea5ff Mon Sep 17 00:00:00 2001 From: Mike Waychison Date: Wed, 10 Aug 2011 21:59:57 -0700 Subject: tcp: initialize variable ecn_ok in syncookies path Using a gcc 4.4.3, warnings are emitted for a possibly uninitialized use of ecn_ok. This can happen if cookie_check_timestamp() returns due to not having seen a timestamp. Defaulting to ecn off seems like a reasonable thing to do in this case, so initialized ecn_ok to false. Signed-off-by: Mike Waychison Signed-off-by: David S. Miller --- net/ipv4/syncookies.c | 2 +- net/ipv6/syncookies.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 92bb9434b338..3bc5c8f7c71b 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -276,7 +276,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, int mss; struct rtable *rt; __u8 rcv_wscale; - bool ecn_ok; + bool ecn_ok = false; if (!sysctl_tcp_syncookies || !th->ack || th->rst) goto out; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 89d5bf806222..ac838965ff34 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -165,7 +165,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) int mss; struct dst_entry *dst; __u8 rcv_wscale; - bool ecn_ok; + bool ecn_ok = false; if (!sysctl_tcp_syncookies || !th->ack || th->rst) goto out; -- cgit v1.2.3 From e33f7a9f37d486f4c6cce5de18a6eea11d68f64f Mon Sep 17 00:00:00 2001 From: Tim Chen Date: Tue, 9 Aug 2011 06:48:32 +0000 Subject: scm: Capture the full credentials of the scm sender This patch corrects an erroneous update of credential's gid with uid introduced in commit 257b5358b32f17 since 2.6.36. Signed-off-by: Tim Chen Acked-by: Eric Dumazet Reviewed-by: James Morris Signed-off-by: David S. Miller --- net/core/scm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/core/scm.c b/net/core/scm.c index 4c1ef026d695..811b53fb330e 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -192,7 +192,7 @@ int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p) goto error; cred->uid = cred->euid = p->creds.uid; - cred->gid = cred->egid = p->creds.uid; + cred->gid = cred->egid = p->creds.gid; put_cred(p->cred); p->cred = cred; } -- cgit v1.2.3 From 94a80d63b245c66745c1d72b8154f67b597e3b89 Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Thu, 11 Aug 2011 00:06:04 +0000 Subject: net/netlabel/netlabel_kapi.c: add missing cleanup code Call cipso_v4_doi_putdef in the case of the failure of the allocation of entry. Reverse the order of the error handling code at the end of the function and insert more labels in order to reduce the number of unnecessary calls to kfree. Signed-off-by: Julia Lawall Signed-off-by: David S. Miller --- net/netlabel/netlabel_kapi.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) (limited to 'net') diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index 58107d060846..9c24de10a657 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -341,11 +341,11 @@ int netlbl_cfg_cipsov4_map_add(u32 doi, entry = kzalloc(sizeof(*entry), GFP_ATOMIC); if (entry == NULL) - return -ENOMEM; + goto out_entry; if (domain != NULL) { entry->domain = kstrdup(domain, GFP_ATOMIC); if (entry->domain == NULL) - goto cfg_cipsov4_map_add_failure; + goto out_domain; } if (addr == NULL && mask == NULL) { @@ -354,13 +354,13 @@ int netlbl_cfg_cipsov4_map_add(u32 doi, } else if (addr != NULL && mask != NULL) { addrmap = kzalloc(sizeof(*addrmap), GFP_ATOMIC); if (addrmap == NULL) - goto cfg_cipsov4_map_add_failure; + goto out_addrmap; INIT_LIST_HEAD(&addrmap->list4); INIT_LIST_HEAD(&addrmap->list6); addrinfo = kzalloc(sizeof(*addrinfo), GFP_ATOMIC); if (addrinfo == NULL) - goto cfg_cipsov4_map_add_failure; + goto out_addrinfo; addrinfo->type_def.cipsov4 = doi_def; addrinfo->type = NETLBL_NLTYPE_CIPSOV4; addrinfo->list.addr = addr->s_addr & mask->s_addr; @@ -374,7 +374,7 @@ int netlbl_cfg_cipsov4_map_add(u32 doi, entry->type = NETLBL_NLTYPE_ADDRSELECT; } else { ret_val = -EINVAL; - goto cfg_cipsov4_map_add_failure; + goto out_addrmap; } ret_val = netlbl_domhsh_add(entry, audit_info); @@ -384,11 +384,15 @@ int netlbl_cfg_cipsov4_map_add(u32 doi, return 0; cfg_cipsov4_map_add_failure: - cipso_v4_doi_putdef(doi_def); + kfree(addrinfo); +out_addrinfo: + kfree(addrmap); +out_addrmap: kfree(entry->domain); +out_domain: kfree(entry); - kfree(addrmap); - kfree(addrinfo); +out_entry: + cipso_v4_doi_putdef(doi_def); return ret_val; } -- cgit v1.2.3 From 5189054dd7ff18576446edc270b6b69fa8285336 Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Thu, 11 Aug 2011 01:59:38 +0000 Subject: net/bridge/netfilter/ebtables.c: use available error handling code Free the locally allocated table and newinfo as done in adjacent error handling code. Signed-off-by: Julia Lawall Signed-off-by: David S. Miller --- net/bridge/netfilter/ebtables.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 2b5ca1a0054d..5864cc491369 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1198,7 +1198,8 @@ ebt_register_table(struct net *net, const struct ebt_table *input_table) if (table->check && table->check(newinfo, table->valid_hooks)) { BUGPRINT("The table doesn't like its own initial data, lol\n"); - return ERR_PTR(-EINVAL); + ret = -EINVAL; + goto free_chainstack; } table->private = newinfo; -- cgit v1.2.3 From 97a804102021431fa6fa33c21c85df762b0f5cb9 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Tue, 9 Aug 2011 04:01:16 +0000 Subject: ipv4: some rt_iif -> rt_route_iif conversions As rt_iif represents input device even for packets coming from loopback with output route, it is not an unique key specific to input routes. Now rt_route_iif has such role, it was fl.iif in 2.6.38, so better to change the checks at some places to save CPU cycles and to restore 2.6.38 semantics. compare_keys: - input routes: only rt_route_iif matters, rt_iif is same - output routes: only rt_oif matters, rt_iif is not used for matching in __ip_route_output_key - now we are back to 2.6.38 state ip_route_input_common: - matching rt_route_iif implies input route - compared to 2.6.38 we eliminated one rth->fl.oif check because it was not needed even for 2.6.38 compare_hash_inputs: Only the change here is not an optimization, it has effect only for output routes. I assume I'm restoring the original intention to ignore oif, it was using fl.iif - now we are back to 2.6.38 state Signed-off-by: Julian Anastasov Signed-off-by: David S. Miller --- net/ipv4/route.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/net/ipv4/route.c b/net/ipv4/route.c index cb7efe0567f0..075212e41b83 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -722,7 +722,7 @@ static inline bool compare_hash_inputs(const struct rtable *rt1, { return ((((__force u32)rt1->rt_key_dst ^ (__force u32)rt2->rt_key_dst) | ((__force u32)rt1->rt_key_src ^ (__force u32)rt2->rt_key_src) | - (rt1->rt_iif ^ rt2->rt_iif)) == 0); + (rt1->rt_route_iif ^ rt2->rt_route_iif)) == 0); } static inline int compare_keys(struct rtable *rt1, struct rtable *rt2) @@ -732,8 +732,7 @@ static inline int compare_keys(struct rtable *rt1, struct rtable *rt2) (rt1->rt_mark ^ rt2->rt_mark) | (rt1->rt_key_tos ^ rt2->rt_key_tos) | (rt1->rt_route_iif ^ rt2->rt_route_iif) | - (rt1->rt_oif ^ rt2->rt_oif) | - (rt1->rt_iif ^ rt2->rt_iif)) == 0; + (rt1->rt_oif ^ rt2->rt_oif)) == 0; } static inline int compare_netns(struct rtable *rt1, struct rtable *rt2) @@ -2321,9 +2320,8 @@ int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr, rth = rcu_dereference(rth->dst.rt_next)) { if ((((__force u32)rth->rt_key_dst ^ (__force u32)daddr) | ((__force u32)rth->rt_key_src ^ (__force u32)saddr) | - (rth->rt_iif ^ iif) | + (rth->rt_route_iif ^ iif) | (rth->rt_key_tos ^ tos)) == 0 && - rt_is_input_route(rth) && rth->rt_mark == skb->mark && net_eq(dev_net(rth->dst.dev), net) && !rt_is_expired(rth)) { -- cgit v1.2.3 From c2bceb3d7f145af5a0916bea700f2f9d380901ea Mon Sep 17 00:00:00 2001 From: Lionel Elie Mamane Date: Sat, 13 Aug 2011 14:04:38 +0000 Subject: sit tunnels: propagate IPv6 transport class to IPv4 Type of Service sit tunnels (IPv6 tunnel over IPv4) do not implement the "tos inherit" case to copy the IPv6 transport class byte from the inner packet to the IPv4 type of service byte in the outer packet. By contrast, ipip tunnels and GRE tunnels do. This patch, adapted from the similar code in net/ipv4/ipip.c and net/ipv4/ip_gre.c, implements that. This patch applies to 3.0.1, and has been tested on that version. Signed-off-by: Lionel Elie Mamane Signed-off-by: David S. Miller --- net/ipv6/sit.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'net') diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 07bf1085458f..00b15ac7a702 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -672,6 +672,9 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, if (skb->protocol != htons(ETH_P_IPV6)) goto tx_error; + if (tos == 1) + tos = ipv6_get_dsfield(iph6); + /* ISATAP (RFC4214) - must come before 6to4 */ if (dev->priv_flags & IFF_ISATAP) { struct neighbour *neigh = NULL; -- cgit v1.2.3 From 8919bc13e8d92c5b082c5c0321567383a071f5bc Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Mon, 15 Aug 2011 05:25:40 +0000 Subject: net_sched: fix port mirror/redirect stats reporting When a redirected or mirrored packet is dropped by the target device we need to record statistics. Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- net/sched/act_mirred.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'net') diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 102fc212cd64..e051398fdf6b 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -196,8 +196,7 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, skb2->skb_iif = skb->dev->ifindex; skb2->dev = dev; - dev_queue_xmit(skb2); - err = 0; + err = dev_queue_xmit(skb2); out: if (err) { -- cgit v1.2.3 From c5114cd59d2664f258b0d021d79b1532d94bdc2b Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 18 Aug 2011 21:29:27 -0700 Subject: vlan: reset headers on accel emulation path It's after all necessary to do reset headers here. The reason is we cannot depend that it gets reseted in __netif_receive_skb once skb is reinjected. For incoming vlanids without vlan_dev, vlan_do_receive() returns false with skb != NULL and __netif_reveive_skb continues, skb is not reinjected. This might be good material for 3.0-stable as well Reported-by: Mike Auty Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- net/8021q/vlan_core.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net') diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 5f27f8e30254..f1f2f7bb6661 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -167,6 +167,8 @@ struct sk_buff *vlan_untag(struct sk_buff *skb) if (unlikely(!skb)) goto err_free; + skb_reset_network_header(skb); + skb_reset_transport_header(skb); return skb; err_free: -- cgit v1.2.3 From 98e77438aed3cd3343cbb86825127b1d9d2bea33 Mon Sep 17 00:00:00 2001 From: Daniel Baluta Date: Fri, 19 Aug 2011 03:19:07 -0700 Subject: ipv6: Fix ipv6_getsockopt for IPV6_2292PKTOPTIONS IPV6_2292PKTOPTIONS is broken for 32-bit applications running in COMPAT mode on 64-bit kernels. The same problem was fixed for IPv4 with the patch: ipv4: Fix ip_getsockopt for IP_PKTOPTIONS, commit dd23198e58cd35259dd09e8892bbdb90f1d57748 Signed-off-by: Sorin Dumitru Signed-off-by: Daniel Baluta Signed-off-by: David S. Miller --- net/ipv6/ipv6_sockglue.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 9cb191ecaba8..147ede38ab48 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -913,7 +913,7 @@ static int ipv6_getsockopt_sticky(struct sock *sk, struct ipv6_txoptions *opt, } static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen) + char __user *optval, int __user *optlen, unsigned flags) { struct ipv6_pinfo *np = inet6_sk(sk); int len; @@ -962,7 +962,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, msg.msg_control = optval; msg.msg_controllen = len; - msg.msg_flags = 0; + msg.msg_flags = flags; lock_sock(sk); skb = np->pktoptions; @@ -1222,7 +1222,7 @@ int ipv6_getsockopt(struct sock *sk, int level, int optname, if(level != SOL_IPV6) return -ENOPROTOOPT; - err = do_ipv6_getsockopt(sk, level, optname, optval, optlen); + err = do_ipv6_getsockopt(sk, level, optname, optval, optlen, 0); #ifdef CONFIG_NETFILTER /* we need to exclude all possible ENOPROTOOPTs except default case */ if (err == -ENOPROTOOPT && optname != IPV6_2292PKTOPTIONS) { @@ -1264,7 +1264,8 @@ int compat_ipv6_getsockopt(struct sock *sk, int level, int optname, return compat_mc_getsockopt(sk, level, optname, optval, optlen, ipv6_getsockopt); - err = do_ipv6_getsockopt(sk, level, optname, optval, optlen); + err = do_ipv6_getsockopt(sk, level, optname, optval, optlen, + MSG_CMSG_COMPAT); #ifdef CONFIG_NETFILTER /* we need to exclude all possible ENOPROTOOPTs except default case */ if (err == -ENOPROTOOPT && optname != IPV6_2292PKTOPTIONS) { -- cgit v1.2.3