From bfcaa50270e18f35220a11d46e98fc6232c24606 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Mon, 25 May 2009 17:23:15 +0200 Subject: netfilter: nf_ct_tcp: fix accepting invalid RST segments Robert L Mathews discovered that some clients send evil TCP RST segments, which are accepted by netfilter conntrack but discarded by the destination. Thus the conntrack entry is destroyed but the destination retransmits data until timeout. The same technique, i.e. sending properly crafted RST segments, can easily be used to bypass connlimit/connbytes based restrictions (the sample script written by Robert can be found in the netfilter mailing list archives). The patch below adds a new flag and new field to struct ip_ct_tcp_state so that checking RST segments can be made more strict and thus TCP conntrack can catch the invalid ones: the RST segment is accepted only if its sequence number higher than or equal to the highest ack we seen from the other direction. (The last_ack field cannot be reused because it is used to catch resent packets.) Signed-off-by: Jozsef Kadlecsik Signed-off-by: Patrick McHardy --- net/netfilter/nf_conntrack_proto_tcp.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'net') diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index b5ccf2b4b2e7..97a6e93d742e 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -634,6 +634,14 @@ static bool tcp_in_window(const struct nf_conn *ct, sender->td_end = end; sender->flags |= IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED; } + if (tcph->ack) { + if (!(sender->flags & IP_CT_TCP_FLAG_MAXACK_SET)) { + sender->td_maxack = ack; + sender->flags |= IP_CT_TCP_FLAG_MAXACK_SET; + } else if (after(ack, sender->td_maxack)) + sender->td_maxack = ack; + } + /* * Update receiver data. */ @@ -918,6 +926,16 @@ static int tcp_packet(struct nf_conn *ct, "nf_ct_tcp: invalid state "); return -NF_ACCEPT; case TCP_CONNTRACK_CLOSE: + if (index == TCP_RST_SET + && (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET) + && before(ntohl(th->seq), ct->proto.tcp.seen[!dir].td_maxack)) { + /* Invalid RST */ + write_unlock_bh(&tcp_lock); + if (LOG_INVALID(net, IPPROTO_TCP)) + nf_log_packet(pf, 0, skb, NULL, NULL, NULL, + "nf_ct_tcp: invalid RST "); + return -NF_ACCEPT; + } if (index == TCP_RST_SET && ((test_bit(IPS_SEEN_REPLY_BIT, &ct->status) && ct->proto.tcp.last_index == TCP_SYN_SET) -- cgit v1.2.3 From b38b1f616867c832301f24eaf259889494d495b3 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 25 May 2009 17:29:43 +0200 Subject: netfilter: nf_ct_dccp: add missing DCCP protocol changes in event cache This patch adds the missing protocol state-change event reporting for DCCP. $ sudo conntrack -E [NEW] dccp 33 240 src=192.168.0.2 dst=192.168.1.2 sport=57040 dport=5001 [UNREPLIED] src=192.168.1.2 dst=192.168.1.100 sport=5001 dport=57040 With this patch: $ sudo conntrack -E [NEW] dccp 33 240 REQUEST src=192.168.0.2 dst=192.168.1.2 sport=57040 dport=5001 [UNREPLIED] src=192.168.1.2 dst=192.168.1.100 sport=5001 dport=57040 Signed-off-by: Pablo Neira Ayuso Signed-off-by: Patrick McHardy --- net/netfilter/nf_conntrack_proto_dccp.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net') diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 8e757dd53396..aee0d6bea309 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -22,6 +22,7 @@ #include #include #include +#include #include static DEFINE_RWLOCK(dccp_lock); @@ -553,6 +554,9 @@ static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb, ct->proto.dccp.state = new_state; write_unlock_bh(&dccp_lock); + if (new_state != old_state) + nf_conntrack_event_cache(IPCT_PROTOINFO, ct); + dn = dccp_pernet(net); nf_ct_refresh_acct(ct, ctinfo, skb, dn->dccp_timeout[new_state]); -- cgit v1.2.3 From c80a5cdfc5ca6533cb893154f546370da1fdb8f0 Mon Sep 17 00:00:00 2001 From: Doug Leith Date: Mon, 25 May 2009 22:44:59 -0700 Subject: tcp: tcp_vegas ssthresh bugfix This patch fixes ssthresh accounting issues in tcp_vegas when cwnd decreases Signed-off-by: Doug Leith Signed-off-by: David S. Miller --- net/ipv4/tcp_vegas.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c index a453aac91bd3..c6743eec9b7d 100644 --- a/net/ipv4/tcp_vegas.c +++ b/net/ipv4/tcp_vegas.c @@ -158,6 +158,11 @@ void tcp_vegas_cwnd_event(struct sock *sk, enum tcp_ca_event event) } EXPORT_SYMBOL_GPL(tcp_vegas_cwnd_event); +static inline u32 tcp_vegas_ssthresh(struct tcp_sock *tp) +{ + return min(tp->snd_ssthresh, tp->snd_cwnd-1); +} + static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 in_flight) { struct tcp_sock *tp = tcp_sk(sk); @@ -221,11 +226,10 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 in_flight) */ diff = tp->snd_cwnd * (rtt-vegas->baseRTT) / vegas->baseRTT; - if (diff > gamma && tp->snd_ssthresh > 2 ) { + if (diff > gamma && tp->snd_cwnd <= tp->snd_ssthresh) { /* Going too fast. Time to slow down * and switch to congestion avoidance. */ - tp->snd_ssthresh = 2; /* Set cwnd to match the actual rate * exactly: @@ -235,6 +239,7 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 in_flight) * utilization. */ tp->snd_cwnd = min(tp->snd_cwnd, (u32)target_cwnd+1); + tp->snd_ssthresh = tcp_vegas_ssthresh(tp); } else if (tp->snd_cwnd <= tp->snd_ssthresh) { /* Slow start. */ @@ -250,6 +255,8 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 in_flight) * we slow down. */ tp->snd_cwnd--; + tp->snd_ssthresh + = tcp_vegas_ssthresh(tp); } else if (diff < alpha) { /* We don't have enough extra packets * in the network, so speed up. -- cgit v1.2.3 From e65fcfd63a9a62baa5708484ff8edbe56eb3e7ec Mon Sep 17 00:00:00 2001 From: Paul Menage Date: Tue, 26 May 2009 20:47:02 -0700 Subject: cls_cgroup: read classid atomically in classifier Avoid reading the unsynchronized value cs->classid multiple times, since it could change concurrently from non-zero to zero; this would result in the classifier returning a positive result with a bogus (zero) classid. Signed-off-by: Paul Menage Reviewed-by: Li Zefan Signed-off-by: David S. Miller --- net/sched/cls_cgroup.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'net') diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index 91a3db4a76f8..cc29b44b1500 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -104,8 +104,7 @@ static int cls_cgroup_classify(struct sk_buff *skb, struct tcf_proto *tp, struct tcf_result *res) { struct cls_cgroup_head *head = tp->root; - struct cgroup_cls_state *cs; - int ret = 0; + u32 classid; /* * Due to the nature of the classifier it is required to ignore all @@ -121,17 +120,18 @@ static int cls_cgroup_classify(struct sk_buff *skb, struct tcf_proto *tp, return -1; rcu_read_lock(); - cs = task_cls_state(current); - if (cs->classid && tcf_em_tree_match(skb, &head->ematches, NULL)) { - res->classid = cs->classid; - res->class = 0; - ret = tcf_exts_exec(skb, &head->exts, res); - } else - ret = -1; - + classid = task_cls_state(current)->classid; rcu_read_unlock(); - return ret; + if (!classid) + return -1; + + if (!tcf_em_tree_match(skb, &head->ematches, NULL)) + return -1; + + res->classid = classid; + res->class = 0; + return tcf_exts_exec(skb, &head->exts, res); } static unsigned long cls_cgroup_get(struct tcf_proto *tp, u32 handle) -- cgit v1.2.3 From 4c713189485dbea875aecd1990daed74908e181d Mon Sep 17 00:00:00 2001 From: Dave Young Date: Wed, 27 May 2009 09:10:28 +0200 Subject: Bluetooth: Remove useless flush_work() causing lockdep warnings The calls to flush_work() are pointless in a single thread workqueue and they are actually causing a lockdep warning. ============================================= [ INFO: possible recursive locking detected ] 2.6.30-rc6-02911-gbb803cf #16 --------------------------------------------- bluetooth/2518 is trying to acquire lock: (bluetooth){+.+.+.}, at: [] flush_work+0x28/0xb0 but task is already holding lock: (bluetooth){+.+.+.}, at: [] worker_thread+0x149/0x25e other info that might help us debug this: 2 locks held by bluetooth/2518: #0: (bluetooth){+.+.+.}, at: [] worker_thread+0x149/0x25e #1: (&conn->work_del){+.+...}, at: [] worker_thread+0x149/0x25e stack backtrace: Pid: 2518, comm: bluetooth Not tainted 2.6.30-rc6-02911-gbb803cf #16 Call Trace: [] ? printk+0xf/0x11 [] __lock_acquire+0x7ce/0xb1b [] lock_acquire+0x90/0xad [] ? flush_work+0x28/0xb0 [] flush_work+0x42/0xb0 [] ? flush_work+0x28/0xb0 [] del_conn+0x1c/0x84 [bluetooth] [] worker_thread+0x18e/0x25e [] ? worker_thread+0x149/0x25e [] ? del_conn+0x0/0x84 [bluetooth] [] ? autoremove_wake_function+0x0/0x33 [] ? worker_thread+0x0/0x25e [] kthread+0x45/0x6b [] ? kthread+0x0/0x6b [] kernel_thread_helper+0x7/0x10 Based on a report by Oliver Hartkopp Signed-off-by: Dave Young Tested-by: Oliver Hartkopp Signed-off-by: Marcel Holtmann --- net/bluetooth/hci_sysfs.c | 6 ------ 1 file changed, 6 deletions(-) (limited to 'net') diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c index 4cc3624bd22d..95f7a7a544b4 100644 --- a/net/bluetooth/hci_sysfs.c +++ b/net/bluetooth/hci_sysfs.c @@ -90,9 +90,6 @@ static void add_conn(struct work_struct *work) struct hci_conn *conn = container_of(work, struct hci_conn, work_add); struct hci_dev *hdev = conn->hdev; - /* ensure previous del is complete */ - flush_work(&conn->work_del); - dev_set_name(&conn->dev, "%s:%d", hdev->name, conn->handle); if (device_add(&conn->dev) < 0) { @@ -118,9 +115,6 @@ static void del_conn(struct work_struct *work) struct hci_conn *conn = container_of(work, struct hci_conn, work_del); struct hci_dev *hdev = conn->hdev; - /* ensure previous add is complete */ - flush_work(&conn->work_add); - if (!device_is_registered(&conn->dev)) return; -- cgit v1.2.3 From 683a04cebc63819a36b1db19843bd17771f05b55 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Wed, 27 May 2009 15:45:34 +0200 Subject: netfilter: xt_hashlimit does a wrong SEQ_SKIP The function dl_seq_show() returns 1 (equal to SEQ_SKIP) in case a seq_printf() call return -1. It should return -1. This SEQ_SKIP behavior brakes processing the proc file e.g. via a pipe or just through less. Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Patrick McHardy --- net/netfilter/xt_hashlimit.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index a5b5369c30f9..219dcdbe388c 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -926,7 +926,7 @@ static int dl_seq_show(struct seq_file *s, void *v) if (!hlist_empty(&htable->hash[*bucket])) { hlist_for_each_entry(ent, pos, &htable->hash[*bucket], node) if (dl_seq_real_show(ent, htable->family, s)) - return 1; + return -1; } return 0; } -- cgit v1.2.3 From eeff9beec3d2563c42cca41e66d4169592bb5475 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 27 May 2009 15:49:11 +0200 Subject: netfilter: nfnetlink_log: fix wrong skbuff size calculation This problem was introduced in 72961ecf84d67d6359a1b30f9b2a8427f13e1e71 since no space was reserved for the new attributes NFULA_HWTYPE, NFULA_HWLEN and NFULA_HWHEADER. Signed-off-by: Pablo Neira Ayuso Signed-off-by: Patrick McHardy --- net/netfilter/nfnetlink_log.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'net') diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index fd326ac27ec8..66a6dd5c519a 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -581,6 +581,12 @@ nfulnl_log_packet(u_int8_t pf, + nla_total_size(sizeof(struct nfulnl_msg_packet_hw)) + nla_total_size(sizeof(struct nfulnl_msg_packet_timestamp)); + if (in && skb_mac_header_was_set(skb)) { + size += nla_total_size(skb->dev->hard_header_len) + + nla_total_size(sizeof(u_int16_t)) /* hwtype */ + + nla_total_size(sizeof(u_int16_t)); /* hwlen */ + } + spin_lock_bh(&inst->lock); if (inst->flags & NFULNL_CFG_F_SEQ) -- cgit v1.2.3 From 12186be7d2e1106cede1cc728526e3d7998cbe94 Mon Sep 17 00:00:00 2001 From: Minoru Usui Date: Tue, 2 Jun 2009 02:17:34 -0700 Subject: net_cls: fix unconfigured struct tcf_proto keeps chaining and avoid kernel panic when we use cls_cgroup This patch fixes a bug which unconfigured struct tcf_proto keeps chaining in tc_ctl_tfilter(), and avoids kernel panic in cls_cgroup_classify() when we use cls_cgroup. When we execute 'tc filter add', tcf_proto is allocated, initialized by classifier's init(), and chained. After it's chained, tc_ctl_tfilter() calls classifier's change(). When classifier's change() fails, tc_ctl_tfilter() does not free and keeps tcf_proto. In addition, cls_cgroup is initialized in change() not in init(). It accesses unconfigured struct tcf_proto which is chained before change(), then hits Oops. Signed-off-by: Minoru Usui Signed-off-by: Jarek Poplawski Signed-off-by: Jamal Hadi Salim Tested-by: Minoru Usui Signed-off-by: David S. Miller --- net/sched/cls_api.c | 23 +++++++++++++++++------ 1 file changed, 17 insertions(+), 6 deletions(-) (limited to 'net') diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 0759f32e9dca..09cdcdfe7e91 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -135,6 +135,7 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n, void *arg) unsigned long cl; unsigned long fh; int err; + int tp_created = 0; if (net != &init_net) return -EINVAL; @@ -266,10 +267,7 @@ replay: goto errout; } - spin_lock_bh(root_lock); - tp->next = *back; - *back = tp; - spin_unlock_bh(root_lock); + tp_created = 1; } else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) goto errout; @@ -296,8 +294,11 @@ replay: switch (n->nlmsg_type) { case RTM_NEWTFILTER: err = -EEXIST; - if (n->nlmsg_flags & NLM_F_EXCL) + if (n->nlmsg_flags & NLM_F_EXCL) { + if (tp_created) + tcf_destroy(tp); goto errout; + } break; case RTM_DELTFILTER: err = tp->ops->delete(tp, fh); @@ -314,8 +315,18 @@ replay: } err = tp->ops->change(tp, cl, t->tcm_handle, tca, &fh); - if (err == 0) + if (err == 0) { + if (tp_created) { + spin_lock_bh(root_lock); + tp->next = *back; + *back = tp; + spin_unlock_bh(root_lock); + } tfilter_notify(skb, n, tp, fh, RTM_NEWTFILTER); + } else { + if (tp_created) + tcf_destroy(tp); + } errout: if (cl) -- cgit v1.2.3