From b9baa0aa66cef9e26b15372d6c56106a4f3b8439 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Mon, 16 May 2016 15:11:18 -0700 Subject: net_sched: close another race condition in tcf_mirred_release() commit dc327f8931cb9d66191f489eb9a852fc04530546 upstream. We saw the following extra refcount release on veth device: kernel: [7957821.463992] unregister_netdevice: waiting for mesos50284 to become free. Usage count = -1 Since we heavily use mirred action to redirect packets to veth, I think this is caused by the following race condition: CPU0: tcf_mirred_release(): (in RCU callback) struct net_device *dev = rcu_dereference_protected(m->tcfm_dev, 1); CPU1: mirred_device_event(): spin_lock_bh(&mirred_list_lock); list_for_each_entry(m, &mirred_list, tcfm_list) { if (rcu_access_pointer(m->tcfm_dev) == dev) { dev_put(dev); /* Note : no rcu grace period necessary, as * net_device are already rcu protected. */ RCU_INIT_POINTER(m->tcfm_dev, NULL); } } spin_unlock_bh(&mirred_list_lock); CPU0: tcf_mirred_release(): spin_lock_bh(&mirred_list_lock); list_del(&m->tcfm_list); spin_unlock_bh(&mirred_list_lock); if (dev) // <======== Stil refers to the old m->tcfm_dev dev_put(dev); // <======== dev_put() is called on it again The action init code path is good because it is impossible to modify an action that is being removed. So, fix this by moving everything under the spinlock. Fixes: 2ee22a90c7af ("net_sched: act_mirred: remove spinlock in fast path") Fixes: 6bd00b850635 ("act_mirred: fix a race condition on mirred_list") Cc: Jamal Hadi Salim Signed-off-by: Cong Wang Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller Cc: Julia Lawall Signed-off-by: Greg Kroah-Hartman --- net/sched/act_mirred.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index e384d6aefa3a..1090a52c03cd 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -36,14 +36,15 @@ static DEFINE_SPINLOCK(mirred_list_lock); static void tcf_mirred_release(struct tc_action *a, int bind) { struct tcf_mirred *m = to_mirred(a); - struct net_device *dev = rcu_dereference_protected(m->tcfm_dev, 1); + struct net_device *dev; /* We could be called either in a RCU callback or with RTNL lock held. */ spin_lock_bh(&mirred_list_lock); list_del(&m->tcfm_list); - spin_unlock_bh(&mirred_list_lock); + dev = rcu_dereference_protected(m->tcfm_dev, 1); if (dev) dev_put(dev); + spin_unlock_bh(&mirred_list_lock); } static const struct nla_policy mirred_policy[TCA_MIRRED_MAX + 1] = { -- cgit v1.2.3 From 804605eae410ef1d1f904706eaf50400c897434b Mon Sep 17 00:00:00 2001 From: "santosh.shilimkar@oracle.com" Date: Thu, 14 Apr 2016 10:43:27 -0700 Subject: RDS: Fix the atomicity for congestion map update commit e47db94e10447fc467777a40302f2b393e9af2fa upstream. Two different threads with different rds sockets may be in rds_recv_rcvbuf_delta() via receive path. If their ports both map to the same word in the congestion map, then using non-atomic ops to update it could cause the map to be incorrect. Lets use atomics to avoid such an issue. Full credit to Wengang for finding the issue, analysing it and also pointing out to offending code with spin lock based fix. Reviewed-by: Leon Romanovsky Signed-off-by: Wengang Wang Signed-off-by: Santosh Shilimkar Signed-off-by: David S. Miller Cc: Julia Lawall Signed-off-by: Greg Kroah-Hartman --- net/rds/cong.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/rds/cong.c b/net/rds/cong.c index e6144b8246fd..6641bcf7c185 100644 --- a/net/rds/cong.c +++ b/net/rds/cong.c @@ -299,7 +299,7 @@ void rds_cong_set_bit(struct rds_cong_map *map, __be16 port) i = be16_to_cpu(port) / RDS_CONG_MAP_PAGE_BITS; off = be16_to_cpu(port) % RDS_CONG_MAP_PAGE_BITS; - __set_bit_le(off, (void *)map->m_page_addrs[i]); + set_bit_le(off, (void *)map->m_page_addrs[i]); } void rds_cong_clear_bit(struct rds_cong_map *map, __be16 port) @@ -313,7 +313,7 @@ void rds_cong_clear_bit(struct rds_cong_map *map, __be16 port) i = be16_to_cpu(port) / RDS_CONG_MAP_PAGE_BITS; off = be16_to_cpu(port) % RDS_CONG_MAP_PAGE_BITS; - __clear_bit_le(off, (void *)map->m_page_addrs[i]); + clear_bit_le(off, (void *)map->m_page_addrs[i]); } static int rds_cong_test_bit(struct rds_cong_map *map, __be16 port) -- cgit v1.2.3 From 428b3cefab22d21013c2a03b8153eefe3df1f576 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 23 Mar 2017 12:39:21 -0700 Subject: net: neigh: guard against NULL solicit() method [ Upstream commit 48481c8fa16410ffa45939b13b6c53c2ca609e5f ] Dmitry posted a nice reproducer of a bug triggering in neigh_probe() when dereferencing a NULL neigh->ops->solicit method. This can happen for arp_direct_ops/ndisc_direct_ops and similar, which can be used for NUD_NOARP neighbours (created when dev->header_ops is NULL). Admin can then force changing nud_state to some other state that would fire neigh timer. Signed-off-by: Eric Dumazet Reported-by: Dmitry Vyukov Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/core/neighbour.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 769cece9b00b..ae92131c4f89 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -859,7 +859,8 @@ static void neigh_probe(struct neighbour *neigh) if (skb) skb = skb_clone(skb, GFP_ATOMIC); write_unlock(&neigh->lock); - neigh->ops->solicit(neigh, skb); + if (neigh->ops->solicit) + neigh->ops->solicit(neigh, skb); atomic_inc(&neigh->probes); kfree_skb(skb); } -- cgit v1.2.3 From 8625dfcfd338254131a7fa650dfbcaf42e4c52ae Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Wed, 29 Mar 2017 08:45:29 +0200 Subject: l2tp: purge socket queues in the .destruct() callback [ Upstream commit e91793bb615cf6cdd59c0b6749fe173687bb0947 ] The Rx path may grab the socket right before pppol2tp_release(), but nothing guarantees that it will enqueue packets before skb_queue_purge(). Therefore, the socket can be destroyed without its queues fully purged. Fix this by purging queues in pppol2tp_session_destruct() where we're guaranteed nothing is still referencing the socket. Fixes: 9e9cb6221aa7 ("l2tp: fix userspace reception on plain L2TP sockets") Signed-off-by: Guillaume Nault Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/l2tp/l2tp_ppp.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 1ad18c55064c..cb0fa348abf9 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -467,6 +467,10 @@ static void pppol2tp_session_close(struct l2tp_session *session) static void pppol2tp_session_destruct(struct sock *sk) { struct l2tp_session *session = sk->sk_user_data; + + skb_queue_purge(&sk->sk_receive_queue); + skb_queue_purge(&sk->sk_write_queue); + if (session) { sk->sk_user_data = NULL; BUG_ON(session->magic != L2TP_SESSION_MAGIC); @@ -505,9 +509,6 @@ static int pppol2tp_release(struct socket *sock) l2tp_session_queue_purge(session); sock_put(sk); } - skb_queue_purge(&sk->sk_receive_queue); - skb_queue_purge(&sk->sk_write_queue); - release_sock(sk); /* This will delete the session context via -- cgit v1.2.3 From cf71bd41f8091588c7b28ebba6eaa635a6874493 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Wed, 29 Mar 2017 16:11:21 +0200 Subject: net/packet: fix overflow in check for tp_frame_nr [ Upstream commit 8f8d28e4d6d815a391285e121c3a53a0b6cb9e7b ] When calculating rb->frames_per_block * req->tp_block_nr the result can overflow. Add a check that tp_block_size * tp_block_nr <= UINT_MAX. Since frames_per_block <= tp_block_size, the expression would never overflow. Signed-off-by: Andrey Konovalov Acked-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/packet/af_packet.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net') diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index d76800108ddb..b4af3f7b57ab 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -4150,6 +4150,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, rb->frames_per_block = req->tp_block_size / req->tp_frame_size; if (unlikely(rb->frames_per_block == 0)) goto out; + if (unlikely(req->tp_block_size > UINT_MAX / req->tp_block_nr)) + goto out; if (unlikely((rb->frames_per_block * req->tp_block_nr) != req->tp_frame_nr)) goto out; -- cgit v1.2.3 From 25adf4e32a890244f4f53d2ab30b423efb5aab41 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Wed, 29 Mar 2017 16:11:22 +0200 Subject: net/packet: fix overflow in check for tp_reserve [ Upstream commit bcc5364bdcfe131e6379363f089e7b4108d35b70 ] When calculating po->tp_hdrlen + po->tp_reserve the result can overflow. Fix by checking that tp_reserve <= INT_MAX on assign. Signed-off-by: Andrey Konovalov Acked-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/packet/af_packet.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net') diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index b4af3f7b57ab..f8d6a0ca9c03 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3626,6 +3626,8 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv return -EBUSY; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; + if (val > INT_MAX) + return -EINVAL; po->tp_reserve = val; return 0; } -- cgit v1.2.3 From f710dbd92b277232079fc662c1dd8433491b7d6c Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Mon, 3 Apr 2017 12:03:13 +0200 Subject: l2tp: take reference on sessions being dumped [ Upstream commit e08293a4ccbcc993ded0fdc46f1e57926b833d63 ] Take a reference on the sessions returned by l2tp_session_find_nth() (and rename it l2tp_session_get_nth() to reflect this change), so that caller is assured that the session isn't going to disappear while processing it. For procfs and debugfs handlers, the session is held in the .start() callback and dropped in .show(). Given that pppol2tp_seq_session_show() dereferences the associated PPPoL2TP socket and that l2tp_dfs_seq_session_show() might call pppol2tp_show(), we also need to call the session's .ref() callback to prevent the socket from going away from under us. Fixes: fd558d186df2 ("l2tp: Split pppol2tp patch into separate l2tp and ppp parts") Fixes: 0ad6614048cf ("l2tp: Add debugfs files for dumping l2tp debug info") Fixes: 309795f4bec2 ("l2tp: Add netlink control API for L2TP") Signed-off-by: Guillaume Nault Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/l2tp/l2tp_core.c | 8 ++++++-- net/l2tp/l2tp_core.h | 3 ++- net/l2tp/l2tp_debugfs.c | 10 +++++++--- net/l2tp/l2tp_netlink.c | 7 +++++-- net/l2tp/l2tp_ppp.c | 10 +++++++--- 5 files changed, 27 insertions(+), 11 deletions(-) (limited to 'net') diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index ec17cbe8a02b..d3dec414fd44 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -278,7 +278,8 @@ struct l2tp_session *l2tp_session_find(struct net *net, struct l2tp_tunnel *tunn } EXPORT_SYMBOL_GPL(l2tp_session_find); -struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth) +struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth, + bool do_ref) { int hash; struct l2tp_session *session; @@ -288,6 +289,9 @@ struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth) for (hash = 0; hash < L2TP_HASH_SIZE; hash++) { hlist_for_each_entry(session, &tunnel->session_hlist[hash], hlist) { if (++count > nth) { + l2tp_session_inc_refcount(session); + if (do_ref && session->ref) + session->ref(session); read_unlock_bh(&tunnel->hlist_lock); return session; } @@ -298,7 +302,7 @@ struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth) return NULL; } -EXPORT_SYMBOL_GPL(l2tp_session_find_nth); +EXPORT_SYMBOL_GPL(l2tp_session_get_nth); /* Lookup a session by interface name. * This is very inefficient but is only used by management interfaces. diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 763e8e241ce3..555d962a62d2 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -243,7 +243,8 @@ out: struct l2tp_session *l2tp_session_find(struct net *net, struct l2tp_tunnel *tunnel, u32 session_id); -struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth); +struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth, + bool do_ref); struct l2tp_session *l2tp_session_find_by_ifname(struct net *net, char *ifname); struct l2tp_tunnel *l2tp_tunnel_find(struct net *net, u32 tunnel_id); struct l2tp_tunnel *l2tp_tunnel_find_nth(struct net *net, int nth); diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index 2d6760a2ae34..d100aed3d06f 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -53,7 +53,7 @@ static void l2tp_dfs_next_tunnel(struct l2tp_dfs_seq_data *pd) static void l2tp_dfs_next_session(struct l2tp_dfs_seq_data *pd) { - pd->session = l2tp_session_find_nth(pd->tunnel, pd->session_idx); + pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx, true); pd->session_idx++; if (pd->session == NULL) { @@ -238,10 +238,14 @@ static int l2tp_dfs_seq_show(struct seq_file *m, void *v) } /* Show the tunnel or session context */ - if (pd->session == NULL) + if (!pd->session) { l2tp_dfs_seq_tunnel_show(m, pd->tunnel); - else + } else { l2tp_dfs_seq_session_show(m, pd->session); + if (pd->session->deref) + pd->session->deref(pd->session); + l2tp_session_dec_refcount(pd->session); + } out: return 0; diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index 2caaa84ce92d..665cc74df5c5 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -827,7 +827,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback goto out; } - session = l2tp_session_find_nth(tunnel, si); + session = l2tp_session_get_nth(tunnel, si, false); if (session == NULL) { ti++; tunnel = NULL; @@ -837,8 +837,11 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback if (l2tp_nl_session_send(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - session, L2TP_CMD_SESSION_GET) < 0) + session, L2TP_CMD_SESSION_GET) < 0) { + l2tp_session_dec_refcount(session); break; + } + l2tp_session_dec_refcount(session); si++; } diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index cb0fa348abf9..ad80ee5400da 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -1575,7 +1575,7 @@ static void pppol2tp_next_tunnel(struct net *net, struct pppol2tp_seq_data *pd) static void pppol2tp_next_session(struct net *net, struct pppol2tp_seq_data *pd) { - pd->session = l2tp_session_find_nth(pd->tunnel, pd->session_idx); + pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx, true); pd->session_idx++; if (pd->session == NULL) { @@ -1702,10 +1702,14 @@ static int pppol2tp_seq_show(struct seq_file *m, void *v) /* Show the tunnel or session context. */ - if (pd->session == NULL) + if (!pd->session) { pppol2tp_seq_tunnel_show(m, pd->tunnel); - else + } else { pppol2tp_seq_session_show(m, pd->session); + if (pd->session->deref) + pd->session->deref(pd->session); + l2tp_session_dec_refcount(pd->session); + } out: return 0; -- cgit v1.2.3 From 593e185eaadeefdc05a5e595428aec468646165a Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Mon, 3 Apr 2017 13:23:15 +0200 Subject: l2tp: fix PPP pseudo-wire auto-loading [ Upstream commit 249ee819e24c180909f43c1173c8ef6724d21faf ] PPP pseudo-wire type is 7 (11 is L2TP_PWTYPE_IP). Fixes: f1f39f911027 ("l2tp: auto load type modules") Signed-off-by: Guillaume Nault Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/l2tp/l2tp_ppp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index ad80ee5400da..8ab9c5d74416 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -1868,4 +1868,4 @@ MODULE_DESCRIPTION("PPP over L2TP over UDP"); MODULE_LICENSE("GPL"); MODULE_VERSION(PPPOL2TP_DRV_VERSION); MODULE_ALIAS("pppox-proto-" __stringify(PX_PROTO_OL2TP)); -MODULE_ALIAS_L2TP_PWTYPE(11); +MODULE_ALIAS_L2TP_PWTYPE(7); -- cgit v1.2.3 From cc5a5c09d32b8bd80477f45f12f47ca43536b19c Mon Sep 17 00:00:00 2001 From: Florian Larysch Date: Mon, 3 Apr 2017 16:46:09 +0200 Subject: net: ipv4: fix multipath RTM_GETROUTE behavior when iif is given [ Upstream commit a8801799c6975601fd58ae62f48964caec2eb83f ] inet_rtm_getroute synthesizes a skeletal ICMP skb, which is passed to ip_route_input when iif is given. If a multipath route is present for the designated destination, ip_multipath_icmp_hash ends up being called, which uses the source/destination addresses within the skb to calculate a hash. However, those are not set in the synthetic skb, causing it to return an arbitrary and incorrect result. Instead, use UDP, which gets no such special treatment. Signed-off-by: Florian Larysch Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/route.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/ipv4/route.c b/net/ipv4/route.c index da4d68d78590..375248b900ba 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2559,7 +2559,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh) skb_reset_network_header(skb); /* Bugfix: need to give ip_route_input enough of an IP header to not gag. */ - ip_hdr(skb)->protocol = IPPROTO_ICMP; + ip_hdr(skb)->protocol = IPPROTO_UDP; skb_reserve(skb, MAX_HEADER + sizeof(struct iphdr)); src = tb[RTA_SRC] ? nla_get_in_addr(tb[RTA_SRC]) : 0; -- cgit v1.2.3 From 52e33b4e505dedc8708581c3dd539ded37df1c9f Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 6 Apr 2017 13:10:52 +0800 Subject: sctp: listen on the sock only when it's state is listening or closed [ Upstream commit 34b2789f1d9bf8dcca9b5cb553d076ca2cd898ee ] Now sctp doesn't check sock's state before listening on it. It could even cause changing a sock with any state to become a listening sock when doing sctp_listen. This patch is to fix it by checking sock's state in sctp_listen, so that it will listen on the sock with right state. Reported-by: Andrey Konovalov Tested-by: Andrey Konovalov Signed-off-by: Xin Long Acked-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/sctp/socket.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'net') diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 5758818435f3..c96d666cef29 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -6394,6 +6394,9 @@ int sctp_inet_listen(struct socket *sock, int backlog) if (sock->state != SS_UNCONNECTED) goto out; + if (!sctp_sstate(sk, LISTENING) && !sctp_sstate(sk, CLOSED)) + goto out; + /* If backlog is zero, disable listening. */ if (!backlog) { if (sctp_sstate(sk, CLOSED)) -- cgit v1.2.3 From 78c4e3d4848d86c1ed36181c71c9c96834e910ed Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 8 Apr 2017 08:07:33 -0700 Subject: tcp: clear saved_syn in tcp_disconnect() [ Upstream commit 17c3060b1701fc69daedb4c90be6325d3d9fca8e ] In the (very unlikely) case a passive socket becomes a listener, we do not want to duplicate its saved SYN headers. This would lead to double frees, use after free, and please hackers and various fuzzers Tested: 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 +0 setsockopt(3, IPPROTO_TCP, TCP_SAVE_SYN, [1], 4) = 0 +0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0 +0 bind(3, ..., ...) = 0 +0 listen(3, 5) = 0 +0 < S 0:0(0) win 32972 +0 > S. 0:0(0) ack 1 <...> +.1 < . 1:1(0) ack 1 win 257 +0 accept(3, ..., ...) = 4 +0 connect(4, AF_UNSPEC, ...) = 0 +0 close(3) = 0 +0 bind(4, ..., ...) = 0 +0 listen(4, 5) = 0 +0 < S 0:0(0) win 32972 +0 > S. 0:0(0) ack 1 <...> +.1 < . 1:1(0) ack 1 win 257 Fixes: cd8ae85299d5 ("tcp: provide SYN headers for passive connections") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 600dcda840d1..e1d51370977b 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2260,6 +2260,7 @@ int tcp_disconnect(struct sock *sk, int flags) tcp_init_send_head(sk); memset(&tp->rx_opt, 0, sizeof(tp->rx_opt)); __sk_dst_reset(sk); + tcp_saved_syn_free(tp); WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); -- cgit v1.2.3 From f6b94906b41497a1fa2c4acd055d550c501cd58b Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 19 Apr 2017 14:19:43 -0700 Subject: net: ipv6: RTF_PCPU should not be settable from userspace [ Upstream commit 557c44be917c322860665be3d28376afa84aa936 ] Andrey reported a fault in the IPv6 route code: kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP KASAN Modules linked in: CPU: 1 PID: 4035 Comm: a.out Not tainted 4.11.0-rc7+ #250 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 task: ffff880069809600 task.stack: ffff880062dc8000 RIP: 0010:ip6_rt_cache_alloc+0xa6/0x560 net/ipv6/route.c:975 RSP: 0018:ffff880062dced30 EFLAGS: 00010206 RAX: dffffc0000000000 RBX: ffff8800670561c0 RCX: 0000000000000006 RDX: 0000000000000003 RSI: ffff880062dcfb28 RDI: 0000000000000018 RBP: ffff880062dced68 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 R13: ffff880062dcfb28 R14: dffffc0000000000 R15: 0000000000000000 FS: 00007feebe37e7c0(0000) GS:ffff88006cb00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000205a0fe4 CR3: 000000006b5c9000 CR4: 00000000000006e0 Call Trace: ip6_pol_route+0x1512/0x1f20 net/ipv6/route.c:1128 ip6_pol_route_output+0x4c/0x60 net/ipv6/route.c:1212 ... Andrey's syzkaller program passes rtmsg.rtmsg_flags with the RTF_PCPU bit set. Flags passed to the kernel are blindly copied to the allocated rt6_info by ip6_route_info_create making a newly inserted route appear as though it is a per-cpu route. ip6_rt_cache_alloc sees the flag set and expects rt->dst.from to be set - which it is not since it is not really a per-cpu copy. The subsequent call to __ip6_dst_alloc then generates the fault. Fix by checking for the flag and failing with EINVAL. Fixes: d52d3997f843f ("ipv6: Create percpu rt6_info") Reported-by: Andrey Konovalov Signed-off-by: David Ahern Acked-by: Martin KaFai Lau Tested-by: Andrey Konovalov Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv6/route.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net') diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 9f0aa255e288..6c91d5c4a92c 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1758,6 +1758,10 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg) int addr_type; int err = -EINVAL; + /* RTF_PCPU is an internal flag; can not be set by userspace */ + if (cfg->fc_flags & RTF_PCPU) + goto out; + if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128) goto out; #ifndef CONFIG_IPV6_SUBTREES -- cgit v1.2.3 From 25c1040233728451a4c56083407ffd398c9f3759 Mon Sep 17 00:00:00 2001 From: Tushar Dave Date: Thu, 20 Apr 2017 15:57:31 -0700 Subject: netpoll: Check for skb->queue_mapping [ Upstream commit c70b17b775edb21280e9de7531acf6db3b365274 ] Reducing real_num_tx_queues needs to be in sync with skb queue_mapping otherwise skbs with queue_mapping greater than real_num_tx_queues can be sent to the underlying driver and can result in kernel panic. One such event is running netconsole and enabling VF on the same device. Or running netconsole and changing number of tx queues via ethtool on same device. e.g. Unable to handle kernel NULL pointer dereference tsk->{mm,active_mm}->context = 0000000000001525 tsk->{mm,active_mm}->pgd = fff800130ff9a000 \|/ ____ \|/ "@'/ .. \`@" /_| \__/ |_\ \__U_/ kworker/48:1(475): Oops [#1] CPU: 48 PID: 475 Comm: kworker/48:1 Tainted: G OE 4.11.0-rc3-davem-net+ #7 Workqueue: events queue_process task: fff80013113299c0 task.stack: fff800131132c000 TSTATE: 0000004480e01600 TPC: 00000000103f9e3c TNPC: 00000000103f9e40 Y: 00000000 Tainted: G OE TPC: g0: 0000000000000000 g1: 0000000000003fff g2: 0000000000000000 g3: 0000000000000001 g4: fff80013113299c0 g5: fff8001fa6808000 g6: fff800131132c000 g7: 00000000000000c0 o0: fff8001fa760c460 o1: fff8001311329a50 o2: fff8001fa7607504 o3: 0000000000000003 o4: fff8001f96e63a40 o5: fff8001311d77ec0 sp: fff800131132f0e1 ret_pc: 000000000049ed94 RPC: l0: 0000000000000000 l1: 0000000000000800 l2: 0000000000000000 l3: 0000000000000000 l4: 000b2aa30e34b10d l5: 0000000000000000 l6: 0000000000000000 l7: fff8001fa7605028 i0: fff80013111a8a00 i1: fff80013155a0780 i2: 0000000000000000 i3: 0000000000000000 i4: 0000000000000000 i5: 0000000000100000 i6: fff800131132f1a1 i7: 00000000103fa4b0 I7: Call Trace: [00000000103fa4b0] ixgbe_xmit_frame+0x30/0xa0 [ixgbe] [0000000000998c74] netpoll_start_xmit+0xf4/0x200 [0000000000998e10] queue_process+0x90/0x160 [0000000000485fa8] process_one_work+0x188/0x480 [0000000000486410] worker_thread+0x170/0x4c0 [000000000048c6b8] kthread+0xd8/0x120 [0000000000406064] ret_from_fork+0x1c/0x2c [0000000000000000] (null) Disabling lock debugging due to kernel taint Caller[00000000103fa4b0]: ixgbe_xmit_frame+0x30/0xa0 [ixgbe] Caller[0000000000998c74]: netpoll_start_xmit+0xf4/0x200 Caller[0000000000998e10]: queue_process+0x90/0x160 Caller[0000000000485fa8]: process_one_work+0x188/0x480 Caller[0000000000486410]: worker_thread+0x170/0x4c0 Caller[000000000048c6b8]: kthread+0xd8/0x120 Caller[0000000000406064]: ret_from_fork+0x1c/0x2c Caller[0000000000000000]: (null) Signed-off-by: Tushar Dave Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/core/netpoll.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 94acfc89ad97..440aa9f6e0a8 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -105,15 +105,21 @@ static void queue_process(struct work_struct *work) while ((skb = skb_dequeue(&npinfo->txq))) { struct net_device *dev = skb->dev; struct netdev_queue *txq; + unsigned int q_index; if (!netif_device_present(dev) || !netif_running(dev)) { kfree_skb(skb); continue; } - txq = skb_get_tx_queue(dev, skb); - local_irq_save(flags); + /* check if skb->queue_mapping is still valid */ + q_index = skb_get_queue_mapping(skb); + if (unlikely(q_index >= dev->real_num_tx_queues)) { + q_index = q_index % dev->real_num_tx_queues; + skb_set_queue_mapping(skb, q_index); + } + txq = netdev_get_tx_queue(dev, q_index); HARD_TX_LOCK(dev, txq, smp_processor_id()); if (netif_xmit_frozen_or_stopped(txq) || netpoll_start_xmit(skb, dev, txq) != NETDEV_TX_OK) { -- cgit v1.2.3 From bdeb026dfd9f27ec2e4a0ea97dab0e6e3d96e632 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Fri, 21 Apr 2017 20:42:16 +0300 Subject: ip6mr: fix notification device destruction [ Upstream commit 723b929ca0f79c0796f160c2eeda4597ee98d2b8 ] Andrey Konovalov reported a BUG caused by the ip6mr code which is caused because we call unregister_netdevice_many for a device that is already being destroyed. In IPv4's ipmr that has been resolved by two commits long time ago by introducing the "notify" parameter to the delete function and avoiding the unregister when called from a notifier, so let's do the same for ip6mr. The trace from Andrey: ------------[ cut here ]------------ kernel BUG at net/core/dev.c:6813! invalid opcode: 0000 [#1] SMP KASAN Modules linked in: CPU: 1 PID: 1165 Comm: kworker/u4:3 Not tainted 4.11.0-rc7+ #251 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Workqueue: netns cleanup_net task: ffff880069208000 task.stack: ffff8800692d8000 RIP: 0010:rollback_registered_many+0x348/0xeb0 net/core/dev.c:6813 RSP: 0018:ffff8800692de7f0 EFLAGS: 00010297 RAX: ffff880069208000 RBX: 0000000000000002 RCX: 0000000000000001 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff88006af90569 RBP: ffff8800692de9f0 R08: ffff8800692dec60 R09: 0000000000000000 R10: 0000000000000006 R11: 0000000000000000 R12: ffff88006af90070 R13: ffff8800692debf0 R14: dffffc0000000000 R15: ffff88006af90000 FS: 0000000000000000(0000) GS:ffff88006cb00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fe7e897d870 CR3: 00000000657e7000 CR4: 00000000000006e0 Call Trace: unregister_netdevice_many.part.105+0x87/0x440 net/core/dev.c:7881 unregister_netdevice_many+0xc8/0x120 net/core/dev.c:7880 ip6mr_device_event+0x362/0x3f0 net/ipv6/ip6mr.c:1346 notifier_call_chain+0x145/0x2f0 kernel/notifier.c:93 __raw_notifier_call_chain kernel/notifier.c:394 raw_notifier_call_chain+0x2d/0x40 kernel/notifier.c:401 call_netdevice_notifiers_info+0x51/0x90 net/core/dev.c:1647 call_netdevice_notifiers net/core/dev.c:1663 rollback_registered_many+0x919/0xeb0 net/core/dev.c:6841 unregister_netdevice_many.part.105+0x87/0x440 net/core/dev.c:7881 unregister_netdevice_many net/core/dev.c:7880 default_device_exit_batch+0x4fa/0x640 net/core/dev.c:8333 ops_exit_list.isra.4+0x100/0x150 net/core/net_namespace.c:144 cleanup_net+0x5a8/0xb40 net/core/net_namespace.c:463 process_one_work+0xc04/0x1c10 kernel/workqueue.c:2097 worker_thread+0x223/0x19c0 kernel/workqueue.c:2231 kthread+0x35e/0x430 kernel/kthread.c:231 ret_from_fork+0x31/0x40 arch/x86/entry/entry_64.S:430 Code: 3c 32 00 0f 85 70 0b 00 00 48 b8 00 02 00 00 00 00 ad de 49 89 47 78 e9 93 fe ff ff 49 8d 57 70 49 8d 5f 78 eb 9e e8 88 7a 14 fe <0f> 0b 48 8b 9d 28 fe ff ff e8 7a 7a 14 fe 48 b8 00 00 00 00 00 RIP: rollback_registered_many+0x348/0xeb0 RSP: ffff8800692de7f0 ---[ end trace e0b29c57e9b3292c ]--- Reported-by: Andrey Konovalov Signed-off-by: Nikolay Aleksandrov Tested-by: Andrey Konovalov Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv6/ip6mr.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) (limited to 'net') diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index d9843e5a667f..8361d73ab653 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -774,7 +774,8 @@ failure: * Delete a VIF entry */ -static int mif6_delete(struct mr6_table *mrt, int vifi, struct list_head *head) +static int mif6_delete(struct mr6_table *mrt, int vifi, int notify, + struct list_head *head) { struct mif_device *v; struct net_device *dev; @@ -820,7 +821,7 @@ static int mif6_delete(struct mr6_table *mrt, int vifi, struct list_head *head) dev->ifindex, &in6_dev->cnf); } - if (v->flags & MIFF_REGISTER) + if ((v->flags & MIFF_REGISTER) && !notify) unregister_netdevice_queue(dev, head); dev_put(dev); @@ -1330,7 +1331,6 @@ static int ip6mr_device_event(struct notifier_block *this, struct mr6_table *mrt; struct mif_device *v; int ct; - LIST_HEAD(list); if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; @@ -1339,10 +1339,9 @@ static int ip6mr_device_event(struct notifier_block *this, v = &mrt->vif6_table[0]; for (ct = 0; ct < mrt->maxvif; ct++, v++) { if (v->dev == dev) - mif6_delete(mrt, ct, &list); + mif6_delete(mrt, ct, 1, NULL); } } - unregister_netdevice_many(&list); return NOTIFY_DONE; } @@ -1551,7 +1550,7 @@ static void mroute_clean_tables(struct mr6_table *mrt, bool all) for (i = 0; i < mrt->maxvif; i++) { if (!all && (mrt->vif6_table[i].flags & VIFF_STATIC)) continue; - mif6_delete(mrt, i, &list); + mif6_delete(mrt, i, 0, &list); } unregister_netdevice_many(&list); @@ -1704,7 +1703,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns if (copy_from_user(&mifi, optval, sizeof(mifi_t))) return -EFAULT; rtnl_lock(); - ret = mif6_delete(mrt, mifi, NULL); + ret = mif6_delete(mrt, mifi, 0, NULL); rtnl_unlock(); return ret; -- cgit v1.2.3 From befb9254243937f676433251cf4f8beb37b02c13 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Tue, 25 Apr 2017 14:37:15 -0700 Subject: ipv6: check skb->protocol before lookup for nexthop [ Upstream commit 199ab00f3cdb6f154ea93fa76fd80192861a821d ] Andrey reported a out-of-bound access in ip6_tnl_xmit(), this is because we use an ipv4 dst in ip6_tnl_xmit() and cast an IPv4 neigh key as an IPv6 address: neigh = dst_neigh_lookup(skb_dst(skb), &ipv6_hdr(skb)->daddr); if (!neigh) goto tx_err_link_failure; addr6 = (struct in6_addr *)&neigh->primary_key; // <=== HERE addr_type = ipv6_addr_type(addr6); if (addr_type == IPV6_ADDR_ANY) addr6 = &ipv6_hdr(skb)->daddr; memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr)); Also the network header of the skb at this point should be still IPv4 for 4in6 tunnels, we shold not just use it as IPv6 header. This patch fixes it by checking if skb->protocol is ETH_P_IPV6: if it is, we are safe to do the nexthop lookup using skb_dst() and ipv6_hdr(skb)->daddr; if not (aka IPv4), we have no clue about which dest address we can pick here, we have to rely on callers to fill it from tunnel config, so just fall to ip6_route_output() to make the decision. Fixes: ea3dc9601bda ("ip6_tunnel: Add support for wildcard tunnel endpoints.") Reported-by: Andrey Konovalov Tested-by: Andrey Konovalov Cc: Steffen Klassert Signed-off-by: Cong Wang Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv6/ip6_tunnel.c | 34 ++++++++++++++++++---------------- 1 file changed, 18 insertions(+), 16 deletions(-) (limited to 'net') diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 6c6161763c2f..97cb02dc5f02 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1049,7 +1049,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, struct ip6_tnl *t = netdev_priv(dev); struct net *net = t->net; struct net_device_stats *stats = &t->dev->stats; - struct ipv6hdr *ipv6h = ipv6_hdr(skb); + struct ipv6hdr *ipv6h; struct ipv6_tel_txoption opt; struct dst_entry *dst = NULL, *ndst = NULL; struct net_device *tdev; @@ -1061,26 +1061,28 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, /* NBMA tunnel */ if (ipv6_addr_any(&t->parms.raddr)) { - struct in6_addr *addr6; - struct neighbour *neigh; - int addr_type; + if (skb->protocol == htons(ETH_P_IPV6)) { + struct in6_addr *addr6; + struct neighbour *neigh; + int addr_type; - if (!skb_dst(skb)) - goto tx_err_link_failure; + if (!skb_dst(skb)) + goto tx_err_link_failure; - neigh = dst_neigh_lookup(skb_dst(skb), - &ipv6_hdr(skb)->daddr); - if (!neigh) - goto tx_err_link_failure; + neigh = dst_neigh_lookup(skb_dst(skb), + &ipv6_hdr(skb)->daddr); + if (!neigh) + goto tx_err_link_failure; - addr6 = (struct in6_addr *)&neigh->primary_key; - addr_type = ipv6_addr_type(addr6); + addr6 = (struct in6_addr *)&neigh->primary_key; + addr_type = ipv6_addr_type(addr6); - if (addr_type == IPV6_ADDR_ANY) - addr6 = &ipv6_hdr(skb)->daddr; + if (addr_type == IPV6_ADDR_ANY) + addr6 = &ipv6_hdr(skb)->daddr; - memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr)); - neigh_release(neigh); + memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr)); + neigh_release(neigh); + } } else if (!(t->parms.flags & (IP6_TNL_F_USE_ORIG_TCLASS | IP6_TNL_F_USE_ORIG_FWMARK))) { /* enable the cache only only if the routing decision does -- cgit v1.2.3 From 5e52fffbb11c28c37fe8e335fdd8e9705daff06d Mon Sep 17 00:00:00 2001 From: Jamie Bainbridge Date: Wed, 26 Apr 2017 10:43:27 +1000 Subject: ipv6: check raw payload size correctly in ioctl [ Upstream commit 105f5528b9bbaa08b526d3405a5bcd2ff0c953c8 ] In situations where an skb is paged, the transport header pointer and tail pointer can be the same because the skb contents are in frags. This results in ioctl(SIOCINQ/FIONREAD) incorrectly returning a length of 0 when the length to receive is actually greater than zero. skb->len is already correctly set in ip6_input_finish() with pskb_pull(), so use skb->len as it always returns the correct result for both linear and paged data. Signed-off-by: Jamie Bainbridge Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv6/raw.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'net') diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 8bca90d6d915..a625f69a28dd 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -1144,8 +1144,7 @@ static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg) spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); if (skb) - amount = skb_tail_pointer(skb) - - skb_transport_header(skb); + amount = skb->len; spin_unlock_bh(&sk->sk_receive_queue.lock); return put_user(amount, (int __user *)arg); } -- cgit v1.2.3 From 91ce8d13faeb32d0b5544674a1ac8d955c8f4891 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 14 Apr 2017 17:22:18 -0400 Subject: p9_client_readdir() fix commit 71d6ad08379304128e4bdfaf0b4185d54375423e upstream. Don't assume that server is sane and won't return more data than asked for. Signed-off-by: Al Viro Signed-off-by: Greg Kroah-Hartman --- net/9p/client.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net') diff --git a/net/9p/client.c b/net/9p/client.c index ea79ee9a7348..f5feac4ff4ec 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -2101,6 +2101,10 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset) trace_9p_protocol_dump(clnt, req->rc); goto free_and_error; } + if (rsize < count) { + pr_err("bogus RREADDIR count (%d > %d)\n", count, rsize); + count = rsize; + } p9_debug(P9_DEBUG_9P, "<<< RREADDIR count %d\n", count); -- cgit v1.2.3