From d93c6258ee4255749c10012c50a31c08f4e9fb16 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 20 Jan 2016 11:16:43 +0100 Subject: netfilter: conntrack: resched in nf_ct_iterate_cleanup Ulrich reports soft lockup with following (shortened) callchain: NMI watchdog: BUG: soft lockup - CPU#1 stuck for 22s! __netif_receive_skb_core+0x6e4/0x774 process_backlog+0x94/0x160 net_rx_action+0x88/0x178 call_do_softirq+0x24/0x3c do_softirq+0x54/0x6c __local_bh_enable_ip+0x7c/0xbc nf_ct_iterate_cleanup+0x11c/0x22c [nf_conntrack] masq_inet_event+0x20/0x30 [nf_nat_masquerade_ipv6] atomic_notifier_call_chain+0x1c/0x2c ipv6_del_addr+0x1bc/0x220 [ipv6] Problem is that nf_ct_iterate_cleanup can run for a very long time since it can be interrupted by softirq processing. Moreover, atomic_notifier_call_chain runs with rcu readlock held. So lets call cond_resched() in nf_ct_iterate_cleanup and defer the call to a work queue for the atomic_notifier_call_chain case. We also need another cond_resched in get_next_corpse, since we have to deal with iter() always returning false, in that case get_next_corpse will walk entire conntrack table. Reported-by: Ulrich Weber Tested-by: Ulrich Weber Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/ipv6/netfilter/nf_nat_masquerade_ipv6.c | 74 +++++++++++++++++++++++++++-- 1 file changed, 71 insertions(+), 3 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c index 31ba7ca19757..051b6a6bfff6 100644 --- a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c @@ -21,6 +21,10 @@ #include #include +#define MAX_WORK_COUNT 16 + +static atomic_t v6_worker_count; + unsigned int nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range *range, const struct net_device *out) @@ -78,14 +82,78 @@ static struct notifier_block masq_dev_notifier = { .notifier_call = masq_device_event, }; +struct masq_dev_work { + struct work_struct work; + struct net *net; + int ifindex; +}; + +static void iterate_cleanup_work(struct work_struct *work) +{ + struct masq_dev_work *w; + long index; + + w = container_of(work, struct masq_dev_work, work); + + index = w->ifindex; + nf_ct_iterate_cleanup(w->net, device_cmp, (void *)index, 0, 0); + + put_net(w->net); + kfree(w); + atomic_dec(&v6_worker_count); + module_put(THIS_MODULE); +} + +/* ipv6 inet notifier is an atomic notifier, i.e. we cannot + * schedule. + * + * Unfortunately, nf_ct_iterate_cleanup can run for a long + * time if there are lots of conntracks and the system + * handles high softirq load, so it frequently calls cond_resched + * while iterating the conntrack table. + * + * So we defer nf_ct_iterate_cleanup walk to the system workqueue. + * + * As we can have 'a lot' of inet_events (depending on amount + * of ipv6 addresses being deleted), we also need to add an upper + * limit to the number of queued work items. + */ static int masq_inet_event(struct notifier_block *this, unsigned long event, void *ptr) { struct inet6_ifaddr *ifa = ptr; - struct netdev_notifier_info info; + const struct net_device *dev; + struct masq_dev_work *w; + struct net *net; + + if (event != NETDEV_DOWN || + atomic_read(&v6_worker_count) >= MAX_WORK_COUNT) + return NOTIFY_DONE; + + dev = ifa->idev->dev; + net = maybe_get_net(dev_net(dev)); + if (!net) + return NOTIFY_DONE; - netdev_notifier_info_init(&info, ifa->idev->dev); - return masq_device_event(this, event, &info); + if (!try_module_get(THIS_MODULE)) + goto err_module; + + w = kmalloc(sizeof(*w), GFP_ATOMIC); + if (w) { + atomic_inc(&v6_worker_count); + + INIT_WORK(&w->work, iterate_cleanup_work); + w->ifindex = dev->ifindex; + w->net = net; + schedule_work(&w->work); + + return NOTIFY_DONE; + } + + module_put(THIS_MODULE); + err_module: + put_net(net); + return NOTIFY_DONE; } static struct notifier_block masq_inet_notifier = { -- cgit v1.2.3 From 16186a82de1fdd868255448274e64ae2616e2640 Mon Sep 17 00:00:00 2001 From: "subashab@codeaurora.org" Date: Tue, 2 Feb 2016 02:11:10 +0000 Subject: ipv6: addrconf: Fix recursive spin lock call A rcu stall with the following backtrace was seen on a system with forwarding, optimistic_dad and use_optimistic set. To reproduce, set these flags and allow ipv6 autoconf. This occurs because the device write_lock is acquired while already holding the read_lock. Back trace below - INFO: rcu_preempt self-detected stall on CPU { 1} (t=2100 jiffies g=3992 c=3991 q=4471) <6> Task dump for CPU 1: <2> kworker/1:0 R running task 12168 15 2 0x00000002 <2> Workqueue: ipv6_addrconf addrconf_dad_work <6> Call trace: <2> [] el1_irq+0x68/0xdc <2> [] _raw_write_lock_bh+0x20/0x30 <2> [] __ipv6_dev_ac_inc+0x64/0x1b4 <2> [] addrconf_join_anycast+0x9c/0xc4 <2> [] __ipv6_ifa_notify+0x160/0x29c <2> [] ipv6_ifa_notify+0x50/0x70 <2> [] addrconf_dad_work+0x314/0x334 <2> [] process_one_work+0x244/0x3fc <2> [] worker_thread+0x2f8/0x418 <2> [] kthread+0xe0/0xec v2: do addrconf_dad_kick inside read lock and then acquire write lock for ipv6_ifa_notify as suggested by Eric Fixes: 7fd2561e4ebdd ("net: ipv6: Add a sysctl to make optimistic addresses useful candidates") Cc: Eric Dumazet Cc: Erik Kline Cc: Hannes Frederic Sowa Signed-off-by: Subash Abhinov Kasiviswanathan Acked-by: Hannes Frederic Sowa Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'net/ipv6') diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 38eeddedfc21..9efd9ffdc34c 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3538,6 +3538,7 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) { struct inet6_dev *idev = ifp->idev; struct net_device *dev = idev->dev; + bool notify = false; addrconf_join_solict(dev, &ifp->addr); @@ -3583,7 +3584,7 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) /* Because optimistic nodes can use this address, * notify listeners. If DAD fails, RTM_DELADDR is sent. */ - ipv6_ifa_notify(RTM_NEWADDR, ifp); + notify = true; } } @@ -3591,6 +3592,8 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) out: spin_unlock(&ifp->lock); read_unlock_bh(&idev->lock); + if (notify) + ipv6_ifa_notify(RTM_NEWADDR, ifp); } static void addrconf_dad_start(struct inet6_ifaddr *ifp) -- cgit v1.2.3 From 44c3d0c1c0a880354e9de5d94175742e2c7c9683 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 2 Feb 2016 17:55:01 -0800 Subject: ipv6: fix a lockdep splat Silence lockdep false positive about rcu_dereference() being used in the wrong context. First one should use rcu_dereference_protected() as we own the spinlock. Second one should be a normal assignation, as no barrier is needed. Fixes: 18367681a10bd ("ipv6 flowlabel: Convert np->ipv6_fl_list to RCU.") Reported-by: Dave Jones Signed-off-by: Eric Dumazet Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/ipv6/ip6_flowlabel.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 1f9ebe3cbb4a..dc2db4f7b182 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -540,12 +540,13 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) } spin_lock_bh(&ip6_sk_fl_lock); for (sflp = &np->ipv6_fl_list; - (sfl = rcu_dereference(*sflp)) != NULL; + (sfl = rcu_dereference_protected(*sflp, + lockdep_is_held(&ip6_sk_fl_lock))) != NULL; sflp = &sfl->next) { if (sfl->fl->label == freq.flr_label) { if (freq.flr_label == (np->flow_label&IPV6_FLOWLABEL_MASK)) np->flow_label &= ~IPV6_FLOWLABEL_MASK; - *sflp = rcu_dereference(sfl->next); + *sflp = sfl->next; spin_unlock_bh(&ip6_sk_fl_lock); fl_release(sfl->fl); kfree_rcu(sfl, rcu); -- cgit v1.2.3 From 9cf7490360bf2c46a16b7525f899e4970c5fc144 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 2 Feb 2016 19:31:12 -0800 Subject: tcp: do not drop syn_recv on all icmp reports Petr Novopashenniy reported that ICMP redirects on SYN_RECV sockets were leading to RST. This is of course incorrect. A specific list of ICMP messages should be able to drop a SYN_RECV. For instance, a REDIRECT on SYN_RECV shall be ignored, as we do not hold a dst per SYN_RECV pseudo request. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=111751 Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table") Reported-by: Petr Novopashenniy Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 2 +- net/ipv4/tcp_ipv4.c | 11 ++++++++--- net/ipv6/tcp_ipv6.c | 5 +++-- 3 files changed, 12 insertions(+), 6 deletions(-) (limited to 'net/ipv6') diff --git a/include/net/tcp.h b/include/net/tcp.h index f6f8f032c73e..ae6468f5c9f3 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -447,7 +447,7 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th); void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb); void tcp_v4_mtu_reduced(struct sock *sk); -void tcp_req_err(struct sock *sk, u32 seq); +void tcp_req_err(struct sock *sk, u32 seq, bool abort); int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb); struct sock *tcp_create_openreq_child(const struct sock *sk, struct request_sock *req, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a4d523709ab3..7f6ff037adaf 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -311,7 +311,7 @@ static void do_redirect(struct sk_buff *skb, struct sock *sk) /* handle ICMP messages on TCP_NEW_SYN_RECV request sockets */ -void tcp_req_err(struct sock *sk, u32 seq) +void tcp_req_err(struct sock *sk, u32 seq, bool abort) { struct request_sock *req = inet_reqsk(sk); struct net *net = sock_net(sk); @@ -323,7 +323,7 @@ void tcp_req_err(struct sock *sk, u32 seq) if (seq != tcp_rsk(req)->snt_isn) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); - } else { + } else if (abort) { /* * Still in SYN_RECV, just remove it silently. * There is no good way to pass the error to the newly @@ -383,7 +383,12 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) } seq = ntohl(th->seq); if (sk->sk_state == TCP_NEW_SYN_RECV) - return tcp_req_err(sk, seq); + return tcp_req_err(sk, seq, + type == ICMP_PARAMETERPROB || + type == ICMP_TIME_EXCEEDED || + (type == ICMP_DEST_UNREACH && + (code == ICMP_NET_UNREACH || + code == ICMP_HOST_UNREACH))); bh_lock_sock(sk); /* If too many ICMPs get dropped on busy diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 006396e31cb0..1a5a70fb8551 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -327,6 +327,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct tcp_sock *tp; __u32 seq, snd_una; struct sock *sk; + bool fatal; int err; sk = __inet6_lookup_established(net, &tcp_hashinfo, @@ -345,8 +346,9 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, return; } seq = ntohl(th->seq); + fatal = icmpv6_err_convert(type, code, &err); if (sk->sk_state == TCP_NEW_SYN_RECV) - return tcp_req_err(sk, seq); + return tcp_req_err(sk, seq, fatal); bh_lock_sock(sk); if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG) @@ -400,7 +402,6 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, goto out; } - icmpv6_err_convert(type, code, &err); /* Might be for an request_sock */ switch (sk->sk_state) { -- cgit v1.2.3 From 7716682cc58e305e22207d5bb315f26af6b1e243 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 18 Feb 2016 05:39:18 -0800 Subject: tcp/dccp: fix another race at listener dismantle Ilya reported following lockdep splat: kernel: ========================= kernel: [ BUG: held lock freed! ] kernel: 4.5.0-rc1-ceph-00026-g5e0a311 #1 Not tainted kernel: ------------------------- kernel: swapper/5/0 is freeing memory ffff880035c9d200-ffff880035c9dbff, with a lock still held there! kernel: (&(&queue->rskq_lock)->rlock){+.-...}, at: [] inet_csk_reqsk_queue_add+0x28/0xa0 kernel: 4 locks held by swapper/5/0: kernel: #0: (rcu_read_lock){......}, at: [] netif_receive_skb_internal+0x4b/0x1f0 kernel: #1: (rcu_read_lock){......}, at: [] ip_local_deliver_finish+0x3f/0x380 kernel: #2: (slock-AF_INET){+.-...}, at: [] sk_clone_lock+0x19b/0x440 kernel: #3: (&(&queue->rskq_lock)->rlock){+.-...}, at: [] inet_csk_reqsk_queue_add+0x28/0xa0 To properly fix this issue, inet_csk_reqsk_queue_add() needs to return to its callers if the child as been queued into accept queue. We also need to make sure listener is still there before calling sk->sk_data_ready(), by holding a reference on it, since the reference carried by the child can disappear as soon as the child is put on accept queue. Reported-by: Ilya Dryomov Fixes: ebb516af60e1 ("tcp/dccp: fix race at listener dismantle phase") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 5 +++-- net/dccp/ipv4.c | 14 +++++++------- net/dccp/ipv6.c | 14 +++++++------- net/ipv4/inet_connection_sock.c | 14 +++++++------- net/ipv4/tcp_ipv4.c | 14 +++++++------- net/ipv6/tcp_ipv6.c | 14 +++++++------- 6 files changed, 38 insertions(+), 37 deletions(-) (limited to 'net/ipv6') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 481fe1c9044c..49dcad4fe99e 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -270,8 +270,9 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, struct sock *newsk, const struct request_sock *req); -void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req, - struct sock *child); +struct sock *inet_csk_reqsk_queue_add(struct sock *sk, + struct request_sock *req, + struct sock *child); void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, unsigned long timeout); struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child, diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 5684e14932bd..902d606324a0 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -824,26 +824,26 @@ lookup: if (sk->sk_state == DCCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); - struct sock *nsk = NULL; + struct sock *nsk; sk = req->rsk_listener; - if (likely(sk->sk_state == DCCP_LISTEN)) { - nsk = dccp_check_req(sk, skb, req); - } else { + if (unlikely(sk->sk_state != DCCP_LISTEN)) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } + sock_hold(sk); + nsk = dccp_check_req(sk, skb, req); if (!nsk) { reqsk_put(req); - goto discard_it; + goto discard_and_relse; } if (nsk == sk) { - sock_hold(sk); reqsk_put(req); } else if (dccp_child_process(sk, nsk, skb)) { dccp_v4_ctl_send_reset(sk, skb); - goto discard_it; + goto discard_and_relse; } else { + sock_put(sk); return 0; } } diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 9c6d0508e63a..b8608b71a66d 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -691,26 +691,26 @@ lookup: if (sk->sk_state == DCCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); - struct sock *nsk = NULL; + struct sock *nsk; sk = req->rsk_listener; - if (likely(sk->sk_state == DCCP_LISTEN)) { - nsk = dccp_check_req(sk, skb, req); - } else { + if (unlikely(sk->sk_state != DCCP_LISTEN)) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } + sock_hold(sk); + nsk = dccp_check_req(sk, skb, req); if (!nsk) { reqsk_put(req); - goto discard_it; + goto discard_and_relse; } if (nsk == sk) { - sock_hold(sk); reqsk_put(req); } else if (dccp_child_process(sk, nsk, skb)) { dccp_v6_ctl_send_reset(sk, skb); - goto discard_it; + goto discard_and_relse; } else { + sock_put(sk); return 0; } } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 46b9c887bede..64148914803a 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -789,14 +789,16 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req, reqsk_put(req); } -void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req, - struct sock *child) +struct sock *inet_csk_reqsk_queue_add(struct sock *sk, + struct request_sock *req, + struct sock *child) { struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; spin_lock(&queue->rskq_lock); if (unlikely(sk->sk_state != TCP_LISTEN)) { inet_child_forget(sk, req, child); + child = NULL; } else { req->sk = child; req->dl_next = NULL; @@ -808,6 +810,7 @@ void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req, sk_acceptq_added(sk); } spin_unlock(&queue->rskq_lock); + return child; } EXPORT_SYMBOL(inet_csk_reqsk_queue_add); @@ -817,11 +820,8 @@ struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child, if (own_req) { inet_csk_reqsk_queue_drop(sk, req); reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req); - inet_csk_reqsk_queue_add(sk, req, child); - /* Warning: caller must not call reqsk_put(req); - * child stole last reference on it. - */ - return child; + if (inet_csk_reqsk_queue_add(sk, req, child)) + return child; } /* Too bad, another child took ownership of the request, undo. */ bh_unlock_sock(child); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index c84477949d3a..487ac67059e2 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1597,30 +1597,30 @@ process: if (sk->sk_state == TCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); - struct sock *nsk = NULL; + struct sock *nsk; sk = req->rsk_listener; if (unlikely(tcp_v4_inbound_md5_hash(sk, skb))) { reqsk_put(req); goto discard_it; } - if (likely(sk->sk_state == TCP_LISTEN)) { - nsk = tcp_check_req(sk, skb, req, false); - } else { + if (unlikely(sk->sk_state != TCP_LISTEN)) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } + sock_hold(sk); + nsk = tcp_check_req(sk, skb, req, false); if (!nsk) { reqsk_put(req); - goto discard_it; + goto discard_and_relse; } if (nsk == sk) { - sock_hold(sk); reqsk_put(req); } else if (tcp_child_process(sk, nsk, skb)) { tcp_v4_send_reset(nsk, skb); - goto discard_it; + goto discard_and_relse; } else { + sock_put(sk); return 0; } } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 1a5a70fb8551..5c8c84273028 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1387,7 +1387,7 @@ process: if (sk->sk_state == TCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); - struct sock *nsk = NULL; + struct sock *nsk; sk = req->rsk_listener; tcp_v6_fill_cb(skb, hdr, th); @@ -1395,24 +1395,24 @@ process: reqsk_put(req); goto discard_it; } - if (likely(sk->sk_state == TCP_LISTEN)) { - nsk = tcp_check_req(sk, skb, req, false); - } else { + if (unlikely(sk->sk_state != TCP_LISTEN)) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } + sock_hold(sk); + nsk = tcp_check_req(sk, skb, req, false); if (!nsk) { reqsk_put(req); - goto discard_it; + goto discard_and_relse; } if (nsk == sk) { - sock_hold(sk); reqsk_put(req); tcp_v6_restore_cb(skb); } else if (tcp_child_process(sk, nsk, skb)) { tcp_v6_send_reset(nsk, skb); - goto discard_it; + goto discard_and_relse; } else { + sock_put(sk); return 0; } } -- cgit v1.2.3 From d13b161c2c7c67401bb222c30302339285ac148e Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Wed, 17 Feb 2016 15:32:53 +0100 Subject: gre: clear IFF_TX_SKB_SHARING ether_setup sets IFF_TX_SKB_SHARING but this is not supported by gre as it modifies the skb on xmit. Also, clean up whitespace in ipgre_tap_setup when we're already touching it. Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- net/ipv4/ip_gre.c | 5 +++-- net/ipv6/ip6_gre.c | 1 + 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 56fdf4e0dce4..41ba68de46d8 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1054,8 +1054,9 @@ static const struct net_device_ops gre_tap_netdev_ops = { static void ipgre_tap_setup(struct net_device *dev) { ether_setup(dev); - dev->netdev_ops = &gre_tap_netdev_ops; - dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + dev->netdev_ops = &gre_tap_netdev_ops; + dev->priv_flags &= ~IFF_TX_SKB_SHARING; + dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; ip_tunnel_setup(dev, gre_tap_net_id); } diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index f37f18b6b40c..a69aad1e29d1 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1512,6 +1512,7 @@ static void ip6gre_tap_setup(struct net_device *dev) dev->destructor = ip6gre_dev_free; dev->features |= NETIF_F_NETNS_LOCAL; + dev->priv_flags &= ~IFF_TX_SKB_SHARING; } static int ip6gre_newlink(struct net *src_net, struct net_device *dev, -- cgit v1.2.3 From a97eb33ff225f34a8124774b3373fd244f0e83ce Mon Sep 17 00:00:00 2001 From: Anton Protopopov Date: Tue, 16 Feb 2016 21:43:16 -0500 Subject: rtnl: RTM_GETNETCONF: fix wrong return value An error response from a RTM_GETNETCONF request can return the positive error value EINVAL in the struct nlmsgerr that can mislead userspace. Signed-off-by: Anton Protopopov Acked-by: Cong Wang Signed-off-by: David S. Miller --- net/ipv4/devinet.c | 2 +- net/ipv6/addrconf.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index cebd9d31e65a..f6303b17546b 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1847,7 +1847,7 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb, if (err < 0) goto errout; - err = EINVAL; + err = -EINVAL; if (!tb[NETCONFA_IFINDEX]) goto errout; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 9efd9ffdc34c..bdd7eac4307a 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -583,7 +583,7 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb, if (err < 0) goto errout; - err = EINVAL; + err = -EINVAL; if (!tb[NETCONFA_IFINDEX]) goto errout; -- cgit v1.2.3