From a11a7f71cac209c7c9cca66eb506e1ebb033a3b3 Mon Sep 17 00:00:00 2001 From: Marcus Huewe Date: Mon, 6 Feb 2017 18:34:56 +0100 Subject: ipv6: addrconf: fix generation of new temporary addresses Under some circumstances it is possible that no new temporary addresses will be generated. For instance, addrconf_prefix_rcv_add_addr() indirectly calls ipv6_create_tempaddr(), which creates a tentative temporary address and starts dad. Next, addrconf_prefix_rcv_add_addr() indirectly calls addrconf_verify_rtnl(). Now, assume that the previously created temporary address has the least preferred lifetime among all existing addresses and is still tentative (that is, dad is still running). Hence, the next run of addrconf_verify_rtnl() is performed when the preferred lifetime of the temporary address ends. If dad succeeds before the next run, the temporary address becomes deprecated during the next run, but no new temporary address is generated. In order to fix this, schedule the next addrconf_verify_rtnl() run slightly before the temporary address becomes deprecated, if dad succeeded. Signed-off-by: Marcus Huewe Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'net') diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 81f7b4ea4281..a7bcc0ab5e99 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -4015,6 +4015,12 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id) if (bump_id) rt_genid_bump_ipv6(dev_net(dev)); + + /* Make sure that a new temporary address will be created + * before this temporary address becomes deprecated. + */ + if (ifp->flags & IFA_F_TEMPORARY) + addrconf_verify_rtnl(); } static void addrconf_dad_run(struct inet6_dev *idev) -- cgit v1.2.3 From d7426c69a1942b2b9b709bf66b944ff09f561484 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Wed, 8 Feb 2017 10:02:13 -0800 Subject: sit: fix a double free on error path Dmitry reported a double free in sit_init_net(): kernel BUG at mm/percpu.c:689! invalid opcode: 0000 [#1] SMP KASAN Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: CPU: 0 PID: 15692 Comm: syz-executor1 Not tainted 4.10.0-rc6-next-20170206 #1 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 task: ffff8801c9cc27c0 task.stack: ffff88017d1d8000 RIP: 0010:pcpu_free_area+0x68b/0x810 mm/percpu.c:689 RSP: 0018:ffff88017d1df488 EFLAGS: 00010046 RAX: 0000000000010000 RBX: 00000000000007c0 RCX: ffffc90002829000 RDX: 0000000000010000 RSI: ffffffff81940efb RDI: ffff8801db841d94 RBP: ffff88017d1df590 R08: dffffc0000000000 R09: 1ffffffff0bb3bdd R10: dffffc0000000000 R11: 00000000000135dd R12: ffff8801db841d80 R13: 0000000000038e40 R14: 00000000000007c0 R15: 00000000000007c0 FS: 00007f6ea608f700(0000) GS:ffff8801dbe00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000002000aff8 CR3: 00000001c8d44000 CR4: 00000000001426f0 DR0: 0000000020000000 DR1: 0000000020000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000600 Call Trace: free_percpu+0x212/0x520 mm/percpu.c:1264 ipip6_dev_free+0x43/0x60 net/ipv6/sit.c:1335 sit_init_net+0x3cb/0xa10 net/ipv6/sit.c:1831 ops_init+0x10a/0x530 net/core/net_namespace.c:115 setup_net+0x2ed/0x690 net/core/net_namespace.c:291 copy_net_ns+0x26c/0x530 net/core/net_namespace.c:396 create_new_namespaces+0x409/0x860 kernel/nsproxy.c:106 unshare_nsproxy_namespaces+0xae/0x1e0 kernel/nsproxy.c:205 SYSC_unshare kernel/fork.c:2281 [inline] SyS_unshare+0x64e/0xfc0 kernel/fork.c:2231 entry_SYSCALL_64_fastpath+0x1f/0xc2 This is because when tunnel->dst_cache init fails, we free dev->tstats once in ipip6_tunnel_init() and twice in sit_init_net(). This looks redundant but its ndo_uinit() does not seem enough to clean up everything here. So avoid this by setting dev->tstats to NULL after the first free, at least for -net. Reported-by: Dmitry Vyukov Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/ipv6/sit.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net') diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index fad992ad4bc8..99853c6e33a8 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1380,6 +1380,7 @@ static int ipip6_tunnel_init(struct net_device *dev) err = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL); if (err) { free_percpu(dev->tstats); + dev->tstats = NULL; return err; } -- cgit v1.2.3 From 217e6fa24ce28ec87fca8da93c9016cb78028612 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Tue, 7 Feb 2017 15:57:20 -0500 Subject: net: introduce device min_header_len The stack must not pass packets to device drivers that are shorter than the minimum link layer header length. Previously, packet sockets would drop packets smaller than or equal to dev->hard_header_len, but this has false positives. Zero length payload is used over Ethernet. Other link layer protocols support variable length headers. Support for validation of these protocols removed the min length check for all protocols. Introduce an explicit dev->min_header_len parameter and drop all packets below this value. Initially, set it to non-zero only for Ethernet and loopback. Other protocols can follow in a patch to net-next. Fixes: 9ed988cd5915 ("packet: validate variable length ll headers") Reported-by: Sowmini Varadhan Signed-off-by: Willem de Bruijn Acked-by: Eric Dumazet Acked-by: Sowmini Varadhan Signed-off-by: David S. Miller --- net/ethernet/eth.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net') diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 8c5a479681ca..516c87e75de7 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -356,6 +356,7 @@ void ether_setup(struct net_device *dev) dev->header_ops = ð_header_ops; dev->type = ARPHRD_ETHER; dev->hard_header_len = ETH_HLEN; + dev->min_header_len = ETH_HLEN; dev->mtu = ETH_DATA_LEN; dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = ETH_DATA_LEN; -- cgit v1.2.3 From 57031eb794906eea4e1c7b31dc1e2429c0af0c66 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Tue, 7 Feb 2017 15:57:21 -0500 Subject: packet: round up linear to header len Link layer protocols may unconditionally pull headers, as Ethernet does in eth_type_trans. Ensure that the entire link layer header always lies in the skb linear segment. tpacket_snd has such a check. Extend this to packet_snd. Variable length link layer headers complicate the computation somewhat. Here skb->len may be smaller than dev->hard_header_len. Round up the linear length to be at least as long as the smallest of the two. Reported-by: Dmitry Vyukov Signed-off-by: Willem de Bruijn Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/packet/af_packet.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 3d555c79a7b5..d56ee46b11fc 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2755,7 +2755,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) struct virtio_net_hdr vnet_hdr = { 0 }; int offset = 0; struct packet_sock *po = pkt_sk(sk); - int hlen, tlen; + int hlen, tlen, linear; int extra_len = 0; /* @@ -2816,8 +2816,9 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) err = -ENOBUFS; hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; - skb = packet_alloc_skb(sk, hlen + tlen, hlen, len, - __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len), + linear = __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len); + linear = max(linear, min_t(int, len, dev->hard_header_len)); + skb = packet_alloc_skb(sk, hlen + tlen, hlen, len, linear, msg->msg_flags & MSG_DONTWAIT, &err); if (skb == NULL) goto out_unlock; -- cgit v1.2.3 From 73d2c6678e6c3af7e7a42b1e78cd0211782ade32 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Tue, 7 Feb 2017 12:59:46 -0800 Subject: ping: fix a null pointer dereference Andrey reported a kernel crash: general protection fault: 0000 [#1] SMP KASAN Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: CPU: 2 PID: 3880 Comm: syz-executor1 Not tainted 4.10.0-rc6+ #124 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 task: ffff880060048040 task.stack: ffff880069be8000 RIP: 0010:ping_v4_push_pending_frames net/ipv4/ping.c:647 [inline] RIP: 0010:ping_v4_sendmsg+0x1acd/0x23f0 net/ipv4/ping.c:837 RSP: 0018:ffff880069bef8b8 EFLAGS: 00010206 RAX: dffffc0000000000 RBX: ffff880069befb90 RCX: 0000000000000000 RDX: 0000000000000018 RSI: ffff880069befa30 RDI: 00000000000000c2 RBP: ffff880069befbb8 R08: 0000000000000008 R09: 0000000000000000 R10: 0000000000000002 R11: 0000000000000000 R12: ffff880069befab0 R13: ffff88006c624a80 R14: ffff880069befa70 R15: 0000000000000000 FS: 00007f6f7c716700(0000) GS:ffff88006de00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000004a6f28 CR3: 000000003a134000 CR4: 00000000000006e0 Call Trace: inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:744 sock_sendmsg_nosec net/socket.c:635 [inline] sock_sendmsg+0xca/0x110 net/socket.c:645 SYSC_sendto+0x660/0x810 net/socket.c:1687 SyS_sendto+0x40/0x50 net/socket.c:1655 entry_SYSCALL_64_fastpath+0x1f/0xc2 This is because we miss a check for NULL pointer for skb_peek() when the queue is empty. Other places already have the same check. Fixes: c319b4d76b9e ("net: ipv4: add IPPROTO_ICMP socket kind") Reported-by: Andrey Konovalov Tested-by: Andrey Konovalov Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/ipv4/ping.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net') diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 86cca610f4c2..68d77b1f1495 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -642,6 +642,8 @@ static int ping_v4_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh, { struct sk_buff *skb = skb_peek(&sk->sk_write_queue); + if (!skb) + return 0; pfh->wcheck = csum_partial((char *)&pfh->icmph, sizeof(struct icmphdr), pfh->wcheck); pfh->icmph.checksum = csum_fold(pfh->wcheck); -- cgit v1.2.3 From 382e1eea2d983cd2343482c6a638f497bb44a636 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 7 Feb 2017 23:10:13 -0800 Subject: net: dsa: Do not destroy invalid network devices dsa_slave_create() can fail, and dsa_user_port_unapply() will properly check for the network device not being NULL before attempting to destroy it. We were not setting the slave network device as NULL if dsa_slave_create() failed, so we would later on be calling dsa_slave_destroy() on a now free'd and unitialized network device, causing crashes in dsa_slave_destroy(). Fixes: 83c0afaec7b7 ("net: dsa: Add new binding implementation") Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- net/dsa/dsa2.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net') diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index da3862124545..0f99297b2fb3 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -273,6 +273,7 @@ static int dsa_user_port_apply(struct device_node *port, u32 index, if (err) { dev_warn(ds->dev, "Failed to create slave %d: %d\n", index, err); + ds->ports[index].netdev = NULL; return err; } -- cgit v1.2.3 From 98e3862ca2b1ae595a13805dcab4c3a6d7718f4d Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Tue, 7 Feb 2017 12:59:47 -0800 Subject: kcm: fix 0-length case for kcm_sendmsg() Dmitry reported a kernel warning: WARNING: CPU: 3 PID: 2936 at net/kcm/kcmsock.c:627 kcm_write_msgs+0x12e3/0x1b90 net/kcm/kcmsock.c:627 CPU: 3 PID: 2936 Comm: a.out Not tainted 4.10.0-rc6+ #209 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:15 [inline] dump_stack+0x2ee/0x3ef lib/dump_stack.c:51 panic+0x1fb/0x412 kernel/panic.c:179 __warn+0x1c4/0x1e0 kernel/panic.c:539 warn_slowpath_null+0x2c/0x40 kernel/panic.c:582 kcm_write_msgs+0x12e3/0x1b90 net/kcm/kcmsock.c:627 kcm_sendmsg+0x163a/0x2200 net/kcm/kcmsock.c:1029 sock_sendmsg_nosec net/socket.c:635 [inline] sock_sendmsg+0xca/0x110 net/socket.c:645 sock_write_iter+0x326/0x600 net/socket.c:848 new_sync_write fs/read_write.c:499 [inline] __vfs_write+0x483/0x740 fs/read_write.c:512 vfs_write+0x187/0x530 fs/read_write.c:560 SYSC_write fs/read_write.c:607 [inline] SyS_write+0xfb/0x230 fs/read_write.c:599 entry_SYSCALL_64_fastpath+0x1f/0xc2 when calling syscall(__NR_write, sock2, 0x208aaf27ul, 0x0ul) on a KCM seqpacket socket. It appears that kcm_sendmsg() does not handle len==0 case correctly, which causes an empty skb is allocated and queued. Fix this by skipping the skb allocation for len==0 case. Reported-by: Dmitry Vyukov Cc: Tom Herbert Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/kcm/kcmsock.c | 40 ++++++++++++++++++++++------------------ 1 file changed, 22 insertions(+), 18 deletions(-) (limited to 'net') diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 7e08a4d3d77d..64f0e8531af0 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -929,23 +929,25 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) goto out_error; } - /* New message, alloc head skb */ - head = alloc_skb(0, sk->sk_allocation); - while (!head) { - kcm_push(kcm); - err = sk_stream_wait_memory(sk, &timeo); - if (err) - goto out_error; - + if (msg_data_left(msg)) { + /* New message, alloc head skb */ head = alloc_skb(0, sk->sk_allocation); - } + while (!head) { + kcm_push(kcm); + err = sk_stream_wait_memory(sk, &timeo); + if (err) + goto out_error; - skb = head; + head = alloc_skb(0, sk->sk_allocation); + } - /* Set ip_summed to CHECKSUM_UNNECESSARY to avoid calling - * csum_and_copy_from_iter from skb_do_copy_data_nocache. - */ - skb->ip_summed = CHECKSUM_UNNECESSARY; + skb = head; + + /* Set ip_summed to CHECKSUM_UNNECESSARY to avoid calling + * csum_and_copy_from_iter from skb_do_copy_data_nocache. + */ + skb->ip_summed = CHECKSUM_UNNECESSARY; + } start: while (msg_data_left(msg)) { @@ -1018,10 +1020,12 @@ wait_for_memory: if (eor) { bool not_busy = skb_queue_empty(&sk->sk_write_queue); - /* Message complete, queue it on send buffer */ - __skb_queue_tail(&sk->sk_write_queue, head); - kcm->seq_skb = NULL; - KCM_STATS_INCR(kcm->stats.tx_msgs); + if (head) { + /* Message complete, queue it on send buffer */ + __skb_queue_tail(&sk->sk_write_queue, head); + kcm->seq_skb = NULL; + KCM_STATS_INCR(kcm->stats.tx_msgs); + } if (msg->msg_flags & MSG_BATCH) { kcm->tx_wait_more = true; -- cgit v1.2.3 From 9c8bb163ae784be4f79ae504e78c862806087c54 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Wed, 8 Feb 2017 21:16:45 +0800 Subject: igmp, mld: Fix memory leak in igmpv3/mld_del_delrec() In function igmpv3/mld_add_delrec() we allocate pmc and put it in idev->mc_tomb, so we should free it when we don't need it in del_delrec(). But I removed kfree(pmc) incorrectly in latest two patches. Now fix it. Fixes: 24803f38a5c0 ("igmp: do not remove igmp souce list info when ...") Fixes: 1666d49e1d41 ("mld: do not remove mld souce list info when ...") Reported-by: Daniel Borkmann Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller --- net/ipv4/igmp.c | 1 + net/ipv6/mcast.c | 1 + 2 files changed, 2 insertions(+) (limited to 'net') diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 5b15459955f8..44fd86de2823 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1172,6 +1172,7 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im) psf->sf_crcount = im->crcount; } in_dev_put(pmc->interface); + kfree(pmc); } spin_unlock_bh(&im->lock); } diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 7139fffd61b6..1bdc703cb966 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -779,6 +779,7 @@ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) psf->sf_crcount = im->mca_crcount; } in6_dev_put(pmc->idev); + kfree(pmc); } spin_unlock_bh(&im->mca_lock); } -- cgit v1.2.3 From 72fb96e7bdbbdd4421b0726992496531060f3636 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 9 Feb 2017 16:15:52 -0800 Subject: l2tp: do not use udp_ioctl() udp_ioctl(), as its name suggests, is used by UDP protocols, but is also used by L2TP :( L2TP should use its own handler, because it really does not look the same. SIOCINQ for instance should not assume UDP checksum or headers. Thanks to Andrey and syzkaller team for providing the report and a nice reproducer. While crashes only happen on recent kernels (after commit 7c13f97ffde6 ("udp: do fwd memory scheduling on dequeue")), this probably needs to be backported to older kernels. Fixes: 7c13f97ffde6 ("udp: do fwd memory scheduling on dequeue") Fixes: 85584672012e ("udp: Fix udp_poll() and ioctl()") Signed-off-by: Eric Dumazet Reported-by: Andrey Konovalov Acked-by: Paolo Abeni Signed-off-by: David S. Miller --- net/l2tp/l2tp_core.h | 1 + net/l2tp/l2tp_ip.c | 27 ++++++++++++++++++++++++++- net/l2tp/l2tp_ip6.c | 2 +- 3 files changed, 28 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 8f560f7140a0..aebf281d09ee 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -263,6 +263,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int l2tp_nl_register_ops(enum l2tp_pwtype pw_type, const struct l2tp_nl_cmd_ops *ops); void l2tp_nl_unregister_ops(enum l2tp_pwtype pw_type); +int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg); /* Session reference counts. Incremented when code obtains a reference * to a session. diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 3d73278b86ca..28c21546d5b6 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -11,6 +11,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include #include #include #include @@ -553,6 +554,30 @@ out: return err ? err : copied; } +int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg) +{ + struct sk_buff *skb; + int amount; + + switch (cmd) { + case SIOCOUTQ: + amount = sk_wmem_alloc_get(sk); + break; + case SIOCINQ: + spin_lock_bh(&sk->sk_receive_queue.lock); + skb = skb_peek(&sk->sk_receive_queue); + amount = skb ? skb->len : 0; + spin_unlock_bh(&sk->sk_receive_queue.lock); + break; + + default: + return -ENOIOCTLCMD; + } + + return put_user(amount, (int __user *)arg); +} +EXPORT_SYMBOL(l2tp_ioctl); + static struct proto l2tp_ip_prot = { .name = "L2TP/IP", .owner = THIS_MODULE, @@ -561,7 +586,7 @@ static struct proto l2tp_ip_prot = { .bind = l2tp_ip_bind, .connect = l2tp_ip_connect, .disconnect = l2tp_ip_disconnect, - .ioctl = udp_ioctl, + .ioctl = l2tp_ioctl, .destroy = l2tp_ip_destroy_sock, .setsockopt = ip_setsockopt, .getsockopt = ip_getsockopt, diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 331ccf5a7bad..f47c45250f86 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -722,7 +722,7 @@ static struct proto l2tp_ip6_prot = { .bind = l2tp_ip6_bind, .connect = l2tp_ip6_connect, .disconnect = l2tp_ip6_disconnect, - .ioctl = udp_ioctl, + .ioctl = l2tp_ioctl, .destroy = l2tp_ip6_destroy_sock, .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, -- cgit v1.2.3