From f1ed10264ed6b66b9cd5e8461cffce69be482356 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Tue, 4 Feb 2020 17:00:27 +0100 Subject: vti[6]: fix packet tx through bpf_redirect() in XinY cases I forgot the 4in6/6in4 cases in my previous patch. Let's fix them. Fixes: 95224166a903 ("vti[6]: fix packet tx through bpf_redirect()") Signed-off-by: Nicolas Dichtel Signed-off-by: Steffen Klassert --- net/ipv4/Kconfig | 1 + net/ipv4/ip_vti.c | 38 ++++++++++++++++++++++++++++++-------- 2 files changed, 31 insertions(+), 8 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index f96bd489b362..6490b845e17b 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -303,6 +303,7 @@ config SYN_COOKIES config NET_IPVTI tristate "Virtual (secure) IP: tunneling" + depends on IPV6 || IPV6=n select INET_TUNNEL select NET_IP_TUNNEL select XFRM diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 37cddd18f282..1b4e6f298648 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -187,17 +187,39 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, int mtu; if (!dst) { - struct rtable *rt; - - fl->u.ip4.flowi4_oif = dev->ifindex; - fl->u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC; - rt = __ip_route_output_key(dev_net(dev), &fl->u.ip4); - if (IS_ERR(rt)) { + switch (skb->protocol) { + case htons(ETH_P_IP): { + struct rtable *rt; + + fl->u.ip4.flowi4_oif = dev->ifindex; + fl->u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC; + rt = __ip_route_output_key(dev_net(dev), &fl->u.ip4); + if (IS_ERR(rt)) { + dev->stats.tx_carrier_errors++; + goto tx_error_icmp; + } + dst = &rt->dst; + skb_dst_set(skb, dst); + break; + } +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + fl->u.ip6.flowi6_oif = dev->ifindex; + fl->u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC; + dst = ip6_route_output(dev_net(dev), NULL, &fl->u.ip6); + if (dst->error) { + dst_release(dst); + dst = NULL; + dev->stats.tx_carrier_errors++; + goto tx_error_icmp; + } + skb_dst_set(skb, dst); + break; +#endif + default: dev->stats.tx_carrier_errors++; goto tx_error_icmp; } - dst = &rt->dst; - skb_dst_set(skb, dst); } dst_hold(dst); -- cgit v1.2.3 From 303d0403b8c25e994e4a6e45389e173cf8706fb5 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Wed, 19 Feb 2020 14:16:32 -0500 Subject: udp: rehash on disconnect As of the below commit, udp sockets bound to a specific address can coexist with one bound to the any addr for the same port. The commit also phased out the use of socket hashing based only on port (hslot), in favor of always hashing on {addr, port} (hslot2). The change broke the following behavior with disconnect (AF_UNSPEC): server binds to 0.0.0.0:1337 server connects to 127.0.0.1:80 server disconnects client connects to 127.0.0.1:1337 client sends "hello" server reads "hello" // times out, packet did not find sk On connect the server acquires a specific source addr suitable for routing to its destination. On disconnect it reverts to the any addr. The connect call triggers a rehash to a different hslot2. On disconnect, add the same to return to the original hslot2. Skip this step if the socket is going to be unhashed completely. Fixes: 4cdeeee9252a ("net: udp: prefer listeners bound to an address") Reported-by: Pavel Roskin Signed-off-by: Willem de Bruijn Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/udp.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'net/ipv4') diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index db76b9609299..08a41f1e1cd2 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1857,8 +1857,12 @@ int __udp_disconnect(struct sock *sk, int flags) inet->inet_dport = 0; sock_rps_reset_rxhash(sk); sk->sk_bound_dev_if = 0; - if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) + if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) { inet_reset_saddr(sk); + if (sk->sk_prot->rehash && + (sk->sk_userlocks & SOCK_BINDPORT_LOCK)) + sk->sk_prot->rehash(sk); + } if (!(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) { sk->sk_prot->unhash(sk); -- cgit v1.2.3 From 3e72dfdf8227b052393f71d820ec7599909dddc2 Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Fri, 21 Feb 2020 12:28:38 +0100 Subject: ipv4: ensure rcu_read_lock() in cipso_v4_error() Similarly to commit c543cb4a5f07 ("ipv4: ensure rcu_read_lock() in ipv4_link_failure()"), __ip_options_compile() must be called under rcu protection. Fixes: 3da1ed7ac398 ("net: avoid use IPCB in cipso_v4_error") Suggested-by: Guillaume Nault Signed-off-by: Matteo Croce Acked-by: Paul Moore Signed-off-by: David S. Miller --- net/ipv4/cipso_ipv4.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'net/ipv4') diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 376882215919..0bd10a1f477f 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1724,6 +1724,7 @@ void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway) { unsigned char optbuf[sizeof(struct ip_options) + 40]; struct ip_options *opt = (struct ip_options *)optbuf; + int res; if (ip_hdr(skb)->protocol == IPPROTO_ICMP || error != -EACCES) return; @@ -1735,7 +1736,11 @@ void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway) memset(opt, 0, sizeof(struct ip_options)); opt->optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr); - if (__ip_options_compile(dev_net(skb->dev), opt, skb, NULL)) + rcu_read_lock(); + res = __ip_options_compile(dev_net(skb->dev), opt, skb, NULL); + rcu_read_unlock(); + + if (res) return; if (gateway) -- cgit v1.2.3 From dad8cea7add96a353fa1898b5ccefbb72da66f29 Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Sat, 22 Feb 2020 11:21:15 -0500 Subject: tcp: fix TFO SYNACK undo to avoid double-timestamp-undo In a rare corner case the new logic for undo of SYNACK RTO could result in triggering the warning in tcp_fastretrans_alert() that says: WARN_ON(tp->retrans_out != 0); The warning looked like: WARNING: CPU: 1 PID: 1 at net/ipv4/tcp_input.c:2818 tcp_ack+0x13e0/0x3270 The sequence that tickles this bug is: - Fast Open server receives TFO SYN with data, sends SYNACK - (client receives SYNACK and sends ACK, but ACK is lost) - server app sends some data packets - (N of the first data packets are lost) - server receives client ACK that has a TS ECR matching first SYNACK, and also SACKs suggesting the first N data packets were lost - server performs TS undo of SYNACK RTO, then immediately enters recovery - buggy behavior then performed a *second* undo that caused the connection to be in CA_Open with retrans_out != 0 Basically, the incoming ACK packet with SACK blocks causes us to first undo the cwnd reduction from the SYNACK RTO, but then immediately enters fast recovery, which then makes us eligible for undo again. And then tcp_rcv_synrecv_state_fastopen() accidentally performs an undo using a "mash-up" of state from two different loss recovery phases: it uses the timestamp info from the ACK of the original SYNACK, and the undo_marker from the fast recovery. This fix refines the logic to only invoke the tcp_try_undo_loss() inside tcp_rcv_synrecv_state_fastopen() if the connection is still in CA_Loss. If peer SACKs triggered fast recovery, then tcp_rcv_synrecv_state_fastopen() can't safely undo. Fixes: 794200d66273 ("tcp: undo cwnd on Fast Open spurious SYNACK retransmit") Signed-off-by: Neal Cardwell Signed-off-by: Yuchung Cheng Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 316ebdf8151d..6b6b57000dad 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6124,7 +6124,11 @@ static void tcp_rcv_synrecv_state_fastopen(struct sock *sk) { struct request_sock *req; - tcp_try_undo_loss(sk, false); + /* If we are still handling the SYNACK RTO, see if timestamp ECR allows + * undo. If peer SACKs triggered fast recovery, we can't undo here. + */ + if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss) + tcp_try_undo_loss(sk, false); /* Reset rtx states to prevent spurious retransmits_timed_out() */ tcp_sk(sk)->retrans_stamp = 0; -- cgit v1.2.3 From 17c25cafd4d3e74c83dce56b158843b19c40b414 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 7 Mar 2020 22:05:14 -0800 Subject: gre: fix uninit-value in __iptunnel_pull_header syzbot found an interesting case of the kernel reading an uninit-value [1] Problem is in the handling of ETH_P_WCCP in gre_parse_header() We look at the byte following GRE options to eventually decide if the options are four bytes longer. Use skb_header_pointer() to not pull bytes if we found that no more bytes were needed. All callers of gre_parse_header() are properly using pskb_may_pull() anyway before proceeding to next header. [1] BUG: KMSAN: uninit-value in pskb_may_pull include/linux/skbuff.h:2303 [inline] BUG: KMSAN: uninit-value in __iptunnel_pull_header+0x30c/0xbd0 net/ipv4/ip_tunnel_core.c:94 CPU: 1 PID: 11784 Comm: syz-executor940 Not tainted 5.6.0-rc2-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x1c9/0x220 lib/dump_stack.c:118 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:118 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:215 pskb_may_pull include/linux/skbuff.h:2303 [inline] __iptunnel_pull_header+0x30c/0xbd0 net/ipv4/ip_tunnel_core.c:94 iptunnel_pull_header include/net/ip_tunnels.h:411 [inline] gre_rcv+0x15e/0x19c0 net/ipv6/ip6_gre.c:606 ip6_protocol_deliver_rcu+0x181b/0x22c0 net/ipv6/ip6_input.c:432 ip6_input_finish net/ipv6/ip6_input.c:473 [inline] NF_HOOK include/linux/netfilter.h:307 [inline] ip6_input net/ipv6/ip6_input.c:482 [inline] ip6_mc_input+0xdf2/0x1460 net/ipv6/ip6_input.c:576 dst_input include/net/dst.h:442 [inline] ip6_rcv_finish net/ipv6/ip6_input.c:76 [inline] NF_HOOK include/linux/netfilter.h:307 [inline] ipv6_rcv+0x683/0x710 net/ipv6/ip6_input.c:306 __netif_receive_skb_one_core net/core/dev.c:5198 [inline] __netif_receive_skb net/core/dev.c:5312 [inline] netif_receive_skb_internal net/core/dev.c:5402 [inline] netif_receive_skb+0x66b/0xf20 net/core/dev.c:5461 tun_rx_batched include/linux/skbuff.h:4321 [inline] tun_get_user+0x6aef/0x6f60 drivers/net/tun.c:1997 tun_chr_write_iter+0x1f2/0x360 drivers/net/tun.c:2026 call_write_iter include/linux/fs.h:1901 [inline] new_sync_write fs/read_write.c:483 [inline] __vfs_write+0xa5a/0xca0 fs/read_write.c:496 vfs_write+0x44a/0x8f0 fs/read_write.c:558 ksys_write+0x267/0x450 fs/read_write.c:611 __do_sys_write fs/read_write.c:623 [inline] __se_sys_write fs/read_write.c:620 [inline] __ia32_sys_write+0xdb/0x120 fs/read_write.c:620 do_syscall_32_irqs_on arch/x86/entry/common.c:339 [inline] do_fast_syscall_32+0x3c7/0x6e0 arch/x86/entry/common.c:410 entry_SYSENTER_compat+0x68/0x77 arch/x86/entry/entry_64_compat.S:139 RIP: 0023:0xf7f62d99 Code: 90 e8 0b 00 00 00 f3 90 0f ae e8 eb f9 8d 74 26 00 89 3c 24 c3 90 90 90 90 90 90 90 90 90 90 90 90 51 52 55 89 e5 0f 34 cd 80 <5d> 5a 59 c3 90 90 90 90 eb 0d 90 90 90 90 90 90 90 90 90 90 90 90 RSP: 002b:00000000fffedb2c EFLAGS: 00000217 ORIG_RAX: 0000000000000004 RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000020002580 RDX: 0000000000000fca RSI: 0000000000000036 RDI: 0000000000000004 RBP: 0000000000008914 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:144 [inline] kmsan_internal_poison_shadow+0x66/0xd0 mm/kmsan/kmsan.c:127 kmsan_slab_alloc+0x8a/0xe0 mm/kmsan/kmsan_hooks.c:82 slab_alloc_node mm/slub.c:2793 [inline] __kmalloc_node_track_caller+0xb40/0x1200 mm/slub.c:4401 __kmalloc_reserve net/core/skbuff.c:142 [inline] __alloc_skb+0x2fd/0xac0 net/core/skbuff.c:210 alloc_skb include/linux/skbuff.h:1051 [inline] alloc_skb_with_frags+0x18c/0xa70 net/core/skbuff.c:5766 sock_alloc_send_pskb+0xada/0xc60 net/core/sock.c:2242 tun_alloc_skb drivers/net/tun.c:1529 [inline] tun_get_user+0x10ae/0x6f60 drivers/net/tun.c:1843 tun_chr_write_iter+0x1f2/0x360 drivers/net/tun.c:2026 call_write_iter include/linux/fs.h:1901 [inline] new_sync_write fs/read_write.c:483 [inline] __vfs_write+0xa5a/0xca0 fs/read_write.c:496 vfs_write+0x44a/0x8f0 fs/read_write.c:558 ksys_write+0x267/0x450 fs/read_write.c:611 __do_sys_write fs/read_write.c:623 [inline] __se_sys_write fs/read_write.c:620 [inline] __ia32_sys_write+0xdb/0x120 fs/read_write.c:620 do_syscall_32_irqs_on arch/x86/entry/common.c:339 [inline] do_fast_syscall_32+0x3c7/0x6e0 arch/x86/entry/common.c:410 entry_SYSENTER_compat+0x68/0x77 arch/x86/entry/entry_64_compat.S:139 Fixes: 95f5c64c3c13 ("gre: Move utility functions to common headers") Fixes: c54419321455 ("GRE: Refactor GRE tunneling code.") Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller --- net/ipv4/gre_demux.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c index 5fd6e8ed02b5..66fdbfe5447c 100644 --- a/net/ipv4/gre_demux.c +++ b/net/ipv4/gre_demux.c @@ -56,7 +56,9 @@ int gre_del_protocol(const struct gre_protocol *proto, u8 version) } EXPORT_SYMBOL_GPL(gre_del_protocol); -/* Fills in tpi and returns header length to be pulled. */ +/* Fills in tpi and returns header length to be pulled. + * Note that caller must use pskb_may_pull() before pulling GRE header. + */ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, bool *csum_err, __be16 proto, int nhs) { @@ -110,8 +112,14 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header */ if (greh->flags == 0 && tpi->proto == htons(ETH_P_WCCP)) { + u8 _val, *val; + + val = skb_header_pointer(skb, nhs + hdr_len, + sizeof(_val), &_val); + if (!val) + return -EINVAL; tpi->proto = proto; - if ((*(u8 *)options & 0xF0) != 0x40) + if ((*val & 0xF0) != 0x40) hdr_len += 4; } tpi->hdr_len = hdr_len; -- cgit v1.2.3 From 83f73c5bb7b9a9135173f0ba2b1aa00c06664ff9 Mon Sep 17 00:00:00 2001 From: Dmitry Yakunin Date: Thu, 5 Mar 2020 15:33:12 +0300 Subject: inet_diag: return classid for all socket types In commit 1ec17dbd90f8 ("inet_diag: fix reporting cgroup classid and fallback to priority") croup classid reporting was fixed. But this works only for TCP sockets because for other socket types icsk parameter can be NULL and classid code path is skipped. This change moves classid handling to inet_diag_msg_attrs_fill() function. Also inet_diag_msg_attrs_size() helper was added and addends in nlmsg_new() were reordered to save order from inet_sk_diag_fill(). Fixes: 1ec17dbd90f8 ("inet_diag: fix reporting cgroup classid and fallback to priority") Signed-off-by: Dmitry Yakunin Reviewed-by: Konstantin Khlebnikov Signed-off-by: David S. Miller --- net/ipv4/inet_diag.c | 44 ++++++++++++++++++++------------------------ net/ipv4/raw_diag.c | 5 +++-- net/ipv4/udp_diag.c | 5 +++-- 3 files changed, 26 insertions(+), 28 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index f11e997e517b..8c8377568a78 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -100,13 +100,9 @@ static size_t inet_sk_attr_size(struct sock *sk, aux = handler->idiag_get_aux_size(sk, net_admin); return nla_total_size(sizeof(struct tcp_info)) - + nla_total_size(1) /* INET_DIAG_SHUTDOWN */ - + nla_total_size(1) /* INET_DIAG_TOS */ - + nla_total_size(1) /* INET_DIAG_TCLASS */ - + nla_total_size(4) /* INET_DIAG_MARK */ - + nla_total_size(4) /* INET_DIAG_CLASS_ID */ - + nla_total_size(sizeof(struct inet_diag_meminfo)) + nla_total_size(sizeof(struct inet_diag_msg)) + + inet_diag_msg_attrs_size() + + nla_total_size(sizeof(struct inet_diag_meminfo)) + nla_total_size(SK_MEMINFO_VARS * sizeof(u32)) + nla_total_size(TCP_CA_NAME_MAX) + nla_total_size(sizeof(struct tcpvegas_info)) @@ -147,6 +143,24 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, sk->sk_mark)) goto errout; + if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) || + ext & (1 << (INET_DIAG_TCLASS - 1))) { + u32 classid = 0; + +#ifdef CONFIG_SOCK_CGROUP_DATA + classid = sock_cgroup_classid(&sk->sk_cgrp_data); +#endif + /* Fallback to socket priority if class id isn't set. + * Classful qdiscs use it as direct reference to class. + * For cgroup2 classid is always zero. + */ + if (!classid) + classid = sk->sk_priority; + + if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid)) + goto errout; + } + r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk)); r->idiag_inode = sock_i_ino(sk); @@ -284,24 +298,6 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, goto errout; } - if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) || - ext & (1 << (INET_DIAG_TCLASS - 1))) { - u32 classid = 0; - -#ifdef CONFIG_SOCK_CGROUP_DATA - classid = sock_cgroup_classid(&sk->sk_cgrp_data); -#endif - /* Fallback to socket priority if class id isn't set. - * Classful qdiscs use it as direct reference to class. - * For cgroup2 classid is always zero. - */ - if (!classid) - classid = sk->sk_priority; - - if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid)) - goto errout; - } - out: nlmsg_end(skb, nlh); return 0; diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c index e35736b99300..a93e7d1e1251 100644 --- a/net/ipv4/raw_diag.c +++ b/net/ipv4/raw_diag.c @@ -100,8 +100,9 @@ static int raw_diag_dump_one(struct sk_buff *in_skb, if (IS_ERR(sk)) return PTR_ERR(sk); - rep = nlmsg_new(sizeof(struct inet_diag_msg) + - sizeof(struct inet_diag_meminfo) + 64, + rep = nlmsg_new(nla_total_size(sizeof(struct inet_diag_msg)) + + inet_diag_msg_attrs_size() + + nla_total_size(sizeof(struct inet_diag_meminfo)) + 64, GFP_KERNEL); if (!rep) { sock_put(sk); diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index 910555a4d9fe..dccd2286bc28 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -64,8 +64,9 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, goto out; err = -ENOMEM; - rep = nlmsg_new(sizeof(struct inet_diag_msg) + - sizeof(struct inet_diag_meminfo) + 64, + rep = nlmsg_new(nla_total_size(sizeof(struct inet_diag_msg)) + + inet_diag_msg_attrs_size() + + nla_total_size(sizeof(struct inet_diag_meminfo)) + 64, GFP_KERNEL); if (!rep) goto out; -- cgit v1.2.3 From d752a4986532cb6305dfd5290a614cde8072769d Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Mon, 9 Mar 2020 22:16:06 -0700 Subject: net: memcg: late association of sock to memcg If a TCP socket is allocated in IRQ context or cloned from unassociated (i.e. not associated to a memcg) in IRQ context then it will remain unassociated for its whole life. Almost half of the TCPs created on the system are created in IRQ context, so, memory used by such sockets will not be accounted by the memcg. This issue is more widespread in cgroup v1 where network memory accounting is opt-in but it can happen in cgroup v2 if the source socket for the cloning was created in root memcg. To fix the issue, just do the association of the sockets at the accept() time in the process context and then force charge the memory buffer already used and reserved by the socket. Signed-off-by: Shakeel Butt Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/inet_connection_sock.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'net/ipv4') diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index a4db79b1b643..65a3b2565102 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -482,6 +482,26 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern) } spin_unlock_bh(&queue->fastopenq.lock); } + + if (mem_cgroup_sockets_enabled) { + int amt; + + /* atomically get the memory usage, set and charge the + * sk->sk_memcg. + */ + lock_sock(newsk); + + /* The sk has not been accepted yet, no need to look at + * sk->sk_wmem_queued. + */ + amt = sk_mem_pages(newsk->sk_forward_alloc + + atomic_read(&sk->sk_rmem_alloc)); + mem_cgroup_sk_alloc(newsk); + if (newsk->sk_memcg && amt) + mem_cgroup_charge_skmem(newsk->sk_memcg, amt); + + release_sock(newsk); + } out: release_sock(sk); if (req) -- cgit v1.2.3 From 06669ea346e476a5339033d77ef175566a40efbb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 11 Mar 2020 11:44:26 -0700 Subject: net: memcg: fix lockdep splat in inet_csk_accept() Locking newsk while still holding the listener lock triggered a lockdep splat [1] We can simply move the memcg code after we release the listener lock, as this can also help if multiple threads are sharing a common listener. Also fix a typo while reading socket sk_rmem_alloc. [1] WARNING: possible recursive locking detected 5.6.0-rc3-syzkaller #0 Not tainted -------------------------------------------- syz-executor598/9524 is trying to acquire lock: ffff88808b5b8b90 (sk_lock-AF_INET6){+.+.}, at: lock_sock include/net/sock.h:1541 [inline] ffff88808b5b8b90 (sk_lock-AF_INET6){+.+.}, at: inet_csk_accept+0x69f/0xd30 net/ipv4/inet_connection_sock.c:492 but task is already holding lock: ffff88808b5b9590 (sk_lock-AF_INET6){+.+.}, at: lock_sock include/net/sock.h:1541 [inline] ffff88808b5b9590 (sk_lock-AF_INET6){+.+.}, at: inet_csk_accept+0x8d/0xd30 net/ipv4/inet_connection_sock.c:445 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(sk_lock-AF_INET6); lock(sk_lock-AF_INET6); *** DEADLOCK *** May be due to missing lock nesting notation 1 lock held by syz-executor598/9524: #0: ffff88808b5b9590 (sk_lock-AF_INET6){+.+.}, at: lock_sock include/net/sock.h:1541 [inline] #0: ffff88808b5b9590 (sk_lock-AF_INET6){+.+.}, at: inet_csk_accept+0x8d/0xd30 net/ipv4/inet_connection_sock.c:445 stack backtrace: CPU: 0 PID: 9524 Comm: syz-executor598 Not tainted 5.6.0-rc3-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x188/0x20d lib/dump_stack.c:118 print_deadlock_bug kernel/locking/lockdep.c:2370 [inline] check_deadlock kernel/locking/lockdep.c:2411 [inline] validate_chain kernel/locking/lockdep.c:2954 [inline] __lock_acquire.cold+0x114/0x288 kernel/locking/lockdep.c:3954 lock_acquire+0x197/0x420 kernel/locking/lockdep.c:4484 lock_sock_nested+0xc5/0x110 net/core/sock.c:2947 lock_sock include/net/sock.h:1541 [inline] inet_csk_accept+0x69f/0xd30 net/ipv4/inet_connection_sock.c:492 inet_accept+0xe9/0x7c0 net/ipv4/af_inet.c:734 __sys_accept4_file+0x3ac/0x5b0 net/socket.c:1758 __sys_accept4+0x53/0x90 net/socket.c:1809 __do_sys_accept4 net/socket.c:1821 [inline] __se_sys_accept4 net/socket.c:1818 [inline] __x64_sys_accept4+0x93/0xf0 net/socket.c:1818 do_syscall_64+0xf6/0x790 arch/x86/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x4445c9 Code: e8 0c 0d 03 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 eb 08 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007ffc35b37608 EFLAGS: 00000246 ORIG_RAX: 0000000000000120 RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00000000004445c9 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000003 RBP: 0000000000000000 R08: 0000000000306777 R09: 0000000000306777 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00000000004053d0 R14: 0000000000000000 R15: 0000000000000000 Fixes: d752a4986532 ("net: memcg: late association of sock to memcg") Signed-off-by: Eric Dumazet Cc: Shakeel Butt Reported-by: syzbot Signed-off-by: David S. Miller --- net/ipv4/inet_connection_sock.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 65a3b2565102..d545fb99a8a1 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -483,27 +483,27 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern) spin_unlock_bh(&queue->fastopenq.lock); } - if (mem_cgroup_sockets_enabled) { +out: + release_sock(sk); + if (newsk && mem_cgroup_sockets_enabled) { int amt; /* atomically get the memory usage, set and charge the - * sk->sk_memcg. + * newsk->sk_memcg. */ lock_sock(newsk); - /* The sk has not been accepted yet, no need to look at - * sk->sk_wmem_queued. + /* The socket has not been accepted yet, no need to look at + * newsk->sk_wmem_queued. */ amt = sk_mem_pages(newsk->sk_forward_alloc + - atomic_read(&sk->sk_rmem_alloc)); + atomic_read(&newsk->sk_rmem_alloc)); mem_cgroup_sk_alloc(newsk); if (newsk->sk_memcg && amt) mem_cgroup_charge_skmem(newsk->sk_memcg, amt); release_sock(newsk); } -out: - release_sock(sk); if (req) reqsk_put(req); return newsk; -- cgit v1.2.3 From e1f8f78ffe9854308b9e12a73ebe4e909074fc33 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Fri, 13 Mar 2020 13:39:36 +0200 Subject: net: ip_gre: Separate ERSPAN newlink / changelink callbacks ERSPAN shares most of the code path with GRE and gretap code. While that helps keep the code compact, it is also error prone. Currently a broken userspace can turn a gretap tunnel into a de facto ERSPAN one by passing IFLA_GRE_ERSPAN_VER. There has been a similar issue in ip6gretap in the past. To prevent these problems in future, split the newlink and changelink code paths. Split the ERSPAN code out of ipgre_netlink_parms() into a new function erspan_netlink_parms(). Extract a piece of common logic from ipgre_newlink() and ipgre_changelink() into ipgre_newlink_encap_setup(). Add erspan_newlink() and erspan_changelink(). Fixes: 84e54fe0a5ea ("gre: introduce native tunnel support for ERSPAN") Signed-off-by: Petr Machata Signed-off-by: David S. Miller --- net/ipv4/ip_gre.c | 103 ++++++++++++++++++++++++++++++++++++++++++++---------- 1 file changed, 85 insertions(+), 18 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 8274f98c511c..7765c65fc7d2 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1153,6 +1153,22 @@ static int ipgre_netlink_parms(struct net_device *dev, if (data[IFLA_GRE_FWMARK]) *fwmark = nla_get_u32(data[IFLA_GRE_FWMARK]); + return 0; +} + +static int erspan_netlink_parms(struct net_device *dev, + struct nlattr *data[], + struct nlattr *tb[], + struct ip_tunnel_parm *parms, + __u32 *fwmark) +{ + struct ip_tunnel *t = netdev_priv(dev); + int err; + + err = ipgre_netlink_parms(dev, data, tb, parms, fwmark); + if (err) + return err; + if (data[IFLA_GRE_ERSPAN_VER]) { t->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]); @@ -1276,45 +1292,70 @@ static void ipgre_tap_setup(struct net_device *dev) ip_tunnel_setup(dev, gre_tap_net_id); } -static int ipgre_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], - struct netlink_ext_ack *extack) +static int +ipgre_newlink_encap_setup(struct net_device *dev, struct nlattr *data[]) { - struct ip_tunnel_parm p; struct ip_tunnel_encap ipencap; - __u32 fwmark = 0; - int err; if (ipgre_netlink_encap_parms(data, &ipencap)) { struct ip_tunnel *t = netdev_priv(dev); - err = ip_tunnel_encap_setup(t, &ipencap); + int err = ip_tunnel_encap_setup(t, &ipencap); if (err < 0) return err; } + return 0; +} + +static int ipgre_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct ip_tunnel_parm p; + __u32 fwmark = 0; + int err; + + err = ipgre_newlink_encap_setup(dev, data); + if (err) + return err; + err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark); if (err < 0) return err; return ip_tunnel_newlink(dev, tb, &p, fwmark); } +static int erspan_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct ip_tunnel_parm p; + __u32 fwmark = 0; + int err; + + err = ipgre_newlink_encap_setup(dev, data); + if (err) + return err; + + err = erspan_netlink_parms(dev, data, tb, &p, &fwmark); + if (err) + return err; + return ip_tunnel_newlink(dev, tb, &p, fwmark); +} + static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); - struct ip_tunnel_encap ipencap; __u32 fwmark = t->fwmark; struct ip_tunnel_parm p; int err; - if (ipgre_netlink_encap_parms(data, &ipencap)) { - err = ip_tunnel_encap_setup(t, &ipencap); - - if (err < 0) - return err; - } + err = ipgre_newlink_encap_setup(dev, data); + if (err) + return err; err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark); if (err < 0) @@ -1327,8 +1368,34 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], t->parms.i_flags = p.i_flags; t->parms.o_flags = p.o_flags; - if (strcmp(dev->rtnl_link_ops->kind, "erspan")) - ipgre_link_update(dev, !tb[IFLA_MTU]); + ipgre_link_update(dev, !tb[IFLA_MTU]); + + return 0; +} + +static int erspan_changelink(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct ip_tunnel *t = netdev_priv(dev); + __u32 fwmark = t->fwmark; + struct ip_tunnel_parm p; + int err; + + err = ipgre_newlink_encap_setup(dev, data); + if (err) + return err; + + err = erspan_netlink_parms(dev, data, tb, &p, &fwmark); + if (err < 0) + return err; + + err = ip_tunnel_changelink(dev, tb, &p, fwmark); + if (err < 0) + return err; + + t->parms.i_flags = p.i_flags; + t->parms.o_flags = p.o_flags; return 0; } @@ -1519,8 +1586,8 @@ static struct rtnl_link_ops erspan_link_ops __read_mostly = { .priv_size = sizeof(struct ip_tunnel), .setup = erspan_setup, .validate = erspan_validate, - .newlink = ipgre_newlink, - .changelink = ipgre_changelink, + .newlink = erspan_newlink, + .changelink = erspan_changelink, .dellink = ip_tunnel_dellink, .get_size = ipgre_get_size, .fill_info = ipgre_fill_info, -- cgit v1.2.3 From 32ca98feab8c9076c89c0697c5a85e46fece809d Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Mon, 16 Mar 2020 19:53:00 +0200 Subject: net: ip_gre: Accept IFLA_INFO_DATA-less configuration The fix referenced below causes a crash when an ERSPAN tunnel is created without passing IFLA_INFO_DATA. Fix by validating passed-in data in the same way as ipgre does. Fixes: e1f8f78ffe98 ("net: ip_gre: Separate ERSPAN newlink / changelink callbacks") Reported-by: syzbot+1b4ebf4dae4e510dd219@syzkaller.appspotmail.com Signed-off-by: Petr Machata Signed-off-by: David S. Miller --- net/ipv4/ip_gre.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/ipv4') diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 7765c65fc7d2..029b24eeafba 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1168,6 +1168,8 @@ static int erspan_netlink_parms(struct net_device *dev, err = ipgre_netlink_parms(dev, data, tb, parms, fwmark); if (err) return err; + if (!data) + return 0; if (data[IFLA_GRE_ERSPAN_VER]) { t->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]); -- cgit v1.2.3 From 8e7ae2518f5265f0ef09d561748098fde5a87ccd Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Fri, 13 Mar 2020 18:02:09 -0700 Subject: bpf: Sanitize the bpf_struct_ops tcp-cc name The bpf_struct_ops tcp-cc name should be sanitized in order to avoid problematic chars (e.g. whitespaces). This patch reuses the bpf_obj_name_cpy() for accepting the same set of characters in order to keep a consistent bpf programming experience. A "size" param is added. Also, the strlen is returned on success so that the caller (like the bpf_tcp_ca here) can error out on empty name. The existing callers of the bpf_obj_name_cpy() only need to change the testing statement to "if (err < 0)". For all these existing callers, the err will be overwritten later, so no extra change is needed for the new strlen return value. v3: - reverse xmas tree style v2: - Save the orig_src to avoid "end - size" (Andrii) Fixes: 0baf26b0fcd7 ("bpf: tcp: Support tcp_congestion_ops in bpf") Signed-off-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200314010209.1131542-1-kafai@fb.com --- net/ipv4/bpf_tcp_ca.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 574972bc7299..2bf3abeb1456 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -184,7 +184,6 @@ static int bpf_tcp_ca_init_member(const struct btf_type *t, { const struct tcp_congestion_ops *utcp_ca; struct tcp_congestion_ops *tcp_ca; - size_t tcp_ca_name_len; int prog_fd; u32 moff; @@ -199,13 +198,11 @@ static int bpf_tcp_ca_init_member(const struct btf_type *t, tcp_ca->flags = utcp_ca->flags; return 1; case offsetof(struct tcp_congestion_ops, name): - tcp_ca_name_len = strnlen(utcp_ca->name, sizeof(utcp_ca->name)); - if (!tcp_ca_name_len || - tcp_ca_name_len == sizeof(utcp_ca->name)) + if (bpf_obj_name_cpy(tcp_ca->name, utcp_ca->name, + sizeof(tcp_ca->name)) <= 0) return -EINVAL; if (tcp_ca_find(utcp_ca->name)) return -EEXIST; - memcpy(tcp_ca->name, utcp_ca->name, sizeof(tcp_ca->name)); return 1; } -- cgit v1.2.3 From b738a185beaab8728943acdb3e67371b8a88185e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 19 Mar 2020 12:49:55 -0700 Subject: tcp: ensure skb->dev is NULL before leaving TCP stack skb->rbnode is sharing three skb fields : next, prev, dev When a packet is sent, TCP keeps the original skb (master) in a rtx queue, which was converted to rbtree a while back. __tcp_transmit_skb() is responsible to clone the master skb, and add the TCP header to the clone before sending it to network layer. skb_clone() already clears skb->next and skb->prev, but copies the master oskb->dev into the clone. We need to clear skb->dev, otherwise lower layers could interpret the value as a pointer to a netdev. This old bug surfaced recently when commit 28f8bfd1ac94 ("netfilter: Support iif matches in POSTROUTING") was merged. Before this netfilter commit, skb->dev value was ignored and changed before reaching dev_queue_xmit() Fixes: 75c119afe14f ("tcp: implement rb-tree based retransmit queue") Fixes: 28f8bfd1ac94 ("netfilter: Support iif matches in POSTROUTING") Signed-off-by: Eric Dumazet Reported-by: Martin Zaharinov Cc: Florian Westphal Cc: Pablo Neira Ayuso Signed-off-by: David S. Miller --- net/ipv4/tcp_output.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 306e25d743e8..e8cf8fde3d37 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1109,6 +1109,10 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, if (unlikely(!skb)) return -ENOBUFS; + /* retransmit skbs might have a non zero value in skb->dev + * because skb->dev is aliased with skb->rbnode.rb_left + */ + skb->dev = NULL; } inet = inet_sk(sk); -- cgit v1.2.3 From 07f8e4d0fddbf2f87e4cefb551278abc38db8cdd Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 20 Mar 2020 16:52:02 +0100 Subject: tcp: also NULL skb->dev when copy was needed In rare cases retransmit logic will make a full skb copy, which will not trigger the zeroing added in recent change b738a185beaa ("tcp: ensure skb->dev is NULL before leaving TCP stack"). Cc: Eric Dumazet Fixes: 75c119afe14f ("tcp: implement rb-tree based retransmit queue") Fixes: 28f8bfd1ac94 ("netfilter: Support iif matches in POSTROUTING") Signed-off-by: Florian Westphal Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_output.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index e8cf8fde3d37..2f45cde168c4 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3041,8 +3041,12 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) tcp_skb_tsorted_save(skb) { nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC); - err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : - -ENOBUFS; + if (nskb) { + nskb->dev = NULL; + err = tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC); + } else { + err = -ENOBUFS; + } } tcp_skb_tsorted_restore(skb); if (!err) { -- cgit v1.2.3 From 6cd6cbf593bfa3ae6fc3ed34ac21da4d35045425 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 18 Mar 2020 19:21:02 -0700 Subject: tcp: repair: fix TCP_QUEUE_SEQ implementation When application uses TCP_QUEUE_SEQ socket option to change tp->rcv_next, we must also update tp->copied_seq. Otherwise, stuff relying on tcp_inq() being precise can eventually be confused. For example, tcp_zerocopy_receive() might crash because it does not expect tcp_recv_skb() to return NULL. We could add tests in various places to fix the issue, or simply make sure tcp_inq() wont return a random value, and leave fast path as it is. Note that this fixes ioctl(fd, SIOCINQ, &val) at the same time. Fixes: ee9952831cfd ("tcp: Initial repair mode") Fixes: 05255b823a61 ("tcp: add TCP_ZEROCOPY_RECEIVE support for zerocopy receive") Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index eb2d80519f8e..dc77c303e6f7 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2948,8 +2948,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level, err = -EPERM; else if (tp->repair_queue == TCP_SEND_QUEUE) WRITE_ONCE(tp->write_seq, val); - else if (tp->repair_queue == TCP_RECV_QUEUE) + else if (tp->repair_queue == TCP_RECV_QUEUE) { WRITE_ONCE(tp->rcv_nxt, val); + WRITE_ONCE(tp->copied_seq, val); + } else err = -EINVAL; break; -- cgit v1.2.3 From dddeb30bfc43926620f954266fd12c65a7206f07 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Thu, 19 Mar 2020 22:54:21 -0400 Subject: ipv4: fix a RCU-list lock in inet_dump_fib() There is a place, inet_dump_fib() fib_table_dump fn_trie_dump_leaf() hlist_for_each_entry_rcu() without rcu_read_lock() will trigger a warning, WARNING: suspicious RCU usage ----------------------------- net/ipv4/fib_trie.c:2216 RCU-list traversed in non-reader section!! other info that might help us debug this: rcu_scheduler_active = 2, debug_locks = 1 1 lock held by ip/1923: #0: ffffffff8ce76e40 (rtnl_mutex){+.+.}, at: netlink_dump+0xd6/0x840 Call Trace: dump_stack+0xa1/0xea lockdep_rcu_suspicious+0x103/0x10d fn_trie_dump_leaf+0x581/0x590 fib_table_dump+0x15f/0x220 inet_dump_fib+0x4ad/0x5d0 netlink_dump+0x350/0x840 __netlink_dump_start+0x315/0x3e0 rtnetlink_rcv_msg+0x4d1/0x720 netlink_rcv_skb+0xf0/0x220 rtnetlink_rcv+0x15/0x20 netlink_unicast+0x306/0x460 netlink_sendmsg+0x44b/0x770 __sys_sendto+0x259/0x270 __x64_sys_sendto+0x80/0xa0 do_syscall_64+0x69/0xf4 entry_SYSCALL_64_after_hwframe+0x49/0xb3 Fixes: 18a8021a7be3 ("net/ipv4: Plumb support for filtering route dumps") Signed-off-by: Qian Cai Reviewed-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/fib_frontend.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/ipv4') diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 577db1d50a24..213be9c050ad 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -997,7 +997,9 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) return -ENOENT; } + rcu_read_lock(); err = fib_table_dump(tb, skb, cb, &filter); + rcu_read_unlock(); return skb->len ? : err; } -- cgit v1.2.3