From 8ddffdb9442a9d60b4a6e679ac48d7d21403a674 Mon Sep 17 00:00:00 2001 From: Martin Willi Date: Tue, 19 Apr 2022 15:47:00 +0200 Subject: netfilter: Update ip6_route_me_harder to consider L3 domain The commit referenced below fixed packet re-routing if Netfilter mangles a routing key property of a packet and the packet is routed in a VRF L3 domain. The fix, however, addressed IPv4 re-routing, only. This commit applies the same behavior for IPv6. While at it, untangle the nested ternary operator to make the code more readable. Fixes: 6d8b49c3a3a3 ("netfilter: Update ip_route_me_harder to consider L3 domain") Cc: stable@vger.kernel.org Signed-off-by: Martin Willi Reviewed-by: David Ahern Signed-off-by: Pablo Neira Ayuso --- net/ipv6/netfilter.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 1da332450d98..8ce60ab89015 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -24,14 +24,13 @@ int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff { const struct ipv6hdr *iph = ipv6_hdr(skb); struct sock *sk = sk_to_full_sk(sk_partial); + struct net_device *dev = skb_dst(skb)->dev; struct flow_keys flkeys; unsigned int hh_len; struct dst_entry *dst; int strict = (ipv6_addr_type(&iph->daddr) & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL)); struct flowi6 fl6 = { - .flowi6_oif = sk && sk->sk_bound_dev_if ? sk->sk_bound_dev_if : - strict ? skb_dst(skb)->dev->ifindex : 0, .flowi6_mark = skb->mark, .flowi6_uid = sock_net_uid(net, sk), .daddr = iph->daddr, @@ -39,6 +38,13 @@ int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff }; int err; + if (sk && sk->sk_bound_dev_if) + fl6.flowi6_oif = sk->sk_bound_dev_if; + else if (strict) + fl6.flowi6_oif = dev->ifindex; + else + fl6.flowi6_oif = l3mdev_master_ifindex(dev); + fib6_rules_early_flow_dissect(net, skb, &fl6, &flkeys); dst = ip6_route_output(net, sk, &fl6); err = dst->error; -- cgit v1.2.3 From fde98ae91f79cab4e020f40c35ed23cbdc59661c Mon Sep 17 00:00:00 2001 From: Peilin Ye Date: Thu, 21 Apr 2022 15:08:38 -0700 Subject: ip6_gre: Make o_seqno start from 0 in native mode For IP6GRE and IP6GRETAP devices, currently o_seqno starts from 1 in native mode. According to RFC 2890 2.2., "The first datagram is sent with a sequence number of 0." Fix it. It is worth mentioning that o_seqno already starts from 0 in collect_md mode, see the "if (tunnel->parms.collect_md)" clause in __gre6_xmit(), where tunnel->o_seqno is passed to gre_build_header() before getting incremented. Fixes: c12b395a4664 ("gre: Support GRE over IPv6") Signed-off-by: Peilin Ye Acked-by: William Tu Signed-off-by: David S. Miller --- net/ipv6/ip6_gre.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 976236736146..d9e4ac94eab4 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -724,6 +724,7 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, { struct ip6_tnl *tunnel = netdev_priv(dev); __be16 protocol; + __be16 flags; if (dev->type == ARPHRD_ETHER) IPCB(skb)->flags = 0; @@ -739,7 +740,6 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, if (tunnel->parms.collect_md) { struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; - __be16 flags; int tun_hlen; tun_info = skb_tunnel_info_txcheck(skb); @@ -770,15 +770,14 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, : 0); } else { - if (tunnel->parms.o_flags & TUNNEL_SEQ) - tunnel->o_seqno++; - if (skb_cow_head(skb, dev->needed_headroom ?: tunnel->hlen)) return -ENOMEM; - gre_build_header(skb, tunnel->tun_hlen, tunnel->parms.o_flags, + flags = tunnel->parms.o_flags; + + gre_build_header(skb, tunnel->tun_hlen, flags, protocol, tunnel->parms.o_key, - htonl(tunnel->o_seqno)); + (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) : 0); } return ip6_tnl_xmit(skb, dev, dsfield, fl6, encap_limit, pmtu, -- cgit v1.2.3 From 31c417c948d7f6909cb63f0ac3298f3c38f8ce20 Mon Sep 17 00:00:00 2001 From: Peilin Ye Date: Thu, 21 Apr 2022 15:09:02 -0700 Subject: ip_gre, ip6_gre: Fix race condition on o_seqno in collect_md mode As pointed out by Jakub Kicinski, currently using TUNNEL_SEQ in collect_md mode is racy for [IP6]GRE[TAP] devices. Consider the following sequence of events: 1. An [IP6]GRE[TAP] device is created in collect_md mode using "ip link add ... external". "ip" ignores "[o]seq" if "external" is specified, so TUNNEL_SEQ is off, and the device is marked as NETIF_F_LLTX (i.e. it uses lockless TX); 2. Someone sets TUNNEL_SEQ on outgoing skb's, using e.g. bpf_skb_set_tunnel_key() in an eBPF program attached to this device; 3. gre_fb_xmit() or __gre6_xmit() processes these skb's: gre_build_header(skb, tun_hlen, flags, protocol, tunnel_id_to_key32(tun_info->key.tun_id), (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) : 0); ^^^^^^^^^^^^^^^^^ Since we are not using the TX lock (&txq->_xmit_lock), multiple CPUs may try to do this tunnel->o_seqno++ in parallel, which is racy. Fix it by making o_seqno atomic_t. As mentioned by Eric Dumazet in commit b790e01aee74 ("ip_gre: lockless xmit"), making o_seqno atomic_t increases "chance for packets being out of order at receiver" when NETIF_F_LLTX is on. Maybe a better fix would be: 1. Do not ignore "oseq" in external mode. Users MUST specify "oseq" if they want the kernel to allow sequencing of outgoing packets; 2. Reject all outgoing TUNNEL_SEQ packets if the device was not created with "oseq". Unfortunately, that would break userspace. We could now make [IP6]GRE[TAP] devices always NETIF_F_LLTX, but let us do it in separate patches to keep this fix minimal. Suggested-by: Jakub Kicinski Fixes: 77a5196a804e ("gre: add sequence number for collect md mode.") Signed-off-by: Peilin Ye Acked-by: William Tu Signed-off-by: David S. Miller --- include/net/ip6_tunnel.h | 2 +- include/net/ip_tunnels.h | 2 +- net/ipv4/ip_gre.c | 6 +++--- net/ipv6/ip6_gre.c | 7 ++++--- 4 files changed, 9 insertions(+), 8 deletions(-) (limited to 'net/ipv6') diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index a38c4f1e4e5c..74b369bddf49 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -58,7 +58,7 @@ struct ip6_tnl { /* These fields used only by GRE */ __u32 i_seqno; /* The last seen seqno */ - __u32 o_seqno; /* The last output seqno */ + atomic_t o_seqno; /* The last output seqno */ int hlen; /* tun_hlen + encap_hlen */ int tun_hlen; /* Precalculated header length */ int encap_hlen; /* Encap header length (FOU,GUE) */ diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 88dee57eac8a..c24fa934221d 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -116,7 +116,7 @@ struct ip_tunnel { /* These four fields used only by GRE */ u32 i_seqno; /* The last seen seqno */ - u32 o_seqno; /* The last output seqno */ + atomic_t o_seqno; /* The last output seqno */ int tun_hlen; /* Precalculated header length */ /* These four fields used only by ERSPAN */ diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 21a8943f6fa4..aacee9dd771b 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -464,7 +464,7 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, /* Push GRE header. */ gre_build_header(skb, tunnel->tun_hlen, flags, proto, tunnel->parms.o_key, - (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) : 0); + (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol); } @@ -502,7 +502,7 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, (TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ); gre_build_header(skb, tunnel_hlen, flags, proto, tunnel_id_to_key32(tun_info->key.tun_id), - (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) : 0); + (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); @@ -579,7 +579,7 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) } gre_build_header(skb, 8, TUNNEL_SEQ, - proto, 0, htonl(tunnel->o_seqno++)); + proto, 0, htonl(atomic_fetch_inc(&tunnel->o_seqno))); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index d9e4ac94eab4..5136959b3dc5 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -766,7 +766,7 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, gre_build_header(skb, tun_hlen, flags, protocol, tunnel_id_to_key32(tun_info->key.tun_id), - (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) + (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); } else { @@ -777,7 +777,8 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, gre_build_header(skb, tunnel->tun_hlen, flags, protocol, tunnel->parms.o_key, - (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) : 0); + (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) + : 0); } return ip6_tnl_xmit(skb, dev, dsfield, fl6, encap_limit, pmtu, @@ -1055,7 +1056,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, /* Push GRE header. */ proto = (t->parms.erspan_ver == 1) ? htons(ETH_P_ERSPAN) : htons(ETH_P_ERSPAN2); - gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(t->o_seqno++)); + gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(atomic_fetch_inc(&t->o_seqno))); /* TooBig packet may have updated dst->dev's mtu */ if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu) -- cgit v1.2.3 From ba5a4fdd63ae0c575707030db0b634b160baddd7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 24 Apr 2022 13:35:09 -0700 Subject: tcp: make sure treq->af_specific is initialized syzbot complained about a recent change in TCP stack, hitting a NULL pointer [1] tcp request sockets have an af_specific pointer, which was used before the blamed change only for SYNACK generation in non SYNCOOKIE mode. tcp requests sockets momentarily created when third packet coming from client in SYNCOOKIE mode were not using treq->af_specific. Make sure this field is populated, in the same way normal TCP requests sockets do in tcp_conn_request(). [1] TCP: request_sock_TCPv6: Possible SYN flooding on port 20002. Sending cookies. Check SNMP counters. general protection fault, probably for non-canonical address 0xdffffc0000000001: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000008-0x000000000000000f] CPU: 1 PID: 3695 Comm: syz-executor864 Not tainted 5.18.0-rc3-syzkaller-00224-g5fd1fe4807f9 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:tcp_create_openreq_child+0xe16/0x16b0 net/ipv4/tcp_minisocks.c:534 Code: 48 c1 ea 03 80 3c 02 00 0f 85 e5 07 00 00 4c 8b b3 28 01 00 00 48 b8 00 00 00 00 00 fc ff df 49 8d 7e 08 48 89 fa 48 c1 ea 03 <80> 3c 02 00 0f 85 c9 07 00 00 48 8b 3c 24 48 89 de 41 ff 56 08 48 RSP: 0018:ffffc90000de0588 EFLAGS: 00010202 RAX: dffffc0000000000 RBX: ffff888076490330 RCX: 0000000000000100 RDX: 0000000000000001 RSI: ffffffff87d67ff0 RDI: 0000000000000008 RBP: ffff88806ee1c7f8 R08: 0000000000000000 R09: 0000000000000000 R10: ffffffff87d67f00 R11: 0000000000000000 R12: ffff88806ee1bfc0 R13: ffff88801b0e0368 R14: 0000000000000000 R15: 0000000000000000 FS: 00007f517fe58700(0000) GS:ffff8880b9d00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007ffcead76960 CR3: 000000006f97b000 CR4: 00000000003506e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: tcp_v6_syn_recv_sock+0x199/0x23b0 net/ipv6/tcp_ipv6.c:1267 tcp_get_cookie_sock+0xc9/0x850 net/ipv4/syncookies.c:207 cookie_v6_check+0x15c3/0x2340 net/ipv6/syncookies.c:258 tcp_v6_cookie_check net/ipv6/tcp_ipv6.c:1131 [inline] tcp_v6_do_rcv+0x1148/0x13b0 net/ipv6/tcp_ipv6.c:1486 tcp_v6_rcv+0x3305/0x3840 net/ipv6/tcp_ipv6.c:1725 ip6_protocol_deliver_rcu+0x2e9/0x1900 net/ipv6/ip6_input.c:422 ip6_input_finish+0x14c/0x2c0 net/ipv6/ip6_input.c:464 NF_HOOK include/linux/netfilter.h:307 [inline] NF_HOOK include/linux/netfilter.h:301 [inline] ip6_input+0x9c/0xd0 net/ipv6/ip6_input.c:473 dst_input include/net/dst.h:461 [inline] ip6_rcv_finish net/ipv6/ip6_input.c:76 [inline] NF_HOOK include/linux/netfilter.h:307 [inline] NF_HOOK include/linux/netfilter.h:301 [inline] ipv6_rcv+0x27f/0x3b0 net/ipv6/ip6_input.c:297 __netif_receive_skb_one_core+0x114/0x180 net/core/dev.c:5405 __netif_receive_skb+0x24/0x1b0 net/core/dev.c:5519 process_backlog+0x3a0/0x7c0 net/core/dev.c:5847 __napi_poll+0xb3/0x6e0 net/core/dev.c:6413 napi_poll net/core/dev.c:6480 [inline] net_rx_action+0x8ec/0xc60 net/core/dev.c:6567 __do_softirq+0x29b/0x9c2 kernel/softirq.c:558 invoke_softirq kernel/softirq.c:432 [inline] __irq_exit_rcu+0x123/0x180 kernel/softirq.c:637 irq_exit_rcu+0x5/0x20 kernel/softirq.c:649 sysvec_apic_timer_interrupt+0x93/0xc0 arch/x86/kernel/apic/apic.c:1097 Fixes: 5b0b9e4c2c89 ("tcp: md5: incorrect tcp_header_len for incoming connections") Signed-off-by: Eric Dumazet Cc: Francesco Ruggeri Signed-off-by: David S. Miller --- include/net/tcp.h | 1 + net/ipv4/syncookies.c | 8 +++++++- net/ipv6/syncookies.c | 3 ++- 3 files changed, 10 insertions(+), 2 deletions(-) (limited to 'net/ipv6') diff --git a/include/net/tcp.h b/include/net/tcp.h index b99d9d9cbd99..cc1295037533 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -480,6 +480,7 @@ int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th, u32 cookie); struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb); struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, + const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb); #ifdef CONFIG_SYN_COOKIES diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 2cb3b852d148..f33c31dd7366 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -281,6 +281,7 @@ bool cookie_ecn_ok(const struct tcp_options_received *tcp_opt, EXPORT_SYMBOL(cookie_ecn_ok); struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, + const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb) { @@ -297,6 +298,10 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, return NULL; treq = tcp_rsk(req); + + /* treq->af_specific might be used to perform TCP_MD5 lookup */ + treq->af_specific = af_ops; + treq->syn_tos = TCP_SKB_CB(skb)->ip_dsfield; #if IS_ENABLED(CONFIG_MPTCP) treq->is_mptcp = sk_is_mptcp(sk); @@ -364,7 +369,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) goto out; ret = NULL; - req = cookie_tcp_reqsk_alloc(&tcp_request_sock_ops, sk, skb); + req = cookie_tcp_reqsk_alloc(&tcp_request_sock_ops, + &tcp_request_sock_ipv4_ops, sk, skb); if (!req) goto out; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index d1b61d00368e..9cc123f000fb 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -170,7 +170,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) goto out; ret = NULL; - req = cookie_tcp_reqsk_alloc(&tcp6_request_sock_ops, sk, skb); + req = cookie_tcp_reqsk_alloc(&tcp6_request_sock_ops, + &tcp_request_sock_ipv6_ops, sk, skb); if (!req) goto out; -- cgit v1.2.3