From b5fc29233d28be7a3322848ebe73ac327559cdb9 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 19 Oct 2022 15:35:59 -0700 Subject: inet6: Remove inet6_destroy_sock() in sk->sk_prot->destroy(). After commit d38afeec26ed ("tcp/udp: Call inet6_destroy_sock() in IPv6 sk->sk_destruct()."), we call inet6_destroy_sock() in sk->sk_destruct() by setting inet6_sock_destruct() to it to make sure we do not leak inet6-specific resources. Now we can remove unnecessary inet6_destroy_sock() calls in sk->sk_prot->destroy(). DCCP and SCTP have their own sk->sk_destruct() function, so we change them separately in the following patches. Signed-off-by: Kuniyuki Iwashima Reviewed-by: Matthieu Baerts Signed-off-by: David S. Miller --- net/ipv6/tcp_ipv6.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'net/ipv6/tcp_ipv6.c') diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 2a3f9296df1e..f676be14e6b6 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1966,12 +1966,6 @@ static int tcp_v6_init_sock(struct sock *sk) return 0; } -static void tcp_v6_destroy_sock(struct sock *sk) -{ - tcp_v4_destroy_sock(sk); - inet6_destroy_sock(sk); -} - #ifdef CONFIG_PROC_FS /* Proc filesystem TCPv6 sock list dumping. */ static void get_openreq6(struct seq_file *seq, @@ -2164,7 +2158,7 @@ struct proto tcpv6_prot = { .accept = inet_csk_accept, .ioctl = tcp_ioctl, .init = tcp_v6_init_sock, - .destroy = tcp_v6_destroy_sock, + .destroy = tcp_v4_destroy_sock, .shutdown = tcp_shutdown, .setsockopt = tcp_setsockopt, .getsockopt = tcp_getsockopt, -- cgit From 77934dc6db0d2b111a8f2759e9ad2fb67f5cffa5 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 18 Nov 2022 17:49:11 -0800 Subject: dccp/tcp: Reset saddr on failure after inet6?_hash_connect(). When connect() is called on a socket bound to the wildcard address, we change the socket's saddr to a local address. If the socket fails to connect() to the destination, we have to reset the saddr. However, when an error occurs after inet_hash6?_connect() in (dccp|tcp)_v[46]_conect(), we forget to reset saddr and leave the socket bound to the address. From the user's point of view, whether saddr is reset or not varies with errno. Let's fix this inconsistent behaviour. Note that after this patch, the repro [0] will trigger the WARN_ON() in inet_csk_get_port() again, but this patch is not buggy and rather fixes a bug papering over the bhash2's bug for which we need another fix. For the record, the repro causes -EADDRNOTAVAIL in inet_hash6_connect() by this sequence: s1 = socket() s1.setsockopt(SOL_SOCKET, SO_REUSEADDR, 1) s1.bind(('127.0.0.1', 10000)) s1.sendto(b'hello', MSG_FASTOPEN, (('127.0.0.1', 10000))) # or s1.connect(('127.0.0.1', 10000)) s2 = socket() s2.setsockopt(SOL_SOCKET, SO_REUSEADDR, 1) s2.bind(('0.0.0.0', 10000)) s2.connect(('127.0.0.1', 10000)) # -EADDRNOTAVAIL s2.listen(32) # WARN_ON(inet_csk(sk)->icsk_bind2_hash != tb2); [0]: https://syzkaller.appspot.com/bug?extid=015d756bbd1f8b5c8f09 Fixes: 3df80d9320bc ("[DCCP]: Introduce DCCPv6") Fixes: 7c657876b63c ("[DCCP]: Initial implementation") Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Kuniyuki Iwashima Acked-by: Joanne Koong Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- net/ipv6/tcp_ipv6.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/ipv6/tcp_ipv6.c') diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 2a3f9296df1e..81b396e5cf79 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -359,6 +359,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, late_failure: tcp_set_state(sk, TCP_CLOSE); + if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) + inet_reset_saddr(sk); failure: inet->inet_dport = 0; sk->sk_route_caps = 0; -- cgit From 8c5dae4c1a49489499e6708c7dd284370ca36287 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 18 Nov 2022 17:49:13 -0800 Subject: dccp/tcp: Update saddr under bhash's lock. When we call connect() for a socket bound to a wildcard address, we update saddr locklessly. However, it could result in a data race; another thread iterating over bhash might see a corrupted address. Let's update saddr under the bhash bucket's lock. Fixes: 3df80d9320bc ("[DCCP]: Introduce DCCPv6") Fixes: 7c657876b63c ("[DCCP]: Initial implementation") Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Kuniyuki Iwashima Acked-by: Joanne Koong Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- net/ipv6/tcp_ipv6.c | 19 +++---------------- 1 file changed, 3 insertions(+), 16 deletions(-) (limited to 'net/ipv6/tcp_ipv6.c') diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 81b396e5cf79..2f3ca3190d26 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -292,24 +292,11 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; if (!saddr) { - struct inet_bind_hashbucket *prev_addr_hashbucket = NULL; - struct in6_addr prev_v6_rcv_saddr; - - if (icsk->icsk_bind2_hash) { - prev_addr_hashbucket = inet_bhashfn_portaddr(tcp_death_row->hashinfo, - sk, net, inet->inet_num); - prev_v6_rcv_saddr = sk->sk_v6_rcv_saddr; - } saddr = &fl6.saddr; - sk->sk_v6_rcv_saddr = *saddr; - if (prev_addr_hashbucket) { - err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk); - if (err) { - sk->sk_v6_rcv_saddr = prev_v6_rcv_saddr; - goto failure; - } - } + err = inet_bhash2_update_saddr(sk, saddr, AF_INET6); + if (err) + goto failure; } /* set the source address */ -- cgit From e0833d1fedb02f038b526ae7dde178a076f56545 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 18 Nov 2022 17:49:14 -0800 Subject: dccp/tcp: Fixup bhash2 bucket when connect() fails. If a socket bound to a wildcard address fails to connect(), we only reset saddr and keep the port. Then, we have to fix up the bhash2 bucket; otherwise, the bucket has an inconsistent address in the list. Also, listen() for such a socket will fire the WARN_ON() in inet_csk_get_port(). [0] Note that when a system runs out of memory, we give up fixing the bucket and unlink sk from bhash and bhash2 by inet_put_port(). [0]: WARNING: CPU: 0 PID: 207 at net/ipv4/inet_connection_sock.c:548 inet_csk_get_port (net/ipv4/inet_connection_sock.c:548 (discriminator 1)) Modules linked in: CPU: 0 PID: 207 Comm: bhash2_prev_rep Not tainted 6.1.0-rc3-00799-gc8421681c845 #63 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.0-1.amzn2022.0.1 04/01/2014 RIP: 0010:inet_csk_get_port (net/ipv4/inet_connection_sock.c:548 (discriminator 1)) Code: 74 a7 eb 93 48 8b 54 24 18 0f b7 cb 4c 89 e6 4c 89 ff e8 48 b2 ff ff 49 8b 87 18 04 00 00 e9 32 ff ff ff 0f 0b e9 34 ff ff ff <0f> 0b e9 42 ff ff ff 41 8b 7f 50 41 8b 4f 54 89 fe 81 f6 00 00 ff RSP: 0018:ffffc900003d7e50 EFLAGS: 00010202 RAX: ffff8881047fb500 RBX: 0000000000004e20 RCX: 0000000000000000 RDX: 000000000000000a RSI: 00000000fffffe00 RDI: 00000000ffffffff RBP: ffffffff8324dc00 R08: 0000000000000001 R09: 0000000000000001 R10: 0000000000000001 R11: 0000000000000001 R12: 0000000000000000 R13: 0000000000000001 R14: 0000000000004e20 R15: ffff8881054e1280 FS: 00007f8ac04dc740(0000) GS:ffff88842fc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020001540 CR3: 00000001055fa003 CR4: 0000000000770ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: inet_csk_listen_start (net/ipv4/inet_connection_sock.c:1205) inet_listen (net/ipv4/af_inet.c:228) __sys_listen (net/socket.c:1810) __x64_sys_listen (net/socket.c:1819 net/socket.c:1817 net/socket.c:1817) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) RIP: 0033:0x7f8ac051de5d Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 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 73 01 c3 48 8b 0d 93 af 1b 00 f7 d8 64 89 01 48 RSP: 002b:00007ffc1c177248 EFLAGS: 00000206 ORIG_RAX: 0000000000000032 RAX: ffffffffffffffda RBX: 0000000020001550 RCX: 00007f8ac051de5d RDX: ffffffffffffff80 RSI: 0000000000000000 RDI: 0000000000000004 RBP: 00007ffc1c177270 R08: 0000000000000018 R09: 0000000000000007 R10: 0000000020001540 R11: 0000000000000206 R12: 00007ffc1c177388 R13: 0000000000401169 R14: 0000000000403e18 R15: 00007f8ac0723000 Fixes: 28044fc1d495 ("net: Add a bhash2 table hashed by port and address") Reported-by: syzbot Reported-by: Mat Martineau Signed-off-by: Kuniyuki Iwashima Acked-by: Joanne Koong Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- net/ipv6/tcp_ipv6.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'net/ipv6/tcp_ipv6.c') diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 2f3ca3190d26..f0548dbcabd2 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -346,8 +346,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, late_failure: tcp_set_state(sk, TCP_CLOSE); - if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) - inet_reset_saddr(sk); + inet_bhash2_reset_saddr(sk); failure: inet->inet_dport = 0; sk->sk_route_caps = 0; -- cgit From 459837b522f7dff3b6681f534d8fff4eca19b7d1 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Wed, 23 Nov 2022 17:38:57 +0000 Subject: net/tcp: Disable TCP-MD5 static key on tcp_md5sig_info destruction To do that, separate two scenarios: - where it's the first MD5 key on the system, which means that enabling of the static key may need to sleep; - copying of an existing key from a listening socket to the request socket upon receiving a signed TCP segment, where static key was already enabled (when the key was added to the listening socket). Now the life-time of the static branch for TCP-MD5 is until: - last tcp_md5sig_info is destroyed - last socket in time-wait state with MD5 key is closed. Which means that after all sockets with TCP-MD5 keys are gone, the system gets back the performance of disabled md5-key static branch. While at here, provide static_key_fast_inc() helper that does ref counter increment in atomic fashion (without grabbing cpus_read_lock() on CONFIG_JUMP_LABEL=y). This is needed to add a new user for a static_key when the caller controls the lifetime of another user. Signed-off-by: Dmitry Safonov Acked-by: Jakub Kicinski Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- net/ipv6/tcp_ipv6.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'net/ipv6/tcp_ipv6.c') diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index f52b6f271a24..80df917ced5f 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -665,12 +665,11 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, int optname, if (ipv6_addr_v4mapped(&sin6->sin6_addr)) return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3], AF_INET, prefixlen, l3index, flags, - cmd.tcpm_key, cmd.tcpm_keylen, - GFP_KERNEL); + cmd.tcpm_key, cmd.tcpm_keylen); return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr, AF_INET6, prefixlen, l3index, flags, - cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); + cmd.tcpm_key, cmd.tcpm_keylen); } static int tcp_v6_md5_hash_headers(struct tcp_md5sig_pool *hp, @@ -1370,9 +1369,8 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * * memory, then we end up not copying the key * across. Shucks. */ - tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newsk->sk_v6_daddr, - AF_INET6, 128, l3index, key->flags, key->key, key->keylen, - sk_gfp_mask(sk, GFP_ATOMIC)); + tcp_md5_key_copy(newsk, (union tcp_md5_addr *)&newsk->sk_v6_daddr, + AF_INET6, 128, l3index, key); } #endif -- cgit From b389d1affc2cc2dc8686cdab303a30b2ad3a81d4 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Wed, 23 Nov 2022 17:38:58 +0000 Subject: net/tcp: Do cleanup on tcp_md5_key_copy() failure If the kernel was short on (atomic) memory and failed to allocate it - don't proceed to creation of request socket. Otherwise the socket would be unsigned and userspace likely doesn't expect that the TCP is not MD5-signed anymore. Signed-off-by: Dmitry Safonov Acked-by: Jakub Kicinski Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- net/ipv6/tcp_ipv6.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'net/ipv6/tcp_ipv6.c') diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 80df917ced5f..11b736a76bd7 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1364,13 +1364,14 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * /* Copy over the MD5 key from the original socket */ key = tcp_v6_md5_do_lookup(sk, &newsk->sk_v6_daddr, l3index); if (key) { - /* We're using one, so create a matching key - * on the newsk structure. If we fail to get - * memory, then we end up not copying the key - * across. Shucks. - */ - tcp_md5_key_copy(newsk, (union tcp_md5_addr *)&newsk->sk_v6_daddr, - AF_INET6, 128, l3index, key); + const union tcp_md5_addr *addr; + + addr = (union tcp_md5_addr *)&newsk->sk_v6_daddr; + if (tcp_md5_key_copy(newsk, addr, AF_INET6, 128, l3index, key)) { + inet_csk_prepare_forced_close(newsk); + tcp_done(newsk); + goto out; + } } #endif -- cgit