linux/net/mptcp/diag.c

111 lines
3.1 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/* MPTCP socket monitoring support
*
* Copyright (c) 2019 Red Hat
*
* Author: Davide Caratti <dcaratti@redhat.com>
*/
#include <linux/kernel.h>
#include <linux/net.h>
#include <linux/inet_diag.h>
#include <net/netlink.h>
#include "protocol.h"
static int subflow_get_info(struct sock *sk, struct sk_buff *skb)
{
struct mptcp_subflow_context *sf;
struct nlattr *start;
u32 flags = 0;
bool slow;
int err;
mptcp: fix possible deadlock in subflow diag Syzbot and Eric reported a lockdep splat in the subflow diag: WARNING: possible circular locking dependency detected 6.8.0-rc4-syzkaller-00212-g40b9385dd8e6 #0 Not tainted syz-executor.2/24141 is trying to acquire lock: ffff888045870130 (k-sk_lock-AF_INET6){+.+.}-{0:0}, at: tcp_diag_put_ulp net/ipv4/tcp_diag.c:100 [inline] ffff888045870130 (k-sk_lock-AF_INET6){+.+.}-{0:0}, at: tcp_diag_get_aux+0x738/0x830 net/ipv4/tcp_diag.c:137 but task is already holding lock: ffffc9000135e488 (&h->lhash2[i].lock){+.+.}-{2:2}, at: spin_lock include/linux/spinlock.h:351 [inline] ffffc9000135e488 (&h->lhash2[i].lock){+.+.}-{2:2}, at: inet_diag_dump_icsk+0x39f/0x1f80 net/ipv4/inet_diag.c:1038 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&h->lhash2[i].lock){+.+.}-{2:2}: lock_acquire+0x1e3/0x530 kernel/locking/lockdep.c:5754 __raw_spin_lock include/linux/spinlock_api_smp.h:133 [inline] _raw_spin_lock+0x2e/0x40 kernel/locking/spinlock.c:154 spin_lock include/linux/spinlock.h:351 [inline] __inet_hash+0x335/0xbe0 net/ipv4/inet_hashtables.c:743 inet_csk_listen_start+0x23a/0x320 net/ipv4/inet_connection_sock.c:1261 __inet_listen_sk+0x2a2/0x770 net/ipv4/af_inet.c:217 inet_listen+0xa3/0x110 net/ipv4/af_inet.c:239 rds_tcp_listen_init+0x3fd/0x5a0 net/rds/tcp_listen.c:316 rds_tcp_init_net+0x141/0x320 net/rds/tcp.c:577 ops_init+0x352/0x610 net/core/net_namespace.c:136 __register_pernet_operations net/core/net_namespace.c:1214 [inline] register_pernet_operations+0x2cb/0x660 net/core/net_namespace.c:1283 register_pernet_device+0x33/0x80 net/core/net_namespace.c:1370 rds_tcp_init+0x62/0xd0 net/rds/tcp.c:735 do_one_initcall+0x238/0x830 init/main.c:1236 do_initcall_level+0x157/0x210 init/main.c:1298 do_initcalls+0x3f/0x80 init/main.c:1314 kernel_init_freeable+0x42f/0x5d0 init/main.c:1551 kernel_init+0x1d/0x2a0 init/main.c:1441 ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1b/0x30 arch/x86/entry/entry_64.S:242 -> #0 (k-sk_lock-AF_INET6){+.+.}-{0:0}: check_prev_add kernel/locking/lockdep.c:3134 [inline] check_prevs_add kernel/locking/lockdep.c:3253 [inline] validate_chain+0x18ca/0x58e0 kernel/locking/lockdep.c:3869 __lock_acquire+0x1345/0x1fd0 kernel/locking/lockdep.c:5137 lock_acquire+0x1e3/0x530 kernel/locking/lockdep.c:5754 lock_sock_fast include/net/sock.h:1723 [inline] subflow_get_info+0x166/0xd20 net/mptcp/diag.c:28 tcp_diag_put_ulp net/ipv4/tcp_diag.c:100 [inline] tcp_diag_get_aux+0x738/0x830 net/ipv4/tcp_diag.c:137 inet_sk_diag_fill+0x10ed/0x1e00 net/ipv4/inet_diag.c:345 inet_diag_dump_icsk+0x55b/0x1f80 net/ipv4/inet_diag.c:1061 __inet_diag_dump+0x211/0x3a0 net/ipv4/inet_diag.c:1263 inet_diag_dump_compat+0x1c1/0x2d0 net/ipv4/inet_diag.c:1371 netlink_dump+0x59b/0xc80 net/netlink/af_netlink.c:2264 __netlink_dump_start+0x5df/0x790 net/netlink/af_netlink.c:2370 netlink_dump_start include/linux/netlink.h:338 [inline] inet_diag_rcv_msg_compat+0x209/0x4c0 net/ipv4/inet_diag.c:1405 sock_diag_rcv_msg+0xe7/0x410 netlink_rcv_skb+0x1e3/0x430 net/netlink/af_netlink.c:2543 sock_diag_rcv+0x2a/0x40 net/core/sock_diag.c:280 netlink_unicast_kernel net/netlink/af_netlink.c:1341 [inline] netlink_unicast+0x7ea/0x980 net/netlink/af_netlink.c:1367 netlink_sendmsg+0xa3b/0xd70 net/netlink/af_netlink.c:1908 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0x221/0x270 net/socket.c:745 ____sys_sendmsg+0x525/0x7d0 net/socket.c:2584 ___sys_sendmsg net/socket.c:2638 [inline] __sys_sendmsg+0x2b0/0x3a0 net/socket.c:2667 do_syscall_64+0xf9/0x240 entry_SYSCALL_64_after_hwframe+0x6f/0x77 As noted by Eric we can break the lock dependency chain avoid dumping any extended info for the mptcp subflow listener: nothing actually useful is presented there. Fixes: b8adb69a7d29 ("mptcp: fix lockless access in subflow ULP diag") Cc: stable@vger.kernel.org Reported-by: Eric Dumazet <edumazet@google.com> Closes: https://lore.kernel.org/netdev/CANn89iJ=Oecw6OZDwmSYc9HJKQ_G32uN11L+oUcMu+TOD5Xiaw@mail.gmail.com/ Suggested-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com> Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org> Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org> Link: https://lore.kernel.org/r/20240223-upstream-net-20240223-misc-fixes-v1-9-162e87e48497@kernel.org Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-02-23 16:14:19 +00:00
if (inet_sk_state_load(sk) == TCP_LISTEN)
return 0;
start = nla_nest_start_noflag(skb, INET_ULP_INFO_MPTCP);
if (!start)
return -EMSGSIZE;
slow = lock_sock_fast(sk);
rcu_read_lock();
sf = rcu_dereference(inet_csk(sk)->icsk_ulp_data);
if (!sf) {
err = 0;
goto nla_failure;
}
if (sf->mp_capable)
flags |= MPTCP_SUBFLOW_FLAG_MCAP_REM;
if (sf->request_mptcp)
flags |= MPTCP_SUBFLOW_FLAG_MCAP_LOC;
if (sf->mp_join)
flags |= MPTCP_SUBFLOW_FLAG_JOIN_REM;
if (sf->request_join)
flags |= MPTCP_SUBFLOW_FLAG_JOIN_LOC;
if (sf->backup)
flags |= MPTCP_SUBFLOW_FLAG_BKUP_REM;
if (sf->request_bkup)
flags |= MPTCP_SUBFLOW_FLAG_BKUP_LOC;
if (sf->fully_established)
flags |= MPTCP_SUBFLOW_FLAG_FULLY_ESTABLISHED;
if (sf->conn_finished)
flags |= MPTCP_SUBFLOW_FLAG_CONNECTED;
if (sf->map_valid)
flags |= MPTCP_SUBFLOW_FLAG_MAPVALID;
if (nla_put_u32(skb, MPTCP_SUBFLOW_ATTR_TOKEN_REM, sf->remote_token) ||
nla_put_u32(skb, MPTCP_SUBFLOW_ATTR_TOKEN_LOC, sf->token) ||
nla_put_u32(skb, MPTCP_SUBFLOW_ATTR_RELWRITE_SEQ,
sf->rel_write_seq) ||
nla_put_u64_64bit(skb, MPTCP_SUBFLOW_ATTR_MAP_SEQ, sf->map_seq,
MPTCP_SUBFLOW_ATTR_PAD) ||
nla_put_u32(skb, MPTCP_SUBFLOW_ATTR_MAP_SFSEQ,
sf->map_subflow_seq) ||
nla_put_u32(skb, MPTCP_SUBFLOW_ATTR_SSN_OFFSET, sf->ssn_offset) ||
nla_put_u16(skb, MPTCP_SUBFLOW_ATTR_MAP_DATALEN,
sf->map_data_len) ||
nla_put_u32(skb, MPTCP_SUBFLOW_ATTR_FLAGS, flags) ||
nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_REM, sf->remote_id) ||
nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_LOC, subflow_get_local_id(sf))) {
err = -EMSGSIZE;
goto nla_failure;
}
rcu_read_unlock();
unlock_sock_fast(sk, slow);
nla_nest_end(skb, start);
return 0;
nla_failure:
rcu_read_unlock();
unlock_sock_fast(sk, slow);
nla_nest_cancel(skb, start);
return err;
}
static size_t subflow_get_info_size(const struct sock *sk)
{
size_t size = 0;
size += nla_total_size(0) + /* INET_ULP_INFO_MPTCP */
nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_TOKEN_REM */
nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_TOKEN_LOC */
nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_RELWRITE_SEQ */
nla_total_size_64bit(8) + /* MPTCP_SUBFLOW_ATTR_MAP_SEQ */
nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_MAP_SFSEQ */
nla_total_size(2) + /* MPTCP_SUBFLOW_ATTR_SSN_OFFSET */
nla_total_size(2) + /* MPTCP_SUBFLOW_ATTR_MAP_DATALEN */
nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_FLAGS */
nla_total_size(1) + /* MPTCP_SUBFLOW_ATTR_ID_REM */
nla_total_size(1) + /* MPTCP_SUBFLOW_ATTR_ID_LOC */
0;
return size;
}
void mptcp_diag_subflow_init(struct tcp_ulp_ops *ops)
{
ops->get_info = subflow_get_info;
ops->get_info_size = subflow_get_info_size;
}