mainline inclusion from mainline-v6.8-rc1 commit 198bc90e0e734e5f98c3d2833e8390cac3df61b2 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8RJRU
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
--------------------------------
When I run syz's reproduction C program locally, it causes the following issue: pvqspinlock: lock 0xffff9d181cd5c660 has corrupted value 0x0! WARNING: CPU: 19 PID: 21160 at __pv_queued_spin_unlock_slowpath (kernel/locking/qspinlock_paravirt.h:508) Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:__pv_queued_spin_unlock_slowpath (kernel/locking/qspinlock_paravirt.h:508) Code: 73 56 3a ff 90 c3 cc cc cc cc 8b 05 bb 1f 48 01 85 c0 74 05 c3 cc cc cc cc 8b 17 48 89 fe 48 c7 c7 30 20 ce 8f e8 ad 56 42 ff <0f> 0b c3 cc cc cc cc 0f 0b 0f 1f 40 00 90 90 90 90 90 90 90 90 90 RSP: 0018:ffffa8d200604cb8 EFLAGS: 00010282 RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffff9d1ef60e0908 RDX: 00000000ffffffd8 RSI: 0000000000000027 RDI: ffff9d1ef60e0900 RBP: ffff9d181cd5c280 R08: 0000000000000000 R09: 00000000ffff7fff R10: ffffa8d200604b68 R11: ffffffff907dcdc8 R12: 0000000000000000 R13: ffff9d181cd5c660 R14: ffff9d1813a3f330 R15: 0000000000001000 FS: 00007fa110184640(0000) GS:ffff9d1ef60c0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020000000 CR3: 000000011f65e000 CR4: 00000000000006f0 Call Trace: <IRQ> _raw_spin_unlock (kernel/locking/spinlock.c:186) inet_csk_reqsk_queue_add (net/ipv4/inet_connection_sock.c:1321) inet_csk_complete_hashdance (net/ipv4/inet_connection_sock.c:1358) tcp_check_req (net/ipv4/tcp_minisocks.c:868) tcp_v4_rcv (net/ipv4/tcp_ipv4.c:2260) ip_protocol_deliver_rcu (net/ipv4/ip_input.c:205) ip_local_deliver_finish (net/ipv4/ip_input.c:234) __netif_receive_skb_one_core (net/core/dev.c:5529) process_backlog (./include/linux/rcupdate.h:779) __napi_poll (net/core/dev.c:6533) net_rx_action (net/core/dev.c:6604) __do_softirq (./arch/x86/include/asm/jump_label.h:27) do_softirq (kernel/softirq.c:454 kernel/softirq.c:441) </IRQ> <TASK> __local_bh_enable_ip (kernel/softirq.c:381) __dev_queue_xmit (net/core/dev.c:4374) ip_finish_output2 (./include/net/neighbour.h:540 net/ipv4/ip_output.c:235) __ip_queue_xmit (net/ipv4/ip_output.c:535) __tcp_transmit_skb (net/ipv4/tcp_output.c:1462) tcp_rcv_synsent_state_process (net/ipv4/tcp_input.c:6469) tcp_rcv_state_process (net/ipv4/tcp_input.c:6657) tcp_v4_do_rcv (net/ipv4/tcp_ipv4.c:1929) __release_sock (./include/net/sock.h:1121 net/core/sock.c:2968) release_sock (net/core/sock.c:3536) inet_wait_for_connect (net/ipv4/af_inet.c:609) __inet_stream_connect (net/ipv4/af_inet.c:702) inet_stream_connect (net/ipv4/af_inet.c:748) __sys_connect (./include/linux/file.h:45 net/socket.c:2064) __x64_sys_connect (net/socket.c:2073 net/socket.c:2070 net/socket.c:2070) do_syscall_64 (arch/x86/entry/common.c:51 arch/x86/entry/common.c:82) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:129) RIP: 0033:0x7fa10ff05a3d Code: 5b 41 5c c3 66 0f 1f 84 00 00 00 00 00 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 ab a3 0e 00 f7 d8 64 89 01 48 RSP: 002b:00007fa110183de8 EFLAGS: 00000202 ORIG_RAX: 000000000000002a RAX: ffffffffffffffda RBX: 0000000020000054 RCX: 00007fa10ff05a3d RDX: 000000000000001c RSI: 0000000020000040 RDI: 0000000000000003 RBP: 00007fa110183e20 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000202 R12: 00007fa110184640 R13: 0000000000000000 R14: 00007fa10fe8b060 R15: 00007fff73e23b20 </TASK>
The issue triggering process is analyzed as follows: Thread A Thread B tcp_v4_rcv //receive ack TCP packet inet_shutdown tcp_check_req tcp_disconnect //disconnect sock ... tcp_set_state(sk, TCP_CLOSE) inet_csk_complete_hashdance ... inet_csk_reqsk_queue_add inet_listen //start listen spin_lock(&queue->rskq_lock) inet_csk_listen_start ... reqsk_queue_alloc ... spin_lock_init spin_unlock(&queue->rskq_lock) //warning
When the socket receives the ACK packet during the three-way handshake, it will hold spinlock. And then the user actively shutdowns the socket and listens to the socket immediately, the spinlock will be initialized. When the socket is going to release the spinlock, a warning is generated. Also the same issue to fastopenq.lock.
Move init spinlock to inet_create and inet_accept to make sure init the accept_queue's spinlocks once.
Fixes: fff1f3001cc5 ("tcp: add a spinlock to protect struct request_sock_queue") Fixes: 168a8f58059a ("tcp: TCP Fast Open Server - main code path") Reported-by: Ming Shu sming56@aliyun.com Signed-off-by: Zhengchao Shao shaozhengchao@huawei.com Reviewed-by: Eric Dumazet edumazet@google.com Link: https://lore.kernel.org/r/20240118012019.1751966-1-shaozhengchao@huawei.com Signed-off-by: Jakub Kicinski kuba@kernel.org
Conflicts: include/net/inet_connection_sock.h net/ipv4/af_inet.c
Signed-off-by: Zhengchao Shao shaozhengchao@huawei.com --- include/net/inet_connection_sock.h | 9 +++++++++ net/core/request_sock.c | 3 --- net/ipv4/af_inet.c | 3 +++ net/ipv4/inet_connection_sock.c | 4 ++++ 4 files changed, 16 insertions(+), 3 deletions(-)
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index da8a582ab032..696f96bd26ef 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -318,4 +318,13 @@ void inet_csk_update_fastreuse(struct inet_bind_bucket *tb, struct sock *sk);
struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu); + +static inline void inet_init_csk_locks(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + spin_lock_init(&icsk->icsk_accept_queue.rskq_lock); + spin_lock_init(&icsk->icsk_accept_queue.fastopenq.lock); +} + #endif /* _INET_CONNECTION_SOCK_H */ diff --git a/net/core/request_sock.c b/net/core/request_sock.c index 9b8727c67b58..ecdad78e7f1a 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -37,9 +37,6 @@
void reqsk_queue_alloc(struct request_sock_queue *queue) { - spin_lock_init(&queue->rskq_lock); - - spin_lock_init(&queue->fastopenq.lock); queue->fastopenq.rskq_rst_head = NULL; queue->fastopenq.rskq_rst_tail = NULL; queue->fastopenq.qlen = 0; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 694b1daaeadc..0a5752f40ea5 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -326,6 +326,9 @@ static int inet_create(struct net *net, struct socket *sock, int protocol, if (INET_PROTOSW_REUSE & answer_flags) sk->sk_reuse = SK_CAN_REUSE;
+ if (INET_PROTOSW_ICSK & answer_flags) + inet_init_csk_locks(sk); + inet = inet_sk(sk); inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 3a6655452460..4c3df3b44f8e 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -524,6 +524,10 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern) } if (req) reqsk_put(req); + + if (newsk) + inet_init_csk_locks(newsk); + return newsk; out_err: newsk = NULL;