Previously, BPF TCP iterator was acquiring fast version of sock lock that
disables the BH. This introduced a circular dependency with code paths that
later acquire sockets hash table bucket lock.
Replace the fast version of sock lock with slow that faciliates BPF
programs executed from the iterator to destroy TCP listening sockets
using the bpf_sock_destroy kfunc (implemened in follow-up commits).
Here is a stack trace that motivated this change:
```
lock_acquire+0xcd/0x330
_raw_spin_lock+0x33/0x40
------> sock lock acquired with BH enabled
sk_clone_lock+0x146/0x520
inet_csk_clone_lock+0x1b/0x110
tcp_create_openreq_child+0x22/0x3f0
tcp_v6_syn_recv_sock+0x96/0x940
lock_acquire+0xcd/0x330
_raw_spin_lock+0x33/0x40
------> Acquire (bucket) lhash2.lock (may cause deadlock if interrupted)
__inet_hash+0x4b/0x210
inet_csk_listen_start+0xe6/0x100
inet_listen+0x95/0x1d0
__sys_listen+0x69/0xb0
__x64_sys_listen+0x14/0x20
do_syscall_64+0x3c/0x90
entry_SYSCALL_64_after_hwframe+0x72/0xdc
lock_acquire+0xcd/0x330
_raw_spin_lock+0x33/0x40
------> Acquire (bucket) lhash2.lock
inet_unhash+0x9a/0x110
tcp_set_state+0x6a/0x210
tcp_abort+0x10d/0x200
bpf_prog_6793c5ca50c43c0d_iter_tcp6_server+0xa4/0xa9
bpf_iter_run_prog+0x1ff/0x340
------> Release (bucket) lhash2.lock
bpf_iter_tcp_seq_show+0xca/0x190
------> Acquire (bucket) lhash2.lock
------> sock lock acquired with BH disabled
bpf_seq_read+0x177/0x450
```
Acked-by: Stanislav Fomichev <sdf@xxxxxxxxxx>
Signed-off-by: Aditi Ghag <aditi.ghag@xxxxxxxxxxxxx>
---
net/ipv4/tcp_ipv4.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index ea370afa70ed..f2d370a9450f 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2962,7 +2962,6 @@ static int bpf_iter_tcp_seq_show(struct seq_file *seq, void *v)
struct bpf_iter_meta meta;
struct bpf_prog *prog;
struct sock *sk = v;
- bool slow;
uid_t uid;
int ret;
@@ -2970,7 +2969,7 @@ static int bpf_iter_tcp_seq_show(struct seq_file *seq, void *v)
return 0;
if (sk_fullsock(sk))
- slow = lock_sock_fast(sk);
+ lock_sock(sk);
if (unlikely(sk_unhashed(sk))) {
ret = SEQ_SKIP;
@@ -2994,7 +2993,7 @@ static int bpf_iter_tcp_seq_show(struct seq_file *seq, void *v)
unlock:
if (sk_fullsock(sk))
- unlock_sock_fast(sk, slow);
+ release_sock(sk);
return ret;
}
--
2.34.1
