mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-26 02:39:48 +00:00
![Liu Jian](/assets/img/avatar_default.png)
When the buffer length of the recvmsg system call is 0, we got the flollowing soft lockup problem: watchdog: BUG: soft lockup - CPU#3 stuck for 27s! [a.out:6149] CPU: 3 PID: 6149 Comm: a.out Kdump: loaded Not tainted 6.2.0+ #30 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.15.0-1 04/01/2014 RIP: 0010:remove_wait_queue+0xb/0xc0 Code: 5e 41 5f c3 cc cc cc cc 0f 1f 80 00 00 00 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa 0f 1f 44 00 00 41 57 <41> 56 41 55 41 54 55 48 89 fd 53 48 89 f3 4c 8d 6b 18 4c 8d 73 20 RSP: 0018:ffff88811b5978b8 EFLAGS: 00000246 RAX: 0000000000000000 RBX: ffff88811a7d3780 RCX: ffffffffb7a4d768 RDX: dffffc0000000000 RSI: ffff88811b597908 RDI: ffff888115408040 RBP: 1ffff110236b2f1b R08: 0000000000000000 R09: ffff88811a7d37e7 R10: ffffed10234fa6fc R11: 0000000000000001 R12: ffff88811179b800 R13: 0000000000000001 R14: ffff88811a7d38a8 R15: ffff88811a7d37e0 FS: 00007f6fb5398740(0000) GS:ffff888237180000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020000000 CR3: 000000010b6ba002 CR4: 0000000000370ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> tcp_msg_wait_data+0x279/0x2f0 tcp_bpf_recvmsg_parser+0x3c6/0x490 inet_recvmsg+0x280/0x290 sock_recvmsg+0xfc/0x120 ____sys_recvmsg+0x160/0x3d0 ___sys_recvmsg+0xf0/0x180 __sys_recvmsg+0xea/0x1a0 do_syscall_64+0x3f/0x90 entry_SYSCALL_64_after_hwframe+0x72/0xdc The logic in tcp_bpf_recvmsg_parser is as follows: msg_bytes_ready: copied = sk_msg_recvmsg(sk, psock, msg, len, flags); if (!copied) { wait data; goto msg_bytes_ready; } In this case, "copied" always is 0, the infinite loop occurs. According to the Linux system call man page, 0 should be returned in this case. Therefore, in tcp_bpf_recvmsg_parser(), if the length is 0, directly return. Also modify several other functions with the same problem. Fixes:1f5be6b3b0
("udp: Implement udp_bpf_recvmsg() for sockmap") Fixes:9825d866ce
("af_unix: Implement unix_dgram_bpf_recvmsg()") Fixes:c5d2177a72
("bpf, sockmap: Fix race in ingress receive verdict with redirect to self") Fixes:604326b41a
("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Liu Jian <liujian56@huawei.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Cc: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20230303080946.1146638-1-liujian56@huawei.com
157 lines
3.7 KiB
C
157 lines
3.7 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/* Copyright (c) 2020 Cloudflare Ltd https://cloudflare.com */
|
|
|
|
#include <linux/skmsg.h>
|
|
#include <net/sock.h>
|
|
#include <net/udp.h>
|
|
#include <net/inet_common.h>
|
|
|
|
#include "udp_impl.h"
|
|
|
|
static struct proto *udpv6_prot_saved __read_mostly;
|
|
|
|
static int sk_udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
|
|
int flags, int *addr_len)
|
|
{
|
|
#if IS_ENABLED(CONFIG_IPV6)
|
|
if (sk->sk_family == AF_INET6)
|
|
return udpv6_prot_saved->recvmsg(sk, msg, len, flags, addr_len);
|
|
#endif
|
|
return udp_prot.recvmsg(sk, msg, len, flags, addr_len);
|
|
}
|
|
|
|
static bool udp_sk_has_data(struct sock *sk)
|
|
{
|
|
return !skb_queue_empty(&udp_sk(sk)->reader_queue) ||
|
|
!skb_queue_empty(&sk->sk_receive_queue);
|
|
}
|
|
|
|
static bool psock_has_data(struct sk_psock *psock)
|
|
{
|
|
return !skb_queue_empty(&psock->ingress_skb) ||
|
|
!sk_psock_queue_empty(psock);
|
|
}
|
|
|
|
#define udp_msg_has_data(__sk, __psock) \
|
|
({ udp_sk_has_data(__sk) || psock_has_data(__psock); })
|
|
|
|
static int udp_msg_wait_data(struct sock *sk, struct sk_psock *psock,
|
|
long timeo)
|
|
{
|
|
DEFINE_WAIT_FUNC(wait, woken_wake_function);
|
|
int ret = 0;
|
|
|
|
if (sk->sk_shutdown & RCV_SHUTDOWN)
|
|
return 1;
|
|
|
|
if (!timeo)
|
|
return ret;
|
|
|
|
add_wait_queue(sk_sleep(sk), &wait);
|
|
sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
|
|
ret = udp_msg_has_data(sk, psock);
|
|
if (!ret) {
|
|
wait_woken(&wait, TASK_INTERRUPTIBLE, timeo);
|
|
ret = udp_msg_has_data(sk, psock);
|
|
}
|
|
sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
|
|
remove_wait_queue(sk_sleep(sk), &wait);
|
|
return ret;
|
|
}
|
|
|
|
static int udp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
|
|
int flags, int *addr_len)
|
|
{
|
|
struct sk_psock *psock;
|
|
int copied, ret;
|
|
|
|
if (unlikely(flags & MSG_ERRQUEUE))
|
|
return inet_recv_error(sk, msg, len, addr_len);
|
|
|
|
if (!len)
|
|
return 0;
|
|
|
|
psock = sk_psock_get(sk);
|
|
if (unlikely(!psock))
|
|
return sk_udp_recvmsg(sk, msg, len, flags, addr_len);
|
|
|
|
if (!psock_has_data(psock)) {
|
|
ret = sk_udp_recvmsg(sk, msg, len, flags, addr_len);
|
|
goto out;
|
|
}
|
|
|
|
msg_bytes_ready:
|
|
copied = sk_msg_recvmsg(sk, psock, msg, len, flags);
|
|
if (!copied) {
|
|
long timeo;
|
|
int data;
|
|
|
|
timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
|
|
data = udp_msg_wait_data(sk, psock, timeo);
|
|
if (data) {
|
|
if (psock_has_data(psock))
|
|
goto msg_bytes_ready;
|
|
ret = sk_udp_recvmsg(sk, msg, len, flags, addr_len);
|
|
goto out;
|
|
}
|
|
copied = -EAGAIN;
|
|
}
|
|
ret = copied;
|
|
out:
|
|
sk_psock_put(sk, psock);
|
|
return ret;
|
|
}
|
|
|
|
enum {
|
|
UDP_BPF_IPV4,
|
|
UDP_BPF_IPV6,
|
|
UDP_BPF_NUM_PROTS,
|
|
};
|
|
|
|
static DEFINE_SPINLOCK(udpv6_prot_lock);
|
|
static struct proto udp_bpf_prots[UDP_BPF_NUM_PROTS];
|
|
|
|
static void udp_bpf_rebuild_protos(struct proto *prot, const struct proto *base)
|
|
{
|
|
*prot = *base;
|
|
prot->close = sock_map_close;
|
|
prot->recvmsg = udp_bpf_recvmsg;
|
|
prot->sock_is_readable = sk_msg_is_readable;
|
|
}
|
|
|
|
static void udp_bpf_check_v6_needs_rebuild(struct proto *ops)
|
|
{
|
|
if (unlikely(ops != smp_load_acquire(&udpv6_prot_saved))) {
|
|
spin_lock_bh(&udpv6_prot_lock);
|
|
if (likely(ops != udpv6_prot_saved)) {
|
|
udp_bpf_rebuild_protos(&udp_bpf_prots[UDP_BPF_IPV6], ops);
|
|
smp_store_release(&udpv6_prot_saved, ops);
|
|
}
|
|
spin_unlock_bh(&udpv6_prot_lock);
|
|
}
|
|
}
|
|
|
|
static int __init udp_bpf_v4_build_proto(void)
|
|
{
|
|
udp_bpf_rebuild_protos(&udp_bpf_prots[UDP_BPF_IPV4], &udp_prot);
|
|
return 0;
|
|
}
|
|
late_initcall(udp_bpf_v4_build_proto);
|
|
|
|
int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
|
|
{
|
|
int family = sk->sk_family == AF_INET ? UDP_BPF_IPV4 : UDP_BPF_IPV6;
|
|
|
|
if (restore) {
|
|
sk->sk_write_space = psock->saved_write_space;
|
|
sock_replace_proto(sk, psock->sk_proto);
|
|
return 0;
|
|
}
|
|
|
|
if (sk->sk_family == AF_INET6)
|
|
udp_bpf_check_v6_needs_rebuild(psock->sk_proto);
|
|
|
|
sock_replace_proto(sk, &udp_bpf_prots[family]);
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL_GPL(udp_bpf_update_proto);
|