linux/net/unix/unix_bpf.c

179 lines
4.6 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2021 Cong Wang <cong.wang@bytedance.com> */
#include <linux/skmsg.h>
#include <linux/bpf.h>
#include <net/sock.h>
#include <net/af_unix.h>
#define unix_sk_has_data(__sk, __psock) \
({ !skb_queue_empty(&__sk->sk_receive_queue) || \
!skb_queue_empty(&__psock->ingress_skb) || \
!list_empty(&__psock->ingress_msg); \
})
static int unix_msg_wait_data(struct sock *sk, struct sk_psock *psock,
long timeo)
{
DEFINE_WAIT_FUNC(wait, woken_wake_function);
struct unix_sock *u = unix_sk(sk);
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);
if (!unix_sk_has_data(sk, psock)) {
mutex_unlock(&u->iolock);
wait_woken(&wait, TASK_INTERRUPTIBLE, timeo);
mutex_lock(&u->iolock);
ret = unix_sk_has_data(sk, psock);
}
sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
remove_wait_queue(sk_sleep(sk), &wait);
return ret;
}
static int __unix_recvmsg(struct sock *sk, struct msghdr *msg,
size_t len, int flags)
{
if (sk->sk_type == SOCK_DGRAM)
return __unix_dgram_recvmsg(sk, msg, len, flags);
else
return __unix_stream_recvmsg(sk, msg, len, flags);
}
static int unix_bpf_recvmsg(struct sock *sk, struct msghdr *msg,
size_t len, int flags, int *addr_len)
{
struct unix_sock *u = unix_sk(sk);
struct sk_psock *psock;
int copied;
bpf, sockmap: Fix an infinite loop error when len is 0 in tcp_bpf_recvmsg_parser() 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: 1f5be6b3b063 ("udp: Implement udp_bpf_recvmsg() for sockmap") Fixes: 9825d866ce0d ("af_unix: Implement unix_dgram_bpf_recvmsg()") Fixes: c5d2177a72a1 ("bpf, sockmap: Fix race in ingress receive verdict with redirect to self") Fixes: 604326b41a6f ("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
2023-03-03 16:09:46 +08:00
if (!len)
return 0;
psock = sk_psock_get(sk);
if (unlikely(!psock))
return __unix_recvmsg(sk, msg, len, flags);
mutex_lock(&u->iolock);
if (!skb_queue_empty(&sk->sk_receive_queue) &&
sk_psock_queue_empty(psock)) {
mutex_unlock(&u->iolock);
sk_psock_put(sk, psock);
return __unix_recvmsg(sk, msg, len, flags);
}
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 = unix_msg_wait_data(sk, psock, timeo);
if (data) {
if (!sk_psock_queue_empty(psock))
goto msg_bytes_ready;
mutex_unlock(&u->iolock);
sk_psock_put(sk, psock);
return __unix_recvmsg(sk, msg, len, flags);
}
copied = -EAGAIN;
}
mutex_unlock(&u->iolock);
sk_psock_put(sk, psock);
return copied;
}
static struct proto *unix_dgram_prot_saved __read_mostly;
static DEFINE_SPINLOCK(unix_dgram_prot_lock);
static struct proto unix_dgram_bpf_prot;
static struct proto *unix_stream_prot_saved __read_mostly;
static DEFINE_SPINLOCK(unix_stream_prot_lock);
static struct proto unix_stream_bpf_prot;
static void unix_dgram_bpf_rebuild_protos(struct proto *prot, const struct proto *base)
{
*prot = *base;
prot->close = sock_map_close;
prot->recvmsg = unix_bpf_recvmsg;
prot->sock_is_readable = sk_msg_is_readable;
}
static void unix_stream_bpf_rebuild_protos(struct proto *prot,
const struct proto *base)
{
*prot = *base;
prot->close = sock_map_close;
prot->recvmsg = unix_bpf_recvmsg;
prot->sock_is_readable = sk_msg_is_readable;
prot->unhash = sock_map_unhash;
}
static void unix_dgram_bpf_check_needs_rebuild(struct proto *ops)
{
if (unlikely(ops != smp_load_acquire(&unix_dgram_prot_saved))) {
spin_lock_bh(&unix_dgram_prot_lock);
if (likely(ops != unix_dgram_prot_saved)) {
unix_dgram_bpf_rebuild_protos(&unix_dgram_bpf_prot, ops);
smp_store_release(&unix_dgram_prot_saved, ops);
}
spin_unlock_bh(&unix_dgram_prot_lock);
}
}
static void unix_stream_bpf_check_needs_rebuild(struct proto *ops)
{
if (unlikely(ops != smp_load_acquire(&unix_stream_prot_saved))) {
spin_lock_bh(&unix_stream_prot_lock);
if (likely(ops != unix_stream_prot_saved)) {
unix_stream_bpf_rebuild_protos(&unix_stream_bpf_prot, ops);
smp_store_release(&unix_stream_prot_saved, ops);
}
spin_unlock_bh(&unix_stream_prot_lock);
}
}
int unix_dgram_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
{
if (sk->sk_type != SOCK_DGRAM)
return -EOPNOTSUPP;
if (restore) {
sk->sk_write_space = psock->saved_write_space;
sock_replace_proto(sk, psock->sk_proto);
return 0;
}
unix_dgram_bpf_check_needs_rebuild(psock->sk_proto);
sock_replace_proto(sk, &unix_dgram_bpf_prot);
return 0;
}
int unix_stream_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
{
if (restore) {
sk->sk_write_space = psock->saved_write_space;
sock_replace_proto(sk, psock->sk_proto);
return 0;
}
unix_stream_bpf_check_needs_rebuild(psock->sk_proto);
sock_replace_proto(sk, &unix_stream_bpf_prot);
return 0;
}
void __init unix_bpf_build_proto(void)
{
unix_dgram_bpf_rebuild_protos(&unix_dgram_bpf_prot, &unix_dgram_proto);
unix_stream_bpf_rebuild_protos(&unix_stream_bpf_prot, &unix_stream_proto);
}