linux-stable/net/core/stream.c
Liu Jian 124b7c7732 net: If sock is dead don't access sock's sk_wq in sk_stream_wait_memory
[ Upstream commit 3f8ef65af9 ]

Fixes the below NULL pointer dereference:

  [...]
  [   14.471200] Call Trace:
  [   14.471562]  <TASK>
  [   14.471882]  lock_acquire+0x245/0x2e0
  [   14.472416]  ? remove_wait_queue+0x12/0x50
  [   14.473014]  ? _raw_spin_lock_irqsave+0x17/0x50
  [   14.473681]  _raw_spin_lock_irqsave+0x3d/0x50
  [   14.474318]  ? remove_wait_queue+0x12/0x50
  [   14.474907]  remove_wait_queue+0x12/0x50
  [   14.475480]  sk_stream_wait_memory+0x20d/0x340
  [   14.476127]  ? do_wait_intr_irq+0x80/0x80
  [   14.476704]  do_tcp_sendpages+0x287/0x600
  [   14.477283]  tcp_bpf_push+0xab/0x260
  [   14.477817]  tcp_bpf_sendmsg_redir+0x297/0x500
  [   14.478461]  ? __local_bh_enable_ip+0x77/0xe0
  [   14.479096]  tcp_bpf_send_verdict+0x105/0x470
  [   14.479729]  tcp_bpf_sendmsg+0x318/0x4f0
  [   14.480311]  sock_sendmsg+0x2d/0x40
  [   14.480822]  ____sys_sendmsg+0x1b4/0x1c0
  [   14.481390]  ? copy_msghdr_from_user+0x62/0x80
  [   14.482048]  ___sys_sendmsg+0x78/0xb0
  [   14.482580]  ? vmf_insert_pfn_prot+0x91/0x150
  [   14.483215]  ? __do_fault+0x2a/0x1a0
  [   14.483738]  ? do_fault+0x15e/0x5d0
  [   14.484246]  ? __handle_mm_fault+0x56b/0x1040
  [   14.484874]  ? lock_is_held_type+0xdf/0x130
  [   14.485474]  ? find_held_lock+0x2d/0x90
  [   14.486046]  ? __sys_sendmsg+0x41/0x70
  [   14.486587]  __sys_sendmsg+0x41/0x70
  [   14.487105]  ? intel_pmu_drain_pebs_core+0x350/0x350
  [   14.487822]  do_syscall_64+0x34/0x80
  [   14.488345]  entry_SYSCALL_64_after_hwframe+0x63/0xcd
  [...]

The test scenario has the following flow:

thread1                               thread2
-----------                           ---------------
 tcp_bpf_sendmsg
  tcp_bpf_send_verdict
   tcp_bpf_sendmsg_redir              sock_close
    tcp_bpf_push_locked                 __sock_release
     tcp_bpf_push                         //inet_release
      do_tcp_sendpages                    sock->ops->release
       sk_stream_wait_memory          	   // tcp_close
          sk_wait_event                      sk->sk_prot->close
           release_sock(__sk);
            ***
                                                lock_sock(sk);
                                                  __tcp_close
                                                    sock_orphan(sk)
                                                      sk->sk_wq  = NULL
                                                release_sock
            ****
           lock_sock(__sk);
          remove_wait_queue(sk_sleep(sk), &wait);
             sk_sleep(sk)
             //NULL pointer dereference
             &rcu_dereference_raw(sk->sk_wq)->wait

While waiting for memory in thread1, the socket is released with its wait
queue because thread2 has closed it. This caused by tcp_bpf_send_verdict
didn't increase the f_count of psock->sk_redir->sk_socket->file in thread1.

We should check if SOCK_DEAD flag is set on wakeup in sk_stream_wait_memory
before accessing the wait queue.

Suggested-by: Jakub Sitnicki <jakub@cloudflare.com>
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: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/bpf/20220823133755.314697-2-liujian56@huawei.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
2022-10-26 12:35:37 +02:00

213 lines
5.4 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* SUCS NET3:
*
* Generic stream handling routines. These are generic for most
* protocols. Even IP. Tonight 8-).
* This is used because TCP, LLC (others too) layer all have mostly
* identical sendmsg() and recvmsg() code.
* So we (will) share it here.
*
* Authors: Arnaldo Carvalho de Melo <acme@conectiva.com.br>
* (from old tcp.c code)
* Alan Cox <alan@lxorguk.ukuu.org.uk> (Borrowed comments 8-))
*/
#include <linux/module.h>
#include <linux/sched/signal.h>
#include <linux/net.h>
#include <linux/signal.h>
#include <linux/tcp.h>
#include <linux/wait.h>
#include <net/sock.h>
/**
* sk_stream_write_space - stream socket write_space callback.
* @sk: socket
*
* FIXME: write proper description
*/
void sk_stream_write_space(struct sock *sk)
{
struct socket *sock = sk->sk_socket;
struct socket_wq *wq;
if (__sk_stream_is_writeable(sk, 1) && sock) {
clear_bit(SOCK_NOSPACE, &sock->flags);
rcu_read_lock();
wq = rcu_dereference(sk->sk_wq);
if (skwq_has_sleeper(wq))
wake_up_interruptible_poll(&wq->wait, EPOLLOUT |
EPOLLWRNORM | EPOLLWRBAND);
if (wq && wq->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN))
sock_wake_async(wq, SOCK_WAKE_SPACE, POLL_OUT);
rcu_read_unlock();
}
}
/**
* sk_stream_wait_connect - Wait for a socket to get into the connected state
* @sk: sock to wait on
* @timeo_p: for how long to wait
*
* Must be called with the socket locked.
*/
int sk_stream_wait_connect(struct sock *sk, long *timeo_p)
{
DEFINE_WAIT_FUNC(wait, woken_wake_function);
struct task_struct *tsk = current;
int done;
do {
int err = sock_error(sk);
if (err)
return err;
if ((1 << sk->sk_state) & ~(TCPF_SYN_SENT | TCPF_SYN_RECV))
return -EPIPE;
if (!*timeo_p)
return -EAGAIN;
if (signal_pending(tsk))
return sock_intr_errno(*timeo_p);
add_wait_queue(sk_sleep(sk), &wait);
sk->sk_write_pending++;
done = sk_wait_event(sk, timeo_p,
!sk->sk_err &&
!((1 << sk->sk_state) &
~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)), &wait);
remove_wait_queue(sk_sleep(sk), &wait);
sk->sk_write_pending--;
} while (!done);
return 0;
}
EXPORT_SYMBOL(sk_stream_wait_connect);
/**
* sk_stream_closing - Return 1 if we still have things to send in our buffers.
* @sk: socket to verify
*/
static inline int sk_stream_closing(struct sock *sk)
{
return (1 << sk->sk_state) &
(TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_LAST_ACK);
}
void sk_stream_wait_close(struct sock *sk, long timeout)
{
if (timeout) {
DEFINE_WAIT_FUNC(wait, woken_wake_function);
add_wait_queue(sk_sleep(sk), &wait);
do {
if (sk_wait_event(sk, &timeout, !sk_stream_closing(sk), &wait))
break;
} while (!signal_pending(current) && timeout);
remove_wait_queue(sk_sleep(sk), &wait);
}
}
EXPORT_SYMBOL(sk_stream_wait_close);
/**
* sk_stream_wait_memory - Wait for more memory for a socket
* @sk: socket to wait for memory
* @timeo_p: for how long
*/
int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
{
int err = 0;
long vm_wait = 0;
long current_timeo = *timeo_p;
DEFINE_WAIT_FUNC(wait, woken_wake_function);
if (sk_stream_memory_free(sk))
current_timeo = vm_wait = (prandom_u32() % (HZ / 5)) + 2;
add_wait_queue(sk_sleep(sk), &wait);
while (1) {
sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
goto do_error;
if (!*timeo_p)
goto do_eagain;
if (signal_pending(current))
goto do_interrupted;
sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
if (sk_stream_memory_free(sk) && !vm_wait)
break;
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
sk->sk_write_pending++;
sk_wait_event(sk, &current_timeo, sk->sk_err ||
(sk->sk_shutdown & SEND_SHUTDOWN) ||
(sk_stream_memory_free(sk) &&
!vm_wait), &wait);
sk->sk_write_pending--;
if (vm_wait) {
vm_wait -= current_timeo;
current_timeo = *timeo_p;
if (current_timeo != MAX_SCHEDULE_TIMEOUT &&
(current_timeo -= vm_wait) < 0)
current_timeo = 0;
vm_wait = 0;
}
*timeo_p = current_timeo;
}
out:
if (!sock_flag(sk, SOCK_DEAD))
remove_wait_queue(sk_sleep(sk), &wait);
return err;
do_error:
err = -EPIPE;
goto out;
do_eagain:
/* Make sure that whenever EAGAIN is returned, EPOLLOUT event can
* be generated later.
* When TCP receives ACK packets that make room, tcp_check_space()
* only calls tcp_new_space() if SOCK_NOSPACE is set.
*/
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
err = -EAGAIN;
goto out;
do_interrupted:
err = sock_intr_errno(*timeo_p);
goto out;
}
EXPORT_SYMBOL(sk_stream_wait_memory);
int sk_stream_error(struct sock *sk, int flags, int err)
{
if (err == -EPIPE)
err = sock_error(sk) ? : -EPIPE;
if (err == -EPIPE && !(flags & MSG_NOSIGNAL))
send_sig(SIGPIPE, current, 0);
return err;
}
EXPORT_SYMBOL(sk_stream_error);
void sk_stream_kill_queues(struct sock *sk)
{
/* First the read buffer. */
__skb_queue_purge(&sk->sk_receive_queue);
/* Next, the write queue. */
WARN_ON(!skb_queue_empty(&sk->sk_write_queue));
/* Account for returned memory. */
sk_mem_reclaim(sk);
WARN_ON(sk->sk_wmem_queued);
WARN_ON(sk->sk_forward_alloc);
/* It is _impossible_ for the backlog to contain anything
* when we get here. All user references to this socket
* have gone away, only the net layer knows can touch it.
*/
}
EXPORT_SYMBOL(sk_stream_kill_queues);