linux/net/unix/scm.c
Eric Dumazet 9d6d7f1cb6 af_unix: annote lockless accesses to unix_tot_inflight & gc_in_progress
wait_for_unix_gc() reads unix_tot_inflight & gc_in_progress
without synchronization.

Adds READ_ONCE()/WRITE_ONCE() and their associated comments
to better document the intent.

BUG: KCSAN: data-race in unix_inflight / wait_for_unix_gc

write to 0xffffffff86e2b7c0 of 4 bytes by task 9380 on cpu 0:
 unix_inflight+0x1e8/0x260 net/unix/scm.c:63
 unix_attach_fds+0x10c/0x1e0 net/unix/scm.c:121
 unix_scm_to_skb net/unix/af_unix.c:1674 [inline]
 unix_dgram_sendmsg+0x679/0x16b0 net/unix/af_unix.c:1817
 unix_seqpacket_sendmsg+0xcc/0x110 net/unix/af_unix.c:2258
 sock_sendmsg_nosec net/socket.c:704 [inline]
 sock_sendmsg net/socket.c:724 [inline]
 ____sys_sendmsg+0x39a/0x510 net/socket.c:2409
 ___sys_sendmsg net/socket.c:2463 [inline]
 __sys_sendmmsg+0x267/0x4c0 net/socket.c:2549
 __do_sys_sendmmsg net/socket.c:2578 [inline]
 __se_sys_sendmmsg net/socket.c:2575 [inline]
 __x64_sys_sendmmsg+0x53/0x60 net/socket.c:2575
 do_syscall_x64 arch/x86/entry/common.c:50 [inline]
 do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80
 entry_SYSCALL_64_after_hwframe+0x44/0xae

read to 0xffffffff86e2b7c0 of 4 bytes by task 9375 on cpu 1:
 wait_for_unix_gc+0x24/0x160 net/unix/garbage.c:196
 unix_dgram_sendmsg+0x8e/0x16b0 net/unix/af_unix.c:1772
 unix_seqpacket_sendmsg+0xcc/0x110 net/unix/af_unix.c:2258
 sock_sendmsg_nosec net/socket.c:704 [inline]
 sock_sendmsg net/socket.c:724 [inline]
 ____sys_sendmsg+0x39a/0x510 net/socket.c:2409
 ___sys_sendmsg net/socket.c:2463 [inline]
 __sys_sendmmsg+0x267/0x4c0 net/socket.c:2549
 __do_sys_sendmmsg net/socket.c:2578 [inline]
 __se_sys_sendmmsg net/socket.c:2575 [inline]
 __x64_sys_sendmmsg+0x53/0x60 net/socket.c:2575
 do_syscall_x64 arch/x86/entry/common.c:50 [inline]
 do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80
 entry_SYSCALL_64_after_hwframe+0x44/0xae

value changed: 0x00000002 -> 0x00000004

Reported by Kernel Concurrency Sanitizer on:
CPU: 1 PID: 9375 Comm: syz-executor.1 Not tainted 5.16.0-rc7-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011

Fixes: 9915672d41 ("af_unix: limit unix_tot_inflight")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Link: https://lore.kernel.org/r/20220114164328.2038499-1-eric.dumazet@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-01-14 18:31:37 -08:00

155 lines
3.7 KiB
C

// SPDX-License-Identifier: GPL-2.0
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/socket.h>
#include <linux/net.h>
#include <linux/fs.h>
#include <net/af_unix.h>
#include <net/scm.h>
#include <linux/init.h>
#include <linux/io_uring.h>
#include "scm.h"
unsigned int unix_tot_inflight;
EXPORT_SYMBOL(unix_tot_inflight);
LIST_HEAD(gc_inflight_list);
EXPORT_SYMBOL(gc_inflight_list);
DEFINE_SPINLOCK(unix_gc_lock);
EXPORT_SYMBOL(unix_gc_lock);
struct sock *unix_get_socket(struct file *filp)
{
struct sock *u_sock = NULL;
struct inode *inode = file_inode(filp);
/* Socket ? */
if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) {
struct socket *sock = SOCKET_I(inode);
struct sock *s = sock->sk;
/* PF_UNIX ? */
if (s && sock->ops && sock->ops->family == PF_UNIX)
u_sock = s;
} else {
/* Could be an io_uring instance */
u_sock = io_uring_get_socket(filp);
}
return u_sock;
}
EXPORT_SYMBOL(unix_get_socket);
/* Keep the number of times in flight count for the file
* descriptor if it is for an AF_UNIX socket.
*/
void unix_inflight(struct user_struct *user, struct file *fp)
{
struct sock *s = unix_get_socket(fp);
spin_lock(&unix_gc_lock);
if (s) {
struct unix_sock *u = unix_sk(s);
if (atomic_long_inc_return(&u->inflight) == 1) {
BUG_ON(!list_empty(&u->link));
list_add_tail(&u->link, &gc_inflight_list);
} else {
BUG_ON(list_empty(&u->link));
}
/* Paired with READ_ONCE() in wait_for_unix_gc() */
WRITE_ONCE(unix_tot_inflight, unix_tot_inflight + 1);
}
user->unix_inflight++;
spin_unlock(&unix_gc_lock);
}
void unix_notinflight(struct user_struct *user, struct file *fp)
{
struct sock *s = unix_get_socket(fp);
spin_lock(&unix_gc_lock);
if (s) {
struct unix_sock *u = unix_sk(s);
BUG_ON(!atomic_long_read(&u->inflight));
BUG_ON(list_empty(&u->link));
if (atomic_long_dec_and_test(&u->inflight))
list_del_init(&u->link);
/* Paired with READ_ONCE() in wait_for_unix_gc() */
WRITE_ONCE(unix_tot_inflight, unix_tot_inflight - 1);
}
user->unix_inflight--;
spin_unlock(&unix_gc_lock);
}
/*
* The "user->unix_inflight" variable is protected by the garbage
* collection lock, and we just read it locklessly here. If you go
* over the limit, there might be a tiny race in actually noticing
* it across threads. Tough.
*/
static inline bool too_many_unix_fds(struct task_struct *p)
{
struct user_struct *user = current_user();
if (unlikely(user->unix_inflight > task_rlimit(p, RLIMIT_NOFILE)))
return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN);
return false;
}
int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
{
int i;
if (too_many_unix_fds(current))
return -ETOOMANYREFS;
/*
* Need to duplicate file references for the sake of garbage
* collection. Otherwise a socket in the fps might become a
* candidate for GC while the skb is not yet queued.
*/
UNIXCB(skb).fp = scm_fp_dup(scm->fp);
if (!UNIXCB(skb).fp)
return -ENOMEM;
for (i = scm->fp->count - 1; i >= 0; i--)
unix_inflight(scm->fp->user, scm->fp->fp[i]);
return 0;
}
EXPORT_SYMBOL(unix_attach_fds);
void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb)
{
int i;
scm->fp = UNIXCB(skb).fp;
UNIXCB(skb).fp = NULL;
for (i = scm->fp->count-1; i >= 0; i--)
unix_notinflight(scm->fp->user, scm->fp->fp[i]);
}
EXPORT_SYMBOL(unix_detach_fds);
void unix_destruct_scm(struct sk_buff *skb)
{
struct scm_cookie scm;
memset(&scm, 0, sizeof(scm));
scm.pid = UNIXCB(skb).pid;
if (UNIXCB(skb).fp)
unix_detach_fds(&scm, skb);
/* Alas, it calls VFS */
/* So fscking what? fput() had been SMP-safe since the last Summer */
scm_destroy(&scm);
sock_wfree(skb);
}
EXPORT_SYMBOL(unix_destruct_scm);