Revision 49054556289e8787501630b7c7a9d407da02e296 authored by Paolo Abeni on 29 September 2021, 09:59:17 UTC, committed by David S. Miller on 30 September 2021, 12:06:47 UTC
Syzkaller reported a false positive deadlock involving
the nl socket lock and the subflow socket lock:
MPTCP: kernel_bind error, err=-98
============================================
WARNING: possible recursive locking detected
5.15.0-rc1-syzkaller #0 Not tainted
--------------------------------------------
syz-executor998/6520 is trying to acquire lock:
ffff8880795718a0 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_close+0x267/0x7b0 net/mptcp/protocol.c:2738
but task is already holding lock:
ffff8880787c8c60 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1612 [inline]
ffff8880787c8c60 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_close+0x23/0x7b0 net/mptcp/protocol.c:2720
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(k-sk_lock-AF_INET);
lock(k-sk_lock-AF_INET);
*** DEADLOCK ***
May be due to missing lock nesting notation
3 locks held by syz-executor998/6520:
#0: ffffffff8d176c50 (cb_lock){++++}-{3:3}, at: genl_rcv+0x15/0x40 net/netlink/genetlink.c:802
#1: ffffffff8d176d08 (genl_mutex){+.+.}-{3:3}, at: genl_lock net/netlink/genetlink.c:33 [inline]
#1: ffffffff8d176d08 (genl_mutex){+.+.}-{3:3}, at: genl_rcv_msg+0x3e0/0x580 net/netlink/genetlink.c:790
#2: ffff8880787c8c60 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1612 [inline]
#2: ffff8880787c8c60 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_close+0x23/0x7b0 net/mptcp/protocol.c:2720
stack backtrace:
CPU: 1 PID: 6520 Comm: syz-executor998 Not tainted 5.15.0-rc1-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
__dump_stack lib/dump_stack.c:88 [inline]
dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106
print_deadlock_bug kernel/locking/lockdep.c:2944 [inline]
check_deadlock kernel/locking/lockdep.c:2987 [inline]
validate_chain kernel/locking/lockdep.c:3776 [inline]
__lock_acquire.cold+0x149/0x3ab kernel/locking/lockdep.c:5015
lock_acquire kernel/locking/lockdep.c:5625 [inline]
lock_acquire+0x1ab/0x510 kernel/locking/lockdep.c:5590
lock_sock_fast+0x36/0x100 net/core/sock.c:3229
mptcp_close+0x267/0x7b0 net/mptcp/protocol.c:2738
inet_release+0x12e/0x280 net/ipv4/af_inet.c:431
__sock_release net/socket.c:649 [inline]
sock_release+0x87/0x1b0 net/socket.c:677
mptcp_pm_nl_create_listen_socket+0x238/0x2c0 net/mptcp/pm_netlink.c:900
mptcp_nl_cmd_add_addr+0x359/0x930 net/mptcp/pm_netlink.c:1170
genl_family_rcv_msg_doit+0x228/0x320 net/netlink/genetlink.c:731
genl_family_rcv_msg net/netlink/genetlink.c:775 [inline]
genl_rcv_msg+0x328/0x580 net/netlink/genetlink.c:792
netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2504
genl_rcv+0x24/0x40 net/netlink/genetlink.c:803
netlink_unicast_kernel net/netlink/af_netlink.c:1314 [inline]
netlink_unicast+0x533/0x7d0 net/netlink/af_netlink.c:1340
netlink_sendmsg+0x86d/0xdb0 net/netlink/af_netlink.c:1929
sock_sendmsg_nosec net/socket.c:704 [inline]
sock_sendmsg+0xcf/0x120 net/socket.c:724
sock_no_sendpage+0x101/0x150 net/core/sock.c:2980
kernel_sendpage.part.0+0x1a0/0x340 net/socket.c:3504
kernel_sendpage net/socket.c:3501 [inline]
sock_sendpage+0xe5/0x140 net/socket.c:1003
pipe_to_sendpage+0x2ad/0x380 fs/splice.c:364
splice_from_pipe_feed fs/splice.c:418 [inline]
__splice_from_pipe+0x43e/0x8a0 fs/splice.c:562
splice_from_pipe fs/splice.c:597 [inline]
generic_splice_sendpage+0xd4/0x140 fs/splice.c:746
do_splice_from fs/splice.c:767 [inline]
direct_splice_actor+0x110/0x180 fs/splice.c:936
splice_direct_to_actor+0x34b/0x8c0 fs/splice.c:891
do_splice_direct+0x1b3/0x280 fs/splice.c:979
do_sendfile+0xae9/0x1240 fs/read_write.c:1249
__do_sys_sendfile64 fs/read_write.c:1314 [inline]
__se_sys_sendfile64 fs/read_write.c:1300 [inline]
__x64_sys_sendfile64+0x1cc/0x210 fs/read_write.c:1300
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x44/0xae
RIP: 0033:0x7f215cb69969
Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 e1 14 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 c0 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007ffc96bb3868 EFLAGS: 00000246 ORIG_RAX: 0000000000000028
RAX: ffffffffffffffda RBX: 00007f215cbad072 RCX: 00007f215cb69969
RDX: 0000000000000000 RSI: 0000000000000004 RDI: 0000000000000005
RBP: 0000000000000000 R08: 00007ffc96bb3a08 R09: 00007ffc96bb3a08
R10: 0000000100000002 R11: 0000000000000246 R12: 00007ffc96bb387c
R13: 431bde82d7b634db R14: 0000000000000000 R15: 0000000000000000
the problem originates from uncorrect lock annotation in the mptcp
code and is only visible since commit 2dcb96bacce3 ("net: core: Correct
the sock::sk_lock.owned lockdep annotations"), but is present since
the port-based endpoint support initial implementation.
This patch addresses the issue introducing a nested variant of
lock_sock_fast() and using it in the relevant code path.
Fixes: 1729cf186d8a ("mptcp: create the listening socket for new port")
Fixes: 2dcb96bacce3 ("net: core: Correct the sock::sk_lock.owned lockdep annotations")
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Reported-and-tested-by: syzbot+1dd53f7a89b299d59eaf@syzkaller.appspotmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
1 parent d88fd1b
checksum.c
// SPDX-License-Identifier: GPL-2.0-or-later
/*
*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* IP/TCP/UDP checksumming routines
*
* Authors: Jorge Cwik, <jorge@laser.satlink.net>
* Arnt Gulbrandsen, <agulbra@nvg.unit.no>
* Tom May, <ftom@netcom.com>
* Andreas Schwab, <schwab@issan.informatik.uni-dortmund.de>
* Lots of code moved from tcp.c and ip.c; see those files
* for more names.
*
* 03/02/96 Jes Sorensen, Andreas Schwab, Roman Hodek:
* Fixed some nasty bugs, causing some horrible crashes.
* A: At some points, the sum (%0) was used as
* length-counter instead of the length counter
* (%1). Thanks to Roman Hodek for pointing this out.
* B: GCC seems to mess up if one uses too many
* data-registers to hold input values and one tries to
* specify d0 and d1 as scratch registers. Letting gcc
* choose these registers itself solves the problem.
*/
/* Revised by Kenneth Albanowski for m68knommu. Basic problem: unaligned access
kills, so most of the assembly has to go. */
#include <linux/export.h>
#include <net/checksum.h>
#include <asm/byteorder.h>
#ifndef do_csum
static inline unsigned short from32to16(unsigned int x)
{
/* add up 16-bit and 16-bit for 16+c bit */
x = (x & 0xffff) + (x >> 16);
/* add up carry.. */
x = (x & 0xffff) + (x >> 16);
return x;
}
static unsigned int do_csum(const unsigned char *buff, int len)
{
int odd;
unsigned int result = 0;
if (len <= 0)
goto out;
odd = 1 & (unsigned long) buff;
if (odd) {
#ifdef __LITTLE_ENDIAN
result += (*buff << 8);
#else
result = *buff;
#endif
len--;
buff++;
}
if (len >= 2) {
if (2 & (unsigned long) buff) {
result += *(unsigned short *) buff;
len -= 2;
buff += 2;
}
if (len >= 4) {
const unsigned char *end = buff + ((unsigned)len & ~3);
unsigned int carry = 0;
do {
unsigned int w = *(unsigned int *) buff;
buff += 4;
result += carry;
result += w;
carry = (w > result);
} while (buff < end);
result += carry;
result = (result & 0xffff) + (result >> 16);
}
if (len & 2) {
result += *(unsigned short *) buff;
buff += 2;
}
}
if (len & 1)
#ifdef __LITTLE_ENDIAN
result += *buff;
#else
result += (*buff << 8);
#endif
result = from32to16(result);
if (odd)
result = ((result >> 8) & 0xff) | ((result & 0xff) << 8);
out:
return result;
}
#endif
#ifndef ip_fast_csum
/*
* This is a version of ip_compute_csum() optimized for IP headers,
* which always checksum on 4 octet boundaries.
*/
__sum16 ip_fast_csum(const void *iph, unsigned int ihl)
{
return (__force __sum16)~do_csum(iph, ihl*4);
}
EXPORT_SYMBOL(ip_fast_csum);
#endif
/*
* computes the checksum of a memory block at buff, length len,
* and adds in "sum" (32-bit)
*
* returns a 32-bit number suitable for feeding into itself
* or csum_tcpudp_magic
*
* this function must be called with even lengths, except
* for the last fragment, which may be odd
*
* it's best to have buff aligned on a 32-bit boundary
*/
__wsum csum_partial(const void *buff, int len, __wsum wsum)
{
unsigned int sum = (__force unsigned int)wsum;
unsigned int result = do_csum(buff, len);
/* add in old sum, and carry.. */
result += sum;
if (sum > result)
result += 1;
return (__force __wsum)result;
}
EXPORT_SYMBOL(csum_partial);
/*
* this routine is used for miscellaneous IP-like checksums, mainly
* in icmp.c
*/
__sum16 ip_compute_csum(const void *buff, int len)
{
return (__force __sum16)~do_csum(buff, len);
}
EXPORT_SYMBOL(ip_compute_csum);
#ifndef csum_tcpudp_nofold
static inline u32 from64to32(u64 x)
{
/* add up 32-bit and 32-bit for 32+c bit */
x = (x & 0xffffffff) + (x >> 32);
/* add up carry.. */
x = (x & 0xffffffff) + (x >> 32);
return (u32)x;
}
__wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
__u32 len, __u8 proto, __wsum sum)
{
unsigned long long s = (__force u32)sum;
s += (__force u32)saddr;
s += (__force u32)daddr;
#ifdef __BIG_ENDIAN
s += proto + len;
#else
s += (proto + len) << 8;
#endif
return (__force __wsum)from64to32(s);
}
EXPORT_SYMBOL(csum_tcpudp_nofold);
#endif
Computing file changes ...
