mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-11-15 00:04:15 +08:00
3d041393ea
Syzkaller reported a lockdep splat:
============================================
WARNING: possible recursive locking detected
6.11.0-rc6-syzkaller-00019-g67784a74e258 #0 Not tainted
--------------------------------------------
syz-executor364/5113 is trying to acquire lock:
ffff8880449f1958 (k-slock-AF_INET){+.-.}-{2:2}, at: spin_lock include/linux/spinlock.h:351 [inline]
ffff8880449f1958 (k-slock-AF_INET){+.-.}-{2:2}, at: sk_clone_lock+0x2cd/0xf40 net/core/sock.c:2328
but task is already holding lock:
ffff88803fe3cb58 (k-slock-AF_INET){+.-.}-{2:2}, at: spin_lock include/linux/spinlock.h:351 [inline]
ffff88803fe3cb58 (k-slock-AF_INET){+.-.}-{2:2}, at: sk_clone_lock+0x2cd/0xf40 net/core/sock.c:2328
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(k-slock-AF_INET);
lock(k-slock-AF_INET);
*** DEADLOCK ***
May be due to missing lock nesting notation
7 locks held by syz-executor364/5113:
#0: ffff8880449f0e18 (sk_lock-AF_INET){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1607 [inline]
#0: ffff8880449f0e18 (sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_sendmsg+0x153/0x1b10 net/mptcp/protocol.c:1806
#1: ffff88803fe39ad8 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1607 [inline]
#1: ffff88803fe39ad8 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_sendmsg_fastopen+0x11f/0x530 net/mptcp/protocol.c:1727
#2: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: rcu_lock_acquire include/linux/rcupdate.h:326 [inline]
#2: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: rcu_read_lock include/linux/rcupdate.h:838 [inline]
#2: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: __ip_queue_xmit+0x5f/0x1b80 net/ipv4/ip_output.c:470
#3: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: rcu_lock_acquire include/linux/rcupdate.h:326 [inline]
#3: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: rcu_read_lock include/linux/rcupdate.h:838 [inline]
#3: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: ip_finish_output2+0x45f/0x1390 net/ipv4/ip_output.c:228
#4: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: local_lock_acquire include/linux/local_lock_internal.h:29 [inline]
#4: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: process_backlog+0x33b/0x15b0 net/core/dev.c:6104
#5: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: rcu_lock_acquire include/linux/rcupdate.h:326 [inline]
#5: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: rcu_read_lock include/linux/rcupdate.h:838 [inline]
#5: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: ip_local_deliver_finish+0x230/0x5f0 net/ipv4/ip_input.c:232
#6: ffff88803fe3cb58 (k-slock-AF_INET){+.-.}-{2:2}, at: spin_lock include/linux/spinlock.h:351 [inline]
#6: ffff88803fe3cb58 (k-slock-AF_INET){+.-.}-{2:2}, at: sk_clone_lock+0x2cd/0xf40 net/core/sock.c:2328
stack backtrace:
CPU: 0 UID: 0 PID: 5113 Comm: syz-executor364 Not tainted 6.11.0-rc6-syzkaller-00019-g67784a74e258 #0
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014
Call Trace:
<IRQ>
__dump_stack lib/dump_stack.c:93 [inline]
dump_stack_lvl+0x241/0x360 lib/dump_stack.c:119
check_deadlock kernel/locking/lockdep.c:3061 [inline]
validate_chain+0x15d3/0x5900 kernel/locking/lockdep.c:3855
__lock_acquire+0x137a/0x2040 kernel/locking/lockdep.c:5142
lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5759
__raw_spin_lock include/linux/spinlock_api_smp.h:133 [inline]
_raw_spin_lock+0x2e/0x40 kernel/locking/spinlock.c:154
spin_lock include/linux/spinlock.h:351 [inline]
sk_clone_lock+0x2cd/0xf40 net/core/sock.c:2328
mptcp_sk_clone_init+0x32/0x13c0 net/mptcp/protocol.c:3279
subflow_syn_recv_sock+0x931/0x1920 net/mptcp/subflow.c:874
tcp_check_req+0xfe4/0x1a20 net/ipv4/tcp_minisocks.c:853
tcp_v4_rcv+0x1c3e/0x37f0 net/ipv4/tcp_ipv4.c:2267
ip_protocol_deliver_rcu+0x22e/0x440 net/ipv4/ip_input.c:205
ip_local_deliver_finish+0x341/0x5f0 net/ipv4/ip_input.c:233
NF_HOOK+0x3a4/0x450 include/linux/netfilter.h:314
NF_HOOK+0x3a4/0x450 include/linux/netfilter.h:314
__netif_receive_skb_one_core net/core/dev.c:5661 [inline]
__netif_receive_skb+0x2bf/0x650 net/core/dev.c:5775
process_backlog+0x662/0x15b0 net/core/dev.c:6108
__napi_poll+0xcb/0x490 net/core/dev.c:6772
napi_poll net/core/dev.c:6841 [inline]
net_rx_action+0x89b/0x1240 net/core/dev.c:6963
handle_softirqs+0x2c4/0x970 kernel/softirq.c:554
do_softirq+0x11b/0x1e0 kernel/softirq.c:455
</IRQ>
<TASK>
__local_bh_enable_ip+0x1bb/0x200 kernel/softirq.c:382
local_bh_enable include/linux/bottom_half.h:33 [inline]
rcu_read_unlock_bh include/linux/rcupdate.h:908 [inline]
__dev_queue_xmit+0x1763/0x3e90 net/core/dev.c:4450
dev_queue_xmit include/linux/netdevice.h:3105 [inline]
neigh_hh_output include/net/neighbour.h:526 [inline]
neigh_output include/net/neighbour.h:540 [inline]
ip_finish_output2+0xd41/0x1390 net/ipv4/ip_output.c:235
ip_local_out net/ipv4/ip_output.c:129 [inline]
__ip_queue_xmit+0x118c/0x1b80 net/ipv4/ip_output.c:535
__tcp_transmit_skb+0x2544/0x3b30 net/ipv4/tcp_output.c:1466
tcp_rcv_synsent_state_process net/ipv4/tcp_input.c:6542 [inline]
tcp_rcv_state_process+0x2c32/0x4570 net/ipv4/tcp_input.c:6729
tcp_v4_do_rcv+0x77d/0xc70 net/ipv4/tcp_ipv4.c:1934
sk_backlog_rcv include/net/sock.h:1111 [inline]
__release_sock+0x214/0x350 net/core/sock.c:3004
release_sock+0x61/0x1f0 net/core/sock.c:3558
mptcp_sendmsg_fastopen+0x1ad/0x530 net/mptcp/protocol.c:1733
mptcp_sendmsg+0x1884/0x1b10 net/mptcp/protocol.c:1812
sock_sendmsg_nosec net/socket.c:730 [inline]
__sock_sendmsg+0x1a6/0x270 net/socket.c:745
____sys_sendmsg+0x525/0x7d0 net/socket.c:2597
___sys_sendmsg net/socket.c:2651 [inline]
__sys_sendmmsg+0x3b2/0x740 net/socket.c:2737
__do_sys_sendmmsg net/socket.c:2766 [inline]
__se_sys_sendmmsg net/socket.c:2763 [inline]
__x64_sys_sendmmsg+0xa0/0xb0 net/socket.c:2763
do_syscall_x64 arch/x86/entry/common.c:52 [inline]
do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83
entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7f04fb13a6b9
Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 01 1a 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 b8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007ffd651f42d8 EFLAGS: 00000246 ORIG_RAX: 0000000000000133
RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007f04fb13a6b9
RDX: 0000000000000001 RSI: 0000000020000d00 RDI: 0000000000000004
RBP: 00007ffd651f4310 R08: 0000000000000001 R09: 0000000000000001
R10: 0000000020000080 R11: 0000000000000246 R12: 00000000000f4240
R13: 00007f04fb187449 R14: 00007ffd651f42f4 R15: 00007ffd651f4300
</TASK>
As noted by Cong Wang, the splat is false positive, but the code
path leading to the report is an unexpected one: a client is
attempting an MPC handshake towards the in-kernel listener created
by the in-kernel PM for a port based signal endpoint.
Such connection will be never accepted; many of them can make the
listener queue full and preventing the creation of MPJ subflow via
such listener - its intended role.
Explicitly detect this scenario at initial-syn time and drop the
incoming MPC request.
Fixes: 1729cf186d ("mptcp: create the listening socket for new port")
Cc: stable@vger.kernel.org
Reported-by: syzbot+f4aacdfef2c6a6529c3e@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=f4aacdfef2c6a6529c3e
Cc: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20241014-net-mptcp-mpc-port-endp-v2-1-7faea8e6b6ae@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
125 lines
5.2 KiB
C
125 lines
5.2 KiB
C
// SPDX-License-Identifier: GPL-2.0-or-later
|
|
|
|
#include <linux/seq_file.h>
|
|
#include <net/ip.h>
|
|
#include <net/mptcp.h>
|
|
#include <net/snmp.h>
|
|
#include <net/net_namespace.h>
|
|
|
|
#include "mib.h"
|
|
|
|
static const struct snmp_mib mptcp_snmp_list[] = {
|
|
SNMP_MIB_ITEM("MPCapableSYNRX", MPTCP_MIB_MPCAPABLEPASSIVE),
|
|
SNMP_MIB_ITEM("MPCapableSYNTX", MPTCP_MIB_MPCAPABLEACTIVE),
|
|
SNMP_MIB_ITEM("MPCapableSYNACKRX", MPTCP_MIB_MPCAPABLEACTIVEACK),
|
|
SNMP_MIB_ITEM("MPCapableACKRX", MPTCP_MIB_MPCAPABLEPASSIVEACK),
|
|
SNMP_MIB_ITEM("MPCapableFallbackACK", MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK),
|
|
SNMP_MIB_ITEM("MPCapableFallbackSYNACK", MPTCP_MIB_MPCAPABLEACTIVEFALLBACK),
|
|
SNMP_MIB_ITEM("MPCapableSYNTXDrop", MPTCP_MIB_MPCAPABLEACTIVEDROP),
|
|
SNMP_MIB_ITEM("MPCapableSYNTXDisabled", MPTCP_MIB_MPCAPABLEACTIVEDISABLED),
|
|
SNMP_MIB_ITEM("MPCapableEndpAttempt", MPTCP_MIB_MPCAPABLEENDPATTEMPT),
|
|
SNMP_MIB_ITEM("MPFallbackTokenInit", MPTCP_MIB_TOKENFALLBACKINIT),
|
|
SNMP_MIB_ITEM("MPTCPRetrans", MPTCP_MIB_RETRANSSEGS),
|
|
SNMP_MIB_ITEM("MPJoinNoTokenFound", MPTCP_MIB_JOINNOTOKEN),
|
|
SNMP_MIB_ITEM("MPJoinSynRx", MPTCP_MIB_JOINSYNRX),
|
|
SNMP_MIB_ITEM("MPJoinSynBackupRx", MPTCP_MIB_JOINSYNBACKUPRX),
|
|
SNMP_MIB_ITEM("MPJoinSynAckRx", MPTCP_MIB_JOINSYNACKRX),
|
|
SNMP_MIB_ITEM("MPJoinSynAckBackupRx", MPTCP_MIB_JOINSYNACKBACKUPRX),
|
|
SNMP_MIB_ITEM("MPJoinSynAckHMacFailure", MPTCP_MIB_JOINSYNACKMAC),
|
|
SNMP_MIB_ITEM("MPJoinAckRx", MPTCP_MIB_JOINACKRX),
|
|
SNMP_MIB_ITEM("MPJoinAckHMacFailure", MPTCP_MIB_JOINACKMAC),
|
|
SNMP_MIB_ITEM("MPJoinSynTx", MPTCP_MIB_JOINSYNTX),
|
|
SNMP_MIB_ITEM("MPJoinSynTxCreatSkErr", MPTCP_MIB_JOINSYNTXCREATSKERR),
|
|
SNMP_MIB_ITEM("MPJoinSynTxBindErr", MPTCP_MIB_JOINSYNTXBINDERR),
|
|
SNMP_MIB_ITEM("MPJoinSynTxConnectErr", MPTCP_MIB_JOINSYNTXCONNECTERR),
|
|
SNMP_MIB_ITEM("DSSNotMatching", MPTCP_MIB_DSSNOMATCH),
|
|
SNMP_MIB_ITEM("DSSCorruptionFallback", MPTCP_MIB_DSSCORRUPTIONFALLBACK),
|
|
SNMP_MIB_ITEM("DSSCorruptionReset", MPTCP_MIB_DSSCORRUPTIONRESET),
|
|
SNMP_MIB_ITEM("InfiniteMapTx", MPTCP_MIB_INFINITEMAPTX),
|
|
SNMP_MIB_ITEM("InfiniteMapRx", MPTCP_MIB_INFINITEMAPRX),
|
|
SNMP_MIB_ITEM("DSSNoMatchTCP", MPTCP_MIB_DSSTCPMISMATCH),
|
|
SNMP_MIB_ITEM("DataCsumErr", MPTCP_MIB_DATACSUMERR),
|
|
SNMP_MIB_ITEM("OFOQueueTail", MPTCP_MIB_OFOQUEUETAIL),
|
|
SNMP_MIB_ITEM("OFOQueue", MPTCP_MIB_OFOQUEUE),
|
|
SNMP_MIB_ITEM("OFOMerge", MPTCP_MIB_OFOMERGE),
|
|
SNMP_MIB_ITEM("NoDSSInWindow", MPTCP_MIB_NODSSWINDOW),
|
|
SNMP_MIB_ITEM("DuplicateData", MPTCP_MIB_DUPDATA),
|
|
SNMP_MIB_ITEM("AddAddr", MPTCP_MIB_ADDADDR),
|
|
SNMP_MIB_ITEM("AddAddrTx", MPTCP_MIB_ADDADDRTX),
|
|
SNMP_MIB_ITEM("AddAddrTxDrop", MPTCP_MIB_ADDADDRTXDROP),
|
|
SNMP_MIB_ITEM("EchoAdd", MPTCP_MIB_ECHOADD),
|
|
SNMP_MIB_ITEM("EchoAddTx", MPTCP_MIB_ECHOADDTX),
|
|
SNMP_MIB_ITEM("EchoAddTxDrop", MPTCP_MIB_ECHOADDTXDROP),
|
|
SNMP_MIB_ITEM("PortAdd", MPTCP_MIB_PORTADD),
|
|
SNMP_MIB_ITEM("AddAddrDrop", MPTCP_MIB_ADDADDRDROP),
|
|
SNMP_MIB_ITEM("MPJoinPortSynRx", MPTCP_MIB_JOINPORTSYNRX),
|
|
SNMP_MIB_ITEM("MPJoinPortSynAckRx", MPTCP_MIB_JOINPORTSYNACKRX),
|
|
SNMP_MIB_ITEM("MPJoinPortAckRx", MPTCP_MIB_JOINPORTACKRX),
|
|
SNMP_MIB_ITEM("MismatchPortSynRx", MPTCP_MIB_MISMATCHPORTSYNRX),
|
|
SNMP_MIB_ITEM("MismatchPortAckRx", MPTCP_MIB_MISMATCHPORTACKRX),
|
|
SNMP_MIB_ITEM("RmAddr", MPTCP_MIB_RMADDR),
|
|
SNMP_MIB_ITEM("RmAddrDrop", MPTCP_MIB_RMADDRDROP),
|
|
SNMP_MIB_ITEM("RmAddrTx", MPTCP_MIB_RMADDRTX),
|
|
SNMP_MIB_ITEM("RmAddrTxDrop", MPTCP_MIB_RMADDRTXDROP),
|
|
SNMP_MIB_ITEM("RmSubflow", MPTCP_MIB_RMSUBFLOW),
|
|
SNMP_MIB_ITEM("MPPrioTx", MPTCP_MIB_MPPRIOTX),
|
|
SNMP_MIB_ITEM("MPPrioRx", MPTCP_MIB_MPPRIORX),
|
|
SNMP_MIB_ITEM("MPFailTx", MPTCP_MIB_MPFAILTX),
|
|
SNMP_MIB_ITEM("MPFailRx", MPTCP_MIB_MPFAILRX),
|
|
SNMP_MIB_ITEM("MPFastcloseTx", MPTCP_MIB_MPFASTCLOSETX),
|
|
SNMP_MIB_ITEM("MPFastcloseRx", MPTCP_MIB_MPFASTCLOSERX),
|
|
SNMP_MIB_ITEM("MPRstTx", MPTCP_MIB_MPRSTTX),
|
|
SNMP_MIB_ITEM("MPRstRx", MPTCP_MIB_MPRSTRX),
|
|
SNMP_MIB_ITEM("RcvPruned", MPTCP_MIB_RCVPRUNED),
|
|
SNMP_MIB_ITEM("SubflowStale", MPTCP_MIB_SUBFLOWSTALE),
|
|
SNMP_MIB_ITEM("SubflowRecover", MPTCP_MIB_SUBFLOWRECOVER),
|
|
SNMP_MIB_ITEM("SndWndShared", MPTCP_MIB_SNDWNDSHARED),
|
|
SNMP_MIB_ITEM("RcvWndShared", MPTCP_MIB_RCVWNDSHARED),
|
|
SNMP_MIB_ITEM("RcvWndConflictUpdate", MPTCP_MIB_RCVWNDCONFLICTUPDATE),
|
|
SNMP_MIB_ITEM("RcvWndConflict", MPTCP_MIB_RCVWNDCONFLICT),
|
|
SNMP_MIB_ITEM("MPCurrEstab", MPTCP_MIB_CURRESTAB),
|
|
SNMP_MIB_ITEM("Blackhole", MPTCP_MIB_BLACKHOLE),
|
|
SNMP_MIB_SENTINEL
|
|
};
|
|
|
|
/* mptcp_mib_alloc - allocate percpu mib counters
|
|
*
|
|
* These are allocated when the first mptcp socket is created so
|
|
* we do not waste percpu memory if mptcp isn't in use.
|
|
*/
|
|
bool mptcp_mib_alloc(struct net *net)
|
|
{
|
|
struct mptcp_mib __percpu *mib = alloc_percpu(struct mptcp_mib);
|
|
|
|
if (!mib)
|
|
return false;
|
|
|
|
if (cmpxchg(&net->mib.mptcp_statistics, NULL, mib))
|
|
free_percpu(mib);
|
|
|
|
return true;
|
|
}
|
|
|
|
void mptcp_seq_show(struct seq_file *seq)
|
|
{
|
|
unsigned long sum[ARRAY_SIZE(mptcp_snmp_list) - 1];
|
|
struct net *net = seq->private;
|
|
int i;
|
|
|
|
seq_puts(seq, "MPTcpExt:");
|
|
for (i = 0; mptcp_snmp_list[i].name; i++)
|
|
seq_printf(seq, " %s", mptcp_snmp_list[i].name);
|
|
|
|
seq_puts(seq, "\nMPTcpExt:");
|
|
|
|
memset(sum, 0, sizeof(sum));
|
|
if (net->mib.mptcp_statistics)
|
|
snmp_get_cpu_field_batch(sum, mptcp_snmp_list,
|
|
net->mib.mptcp_statistics);
|
|
|
|
for (i = 0; mptcp_snmp_list[i].name; i++)
|
|
seq_printf(seq, " %lu", sum[i]);
|
|
|
|
seq_putc(seq, '\n');
|
|
}
|