With Eric's ref tracker, syzbot finally found a repro for
use-after-free in tcp_write_timer_handler() by kernel TCP
sockets. [0]
If SMC creates a kernel socket in __smc_create(), the kernel
socket is supposed to be freed in smc_clcsock_release() by
calling sock_release() when we close() the parent SMC socket.
However, at the end of smc_clcsock_release(), the kernel
socket's sk_state might not be TCP_CLOSE. This means that
we have not called inet_csk_destroy_sock() in __tcp_close()
and have not stopped the TCP timers.
The kernel socket's TCP timers can be fired later, so we
need to hold a refcnt for net as we do for MPTCP subflows
in mptcp_subflow_create_socket().
[0]:
leaked reference.
sk_alloc (./include/net/net_namespace.h:335 net/core/sock.c:2108)
inet_create (net/ipv4/af_inet.c:319 net/ipv4/af_inet.c:244)
__sock_create (net/socket.c:1546)
smc_create (net/smc/af_smc.c:3269 net/smc/af_smc.c:3284)
__sock_create (net/socket.c:1546)
__sys_socket (net/socket.c:1634 net/socket.c:1618 net/socket.c:1661)
__x64_sys_socket (net/socket.c:1672)
do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80)
entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120)
==================================================================
BUG: KASAN: slab-use-after-free in tcp_write_timer_handler (net/ipv4/tcp_timer.c:378 net/ipv4/tcp_timer.c:624 net/ipv4/tcp_timer.c:594)
Read of size 1 at addr ffff888052b65e0d by task syzrepro/18091
CPU: 0 PID: 18091 Comm: syzrepro Tainted: G W 6.3.0-rc4-01174-gb5d54eb5899a #7
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.0-1.amzn2022.0.1 04/01/2014
Call Trace:
<IRQ>
dump_stack_lvl (lib/dump_stack.c:107)
print_report (mm/kasan/report.c:320 mm/kasan/report.c:430)
kasan_report (mm/kasan/report.c:538)
tcp_write_timer_handler (net/ipv4/tcp_timer.c:378 net/ipv4/tcp_timer.c:624 net/ipv4/tcp_timer.c:594)
tcp_write_timer (./include/linux/spinlock.h:390 net/ipv4/tcp_timer.c:643)
call_timer_fn (./arch/x86/include/asm/jump_label.h:27 ./include/linux/jump_label.h:207 ./include/trace/events/timer.h:127 kernel/time/timer.c:1701)
__run_timers.part.0 (kernel/time/timer.c:1752 kernel/time/timer.c:2022)
run_timer_softirq (kernel/time/timer.c:2037)
__do_softirq (./arch/x86/include/asm/jump_label.h:27 ./include/linux/jump_label.h:207 ./include/trace/events/irq.h:142 kernel/softirq.c:572)
__irq_exit_rcu (kernel/softirq.c:445 kernel/softirq.c:650)
irq_exit_rcu (kernel/softirq.c:664)
sysvec_apic_timer_interrupt (arch/x86/kernel/apic/apic.c:1107 (discriminator 14))
</IRQ>
Fixes: ac7138746e14 ("smc: establish new socket family")
Reported-by: syzbot+7e1e1bdb852961150198@syzkaller.appspotmail.com
Link: https://lore.kernel.org/netdev/000000000000a3f51805f8bcc43a@google.com/
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
CLC message initialization was not properly reversed in error handling path. Reported-and-suggested-by: Alexander Gordeev <agordeev@linux.ibm.com> Signed-off-by: Stefan Raspl <raspl@linux.ibm.com> Signed-off-by: Wenjia Zhang <wenjia@linux.ibm.com> Reviewed-by: Tony Lu <tonylu@linux.alibaba.com> Signed-off-by: David S. Miller <davem@davemloft.net>
The following LOCKDEP was detected:
Workqueue: events smc_lgr_free_work [smc]
WARNING: possible circular locking dependency detected
6.1.0-20221027.rc2.git8.56bc5b569087.300.fc36.s390x+debug #1 Not tainted
------------------------------------------------------
kworker/3:0/176251 is trying to acquire lock:
00000000f1467148 ((wq_completion)smc_tx_wq-00000000#2){+.+.}-{0:0},
at: __flush_workqueue+0x7a/0x4f0
but task is already holding lock:
0000037fffe97dc8 ((work_completion)(&(&lgr->free_work)->work)){+.+.}-{0:0},
at: process_one_work+0x232/0x730
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #4 ((work_completion)(&(&lgr->free_work)->work)){+.+.}-{0:0}:
__lock_acquire+0x58e/0xbd8
lock_acquire.part.0+0xe2/0x248
lock_acquire+0xac/0x1c8
__flush_work+0x76/0xf0
__cancel_work_timer+0x170/0x220
__smc_lgr_terminate.part.0+0x34/0x1c0 [smc]
smc_connect_rdma+0x15e/0x418 [smc]
__smc_connect+0x234/0x480 [smc]
smc_connect+0x1d6/0x230 [smc]
__sys_connect+0x90/0xc0
__do_sys_socketcall+0x186/0x370
__do_syscall+0x1da/0x208
system_call+0x82/0xb0
-> #3 (smc_client_lgr_pending){+.+.}-{3:3}:
__lock_acquire+0x58e/0xbd8
lock_acquire.part.0+0xe2/0x248
lock_acquire+0xac/0x1c8
__mutex_lock+0x96/0x8e8
mutex_lock_nested+0x32/0x40
smc_connect_rdma+0xa4/0x418 [smc]
__smc_connect+0x234/0x480 [smc]
smc_connect+0x1d6/0x230 [smc]
__sys_connect+0x90/0xc0
__do_sys_socketcall+0x186/0x370
__do_syscall+0x1da/0x208
system_call+0x82/0xb0
-> #2 (sk_lock-AF_SMC){+.+.}-{0:0}:
__lock_acquire+0x58e/0xbd8
lock_acquire.part.0+0xe2/0x248
lock_acquire+0xac/0x1c8
lock_sock_nested+0x46/0xa8
smc_tx_work+0x34/0x50 [smc]
process_one_work+0x30c/0x730
worker_thread+0x62/0x420
kthread+0x138/0x150
__ret_from_fork+0x3c/0x58
ret_from_fork+0xa/0x40
-> #1 ((work_completion)(&(&smc->conn.tx_work)->work)){+.+.}-{0:0}:
__lock_acquire+0x58e/0xbd8
lock_acquire.part.0+0xe2/0x248
lock_acquire+0xac/0x1c8
process_one_work+0x2bc/0x730
worker_thread+0x62/0x420
kthread+0x138/0x150
__ret_from_fork+0x3c/0x58
ret_from_fork+0xa/0x40
-> #0 ((wq_completion)smc_tx_wq-00000000#2){+.+.}-{0:0}:
check_prev_add+0xd8/0xe88
validate_chain+0x70c/0xb20
__lock_acquire+0x58e/0xbd8
lock_acquire.part.0+0xe2/0x248
lock_acquire+0xac/0x1c8
__flush_workqueue+0xaa/0x4f0
drain_workqueue+0xaa/0x158
destroy_workqueue+0x44/0x2d8
smc_lgr_free+0x9e/0xf8 [smc]
process_one_work+0x30c/0x730
worker_thread+0x62/0x420
kthread+0x138/0x150
__ret_from_fork+0x3c/0x58
ret_from_fork+0xa/0x40
other info that might help us debug this:
Chain exists of:
(wq_completion)smc_tx_wq-00000000#2
--> smc_client_lgr_pending
--> (work_completion)(&(&lgr->free_work)->work)
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock((work_completion)(&(&lgr->free_work)->work));
lock(smc_client_lgr_pending);
lock((work_completion)
(&(&lgr->free_work)->work));
lock((wq_completion)smc_tx_wq-00000000#2);
*** DEADLOCK ***
2 locks held by kworker/3:0/176251:
#0: 0000000080183548
((wq_completion)events){+.+.}-{0:0},
at: process_one_work+0x232/0x730
#1: 0000037fffe97dc8
((work_completion)
(&(&lgr->free_work)->work)){+.+.}-{0:0},
at: process_one_work+0x232/0x730
stack backtrace:
CPU: 3 PID: 176251 Comm: kworker/3:0 Not tainted
Hardware name: IBM 8561 T01 701 (z/VM 7.2.0)
Call Trace:
[<000000002983c3e4>] dump_stack_lvl+0xac/0x100
[<0000000028b477ae>] check_noncircular+0x13e/0x160
[<0000000028b48808>] check_prev_add+0xd8/0xe88
[<0000000028b49cc4>] validate_chain+0x70c/0xb20
[<0000000028b4bd26>] __lock_acquire+0x58e/0xbd8
[<0000000028b4cf6a>] lock_acquire.part.0+0xe2/0x248
[<0000000028b4d17c>] lock_acquire+0xac/0x1c8
[<0000000028addaaa>] __flush_workqueue+0xaa/0x4f0
[<0000000028addf9a>] drain_workqueue+0xaa/0x158
[<0000000028ae303c>] destroy_workqueue+0x44/0x2d8
[<000003ff8029af26>] smc_lgr_free+0x9e/0xf8 [smc]
[<0000000028adf3d4>] process_one_work+0x30c/0x730
[<0000000028adf85a>] worker_thread+0x62/0x420
[<0000000028aeac50>] kthread+0x138/0x150
[<0000000028a63914>] __ret_from_fork+0x3c/0x58
[<00000000298503da>] ret_from_fork+0xa/0x40
INFO: lockdep is turned off.
===================================================================
This deadlock occurs because cancel_delayed_work_sync() waits for
the work(&lgr->free_work) to finish, while the &lgr->free_work
waits for the work(lgr->tx_wq), which needs the sk_lock-AF_SMC, that
is already used under the mutex_lock.
The solution is to use cancel_delayed_work() instead, which kills
off a pending work.
Fixes: a52bcc919b14 ("net/smc: improve termination processing")
Signed-off-by: Wenjia Zhang <wenjia@linux.ibm.com>
Reviewed-by: Jan Karcher <jaka@linux.ibm.com>
Reviewed-by: Karsten Graul <kgraul@linux.ibm.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When performing a stress test on SMC-R by rmmod mlx5_ib driver
during the wrk/nginx test, we found that there is a probability
of triggering a panic while terminating all link groups.
This issue dues to the race between smc_smcr_terminate_all()
and smc_buf_create().
smc_smcr_terminate_all
smc_buf_create
/* init */
conn->sndbuf_desc = NULL;
...
__smc_lgr_terminate
smc_conn_kill
smc_close_abort
smc_cdc_get_slot_and_msg_send
__softirqentry_text_start
smc_wr_tx_process_cqe
smc_cdc_tx_handler
READ(conn->sndbuf_desc->len);
/* panic dues to NULL sndbuf_desc */
conn->sndbuf_desc = xxx;
This patch tries to fix the issue by always to check the sndbuf_desc
before send any cdc msg, to make sure that no null pointer is
seen during cqe processing.
Fixes: 0b29ec643613 ("net/smc: immediate termination for SMCR link groups")
Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Link: https://lore.kernel.org/r/1678263432-17329-1-git-send-email-alibuda@linux.alibaba.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Before determining whether the msg has unsupported options, it has been
prematurely terminated by the wrong status check.
For the application, the general usages of MSG_FASTOPEN likes
fd = socket(...)
/* rather than connect */
sendto(fd, data, len, MSG_FASTOPEN)
Hence, We need to check the flag before state check, because the sock
state here is always SMC_INIT when applications tries MSG_FASTOPEN.
Once we found unsupported options, fallback it to TCP.
Fixes: ee9dfbef02d1 ("net/smc: handle sockopts forcing fallback")
Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
Signed-off-by: Simon Horman <simon.horman@corigine.com>
v2 -> v1: Optimize code style
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Per-next-PR merge.
net/smc/af_smc.c
b5dd4d698171 ("net/smc: llc_conf_mutex refactor, replace it with rw_semaphore")
e40b801b3603 ("net/smc: fix potential panic dues to unprotected smc_llc_srv_add_link()")
https://lore.kernel.org/all/20230221124008.6303c330@canb.auug.org.au/
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
There is a certain probability that following
exceptions will occur in the wrk benchmark test:
Running 10s test @ http://11.213.45.6:80
8 threads and 64 connections
Thread Stats Avg Stdev Max +/- Stdev
Latency 3.72ms 13.94ms 245.33ms 94.17%
Req/Sec 1.96k 713.67 5.41k 75.16%
155262 requests in 10.10s, 23.10MB read
Non-2xx or 3xx responses: 3
We will find that the error is HTTP 400 error, which is a serious
exception in our test, which means the application data was
corrupted.
Consider the following scenarios:
CPU0 CPU1
buf_desc->used = 0;
cmpxchg(buf_desc->used, 0, 1)
deal_with(buf_desc)
memset(buf_desc->cpu_addr,0);
This will cause the data received by a victim connection to be cleared,
thus triggering an HTTP 400 error in the server.
This patch exchange the order between clear used and memset, add
barrier to ensure memory consistency.
Fixes: 1c5526968e27 ("net/smc: Clear memory when release and reuse buffer")
Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There is a certain chance to trigger the following panic:
PID: 5900 TASK: ffff88c1c8af4100 CPU: 1 COMMAND: "kworker/1:48"
#0 [ffff9456c1cc79a0] machine_kexec at ffffffff870665b7
#1 [ffff9456c1cc79f0] __crash_kexec at ffffffff871b4c7a
#2 [ffff9456c1cc7ab0] crash_kexec at ffffffff871b5b60
#3 [ffff9456c1cc7ac0] oops_end at ffffffff87026ce7
#4 [ffff9456c1cc7ae0] page_fault_oops at ffffffff87075715
#5 [ffff9456c1cc7b58] exc_page_fault at ffffffff87ad0654
#6 [ffff9456c1cc7b80] asm_exc_page_fault at ffffffff87c00b62
[exception RIP: ib_alloc_mr+19]
RIP: ffffffffc0c9cce3 RSP: ffff9456c1cc7c38 RFLAGS: 00010202
RAX: 0000000000000000 RBX: 0000000000000002 RCX: 0000000000000004
RDX: 0000000000000010 RSI: 0000000000000000 RDI: 0000000000000000
RBP: ffff88c1ea281d00 R8: 000000020a34ffff R9: ffff88c1350bbb20
R10: 0000000000000000 R11: 0000000000000001 R12: 0000000000000000
R13: 0000000000000010 R14: ffff88c1ab040a50 R15: ffff88c1ea281d00
ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018
#7 [ffff9456c1cc7c60] smc_ib_get_memory_region at ffffffffc0aff6df [smc]
#8 [ffff9456c1cc7c88] smcr_buf_map_link at ffffffffc0b0278c [smc]
#9 [ffff9456c1cc7ce0] __smc_buf_create at ffffffffc0b03586 [smc]
The reason here is that when the server tries to create a second link,
smc_llc_srv_add_link() has no protection and may add a new link to
link group. This breaks the security environment protected by
llc_conf_mutex.
Fixes: 2d2209f20189 ("net/smc: first part of add link processing as SMC server")
Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
Reviewed-by: Larysa Zaremba <larysa.zaremba@intel.com>
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit e48c414ee61f ("[INET]: Generalise the TCP sock ID lookup routines")
commented out the definition of SOCK_REFCNT_DEBUG in 2005 and later another
commit 463c84b97f24 ("[NET]: Introduce inet_connection_sock") removed it.
Since we could track all of them through bpf and kprobe related tools
and the feature could print loads of information which might not be
that helpful even under a little bit pressure, the whole feature which
has been inactive for many years is no longer supported.
Link: https://lore.kernel.org/lkml/20230211065153.54116-1-kerneljasonxing@gmail.com/
Suggested-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Acked-by: Wenjia Zhang <wenjia@linux.ibm.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
It's clear that rmbs_lock and sndbufs_lock are aims to protect the rmbs list or the sndbufs list. During connection establieshment, smc_buf_get_slot() will always be invoked, and it only performs read semantics in rmbs list and sndbufs list. Based on the above considerations, we replace mutex with rw_semaphore. Only smc_buf_get_slot() use down_read() to allow smc_buf_get_slot() run concurrently, other part use down_write() to keep exclusive semantics. Signed-off-by: D. Wythe <alibuda@linux.alibaba.com> Signed-off-by: David S. Miller <davem@davemloft.net>