Re: [syzbot] [net?] WARNING in netdev_queue_get_dma_dev

On 8/4/26 22:00, Jakub Kicinski wrote:
> Hi Pavel, could you TAL?

It complains on not holding rtnl, so the netdev should be not
qops-enabled, and we acquire it with netdev_get_by_index_lock().
It's going to be rejected later, but not sure whether netdev->lock
protects its device and leasing logic well in this case.

As a quick fix, let's fail it early in zcrx if there is no qops.


> On Tue, 04 Aug 2026 07:32:44 -0700 syzbot wrote:
>> Hello,
>>
>> syzbot found the following issue on:
>>
>> HEAD commit:    075b74841bd0 Linux 7.2-rc6
>> git tree:       upstream
>> console+strace: https://syzkaller.appspot.com/x/log.txt?x=176a7db9580000
>> kernel config:  https://syzkaller.appspot.com/x/.config?x=145fa60d73086782
>> dashboard link: https://syzkaller.appspot.com/bug?extid=a78926bdac2adb52dc0e
>> compiler:       gcc (Debian 14.2.0-19) 14.2.0, GNU ld (GNU Binutils for Debian) 2.44
>> syz repro:      https://syzkaller.appspot.com/x/repro.syz?x=16225db9580000
>> C reproducer:   https://syzkaller.appspot.com/x/repro.c?x=17bade32580000
>>
>> Downloadable assets:
>> disk image: https://storage.googleapis.com/syzbot-assets/1dc04730d019/disk-075b7484.raw.xz
>> vmlinux: https://storage.googleapis.com/syzbot-assets/d76da42271f4/vmlinux-075b7484.xz
>> kernel image: https://storage.googleapis.com/syzbot-assets/07b1cdbcbe45/bzImage-075b7484.xz
>>
>> IMPORTANT: if you fix the issue, please add the following tag to the commit:
>> Reported-by: [email protected]
>>
>> ------------[ cut here ]------------
>> RTNL: assertion failed at ./include/net/netdev_lock.h (72)
>> WARNING: ./include/net/netdev_lock.h:72 at netdev_assert_locked_ops_compat include/net/netdev_lock.h:72 [inline], CPU#1: syz-executor223/5620
>> WARNING: ./include/net/netdev_lock.h:72 at netdev_queue_get_dma_dev+0x52e/0x660 net/core/netdev_queues.c:43, CPU#1: syz-executor223/5620
>> Modules linked in:
>> CPU: 1 UID: 0 PID: 5620 Comm: syz-executor223 Not tainted syzkaller #0 PREEMPT(full)
>> Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/16/2026
>> RIP: 0010:netdev_assert_locked_ops_compat include/net/netdev_lock.h:72 [inline]
>> RIP: 0010:netdev_queue_get_dma_dev+0x53a/0x660 net/core/netdev_queues.c:43
>> Code: 89 c5 89 c6 e8 27 f7 68 f8 45 85 ed 0f 85 be fb ff ff e8 a9 fc 68 f8 48 8d 3d 12 0e 90 07 ba 48 00 00 00 48 c7 c6 a0 88 18 8d <67> 48 0f b9 3a e9 9c fb ff ff e8 87 fc 68 f8 48 8d bd 00 08 00 00
>> RSP: 0018:ffffc90003b47a80 EFLAGS: 00010293
>> RAX: 0000000000000000 RBX: ffff888029874000 RCX: ffffffff89a16569
>> RDX: 0000000000000048 RSI: ffffffff8d1888a0 RDI: ffffffff91317390
>> RBP: 0000000000000000 R08: 0000000000000005 R09: 0000000000000000
>> R10: 0000000000000000 R11: 0000000000000001 R12: 0000000000000000
>> R13: 0000000000000000 R14: ffff88807b3f2568 R15: ffffc90003b47be0
>> FS:  00005555885ac400(0000) GS:ffff888123ed8000(0000) knlGS:0000000000000000
>> CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
>> CR2: 0000200000001000 CR3: 000000006f8b6000 CR4: 00000000003526f0
>> Call Trace:
>>   <TASK>
>>   zcrx_register_netdev io_uring/zcrx.c:831 [inline]
>>   io_register_zcrx+0xe94/0x1d30 io_uring/zcrx.c:983
>>   __io_uring_register io_uring/register.c:942 [inline]
>>   __do_sys_io_uring_register+0x1193/0x1bc0 io_uring/register.c:1040
>>   do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
>>   do_syscall_64+0x115/0x870 arch/x86/entry/syscall_64.c:94
>>   entry_SYSCALL_64_after_hwframe+0x77/0x7f
>> RIP: 0033:0x7fd0b54bbcb9
>> Code: c0 79 93 eb d5 48 8d 7c 1d 00 eb 99 0f 1f 44 00 00 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 d8 ff ff ff f7 d8 64 89 01 48
>> RSP: 002b:00007ffe25f0a7f8 EFLAGS: 00000246 ORIG_RAX: 00000000000001ab
>> RAX: ffffffffffffffda RBX: 00007ffe25f0a928 RCX: 00007fd0b54bbcb9
>> RDX: 0000200000000400 RSI: 0000000000000020 RDI: 0000000000000003
>> RBP: 0000000000000001 R08: 0000000000000000 R09: 00007ffe25f0a928
>> R10: 0000000000000001 R11: 0000000000000246 R12: 00007ffe25f0a918
>> R13: 0000000000000002 R14: 00007fd0b554cca0 R15: 0000000000000002
>>   </TASK>
>> ----------------
>> Code disassembly (best guess):
>>     0:	89 c5                	mov    %eax,%ebp
>>     2:	89 c6                	mov    %eax,%esi
>>     4:	e8 27 f7 68 f8       	call   0xf868f730
>>     9:	45 85 ed             	test   %r13d,%r13d
>>     c:	0f 85 be fb ff ff    	jne    0xfffffbd0
>>    12:	e8 a9 fc 68 f8       	call   0xf868fcc0
>>    17:	48 8d 3d 12 0e 90 07 	lea    0x7900e12(%rip),%rdi        # 0x7900e30
>>    1e:	ba 48 00 00 00       	mov    $0x48,%edx
>>    23:	48 c7 c6 a0 88 18 8d 	mov    $0xffffffff8d1888a0,%rsi
>> * 2a:	67 48 0f b9 3a       	ud1    (%edx),%rdi <-- trapping instruction
>>    2f:	e9 9c fb ff ff       	jmp    0xfffffbd0
>>    34:	e8 87 fc 68 f8       	call   0xf868fcc0
>>    39:	48 8d bd 00 08 00 00 	lea    0x800(%rbp),%rdi
>>
>>
>> ---
>> This report is generated by a bot. It may contain errors.
>> See https://goo.gl/tpsmEJ for more information about syzbot.
>> syzbot engineers can be reached at [email protected].
>>
>> syzbot will keep track of this issue. See:
>> https://goo.gl/tpsmEJ#status for how to communicate with syzbot.
>>
>> If the report is already addressed, let syzbot know by replying with:
>> #syz fix: exact-commit-title
>>
>> If you want syzbot to run the reproducer, reply with:
>> #syz test: git://repo/address.git branch-or-commit-hash
>> If you attach or paste a git patch, syzbot will apply it before testing.
>>
>> If you want to overwrite report's subsystems, reply with:
>> #syz set subsystems: new-subsystem
>> (See the list of subsystem names on the web dashboard)
>>
>> If the report is a duplicate of another one, reply with:
>> #syz dup: exact-subject-of-another-report
>>
>> If you want to undo deduplication, reply with:
>> #syz undup
> 

-- 
Pavel Begunkov