4.16-RC7 WARNING: CPU: 2 PID: 0 at block/blk-mq.c:1400 __blk_mq_delay_run_hw_queue

From: Stefan Haberland
Date: Tue Mar 27 2018 - 06:04:38 EST


Hi,

I get the following warning in __blk_mq_delay_run_hw_queue when the scheduler is set to mq-deadline for DASD devices on s390.

What I see is that for whatever reason there is a hctx nr 0 which has no hctx->tags pointer set.
From my observation it is always hctx nr 0 which has a tags NULL pointer in it and I see other hctx which have the hctx->tags pointer set correctly.


[ÂÂÂ 2.169986] WARNING: CPU: 0 PID: 0 at block/blk-mq.c:1402 __blk_mq_delay_run_hw_queue+0xe8/0x118
[ÂÂÂ 2.170007] Modules linked in:
[ÂÂÂ 2.170014] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.16.0-rc7-04107-g91a05d9e1d6b-dirty #147
[ÂÂÂ 2.170019] Hardware name: IBM 2964 N96 702 (z/VM 6.4.0)
[ÂÂÂ 2.170024] Krnl PSW : 0000000076fd6c7f 00000000c244c24d (__blk_mq_delay_run_hw_queue+0xe8/0x118)
[ÂÂÂ 2.170035]ÂÂÂÂÂÂÂÂÂÂÂ R:0 T:1 IO:0 EX:0 Key:0 M:1 W:0 P:0 AS:3 CC:0 PM:0 RI:0 EA:3
[ÂÂÂ 2.170041] Krnl GPRS: 00000000599ec58a 0000000002a94000 0000000002a94000 0000000000000001
[ÂÂÂ 2.170047]ÂÂÂÂÂÂÂÂÂÂÂ 0000000000000000 000000006e761e98 0000000002a96980 0000000002a96800
[ÂÂÂ 2.170052]ÂÂÂÂÂÂÂÂÂÂÂ 0000000002d87ce0 00000000737fbda8 0000000000000000 0000000000000001
[ÂÂÂ 2.170058]ÂÂÂÂÂÂÂÂÂÂÂ 0000000000000001 0000000000aedd10 00000000737fbc38 00000000737fbc00
[ÂÂÂ 2.170069] Krnl Code: 00000000006ea3c8: ebaff0a00004 lmgÂÂÂÂ %r10,%r15,160(%r15)
ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ 00000000006ea3ce: c0f4ffff5e0d brclÂÂÂ 15,6d5fe8
ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ #00000000006ea3d4: a7f40001 brcÂÂÂÂ 15,6ea3d6
ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ >00000000006ea3d8: e340f0c00004ÂÂÂÂÂÂÂ lgÂÂÂÂÂ %r4,192(%r15)
ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ 00000000006ea3de: ebaff0a00004 lmgÂÂÂÂ %r10,%r15,160(%r15)
ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ 00000000006ea3e4: 07f4 bcrÂÂÂÂ 15,%r4
ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ 00000000006ea3e6: 41b01100 laÂÂÂÂÂ %r11,256(%r1)
ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ 00000000006ea3ea: 182a lrÂÂÂÂÂ %r2,%r10
[ÂÂÂ 2.170158] Call Trace:
[ÂÂÂ 2.170205] ([<0000000002a96800>] 0x2a96800)
[ÂÂÂ 2.170248]Â [<00000000006ea4c0>] blk_mq_run_hw_queue+0xa0/0x100
[ÂÂÂ 2.170262]Â [<00000000006ea59c>] blk_mq_run_hw_queues+0x7c/0x98
[ÂÂÂ 2.170295]Â [<00000000006e88f6>] __blk_mq_complete_request+0x10e/0x1e0
[ÂÂÂ 2.170300]Â [<00000000006e9e30>] blk_mq_complete_request+0x80/0xa0
[ÂÂÂ 2.170307]Â [<000000000087fad0>] dasd_block_tasklet+0x218/0x480
[ÂÂÂ 2.170415]Â [<000000000017c3f8>] tasklet_hi_action+0xa0/0x138
[ÂÂÂ 2.170434]Â [<0000000000a91c10>] __do_softirq+0xc8/0x540
[ÂÂÂ 2.170471]Â [<000000000017bd4e>] irq_exit+0x136/0x140
[ÂÂÂ 2.170478]Â [<000000000010c912>] do_IRQ+0x8a/0xb8
[ÂÂÂ 2.170518]Â [<0000000000a90ee0>] io_int_handler+0x138/0x2e0
[ÂÂÂ 2.170524]Â [<0000000000102cd0>] enabled_wait+0x58/0x128
[ÂÂÂ 2.170562] ([<0000000000102cb8>] enabled_wait+0x40/0x128)
[ÂÂÂ 2.170577]Â [<000000000010319a>] arch_cpu_idle+0x32/0x48
[ÂÂÂ 2.170604]Â [<0000000000a8f636>] default_idle_call+0x3e/0x58
[ÂÂÂ 2.170613]Â [<00000000001cd5d2>] do_idle+0xda/0x190
[ÂÂÂ 2.170621]Â [<00000000001cd93e>] cpu_startup_entry+0x3e/0x48
[ÂÂÂ 2.170633]Â [<0000000000e5ebf4>] start_kernel+0x47c/0x490
[ÂÂÂ 2.170641]Â [<0000000000100020>] _stext+0x20/0x80
[ÂÂÂ 2.170650] 2 locks held by swapper/0/0:
[ÂÂÂ 2.170658]Â #0:Â (&(&dq->lock)->rlock){..-.}, at: [<00000000b45eaf9e>] dasd_block_tasklet+0x1cc/0x480
[ÂÂÂ 2.170676]Â #1:Â (rcu_read_lock){....}, at: [<00000000bc7fa045>] hctx_lock+0x34/0x110
[ÂÂÂ 2.170750] Last Breaking-Event-Address:
[ÂÂÂ 2.170758]Â [<00000000006ea3d4>] __blk_mq_delay_run_hw_queue+0xe4/0x118
[ÂÂÂ 2.170803] ---[ end trace 1073cf0de1fd32d0 ]---



Regards,
Stefan