From: Florian Bezdeka <florian.bezdeka@siemens.com>
To: xenomai@lists.linux.dev
Cc: Jan Kiszka <jan.kiszka@siemens.com>, rpm@xenomai.org
Subject: Dovetail 6.1.54: IRQ handler enables HW irqs
Date: Mon, 02 Oct 2023 14:34:54 +0200 [thread overview]
Message-ID: <1cd875106cdf555e52734462a9d846ffd3549556.camel@siemens.com> (raw)
Hi Philippe, Hi Jan,
I'm currently testing the latest Dovetail 6.1.x release, which is
6.1.54 to my best knowledge.
After updating I run into the following problem. There have been recent
changes to the handling of per-cpu IRQs, that might be related.
The problem occurs when using stress-ng to simulate system load when
running on VirtualBox as VMM on a Windows Host. The Linux host is still
running the test but might be affected too.
The machine "dies"/"hangs" a few seconds after the first reporting.
[ 71.553200] ------------[ cut here ]------------
[ 71.557426] irq 21 handler ahci_single_level_irq_intr+0x0/0x60 [libahci] enabled interrupts
[ 71.565260] WARNING: CPU: 1 PID: 192 at kernel/irq/handle.c:168 __handle_irq_event_percpu+0x14c/0x180
[ 71.573165] Modules linked in: intel_rapl_msr intel_rapl_common
intel_pmc_core ghash_clmulni_intel sha512_ssse3 sha512_generic vmwgfx
drm_ttm_helper snd_intel8x0 ttm snd_ac97_codec aesni_intel crypto_simd
ac97_bus cryptd drm_kms_helper rapl snd_pcm fb_sys_fops syscopyarea
snd_timer pcspkr sysfillrect snd sysimgblt vboxguest soundcore ac button
joydev evdev serio_raw sg binfmt_misc loop fuse efi_pstore drm dm_mod
dax configfs ip_tables x_tables autofs4 ext4 crc32c_generic crc16
mbcache jbd2 hid_generic usbhid sd_mod t10_pi hid crc64_rocksoft crc64
sr_mod crc_t10dif cdrom crct10dif_generic ata_generic ahci ata_piix
libahci ohci_pci ohci_hcd ehci_pci ehci_hcd libata crct10dif_pclmul
usbcore crct10dif_common scsi_mod video crc32_pclmul psmouse e1000
scsi_common i2c_piix4 crc32c_intel usb_common battery wmi
[ 71.590746] stress-ng-iomix (639): drop_caches: 3
[ 71.625329] CPU: 1 PID: 192 Comm: jbd2/sda1-8 Not tainted 6.1.54-xenomai-0 #1
[ 71.625336] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[ 71.625339] RIP: 0010:__handle_irq_event_percpu+0x14c/0x180
[ 71.625348] Code: 44 00 00 e9 0d ff ff ff 80 3d 6a de 8e 01 00 75 1b
48 8b 13 44 89 ee 48 c7 c7 08 79 f4 a9 c6 05 54 de 8e 01 01 e8 24 64 f8
ff <0f> 0b fa e9 01 ff ff ff f0 48 0f ba 6b 40 01 0f 82 c5 fe ff ff e9
[ 71.625352] RSP: 0000:ffff98c4000e0f58 EFLAGS: 00010282
[ 71.625356] RAX: 0000000000000000 RBX: ffff88bbc134e380 RCX: 0000000000000000
[ 71.625359] RDX: 0000000000010003 RSI: ffffffffa9f8477e RDI: 00000000ffffffff
[ 71.625362] RBP: 0000000000000001 R08: 0000000000000000 R09: ffff98c4000e0dc0
[ 71.625364] R10: 0000000000000003 R11: ffffffffaa6d1048 R12: 0000000000000000
[ 71.625366] R13: 0000000000000015 R14: ffff88bc352f5800 R15: 0000000000000000
[ 71.625371] FS: 0000000000000000(0000) GS:ffff88bc3dc80000(0000) knlGS:0000000000000000
[ 71.625375] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 71.625377] CR2: 00007f7072a14e80 CR3: 0000000007b7e002 CR4: 00000000000306e0
[ 71.625380] Call Trace:
[ 71.625383] <IRQ>
[ 71.625388] ? __warn+0x7d/0xc0
[ 71.625396] ? __handle_irq_event_percpu+0x14c/0x180
[ 71.625400] ? report_bug+0xe6/0x170
[ 71.625405] ? handle_bug+0x3c/0x70
[ 71.625409] ? exc_invalid_op+0x13/0x60
[ 71.625413] ? asm_exc_invalid_op+0x16/0x20
[ 71.625419] ? __handle_irq_event_percpu+0x14c/0x180
[ 71.625423] ? __handle_irq_event_percpu+0x14c/0x180
[ 71.625426] handle_irq_event+0x34/0x70
[ 71.625430] handle_fasteoi_irq+0x90/0x1e0
[ 71.625435] __common_interrupt+0x66/0x100
[ 71.625440] common_interrupt+0xb4/0xd0
[ 71.625446] </IRQ>
[ 71.625447] <TASK>
[ 71.625449] asm_common_interrupt+0x22/0x40
[ 71.625453] RIP: 0010:_raw_spin_unlock_irqrestore+0x19/0x40
[ 71.625459] Code: 00 00 31 c0 eb f1 66 66 2e 0f 1f 84 00 00 00 00 00
0f 1f 44 00 00 e8 6a 06 00 00 90 f7 c6 00 02 00 00 74 01 fb bf 01 00 00
00 <e8> 82 6d 6f ff 65 8b 05 2b f9 84 56 85 c0 74 05 c3 cc cc cc cc 0f
[ 71.625462] RSP: 0000:ffff98c400607990 EFLAGS: 00010206
[ 71.625466] RAX: 0000000000000001 RBX: 0000000000000000 RCX: ffff88bbc2441828
[ 71.625468] RDX: ffff88bbf6036040 RSI: 0000000000000293 RDI: 0000000000000001
[ 71.625470] RBP: 0000000000000293 R08: 0000000000000001 R09: 00000000749c8fff
[ 71.625472] R10: ffff88bbc18d8000 R11: 0000000000000000 R12: ffff88bbf6034000
[ 71.625474] R13: ffff88bbc18da000 R14: ffff88bbc18d8000 R15: ffff98c400607a88
[ 71.625479] ata_scsi_queuecmd+0x4f/0x80 [libata]
[ 71.625519] scsi_queue_rq+0x2c0/0xbc0 [scsi_mod]
[ 71.625547] blk_mq_dispatch_rq_list+0x211/0x970
[ 71.625554] ? sbitmap_get+0x90/0x1b0
[ 71.625560] blk_mq_do_dispatch_sched+0x324/0x3c0
[ 71.625567] __blk_mq_sched_dispatch_requests+0xec/0x130
[ 71.625573] blk_mq_sched_dispatch_requests+0x30/0x60
[ 71.625577] __blk_mq_run_hw_queue+0x34/0x90
[ 71.625583] blk_mq_sched_insert_requests+0x6b/0x150
[ 71.625588] blk_mq_flush_plug_list.part.0+0x134/0x2d0
[ 71.625593] __blk_flush_plug+0xf1/0x150
[ 71.625597] ? submit_bio_noacct_nocheck+0x32e/0x370
[ 71.625601] ? preempt_count_add+0x6a/0xa0
[ 71.625605] blk_finish_plug+0x25/0x40
[ 71.625610] jbd2_journal_commit_transaction+0x1001/0x1a70 [jbd2]
[ 71.858415] ? _raw_spin_unlock+0x15/0x30
[ 71.861278] ? finish_task_switch.isra.0+0x94/0x2f0
[ 71.864680] kjournald2+0xa9/0x280 [jbd2]
[ 71.867591] ? cpuusage_read+0x10/0x10
[ 71.870292] ? jbd2_fc_wait_bufs+0xa0/0xa0 [jbd2]
[ 71.873481] kthread+0xe9/0x110
[ 71.875779] ? kthread_complete_and_exit+0x20/0x20
[ 71.878792] ret_from_fork+0x22/0x30
[ 71.881232] </TASK>
[ 71.882849] ---[ end trace 0000000000000000 ]---
next reply other threads:[~2023-10-02 12:35 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-10-02 12:34 Florian Bezdeka [this message]
2023-10-03 6:56 ` Dovetail 6.1.54: IRQ handler enables HW irqs Philippe Gerum
2023-10-05 7:05 ` Florian Bezdeka
2023-10-09 9:37 ` Bezdeka, Florian
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1cd875106cdf555e52734462a9d846ffd3549556.camel@siemens.com \
--to=florian.bezdeka@siemens.com \
--cc=jan.kiszka@siemens.com \
--cc=rpm@xenomai.org \
--cc=xenomai@lists.linux.dev \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).