* NMI: IOCK error (debug interrupt?) for reason 71 on CPU 0 @ 2025-09-18 8:27 Uwe Kleine-König 2025-09-18 8:57 ` Uwe Kleine-König 0 siblings, 1 reply; 7+ messages in thread From: Uwe Kleine-König @ 2025-09-18 8:27 UTC (permalink / raw) To: Rafael J. Wysocki Cc: 1111027, Thomas Gleixner, Thorsten Sperber, linux-kernel [-- Attachment #1: Type: text/plain, Size: 1181 bytes --] Control: forwarded 1111027 https://lore.kernel.org/lkml/tfwuhg7fxlvb3iix2k4qqh74dcmwgcipprlehy7zlaz3btmtym@2x2vsccw5yzs Hello Rafael, Thorsten (on Cc:) reported a bug against the 6.12.38 Debian kernel running on an HP Microserver Gen8 after upgrading from an older Debian release (which uses a kernel based on 6.1.y). The problem is that the machine sometimes just hangs, requiring to unplug the PSU to revive it. A key hint seems to me a kernel message: [Fr Sep 5 21:12:34 2025] NMI: IOCK error (debug interrupt?) for reason 71 on CPU 0. (sometimes also "reason 61") that happens just before the hang. See https://bugs.debian.org/1111027 for all the details. I asked Thomas on irc if that rings a bell for him and he forwarded me to you. Do you have an idea for a reason for this message and the corresponding(?) machine hang? The bug reporter up to now was very cooperative for debug measures (e.g. a BIOS update). I would expect him to be open to support you if questions should arise or a patch should be tested. A complication however is that the trigger for the problem is unknown and it takes up to several days to happen. Thanks in advance for your feedback, Uwe [-- Attachment #2: signature.asc --] [-- Type: application/pgp-signature, Size: 488 bytes --] ^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: NMI: IOCK error (debug interrupt?) for reason 71 on CPU 0 2025-09-18 8:27 NMI: IOCK error (debug interrupt?) for reason 71 on CPU 0 Uwe Kleine-König @ 2025-09-18 8:57 ` Uwe Kleine-König 2025-09-22 17:33 ` Thorsten Sperber 0 siblings, 1 reply; 7+ messages in thread From: Uwe Kleine-König @ 2025-09-18 8:57 UTC (permalink / raw) To: Thorsten Sperber Cc: 1111027, Thomas Gleixner, Rafael J. Wysocki, linux-kernel [-- Attachment #1: Type: text/plain, Size: 367 bytes --] Hello Thorsten, after writing the mail to Rafael Thomas provided the idea on irc to test using intel_idle.max_cstate=2 (or =1 or =0) on the kernel command line given that the splat hints at this happening for C3. Can you please add this (with =2) to your bootloader and if the problem happens again, tell us here and reduce the number further? Best regards Uwe [-- Attachment #2: signature.asc --] [-- Type: application/pgp-signature, Size: 488 bytes --] ^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: NMI: IOCK error (debug interrupt?) for reason 71 on CPU 0 2025-09-18 8:57 ` Uwe Kleine-König @ 2025-09-22 17:33 ` Thorsten Sperber 2025-09-23 10:31 ` Thomas Gleixner 0 siblings, 1 reply; 7+ messages in thread From: Thorsten Sperber @ 2025-09-22 17:33 UTC (permalink / raw) To: Uwe Kleine-König Cc: 1111027, Thomas Gleixner, Rafael J. Wysocki, linux-kernel Hi, thanks for your help. It's been four days now, I'd say above average (last was five days) - and no crash yet. I'm going to wait at least until the weekend before naming a winner, but that's already looking pretty good. Just to get things right: the machine stopped crashing fatally - I believe with the addition of intel_iommu=off. It starts flashing red, logs those errors in kernel buffer, but stays running. I'd like to backtrack that later on, maybe after the weekend, removing all params and seeing where things go. Unless you'd like me to test something else before that. Best regards Thorsten On 9/18/25 10:57, Uwe Kleine-König wrote: > Hello Thorsten, > > after writing the mail to Rafael Thomas provided the idea on irc to test > using > > intel_idle.max_cstate=2 > > (or =1 or =0) on the kernel command line given that the splat hints at > this happening for C3. > > Can you please add this (with =2) to your bootloader and if the problem > happens again, tell us here and reduce the number further? > > Best regards > Uwe ^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: NMI: IOCK error (debug interrupt?) for reason 71 on CPU 0 2025-09-22 17:33 ` Thorsten Sperber @ 2025-09-23 10:31 ` Thomas Gleixner 2025-09-24 17:20 ` Thorsten Sperber 0 siblings, 1 reply; 7+ messages in thread From: Thomas Gleixner @ 2025-09-23 10:31 UTC (permalink / raw) To: Thorsten Sperber, Uwe Kleine-König Cc: 1111027, Rafael J. Wysocki, linux-kernel On Mon, Sep 22 2025 at 19:33, Thorsten Sperber wrote: > > thanks for your help. It's been four days now, I'd say above average > (last was five days) - and no crash yet. I'm going to wait at least > until the weekend before naming a winner, but that's already looking > pretty good. Thanks for trying. I suggested to try intel_idle.max_cstate=2 because these unknown NMI backtraces all originated from a MWAIT(C3). Can you reboot into the working 6.1.y kernel at some point and check which idle driver is used there? cat /sys/devices/system/cpu/cpuidle/current_driver and which states are advertised: ls /sys/devices/system/cpu/cpu0/cpuidle/state Thanks, tglx ^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: NMI: IOCK error (debug interrupt?) for reason 71 on CPU 0 2025-09-23 10:31 ` Thomas Gleixner @ 2025-09-24 17:20 ` Thorsten Sperber 2025-09-24 22:10 ` Thomas Gleixner 0 siblings, 1 reply; 7+ messages in thread From: Thorsten Sperber @ 2025-09-24 17:20 UTC (permalink / raw) To: Thomas Gleixner, Uwe Kleine-König Cc: 1111027, Rafael J. Wysocki, linux-kernel Hi again, another stacktrace today (now 19:00:36 up 5 days, 23:04, 2 users, load average: 0,00, 0,00, 0,00): [Mi Sep 24 14:10:19 2025] NMI: IOCK error (debug interrupt?) for reason 61 on CPU 0. [Mi Sep 24 14:10:19 2025] CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.12.43+deb13-amd64 #1 Debian 6.12.43-1 [Mi Sep 24 14:10:19 2025] Hardware name: HP ProLiant MicroServer Gen8, BIOS J06 04/04/2019 [Mi Sep 24 14:10:19 2025] RIP: 0010:intel_idle+0x55/0x90 [Mi Sep 24 14:10:19 2025] Code: 2d 5c 8c 40 00 eb 47 cc cc cc 48 89 f0 0f 1f 00 31 c9 48 89 ca 0f 01 c8 48 8b 06 a8 08 75 0b b9 01 00 00 00 4c 89 c0 0f 01 c9 <f0> 80 66 02 df f0 83 44 24 fc 00 48 8b 06 a8 08 74 0b 65 81 25 a6 [Mi Sep 24 14:10:19 2025] RSP: 0018:ffffffff9d203e38 EFLAGS: 00000046 [Mi Sep 24 14:10:19 2025] RAX: 0000000000000001 RBX: 0000000000000002 RCX: 0000000000000001 [Mi Sep 24 14:10:19 2025] RDX: 0000000000000000 RSI: ffffffff9d210940 RDI: 0000000000000002 [Mi Sep 24 14:10:19 2025] RBP: ffff93c7016400c0 R08: 0000000000000001 R09: 000000000001e83e [Mi Sep 24 14:10:19 2025] R10: ffff93c7016347a4 R11: 071c71c71c71c71c R12: ffffffff9d3b70c0 [Mi Sep 24 14:10:19 2025] R13: ffffffff9d3b71a8 R14: 0000000000000002 R15: 0000000000000000 [Mi Sep 24 14:10:19 2025] FS: 0000000000000000(0000) GS:ffff93c701600000(0000) knlGS:0000000000000000 [Mi Sep 24 14:10:19 2025] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [Mi Sep 24 14:10:19 2025] CR2: 00007fff42aa7f48 CR3: 0000000108fe6003 CR4: 00000000001726f0 [Mi Sep 24 14:10:19 2025] Call Trace: [Mi Sep 24 14:10:19 2025] <TASK> [Mi Sep 24 14:10:19 2025] cpuidle_enter_state+0x81/0x420 [Mi Sep 24 14:10:19 2025] cpuidle_enter+0x2d/0x40 [Mi Sep 24 14:10:19 2025] do_idle+0x1e5/0x240 [Mi Sep 24 14:10:19 2025] cpu_startup_entry+0x29/0x30 [Mi Sep 24 14:10:19 2025] rest_init+0xcc/0xd0 [Mi Sep 24 14:10:19 2025] start_kernel+0x74c/0x750 [Mi Sep 24 14:10:19 2025] x86_64_start_reservations+0x24/0x30 [Mi Sep 24 14:10:19 2025] x86_64_start_kernel+0x95/0xa0 [Mi Sep 24 14:10:19 2025] common_startup_64+0x13e/0x141 [Mi Sep 24 14:10:19 2025] </TASK> [Mi Sep 24 14:10:21 2025] NMI: IOCK error (debug interrupt?) for reason 71 on CPU 0. [Mi Sep 24 14:10:21 2025] CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.12.43+deb13-amd64 #1 Debian 6.12.43-1 [Mi Sep 24 14:10:21 2025] Hardware name: HP ProLiant MicroServer Gen8, BIOS J06 04/04/2019 [Mi Sep 24 14:10:21 2025] RIP: 0010:intel_idle+0x55/0x90 [Mi Sep 24 14:10:21 2025] Code: 2d 5c 8c 40 00 eb 47 cc cc cc 48 89 f0 0f 1f 00 31 c9 48 89 ca 0f 01 c8 48 8b 06 a8 08 75 0b b9 01 00 00 00 4c 89 c0 0f 01 c9 <f0> 80 66 02 df f0 83 44 24 fc 00 48 8b 06 a8 08 74 0b 65 81 25 a6 [Mi Sep 24 14:10:21 2025] RSP: 0018:ffffffff9d203e38 EFLAGS: 00000046 [Mi Sep 24 14:10:21 2025] RAX: 0000000000000001 RBX: 0000000000000002 RCX: 0000000000000001 [Mi Sep 24 14:10:21 2025] RDX: 0000000000000000 RSI: ffffffff9d210940 RDI: 0000000000000002 [Mi Sep 24 14:10:21 2025] RBP: ffff93c7016400c0 R08: 0000000000000001 R09: 000000000001e83e [Mi Sep 24 14:10:21 2025] R10: ffff93c7016347a4 R11: 071c71c71c71c71c R12: ffffffff9d3b70c0 [Mi Sep 24 14:10:21 2025] R13: ffffffff9d3b71a8 R14: 0000000000000002 R15: 0000000000000000 [Mi Sep 24 14:10:21 2025] FS: 0000000000000000(0000) GS:ffff93c701600000(0000) knlGS:0000000000000000 [Mi Sep 24 14:10:21 2025] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [Mi Sep 24 14:10:21 2025] CR2: 00007fff42aa7f48 CR3: 0000000108fe6003 CR4: 00000000001726f0 [Mi Sep 24 14:10:21 2025] Call Trace: [Mi Sep 24 14:10:21 2025] <TASK> [Mi Sep 24 14:10:21 2025] cpuidle_enter_state+0x81/0x420 [Mi Sep 24 14:10:21 2025] cpuidle_enter+0x2d/0x40 [Mi Sep 24 14:10:21 2025] do_idle+0x1e5/0x240 [Mi Sep 24 14:10:21 2025] cpu_startup_entry+0x29/0x30 [Mi Sep 24 14:10:21 2025] rest_init+0xcc/0xd0 [Mi Sep 24 14:10:21 2025] start_kernel+0x74c/0x750 [Mi Sep 24 14:10:21 2025] x86_64_start_reservations+0x24/0x30 [Mi Sep 24 14:10:21 2025] x86_64_start_kernel+0x95/0xa0 [Mi Sep 24 14:10:21 2025] common_startup_64+0x13e/0x141 [Mi Sep 24 14:10:21 2025] </TASK> [Mi Sep 24 14:10:23 2025] NMI: IOCK error (debug interrupt?) for reason 61 on CPU 0. [Mi Sep 24 14:10:23 2025] CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.12.43+deb13-amd64 #1 Debian 6.12.43-1 [Mi Sep 24 14:10:23 2025] Hardware name: HP ProLiant MicroServer Gen8, BIOS J06 04/04/2019 [Mi Sep 24 14:10:23 2025] RIP: 0010:intel_idle+0x55/0x90 [Mi Sep 24 14:10:23 2025] Code: 2d 5c 8c 40 00 eb 47 cc cc cc 48 89 f0 0f 1f 00 31 c9 48 89 ca 0f 01 c8 48 8b 06 a8 08 75 0b b9 01 00 00 00 4c 89 c0 0f 01 c9 <f0> 80 66 02 df f0 83 44 24 fc 00 48 8b 06 a8 08 74 0b 65 81 25 a6 [Mi Sep 24 14:10:23 2025] RSP: 0018:ffffffff9d203e38 EFLAGS: 00000046 [Mi Sep 24 14:10:23 2025] RAX: 0000000000000001 RBX: 0000000000000002 RCX: 0000000000000001 [Mi Sep 24 14:10:23 2025] RDX: 0000000000000000 RSI: ffffffff9d210940 RDI: 0000000000000002 [Mi Sep 24 14:10:23 2025] RBP: ffff93c7016400c0 R08: 0000000000000001 R09: 000000000001e83e [Mi Sep 24 14:10:23 2025] R10: ffff93c7016347a4 R11: 071c71c71c71c71c R12: ffffffff9d3b70c0 [Mi Sep 24 14:10:23 2025] R13: ffffffff9d3b71a8 R14: 0000000000000002 R15: 0000000000000000 [Mi Sep 24 14:10:23 2025] FS: 0000000000000000(0000) GS:ffff93c701600000(0000) knlGS:0000000000000000 [Mi Sep 24 14:10:23 2025] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [Mi Sep 24 14:10:23 2025] CR2: 00007fff42aa7f48 CR3: 0000000108fe6003 CR4: 00000000001726f0 [Mi Sep 24 14:10:23 2025] Call Trace: [Mi Sep 24 14:10:23 2025] <TASK> [Mi Sep 24 14:10:23 2025] cpuidle_enter_state+0x81/0x420 [Mi Sep 24 14:10:23 2025] cpuidle_enter+0x2d/0x40 [Mi Sep 24 14:10:23 2025] do_idle+0x1e5/0x240 [Mi Sep 24 14:10:23 2025] cpu_startup_entry+0x29/0x30 [Mi Sep 24 14:10:23 2025] rest_init+0xcc/0xd0 [Mi Sep 24 14:10:23 2025] start_kernel+0x74c/0x750 [Mi Sep 24 14:10:23 2025] x86_64_start_reservations+0x24/0x30 [Mi Sep 24 14:10:23 2025] x86_64_start_kernel+0x95/0xa0 [Mi Sep 24 14:10:23 2025] common_startup_64+0x13e/0x141 [Mi Sep 24 14:10:23 2025] </TASK> [Mi Sep 24 14:10:25 2025] NMI: IOCK error (debug interrupt?) for reason 71 on CPU 0. [Mi Sep 24 14:10:25 2025] CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.12.43+deb13-amd64 #1 Debian 6.12.43-1 [Mi Sep 24 14:10:25 2025] Hardware name: HP ProLiant MicroServer Gen8, BIOS J06 04/04/2019 [Mi Sep 24 14:10:25 2025] RIP: 0010:intel_idle+0x55/0x90 [Mi Sep 24 14:10:25 2025] Code: 2d 5c 8c 40 00 eb 47 cc cc cc 48 89 f0 0f 1f 00 31 c9 48 89 ca 0f 01 c8 48 8b 06 a8 08 75 0b b9 01 00 00 00 4c 89 c0 0f 01 c9 <f0> 80 66 02 df f0 83 44 24 fc 00 48 8b 06 a8 08 74 0b 65 81 25 a6 [Mi Sep 24 14:10:25 2025] RSP: 0018:ffffffff9d203e38 EFLAGS: 00000046 [Mi Sep 24 14:10:25 2025] RAX: 0000000000000001 RBX: 0000000000000002 RCX: 0000000000000001 [Mi Sep 24 14:10:25 2025] RDX: 0000000000000000 RSI: ffffffff9d210940 RDI: 0000000000000002 [Mi Sep 24 14:10:25 2025] RBP: ffff93c7016400c0 R08: 0000000000000001 R09: 000000000001e83e [Mi Sep 24 14:10:25 2025] R10: ffff93c7016347a4 R11: 071c71c71c71c71c R12: ffffffff9d3b70c0 [Mi Sep 24 14:10:25 2025] R13: ffffffff9d3b71a8 R14: 0000000000000002 R15: 0000000000000000 [Mi Sep 24 14:10:25 2025] FS: 0000000000000000(0000) GS:ffff93c701600000(0000) knlGS:0000000000000000 [Mi Sep 24 14:10:25 2025] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [Mi Sep 24 14:10:25 2025] CR2: 00007fff42aa7f48 CR3: 0000000108fe6003 CR4: 00000000001726f0 [Mi Sep 24 14:10:25 2025] Call Trace: [Mi Sep 24 14:10:25 2025] <TASK> [Mi Sep 24 14:10:25 2025] cpuidle_enter_state+0x81/0x420 [Mi Sep 24 14:10:25 2025] cpuidle_enter+0x2d/0x40 [Mi Sep 24 14:10:25 2025] do_idle+0x1e5/0x240 [Mi Sep 24 14:10:25 2025] cpu_startup_entry+0x29/0x30 [Mi Sep 24 14:10:25 2025] rest_init+0xcc/0xd0 [Mi Sep 24 14:10:25 2025] start_kernel+0x74c/0x750 [Mi Sep 24 14:10:25 2025] x86_64_start_reservations+0x24/0x30 [Mi Sep 24 14:10:25 2025] x86_64_start_kernel+0x95/0xa0 [Mi Sep 24 14:10:25 2025] common_startup_64+0x13e/0x141 [Mi Sep 24 14:10:25 2025] </TASK> [Mi Sep 24 14:10:27 2025] NMI: IOCK error (debug interrupt?) for reason 71 on CPU 0. [Mi Sep 24 14:10:27 2025] CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.12.43+deb13-amd64 #1 Debian 6.12.43-1 [Mi Sep 24 14:10:27 2025] Hardware name: HP ProLiant MicroServer Gen8, BIOS J06 04/04/2019 [Mi Sep 24 14:10:27 2025] RIP: 0010:intel_idle+0x55/0x90 [Mi Sep 24 14:10:27 2025] Code: 2d 5c 8c 40 00 eb 47 cc cc cc 48 89 f0 0f 1f 00 31 c9 48 89 ca 0f 01 c8 48 8b 06 a8 08 75 0b b9 01 00 00 00 4c 89 c0 0f 01 c9 <f0> 80 66 02 df f0 83 44 24 fc 00 48 8b 06 a8 08 74 0b 65 81 25 a6 [Mi Sep 24 14:10:27 2025] RSP: 0018:ffffffff9d203e38 EFLAGS: 00000046 [Mi Sep 24 14:10:27 2025] RAX: 0000000000000001 RBX: 0000000000000002 RCX: 0000000000000001 [Mi Sep 24 14:10:27 2025] RDX: 0000000000000000 RSI: ffffffff9d210940 RDI: 0000000000000002 [Mi Sep 24 14:10:27 2025] RBP: ffff93c7016400c0 R08: 0000000000000001 R09: 000000000001e83e [Mi Sep 24 14:10:27 2025] R10: ffff93c7016347a4 R11: 071c71c71c71c71c R12: ffffffff9d3b70c0 [Mi Sep 24 14:10:27 2025] R13: ffffffff9d3b71a8 R14: 0000000000000002 R15: 0000000000000000 [Mi Sep 24 14:10:27 2025] FS: 0000000000000000(0000) GS:ffff93c701600000(0000) knlGS:0000000000000000 [Mi Sep 24 14:10:27 2025] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [Mi Sep 24 14:10:27 2025] CR2: 00007fff42aa7f48 CR3: 0000000108fe6003 CR4: 00000000001726f0 [Mi Sep 24 14:10:27 2025] Call Trace: [Mi Sep 24 14:10:27 2025] <TASK> [Mi Sep 24 14:10:27 2025] cpuidle_enter_state+0x81/0x420 [Mi Sep 24 14:10:27 2025] cpuidle_enter+0x2d/0x40 [Mi Sep 24 14:10:27 2025] do_idle+0x1e5/0x240 [Mi Sep 24 14:10:27 2025] cpu_startup_entry+0x29/0x30 [Mi Sep 24 14:10:27 2025] rest_init+0xcc/0xd0 [Mi Sep 24 14:10:27 2025] start_kernel+0x74c/0x750 [Mi Sep 24 14:10:27 2025] x86_64_start_reservations+0x24/0x30 [Mi Sep 24 14:10:27 2025] x86_64_start_kernel+0x95/0xa0 [Mi Sep 24 14:10:27 2025] common_startup_64+0x13e/0x141 [Mi Sep 24 14:10:27 2025] </TASK> [Mi Sep 24 14:10:29 2025] NMI: IOCK error (debug interrupt?) for reason 71 on CPU 0. [Mi Sep 24 14:10:29 2025] CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.12.43+deb13-amd64 #1 Debian 6.12.43-1 [Mi Sep 24 14:10:29 2025] Hardware name: HP ProLiant MicroServer Gen8, BIOS J06 04/04/2019 [Mi Sep 24 14:10:29 2025] RIP: 0010:intel_idle+0x55/0x90 [Mi Sep 24 14:10:29 2025] Code: 2d 5c 8c 40 00 eb 47 cc cc cc 48 89 f0 0f 1f 00 31 c9 48 89 ca 0f 01 c8 48 8b 06 a8 08 75 0b b9 01 00 00 00 4c 89 c0 0f 01 c9 <f0> 80 66 02 df f0 83 44 24 fc 00 48 8b 06 a8 08 74 0b 65 81 25 a6 [Mi Sep 24 14:10:29 2025] RSP: 0018:ffffffff9d203e38 EFLAGS: 00000046 [Mi Sep 24 14:10:29 2025] RAX: 0000000000000001 RBX: 0000000000000002 RCX: 0000000000000001 [Mi Sep 24 14:10:29 2025] RDX: 0000000000000000 RSI: ffffffff9d210940 RDI: 0000000000000002 [Mi Sep 24 14:10:29 2025] RBP: ffff93c7016400c0 R08: 0000000000000001 R09: 000000000001e83e [Mi Sep 24 14:10:29 2025] R10: ffff93c7016347a4 R11: 071c71c71c71c71c R12: ffffffff9d3b70c0 [Mi Sep 24 14:10:29 2025] R13: ffffffff9d3b71a8 R14: 0000000000000002 R15: 0000000000000000 [Mi Sep 24 14:10:29 2025] FS: 0000000000000000(0000) GS:ffff93c701600000(0000) knlGS:0000000000000000 [Mi Sep 24 14:10:29 2025] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [Mi Sep 24 14:10:29 2025] CR2: 00007fff42aa7f48 CR3: 0000000108fe6003 CR4: 00000000001726f0 [Mi Sep 24 14:10:29 2025] Call Trace: [Mi Sep 24 14:10:29 2025] <TASK> [Mi Sep 24 14:10:29 2025] cpuidle_enter_state+0x81/0x420 [Mi Sep 24 14:10:29 2025] cpuidle_enter+0x2d/0x40 [Mi Sep 24 14:10:29 2025] do_idle+0x1e5/0x240 [Mi Sep 24 14:10:29 2025] cpu_startup_entry+0x29/0x30 [Mi Sep 24 14:10:29 2025] rest_init+0xcc/0xd0 [Mi Sep 24 14:10:29 2025] start_kernel+0x74c/0x750 [Mi Sep 24 14:10:29 2025] x86_64_start_reservations+0x24/0x30 [Mi Sep 24 14:10:29 2025] x86_64_start_kernel+0x95/0xa0 [Mi Sep 24 14:10:29 2025] common_startup_64+0x13e/0x141 [Mi Sep 24 14:10:29 2025] </TASK> [Mi Sep 24 14:10:31 2025] clocksource: Long readout interval, skipping watchdog check: cs_nsec: 11520027553 wd_nsec: 11520025207 # cat /proc/cmdline BOOT_IMAGE=/vmlinuz-6.12.43+deb13-amd64 root=/dev/mapper/thecube--vg-root ro quiet intel_iommu=off intel_idle.max_cstate=2 Rebooting into 6.1. gave me: # uname -a Linux thecube 6.1.0-40-amd64 #1 SMP PREEMPT_DYNAMIC Debian 6.1.153-1 (2025-09-20) x86_64 GNU/Linux # cat /proc/cmdline BOOT_IMAGE=/vmlinuz-6.1.0-40-amd64 root=/dev/mapper/thecube--vg-root ro quiet intel_iommu=off intel_idle.max_cstate=2 # cat /sys/devices/system/cpu/cpuidle/current_driver intel_idle # ls -l /sys/devices/system/cpu/cpu0/cpuidle/ insgesamt 0 drwxr-xr-x 2 root root 0 24. Sep 19:14 state0 drwxr-xr-x 3 root root 0 24. Sep 19:14 state1 drwxr-xr-x 3 root root 0 24. Sep 19:14 state2 # cat /sys/devices/system/cpu/cpu0/cpuidle/state*/name POLL C1 C1E Will now remove intel_iommu=off and see if that actually stops the machine when crashing again. Best regards, Thorsten PS: @Uwe, gmail won't tolerate my mailserver, sorry :( On 9/23/25 12:31, Thomas Gleixner wrote: > On Mon, Sep 22 2025 at 19:33, Thorsten Sperber wrote: >> thanks for your help. It's been four days now, I'd say above average >> (last was five days) - and no crash yet. I'm going to wait at least >> until the weekend before naming a winner, but that's already looking >> pretty good. > Thanks for trying. > > I suggested to try intel_idle.max_cstate=2 because these unknown NMI > backtraces all originated from a MWAIT(C3). > > Can you reboot into the working 6.1.y kernel at some point and check > which idle driver is used there? > > cat /sys/devices/system/cpu/cpuidle/current_driver > > and which states are advertised: > > ls /sys/devices/system/cpu/cpu0/cpuidle/state > > Thanks, > > tglx > ^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: NMI: IOCK error (debug interrupt?) for reason 71 on CPU 0 2025-09-24 17:20 ` Thorsten Sperber @ 2025-09-24 22:10 ` Thomas Gleixner 2025-09-25 15:27 ` Thorsten Sperber 0 siblings, 1 reply; 7+ messages in thread From: Thomas Gleixner @ 2025-09-24 22:10 UTC (permalink / raw) To: Thorsten Sperber, Uwe Kleine-König Cc: 1111027, Rafael J. Wysocki, linux-kernel On Wed, Sep 24 2025 at 19:20, Thorsten Sperber wrote: > [Mi Sep 24 14:10:21 2025] NMI: IOCK error (debug interrupt?) for reason 71 on CPU 0. > [Mi Sep 24 14:10:21 2025] CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.12.43+deb13-amd64 #1 Debian 6.12.43-1 > [Mi Sep 24 14:10:21 2025] Hardware name: HP ProLiant MicroServer Gen8, BIOS J06 04/04/2019 > [Mi Sep 24 14:10:21 2025] RIP: 0010:intel_idle+0x55/0x90 > [Mi Sep 24 14:10:21 2025] Code: 2d 5c 8c 40 00 eb 47 cc cc cc 48 89 f0 0f 1f 00 31 c9 48 89 ca 0f 01 c8 48 8b 06 a8 08 75 0b b9 01 00 00 00 4c 89 c0 0f 01 c9 <f0> 80 66 02 df f0 83 44 24 fc 00 48 8b 06 a8 08 74 0b 65 81 25 a6 > [Mi Sep 24 14:10:21 2025] RSP: 0018:ffffffff9d203e38 EFLAGS: 00000046 > [Mi Sep 24 14:10:21 2025] RAX: 0000000000000001 RBX: 0000000000000002 RCX: 0000000000000001 That's a MWAIT(C1 Substate 1). Hmmm... > # cat /proc/cmdline > BOOT_IMAGE=/vmlinuz-6.1.0-40-amd64 root=/dev/mapper/thecube--vg-root ro quiet intel_iommu=off intel_idle.max_cstate=2 > > # cat /sys/devices/system/cpu/cpuidle/current_driver > intel_idle > > # ls -l /sys/devices/system/cpu/cpu0/cpuidle/ > insgesamt 0 > drwxr-xr-x 2 root root 0 24. Sep 19:14 state0 > drwxr-xr-x 3 root root 0 24. Sep 19:14 state1 > drwxr-xr-x 3 root root 0 24. Sep 19:14 state2 > > # cat /sys/devices/system/cpu/cpu0/cpuidle/state*/name > POLL > C1 > C1E What's the output for the above on 6.12? ^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: NMI: IOCK error (debug interrupt?) for reason 71 on CPU 0 2025-09-24 22:10 ` Thomas Gleixner @ 2025-09-25 15:27 ` Thorsten Sperber 0 siblings, 0 replies; 7+ messages in thread From: Thorsten Sperber @ 2025-09-25 15:27 UTC (permalink / raw) To: Thomas Gleixner, Uwe Kleine-König Cc: 1111027, Rafael J. Wysocki, linux-kernel On 9/25/25 00:10, Thomas Gleixner wrote: >> # cat /proc/cmdline >> BOOT_IMAGE=/vmlinuz-6.1.0-40-amd64 root=/dev/mapper/thecube--vg-root ro quiet intel_iommu=off intel_idle.max_cstate=2 >> >> # cat /sys/devices/system/cpu/cpuidle/current_driver >> intel_idle >> >> # ls -l /sys/devices/system/cpu/cpu0/cpuidle/ >> insgesamt 0 >> drwxr-xr-x 2 root root 0 24. Sep 19:14 state0 >> drwxr-xr-x 3 root root 0 24. Sep 19:14 state1 >> drwxr-xr-x 3 root root 0 24. Sep 19:14 state2 >> >> # cat /sys/devices/system/cpu/cpu0/cpuidle/state*/name >> POLL >> C1 >> C1E > What's the output for the above on 6.12? > All the same (apart from the cmdline of course). Btw, error appeared in the morning (without intel_iommu=off), still without halting/crashing the system. Bugs me a little that I can't exactly reproduce the "crash to coldstart" situation again. Just in case someone sees something new: # cat /proc/cmdline BOOT_IMAGE=/vmlinuz-6.12.43+deb13-amd64 root=/dev/mapper/thecube--vg-root ro quiet intel_idle.max_cstate=2 [Do Sep 25 07:15:50 2025] NMI: IOCK error (debug interrupt?) for reason 61 on CPU 0. [Do Sep 25 07:15:50 2025] CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.12.43+deb13-amd64 #1 Debian 6.12.43-1 [Do Sep 25 07:15:50 2025] Hardware name: HP ProLiant MicroServer Gen8, BIOS J06 04/04/2019 [Do Sep 25 07:15:50 2025] RIP: 0010:intel_idle+0x55/0x90 [Do Sep 25 07:15:50 2025] Code: 2d 5c 8c 40 00 eb 47 cc cc cc 48 89 f0 0f 1f 00 31 c9 48 89 ca 0f 01 c8 48 8b 06 a8 08 75 0b b9 01 00 00 00 4c 89 c0 0f 01 c9 <f0> 80 66 02 df f0 83 44 24 fc 00 48 8b 06 a8 08 74 0b 65 81 25 a6 [Do Sep 25 07:15:50 2025] RSP: 0018:ffffffff97203e38 EFLAGS: 00000046 [Do Sep 25 07:15:50 2025] RAX: 0000000000000001 RBX: 0000000000000002 RCX: 0000000000000001 [Do Sep 25 07:15:50 2025] RDX: 0000000000000000 RSI: ffffffff97210940 RDI: 0000000000000002 [Do Sep 25 07:15:50 2025] RBP: ffff9a5b416400c0 R08: 0000000000000001 R09: 000000000001e83e [Do Sep 25 07:15:50 2025] R10: ffff9a5b416347a4 R11: 071c71c71c71c71c R12: ffffffff973b70c0 [Do Sep 25 07:15:50 2025] R13: ffffffff973b71a8 R14: 0000000000000002 R15: 0000000000000000 [Do Sep 25 07:15:50 2025] FS: 0000000000000000(0000) GS:ffff9a5b41600000(0000) knlGS:0000000000000000 [Do Sep 25 07:15:50 2025] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [Do Sep 25 07:15:50 2025] CR2: 00007ffe16efe098 CR3: 0000000103a60005 CR4: 00000000001726f0 [Do Sep 25 07:15:50 2025] Call Trace: [Do Sep 25 07:15:50 2025] <TASK> [Do Sep 25 07:15:50 2025] cpuidle_enter_state+0x81/0x420 [Do Sep 25 07:15:50 2025] cpuidle_enter+0x2d/0x40 [Do Sep 25 07:15:50 2025] do_idle+0x1e5/0x240 [Do Sep 25 07:15:50 2025] cpu_startup_entry+0x29/0x30 [Do Sep 25 07:15:50 2025] rest_init+0xcc/0xd0 [Do Sep 25 07:15:50 2025] start_kernel+0x74c/0x750 [Do Sep 25 07:15:50 2025] x86_64_start_reservations+0x24/0x30 [Do Sep 25 07:15:50 2025] x86_64_start_kernel+0x95/0xa0 [Do Sep 25 07:15:50 2025] common_startup_64+0x13e/0x141 [Do Sep 25 07:15:50 2025] </TASK> [Do Sep 25 07:15:52 2025] NMI: IOCK error (debug interrupt?) for reason 61 on CPU 0. [Do Sep 25 07:15:52 2025] CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.12.43+deb13-amd64 #1 Debian 6.12.43-1 [Do Sep 25 07:15:52 2025] Hardware name: HP ProLiant MicroServer Gen8, BIOS J06 04/04/2019 [Do Sep 25 07:15:52 2025] RIP: 0010:intel_idle+0x55/0x90 [Do Sep 25 07:15:52 2025] Code: 2d 5c 8c 40 00 eb 47 cc cc cc 48 89 f0 0f 1f 00 31 c9 48 89 ca 0f 01 c8 48 8b 06 a8 08 75 0b b9 01 00 00 00 4c 89 c0 0f 01 c9 <f0> 80 66 02 df f0 83 44 24 fc 00 48 8b 06 a8 08 74 0b 65 81 25 a6 [Do Sep 25 07:15:52 2025] RSP: 0018:ffffffff97203e38 EFLAGS: 00000046 [Do Sep 25 07:15:52 2025] RAX: 0000000000000001 RBX: 0000000000000002 RCX: 0000000000000001 [Do Sep 25 07:15:52 2025] RDX: 0000000000000000 RSI: ffffffff97210940 RDI: 0000000000000002 [Do Sep 25 07:15:52 2025] RBP: ffff9a5b416400c0 R08: 0000000000000001 R09: 000000000001e83e [Do Sep 25 07:15:52 2025] R10: ffff9a5b416347a4 R11: 071c71c71c71c71c R12: ffffffff973b70c0 [Do Sep 25 07:15:52 2025] R13: ffffffff973b71a8 R14: 0000000000000002 R15: 0000000000000000 [Do Sep 25 07:15:52 2025] FS: 0000000000000000(0000) GS:ffff9a5b41600000(0000) knlGS:0000000000000000 [Do Sep 25 07:15:52 2025] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [Do Sep 25 07:15:52 2025] CR2: 00007ffe16efe098 CR3: 0000000103a60005 CR4: 00000000001726f0 [Do Sep 25 07:15:52 2025] Call Trace: [Do Sep 25 07:15:52 2025] <TASK> [Do Sep 25 07:15:52 2025] cpuidle_enter_state+0x81/0x420 [Do Sep 25 07:15:52 2025] cpuidle_enter+0x2d/0x40 [Do Sep 25 07:15:52 2025] do_idle+0x1e5/0x240 [Do Sep 25 07:15:52 2025] cpu_startup_entry+0x29/0x30 [Do Sep 25 07:15:52 2025] rest_init+0xcc/0xd0 [Do Sep 25 07:15:52 2025] start_kernel+0x74c/0x750 [Do Sep 25 07:15:52 2025] x86_64_start_reservations+0x24/0x30 [Do Sep 25 07:15:52 2025] x86_64_start_kernel+0x95/0xa0 [Do Sep 25 07:15:52 2025] common_startup_64+0x13e/0x141 [Do Sep 25 07:15:52 2025] </TASK> [Do Sep 25 07:15:54 2025] NMI: IOCK error (debug interrupt?) for reason 61 on CPU 0. [Do Sep 25 07:15:54 2025] CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.12.43+deb13-amd64 #1 Debian 6.12.43-1 [Do Sep 25 07:15:54 2025] Hardware name: HP ProLiant MicroServer Gen8, BIOS J06 04/04/2019 [Do Sep 25 07:15:54 2025] RIP: 0010:intel_idle+0x55/0x90 [Do Sep 25 07:15:54 2025] Code: 2d 5c 8c 40 00 eb 47 cc cc cc 48 89 f0 0f 1f 00 31 c9 48 89 ca 0f 01 c8 48 8b 06 a8 08 75 0b b9 01 00 00 00 4c 89 c0 0f 01 c9 <f0> 80 66 02 df f0 83 44 24 fc 00 48 8b 06 a8 08 74 0b 65 81 25 a6 [Do Sep 25 07:15:54 2025] RSP: 0018:ffffffff97203e38 EFLAGS: 00000046 [Do Sep 25 07:15:54 2025] RAX: 0000000000000001 RBX: 0000000000000002 RCX: 0000000000000001 [Do Sep 25 07:15:54 2025] RDX: 0000000000000000 RSI: ffffffff97210940 RDI: 0000000000000002 [Do Sep 25 07:15:54 2025] RBP: ffff9a5b416400c0 R08: 0000000000000001 R09: 000000000001e83e [Do Sep 25 07:15:54 2025] R10: ffff9a5b416347a4 R11: 071c71c71c71c71c R12: ffffffff973b70c0 [Do Sep 25 07:15:54 2025] R13: ffffffff973b71a8 R14: 0000000000000002 R15: 0000000000000000 [Do Sep 25 07:15:54 2025] FS: 0000000000000000(0000) GS:ffff9a5b41600000(0000) knlGS:0000000000000000 [Do Sep 25 07:15:54 2025] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [Do Sep 25 07:15:54 2025] CR2: 00007ffe16efe098 CR3: 0000000103a60005 CR4: 00000000001726f0 [Do Sep 25 07:15:54 2025] Call Trace: [Do Sep 25 07:15:54 2025] <TASK> [Do Sep 25 07:15:54 2025] cpuidle_enter_state+0x81/0x420 [Do Sep 25 07:15:54 2025] cpuidle_enter+0x2d/0x40 [Do Sep 25 07:15:54 2025] do_idle+0x1e5/0x240 [Do Sep 25 07:15:54 2025] cpu_startup_entry+0x29/0x30 [Do Sep 25 07:15:54 2025] rest_init+0xcc/0xd0 [Do Sep 25 07:15:54 2025] start_kernel+0x74c/0x750 [Do Sep 25 07:15:54 2025] x86_64_start_reservations+0x24/0x30 [Do Sep 25 07:15:54 2025] x86_64_start_kernel+0x95/0xa0 [Do Sep 25 07:15:54 2025] common_startup_64+0x13e/0x141 [Do Sep 25 07:15:54 2025] </TASK> [Do Sep 25 07:15:56 2025] NMI: IOCK error (debug interrupt?) for reason 71 on CPU 0. [Do Sep 25 07:15:56 2025] CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.12.43+deb13-amd64 #1 Debian 6.12.43-1 [Do Sep 25 07:15:56 2025] Hardware name: HP ProLiant MicroServer Gen8, BIOS J06 04/04/2019 [Do Sep 25 07:15:56 2025] RIP: 0010:intel_idle+0x55/0x90 [Do Sep 25 07:15:56 2025] Code: 2d 5c 8c 40 00 eb 47 cc cc cc 48 89 f0 0f 1f 00 31 c9 48 89 ca 0f 01 c8 48 8b 06 a8 08 75 0b b9 01 00 00 00 4c 89 c0 0f 01 c9 <f0> 80 66 02 df f0 83 44 24 fc 00 48 8b 06 a8 08 74 0b 65 81 25 a6 [Do Sep 25 07:15:56 2025] RSP: 0018:ffffffff97203e38 EFLAGS: 00000046 [Do Sep 25 07:15:56 2025] RAX: 0000000000000001 RBX: 0000000000000002 RCX: 0000000000000001 [Do Sep 25 07:15:56 2025] RDX: 0000000000000000 RSI: ffffffff97210940 RDI: 0000000000000002 [Do Sep 25 07:15:56 2025] RBP: ffff9a5b416400c0 R08: 0000000000000001 R09: 000000000001e83e [Do Sep 25 07:15:56 2025] R10: ffff9a5b416347a4 R11: 071c71c71c71c71c R12: ffffffff973b70c0 [Do Sep 25 07:15:56 2025] R13: ffffffff973b71a8 R14: 0000000000000002 R15: 0000000000000000 [Do Sep 25 07:15:56 2025] FS: 0000000000000000(0000) GS:ffff9a5b41600000(0000) knlGS:0000000000000000 [Do Sep 25 07:15:56 2025] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [Do Sep 25 07:15:56 2025] CR2: 00007ffe16efe098 CR3: 0000000103a60005 CR4: 00000000001726f0 [Do Sep 25 07:15:56 2025] Call Trace: [Do Sep 25 07:15:56 2025] <TASK> [Do Sep 25 07:15:56 2025] cpuidle_enter_state+0x81/0x420 [Do Sep 25 07:15:56 2025] cpuidle_enter+0x2d/0x40 [Do Sep 25 07:15:56 2025] do_idle+0x1e5/0x240 [Do Sep 25 07:15:56 2025] cpu_startup_entry+0x29/0x30 [Do Sep 25 07:15:56 2025] rest_init+0xcc/0xd0 [Do Sep 25 07:15:56 2025] start_kernel+0x74c/0x750 [Do Sep 25 07:15:56 2025] x86_64_start_reservations+0x24/0x30 [Do Sep 25 07:15:56 2025] x86_64_start_kernel+0x95/0xa0 [Do Sep 25 07:15:56 2025] common_startup_64+0x13e/0x141 [Do Sep 25 07:15:56 2025] </TASK> [Do Sep 25 07:15:58 2025] NMI: IOCK error (debug interrupt?) for reason 71 on CPU 0. [Do Sep 25 07:15:58 2025] CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.12.43+deb13-amd64 #1 Debian 6.12.43-1 [Do Sep 25 07:15:58 2025] Hardware name: HP ProLiant MicroServer Gen8, BIOS J06 04/04/2019 [Do Sep 25 07:15:58 2025] RIP: 0010:intel_idle+0x55/0x90 [Do Sep 25 07:15:58 2025] Code: 2d 5c 8c 40 00 eb 47 cc cc cc 48 89 f0 0f 1f 00 31 c9 48 89 ca 0f 01 c8 48 8b 06 a8 08 75 0b b9 01 00 00 00 4c 89 c0 0f 01 c9 <f0> 80 66 02 df f0 83 44 24 fc 00 48 8b 06 a8 08 74 0b 65 81 25 a6 [Do Sep 25 07:15:58 2025] RSP: 0018:ffffffff97203e38 EFLAGS: 00000046 [Do Sep 25 07:15:58 2025] RAX: 0000000000000001 RBX: 0000000000000002 RCX: 0000000000000001 [Do Sep 25 07:15:58 2025] RDX: 0000000000000000 RSI: ffffffff97210940 RDI: 0000000000000002 [Do Sep 25 07:15:58 2025] RBP: ffff9a5b416400c0 R08: 0000000000000001 R09: 000000000001e83e [Do Sep 25 07:15:58 2025] R10: ffff9a5b416347a4 R11: 071c71c71c71c71c R12: ffffffff973b70c0 [Do Sep 25 07:15:58 2025] R13: ffffffff973b71a8 R14: 0000000000000002 R15: 0000000000000000 [Do Sep 25 07:15:58 2025] FS: 0000000000000000(0000) GS:ffff9a5b41600000(0000) knlGS:0000000000000000 [Do Sep 25 07:15:58 2025] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [Do Sep 25 07:15:58 2025] CR2: 00007ffe16efe098 CR3: 0000000103a60005 CR4: 00000000001726f0 [Do Sep 25 07:15:58 2025] Call Trace: [Do Sep 25 07:15:58 2025] <TASK> [Do Sep 25 07:15:58 2025] cpuidle_enter_state+0x81/0x420 [Do Sep 25 07:15:58 2025] cpuidle_enter+0x2d/0x40 [Do Sep 25 07:15:58 2025] do_idle+0x1e5/0x240 [Do Sep 25 07:15:58 2025] cpu_startup_entry+0x29/0x30 [Do Sep 25 07:15:58 2025] rest_init+0xcc/0xd0 [Do Sep 25 07:15:58 2025] start_kernel+0x74c/0x750 [Do Sep 25 07:15:58 2025] x86_64_start_reservations+0x24/0x30 [Do Sep 25 07:15:58 2025] x86_64_start_kernel+0x95/0xa0 [Do Sep 25 07:15:58 2025] common_startup_64+0x13e/0x141 [Do Sep 25 07:15:58 2025] </TASK> [Do Sep 25 07:16:00 2025] clocksource: Long readout interval, skipping watchdog check: cs_nsec: 7623994708 wd_nsec: 7623993107 Guess I'll remove all customization next. Best regards, Thorsten ^ permalink raw reply [flat|nested] 7+ messages in thread
end of thread, other threads:[~2025-09-25 15:27 UTC | newest] Thread overview: 7+ messages (download: mbox.gz follow: Atom feed -- links below jump to the message on this page -- 2025-09-18 8:27 NMI: IOCK error (debug interrupt?) for reason 71 on CPU 0 Uwe Kleine-König 2025-09-18 8:57 ` Uwe Kleine-König 2025-09-22 17:33 ` Thorsten Sperber 2025-09-23 10:31 ` Thomas Gleixner 2025-09-24 17:20 ` Thorsten Sperber 2025-09-24 22:10 ` Thomas Gleixner 2025-09-25 15:27 ` Thorsten Sperber
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.