linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* WARNING: CPU: 112 PID: 2041 at kernel/sched/sched.h:1453
@ 2021-07-28 13:11 Bruno Goncalves
  2021-07-28 15:55 ` Dietmar Eggemann
  0 siblings, 1 reply; 7+ messages in thread
From: Bruno Goncalves @ 2021-07-28 13:11 UTC (permalink / raw)
  To: CKI Project, linux-kernel; +Cc: nathan, Memory Management

Hello,

Since this commit (Commit: 45312bd762d3 - Merge tag 'zonefs-5.14-rc2')
we started to see the following call trace, it seems to be
reproducible only on aarch64.

[  384.485614] ------------[ cut here ]------------
[  384.490227] rq->clock_update_flags < RQCF_ACT_SKIP
[  384.490232] WARNING: CPU: 112 PID: 2041 at
kernel/sched/sched.h:1453 sub_running_bw.isra.0+0x190/0x1a0
[  384.504312] Modules linked in: mlx5_ib ib_uverbs ib_core rfkill
sunrpc acpi_ipmi ipmi_ssif mlx5_core mlxfw psample ipmi_devintf
arm_cmn ipmi_msghandler arm_dsu_pmu cppc_cpufreq acpi_tad vfat fat
fuse zram ip_tables x_tables xfs crct10dif_ce ghash_ce ast
i2c_algo_bit drm_vram_helper sbsa_gwdt drm_kms_helper syscopyarea
sysfillrect sysimgblt fb_sys_fops cec drm_ttm_helper ttm nvme
nvme_core drm xgene_hwmon aes_neon_bs
[  384.541165] CPU: 112 PID: 2041 Comm: sugov:112 Tainted: G        W
       5.14.0-rc1 #1
[  384.549244] Hardware name: WIWYNN Mt.Jade Server System
B81.030Z1.0007/Mt.Jade Motherboard, BIOS 1.6.20210526 (SCP:
1.06.20210526) 2021/05/26
[  384.561922] pstate: 404000c9 (nZcv daIF +PAN -UAO -TCO BTYPE=--)
[  384.567918] pc : sub_running_bw.isra.0+0x190/0x1a0
[  384.572698] lr : sub_running_bw.isra.0+0x190/0x1a0
[  384.577477] sp : ffff800024c4bb20
[  384.580779] x29: ffff800024c4bb20 x28: 0000000000000000 x27: ffffb9a9bbe1d200
[  384.587904] x26: 0000000000000074 x25: 0000000000000011 x24: ffffb9a9bdff9000
[  384.595029] x23: ffff07ffb36fcaa0 x22: ffff401ee09b65c0 x21: ffffb9a9bbe1de00
[  384.602153] x20: ffff401ee09a3360 x19: ffff401ee09b6f58 x18: 0000000000000000
[  384.609277] x17: ffff867522f0c000 x16: ffff800010384000 x15: 0000000000000030
[  384.616401] x14: 0000000000000000 x13: 50494b535f544341 x12: 5f46435152203c20
[  384.623526] x11: ffff401ee04b0ea8 x10: ffff401ee021e068 x9 : ffffb9a9bbe4214c
[  384.630650] x8 : 0000000000010ea8 x7 : ffff401ee01e0000 x6 : 0000000000017ffd
[  384.637774] x5 : ffff401ee09a3490 x4 : 0000000000000001 x3 : ffff867522f0c000
[  384.644898] x2 : ffff401ee09a3498 x1 : ffff07ffb53cc000 x0 : 0000000000000026
[  384.652022] Call trace:
[  384.654457]  sub_running_bw.isra.0+0x190/0x1a0
[  384.658890]  migrate_task_rq_dl+0xf8/0x1e0
[  384.662975]  set_task_cpu+0xa8/0x1f0
[  384.666540]  try_to_wake_up+0x150/0x3d4
[  384.670365]  wake_up_q+0x64/0xc0
[  384.673582]  __up_write+0xd0/0x1c0
[  384.676974]  up_write+0x4c/0x2b0
[  384.680191]  cppc_set_perf+0x120/0x2d0
[  384.683931]  cppc_cpufreq_set_target+0xe0/0x1a4 [cppc_cpufreq]
[  384.689756]  __cpufreq_driver_target+0x74/0x140
[  384.694277]  sugov_work+0x64/0x80
[  384.697580]  kthread_worker_fn+0xe0/0x230
[  384.701580]  kthread+0x138/0x140
[  384.704797]  ret_from_fork+0x10/0x18


More logs can be found checking out dmesg logs on:
https://arr-cki-prod-datawarehouse-public.s3.amazonaws.com/index.html?prefix=datawarehouse-public/2021/07/16/338525814/build_aarch64_redhat%3A1431434591/tests/storage_software_RAID_testing/
https://arr-cki-prod-datawarehouse-public.s3.amazonaws.com/index.html?prefix=datawarehouse-public/2021/07/16/338525814/build_aarch64_redhat%3A1431434591/tests/xfstests_btrfs/
https://arr-cki-prod-datawarehouse-public.s3.amazonaws.com/index.html?prefix=datawarehouse-public/2021/07/16/338525814/build_aarch64_redhat%3A1431434591/tests/xfstests_ext4/
https://arr-cki-prod-datawarehouse-public.s3.amazonaws.com/index.html?prefix=datawarehouse-public/2021/07/16/338525814/build_aarch64_redhat%3A1431434591/tests/xfstests_xfs/

Thank you,
Bruno Goncalves


^ permalink raw reply	[flat|nested] 7+ messages in thread

* Re: WARNING: CPU: 112 PID: 2041 at kernel/sched/sched.h:1453
  2021-07-28 13:11 WARNING: CPU: 112 PID: 2041 at kernel/sched/sched.h:1453 Bruno Goncalves
@ 2021-07-28 15:55 ` Dietmar Eggemann
  2021-07-29 12:36   ` Bruno Goncalves
  0 siblings, 1 reply; 7+ messages in thread
From: Dietmar Eggemann @ 2021-07-28 15:55 UTC (permalink / raw)
  To: Bruno Goncalves, CKI Project, linux-kernel; +Cc: nathan, Memory Management

On 28/07/2021 15:11, Bruno Goncalves wrote:
> Hello,
> 
> Since this commit (Commit: 45312bd762d3 - Merge tag 'zonefs-5.14-rc2')
> we started to see the following call trace, it seems to be
> reproducible only on aarch64.

It should happen on platforms using a slow-switching cpufreq driver.

Only in this case you have n (depends on nbr of frequency domains)
special-purpose DL threads when using schedutil CPUFreq governor:

root@juno: ps -eTo comm,pid,pri,class | grep sugov

sugov:0           132 140 DLN
sugov:1           134 140 DLN

> 
> [  384.485614] ------------[ cut here ]------------
> [  384.490227] rq->clock_update_flags < RQCF_ACT_SKIP
> [  384.490232] WARNING: CPU: 112 PID: 2041 at
> kernel/sched/sched.h:1453 sub_running_bw.isra.0+0x190/0x1a0
> [  384.504312] Modules linked in: mlx5_ib ib_uverbs ib_core rfkill
> sunrpc acpi_ipmi ipmi_ssif mlx5_core mlxfw psample ipmi_devintf
> arm_cmn ipmi_msghandler arm_dsu_pmu cppc_cpufreq acpi_tad vfat fat
> fuse zram ip_tables x_tables xfs crct10dif_ce ghash_ce ast
> i2c_algo_bit drm_vram_helper sbsa_gwdt drm_kms_helper syscopyarea
> sysfillrect sysimgblt fb_sys_fops cec drm_ttm_helper ttm nvme
> nvme_core drm xgene_hwmon aes_neon_bs
> [  384.541165] CPU: 112 PID: 2041 Comm: sugov:112 Tainted: G        W
>        5.14.0-rc1 #1
> [  384.549244] Hardware name: WIWYNN Mt.Jade Server System
> B81.030Z1.0007/Mt.Jade Motherboard, BIOS 1.6.20210526 (SCP:
> 1.06.20210526) 2021/05/26
> [  384.561922] pstate: 404000c9 (nZcv daIF +PAN -UAO -TCO BTYPE=--)
> [  384.567918] pc : sub_running_bw.isra.0+0x190/0x1a0
> [  384.572698] lr : sub_running_bw.isra.0+0x190/0x1a0
> [  384.577477] sp : ffff800024c4bb20
> [  384.580779] x29: ffff800024c4bb20 x28: 0000000000000000 x27: ffffb9a9bbe1d200
> [  384.587904] x26: 0000000000000074 x25: 0000000000000011 x24: ffffb9a9bdff9000
> [  384.595029] x23: ffff07ffb36fcaa0 x22: ffff401ee09b65c0 x21: ffffb9a9bbe1de00
> [  384.602153] x20: ffff401ee09a3360 x19: ffff401ee09b6f58 x18: 0000000000000000
> [  384.609277] x17: ffff867522f0c000 x16: ffff800010384000 x15: 0000000000000030
> [  384.616401] x14: 0000000000000000 x13: 50494b535f544341 x12: 5f46435152203c20
> [  384.623526] x11: ffff401ee04b0ea8 x10: ffff401ee021e068 x9 : ffffb9a9bbe4214c
> [  384.630650] x8 : 0000000000010ea8 x7 : ffff401ee01e0000 x6 : 0000000000017ffd
> [  384.637774] x5 : ffff401ee09a3490 x4 : 0000000000000001 x3 : ffff867522f0c000
> [  384.644898] x2 : ffff401ee09a3498 x1 : ffff07ffb53cc000 x0 : 0000000000000026
> [  384.652022] Call trace:
> [  384.654457]  sub_running_bw.isra.0+0x190/0x1a0
> [  384.658890]  migrate_task_rq_dl+0xf8/0x1e0
> [  384.662975]  set_task_cpu+0xa8/0x1f0
> [  384.666540]  try_to_wake_up+0x150/0x3d4
> [  384.670365]  wake_up_q+0x64/0xc0
> [  384.673582]  __up_write+0xd0/0x1c0
> [  384.676974]  up_write+0x4c/0x2b0
> [  384.680191]  cppc_set_perf+0x120/0x2d0
> [  384.683931]  cppc_cpufreq_set_target+0xe0/0x1a4 [cppc_cpufreq]
> [  384.689756]  __cpufreq_driver_target+0x74/0x140
> [  384.694277]  sugov_work+0x64/0x80
> [  384.697580]  kthread_worker_fn+0xe0/0x230
> [  384.701580]  kthread+0x138/0x140
> [  384.704797]  ret_from_fork+0x10/0x18

Don't quite get this.
`sugov:112` should be a special DL entity (dl_se->flags &
SCHED_FLAG_SUGOV) so sub_running_bw() should not call __sub_running_bw()
and hence there won't be a call to cpufreq_update_util() which calls
q_clock(rq) -> assert_clock_updated()?

Can't reproduce it on my Juno (arm64) (slow-switching (scpi-cpufreq
driver)).

^ permalink raw reply	[flat|nested] 7+ messages in thread

* Re: WARNING: CPU: 112 PID: 2041 at kernel/sched/sched.h:1453
  2021-07-28 15:55 ` Dietmar Eggemann
@ 2021-07-29 12:36   ` Bruno Goncalves
  2021-07-29 14:38     ` Dietmar Eggemann
  0 siblings, 1 reply; 7+ messages in thread
From: Bruno Goncalves @ 2021-07-29 12:36 UTC (permalink / raw)
  To: Dietmar Eggemann
  Cc: CKI Project, linux-kernel, nathan, Memory Management, linux-arm-kernel

On Wed, Jul 28, 2021 at 5:55 PM Dietmar Eggemann
<dietmar.eggemann@arm.com> wrote:
>
> On 28/07/2021 15:11, Bruno Goncalves wrote:
> > Hello,
> >
> > Since this commit (Commit: 45312bd762d3 - Merge tag 'zonefs-5.14-rc2')
> > we started to see the following call trace, it seems to be
> > reproducible only on aarch64.
>
> It should happen on platforms using a slow-switching cpufreq driver.
>
> Only in this case you have n (depends on nbr of frequency domains)
> special-purpose DL threads when using schedutil CPUFreq governor:
>
> root@juno: ps -eTo comm,pid,pri,class | grep sugov
>
> sugov:0           132 140 DLN
> sugov:1           134 140 DLN
>
> >
> > [  384.485614] ------------[ cut here ]------------
> > [  384.490227] rq->clock_update_flags < RQCF_ACT_SKIP
> > [  384.490232] WARNING: CPU: 112 PID: 2041 at
> > kernel/sched/sched.h:1453 sub_running_bw.isra.0+0x190/0x1a0
> > [  384.504312] Modules linked in: mlx5_ib ib_uverbs ib_core rfkill
> > sunrpc acpi_ipmi ipmi_ssif mlx5_core mlxfw psample ipmi_devintf
> > arm_cmn ipmi_msghandler arm_dsu_pmu cppc_cpufreq acpi_tad vfat fat
> > fuse zram ip_tables x_tables xfs crct10dif_ce ghash_ce ast
> > i2c_algo_bit drm_vram_helper sbsa_gwdt drm_kms_helper syscopyarea
> > sysfillrect sysimgblt fb_sys_fops cec drm_ttm_helper ttm nvme
> > nvme_core drm xgene_hwmon aes_neon_bs
> > [  384.541165] CPU: 112 PID: 2041 Comm: sugov:112 Tainted: G        W
> >        5.14.0-rc1 #1
> > [  384.549244] Hardware name: WIWYNN Mt.Jade Server System
> > B81.030Z1.0007/Mt.Jade Motherboard, BIOS 1.6.20210526 (SCP:
> > 1.06.20210526) 2021/05/26
> > [  384.561922] pstate: 404000c9 (nZcv daIF +PAN -UAO -TCO BTYPE=--)
> > [  384.567918] pc : sub_running_bw.isra.0+0x190/0x1a0
> > [  384.572698] lr : sub_running_bw.isra.0+0x190/0x1a0
> > [  384.577477] sp : ffff800024c4bb20
> > [  384.580779] x29: ffff800024c4bb20 x28: 0000000000000000 x27: ffffb9a9bbe1d200
> > [  384.587904] x26: 0000000000000074 x25: 0000000000000011 x24: ffffb9a9bdff9000
> > [  384.595029] x23: ffff07ffb36fcaa0 x22: ffff401ee09b65c0 x21: ffffb9a9bbe1de00
> > [  384.602153] x20: ffff401ee09a3360 x19: ffff401ee09b6f58 x18: 0000000000000000
> > [  384.609277] x17: ffff867522f0c000 x16: ffff800010384000 x15: 0000000000000030
> > [  384.616401] x14: 0000000000000000 x13: 50494b535f544341 x12: 5f46435152203c20
> > [  384.623526] x11: ffff401ee04b0ea8 x10: ffff401ee021e068 x9 : ffffb9a9bbe4214c
> > [  384.630650] x8 : 0000000000010ea8 x7 : ffff401ee01e0000 x6 : 0000000000017ffd
> > [  384.637774] x5 : ffff401ee09a3490 x4 : 0000000000000001 x3 : ffff867522f0c000
> > [  384.644898] x2 : ffff401ee09a3498 x1 : ffff07ffb53cc000 x0 : 0000000000000026
> > [  384.652022] Call trace:
> > [  384.654457]  sub_running_bw.isra.0+0x190/0x1a0
> > [  384.658890]  migrate_task_rq_dl+0xf8/0x1e0
> > [  384.662975]  set_task_cpu+0xa8/0x1f0
> > [  384.666540]  try_to_wake_up+0x150/0x3d4
> > [  384.670365]  wake_up_q+0x64/0xc0
> > [  384.673582]  __up_write+0xd0/0x1c0
> > [  384.676974]  up_write+0x4c/0x2b0
> > [  384.680191]  cppc_set_perf+0x120/0x2d0
> > [  384.683931]  cppc_cpufreq_set_target+0xe0/0x1a4 [cppc_cpufreq]
> > [  384.689756]  __cpufreq_driver_target+0x74/0x140
> > [  384.694277]  sugov_work+0x64/0x80
> > [  384.697580]  kthread_worker_fn+0xe0/0x230
> > [  384.701580]  kthread+0x138/0x140
> > [  384.704797]  ret_from_fork+0x10/0x18
>
> Don't quite get this.
> `sugov:112` should be a special DL entity (dl_se->flags &
> SCHED_FLAG_SUGOV) so sub_running_bw() should not call __sub_running_bw()
> and hence there won't be a call to cpufreq_update_util() which calls
> q_clock(rq) -> assert_clock_updated()?
>
> Can't reproduce it on my Juno (arm64) (slow-switching (scpi-cpufreq
> driver)).

We seem to be able to reproduce this only on Ampere Altra machines,
specifically on mtjade and mtsnow cpus.

# cpupower frequency-info
analyzing CPU 0:
  driver: cppc_cpufreq
  CPUs which run at the same hardware frequency: 0
  CPUs which need to have their frequency coordinated by software: 0
  maximum transition latency:  Cannot determine or is not supported.
  hardware limits: 1000 MHz - 2.80 GHz
  available cpufreq governors: conservative ondemand userspace
powersave performance schedutil
  current policy: frequency should be within 2.00 GHz and 2.80 GHz.
                  The governor "schedutil" may decide which speed to use
                  within this range.
  current CPU frequency: 1.55 GHz (asserted by call to hardware)

# ps -eTo comm,pid,pri,class | grep sugov
sugov:0            1082 140 DLN
sugov:1            1085 140 DLN
...
sugov:78           1319 140 DLN
sugov:79           1320 140 DLN


Bruno


>


^ permalink raw reply	[flat|nested] 7+ messages in thread

* Re: WARNING: CPU: 112 PID: 2041 at kernel/sched/sched.h:1453
  2021-07-29 12:36   ` Bruno Goncalves
@ 2021-07-29 14:38     ` Dietmar Eggemann
  2021-07-30 12:22       ` Dietmar Eggemann
  0 siblings, 1 reply; 7+ messages in thread
From: Dietmar Eggemann @ 2021-07-29 14:38 UTC (permalink / raw)
  To: Bruno Goncalves
  Cc: CKI Project, linux-kernel, nathan, Memory Management, linux-arm-kernel

On 29/07/2021 14:36, Bruno Goncalves wrote:
> On Wed, Jul 28, 2021 at 5:55 PM Dietmar Eggemann
> <dietmar.eggemann@arm.com> wrote:
>>
>> On 28/07/2021 15:11, Bruno Goncalves wrote:

[...]

>> Can't reproduce it on my Juno (arm64) (slow-switching (scpi-cpufreq
>> driver)).
> 
> We seem to be able to reproduce this only on Ampere Altra machines,
> specifically on mtjade and mtsnow cpus.
> 
> # cpupower frequency-info
> analyzing CPU 0:
>   driver: cppc_cpufreq
>   CPUs which run at the same hardware frequency: 0
>   CPUs which need to have their frequency coordinated by software: 0
>   maximum transition latency:  Cannot determine or is not supported.
>   hardware limits: 1000 MHz - 2.80 GHz
>   available cpufreq governors: conservative ondemand userspace
> powersave performance schedutil
>   current policy: frequency should be within 2.00 GHz and 2.80 GHz.
>                   The governor "schedutil" may decide which speed to use
>                   within this range.
>   current CPU frequency: 1.55 GHz (asserted by call to hardware)
> 
> # ps -eTo comm,pid,pri,class | grep sugov
> sugov:0            1082 140 DLN
> sugov:1            1085 140 DLN
> ...
> sugov:78           1319 140 DLN
> sugov:79           1320 140 DLN

Thanks! In the meantime I got access to an Ampere Altra so I can try
5.14.0-rc1 later today.

^ permalink raw reply	[flat|nested] 7+ messages in thread

* Re: WARNING: CPU: 112 PID: 2041 at kernel/sched/sched.h:1453
  2021-07-29 14:38     ` Dietmar Eggemann
@ 2021-07-30 12:22       ` Dietmar Eggemann
  2021-07-30 15:23         ` Bruno Goncalves
  0 siblings, 1 reply; 7+ messages in thread
From: Dietmar Eggemann @ 2021-07-30 12:22 UTC (permalink / raw)
  To: Bruno Goncalves
  Cc: CKI Project, linux-kernel, nathan, Memory Management, linux-arm-kernel

On 29/07/2021 16:38, Dietmar Eggemann wrote:
> On 29/07/2021 14:36, Bruno Goncalves wrote:
>> On Wed, Jul 28, 2021 at 5:55 PM Dietmar Eggemann
>> <dietmar.eggemann@arm.com> wrote:
>>>
>>> On 28/07/2021 15:11, Bruno Goncalves wrote:
> 
> [...]
> 
>>> Can't reproduce it on my Juno (arm64) (slow-switching (scpi-cpufreq
>>> driver)).
>>
>> We seem to be able to reproduce this only on Ampere Altra machines,
>> specifically on mtjade and mtsnow cpus.
>>
>> # cpupower frequency-info
>> analyzing CPU 0:
>>   driver: cppc_cpufreq
>>   CPUs which run at the same hardware frequency: 0
>>   CPUs which need to have their frequency coordinated by software: 0
>>   maximum transition latency:  Cannot determine or is not supported.
>>   hardware limits: 1000 MHz - 2.80 GHz
>>   available cpufreq governors: conservative ondemand userspace
>> powersave performance schedutil
>>   current policy: frequency should be within 2.00 GHz and 2.80 GHz.
>>                   The governor "schedutil" may decide which speed to use
>>                   within this range.
>>   current CPU frequency: 1.55 GHz (asserted by call to hardware)
>>
>> # ps -eTo comm,pid,pri,class | grep sugov
>> sugov:0            1082 140 DLN
>> sugov:1            1085 140 DLN
>> ...
>> sugov:78           1319 140 DLN
>> sugov:79           1320 140 DLN
> 
> Thanks! In the meantime I got access to an Ampere Altra so I can try
> 5.14.0-rc1 later today.

The task causing this seem to be the new `cppc_fie` DL task introduced
by commit 1eb5dde674f5 "cpufreq: CPPC: Add support for frequency
invariance" in v5.14-rc1.

With `CONFIG_ACPI_CPPC_CPUFREQ_FIE=y` and schedutil cpufreq governor on
slow-switching system:

DL task curr=`sugov:X` makes p=`cppc_fie` migrate and since it is in
`non_contending` state, migrate_task_rq_dl() calls 

  sub_running_bw()->__sub_running_bw()->cpufreq_update_util()->
  rq_clock()->assert_clock_updated()

on p. 

Can you try this snippet? It should fix it.

--8<--

From: Dietmar Eggemann <dietmar.eggemann@arm.com>
Date: Fri, 30 Jul 2021 14:03:40 +0200
Subject: [PATCH] sched/deadline: Fix missing clock update in
 migrate_task_rq_dl()

Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
---
 kernel/sched/deadline.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index aaacd6cfd42f..4920f498492f 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1733,6 +1733,7 @@ static void migrate_task_rq_dl(struct task_struct *p, int new_cpu __maybe_unused
 	 */
 	raw_spin_rq_lock(rq);
 	if (p->dl.dl_non_contending) {
+		update_rq_clock(rq);
 		sub_running_bw(&p->dl, &rq->dl);
 		p->dl.dl_non_contending = 0;
 		/*
-- 
2.25.1

^ permalink raw reply	[flat|nested] 7+ messages in thread

* Re: WARNING: CPU: 112 PID: 2041 at kernel/sched/sched.h:1453
  2021-07-30 12:22       ` Dietmar Eggemann
@ 2021-07-30 15:23         ` Bruno Goncalves
  2021-08-02  8:43           ` Dietmar Eggemann
  0 siblings, 1 reply; 7+ messages in thread
From: Bruno Goncalves @ 2021-07-30 15:23 UTC (permalink / raw)
  To: Dietmar Eggemann
  Cc: CKI Project, linux-kernel, nathan, Memory Management, linux-arm-kernel

On Fri, Jul 30, 2021 at 2:22 PM Dietmar Eggemann
<dietmar.eggemann@arm.com> wrote:
>
> On 29/07/2021 16:38, Dietmar Eggemann wrote:
> > On 29/07/2021 14:36, Bruno Goncalves wrote:
> >> On Wed, Jul 28, 2021 at 5:55 PM Dietmar Eggemann
> >> <dietmar.eggemann@arm.com> wrote:
> >>>
> >>> On 28/07/2021 15:11, Bruno Goncalves wrote:
> >
> > [...]
> >
> >>> Can't reproduce it on my Juno (arm64) (slow-switching (scpi-cpufreq
> >>> driver)).
> >>
> >> We seem to be able to reproduce this only on Ampere Altra machines,
> >> specifically on mtjade and mtsnow cpus.
> >>
> >> # cpupower frequency-info
> >> analyzing CPU 0:
> >>   driver: cppc_cpufreq
> >>   CPUs which run at the same hardware frequency: 0
> >>   CPUs which need to have their frequency coordinated by software: 0
> >>   maximum transition latency:  Cannot determine or is not supported.
> >>   hardware limits: 1000 MHz - 2.80 GHz
> >>   available cpufreq governors: conservative ondemand userspace
> >> powersave performance schedutil
> >>   current policy: frequency should be within 2.00 GHz and 2.80 GHz.
> >>                   The governor "schedutil" may decide which speed to use
> >>                   within this range.
> >>   current CPU frequency: 1.55 GHz (asserted by call to hardware)
> >>
> >> # ps -eTo comm,pid,pri,class | grep sugov
> >> sugov:0            1082 140 DLN
> >> sugov:1            1085 140 DLN
> >> ...
> >> sugov:78           1319 140 DLN
> >> sugov:79           1320 140 DLN
> >
> > Thanks! In the meantime I got access to an Ampere Altra so I can try
> > 5.14.0-rc1 later today.
>
> The task causing this seem to be the new `cppc_fie` DL task introduced
> by commit 1eb5dde674f5 "cpufreq: CPPC: Add support for frequency
> invariance" in v5.14-rc1.
>
> With `CONFIG_ACPI_CPPC_CPUFREQ_FIE=y` and schedutil cpufreq governor on
> slow-switching system:
>
> DL task curr=`sugov:X` makes p=`cppc_fie` migrate and since it is in
> `non_contending` state, migrate_task_rq_dl() calls
>
>   sub_running_bw()->__sub_running_bw()->cpufreq_update_util()->
>   rq_clock()->assert_clock_updated()
>
> on p.
>
> Can you try this snippet? It should fix it.

Thank you, I've tried the patch and it fixes the issue.

Bruno

>
> --8<--
>
> From: Dietmar Eggemann <dietmar.eggemann@arm.com>
> Date: Fri, 30 Jul 2021 14:03:40 +0200
> Subject: [PATCH] sched/deadline: Fix missing clock update in
>  migrate_task_rq_dl()
>
> Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
> ---
>  kernel/sched/deadline.c | 1 +
>  1 file changed, 1 insertion(+)
>
> diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
> index aaacd6cfd42f..4920f498492f 100644
> --- a/kernel/sched/deadline.c
> +++ b/kernel/sched/deadline.c
> @@ -1733,6 +1733,7 @@ static void migrate_task_rq_dl(struct task_struct *p, int new_cpu __maybe_unused
>          */
>         raw_spin_rq_lock(rq);
>         if (p->dl.dl_non_contending) {
> +               update_rq_clock(rq);
>                 sub_running_bw(&p->dl, &rq->dl);
>                 p->dl.dl_non_contending = 0;
>                 /*
> --
> 2.25.1
>


^ permalink raw reply	[flat|nested] 7+ messages in thread

* Re: WARNING: CPU: 112 PID: 2041 at kernel/sched/sched.h:1453
  2021-07-30 15:23         ` Bruno Goncalves
@ 2021-08-02  8:43           ` Dietmar Eggemann
  0 siblings, 0 replies; 7+ messages in thread
From: Dietmar Eggemann @ 2021-08-02  8:43 UTC (permalink / raw)
  To: Bruno Goncalves
  Cc: CKI Project, linux-kernel, nathan, Memory Management, linux-arm-kernel

On 30/07/2021 17:23, Bruno Goncalves wrote:
> On Fri, Jul 30, 2021 at 2:22 PM Dietmar Eggemann
> <dietmar.eggemann@arm.com> wrote:
>>
>> On 29/07/2021 16:38, Dietmar Eggemann wrote:
>>> On 29/07/2021 14:36, Bruno Goncalves wrote:
>>>> On Wed, Jul 28, 2021 at 5:55 PM Dietmar Eggemann
>>>> <dietmar.eggemann@arm.com> wrote:
>>>>>
>>>>> On 28/07/2021 15:11, Bruno Goncalves wrote:

[...]

>> The task causing this seem to be the new `cppc_fie` DL task introduced
>> by commit 1eb5dde674f5 "cpufreq: CPPC: Add support for frequency
>> invariance" in v5.14-rc1.
>>
>> With `CONFIG_ACPI_CPPC_CPUFREQ_FIE=y` and schedutil cpufreq governor on
>> slow-switching system:
>>
>> DL task curr=`sugov:X` makes p=`cppc_fie` migrate and since it is in
>> `non_contending` state, migrate_task_rq_dl() calls
>>
>>   sub_running_bw()->__sub_running_bw()->cpufreq_update_util()->
>>   rq_clock()->assert_clock_updated()
>>
>> on p.
>>
>> Can you try this snippet? It should fix it.
> 
> Thank you, I've tried the patch and it fixes the issue.

Thanks for testing! Let me send out a proper patch then.

^ permalink raw reply	[flat|nested] 7+ messages in thread

end of thread, other threads:[~2021-08-02  8:43 UTC | newest]

Thread overview: 7+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-07-28 13:11 WARNING: CPU: 112 PID: 2041 at kernel/sched/sched.h:1453 Bruno Goncalves
2021-07-28 15:55 ` Dietmar Eggemann
2021-07-29 12:36   ` Bruno Goncalves
2021-07-29 14:38     ` Dietmar Eggemann
2021-07-30 12:22       ` Dietmar Eggemann
2021-07-30 15:23         ` Bruno Goncalves
2021-08-02  8:43           ` Dietmar Eggemann

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 NNTP newsgroup(s).