From: "Lazar, Lijo" <lijo.lazar@amd.com>
To: "Quan, Evan" <Evan.Quan@amd.com>,
"Michel Dänzer" <michel@daenzer.net>,
"Deucher, Alexander" <Alexander.Deucher@amd.com>,
"Koenig, Christian" <Christian.Koenig@amd.com>
Cc: "Liu, Leo" <Leo.Liu@amd.com>, "Zhu, James" <James.Zhu@amd.com>,
"amd-gfx@lists.freedesktop.org" <amd-gfx@lists.freedesktop.org>,
"dri-devel@lists.freedesktop.org"
<dri-devel@lists.freedesktop.org>
Subject: Re: [PATCH v3] drm/amdgpu: Cancel delayed work when GFXOFF is disabled
Date: Tue, 17 Aug 2021 13:47:08 +0530 [thread overview]
Message-ID: <2edaef45-504a-b1c7-28e4-adc0d030715a@amd.com> (raw)
In-Reply-To: <DM6PR12MB26191A1092AA54AA6405F0DAE4FE9@DM6PR12MB2619.namprd12.prod.outlook.com>
On 8/17/2021 1:21 PM, Quan, Evan wrote:
> [AMD Official Use Only]
>
>
>
>> -----Original Message-----
>> From: amd-gfx <amd-gfx-bounces@lists.freedesktop.org> On Behalf Of
>> Michel Dänzer
>> Sent: Monday, August 16, 2021 6:35 PM
>> To: Deucher, Alexander <Alexander.Deucher@amd.com>; Koenig, Christian
>> <Christian.Koenig@amd.com>
>> Cc: Liu, Leo <Leo.Liu@amd.com>; Zhu, James <James.Zhu@amd.com>; amd-
>> gfx@lists.freedesktop.org; dri-devel@lists.freedesktop.org
>> Subject: [PATCH v3] drm/amdgpu: Cancel delayed work when GFXOFF is
>> disabled
>>
>> From: Michel Dänzer <mdaenzer@redhat.com>
>>
>> schedule_delayed_work does not push back the work if it was already
>> scheduled before, so amdgpu_device_delay_enable_gfx_off ran ~100 ms
>> after the first time GFXOFF was disabled and re-enabled, even if GFXOFF
>> was disabled and re-enabled again during those 100 ms.
>>
>> This resulted in frame drops / stutter with the upcoming mutter 41
>> release on Navi 14, due to constantly enabling GFXOFF in the HW and
>> disabling it again (for getting the GPU clock counter).
>>
>> To fix this, call cancel_delayed_work_sync when the disable count
>> transitions from 0 to 1, and only schedule the delayed work on the
>> reverse transition, not if the disable count was already 0. This makes
>> sure the delayed work doesn't run at unexpected times, and allows it to
>> be lock-free.
>>
>> v2:
>> * Use cancel_delayed_work_sync & mutex_trylock instead of
>> mod_delayed_work.
>> v3:
>> * Make amdgpu_device_delay_enable_gfx_off lock-free (Christian König)
>>
>> Cc: stable@vger.kernel.org
>> Signed-off-by: Michel Dänzer <mdaenzer@redhat.com>
>> ---
>> drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 11 +++++------
>> drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c | 22 +++++++++++++++++-
>> ----
>> 2 files changed, 22 insertions(+), 11 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
>> b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
>> index f3fd5ec710b6..f944ed858f3e 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
>> @@ -2777,12 +2777,11 @@ static void
>> amdgpu_device_delay_enable_gfx_off(struct work_struct *work)
>> struct amdgpu_device *adev =
>> container_of(work, struct amdgpu_device,
>> gfx.gfx_off_delay_work.work);
>>
>> - mutex_lock(&adev->gfx.gfx_off_mutex);
>> - if (!adev->gfx.gfx_off_state && !adev->gfx.gfx_off_req_count) {
>> - if (!amdgpu_dpm_set_powergating_by_smu(adev,
>> AMD_IP_BLOCK_TYPE_GFX, true))
>> - adev->gfx.gfx_off_state = true;
>> - }
>> - mutex_unlock(&adev->gfx.gfx_off_mutex);
>> + WARN_ON_ONCE(adev->gfx.gfx_off_state);
>> + WARN_ON_ONCE(adev->gfx.gfx_off_req_count);
>> +
>> + if (!amdgpu_dpm_set_powergating_by_smu(adev,
>> AMD_IP_BLOCK_TYPE_GFX, true))
>> + adev->gfx.gfx_off_state = true;
>> }
>>
>> /**
>> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
>> b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
>> index a0be0772c8b3..ca91aafcb32b 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
>> @@ -563,15 +563,26 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device
>> *adev, bool enable)
>>
>> mutex_lock(&adev->gfx.gfx_off_mutex);
>>
>> - if (!enable)
>> - adev->gfx.gfx_off_req_count++;
>> - else if (adev->gfx.gfx_off_req_count > 0)
>> + if (enable) {
>> + /* If the count is already 0, it means there's an imbalance bug
>> somewhere.
>> + * Note that the bug may be in a different caller than the one
>> which triggers the
>> + * WARN_ON_ONCE.
>> + */
>> + if (WARN_ON_ONCE(adev->gfx.gfx_off_req_count == 0))
>> + goto unlock;
>> +
>> adev->gfx.gfx_off_req_count--;
>> + } else {
>> + adev->gfx.gfx_off_req_count++;
>> + }
>>
>> if (enable && !adev->gfx.gfx_off_state && !adev-
>>> gfx.gfx_off_req_count) {
>> schedule_delayed_work(&adev->gfx.gfx_off_delay_work,
>> GFX_OFF_DELAY_ENABLE);
>> - } else if (!enable && adev->gfx.gfx_off_state) {
>> - if (!amdgpu_dpm_set_powergating_by_smu(adev,
>> AMD_IP_BLOCK_TYPE_GFX, false)) {
>> + } else if (!enable && adev->gfx.gfx_off_req_count == 1) {
> [Quan, Evan] It seems here will leave a small time window for race condition. If amdgpu_device_delay_enable_gfx_off() happens to occur here, it will "WARN_ON_ONCE(adev->gfx.gfx_off_req_count);". How about something as below?
> @@ -573,13 +573,11 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable)
> goto unlock;
>
> adev->gfx.gfx_off_req_count--;
> - } else {
> - adev->gfx.gfx_off_req_count++;
> }
>
> if (enable && !adev->gfx.gfx_off_state && !adev->gfx.gfx_off_req_count) {
> schedule_delayed_work(&adev->gfx.gfx_off_delay_work, GFX_OFF_DELAY_ENABLE);
> - } else if (!enable && adev->gfx.gfx_off_req_count == 1) {
> + } else if (!enable && adev->gfx.gfx_off_req_count == 0) {
> cancel_delayed_work_sync(&adev->gfx.gfx_off_delay_work);
>
> if (adev->gfx.gfx_off_state &&
> @@ -593,6 +591,9 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable)
> }
> }
>
> + if (!enable)
> + adev->gfx.gfx_off_req_count++;
> +
> unlock:
>
Hi Evan,
It's not a race per se, it is just an undesirable condition of Enable
Gfxoff immediately followed by a Disable GfxOff. The purpose of the WARN
is to intimate the user about it.
There are other cases - for ex: if amdgpu_device_delay_enable_gfx_off()
called amdgpu_dpm_set_powergating_by_smu() already at the same place you
pointed out. In this case WARN doesn't get printed, but it's not an
optimal situation either. Probably it makes sense to move the WARN_ON as
the last line of amdgpu_device_delay_enable_gfx_off. Either way, I don't
think it's a race condition.
Thanks,
Lijo
> BR
> Evan
>> + cancel_delayed_work_sync(&adev-
>>> gfx.gfx_off_delay_work);
>> +
>> + if (adev->gfx.gfx_off_state &&
>> + !amdgpu_dpm_set_powergating_by_smu(adev,
>> AMD_IP_BLOCK_TYPE_GFX, false)) {
>> adev->gfx.gfx_off_state = false;
>>
>> if (adev->gfx.funcs->init_spm_golden) {
>> @@ -581,6 +592,7 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device
>> *adev, bool enable)
>> }
>> }
>>
>> +unlock:
>> mutex_unlock(&adev->gfx.gfx_off_mutex);
>> }
>>
>> --
>> 2.32.0
next prev parent reply other threads:[~2021-08-17 8:17 UTC|newest]
Thread overview: 49+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-08-11 16:52 [PATCH 1/2] drm/amdgpu: Use mod_delayed_work in amdgpu_gfx_off_ctrl Michel Dänzer
2021-08-11 16:52 ` [PATCH 2/2] drm/amdgpu: Use mod_delayed_work in JPEG/UVD/VCE/VCN ring_end_use hooks Michel Dänzer
2021-08-11 20:34 ` Alex Deucher
2021-08-11 21:00 ` Zhu, James
2021-08-11 21:34 ` AW: " Koenig, Christian
2021-08-11 22:12 ` Zhu, James
2021-08-11 22:22 ` Zhu, James
2021-08-12 2:42 ` Quan, Evan
2021-08-12 5:55 ` AW: " Koenig, Christian
2021-08-12 8:11 ` Michel Dänzer
2021-08-12 11:33 ` Lazar, Lijo
2021-08-12 16:54 ` Michel Dänzer
2021-08-13 4:23 ` Lazar, Lijo
2021-08-13 10:31 ` Michel Dänzer
2021-08-13 11:18 ` Lazar, Lijo
2021-08-16 7:33 ` Christian König
2021-08-12 2:43 ` [PATCH 1/2] drm/amdgpu: Use mod_delayed_work in amdgpu_gfx_off_ctrl Quan, Evan
2021-08-13 10:29 ` [PATCH] drm/amdgpu: Cancel delayed work when GFXOFF is disabled Michel Dänzer
2021-08-13 11:50 ` Lazar, Lijo
2021-08-13 13:34 ` Michel Dänzer
2021-08-13 14:14 ` Lazar, Lijo
2021-08-13 14:40 ` Michel Dänzer
2021-08-13 15:07 ` Lazar, Lijo
2021-08-13 16:00 ` Michel Dänzer
2021-08-16 4:13 ` Lazar, Lijo
2021-08-16 10:45 ` Michel Dänzer
2021-08-16 7:38 ` Christian König
2021-08-16 10:38 ` Michel Dänzer
2021-08-16 10:20 ` Quan, Evan
2021-08-16 10:43 ` Michel Dänzer
2021-08-16 10:35 ` [PATCH v3] " Michel Dänzer
2021-08-16 11:33 ` Lazar, Lijo
2021-08-16 12:06 ` Christian König
2021-08-16 15:06 ` Michel Dänzer
2021-08-16 19:02 ` Alex Deucher
2021-08-17 7:51 ` Quan, Evan
2021-08-17 8:17 ` Lazar, Lijo [this message]
2021-08-17 8:35 ` Michel Dänzer
2021-08-17 8:23 ` [PATCH] " Michel Dänzer
2021-08-17 9:12 ` Lazar, Lijo
2021-08-17 9:26 ` Michel Dänzer
2021-08-17 9:37 ` Lazar, Lijo
2021-08-17 9:59 ` Michel Dänzer
2021-08-17 10:37 ` Lazar, Lijo
2021-08-17 11:06 ` Michel Dänzer
2021-08-17 11:49 ` Lazar, Lijo
2021-08-17 12:55 ` Lazar, Lijo
2021-08-17 9:33 ` Quan, Evan
2021-08-18 21:56 ` Alex Deucher
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=2edaef45-504a-b1c7-28e4-adc0d030715a@amd.com \
--to=lijo.lazar@amd.com \
--cc=Alexander.Deucher@amd.com \
--cc=Christian.Koenig@amd.com \
--cc=Evan.Quan@amd.com \
--cc=James.Zhu@amd.com \
--cc=Leo.Liu@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=dri-devel@lists.freedesktop.org \
--cc=michel@daenzer.net \
/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