* [PATCH] drm/amdgpu: Do gpu recovery when no job is running
@ 2020-09-09 8:56 Liu ChengZhe
2020-09-09 9:13 ` Christian König
0 siblings, 1 reply; 4+ messages in thread
From: Liu ChengZhe @ 2020-09-09 8:56 UTC (permalink / raw)
To: amd-gfx
Cc: Jack Xiao, Feifei Xu, Kevin Wang, Liu ChengZhe, Tuikov Luben,
Deucher Alexander, Xiaojie Yuan, Christian König,
Hawking Zhang
In function flr_work, do gpu recovery when no job is running
instead of when some job is running. Because if there is job
in list, amdgpu_job_timedout will do the gpu recovery.
Signed-off-by: Liu ChengZhe <ChengZhe.Liu@amd.com>
---
drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c | 3 ++-
drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c | 2 +-
2 files changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
index 9c07014d9bd6..f5ce9a9f4cf5 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
@@ -262,7 +262,8 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
/* Trigger recovery for world switch failure if no TDR */
if (amdgpu_device_should_recover_gpu(adev)
- && (amdgpu_device_has_job_running(adev) || adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT))
+ && (!amdgpu_device_has_job_running(adev) ||
+ adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT))
amdgpu_device_gpu_recover(adev, NULL);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
index 9c23abf9b140..666ed99cc14b 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
@@ -283,7 +283,7 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work)
/* Trigger recovery for world switch failure if no TDR */
if (amdgpu_device_should_recover_gpu(adev)
- && (amdgpu_device_has_job_running(adev) ||
+ && (!amdgpu_device_has_job_running(adev) ||
adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT ||
adev->gfx_timeout == MAX_SCHEDULE_TIMEOUT ||
adev->compute_timeout == MAX_SCHEDULE_TIMEOUT ||
--
2.25.1
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply related [flat|nested] 4+ messages in thread
* Re: [PATCH] drm/amdgpu: Do gpu recovery when no job is running
2020-09-09 8:56 [PATCH] drm/amdgpu: Do gpu recovery when no job is running Liu ChengZhe
@ 2020-09-09 9:13 ` Christian König
2020-09-09 18:34 ` Luben Tuikov
0 siblings, 1 reply; 4+ messages in thread
From: Christian König @ 2020-09-09 9:13 UTC (permalink / raw)
To: Liu ChengZhe, amd-gfx
Cc: Jack Xiao, Feifei Xu, Kevin Wang, Tuikov Luben,
Deucher Alexander, Xiaojie Yuan, Hawking Zhang
Am 09.09.20 um 10:56 schrieb Liu ChengZhe:
> In function flr_work, do gpu recovery when no job is running
> instead of when some job is running. Because if there is job
> in list, amdgpu_job_timedout will do the gpu recovery.
Maybe write something like "Fix the logic by inverting it".
With that the patch is Acked-by: Christian König <christian.koenig@amd.com>
>
> Signed-off-by: Liu ChengZhe <ChengZhe.Liu@amd.com>
> ---
> drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c | 3 ++-
> drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c | 2 +-
> 2 files changed, 3 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
> index 9c07014d9bd6..f5ce9a9f4cf5 100644
> --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
> +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
> @@ -262,7 +262,8 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
>
> /* Trigger recovery for world switch failure if no TDR */
> if (amdgpu_device_should_recover_gpu(adev)
> - && (amdgpu_device_has_job_running(adev) || adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT))
> + && (!amdgpu_device_has_job_running(adev) ||
> + adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT))
> amdgpu_device_gpu_recover(adev, NULL);
> }
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
> index 9c23abf9b140..666ed99cc14b 100644
> --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
> +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
> @@ -283,7 +283,7 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work)
>
> /* Trigger recovery for world switch failure if no TDR */
> if (amdgpu_device_should_recover_gpu(adev)
> - && (amdgpu_device_has_job_running(adev) ||
> + && (!amdgpu_device_has_job_running(adev) ||
> adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT ||
> adev->gfx_timeout == MAX_SCHEDULE_TIMEOUT ||
> adev->compute_timeout == MAX_SCHEDULE_TIMEOUT ||
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH] drm/amdgpu: Do gpu recovery when no job is running
2020-09-09 9:13 ` Christian König
@ 2020-09-09 18:34 ` Luben Tuikov
0 siblings, 0 replies; 4+ messages in thread
From: Luben Tuikov @ 2020-09-09 18:34 UTC (permalink / raw)
To: Christian König, Liu ChengZhe, amd-gfx
Cc: Jack Xiao, Feifei Xu, Kevin Wang, Deucher Alexander,
Hawking Zhang, Xiaojie Yuan
On 2020-09-09 5:13 a.m., Christian König wrote:
> Am 09.09.20 um 10:56 schrieb Liu ChengZhe:
>> In function flr_work, do gpu recovery when no job is running
>> instead of when some job is running. Because if there is job
^a
>> in list, amdgpu_job_timedout will do the gpu recovery.
^the ^remove "the".
To become: "is a job in the list", and "will do GPU recovery."
>
> Maybe write something like "Fix the logic by inverting it".
Your commit message is fine, but as Christian pointed out,
_add_ a sentence to the commit message, possibly in a new
paragraph, simply stating that you're inverting the logic,
possibly just cutting and pasting what he wrote above.
Regards,
Luben
>
> With that the patch is Acked-by: Christian König <christian.koenig@amd.com>
>
>>
>> Signed-off-by: Liu ChengZhe <ChengZhe.Liu@amd.com>
>> ---
>> drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c | 3 ++-
>> drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c | 2 +-
>> 2 files changed, 3 insertions(+), 2 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
>> index 9c07014d9bd6..f5ce9a9f4cf5 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
>> +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
>> @@ -262,7 +262,8 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
>>
>> /* Trigger recovery for world switch failure if no TDR */
>> if (amdgpu_device_should_recover_gpu(adev)
>> - && (amdgpu_device_has_job_running(adev) || adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT))
>> + && (!amdgpu_device_has_job_running(adev) ||
>> + adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT))
>> amdgpu_device_gpu_recover(adev, NULL);
>> }
>>
>> diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
>> index 9c23abf9b140..666ed99cc14b 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
>> +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
>> @@ -283,7 +283,7 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work)
>>
>> /* Trigger recovery for world switch failure if no TDR */
>> if (amdgpu_device_should_recover_gpu(adev)
>> - && (amdgpu_device_has_job_running(adev) ||
>> + && (!amdgpu_device_has_job_running(adev) ||
>> adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT ||
>> adev->gfx_timeout == MAX_SCHEDULE_TIMEOUT ||
>> adev->compute_timeout == MAX_SCHEDULE_TIMEOUT ||
>
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply [flat|nested] 4+ messages in thread
* [PATCH] drm/amdgpu: Do gpu recovery when no job is running
@ 2020-09-09 9:32 Liu ChengZhe
0 siblings, 0 replies; 4+ messages in thread
From: Liu ChengZhe @ 2020-09-09 9:32 UTC (permalink / raw)
To: amd-gfx
Cc: Jack Xiao, Feifei Xu, Kevin Wang, Liu ChengZhe, Tuikov Luben,
Deucher Alexander, Xiaojie Yuan, Christian König,
Hawking Zhang
In function flr_work, we should do gpu recovery when no job
is running. Fix the logic by inverting it.
v2: modify the description
Signed-off-by: Liu ChengZhe <ChengZhe.Liu@amd.com>
---
drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c | 3 ++-
drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c | 2 +-
2 files changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
index 9c07014d9bd6..f5ce9a9f4cf5 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
@@ -262,7 +262,8 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
/* Trigger recovery for world switch failure if no TDR */
if (amdgpu_device_should_recover_gpu(adev)
- && (amdgpu_device_has_job_running(adev) || adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT))
+ && (!amdgpu_device_has_job_running(adev) ||
+ adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT))
amdgpu_device_gpu_recover(adev, NULL);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
index 9c23abf9b140..666ed99cc14b 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
@@ -283,7 +283,7 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work)
/* Trigger recovery for world switch failure if no TDR */
if (amdgpu_device_should_recover_gpu(adev)
- && (amdgpu_device_has_job_running(adev) ||
+ && (!amdgpu_device_has_job_running(adev) ||
adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT ||
adev->gfx_timeout == MAX_SCHEDULE_TIMEOUT ||
adev->compute_timeout == MAX_SCHEDULE_TIMEOUT ||
--
2.25.1
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply related [flat|nested] 4+ messages in thread
end of thread, other threads:[~2020-09-09 18:34 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-09-09 8:56 [PATCH] drm/amdgpu: Do gpu recovery when no job is running Liu ChengZhe
2020-09-09 9:13 ` Christian König
2020-09-09 18:34 ` Luben Tuikov
2020-09-09 9:32 Liu ChengZhe
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.