* [PATCH 1/1] drm/ttm: Ignore signaled move fences
@ 2021-02-27 3:45 ` Felix Kuehling
0 siblings, 0 replies; 10+ messages in thread
From: Felix Kuehling @ 2021-02-27 3:45 UTC (permalink / raw)
To: dri-devel, amd-gfx
Move fences that have already signaled should not prevent memory
allocations with no_wait_gpu.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
---
drivers/gpu/drm/ttm/ttm_bo.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 3a10bebb75d6..de1ec838cf8b 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -730,8 +730,9 @@ static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo,
return 0;
if (no_wait_gpu) {
+ ret = dma_fence_is_signaled(fence) ? 0 : -EBUSY;
dma_fence_put(fence);
- return -EBUSY;
+ return ret;
}
dma_resv_add_shared_fence(bo->base.resv, fence);
--
2.30.0
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH 1/1] drm/ttm: Ignore signaled move fences
@ 2021-02-27 3:45 ` Felix Kuehling
0 siblings, 0 replies; 10+ messages in thread
From: Felix Kuehling @ 2021-02-27 3:45 UTC (permalink / raw)
To: dri-devel, amd-gfx
Move fences that have already signaled should not prevent memory
allocations with no_wait_gpu.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
---
drivers/gpu/drm/ttm/ttm_bo.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 3a10bebb75d6..de1ec838cf8b 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -730,8 +730,9 @@ static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo,
return 0;
if (no_wait_gpu) {
+ ret = dma_fence_is_signaled(fence) ? 0 : -EBUSY;
dma_fence_put(fence);
- return -EBUSY;
+ return ret;
}
dma_resv_add_shared_fence(bo->base.resv, fence);
--
2.30.0
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel
^ permalink raw reply related [flat|nested] 10+ messages in thread* Re: [PATCH 1/1] drm/ttm: Ignore signaled move fences
2021-02-27 3:45 ` Felix Kuehling
@ 2021-03-01 15:09 ` Christian König
-1 siblings, 0 replies; 10+ messages in thread
From: Christian König @ 2021-03-01 15:09 UTC (permalink / raw)
To: Felix Kuehling, dri-devel, amd-gfx
Am 27.02.21 um 04:45 schrieb Felix Kuehling:
> Move fences that have already signaled should not prevent memory
> allocations with no_wait_gpu.
>
> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
> ---
> drivers/gpu/drm/ttm/ttm_bo.c | 3 ++-
> 1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
> index 3a10bebb75d6..de1ec838cf8b 100644
> --- a/drivers/gpu/drm/ttm/ttm_bo.c
> +++ b/drivers/gpu/drm/ttm/ttm_bo.c
> @@ -730,8 +730,9 @@ static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo,
> return 0;
>
> if (no_wait_gpu) {
> + ret = dma_fence_is_signaled(fence) ? 0 : -EBUSY;
> dma_fence_put(fence);
> - return -EBUSY;
> + return ret;
> }
>
> dma_resv_add_shared_fence(bo->base.resv, fence);
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply [flat|nested] 10+ messages in thread* Re: [PATCH 1/1] drm/ttm: Ignore signaled move fences
@ 2021-03-01 15:09 ` Christian König
0 siblings, 0 replies; 10+ messages in thread
From: Christian König @ 2021-03-01 15:09 UTC (permalink / raw)
To: Felix Kuehling, dri-devel, amd-gfx
Am 27.02.21 um 04:45 schrieb Felix Kuehling:
> Move fences that have already signaled should not prevent memory
> allocations with no_wait_gpu.
>
> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
> ---
> drivers/gpu/drm/ttm/ttm_bo.c | 3 ++-
> 1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
> index 3a10bebb75d6..de1ec838cf8b 100644
> --- a/drivers/gpu/drm/ttm/ttm_bo.c
> +++ b/drivers/gpu/drm/ttm/ttm_bo.c
> @@ -730,8 +730,9 @@ static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo,
> return 0;
>
> if (no_wait_gpu) {
> + ret = dma_fence_is_signaled(fence) ? 0 : -EBUSY;
> dma_fence_put(fence);
> - return -EBUSY;
> + return ret;
> }
>
> dma_resv_add_shared_fence(bo->base.resv, fence);
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel
^ permalink raw reply [flat|nested] 10+ messages in thread* Re: [PATCH 1/1] drm/ttm: Ignore signaled move fences
2021-03-01 15:09 ` Christian König
@ 2021-03-05 1:21 ` Felix Kuehling
-1 siblings, 0 replies; 10+ messages in thread
From: Felix Kuehling @ 2021-03-05 1:21 UTC (permalink / raw)
To: Christian König, dri-devel, amd-gfx
Am 2021-03-01 um 10:09 a.m. schrieb Christian König:
> Am 27.02.21 um 04:45 schrieb Felix Kuehling:
>> Move fences that have already signaled should not prevent memory
>> allocations with no_wait_gpu.
>>
>> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
>
> Reviewed-by: Christian König <christian.koenig@amd.com>
I work on this on Alex's rebased amd-staging-drm-next. Should this go
into any other branches?
Thanks,
Felix
>
>> ---
>> drivers/gpu/drm/ttm/ttm_bo.c | 3 ++-
>> 1 file changed, 2 insertions(+), 1 deletion(-)
>>
>> diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
>> index 3a10bebb75d6..de1ec838cf8b 100644
>> --- a/drivers/gpu/drm/ttm/ttm_bo.c
>> +++ b/drivers/gpu/drm/ttm/ttm_bo.c
>> @@ -730,8 +730,9 @@ static int ttm_bo_add_move_fence(struct
>> ttm_buffer_object *bo,
>> return 0;
>> if (no_wait_gpu) {
>> + ret = dma_fence_is_signaled(fence) ? 0 : -EBUSY;
>> dma_fence_put(fence);
>> - return -EBUSY;
>> + return ret;
>> }
>> dma_resv_add_shared_fence(bo->base.resv, fence);
>
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply [flat|nested] 10+ messages in thread* Re: [PATCH 1/1] drm/ttm: Ignore signaled move fences
@ 2021-03-05 1:21 ` Felix Kuehling
0 siblings, 0 replies; 10+ messages in thread
From: Felix Kuehling @ 2021-03-05 1:21 UTC (permalink / raw)
To: Christian König, dri-devel, amd-gfx
Am 2021-03-01 um 10:09 a.m. schrieb Christian König:
> Am 27.02.21 um 04:45 schrieb Felix Kuehling:
>> Move fences that have already signaled should not prevent memory
>> allocations with no_wait_gpu.
>>
>> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
>
> Reviewed-by: Christian König <christian.koenig@amd.com>
I work on this on Alex's rebased amd-staging-drm-next. Should this go
into any other branches?
Thanks,
Felix
>
>> ---
>> drivers/gpu/drm/ttm/ttm_bo.c | 3 ++-
>> 1 file changed, 2 insertions(+), 1 deletion(-)
>>
>> diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
>> index 3a10bebb75d6..de1ec838cf8b 100644
>> --- a/drivers/gpu/drm/ttm/ttm_bo.c
>> +++ b/drivers/gpu/drm/ttm/ttm_bo.c
>> @@ -730,8 +730,9 @@ static int ttm_bo_add_move_fence(struct
>> ttm_buffer_object *bo,
>> return 0;
>> if (no_wait_gpu) {
>> + ret = dma_fence_is_signaled(fence) ? 0 : -EBUSY;
>> dma_fence_put(fence);
>> - return -EBUSY;
>> + return ret;
>> }
>> dma_resv_add_shared_fence(bo->base.resv, fence);
>
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel
^ permalink raw reply [flat|nested] 10+ messages in thread* Re: [PATCH 1/1] drm/ttm: Ignore signaled move fences
2021-03-05 1:21 ` Felix Kuehling
@ 2021-03-05 7:56 ` Christian König
-1 siblings, 0 replies; 10+ messages in thread
From: Christian König @ 2021-03-05 7:56 UTC (permalink / raw)
To: Felix Kuehling, dri-devel, amd-gfx
Am 05.03.21 um 02:21 schrieb Felix Kuehling:
> Am 2021-03-01 um 10:09 a.m. schrieb Christian König:
>> Am 27.02.21 um 04:45 schrieb Felix Kuehling:
>>> Move fences that have already signaled should not prevent memory
>>> allocations with no_wait_gpu.
>>>
>>> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
>> Reviewed-by: Christian König <christian.koenig@amd.com>
> I work on this on Alex's rebased amd-staging-drm-next. Should this go
> into any other branches?
I have a branch with stuff for 5.13 which I want to push to
drm-misc-next as soon as 5.12-rc1 is out.
Going to add this one here to that collection as well unless you say
that this is really a bug fix and we need it earlier.
Regards,
Christian.
>
> Thanks,
> Felix
>
>
>>> ---
>>> drivers/gpu/drm/ttm/ttm_bo.c | 3 ++-
>>> 1 file changed, 2 insertions(+), 1 deletion(-)
>>>
>>> diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
>>> index 3a10bebb75d6..de1ec838cf8b 100644
>>> --- a/drivers/gpu/drm/ttm/ttm_bo.c
>>> +++ b/drivers/gpu/drm/ttm/ttm_bo.c
>>> @@ -730,8 +730,9 @@ static int ttm_bo_add_move_fence(struct
>>> ttm_buffer_object *bo,
>>> return 0;
>>> if (no_wait_gpu) {
>>> + ret = dma_fence_is_signaled(fence) ? 0 : -EBUSY;
>>> dma_fence_put(fence);
>>> - return -EBUSY;
>>> + return ret;
>>> }
>>> dma_resv_add_shared_fence(bo->base.resv, fence);
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply [flat|nested] 10+ messages in thread* Re: [PATCH 1/1] drm/ttm: Ignore signaled move fences
@ 2021-03-05 7:56 ` Christian König
0 siblings, 0 replies; 10+ messages in thread
From: Christian König @ 2021-03-05 7:56 UTC (permalink / raw)
To: Felix Kuehling, dri-devel, amd-gfx
Am 05.03.21 um 02:21 schrieb Felix Kuehling:
> Am 2021-03-01 um 10:09 a.m. schrieb Christian König:
>> Am 27.02.21 um 04:45 schrieb Felix Kuehling:
>>> Move fences that have already signaled should not prevent memory
>>> allocations with no_wait_gpu.
>>>
>>> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
>> Reviewed-by: Christian König <christian.koenig@amd.com>
> I work on this on Alex's rebased amd-staging-drm-next. Should this go
> into any other branches?
I have a branch with stuff for 5.13 which I want to push to
drm-misc-next as soon as 5.12-rc1 is out.
Going to add this one here to that collection as well unless you say
that this is really a bug fix and we need it earlier.
Regards,
Christian.
>
> Thanks,
> Felix
>
>
>>> ---
>>> drivers/gpu/drm/ttm/ttm_bo.c | 3 ++-
>>> 1 file changed, 2 insertions(+), 1 deletion(-)
>>>
>>> diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
>>> index 3a10bebb75d6..de1ec838cf8b 100644
>>> --- a/drivers/gpu/drm/ttm/ttm_bo.c
>>> +++ b/drivers/gpu/drm/ttm/ttm_bo.c
>>> @@ -730,8 +730,9 @@ static int ttm_bo_add_move_fence(struct
>>> ttm_buffer_object *bo,
>>> return 0;
>>> if (no_wait_gpu) {
>>> + ret = dma_fence_is_signaled(fence) ? 0 : -EBUSY;
>>> dma_fence_put(fence);
>>> - return -EBUSY;
>>> + return ret;
>>> }
>>> dma_resv_add_shared_fence(bo->base.resv, fence);
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel
^ permalink raw reply [flat|nested] 10+ messages in thread* Re: [PATCH 1/1] drm/ttm: Ignore signaled move fences
2021-03-05 7:56 ` Christian König
@ 2021-03-05 18:20 ` Felix Kuehling
-1 siblings, 0 replies; 10+ messages in thread
From: Felix Kuehling @ 2021-03-05 18:20 UTC (permalink / raw)
To: Christian König, dri-devel, amd-gfx
It fixed an intermittent failure to allocate page tables in the page
fault handler (turning retry faults into no-retry faults). I'm not sure
if this caused real problems. I think it could potentially result in
fault storms and a failure to report page faults properly. I'm not sure
if it's a regression or was always present. So I'm not sure if it's an
urgent fix.
Regards,
Felix
Am 2021-03-05 um 2:56 a.m. schrieb Christian König:
>
>
> Am 05.03.21 um 02:21 schrieb Felix Kuehling:
>> Am 2021-03-01 um 10:09 a.m. schrieb Christian König:
>>> Am 27.02.21 um 04:45 schrieb Felix Kuehling:
>>>> Move fences that have already signaled should not prevent memory
>>>> allocations with no_wait_gpu.
>>>>
>>>> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
>>> Reviewed-by: Christian König <christian.koenig@amd.com>
>> I work on this on Alex's rebased amd-staging-drm-next. Should this go
>> into any other branches?
>
> I have a branch with stuff for 5.13 which I want to push to
> drm-misc-next as soon as 5.12-rc1 is out.
>
> Going to add this one here to that collection as well unless you say
> that this is really a bug fix and we need it earlier.
>
> Regards,
> Christian.
>
>>
>> Thanks,
>> Felix
>>
>>
>>>> ---
>>>> drivers/gpu/drm/ttm/ttm_bo.c | 3 ++-
>>>> 1 file changed, 2 insertions(+), 1 deletion(-)
>>>>
>>>> diff --git a/drivers/gpu/drm/ttm/ttm_bo.c
>>>> b/drivers/gpu/drm/ttm/ttm_bo.c
>>>> index 3a10bebb75d6..de1ec838cf8b 100644
>>>> --- a/drivers/gpu/drm/ttm/ttm_bo.c
>>>> +++ b/drivers/gpu/drm/ttm/ttm_bo.c
>>>> @@ -730,8 +730,9 @@ static int ttm_bo_add_move_fence(struct
>>>> ttm_buffer_object *bo,
>>>> return 0;
>>>> if (no_wait_gpu) {
>>>> + ret = dma_fence_is_signaled(fence) ? 0 : -EBUSY;
>>>> dma_fence_put(fence);
>>>> - return -EBUSY;
>>>> + return ret;
>>>> }
>>>> dma_resv_add_shared_fence(bo->base.resv, fence);
>
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply [flat|nested] 10+ messages in thread* Re: [PATCH 1/1] drm/ttm: Ignore signaled move fences
@ 2021-03-05 18:20 ` Felix Kuehling
0 siblings, 0 replies; 10+ messages in thread
From: Felix Kuehling @ 2021-03-05 18:20 UTC (permalink / raw)
To: Christian König, dri-devel, amd-gfx
It fixed an intermittent failure to allocate page tables in the page
fault handler (turning retry faults into no-retry faults). I'm not sure
if this caused real problems. I think it could potentially result in
fault storms and a failure to report page faults properly. I'm not sure
if it's a regression or was always present. So I'm not sure if it's an
urgent fix.
Regards,
Felix
Am 2021-03-05 um 2:56 a.m. schrieb Christian König:
>
>
> Am 05.03.21 um 02:21 schrieb Felix Kuehling:
>> Am 2021-03-01 um 10:09 a.m. schrieb Christian König:
>>> Am 27.02.21 um 04:45 schrieb Felix Kuehling:
>>>> Move fences that have already signaled should not prevent memory
>>>> allocations with no_wait_gpu.
>>>>
>>>> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
>>> Reviewed-by: Christian König <christian.koenig@amd.com>
>> I work on this on Alex's rebased amd-staging-drm-next. Should this go
>> into any other branches?
>
> I have a branch with stuff for 5.13 which I want to push to
> drm-misc-next as soon as 5.12-rc1 is out.
>
> Going to add this one here to that collection as well unless you say
> that this is really a bug fix and we need it earlier.
>
> Regards,
> Christian.
>
>>
>> Thanks,
>> Felix
>>
>>
>>>> ---
>>>> drivers/gpu/drm/ttm/ttm_bo.c | 3 ++-
>>>> 1 file changed, 2 insertions(+), 1 deletion(-)
>>>>
>>>> diff --git a/drivers/gpu/drm/ttm/ttm_bo.c
>>>> b/drivers/gpu/drm/ttm/ttm_bo.c
>>>> index 3a10bebb75d6..de1ec838cf8b 100644
>>>> --- a/drivers/gpu/drm/ttm/ttm_bo.c
>>>> +++ b/drivers/gpu/drm/ttm/ttm_bo.c
>>>> @@ -730,8 +730,9 @@ static int ttm_bo_add_move_fence(struct
>>>> ttm_buffer_object *bo,
>>>> return 0;
>>>> if (no_wait_gpu) {
>>>> + ret = dma_fence_is_signaled(fence) ? 0 : -EBUSY;
>>>> dma_fence_put(fence);
>>>> - return -EBUSY;
>>>> + return ret;
>>>> }
>>>> dma_resv_add_shared_fence(bo->base.resv, fence);
>
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel
^ permalink raw reply [flat|nested] 10+ messages in thread
end of thread, other threads:[~2021-03-05 18:20 UTC | newest]
Thread overview: 10+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2021-02-27 3:45 [PATCH 1/1] drm/ttm: Ignore signaled move fences Felix Kuehling
2021-02-27 3:45 ` Felix Kuehling
2021-03-01 15:09 ` Christian König
2021-03-01 15:09 ` Christian König
2021-03-05 1:21 ` Felix Kuehling
2021-03-05 1:21 ` Felix Kuehling
2021-03-05 7:56 ` Christian König
2021-03-05 7:56 ` Christian König
2021-03-05 18:20 ` Felix Kuehling
2021-03-05 18:20 ` Felix Kuehling
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.