* [PATCH] drm/amdgpu: use queue 0 for kiq ring
@ 2018-01-22 13:45 Huang Rui
[not found] ` <1516628738-16083-1-git-send-email-ray.huang-5C7GfCeVMHo@public.gmane.org>
0 siblings, 1 reply; 6+ messages in thread
From: Huang Rui @ 2018-01-22 13:45 UTC (permalink / raw)
To: Alex Deucher, amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW; +Cc: Huang Rui
It must use queue id 0, because CGPG_IDLE/SAVE/LOAD/RUN only can be issued on
queue 0.
Signed-off-by: Huang Rui <ray.huang@amd.com>
Acked-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index ef04336..0cfb939 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -179,8 +179,12 @@ static int amdgpu_gfx_kiq_acquire(struct amdgpu_device *adev,
amdgpu_gfx_bit_to_queue(adev, queue_bit, &mec, &pipe, &queue);
- /* Using pipes 2/3 from MEC 2 seems cause problems */
- if (mec == 1 && pipe > 1)
+ /*
+ * 1. Using pipes 2/3 from MEC 2 seems cause problems.
+ * 2. It must use queue id 0, because CGPG_IDLE/SAVE/LOAD/RUN
+ * only can be issued on queue 0.
+ */
+ if ((mec == 1 && pipe > 1) || queue != 0)
continue;
ring->me = mec + 1;
--
2.7.4
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply related [flat|nested] 6+ messages in thread
* Re: [PATCH] drm/amdgpu: use queue 0 for kiq ring
[not found] ` <1516628738-16083-1-git-send-email-ray.huang-5C7GfCeVMHo@public.gmane.org>
@ 2018-01-22 15:19 ` Alex Deucher
2018-01-22 17:53 ` Andres Rodriguez
2018-01-22 22:28 ` Felix Kuehling
2 siblings, 0 replies; 6+ messages in thread
From: Alex Deucher @ 2018-01-22 15:19 UTC (permalink / raw)
To: Huang Rui; +Cc: Alex Deucher, amd-gfx list
On Mon, Jan 22, 2018 at 8:45 AM, Huang Rui <ray.huang@amd.com> wrote:
> It must use queue id 0, because CGPG_IDLE/SAVE/LOAD/RUN only can be issued on
> queue 0.
>
> Signed-off-by: Huang Rui <ray.huang@amd.com>
> Acked-by: Hawking Zhang <Hawking.Zhang@amd.com>
> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c | 8 ++++++--
> 1 file changed, 6 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
> index ef04336..0cfb939 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
> @@ -179,8 +179,12 @@ static int amdgpu_gfx_kiq_acquire(struct amdgpu_device *adev,
>
> amdgpu_gfx_bit_to_queue(adev, queue_bit, &mec, &pipe, &queue);
>
> - /* Using pipes 2/3 from MEC 2 seems cause problems */
> - if (mec == 1 && pipe > 1)
> + /*
> + * 1. Using pipes 2/3 from MEC 2 seems cause problems.
> + * 2. It must use queue id 0, because CGPG_IDLE/SAVE/LOAD/RUN
> + * only can be issued on queue 0.
> + */
> + if ((mec == 1 && pipe > 1) || queue != 0)
> continue;
>
> ring->me = mec + 1;
> --
> 2.7.4
>
> _______________________________________________
> amd-gfx mailing list
> amd-gfx@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH] drm/amdgpu: use queue 0 for kiq ring
[not found] ` <1516628738-16083-1-git-send-email-ray.huang-5C7GfCeVMHo@public.gmane.org>
2018-01-22 15:19 ` Alex Deucher
@ 2018-01-22 17:53 ` Andres Rodriguez
[not found] ` <aaf8651b-6165-19b5-5508-4f3cba3f1e85-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2018-01-22 22:28 ` Felix Kuehling
2 siblings, 1 reply; 6+ messages in thread
From: Andres Rodriguez @ 2018-01-22 17:53 UTC (permalink / raw)
To: Huang Rui, Alex Deucher, amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW
Cc: andresx7-Re5JQEeQqe8AvxtiuMwx3w
On 2018-01-22 08:45 AM, Huang Rui wrote:
> It must use queue id 0, because CGPG_IDLE/SAVE/LOAD/RUN only can be issued on
> queue 0.
>
> Signed-off-by: Huang Rui <ray.huang@amd.com>
> Acked-by: Hawking Zhang <Hawking.Zhang@amd.com>
> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c | 8 ++++++--
> 1 file changed, 6 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
> index ef04336..0cfb939 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
> @@ -179,8 +179,12 @@ static int amdgpu_gfx_kiq_acquire(struct amdgpu_device *adev,
>
> amdgpu_gfx_bit_to_queue(adev, queue_bit, &mec, &pipe, &queue);
>
> - /* Using pipes 2/3 from MEC 2 seems cause problems */
> - if (mec == 1 && pipe > 1)
> + /*
> + * 1. Using pipes 2/3 from MEC 2 seems cause problems.'
Could this have been related to #2? Should we just simplify this by
guaranteeing KIQ MEC[0] PIPE[0] QUEUE[0]?
Regards,
Andres
> + * 2. It must use queue id 0, because CGPG_IDLE/SAVE/LOAD/RUN
> + * only can be issued on queue 0.
> + */
> + if ((mec == 1 && pipe > 1) || queue != 0)
> continue;
>
> ring->me = mec + 1;
>
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH] drm/amdgpu: use queue 0 for kiq ring
[not found] ` <aaf8651b-6165-19b5-5508-4f3cba3f1e85-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
@ 2018-01-22 20:49 ` Alex Deucher
0 siblings, 0 replies; 6+ messages in thread
From: Alex Deucher @ 2018-01-22 20:49 UTC (permalink / raw)
To: Andres Rodriguez; +Cc: Alex Deucher, Huang Rui, amd-gfx list
On Mon, Jan 22, 2018 at 12:53 PM, Andres Rodriguez <andresx7@gmail.com> wrote:
>
>
> On 2018-01-22 08:45 AM, Huang Rui wrote:
>>
>> It must use queue id 0, because CGPG_IDLE/SAVE/LOAD/RUN only can be issued
>> on
>> queue 0.
>>
>> Signed-off-by: Huang Rui <ray.huang@amd.com>
>> Acked-by: Hawking Zhang <Hawking.Zhang@amd.com>
>> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
>> ---
>> drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c | 8 ++++++--
>> 1 file changed, 6 insertions(+), 2 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
>> b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
>> index ef04336..0cfb939 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
>> @@ -179,8 +179,12 @@ static int amdgpu_gfx_kiq_acquire(struct
>> amdgpu_device *adev,
>> amdgpu_gfx_bit_to_queue(adev, queue_bit, &mec, &pipe,
>> &queue);
>> - /* Using pipes 2/3 from MEC 2 seems cause problems */
>> - if (mec == 1 && pipe > 1)
>> + /*
>> + * 1. Using pipes 2/3 from MEC 2 seems cause problems.'
>
>
> Could this have been related to #2? Should we just simplify this by
> guaranteeing KIQ MEC[0] PIPE[0] QUEUE[0]?
>
It's possible. Other OSes use a hardcoded config for KIQ so there may
be corner cases we never validated when using a non-standard config.
Alex
> Regards,
> Andres
>
>> + * 2. It must use queue id 0, because
>> CGPG_IDLE/SAVE/LOAD/RUN
>> + * only can be issued on queue 0.
>> + */
>> + if ((mec == 1 && pipe > 1) || queue != 0)
>> continue;
>> ring->me = mec + 1;
>>
> _______________________________________________
> amd-gfx mailing list
> amd-gfx@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH] drm/amdgpu: use queue 0 for kiq ring
[not found] ` <1516628738-16083-1-git-send-email-ray.huang-5C7GfCeVMHo@public.gmane.org>
2018-01-22 15:19 ` Alex Deucher
2018-01-22 17:53 ` Andres Rodriguez
@ 2018-01-22 22:28 ` Felix Kuehling
[not found] ` <ef29adff-9d94-9381-71ea-fcbda0ec48b5-5C7GfCeVMHo@public.gmane.org>
2 siblings, 1 reply; 6+ messages in thread
From: Felix Kuehling @ 2018-01-22 22:28 UTC (permalink / raw)
To: Huang Rui, Alex Deucher, amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW
KFD currently hard-codes MEC2, Pipe0, Queue0 for the HIQ. (For some
reason KFD numbers MECs starting from 1, not 0.)
So that narrows your choice for KIQ on MEC2 down to pipe == 1, queue == 0.
Regards,
Felix
On 2018-01-22 08:45 AM, Huang Rui wrote:
> It must use queue id 0, because CGPG_IDLE/SAVE/LOAD/RUN only can be issued on
> queue 0.
>
> Signed-off-by: Huang Rui <ray.huang@amd.com>
> Acked-by: Hawking Zhang <Hawking.Zhang@amd.com>
> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c | 8 ++++++--
> 1 file changed, 6 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
> index ef04336..0cfb939 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
> @@ -179,8 +179,12 @@ static int amdgpu_gfx_kiq_acquire(struct amdgpu_device *adev,
>
> amdgpu_gfx_bit_to_queue(adev, queue_bit, &mec, &pipe, &queue);
>
> - /* Using pipes 2/3 from MEC 2 seems cause problems */
> - if (mec == 1 && pipe > 1)
> + /*
> + * 1. Using pipes 2/3 from MEC 2 seems cause problems.
> + * 2. It must use queue id 0, because CGPG_IDLE/SAVE/LOAD/RUN
> + * only can be issued on queue 0.
> + */
> + if ((mec == 1 && pipe > 1) || queue != 0)
> continue;
>
> ring->me = mec + 1;
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH] drm/amdgpu: use queue 0 for kiq ring
[not found] ` <ef29adff-9d94-9381-71ea-fcbda0ec48b5-5C7GfCeVMHo@public.gmane.org>
@ 2018-01-23 1:11 ` Huang Rui
0 siblings, 0 replies; 6+ messages in thread
From: Huang Rui @ 2018-01-23 1:11 UTC (permalink / raw)
To: Kuehling, Felix
Cc: Deucher, Alexander, amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW
On Tue, Jan 23, 2018 at 06:28:52AM +0800, Kuehling, Felix wrote:
> KFD currently hard-codes MEC2, Pipe0, Queue0 for the HIQ. (For some
> reason KFD numbers MECs starting from 1, not 0.)
>
> So that narrows your choice for KIQ on MEC2 down to pipe == 1, queue == 0.
>
Yes, actually, we use mec2 pipe1 queue0 for KIQ at current for this patch.
Thanks
Ray
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2018-01-23 1:11 UTC | newest]
Thread overview: 6+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2018-01-22 13:45 [PATCH] drm/amdgpu: use queue 0 for kiq ring Huang Rui
[not found] ` <1516628738-16083-1-git-send-email-ray.huang-5C7GfCeVMHo@public.gmane.org>
2018-01-22 15:19 ` Alex Deucher
2018-01-22 17:53 ` Andres Rodriguez
[not found] ` <aaf8651b-6165-19b5-5508-4f3cba3f1e85-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2018-01-22 20:49 ` Alex Deucher
2018-01-22 22:28 ` Felix Kuehling
[not found] ` <ef29adff-9d94-9381-71ea-fcbda0ec48b5-5C7GfCeVMHo@public.gmane.org>
2018-01-23 1:11 ` Huang Rui
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.