* [PATCH] drm/amdgpu: disable KIQ IB tests on Polaris for now
@ 2018-09-19 9:59 Christian König
[not found] ` <20180919095908.1163-1-christian.koenig-5C7GfCeVMHo@public.gmane.org>
0 siblings, 1 reply; 2+ messages in thread
From: Christian König @ 2018-09-19 9:59 UTC (permalink / raw)
To: amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW, tom.stdenis-5C7GfCeVMHo
KIQ interrupts doesn't seem to work on Polaris.
Signed-off-by: Christian König <christian.koenig@amd.com>
---
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 470dc80f4fe7..5e6a8af380af 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -885,6 +885,12 @@ static int gfx_v8_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
uint32_t tmp;
long r;
+ /* Disable the KIQ IB test on Polaris for now because interrupts doesn't
+ * work as they should.
+ */
+ if (ring == &adev->gfx.kiq.ring && adev->asic_type >= CHIP_POLARIS10)
+ return 0;
+
r = amdgpu_device_wb_get(adev, &index);
if (r) {
dev_err(adev->dev, "(%ld) failed to allocate wb slot\n", r);
--
2.17.1
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply related [flat|nested] 2+ messages in thread
* Re: [PATCH] drm/amdgpu: disable KIQ IB tests on Polaris for now
[not found] ` <20180919095908.1163-1-christian.koenig-5C7GfCeVMHo@public.gmane.org>
@ 2018-09-19 15:27 ` Alex Deucher
0 siblings, 0 replies; 2+ messages in thread
From: Alex Deucher @ 2018-09-19 15:27 UTC (permalink / raw)
To: Christian König; +Cc: Tom St Denis, amd-gfx list
On Wed, Sep 19, 2018 at 5:59 AM Christian König
<ckoenig.leichtzumerken@gmail.com> wrote:
>
> KIQ interrupts doesn't seem to work on Polaris.
>
> Signed-off-by: Christian König <christian.koenig@amd.com>
Maybe just skip IB tests for KIQ in general. I don't think we ever
submit IBs to the KIQ anyway. As long as the ring test passes, I
think we are fine.
IIRC, KIQ doesn't use the EOP interrupts (don't remember if it
supports it or not), we use some other CP interrupt.
Alex
> ---
> drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 6 ++++++
> 1 file changed, 6 insertions(+)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
> index 470dc80f4fe7..5e6a8af380af 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
> @@ -885,6 +885,12 @@ static int gfx_v8_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
> uint32_t tmp;
> long r;
>
> + /* Disable the KIQ IB test on Polaris for now because interrupts doesn't
> + * work as they should.
> + */
> + if (ring == &adev->gfx.kiq.ring && adev->asic_type >= CHIP_POLARIS10)
> + return 0;
> +
> r = amdgpu_device_wb_get(adev, &index);
> if (r) {
> dev_err(adev->dev, "(%ld) failed to allocate wb slot\n", r);
> --
> 2.17.1
>
> _______________________________________________
> 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] 2+ messages in thread
end of thread, other threads:[~2018-09-19 15:27 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2018-09-19 9:59 [PATCH] drm/amdgpu: disable KIQ IB tests on Polaris for now Christian König
[not found] ` <20180919095908.1163-1-christian.koenig-5C7GfCeVMHo@public.gmane.org>
2018-09-19 15:27 ` Alex Deucher
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.