[PATCH] drm/radeon: Take IH ring into account for test size calculation.

[PATCH] drm/radeon: Take IH ring into account for test size calculation.

[Michel Dänzer]

From: Michel Dänzer <michel.daenzer@amd.com>

Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
---
 drivers/gpu/drm/radeon/radeon_test.c |   10 +++++++---
 1 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_test.c b/drivers/gpu/drm/radeon/radeon_test.c
index dee4a0c..1ebd0fe 100644
--- a/drivers/gpu/drm/radeon/radeon_test.c
+++ b/drivers/gpu/drm/radeon/radeon_test.c
@@ -40,10 +40,14 @@ void radeon_test_moves(struct radeon_device *rdev)
 	size = 1024 * 1024;
 
 	/* Number of tests =
-	 * (Total GTT - IB pool - writeback page - ring buffer) / test size
+	 * (Total GTT - IB pool - writeback page - ring buffers) / test size
 	 */
-	n = ((u32)(rdev->mc.gtt_size - RADEON_IB_POOL_SIZE*64*1024 - RADEON_GPU_PAGE_SIZE -
-	     rdev->cp.ring_size)) / size;
+	n = rdev->mc.gtt_size - RADEON_IB_POOL_SIZE*64*1024 - rdev->cp.ring_size;
+	if (rdev->wb.wb_obj)
+		n -= RADEON_GPU_PAGE_SIZE;
+	if (rdev->ih.ring_obj)
+		n -= rdev->ih.ring_size;
+	n /= size;
 
 	gtt_obj = kzalloc(n * sizeof(*gtt_obj), GFP_KERNEL);
 	if (!gtt_obj) {
-- 
1.7.5.4


_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH] drm/radeon: Take IH ring into account for test size calculation.

[Alex Deucher]

2011/8/19 Michel Dänzer <michel@daenzer.net>:
> From: Michel Dänzer <michel.daenzer@amd.com>
>
> Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>

Should probably also take into account the additional CP rings we
allocate on cayman.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>

> ---
>  drivers/gpu/drm/radeon/radeon_test.c |   10 +++++++---
>  1 files changed, 7 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/gpu/drm/radeon/radeon_test.c b/drivers/gpu/drm/radeon/radeon_test.c
> index dee4a0c..1ebd0fe 100644
> --- a/drivers/gpu/drm/radeon/radeon_test.c
> +++ b/drivers/gpu/drm/radeon/radeon_test.c
> @@ -40,10 +40,14 @@ void radeon_test_moves(struct radeon_device *rdev)
>        size = 1024 * 1024;
>
>        /* Number of tests =
> -        * (Total GTT - IB pool - writeback page - ring buffer) / test size
> +        * (Total GTT - IB pool - writeback page - ring buffers) / test size
>         */
> -       n = ((u32)(rdev->mc.gtt_size - RADEON_IB_POOL_SIZE*64*1024 - RADEON_GPU_PAGE_SIZE -
> -            rdev->cp.ring_size)) / size;
> +       n = rdev->mc.gtt_size - RADEON_IB_POOL_SIZE*64*1024 - rdev->cp.ring_size;
> +       if (rdev->wb.wb_obj)
> +               n -= RADEON_GPU_PAGE_SIZE;
> +       if (rdev->ih.ring_obj)
> +               n -= rdev->ih.ring_size;
> +       n /= size;
>
>        gtt_obj = kzalloc(n * sizeof(*gtt_obj), GFP_KERNEL);
>        if (!gtt_obj) {
> --
> 1.7.5.4
>
>
> _______________________________________________
> dri-devel mailing list
> dri-devel@lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/dri-devel
>

Re: [PATCH] drm/radeon: Take IH ring into account for test size calculation.

[Michel Dänzer]

On Fre, 2011-08-19 at 14:59 -0400, Alex Deucher wrote: 
> 2011/8/19 Michel Dänzer <michel@daenzer.net>:
> > From: Michel Dänzer <michel.daenzer@amd.com>
> >
> > Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
> 
> Should probably also take into account the additional CP rings we
> allocate on cayman.

Thanks for the heads up.

As we'd probably keep missing new additions like that, I'll post a
followup patch to just silently abort on BO allocation/pinning failure
instead.


-- 
Earthling Michel Dänzer           |                   http://www.amd.com
Libre software enthusiast         |          Debian, X and DRI developer
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel