nv-tegra-mirror/linux-nvgpu
1
0
Fork 0
mirror of git://nv-tegra.nvidia.com/linux-nvgpu.git synced 2025-12-25 02:52:51 +03:00
Code Issues Packages Projects Releases Wiki Activity

gpu: nvgpu: cde: Allow large surfaces

Browse Source 
Currently cde swizzling application forces upper limit to surface
size. The limitation is artificial (i.e. nothing prevents shader
handling larger surfaces). Therefore, make the error condition a
warning.

Change-Id: I8f0cda7f2e9e9ecc90589e5a4b4091abcb513482
Signed-off-by: Arto Merilainen <amerilainen@nvidia.com>
Reviewed-on: http://git-master/r/454591
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
This commit is contained in:
Arto Merilainen
2014-08-08 22:49:17 +03:00
committed by Dan Willemsen
parent dde83cb0d2
commit 42d37357f8
1 changed files with 3 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
drivers/gpu/nvgpu/gk20a/cde_gk20a.c
View File

@@ -1013,10 +1013,9 @@ static int gk20a_buffer_convert_gpu_to_cde(
const int gridw = roundup(tilepitch, wgx) / wgx;
const int gridh = roundup(ytilesaligned, wgy) / wgy;
if (xtiles > 4096 / 8 || ytiles > 4096 / 8) {
gk20a_warn(&g->dev->dev, "cde: too large surface");
return -EINVAL;
}
if (xtiles > 4096 / 8 || ytiles > 4096 / 8)
gk20a_warn(&g->dev->dev, "cde: surface is exceptionally large (xtiles=%d, ytiles=%d)",
xtiles, ytiles);
gk20a_dbg(gpu_dbg_cde, "w=%d, h=%d, bh_log2=%d, compbits_offset=0x%llx",
width, height, block_height_log2, compbits_offset);