Am 20.04.2017 um 14:43 schrieb Alex Deucher: > On Wed, Apr 19, 2017 at 11:47 PM, Chunming Zhou <David1.Zhou at amd.com> wrote: >> Change-Id: Icdf2486a2d1116e71dc8958cda679a4a83838489 >> Signed-off-by: Chunming Zhou <David1.Zhou at amd.com> >> --- >> drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 2 +- >> 1 file changed, 1 insertion(+), 1 deletion(-) >> >> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c >> index d74a406..8f201a3 100644 >> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c >> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c >> @@ -65,7 +65,7 @@ >> #define KMS_DRIVER_PATCHLEVEL 0 >> >> int amdgpu_vram_limit = 0; >> -int amdgpu_gart_size = -1; /* auto */ >> +int amdgpu_gart_size = 3072; /* 3GB by default */ > This breaks the auto setting. Please add a global define for gtt size > (e.g., AMDGPU_DEFAULT_GTT_SIZE_MB) and switch the gmc modules to use > that rather than the hardcoded 1024ULL. I think this change isn't necessary any more. Looks like I've found and fixed the root cause of the issue with "drm/amdgpu: fix amdgpu_ttm_bo_eviction_valuable". Please test that patch if your test case now works without any additional changes. Christian. > > Alex > >> int amdgpu_moverate = -1; /* auto */ >> int amdgpu_benchmarking = 0; >> int amdgpu_testing = 0; >> -- >> 1.9.1 >> >> _______________________________________________ >> amd-gfx mailing list >> amd-gfx at lists.freedesktop.org >> https://lists.freedesktop.org/mailman/listinfo/amd-gfx > _______________________________________________ > amd-gfx mailing list > amd-gfx at lists.freedesktop.org > https://lists.freedesktop.org/mailman/listinfo/amd-gfx
