Re: [PATCH 1/3] drm/amdgpu: Fix hard hang for S/G display BOs.

2019-07-24 Thread Michel Dänzer
On 2019-07-23 7:31 p.m., Grodzovsky, Andrey wrote: > On 7/23/19 12:18 PM, Michel Dänzer wrote: >> >> Anyway, this should be handled in amdgpu_display_supported_domains >> instead (e.g. by not allowing GTT if CONFIG_X86_32 is defined), > > > We have drm_arch_can_wc_memory function to cover all the

Re: [PATCH 1/3] drm/amdgpu: Fix hard hang for S/G display BOs.

2019-07-23 Thread Grodzovsky, Andrey
On 7/23/19 12:18 PM, Michel Dänzer wrote: > On 2019-07-23 6:04 p.m., Andrey Grodzovsky wrote: >> HW requires for caching to be unset for scanout BO >> mappings when the BO placement is in GTT memory. >> Usually the flag to unset is passed from user mode >> but for FB mode this was missing. >> >> S

Re: [PATCH 1/3] drm/amdgpu: Fix hard hang for S/G display BOs.

2019-07-23 Thread Michel Dänzer
On 2019-07-23 6:04 p.m., Andrey Grodzovsky wrote: > HW requires for caching to be unset for scanout BO > mappings when the BO placement is in GTT memory. > Usually the flag to unset is passed from user mode > but for FB mode this was missing. > > Suggested-by: Alex Deucher > Signed-off-by: Andrey

[PATCH 1/3] drm/amdgpu: Fix hard hang for S/G display BOs.

2019-07-23 Thread Andrey Grodzovsky
HW requires for caching to be unset for scanout BO mappings when the BO placement is in GTT memory. Usually the flag to unset is passed from user mode but for FB mode this was missing. Suggested-by: Alex Deucher Signed-off-by: Andrey Grodzovsky Reviewed-by: Alex Deucher Tested-by: Shirish S --