While support for 48b ppgtt is here, parameter enabling it is not known
to the sanitize function. Let's update it to allow selecting
full_48bit_ppgtt using module parameter.
Cc: Michel Thierry
Cc: Mika Kuoppala
Signed-off-by: Michał Winiarski
---
drivers/gpu/drm/i915/i915_gem_gtt.
using softpin.
Michał Winiarski (1):
drm/i915/gtt: Allow adventurous users to select enable_ppgtt=3
is not strictly necessary for softpin itself, but it is needed for SVM usecase.
Chris Wilson (1):
drm/i915: Add soft-pinning API for execbuffer
is just v5 from Thomas Daniel rebased on top of cu
ichel Thierry
Cc: Ben Widawsky
Cc: Chris Wilson
Signed-off-by: Michał Winiarski
---
include/drm/i915_drm.h| 4 +-
intel/intel_bufmgr.c | 9 +++
intel/intel_bufmgr.h | 1 +
intel/intel_bufmgr_gem.c | 176 --
intel/intel_bufmgr_p
on
Signed-off-by: Thomas Daniel
Signed-off-by: Michał Winiarski
---
drivers/gpu/drm/i915/i915_dma.c| 3 ++
drivers/gpu/drm/i915/i915_drv.h| 3 ++
drivers/gpu/drm/i915/i915_gem.c| 52 ++
drivers/gpu/drm/i915/i915_gem_evict.c
---
include/drm/i915_drm.h| 3 ++-
intel/intel_bufmgr.c | 11 +++
intel/intel_bufmgr.h | 1 +
intel/intel_bufmgr_gem.c | 43 +--
intel/intel_bufmgr_priv.h | 8
5 files changed, 55 insertions(+), 11 deletions(-)
diff --git
-0xf000)
> + * General State Heap (GSH) or Intructions State Heap (ISH) must
> + * be in a 32-bit range. 48-bit range will only be used when explicitly
> + * requested.
> + */
> + void (*bo_set_supports_48b_address) (drm_intel_bo *bo);
> + void (*bo_clear_supports_48b_address) (drm_intel_bo *bo);
> +
> + /**
>* Add relocation entry in reloc_buf, which will be updated with the
>* target buffer's real offset on on command submission.
>*
> --
> 2.5.0
You also haven't updated the dump_validation_list with proper format specifier
(addresses are truncated otherwise).
I really don't like hiding set_supports_48b_address/clear_supports_48b_address
in emit reloc - making this explicit would be a better approach.
Of course this is just my opinion, but let me post a bit different version of
this API - just as an RFC so you can see how it would look with explicit set on
bo and without adding another emit_reloc variant.
--
Michał Winiarski
Intel VPG
___
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/mesa-dev
