On Mon, 19 Aug 2019 at 17:45, Chris Wilson <[email protected]> wrote: > > Inside gtt_restore_mappings() we currently take the obj->resv->lock, but > in the future we need to avoid taking this fs-reclaim tainted lock as we > need to extend the coverage of the vm->mutex. Take advantage of the > single-threaded nature of the early resume phase, and do a single > wbinvd() to flush all the GTT objects en masse. > > Signed-off-by: Chris Wilson <[email protected]> Reviewed-by: Matthew Auld <[email protected]> _______________________________________________ Intel-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/intel-gfx
- [Intel-gfx] [PATCH 01/10] drm/i915: Use 0 for the unordered c... Chris Wilson
- [Intel-gfx] [PATCH 03/10] drm/i915: Assume exclusive acc... Chris Wilson
- Re: [Intel-gfx] [PATCH 03/10] drm/i915: Assume exclu... Matthew Auld
- [Intel-gfx] [PATCH 02/10] drm/i915: Generalise the clflu... Chris Wilson
- Re: [Intel-gfx] [PATCH 02/10] drm/i915: Generalise t... Matthew Auld
- Re: [Intel-gfx] [PATCH 02/10] drm/i915: Generali... Chris Wilson
- [Intel-gfx] [PATCH 09/10] drm/i915: Make shrink/unshrink... Chris Wilson
- [Intel-gfx] [PATCH 10/10] drm/i915: Be defensive when st... Chris Wilson
- [Intel-gfx] [PATCH 06/10] drm/i915: Only track bound ele... Chris Wilson
- [Intel-gfx] [PATCH 05/10] drm/i915: Track ggtt fence res... Chris Wilson
- [Intel-gfx] [PATCH 04/10] drm/i915: Replace PIN_NONFAULT... Chris Wilson
- [Intel-gfx] [PATCH 08/10] drm/i915: Replace i915_vma_put... Chris Wilson
- [Intel-gfx] [PATCH 07/10] drm/i915: Pull obj->userfau... Chris Wilson
