[Intel-gfx] [PATCH 10/19] drm/i915: support 1G pages for the 48b PPGTT
Chris Wilson
chris at chris-wilson.co.uk
Wed Jun 21 21:49:07 UTC 2017
Quoting Matthew Auld (2017-06-21 21:33:36)
> Support inserting 1G gtt pages into the 48b PPGTT.
>
> Signed-off-by: Matthew Auld <matthew.auld at intel.com>
> Cc: Joonas Lahtinen <joonas.lahtinen at linux.intel.com>
> ---
> drivers/gpu/drm/i915/i915_gem_gtt.c | 72 ++++++++++++++++++++++++++++++++++---
> drivers/gpu/drm/i915/i915_gem_gtt.h | 2 ++
> 2 files changed, 70 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
> index de67084d5fcf..6fe10ee7dca8 100644
> --- a/drivers/gpu/drm/i915/i915_gem_gtt.c
> +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
> @@ -922,6 +922,65 @@ static void gen8_ppgtt_insert_3lvl(struct i915_address_space *vm,
> cache_level);
> }
>
> +static void gen8_ppgtt_insert_huge_entries(struct i915_vma *vma,
> + struct i915_page_directory_pointer **pdps,
> + struct sgt_dma *iter,
> + enum i915_cache_level cache_level)
> +{
> + const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level);
> + u64 start = vma->node.start;
> +
> + do {
> + struct gen8_insert_pte idx = gen8_insert_pte(start);
> + struct i915_page_directory_pointer *pdp = pdps[idx.pml4e];
> + struct i915_page_directory *pd = pdp->page_directory[idx.pdpe];
> + struct i915_page_table *pt = pd->page_table[idx.pde];
> + dma_addr_t rem = iter->max - iter->dma;
> + unsigned int page_size;
> + gen8_pte_t encode = pte_encode;
> + gen8_pte_t *vaddr;
> + u16 index, max;
> +
> + if (unlikely(vma->page_sizes.sg & I915_GTT_PAGE_SIZE_1G) &&
> + IS_ALIGNED(iter->dma, I915_GTT_PAGE_SIZE_1G) &&
> + rem >= I915_GTT_PAGE_SIZE_1G && !(idx.pte | idx.pde)) {
> + vaddr = kmap_atomic_px(pdp);
> + index = idx.pdpe;
> + max = GEN8_PML4ES_PER_PML4;
> + page_size = I915_GTT_PAGE_SIZE_1G;
> + encode |= GEN8_PDPE_PS_1G;
> + } else {
> + vaddr = kmap_atomic_px(pt);
> + index = idx.pte;
> + max = GEN8_PTES;
> + page_size = I915_GTT_PAGE_SIZE;
> + }
> +
> + do {
> + vaddr[index++] = encode | iter->dma;
> +
> + start += page_size;
> + iter->dma += page_size;
> + if (iter->dma >= iter->max) {
> + iter->sg = __sg_next(iter->sg);
> + if (!iter->sg)
> + break;
> +
> + iter->dma = sg_dma_address(iter->sg);
> + iter->max = iter->dma + iter->sg->length;
> +
> + if (unlikely(!IS_ALIGNED(iter->dma, page_size)))
> + break;
> + }
> + rem = iter->max - iter->dma;
> +
> + } while (rem >= page_size && index < max);
Where does idx advance?
> +
> + kunmap_atomic(vaddr);
> +
> + } while (iter->sg);
> +}
More information about the Intel-gfx
mailing list