We only apply the hugepage PD redirection inside the ppGTT, so during i915_vma_insert() we want to exclude the GGTT from the additional alignment constraints (thereby avoiding the extra GTT pressure from fragmentation). Add an assert to document that intention alongside the comment. v2: After discussion with Matthew, make it a blanket GGTT ban (previously we allowed the expansion for appgtt, and so indirectly ggtt). There are issues we need to fix before allowing the current appgtt to be used with hugepages, and if we do, we probably want more care over when to expand/align, as the mappable aperture inside the ggtt is precious. Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx> Cc: Matthew Auld <matthew.william.auld@xxxxxxxxx> Cc: Joonas Lahtinen <joonas.lahtinen@xxxxxxxxxxxxxxx> Reviewed-by: Matthew Auld <matthew.william.auld@xxxxxxxxx> --- drivers/gpu/drm/i915/i915_vma.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index df6b63a4dfe6..d006a35cde3b 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -538,6 +538,13 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags) rounddown_pow_of_two(vma->page_sizes.sg | I915_GTT_PAGE_SIZE_2M); + /* + * Check we don't expand for the limited Global GTT + * (mappable aperture is even more precious!). This + * also checks that we exclude the aliasing-ppgtt. + */ + GEM_BUG_ON(i915_vma_is_ggtt(vma)); + alignment = max(alignment, page_alignment); if (vma->page_sizes.sg & I915_GTT_PAGE_SIZE_64K) -- 2.14.2 _______________________________________________ Intel-gfx mailing list Intel-gfx@xxxxxxxxxxxxxxxxxxxxx https://lists.freedesktop.org/mailman/listinfo/intel-gfx
