[PATCH 07/20] drm/i915: align the vma start to the largest gtt page size

[Matthew Auld]

For the 48b PPGTT try to align the vma start address to the required
page size boundary to guarantee we use said page size in the gtt. If we
are dealing with multiple page sizes, we can't guarantee anything and
just align to the largest. For soft pinning and objects which need to be
tightly packed into the lower 32bits we don't force any alignment.

v2: various improvements suggested by Chris

v3: use set_pages and better placement of page_sizes

Signed-off-by: Matthew Auld <matthew.auld at intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen at linux.intel.com>
Cc: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_gem_gtt.c |  8 ++++++++
 drivers/gpu/drm/i915/i915_vma.c     | 12 ++++++++++++
 drivers/gpu/drm/i915/i915_vma.h     |  1 +
 3 files changed, 21 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 071ba8e56606..ae362abd4729 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -221,6 +221,9 @@ static int ppgtt_set_pages(struct i915_vma *vma)
 
 	vma->pages = vma->obj->mm.pages;
 
+	vma->page_sizes.phys = vma->obj->mm.page_sizes.phys;
+	vma->page_sizes.sg = vma->obj->mm.page_sizes.sg;
+
 	return 0;
 }
 
@@ -233,6 +236,8 @@ static void clear_pages(struct i915_vma *vma)
 		kfree(vma->pages);
 	}
 	vma->pages = NULL;
+
+	memset(&vma->page_sizes, 0, sizeof(struct i915_page_sizes));
 }
 
 static gen8_pte_t gen8_pte_encode(dma_addr_t addr,
@@ -2466,6 +2471,9 @@ static int ggtt_set_pages(struct i915_vma *vma)
 	if (ret)
 		return ret;
 
+	vma->page_sizes.phys = vma->obj->mm.page_sizes.phys;
+	vma->page_sizes.sg = vma->obj->mm.page_sizes.sg;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 9517b1ce73dd..548730c5705c 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -493,6 +493,18 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 		if (ret)
 			goto err_clear;
 	} else {
+		/* We only support huge gtt pages through the 48b PPGTT,
+		 * however we also don't want to force any alignment for
+		 * objects which need to be tightly packed into the low 32bits.
+		 */
+		if (end > (1ULL << 32) &&
+		    vma->page_sizes.sg > I915_GTT_PAGE_SIZE) {
+			u64 page_alignment =
+				rounddown_pow_of_two(vma->page_sizes.sg);
+
+			alignment = max(alignment, page_alignment);
+		}
+
 		ret = i915_gem_gtt_insert(vma->vm, &vma->node,
 					  size, alignment, obj->cache_level,
 					  start, end, flags);
diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h
index 4a673fc1a432..58256aec35f8 100644
--- a/drivers/gpu/drm/i915/i915_vma.h
+++ b/drivers/gpu/drm/i915/i915_vma.h
@@ -55,6 +55,7 @@ struct i915_vma {
 	void __iomem *iomap;
 	u64 size;
 	u64 display_alignment;
+	struct i915_page_sizes page_sizes;
 
 	u32 fence_size;
 	u32 fence_alignment;
-- 
2.9.4