[Intel-gfx] [PATCH v2 3/3] drm/i915: Use page coloring to provide the guard page at the end of the GTT

[Chris Wilson]

As we now mark the reserved hole (drm_mm.head_node) with the special
UNEVICTABLE color, we can use the page coloring to avoid prefetching of
the CS beyond the end of the GTT.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_gem_evict.c | 10 ++++++++--
 drivers/gpu/drm/i915/i915_gem_gtt.c   | 19 ++++++++++++-------
 2 files changed, 20 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index c181b1bb3d2c..776c508cb9ae 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -258,6 +258,9 @@ int i915_gem_evict_for_node(struct i915_address_space *vm,
 	int ret = 0;
 
 	lockdep_assert_held(&vm->i915->drm.struct_mutex);
+	GEM_BUG_ON(!IS_ALIGNED(start, I915_GTT_PAGE_SIZE));
+	GEM_BUG_ON(!IS_ALIGNED(end, I915_GTT_PAGE_SIZE));
+
 	trace_i915_gem_evict_node(vm, target, flags);
 
 	/* Retire before we search the active list. Although we have
@@ -273,9 +276,11 @@ int i915_gem_evict_for_node(struct i915_address_space *vm,
 		/* Expand search to cover neighbouring guard pages (or lack!) */
 		if (start > vm->start)
 			start -= I915_GTT_PAGE_SIZE;
-		if (end < vm->start + vm->total)
-			end += I915_GTT_PAGE_SIZE;
+
+		/* Always look at the page afterwards to avoid the end-of-GTT */
+		end += I915_GTT_PAGE_SIZE;
 	}
+	GEM_BUG_ON(start >= end);
 
 	drm_mm_for_each_node_in_range(node, &vm->mm, start, end) {
 		/* If we find any non-objects (!vma), we cannot evict them */
@@ -284,6 +289,7 @@ int i915_gem_evict_for_node(struct i915_address_space *vm,
 			break;
 		}
 
+		GEM_BUG_ON(!node->allocated);
 		vma = container_of(node, typeof(*vma), node);
 
 		/* If we are using coloring to insert guard pages between
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 75cd2a56b8b4..959764394718 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2718,11 +2718,16 @@ static void i915_gtt_color_adjust(const struct drm_mm_node *node,
 				  u64 *start,
 				  u64 *end)
 {
-	if (node->color != color)
+	if (node->allocated && node->color != color)
 		*start += I915_GTT_PAGE_SIZE;
 
+	/* Also leave a space between the unallocated reserved node after the
+	 * GTT and any objects within the GTT, i.e. we use the color adjustment
+	 * to insert a guard page to prevent prefetches crossing over the
+	 * GTT boundary.
+	 */
 	node = list_next_entry(node, node_list);
-	if (node->allocated && node->color != color)
+	if (node->color != color)
 		*end -= I915_GTT_PAGE_SIZE;
 }
 
@@ -3241,14 +3246,14 @@ int i915_ggtt_init_hw(struct drm_i915_private *dev_priv)
 
 	INIT_LIST_HEAD(&dev_priv->vm_list);
 
-	/* Subtract the guard page before address space initialization to
-	 * shrink the range used by drm_mm.
+	/* Note that we use page colouring to enforce a guard page at the
+	 * end of the address space. This is required as the CS may prefetch
+	 * beyond the end of the batch buffer, across the page boundary,
+	 * and beyond the end of the GTT if we do provide a guard.
 	 */
 	mutex_lock(&dev_priv->drm.struct_mutex);
-	ggtt->base.total -= I915_GTT_PAGE_SIZE;
 	i915_address_space_init(&ggtt->base, dev_priv, "[global]");
-	ggtt->base.total += I915_GTT_PAGE_SIZE;
-	if (!HAS_LLC(dev_priv))
+	if (!HAS_LLC(dev_priv) && !USES_PPGTT(dev_priv))
 		ggtt->base.mm.color_adjust = i915_gtt_color_adjust;
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 
-- 
2.11.0