[Intel-gfx] [PATCH v2 3/5] drm/i915: Encourage our shrinker more when our shmemfs allocations fails

[Chris Wilson]

Commit 24f8e00a8a2e ("drm/i915: Prefer to report ENOMEM rather than
incur the oom for gfx allocations") made the bold decision to try and
avoid the oomkiller by reporting -ENOMEM to userspace if our allocation
failed after attempting to free enough buffer objects. In short, it
appears we were giving up too easily (even before we start wondering if
one pass of reclaim is as strong as we would like). Part of the problem
is that if we only shrink just enough pages for our expected allocation,
the likelihood of those pages becoming available to us is less than 100%
To counter-act that we ask for twice the number of pages to be made
available. Furthermore, we allow the shrinker to pull pages from the
active list in later passes.

Fixes: 24f8e00a8a2e ("drm/i915: Prefer to report ENOMEM rather than incur the oom for gfx allocations")
Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen at linux.intel.com>
Cc: Daniel Vetter <daniel.vetter at ffwll.ch>
---
 drivers/gpu/drm/i915/i915_gem.c | 52 ++++++++++++++++++++++++-----------------
 1 file changed, 31 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index a637cc05cc4a..62f8d1492c2d 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2337,8 +2337,8 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj)
 	struct page *page;
 	unsigned long last_pfn = 0;	/* suppress gcc warning */
 	unsigned int max_segment;
+	gfp_t noreclaim;
 	int ret;
-	gfp_t gfp;
 
 	/* Assert that the object is not currently in any GPU domain. As it
 	 * wasn't in the GTT, there shouldn't be any way it could have been in
@@ -2367,22 +2367,33 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj)
 	 * Fail silently without starting the shrinker
 	 */
 	mapping = obj->base.filp->f_mapping;
-	gfp = mapping_gfp_constraint(mapping, ~(__GFP_IO | __GFP_RECLAIM));
-	gfp |= __GFP_NORETRY | __GFP_NOWARN;
+	noreclaim = mapping_gfp_constraint(mapping,
+					   ~(__GFP_IO | __GFP_RECLAIM));
+	noreclaim |= __GFP_NORETRY | __GFP_NOWARN;
+
 	sg = st->sgl;
 	st->nents = 0;
 	for (i = 0; i < page_count; i++) {
-		page = shmem_read_mapping_page_gfp(mapping, i, gfp);
-		if (unlikely(IS_ERR(page))) {
-			i915_gem_shrink(dev_priv,
-					page_count,
-					I915_SHRINK_BOUND |
-					I915_SHRINK_UNBOUND |
-					I915_SHRINK_PURGEABLE);
+		const unsigned int shrink[] = {
+			I915_SHRINK_BOUND | I915_SHRINK_UNBOUND | I915_SHRINK_PURGEABLE,
+			I915_SHRINK_BOUND | I915_SHRINK_UNBOUND | I915_SHRINK_PURGEABLE | I915_SHRINK_ACTIVE,
+			I915_SHRINK_BOUND | I915_SHRINK_UNBOUND | I915_SHRINK_ACTIVE,
+			0,
+		}, *s = shrink;
+		gfp_t gfp = noreclaim;
+
+		do {
 			page = shmem_read_mapping_page_gfp(mapping, i, gfp);
-		}
-		if (unlikely(IS_ERR(page))) {
-			gfp_t reclaim;
+			if (likely(!IS_ERR(page)))
+				break;
+
+			if (!*s) {
+				ret = PTR_ERR(page);
+				goto err_sg;
+			}
+
+			i915_gem_shrink(dev_priv, 2 * page_count, *s++);
+			cond_resched();
 
 			/* We've tried hard to allocate the memory by reaping
 			 * our own buffer, now let the real VM do its job and
@@ -2392,15 +2403,13 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj)
 			 * defer the oom here by reporting the ENOMEM back
 			 * to userspace.
 			 */
-			reclaim = mapping_gfp_mask(mapping);
-			reclaim |= __GFP_NORETRY; /* reclaim, but no oom */
-
-			page = shmem_read_mapping_page_gfp(mapping, i, reclaim);
-			if (IS_ERR(page)) {
-				ret = PTR_ERR(page);
-				goto err_sg;
+			if (!*s) {
+				/* reclaim and warn, but no oom */
+				gfp = mapping_gfp_mask(mapping);
+				gfp |= __GFP_NORETRY;
 			}
-		}
+		} while (1);
+
 		if (!i ||
 		    sg->length >= max_segment ||
 		    page_to_pfn(page) != last_pfn + 1) {
@@ -4281,6 +4290,7 @@ i915_gem_object_create(struct drm_i915_private *dev_priv, u64 size)
 
 	mapping = obj->base.filp->f_mapping;
 	mapping_set_gfp_mask(mapping, mask);
+	GEM_BUG_ON(!(mapping_gfp_mask(mapping) & __GFP_RECLAIM));
 
 	i915_gem_object_init(obj, &i915_gem_object_ops);
 
-- 
2.11.0