Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH v2 1/2] gpu/buddy: fix missing split-undo on allocation-search exhaustion
@ 2026-09-29 10:54 Arunpravin Paneer Selvam
  2026-09-29 10:54 ` [PATCH v2 2/2] gpu/buddy: add range-restricted contiguous allocation fallback Arunpravin Paneer Selvam
                   ` (4 more replies)
  0 siblings, 5 replies; 7+ messages in thread
From: Arunpravin Paneer Selvam @ 2026-09-29 10:54 UTC (permalink / raw)
  To: matthew.auld, dri-devel, intel-gfx, intel-xe, amd-gfx
  Cc: christian.koenig, alexander.deucher, Anand.Raghavendra,
	Arunpravin Paneer Selvam

From: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam@amd.com>

__alloc_range_bias() only undid splits made during its search when
split_block() itself failed. Its DFS-exhaustion failure path (-ENOSPC,
when no suitable block is found) skipped the undo, leaving the buddy
tree needlessly fragmented over repeated failed allocation attempts.

Fix by recording every successful split_block() call in a list and
unconditionally undoing those splits on every failure exit, via a
new single-level gpu_buddy_merge_one_level() helper (the original
__gpu_buddy_undo_splits() cascaded merges upward, which is unsafe
when called per split-list entry).

Resolves the igt@kms_plane@plane-panning-bottom-right@pipe-a/pipe-b
regression.

v2:
 - Drop the undo from __alloc_range(): it allocates every block it walks,
   so freeing that list on failure already merges the splits. (Matthew)

Fixes: 1ad5e807f716 ("gpu/buddy: replace dual-tree/force_merge with decoupled dirty tracker")
Assisted-by: Claude:claude-opus-4-8
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Christian König <christian.koenig@amd.com>
Signed-off-by: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam@amd.com>
---
 drivers/gpu/buddy.c | 54 +++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 52 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/buddy.c b/drivers/gpu/buddy.c
index 2f2aaadafe35..e5c9e21cd077 100644
--- a/drivers/gpu/buddy.c
+++ b/drivers/gpu/buddy.c
@@ -1240,6 +1240,52 @@ static void __gpu_buddy_undo_splits(struct gpu_buddy *mm,
 	}
 }
 
+static void gpu_buddy_merge_one_level(struct gpu_buddy *mm,
+				      struct gpu_buddy_block *block)
+{
+	struct gpu_buddy_block *buddy = __get_buddy(block);
+	struct gpu_buddy_block *parent = block->parent;
+	enum gpu_block_state block_state;
+
+	if (!buddy || !gpu_buddy_block_is_free(block) ||
+	    !gpu_buddy_block_is_free(buddy))
+		return;
+
+	block_state = gpu_block_cached_state(block);
+	if (gpu_block_cached_state(buddy) != block_state)
+		block_state = GPU_BLOCK_MIXED;
+
+	rbtree_remove(mm, block);
+	rbtree_remove(mm, buddy);
+	mm->free_scoreboard[gpu_buddy_block_order(block)] -= 2;
+
+	gpu_block_free(mm, block);
+	gpu_block_free(mm, buddy);
+
+	__mark_free(mm, parent, block_state);
+}
+
+static void gpu_buddy_undo_splits(struct gpu_buddy *mm,
+				  struct gpu_buddy_block *block,
+				  struct list_head *splits)
+{
+	if (block)
+		gpu_buddy_merge_one_level(mm, block);
+
+	while (!list_empty(splits)) {
+		struct gpu_buddy_block *parent =
+			list_first_entry(splits, struct gpu_buddy_block,
+					 tmp_link);
+
+		list_del(&parent->tmp_link);
+
+		if (!gpu_buddy_block_is_split(parent))
+			continue;
+
+		gpu_buddy_merge_one_level(mm, parent->left);
+	}
+}
+
 static struct gpu_buddy_block *
 __alloc_range_bias(struct gpu_buddy *mm,
 		   u64 start, u64 end,
@@ -1249,6 +1295,7 @@ __alloc_range_bias(struct gpu_buddy *mm,
 	u64 req_size = mm->chunk_size << order;
 	struct gpu_buddy_block *block;
 	LIST_HEAD(dfs);
+	LIST_HEAD(splits);
 	int err;
 	int i;
 
@@ -1313,6 +1360,8 @@ __alloc_range_bias(struct gpu_buddy *mm,
 			err = split_block(mm, block);
 			if (unlikely(err))
 				goto err_undo;
+
+			list_add(&block->tmp_link, &splits);
 		}
 
 		/*
@@ -1349,7 +1398,7 @@ __alloc_range_bias(struct gpu_buddy *mm,
 		}
 	} while (1);
 
-	return ERR_PTR(-ENOSPC);
+	err = -ENOSPC;
 
 err_undo:
 	/*
@@ -1357,7 +1406,8 @@ __alloc_range_bias(struct gpu_buddy *mm,
 	 * bigger is better, so make sure we merge everything back before we
 	 * free the allocated blocks.
 	 */
-	__gpu_buddy_undo_splits(mm, block);
+	gpu_buddy_undo_splits(mm, block, &splits);
+
 	return ERR_PTR(err);
 }
 

base-commit: 90780f2c3d30187116128f71bcf92c8ab63400e7
-- 
2.43.0


^ permalink raw reply related	[flat|nested] 7+ messages in thread
end of thread, other threads:[~2026-09-30  6:13 UTC | newest]

Thread overview: 7+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-09-29 10:54 [PATCH v2 1/2] gpu/buddy: fix missing split-undo on allocation-search exhaustion Arunpravin Paneer Selvam
2026-09-29 10:54 ` [PATCH v2 2/2] gpu/buddy: add range-restricted contiguous allocation fallback Arunpravin Paneer Selvam
2026-09-29 11:22 ` ✓ CI.KUnit: success for series starting with [v2,1/2] gpu/buddy: fix missing split-undo on allocation-search exhaustion Patchwork
2026-09-29 11:45 ` [PATCH v2 1/2] " Matthew Auld
2026-09-30  6:13   ` Arunpravin Paneer Selvam
2026-09-29 12:21 ` ✓ Xe.CI.BAT: success for series starting with [v2,1/2] " Patchwork
2026-09-29 13:45 ` ✗ Xe.CI.FULL: failure " Patchwork

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox