[PATCH v11 2/2] gpu/tests/buddy: add dirty tracker performance KUnit test

Add gpu_test_buddy_dirty_tracker_performance to demonstrate the key
advantage of the decoupled dirty-tracker design over the old dual-tree
/ force_merge approach.

The test runs two scenarios on a 4 GiB pool after alternating
clear/dirty fragmentation at 4 KiB granularity:

  1. Contiguous 2 GiB alloc: smaller than the 4 GiB span so it routes
     through the contiguous allocator rather than the exact-range fast
     path.  The old design requires __force_merge() to rebuild the
     block; the new design coalesces during free() so the alloc is
     O(log N).

       old (force_merge) - 45 ms
       dirty tracker design - 11 ms

  2. Repeated 256 KiB alloc throughput: the old design pays
     __force_merge() on every alloc; the new design does not.

       old (force_merge) - 86 ms
       dirty tracker design - 20 ms

v2:
 - Force a contiguous 256 KiB allocation in the repeated-alloc loop so
   the baseline actually exercises __force_merge(). (sashiko)

v3:
 - Make the first test allocate 2 GiB instead of the full 4 GiB pool,
   so it really uses the contiguous path; update the numbers. (sashiko)

Assisted-by: Claude:claude-opus-4-8
Cc: Matthew Auld <[email protected]>
Cc: Christian König <[email protected]>
Signed-off-by: Arunpravin Paneer Selvam <[email protected]>
Reviewed-by: Matthew Auld <[email protected]>
---
 drivers/gpu/tests/gpu_buddy_test.c | 116 +++++++++++++++++++++++++++++
 1 file changed, 116 insertions(+)

diff --git a/drivers/gpu/tests/gpu_buddy_test.c b/drivers/gpu/tests/gpu_buddy_test.c
index 6ce485eae83e..b75d32ca6ca0 100644
--- a/drivers/gpu/tests/gpu_buddy_test.c
+++ b/drivers/gpu/tests/gpu_buddy_test.c
@@ -283,6 +283,121 @@ static void gpu_test_buddy_fragmentation_performance(struct kunit *test)
 	gpu_buddy_fini(&mm);
 }
 
+static void gpu_test_buddy_dirty_tracker_performance(struct kunit *test)
+{
+	struct gpu_buddy_block *block, *tmp;
+	unsigned long elapsed_ms;
+	LIST_HEAD(clear_blocks);
+	LIST_HEAD(dirty_blocks);
+	LIST_HEAD(allocated);
+	struct gpu_buddy mm;
+	LIST_HEAD(results);
+	ktime_t start, end;
+	int i, count;
+
+	/*
+	 * Contiguous alloc latency after alternating clear/dirty fragmentation
+	 *
+	 * Fill a 4 GiB pool with 4 KiB allocations, partition them into
+	 * alternating cleared and dirty sets, then free both.  In the old
+	 * dual-tree design every adjacent buddy pair has one cleared half and
+	 * one dirty half, so the pair sits on opposite sides of the clear/dirty
+	 * merge barrier and cannot be coalesced at free() time.  The pool
+	 * stays fully fragmented and the subsequent contiguous 2 GiB allocation
+	 * (smaller than the 4 GiB span so it routes through the contiguous
+	 * allocator rather than the exact-range fast path) has to invoke
+	 * __force_merge() to rebuild a 2 GiB block before it can succeed.  With
+	 * the dirty-tracker design buddy pairs coalesce unconditionally during
+	 * free(), so the pool is already at max_order before the timed alloc
+	 * begins and __force_merge() is not needed.
+	 */
+	KUNIT_ASSERT_FALSE_MSG(test, gpu_buddy_init(&mm, SZ_4G, SZ_4K),
+			       "buddy_init failed\n");
+
+	for (i = 0; i < SZ_4G / SZ_4K; i++)
+		KUNIT_ASSERT_FALSE_MSG(test,
+				       gpu_buddy_alloc_blocks(&mm, 0, SZ_4G, SZ_4K, SZ_4K,
+							      &allocated, 0),
+				       "buddy_alloc hit an error size=%u\n", SZ_4K);
+
+	count = 0;
+	list_for_each_entry_safe(block, tmp, &allocated, link) {
+		if (count++ % 2 == 0)
+			list_move_tail(&block->link, &clear_blocks);
+		else
+			list_move_tail(&block->link, &dirty_blocks);
+	}
+
+	gpu_buddy_free_list(&mm, &clear_blocks, GPU_BUDDY_CLEARED);
+	gpu_buddy_free_list(&mm, &dirty_blocks, 0);
+
+	start = ktime_get();
+	KUNIT_ASSERT_FALSE_MSG(test,
+			       gpu_buddy_alloc_blocks(&mm, 0, SZ_4G, SZ_2G, SZ_2G,
+						      &results,
+						      GPU_BUDDY_CONTIGUOUS_ALLOCATION),
+			       "contiguous alloc failed\n");
+	end = ktime_get();
+	elapsed_ms = ktime_to_ms(ktime_sub(end, start));
+
+	kunit_info(test, "Contiguous alloc after fragmentation: %lu ms\n",
+		   elapsed_ms);
+
+	gpu_buddy_free_list(&mm, &results, 0);
+	gpu_buddy_fini(&mm);
+
+	/*
+	 * Repeated alloc throughput from a maximally fragmented pool
+	 *
+	 * Fill a 4 GiB pool with 4 KiB allocations, free even-indexed blocks
+	 * as cleared and odd-indexed blocks as dirty.  The alternating pattern
+	 * ensures every adjacent buddy pair has one cleared half and one dirty
+	 * half, so each pair lands on opposite sides of the old merge barrier.
+	 * Each of the 16 384 x 256 KiB allocations in the timed loop asks for a
+	 * single contiguous block (size == min_block_size, CONTIGUOUS flag), so
+	 * it cannot be satisfied by 64 stray 4 KiB blocks: under the old design
+	 * every alloc has to pay the __force_merge() cost to rebuild a 256 KiB
+	 * block.  With the dirty-tracker design the pool collapses to one
+	 * max_order block during free(), so each alloc is a simple O(log N)
+	 * split.
+	 */
+	KUNIT_ASSERT_FALSE_MSG(test, gpu_buddy_init(&mm, SZ_4G, SZ_4K),
+			       "buddy_init failed\n");
+
+	for (i = 0; i < SZ_4G / SZ_4K; i++)
+		KUNIT_ASSERT_FALSE_MSG(test,
+				       gpu_buddy_alloc_blocks(&mm, 0, SZ_4G, SZ_4K, SZ_4K,
+							      &allocated, 0),
+				       "buddy_alloc hit an error size=%u\n", SZ_4K);
+
+	count = 0;
+	list_for_each_entry_safe(block, tmp, &allocated, link) {
+		if (count++ % 2 == 0)
+			list_move_tail(&block->link, &clear_blocks);
+		else
+			list_move_tail(&block->link, &dirty_blocks);
+	}
+
+	gpu_buddy_free_list(&mm, &clear_blocks, GPU_BUDDY_CLEARED);
+	gpu_buddy_free_list(&mm, &dirty_blocks, 0);
+
+	start = ktime_get();
+	for (i = 0; i < SZ_4G / SZ_256K; i++)
+		KUNIT_ASSERT_FALSE_MSG(test,
+				       gpu_buddy_alloc_blocks(&mm, 0, SZ_4G, SZ_256K, SZ_256K,
+							      &results,
+							      GPU_BUDDY_CONTIGUOUS_ALLOCATION),
+				       "buddy_alloc hit an error size=%u\n", SZ_256K);
+	end = ktime_get();
+	elapsed_ms = ktime_to_ms(ktime_sub(end, start));
+
+	kunit_info(test, "Repeated 256 KiB allocs from fragmented pool: %lu ms\n",
+		   elapsed_ms);
+
+	gpu_buddy_free_list(&mm, &results, 0);
+	gpu_buddy_fini(&mm);
+}
+
 static void gpu_test_buddy_alloc_range_bias(struct kunit *test)
 {
 	u32 mm_size, size, ps, bias_size, bias_start, bias_end, bias_rem;
@@ -1492,6 +1607,7 @@ static struct kunit_case gpu_buddy_tests[] = {
 	KUNIT_CASE(gpu_test_buddy_alloc_range),
 	KUNIT_CASE(gpu_test_buddy_alloc_range_bias),
 	KUNIT_CASE_SLOW(gpu_test_buddy_fragmentation_performance),
+	KUNIT_CASE_SLOW(gpu_test_buddy_dirty_tracker_performance),
 	KUNIT_CASE(gpu_test_buddy_alloc_exceeds_max_order),
 	KUNIT_CASE(gpu_test_buddy_offset_aligned_allocation),
 	KUNIT_CASE(gpu_test_buddy_subtree_offset_alignment_stress),
-- 
2.34.1