drm/buddy: Implement tracking clear page feature

- Add tracking clear page feature.

- Driver should enable the DRM_BUDDY_CLEARED flag if it
  successfully clears the blocks in the free path. On the otherhand,
  DRM buddy marks each block as cleared.

- Track the available cleared pages size

- If driver requests cleared memory we prefer cleared memory
  but fallback to uncleared if we can't find the cleared blocks.
  when driver requests uncleared memory we try to use uncleared but
  fallback to cleared memory if necessary.

- When a block gets freed we clear it and mark the freed block as cleared,
  when there are buddies which are cleared as well we can merge them.
  Otherwise, we prefer to keep the blocks as separated.

- Add a function to support defragmentation.

v1:
  - Depends on the flag check DRM_BUDDY_CLEARED, enable the block as
    cleared. Else, reset the clear flag for each block in the list(Christian)
  - For merging the 2 cleared blocks compare as below,
    drm_buddy_is_clear(block) != drm_buddy_is_clear(buddy)(Christian)
  - Defragment the memory beginning from min_order
    till the required memory space is available.

v2: (Matthew)
  - Add a wrapper drm_buddy_free_list_internal for the freeing of blocks
    operation within drm buddy.
  - Write a macro block_incompatible() to allocate the required blocks.
  - Update the xe driver for the drm_buddy_free_list change in arguments.
  - add a warning if the two blocks are incompatible on
    defragmentation
  - call full defragmentation in the fini() function
  - place a condition to test if min_order is equal to 0
  - replace the list with safe_reverse() variant as we might
    remove the block from the list.

v3:
  - fix Gitlab user reported lockup issue.
  - Keep DRM_BUDDY_HEADER_CLEAR define sorted(Matthew)
  - modify to pass the root order instead max_order in fini()
    function(Matthew)
  - change bool 1 to true(Matthew)
  - add check if min_block_size is power of 2(Matthew)
  - modify the min_block_size datatype to u64(Matthew)

v4:
  - rename the function drm_buddy_defrag with __force_merge.
  - Include __force_merge directly in drm buddy file and remove
    the defrag use in amdgpu driver.
  - Remove list_empty() check(Matthew)
  - Remove unnecessary space, headers and placement of new variables(Matthew)
  - Add a unit test case(Matthew)

v5:
  - remove force merge support to actual range allocation and not to bail
    out when contains && split(Matthew)
  - add range support to force merge function.

v6:
  - modify the alloc_range() function clear page non merged blocks
    allocation(Matthew)
  - correct the list_insert function name(Matthew).
Signed-off-by: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam@amd.com>
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Suggested-by: Christian König <christian.koenig@amd.com>
Suggested-by: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240419063538.11957-1-Arunpravin.PaneerSelvam@amd.comSigned-off-by: Christian König <christian.koenig@amd.com>

drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c

@@ -571,7 +571,7 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
 	return 0;
 
 error_free_blocks:
-	drm_buddy_free_list(mm, &vres->blocks);
+	drm_buddy_free_list(mm, &vres->blocks, 0);
 	mutex_unlock(&mgr->lock);
 error_fini:
 	ttm_resource_fini(man, &vres->base);
@@ -604,7 +604,7 @@ static void amdgpu_vram_mgr_del(struct ttm_resource_manager *man,
 
 	amdgpu_vram_mgr_do_reserve(man);
 
-	drm_buddy_free_list(mm, &vres->blocks);
+	drm_buddy_free_list(mm, &vres->blocks, 0);
 	mutex_unlock(&mgr->lock);
 
 	atomic64_sub(vis_usage, &mgr->vis_usage);
@@ -912,7 +912,7 @@ void amdgpu_vram_mgr_fini(struct amdgpu_device *adev)
 		kfree(rsv);
 
 	list_for_each_entry_safe(rsv, temp, &mgr->reserved_pages, blocks) {
-		drm_buddy_free_list(&mgr->mm, &rsv->allocated);
+		drm_buddy_free_list(&mgr->mm, &rsv->allocated, 0);
 		kfree(rsv);
 	}
 	if (!adev->gmc.is_app_apu)

drivers/gpu/drm/i915/i915_ttm_buddy_manager.c

@@ -126,7 +126,7 @@ static int i915_ttm_buddy_man_alloc(struct ttm_resource_manager *man,
 	return 0;
 
 err_free_blocks:
-	drm_buddy_free_list(mm, &bman_res->blocks);
+	drm_buddy_free_list(mm, &bman_res->blocks, 0);
 	mutex_unlock(&bman->lock);
 err_free_res:
 	ttm_resource_fini(man, &bman_res->base);
@@ -141,7 +141,7 @@ static void i915_ttm_buddy_man_free(struct ttm_resource_manager *man,
 	struct i915_ttm_buddy_manager *bman = to_buddy_manager(man);
 
 	mutex_lock(&bman->lock);
-	drm_buddy_free_list(&bman->mm, &bman_res->blocks);
+	drm_buddy_free_list(&bman->mm, &bman_res->blocks, 0);
 	bman->visible_avail += bman_res->used_visible_size;
 	mutex_unlock(&bman->lock);
 
@@ -345,7 +345,7 @@ int i915_ttm_buddy_man_fini(struct ttm_device *bdev, unsigned int type)
 	ttm_set_driver_manager(bdev, type, NULL);
 
 	mutex_lock(&bman->lock);
-	drm_buddy_free_list(mm, &bman->reserved);
+	drm_buddy_free_list(mm, &bman->reserved, 0);
 	drm_buddy_fini(mm);
 	bman->visible_avail += bman->visible_reserved;
 	WARN_ON_ONCE(bman->visible_avail != bman->visible_size);

drivers/gpu/drm/tests/drm_buddy_test.c

@@ -103,7 +103,7 @@ static void drm_test_buddy_alloc_range_bias(struct kunit *test)
 							      DRM_BUDDY_RANGE_ALLOCATION),
 				       "buddy_alloc i failed with bias(%x-%x), size=%u, ps=%u\n",
 				       bias_start, bias_end, bias_size, bias_size);
-		drm_buddy_free_list(&mm, &tmp);
+		drm_buddy_free_list(&mm, &tmp, 0);
 
 		/* single page with internal round_up */
 		KUNIT_ASSERT_FALSE_MSG(test,
@@ -113,7 +113,7 @@ static void drm_test_buddy_alloc_range_bias(struct kunit *test)
 							      DRM_BUDDY_RANGE_ALLOCATION),
 				       "buddy_alloc failed with bias(%x-%x), size=%u, ps=%u\n",
 				       bias_start, bias_end, ps, bias_size);
-		drm_buddy_free_list(&mm, &tmp);
+		drm_buddy_free_list(&mm, &tmp, 0);
 
 		/* random size within */
 		size = max(round_up(prandom_u32_state(&prng) % bias_rem, ps), ps);
@@ -153,14 +153,14 @@ static void drm_test_buddy_alloc_range_bias(struct kunit *test)
 			 * unallocated, and ideally not always on the bias
 			 * boundaries.
 			 */
-			drm_buddy_free_list(&mm, &tmp);
+			drm_buddy_free_list(&mm, &tmp, 0);
 		} else {
 			list_splice_tail(&tmp, &allocated);
 		}
 	}
 
 	kfree(order);
-	drm_buddy_free_list(&mm, &allocated);
+	drm_buddy_free_list(&mm, &allocated, 0);
 	drm_buddy_fini(&mm);
 
 	/*
@@ -220,7 +220,7 @@ static void drm_test_buddy_alloc_range_bias(struct kunit *test)
 			      "buddy_alloc passed with bias(%x-%x), size=%u\n",
 			      bias_start, bias_end, ps);
 
-	drm_buddy_free_list(&mm, &allocated);
+	drm_buddy_free_list(&mm, &allocated, 0);
 	drm_buddy_fini(&mm);
 }
 
@@ -269,7 +269,7 @@ static void drm_test_buddy_alloc_contiguous(struct kunit *test)
 							   DRM_BUDDY_CONTIGUOUS_ALLOCATION),
 			       "buddy_alloc didn't error size=%lu\n", 3 * ps);
 
-	drm_buddy_free_list(&mm, &middle);
+	drm_buddy_free_list(&mm, &middle, 0);
 	KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
 							   3 * ps, ps, &allocated,
 							   DRM_BUDDY_CONTIGUOUS_ALLOCATION),
@@ -279,7 +279,7 @@ static void drm_test_buddy_alloc_contiguous(struct kunit *test)
 							   DRM_BUDDY_CONTIGUOUS_ALLOCATION),
 			       "buddy_alloc didn't error size=%lu\n", 2 * ps);
 
-	drm_buddy_free_list(&mm, &right);
+	drm_buddy_free_list(&mm, &right, 0);
 	KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
 							   3 * ps, ps, &allocated,
 							   DRM_BUDDY_CONTIGUOUS_ALLOCATION),
@@ -294,7 +294,7 @@ static void drm_test_buddy_alloc_contiguous(struct kunit *test)
 							    DRM_BUDDY_CONTIGUOUS_ALLOCATION),
 			       "buddy_alloc hit an error size=%lu\n", 2 * ps);
 
-	drm_buddy_free_list(&mm, &left);
+	drm_buddy_free_list(&mm, &left, 0);
 	KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
 							    3 * ps, ps, &allocated,
 							    DRM_BUDDY_CONTIGUOUS_ALLOCATION),
@@ -306,7 +306,7 @@ static void drm_test_buddy_alloc_contiguous(struct kunit *test)
 
 	KUNIT_ASSERT_EQ(test, total, ps * 2 + ps * 3);
 
-	drm_buddy_free_list(&mm, &allocated);
+	drm_buddy_free_list(&mm, &allocated, 0);
 	drm_buddy_fini(&mm);
 }
 
@@ -375,7 +375,7 @@ static void drm_test_buddy_alloc_pathological(struct kunit *test)
 							  top, max_order);
 	}
 
-	drm_buddy_free_list(&mm, &holes);
+	drm_buddy_free_list(&mm, &holes, 0);
 
 	/* Nothing larger than blocks of chunk_size now available */
 	for (order = 1; order <= max_order; order++) {
@@ -387,7 +387,7 @@ static void drm_test_buddy_alloc_pathological(struct kunit *test)
 	}
 
 	list_splice_tail(&holes, &blocks);
-	drm_buddy_free_list(&mm, &blocks);
+	drm_buddy_free_list(&mm, &blocks, 0);
 	drm_buddy_fini(&mm);
 }
 
@@ -482,7 +482,7 @@ static void drm_test_buddy_alloc_pessimistic(struct kunit *test)
 
 	list_del(&block->link);
 	drm_buddy_free_block(&mm, block);
-	drm_buddy_free_list(&mm, &blocks);
+	drm_buddy_free_list(&mm, &blocks, 0);
 	drm_buddy_fini(&mm);
 }
 
@@ -528,7 +528,7 @@ static void drm_test_buddy_alloc_optimistic(struct kunit *test)
 							   size, size, &tmp, flags),
 						  "buddy_alloc unexpectedly succeeded, it should be full!");
 
-	drm_buddy_free_list(&mm, &blocks);
+	drm_buddy_free_list(&mm, &blocks, 0);
 	drm_buddy_fini(&mm);
 }
 
@@ -563,7 +563,7 @@ static void drm_test_buddy_alloc_limit(struct kunit *test)
 						drm_buddy_block_size(&mm, block),
 						BIT_ULL(mm.max_order) * PAGE_SIZE);
 
-	drm_buddy_free_list(&mm, &allocated);
+	drm_buddy_free_list(&mm, &allocated, 0);
 	drm_buddy_fini(&mm);
 }
 

drivers/gpu/drm/xe/xe_ttm_vram_mgr.c

@@ -196,7 +196,7 @@ static int xe_ttm_vram_mgr_new(struct ttm_resource_manager *man,
 	return 0;
 
 error_free_blocks:
-	drm_buddy_free_list(mm, &vres->blocks);
+	drm_buddy_free_list(mm, &vres->blocks, 0);
 	mutex_unlock(&mgr->lock);
 error_fini:
 	ttm_resource_fini(man, &vres->base);
@@ -214,7 +214,7 @@ static void xe_ttm_vram_mgr_del(struct ttm_resource_manager *man,
 	struct drm_buddy *mm = &mgr->mm;
 
 	mutex_lock(&mgr->lock);
-	drm_buddy_free_list(mm, &vres->blocks);
+	drm_buddy_free_list(mm, &vres->blocks, 0);
 	mgr->visible_avail += vres->used_visible_size;
 	mutex_unlock(&mgr->lock);
 

include/drm/drm_buddy.h

@@ -25,6 +25,8 @@
 #define DRM_BUDDY_RANGE_ALLOCATION		BIT(0)
 #define DRM_BUDDY_TOPDOWN_ALLOCATION		BIT(1)
 #define DRM_BUDDY_CONTIGUOUS_ALLOCATION		BIT(2)
+#define DRM_BUDDY_CLEAR_ALLOCATION		BIT(3)
+#define DRM_BUDDY_CLEARED			BIT(4)
 
 struct drm_buddy_block {
 #define DRM_BUDDY_HEADER_OFFSET GENMASK_ULL(63, 12)
@@ -32,8 +34,9 @@ struct drm_buddy_block {
 #define   DRM_BUDDY_ALLOCATED	   (1 << 10)
 #define   DRM_BUDDY_FREE	   (2 << 10)
 #define   DRM_BUDDY_SPLIT	   (3 << 10)
+#define DRM_BUDDY_HEADER_CLEAR  GENMASK_ULL(9, 9)
 /* Free to be used, if needed in the future */
-#define DRM_BUDDY_HEADER_UNUSED GENMASK_ULL(9, 6)
+#define DRM_BUDDY_HEADER_UNUSED GENMASK_ULL(8, 6)
 #define DRM_BUDDY_HEADER_ORDER  GENMASK_ULL(5, 0)
 	u64 header;
 
@@ -86,6 +89,7 @@ struct drm_buddy {
 	u64 chunk_size;
 	u64 size;
 	u64 avail;
+	u64 clear_avail;
 };
 
 static inline u64
@@ -112,6 +116,12 @@ drm_buddy_block_is_allocated(struct drm_buddy_block *block)
 	return drm_buddy_block_state(block) == DRM_BUDDY_ALLOCATED;
 }
 
+static inline bool
+drm_buddy_block_is_clear(struct drm_buddy_block *block)
+{
+	return block->header & DRM_BUDDY_HEADER_CLEAR;
+}
+
 static inline bool
 drm_buddy_block_is_free(struct drm_buddy_block *block)
 {
@@ -150,7 +160,9 @@ int drm_buddy_block_trim(struct drm_buddy *mm,
 
 void drm_buddy_free_block(struct drm_buddy *mm, struct drm_buddy_block *block);
 
-void drm_buddy_free_list(struct drm_buddy *mm, struct list_head *objects);
+void drm_buddy_free_list(struct drm_buddy *mm,
+			 struct list_head *objects,
+			 unsigned int flags);
 
 void drm_buddy_print(struct drm_buddy *mm, struct drm_printer *p);
 void drm_buddy_block_print(struct drm_buddy *mm,