diff mbox series

[v13,3/5] drm: implement a method to free unused pages

Message ID 20220221164552.2434-3-Arunpravin.PaneerSelvam@amd.com (mailing list archive)
State New, archived
Headers show
Series [v13,1/5] drm: improve drm_buddy_alloc function | expand

Commit Message

Paneer Selvam, Arunpravin Feb. 21, 2022, 4:45 p.m. UTC
On contiguous allocation, we round up the size
to the *next* power of 2, implement a function
to free the unused pages after the newly allocate block.

v2(Matthew Auld):
  - replace function name 'drm_buddy_free_unused_pages' with
    drm_buddy_block_trim
  - replace input argument name 'actual_size' with 'new_size'
  - add more validation checks for input arguments
  - add overlaps check to avoid needless searching and splitting
  - merged the below patch to see the feature in action
     - add free unused pages support to i915 driver
  - lock drm_buddy_block_trim() function as it calls mark_free/mark_split
    are all globally visible

v3(Matthew Auld):
  - remove trim method error handling as we address the failure case
    at drm_buddy_block_trim() function

v4:
  - in case of trim, at __alloc_range() split_block failure path
    marks the block as free and removes it from the original list,
    potentially also freeing it, to overcome this problem, we turn
    the drm_buddy_block_trim() input node into a temporary node to
    prevent recursively freeing itself, but still retain the
    un-splitting/freeing of the other nodes(Matthew Auld)

  - modify the drm_buddy_block_trim() function return type

v5(Matthew Auld):
  - revert drm_buddy_block_trim() function return type changes in v4
  - modify drm_buddy_block_trim() passing argument n_pages to original_size
    as n_pages has already been rounded up to the next power-of-two and
    passing n_pages results noop

v6:
  - fix warnings reported by kernel test robot <lkp@intel.com>

v7:
  - modify drm_buddy_block_trim() function doc description
  - at drm_buddy_block_trim() handle non-allocated block as
    a serious programmer error
  - fix a typo

Signed-off-by: Arunpravin <Arunpravin.PaneerSelvam@amd.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
---
 drivers/gpu/drm/drm_buddy.c                   | 69 +++++++++++++++++++
 drivers/gpu/drm/i915/i915_ttm_buddy_manager.c | 10 +++
 include/drm/drm_buddy.h                       |  4 ++
 3 files changed, 83 insertions(+)
diff mbox series

Patch

diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c
index 72ee3cd96a24..edef30be8304 100644
--- a/drivers/gpu/drm/drm_buddy.c
+++ b/drivers/gpu/drm/drm_buddy.c
@@ -525,6 +525,75 @@  static int __drm_buddy_alloc_range(struct drm_buddy *mm,
 	return __alloc_range(mm, &dfs, start, size, blocks);
 }
 
+/**
+ * drm_buddy_block_trim - free unused pages
+ *
+ * @mm: DRM buddy manager
+ * @new_size: original size requested
+ * @blocks: Input and output list of allocated blocks.
+ * MUST contain single block as input to be trimmed.
+ * On success will contain the newly allocated blocks
+ * making up the @new_size. Blocks always appear in
+ * ascending order
+ *
+ * For contiguous allocation, we round up the size to the nearest
+ * power of two value, drivers consume *actual* size, so remaining
+ * portions are unused and can be optionally freed with this function
+ *
+ * Returns:
+ * 0 on success, error code on failure.
+ */
+int drm_buddy_block_trim(struct drm_buddy *mm,
+			 u64 new_size,
+			 struct list_head *blocks)
+{
+	struct drm_buddy_block *parent;
+	struct drm_buddy_block *block;
+	LIST_HEAD(dfs);
+	u64 new_start;
+	int err;
+
+	if (!list_is_singular(blocks))
+		return -EINVAL;
+
+	block = list_first_entry(blocks,
+				 struct drm_buddy_block,
+				 link);
+
+	if (WARN_ON(!drm_buddy_block_is_allocated(block)))
+		return -EINVAL;
+
+	if (new_size > drm_buddy_block_size(mm, block))
+		return -EINVAL;
+
+	if (!new_size || !IS_ALIGNED(new_size, mm->chunk_size))
+		return -EINVAL;
+
+	if (new_size == drm_buddy_block_size(mm, block))
+		return 0;
+
+	list_del(&block->link);
+	mark_free(mm, block);
+	mm->avail += drm_buddy_block_size(mm, block);
+
+	/* Prevent recursively freeing this node */
+	parent = block->parent;
+	block->parent = NULL;
+
+	new_start = drm_buddy_block_offset(block);
+	list_add(&block->tmp_link, &dfs);
+	err =  __alloc_range(mm, &dfs, new_start, new_size, blocks);
+	if (err) {
+		mark_allocated(block);
+		mm->avail -= drm_buddy_block_size(mm, block);
+		list_add(&block->link, blocks);
+	}
+
+	block->parent = parent;
+	return err;
+}
+EXPORT_SYMBOL(drm_buddy_block_trim);
+
 /**
  * drm_buddy_alloc_blocks - allocate power-of-two blocks
  *
diff --git a/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c
index 7f553cceb6c0..76d5211c25eb 100644
--- a/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c
+++ b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c
@@ -97,6 +97,16 @@  static int i915_ttm_buddy_man_alloc(struct ttm_resource_manager *man,
 	if (unlikely(err))
 		goto err_free_blocks;
 
+	if (place->flags & TTM_PL_FLAG_CONTIGUOUS) {
+		u64 original_size = (u64)bman_res->base.num_pages << PAGE_SHIFT;
+
+		mutex_lock(&bman->lock);
+		drm_buddy_block_trim(mm,
+				     original_size,
+				     &bman_res->blocks);
+		mutex_unlock(&bman->lock);
+	}
+
 	*res = &bman_res->base;
 	return 0;
 
diff --git a/include/drm/drm_buddy.h b/include/drm/drm_buddy.h
index f0378fb48d06..bd21f9dfd15e 100644
--- a/include/drm/drm_buddy.h
+++ b/include/drm/drm_buddy.h
@@ -140,6 +140,10 @@  int drm_buddy_alloc_blocks(struct drm_buddy *mm,
 			   struct list_head *blocks,
 			   unsigned long flags);
 
+int drm_buddy_block_trim(struct drm_buddy *mm,
+			 u64 new_size,
+			 struct list_head *blocks);
+
 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);