Files
linux-stable-mirror/include/drm/drm_buddy.h
Arunpravin Paneer Selvam 6417428ce5 drm/buddy: Separate clear and dirty free block trees
commit d4cd665c98 upstream.

Maintain two separate RB trees per order - one for clear (zeroed) blocks
and another for dirty (uncleared) blocks. This separation improves
code clarity and makes it more obvious which tree is being searched
during allocation. It also improves scalability and efficiency when
searching for a specific type of block, avoiding unnecessary checks
and making the allocator more predictable under fragmentation.

The changes have been validated using the existing drm_buddy_test
KUnit test cases, along with selected graphics workloads,
to ensure correctness and avoid regressions.

v2: Missed adding the suggested-by tag. Added it in v2.

v3(Matthew):
  - Remove the double underscores from the internal functions.
  - Rename the internal functions to have less generic names.
  - Fix the error handling code.
  - Pass tree argument for the tree macro.
  - Use the existing dirty/free bit instead of new tree field.
  - Make free_trees[] instead of clear_tree and dirty_tree for
    more cleaner approach.

v4:
  - A bug was reported by Intel CI and it is fixed by
    Matthew Auld.
  - Replace the get_root function with
    &mm->free_trees[tree][order] (Matthew)
  - Remove the unnecessary rbtree_is_empty() check (Matthew)
  - Remove the unnecessary get_tree_for_flags() function.
  - Rename get_tree_for_block() name with get_block_tree() for more
    clarity.

v5(Jani Nikula):
  - Don't use static inline in .c files.
  - enum free_tree and enumerator names are quite generic for a header
    and usage and the whole enum should be an implementation detail.

v6:
  - Rewrite the __force_merge() function using the rb_last() and rb_prev().

v7(Matthew):
  - Replace the open-coded tree iteration for loops with the
    for_each_free_tree() macro throughout the code.
  - Fixed out_free_roots to prevent double decrement of i,
    addressing potential crash.
  - Replaced enum drm_buddy_free_tree with unsigned int
    in for_each_free_tree loops.

Cc: stable@vger.kernel.org
Fixes: a68c7eaa7a ("drm/amdgpu: Enable clear page functionality")
Signed-off-by: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam@amd.com>
Suggested-by: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4260
Link: https://lore.kernel.org/r/20251006095124.1663-2-Arunpravin.PaneerSelvam@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2026-01-08 10:14:52 +01:00

181 lines
4.6 KiB
C

/* SPDX-License-Identifier: MIT */
/*
* Copyright © 2021 Intel Corporation
*/
#ifndef __DRM_BUDDY_H__
#define __DRM_BUDDY_H__
#include <linux/bitops.h>
#include <linux/list.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/rbtree.h>
#include <drm/drm_print.h>
#define range_overflows(start, size, max) ({ \
typeof(start) start__ = (start); \
typeof(size) size__ = (size); \
typeof(max) max__ = (max); \
(void)(&start__ == &size__); \
(void)(&start__ == &max__); \
start__ >= max__ || size__ > max__ - start__; \
})
#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)
#define DRM_BUDDY_TRIM_DISABLE BIT(5)
struct drm_buddy_block {
#define DRM_BUDDY_HEADER_OFFSET GENMASK_ULL(63, 12)
#define DRM_BUDDY_HEADER_STATE GENMASK_ULL(11, 10)
#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(8, 6)
#define DRM_BUDDY_HEADER_ORDER GENMASK_ULL(5, 0)
u64 header;
struct drm_buddy_block *left;
struct drm_buddy_block *right;
struct drm_buddy_block *parent;
void *private; /* owned by creator */
/*
* While the block is allocated by the user through drm_buddy_alloc*,
* the user has ownership of the link, for example to maintain within
* a list, if so desired. As soon as the block is freed with
* drm_buddy_free* ownership is given back to the mm.
*/
union {
struct rb_node rb;
struct list_head link;
};
struct list_head tmp_link;
};
/* Order-zero must be at least SZ_4K */
#define DRM_BUDDY_MAX_ORDER (63 - 12)
/*
* Binary Buddy System.
*
* Locking should be handled by the user, a simple mutex around
* drm_buddy_alloc* and drm_buddy_free* should suffice.
*/
struct drm_buddy {
/* Maintain a free list for each order. */
struct rb_root **free_trees;
/*
* Maintain explicit binary tree(s) to track the allocation of the
* address space. This gives us a simple way of finding a buddy block
* and performing the potentially recursive merge step when freeing a
* block. Nodes are either allocated or free, in which case they will
* also exist on the respective free list.
*/
struct drm_buddy_block **roots;
/*
* Anything from here is public, and remains static for the lifetime of
* the mm. Everything above is considered do-not-touch.
*/
unsigned int n_roots;
unsigned int max_order;
/* Must be at least SZ_4K */
u64 chunk_size;
u64 size;
u64 avail;
u64 clear_avail;
};
static inline u64
drm_buddy_block_offset(const struct drm_buddy_block *block)
{
return block->header & DRM_BUDDY_HEADER_OFFSET;
}
static inline unsigned int
drm_buddy_block_order(struct drm_buddy_block *block)
{
return block->header & DRM_BUDDY_HEADER_ORDER;
}
static inline unsigned int
drm_buddy_block_state(struct drm_buddy_block *block)
{
return block->header & DRM_BUDDY_HEADER_STATE;
}
static inline bool
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)
{
return drm_buddy_block_state(block) == DRM_BUDDY_FREE;
}
static inline bool
drm_buddy_block_is_split(struct drm_buddy_block *block)
{
return drm_buddy_block_state(block) == DRM_BUDDY_SPLIT;
}
static inline u64
drm_buddy_block_size(struct drm_buddy *mm,
struct drm_buddy_block *block)
{
return mm->chunk_size << drm_buddy_block_order(block);
}
int drm_buddy_init(struct drm_buddy *mm, u64 size, u64 chunk_size);
void drm_buddy_fini(struct drm_buddy *mm);
struct drm_buddy_block *
drm_get_buddy(struct drm_buddy_block *block);
int drm_buddy_alloc_blocks(struct drm_buddy *mm,
u64 start, u64 end, u64 size,
u64 min_page_size,
struct list_head *blocks,
unsigned long flags);
int drm_buddy_block_trim(struct drm_buddy *mm,
u64 *start,
u64 new_size,
struct list_head *blocks);
void drm_buddy_reset_clear(struct drm_buddy *mm, bool is_clear);
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,
unsigned int flags);
void drm_buddy_print(struct drm_buddy *mm, struct drm_printer *p);
void drm_buddy_block_print(struct drm_buddy *mm,
struct drm_buddy_block *block,
struct drm_printer *p);
#endif