[PATCH 04/13] drm: make drm_buddy_alloc a commonplace
Arunpravin
Arunpravin.PaneerSelvam at amd.com
Tue Oct 19 22:54:00 UTC 2021
- Make drm_buddy_alloc a single function to handle
range allocation and non-range allocation demands.
- Implemented a new function alloc_range() which allocates
the requested order (in bytes) comply with range limitations
- Moved memory alignment logic from i915 driver
Signed-off-by: Arunpravin <Arunpravin.PaneerSelvam at amd.com>
---
drivers/gpu/drm/drm_buddy.c | 208 +++++++++++++++++++++++++++++++-----
include/drm/drm_buddy.h | 18 +++-
2 files changed, 194 insertions(+), 32 deletions(-)
diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c
index 0398706cb7ae..f5f299dd9131 100644
--- a/drivers/gpu/drm/drm_buddy.c
+++ b/drivers/gpu/drm/drm_buddy.c
@@ -246,27 +246,112 @@ void drm_buddy_free_list(struct drm_buddy_mm *mm, struct list_head *objects)
INIT_LIST_HEAD(objects);
}
-/*
- * Allocate power-of-two block. The order value here translates to:
- *
- * 0 = 2^0 * mm->chunk_size
- * 1 = 2^1 * mm->chunk_size
- * 2 = 2^2 * mm->chunk_size
- * ...
- */
-struct drm_buddy_block *
-drm_buddy_alloc(struct drm_buddy_mm *mm, unsigned int order)
+static inline bool overlaps(u64 s1, u64 e1, u64 s2, u64 e2)
+{
+ return s1 <= e2 && e1 >= s2;
+}
+
+static inline bool contains(u64 s1, u64 e1, u64 s2, u64 e2)
+{
+ return s1 <= s2 && e1 >= e2;
+}
+
+static struct drm_buddy_block *
+alloc_range(struct drm_buddy_mm *mm,
+ u64 start, u64 end,
+ unsigned int order)
+{
+ struct drm_buddy_block *block;
+ struct drm_buddy_block *buddy;
+ LIST_HEAD(dfs);
+ int err;
+ int i;
+
+ end = end - 1;
+
+ for (i = 0; i < mm->n_roots; ++i)
+ list_add_tail(&mm->roots[i]->tmp_link, &dfs);
+
+ do {
+ u64 block_start;
+ u64 block_end;
+
+ block = list_first_entry_or_null(&dfs,
+ struct drm_buddy_block,
+ tmp_link);
+
+ if (!block)
+ break;
+
+ list_del(&block->tmp_link);
+
+ if (drm_buddy_block_order(block) < order)
+ continue;
+
+ block_start = drm_buddy_block_offset(block);
+ block_end = block_start + drm_buddy_block_size(mm, block) - 1;
+
+ if (!overlaps(start, end, block_start, block_end))
+ continue;
+
+ if (drm_buddy_block_is_allocated(block))
+ continue;
+
+ if (contains(start, end, block_start, block_end)
+ && order == drm_buddy_block_order(block)) {
+ /*
+ * Find the free block within the range.
+ */
+ if (drm_buddy_block_is_free(block))
+ return block;
+
+ continue;
+ }
+
+ if (!drm_buddy_block_is_split(block)) {
+ err = split_block(mm, block);
+ if (unlikely(err))
+ goto err_undo;
+ }
+
+ list_add(&block->left->tmp_link, &dfs);
+ list_add(&block->right->tmp_link, &dfs);
+ } while (1);
+
+ return ERR_PTR(-ENOSPC);
+
+err_undo:
+ /*
+ * We really don't want to leave around a bunch of split blocks, since
+ * bigger is better, so make sure we merge everything back before we
+ * free the allocated blocks.
+ */
+ buddy = get_buddy(block);
+ if (buddy &&
+ (drm_buddy_block_is_free(block) &&
+ drm_buddy_block_is_free(buddy)))
+ __drm_buddy_free(mm, block);
+ return ERR_PTR(err);
+}
+
+static struct drm_buddy_block *
+alloc_from_freelist(struct drm_buddy_mm *mm,
+ unsigned int order,
+ unsigned long flags)
{
struct drm_buddy_block *block = NULL;
unsigned int i;
int err;
for (i = order; i <= mm->max_order; ++i) {
- block = list_first_entry_or_null(&mm->free_list[i],
- struct drm_buddy_block,
- link);
- if (block)
- break;
+ if (!list_empty(&mm->free_list[i])) {
+ block = list_first_entry_or_null(&mm->free_list[i],
+ struct drm_buddy_block,
+ link);
+
+ if (block)
+ break;
+ }
}
if (!block)
@@ -276,33 +361,100 @@ drm_buddy_alloc(struct drm_buddy_mm *mm, unsigned int order)
while (i != order) {
err = split_block(mm, block);
+
if (unlikely(err))
- goto out_free;
+ goto err_undo;
- /* Go low */
- block = block->left;
+ block = block->right;
i--;
}
- mark_allocated(block);
- mm->avail -= drm_buddy_block_size(mm, block);
- kmemleak_update_trace(block);
return block;
-out_free:
+err_undo:
if (i != order)
__drm_buddy_free(mm, block);
return ERR_PTR(err);
}
-static inline bool overlaps(u64 s1, u64 e1, u64 s2, u64 e2)
+/*
+ * Allocate power-of-two block. The order value here translates to:
+ *
+ * 0 = 2^0 * mm->chunk_size
+ * 1 = 2^1 * mm->chunk_size
+ * 2 = 2^2 * mm->chunk_size
+ * ...
+ */
+int drm_buddy_alloc(struct drm_buddy_mm *mm,
+ u64 start, u64 end, u64 size,
+ u64 min_page_size,
+ struct list_head *blocks,
+ unsigned long flags)
{
- return s1 <= e2 && e1 >= s2;
-}
+ struct drm_buddy_block *block = NULL;
+ unsigned int min_order, order;
+ unsigned long pages;
+ LIST_HEAD(allocated);
+ int err;
-static inline bool contains(u64 s1, u64 e1, u64 s2, u64 e2)
-{
- return s1 <= s2 && e1 >= e2;
+ if (size < mm->chunk_size)
+ return -EINVAL;
+
+ if (!IS_ALIGNED(start, mm->chunk_size))
+ return -EINVAL;
+
+ if (!IS_ALIGNED(end, mm->chunk_size))
+ return -EINVAL;
+
+ if (!IS_ALIGNED(size, mm->chunk_size))
+ return -EINVAL;
+
+ if (check_range_overflow(start, end, size, mm->size))
+ return -EINVAL;
+
+ pages = size >> ilog2(mm->chunk_size);
+ min_order = ilog2(min_page_size) - ilog2(mm->chunk_size);
+
+ do {
+ order = fls(pages) - 1;
+ BUG_ON(order > mm->max_order);
+ BUG_ON(order < min_order);
+
+ do {
+ if (flags & DRM_BUDDY_RANGE_ALLOCATION)
+ /* Allocate traversing within the range */
+ block = alloc_range(mm, start, end, order);
+ else
+ /* Allocate from freelist */
+ block = alloc_from_freelist(mm, order, flags);
+
+ if (!IS_ERR(block))
+ break;
+
+ if (order-- == min_order) {
+ err = -ENOSPC;
+ goto err_free;
+ }
+ } while (1);
+
+ mark_allocated(block);
+ mm->avail -= drm_buddy_block_size(mm, block);
+ kmemleak_update_trace(block);
+
+ list_add_tail(&block->link, &allocated);
+
+ pages -= BIT(order);
+
+ if (!pages)
+ break;
+ } while (1);
+
+ list_splice_tail(&allocated, blocks);
+ return 0;
+
+err_free:
+ drm_buddy_free_list(mm, &allocated);
+ return err;
}
/*
diff --git a/include/drm/drm_buddy.h b/include/drm/drm_buddy.h
index 390b133fe342..c64fd4062cb6 100644
--- a/include/drm/drm_buddy.h
+++ b/include/drm/drm_buddy.h
@@ -13,15 +13,22 @@
#include <drm/drm_print.h>
-#define range_overflows(start, size, max) ({ \
+#define check_range_overflow(start, end, size, max) ({ \
typeof(start) start__ = (start); \
+ typeof(end) end__ = (end);\
typeof(size) size__ = (size); \
typeof(max) max__ = (max); \
(void)(&start__ == &size__); \
(void)(&start__ == &max__); \
- start__ >= max__ || size__ > max__ - start__; \
+ (void)(&start__ == &end__); \
+ (void)(&end__ == &size__); \
+ (void)(&end__ == &max__); \
+ start__ >= max__ || end__ > max__ \
+ || size__ > end__ - start__; \
})
+#define DRM_BUDDY_RANGE_ALLOCATION (1 << 1)
+
struct drm_buddy_block {
#define DRM_BUDDY_HEADER_OFFSET GENMASK_ULL(63, 12)
#define DRM_BUDDY_HEADER_STATE GENMASK_ULL(11, 10)
@@ -131,8 +138,11 @@ int drm_buddy_init(struct drm_buddy_mm *mm, u64 size, u64 chunk_size);
void drm_buddy_fini(struct drm_buddy_mm *mm);
-struct drm_buddy_block *
-drm_buddy_alloc(struct drm_buddy_mm *mm, unsigned int order);
+int drm_buddy_alloc(struct drm_buddy_mm *mm,
+ u64 start, u64 end, u64 size,
+ u64 min_page_size,
+ struct list_head *blocks,
+ unsigned long flags);
int drm_buddy_alloc_range(struct drm_buddy_mm *mm,
struct list_head *blocks,
--
2.25.1
More information about the amd-gfx
mailing list