@@ -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)
@@ -57,6 +57,16 @@ static void list_insert_sorted(struct drm_buddy *mm,
__list_add(&block->link, node->link.prev, &node->link);
}
+static void clear_reset(struct drm_buddy_block *block)
+{
+ block->header &= ~DRM_BUDDY_HEADER_CLEAR;
+}
+
+static void mark_cleared(struct drm_buddy_block *block)
+{
+ block->header |= DRM_BUDDY_HEADER_CLEAR;
+}
+
static void mark_allocated(struct drm_buddy_block *block)
{
block->header &= ~DRM_BUDDY_HEADER_STATE;
@@ -223,6 +233,12 @@ static int split_block(struct drm_buddy *mm,
mark_free(mm, block->left);
mark_free(mm, block->right);
+ if (drm_buddy_block_is_clear(block)) {
+ mark_cleared(block->left);
+ mark_cleared(block->right);
+ clear_reset(block);
+ }
+
mark_split(block);
return 0;
@@ -273,6 +289,13 @@ static void __drm_buddy_free(struct drm_buddy *mm,
if (!drm_buddy_block_is_free(buddy))
break;
+ if (drm_buddy_block_is_clear(block) !=
+ drm_buddy_block_is_clear(buddy))
+ break;
+
+ if (drm_buddy_block_is_clear(block))
+ mark_cleared(parent);
+
list_del(&buddy->link);
drm_block_free(mm, block);
@@ -295,26 +318,59 @@ void drm_buddy_free_block(struct drm_buddy *mm,
{
BUG_ON(!drm_buddy_block_is_allocated(block));
mm->avail += drm_buddy_block_size(mm, block);
+ if (drm_buddy_block_is_clear(block))
+ mm->clear_avail += drm_buddy_block_size(mm, block);
+
__drm_buddy_free(mm, block);
}
EXPORT_SYMBOL(drm_buddy_free_block);
-/**
- * drm_buddy_free_list - free blocks
- *
- * @mm: DRM buddy manager
- * @objects: input list head to free blocks
- */
-void drm_buddy_free_list(struct drm_buddy *mm, struct list_head *objects)
+static void __drm_buddy_free_list(struct drm_buddy *mm,
+ struct list_head *objects,
+ bool mark_clear,
+ bool mark_dirty)
{
struct drm_buddy_block *block, *on;
+ WARN_ON(mark_dirty && mark_clear);
+
list_for_each_entry_safe(block, on, objects, link) {
+ if (mark_clear)
+ mark_cleared(block);
+ else if (mark_dirty)
+ clear_reset(block);
drm_buddy_free_block(mm, block);
cond_resched();
}
INIT_LIST_HEAD(objects);
}
+
+static void drm_buddy_free_list_internal(struct drm_buddy *mm,
+ struct list_head *objects)
+{
+ /*
+ * Don't touch the clear/dirty bit, since allocation is still internal
+ * at this point. For example we might have just failed part of the
+ * allocation.
+ */
+ __drm_buddy_free_list(mm, objects, false, false);
+}
+
+/**
+ * drm_buddy_free_list - free blocks
+ *
+ * @mm: DRM buddy manager
+ * @objects: input list head to free blocks
+ * @flags: optional flags like DRM_BUDDY_CLEARED
+ */
+void drm_buddy_free_list(struct drm_buddy *mm,
+ struct list_head *objects,
+ unsigned int flags)
+{
+ bool mark_clear = flags & DRM_BUDDY_CLEARED;
+
+ __drm_buddy_free_list(mm, objects, mark_clear, !mark_clear);
+}
EXPORT_SYMBOL(drm_buddy_free_list);
static inline bool overlaps(u64 s1, u64 e1, u64 s2, u64 e2)
@@ -327,10 +383,19 @@ static inline bool contains(u64 s1, u64 e1, u64 s2, u64 e2)
return s1 <= s2 && e1 >= e2;
}
+static bool block_incompatible(struct drm_buddy_block *block, unsigned int flags)
+{
+ bool needs_clear = flags & DRM_BUDDY_CLEAR_ALLOCATION;
+
+ return needs_clear != drm_buddy_block_is_clear(block);
+}
+
static struct drm_buddy_block *
-alloc_range_bias(struct drm_buddy *mm,
- u64 start, u64 end,
- unsigned int order)
+__alloc_range_bias(struct drm_buddy *mm,
+ u64 start, u64 end,
+ unsigned int order,
+ unsigned long flags,
+ bool fallback)
{
struct drm_buddy_block *block;
struct drm_buddy_block *buddy;
@@ -369,6 +434,9 @@ alloc_range_bias(struct drm_buddy *mm,
if (contains(start, end, block_start, block_end) &&
order == drm_buddy_block_order(block)) {
+ if (!fallback && block_incompatible(block, flags))
+ continue;
+
/*
* Find the free block within the range.
*/
@@ -405,25 +473,52 @@ alloc_range_bias(struct drm_buddy *mm,
}
static struct drm_buddy_block *
-get_maxblock(struct drm_buddy *mm, unsigned int order)
+__drm_buddy_alloc_range_bias(struct drm_buddy *mm,
+ u64 start, u64 end,
+ unsigned int order,
+ unsigned long flags)
{
- struct drm_buddy_block *max_block = NULL, *node;
+ struct drm_buddy_block *block;
+ bool fallback = 0;
+
+ block = __alloc_range_bias(mm, start, end, order,
+ flags, fallback);
+ if (IS_ERR(block))
+ return __alloc_range_bias(mm, start, end, order,
+ flags, !fallback);
+
+ return block;
+}
+
+static struct drm_buddy_block *
+get_maxblock(struct drm_buddy *mm, unsigned int order,
+ unsigned long flags)
+{
+ struct drm_buddy_block *max_block = NULL, *block = NULL;
unsigned int i;
for (i = order; i <= mm->max_order; ++i) {
- if (!list_empty(&mm->free_list[i])) {
- node = list_last_entry(&mm->free_list[i],
- struct drm_buddy_block,
- link);
- if (!max_block) {
- max_block = node;
+ struct drm_buddy_block *tmp_block;
+
+ list_for_each_entry_reverse(tmp_block, &mm->free_list[i], link) {
+ if (block_incompatible(tmp_block, flags))
continue;
- }
- if (drm_buddy_block_offset(node) >
- drm_buddy_block_offset(max_block)) {
- max_block = node;
- }
+ block = tmp_block;
+ break;
+ }
+
+ if (!block)
+ continue;
+
+ if (!max_block) {
+ max_block = block;
+ continue;
+ }
+
+ if (drm_buddy_block_offset(block) >
+ drm_buddy_block_offset(max_block)) {
+ max_block = block;
}
}
@@ -440,11 +535,29 @@ alloc_from_freelist(struct drm_buddy *mm,
int err;
if (flags & DRM_BUDDY_TOPDOWN_ALLOCATION) {
- block = get_maxblock(mm, order);
+ block = get_maxblock(mm, order, flags);
if (block)
/* Store the obtained block order */
tmp = drm_buddy_block_order(block);
} else {
+ for (tmp = order; tmp <= mm->max_order; ++tmp) {
+ struct drm_buddy_block *tmp_block;
+
+ list_for_each_entry_reverse(tmp_block, &mm->free_list[tmp], link) {
+ if (block_incompatible(tmp_block, flags))
+ continue;
+
+ block = tmp_block;
+ break;
+ }
+
+ if (block)
+ break;
+ }
+ }
+
+ if (!block) {
+ /* Fallback method */
for (tmp = order; tmp <= mm->max_order; ++tmp) {
if (!list_empty(&mm->free_list[tmp])) {
block = list_last_entry(&mm->free_list[tmp],
@@ -454,10 +567,10 @@ alloc_from_freelist(struct drm_buddy *mm,
break;
}
}
- }
- if (!block)
- return ERR_PTR(-ENOSPC);
+ if (!block)
+ return ERR_PTR(-ENOSPC);
+ }
BUG_ON(!drm_buddy_block_is_free(block));
@@ -524,6 +637,8 @@ static int __alloc_range(struct drm_buddy *mm,
mark_allocated(block);
total_allocated += drm_buddy_block_size(mm, block);
mm->avail -= drm_buddy_block_size(mm, block);
+ if (drm_buddy_block_is_clear(block))
+ mm->clear_avail -= drm_buddy_block_size(mm, block);
list_add_tail(&block->link, &allocated);
continue;
}
@@ -558,7 +673,7 @@ static int __alloc_range(struct drm_buddy *mm,
list_splice_tail(&allocated, blocks);
*total_allocated_on_err = total_allocated;
} else {
- drm_buddy_free_list(mm, &allocated);
+ drm_buddy_free_list_internal(mm, &allocated);
}
return err;
@@ -624,11 +739,11 @@ static int __alloc_contig_try_harder(struct drm_buddy *mm,
list_splice(&blocks_lhs, blocks);
return 0;
} else if (err != -ENOSPC) {
- drm_buddy_free_list(mm, blocks);
+ drm_buddy_free_list_internal(mm, blocks);
return err;
}
/* Free blocks for the next iteration */
- drm_buddy_free_list(mm, blocks);
+ drm_buddy_free_list_internal(mm, blocks);
}
return -ENOSPC;
@@ -684,6 +799,8 @@ int drm_buddy_block_trim(struct drm_buddy *mm,
list_del(&block->link);
mark_free(mm, block);
mm->avail += drm_buddy_block_size(mm, block);
+ if (drm_buddy_block_is_clear(block))
+ mm->clear_avail += drm_buddy_block_size(mm, block);
/* Prevent recursively freeing this node */
parent = block->parent;
@@ -695,6 +812,8 @@ int drm_buddy_block_trim(struct drm_buddy *mm,
if (err) {
mark_allocated(block);
mm->avail -= drm_buddy_block_size(mm, block);
+ if (drm_buddy_block_is_clear(block))
+ mm->clear_avail -= drm_buddy_block_size(mm, block);
list_add(&block->link, blocks);
}
@@ -782,7 +901,8 @@ int drm_buddy_alloc_blocks(struct drm_buddy *mm,
do {
if (flags & DRM_BUDDY_RANGE_ALLOCATION)
/* Allocate traversing within the range */
- block = alloc_range_bias(mm, start, end, order);
+ block = __drm_buddy_alloc_range_bias(mm, start, end,
+ order, flags);
else
/* Allocate from freelist */
block = alloc_from_freelist(mm, order, flags);
@@ -808,6 +928,8 @@ int drm_buddy_alloc_blocks(struct drm_buddy *mm,
mark_allocated(block);
mm->avail -= drm_buddy_block_size(mm, block);
+ if (drm_buddy_block_is_clear(block))
+ mm->clear_avail -= drm_buddy_block_size(mm, block);
kmemleak_update_trace(block);
list_add_tail(&block->link, &allocated);
@@ -846,7 +968,7 @@ int drm_buddy_alloc_blocks(struct drm_buddy *mm,
return 0;
err_free:
- drm_buddy_free_list(mm, &allocated);
+ drm_buddy_free_list_internal(mm, &allocated);
return err;
}
EXPORT_SYMBOL(drm_buddy_alloc_blocks);
@@ -879,8 +1001,8 @@ void drm_buddy_print(struct drm_buddy *mm, struct drm_printer *p)
{
int order;
- drm_printf(p, "chunk_size: %lluKiB, total: %lluMiB, free: %lluMiB\n",
- mm->chunk_size >> 10, mm->size >> 20, mm->avail >> 20);
+ drm_printf(p, "chunk_size: %lluKiB, total: %lluMiB, free: %lluMiB, clear_free: %lluMiB\n",
+ mm->chunk_size >> 10, mm->size >> 20, mm->avail >> 20, mm->clear_avail >> 20);
for (order = mm->max_order; order >= 0; order--) {
struct drm_buddy_block *block;
@@ -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);
@@ -83,7 +83,7 @@ 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++) {
@@ -95,7 +95,7 @@ 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);
}
@@ -190,7 +190,7 @@ 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);
}
@@ -236,7 +236,7 @@ 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);
}
@@ -271,7 +271,7 @@ 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);
}
@@ -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);
@@ -6,6 +6,7 @@
#ifndef __DRM_BUDDY_H__
#define __DRM_BUDDY_H__
+#include <linux/bitfield.h>
#include <linux/bitops.h>
#include <linux/list.h>
#include <linux/slab.h>
@@ -25,15 +26,20 @@
#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)
#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(9, 6)
+#define DRM_BUDDY_HEADER_UNUSED GENMASK_ULL(8, 6)
#define DRM_BUDDY_HEADER_ORDER GENMASK_ULL(5, 0)
u64 header;
@@ -86,6 +92,7 @@ struct drm_buddy {
u64 chunk_size;
u64 size;
u64 avail;
+ u64 clear_avail;
};
static inline u64
@@ -112,6 +119,12 @@ 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 +163,9 @@ 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,