Re: [PATCH v3 5/5] gpu/buddy: Track per-order used blocks with a scoreboard

[Francois Dugast <francois.dugast@intel.com>]

On Mon, May 18, 2026 at 05:02:32PM +0100, Matthew Auld wrote:
> On 18/05/2026 15:14, Francois Dugast wrote:
> > Extend the scoreboard approach from the previous commit to used blocks,
> > so drm_buddy_print() can report per-order allocation pressure in O(1).
> > 
> > Unlike free blocks, an allocated block can leave the allocated state
> > through mark_free() (normal free and gpu_buddy_block_trim()) or be
> > consumed directly by gpu_block_free() during coalescing. Both sites are
> > guarded by gpu_buddy_block_is_allocated() and paired with the increment
> > in mark_allocated().
> > 
> > v2:
> > - Update after fix for use-after-free in split_block() call sites
> > - Change goto label to out_free_used_scoreboard for clarity
> > - Make drm_buddy_print() and gpu_buddy_print() symmetric for used and
> >    free
> > 
> > Signed-off-by: Francois Dugast <francois.dugast@intel.com>
> > Assisted-by: GitHub Copilot:claude-sonnet-4.6
> 
> Could potentially also assert that used_scoreboard is empty at fini(), as a
> quick sanity check that nothing got leaked/missed with the accounting. Would
> also then be checked across the selftests.

Good idea, will do.

> 
> Reviewed-by: Matthew Auld <matthew.auld@intel.com>
> 
> > ---
> >   drivers/gpu/buddy.c         | 39 +++++++++++++++++++++++++++----------
> >   drivers/gpu/drm/drm_buddy.c | 18 +++++++++++------
> >   include/linux/gpu_buddy.h   |  8 ++++++++
> >   3 files changed, 49 insertions(+), 16 deletions(-)
> > 
> > diff --git a/drivers/gpu/buddy.c b/drivers/gpu/buddy.c
> > index de18b63fef0a..f81d0d8fde15 100644
> > --- a/drivers/gpu/buddy.c
> > +++ b/drivers/gpu/buddy.c
> > @@ -194,6 +194,7 @@ static void mark_allocated(struct gpu_buddy *mm,
> >   	block->header |= GPU_BUDDY_ALLOCATED;
> >   	mm->free_scoreboard[gpu_buddy_block_order(block)]--;
> > +	mm->used_scoreboard[gpu_buddy_block_order(block)]++;
> >   	rbtree_remove(mm, block);
> >   }
> > @@ -203,6 +204,9 @@ static void mark_free(struct gpu_buddy *mm,
> >   {
> >   	enum gpu_buddy_free_tree tree;
> > +	if (gpu_buddy_block_is_allocated(block))
> > +		mm->used_scoreboard[gpu_buddy_block_order(block)]--;
> > +
> >   	block->header &= ~GPU_BUDDY_HEADER_STATE;
> >   	block->header |= GPU_BUDDY_FREE;
> > @@ -281,6 +285,9 @@ static unsigned int __gpu_buddy_free(struct gpu_buddy *mm,
> >   		if (force_merge && gpu_buddy_block_is_clear(buddy))
> >   			mm->clear_avail -= gpu_buddy_block_size(mm, buddy);
> > +		if (gpu_buddy_block_is_allocated(block))
> > +			mm->used_scoreboard[gpu_buddy_block_order(block)]--;
> > +
> >   		gpu_block_free(mm, block);
> >   		gpu_block_free(mm, buddy);
> > @@ -398,11 +405,17 @@ int gpu_buddy_init(struct gpu_buddy *mm, u64 size, u64 chunk_size)
> >   	if (!mm->free_scoreboard)
> >   		return -ENOMEM;
> > +	mm->used_scoreboard = kcalloc(mm->max_order + 1,
> > +				      sizeof(*mm->used_scoreboard),
> > +				      GFP_KERNEL);
> > +	if (!mm->used_scoreboard)
> > +		goto out_free_free_scoreboard;
> > +
> >   	mm->free_trees = kmalloc_array(GPU_BUDDY_MAX_FREE_TREES,
> >   				       sizeof(*mm->free_trees),
> >   				       GFP_KERNEL);
> >   	if (!mm->free_trees)
> > -		goto out_free_scoreboard;
> > +		goto out_free_used_scoreboard;
> >   	for_each_free_tree(i) {
> >   		mm->free_trees[i] = kmalloc_array(mm->max_order + 1,
> > @@ -464,7 +477,9 @@ int gpu_buddy_init(struct gpu_buddy *mm, u64 size, u64 chunk_size)
> >   	while (i--)
> >   		kfree(mm->free_trees[i]);
> >   	kfree(mm->free_trees);
> > -out_free_scoreboard:
> > +out_free_used_scoreboard:
> > +	kfree(mm->used_scoreboard);
> > +out_free_free_scoreboard:
> >   	kfree(mm->free_scoreboard);
> >   	return -ENOMEM;
> >   }
> > @@ -505,6 +520,7 @@ void gpu_buddy_fini(struct gpu_buddy *mm)
> >   	kfree(mm->free_trees);
> >   	kfree(mm->roots);
> >   	kfree(mm->free_scoreboard);
> > +	kfree(mm->used_scoreboard);
> >   }
> >   EXPORT_SYMBOL(gpu_buddy_fini);
> > @@ -1505,15 +1521,18 @@ void gpu_buddy_print(struct gpu_buddy *mm)
> >   		mm->chunk_size >> 10, mm->size >> 20, mm->avail >> 20, mm->clear_avail >> 20);
> >   	for (order = mm->max_order; order >= 0; order--) {
> > -		u64 count = mm->free_scoreboard[order];
> > -		u64 free = count * (mm->chunk_size << order);
> > -
> > -		if (free < SZ_1M)
> > -			pr_info("order-%2d free: %8llu KiB, blocks: %llu\n",
> > -				order, free >> 10, count);
> > +		u64 free_count = mm->free_scoreboard[order];
> > +		u64 used_count = mm->used_scoreboard[order];
> > +		u64 block_size = mm->chunk_size << order;
> > +		u64 free = free_count * block_size;
> > +		u64 used = used_count * block_size;
> > +
> > +		if (block_size < SZ_1M)
> > +			pr_info("order-%2d free: %8llu KiB, used: %8llu KiB, free_blocks: %llu, used_blocks: %llu\n",
> > +				order, free >> 10, used >> 10, free_count, used_count);
> >   		else
> > -			pr_info("order-%2d free: %8llu MiB, blocks: %llu\n",
> > -				order, free >> 20, count);
> > +			pr_info("order-%2d free: %8llu MiB, used: %8llu MiB, free_blocks: %llu, used_blocks: %llu\n",
> > +				order, free >> 20, used >> 20, free_count, used_count);
> >   	}
> >   }
> >   EXPORT_SYMBOL(gpu_buddy_print);
> > diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c
> > index eef995e08a37..1536e59c6fe7 100644
> > --- a/drivers/gpu/drm/drm_buddy.c
> > +++ b/drivers/gpu/drm/drm_buddy.c
> > @@ -47,17 +47,23 @@ void drm_buddy_print(struct gpu_buddy *mm, struct drm_printer *p)
> >   		   mm->chunk_size >> 10, mm->size >> 20, mm->avail >> 20, mm->clear_avail >> 20);
> >   	for (order = mm->max_order; order >= 0; order--) {
> > -		u64 count = mm->free_scoreboard[order];
> > -		u64 free = count * (mm->chunk_size << order);
> > +		u64 free_count = mm->free_scoreboard[order];
> > +		u64 used_count = mm->used_scoreboard[order];
> > +		u64 block_size = mm->chunk_size << order;
> > +		u64 free = free_count * block_size;
> > +		u64 used = used_count * block_size;
> >   		drm_printf(p, "order-%2d ", order);
> > -		if (free < SZ_1M)
> > -			drm_printf(p, "free: %8llu KiB", free >> 10);
> > +		if (block_size < SZ_1M)
> > +			drm_printf(p, "free: %8llu KiB, used: %8llu KiB",
> > +				   free >> 10, used >> 10);
> >   		else
> > -			drm_printf(p, "free: %8llu MiB", free >> 20);
> > +			drm_printf(p, "free: %8llu MiB, used: %8llu MiB",
> > +				   free >> 20, used >> 20);
> > -		drm_printf(p, ", blocks: %llu\n", count);
> > +		drm_printf(p, ", free_blocks: %llu, used_blocks: %llu\n",
> > +			   free_count, used_count);
> >   	}
> >   }
> >   EXPORT_SYMBOL(drm_buddy_print);
> > diff --git a/include/linux/gpu_buddy.h b/include/linux/gpu_buddy.h
> > index a28f7d7637ca..e037714563d8 100644
> > --- a/include/linux/gpu_buddy.h
> > +++ b/include/linux/gpu_buddy.h
> > @@ -180,6 +180,14 @@ struct gpu_buddy {
> >   	 * called on a free block.
> >   	 */
> >   	u64 *free_scoreboard;
> > +	/*
> > +	 * Per-order used block scoreboard: used_scoreboard[order] holds the
> > +	 * number of blocks of that order currently in the allocated state.
> > +	 * Incremented in mark_allocated(), decremented in mark_free() (guarded
> > +	 * by gpu_buddy_block_is_allocated()) and in __gpu_buddy_free() when an
> > +	 * allocated block is consumed directly during buddy coalescing.
> > +	 */
> > +	u64 *used_scoreboard;
> >   /* public: */
> >   	unsigned int n_roots;
> >   	unsigned int max_order;
>