[PATCH 06/17] ttm/pool: make pool shrinker NUMA aware

[Christian König]

On 30.06.25 06:49, Dave Airlie wrote:
> From: Dave Airlie <airlied at redhat.com>
> 
> This enable NUMA awareness for the shrinker on the
> ttm pools.


Looks good from my side, but the last time I suggested this Sima explicitly told me that it isn't very fruitful. Adding her to comment as well.

Christian.

> 
> Cc: Christian Koenig <christian.koenig at amd.com>
> Cc: Dave Chinner <david at fromorbit.com>
> Signed-off-by: Dave Airlie <airlied at redhat.com>
> ---
>  drivers/gpu/drm/ttm/ttm_pool.c | 38 +++++++++++++++++++---------------
>  1 file changed, 21 insertions(+), 17 deletions(-)
> 
> diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
> index 95bbbc843b97..66cd963b24dc 100644
> --- a/drivers/gpu/drm/ttm/ttm_pool.c
> +++ b/drivers/gpu/drm/ttm/ttm_pool.c
> @@ -416,12 +416,12 @@ static struct ttm_pool_type *ttm_pool_select_type(struct ttm_pool *pool,
>  	return NULL;
>  }
>  
> -/* Free pages using the global shrinker list */
> -static unsigned int ttm_pool_shrink(void)
> +/* Free pages using the per-node shrinker list */
> +static unsigned int ttm_pool_shrink(int nid, unsigned long num_to_free)
>  {
> +	LIST_HEAD(dispose);
>  	struct ttm_pool_type *pt;
>  	unsigned int num_pages;
> -	struct page *p;
>  
>  	down_read(&pool_shrink_rwsem);
>  	spin_lock(&shrinker_lock);
> @@ -429,13 +429,10 @@ static unsigned int ttm_pool_shrink(void)
>  	list_move_tail(&pt->shrinker_list, &shrinker_list);
>  	spin_unlock(&shrinker_lock);
>  
> -	p = ttm_pool_type_take(pt, ttm_pool_nid(pt->pool));
> -	if (p) {
> -		ttm_pool_free_page(pt->pool, pt->caching, pt->order, p, true);
> -		num_pages = 1 << pt->order;
> -	} else {
> -		num_pages = 0;
> -	}
> +	num_pages = list_lru_walk_node(&pt->pages, nid, pool_move_to_dispose_list, &dispose, &num_to_free);
> +	num_pages *= 1 << pt->order;
> +
> +	ttm_pool_dispose_list(pt, &dispose);
>  	up_read(&pool_shrink_rwsem);
>  
>  	return num_pages;
> @@ -784,6 +781,7 @@ static int __ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt,
>  		pt = ttm_pool_select_type(pool, page_caching, order);
>  		if (pt && allow_pools)
>  			p = ttm_pool_type_take(pt, ttm_pool_nid(pool));
> +
>  		/*
>  		 * If that fails or previously failed, allocate from system.
>  		 * Note that this also disallows additional pool allocations using
> @@ -932,8 +930,10 @@ void ttm_pool_free(struct ttm_pool *pool, struct ttm_tt *tt)
>  {
>  	ttm_pool_free_range(pool, tt, tt->caching, 0, tt->num_pages);
>  
> -	while (atomic_long_read(&allocated_pages) > page_pool_size)
> -		ttm_pool_shrink();
> +	while (atomic_long_read(&allocated_pages) > page_pool_size) {
> +		unsigned long diff = page_pool_size - atomic_long_read(&allocated_pages);
> +		ttm_pool_shrink(ttm_pool_nid(pool), diff);
> +	}
>  }
>  EXPORT_SYMBOL(ttm_pool_free);
>  
> @@ -1190,7 +1190,7 @@ static unsigned long ttm_pool_shrinker_scan(struct shrinker *shrink,
>  	unsigned long num_freed = 0;
>  
>  	do
> -		num_freed += ttm_pool_shrink();
> +		num_freed += ttm_pool_shrink(sc->nid, sc->nr_to_scan);
>  	while (num_freed < sc->nr_to_scan &&
>  	       atomic_long_read(&allocated_pages));
>  
> @@ -1323,11 +1323,15 @@ static int ttm_pool_debugfs_shrink_show(struct seq_file *m, void *data)
>  		.nr_to_scan = TTM_SHRINKER_BATCH,
>  	};
>  	unsigned long count;
> +	int nid;
>  
>  	fs_reclaim_acquire(GFP_KERNEL);
> -	count = ttm_pool_shrinker_count(mm_shrinker, &sc);
> -	seq_printf(m, "%lu/%lu\n", count,
> -		   ttm_pool_shrinker_scan(mm_shrinker, &sc));
> +	for_each_node(nid) {
> +		sc.nid = nid;
> +		count = ttm_pool_shrinker_count(mm_shrinker, &sc);
> +		seq_printf(m, "%d: %lu/%lu\n", nid, count,
> +			   ttm_pool_shrinker_scan(mm_shrinker, &sc));
> +	}
>  	fs_reclaim_release(GFP_KERNEL);
>  
>  	return 0;
> @@ -1375,7 +1379,7 @@ int ttm_pool_mgr_init(unsigned long num_pages)
>  #endif
>  #endif
>  
> -	mm_shrinker = shrinker_alloc(0, "drm-ttm_pool");
> +	mm_shrinker = shrinker_alloc(SHRINKER_NUMA_AWARE, "drm-ttm_pool");
>  	if (!mm_shrinker)
>  		return -ENOMEM;
>