[PATCH 2/2] drm/ttm: optimize the pool shrinker a bit v2

[Huang Rui]

On Thu, Apr 15, 2021 at 07:56:24PM +0800, Christian König wrote:
> Switch back to using a spinlock again by moving the IOMMU unmap outside
> of the locked region.
> 
> v2: Add a comment explaining why we need sync_shrinkers().
> 
> Signed-off-by: Christian König <christian.koenig at amd.com>

Series look good for me as well.

Acked-by: Huang Rui <ray.huang at amd.com>

> ---
>  drivers/gpu/drm/ttm/ttm_pool.c | 44 +++++++++++++++++-----------------
>  1 file changed, 22 insertions(+), 22 deletions(-)
> 
> diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
> index cb38b1a17b09..955836d569cc 100644
> --- a/drivers/gpu/drm/ttm/ttm_pool.c
> +++ b/drivers/gpu/drm/ttm/ttm_pool.c
> @@ -70,7 +70,7 @@ static struct ttm_pool_type global_uncached[MAX_ORDER];
>  static struct ttm_pool_type global_dma32_write_combined[MAX_ORDER];
>  static struct ttm_pool_type global_dma32_uncached[MAX_ORDER];
>  
> -static struct mutex shrinker_lock;
> +static spinlock_t shrinker_lock;
>  static struct list_head shrinker_list;
>  static struct shrinker mm_shrinker;
>  
> @@ -263,9 +263,9 @@ static void ttm_pool_type_init(struct ttm_pool_type *pt, struct ttm_pool *pool,
>  	spin_lock_init(&pt->lock);
>  	INIT_LIST_HEAD(&pt->pages);
>  
> -	mutex_lock(&shrinker_lock);
> +	spin_lock(&shrinker_lock);
>  	list_add_tail(&pt->shrinker_list, &shrinker_list);
> -	mutex_unlock(&shrinker_lock);
> +	spin_unlock(&shrinker_lock);
>  }
>  
>  /* Remove a pool_type from the global shrinker list and free all pages */
> @@ -273,9 +273,9 @@ static void ttm_pool_type_fini(struct ttm_pool_type *pt)
>  {
>  	struct page *p;
>  
> -	mutex_lock(&shrinker_lock);
> +	spin_lock(&shrinker_lock);
>  	list_del(&pt->shrinker_list);
> -	mutex_unlock(&shrinker_lock);
> +	spin_unlock(&shrinker_lock);
>  
>  	while ((p = ttm_pool_type_take(pt)))
>  		ttm_pool_free_page(pt->pool, pt->caching, pt->order, p);
> @@ -313,24 +313,19 @@ static struct ttm_pool_type *ttm_pool_select_type(struct ttm_pool *pool,
>  static unsigned int ttm_pool_shrink(void)
>  {
>  	struct ttm_pool_type *pt;
> -	unsigned int num_freed;
>  	struct page *p;
>  
> -	mutex_lock(&shrinker_lock);
> +	spin_lock(&shrinker_lock);
>  	pt = list_first_entry(&shrinker_list, typeof(*pt), shrinker_list);
> +	list_move_tail(&pt->shrinker_list, &shrinker_list);
> +	spin_unlock(&shrinker_lock);
>  
>  	p = ttm_pool_type_take(pt);
> -	if (p) {
> -		ttm_pool_free_page(pt->pool, pt->caching, pt->order, p);
> -		num_freed = 1 << pt->order;
> -	} else {
> -		num_freed = 0;
> -	}
> -
> -	list_move_tail(&pt->shrinker_list, &shrinker_list);
> -	mutex_unlock(&shrinker_lock);
> +	if (!p)
> +		return 0;
>  
> -	return num_freed;
> +	ttm_pool_free_page(pt->pool, pt->caching, pt->order, p);
> +	return 1 << pt->order;
>  }
>  
>  /* Return the allocation order based for a page */
> @@ -530,6 +525,11 @@ void ttm_pool_fini(struct ttm_pool *pool)
>  			for (j = 0; j < MAX_ORDER; ++j)
>  				ttm_pool_type_fini(&pool->caching[i].orders[j]);
>  	}
> +
> +	/* We removed the pool types from the LRU, but we need to also make sure
> +	 * that no shrinker is concurrently freeing pages from the pool.
> +	 */
> +	sync_shrinkers();
>  }
>  
>  /* As long as pages are available make sure to release at least one */
> @@ -604,7 +604,7 @@ static int ttm_pool_debugfs_globals_show(struct seq_file *m, void *data)
>  {
>  	ttm_pool_debugfs_header(m);
>  
> -	mutex_lock(&shrinker_lock);
> +	spin_lock(&shrinker_lock);
>  	seq_puts(m, "wc\t:");
>  	ttm_pool_debugfs_orders(global_write_combined, m);
>  	seq_puts(m, "uc\t:");
> @@ -613,7 +613,7 @@ static int ttm_pool_debugfs_globals_show(struct seq_file *m, void *data)
>  	ttm_pool_debugfs_orders(global_dma32_write_combined, m);
>  	seq_puts(m, "uc 32\t:");
>  	ttm_pool_debugfs_orders(global_dma32_uncached, m);
> -	mutex_unlock(&shrinker_lock);
> +	spin_unlock(&shrinker_lock);
>  
>  	ttm_pool_debugfs_footer(m);
>  
> @@ -640,7 +640,7 @@ int ttm_pool_debugfs(struct ttm_pool *pool, struct seq_file *m)
>  
>  	ttm_pool_debugfs_header(m);
>  
> -	mutex_lock(&shrinker_lock);
> +	spin_lock(&shrinker_lock);
>  	for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i) {
>  		seq_puts(m, "DMA ");
>  		switch (i) {
> @@ -656,7 +656,7 @@ int ttm_pool_debugfs(struct ttm_pool *pool, struct seq_file *m)
>  		}
>  		ttm_pool_debugfs_orders(pool->caching[i].orders, m);
>  	}
> -	mutex_unlock(&shrinker_lock);
> +	spin_unlock(&shrinker_lock);
>  
>  	ttm_pool_debugfs_footer(m);
>  	return 0;
> @@ -693,7 +693,7 @@ int ttm_pool_mgr_init(unsigned long num_pages)
>  	if (!page_pool_size)
>  		page_pool_size = num_pages;
>  
> -	mutex_init(&shrinker_lock);
> +	spin_lock_init(&shrinker_lock);
>  	INIT_LIST_HEAD(&shrinker_list);
>  
>  	for (i = 0; i < MAX_ORDER; ++i) {
> -- 
> 2.25.1
>