[PATCH] udmabuf: use kmem_cache to alloc udmabuf folio

[PATCH] udmabuf: use kmem_cache to alloc udmabuf folio

[Huan Yang]

The current udmabuf_folio contains a list_head and the corresponding
folio pointer, with a size of 24 bytes. udmabuf_folio uses kmalloc to
allocate memory.

However, kmalloc is a public pool, starting from 64 bytes. This means
that each udmabuf_folio allocation will waste 40 bytes.

Considering that each udmabuf creates a folio corresponding to a
udmabuf_folio, the wasted memory can be significant in the case of
memory fragmentation.

Furthermore, if udmabuf is frequently used, the allocation and
deallocation of udmabuf_folio will also be frequent.

Therefore, this patch adds a kmem_cache dedicated to the allocation and
deallocation of udmabuf_folio.This is expected to improve the
performance of allocation and deallocation within the expected range,
while also avoiding memory waste.

Signed-off-by: Huan Yang <link@vivo.com>
---
 drivers/dma-buf/udmabuf.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c
index 047c3cd2ceff..db4de8c745ce 100644
--- a/drivers/dma-buf/udmabuf.c
+++ b/drivers/dma-buf/udmabuf.c
@@ -24,6 +24,8 @@ static int size_limit_mb = 64;
 module_param(size_limit_mb, int, 0644);
 MODULE_PARM_DESC(size_limit_mb, "Max size of a dmabuf, in megabytes. Default is 64.");
 
+static struct kmem_cache *udmabuf_folio_cachep;
+
 struct udmabuf {
 	pgoff_t pagecount;
 	struct folio **folios;
@@ -169,7 +171,7 @@ static void unpin_all_folios(struct list_head *unpin_list)
 		unpin_folio(ubuf_folio->folio);
 
 		list_del(&ubuf_folio->list);
-		kfree(ubuf_folio);
+		kmem_cache_free(udmabuf_folio_cachep, ubuf_folio);
 	}
 }
 
@@ -178,7 +180,7 @@ static int add_to_unpin_list(struct list_head *unpin_list,
 {
 	struct udmabuf_folio *ubuf_folio;
 
-	ubuf_folio = kzalloc(sizeof(*ubuf_folio), GFP_KERNEL);
+	ubuf_folio = kmem_cache_alloc(udmabuf_folio_cachep, GFP_KERNEL);
 	if (!ubuf_folio)
 		return -ENOMEM;
 
@@ -492,10 +494,20 @@ static int __init udmabuf_dev_init(void)
 	if (ret < 0) {
 		pr_err("Could not setup DMA mask for udmabuf device\n");
 		misc_deregister(&udmabuf_misc);
-		return ret;
+		goto err;
+	}
+
+	udmabuf_folio_cachep = KMEM_CACHE(udmabuf_folio, 0);
+	if (unlikely(!udmabuf_folio_cachep)) {
+		ret = -ENOMEM;
+		goto err;
 	}
 
 	return 0;
+
+err:
+	misc_deregister(&udmabuf_misc);
+	return ret;
 }
 
 static void __exit udmabuf_dev_exit(void)

base-commit: cd19ac2f903276b820f5d0d89de0c896c27036ed
-- 
2.45.2

Re: [PATCH] udmabuf: use kmem_cache to alloc udmabuf folio

[Daniel Vetter]

On Wed, Jul 31, 2024 at 11:34:49AM +0800, Huan Yang wrote:
> The current udmabuf_folio contains a list_head and the corresponding
> folio pointer, with a size of 24 bytes. udmabuf_folio uses kmalloc to
> allocate memory.
> 
> However, kmalloc is a public pool, starting from 64 bytes. This means
> that each udmabuf_folio allocation will waste 40 bytes.
> 
> Considering that each udmabuf creates a folio corresponding to a
> udmabuf_folio, the wasted memory can be significant in the case of
> memory fragmentation.
> 
> Furthermore, if udmabuf is frequently used, the allocation and
> deallocation of udmabuf_folio will also be frequent.
> 
> Therefore, this patch adds a kmem_cache dedicated to the allocation and
> deallocation of udmabuf_folio.This is expected to improve the
> performance of allocation and deallocation within the expected range,
> while also avoiding memory waste.
> 
> Signed-off-by: Huan Yang <link@vivo.com>
> ---
>  drivers/dma-buf/udmabuf.c | 18 +++++++++++++++---
>  1 file changed, 15 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c
> index 047c3cd2ceff..db4de8c745ce 100644
> --- a/drivers/dma-buf/udmabuf.c
> +++ b/drivers/dma-buf/udmabuf.c
> @@ -24,6 +24,8 @@ static int size_limit_mb = 64;
>  module_param(size_limit_mb, int, 0644);
>  MODULE_PARM_DESC(size_limit_mb, "Max size of a dmabuf, in megabytes. Default is 64.");
>  
> +static struct kmem_cache *udmabuf_folio_cachep;
> +
>  struct udmabuf {
>  	pgoff_t pagecount;
>  	struct folio **folios;
> @@ -169,7 +171,7 @@ static void unpin_all_folios(struct list_head *unpin_list)
>  		unpin_folio(ubuf_folio->folio);
>  
>  		list_del(&ubuf_folio->list);
> -		kfree(ubuf_folio);
> +		kmem_cache_free(udmabuf_folio_cachep, ubuf_folio);
>  	}
>  }
>  
> @@ -178,7 +180,7 @@ static int add_to_unpin_list(struct list_head *unpin_list,
>  {
>  	struct udmabuf_folio *ubuf_folio;
>  
> -	ubuf_folio = kzalloc(sizeof(*ubuf_folio), GFP_KERNEL);
> +	ubuf_folio = kmem_cache_alloc(udmabuf_folio_cachep, GFP_KERNEL);
>  	if (!ubuf_folio)
>  		return -ENOMEM;
>  
> @@ -492,10 +494,20 @@ static int __init udmabuf_dev_init(void)
>  	if (ret < 0) {
>  		pr_err("Could not setup DMA mask for udmabuf device\n");
>  		misc_deregister(&udmabuf_misc);

misc_deregister() is now called twice in this error path, I think you've
forgotten to delete this line too?

Otherwise lgtm.
-Sima

> -		return ret;
> +		goto err;
> +	}
> +
> +	udmabuf_folio_cachep = KMEM_CACHE(udmabuf_folio, 0);
> +	if (unlikely(!udmabuf_folio_cachep)) {
> +		ret = -ENOMEM;
> +		goto err;
>  	}
>  
>  	return 0;
> +
> +err:
> +	misc_deregister(&udmabuf_misc);
> +	return ret;
>  }
>  
>  static void __exit udmabuf_dev_exit(void)
> 
> base-commit: cd19ac2f903276b820f5d0d89de0c896c27036ed
> -- 
> 2.45.2
> 

-- 
Daniel Vetter
Software Engineer, Intel Corporation
http://blog.ffwll.ch