Re: [PATCH v11 04/25] mm: devmap: refactor 1-based refcounting for ZONE_DEVICE pages

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On Mon, Dec 16, 2019 at 02:25:16PM -0800, John Hubbard wrote:
> An upcoming patch changes and complicates the refcounting and
> especially the "put page" aspects of it. In order to keep
> everything clean, refactor the devmap page release routines:
> 
> * Rename put_devmap_managed_page() to page_is_devmap_managed(),
>   and limit the functionality to "read only": return a bool,
>   with no side effects.
> 
> * Add a new routine, put_devmap_managed_page(), to handle checking
>   what kind of page it is, and what kind of refcount handling it
>   requires.
> 
> * Rename __put_devmap_managed_page() to free_devmap_managed_page(),
>   and limit the functionality to unconditionally freeing a devmap
>   page.

What the reason to separate put_devmap_managed_page() from
free_devmap_managed_page() if free_devmap_managed_page() has exacly one
caller? Is it preparation for the next patches?

> This is originally based on a separate patch by Ira Weiny, which
> applied to an early version of the put_user_page() experiments.
> Since then, Jérôme Glisse suggested the refactoring described above.
> 
> Cc: Christoph Hellwig <hch@xxxxxx>
> Suggested-by: Jérôme Glisse <jglisse@xxxxxxxxxx>
> Reviewed-by: Dan Williams <dan.j.williams@xxxxxxxxx>
> Reviewed-by: Jan Kara <jack@xxxxxxx>
> Signed-off-by: Ira Weiny <ira.weiny@xxxxxxxxx>
> Signed-off-by: John Hubbard <jhubbard@xxxxxxxxxx>
> ---
>  include/linux/mm.h | 17 +++++++++++++----
>  mm/memremap.c      | 16 ++--------------
>  mm/swap.c          | 24 ++++++++++++++++++++++++
>  3 files changed, 39 insertions(+), 18 deletions(-)
> 
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index c97ea3b694e6..77a4df06c8a7 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -952,9 +952,10 @@ static inline bool is_zone_device_page(const struct page *page)
>  #endif
>  
>  #ifdef CONFIG_DEV_PAGEMAP_OPS
> -void __put_devmap_managed_page(struct page *page);
> +void free_devmap_managed_page(struct page *page);
>  DECLARE_STATIC_KEY_FALSE(devmap_managed_key);
> -static inline bool put_devmap_managed_page(struct page *page)
> +
> +static inline bool page_is_devmap_managed(struct page *page)
>  {
>  	if (!static_branch_unlikely(&devmap_managed_key))
>  		return false;
> @@ -963,7 +964,6 @@ static inline bool put_devmap_managed_page(struct page *page)
>  	switch (page->pgmap->type) {
>  	case MEMORY_DEVICE_PRIVATE:
>  	case MEMORY_DEVICE_FS_DAX:
> -		__put_devmap_managed_page(page);
>  		return true;
>  	default:
>  		break;
> @@ -971,7 +971,14 @@ static inline bool put_devmap_managed_page(struct page *page)
>  	return false;
>  }
>  
> +bool put_devmap_managed_page(struct page *page);
> +
>  #else /* CONFIG_DEV_PAGEMAP_OPS */
> +static inline bool page_is_devmap_managed(struct page *page)
> +{
> +	return false;
> +}
> +
>  static inline bool put_devmap_managed_page(struct page *page)
>  {
>  	return false;
> @@ -1028,8 +1035,10 @@ static inline void put_page(struct page *page)
>  	 * need to inform the device driver through callback. See
>  	 * include/linux/memremap.h and HMM for details.
>  	 */
> -	if (put_devmap_managed_page(page))
> +	if (page_is_devmap_managed(page)) {
> +		put_devmap_managed_page(page);

put_devmap_managed_page() has yet another page_is_devmap_managed() check
inside. It looks strange.

>  		return;
> +	}
>  
>  	if (put_page_testzero(page))
>  		__put_page(page);
> diff --git a/mm/memremap.c b/mm/memremap.c
> index e899fa876a62..2ba773859031 100644
> --- a/mm/memremap.c
> +++ b/mm/memremap.c
> @@ -411,20 +411,8 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
>  EXPORT_SYMBOL_GPL(get_dev_pagemap);
>  
>  #ifdef CONFIG_DEV_PAGEMAP_OPS
> -void __put_devmap_managed_page(struct page *page)
> +void free_devmap_managed_page(struct page *page)
>  {
> -	int count = page_ref_dec_return(page);
> -
> -	/* still busy */
> -	if (count > 1)
> -		return;
> -
> -	/* only triggered by the dev_pagemap shutdown path */
> -	if (count == 0) {
> -		__put_page(page);
> -		return;
> -	}
> -
>  	/* notify page idle for dax */
>  	if (!is_device_private_page(page)) {
>  		wake_up_var(&page->_refcount);
> @@ -461,5 +449,5 @@ void __put_devmap_managed_page(struct page *page)
>  	page->mapping = NULL;
>  	page->pgmap->ops->page_free(page);
>  }
> -EXPORT_SYMBOL(__put_devmap_managed_page);
> +EXPORT_SYMBOL(free_devmap_managed_page);
>  #endif /* CONFIG_DEV_PAGEMAP_OPS */
> diff --git a/mm/swap.c b/mm/swap.c
> index 5341ae93861f..49f7c2eea0ba 100644
> --- a/mm/swap.c
> +++ b/mm/swap.c
> @@ -1102,3 +1102,27 @@ void __init swap_setup(void)
>  	 * _really_ don't want to cluster much more
>  	 */
>  }
> +
> +#ifdef CONFIG_DEV_PAGEMAP_OPS
> +bool put_devmap_managed_page(struct page *page)
> +{
> +	bool is_devmap = page_is_devmap_managed(page);
> +
> +	if (is_devmap) {

Reversing the condition would save you an indentation level.

> +		int count = page_ref_dec_return(page);
> +
> +		/*
> +		 * devmap page refcounts are 1-based, rather than 0-based: if
> +		 * refcount is 1, then the page is free and the refcount is
> +		 * stable because nobody holds a reference on the page.
> +		 */
> +		if (count == 1)
> +			free_devmap_managed_page(page);
> +		else if (!count)
> +			__put_page(page);
> +	}
> +
> +	return is_devmap;
> +}
> +EXPORT_SYMBOL(put_devmap_managed_page);
> +#endif
> -- 
> 2.24.1
> 
> 

-- 
 Kirill A. Shutemov



[Index of Archives]     [Kernel Newbies]     [Security]     [Netfilter]     [Bugtraq]     [Linux FS]     [Yosemite Forum]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux RAID]     [Samba]     [Video 4 Linux]     [Device Mapper]     [Linux Resources]

  Powered by Linux