Re: [PATCH 12/13] writeback: add a writeback iterator

From: Brian Foster <bfoster@redhat.com>
To: Christoph Hellwig <hch@lst.de>
Cc: linux-mm@kvack.org, Matthew Wilcox <willy@infradead.org>,
	Jan Kara <jack@suse.com>, David Howells <dhowells@redhat.com>,
	Christian Brauner <brauner@kernel.org>,
	"Darrick J. Wong" <djwong@kernel.org>,
	linux-xfs@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	linux-kernel@vger.kernel.org
Subject: Re: [PATCH 12/13] writeback: add a writeback iterator
Date: Mon, 5 Feb 2024 10:33:52 -0500	[thread overview]
Message-ID: <ZcD/4HNZt1zu2eZF@bfoster> (raw)
In-Reply-To: <20240203071147.862076-13-hch@lst.de>

On Sat, Feb 03, 2024 at 08:11:46AM +0100, Christoph Hellwig wrote:
> Refactor the code left in write_cache_pages into an iterator that the
> file system can call to get the next folio for a writeback operation:
> 
> 	struct folio *folio = NULL;
> 
> 	while ((folio = writeback_iter(mapping, wbc, folio, &error))) {
> 		error = <do per-foli writeback>;
> 	}
> 
> The twist here is that the error value is passed by reference, so that
> the iterator can restore it when breaking out of the loop.
> 
> Handling of the magic AOP_WRITEPAGE_ACTIVATE value stays outside the
> iterator and needs is just kept in the write_cache_pages legacy wrapper.
> in preparation for eventually killing it off.
> 
> Heavily based on a for_each* based iterator from Matthew Wilcox.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> ---
>  include/linux/writeback.h |   4 +
>  mm/page-writeback.c       | 192 ++++++++++++++++++++++----------------
>  2 files changed, 118 insertions(+), 78 deletions(-)
> 
...
> diff --git a/mm/page-writeback.c b/mm/page-writeback.c
> index 3abb053e70580e..5fe4cdb7dbd61a 100644
> --- a/mm/page-writeback.c
> +++ b/mm/page-writeback.c
...
> @@ -2434,69 +2434,68 @@ static struct folio *writeback_get_folio(struct address_space *mapping,
>  }
>  
>  /**
...
>   */
> -int write_cache_pages(struct address_space *mapping,
> -		      struct writeback_control *wbc, writepage_t writepage,
> -		      void *data)
> +struct folio *writeback_iter(struct address_space *mapping,
> +		struct writeback_control *wbc, struct folio *folio, int *error)
>  {
...
> +	} else {
>  		wbc->nr_to_write -= folio_nr_pages(folio);
>  
> -		if (error == AOP_WRITEPAGE_ACTIVATE) {
> -			folio_unlock(folio);
> -			error = 0;
> -		}
> +		WARN_ON_ONCE(*error > 0);

Why the warning on writeback error here? It looks like new behavior, but
maybe I missed something. Otherwise the factoring LGTM.

Brian

>  
>  		/*
>  		 * For integrity writeback we have to keep going until we have
> @@ -2510,33 +2509,70 @@ int write_cache_pages(struct address_space *mapping,
>  		 * wbc->nr_to_write or encounter the first error.
>  		 */
>  		if (wbc->sync_mode == WB_SYNC_ALL) {
> -			if (error && !ret)
> -				ret = error;
> +			if (*error && !wbc->saved_err)
> +				wbc->saved_err = *error;
>  		} else {
> -			if (error || wbc->nr_to_write <= 0)
> +			if (*error || wbc->nr_to_write <= 0)
>  				goto done;
>  		}
>  	}
>  
> -	/*
> -	 * For range cyclic writeback we need to remember where we stopped so
> -	 * that we can continue there next time we are called.  If  we hit the
> -	 * last page and there is more work to be done, wrap back to the start
> -	 * of the file.
> -	 *
> -	 * For non-cyclic writeback we always start looking up at the beginning
> -	 * of the file if we are called again, which can only happen due to
> -	 * -ENOMEM from the file system.
> -	 */
> -	folio_batch_release(&wbc->fbatch);
> -	if (wbc->range_cyclic)
> -		mapping->writeback_index = 0;
> -	return ret;
> +	folio = writeback_get_folio(mapping, wbc);
> +	if (!folio) {
> +		/*
> +		 * To avoid deadlocks between range_cyclic writeback and callers
> +		 * that hold pages in PageWriteback to aggregate I/O until
> +		 * the writeback iteration finishes, we do not loop back to the
> +		 * start of the file.  Doing so causes a page lock/page
> +		 * writeback access order inversion - we should only ever lock
> +		 * multiple pages in ascending page->index order, and looping
> +		 * back to the start of the file violates that rule and causes
> +		 * deadlocks.
> +		 */
> +		if (wbc->range_cyclic)
> +			mapping->writeback_index = 0;
> +
> +		/*
> +		 * Return the first error we encountered (if there was any) to
> +		 * the caller.
> +		 */
> +		*error = wbc->saved_err;
> +	}
> +	return folio;
>  
>  done:
>  	folio_batch_release(&wbc->fbatch);
>  	if (wbc->range_cyclic)
>  		mapping->writeback_index = folio->index + folio_nr_pages(folio);
> +	return NULL;
> +}
> +
> +/**
> + * write_cache_pages - walk the list of dirty pages of the given address space and write all of them.
> + * @mapping: address space structure to write
> + * @wbc: subtract the number of written pages from *@wbc->nr_to_write
> + * @writepage: function called for each page
> + * @data: data passed to writepage function
> + *
> + * Return: %0 on success, negative error code otherwise
> + *
> + * Note: please use writeback_iter() instead.
> + */
> +int write_cache_pages(struct address_space *mapping,
> +		      struct writeback_control *wbc, writepage_t writepage,
> +		      void *data)
> +{
> +	struct folio *folio = NULL;
> +	int error;
> +
> +	while ((folio = writeback_iter(mapping, wbc, folio, &error))) {
> +		error = writepage(folio, wbc, data);
> +		if (error == AOP_WRITEPAGE_ACTIVATE) {
> +			folio_unlock(folio);
> +			error = 0;
> +		}
> +	}
> +
>  	return error;
>  }
>  EXPORT_SYMBOL(write_cache_pages);
> -- 
> 2.39.2
> 
> 