Re: [PATCH v2 05/10] ceph: convert ceph_submit_write() to folios

[Tal Zussman]

On 8/4/26 2:52 PM, Tal Zussman wrote:
> Convert the request assembly loop and error paths in ceph_submit_write()
> to folios. This drops ceph's uses of the set_page_writeback(),
> redirty_page_for_writepage(), and unlock_page() compatibility wrappers
> in the writeback submission path.
> 
> Add ceph_folio_start_fscache(), a folio counterpart of
> ceph_set_page_fscache(). The remaining caller of the latter in
> write_folio_nounlock() will be converted separately.
> 
> In total, this removes nine calls to compound_head() hidden in the
> page-based APIs, while adding four explicit ones via page_folio().
> 
> Note that get_writepages_data_length() must still be passed the
> possibly-bounce folio, not the unwrapped pagecache folio, as it checks
> fscrypt_is_bounce_folio() to round encrypted lengths up to the fscrypt
> block size.
> 
> No functional change.
> 
> Signed-off-by: Tal Zussman <tz2294@xxxxxxxxxxxx>
> ---
>  fs/ceph/addr.c | 44 ++++++++++++++++++++++++++------------------
>  1 file changed, 26 insertions(+), 18 deletions(-)
> 
> diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
> index c81e9da42df9..a96986c503bf 100644
> --- a/fs/ceph/addr.c
> +++ b/fs/ceph/addr.c
> @@ -553,6 +553,11 @@ const struct netfs_request_ops ceph_netfs_ops = {
>  };
>  
>  #ifdef CONFIG_CEPH_FSCACHE
> +static void ceph_folio_start_fscache(struct folio *folio)
> +{
> +	folio_start_private_2(folio); /* [DEPRECATED] */
> +}
> +
>  static void ceph_set_page_fscache(struct page *page)
>  {
>  	folio_start_private_2(page_folio(page)); /* [DEPRECATED] */
> @@ -575,6 +580,10 @@ static void ceph_fscache_write_to_cache(struct inode *inode, u64 off, u64 len, b
>  			       ceph_fscache_write_terminated, inode, true, caching);
>  }
>  #else
> +static inline void ceph_folio_start_fscache(struct folio *folio)
> +{
> +}
> +
>  static inline void ceph_set_page_fscache(struct page *page)
>  {
>  }
> @@ -1436,14 +1445,14 @@ int ceph_submit_write(struct address_space *mapping,
>  	struct ceph_client *cl = fsc->client;
>  	struct ceph_vino vino = ceph_vino(inode);
>  	struct ceph_osd_request *req = NULL;
> -	struct page *page = NULL;
> +	struct folio *folio = NULL;
>  	bool caching = ceph_is_cache_enabled(inode);
>  	u64 offset;
>  	u64 len;
>  	unsigned i;
>  
>  new_request:
> -	offset = ceph_fscrypt_page_offset(ceph_wbc->pages[0]);
> +	offset = ceph_fscrypt_folio_offset(page_folio(ceph_wbc->pages[0]));
>  	len = ceph_wbc->wsize;
>  
>  	req = ceph_osdc_new_request(&fsc->client->osdc,
> @@ -1467,29 +1476,28 @@ int ceph_submit_write(struct address_space *mapping,
>  		BUG_ON(IS_ERR(req));
>  	}
>  
> -	page = ceph_wbc->pages[ceph_wbc->locked_pages - 1];
> -	BUG_ON(len < ceph_fscrypt_page_offset(page) + thp_size(page) - offset);
> +	folio = page_folio(ceph_wbc->pages[ceph_wbc->locked_pages - 1]);
> +	BUG_ON(len < ceph_fscrypt_folio_offset(folio) + folio_size(folio) - offset);
>  
>  	if (!ceph_inc_osd_stopping_blocker(fsc->mdsc)) {
>  		for (i = 0; i < folio_batch_count(&ceph_wbc->fbatch); i++) {
> -			struct folio *folio = ceph_wbc->fbatch.folios[i];
> +			folio = ceph_wbc->fbatch.folios[i];
>  
>  			if (!folio)
>  				continue;

This, ...

>  
> -			page = &folio->page;
> -			redirty_page_for_writepage(wbc, page);
> -			unlock_page(page);
> +			folio_redirty_for_writepage(wbc, folio);
> +			folio_unlock(folio);
>  		}
>  
>  		for (i = 0; i < ceph_wbc->locked_pages; i++) {
> -			page = ceph_fscrypt_pagecache_page(ceph_wbc->pages[i]);
> +			folio = ceph_fscrypt_pagecache_folio(page_folio(ceph_wbc->pages[i]));
>  
> -			if (!page)
> +			if (!folio)
>  				continue;
>  

... and this check are unnecessary. ceph_fscrypt_pagecache_page() can't
take or return NULL, and ceph_shift_unused_folios_left() compacts NULLs
out of ceph_wbc->fbatch. Will remove both in v3.

> -			redirty_page_for_writepage(wbc, page);
> -			unlock_page(page);
> +			folio_redirty_for_writepage(wbc, folio);
> +			folio_unlock(folio);
>  		}
>  
>  		ceph_osdc_put_request(req);
> @@ -1506,8 +1514,8 @@ int ceph_submit_write(struct address_space *mapping,
>  	for (i = 0; i < ceph_wbc->locked_pages; i++) {
>  		u64 cur_offset;
>  
> -		page = ceph_fscrypt_pagecache_page(ceph_wbc->pages[i]);
> -		cur_offset = page_offset(page);
> +		folio = ceph_fscrypt_pagecache_folio(page_folio(ceph_wbc->pages[i]));
> +		cur_offset = folio_pos(folio);
>  
>  		/*
>  		 * Discontinuity in page range? Ceph can handle that by just passing
> @@ -1540,12 +1548,12 @@ int ceph_submit_write(struct address_space *mapping,
>  			ceph_wbc->op_idx++;
>  		}
>  
> -		set_page_writeback(page);
> +		folio_start_writeback(folio);
>  
>  		if (caching)
> -			ceph_set_page_fscache(page);
> +			ceph_folio_start_fscache(folio);
>  
> -		len += thp_size(page);
> +		len += folio_size(folio);
>  	}
>  
>  	ceph_fscache_write_to_cache(inode, offset, len, caching);
> @@ -1556,7 +1564,7 @@ int ceph_submit_write(struct address_space *mapping,
>  		/* writepages_finish() clears writeback pages
>  		 * according to the data length, so make sure
>  		 * data length covers all locked pages */
> -		u64 min_len = len + 1 - thp_size(page);
> +		u64 min_len = len + 1 - folio_size(folio);
>  		len = get_writepages_data_length(inode,
>  						 page_folio(ceph_wbc->pages[i - 1]),
>  						 offset);
>