Re: [PATCH v2 08/14] f2fs: optimize small block size large folio read

[Chao Yu]

On 9/15/26 12:19, Nanzhe Zhao wrote:
> The original f2fs_read_data_large_folio() implementation has limited
> benefit with a 4KB block size, mainly because updating
> read_pages_pending greatly increases the number of spinlock
> operations.
> 
> Use len_blks to batch read_pages_pending and iostat updates for
> contiguous mapped blocks. If the contiguous mapping covers the whole
> folio, skip f2fs_folio_state allocation for that folio.
> 
> Signed-off-by: Nanzhe Zhao <zhaonanzhe@xxxxxxxxxx>
> ---
>  fs/f2fs/data.c | 65 ++++++++++++++++++++++++++++++++++----------------
>  1 file changed, 45 insertions(+), 20 deletions(-)
> 
> diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
> index 287d83debf95..09ad5cf0d9aa 100644
> --- a/fs/f2fs/data.c
> +++ b/fs/f2fs/data.c
> @@ -173,8 +173,9 @@ static void f2fs_finish_read_bio(struct bio *bio, bool in_task)
>  			continue;
>  		}
>  
> -		if (folio_test_large(folio)) {
> -			struct f2fs_folio_state *ffs = folio->private;
> +		if (f2fs_folio_has_ffs(folio)) {
> +			struct f2fs_folio_state *ffs =
> +				(struct f2fs_folio_state *)folio->private;

I just notice that in somewhere, we missed to cast the private field to
f2fs_folio_state pointer as below, please take a look.

ffs = folio->private;

>  
>  			spin_lock_irqsave(&ffs->state_lock, flags);
>  			ffs->read_pages_pending -= nr_pages;
> @@ -2844,8 +2845,7 @@ static int f2fs_read_data_large_folio(struct inode *inode,
>  	pgoff_t index, offset, next_pgofs = 0;
>  	unsigned max_nr_pages = rac ? readahead_count(rac) :
>  				folio_nr_pages(folio);
> -	unsigned int nrpages;
> -	struct f2fs_folio_state *ffs;
> +	unsigned int nrpages, len_blks;
>  	int ret = 0;
>  	bool folio_in_bio = false;
>  
> @@ -2868,11 +2868,17 @@ static int f2fs_read_data_large_folio(struct inode *inode,
>  	folio_in_bio = false;
>  	index = folio->index;
>  	offset = 0;
> -	ffs = NULL;
>  	nrpages = folio_nr_pages(folio);
>  
> -	for (; nrpages; nrpages--, max_nr_pages--, index++, offset++) {
> +	for (; nrpages;
> +	     nrpages -= len_blks, max_nr_pages -= len_blks,
> +	     index += len_blks, offset += len_blks) {
>  		sector_t block_nr;
> +		bool whole_folio_in_bio;
> +		unsigned int i;
> +
> +		len_blks = 1;
> +
>  		/*
>  		 * Map blocks using the previous result first.
>  		 */
> @@ -2901,13 +2907,31 @@ static int f2fs_read_data_large_folio(struct inode *inode,
>  got_it:
>  		if ((map.m_flags & F2FS_MAP_MAPPED)) {
>  			block_nr = map.m_pblk + index - map.m_lblk;
> -			if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), block_nr,
> +
> +			len_blks = min_t(unsigned int, nrpages, max_nr_pages);
> +			len_blks = min_t(unsigned int, len_blks,
> +					(unsigned int)(map.m_lblk + map.m_len - index));
> +
> +			for (i = 0; i < len_blks; i++) {
> +				if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode),
> +						block_nr + i,
>  						DATA_GENERIC_ENHANCE_READ)) {
> -				ret = -EFSCORRUPTED;
> -				goto err_out;
> +					ret = -EFSCORRUPTED;
> +					goto err_out;
> +				}
>  			}
> +
> +			/*
> +			 * If an entire folio is added to one bio,
> +			 * folio_end_read() can complete the folio read status
> +			 * without relying on f2fs_folio_state.
> +			 */
> +			whole_folio_in_bio = offset == 0 &&
> +					len_blks == folio_nr_pages(folio);
> +
>  		} else {
>  			size_t page_offset = offset << PAGE_SHIFT;
> +
>  			folio_zero_range(folio, page_offset, PAGE_SIZE);
>  			if (vi && !fsverity_verify_blocks(vi, folio, PAGE_SIZE, page_offset)) {
>  				ret = -EIO;
> @@ -2917,15 +2941,13 @@ static int f2fs_read_data_large_folio(struct inode *inode,
>  		}
>  
>  		/* We must increment read_pages_pending before possible BIOs submitting
> -		 * to prevent from premature folio_end_read() call on folio
> +		 * to prevent from premature folio_end_read() call on folio.
>  		 */
> -		if (folio_test_large(folio)) {
> -			ffs = f2fs_ffs_find_or_alloc(folio);
> +		if (folio_test_large(folio) && !whole_folio_in_bio) {
> +			f2fs_ffs_find_or_alloc(folio);

Need to check return value?

Thanks,

>  
>  			/* set the bitmap to wait */
> -			spin_lock_irq(&ffs->state_lock);
> -			ffs->read_pages_pending++;
> -			spin_unlock_irq(&ffs->state_lock);
> +			f2fs_update_read_folio_pending(folio, len_blks);
>  		}
>  
>  		/*
> @@ -2949,17 +2971,20 @@ static int f2fs_read_data_large_folio(struct inode *inode,
>  		 * If the page is under writeback, we need to wait for
>  		 * its completion to see the correct decrypted data.
>  		 */
> -		f2fs_wait_on_block_writeback(inode, block_nr);
> +		for (i = 0; i < len_blks; i++)
> +			f2fs_wait_on_block_writeback(inode, block_nr + i);
>  
> -		if (!bio_add_folio(bio, folio, F2FS_BLKSIZE(F2FS_I_SB(inode)),
> +		if (!bio_add_folio(bio, folio,
> +				len_blks * F2FS_BLKSIZE(F2FS_I_SB(inode)),
>  				offset << PAGE_SHIFT))
>  			goto submit_and_realloc;
>  
>  		folio_in_bio = true;
> -		inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA);
> +		for (i = 0; i < len_blks; i++)
> +			inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA);
>  		f2fs_update_iostat(F2FS_I_SB(inode), NULL, FS_DATA_READ_IO,
> -				F2FS_BLKSIZE(F2FS_I_SB(inode)));
> -		last_block_in_bio = block_nr;
> +				len_blks * F2FS_BLKSIZE(F2FS_I_SB(inode)));
> +		last_block_in_bio = block_nr + len_blks - 1;
>  	}
>  	trace_f2fs_read_folio(folio, DATA);
>  err_out: