Re: [PATCH 05/14] f2fs: support large folio writeback

[Chao Yu <chao@kernel.org>]

On 8/26/26 16:26, Nanzhe Zhao wrote:
> Large folio can contain multiple dirty ranges.
> Add a folio-based writeback path for large-folio mapping files
> and keep the legacy f2fs_write_cache_pages() path unchanged for
> non large-folio mapping files.
> 
> Signed-off-by: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
> ---
>  fs/f2fs/data.c | 404 ++++++++++++++++++++++++++++++++++++++++++++++++-
>  1 file changed, 398 insertions(+), 6 deletions(-)
> 
> diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
> index dff802725544..608d8ea8e607 100644
> --- a/fs/f2fs/data.c
> +++ b/fs/f2fs/data.c
> @@ -358,6 +358,7 @@ static void f2fs_write_end_bio(struct bio *bio)
>  		struct folio *folio = fi.folio;
>  		unsigned int nr_pages = fi.length >> PAGE_SHIFT;
>  		enum count_type type;
> +		bool finished = true;
>  
>  		if (fscrypt_is_bounce_folio(folio)) {
>  			struct folio *io_folio = folio;
> @@ -388,11 +389,20 @@ static void f2fs_write_end_bio(struct bio *bio)
>  				folio->index, NODE_TYPE_REGULAR, true);
>  			f2fs_bug_on(sbi, folio->index != nid_of_node(folio));
>  		}
> +		if (f2fs_folio_has_ffs(folio)) {
> +			struct f2fs_folio_state *ffs =
> +				(struct f2fs_folio_state *)folio->private;
> +
> +			finished = atomic_sub_and_test(nr_pages,
> +					&ffs->write_pages_pending);
> +		}
> +
> +		while (nr_pages--)
> +			dec_page_count(sbi, type);
> +
>  		if (f2fs_in_warm_node_list(folio))
>  			f2fs_del_fsync_node_entry(sbi, folio);
>  
> -		dec_page_count(sbi, type);

We should not relocate dec_page_count() above f2fs_in_warm_node_list() to
avoid racing bugs.

> -
>  		/*
>  		 * we should access sbi before folio_end_writeback() to
>  		 * avoid racing w/ kill_f2fs_super()
> @@ -401,8 +411,10 @@ static void f2fs_write_end_bio(struct bio *bio)
>  				wq_has_sleeper(&sbi->cp_wait))
>  			wake_up(&sbi->cp_wait);
>  
> -		folio_clear_f2fs_gcing(folio);
> -		folio_end_writeback(folio);
> +		if (finished) {
> +			folio_clear_f2fs_gcing(folio);
> +			folio_end_writeback(folio);
> +		}
>  	}
>  
>  	bio_put(bio);
> @@ -2669,7 +2681,7 @@ static void f2fs_ffs_mark_subrange_uptodate(struct folio *folio, size_t offset,
>  		folio_mark_uptodate(folio);
>  }
>  
> -static void f2fs_ffs_mark_subrange_dirty(struct folio *folio,
> +void f2fs_ffs_mark_subrange_dirty(struct folio *folio,
>  				    size_t offset, size_t len)
>  {
>  	struct f2fs_folio_state *ffs;
> @@ -2692,6 +2704,86 @@ static void f2fs_ffs_mark_subrange_dirty(struct folio *folio,
>  	spin_unlock_irqrestore(&ffs->state_lock, flags);
>  }
>  
> +static bool __ffs_clear_subrange_dirty(struct folio *folio,
> +			struct f2fs_folio_state *ffs, size_t offset, size_t len)
> +{
> +	unsigned int nr_subpages = folio_nr_pages(folio);
> +	unsigned int start, end;
> +
> +	start = offset >> PAGE_SHIFT;
> +	end = (offset + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
> +	end = min(end, nr_subpages);
> +
> +	bitmap_clear(ffs->state, nr_subpages + start, end - start);
> +	return find_next_bit(ffs->state, 2 * nr_subpages, nr_subpages) <
> +			2 * nr_subpages;
> +}
> +
> +void f2fs_ffs_clear_subrange_dirty(struct folio *folio, size_t offset, size_t len)
> +{
> +	struct f2fs_folio_state *ffs;
> +	unsigned long flags;
> +
> +	if (!f2fs_folio_has_ffs(folio))
> +		return;
> +
> +	ffs = (struct f2fs_folio_state *)folio->private;
> +	spin_lock_irqsave(&ffs->state_lock, flags);
> +	__ffs_clear_subrange_dirty(folio, ffs, offset, len);
> +	spin_unlock_irqrestore(&ffs->state_lock, flags);
> +}
> +
> +static unsigned int ffs_next_dirty_subpage(struct f2fs_folio_state *ffs,
> +			const struct folio *folio, unsigned int start,
> +			unsigned int end)
> +{
> +	unsigned int nr_subpages = folio_nr_pages(folio);
> +
> +	return find_next_bit(ffs->state, nr_subpages + end + 1,
> +			nr_subpages + start) - nr_subpages;
> +}
> +
> +static unsigned int ffs_next_clean_subpage(struct f2fs_folio_state *ffs,
> +			const struct folio *folio, unsigned int start,
> +			unsigned int end)
> +{
> +	unsigned int nr_subpages = folio_nr_pages(folio);
> +
> +	return find_next_zero_bit(ffs->state, nr_subpages + end + 1,
> +			nr_subpages + start) - nr_subpages;
> +}
> +
> +static unsigned int ffs_find_dirty_range(struct folio *folio,
> +					u64 *range_start, u64 range_end)
> +{
> +	struct f2fs_folio_state *ffs;
> +	unsigned int start, end, nr_pages;
> +
> +	if (*range_start >= range_end)
> +		return 0;
> +
> +	if (!f2fs_folio_has_ffs(folio))
> +		return range_end - *range_start;
> +
> +	ffs = (struct f2fs_folio_state *)folio->private;
> +	start = offset_in_folio(folio, *range_start) >> PAGE_SHIFT;
> +	end = DIV_ROUND_UP(min_not_zero(offset_in_folio(folio, range_end),
> +					folio_size(folio)), PAGE_SIZE) - 1;
> +
> +	start = ffs_next_dirty_subpage(ffs, folio, start, end);
> +	if (start > end)
> +		return 0;
> +
> +	if (start == end)
> +		nr_pages = 1;
> +	else
> +		nr_pages = ffs_next_clean_subpage(ffs, folio,
> +						 start + 1, end) - start;
> +
> +	*range_start = folio_pos(folio) + ((u64)start << PAGE_SHIFT);
> +	return (u64)nr_pages << PAGE_SHIFT;
> +}
> +
>  static bool find_next_valid_block(const struct folio *folio,
>  				  size_t orig_off, size_t *need_off,
>  				  size_t len)
> @@ -3309,6 +3401,139 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
>  	return err;
>  }
>  
> +static int f2fs_write_single_data_folio(struct folio *folio, int *submitted,
> +					struct writeback_control *wbc,
> +					enum iostat_type io_type,
> +					u64 start, u64 end)
> +{
> +	struct inode *inode = folio->mapping->host;
> +	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
> +	bool atomic_commit = f2fs_is_atomic_file(inode) &&
> +				folio_test_f2fs_atomic(folio);
> +	struct inode *dn_inode = atomic_commit ?
> +				F2FS_I(inode)->cow_inode : inode;
> +	u64 pos = folio_pos(folio);
> +	pgoff_t start_idx = (start - pos) >> PAGE_SHIFT;
> +	pgoff_t end_idx = (end - 1 - pos) >> PAGE_SHIFT;
> +	int local_submitted = 0;
> +	int err = 0;
> +
> +	for (pgoff_t i = start_idx; i <= end_idx; i++) {
> +		struct dnode_of_data dn;
> +		struct node_info ni;
> +		pgoff_t data_idx = folio->index + i;
> +		bool ipu_force = false;
> +		struct f2fs_io_info fio = {
> +			.sbi = sbi,
> +			.ino = inode->i_ino,
> +			.type = DATA,
> +			.op = REQ_OP_WRITE,
> +			.op_flags = wbc_to_write_flags(wbc),
> +			.old_blkaddr = NULL_ADDR,
> +			.folio = folio,
> +			.folio_offset = i,
> +			.folio_blkcnt = 1,
> +			.encrypted_page = NULL,
> +			.submitted = 0,
> +			.need_lock = LOCK_DONE,
> +			.meta_gc = f2fs_meta_inode_gc_required(inode) ? 1 : 0,
> +			.io_type = io_type,
> +			.io_wbc = wbc,
> +		};
> +
> +		if (f2fs_folio_has_ffs(folio)) {
> +			struct f2fs_folio_state *ffs =
> +				(struct f2fs_folio_state *)folio->private;
> +
> +			atomic_inc(&ffs->write_pages_pending);
> +		}
> +
> +		set_new_dnode(&dn, dn_inode, NULL, NULL, 0);
> +
> +		if (!atomic_commit && need_inplace_update(&fio) &&

In f2fs_write_single_data_page(), we didn't have !atomic_commit condition
in the check? can we drop !atomic_commit check?

need_inplace_update() has checked w/ f2fs_used_in_atomic_write().

- need_inplace_update
 - f2fs_should_update_outplace
  - f2fs_used_in_atomic_write

static inline bool f2fs_used_in_atomic_write(struct inode *inode)
{
	return f2fs_is_atomic_file(inode) || f2fs_is_cow_file(inode);
}

> +		    f2fs_lookup_read_extent_cache_block(inode, data_idx,
> +							&fio.old_blkaddr)) {
> +			if (!f2fs_is_valid_blkaddr(sbi, fio.old_blkaddr,
> +						   DATA_GENERIC_ENHANCE)) {
> +				err = -EFSCORRUPTED;
> +				goto rollback;
> +			}
> +			ipu_force = true;
> +			goto got_it;
> +		}
> +
> +		err = f2fs_get_dnode_of_data(&dn, data_idx, LOOKUP_NODE);
> +		if (err)
> +			goto rollback;
> +
> +		fio.old_blkaddr = dn.data_blkaddr;
> +
> +got_it:
> +		if (__is_valid_data_blkaddr(fio.old_blkaddr) &&
> +		    !f2fs_is_valid_blkaddr(sbi, fio.old_blkaddr,
> +					   DATA_GENERIC_ENHANCE)) {
> +			err = -EFSCORRUPTED;
> +			goto rollback;
> +		}
> +
> +		if (fio.meta_gc)
> +			f2fs_wait_on_block_writeback(inode, fio.old_blkaddr);
> +
> +		if (!atomic_commit && (ipu_force ||
> +		    (__is_valid_data_blkaddr(fio.old_blkaddr) &&
> +					    need_inplace_update(&fio)))) {
> +			err = f2fs_encrypt_one_page(&fio);
> +			if (err)
> +				goto rollback;
> +
> +			f2fs_put_dnode(&dn);
> +			err = f2fs_inplace_write_data(&fio);
> +			if (err) {
> +				if (fscrypt_inode_uses_fs_layer_crypto(inode))
> +					fscrypt_finalize_bounce_page(
> +							&fio.encrypted_page);
> +				goto rollback_no_dnode;
> +			}
> +
> +			local_submitted++;
> +			set_inode_flag(inode, FI_UPDATE_WRITE);

			trace_f2fs_do_write_data_page(folio, IPU);

> +			continue;
> +		}
> +
> +		err = f2fs_get_node_info(sbi, dn.nid, &ni, false);
> +		if (err)
> +			goto rollback;
> +
> +		fio.version = ni.version;
> +
> +		err = f2fs_encrypt_one_page(&fio);
> +		if (err)
> +			goto rollback;
> +
> +		f2fs_outplace_write_data(&dn, &fio);
> +		local_submitted++;
> +		set_inode_flag(inode, FI_APPEND_WRITE);
> +		trace_f2fs_do_write_data_page(folio, OPU);
> +		f2fs_put_dnode(&dn);
> +		continue;
> +
> +rollback:
> +		f2fs_put_dnode(&dn);
> +rollback_no_dnode:
> +		if (f2fs_folio_has_ffs(folio)) {
> +			struct f2fs_folio_state *ffs =
> +				(struct f2fs_folio_state *)folio->private;
> +
> +			atomic_dec(&ffs->write_pages_pending);
> +		}
> +		break;
> +	}
> +
> +	if (submitted)
> +		*submitted = local_submitted;
> +	return err;
> +}
> +
>  int f2fs_write_single_data_page(struct folio *folio, int *submitted,
>  				struct bio **bio,
>  				sector_t *last_block,
> @@ -3757,6 +3982,170 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
>  	return ret;
>  }
>  
> +static int f2fs_write_cache_folios(struct address_space *mapping,
> +				   struct writeback_control *wbc,
> +				   enum iostat_type io_type)
> +{
> +	struct folio *folio = NULL;
> +	struct inode *inode = mapping->host;
> +	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
> +	struct f2fs_lock_context lc;
> +	u64 pos = 0;
> +	u64 end_pos = 0;
> +	u32 r_len = 0;
> +	int err = 0;
> +	int submitted = 0;
> +	int nwritten = 0;
> +	bool op_locked = false;
> +	bool next = false;
> +	bool retry = false;
> +
> +	if (get_dirty_pages(inode) <= SM_I(sbi)->min_hot_blocks)
> +		set_inode_flag(inode, FI_HOT_DATA);
> +	else
> +		clear_inode_flag(inode, FI_HOT_DATA);
> +
> +	while ((folio = writeback_iter(mapping, wbc, folio, &err))) {
> +		struct f2fs_folio_state *ffs = NULL;
> +		u64 isize;
> +		size_t poff;
> +		pgoff_t end_index;
> +		bool verity_in_progress;
> +		int folio_submitted = 0;
> +		bool bias_added = false;
> +
> +		submitted = 0;
> +		next = true;
> +		retry = false;
> +
> +		if (atomic_read(&sbi->wb_sync_req[DATA]) &&
> +		    wbc->sync_mode == WB_SYNC_NONE) {
> +			folio_redirty_for_writepage(wbc, folio);
> +			next = false;
> +			goto retry_out;
> +		}
> +retry:
> +		pos = folio_pos(folio);
> +		end_pos = pos + folio_size(folio);
> +		isize = i_size_read(inode);
> +		verity_in_progress = f2fs_verity_in_progress(inode);
> +		poff = 0;
> +		end_index = 0;
> +
> +		if (retry) {
> +			if (unlikely(folio->mapping != mapping))
> +				goto retry_out;
> +
> +			if (!folio_test_dirty(folio))
> +				goto retry_out;
> +
> +			if (folio_test_writeback(folio)) {
> +				if (wbc->sync_mode == WB_SYNC_NONE)
> +					goto retry_out;
> +				f2fs_folio_wait_writeback(folio, DATA, true, true);
> +			}
> +
> +			if (!folio_clear_dirty_for_io(folio))
> +				goto retry_out;
> +		}
> +
> +		/* To avoid dealing with the complexity for one subrange is in bio
> +		 * while we trylock_op failed before writing another subrange.
> +		 * Try to lock_op before any subrange write for the folio.
> +		 */
> +		if (!op_locked) {
> +			if (!f2fs_trylock_op(sbi, &lc)) {
> +				folio_redirty_for_writepage(wbc, folio);
> +				err = 0;
> +				if (wbc->sync_mode != WB_SYNC_ALL)
> +					goto retry_out;
> +
> +				retry = true;
> +				folio_unlock(folio);
> +				f2fs_io_schedule_timeout(DEFAULT_SCHEDULE_TIMEOUT);
> +				folio_lock(folio);
> +				goto retry;
> +			}
> +			op_locked = true;
> +		}
> +
> +		if (!verity_in_progress) {
> +			poff = offset_in_folio(folio, isize);
> +			end_index = isize >> PAGE_SHIFT;
> +
> +			if (folio->index > end_index ||
> +			    (folio->index == end_index && poff == 0))
> +				goto out;
> +
> +			if (end_pos > isize) {
> +				folio_zero_segment(folio, poff, folio_size(folio));
> +				end_pos = isize;
> +			}
> +		}
> +
> +		folio_start_writeback(folio);
> +
> +		if (folio_test_large(folio)) {
> +			if (!f2fs_folio_has_ffs(folio)) {

Can you explain why there is no ffs for a dirty large folio?

Thanks,

> +				ffs = f2fs_ffs_find_or_alloc(folio);
> +				f2fs_ffs_mark_subrange_dirty(folio, 0, end_pos - pos);
> +			} else {
> +				ffs = (struct f2fs_folio_state *)folio->private;
> +			}
> +			if (f2fs_folio_has_ffs(folio) && !bias_added) {
> +				WARN_ON_ONCE(atomic_read(&ffs->write_pages_pending) != 0);
> +				atomic_inc(&ffs->write_pages_pending);
> +				bias_added = true;
> +			}
> +		}
> +
> +		while ((r_len = ffs_find_dirty_range(folio, &pos, end_pos))) {
> +			err = f2fs_write_single_data_folio(folio, &submitted,
> +					wbc, io_type, pos, pos + r_len);
> +			folio_submitted += submitted;
> +			if (err)
> +				goto out;
> +
> +			nwritten += submitted;
> +			pos += r_len;
> +		}
> +
> +		if (!err && folio_submitted &&
> +		    f2fs_is_atomic_file(inode) &&
> +		    folio_test_f2fs_atomic(folio))
> +			folio_clear_f2fs_atomic(folio);
> +
> +out:
> +		f2fs_ffs_clear_subrange_dirty(folio, 0, folio_size(folio));
> +		inode_dec_dirty_pages(inode);
> +
> +		if (bias_added) {
> +			if (atomic_dec_and_test(&ffs->write_pages_pending))
> +				folio_end_writeback(folio);
> +		} else if (!folio_submitted && folio_test_writeback(folio)) {
> +			folio_end_writeback(folio);
> +		}
> +
> +retry_out:
> +		if (folio_test_locked(folio))
> +			folio_unlock(folio);
> +
> +		if (op_locked) {
> +			f2fs_unlock_op(sbi, &lc);
> +			op_locked = false;
> +		}
> +
> +		if (err || !next)
> +			break;
> +	}
> +
> +	if (nwritten)
> +		f2fs_submit_merged_write_cond(F2FS_M_SB(mapping), mapping->host,
> +					       NULL, 0, DATA);
> +
> +	return err;
> +}
> +
>  static inline bool __should_serialize_io(struct inode *inode,
>  					struct writeback_control *wbc)
>  {
> @@ -3851,7 +4240,10 @@ static int __f2fs_write_data_pages(struct address_space *mapping,
>  	account_writeback(inode, true);
>  
>  	blk_start_plug(&plug);
> -	ret = f2fs_write_cache_pages(mapping, wbc, io_type);
> +	if (mapping_large_folio_support(inode->i_mapping))
> +		ret = f2fs_write_cache_folios(mapping, wbc, io_type);
> +	else
> +		ret = f2fs_write_cache_pages(mapping, wbc, io_type);
>  	blk_finish_plug(&plug);
>  
>  	account_writeback(inode, false);