On Thu, Jul 31, 2025 at 05:21:31PM -0700, Joanne Koong wrote:
> Add granular dirty and writeback accounting for large folios. These
> stats are used by the mm layer for dirty balancing and throttling.
> Having granular dirty and writeback accounting helps prevent
> over-aggressive balancing and throttling.
>
> There are 4 places in iomap this commit affects:
> a) filemap dirtying, which now calls filemap_dirty_folio_pages()
> b) writeback_iter with setting the wbc->no_stats_accounting bit and
> calling clear_dirty_for_io_stats()
> c) starting writeback, which now calls __folio_start_writeback()
> d) ending writeback, which now calls folio_end_writeback_pages()
>
> This relies on using the ifs->state dirty bitmap to track dirty pages in
> the folio. As such, this can only be utilized on filesystems where the
> block size >= PAGE_SIZE.
Apologies for my slow responses this month. :)
I wonder, does this cause an observable change in the writeback
accounting and throttling behavior for non-fuse filesystems like XFS
that use large folios? I *think* this does actually reduce throttling
for XFS, but it might not be so noticeable because the limits are much
more generous outside of fuse?
> Signed-off-by: Joanne Koong <joannelkoong@xxxxxxxxx>
> ---
> fs/iomap/buffered-io.c | 136 ++++++++++++++++++++++++++++++++++++++---
> 1 file changed, 128 insertions(+), 8 deletions(-)
>
> diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
> index bcc6e0e5334e..626c3c8399cc 100644
> --- a/fs/iomap/buffered-io.c
> +++ b/fs/iomap/buffered-io.c
> @@ -20,6 +20,8 @@ struct iomap_folio_state {
> spinlock_t state_lock;
> unsigned int read_bytes_pending;
> atomic_t write_bytes_pending;
> + /* number of pages being currently written back */
> + unsigned nr_pages_writeback;
>
> /*
> * Each block has two bits in this bitmap:
> @@ -81,6 +83,25 @@ static inline bool ifs_block_is_dirty(struct folio *folio,
> return test_bit(block + blks_per_folio, ifs->state);
> }
>
> +static unsigned ifs_count_dirty_pages(struct folio *folio)
> +{
> + struct iomap_folio_state *ifs = folio->private;
> + struct inode *inode = folio->mapping->host;
> + unsigned block_size = 1 << inode->i_blkbits;
> + unsigned start_blk = 0;
> + unsigned end_blk = min((unsigned)(i_size_read(inode) >> inode->i_blkbits),
> + i_blocks_per_folio(inode, folio));
> + unsigned nblks = 0;
> +
> + while (start_blk < end_blk) {
> + if (ifs_block_is_dirty(folio, ifs, start_blk))
> + nblks++;
> + start_blk++;
> + }
Hmm, isn't this bitmap_weight(ifs->state, blks_per_folio) ?
Ohh wait no, the dirty bitmap doesn't start on a byte boundary because
the format of the bitmap is [uptodate bits][dirty bits].
Maybe those two should be reversed, because I bet the dirty state gets
changed a lot more over the lifetime of a folio than the uptodate bits.
> +
> + return nblks * (block_size >> PAGE_SHIFT);
> +}
> +
> static unsigned ifs_find_dirty_range(struct folio *folio,
> struct iomap_folio_state *ifs, u64 *range_start, u64 range_end)
> {
> @@ -165,6 +186,63 @@ static void iomap_set_range_dirty(struct folio *folio, size_t off, size_t len)
> ifs_set_range_dirty(folio, ifs, off, len);
> }
>
> +static long iomap_get_range_newly_dirtied(struct folio *folio, loff_t pos,
> + unsigned len)
> +{
> + struct iomap_folio_state *ifs = folio->private;
> + struct inode *inode = folio->mapping->host;
> + unsigned start_blk = pos >> inode->i_blkbits;
> + unsigned end_blk = min((unsigned)((pos + len - 1) >> inode->i_blkbits),
> + i_blocks_per_folio(inode, folio) - 1);
> + unsigned nblks = 0;
> + unsigned block_size = 1 << inode->i_blkbits;
> +
> + while (start_blk <= end_blk) {
> + if (!ifs_block_is_dirty(folio, ifs, start_blk))
> + nblks++;
> + start_blk++;
> + }
...then this becomes (endblk - startblk) - bitmap_weight().
> +
> + return nblks * (block_size >> PAGE_SHIFT);
> +}
> +
> +static bool iomap_granular_dirty_pages(struct folio *folio)
> +{
> + struct iomap_folio_state *ifs = folio->private;
> + struct inode *inode;
> + unsigned block_size;
> +
> + if (!ifs)
> + return false;
> +
> + inode = folio->mapping->host;
> + block_size = 1 << inode->i_blkbits;
> +
> + if (block_size >= PAGE_SIZE) {
> + WARN_ON(block_size & (PAGE_SIZE - 1));
> + return true;
> + }
> + return false;
> +}
> +
> +static bool iomap_dirty_folio_range(struct address_space *mapping, struct folio *folio,
> + loff_t pos, unsigned len)
> +{
> + long nr_new_dirty_pages;
> +
> + if (!iomap_granular_dirty_pages(folio)) {
> + iomap_set_range_dirty(folio, pos, len);
> + return filemap_dirty_folio(mapping, folio);
> + }
> +
> + nr_new_dirty_pages = iomap_get_range_newly_dirtied(folio, pos, len);
> + if (!nr_new_dirty_pages)
> + return false;
> +
> + iomap_set_range_dirty(folio, pos, len);
> + return filemap_dirty_folio_pages(mapping, folio, nr_new_dirty_pages);
> +}
> +
> static struct iomap_folio_state *ifs_alloc(struct inode *inode,
> struct folio *folio, unsigned int flags)
> {
> @@ -661,8 +739,7 @@ bool iomap_dirty_folio(struct address_space *mapping, struct folio *folio)
> size_t len = folio_size(folio);
>
> ifs_alloc(inode, folio, 0);
> - iomap_set_range_dirty(folio, 0, len);
> - return filemap_dirty_folio(mapping, folio);
> + return iomap_dirty_folio_range(mapping, folio, 0, len);
> }
> EXPORT_SYMBOL_GPL(iomap_dirty_folio);
>
> @@ -886,8 +963,8 @@ static bool __iomap_write_end(struct inode *inode, loff_t pos, size_t len,
> if (unlikely(copied < len && !folio_test_uptodate(folio)))
> return false;
> iomap_set_range_uptodate(folio, offset_in_folio(folio, pos), len);
> - iomap_set_range_dirty(folio, offset_in_folio(folio, pos), copied);
> - filemap_dirty_folio(inode->i_mapping, folio);
> + iomap_dirty_folio_range(inode->i_mapping, folio,
> + offset_in_folio(folio, pos), copied);
> return true;
> }
>
> @@ -1560,6 +1637,29 @@ void iomap_start_folio_write(struct inode *inode, struct folio *folio,
> }
> EXPORT_SYMBOL_GPL(iomap_start_folio_write);
>
> +static void iomap_folio_start_writeback(struct folio *folio)
> +{
> + struct iomap_folio_state *ifs = folio->private;
> +
> + if (!iomap_granular_dirty_pages(folio))
> + return folio_start_writeback(folio);
> +
> + __folio_start_writeback(folio, false, ifs->nr_pages_writeback);
> +}
> +
> +static void iomap_folio_end_writeback(struct folio *folio)
> +{
> + struct iomap_folio_state *ifs = folio->private;
> + long nr_pages_writeback;
> +
> + if (!iomap_granular_dirty_pages(folio))
> + return folio_end_writeback(folio);
> +
> + nr_pages_writeback = ifs->nr_pages_writeback;
> + ifs->nr_pages_writeback = 0;
> + folio_end_writeback_pages(folio, nr_pages_writeback);
> +}
> +
> void iomap_finish_folio_write(struct inode *inode, struct folio *folio,
> size_t len)
> {
> @@ -1569,7 +1669,7 @@ void iomap_finish_folio_write(struct inode *inode, struct folio *folio,
> WARN_ON_ONCE(ifs && atomic_read(&ifs->write_bytes_pending) <= 0);
>
> if (!ifs || atomic_sub_and_test(len, &ifs->write_bytes_pending))
> - folio_end_writeback(folio);
> + iomap_folio_end_writeback(folio);
> }
> EXPORT_SYMBOL_GPL(iomap_finish_folio_write);
>
> @@ -1657,6 +1757,21 @@ static bool iomap_writeback_handle_eof(struct folio *folio, struct inode *inode,
> return true;
> }
>
> +static void iomap_update_dirty_stats(struct folio *folio)
> +{
> + struct iomap_folio_state *ifs = folio->private;
> + long nr_dirty_pages;
> +
> + if (iomap_granular_dirty_pages(folio)) {
> + nr_dirty_pages = ifs_count_dirty_pages(folio);
> + ifs->nr_pages_writeback = nr_dirty_pages;
> + } else {
> + nr_dirty_pages = folio_nr_pages(folio);
> + }
> +
> + clear_dirty_for_io_stats(folio, nr_dirty_pages);
> +}
> +
> int iomap_writeback_folio(struct iomap_writepage_ctx *wpc, struct folio *folio)
> {
> struct iomap_folio_state *ifs = folio->private;
> @@ -1674,6 +1789,8 @@ int iomap_writeback_folio(struct iomap_writepage_ctx *wpc, struct folio *folio)
>
> trace_iomap_writeback_folio(inode, pos, folio_size(folio));
>
> + iomap_update_dirty_stats(folio);
> +
> if (!iomap_writeback_handle_eof(folio, inode, &end_pos))
> return 0;
> WARN_ON_ONCE(end_pos <= pos);
> @@ -1681,6 +1798,7 @@ int iomap_writeback_folio(struct iomap_writepage_ctx *wpc, struct folio *folio)
> if (i_blocks_per_folio(inode, folio) > 1) {
> if (!ifs) {
> ifs = ifs_alloc(inode, folio, 0);
> + ifs->nr_pages_writeback = folio_nr_pages(folio);
> iomap_set_range_dirty(folio, 0, end_pos - pos);
> }
>
> @@ -1698,7 +1816,7 @@ int iomap_writeback_folio(struct iomap_writepage_ctx *wpc, struct folio *folio)
> * Set the writeback bit ASAP, as the I/O completion for the single
> * block per folio case happen hit as soon as we're submitting the bio.
> */
> - folio_start_writeback(folio);
> + iomap_folio_start_writeback(folio);
>
> /*
> * Walk through the folio to find dirty areas to write back.
> @@ -1731,10 +1849,10 @@ int iomap_writeback_folio(struct iomap_writepage_ctx *wpc, struct folio *folio)
> */
> if (ifs) {
> if (atomic_dec_and_test(&ifs->write_bytes_pending))
> - folio_end_writeback(folio);
> + iomap_folio_end_writeback(folio);
> } else {
> if (!wb_pending)
> - folio_end_writeback(folio);
> + iomap_folio_end_writeback(folio);
> }
> mapping_set_error(inode->i_mapping, error);
> return error;
> @@ -1756,6 +1874,8 @@ iomap_writepages(struct iomap_writepage_ctx *wpc)
> PF_MEMALLOC))
> return -EIO;
>
> + wpc->wbc->no_stats_accounting = true;
> +
> while ((folio = writeback_iter(mapping, wpc->wbc, folio, &error))) {
> error = iomap_writeback_folio(wpc, folio);
> folio_unlock(folio);
> --
> 2.47.3
>
>
