mm: track DONTCACHE dirty pages per bdi_writeback

Add a per-wb WB_DONTCACHE_DIRTY counter that tracks the number of dirty
pages with the dropbehind flag set (i.e., pages dirtied via RWF_DONTCACHE
writes).

Increment the counter alongside WB_RECLAIMABLE in folio_account_dirtied()
when the folio has the dropbehind flag set, and decrement it in
folio_clear_dirty_for_io() and folio_account_cleaned(). Also decrement it
when a non-DONTCACHE lookup atomically clears the dropbehind flag on a
dirty folio in __filemap_get_folio_mpol(), using folio_test_clear_dropbehind()
to prevent concurrent lookups from double-decrementing the counter, and
guarding the decrement with mapping_can_writeback() to match the increment
path.

Transfer the counter alongside WB_RECLAIMABLE in inode_do_switch_wbs() so
that the stat is properly migrated when an inode switches cgroup writeback
domains.

The counter will be used by the writeback flusher to determine how many
pages to write back when expediting writeback for IOCB_DONTCACHE writes,
without flushing the entire BDI's dirty pages.

Suggested-by: Jan Kara <jack@suse.cz>
Assisted-by: Claude:claude-opus-4-6
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Link: https://patch.msgid.link/20260511-dontcache-v7-2-2848ddce8090@kernel.org
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Signed-off-by: Christian Brauner (Amutable) <brauner@kernel.org>

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 900ad7818bd4178dbd7f7313bbae3bdb035284f2..b303516f27535bcda5b12f9253654b5df1633279 100644 (file)
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -432,6 +432,10 @@ static bool inode_do_switch_wbs(struct inode *inode,
                        long nr = folio_nr_pages(folio);
                        wb_stat_mod(old_wb, WB_RECLAIMABLE, -nr);
                        wb_stat_mod(new_wb, WB_RECLAIMABLE, nr);
+                       if (folio_test_dropbehind(folio)) {
+                               wb_stat_mod(old_wb, WB_DONTCACHE_DIRTY, -nr);
+                               wb_stat_mod(new_wb, WB_DONTCACHE_DIRTY, nr);
+                       }
                }
        }
 

diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index a06b93446d101a4e1457bf5272a5f1e0ef19720c..cb660dd372866b9dffb8cfa66ee03d890076bb6a 100644 (file)
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -33,6 +33,7 @@ enum wb_stat_item {
        WB_WRITEBACK,
        WB_DIRTIED,
        WB_WRITTEN,
+       WB_DONTCACHE_DIRTY,
        NR_WB_STAT_ITEMS
 };
 

diff --git a/mm/filemap.c b/mm/filemap.c
index 4e636647100c1dddab3b319a1946510089105dbe..179f2886f8c0e8d592d104f32dcfd18800df1164 100644 (file)
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2052,8 +2052,19 @@ no_page:
        if (!folio)
                return ERR_PTR(-ENOENT);
        /* not an uncached lookup, clear uncached if set */
-       if (folio_test_dropbehind(folio) && !(fgp_flags & FGP_DONTCACHE))
-               folio_clear_dropbehind(folio);
+       if (!(fgp_flags & FGP_DONTCACHE) && folio_test_clear_dropbehind(folio)) {
+               if (folio_test_dirty(folio) &&
+                   mapping_can_writeback(mapping)) {
+                       struct inode *inode = mapping->host;
+                       struct bdi_writeback *wb;
+                       struct wb_lock_cookie cookie = {};
+                       long nr = folio_nr_pages(folio);
+
+                       wb = unlocked_inode_to_wb_begin(inode, &cookie);
+                       wb_stat_mod(wb, WB_DONTCACHE_DIRTY, -nr);
+                       unlocked_inode_to_wb_end(inode, &cookie);
+               }
+       }
        return folio;
 }
 EXPORT_SYMBOL(__filemap_get_folio_mpol);

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 88cd53d4ba0929e3d4e74d7d72d36b3ceca51189..8e520717d1f6a6a6da405ccab38a3451182d3913 100644 (file)
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2630,6 +2630,8 @@ static void folio_account_dirtied(struct folio *folio,
                wb = inode_to_wb(inode);
 
                lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, nr);
+               if (folio_test_dropbehind(folio))
+                       wb_stat_mod(wb, WB_DONTCACHE_DIRTY, nr);
                __zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr);
                __node_stat_mod_folio(folio, NR_DIRTIED, nr);
                wb_stat_mod(wb, WB_RECLAIMABLE, nr);
@@ -2651,6 +2653,8 @@ void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb)
        long nr = folio_nr_pages(folio);
 
        lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, -nr);
+       if (folio_test_dropbehind(folio))
+               wb_stat_mod(wb, WB_DONTCACHE_DIRTY, -nr);
        zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr);
        wb_stat_mod(wb, WB_RECLAIMABLE, -nr);
        task_io_account_cancelled_write(nr * PAGE_SIZE);
@@ -2920,6 +2924,8 @@ bool folio_clear_dirty_for_io(struct folio *folio)
                if (folio_test_clear_dirty(folio)) {
                        long nr = folio_nr_pages(folio);
                        lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, -nr);
+                       if (folio_test_dropbehind(folio))
+                               wb_stat_mod(wb, WB_DONTCACHE_DIRTY, -nr);
                        zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr);
                        wb_stat_mod(wb, WB_RECLAIMABLE, -nr);
                        ret = true;