Merge patch series "mm: improve write performance with RWF_DONTCACHE"

Jeff Layton <jlayton@kernel.org> says:

This patch series is intended to improve write performance with
RWF_DONTCACHE. This version fixes additional stat accounting issues
found during review: integer promotion on 32-bit, cgroup writeback
domain migration, folio split flag preservation, and a UAF that could
occur in filemap_dontcache_kick_writeback().

* patches from https://patch.msgid.link/20260511-dontcache-v7-0-2848ddce8090@kernel.org:
  mm: kick writeback flusher for IOCB_DONTCACHE with targeted dirty tracking
  mm: track DONTCACHE dirty pages per bdi_writeback
  mm: preserve PG_dropbehind flag during folio split

Link: https://patch.msgid.link/20260511-dontcache-v7-0-2848ddce8090@kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>

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);
+			}
 		}
 	}
 
@@ -2392,6 +2396,27 @@ static long wb_check_start_all(struct bdi_writeback *wb)
 	return nr_pages;
 }
 
+static long wb_check_start_dontcache(struct bdi_writeback *wb)
+{
+	long nr_pages;
+
+	if (!test_and_clear_bit(WB_start_dontcache, &wb->state))
+		return 0;
+
+	nr_pages = wb_stat_sum(wb, WB_DONTCACHE_DIRTY);
+	if (nr_pages) {
+		struct wb_writeback_work work = {
+			.nr_pages	= nr_pages,
+			.sync_mode	= WB_SYNC_NONE,
+			.range_cyclic	= 1,
+			.reason		= WB_REASON_DONTCACHE,
+		};
+
+		nr_pages = wb_writeback(wb, &work);
+	}
+
+	return nr_pages;
+}
 
 /*
  * Retrieve work items and do the writeback they describe
@@ -2413,6 +2438,11 @@ static long wb_do_writeback(struct bdi_writeback *wb)
 	 */
 	wrote += wb_check_start_all(wb);
 
+	/*
+	 * Check for dontcache writeback request
+	 */
+	wrote += wb_check_start_dontcache(wb);
+
 	/*
 	 * Check for periodic writeback, kupdated() style
 	 */
@@ -2487,6 +2517,43 @@ void wakeup_flusher_threads_bdi(struct backing_dev_info *bdi,
 	rcu_read_unlock();
 }
 
+/**
+ * filemap_dontcache_kick_writeback - kick flusher for IOCB_DONTCACHE writes
+ * @mapping:	address_space that was just written to
+ *
+ * Kick the writeback flusher thread to expedite writeback of dontcache dirty
+ * pages. Queue writeback for the inode's wb for as many pages as there are
+ * dontcache pages, but don't restrict writeback to dontcache pages only.
+ *
+ * This significantly improves performance over either writing all wb's pages
+ * or writing only dontcache pages.  Although it doesn't guarantee quick
+ * writeback and reclaim of dontcache pages, it keeps the amount of dirty pages
+ * in check. Over longer term dontcache pages get written and reclaimed by
+ * background writeback even with this rough heuristic.
+ */
+void filemap_dontcache_kick_writeback(struct address_space *mapping)
+{
+	struct inode *inode = mapping->host;
+	struct bdi_writeback *wb;
+	struct wb_lock_cookie cookie = {};
+	bool need_wakeup = false;
+
+	wb = unlocked_inode_to_wb_begin(inode, &cookie);
+	if (wb_has_dirty_io(wb) &&
+	    !test_bit(WB_start_dontcache, &wb->state) &&
+	    !test_and_set_bit(WB_start_dontcache, &wb->state)) {
+		wb_get(wb);
+		need_wakeup = true;
+	}
+	unlocked_inode_to_wb_end(inode, &cookie);
+
+	if (need_wakeup) {
+		wb_wakeup(wb);
+		wb_put(wb);
+	}
+}
+EXPORT_SYMBOL_GPL(filemap_dontcache_kick_writeback);
+
 /*
  * Wakeup the flusher threads to start writeback of all currently dirty pages
  */

include/linux/backing-dev-defs.h

@@ -26,6 +26,7 @@ enum wb_state {
 	WB_writeback_running,	/* Writeback is in progress */
 	WB_has_dirty_io,	/* Dirty inodes on ->b_{dirty|io|more_io} */
 	WB_start_all,		/* nr_pages == 0 (all) work pending */
+	WB_start_dontcache,	/* dontcache writeback pending */
 };
 
 enum wb_stat_item {
@@ -33,6 +34,7 @@ enum wb_stat_item {
 	WB_WRITEBACK,
 	WB_DIRTIED,
 	WB_WRITTEN,
+	WB_DONTCACHE_DIRTY,
 	NR_WB_STAT_ITEMS
 };
 
@@ -55,6 +57,7 @@ enum wb_reason {
 	 */
 	WB_REASON_FORKER_THREAD,
 	WB_REASON_FOREIGN_FLUSH,
+	WB_REASON_DONTCACHE,
 
 	WB_REASON_MAX,
 };

include/linux/fs.h

@@ -2624,6 +2624,7 @@ extern int __must_check file_write_and_wait_range(struct file *file,
 						loff_t start, loff_t end);
 int filemap_flush_range(struct address_space *mapping, loff_t start,
 		loff_t end);
+void filemap_dontcache_kick_writeback(struct address_space *mapping);
 
 static inline int file_write_and_wait(struct file *file)
 {
@@ -2657,10 +2658,7 @@ static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count)
 		if (ret)
 			return ret;
 	} else if (iocb->ki_flags & IOCB_DONTCACHE) {
-		struct address_space *mapping = iocb->ki_filp->f_mapping;
-
-		filemap_flush_range(mapping, iocb->ki_pos - count,
-				iocb->ki_pos - 1);
+		filemap_dontcache_kick_writeback(iocb->ki_filp->f_mapping);
 	}
 
 	return count;

include/trace/events/writeback.h

@@ -44,7 +44,8 @@
 	EM( WB_REASON_PERIODIC,			"periodic")		\
 	EM( WB_REASON_FS_FREE_SPACE,		"fs_free_space")	\
 	EM( WB_REASON_FORKER_THREAD,		"forker_thread")	\
-	EMe(WB_REASON_FOREIGN_FLUSH,		"foreign_flush")
+	EM( WB_REASON_FOREIGN_FLUSH,		"foreign_flush")	\
+	EMe(WB_REASON_DONTCACHE,		"dontcache")
 
 WB_WORK_REASON
 

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);

mm/huge_memory.c

@@ -3642,6 +3642,7 @@ static void __split_folio_to_order(struct folio *folio, int old_order,
 				 (1L << PG_arch_3) |
 #endif
 				 (1L << PG_dirty) |
+				 (1L << PG_dropbehind) |
 				 LRU_GEN_MASK | LRU_REFS_MASK));
 
 		if (handle_hwpoison &&

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;