Merge tag 'vfs-6.19-rc1.writeback' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull writeback updates from Christian Brauner:
 "Features:

   - Allow file systems to increase the minimum writeback chunk size.

     The relatively low minimal writeback size of 4MiB means that
     written back inodes on rotational media are switched a lot. Besides
     introducing additional seeks, this also can lead to extreme file
     fragmentation on zoned devices when a lot of files are cached
     relative to the available writeback bandwidth.

     This adds a superblock field that allows the file system to
     override the default size, and sets it to the zone size for zoned
     XFS.

   - Add logging for slow writeback when it exceeds
     sysctl_hung_task_timeout_secs. This helps identify tasks waiting
     for a long time and pinpoint potential issues. Recording the
     starting jiffies is also useful when debugging a crashed vmcore.

   - Wake up waiting tasks when finishing the writeback of a chunk

  Cleanups:

   - filemap_* writeback interface cleanups.

     Adding filemap_fdatawrite_wbc ended up being a mistake, as all but
     the original btrfs caller should be using better high level
     interfaces instead.

     This series removes all these low-level interfaces, switches btrfs
     to a more specific interface, and cleans up other too low-level
     interfaces. With this the writeback_control that is passed to the
     writeback code is only initialized in three places.

   - Remove __filemap_fdatawrite, __filemap_fdatawrite_range, and
     filemap_fdatawrite_wbc

   - Add filemap_flush_nr helper for btrfs

   - Push struct writeback_control into start_delalloc_inodes in btrfs

   - Rename filemap_fdatawrite_range_kick to filemap_flush_range

   - Stop opencoding filemap_fdatawrite_range in 9p, ocfs2, and mm

   - Make wbc_to_tag() inline and use it in fs"

* tag 'vfs-6.19-rc1.writeback' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  fs: Make wbc_to_tag() inline and use it in fs.
  xfs: set s_min_writeback_pages for zoned file systems
  writeback: allow the file system to override MIN_WRITEBACK_PAGES
  writeback: cleanup writeback_chunk_size
  mm: rename filemap_fdatawrite_range_kick to filemap_flush_range
  mm: remove __filemap_fdatawrite_range
  mm: remove filemap_fdatawrite_wbc
  mm: remove __filemap_fdatawrite
  mm,btrfs: add a filemap_flush_nr helper
  btrfs: push struct writeback_control into start_delalloc_inodes
  btrfs: use the local tmp_inode variable in start_delalloc_inodes
  ocfs2: don't opencode filemap_fdatawrite_range in ocfs2_journal_submit_inode_data_buffers
  9p: don't opencode filemap_fdatawrite_range in v9fs_mmap_vm_close
  mm: don't opencode filemap_fdatawrite_range in filemap_invalidate_inode
  writeback: Add logging for slow writeback (exceeds sysctl_hung_task_timeout_secs)
  writeback: Wake up waiting tasks when finishing the writeback of a chunk.

1 files changed, 34 insertions, 21 deletions

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 917a450c503b..6800886c4d10 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -14,6 +14,7 @@
  *		Additions for address_space-based writeback
  */
 
+#include <linux/sched/sysctl.h>
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/spinlock.h>
@@ -32,11 +33,6 @@
 #include "internal.h"
 
 /*
- * 4MB minimal write chunk size
- */
-#define MIN_WRITEBACK_PAGES	(4096UL >> (PAGE_SHIFT - 10))
-
-/*
  * Passed into wb_writeback(), essentially a subset of writeback_control
  */
 struct wb_writeback_work {
@@ -200,6 +196,19 @@ static void wb_queue_work(struct bdi_writeback *wb,
 	spin_unlock_irq(&wb->work_lock);
 }
 
+static bool wb_wait_for_completion_cb(struct wb_completion *done)
+{
+	unsigned long waited_secs = (jiffies - done->wait_start) / HZ;
+
+	done->progress_stamp = jiffies;
+	if (waited_secs > sysctl_hung_task_timeout_secs)
+		pr_info("INFO: The task %s:%d has been waiting for writeback "
+			"completion for more than %lu seconds.",
+			current->comm, current->pid, waited_secs);
+
+	return !atomic_read(&done->cnt);
+}
+
 /**
  * wb_wait_for_completion - wait for completion of bdi_writeback_works
  * @done: target wb_completion
@@ -212,8 +221,9 @@ static void wb_queue_work(struct bdi_writeback *wb,
  */
 void wb_wait_for_completion(struct wb_completion *done)
 {
+	done->wait_start = jiffies;
 	atomic_dec(&done->cnt);		/* put down the initial count */
-	wait_event(*done->waitq, !atomic_read(&done->cnt));
+	wait_event(*done->waitq, wb_wait_for_completion_cb(done));
 }
 
 #ifdef CONFIG_CGROUP_WRITEBACK
@@ -808,9 +818,9 @@ static void wbc_attach_and_unlock_inode(struct writeback_control *wbc,
  * @wbc: writeback_control of interest
  * @inode: target inode
  *
- * This function is to be used by __filemap_fdatawrite_range(), which is an
- * alternative entry point into writeback code, and first ensures @inode is
- * associated with a bdi_writeback and attaches it to @wbc.
+ * This function is to be used by filemap_writeback(), which is an alternative
+ * entry point into writeback code, and first ensures @inode is associated with
+ * a bdi_writeback and attaches it to @wbc.
  */
 void wbc_attach_fdatawrite_inode(struct writeback_control *wbc,
 		struct inode *inode)
@@ -1882,8 +1892,8 @@ out:
 	return ret;
 }
 
-static long writeback_chunk_size(struct bdi_writeback *wb,
-				 struct wb_writeback_work *work)
+static long writeback_chunk_size(struct super_block *sb,
+		struct bdi_writeback *wb, struct wb_writeback_work *work)
 {
 	long pages;
 
@@ -1901,16 +1911,13 @@ static long writeback_chunk_size(struct bdi_writeback *wb,
 	 *                   (maybe slowly) sync all tagged pages
 	 */
 	if (work->sync_mode == WB_SYNC_ALL || work->tagged_writepages)
-		pages = LONG_MAX;
-	else {
-		pages = min(wb->avg_write_bandwidth / 2,
-			    global_wb_domain.dirty_limit / DIRTY_SCOPE);
-		pages = min(pages, work->nr_pages);
-		pages = round_down(pages + MIN_WRITEBACK_PAGES,
-				   MIN_WRITEBACK_PAGES);
-	}
+		return LONG_MAX;
 
-	return pages;
+	pages = min(wb->avg_write_bandwidth / 2,
+		    global_wb_domain.dirty_limit / DIRTY_SCOPE);
+	pages = min(pages, work->nr_pages);
+	return round_down(pages + sb->s_min_writeback_pages,
+			sb->s_min_writeback_pages);
 }
 
 /*
@@ -2012,7 +2019,7 @@ static long writeback_sb_inodes(struct super_block *sb,
 		inode_state_set(inode, I_SYNC);
 		wbc_attach_and_unlock_inode(&wbc, inode);
 
-		write_chunk = writeback_chunk_size(wb, work);
+		write_chunk = writeback_chunk_size(inode->i_sb, wb, work);
 		wbc.nr_to_write = write_chunk;
 		wbc.pages_skipped = 0;
 
@@ -2022,6 +2029,12 @@ static long writeback_sb_inodes(struct super_block *sb,
 		 */
 		__writeback_single_inode(inode, &wbc);
 
+		/* Report progress to inform the hung task detector of the progress. */
+		if (work->done && work->done->progress_stamp &&
+		   (jiffies - work->done->progress_stamp) > HZ *
+		   sysctl_hung_task_timeout_secs / 2)
+			wake_up_all(work->done->waitq);
+
 		wbc_detach_inode(&wbc);
 		work->nr_pages -= write_chunk - wbc.nr_to_write;
 		wrote = write_chunk - wbc.nr_to_write - wbc.pages_skipped;