Add new functions for triggering inode writeback

When btrfs is running low on metadata space, it needs to force delayed
allocation pages to disk.  It currently does this with a suboptimal walk
of a private list of inodes with delayed allocation, and it would be
much better if we used the generic flusher threads.

writeback_inodes_sb_if_idle would be ideal, but it waits for the flusher
thread to start IO on all the dirty pages in the FS before it returns.
This adds variants of writeback_inodes_sb* that allow the caller to
control how many pages get sent down.

Signed-off-by: Chris Mason <chris.mason@oracle.com>

1 files changed, 42 insertions, 10 deletions

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index ab38fef1c9a1..1e23c33ea5cf 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -1069,33 +1069,44 @@ static void wait_sb_inodes(struct super_block *sb)
 }
 
 /**
- * writeback_inodes_sb  -       writeback dirty inodes from given super_block
+ * writeback_inodes_sb_nr -     writeback dirty inodes from given super_block
  * @sb: the superblock
+ * @nr: the number of pages to write
  *
  * Start writeback on some inodes on this super_block. No guarantees are made
  * on how many (if any) will be written, and this function does not wait
- * for IO completion of submitted IO. The number of pages submitted is
- * returned.
+ * for IO completion of submitted IO.
  */
-void writeback_inodes_sb(struct super_block *sb)
+void writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr)
 {
-        unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY);
-        unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS);
         DECLARE_COMPLETION_ONSTACK(done);
         struct wb_writeback_work work = {
                 .sb             = sb,
                 .sync_mode      = WB_SYNC_NONE,
                 .done           = &done,
+                .nr_pages       = nr,
         };
 
         WARN_ON(!rwsem_is_locked(&sb->s_umount));
-
-        work.nr_pages = nr_dirty + nr_unstable +
-                        (inodes_stat.nr_inodes - inodes_stat.nr_unused);
-
         bdi_queue_work(sb->s_bdi, &work);
         wait_for_completion(&done);
 }
+EXPORT_SYMBOL(writeback_inodes_sb_nr);
+
+/**
+ * writeback_inodes_sb  -       writeback dirty inodes from given super_block
+ * @sb: the superblock
+ *
+ * Start writeback on some inodes on this super_block. No guarantees are made
+ * on how many (if any) will be written, and this function does not wait
+ * for IO completion of submitted IO.
+ */
+void writeback_inodes_sb(struct super_block *sb)
+{
+        return writeback_inodes_sb_nr(sb, global_page_state(NR_FILE_DIRTY) +
+                              global_page_state(NR_UNSTABLE_NFS) +
+                              (inodes_stat.nr_inodes - inodes_stat.nr_unused));
+}
 EXPORT_SYMBOL(writeback_inodes_sb);
 
 /**
@@ -1118,6 +1129,27 @@ int writeback_inodes_sb_if_idle(struct super_block *sb)
 EXPORT_SYMBOL(writeback_inodes_sb_if_idle);
 
 /**
+ * writeback_inodes_sb_if_idle  -       start writeback if none underway
+ * @sb: the superblock
+ * @nr: the number of pages to write
+ *
+ * Invoke writeback_inodes_sb if no writeback is currently underway.
+ * Returns 1 if writeback was started, 0 if not.
+ */
+int writeback_inodes_sb_nr_if_idle(struct super_block *sb,
+                                   unsigned long nr)
+{
+        if (!writeback_in_progress(sb->s_bdi)) {
+                down_read(&sb->s_umount);
+                writeback_inodes_sb_nr(sb, nr);
+                up_read(&sb->s_umount);
+                return 1;
+        } else
+                return 0;
+}
+EXPORT_SYMBOL(writeback_inodes_sb_nr_if_idle);
+
+/**
  * sync_inodes_sb       -       sync sb inode pages
  * @sb: the superblock
  *