Merge branch 'for-3.20/bdi' of git://git.kernel.dk/linux-block

Pull backing device changes from Jens Axboe:
 "This contains a cleanup of how the backing device is handled, in
  preparation for a rework of the life time rules.  In this part, the
  most important change is to split the unrelated nommu mmap flags from
  it, but also removing a backing_dev_info pointer from the
  address_space (and inode), and a cleanup of other various minor bits.

  Christoph did all the work here, I just fixed an oops with pages that
  have a swap backing.  Arnd fixed a missing export, and Oleg killed the
  lustre backing_dev_info from staging.  Last patch was from Al,
  unexporting parts that are now no longer needed outside"

* 'for-3.20/bdi' of git://git.kernel.dk/linux-block:
  Make super_blocks and sb_lock static
  mtd: export new mtd_mmap_capabilities
  fs: make inode_to_bdi() handle NULL inode
  staging/lustre/llite: get rid of backing_dev_info
  fs: remove default_backing_dev_info
  fs: don't reassign dirty inodes to default_backing_dev_info
  nfs: don't call bdi_unregister
  ceph: remove call to bdi_unregister
  fs: remove mapping->backing_dev_info
  fs: export inode_to_bdi and use it in favor of mapping->backing_dev_info
  nilfs2: set up s_bdi like the generic mount_bdev code
  block_dev: get bdev inode bdi directly from the block device
  block_dev: only write bdev inode on close
  fs: introduce f_op->mmap_capabilities for nommu mmap support
  fs: kill BDI_CAP_SWAP_BACKED
  fs: deduplicate noop_backing_dev_info

1 files changed, 25 insertions, 82 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 0ae0df55000b..7690ec77c722 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -14,19 +14,10 @@
 
 static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
 
-struct backing_dev_info default_backing_dev_info = {
-	.name		= "default",
-	.ra_pages	= VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE,
-	.state		= 0,
-	.capabilities	= BDI_CAP_MAP_COPY,
-};
-EXPORT_SYMBOL_GPL(default_backing_dev_info);
-
 struct backing_dev_info noop_backing_dev_info = {
 	.name		= "noop",
 	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
 };
-EXPORT_SYMBOL_GPL(noop_backing_dev_info);
 
 static struct class *bdi_class;
 
@@ -40,17 +31,6 @@ LIST_HEAD(bdi_list);
 /* bdi_wq serves all asynchronous writeback tasks */
 struct workqueue_struct *bdi_wq;
 
-static void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2)
-{
-	if (wb1 < wb2) {
-		spin_lock(&wb1->list_lock);
-		spin_lock_nested(&wb2->list_lock, 1);
-	} else {
-		spin_lock(&wb2->list_lock);
-		spin_lock_nested(&wb1->list_lock, 1);
-	}
-}
-
 #ifdef CONFIG_DEBUG_FS
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
@@ -264,9 +244,6 @@ static int __init default_bdi_init(void)
 	if (!bdi_wq)
 		return -ENOMEM;
 
-	err = bdi_init(&default_backing_dev_info);
-	if (!err)
-		bdi_register(&default_backing_dev_info, NULL, "default");
 	err = bdi_init(&noop_backing_dev_info);
 
 	return err;
@@ -355,19 +332,19 @@ EXPORT_SYMBOL(bdi_register_dev);
  */
 static void bdi_wb_shutdown(struct backing_dev_info *bdi)
 {
-	if (!bdi_cap_writeback_dirty(bdi))
+	/* Make sure nobody queues further work */
+	spin_lock_bh(&bdi->wb_lock);
+	if (!test_and_clear_bit(BDI_registered, &bdi->state)) {
+		spin_unlock_bh(&bdi->wb_lock);
 		return;
+	}
+	spin_unlock_bh(&bdi->wb_lock);
 
 	/*
 	 * Make sure nobody finds us on the bdi_list anymore
 	 */
 	bdi_remove_from_list(bdi);
 
-	/* Make sure nobody queues further work */
-	spin_lock_bh(&bdi->wb_lock);
-	clear_bit(BDI_registered, &bdi->state);
-	spin_unlock_bh(&bdi->wb_lock);
-
 	/*
 	 * Drain work list and shutdown the delayed_work.  At this point,
 	 * @bdi->bdi_list is empty telling bdi_Writeback_workfn() that @bdi
@@ -375,37 +352,22 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi)
 	 */
 	mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
 	flush_delayed_work(&bdi->wb.dwork);
-	WARN_ON(!list_empty(&bdi->work_list));
-	WARN_ON(delayed_work_pending(&bdi->wb.dwork));
 }
 
 /*
- * This bdi is going away now, make sure that no super_blocks point to it
+ * Called when the device behind @bdi has been removed or ejected.
+ *
+ * We can't really do much here except for reducing the dirty ratio at
+ * the moment.  In the future we should be able to set a flag so that
+ * the filesystem can handle errors at mark_inode_dirty time instead
+ * of only at writeback time.
  */
-static void bdi_prune_sb(struct backing_dev_info *bdi)
-{
-	struct super_block *sb;
-
-	spin_lock(&sb_lock);
-	list_for_each_entry(sb, &super_blocks, s_list) {
-		if (sb->s_bdi == bdi)
-			sb->s_bdi = &default_backing_dev_info;
-	}
-	spin_unlock(&sb_lock);
-}
-
 void bdi_unregister(struct backing_dev_info *bdi)
 {
-	if (bdi->dev) {
-		bdi_set_min_ratio(bdi, 0);
-		trace_writeback_bdi_unregister(bdi);
-		bdi_prune_sb(bdi);
+	if (WARN_ON_ONCE(!bdi->dev))
+		return;
 
-		bdi_wb_shutdown(bdi);
-		bdi_debug_unregister(bdi);
-		device_unregister(bdi->dev);
-		bdi->dev = NULL;
-	}
+	bdi_set_min_ratio(bdi, 0);
 }
 EXPORT_SYMBOL(bdi_unregister);
 
@@ -474,37 +436,19 @@ void bdi_destroy(struct backing_dev_info *bdi)
 {
 	int i;
 
-	/*
-	 * Splice our entries to the default_backing_dev_info.  This
-	 * condition shouldn't happen.  @wb must be empty at this point and
-	 * dirty inodes on it might cause other issues.  This workaround is
-	 * added by ce5f8e779519 ("writeback: splice dirty inode entries to
-	 * default bdi on bdi_destroy()") without root-causing the issue.
-	 *
-	 * http://lkml.kernel.org/g/1253038617-30204-11-git-send-email-jens.axboe@oracle.com
-	 * http://thread.gmane.org/gmane.linux.file-systems/35341/focus=35350
-	 *
-	 * We should probably add WARN_ON() to find out whether it still
-	 * happens and track it down if so.
-	 */
-	if (bdi_has_dirty_io(bdi)) {
-		struct bdi_writeback *dst = &default_backing_dev_info.wb;
-
-		bdi_lock_two(&bdi->wb, dst);
-		list_splice(&bdi->wb.b_dirty, &dst->b_dirty);
-		list_splice(&bdi->wb.b_io, &dst->b_io);
-		list_splice(&bdi->wb.b_more_io, &dst->b_more_io);
-		spin_unlock(&bdi->wb.list_lock);
-		spin_unlock(&dst->list_lock);
-	}
-
-	bdi_unregister(bdi);
+	bdi_wb_shutdown(bdi);
 
+	WARN_ON(!list_empty(&bdi->work_list));
 	WARN_ON(delayed_work_pending(&bdi->wb.dwork));
 
+	if (bdi->dev) {
+		bdi_debug_unregister(bdi);
+		device_unregister(bdi->dev);
+		bdi->dev = NULL;
+	}
+
 	for (i = 0; i < NR_BDI_STAT_ITEMS; i++)
 		percpu_counter_destroy(&bdi->bdi_stat[i]);
-
 	fprop_local_destroy_percpu(&bdi->completions);
 }
 EXPORT_SYMBOL(bdi_destroy);
@@ -513,13 +457,12 @@ EXPORT_SYMBOL(bdi_destroy);
  * For use from filesystems to quickly init and register a bdi associated
  * with dirty writeback
  */
-int bdi_setup_and_register(struct backing_dev_info *bdi, char *name,
-			   unsigned int cap)
+int bdi_setup_and_register(struct backing_dev_info *bdi, char *name)
 {
 	int err;
 
 	bdi->name = name;
-	bdi->capabilities = cap;
+	bdi->capabilities = 0;
 	err = bdi_init(bdi);
 	if (err)
 		return err;