Merge tag 'for-5.16/inode-sync-2021-10-29' of git://git.kernel.dk/linux-block

Pull block inode sync updates from Jens Axboe:
"This contains improvements to how bdev inode syncing is handled,
unifying the API"

* tag 'for-5.16/inode-sync-2021-10-29' of git://git.kernel.dk/linux-block:
block: simplify the block device syncing code
ntfs3: use sync_blockdev_nowait
fat: use sync_blockdev_nowait
btrfs: use sync_blockdev
xen-blkback: use sync_blockdev
block: remove __sync_blockdev
fs: remove __sync_filesystem

block/bdev.c

···
 
 EXPORT_SYMBOL(sb_min_blocksize);
 
-int __sync_blockdev(struct block_device *bdev, int wait)
+int sync_blockdev_nowait(struct block_device *bdev)
 {
 	if (!bdev)
 		return 0;
-	if (!wait)
-		return filemap_flush(bdev->bd_inode->i_mapping);
-	return filemap_write_and_wait(bdev->bd_inode->i_mapping);
+	return filemap_flush(bdev->bd_inode->i_mapping);
 }
+EXPORT_SYMBOL_GPL(sync_blockdev_nowait);
 
 /*
  * Write out and wait upon all the dirty data associated with a block
···
  */
 int sync_blockdev(struct block_device *bdev)
 {
-	return __sync_blockdev(bdev, 1);
+	if (!bdev)
+		return 0;
+	return filemap_write_and_wait(bdev->bd_inode->i_mapping);
 }
 EXPORT_SYMBOL(sync_blockdev);
 
···
 }
 EXPORT_SYMBOL(__invalidate_device);
 
-void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg)
+void sync_bdevs(bool wait)
 {
 	struct inode *inode, *old_inode = NULL;
 
···
 		bdev = I_BDEV(inode);
 
 		mutex_lock(&bdev->bd_disk->open_mutex);
-		if (bdev->bd_openers)
-			func(bdev, arg);
+		if (!bdev->bd_openers) {
+			; /* skip */
+		} else if (wait) {
+			/*
+			 * We keep the error status of individual mapping so
+			 * that applications can catch the writeback error using
+			 * fsync(2). See filemap_fdatawait_keep_errors() for
+			 * details.
+			 */
+			filemap_fdatawait_keep_errors(inode->i_mapping);
+		} else {
+			filemap_fdatawrite(inode->i_mapping);
+		}
 		mutex_unlock(&bdev->bd_disk->open_mutex);
 
 		spin_lock(&blockdev_superblock->s_inode_list_lock);

drivers/block/xen-blkback/xenbus.c

···
 		return;
 	}
 
-	err = filemap_write_and_wait(blkif->vbd.bdev->bd_inode->i_mapping);
+	err = sync_blockdev(blkif->vbd.bdev);
 	if (err) {
 		xenbus_dev_error(blkif->be->dev, err, "block flush");
 		return;

fs/btrfs/volumes.c

···
 	}
 
 	if (flush)
-		filemap_write_and_wait((*bdev)->bd_inode->i_mapping);
+		sync_blockdev(*bdev);
 	ret = set_blocksize(*bdev, BTRFS_BDEV_BLOCKSIZE);
 	if (ret) {
 		blkdev_put(*bdev, flags);

fs/fat/inode.c

···
 		ret = writeback_inode(i1);
 	if (!ret && i2)
 		ret = writeback_inode(i2);
-	if (!ret) {
-		struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping;
-		ret = filemap_flush(mapping);
-	}
+	if (!ret)
+		ret = sync_blockdev_nowait(sb->s_bdev);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(fat_flush_inodes);

fs/internal.h

···
 #ifdef CONFIG_BLOCK
 extern void __init bdev_cache_init(void);
 
-extern int __sync_blockdev(struct block_device *bdev, int wait);
-void iterate_bdevs(void (*)(struct block_device *, void *), void *);
 void emergency_thaw_bdev(struct super_block *sb);
 #else
 static inline void bdev_cache_init(void)
-{
-}
-
-static inline int __sync_blockdev(struct block_device *bdev, int wait)
-{
-	return 0;
-}
-static inline void iterate_bdevs(void (*f)(struct block_device *, void *),
-		void *arg)
 {
 }
 static inline int emergency_thaw_bdev(struct super_block *sb)

fs/ntfs3/inode.c

···
 	if (!ret && i2)
 		ret = writeback_inode(i2);
 	if (!ret)
-		ret = filemap_flush(sb->s_bdev->bd_inode->i_mapping);
+		ret = sync_blockdev_nowait(sb->s_bdev);
 	return ret;
 }
 

fs/sync.c

···
  * High-level sync()-related operations
  */
 
+#include <linux/blkdev.h>
 #include <linux/kernel.h>
 #include <linux/file.h>
 #include <linux/fs.h>
···
 
 #define VALID_FLAGS (SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE| \
 			SYNC_FILE_RANGE_WAIT_AFTER)
-
-/*
- * Do the filesystem syncing work. For simple filesystems
- * writeback_inodes_sb(sb) just dirties buffers with inodes so we have to
- * submit IO for these buffers via __sync_blockdev(). This also speeds up the
- * wait == 1 case since in that case write_inode() functions do
- * sync_dirty_buffer() and thus effectively write one block at a time.
- */
-static int __sync_filesystem(struct super_block *sb, int wait)
-{
-	if (wait)
-		sync_inodes_sb(sb);
-	else
-		writeback_inodes_sb(sb, WB_REASON_SYNC);
-
-	if (sb->s_op->sync_fs)
-		sb->s_op->sync_fs(sb, wait);
-	return __sync_blockdev(sb->s_bdev, wait);
-}
 
 /*
  * Write out and wait upon all dirty data associated with this
···
 	if (sb_rdonly(sb))
 		return 0;
 
-	ret = __sync_filesystem(sb, 0);
+	/*
+	 * Do the filesystem syncing work.  For simple filesystems
+	 * writeback_inodes_sb(sb) just dirties buffers with inodes so we have
+	 * to submit I/O for these buffers via sync_blockdev().  This also
+	 * speeds up the wait == 1 case since in that case write_inode()
+	 * methods call sync_dirty_buffer() and thus effectively write one block
+	 * at a time.
+	 */
+	writeback_inodes_sb(sb, WB_REASON_SYNC);
+	if (sb->s_op->sync_fs)
+		sb->s_op->sync_fs(sb, 0);
+	ret = sync_blockdev_nowait(sb->s_bdev);
 	if (ret < 0)
 		return ret;
-	return __sync_filesystem(sb, 1);
+
+	sync_inodes_sb(sb);
+	if (sb->s_op->sync_fs)
+		sb->s_op->sync_fs(sb, 1);
+	return sync_blockdev(sb->s_bdev);
 }
 EXPORT_SYMBOL(sync_filesystem);
 
···
 	if (!sb_rdonly(sb) && !(sb->s_iflags & SB_I_SKIP_SYNC) &&
 	    sb->s_op->sync_fs)
 		sb->s_op->sync_fs(sb, *(int *)arg);
-}
-
-static void fdatawrite_one_bdev(struct block_device *bdev, void *arg)
-{
-	filemap_fdatawrite(bdev->bd_inode->i_mapping);
-}
-
-static void fdatawait_one_bdev(struct block_device *bdev, void *arg)
-{
-	/*
-	 * We keep the error status of individual mapping so that
-	 * applications can catch the writeback error using fsync(2).
-	 * See filemap_fdatawait_keep_errors() for details.
-	 */
-	filemap_fdatawait_keep_errors(bdev->bd_inode->i_mapping);
 }
 
 /*
···
 	iterate_supers(sync_inodes_one_sb, NULL);
 	iterate_supers(sync_fs_one_sb, &nowait);
 	iterate_supers(sync_fs_one_sb, &wait);
-	iterate_bdevs(fdatawrite_one_bdev, NULL);
-	iterate_bdevs(fdatawait_one_bdev, NULL);
+	sync_bdevs(false);
+	sync_bdevs(true);
 	if (unlikely(laptop_mode))
 		laptop_sync_completion();
 }
···
 	 */
 	iterate_supers(sync_inodes_one_sb, &nowait);
 	iterate_supers(sync_fs_one_sb, &nowait);
-	iterate_bdevs(fdatawrite_one_bdev, NULL);
+	sync_bdevs(false);
 	iterate_supers(sync_inodes_one_sb, &nowait);
 	iterate_supers(sync_fs_one_sb, &nowait);
-	iterate_bdevs(fdatawrite_one_bdev, NULL);
+	sync_bdevs(false);
 	printk("Emergency Sync complete\n");
 	kfree(work);
 }

include/linux/blkdev.h

···
 #ifdef CONFIG_BLOCK
 void invalidate_bdev(struct block_device *bdev);
 int sync_blockdev(struct block_device *bdev);
+int sync_blockdev_nowait(struct block_device *bdev);
+void sync_bdevs(bool wait);
 #else
 static inline void invalidate_bdev(struct block_device *bdev)
 {
···
 static inline int sync_blockdev(struct block_device *bdev)
 {
 	return 0;
+}
+static inline int sync_blockdev_nowait(struct block_device *bdev)
+{
+	return 0;
+}
+static inline void sync_bdevs(bool wait)
+{
 }
 #endif
 int fsync_bdev(struct block_device *bdev);