Merge tag 'for-f2fs-4.1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "New features:
   - in-memory extent_cache
   - fs_shutdown to test power-off-recovery
   - use inline_data to store symlink path
   - show f2fs as a non-misc filesystem

  Major fixes:
   - avoid CPU stalls on sync_dirty_dir_inodes
   - fix some power-off-recovery procedure
   - fix handling of broken symlink correctly
   - fix missing dot and dotdot made by sudden power cuts
   - handle wrong data index during roll-forward recovery
   - preallocate data blocks for direct_io

  ... and a bunch of minor bug fixes and cleanups"

* tag 'for-f2fs-4.1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (71 commits)
  f2fs: pass checkpoint reason on roll-forward recovery
  f2fs: avoid abnormal behavior on broken symlink
  f2fs: flush symlink path to avoid broken symlink after POR
  f2fs: change 0 to false for bool type
  f2fs: do not recover wrong data index
  f2fs: do not increase link count during recovery
  f2fs: assign parent's i_mode for empty dir
  f2fs: add F2FS_INLINE_DOTS to recover missing dot dentries
  f2fs: fix mismatching lock and unlock pages for roll-forward recovery
  f2fs: fix sparse warnings
  f2fs: limit b_size of mapped bh in f2fs_map_bh
  f2fs: persist system.advise into on-disk inode
  f2fs: avoid NULL pointer dereference in f2fs_xattr_advise_get
  f2fs: preallocate fallocated blocks for direct IO
  f2fs: enable inline data by default
  f2fs: preserve extent info for extent cache
  f2fs: initialize extent tree with on-disk extent info of inode
  f2fs: introduce __{find,grab}_extent_tree
  f2fs: split set_data_blkaddr from f2fs_update_extent_cache
  f2fs: enable fast symlink by utilizing inline data
  ...

1 files changed, 58 insertions, 6 deletions

diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index df6a0596eccf..a6f3f6186588 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -241,6 +241,8 @@ go_write:
 		 * will be used only for fsynced inodes after checkpoint.
 		 */
 		try_to_fix_pino(inode);
+		clear_inode_flag(fi, FI_APPEND_WRITE);
+		clear_inode_flag(fi, FI_UPDATE_WRITE);
 		goto out;
 	}
 sync_nodes:
@@ -433,8 +435,12 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
 			continue;
 
 		dn->data_blkaddr = NULL_ADDR;
-		update_extent_cache(dn);
+		set_data_blkaddr(dn);
+		f2fs_update_extent_cache(dn);
 		invalidate_blocks(sbi, blkaddr);
+		if (dn->ofs_in_node == 0 && IS_INODE(dn->node_page))
+			clear_inode_flag(F2FS_I(dn->inode),
+						FI_FIRST_BLOCK_WRITTEN);
 		nr_free++;
 	}
 	if (nr_free) {
@@ -454,15 +460,16 @@ void truncate_data_blocks(struct dnode_of_data *dn)
 	truncate_data_blocks_range(dn, ADDRS_PER_BLOCK);
 }
 
-static int truncate_partial_data_page(struct inode *inode, u64 from)
+static int truncate_partial_data_page(struct inode *inode, u64 from,
+								bool force)
 {
 	unsigned offset = from & (PAGE_CACHE_SIZE - 1);
 	struct page *page;
 
-	if (!offset)
+	if (!offset && !force)
 		return 0;
 
-	page = find_data_page(inode, from >> PAGE_CACHE_SHIFT, false);
+	page = find_data_page(inode, from >> PAGE_CACHE_SHIFT, force);
 	if (IS_ERR(page))
 		return 0;
 
@@ -473,7 +480,8 @@ static int truncate_partial_data_page(struct inode *inode, u64 from)
 
 	f2fs_wait_on_page_writeback(page, DATA);
 	zero_user(page, offset, PAGE_CACHE_SIZE - offset);
-	set_page_dirty(page);
+	if (!force)
+		set_page_dirty(page);
 out:
 	f2fs_put_page(page, 1);
 	return 0;
@@ -487,6 +495,7 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock)
 	pgoff_t free_from;
 	int count = 0, err = 0;
 	struct page *ipage;
+	bool truncate_page = false;
 
 	trace_f2fs_truncate_blocks_enter(inode, from);
 
@@ -502,7 +511,10 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock)
 	}
 
 	if (f2fs_has_inline_data(inode)) {
+		if (truncate_inline_inode(ipage, from))
+			set_page_dirty(ipage);
 		f2fs_put_page(ipage, 1);
+		truncate_page = true;
 		goto out;
 	}
 
@@ -533,7 +545,7 @@ out:
 
 	/* lastly zero out the first data page */
 	if (!err)
-		err = truncate_partial_data_page(inode, from);
+		err = truncate_partial_data_page(inode, from, truncate_page);
 
 	trace_f2fs_truncate_blocks_exit(inode, err);
 	return err;
@@ -997,6 +1009,9 @@ static int f2fs_ioc_release_volatile_write(struct file *filp)
 	if (!f2fs_is_volatile_file(inode))
 		return 0;
 
+	if (!f2fs_is_first_block_written(inode))
+		return truncate_partial_data_page(inode, 0, true);
+
 	punch_hole(inode, 0, F2FS_BLKSIZE);
 	return 0;
 }
@@ -1029,6 +1044,41 @@ static int f2fs_ioc_abort_volatile_write(struct file *filp)
 	return ret;
 }
 
+static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
+{
+	struct inode *inode = file_inode(filp);
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct super_block *sb = sbi->sb;
+	__u32 in;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (get_user(in, (__u32 __user *)arg))
+		return -EFAULT;
+
+	switch (in) {
+	case F2FS_GOING_DOWN_FULLSYNC:
+		sb = freeze_bdev(sb->s_bdev);
+		if (sb && !IS_ERR(sb)) {
+			f2fs_stop_checkpoint(sbi);
+			thaw_bdev(sb->s_bdev, sb);
+		}
+		break;
+	case F2FS_GOING_DOWN_METASYNC:
+		/* do checkpoint only */
+		f2fs_sync_fs(sb, 1);
+		f2fs_stop_checkpoint(sbi);
+		break;
+	case F2FS_GOING_DOWN_NOSYNC:
+		f2fs_stop_checkpoint(sbi);
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
 static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
@@ -1078,6 +1128,8 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		return f2fs_ioc_release_volatile_write(filp);
 	case F2FS_IOC_ABORT_VOLATILE_WRITE:
 		return f2fs_ioc_abort_volatile_write(filp);
+	case F2FS_IOC_SHUTDOWN:
+		return f2fs_ioc_shutdown(filp, arg);
 	case FITRIM:
 		return f2fs_ioc_fitrim(filp, arg);
 	default: