Merge tag 'for-f2fs-4.7' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this round, as Ted pointed out, fscrypto allows one more key prefix
  given by filesystem to resolve backward compatibility issues.  Other
  than that, we've fixed several error handling cases by introducing
  a fault injection facility.  We've also achieved performance
  improvement in some workloads as well as a bunch of bug fixes.

  Summary:

  Enhancements:
   - fs-specific prefix for fscrypto
   - fault injection facility
   - expose validity bitmaps for user to be aware of fragmentation
   - fallocate/rm/preallocation speed up
   - use percpu counters

  Bug fixes:
   - some inline_dentry/inline_data bugs
   - error handling for atomic/volatile/orphan inodes
   - recover broken superblock"

* tag 'for-f2fs-4.7' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (73 commits)
  f2fs: fix to update dirty page count correctly
  f2fs: flush pending bios right away when error occurs
  f2fs: avoid ENOSPC fault in the recovery process
  f2fs: make exit_f2fs_fs more clear
  f2fs: use percpu_counter for total_valid_inode_count
  f2fs: use percpu_counter for alloc_valid_block_count
  f2fs: use percpu_counter for # of dirty pages in inode
  f2fs: use percpu_counter for page counters
  f2fs: use bio count instead of F2FS_WRITEBACK page count
  f2fs: manipulate dirty file inodes when DATA_FLUSH is set
  f2fs: add fault injection to sysfs
  f2fs: no need inc dirty pages under inode lock
  f2fs: fix incorrect error path handling in f2fs_move_rehashed_dirents
  f2fs: fix i_current_depth during inline dentry conversion
  f2fs: correct return value type of f2fs_fill_super
  f2fs: fix deadlock when flush inline data
  f2fs: avoid f2fs_bug_on during recovery
  f2fs: show # of orphan inodes
  f2fs: support in batch fzero in dnode page
  f2fs: support in batch multi blocks preallocation
  ...

1 files changed, 244 insertions, 72 deletions

diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 1a33de9d84b1..1f21aae80c40 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -407,6 +407,29 @@ cache:
 	up_write(&nm_i->nat_tree_lock);
 }
 
+/*
+ * readahead MAX_RA_NODE number of node pages.
+ */
+static void ra_node_pages(struct page *parent, int start, int n)
+{
+	struct f2fs_sb_info *sbi = F2FS_P_SB(parent);
+	struct blk_plug plug;
+	int i, end;
+	nid_t nid;
+
+	blk_start_plug(&plug);
+
+	/* Then, try readahead for siblings of the desired node */
+	end = start + n;
+	end = min(end, NIDS_PER_BLOCK);
+	for (i = start; i < end; i++) {
+		nid = get_nid(parent, i, false);
+		ra_node_page(sbi, nid);
+	}
+
+	blk_finish_plug(&plug);
+}
+
 pgoff_t get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs)
 {
 	const long direct_index = ADDRS_PER_INODE(dn->inode);
@@ -707,6 +730,8 @@ static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs,
 		return PTR_ERR(page);
 	}
 
+	ra_node_pages(page, ofs, NIDS_PER_BLOCK);
+
 	rn = F2FS_NODE(page);
 	if (depth < 3) {
 		for (i = ofs; i < NIDS_PER_BLOCK; i++, freed++) {
@@ -784,6 +809,8 @@ static int truncate_partial_nodes(struct dnode_of_data *dn,
 		nid[i + 1] = get_nid(pages[i], offset[i + 1], false);
 	}
 
+	ra_node_pages(pages[idx], offset[idx + 1], NIDS_PER_BLOCK);
+
 	/* free direct nodes linked to a partial indirect node */
 	for (i = offset[idx + 1]; i < NIDS_PER_BLOCK; i++) {
 		child_nid = get_nid(pages[idx], i, false);
@@ -832,7 +859,7 @@ int truncate_inode_blocks(struct inode *inode, pgoff_t from)
 	trace_f2fs_truncate_inode_blocks_enter(inode, from);
 
 	level = get_node_path(inode, from, offset, noffset);
-restart:
+
 	page = get_node_page(sbi, inode->i_ino);
 	if (IS_ERR(page)) {
 		trace_f2fs_truncate_inode_blocks_exit(inode, PTR_ERR(page));
@@ -896,10 +923,7 @@ skip_partial:
 		if (offset[1] == 0 &&
 				ri->i_nid[offset[0] - NODE_DIR1_BLOCK]) {
 			lock_page(page);
-			if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
-				f2fs_put_page(page, 1);
-				goto restart;
-			}
+			BUG_ON(page->mapping != NODE_MAPPING(sbi));
 			f2fs_wait_on_page_writeback(page, NODE, true);
 			ri->i_nid[offset[0] - NODE_DIR1_BLOCK] = 0;
 			set_page_dirty(page);
@@ -998,7 +1022,7 @@ struct page *new_node_page(struct dnode_of_data *dn,
 	if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)))
 		return ERR_PTR(-EPERM);
 
-	page = grab_cache_page(NODE_MAPPING(sbi), dn->nid);
+	page = f2fs_grab_cache_page(NODE_MAPPING(sbi), dn->nid, false);
 	if (!page)
 		return ERR_PTR(-ENOMEM);
 
@@ -1090,7 +1114,7 @@ void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid)
 	if (apage)
 		return;
 
-	apage = grab_cache_page(NODE_MAPPING(sbi), nid);
+	apage = f2fs_grab_cache_page(NODE_MAPPING(sbi), nid, false);
 	if (!apage)
 		return;
 
@@ -1098,29 +1122,6 @@ void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid)
 	f2fs_put_page(apage, err ? 1 : 0);
 }
 
-/*
- * readahead MAX_RA_NODE number of node pages.
- */
-static void ra_node_pages(struct page *parent, int start)
-{
-	struct f2fs_sb_info *sbi = F2FS_P_SB(parent);
-	struct blk_plug plug;
-	int i, end;
-	nid_t nid;
-
-	blk_start_plug(&plug);
-
-	/* Then, try readahead for siblings of the desired node */
-	end = start + MAX_RA_NODE;
-	end = min(end, NIDS_PER_BLOCK);
-	for (i = start; i < end; i++) {
-		nid = get_nid(parent, i, false);
-		ra_node_page(sbi, nid);
-	}
-
-	blk_finish_plug(&plug);
-}
-
 static struct page *__get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid,
 					struct page *parent, int start)
 {
@@ -1131,7 +1132,7 @@ static struct page *__get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid,
 		return ERR_PTR(-ENOENT);
 	f2fs_bug_on(sbi, check_nid_range(sbi, nid));
 repeat:
-	page = grab_cache_page(NODE_MAPPING(sbi), nid);
+	page = f2fs_grab_cache_page(NODE_MAPPING(sbi), nid, false);
 	if (!page)
 		return ERR_PTR(-ENOMEM);
 
@@ -1144,7 +1145,7 @@ repeat:
 	}
 
 	if (parent)
-		ra_node_pages(parent, start + 1);
+		ra_node_pages(parent, start + 1, MAX_RA_NODE);
 
 	lock_page(page);
 
@@ -1196,19 +1197,17 @@ static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino)
 {
 	struct inode *inode;
 	struct page *page;
+	int ret;
 
 	/* should flush inline_data before evict_inode */
 	inode = ilookup(sbi->sb, ino);
 	if (!inode)
 		return;
 
-	page = pagecache_get_page(inode->i_mapping, 0, FGP_NOWAIT, 0);
+	page = pagecache_get_page(inode->i_mapping, 0, FGP_LOCK|FGP_NOWAIT, 0);
 	if (!page)
 		goto iput_out;
 
-	if (!trylock_page(page))
-		goto release_out;
-
 	if (!PageUptodate(page))
 		goto page_out;
 
@@ -1218,24 +1217,214 @@ static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino)
 	if (!clear_page_dirty_for_io(page))
 		goto page_out;
 
-	if (!f2fs_write_inline_data(inode, page))
-		inode_dec_dirty_pages(inode);
-	else
+	ret = f2fs_write_inline_data(inode, page);
+	inode_dec_dirty_pages(inode);
+	if (ret)
 		set_page_dirty(page);
 page_out:
-	unlock_page(page);
-release_out:
-	f2fs_put_page(page, 0);
+	f2fs_put_page(page, 1);
 iput_out:
 	iput(inode);
 }
 
-int sync_node_pages(struct f2fs_sb_info *sbi, nid_t ino,
-					struct writeback_control *wbc)
+void move_node_page(struct page *node_page, int gc_type)
+{
+	if (gc_type == FG_GC) {
+		struct f2fs_sb_info *sbi = F2FS_P_SB(node_page);
+		struct writeback_control wbc = {
+			.sync_mode = WB_SYNC_ALL,
+			.nr_to_write = 1,
+			.for_reclaim = 0,
+		};
+
+		set_page_dirty(node_page);
+		f2fs_wait_on_page_writeback(node_page, NODE, true);
+
+		f2fs_bug_on(sbi, PageWriteback(node_page));
+		if (!clear_page_dirty_for_io(node_page))
+			goto out_page;
+
+		if (NODE_MAPPING(sbi)->a_ops->writepage(node_page, &wbc))
+			unlock_page(node_page);
+		goto release_page;
+	} else {
+		/* set page dirty and write it */
+		if (!PageWriteback(node_page))
+			set_page_dirty(node_page);
+	}
+out_page:
+	unlock_page(node_page);
+release_page:
+	f2fs_put_page(node_page, 0);
+}
+
+static struct page *last_fsync_dnode(struct f2fs_sb_info *sbi, nid_t ino)
 {
 	pgoff_t index, end;
 	struct pagevec pvec;
-	int step = ino ? 2 : 0;
+	struct page *last_page = NULL;
+
+	pagevec_init(&pvec, 0);
+	index = 0;
+	end = ULONG_MAX;
+
+	while (index <= end) {
+		int i, nr_pages;
+		nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index,
+				PAGECACHE_TAG_DIRTY,
+				min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
+		if (nr_pages == 0)
+			break;
+
+		for (i = 0; i < nr_pages; i++) {
+			struct page *page = pvec.pages[i];
+
+			if (unlikely(f2fs_cp_error(sbi))) {
+				f2fs_put_page(last_page, 0);
+				pagevec_release(&pvec);
+				return ERR_PTR(-EIO);
+			}
+
+			if (!IS_DNODE(page) || !is_cold_node(page))
+				continue;
+			if (ino_of_node(page) != ino)
+				continue;
+
+			lock_page(page);
+
+			if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
+continue_unlock:
+				unlock_page(page);
+				continue;
+			}
+			if (ino_of_node(page) != ino)
+				goto continue_unlock;
+
+			if (!PageDirty(page)) {
+				/* someone wrote it for us */
+				goto continue_unlock;
+			}
+
+			if (last_page)
+				f2fs_put_page(last_page, 0);
+
+			get_page(page);
+			last_page = page;
+			unlock_page(page);
+		}
+		pagevec_release(&pvec);
+		cond_resched();
+	}
+	return last_page;
+}
+
+int fsync_node_pages(struct f2fs_sb_info *sbi, nid_t ino,
+			struct writeback_control *wbc, bool atomic)
+{
+	pgoff_t index, end;
+	struct pagevec pvec;
+	int ret = 0;
+	struct page *last_page = NULL;
+	bool marked = false;
+
+	if (atomic) {
+		last_page = last_fsync_dnode(sbi, ino);
+		if (IS_ERR_OR_NULL(last_page))
+			return PTR_ERR_OR_ZERO(last_page);
+	}
+retry:
+	pagevec_init(&pvec, 0);
+	index = 0;
+	end = ULONG_MAX;
+
+	while (index <= end) {
+		int i, nr_pages;
+		nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index,
+				PAGECACHE_TAG_DIRTY,
+				min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
+		if (nr_pages == 0)
+			break;
+
+		for (i = 0; i < nr_pages; i++) {
+			struct page *page = pvec.pages[i];
+
+			if (unlikely(f2fs_cp_error(sbi))) {
+				f2fs_put_page(last_page, 0);
+				pagevec_release(&pvec);
+				return -EIO;
+			}
+
+			if (!IS_DNODE(page) || !is_cold_node(page))
+				continue;
+			if (ino_of_node(page) != ino)
+				continue;
+
+			lock_page(page);
+
+			if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
+continue_unlock:
+				unlock_page(page);
+				continue;
+			}
+			if (ino_of_node(page) != ino)
+				goto continue_unlock;
+
+			if (!PageDirty(page) && page != last_page) {
+				/* someone wrote it for us */
+				goto continue_unlock;
+			}
+
+			f2fs_wait_on_page_writeback(page, NODE, true);
+			BUG_ON(PageWriteback(page));
+
+			if (!atomic || page == last_page) {
+				set_fsync_mark(page, 1);
+				if (IS_INODE(page))
+					set_dentry_mark(page,
+						need_dentry_mark(sbi, ino));
+				/*  may be written by other thread */
+				if (!PageDirty(page))
+					set_page_dirty(page);
+			}
+
+			if (!clear_page_dirty_for_io(page))
+				goto continue_unlock;
+
+			ret = NODE_MAPPING(sbi)->a_ops->writepage(page, wbc);
+			if (ret) {
+				unlock_page(page);
+				f2fs_put_page(last_page, 0);
+				break;
+			}
+			if (page == last_page) {
+				f2fs_put_page(page, 0);
+				marked = true;
+				break;
+			}
+		}
+		pagevec_release(&pvec);
+		cond_resched();
+
+		if (ret || marked)
+			break;
+	}
+	if (!ret && atomic && !marked) {
+		f2fs_msg(sbi->sb, KERN_DEBUG,
+			"Retry to write fsync mark: ino=%u, idx=%lx",
+					ino, last_page->index);
+		lock_page(last_page);
+		set_page_dirty(last_page);
+		unlock_page(last_page);
+		goto retry;
+	}
+	return ret ? -EIO: 0;
+}
+
+int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc)
+{
+	pgoff_t index, end;
+	struct pagevec pvec;
+	int step = 0;
 	int nwritten = 0;
 
 	pagevec_init(&pvec, 0);
@@ -1274,15 +1463,8 @@ next_step:
 			if (step == 2 && (!IS_DNODE(page) ||
 						!is_cold_node(page)))
 				continue;
-
-			/*
-			 * If an fsync mode,
-			 * we should not skip writing node pages.
-			 */
 lock_node:
-			if (ino && ino_of_node(page) == ino)
-				lock_page(page);
-			else if (!trylock_page(page))
+			if (!trylock_page(page))
 				continue;
 
 			if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
@@ -1290,8 +1472,6 @@ continue_unlock:
 				unlock_page(page);
 				continue;
 			}
-			if (ino && ino_of_node(page) != ino)
-				goto continue_unlock;
 
 			if (!PageDirty(page)) {
 				/* someone wrote it for us */
@@ -1299,7 +1479,7 @@ continue_unlock:
 			}
 
 			/* flush inline_data */
-			if (!ino && is_inline_node(page)) {
+			if (is_inline_node(page)) {
 				clear_inline_node(page);
 				unlock_page(page);
 				flush_inline_data(sbi, ino_of_node(page));
@@ -1312,17 +1492,8 @@ continue_unlock:
 			if (!clear_page_dirty_for_io(page))
 				goto continue_unlock;
 
-			/* called by fsync() */
-			if (ino && IS_DNODE(page)) {
-				set_fsync_mark(page, 1);
-				if (IS_INODE(page))
-					set_dentry_mark(page,
-						need_dentry_mark(sbi, ino));
-				nwritten++;
-			} else {
-				set_fsync_mark(page, 0);
-				set_dentry_mark(page, 0);
-			}
+			set_fsync_mark(page, 0);
+			set_dentry_mark(page, 0);
 
 			if (NODE_MAPPING(sbi)->a_ops->writepage(page, wbc))
 				unlock_page(page);
@@ -1470,7 +1641,7 @@ static int f2fs_write_node_pages(struct address_space *mapping,
 
 	diff = nr_pages_to_write(sbi, NODE, wbc);
 	wbc->sync_mode = WB_SYNC_NONE;
-	sync_node_pages(sbi, 0, wbc);
+	sync_node_pages(sbi, wbc);
 	wbc->nr_to_write = max((long)0, wbc->nr_to_write - diff);
 	return 0;
 
@@ -1524,7 +1695,6 @@ static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct free_nid *i;
 	struct nat_entry *ne;
-	bool allocated = false;
 
 	if (!available_free_memory(sbi, FREE_NIDS))
 		return -1;
@@ -1538,8 +1708,6 @@ static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
 		ne = __lookup_nat_cache(nm_i, nid);
 		if (ne && (!get_nat_flag(ne, IS_CHECKPOINTED) ||
 				nat_get_blkaddr(ne) != NULL_ADDR))
-			allocated = true;
-		if (allocated)
 			return 0;
 	}
 
@@ -1672,6 +1840,10 @@ bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid)
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct free_nid *i = NULL;
 retry:
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	if (time_to_inject(FAULT_ALLOC_NID))
+		return false;
+#endif
 	if (unlikely(sbi->total_valid_node_count + 1 > nm_i->available_nids))
 		return false;
 
@@ -1846,7 +2018,7 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
 	if (unlikely(old_ni.blk_addr != NULL_ADDR))
 		return -EINVAL;
 
-	ipage = grab_cache_page(NODE_MAPPING(sbi), ino);
+	ipage = f2fs_grab_cache_page(NODE_MAPPING(sbi), ino, false);
 	if (!ipage)
 		return -ENOMEM;