Merge tag 'f2fs-for-4.19' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this round, we've tuned f2fs to improve general performance by
  serializing block allocation and enhancing discard flows like fstrim
  which avoids user IO contention. And we've added fsync_mode=nobarrier
  which gives an option to user where it skips issuing cache_flush
  commands to underlying flash storage. And there are many bug fixes
  related to fuzzed images, revoked atomic writes, quota ops, and minor
  direct IO.

  Enhancements:
   - add fsync_mode=nobarrier which bypasses cache_flush command
   - enhance the discarding flow which avoids user IOs and issues in
     LBA order
   - readahead some encrypted blocks during GC
   - enable in-memory inode checksum to verify the blocks if
     F2FS_CHECK_FS is set
   - enhance nat_bits behavior
   - set -o discard by default
   - set REQ_RAHEAD to bio in ->readpages

  Bug fixes:
   - fix a corner case to corrupt atomic_writes revoking flow
   - revisit i_gc_rwsem to fix race conditions
   - fix some dio behaviors captured by xfstests
   - correct handling errors given by quota-related failures
   - add many sanity check flows to avoid fuzz test failures
   - add more error number propagation to their callers
   - fix several corner cases to continue fault injection w/ shutdown
     loop"

* tag 'f2fs-for-4.19' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (89 commits)
  f2fs: readahead encrypted block during GC
  f2fs: avoid fi->i_gc_rwsem[WRITE] lock in f2fs_gc
  f2fs: fix performance issue observed with multi-thread sequential read
  f2fs: fix to skip verifying block address for non-regular inode
  f2fs: rework fault injection handling to avoid a warning
  f2fs: support fault_type mount option
  f2fs: fix to return success when trimming meta area
  f2fs: fix use-after-free of dicard command entry
  f2fs: support discard submission error injection
  f2fs: split discard command in prior to block layer
  f2fs: wake up gc thread immediately when gc_urgent is set
  f2fs: fix incorrect range->len in f2fs_trim_fs()
  f2fs: refresh recent accessed nat entry in lru list
  f2fs: fix avoid race between truncate and background GC
  f2fs: avoid race between zero_range and background GC
  f2fs: fix to do sanity check with block address in main area v2
  f2fs: fix to do sanity check with inline flags
  f2fs: fix to reset i_gc_failures correctly
  f2fs: fix invalid memory access
  f2fs: fix to avoid broken of dnode block list
  ...

1 files changed, 306 insertions, 74 deletions

diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 10643b11bd59..dd2e45a661aa 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -28,6 +28,7 @@
 static struct kmem_cache *nat_entry_slab;
 static struct kmem_cache *free_nid_slab;
 static struct kmem_cache *nat_entry_set_slab;
+static struct kmem_cache *fsync_node_entry_slab;
 
 /*
  * Check whether the given nid is within node id range.
@@ -112,25 +113,22 @@ static void clear_node_page_dirty(struct page *page)
 
 static struct page *get_current_nat_page(struct f2fs_sb_info *sbi, nid_t nid)
 {
-	pgoff_t index = current_nat_addr(sbi, nid);
-	return f2fs_get_meta_page(sbi, index);
+	return f2fs_get_meta_page_nofail(sbi, current_nat_addr(sbi, nid));
 }
 
 static struct page *get_next_nat_page(struct f2fs_sb_info *sbi, nid_t nid)
 {
 	struct page *src_page;
 	struct page *dst_page;
-	pgoff_t src_off;
 	pgoff_t dst_off;
 	void *src_addr;
 	void *dst_addr;
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 
-	src_off = current_nat_addr(sbi, nid);
-	dst_off = next_nat_addr(sbi, src_off);
+	dst_off = next_nat_addr(sbi, current_nat_addr(sbi, nid));
 
 	/* get current nat block page with lock */
-	src_page = f2fs_get_meta_page(sbi, src_off);
+	src_page = get_current_nat_page(sbi, nid);
 	dst_page = f2fs_grab_meta_page(sbi, dst_off);
 	f2fs_bug_on(sbi, PageDirty(src_page));
 
@@ -176,14 +174,30 @@ static struct nat_entry *__init_nat_entry(struct f2fs_nm_info *nm_i,
 
 	if (raw_ne)
 		node_info_from_raw_nat(&ne->ni, raw_ne);
+
+	spin_lock(&nm_i->nat_list_lock);
 	list_add_tail(&ne->list, &nm_i->nat_entries);
+	spin_unlock(&nm_i->nat_list_lock);
+
 	nm_i->nat_cnt++;
 	return ne;
 }
 
 static struct nat_entry *__lookup_nat_cache(struct f2fs_nm_info *nm_i, nid_t n)
 {
-	return radix_tree_lookup(&nm_i->nat_root, n);
+	struct nat_entry *ne;
+
+	ne = radix_tree_lookup(&nm_i->nat_root, n);
+
+	/* for recent accessed nat entry, move it to tail of lru list */
+	if (ne && !get_nat_flag(ne, IS_DIRTY)) {
+		spin_lock(&nm_i->nat_list_lock);
+		if (!list_empty(&ne->list))
+			list_move_tail(&ne->list, &nm_i->nat_entries);
+		spin_unlock(&nm_i->nat_list_lock);
+	}
+
+	return ne;
 }
 
 static unsigned int __gang_lookup_nat_cache(struct f2fs_nm_info *nm_i,
@@ -194,7 +208,6 @@ static unsigned int __gang_lookup_nat_cache(struct f2fs_nm_info *nm_i,
 
 static void __del_from_nat_cache(struct f2fs_nm_info *nm_i, struct nat_entry *e)
 {
-	list_del(&e->list);
 	radix_tree_delete(&nm_i->nat_root, nat_get_nid(e));
 	nm_i->nat_cnt--;
 	__free_nat_entry(e);
@@ -245,16 +258,21 @@ static void __set_nat_cache_dirty(struct f2fs_nm_info *nm_i,
 	nm_i->dirty_nat_cnt++;
 	set_nat_flag(ne, IS_DIRTY, true);
 refresh_list:
+	spin_lock(&nm_i->nat_list_lock);
 	if (new_ne)
 		list_del_init(&ne->list);
 	else
 		list_move_tail(&ne->list, &head->entry_list);
+	spin_unlock(&nm_i->nat_list_lock);
 }
 
 static void __clear_nat_cache_dirty(struct f2fs_nm_info *nm_i,
 		struct nat_entry_set *set, struct nat_entry *ne)
 {
+	spin_lock(&nm_i->nat_list_lock);
 	list_move_tail(&ne->list, &nm_i->nat_entries);
+	spin_unlock(&nm_i->nat_list_lock);
+
 	set_nat_flag(ne, IS_DIRTY, false);
 	set->entry_cnt--;
 	nm_i->dirty_nat_cnt--;
@@ -267,6 +285,72 @@ static unsigned int __gang_lookup_nat_set(struct f2fs_nm_info *nm_i,
 							start, nr);
 }
 
+bool f2fs_in_warm_node_list(struct f2fs_sb_info *sbi, struct page *page)
+{
+	return NODE_MAPPING(sbi) == page->mapping &&
+			IS_DNODE(page) && is_cold_node(page);
+}
+
+void f2fs_init_fsync_node_info(struct f2fs_sb_info *sbi)
+{
+	spin_lock_init(&sbi->fsync_node_lock);
+	INIT_LIST_HEAD(&sbi->fsync_node_list);
+	sbi->fsync_seg_id = 0;
+	sbi->fsync_node_num = 0;
+}
+
+static unsigned int f2fs_add_fsync_node_entry(struct f2fs_sb_info *sbi,
+							struct page *page)
+{
+	struct fsync_node_entry *fn;
+	unsigned long flags;
+	unsigned int seq_id;
+
+	fn = f2fs_kmem_cache_alloc(fsync_node_entry_slab, GFP_NOFS);
+
+	get_page(page);
+	fn->page = page;
+	INIT_LIST_HEAD(&fn->list);
+
+	spin_lock_irqsave(&sbi->fsync_node_lock, flags);
+	list_add_tail(&fn->list, &sbi->fsync_node_list);
+	fn->seq_id = sbi->fsync_seg_id++;
+	seq_id = fn->seq_id;
+	sbi->fsync_node_num++;
+	spin_unlock_irqrestore(&sbi->fsync_node_lock, flags);
+
+	return seq_id;
+}
+
+void f2fs_del_fsync_node_entry(struct f2fs_sb_info *sbi, struct page *page)
+{
+	struct fsync_node_entry *fn;
+	unsigned long flags;
+
+	spin_lock_irqsave(&sbi->fsync_node_lock, flags);
+	list_for_each_entry(fn, &sbi->fsync_node_list, list) {
+		if (fn->page == page) {
+			list_del(&fn->list);
+			sbi->fsync_node_num--;
+			spin_unlock_irqrestore(&sbi->fsync_node_lock, flags);
+			kmem_cache_free(fsync_node_entry_slab, fn);
+			put_page(page);
+			return;
+		}
+	}
+	spin_unlock_irqrestore(&sbi->fsync_node_lock, flags);
+	f2fs_bug_on(sbi, 1);
+}
+
+void f2fs_reset_fsync_node_info(struct f2fs_sb_info *sbi)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&sbi->fsync_node_lock, flags);
+	sbi->fsync_seg_id = 0;
+	spin_unlock_irqrestore(&sbi->fsync_node_lock, flags);
+}
+
 int f2fs_need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
@@ -371,7 +455,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
 			new_blkaddr == NULL_ADDR);
 	f2fs_bug_on(sbi, nat_get_blkaddr(e) == NEW_ADDR &&
 			new_blkaddr == NEW_ADDR);
-	f2fs_bug_on(sbi, is_valid_blkaddr(nat_get_blkaddr(e)) &&
+	f2fs_bug_on(sbi, is_valid_data_blkaddr(sbi, nat_get_blkaddr(e)) &&
 			new_blkaddr == NEW_ADDR);
 
 	/* increment version no as node is removed */
@@ -382,7 +466,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
 
 	/* change address */
 	nat_set_blkaddr(e, new_blkaddr);
-	if (!is_valid_blkaddr(new_blkaddr))
+	if (!is_valid_data_blkaddr(sbi, new_blkaddr))
 		set_nat_flag(e, IS_CHECKPOINTED, false);
 	__set_nat_cache_dirty(nm_i, e);
 
@@ -405,13 +489,25 @@ int f2fs_try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink)
 	if (!down_write_trylock(&nm_i->nat_tree_lock))
 		return 0;
 
-	while (nr_shrink && !list_empty(&nm_i->nat_entries)) {
+	spin_lock(&nm_i->nat_list_lock);
+	while (nr_shrink) {
 		struct nat_entry *ne;
+
+		if (list_empty(&nm_i->nat_entries))
+			break;
+
 		ne = list_first_entry(&nm_i->nat_entries,
 					struct nat_entry, list);
+		list_del(&ne->list);
+		spin_unlock(&nm_i->nat_list_lock);
+
 		__del_from_nat_cache(nm_i, ne);
 		nr_shrink--;
+
+		spin_lock(&nm_i->nat_list_lock);
 	}
+	spin_unlock(&nm_i->nat_list_lock);
+
 	up_write(&nm_i->nat_tree_lock);
 	return nr - nr_shrink;
 }
@@ -419,7 +515,7 @@ int f2fs_try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink)
 /*
  * This function always returns success
  */
-void f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid,
+int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid,
 						struct node_info *ni)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
@@ -443,7 +539,7 @@ void f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid,
 		ni->blk_addr = nat_get_blkaddr(e);
 		ni->version = nat_get_version(e);
 		up_read(&nm_i->nat_tree_lock);
-		return;
+		return 0;
 	}
 
 	memset(&ne, 0, sizeof(struct f2fs_nat_entry));
@@ -466,6 +562,9 @@ void f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid,
 	up_read(&nm_i->nat_tree_lock);
 
 	page = f2fs_get_meta_page(sbi, index);
+	if (IS_ERR(page))
+		return PTR_ERR(page);
+
 	nat_blk = (struct f2fs_nat_block *)page_address(page);
 	ne = nat_blk->entries[nid - start_nid];
 	node_info_from_raw_nat(ni, &ne);
@@ -473,6 +572,7 @@ void f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid,
 cache:
 	/* cache nat entry */
 	cache_nat_entry(sbi, nid, &ne);
+	return 0;
 }
 
 /*
@@ -722,12 +822,15 @@ release_out:
 	return err;
 }
 
-static void truncate_node(struct dnode_of_data *dn)
+static int truncate_node(struct dnode_of_data *dn)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
 	struct node_info ni;
+	int err;
 
-	f2fs_get_node_info(sbi, dn->nid, &ni);
+	err = f2fs_get_node_info(sbi, dn->nid, &ni);
+	if (err)
+		return err;
 
 	/* Deallocate node address */
 	f2fs_invalidate_blocks(sbi, ni.blk_addr);
@@ -750,11 +853,14 @@ static void truncate_node(struct dnode_of_data *dn)
 
 	dn->node_page = NULL;
 	trace_f2fs_truncate_node(dn->inode, dn->nid, ni.blk_addr);
+
+	return 0;
 }
 
 static int truncate_dnode(struct dnode_of_data *dn)
 {
 	struct page *page;
+	int err;
 
 	if (dn->nid == 0)
 		return 1;
@@ -770,7 +876,10 @@ static int truncate_dnode(struct dnode_of_data *dn)
 	dn->node_page = page;
 	dn->ofs_in_node = 0;
 	f2fs_truncate_data_blocks(dn);
-	truncate_node(dn);
+	err = truncate_node(dn);
+	if (err)
+		return err;
+
 	return 1;
 }
 
@@ -835,7 +944,9 @@ static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs,
 	if (!ofs) {
 		/* remove current indirect node */
 		dn->node_page = page;
-		truncate_node(dn);
+		ret = truncate_node(dn);
+		if (ret)
+			goto out_err;
 		freed++;
 	} else {
 		f2fs_put_page(page, 1);
@@ -893,7 +1004,9 @@ static int truncate_partial_nodes(struct dnode_of_data *dn,
 	if (offset[idx + 1] == 0) {
 		dn->node_page = pages[idx];
 		dn->nid = nid[idx];
-		truncate_node(dn);
+		err = truncate_node(dn);
+		if (err)
+			goto fail;
 	} else {
 		f2fs_put_page(pages[idx], 1);
 	}
@@ -1014,6 +1127,7 @@ int f2fs_truncate_xattr_node(struct inode *inode)
 	nid_t nid = F2FS_I(inode)->i_xattr_nid;
 	struct dnode_of_data dn;
 	struct page *npage;
+	int err;
 
 	if (!nid)
 		return 0;
@@ -1022,10 +1136,15 @@ int f2fs_truncate_xattr_node(struct inode *inode)
 	if (IS_ERR(npage))
 		return PTR_ERR(npage);
 
+	set_new_dnode(&dn, inode, NULL, npage, nid);
+	err = truncate_node(&dn);
+	if (err) {
+		f2fs_put_page(npage, 1);
+		return err;
+	}
+
 	f2fs_i_xnid_write(inode, 0);
 
-	set_new_dnode(&dn, inode, NULL, npage, nid);
-	truncate_node(&dn);
 	return 0;
 }
 
@@ -1055,11 +1174,19 @@ int f2fs_remove_inode_page(struct inode *inode)
 		f2fs_truncate_data_blocks_range(&dn, 1);
 
 	/* 0 is possible, after f2fs_new_inode() has failed */
+	if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) {
+		f2fs_put_dnode(&dn);
+		return -EIO;
+	}
 	f2fs_bug_on(F2FS_I_SB(inode),
 			inode->i_blocks != 0 && inode->i_blocks != 8);
 
 	/* will put inode & node pages */
-	truncate_node(&dn);
+	err = truncate_node(&dn);
+	if (err) {
+		f2fs_put_dnode(&dn);
+		return err;
+	}
 	return 0;
 }
 
@@ -1092,7 +1219,11 @@ struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs)
 		goto fail;
 
 #ifdef CONFIG_F2FS_CHECK_FS
-	f2fs_get_node_info(sbi, dn->nid, &new_ni);
+	err = f2fs_get_node_info(sbi, dn->nid, &new_ni);
+	if (err) {
+		dec_valid_node_count(sbi, dn->inode, !ofs);
+		goto fail;
+	}
 	f2fs_bug_on(sbi, new_ni.blk_addr != NULL_ADDR);
 #endif
 	new_ni.nid = dn->nid;
@@ -1140,13 +1271,21 @@ static int read_node_page(struct page *page, int op_flags)
 		.page = page,
 		.encrypted_page = NULL,
 	};
+	int err;
 
-	if (PageUptodate(page))
+	if (PageUptodate(page)) {
+#ifdef CONFIG_F2FS_CHECK_FS
+		f2fs_bug_on(sbi, !f2fs_inode_chksum_verify(sbi, page));
+#endif
 		return LOCKED_PAGE;
+	}
 
-	f2fs_get_node_info(sbi, page->index, &ni);
+	err = f2fs_get_node_info(sbi, page->index, &ni);
+	if (err)
+		return err;
 
-	if (unlikely(ni.blk_addr == NULL_ADDR)) {
+	if (unlikely(ni.blk_addr == NULL_ADDR) ||
+			is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN)) {
 		ClearPageUptodate(page);
 		return -ENOENT;
 	}
@@ -1348,7 +1487,7 @@ continue_unlock:
 
 static int __write_node_page(struct page *page, bool atomic, bool *submitted,
 				struct writeback_control *wbc, bool do_balance,
-				enum iostat_type io_type)
+				enum iostat_type io_type, unsigned int *seq_id)
 {
 	struct f2fs_sb_info *sbi = F2FS_P_SB(page);
 	nid_t nid;
@@ -1365,6 +1504,7 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
 		.io_type = io_type,
 		.io_wbc = wbc,
 	};
+	unsigned int seq;
 
 	trace_f2fs_writepage(page, NODE);
 
@@ -1374,10 +1514,17 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
 	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
 		goto redirty_out;
 
+	if (wbc->sync_mode == WB_SYNC_NONE &&
+			IS_DNODE(page) && is_cold_node(page))
+		goto redirty_out;
+
 	/* get old block addr of this node page */
 	nid = nid_of_node(page);
 	f2fs_bug_on(sbi, page->index != nid);
 
+	if (f2fs_get_node_info(sbi, nid, &ni))
+		goto redirty_out;
+
 	if (wbc->for_reclaim) {
 		if (!down_read_trylock(&sbi->node_write))
 			goto redirty_out;
@@ -1385,8 +1532,6 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
 		down_read(&sbi->node_write);
 	}
 
-	f2fs_get_node_info(sbi, nid, &ni);
-
 	/* This page is already truncated */
 	if (unlikely(ni.blk_addr == NULL_ADDR)) {
 		ClearPageUptodate(page);
@@ -1396,11 +1541,22 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
 		return 0;
 	}
 
+	if (__is_valid_data_blkaddr(ni.blk_addr) &&
+		!f2fs_is_valid_blkaddr(sbi, ni.blk_addr, DATA_GENERIC))
+		goto redirty_out;
+
 	if (atomic && !test_opt(sbi, NOBARRIER))
 		fio.op_flags |= REQ_PREFLUSH | REQ_FUA;
 
 	set_page_writeback(page);
 	ClearPageError(page);
+
+	if (f2fs_in_warm_node_list(sbi, page)) {
+		seq = f2fs_add_fsync_node_entry(sbi, page);
+		if (seq_id)
+			*seq_id = seq;
+	}
+
 	fio.old_blkaddr = ni.blk_addr;
 	f2fs_do_write_node_page(nid, &fio);
 	set_node_addr(sbi, &ni, fio.new_blkaddr, is_fsync_dnode(page));
@@ -1448,7 +1604,7 @@ void f2fs_move_node_page(struct page *node_page, int gc_type)
 			goto out_page;
 
 		if (__write_node_page(node_page, false, NULL,
-					&wbc, false, FS_GC_NODE_IO))
+					&wbc, false, FS_GC_NODE_IO, NULL))
 			unlock_page(node_page);
 		goto release_page;
 	} else {
@@ -1465,11 +1621,13 @@ release_page:
 static int f2fs_write_node_page(struct page *page,
 				struct writeback_control *wbc)
 {
-	return __write_node_page(page, false, NULL, wbc, false, FS_NODE_IO);
+	return __write_node_page(page, false, NULL, wbc, false,
+						FS_NODE_IO, NULL);
 }
 
 int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
-			struct writeback_control *wbc, bool atomic)
+			struct writeback_control *wbc, bool atomic,
+			unsigned int *seq_id)
 {
 	pgoff_t index;
 	pgoff_t last_idx = ULONG_MAX;
@@ -1550,7 +1708,7 @@ continue_unlock:
 			ret = __write_node_page(page, atomic &&
 						page == last_page,
 						&submitted, wbc, true,
-						FS_NODE_IO);
+						FS_NODE_IO, seq_id);
 			if (ret) {
 				unlock_page(page);
 				f2fs_put_page(last_page, 0);
@@ -1633,7 +1791,9 @@ next_step:
 						!is_cold_node(page)))
 				continue;
 lock_node:
-			if (!trylock_page(page))
+			if (wbc->sync_mode == WB_SYNC_ALL)
+				lock_page(page);
+			else if (!trylock_page(page))
 				continue;
 
 			if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
@@ -1665,7 +1825,7 @@ continue_unlock:
 			set_dentry_mark(page, 0);
 
 			ret = __write_node_page(page, false, &submitted,
-						wbc, do_balance, io_type);
+						wbc, do_balance, io_type, NULL);
 			if (ret)
 				unlock_page(page);
 			else if (submitted)
@@ -1684,10 +1844,12 @@ continue_unlock:
 	}
 
 	if (step < 2) {
+		if (wbc->sync_mode == WB_SYNC_NONE && step == 1)
+			goto out;
 		step++;
 		goto next_step;
 	}
-
+out:
 	if (nwritten)
 		f2fs_submit_merged_write(sbi, NODE);
 
@@ -1696,35 +1858,46 @@ continue_unlock:
 	return ret;
 }
 
-int f2fs_wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino)
+int f2fs_wait_on_node_pages_writeback(struct f2fs_sb_info *sbi,
+						unsigned int seq_id)
 {
-	pgoff_t index = 0;
-	struct pagevec pvec;
+	struct fsync_node_entry *fn;
+	struct page *page;
+	struct list_head *head = &sbi->fsync_node_list;
+	unsigned long flags;
+	unsigned int cur_seq_id = 0;
 	int ret2, ret = 0;
-	int nr_pages;
 
-	pagevec_init(&pvec);
+	while (seq_id && cur_seq_id < seq_id) {
+		spin_lock_irqsave(&sbi->fsync_node_lock, flags);
+		if (list_empty(head)) {
+			spin_unlock_irqrestore(&sbi->fsync_node_lock, flags);
+			break;
+		}
+		fn = list_first_entry(head, struct fsync_node_entry, list);
+		if (fn->seq_id > seq_id) {
+			spin_unlock_irqrestore(&sbi->fsync_node_lock, flags);
+			break;
+		}
+		cur_seq_id = fn->seq_id;
+		page = fn->page;
+		get_page(page);
+		spin_unlock_irqrestore(&sbi->fsync_node_lock, flags);
 
-	while ((nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index,
-				PAGECACHE_TAG_WRITEBACK))) {
-		int i;
+		f2fs_wait_on_page_writeback(page, NODE, true);
+		if (TestClearPageError(page))
+			ret = -EIO;
 
-		for (i = 0; i < nr_pages; i++) {
-			struct page *page = pvec.pages[i];
+		put_page(page);
 
-			if (ino && ino_of_node(page) == ino) {
-				f2fs_wait_on_page_writeback(page, NODE, true);
-				if (TestClearPageError(page))
-					ret = -EIO;
-			}
-		}
-		pagevec_release(&pvec);
-		cond_resched();
+		if (ret)
+			break;
 	}
 
 	ret2 = filemap_check_errors(NODE_MAPPING(sbi));
 	if (!ret)
 		ret = ret2;
+
 	return ret;
 }
 
@@ -1774,6 +1947,10 @@ static int f2fs_set_node_page_dirty(struct page *page)
 
 	if (!PageUptodate(page))
 		SetPageUptodate(page);
+#ifdef CONFIG_F2FS_CHECK_FS
+	if (IS_INODE(page))
+		f2fs_inode_chksum_set(F2FS_P_SB(page), page);
+#endif
 	if (!PageDirty(page)) {
 		__set_page_dirty_nobuffers(page);
 		inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_NODES);
@@ -1968,7 +2145,7 @@ static void remove_free_nid(struct f2fs_sb_info *sbi, nid_t nid)
 		kmem_cache_free(free_nid_slab, i);
 }
 
-static void scan_nat_page(struct f2fs_sb_info *sbi,
+static int scan_nat_page(struct f2fs_sb_info *sbi,
 			struct page *nat_page, nid_t start_nid)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
@@ -1986,7 +2163,10 @@ static void scan_nat_page(struct f2fs_sb_info *sbi,
 			break;
 
 		blk_addr = le32_to_cpu(nat_blk->entries[i].block_addr);
-		f2fs_bug_on(sbi, blk_addr == NEW_ADDR);
+
+		if (blk_addr == NEW_ADDR)
+			return -EINVAL;
+
 		if (blk_addr == NULL_ADDR) {
 			add_free_nid(sbi, start_nid, true, true);
 		} else {
@@ -1995,6 +2175,8 @@ static void scan_nat_page(struct f2fs_sb_info *sbi,
 			spin_unlock(&NM_I(sbi)->nid_list_lock);
 		}
 	}
+
+	return 0;
 }
 
 static void scan_curseg_cache(struct f2fs_sb_info *sbi)
@@ -2050,11 +2232,11 @@ out:
 	up_read(&nm_i->nat_tree_lock);
 }
 
-static void __f2fs_build_free_nids(struct f2fs_sb_info *sbi,
+static int __f2fs_build_free_nids(struct f2fs_sb_info *sbi,
 						bool sync, bool mount)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
-	int i = 0;
+	int i = 0, ret;
 	nid_t nid = nm_i->next_scan_nid;
 
 	if (unlikely(nid >= nm_i->max_nid))
@@ -2062,17 +2244,17 @@ static void __f2fs_build_free_nids(struct f2fs_sb_info *sbi,
 
 	/* Enough entries */
 	if (nm_i->nid_cnt[FREE_NID] >= NAT_ENTRY_PER_BLOCK)
-		return;
+		return 0;
 
 	if (!sync && !f2fs_available_free_memory(sbi, FREE_NIDS))
-		return;
+		return 0;
 
 	if (!mount) {
 		/* try to find free nids in free_nid_bitmap */
 		scan_free_nid_bits(sbi);
 
 		if (nm_i->nid_cnt[FREE_NID] >= NAT_ENTRY_PER_BLOCK)
-			return;
+			return 0;
 	}
 
 	/* readahead nat pages to be scanned */
@@ -2086,8 +2268,16 @@ static void __f2fs_build_free_nids(struct f2fs_sb_info *sbi,
 						nm_i->nat_block_bitmap)) {
 			struct page *page = get_current_nat_page(sbi, nid);
 
-			scan_nat_page(sbi, page, nid);
+			ret = scan_nat_page(sbi, page, nid);
 			f2fs_put_page(page, 1);
+
+			if (ret) {
+				up_read(&nm_i->nat_tree_lock);
+				f2fs_bug_on(sbi, !mount);
+				f2fs_msg(sbi->sb, KERN_ERR,
+					"NAT is corrupt, run fsck to fix it");
+				return -EINVAL;
+			}
 		}
 
 		nid += (NAT_ENTRY_PER_BLOCK - (nid % NAT_ENTRY_PER_BLOCK));
@@ -2108,13 +2298,19 @@ static void __f2fs_build_free_nids(struct f2fs_sb_info *sbi,
 
 	f2fs_ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid),
 					nm_i->ra_nid_pages, META_NAT, false);
+
+	return 0;
 }
 
-void f2fs_build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount)
+int f2fs_build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount)
 {
+	int ret;
+
 	mutex_lock(&NM_I(sbi)->build_lock);
-	__f2fs_build_free_nids(sbi, sync, mount);
+	ret = __f2fs_build_free_nids(sbi, sync, mount);
 	mutex_unlock(&NM_I(sbi)->build_lock);
+
+	return ret;
 }
 
 /*
@@ -2127,12 +2323,11 @@ bool f2fs_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(sbi, FAULT_ALLOC_NID)) {
 		f2fs_show_injection_info(FAULT_ALLOC_NID);
 		return false;
 	}
-#endif
+
 	spin_lock(&nm_i->nid_list_lock);
 
 	if (unlikely(nm_i->available_nids == 0)) {
@@ -2277,12 +2472,16 @@ int f2fs_recover_xattr_data(struct inode *inode, struct page *page)
 	struct dnode_of_data dn;
 	struct node_info ni;
 	struct page *xpage;
+	int err;
 
 	if (!prev_xnid)
 		goto recover_xnid;
 
 	/* 1: invalidate the previous xattr nid */
-	f2fs_get_node_info(sbi, prev_xnid, &ni);
+	err = f2fs_get_node_info(sbi, prev_xnid, &ni);
+	if (err)
+		return err;
+
 	f2fs_invalidate_blocks(sbi, ni.blk_addr);
 	dec_valid_node_count(sbi, inode, false);
 	set_node_addr(sbi, &ni, NULL_ADDR, false);
@@ -2317,8 +2516,11 @@ int f2fs_recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
 	nid_t ino = ino_of_node(page);
 	struct node_info old_ni, new_ni;
 	struct page *ipage;
+	int err;
 
-	f2fs_get_node_info(sbi, ino, &old_ni);
+	err = f2fs_get_node_info(sbi, ino, &old_ni);
+	if (err)
+		return err;
 
 	if (unlikely(old_ni.blk_addr != NULL_ADDR))
 		return -EINVAL;
@@ -2372,7 +2574,7 @@ retry:
 	return 0;
 }
 
-void f2fs_restore_node_summary(struct f2fs_sb_info *sbi,
+int f2fs_restore_node_summary(struct f2fs_sb_info *sbi,
 			unsigned int segno, struct f2fs_summary_block *sum)
 {
 	struct f2fs_node *rn;
@@ -2394,6 +2596,9 @@ void f2fs_restore_node_summary(struct f2fs_sb_info *sbi,
 		for (idx = addr; idx < addr + nrpages; idx++) {
 			struct page *page = f2fs_get_tmp_page(sbi, idx);
 
+			if (IS_ERR(page))
+				return PTR_ERR(page);
+
 			rn = F2FS_NODE(page);
 			sum_entry->nid = rn->footer.nid;
 			sum_entry->version = 0;
@@ -2405,6 +2610,7 @@ void f2fs_restore_node_summary(struct f2fs_sb_info *sbi,
 		invalidate_mapping_pages(META_MAPPING(sbi), addr,
 							addr + nrpages);
 	}
+	return 0;
 }
 
 static void remove_nats_in_journal(struct f2fs_sb_info *sbi)
@@ -2582,6 +2788,13 @@ void f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	nid_t set_idx = 0;
 	LIST_HEAD(sets);
 
+	/* during unmount, let's flush nat_bits before checking dirty_nat_cnt */
+	if (enabled_nat_bits(sbi, cpc)) {
+		down_write(&nm_i->nat_tree_lock);
+		remove_nats_in_journal(sbi);
+		up_write(&nm_i->nat_tree_lock);
+	}
+
 	if (!nm_i->dirty_nat_cnt)
 		return;
 
@@ -2634,7 +2847,13 @@ static int __get_nat_bitmaps(struct f2fs_sb_info *sbi)
 	nat_bits_addr = __start_cp_addr(sbi) + sbi->blocks_per_seg -
 						nm_i->nat_bits_blocks;
 	for (i = 0; i < nm_i->nat_bits_blocks; i++) {
-		struct page *page = f2fs_get_meta_page(sbi, nat_bits_addr++);
+		struct page *page;
+
+		page = f2fs_get_meta_page(sbi, nat_bits_addr++);
+		if (IS_ERR(page)) {
+			disable_nat_bits(sbi, true);
+			return PTR_ERR(page);
+		}
 
 		memcpy(nm_i->nat_bits + (i << F2FS_BLKSIZE_BITS),
 					page_address(page), F2FS_BLKSIZE);
@@ -2718,6 +2937,7 @@ static int init_node_manager(struct f2fs_sb_info *sbi)
 	INIT_RADIX_TREE(&nm_i->nat_root, GFP_NOIO);
 	INIT_RADIX_TREE(&nm_i->nat_set_root, GFP_NOIO);
 	INIT_LIST_HEAD(&nm_i->nat_entries);
+	spin_lock_init(&nm_i->nat_list_lock);
 
 	mutex_init(&nm_i->build_lock);
 	spin_lock_init(&nm_i->nid_list_lock);
@@ -2762,8 +2982,8 @@ static int init_free_nid_cache(struct f2fs_sb_info *sbi)
 
 	for (i = 0; i < nm_i->nat_blocks; i++) {
 		nm_i->free_nid_bitmap[i] = f2fs_kvzalloc(sbi,
-				NAT_ENTRY_BITMAP_SIZE_ALIGNED, GFP_KERNEL);
-		if (!nm_i->free_nid_bitmap)
+			f2fs_bitmap_size(NAT_ENTRY_PER_BLOCK), GFP_KERNEL);
+		if (!nm_i->free_nid_bitmap[i])
 			return -ENOMEM;
 	}
 
@@ -2801,8 +3021,7 @@ int f2fs_build_node_manager(struct f2fs_sb_info *sbi)
 	/* load free nid status from nat_bits table */
 	load_free_nid_bitmap(sbi);
 
-	f2fs_build_free_nids(sbi, true, true);
-	return 0;
+	return f2fs_build_free_nids(sbi, true, true);
 }
 
 void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi)
@@ -2837,8 +3056,13 @@ void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi)
 		unsigned idx;
 
 		nid = nat_get_nid(natvec[found - 1]) + 1;
-		for (idx = 0; idx < found; idx++)
+		for (idx = 0; idx < found; idx++) {
+			spin_lock(&nm_i->nat_list_lock);
+			list_del(&natvec[idx]->list);
+			spin_unlock(&nm_i->nat_list_lock);
+
 			__del_from_nat_cache(nm_i, natvec[idx]);
+		}
 	}
 	f2fs_bug_on(sbi, nm_i->nat_cnt);
 
@@ -2893,8 +3117,15 @@ int __init f2fs_create_node_manager_caches(void)
 			sizeof(struct nat_entry_set));
 	if (!nat_entry_set_slab)
 		goto destroy_free_nid;
+
+	fsync_node_entry_slab = f2fs_kmem_cache_create("fsync_node_entry",
+			sizeof(struct fsync_node_entry));
+	if (!fsync_node_entry_slab)
+		goto destroy_nat_entry_set;
 	return 0;
 
+destroy_nat_entry_set:
+	kmem_cache_destroy(nat_entry_set_slab);
 destroy_free_nid:
 	kmem_cache_destroy(free_nid_slab);
 destroy_nat_entry:
@@ -2905,6 +3136,7 @@ fail:
 
 void f2fs_destroy_node_manager_caches(void)
 {
+	kmem_cache_destroy(fsync_node_entry_slab);
 	kmem_cache_destroy(nat_entry_set_slab);
 	kmem_cache_destroy(free_nid_slab);
 	kmem_cache_destroy(nat_entry_slab);