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
  ...

MAINTAINERS

@@ -4793,7 +4793,7 @@ F:	include/linux/fscache*.h
 F2FS FILE SYSTEM
 M:	Jaegeuk Kim <jaegeuk@kernel.org>
 M:	Changman Lee <cm224.lee@samsung.com>
-R:	Chao Yu <chao2.yu@samsung.com>
+R:	Chao Yu <yuchao0@huawei.com>
 L:	linux-f2fs-devel@lists.sourceforge.net
 W:	http://en.wikipedia.org/wiki/F2FS
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs.git

fs/crypto/keyinfo.c

@@ -78,6 +78,67 @@ out:
 	return res;
 }
 
+static int validate_user_key(struct fscrypt_info *crypt_info,
+			struct fscrypt_context *ctx, u8 *raw_key,
+			u8 *prefix, int prefix_size)
+{
+	u8 *full_key_descriptor;
+	struct key *keyring_key;
+	struct fscrypt_key *master_key;
+	const struct user_key_payload *ukp;
+	int full_key_len = prefix_size + (FS_KEY_DESCRIPTOR_SIZE * 2) + 1;
+	int res;
+
+	full_key_descriptor = kmalloc(full_key_len, GFP_NOFS);
+	if (!full_key_descriptor)
+		return -ENOMEM;
+
+	memcpy(full_key_descriptor, prefix, prefix_size);
+	sprintf(full_key_descriptor + prefix_size,
+			"%*phN", FS_KEY_DESCRIPTOR_SIZE,
+			ctx->master_key_descriptor);
+	full_key_descriptor[full_key_len - 1] = '\0';
+	keyring_key = request_key(&key_type_logon, full_key_descriptor, NULL);
+	kfree(full_key_descriptor);
+	if (IS_ERR(keyring_key))
+		return PTR_ERR(keyring_key);
+
+	if (keyring_key->type != &key_type_logon) {
+		printk_once(KERN_WARNING
+				"%s: key type must be logon\n", __func__);
+		res = -ENOKEY;
+		goto out;
+	}
+	down_read(&keyring_key->sem);
+	ukp = user_key_payload(keyring_key);
+	if (ukp->datalen != sizeof(struct fscrypt_key)) {
+		res = -EINVAL;
+		up_read(&keyring_key->sem);
+		goto out;
+	}
+	master_key = (struct fscrypt_key *)ukp->data;
+	BUILD_BUG_ON(FS_AES_128_ECB_KEY_SIZE != FS_KEY_DERIVATION_NONCE_SIZE);
+
+	if (master_key->size != FS_AES_256_XTS_KEY_SIZE) {
+		printk_once(KERN_WARNING
+				"%s: key size incorrect: %d\n",
+				__func__, master_key->size);
+		res = -ENOKEY;
+		up_read(&keyring_key->sem);
+		goto out;
+	}
+	res = derive_key_aes(ctx->nonce, master_key->raw, raw_key);
+	up_read(&keyring_key->sem);
+	if (res)
+		goto out;
+
+	crypt_info->ci_keyring_key = keyring_key;
+	return 0;
+out:
+	key_put(keyring_key);
+	return res;
+}
+
 static void put_crypt_info(struct fscrypt_info *ci)
 {
 	if (!ci)
@@ -91,12 +152,7 @@ static void put_crypt_info(struct fscrypt_info *ci)
 int get_crypt_info(struct inode *inode)
 {
 	struct fscrypt_info *crypt_info;
-	u8 full_key_descriptor[FS_KEY_DESC_PREFIX_SIZE +
-				(FS_KEY_DESCRIPTOR_SIZE * 2) + 1];
-	struct key *keyring_key = NULL;
-	struct fscrypt_key *master_key;
 	struct fscrypt_context ctx;
-	const struct user_key_payload *ukp;
 	struct crypto_skcipher *ctfm;
 	const char *cipher_str;
 	u8 raw_key[FS_MAX_KEY_SIZE];
@@ -167,48 +223,24 @@ retry:
 		memset(raw_key, 0x42, FS_AES_256_XTS_KEY_SIZE);
 		goto got_key;
 	}
-	memcpy(full_key_descriptor, FS_KEY_DESC_PREFIX,
-					FS_KEY_DESC_PREFIX_SIZE);
-	sprintf(full_key_descriptor + FS_KEY_DESC_PREFIX_SIZE,
-					"%*phN", FS_KEY_DESCRIPTOR_SIZE,
-					ctx.master_key_descriptor);
-	full_key_descriptor[FS_KEY_DESC_PREFIX_SIZE +
-					(2 * FS_KEY_DESCRIPTOR_SIZE)] = '\0';
-	keyring_key = request_key(&key_type_logon, full_key_descriptor, NULL);
-	if (IS_ERR(keyring_key)) {
-		res = PTR_ERR(keyring_key);
-		keyring_key = NULL;
-		goto out;
-	}
-	crypt_info->ci_keyring_key = keyring_key;
-	if (keyring_key->type != &key_type_logon) {
-		printk_once(KERN_WARNING
-				"%s: key type must be logon\n", __func__);
-		res = -ENOKEY;
-		goto out;
-	}
-	down_read(&keyring_key->sem);
-	ukp = user_key_payload(keyring_key);
-	if (ukp->datalen != sizeof(struct fscrypt_key)) {
-		res = -EINVAL;
-		up_read(&keyring_key->sem);
-		goto out;
-	}
-	master_key = (struct fscrypt_key *)ukp->data;
-	BUILD_BUG_ON(FS_AES_128_ECB_KEY_SIZE != FS_KEY_DERIVATION_NONCE_SIZE);
 
-	if (master_key->size != FS_AES_256_XTS_KEY_SIZE) {
-		printk_once(KERN_WARNING
-				"%s: key size incorrect: %d\n",
-				__func__, master_key->size);
-		res = -ENOKEY;
-		up_read(&keyring_key->sem);
+	res = validate_user_key(crypt_info, &ctx, raw_key,
+			FS_KEY_DESC_PREFIX, FS_KEY_DESC_PREFIX_SIZE);
+	if (res && inode->i_sb->s_cop->key_prefix) {
+		u8 *prefix = NULL;
+		int prefix_size, res2;
+
+		prefix_size = inode->i_sb->s_cop->key_prefix(inode, &prefix);
+		res2 = validate_user_key(crypt_info, &ctx, raw_key,
+							prefix, prefix_size);
+		if (res2) {
+			if (res2 == -ENOKEY)
+				res = -ENOKEY;
+			goto out;
+		}
+	} else if (res) {
 		goto out;
 	}
-	res = derive_key_aes(ctx.nonce, master_key->raw, raw_key);
-	up_read(&keyring_key->sem);
-	if (res)
-		goto out;
 got_key:
 	ctfm = crypto_alloc_skcipher(cipher_str, 0, 0);
 	if (!ctfm || IS_ERR(ctfm)) {

fs/f2fs/Kconfig

@@ -94,3 +94,11 @@ config F2FS_IO_TRACE
 	  information and block IO patterns in the filesystem level.
 
 	  If unsure, say N.
+
+config F2FS_FAULT_INJECTION
+	bool "F2FS fault injection facility"
+	depends on F2FS_FS
+	help
+	  Test F2FS to inject faults such as ENOMEM, ENOSPC, and so on.
+
+	  If unsure, say N.

fs/f2fs/acl.c

@@ -115,7 +115,7 @@ static void *f2fs_acl_to_disk(const struct posix_acl *acl, size_t *size)
 	struct f2fs_acl_entry *entry;
 	int i;
 
-	f2fs_acl = kmalloc(sizeof(struct f2fs_acl_header) + acl->a_count *
+	f2fs_acl = f2fs_kmalloc(sizeof(struct f2fs_acl_header) + acl->a_count *
 			sizeof(struct f2fs_acl_entry), GFP_NOFS);
 	if (!f2fs_acl)
 		return ERR_PTR(-ENOMEM);
@@ -175,7 +175,7 @@ static struct posix_acl *__f2fs_get_acl(struct inode *inode, int type,
 
 	retval = f2fs_getxattr(inode, name_index, "", NULL, 0, dpage);
 	if (retval > 0) {
-		value = kmalloc(retval, GFP_F2FS_ZERO);
+		value = f2fs_kmalloc(retval, GFP_F2FS_ZERO);
 		if (!value)
 			return ERR_PTR(-ENOMEM);
 		retval = f2fs_getxattr(inode, name_index, "", value,

fs/f2fs/checkpoint.c

@@ -26,6 +26,14 @@
 static struct kmem_cache *ino_entry_slab;
 struct kmem_cache *inode_entry_slab;
 
+void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io)
+{
+	set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG);
+	sbi->sb->s_flags |= MS_RDONLY;
+	if (!end_io)
+		f2fs_flush_merged_bios(sbi);
+}
+
 /*
  * We guarantee no failure on the returned page.
  */
@@ -34,7 +42,7 @@ struct page *grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
 	struct address_space *mapping = META_MAPPING(sbi);
 	struct page *page = NULL;
 repeat:
-	page = grab_cache_page(mapping, index);
+	page = f2fs_grab_cache_page(mapping, index, false);
 	if (!page) {
 		cond_resched();
 		goto repeat;
@@ -64,7 +72,7 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
 	if (unlikely(!is_meta))
 		fio.rw &= ~REQ_META;
 repeat:
-	page = grab_cache_page(mapping, index);
+	page = f2fs_grab_cache_page(mapping, index, false);
 	if (!page) {
 		cond_resched();
 		goto repeat;
@@ -91,7 +99,7 @@ repeat:
 	 * meta page.
 	 */
 	if (unlikely(!PageUptodate(page)))
-		f2fs_stop_checkpoint(sbi);
+		f2fs_stop_checkpoint(sbi, false);
 out:
 	return page;
 }
@@ -186,7 +194,8 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
 			BUG();
 		}
 
-		page = grab_cache_page(META_MAPPING(sbi), fio.new_blkaddr);
+		page = f2fs_grab_cache_page(META_MAPPING(sbi),
+						fio.new_blkaddr, false);
 		if (!page)
 			continue;
 		if (PageUptodate(page)) {
@@ -211,7 +220,7 @@ void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index)
 	bool readahead = false;
 
 	page = find_get_page(META_MAPPING(sbi), index);
-	if (!page || (page && !PageUptodate(page)))
+	if (!page || !PageUptodate(page))
 		readahead = true;
 	f2fs_put_page(page, 0);
 
@@ -448,12 +457,12 @@ bool exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode)
 	return e ? true : false;
 }
 
-void release_ino_entry(struct f2fs_sb_info *sbi)
+void release_ino_entry(struct f2fs_sb_info *sbi, bool all)
 {
 	struct ino_entry *e, *tmp;
 	int i;
 
-	for (i = APPEND_INO; i <= UPDATE_INO; i++) {
+	for (i = all ? ORPHAN_INO: APPEND_INO; i <= UPDATE_INO; i++) {
 		struct inode_management *im = &sbi->im[i];
 
 		spin_lock(&im->ino_lock);
@@ -473,6 +482,13 @@ int acquire_orphan_inode(struct f2fs_sb_info *sbi)
 	int err = 0;
 
 	spin_lock(&im->ino_lock);
+
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	if (time_to_inject(FAULT_ORPHAN)) {
+		spin_unlock(&im->ino_lock);
+		return -ENOSPC;
+	}
+#endif
 	if (unlikely(im->ino_num >= sbi->max_orphans))
 		err = -ENOSPC;
 	else
@@ -777,43 +793,32 @@ void update_dirty_page(struct inode *inode, struct page *page)
 			!S_ISLNK(inode->i_mode))
 		return;
 
-	spin_lock(&sbi->inode_lock[type]);
-	__add_dirty_inode(inode, type);
-	inode_inc_dirty_pages(inode);
-	spin_unlock(&sbi->inode_lock[type]);
+	if (type != FILE_INODE || test_opt(sbi, DATA_FLUSH)) {
+		spin_lock(&sbi->inode_lock[type]);
+		__add_dirty_inode(inode, type);
+		spin_unlock(&sbi->inode_lock[type]);
+	}
 
+	inode_inc_dirty_pages(inode);
 	SetPagePrivate(page);
 	f2fs_trace_pid(page);
 }
 
-void add_dirty_dir_inode(struct inode *inode)
-{
-	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-
-	spin_lock(&sbi->inode_lock[DIR_INODE]);
-	__add_dirty_inode(inode, DIR_INODE);
-	spin_unlock(&sbi->inode_lock[DIR_INODE]);
-}
-
 void remove_dirty_inode(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct f2fs_inode_info *fi = F2FS_I(inode);
 	enum inode_type type = S_ISDIR(inode->i_mode) ? DIR_INODE : FILE_INODE;
 
 	if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) &&
 			!S_ISLNK(inode->i_mode))
 		return;
 
+	if (type == FILE_INODE && !test_opt(sbi, DATA_FLUSH))
+		return;
+
 	spin_lock(&sbi->inode_lock[type]);
 	__remove_dirty_inode(inode, type);
 	spin_unlock(&sbi->inode_lock[type]);
-
-	/* Only from the recovery routine */
-	if (is_inode_flag_set(fi, FI_DELAY_IPUT)) {
-		clear_inode_flag(fi, FI_DELAY_IPUT);
-		iput(inode);
-	}
 }
 
 int sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type)
@@ -892,7 +897,7 @@ retry_flush_nodes:
 
 	if (get_pages(sbi, F2FS_DIRTY_NODES)) {
 		up_write(&sbi->node_write);
-		err = sync_node_pages(sbi, 0, &wbc);
+		err = sync_node_pages(sbi, &wbc);
 		if (err) {
 			f2fs_unlock_all(sbi);
 			goto out;
@@ -917,7 +922,7 @@ static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)
 	for (;;) {
 		prepare_to_wait(&sbi->cp_wait, &wait, TASK_UNINTERRUPTIBLE);
 
-		if (!get_pages(sbi, F2FS_WRITEBACK))
+		if (!atomic_read(&sbi->nr_wb_bios))
 			break;
 
 		io_schedule_timeout(5*HZ);
@@ -1082,7 +1087,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	/* update user_block_counts */
 	sbi->last_valid_block_count = sbi->total_valid_block_count;
-	sbi->alloc_valid_block_count = 0;
+	percpu_counter_set(&sbi->alloc_valid_block_count, 0);
 
 	/* Here, we only have one bio having CP pack */
 	sync_meta_pages(sbi, META_FLUSH, LONG_MAX);
@@ -1098,7 +1103,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 		invalidate_mapping_pages(META_MAPPING(sbi), discard_blk,
 								discard_blk);
 
-	release_ino_entry(sbi);
+	release_ino_entry(sbi, false);
 
 	if (unlikely(f2fs_cp_error(sbi)))
 		return -EIO;

fs/f2fs/data.c

@@ -68,13 +68,12 @@ static void f2fs_write_end_io(struct bio *bio)
 
 		if (unlikely(bio->bi_error)) {
 			set_bit(AS_EIO, &page->mapping->flags);
-			f2fs_stop_checkpoint(sbi);
+			f2fs_stop_checkpoint(sbi, true);
 		}
 		end_page_writeback(page);
-		dec_page_count(sbi, F2FS_WRITEBACK);
 	}
-
-	if (!get_pages(sbi, F2FS_WRITEBACK) && wq_has_sleeper(&sbi->cp_wait))
+	if (atomic_dec_and_test(&sbi->nr_wb_bios) &&
+				wq_has_sleeper(&sbi->cp_wait))
 		wake_up(&sbi->cp_wait);
 
 	bio_put(bio);
@@ -98,6 +97,14 @@ static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr,
 	return bio;
 }
 
+static inline void __submit_bio(struct f2fs_sb_info *sbi, int rw,
+						struct bio *bio)
+{
+	if (!is_read_io(rw))
+		atomic_inc(&sbi->nr_wb_bios);
+	submit_bio(rw, bio);
+}
+
 static void __submit_merged_bio(struct f2fs_bio_info *io)
 {
 	struct f2fs_io_info *fio = &io->fio;
@@ -110,7 +117,7 @@ static void __submit_merged_bio(struct f2fs_bio_info *io)
 	else
 		trace_f2fs_submit_write_bio(io->sbi->sb, fio, io->bio);
 
-	submit_bio(fio->rw, io->bio);
+	__submit_bio(io->sbi, fio->rw, io->bio);
 	io->bio = NULL;
 }
 
@@ -228,7 +235,7 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
 		return -EFAULT;
 	}
 
-	submit_bio(fio->rw, bio);
+	__submit_bio(fio->sbi, fio->rw, bio);
 	return 0;
 }
 
@@ -248,9 +255,6 @@ void f2fs_submit_page_mbio(struct f2fs_io_info *fio)
 
 	down_write(&io->io_rwsem);
 
-	if (!is_read)
-		inc_page_count(sbi, F2FS_WRITEBACK);
-
 	if (io->bio && (io->last_block_in_bio != fio->new_blkaddr - 1 ||
 						io->fio.rw != fio->rw))
 		__submit_merged_bio(io);
@@ -278,6 +282,16 @@ alloc_new:
 	trace_f2fs_submit_page_mbio(fio->page, fio);
 }
 
+static void __set_data_blkaddr(struct dnode_of_data *dn)
+{
+	struct f2fs_node *rn = F2FS_NODE(dn->node_page);
+	__le32 *addr_array;
+
+	/* Get physical address of data block */
+	addr_array = blkaddr_in_node(rn);
+	addr_array[dn->ofs_in_node] = cpu_to_le32(dn->data_blkaddr);
+}
+
 /*
  * Lock ordering for the change of data block address:
  * ->data_page
@@ -286,19 +300,9 @@ alloc_new:
  */
 void set_data_blkaddr(struct dnode_of_data *dn)
 {
-	struct f2fs_node *rn;
-	__le32 *addr_array;
-	struct page *node_page = dn->node_page;
-	unsigned int ofs_in_node = dn->ofs_in_node;
-
-	f2fs_wait_on_page_writeback(node_page, NODE, true);
-
-	rn = F2FS_NODE(node_page);
-
-	/* Get physical address of data block */
-	addr_array = blkaddr_in_node(rn);
-	addr_array[ofs_in_node] = cpu_to_le32(dn->data_blkaddr);
-	if (set_page_dirty(node_page))
+	f2fs_wait_on_page_writeback(dn->node_page, NODE, true);
+	__set_data_blkaddr(dn);
+	if (set_page_dirty(dn->node_page))
 		dn->node_changed = true;
 }
 
@@ -309,24 +313,53 @@ void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr)
 	f2fs_update_extent_cache(dn);
 }
 
-int reserve_new_block(struct dnode_of_data *dn)
+/* dn->ofs_in_node will be returned with up-to-date last block pointer */
+int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
 
+	if (!count)
+		return 0;
+
 	if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)))
 		return -EPERM;
-	if (unlikely(!inc_valid_block_count(sbi, dn->inode, 1)))
+	if (unlikely(!inc_valid_block_count(sbi, dn->inode, &count)))
 		return -ENOSPC;
 
-	trace_f2fs_reserve_new_block(dn->inode, dn->nid, dn->ofs_in_node);
+	trace_f2fs_reserve_new_blocks(dn->inode, dn->nid,
+						dn->ofs_in_node, count);
+
+	f2fs_wait_on_page_writeback(dn->node_page, NODE, true);
+
+	for (; count > 0; dn->ofs_in_node++) {
+		block_t blkaddr =
+			datablock_addr(dn->node_page, dn->ofs_in_node);
+		if (blkaddr == NULL_ADDR) {
+			dn->data_blkaddr = NEW_ADDR;
+			__set_data_blkaddr(dn);
+			count--;
+		}
+	}
+
+	if (set_page_dirty(dn->node_page))
+		dn->node_changed = true;
 
-	dn->data_blkaddr = NEW_ADDR;
-	set_data_blkaddr(dn);
 	mark_inode_dirty(dn->inode);
 	sync_inode_page(dn);
 	return 0;
 }
 
+/* Should keep dn->ofs_in_node unchanged */
+int reserve_new_block(struct dnode_of_data *dn)
+{
+	unsigned int ofs_in_node = dn->ofs_in_node;
+	int ret;
+
+	ret = reserve_new_blocks(dn, 1);
+	dn->ofs_in_node = ofs_in_node;
+	return ret;
+}
+
 int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index)
 {
 	bool need_put = dn->inode_page ? false : true;
@@ -545,6 +578,7 @@ static int __allocate_data_block(struct dnode_of_data *dn)
 	struct node_info ni;
 	int seg = CURSEG_WARM_DATA;
 	pgoff_t fofs;
+	blkcnt_t count = 1;
 
 	if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)))
 		return -EPERM;
@@ -553,7 +587,7 @@ static int __allocate_data_block(struct dnode_of_data *dn)
 	if (dn->data_blkaddr == NEW_ADDR)
 		goto alloc;
 
-	if (unlikely(!inc_valid_block_count(sbi, dn->inode, 1)))
+	if (unlikely(!inc_valid_block_count(sbi, dn->inode, &count)))
 		return -ENOSPC;
 
 alloc:
@@ -582,8 +616,8 @@ ssize_t f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
 	struct f2fs_map_blocks map;
 	ssize_t ret = 0;
 
-	map.m_lblk = F2FS_BYTES_TO_BLK(iocb->ki_pos);
-	map.m_len = F2FS_BLK_ALIGN(iov_iter_count(from));
+	map.m_lblk = F2FS_BLK_ALIGN(iocb->ki_pos);
+	map.m_len = F2FS_BYTES_TO_BLK(iov_iter_count(from));
 	map.m_next_pgofs = NULL;
 
 	if (f2fs_encrypted_inode(inode))
@@ -621,8 +655,10 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
 	struct dnode_of_data dn;
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	int mode = create ? ALLOC_NODE : LOOKUP_NODE_RA;
-	pgoff_t pgofs, end_offset;
+	pgoff_t pgofs, end_offset, end;
 	int err = 0, ofs = 1;
+	unsigned int ofs_in_node, last_ofs_in_node;
+	blkcnt_t prealloc;
 	struct extent_info ei;
 	bool allocated = false;
 	block_t blkaddr;
@@ -632,6 +668,7 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
 
 	/* it only supports block size == page size */
 	pgofs =	(pgoff_t)map->m_lblk;
+	end = pgofs + maxblocks;
 
 	if (!create && f2fs_lookup_extent_cache(inode, pgofs, &ei)) {
 		map->m_pblk = ei.blk + pgofs - ei.fofs;
@@ -648,6 +685,8 @@ next_dnode:
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
 	err = get_dnode_of_data(&dn, pgofs, mode);
 	if (err) {
+		if (flag == F2FS_GET_BLOCK_BMAP)
+			map->m_pblk = 0;
 		if (err == -ENOENT) {
 			err = 0;
 			if (map->m_next_pgofs)
@@ -657,6 +696,8 @@ next_dnode:
 		goto unlock_out;
 	}
 
+	prealloc = 0;
+	ofs_in_node = dn.ofs_in_node;
 	end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
 
 next_block:
@@ -669,31 +710,41 @@ next_block:
 				goto sync_out;
 			}
 			if (flag == F2FS_GET_BLOCK_PRE_AIO) {
-				if (blkaddr == NULL_ADDR)
-					err = reserve_new_block(&dn);
+				if (blkaddr == NULL_ADDR) {
+					prealloc++;
+					last_ofs_in_node = dn.ofs_in_node;
+				}
 			} else {
 				err = __allocate_data_block(&dn);
+				if (!err) {
+					set_inode_flag(F2FS_I(inode),
+							FI_APPEND_WRITE);
+					allocated = true;
+				}
 			}
 			if (err)
 				goto sync_out;
-			allocated = true;
 			map->m_flags = F2FS_MAP_NEW;
 			blkaddr = dn.data_blkaddr;
 		} else {
+			if (flag == F2FS_GET_BLOCK_BMAP) {
+				map->m_pblk = 0;
+				goto sync_out;
+			}
 			if (flag == F2FS_GET_BLOCK_FIEMAP &&
 						blkaddr == NULL_ADDR) {
 				if (map->m_next_pgofs)
 					*map->m_next_pgofs = pgofs + 1;
 			}
 			if (flag != F2FS_GET_BLOCK_FIEMAP ||
-						blkaddr != NEW_ADDR) {
-				if (flag == F2FS_GET_BLOCK_BMAP)
-					err = -ENOENT;
+						blkaddr != NEW_ADDR)
 				goto sync_out;
-			}
 		}
 	}
 
+	if (flag == F2FS_GET_BLOCK_PRE_AIO)
+		goto skip;
+
 	if (map->m_len == 0) {
 		/* preallocated unwritten block should be mapped for fiemap. */
 		if (blkaddr == NEW_ADDR)
@@ -705,32 +756,49 @@ next_block:
 	} else if ((map->m_pblk != NEW_ADDR &&
 			blkaddr == (map->m_pblk + ofs)) ||
 			(map->m_pblk == NEW_ADDR && blkaddr == NEW_ADDR) ||
-			flag == F2FS_GET_BLOCK_PRE_DIO ||
-			flag == F2FS_GET_BLOCK_PRE_AIO) {
+			flag == F2FS_GET_BLOCK_PRE_DIO) {
 		ofs++;
 		map->m_len++;
 	} else {
 		goto sync_out;
 	}
 
+skip:
 	dn.ofs_in_node++;
 	pgofs++;
 
-	if (map->m_len < maxblocks) {
-		if (dn.ofs_in_node < end_offset)
-			goto next_block;
+	/* preallocate blocks in batch for one dnode page */
+	if (flag == F2FS_GET_BLOCK_PRE_AIO &&
+			(pgofs == end || dn.ofs_in_node == end_offset)) {
 
-		if (allocated)
-			sync_inode_page(&dn);
-		f2fs_put_dnode(&dn);
+		dn.ofs_in_node = ofs_in_node;
+		err = reserve_new_blocks(&dn, prealloc);
+		if (err)
+			goto sync_out;
 
-		if (create) {
-			f2fs_unlock_op(sbi);
-			f2fs_balance_fs(sbi, allocated);
+		map->m_len += dn.ofs_in_node - ofs_in_node;
+		if (prealloc && dn.ofs_in_node != last_ofs_in_node + 1) {
+			err = -ENOSPC;
+			goto sync_out;
 		}
-		allocated = false;
-		goto next_dnode;
+		dn.ofs_in_node = end_offset;
+	}
+
+	if (pgofs >= end)
+		goto sync_out;
+	else if (dn.ofs_in_node < end_offset)
+		goto next_block;
+
+	if (allocated)
+		sync_inode_page(&dn);
+	f2fs_put_dnode(&dn);
+
+	if (create) {
+		f2fs_unlock_op(sbi);
+		f2fs_balance_fs(sbi, allocated);
 	}
+	allocated = false;
+	goto next_dnode;
 
 sync_out:
 	if (allocated)
@@ -983,7 +1051,7 @@ got_it:
 		 */
 		if (bio && (last_block_in_bio != block_nr - 1)) {
 submit_and_realloc:
-			submit_bio(READ, bio);
+			__submit_bio(F2FS_I_SB(inode), READ, bio);
 			bio = NULL;
 		}
 		if (bio == NULL) {
@@ -1026,7 +1094,7 @@ set_error_page:
 		goto next_page;
 confused:
 		if (bio) {
-			submit_bio(READ, bio);
+			__submit_bio(F2FS_I_SB(inode), READ, bio);
 			bio = NULL;
 		}
 		unlock_page(page);
@@ -1036,7 +1104,7 @@ next_page:
 	}
 	BUG_ON(pages && !list_empty(pages));
 	if (bio)
-		submit_bio(READ, bio);
+		__submit_bio(F2FS_I_SB(inode), READ, bio);
 	return 0;
 }
 
@@ -1177,8 +1245,10 @@ write:
 		goto redirty_out;
 	if (f2fs_is_drop_cache(inode))
 		goto out;
-	if (f2fs_is_volatile_file(inode) && !wbc->for_reclaim &&
-			available_free_memory(sbi, BASE_CHECK))
+	/* we should not write 0'th page having journal header */
+	if (f2fs_is_volatile_file(inode) && (!page->index ||
+			(!wbc->for_reclaim &&
+			available_free_memory(sbi, BASE_CHECK))))
 		goto redirty_out;
 
 	/* Dentry blocks are controlled by checkpoint */
@@ -1480,7 +1550,8 @@ restart:
 		if (pos + len <= MAX_INLINE_DATA) {
 			read_inline_data(page, ipage);
 			set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
-			set_inline_node(ipage);
+			if (inode->i_nlink)
+				set_inline_node(ipage);
 		} else {
 			err = f2fs_convert_inline_page(&dn, page);
 			if (err)
@@ -1496,7 +1567,7 @@ restart:
 		} else {
 			/* hole case */
 			err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
-			if (err || (!err && dn.data_blkaddr == NULL_ADDR)) {
+			if (err || dn.data_blkaddr == NULL_ADDR) {
 				f2fs_put_dnode(&dn);
 				f2fs_lock_op(sbi);
 				locked = true;
@@ -1683,8 +1754,12 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	trace_f2fs_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
 
 	err = blockdev_direct_IO(iocb, inode, iter, get_data_block_dio);
-	if (err < 0 && iov_iter_rw(iter) == WRITE)
-		f2fs_write_failed(mapping, offset + count);
+	if (iov_iter_rw(iter) == WRITE) {
+		if (err > 0)
+			set_inode_flag(F2FS_I(inode), FI_UPDATE_WRITE);
+		else if (err < 0)
+			f2fs_write_failed(mapping, offset + count);
+	}
 
 	trace_f2fs_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), err);
 
@@ -1714,6 +1789,7 @@ void f2fs_invalidate_page(struct page *page, unsigned int offset,
 	if (IS_ATOMIC_WRITTEN_PAGE(page))
 		return;
 
+	set_page_private(page, 0);
 	ClearPagePrivate(page);
 }
 
@@ -1727,6 +1803,7 @@ int f2fs_release_page(struct page *page, gfp_t wait)
 	if (IS_ATOMIC_WRITTEN_PAGE(page))
 		return 0;
 
+	set_page_private(page, 0);
 	ClearPagePrivate(page);
 	return 1;
 }

fs/f2fs/debug.c

@@ -48,7 +48,7 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 	si->ndirty_dirs = sbi->ndirty_inode[DIR_INODE];
 	si->ndirty_files = sbi->ndirty_inode[FILE_INODE];
 	si->inmem_pages = get_pages(sbi, F2FS_INMEM_PAGES);
-	si->wb_pages = get_pages(sbi, F2FS_WRITEBACK);
+	si->wb_bios = atomic_read(&sbi->nr_wb_bios);
 	si->total_count = (int)sbi->user_block_count / sbi->blocks_per_seg;
 	si->rsvd_segs = reserved_segments(sbi);
 	si->overp_segs = overprovision_segments(sbi);
@@ -58,6 +58,7 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 	si->inline_xattr = atomic_read(&sbi->inline_xattr);
 	si->inline_inode = atomic_read(&sbi->inline_inode);
 	si->inline_dir = atomic_read(&sbi->inline_dir);
+	si->orphans = sbi->im[ORPHAN_INO].ino_num;
 	si->utilization = utilization(sbi);
 
 	si->free_segs = free_segments(sbi);
@@ -143,6 +144,7 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
 	si->base_mem = sizeof(struct f2fs_sb_info) + sbi->sb->s_blocksize;
 	si->base_mem += 2 * sizeof(struct f2fs_inode_info);
 	si->base_mem += sizeof(*sbi->ckpt);
+	si->base_mem += sizeof(struct percpu_counter) * NR_COUNT_TYPE;
 
 	/* build sm */
 	si->base_mem += sizeof(struct f2fs_sm_info);
@@ -192,7 +194,7 @@ get_cache:
 	si->cache_mem += NM_I(sbi)->dirty_nat_cnt *
 					sizeof(struct nat_entry_set);
 	si->cache_mem += si->inmem_pages * sizeof(struct inmem_pages);
-	for (i = 0; i <= UPDATE_INO; i++)
+	for (i = 0; i <= ORPHAN_INO; i++)
 		si->cache_mem += sbi->im[i].ino_num * sizeof(struct ino_entry);
 	si->cache_mem += atomic_read(&sbi->total_ext_tree) *
 						sizeof(struct extent_tree);
@@ -216,8 +218,9 @@ static int stat_show(struct seq_file *s, void *v)
 	list_for_each_entry(si, &f2fs_stat_list, stat_list) {
 		update_general_status(si->sbi);
 
-		seq_printf(s, "\n=====[ partition info(%pg). #%d ]=====\n",
-			si->sbi->sb->s_bdev, i++);
+		seq_printf(s, "\n=====[ partition info(%pg). #%d, %s]=====\n",
+			si->sbi->sb->s_bdev, i++,
+			f2fs_readonly(si->sbi->sb) ? "RO": "RW");
 		seq_printf(s, "[SB: 1] [CP: 2] [SIT: %d] [NAT: %d] ",
 			   si->sit_area_segs, si->nat_area_segs);
 		seq_printf(s, "[SSA: %d] [MAIN: %d",
@@ -237,6 +240,8 @@ static int stat_show(struct seq_file *s, void *v)
 			   si->inline_inode);
 		seq_printf(s, "  - Inline_dentry Inode: %u\n",
 			   si->inline_dir);
+		seq_printf(s, "  - Orphan Inode: %u\n",
+			   si->orphans);
 		seq_printf(s, "\nMain area: %d segs, %d secs %d zones\n",
 			   si->main_area_segs, si->main_area_sections,
 			   si->main_area_zones);
@@ -295,15 +300,15 @@ static int stat_show(struct seq_file *s, void *v)
 		seq_printf(s, "  - Inner Struct Count: tree: %d(%d), node: %d\n",
 				si->ext_tree, si->zombie_tree, si->ext_node);
 		seq_puts(s, "\nBalancing F2FS Async:\n");
-		seq_printf(s, "  - inmem: %4d, wb: %4d\n",
-			   si->inmem_pages, si->wb_pages);
-		seq_printf(s, "  - nodes: %4d in %4d\n",
+		seq_printf(s, "  - inmem: %4lld, wb_bios: %4d\n",
+			   si->inmem_pages, si->wb_bios);
+		seq_printf(s, "  - nodes: %4lld in %4d\n",
 			   si->ndirty_node, si->node_pages);
-		seq_printf(s, "  - dents: %4d in dirs:%4d\n",
+		seq_printf(s, "  - dents: %4lld in dirs:%4d\n",
 			   si->ndirty_dent, si->ndirty_dirs);
-		seq_printf(s, "  - datas: %4d in files:%4d\n",
+		seq_printf(s, "  - datas: %4lld in files:%4d\n",
 			   si->ndirty_data, si->ndirty_files);
-		seq_printf(s, "  - meta: %4d in %4d\n",
+		seq_printf(s, "  - meta: %4lld in %4d\n",
 			   si->ndirty_meta, si->meta_pages);
 		seq_printf(s, "  - NATs: %9d/%9d\n  - SITs: %9d/%9d\n",
 			   si->dirty_nats, si->nats, si->dirty_sits, si->sits);

fs/f2fs/dir.c

@@ -48,7 +48,6 @@ unsigned char f2fs_filetype_table[F2FS_FT_MAX] = {
 	[F2FS_FT_SYMLINK]	= DT_LNK,
 };
 
-#define S_SHIFT 12
 static unsigned char f2fs_type_by_mode[S_IFMT >> S_SHIFT] = {
 	[S_IFREG >> S_SHIFT]	= F2FS_FT_REG_FILE,
 	[S_IFDIR >> S_SHIFT]	= F2FS_FT_DIR,
@@ -64,6 +63,13 @@ void set_de_type(struct f2fs_dir_entry *de, umode_t mode)
 	de->file_type = f2fs_type_by_mode[(mode & S_IFMT) >> S_SHIFT];
 }
 
+unsigned char get_de_type(struct f2fs_dir_entry *de)
+{
+	if (de->file_type < F2FS_FT_MAX)
+		return f2fs_filetype_table[de->file_type];
+	return DT_UNKNOWN;
+}
+
 static unsigned long dir_block_index(unsigned int level,
 				int dir_level, unsigned int idx)
 {
@@ -95,11 +101,6 @@ static struct f2fs_dir_entry *find_in_block(struct page *dentry_page,
 	else
 		kunmap(dentry_page);
 
-	/*
-	 * For the most part, it should be a bug when name_len is zero.
-	 * We stop here for figuring out where the bugs has occurred.
-	 */
-	f2fs_bug_on(F2FS_P_SB(dentry_page), d.max < 0);
 	return de;
 }
 
@@ -124,6 +125,11 @@ struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *fname,
 
 		de = &d->dentry[bit_pos];
 
+		if (unlikely(!de->name_len)) {
+			bit_pos++;
+			continue;
+		}
+
 		/* encrypted case */
 		de_name.name = d->filename[bit_pos];
 		de_name.len = le16_to_cpu(de->name_len);
@@ -141,10 +147,6 @@ struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *fname,
 			*max_slots = max_len;
 		max_len = 0;
 
-		/* remain bug on condition */
-		if (unlikely(!de->name_len))
-			d->max = -1;
-
 		bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
 	}
 
@@ -389,9 +391,14 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
 			return page;
 
 		if (S_ISDIR(inode->i_mode)) {
+			/* in order to handle error case */
+			get_page(page);
 			err = make_empty_dir(inode, dir, page);
-			if (err)
-				goto error;
+			if (err) {
+				lock_page(page);
+				goto put_error;
+			}
+			put_page(page);
 		}
 
 		err = f2fs_init_acl(inode, dir, page, dpage);
@@ -435,13 +442,12 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
 	return page;
 
 put_error:
-	f2fs_put_page(page, 1);
-error:
-	/* once the failed inode becomes a bad inode, i_mode is S_IFREG */
+	/* truncate empty dir pages */
 	truncate_inode_pages(&inode->i_data, 0);
-	truncate_blocks(inode, 0, false);
-	remove_dirty_inode(inode);
-	remove_inode_page(inode);
+
+	clear_nlink(inode);
+	update_inode(inode, page);
+	f2fs_put_page(page, 1);
 	return ERR_PTR(err);
 }
 
@@ -509,11 +515,7 @@ void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d,
 	}
 }
 
-/*
- * Caller should grab and release a rwsem by calling f2fs_lock_op() and
- * f2fs_unlock_op().
- */
-int __f2fs_add_link(struct inode *dir, const struct qstr *name,
+int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name,
 				struct inode *inode, nid_t ino, umode_t mode)
 {
 	unsigned int bit_pos;
@@ -526,28 +528,11 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name,
 	struct f2fs_dentry_block *dentry_blk = NULL;
 	struct f2fs_dentry_ptr d;
 	struct page *page = NULL;
-	struct fscrypt_name fname;
-	struct qstr new_name;
-	int slots, err;
-
-	err = fscrypt_setup_filename(dir, name, 0, &fname);
-	if (err)
-		return err;
-
-	new_name.name = fname_name(&fname);
-	new_name.len = fname_len(&fname);
-
-	if (f2fs_has_inline_dentry(dir)) {
-		err = f2fs_add_inline_entry(dir, &new_name, inode, ino, mode);
-		if (!err || err != -EAGAIN)
-			goto out;
-		else
-			err = 0;
-	}
+	int slots, err = 0;
 
 	level = 0;
-	slots = GET_DENTRY_SLOTS(new_name.len);
-	dentry_hash = f2fs_dentry_hash(&new_name);
+	slots = GET_DENTRY_SLOTS(new_name->len);
+	dentry_hash = f2fs_dentry_hash(new_name);
 
 	current_depth = F2FS_I(dir)->i_current_depth;
 	if (F2FS_I(dir)->chash == dentry_hash) {
@@ -556,10 +541,12 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name,
 	}
 
 start:
-	if (unlikely(current_depth == MAX_DIR_HASH_DEPTH)) {
-		err = -ENOSPC;
-		goto out;
-	}
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	if (time_to_inject(FAULT_DIR_DEPTH))
+		return -ENOSPC;
+#endif
+	if (unlikely(current_depth == MAX_DIR_HASH_DEPTH))
+		return -ENOSPC;
 
 	/* Increase the depth, if required */
 	if (level == current_depth)
@@ -573,10 +560,8 @@ start:
 
 	for (block = bidx; block <= (bidx + nblock - 1); block++) {
 		dentry_page = get_new_data_page(dir, NULL, block, true);
-		if (IS_ERR(dentry_page)) {
-			err = PTR_ERR(dentry_page);
-			goto out;
-		}
+		if (IS_ERR(dentry_page))
+			return PTR_ERR(dentry_page);
 
 		dentry_blk = kmap(dentry_page);
 		bit_pos = room_for_filename(&dentry_blk->dentry_bitmap,
@@ -596,7 +581,7 @@ add_dentry:
 
 	if (inode) {
 		down_write(&F2FS_I(inode)->i_sem);
-		page = init_inode_metadata(inode, dir, &new_name, NULL);
+		page = init_inode_metadata(inode, dir, new_name, NULL);
 		if (IS_ERR(page)) {
 			err = PTR_ERR(page);
 			goto fail;
@@ -606,7 +591,7 @@ add_dentry:
 	}
 
 	make_dentry_ptr(NULL, &d, (void *)dentry_blk, 1);
-	f2fs_update_dentry(ino, mode, &d, &new_name, dentry_hash, bit_pos);
+	f2fs_update_dentry(ino, mode, &d, new_name, dentry_hash, bit_pos);
 
 	set_page_dirty(dentry_page);
 
@@ -628,7 +613,34 @@ fail:
 	}
 	kunmap(dentry_page);
 	f2fs_put_page(dentry_page, 1);
-out:
+
+	return err;
+}
+
+/*
+ * Caller should grab and release a rwsem by calling f2fs_lock_op() and
+ * f2fs_unlock_op().
+ */
+int __f2fs_add_link(struct inode *dir, const struct qstr *name,
+				struct inode *inode, nid_t ino, umode_t mode)
+{
+	struct fscrypt_name fname;
+	struct qstr new_name;
+	int err;
+
+	err = fscrypt_setup_filename(dir, name, 0, &fname);
+	if (err)
+		return err;
+
+	new_name.name = fname_name(&fname);
+	new_name.len = fname_len(&fname);
+
+	err = -EAGAIN;
+	if (f2fs_has_inline_dentry(dir))
+		err = f2fs_add_inline_entry(dir, &new_name, inode, ino, mode);
+	if (err == -EAGAIN)
+		err = f2fs_add_regular_entry(dir, &new_name, inode, ino, mode);
+
 	fscrypt_free_filename(&fname);
 	f2fs_update_time(F2FS_I_SB(dir), REQ_TIME);
 	return err;
@@ -792,10 +804,7 @@ bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
 			continue;
 		}
 
-		if (de->file_type < F2FS_FT_MAX)
-			d_type = f2fs_filetype_table[de->file_type];
-		else
-			d_type = DT_UNKNOWN;
+		d_type = get_de_type(de);
 
 		de_name.name = d->filename[bit_pos];
 		de_name.len = le16_to_cpu(de->name_len);
@@ -804,7 +813,7 @@ bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
 			int save_len = fstr->len;
 			int ret;
 
-			de_name.name = kmalloc(de_name.len, GFP_NOFS);
+			de_name.name = f2fs_kmalloc(de_name.len, GFP_NOFS);
 			if (!de_name.name)
 				return false;
 
@@ -887,6 +896,7 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
 		kunmap(dentry_page);
 		f2fs_put_page(dentry_page, 1);
 	}
+	err = 0;
 out:
 	fscrypt_fname_free_buffer(&fstr);
 	return err;

fs/f2fs/extent_cache.c

@@ -196,8 +196,7 @@ bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext)
 	if (!i_ext || !i_ext->len)
 		return false;
 
-	set_extent_info(&ei, le32_to_cpu(i_ext->fofs),
-		le32_to_cpu(i_ext->blk), le32_to_cpu(i_ext->len));
+	get_extent_info(&ei, i_ext);
 
 	write_lock(&et->lock);
 	if (atomic_read(&et->node_cnt))

fs/f2fs/f2fs.h

@@ -37,6 +37,57 @@
 	} while (0)
 #endif
 
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+enum {
+	FAULT_KMALLOC,
+	FAULT_PAGE_ALLOC,
+	FAULT_ALLOC_NID,
+	FAULT_ORPHAN,
+	FAULT_BLOCK,
+	FAULT_DIR_DEPTH,
+	FAULT_MAX,
+};
+
+struct f2fs_fault_info {
+	atomic_t inject_ops;
+	unsigned int inject_rate;
+	unsigned int inject_type;
+};
+
+extern struct f2fs_fault_info f2fs_fault;
+extern char *fault_name[FAULT_MAX];
+#define IS_FAULT_SET(type) (f2fs_fault.inject_type & (1 << (type)))
+
+static inline bool time_to_inject(int type)
+{
+	if (!f2fs_fault.inject_rate)
+		return false;
+	if (type == FAULT_KMALLOC && !IS_FAULT_SET(type))
+		return false;
+	else if (type == FAULT_PAGE_ALLOC && !IS_FAULT_SET(type))
+		return false;
+	else if (type == FAULT_ALLOC_NID && !IS_FAULT_SET(type))
+		return false;
+	else if (type == FAULT_ORPHAN && !IS_FAULT_SET(type))
+		return false;
+	else if (type == FAULT_BLOCK && !IS_FAULT_SET(type))
+		return false;
+	else if (type == FAULT_DIR_DEPTH && !IS_FAULT_SET(type))
+		return false;
+
+	atomic_inc(&f2fs_fault.inject_ops);
+	if (atomic_read(&f2fs_fault.inject_ops) >= f2fs_fault.inject_rate) {
+		atomic_set(&f2fs_fault.inject_ops, 0);
+		printk("%sF2FS-fs : inject %s in %pF\n",
+				KERN_INFO,
+				fault_name[type],
+				__builtin_return_address(0));
+		return true;
+	}
+	return false;
+}
+#endif
+
 /*
  * For mount options
  */
@@ -56,6 +107,7 @@
 #define F2FS_MOUNT_EXTENT_CACHE		0x00002000
 #define F2FS_MOUNT_FORCE_FG_GC		0x00004000
 #define F2FS_MOUNT_DATA_FLUSH		0x00008000
+#define F2FS_MOUNT_FAULT_INJECTION	0x00010000
 
 #define clear_opt(sbi, option)	(sbi->mount_opt.opt &= ~F2FS_MOUNT_##option)
 #define set_opt(sbi, option)	(sbi->mount_opt.opt |= F2FS_MOUNT_##option)
@@ -159,7 +211,6 @@ struct fsync_inode_entry {
 	struct inode *inode;	/* vfs inode pointer */
 	block_t blkaddr;	/* block address locating the last fsync */
 	block_t last_dentry;	/* block address locating the last dentry */
-	block_t last_inode;	/* block address locating the last inode */
 };
 
 #define nats_in_cursum(jnl)		(le16_to_cpu(jnl->n_nats))
@@ -385,7 +436,7 @@ struct f2fs_inode_info {
 	/* Use below internally in f2fs*/
 	unsigned long flags;		/* use to pass per-file flags */
 	struct rw_semaphore i_sem;	/* protect fi info */
-	atomic_t dirty_pages;		/* # of dirty pages */
+	struct percpu_counter dirty_pages;	/* # of dirty pages */
 	f2fs_hash_t chash;		/* hash value of given file name */
 	unsigned int clevel;		/* maximum level of given file name */
 	nid_t i_xattr_nid;		/* node id that contains xattrs */
@@ -398,11 +449,11 @@ struct f2fs_inode_info {
 };
 
 static inline void get_extent_info(struct extent_info *ext,
-					struct f2fs_extent i_ext)
+					struct f2fs_extent *i_ext)
 {
-	ext->fofs = le32_to_cpu(i_ext.fofs);
-	ext->blk = le32_to_cpu(i_ext.blk);
-	ext->len = le32_to_cpu(i_ext.len);
+	ext->fofs = le32_to_cpu(i_ext->fofs);
+	ext->blk = le32_to_cpu(i_ext->blk);
+	ext->len = le32_to_cpu(i_ext->len);
 }
 
 static inline void set_raw_extent(struct extent_info *ext,
@@ -599,7 +650,6 @@ struct f2fs_sm_info {
  * dirty dentry blocks, dirty node blocks, and dirty meta blocks.
  */
 enum count_type {
-	F2FS_WRITEBACK,
 	F2FS_DIRTY_DENTS,
 	F2FS_DIRTY_DATA,
 	F2FS_DIRTY_NODES,
@@ -672,6 +722,7 @@ enum {
 	SBI_IS_CLOSE,				/* specify unmounting */
 	SBI_NEED_FSCK,				/* need fsck.f2fs to fix */
 	SBI_POR_DOING,				/* recovery is doing or not */
+	SBI_NEED_SB_WRITE,			/* need to recover superblock */
 };
 
 enum {
@@ -680,6 +731,10 @@ enum {
 	MAX_TIME,
 };
 
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+#define F2FS_KEY_DESC_PREFIX "f2fs:"
+#define F2FS_KEY_DESC_PREFIX_SIZE 5
+#endif
 struct f2fs_sb_info {
 	struct super_block *sb;			/* pointer to VFS super block */
 	struct proc_dir_entry *s_proc;		/* proc entry */
@@ -687,6 +742,10 @@ struct f2fs_sb_info {
 	int valid_super_block;			/* valid super block no */
 	int s_flag;				/* flags for sbi */
 
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+	u8 key_prefix[F2FS_KEY_DESC_PREFIX_SIZE];
+	u8 key_prefix_size;
+#endif
 	/* for node-related operations */
 	struct f2fs_nm_info *nm_info;		/* node manager */
 	struct inode *node_inode;		/* cache node blocks */
@@ -742,18 +801,24 @@ struct f2fs_sb_info {
 	unsigned int total_sections;		/* total section count */
 	unsigned int total_node_count;		/* total node block count */
 	unsigned int total_valid_node_count;	/* valid node block count */
-	unsigned int total_valid_inode_count;	/* valid inode count */
 	loff_t max_file_blocks;			/* max block index of file */
 	int active_logs;			/* # of active logs */
 	int dir_level;				/* directory level */
 
 	block_t user_block_count;		/* # of user blocks */
 	block_t total_valid_block_count;	/* # of valid blocks */
-	block_t alloc_valid_block_count;	/* # of allocated blocks */
 	block_t discard_blks;			/* discard command candidats */
 	block_t last_valid_block_count;		/* for recovery */
 	u32 s_next_generation;			/* for NFS support */
-	atomic_t nr_pages[NR_COUNT_TYPE];	/* # of pages, see count_type */
+	atomic_t nr_wb_bios;			/* # of writeback bios */
+
+	/* # of pages, see count_type */
+	struct percpu_counter nr_pages[NR_COUNT_TYPE];
+	/* # of allocated blocks */
+	struct percpu_counter alloc_valid_block_count;
+
+	/* valid inode count */
+	struct percpu_counter total_valid_inode_count;
 
 	struct f2fs_mount_info mount_opt;	/* mount options */
 
@@ -1055,21 +1120,33 @@ static inline bool f2fs_has_xattr_block(unsigned int ofs)
 }
 
 static inline bool inc_valid_block_count(struct f2fs_sb_info *sbi,
-				 struct inode *inode, blkcnt_t count)
+				 struct inode *inode, blkcnt_t *count)
 {
 	block_t	valid_block_count;
 
 	spin_lock(&sbi->stat_lock);
-	valid_block_count =
-		sbi->total_valid_block_count + (block_t)count;
-	if (unlikely(valid_block_count > sbi->user_block_count)) {
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	if (time_to_inject(FAULT_BLOCK)) {
 		spin_unlock(&sbi->stat_lock);
 		return false;
 	}
-	inode->i_blocks += count;
-	sbi->total_valid_block_count = valid_block_count;
-	sbi->alloc_valid_block_count += (block_t)count;
+#endif
+	valid_block_count =
+		sbi->total_valid_block_count + (block_t)(*count);
+	if (unlikely(valid_block_count > sbi->user_block_count)) {
+		*count = sbi->user_block_count - sbi->total_valid_block_count;
+		if (!*count) {
+			spin_unlock(&sbi->stat_lock);
+			return false;
+		}
+	}
+	/* *count can be recalculated */
+	inode->i_blocks += *count;
+	sbi->total_valid_block_count =
+		sbi->total_valid_block_count + (block_t)(*count);
 	spin_unlock(&sbi->stat_lock);
+
+	percpu_counter_add(&sbi->alloc_valid_block_count, (*count));
 	return true;
 }
 
@@ -1087,20 +1164,20 @@ static inline void dec_valid_block_count(struct f2fs_sb_info *sbi,
 
 static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type)
 {
-	atomic_inc(&sbi->nr_pages[count_type]);
+	percpu_counter_inc(&sbi->nr_pages[count_type]);
 	set_sbi_flag(sbi, SBI_IS_DIRTY);
 }
 
 static inline void inode_inc_dirty_pages(struct inode *inode)
 {
-	atomic_inc(&F2FS_I(inode)->dirty_pages);
+	percpu_counter_inc(&F2FS_I(inode)->dirty_pages);
 	inc_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ?
 				F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA);
 }
 
 static inline void dec_page_count(struct f2fs_sb_info *sbi, int count_type)
 {
-	atomic_dec(&sbi->nr_pages[count_type]);
+	percpu_counter_dec(&sbi->nr_pages[count_type]);
 }
 
 static inline void inode_dec_dirty_pages(struct inode *inode)
@@ -1109,26 +1186,28 @@ static inline void inode_dec_dirty_pages(struct inode *inode)
 			!S_ISLNK(inode->i_mode))
 		return;
 
-	atomic_dec(&F2FS_I(inode)->dirty_pages);
+	percpu_counter_dec(&F2FS_I(inode)->dirty_pages);
 	dec_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ?
 				F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA);
 }
 
-static inline int get_pages(struct f2fs_sb_info *sbi, int count_type)
+static inline s64 get_pages(struct f2fs_sb_info *sbi, int count_type)
 {
-	return atomic_read(&sbi->nr_pages[count_type]);
+	return percpu_counter_sum_positive(&sbi->nr_pages[count_type]);
 }
 
-static inline int get_dirty_pages(struct inode *inode)
+static inline s64 get_dirty_pages(struct inode *inode)
 {
-	return atomic_read(&F2FS_I(inode)->dirty_pages);
+	return percpu_counter_sum_positive(&F2FS_I(inode)->dirty_pages);
 }
 
 static inline int get_blocktype_secs(struct f2fs_sb_info *sbi, int block_type)
 {
 	unsigned int pages_per_sec = sbi->segs_per_sec * sbi->blocks_per_seg;
-	return ((get_pages(sbi, block_type) + pages_per_sec - 1)
-			>> sbi->log_blocks_per_seg) / sbi->segs_per_sec;
+	unsigned int segs = (get_pages(sbi, block_type) + pages_per_sec - 1) >>
+						sbi->log_blocks_per_seg;
+
+	return segs / sbi->segs_per_sec;
 }
 
 static inline block_t valid_user_blocks(struct f2fs_sb_info *sbi)
@@ -1217,11 +1296,11 @@ static inline bool inc_valid_node_count(struct f2fs_sb_info *sbi,
 	if (inode)
 		inode->i_blocks++;
 
-	sbi->alloc_valid_block_count++;
 	sbi->total_valid_node_count++;
 	sbi->total_valid_block_count++;
 	spin_unlock(&sbi->stat_lock);
 
+	percpu_counter_inc(&sbi->alloc_valid_block_count);
 	return true;
 }
 
@@ -1248,28 +1327,30 @@ static inline unsigned int valid_node_count(struct f2fs_sb_info *sbi)
 
 static inline void inc_valid_inode_count(struct f2fs_sb_info *sbi)
 {
-	spin_lock(&sbi->stat_lock);
-	f2fs_bug_on(sbi, sbi->total_valid_inode_count == sbi->total_node_count);
-	sbi->total_valid_inode_count++;
-	spin_unlock(&sbi->stat_lock);
+	percpu_counter_inc(&sbi->total_valid_inode_count);
 }
 
 static inline void dec_valid_inode_count(struct f2fs_sb_info *sbi)
 {
-	spin_lock(&sbi->stat_lock);
-	f2fs_bug_on(sbi, !sbi->total_valid_inode_count);
-	sbi->total_valid_inode_count--;
-	spin_unlock(&sbi->stat_lock);
+	percpu_counter_dec(&sbi->total_valid_inode_count);
 }
 
-static inline unsigned int valid_inode_count(struct f2fs_sb_info *sbi)
+static inline s64 valid_inode_count(struct f2fs_sb_info *sbi)
 {
-	return sbi->total_valid_inode_count;
+	return percpu_counter_sum_positive(&sbi->total_valid_inode_count);
 }
 
 static inline struct page *f2fs_grab_cache_page(struct address_space *mapping,
 						pgoff_t index, bool for_write)
 {
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	struct page *page = find_lock_page(mapping, index);
+	if (page)
+		return page;
+
+	if (time_to_inject(FAULT_PAGE_ALLOC))
+		return NULL;
+#endif
 	if (!for_write)
 		return grab_cache_page(mapping, index);
 	return grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS);
@@ -1435,7 +1516,6 @@ enum {
 	FI_NO_ALLOC,		/* should not allocate any blocks */
 	FI_FREE_NID,		/* free allocated nide */
 	FI_UPDATE_DIR,		/* should update inode block for consistency */
-	FI_DELAY_IPUT,		/* used for the recovery */
 	FI_NO_EXTENT,		/* not to use the extent cache */
 	FI_INLINE_XATTR,	/* used for inline xattr */
 	FI_INLINE_DATA,		/* used for inline data*/
@@ -1618,12 +1698,6 @@ static inline bool f2fs_cp_error(struct f2fs_sb_info *sbi)
 	return is_set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG);
 }
 
-static inline void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi)
-{
-	set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG);
-	sbi->sb->s_flags |= MS_RDONLY;
-}
-
 static inline bool is_dot_dotdot(const struct qstr *str)
 {
 	if (str->len == 1 && str->name[0] == '.')
@@ -1644,6 +1718,15 @@ static inline bool f2fs_may_extent_tree(struct inode *inode)
 	return S_ISREG(inode->i_mode);
 }
 
+static inline void *f2fs_kmalloc(size_t size, gfp_t flags)
+{
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	if (time_to_inject(FAULT_KMALLOC))
+		return NULL;
+#endif
+	return kmalloc(size, flags);
+}
+
 static inline void *f2fs_kvmalloc(size_t size, gfp_t flags)
 {
 	void *ret;
@@ -1710,7 +1793,7 @@ struct dentry *f2fs_get_parent(struct dentry *child);
  */
 extern unsigned char f2fs_filetype_table[F2FS_FT_MAX];
 void set_de_type(struct f2fs_dir_entry *, umode_t);
-
+unsigned char get_de_type(struct f2fs_dir_entry *);
 struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *,
 			f2fs_hash_t, int *, struct f2fs_dentry_ptr *);
 bool f2fs_fill_dentries(struct dir_context *, struct f2fs_dentry_ptr *,
@@ -1731,6 +1814,8 @@ void f2fs_set_link(struct inode *, struct f2fs_dir_entry *,
 int update_dent_inode(struct inode *, struct inode *, const struct qstr *);
 void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *,
 			const struct qstr *, f2fs_hash_t , unsigned int);
+int f2fs_add_regular_entry(struct inode *, const struct qstr *,
+						struct inode *, nid_t, umode_t);
 int __f2fs_add_link(struct inode *, const struct qstr *, struct inode *, nid_t,
 			umode_t);
 void f2fs_delete_entry(struct f2fs_dir_entry *, struct page *, struct inode *,
@@ -1781,7 +1866,10 @@ void ra_node_page(struct f2fs_sb_info *, nid_t);
 struct page *get_node_page(struct f2fs_sb_info *, pgoff_t);
 struct page *get_node_page_ra(struct page *, int);
 void sync_inode_page(struct dnode_of_data *);
-int sync_node_pages(struct f2fs_sb_info *, nid_t, struct writeback_control *);
+void move_node_page(struct page *, int);
+int fsync_node_pages(struct f2fs_sb_info *, nid_t, struct writeback_control *,
+								bool);
+int sync_node_pages(struct f2fs_sb_info *, struct writeback_control *);
 bool alloc_nid(struct f2fs_sb_info *, nid_t *);
 void alloc_nid_done(struct f2fs_sb_info *, nid_t);
 void alloc_nid_failed(struct f2fs_sb_info *, nid_t);
@@ -1843,6 +1931,7 @@ void destroy_segment_manager_caches(void);
 /*
  * checkpoint.c
  */
+void f2fs_stop_checkpoint(struct f2fs_sb_info *, bool);
 struct page *grab_meta_page(struct f2fs_sb_info *, pgoff_t);
 struct page *get_meta_page(struct f2fs_sb_info *, pgoff_t);
 struct page *get_tmp_page(struct f2fs_sb_info *, pgoff_t);
@@ -1852,7 +1941,7 @@ void ra_meta_pages_cond(struct f2fs_sb_info *, pgoff_t);
 long sync_meta_pages(struct f2fs_sb_info *, enum page_type, long);
 void add_ino_entry(struct f2fs_sb_info *, nid_t, int type);
 void remove_ino_entry(struct f2fs_sb_info *, nid_t, int type);
-void release_ino_entry(struct f2fs_sb_info *);
+void release_ino_entry(struct f2fs_sb_info *, bool);
 bool exist_written_data(struct f2fs_sb_info *, nid_t, int);
 int acquire_orphan_inode(struct f2fs_sb_info *);
 void release_orphan_inode(struct f2fs_sb_info *);
@@ -1861,7 +1950,6 @@ void remove_orphan_inode(struct f2fs_sb_info *, nid_t);
 int recover_orphan_inodes(struct f2fs_sb_info *);
 int get_valid_checkpoint(struct f2fs_sb_info *);
 void update_dirty_page(struct inode *, struct page *);
-void add_dirty_dir_inode(struct inode *);
 void remove_dirty_inode(struct inode *);
 int sync_dirty_inodes(struct f2fs_sb_info *, enum inode_type);
 int write_checkpoint(struct f2fs_sb_info *, struct cp_control *);
@@ -1880,6 +1968,7 @@ int f2fs_submit_page_bio(struct f2fs_io_info *);
 void f2fs_submit_page_mbio(struct f2fs_io_info *);
 void set_data_blkaddr(struct dnode_of_data *);
 void f2fs_update_data_blkaddr(struct dnode_of_data *, block_t);
+int reserve_new_blocks(struct dnode_of_data *, blkcnt_t);
 int reserve_new_block(struct dnode_of_data *);
 int f2fs_get_block(struct dnode_of_data *, pgoff_t);
 ssize_t f2fs_preallocate_blocks(struct kiocb *, struct iov_iter *);
@@ -1906,7 +1995,7 @@ void build_gc_manager(struct f2fs_sb_info *);
 /*
  * recovery.c
  */
-int recover_fsync_data(struct f2fs_sb_info *);
+int recover_fsync_data(struct f2fs_sb_info *, bool);
 bool space_for_roll_forward(struct f2fs_sb_info *);
 
 /*
@@ -1921,12 +2010,12 @@ struct f2fs_stat_info {
 	unsigned long long hit_largest, hit_cached, hit_rbtree;
 	unsigned long long hit_total, total_ext;
 	int ext_tree, zombie_tree, ext_node;
-	int ndirty_node, ndirty_meta;
-	int ndirty_dent, ndirty_dirs, ndirty_data, ndirty_files;
+	s64 ndirty_node, ndirty_dent, ndirty_meta, ndirty_data, inmem_pages;
+	unsigned int ndirty_dirs, ndirty_files;
 	int nats, dirty_nats, sits, dirty_sits, fnids;
 	int total_count, utilization;
-	int bg_gc, inmem_pages, wb_pages;
-	int inline_xattr, inline_inode, inline_dir;
+	int bg_gc, wb_bios;
+	int inline_xattr, inline_inode, inline_dir, orphans;
 	unsigned int valid_count, valid_node_count, valid_inode_count;
 	unsigned int bimodal, avg_vblocks;
 	int util_free, util_valid, util_invalid;

fs/f2fs/file.c

@@ -182,7 +182,8 @@ static void try_to_fix_pino(struct inode *inode)
 	}
 }
 
-int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
+static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
+						int datasync, bool atomic)
 {
 	struct inode *inode = file->f_mapping->host;
 	struct f2fs_inode_info *fi = F2FS_I(inode);
@@ -256,7 +257,9 @@ go_write:
 		goto out;
 	}
 sync_nodes:
-	sync_node_pages(sbi, ino, &wbc);
+	ret = fsync_node_pages(sbi, ino, &wbc, atomic);
+	if (ret)
+		goto out;
 
 	/* if cp_error was enabled, we should avoid infinite loop */
 	if (unlikely(f2fs_cp_error(sbi))) {
@@ -288,6 +291,11 @@ out:
 	return ret;
 }
 
+int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
+{
+	return f2fs_do_sync_file(file, start, end, datasync, false);
+}
+
 static pgoff_t __get_first_dirty_index(struct address_space *mapping,
 						pgoff_t pgofs, int whence)
 {
@@ -555,6 +563,9 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock)
 
 	free_from = (pgoff_t)F2FS_BYTES_TO_BLK(from + blocksize - 1);
 
+	if (free_from >= sbi->max_file_blocks)
+		goto free_partial;
+
 	if (lock)
 		f2fs_lock_op(sbi);
 
@@ -573,7 +584,7 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock)
 	}
 
 	set_new_dnode(&dn, inode, ipage, NULL, 0);
-	err = get_dnode_of_data(&dn, free_from, LOOKUP_NODE);
+	err = get_dnode_of_data(&dn, free_from, LOOKUP_NODE_RA);
 	if (err) {
 		if (err == -ENOENT)
 			goto free_next;
@@ -596,7 +607,7 @@ free_next:
 out:
 	if (lock)
 		f2fs_unlock_op(sbi);
-
+free_partial:
 	/* lastly zero out the first data page */
 	if (!err)
 		err = truncate_partial_data_page(inode, from, truncate_page);
@@ -986,6 +997,49 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 	return ret;
 }
 
+static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start,
+								pgoff_t end)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
+	pgoff_t index = start;
+	unsigned int ofs_in_node = dn->ofs_in_node;
+	blkcnt_t count = 0;
+	int ret;
+
+	for (; index < end; index++, dn->ofs_in_node++) {
+		if (datablock_addr(dn->node_page, dn->ofs_in_node) == NULL_ADDR)
+			count++;
+	}
+
+	dn->ofs_in_node = ofs_in_node;
+	ret = reserve_new_blocks(dn, count);
+	if (ret)
+		return ret;
+
+	dn->ofs_in_node = ofs_in_node;
+	for (index = start; index < end; index++, dn->ofs_in_node++) {
+		dn->data_blkaddr =
+				datablock_addr(dn->node_page, dn->ofs_in_node);
+		/*
+		 * reserve_new_blocks will not guarantee entire block
+		 * allocation.
+		 */
+		if (dn->data_blkaddr == NULL_ADDR) {
+			ret = -ENOSPC;
+			break;
+		}
+		if (dn->data_blkaddr != NEW_ADDR) {
+			invalidate_blocks(sbi, dn->data_blkaddr);
+			dn->data_blkaddr = NEW_ADDR;
+			set_data_blkaddr(dn);
+		}
+	}
+
+	f2fs_update_extent_cache_range(dn, start, 0, index - start);
+
+	return ret;
+}
+
 static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
 								int mode)
 {
@@ -1036,35 +1090,32 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
 					(loff_t)pg_start << PAGE_SHIFT);
 		}
 
-		for (index = pg_start; index < pg_end; index++) {
+		for (index = pg_start; index < pg_end;) {
 			struct dnode_of_data dn;
-			struct page *ipage;
+			unsigned int end_offset;
+			pgoff_t end;
 
 			f2fs_lock_op(sbi);
 
-			ipage = get_node_page(sbi, inode->i_ino);
-			if (IS_ERR(ipage)) {
-				ret = PTR_ERR(ipage);
-				f2fs_unlock_op(sbi);
-				goto out;
-			}
-
-			set_new_dnode(&dn, inode, ipage, NULL, 0);
-			ret = f2fs_reserve_block(&dn, index);
+			set_new_dnode(&dn, inode, NULL, NULL, 0);
+			ret = get_dnode_of_data(&dn, index, ALLOC_NODE);
 			if (ret) {
 				f2fs_unlock_op(sbi);
 				goto out;
 			}
 
-			if (dn.data_blkaddr != NEW_ADDR) {
-				invalidate_blocks(sbi, dn.data_blkaddr);
-				f2fs_update_data_blkaddr(&dn, NEW_ADDR);
-			}
+			end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
+			end = min(pg_end, end_offset - dn.ofs_in_node + index);
+
+			ret = f2fs_do_zero_range(&dn, index, end);
 			f2fs_put_dnode(&dn);
 			f2fs_unlock_op(sbi);
+			if (ret)
+				goto out;
 
+			index = end;
 			new_size = max_t(loff_t, new_size,
-				(loff_t)(index + 1) << PAGE_SHIFT);
+					(loff_t)index << PAGE_SHIFT);
 		}
 
 		if (off_end) {
@@ -1147,10 +1198,11 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
 					loff_t len, int mode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	pgoff_t index, pg_start, pg_end;
+	struct f2fs_map_blocks map = { .m_next_pgofs = NULL };
+	pgoff_t pg_end;
 	loff_t new_size = i_size_read(inode);
-	loff_t off_start, off_end;
-	int ret = 0;
+	loff_t off_end;
+	int ret;
 
 	ret = inode_newsize_ok(inode, (len + offset));
 	if (ret)
@@ -1162,43 +1214,35 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
 
 	f2fs_balance_fs(sbi, true);
 
-	pg_start = ((unsigned long long) offset) >> PAGE_SHIFT;
-	pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT;
-
-	off_start = offset & (PAGE_SIZE - 1);
+	pg_end = ((unsigned long long)offset + len) >> PAGE_SHIFT;
 	off_end = (offset + len) & (PAGE_SIZE - 1);
 
-	f2fs_lock_op(sbi);
+	map.m_lblk = ((unsigned long long)offset) >> PAGE_SHIFT;
+	map.m_len = pg_end - map.m_lblk;
+	if (off_end)
+		map.m_len++;
 
-	for (index = pg_start; index <= pg_end; index++) {
-		struct dnode_of_data dn;
+	ret = f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_AIO);
+	if (ret) {
+		pgoff_t last_off;
 
-		if (index == pg_end && !off_end)
-			goto noalloc;
+		if (!map.m_len)
+			return ret;
 
-		set_new_dnode(&dn, inode, NULL, NULL, 0);
-		ret = f2fs_reserve_block(&dn, index);
-		if (ret)
-			break;
-noalloc:
-		if (pg_start == pg_end)
-			new_size = offset + len;
-		else if (index == pg_start && off_start)
-			new_size = (loff_t)(index + 1) << PAGE_SHIFT;
-		else if (index == pg_end)
-			new_size = ((loff_t)index << PAGE_SHIFT) +
-								off_end;
-		else
-			new_size += PAGE_SIZE;
+		last_off = map.m_lblk + map.m_len - 1;
+
+		/* update new size to the failed position */
+		new_size = (last_off == pg_end) ? offset + len:
+					(loff_t)(last_off + 1) << PAGE_SHIFT;
+	} else {
+		new_size = ((loff_t)pg_end << PAGE_SHIFT) + off_end;
 	}
 
-	if (!(mode & FALLOC_FL_KEEP_SIZE) &&
-		i_size_read(inode) < new_size) {
+	if (!(mode & FALLOC_FL_KEEP_SIZE) && i_size_read(inode) < new_size) {
 		i_size_write(inode, new_size);
 		mark_inode_dirty(inode);
 		update_inode_page(inode);
 	}
-	f2fs_unlock_op(sbi);
 
 	return ret;
 }
@@ -1254,10 +1298,19 @@ out:
 
 static int f2fs_release_file(struct inode *inode, struct file *filp)
 {
+	/*
+	 * f2fs_relase_file is called at every close calls. So we should
+	 * not drop any inmemory pages by close called by other process.
+	 */
+	if (!(filp->f_mode & FMODE_WRITE) ||
+			atomic_read(&inode->i_writecount) != 1)
+		return 0;
+
 	/* some remained atomic pages should discarded */
 	if (f2fs_is_atomic_file(inode))
 		drop_inmem_pages(inode);
 	if (f2fs_is_volatile_file(inode)) {
+		clear_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
 		set_inode_flag(F2FS_I(inode), FI_DROP_CACHE);
 		filemap_fdatawrite(inode->i_mapping);
 		clear_inode_flag(F2FS_I(inode), FI_DROP_CACHE);
@@ -1294,20 +1347,16 @@ static int f2fs_ioc_setflags(struct file *filp, unsigned long arg)
 	unsigned int oldflags;
 	int ret;
 
+	if (!inode_owner_or_capable(inode))
+		return -EACCES;
+
+	if (get_user(flags, (int __user *)arg))
+		return -EFAULT;
+
 	ret = mnt_want_write_file(filp);
 	if (ret)
 		return ret;
 
-	if (!inode_owner_or_capable(inode)) {
-		ret = -EACCES;
-		goto out;
-	}
-
-	if (get_user(flags, (int __user *)arg)) {
-		ret = -EFAULT;
-		goto out;
-	}
-
 	flags = f2fs_mask_flags(inode->i_mode, flags);
 
 	inode_lock(inode);
@@ -1350,17 +1399,35 @@ static int f2fs_ioc_start_atomic_write(struct file *filp)
 	if (!inode_owner_or_capable(inode))
 		return -EACCES;
 
+	ret = mnt_want_write_file(filp);
+	if (ret)
+		return ret;
+
+	inode_lock(inode);
+
 	if (f2fs_is_atomic_file(inode))
-		return 0;
+		goto out;
 
 	ret = f2fs_convert_inline_inode(inode);
 	if (ret)
-		return ret;
+		goto out;
 
 	set_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
 	f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
 
-	return 0;
+	if (!get_dirty_pages(inode))
+		goto out;
+
+	f2fs_msg(F2FS_I_SB(inode)->sb, KERN_WARNING,
+		"Unexpected flush for atomic writes: ino=%lu, npages=%lld",
+					inode->i_ino, get_dirty_pages(inode));
+	ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX);
+	if (ret)
+		clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
+out:
+	inode_unlock(inode);
+	mnt_drop_write_file(filp);
+	return ret;
 }
 
 static int f2fs_ioc_commit_atomic_write(struct file *filp)
@@ -1371,13 +1438,15 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp)
 	if (!inode_owner_or_capable(inode))
 		return -EACCES;
 
-	if (f2fs_is_volatile_file(inode))
-		return 0;
-
 	ret = mnt_want_write_file(filp);
 	if (ret)
 		return ret;
 
+	inode_lock(inode);
+
+	if (f2fs_is_volatile_file(inode))
+		goto err_out;
+
 	if (f2fs_is_atomic_file(inode)) {
 		clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
 		ret = commit_inmem_pages(inode);
@@ -1387,8 +1456,9 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp)
 		}
 	}
 
-	ret = f2fs_sync_file(filp, 0, LLONG_MAX, 0);
+	ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
 err_out:
+	inode_unlock(inode);
 	mnt_drop_write_file(filp);
 	return ret;
 }
@@ -1401,32 +1471,54 @@ static int f2fs_ioc_start_volatile_write(struct file *filp)
 	if (!inode_owner_or_capable(inode))
 		return -EACCES;
 
+	ret = mnt_want_write_file(filp);
+	if (ret)
+		return ret;
+
+	inode_lock(inode);
+
 	if (f2fs_is_volatile_file(inode))
-		return 0;
+		goto out;
 
 	ret = f2fs_convert_inline_inode(inode);
 	if (ret)
-		return ret;
+		goto out;
 
 	set_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
 	f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
-	return 0;
+out:
+	inode_unlock(inode);
+	mnt_drop_write_file(filp);
+	return ret;
 }
 
 static int f2fs_ioc_release_volatile_write(struct file *filp)
 {
 	struct inode *inode = file_inode(filp);
+	int ret;
 
 	if (!inode_owner_or_capable(inode))
 		return -EACCES;
 
+	ret = mnt_want_write_file(filp);
+	if (ret)
+		return ret;
+
+	inode_lock(inode);
+
 	if (!f2fs_is_volatile_file(inode))
-		return 0;
+		goto out;
 
-	if (!f2fs_is_first_block_written(inode))
-		return truncate_partial_data_page(inode, 0, true);
+	if (!f2fs_is_first_block_written(inode)) {
+		ret = truncate_partial_data_page(inode, 0, true);
+		goto out;
+	}
 
-	return punch_hole(inode, 0, F2FS_BLKSIZE);
+	ret = punch_hole(inode, 0, F2FS_BLKSIZE);
+out:
+	inode_unlock(inode);
+	mnt_drop_write_file(filp);
+	return ret;
 }
 
 static int f2fs_ioc_abort_volatile_write(struct file *filp)
@@ -1441,15 +1533,17 @@ static int f2fs_ioc_abort_volatile_write(struct file *filp)
 	if (ret)
 		return ret;
 
-	if (f2fs_is_atomic_file(inode)) {
-		clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
+	inode_lock(inode);
+
+	if (f2fs_is_atomic_file(inode))
 		drop_inmem_pages(inode);
-	}
 	if (f2fs_is_volatile_file(inode)) {
 		clear_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
-		ret = f2fs_sync_file(filp, 0, LLONG_MAX, 0);
+		ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
 	}
 
+	inode_unlock(inode);
+
 	mnt_drop_write_file(filp);
 	f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
 	return ret;
@@ -1461,6 +1555,7 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct super_block *sb = sbi->sb;
 	__u32 in;
+	int ret;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -1468,31 +1563,38 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
 	if (get_user(in, (__u32 __user *)arg))
 		return -EFAULT;
 
+	ret = mnt_want_write_file(filp);
+	if (ret)
+		return ret;
+
 	switch (in) {
 	case F2FS_GOING_DOWN_FULLSYNC:
 		sb = freeze_bdev(sb->s_bdev);
 		if (sb && !IS_ERR(sb)) {
-			f2fs_stop_checkpoint(sbi);
+			f2fs_stop_checkpoint(sbi, false);
 			thaw_bdev(sb->s_bdev, sb);
 		}
 		break;
 	case F2FS_GOING_DOWN_METASYNC:
 		/* do checkpoint only */
 		f2fs_sync_fs(sb, 1);
-		f2fs_stop_checkpoint(sbi);
+		f2fs_stop_checkpoint(sbi, false);
 		break;
 	case F2FS_GOING_DOWN_NOSYNC:
-		f2fs_stop_checkpoint(sbi);
+		f2fs_stop_checkpoint(sbi, false);
 		break;
 	case F2FS_GOING_DOWN_METAFLUSH:
 		sync_meta_pages(sbi, META, LONG_MAX);
-		f2fs_stop_checkpoint(sbi);
+		f2fs_stop_checkpoint(sbi, false);
 		break;
 	default:
-		return -EINVAL;
+		ret = -EINVAL;
+		goto out;
 	}
 	f2fs_update_time(sbi, REQ_TIME);
-	return 0;
+out:
+	mnt_drop_write_file(filp);
+	return ret;
 }
 
 static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg)
@@ -1513,9 +1615,14 @@ static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg)
 				sizeof(range)))
 		return -EFAULT;
 
+	ret = mnt_want_write_file(filp);
+	if (ret)
+		return ret;
+
 	range.minlen = max((unsigned int)range.minlen,
 				q->limits.discard_granularity);
 	ret = f2fs_trim_fs(F2FS_SB(sb), &range);
+	mnt_drop_write_file(filp);
 	if (ret < 0)
 		return ret;
 
@@ -1540,13 +1647,21 @@ static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg)
 {
 	struct fscrypt_policy policy;
 	struct inode *inode = file_inode(filp);
+	int ret;
 
 	if (copy_from_user(&policy, (struct fscrypt_policy __user *)arg,
 							sizeof(policy)))
 		return -EFAULT;
 
+	ret = mnt_want_write_file(filp);
+	if (ret)
+		return ret;
+
 	f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
-	return fscrypt_process_policy(inode, &policy);
+	ret = fscrypt_process_policy(inode, &policy);
+
+	mnt_drop_write_file(filp);
+	return ret;
 }
 
 static int f2fs_ioc_get_encryption_policy(struct file *filp, unsigned long arg)
@@ -1603,6 +1718,7 @@ static int f2fs_ioc_gc(struct file *filp, unsigned long arg)
 	struct inode *inode = file_inode(filp);
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	__u32 sync;
+	int ret;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -1613,20 +1729,30 @@ static int f2fs_ioc_gc(struct file *filp, unsigned long arg)
 	if (f2fs_readonly(sbi->sb))
 		return -EROFS;
 
+	ret = mnt_want_write_file(filp);
+	if (ret)
+		return ret;
+
 	if (!sync) {
-		if (!mutex_trylock(&sbi->gc_mutex))
-			return -EBUSY;
+		if (!mutex_trylock(&sbi->gc_mutex)) {
+			ret = -EBUSY;
+			goto out;
+		}
 	} else {
 		mutex_lock(&sbi->gc_mutex);
 	}
 
-	return f2fs_gc(sbi, sync);
+	ret = f2fs_gc(sbi, sync);
+out:
+	mnt_drop_write_file(filp);
+	return ret;
 }
 
 static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	int ret;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -1634,7 +1760,14 @@ static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg)
 	if (f2fs_readonly(sbi->sb))
 		return -EROFS;
 
-	return f2fs_sync_fs(sbi->sb, 1);
+	ret = mnt_want_write_file(filp);
+	if (ret)
+		return ret;
+
+	ret = f2fs_sync_fs(sbi->sb, 1);
+
+	mnt_drop_write_file(filp);
+	return ret;
 }
 
 static int f2fs_defragment_range(struct f2fs_sb_info *sbi,

fs/f2fs/gc.c

@@ -96,7 +96,7 @@ int start_gc_thread(struct f2fs_sb_info *sbi)
 	dev_t dev = sbi->sb->s_bdev->bd_dev;
 	int err = 0;
 
-	gc_th = kmalloc(sizeof(struct f2fs_gc_kthread), GFP_KERNEL);
+	gc_th = f2fs_kmalloc(sizeof(struct f2fs_gc_kthread), GFP_KERNEL);
 	if (!gc_th) {
 		err = -ENOMEM;
 		goto out;
@@ -465,15 +465,7 @@ next_step:
 			continue;
 		}
 
-		/* set page dirty and write it */
-		if (gc_type == FG_GC) {
-			f2fs_wait_on_page_writeback(node_page, NODE, true);
-			set_page_dirty(node_page);
-		} else {
-			if (!PageWriteback(node_page))
-				set_page_dirty(node_page);
-		}
-		f2fs_put_page(node_page, 1);
+		move_node_page(node_page, gc_type);
 		stat_inc_node_blk_count(sbi, 1, gc_type);
 	}
 
@@ -834,18 +826,9 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi,
 		f2fs_put_page(sum_page, 0);
 	}
 
-	if (gc_type == FG_GC) {
-		if (type == SUM_TYPE_NODE) {
-			struct writeback_control wbc = {
-				.sync_mode = WB_SYNC_ALL,
-				.nr_to_write = LONG_MAX,
-				.for_reclaim = 0,
-			};
-			sync_node_pages(sbi, 0, &wbc);
-		} else {
-			f2fs_submit_merged_bio(sbi, DATA, WRITE);
-		}
-	}
+	if (gc_type == FG_GC)
+		f2fs_submit_merged_bio(sbi,
+				(type == SUM_TYPE_NODE) ? NODE : DATA, WRITE);
 
 	blk_finish_plug(&plug);
 

fs/f2fs/inline.c

@@ -161,7 +161,7 @@ int f2fs_convert_inline_inode(struct inode *inode)
 	if (!f2fs_has_inline_data(inode))
 		return 0;
 
-	page = grab_cache_page(inode->i_mapping, 0);
+	page = f2fs_grab_cache_page(inode->i_mapping, 0, false);
 	if (!page)
 		return -ENOMEM;
 
@@ -303,11 +303,6 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
 	else
 		f2fs_put_page(ipage, 0);
 
-	/*
-	 * For the most part, it should be a bug when name_len is zero.
-	 * We stop here for figuring out where the bugs has occurred.
-	 */
-	f2fs_bug_on(sbi, d.max < 0);
 	return de;
 }
 
@@ -355,7 +350,7 @@ int make_empty_inline_dir(struct inode *inode, struct inode *parent,
  * NOTE: ipage is grabbed by caller, but if any error occurs, we should
  * release ipage in this function.
  */
-static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
+static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage,
 				struct f2fs_inline_dentry *inline_dentry)
 {
 	struct page *page;
@@ -363,7 +358,7 @@ static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
 	struct f2fs_dentry_block *dentry_blk;
 	int err;
 
-	page = grab_cache_page(dir->i_mapping, 0);
+	page = f2fs_grab_cache_page(dir->i_mapping, 0, false);
 	if (!page) {
 		f2fs_put_page(ipage, 1);
 		return -ENOMEM;
@@ -405,6 +400,7 @@ static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
 	stat_dec_inline_dir(dir);
 	clear_inode_flag(F2FS_I(dir), FI_INLINE_DENTRY);
 
+	F2FS_I(dir)->i_current_depth = 1;
 	if (i_size_read(dir) < PAGE_SIZE) {
 		i_size_write(dir, PAGE_SIZE);
 		set_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
@@ -416,6 +412,105 @@ out:
 	return err;
 }
 
+static int f2fs_add_inline_entries(struct inode *dir,
+			struct f2fs_inline_dentry *inline_dentry)
+{
+	struct f2fs_dentry_ptr d;
+	unsigned long bit_pos = 0;
+	int err = 0;
+
+	make_dentry_ptr(NULL, &d, (void *)inline_dentry, 2);
+
+	while (bit_pos < d.max) {
+		struct f2fs_dir_entry *de;
+		struct qstr new_name;
+		nid_t ino;
+		umode_t fake_mode;
+
+		if (!test_bit_le(bit_pos, d.bitmap)) {
+			bit_pos++;
+			continue;
+		}
+
+		de = &d.dentry[bit_pos];
+
+		if (unlikely(!de->name_len)) {
+			bit_pos++;
+			continue;
+		}
+
+		new_name.name = d.filename[bit_pos];
+		new_name.len = de->name_len;
+
+		ino = le32_to_cpu(de->ino);
+		fake_mode = get_de_type(de) << S_SHIFT;
+
+		err = f2fs_add_regular_entry(dir, &new_name, NULL,
+							ino, fake_mode);
+		if (err)
+			goto punch_dentry_pages;
+
+		bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
+	}
+	return 0;
+punch_dentry_pages:
+	truncate_inode_pages(&dir->i_data, 0);
+	truncate_blocks(dir, 0, false);
+	remove_dirty_inode(dir);
+	return err;
+}
+
+static int f2fs_move_rehashed_dirents(struct inode *dir, struct page *ipage,
+				struct f2fs_inline_dentry *inline_dentry)
+{
+	struct f2fs_inline_dentry *backup_dentry;
+	struct f2fs_inode_info *fi = F2FS_I(dir);
+	int err;
+
+	backup_dentry = f2fs_kmalloc(sizeof(struct f2fs_inline_dentry),
+							GFP_F2FS_ZERO);
+	if (!backup_dentry) {
+		f2fs_put_page(ipage, 1);
+		return -ENOMEM;
+	}
+
+	memcpy(backup_dentry, inline_dentry, MAX_INLINE_DATA);
+	truncate_inline_inode(ipage, 0);
+
+	unlock_page(ipage);
+
+	err = f2fs_add_inline_entries(dir, backup_dentry);
+	if (err)
+		goto recover;
+
+	lock_page(ipage);
+
+	stat_dec_inline_dir(dir);
+	clear_inode_flag(fi, FI_INLINE_DENTRY);
+	update_inode(dir, ipage);
+	kfree(backup_dentry);
+	return 0;
+recover:
+	lock_page(ipage);
+	memcpy(inline_dentry, backup_dentry, MAX_INLINE_DATA);
+	fi->i_current_depth = 0;
+	i_size_write(dir, MAX_INLINE_DATA);
+	update_inode(dir, ipage);
+	f2fs_put_page(ipage, 1);
+
+	kfree(backup_dentry);
+	return err;
+}
+
+static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
+				struct f2fs_inline_dentry *inline_dentry)
+{
+	if (!F2FS_I(dir)->i_dir_level)
+		return f2fs_move_inline_dirents(dir, ipage, inline_dentry);
+	else
+		return f2fs_move_rehashed_dirents(dir, ipage, inline_dentry);
+}
+
 int f2fs_add_inline_entry(struct inode *dir, const struct qstr *name,
 			struct inode *inode, nid_t ino, umode_t mode)
 {

fs/f2fs/inode.c

@@ -283,7 +283,7 @@ retry:
 			cond_resched();
 			goto retry;
 		} else if (err != -ENOENT) {
-			f2fs_stop_checkpoint(sbi);
+			f2fs_stop_checkpoint(sbi, false);
 		}
 		return 0;
 	}
@@ -344,7 +344,7 @@ void f2fs_evict_inode(struct inode *inode)
 	sb_start_intwrite(inode->i_sb);
 	set_inode_flag(fi, FI_NO_ALLOC);
 	i_size_write(inode, 0);
-
+retry:
 	if (F2FS_HAS_BLOCKS(inode))
 		err = f2fs_truncate(inode, true);
 
@@ -354,6 +354,12 @@ void f2fs_evict_inode(struct inode *inode)
 		f2fs_unlock_op(sbi);
 	}
 
+	/* give more chances, if ENOMEM case */
+	if (err == -ENOMEM) {
+		err = 0;
+		goto retry;
+	}
+
 	sb_end_intwrite(inode->i_sb);
 no_delete:
 	stat_dec_inline_xattr(inode);
@@ -368,26 +374,11 @@ no_delete:
 	if (is_inode_flag_set(fi, FI_UPDATE_WRITE))
 		add_ino_entry(sbi, inode->i_ino, UPDATE_INO);
 	if (is_inode_flag_set(fi, FI_FREE_NID)) {
-		if (err && err != -ENOENT)
-			alloc_nid_done(sbi, inode->i_ino);
-		else
-			alloc_nid_failed(sbi, inode->i_ino);
+		alloc_nid_failed(sbi, inode->i_ino);
 		clear_inode_flag(fi, FI_FREE_NID);
 	}
-
-	if (err && err != -ENOENT) {
-		if (!exist_written_data(sbi, inode->i_ino, ORPHAN_INO)) {
-			/*
-			 * get here because we failed to release resource
-			 * of inode previously, reminder our user to run fsck
-			 * for fixing.
-			 */
-			set_sbi_flag(sbi, SBI_NEED_FSCK);
-			f2fs_msg(sbi->sb, KERN_WARNING,
-				"inode (ino:%lu) resource leak, run fsck "
-				"to fix this issue!", inode->i_ino);
-		}
-	}
+	f2fs_bug_on(sbi, err &&
+		!exist_written_data(sbi, inode->i_ino, ORPHAN_INO));
 out_clear:
 	fscrypt_put_encryption_info(inode, NULL);
 	clear_inode(inode);
@@ -397,37 +388,32 @@ out_clear:
 void handle_failed_inode(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	int err = 0;
+	struct node_info ni;
 
-	clear_nlink(inode);
-	make_bad_inode(inode);
+	/* don't make bad inode, since it becomes a regular file. */
 	unlock_new_inode(inode);
 
-	i_size_write(inode, 0);
-	if (F2FS_HAS_BLOCKS(inode))
-		err = f2fs_truncate(inode, false);
-
-	if (!err)
-		err = remove_inode_page(inode);
-
 	/*
-	 * if we skip truncate_node in remove_inode_page bacause we failed
-	 * before, it's better to find another way to release resource of
-	 * this inode (e.g. valid block count, node block or nid). Here we
-	 * choose to add this inode to orphan list, so that we can call iput
-	 * for releasing in orphan recovery flow.
-	 *
 	 * Note: we should add inode to orphan list before f2fs_unlock_op()
 	 * so we can prevent losing this orphan when encoutering checkpoint
 	 * and following suddenly power-off.
 	 */
-	if (err && err != -ENOENT) {
-		err = acquire_orphan_inode(sbi);
-		if (!err)
+	get_node_info(sbi, inode->i_ino, &ni);
+
+	if (ni.blk_addr != NULL_ADDR) {
+		int err = acquire_orphan_inode(sbi);
+		if (err) {
+			set_sbi_flag(sbi, SBI_NEED_FSCK);
+			f2fs_msg(sbi->sb, KERN_WARNING,
+				"Too many orphan inodes, run fsck to fix.");
+		} else {
 			add_orphan_inode(sbi, inode->i_ino);
+		}
+		alloc_nid_done(sbi, inode->i_ino);
+	} else {
+		set_inode_flag(F2FS_I(inode), FI_FREE_NID);
 	}
 
-	set_inode_flag(F2FS_I(inode), FI_FREE_NID);
 	f2fs_unlock_op(sbi);
 
 	/* iput will drop the inode object */

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;
 

fs/f2fs/recovery.c

@@ -49,8 +49,9 @@ static struct kmem_cache *fsync_entry_slab;
 
 bool space_for_roll_forward(struct f2fs_sb_info *sbi)
 {
-	if (sbi->last_valid_block_count + sbi->alloc_valid_block_count
-			> sbi->user_block_count)
+	s64 nalloc = percpu_counter_sum_positive(&sbi->alloc_valid_block_count);
+
+	if (sbi->last_valid_block_count + nalloc > sbi->user_block_count)
 		return false;
 	return true;
 }
@@ -67,7 +68,30 @@ static struct fsync_inode_entry *get_fsync_inode(struct list_head *head,
 	return NULL;
 }
 
-static int recover_dentry(struct inode *inode, struct page *ipage)
+static struct fsync_inode_entry *add_fsync_inode(struct list_head *head,
+							struct inode *inode)
+{
+	struct fsync_inode_entry *entry;
+
+	entry = kmem_cache_alloc(fsync_entry_slab, GFP_F2FS_ZERO);
+	if (!entry)
+		return NULL;
+
+	entry->inode = inode;
+	list_add_tail(&entry->list, head);
+
+	return entry;
+}
+
+static void del_fsync_inode(struct fsync_inode_entry *entry)
+{
+	iput(entry->inode);
+	list_del(&entry->list);
+	kmem_cache_free(fsync_entry_slab, entry);
+}
+
+static int recover_dentry(struct inode *inode, struct page *ipage,
+						struct list_head *dir_list)
 {
 	struct f2fs_inode *raw_inode = F2FS_INODE(ipage);
 	nid_t pino = le32_to_cpu(raw_inode->i_pino);
@@ -75,18 +99,29 @@ static int recover_dentry(struct inode *inode, struct page *ipage)
 	struct qstr name;
 	struct page *page;
 	struct inode *dir, *einode;
+	struct fsync_inode_entry *entry;
 	int err = 0;
 
-	dir = f2fs_iget(inode->i_sb, pino);
-	if (IS_ERR(dir)) {
-		err = PTR_ERR(dir);
-		goto out;
+	entry = get_fsync_inode(dir_list, pino);
+	if (!entry) {
+		dir = f2fs_iget(inode->i_sb, pino);
+		if (IS_ERR(dir)) {
+			err = PTR_ERR(dir);
+			goto out;
+		}
+
+		entry = add_fsync_inode(dir_list, dir);
+		if (!entry) {
+			err = -ENOMEM;
+			iput(dir);
+			goto out;
+		}
 	}
 
-	if (file_enc_name(inode)) {
-		iput(dir);
+	dir = entry->inode;
+
+	if (file_enc_name(inode))
 		return 0;
-	}
 
 	name.len = le32_to_cpu(raw_inode->i_namelen);
 	name.name = raw_inode->i_name;
@@ -94,7 +129,7 @@ static int recover_dentry(struct inode *inode, struct page *ipage)
 	if (unlikely(name.len > F2FS_NAME_LEN)) {
 		WARN_ON(1);
 		err = -ENAMETOOLONG;
-		goto out_err;
+		goto out;
 	}
 retry:
 	de = f2fs_find_entry(dir, &name, &page);
@@ -120,23 +155,12 @@ retry:
 		goto retry;
 	}
 	err = __f2fs_add_link(dir, &name, inode, inode->i_ino, inode->i_mode);
-	if (err)
-		goto out_err;
-
-	if (is_inode_flag_set(F2FS_I(dir), FI_DELAY_IPUT)) {
-		iput(dir);
-	} else {
-		add_dirty_dir_inode(dir);
-		set_inode_flag(F2FS_I(dir), FI_DELAY_IPUT);
-	}
 
 	goto out;
 
 out_unmap_put:
 	f2fs_dentry_kunmap(dir, page);
 	f2fs_put_page(page, 0);
-out_err:
-	iput(dir);
 out:
 	f2fs_msg(inode->i_sb, KERN_NOTICE,
 			"%s: ino = %x, name = %s, dir = %lx, err = %d",
@@ -198,6 +222,7 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
 {
 	unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi));
 	struct curseg_info *curseg;
+	struct inode *inode;
 	struct page *page = NULL;
 	block_t blkaddr;
 	int err = 0;
@@ -206,8 +231,6 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
 	curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
 	blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
 
-	ra_meta_pages(sbi, blkaddr, 1, META_POR, true);
-
 	while (1) {
 		struct fsync_inode_entry *entry;
 
@@ -233,35 +256,32 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
 					break;
 			}
 
-			/* add this fsync inode to the list */
-			entry = kmem_cache_alloc(fsync_entry_slab, GFP_F2FS_ZERO);
-			if (!entry) {
-				err = -ENOMEM;
-				break;
-			}
 			/*
 			 * CP | dnode(F) | inode(DF)
 			 * For this case, we should not give up now.
 			 */
-			entry->inode = f2fs_iget(sbi->sb, ino_of_node(page));
-			if (IS_ERR(entry->inode)) {
-				err = PTR_ERR(entry->inode);
-				kmem_cache_free(fsync_entry_slab, entry);
+			inode = f2fs_iget(sbi->sb, ino_of_node(page));
+			if (IS_ERR(inode)) {
+				err = PTR_ERR(inode);
 				if (err == -ENOENT) {
 					err = 0;
 					goto next;
 				}
 				break;
 			}
-			list_add_tail(&entry->list, head);
+
+			/* add this fsync inode to the list */
+			entry = add_fsync_inode(head, inode);
+			if (!entry) {
+				err = -ENOMEM;
+				iput(inode);
+				break;
+			}
 		}
 		entry->blkaddr = blkaddr;
 
-		if (IS_INODE(page)) {
-			entry->last_inode = blkaddr;
-			if (is_dent_dnode(page))
-				entry->last_dentry = blkaddr;
-		}
+		if (IS_INODE(page) && is_dent_dnode(page))
+			entry->last_dentry = blkaddr;
 next:
 		/* check next segment */
 		blkaddr = next_blkaddr_of_node(page);
@@ -277,11 +297,8 @@ static void destroy_fsync_dnodes(struct list_head *head)
 {
 	struct fsync_inode_entry *entry, *tmp;
 
-	list_for_each_entry_safe(entry, tmp, head, list) {
-		iput(entry->inode);
-		list_del(&entry->list);
-		kmem_cache_free(fsync_entry_slab, entry);
-	}
+	list_for_each_entry_safe(entry, tmp, head, list)
+		del_fsync_inode(entry);
 }
 
 static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
@@ -444,8 +461,7 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 		 */
 		if (dest == NEW_ADDR) {
 			truncate_data_blocks_range(&dn, 1);
-			err = reserve_new_block(&dn);
-			f2fs_bug_on(sbi, err);
+			reserve_new_block(&dn);
 			continue;
 		}
 
@@ -454,6 +470,10 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 
 			if (src == NULL_ADDR) {
 				err = reserve_new_block(&dn);
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+				while (err)
+					err = reserve_new_block(&dn);
+#endif
 				/* We should not get -ENOSPC */
 				f2fs_bug_on(sbi, err);
 			}
@@ -486,7 +506,8 @@ out:
 	return err;
 }
 
-static int recover_data(struct f2fs_sb_info *sbi, struct list_head *head)
+static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list,
+						struct list_head *dir_list)
 {
 	unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi));
 	struct curseg_info *curseg;
@@ -513,7 +534,7 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *head)
 			break;
 		}
 
-		entry = get_fsync_inode(head, ino_of_node(page));
+		entry = get_fsync_inode(inode_list, ino_of_node(page));
 		if (!entry)
 			goto next;
 		/*
@@ -521,10 +542,10 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *head)
 		 * In this case, we can lose the latest inode(x).
 		 * So, call recover_inode for the inode update.
 		 */
-		if (entry->last_inode == blkaddr)
+		if (IS_INODE(page))
 			recover_inode(entry->inode, page);
 		if (entry->last_dentry == blkaddr) {
-			err = recover_dentry(entry->inode, page);
+			err = recover_dentry(entry->inode, page, dir_list);
 			if (err) {
 				f2fs_put_page(page, 1);
 				break;
@@ -536,11 +557,8 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *head)
 			break;
 		}
 
-		if (entry->blkaddr == blkaddr) {
-			iput(entry->inode);
-			list_del(&entry->list);
-			kmem_cache_free(fsync_entry_slab, entry);
-		}
+		if (entry->blkaddr == blkaddr)
+			del_fsync_inode(entry);
 next:
 		/* check next segment */
 		blkaddr = next_blkaddr_of_node(page);
@@ -551,12 +569,14 @@ next:
 	return err;
 }
 
-int recover_fsync_data(struct f2fs_sb_info *sbi)
+int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
 	struct list_head inode_list;
+	struct list_head dir_list;
 	block_t blkaddr;
 	int err;
+	int ret = 0;
 	bool need_writecp = false;
 
 	fsync_entry_slab = f2fs_kmem_cache_create("f2fs_fsync_inode_entry",
@@ -565,6 +585,7 @@ int recover_fsync_data(struct f2fs_sb_info *sbi)
 		return -ENOMEM;
 
 	INIT_LIST_HEAD(&inode_list);
+	INIT_LIST_HEAD(&dir_list);
 
 	/* prevent checkpoint */
 	mutex_lock(&sbi->cp_mutex);
@@ -573,21 +594,22 @@ int recover_fsync_data(struct f2fs_sb_info *sbi)
 
 	/* step #1: find fsynced inode numbers */
 	err = find_fsync_dnodes(sbi, &inode_list);
-	if (err)
+	if (err || list_empty(&inode_list))
 		goto out;
 
-	if (list_empty(&inode_list))
+	if (check_only) {
+		ret = 1;
 		goto out;
+	}
 
 	need_writecp = true;
 
 	/* step #2: recover data */
-	err = recover_data(sbi, &inode_list);
+	err = recover_data(sbi, &inode_list, &dir_list);
 	if (!err)
 		f2fs_bug_on(sbi, !list_empty(&inode_list));
 out:
 	destroy_fsync_dnodes(&inode_list);
-	kmem_cache_destroy(fsync_entry_slab);
 
 	/* truncate meta pages to be used by the recovery */
 	truncate_inode_pages_range(META_MAPPING(sbi),
@@ -625,5 +647,8 @@ out:
 	} else {
 		mutex_unlock(&sbi->cp_mutex);
 	}
-	return err;
+
+	destroy_fsync_dnodes(&dir_list);
+	kmem_cache_destroy(fsync_entry_slab);
+	return ret ? ret: err;
 }

fs/f2fs/segment.c

@@ -223,9 +223,11 @@ static int __revoke_inmem_pages(struct inode *inode,
 			f2fs_put_dnode(&dn);
 		}
 next:
-		ClearPageUptodate(page);
+		/* we don't need to invalidate this in the sccessful status */
+		if (drop || recover)
+			ClearPageUptodate(page);
 		set_page_private(page, 0);
-		ClearPageUptodate(page);
+		ClearPagePrivate(page);
 		f2fs_put_page(page, 1);
 
 		list_del(&cur->list);
@@ -239,6 +241,8 @@ void drop_inmem_pages(struct inode *inode)
 {
 	struct f2fs_inode_info *fi = F2FS_I(inode);
 
+	clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
+
 	mutex_lock(&fi->inmem_lock);
 	__revoke_inmem_pages(inode, &fi->inmem_pages, true, false);
 	mutex_unlock(&fi->inmem_lock);

fs/f2fs/segment.h

@@ -158,16 +158,17 @@ struct victim_sel_policy {
 };
 
 struct seg_entry {
-	unsigned short valid_blocks;	/* # of valid blocks */
+	unsigned int type:6;		/* segment type like CURSEG_XXX_TYPE */
+	unsigned int valid_blocks:10;	/* # of valid blocks */
+	unsigned int ckpt_valid_blocks:10;	/* # of valid blocks last cp */
+	unsigned int padding:6;		/* padding */
 	unsigned char *cur_valid_map;	/* validity bitmap of blocks */
 	/*
 	 * # of valid blocks and the validity bitmap stored in the the last
 	 * checkpoint pack. This information is used by the SSR mode.
 	 */
-	unsigned short ckpt_valid_blocks;
-	unsigned char *ckpt_valid_map;
+	unsigned char *ckpt_valid_map;	/* validity bitmap of blocks last cp */
 	unsigned char *discard_map;
-	unsigned char type;		/* segment type like CURSEG_XXX_TYPE */
 	unsigned long long mtime;	/* modification time of the segment */
 };
 

fs/f2fs/super.c

@@ -39,6 +39,30 @@ static struct proc_dir_entry *f2fs_proc_root;
 static struct kmem_cache *f2fs_inode_cachep;
 static struct kset *f2fs_kset;
 
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+struct f2fs_fault_info f2fs_fault;
+
+char *fault_name[FAULT_MAX] = {
+	[FAULT_KMALLOC]		= "kmalloc",
+	[FAULT_PAGE_ALLOC]	= "page alloc",
+	[FAULT_ALLOC_NID]	= "alloc nid",
+	[FAULT_ORPHAN]		= "orphan",
+	[FAULT_BLOCK]		= "no more block",
+	[FAULT_DIR_DEPTH]	= "too big dir depth",
+};
+
+static void f2fs_build_fault_attr(unsigned int rate)
+{
+	if (rate) {
+		atomic_set(&f2fs_fault.inject_ops, 0);
+		f2fs_fault.inject_rate = rate;
+		f2fs_fault.inject_type = (1 << FAULT_MAX) - 1;
+	} else {
+		memset(&f2fs_fault, 0, sizeof(struct f2fs_fault_info));
+	}
+}
+#endif
+
 /* f2fs-wide shrinker description */
 static struct shrinker f2fs_shrinker_info = {
 	.scan_objects = f2fs_shrink_scan,
@@ -68,6 +92,7 @@ enum {
 	Opt_noextent_cache,
 	Opt_noinline_data,
 	Opt_data_flush,
+	Opt_fault_injection,
 	Opt_err,
 };
 
@@ -93,6 +118,7 @@ static match_table_t f2fs_tokens = {
 	{Opt_noextent_cache, "noextent_cache"},
 	{Opt_noinline_data, "noinline_data"},
 	{Opt_data_flush, "data_flush"},
+	{Opt_fault_injection, "fault_injection=%u"},
 	{Opt_err, NULL},
 };
 
@@ -102,6 +128,10 @@ enum {
 	SM_INFO,	/* struct f2fs_sm_info */
 	NM_INFO,	/* struct f2fs_nm_info */
 	F2FS_SBI,	/* struct f2fs_sb_info */
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	FAULT_INFO_RATE,	/* struct f2fs_fault_info */
+	FAULT_INFO_TYPE,	/* struct f2fs_fault_info */
+#endif
 };
 
 struct f2fs_attr {
@@ -123,6 +153,11 @@ static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type)
 		return (unsigned char *)NM_I(sbi);
 	else if (struct_type == F2FS_SBI)
 		return (unsigned char *)sbi;
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	else if (struct_type == FAULT_INFO_RATE ||
+					struct_type == FAULT_INFO_TYPE)
+		return (unsigned char *)&f2fs_fault;
+#endif
 	return NULL;
 }
 
@@ -172,6 +207,10 @@ static ssize_t f2fs_sbi_store(struct f2fs_attr *a,
 	ret = kstrtoul(skip_spaces(buf), 0, &t);
 	if (ret < 0)
 		return ret;
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	if (a->struct_type == FAULT_INFO_TYPE && t >= (1 << FAULT_MAX))
+		return -EINVAL;
+#endif
 	*ui = t;
 	return count;
 }
@@ -237,6 +276,10 @@ F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, cp_interval, interval_time[CP_TIME]);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, idle_interval, interval_time[REQ_TIME]);
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+F2FS_RW_ATTR(FAULT_INFO_RATE, f2fs_fault_info, inject_rate, inject_rate);
+F2FS_RW_ATTR(FAULT_INFO_TYPE, f2fs_fault_info, inject_type, inject_type);
+#endif
 F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes);
 
 #define ATTR_LIST(name) (&f2fs_attr_##name.attr)
@@ -273,6 +316,22 @@ static struct kobj_type f2fs_ktype = {
 	.release	= f2fs_sb_release,
 };
 
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+/* sysfs for f2fs fault injection */
+static struct kobject f2fs_fault_inject;
+
+static struct attribute *f2fs_fault_attrs[] = {
+	ATTR_LIST(inject_rate),
+	ATTR_LIST(inject_type),
+	NULL
+};
+
+static struct kobj_type f2fs_fault_ktype = {
+	.default_attrs	= f2fs_fault_attrs,
+	.sysfs_ops	= &f2fs_attr_ops,
+};
+#endif
+
 void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...)
 {
 	struct va_format vaf;
@@ -300,6 +359,10 @@ static int parse_options(struct super_block *sb, char *options)
 	char *p, *name;
 	int arg = 0;
 
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	f2fs_build_fault_attr(0);
+#endif
+
 	if (!options)
 		return 0;
 
@@ -433,6 +496,16 @@ static int parse_options(struct super_block *sb, char *options)
 		case Opt_data_flush:
 			set_opt(sbi, DATA_FLUSH);
 			break;
+		case Opt_fault_injection:
+			if (args->from && match_int(args, &arg))
+				return -EINVAL;
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+			f2fs_build_fault_attr(arg);
+#else
+			f2fs_msg(sb, KERN_INFO,
+				"FAULT_INJECTION was not selected");
+#endif
+			break;
 		default:
 			f2fs_msg(sb, KERN_ERR,
 				"Unrecognized mount option \"%s\" or missing value",
@@ -453,9 +526,13 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
 
 	init_once((void *) fi);
 
+	if (percpu_counter_init(&fi->dirty_pages, 0, GFP_NOFS)) {
+		kmem_cache_free(f2fs_inode_cachep, fi);
+		return NULL;
+	}
+
 	/* Initialize f2fs-specific inode info */
 	fi->vfs_inode.i_version = 1;
-	atomic_set(&fi->dirty_pages, 0);
 	fi->i_current_depth = 1;
 	fi->i_advise = 0;
 	init_rwsem(&fi->i_sem);
@@ -530,15 +607,27 @@ static void f2fs_i_callback(struct rcu_head *head)
 
 static void f2fs_destroy_inode(struct inode *inode)
 {
+	percpu_counter_destroy(&F2FS_I(inode)->dirty_pages);
 	call_rcu(&inode->i_rcu, f2fs_i_callback);
 }
 
+static void destroy_percpu_info(struct f2fs_sb_info *sbi)
+{
+	int i;
+
+	for (i = 0; i < NR_COUNT_TYPE; i++)
+		percpu_counter_destroy(&sbi->nr_pages[i]);
+	percpu_counter_destroy(&sbi->alloc_valid_block_count);
+	percpu_counter_destroy(&sbi->total_valid_inode_count);
+}
+
 static void f2fs_put_super(struct super_block *sb)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 
 	if (sbi->s_proc) {
 		remove_proc_entry("segment_info", sbi->s_proc);
+		remove_proc_entry("segment_bits", sbi->s_proc);
 		remove_proc_entry(sb->s_id, f2fs_proc_root);
 	}
 	kobject_del(&sbi->s_kobj);
@@ -568,15 +657,14 @@ static void f2fs_put_super(struct super_block *sb)
 	 * normally superblock is clean, so we need to release this.
 	 * In addition, EIO will skip do checkpoint, we need this as well.
 	 */
-	release_ino_entry(sbi);
+	release_ino_entry(sbi, true);
 	release_discard_addrs(sbi);
 
 	f2fs_leave_shrinker(sbi);
 	mutex_unlock(&sbi->umount_mutex);
 
 	/* our cp_error case, we can wait for any writeback page */
-	if (get_pages(sbi, F2FS_WRITEBACK))
-		f2fs_flush_merged_bios(sbi);
+	f2fs_flush_merged_bios(sbi);
 
 	iput(sbi->node_inode);
 	iput(sbi->meta_inode);
@@ -593,6 +681,8 @@ static void f2fs_put_super(struct super_block *sb)
 	if (sbi->s_chksum_driver)
 		crypto_free_shash(sbi->s_chksum_driver);
 	kfree(sbi->raw_super);
+
+	destroy_percpu_info(sbi);
 	kfree(sbi);
 }
 
@@ -745,19 +835,47 @@ static int segment_info_seq_show(struct seq_file *seq, void *offset)
 	return 0;
 }
 
-static int segment_info_open_fs(struct inode *inode, struct file *file)
+static int segment_bits_seq_show(struct seq_file *seq, void *offset)
 {
-	return single_open(file, segment_info_seq_show, PDE_DATA(inode));
+	struct super_block *sb = seq->private;
+	struct f2fs_sb_info *sbi = F2FS_SB(sb);
+	unsigned int total_segs =
+			le32_to_cpu(sbi->raw_super->segment_count_main);
+	int i, j;
+
+	seq_puts(seq, "format: segment_type|valid_blocks|bitmaps\n"
+		"segment_type(0:HD, 1:WD, 2:CD, 3:HN, 4:WN, 5:CN)\n");
+
+	for (i = 0; i < total_segs; i++) {
+		struct seg_entry *se = get_seg_entry(sbi, i);
+
+		seq_printf(seq, "%-10d", i);
+		seq_printf(seq, "%d|%-3u|", se->type,
+					get_valid_blocks(sbi, i, 1));
+		for (j = 0; j < SIT_VBLOCK_MAP_SIZE; j++)
+			seq_printf(seq, "%x ", se->cur_valid_map[j]);
+		seq_putc(seq, '\n');
+	}
+	return 0;
 }
 
-static const struct file_operations f2fs_seq_segment_info_fops = {
-	.owner = THIS_MODULE,
-	.open = segment_info_open_fs,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
+#define F2FS_PROC_FILE_DEF(_name)					\
+static int _name##_open_fs(struct inode *inode, struct file *file)	\
+{									\
+	return single_open(file, _name##_seq_show, PDE_DATA(inode));	\
+}									\
+									\
+static const struct file_operations f2fs_seq_##_name##_fops = {		\
+	.owner = THIS_MODULE,						\
+	.open = _name##_open_fs,					\
+	.read = seq_read,						\
+	.llseek = seq_lseek,						\
+	.release = single_release,					\
 };
 
+F2FS_PROC_FILE_DEF(segment_info);
+F2FS_PROC_FILE_DEF(segment_bits);
+
 static void default_options(struct f2fs_sb_info *sbi)
 {
 	/* init some FS parameters */
@@ -791,13 +909,15 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	org_mount_opt = sbi->mount_opt;
 	active_logs = sbi->active_logs;
 
-	if (*flags & MS_RDONLY) {
-		set_opt(sbi, FASTBOOT);
-		set_sbi_flag(sbi, SBI_IS_DIRTY);
+	/* recover superblocks we couldn't write due to previous RO mount */
+	if (!(*flags & MS_RDONLY) && is_sbi_flag_set(sbi, SBI_NEED_SB_WRITE)) {
+		err = f2fs_commit_super(sbi, false);
+		f2fs_msg(sb, KERN_INFO,
+			"Try to recover all the superblocks, ret: %d", err);
+		if (!err)
+			clear_sbi_flag(sbi, SBI_NEED_SB_WRITE);
 	}
 
-	sync_filesystem(sb);
-
 	sbi->mount_opt.opt = 0;
 	default_options(sbi);
 
@@ -829,7 +949,6 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	if ((*flags & MS_RDONLY) || !test_opt(sbi, BG_GC)) {
 		if (sbi->gc_thread) {
 			stop_gc_thread(sbi);
-			f2fs_sync_fs(sb, 1);
 			need_restart_gc = true;
 		}
 	} else if (!sbi->gc_thread) {
@@ -839,6 +958,16 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 		need_stop_gc = true;
 	}
 
+	if (*flags & MS_RDONLY) {
+		writeback_inodes_sb(sb, WB_REASON_SYNC);
+		sync_inodes_sb(sb);
+
+		set_sbi_flag(sbi, SBI_IS_DIRTY);
+		set_sbi_flag(sbi, SBI_IS_CLOSE);
+		f2fs_sync_fs(sb, 1);
+		clear_sbi_flag(sbi, SBI_IS_CLOSE);
+	}
+
 	/*
 	 * We stop issue flush thread if FS is mounted as RO
 	 * or if flush_merge is not passed in mount option.
@@ -852,8 +981,9 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	}
 skip:
 	/* Update the POSIXACL Flag */
-	 sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
+	sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
 		(test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0);
+
 	return 0;
 restore_gc:
 	if (need_restart_gc) {
@@ -893,6 +1023,12 @@ static int f2fs_get_context(struct inode *inode, void *ctx, size_t len)
 				ctx, len, NULL);
 }
 
+static int f2fs_key_prefix(struct inode *inode, u8 **key)
+{
+	*key = F2FS_I_SB(inode)->key_prefix;
+	return F2FS_I_SB(inode)->key_prefix_size;
+}
+
 static int f2fs_set_context(struct inode *inode, const void *ctx, size_t len,
 							void *fs_data)
 {
@@ -909,6 +1045,7 @@ static unsigned f2fs_max_namelen(struct inode *inode)
 
 static struct fscrypt_operations f2fs_cryptops = {
 	.get_context	= f2fs_get_context,
+	.key_prefix	= f2fs_key_prefix,
 	.set_context	= f2fs_set_context,
 	.is_encrypted	= f2fs_encrypted_inode,
 	.empty_dir	= f2fs_empty_dir,
@@ -998,11 +1135,12 @@ static int __f2fs_commit_super(struct buffer_head *bh,
 	return __sync_dirty_buffer(bh, WRITE_FLUSH_FUA);
 }
 
-static inline bool sanity_check_area_boundary(struct super_block *sb,
+static inline bool sanity_check_area_boundary(struct f2fs_sb_info *sbi,
 					struct buffer_head *bh)
 {
 	struct f2fs_super_block *raw_super = (struct f2fs_super_block *)
 					(bh->b_data + F2FS_SUPER_OFFSET);
+	struct super_block *sb = sbi->sb;
 	u32 segment0_blkaddr = le32_to_cpu(raw_super->segment0_blkaddr);
 	u32 cp_blkaddr = le32_to_cpu(raw_super->cp_blkaddr);
 	u32 sit_blkaddr = le32_to_cpu(raw_super->sit_blkaddr);
@@ -1081,6 +1219,7 @@ static inline bool sanity_check_area_boundary(struct super_block *sb,
 				segment0_blkaddr) >> log_blocks_per_seg);
 
 		if (f2fs_readonly(sb) || bdev_read_only(sb->s_bdev)) {
+			set_sbi_flag(sbi, SBI_NEED_SB_WRITE);
 			res = "internally";
 		} else {
 			err = __f2fs_commit_super(bh, NULL);
@@ -1098,11 +1237,12 @@ static inline bool sanity_check_area_boundary(struct super_block *sb,
 	return false;
 }
 
-static int sanity_check_raw_super(struct super_block *sb,
+static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
 				struct buffer_head *bh)
 {
 	struct f2fs_super_block *raw_super = (struct f2fs_super_block *)
 					(bh->b_data + F2FS_SUPER_OFFSET);
+	struct super_block *sb = sbi->sb;
 	unsigned int blocksize;
 
 	if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic)) {
@@ -1169,7 +1309,7 @@ static int sanity_check_raw_super(struct super_block *sb,
 	}
 
 	/* check CP/SIT/NAT/SSA/MAIN_AREA area boundary */
-	if (sanity_check_area_boundary(sb, bh))
+	if (sanity_check_area_boundary(sbi, bh))
 		return 1;
 
 	return 0;
@@ -1201,7 +1341,6 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi)
 static void init_sb_info(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_super_block *raw_super = sbi->raw_super;
-	int i;
 
 	sbi->log_sectors_per_block =
 		le32_to_cpu(raw_super->log_sectors_per_block);
@@ -1221,9 +1360,6 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
 	sbi->cur_victim_sec = NULL_SECNO;
 	sbi->max_victim_search = DEF_MAX_VICTIM_SEARCH;
 
-	for (i = 0; i < NR_COUNT_TYPE; i++)
-		atomic_set(&sbi->nr_pages[i], 0);
-
 	sbi->dir_level = DEF_DIR_LEVEL;
 	sbi->interval_time[CP_TIME] = DEF_CP_INTERVAL;
 	sbi->interval_time[REQ_TIME] = DEF_IDLE_INTERVAL;
@@ -1231,6 +1367,30 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
 
 	INIT_LIST_HEAD(&sbi->s_list);
 	mutex_init(&sbi->umount_mutex);
+
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+	memcpy(sbi->key_prefix, F2FS_KEY_DESC_PREFIX,
+				F2FS_KEY_DESC_PREFIX_SIZE);
+	sbi->key_prefix_size = F2FS_KEY_DESC_PREFIX_SIZE;
+#endif
+}
+
+static int init_percpu_info(struct f2fs_sb_info *sbi)
+{
+	int i, err;
+
+	for (i = 0; i < NR_COUNT_TYPE; i++) {
+		err = percpu_counter_init(&sbi->nr_pages[i], 0, GFP_KERNEL);
+		if (err)
+			return err;
+	}
+
+	err = percpu_counter_init(&sbi->alloc_valid_block_count, 0, GFP_KERNEL);
+	if (err)
+		return err;
+
+	return percpu_counter_init(&sbi->total_valid_inode_count, 0,
+								GFP_KERNEL);
 }
 
 /*
@@ -1239,10 +1399,11 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
  * to get the first valid one. If any one of them is broken, we pass
  * them recovery flag back to the caller.
  */
-static int read_raw_super_block(struct super_block *sb,
+static int read_raw_super_block(struct f2fs_sb_info *sbi,
 			struct f2fs_super_block **raw_super,
 			int *valid_super_block, int *recovery)
 {
+	struct super_block *sb = sbi->sb;
 	int block;
 	struct buffer_head *bh;
 	struct f2fs_super_block *super;
@@ -1262,7 +1423,7 @@ static int read_raw_super_block(struct super_block *sb,
 		}
 
 		/* sanity checking of raw super */
-		if (sanity_check_raw_super(sb, bh)) {
+		if (sanity_check_raw_super(sbi, bh)) {
 			f2fs_msg(sb, KERN_ERR,
 				"Can't find valid F2FS filesystem in %dth superblock",
 				block + 1);
@@ -1298,6 +1459,12 @@ int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover)
 	struct buffer_head *bh;
 	int err;
 
+	if ((recover && f2fs_readonly(sbi->sb)) ||
+				bdev_read_only(sbi->sb->s_bdev)) {
+		set_sbi_flag(sbi, SBI_NEED_SB_WRITE);
+		return -EROFS;
+	}
+
 	/* write back-up superblock first */
 	bh = sb_getblk(sbi->sb, sbi->valid_super_block ? 0: 1);
 	if (!bh)
@@ -1323,7 +1490,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	struct f2fs_sb_info *sbi;
 	struct f2fs_super_block *raw_super;
 	struct inode *root;
-	long err;
+	int err;
 	bool retry = true, need_fsck = false;
 	char *options = NULL;
 	int recovery, i, valid_super_block;
@@ -1340,6 +1507,8 @@ try_onemore:
 	if (!sbi)
 		return -ENOMEM;
 
+	sbi->sb = sb;
+
 	/* Load the checksum driver */
 	sbi->s_chksum_driver = crypto_alloc_shash("crc32", 0, 0);
 	if (IS_ERR(sbi->s_chksum_driver)) {
@@ -1355,7 +1524,7 @@ try_onemore:
 		goto free_sbi;
 	}
 
-	err = read_raw_super_block(sb, &raw_super, &valid_super_block,
+	err = read_raw_super_block(sbi, &raw_super, &valid_super_block,
 								&recovery);
 	if (err)
 		goto free_sbi;
@@ -1390,7 +1559,6 @@ try_onemore:
 	memcpy(sb->s_uuid, raw_super->uuid, sizeof(raw_super->uuid));
 
 	/* init f2fs-specific super block info */
-	sbi->sb = sb;
 	sbi->raw_super = raw_super;
 	sbi->valid_super_block = valid_super_block;
 	mutex_init(&sbi->gc_mutex);
@@ -1415,6 +1583,10 @@ try_onemore:
 	init_waitqueue_head(&sbi->cp_wait);
 	init_sb_info(sbi);
 
+	err = init_percpu_info(sbi);
+	if (err)
+		goto free_options;
+
 	/* get an inode for meta space */
 	sbi->meta_inode = f2fs_iget(sb, F2FS_META_INO(sbi));
 	if (IS_ERR(sbi->meta_inode)) {
@@ -1431,13 +1603,13 @@ try_onemore:
 
 	sbi->total_valid_node_count =
 				le32_to_cpu(sbi->ckpt->valid_node_count);
-	sbi->total_valid_inode_count =
-				le32_to_cpu(sbi->ckpt->valid_inode_count);
+	percpu_counter_set(&sbi->total_valid_inode_count,
+				le32_to_cpu(sbi->ckpt->valid_inode_count));
 	sbi->user_block_count = le64_to_cpu(sbi->ckpt->user_block_count);
 	sbi->total_valid_block_count =
 				le64_to_cpu(sbi->ckpt->valid_block_count);
 	sbi->last_valid_block_count = sbi->total_valid_block_count;
-	sbi->alloc_valid_block_count = 0;
+
 	for (i = 0; i < NR_INODE_TYPE; i++) {
 		INIT_LIST_HEAD(&sbi->inode_list[i]);
 		spin_lock_init(&sbi->inode_lock[i]);
@@ -1515,9 +1687,12 @@ try_onemore:
 	if (f2fs_proc_root)
 		sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root);
 
-	if (sbi->s_proc)
+	if (sbi->s_proc) {
 		proc_create_data("segment_info", S_IRUGO, sbi->s_proc,
 				 &f2fs_seq_segment_info_fops, sb);
+		proc_create_data("segment_bits", S_IRUGO, sbi->s_proc,
+				 &f2fs_seq_segment_bits_fops, sb);
+	}
 
 	sbi->s_kobj.kset = f2fs_kset;
 	init_completion(&sbi->s_kobj_unregister);
@@ -1541,14 +1716,24 @@ try_onemore:
 		if (need_fsck)
 			set_sbi_flag(sbi, SBI_NEED_FSCK);
 
-		err = recover_fsync_data(sbi);
-		if (err) {
+		err = recover_fsync_data(sbi, false);
+		if (err < 0) {
 			need_fsck = true;
 			f2fs_msg(sb, KERN_ERR,
-				"Cannot recover all fsync data errno=%ld", err);
+				"Cannot recover all fsync data errno=%d", err);
+			goto free_kobj;
+		}
+	} else {
+		err = recover_fsync_data(sbi, true);
+
+		if (!f2fs_readonly(sb) && err > 0) {
+			err = -EINVAL;
+			f2fs_msg(sb, KERN_ERR,
+				"Need to recover fsync data");
 			goto free_kobj;
 		}
 	}
+
 	/* recover_fsync_data() cleared this already */
 	clear_sbi_flag(sbi, SBI_POR_DOING);
 
@@ -1565,10 +1750,10 @@ try_onemore:
 	kfree(options);
 
 	/* recover broken superblock */
-	if (recovery && !f2fs_readonly(sb) && !bdev_read_only(sb->s_bdev)) {
+	if (recovery) {
 		err = f2fs_commit_super(sbi, true);
 		f2fs_msg(sb, KERN_INFO,
-			"Try to recover %dth superblock, ret: %ld",
+			"Try to recover %dth superblock, ret: %d",
 			sbi->valid_super_block ? 1 : 2, err);
 	}
 
@@ -1583,6 +1768,7 @@ free_kobj:
 free_proc:
 	if (sbi->s_proc) {
 		remove_proc_entry("segment_info", sbi->s_proc);
+		remove_proc_entry("segment_bits", sbi->s_proc);
 		remove_proc_entry(sb->s_id, f2fs_proc_root);
 	}
 	f2fs_destroy_stats(sbi);
@@ -1603,6 +1789,7 @@ free_meta_inode:
 	make_bad_inode(sbi->meta_inode);
 	iput(sbi->meta_inode);
 free_options:
+	destroy_percpu_info(sbi);
 	kfree(options);
 free_sb_buf:
 	kfree(raw_super);
@@ -1688,6 +1875,16 @@ static int __init init_f2fs_fs(void)
 		err = -ENOMEM;
 		goto free_extent_cache;
 	}
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	f2fs_fault_inject.kset = f2fs_kset;
+	f2fs_build_fault_attr(0);
+	err = kobject_init_and_add(&f2fs_fault_inject, &f2fs_fault_ktype,
+				NULL, "fault_injection");
+	if (err) {
+		f2fs_fault_inject.kset = NULL;
+		goto free_kset;
+	}
+#endif
 	err = register_shrinker(&f2fs_shrinker_info);
 	if (err)
 		goto free_kset;
@@ -1706,6 +1903,10 @@ free_filesystem:
 free_shrinker:
 	unregister_shrinker(&f2fs_shrinker_info);
 free_kset:
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	if (f2fs_fault_inject.kset)
+		kobject_put(&f2fs_fault_inject);
+#endif
 	kset_unregister(f2fs_kset);
 free_extent_cache:
 	destroy_extent_cache();
@@ -1725,14 +1926,17 @@ static void __exit exit_f2fs_fs(void)
 {
 	remove_proc_entry("fs/f2fs", NULL);
 	f2fs_destroy_root_stats();
-	unregister_shrinker(&f2fs_shrinker_info);
 	unregister_filesystem(&f2fs_fs_type);
+	unregister_shrinker(&f2fs_shrinker_info);
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	kobject_put(&f2fs_fault_inject);
+#endif
+	kset_unregister(f2fs_kset);
 	destroy_extent_cache();
 	destroy_checkpoint_caches();
 	destroy_segment_manager_caches();
 	destroy_node_manager_caches();
 	destroy_inodecache();
-	kset_unregister(f2fs_kset);
 	f2fs_destroy_trace_ios();
 }
 

fs/f2fs/xattr.c

@@ -498,7 +498,7 @@ static int __f2fs_setxattr(struct inode *inode, int index,
 			free = free + ENTRY_SIZE(here);
 
 		if (unlikely(free < newsize)) {
-			error = -ENOSPC;
+			error = -E2BIG;
 			goto exit;
 		}
 	}
@@ -526,7 +526,6 @@ static int __f2fs_setxattr(struct inode *inode, int index,
 		 * Before we come here, old entry is removed.
 		 * We just write new entry.
 		 */
-		memset(last, 0, newsize);
 		last->e_name_index = index;
 		last->e_name_len = len;
 		memcpy(last->e_name, name, len);

include/linux/f2fs_fs.h

@@ -508,4 +508,6 @@ enum {
 	F2FS_FT_MAX
 };
 
+#define S_SHIFT 12
+
 #endif  /* _LINUX_F2FS_FS_H */

include/linux/fscrypto.h

@@ -175,6 +175,7 @@ struct fscrypt_name {
  */
 struct fscrypt_operations {
 	int (*get_context)(struct inode *, void *, size_t);
+	int (*key_prefix)(struct inode *, u8 **);
 	int (*prepare_context)(struct inode *);
 	int (*set_context)(struct inode *, const void *, size_t, void *);
 	int (*dummy_context)(struct inode *);

include/trace/events/f2fs.h

@@ -694,28 +694,32 @@ TRACE_EVENT(f2fs_direct_IO_exit,
 		__entry->ret)
 );
 
-TRACE_EVENT(f2fs_reserve_new_block,
+TRACE_EVENT(f2fs_reserve_new_blocks,
 
-	TP_PROTO(struct inode *inode, nid_t nid, unsigned int ofs_in_node),
+	TP_PROTO(struct inode *inode, nid_t nid, unsigned int ofs_in_node,
+							blkcnt_t count),
 
-	TP_ARGS(inode, nid, ofs_in_node),
+	TP_ARGS(inode, nid, ofs_in_node, count),
 
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
 		__field(nid_t, nid)
 		__field(unsigned int, ofs_in_node)
+		__field(blkcnt_t, count)
 	),
 
 	TP_fast_assign(
 		__entry->dev	= inode->i_sb->s_dev;
 		__entry->nid	= nid;
 		__entry->ofs_in_node = ofs_in_node;
+		__entry->count = count;
 	),
 
-	TP_printk("dev = (%d,%d), nid = %u, ofs_in_node = %u",
+	TP_printk("dev = (%d,%d), nid = %u, ofs_in_node = %u, count = %llu",
 		show_dev(__entry),
 		(unsigned int)__entry->nid,
-		__entry->ofs_in_node)
+		__entry->ofs_in_node,
+		(unsigned long long)__entry->count)
 );
 
 DECLARE_EVENT_CLASS(f2fs__submit_page_bio,
@@ -1271,14 +1275,14 @@ TRACE_EVENT(f2fs_destroy_extent_tree,
 
 DECLARE_EVENT_CLASS(f2fs_sync_dirty_inodes,
 
-	TP_PROTO(struct super_block *sb, int type, int count),
+	TP_PROTO(struct super_block *sb, int type, s64 count),
 
 	TP_ARGS(sb, type, count),
 
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(int, type)
-		__field(int, count)
+		__field(s64, count)
 	),
 
 	TP_fast_assign(
@@ -1287,7 +1291,7 @@ DECLARE_EVENT_CLASS(f2fs_sync_dirty_inodes,
 		__entry->count	= count;
 	),
 
-	TP_printk("dev = (%d,%d), %s, dirty count = %d",
+	TP_printk("dev = (%d,%d), %s, dirty count = %lld",
 		show_dev(__entry),
 		show_file_type(__entry->type),
 		__entry->count)
@@ -1295,14 +1299,14 @@ DECLARE_EVENT_CLASS(f2fs_sync_dirty_inodes,
 
 DEFINE_EVENT(f2fs_sync_dirty_inodes, f2fs_sync_dirty_inodes_enter,
 
-	TP_PROTO(struct super_block *sb, int type, int count),
+	TP_PROTO(struct super_block *sb, int type, s64 count),
 
 	TP_ARGS(sb, type, count)
 );
 
 DEFINE_EVENT(f2fs_sync_dirty_inodes, f2fs_sync_dirty_inodes_exit,
 
-	TP_PROTO(struct super_block *sb, int type, int count),
+	TP_PROTO(struct super_block *sb, int type, s64 count),
 
 	TP_ARGS(sb, type, count)
 );