Merge tag 'f2fs-for-4.16-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this round, we've followed up to support some generic features such
  as cgroup, block reservation, linking fscrypt_ops, delivering
  write_hints, and some ioctls. And, we could fix some corner cases in
  terms of power-cut recovery and subtle deadlocks.

  Enhancements:
   - bitmap operations to handle NAT blocks
   - readahead to improve readdir speed
   - switch to use fscrypt_*
   - apply write hints for direct IO
   - add reserve_root=%u,resuid=%u,resgid=%u to reserve blocks for root/uid/gid
   - modify b_avail and b_free to consider root reserved blocks
   - support cgroup writeback
   - support FIEMAP_FLAG_XATTR for fibmap
   - add F2FS_IOC_PRECACHE_EXTENTS to pre-cache extents
   - add F2FS_IOC_{GET/SET}_PIN_FILE to pin LBAs for data blocks
   - support inode creation time

  Bug fixs:
   - sysfile-based quota operations
   - memory footprint accounting
   - allow to write data on partial preallocation case
   - fix deadlock case on fallocate
   - fix to handle fill_super errors
   - fix missing inode updates of fsync'ed file
   - recover renamed file which was fsycn'ed before
   - drop inmemory pages in corner error case
   - keep last_disk_size correctly
   - recover missing i_inline flags during roll-forward

  Various clean-up patches were added as well"

* tag 'f2fs-for-4.16-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (72 commits)
  f2fs: support inode creation time
  f2fs: rebuild sit page from sit info in mem
  f2fs: stop issuing discard if fs is readonly
  f2fs: clean up duplicated assignment in init_discard_policy
  f2fs: use GFP_F2FS_ZERO for cleanup
  f2fs: allow to recover node blocks given updated checkpoint
  f2fs: recover some i_inline flags
  f2fs: correct removexattr behavior for null valued extended attribute
  f2fs: drop page cache after fs shutdown
  f2fs: stop gc/discard thread after fs shutdown
  f2fs: hanlde error case in f2fs_ioc_shutdown
  f2fs: split need_inplace_update
  f2fs: fix to update last_disk_size correctly
  f2fs: kill F2FS_INLINE_XATTR_ADDRS for cleanup
  f2fs: clean up error path of fill_super
  f2fs: avoid hungtask when GC encrypted block if io_bits is set
  f2fs: allow quota to use reserved blocks
  f2fs: fix to drop all inmem pages correctly
  f2fs: speed up defragment on sparse file
  f2fs: support F2FS_IOC_PRECACHE_EXTENTS
  ...

Documentation/ABI/testing/sysfs-fs-f2fs

@@ -186,3 +186,9 @@ Date:		August 2017
 Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
 Description:
 		 Controls sleep time of GC urgent mode
+
+What:		/sys/fs/f2fs/<disk>/readdir_ra
+Date:		November 2017
+Contact:	"Sheng Yong" <shengyong1@huawei.com>
+Description:
+		 Controls readahead inode block in readdir.

fs/f2fs/acl.c

@@ -270,7 +270,7 @@ static struct posix_acl *f2fs_acl_clone(const struct posix_acl *acl,
 				sizeof(struct posix_acl_entry);
 		clone = kmemdup(acl, size, flags);
 		if (clone)
-			atomic_set(&clone->a_refcount, 1);
+			refcount_set(&clone->a_refcount, 1);
 	}
 	return clone;
 }

fs/f2fs/checkpoint.c

@@ -237,12 +237,15 @@ static int __f2fs_write_meta_page(struct page *page,
 
 	trace_f2fs_writepage(page, META);
 
+	if (unlikely(f2fs_cp_error(sbi))) {
+		dec_page_count(sbi, F2FS_DIRTY_META);
+		unlock_page(page);
+		return 0;
+	}
 	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
 		goto redirty_out;
 	if (wbc->for_reclaim && page->index < GET_SUM_BLOCK(sbi, 0))
 		goto redirty_out;
-	if (unlikely(f2fs_cp_error(sbi)))
-		goto redirty_out;
 
 	write_meta_page(sbi, page, io_type);
 	dec_page_count(sbi, F2FS_DIRTY_META);
@@ -793,7 +796,7 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi)
 	block_t cp_blk_no;
 	int i;
 
-	sbi->ckpt = kzalloc(cp_blks * blk_size, GFP_KERNEL);
+	sbi->ckpt = f2fs_kzalloc(sbi, cp_blks * blk_size, GFP_KERNEL);
 	if (!sbi->ckpt)
 		return -ENOMEM;
 	/*
@@ -1154,6 +1157,7 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	/* set this flag to activate crc|cp_ver for recovery */
 	__set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG);
+	__clear_ckpt_flags(ckpt, CP_NOCRC_RECOVERY_FLAG);
 
 	spin_unlock_irqrestore(&sbi->cp_lock, flags);
 }

fs/f2fs/debug.c

@@ -49,14 +49,7 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 	si->ndirty_imeta = get_pages(sbi, F2FS_DIRTY_IMETA);
 	si->ndirty_dirs = sbi->ndirty_inode[DIR_INODE];
 	si->ndirty_files = sbi->ndirty_inode[FILE_INODE];
-
-	si->nquota_files = 0;
-	if (f2fs_sb_has_quota_ino(sbi->sb)) {
-		for (i = 0; i < MAXQUOTAS; i++) {
-			if (f2fs_qf_ino(sbi->sb, i))
-				si->nquota_files++;
-		}
-	}
+	si->nquota_files = sbi->nquota_files;
 	si->ndirty_all = sbi->ndirty_inode[DIRTY_META];
 	si->inmem_pages = get_pages(sbi, F2FS_INMEM_PAGES);
 	si->aw_cnt = atomic_read(&sbi->aw_cnt);
@@ -186,7 +179,6 @@ 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);
@@ -447,7 +439,7 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi)
 	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
 	struct f2fs_stat_info *si;
 
-	si = kzalloc(sizeof(struct f2fs_stat_info), GFP_KERNEL);
+	si = f2fs_kzalloc(sbi, sizeof(struct f2fs_stat_info), GFP_KERNEL);
 	if (!si)
 		return -ENOMEM;
 

fs/f2fs/dir.c

@@ -713,6 +713,8 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
 
 	f2fs_update_time(F2FS_I_SB(dir), REQ_TIME);
 
+	add_ino_entry(F2FS_I_SB(dir), dir->i_ino, TRANS_DIR_INO);
+
 	if (f2fs_has_inline_dentry(dir))
 		return f2fs_delete_inline_entry(dentry, page, dir, inode);
 
@@ -798,6 +800,7 @@ int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
 	unsigned int bit_pos;
 	struct f2fs_dir_entry *de = NULL;
 	struct fscrypt_str de_name = FSTR_INIT(NULL, 0);
+	struct f2fs_sb_info *sbi = F2FS_I_SB(d->inode);
 
 	bit_pos = ((unsigned long)ctx->pos % d->max);
 
@@ -836,6 +839,9 @@ int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
 					le32_to_cpu(de->ino), d_type))
 			return 1;
 
+		if (sbi->readdir_ra == 1)
+			ra_node_page(sbi, le32_to_cpu(de->ino));
+
 		bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
 		ctx->pos = start_pos + bit_pos;
 	}

fs/f2fs/gc.c

@@ -624,6 +624,11 @@ static void move_data_block(struct inode *inode, block_t bidx,
 	if (f2fs_is_atomic_file(inode))
 		goto out;
 
+	if (f2fs_is_pinned_file(inode)) {
+		f2fs_pin_file_control(inode, true);
+		goto out;
+	}
+
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
 	err = get_dnode_of_data(&dn, bidx, LOOKUP_NODE);
 	if (err)
@@ -686,7 +691,12 @@ static void move_data_block(struct inode *inode, block_t bidx,
 	fio.op = REQ_OP_WRITE;
 	fio.op_flags = REQ_SYNC;
 	fio.new_blkaddr = newaddr;
-	f2fs_submit_page_write(&fio);
+	err = f2fs_submit_page_write(&fio);
+	if (err) {
+		if (PageWriteback(fio.encrypted_page))
+			end_page_writeback(fio.encrypted_page);
+		goto put_page_out;
+	}
 
 	f2fs_update_iostat(fio.sbi, FS_GC_DATA_IO, F2FS_BLKSIZE);
 
@@ -720,6 +730,11 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type,
 
 	if (f2fs_is_atomic_file(inode))
 		goto out;
+	if (f2fs_is_pinned_file(inode)) {
+		if (gc_type == FG_GC)
+			f2fs_pin_file_control(inode, true);
+		goto out;
+	}
 
 	if (gc_type == BG_GC) {
 		if (PageWriteback(page))
@@ -1091,6 +1106,7 @@ void build_gc_manager(struct f2fs_sb_info *sbi)
 
 	sbi->fggc_threshold = div64_u64((main_count - ovp_count) *
 				BLKS_PER_SEC(sbi), (main_count - resv_count));
+	sbi->gc_pin_file_threshold = DEF_GC_FAILED_PINNED_FILES;
 
 	/* give warm/cold data area from slower device */
 	if (sbi->s_ndevs && sbi->segs_per_sec == 1)

fs/f2fs/gc.h

@@ -20,6 +20,8 @@
 #define LIMIT_INVALID_BLOCK	40 /* percentage over total user space */
 #define LIMIT_FREE_BLOCK	40 /* percentage over invalid + free space */
 
+#define DEF_GC_FAILED_PINNED_FILES	2048
+
 /* Search max. number of dirty segments to select a victim segment */
 #define DEF_MAX_VICTIM_SEARCH 4096 /* covers 8GB */
 

fs/f2fs/inode.c

@@ -22,6 +22,9 @@
 
 void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync)
 {
+	if (is_inode_flag_set(inode, FI_NEW_INODE))
+		return;
+
 	if (f2fs_inode_dirtied(inode, sync))
 		return;
 
@@ -275,6 +278,12 @@ static int do_read_inode(struct inode *inode)
 		i_projid = F2FS_DEF_PROJID;
 	fi->i_projid = make_kprojid(&init_user_ns, i_projid);
 
+	if (f2fs_has_extra_attr(inode) && f2fs_sb_has_inode_crtime(sbi->sb) &&
+			F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, i_crtime)) {
+		fi->i_crtime.tv_sec = le64_to_cpu(ri->i_crtime);
+		fi->i_crtime.tv_nsec = le32_to_cpu(ri->i_crtime_nsec);
+	}
+
 	f2fs_put_page(node_page, 1);
 
 	stat_inc_inline_xattr(inode);
@@ -360,14 +369,15 @@ struct inode *f2fs_iget_retry(struct super_block *sb, unsigned long ino)
 	return inode;
 }
 
-int update_inode(struct inode *inode, struct page *node_page)
+void update_inode(struct inode *inode, struct page *node_page)
 {
 	struct f2fs_inode *ri;
 	struct extent_tree *et = F2FS_I(inode)->extent_tree;
 
-	f2fs_inode_synced(inode);
-
 	f2fs_wait_on_page_writeback(node_page, NODE, true);
+	set_page_dirty(node_page);
+
+	f2fs_inode_synced(inode);
 
 	ri = F2FS_INODE(node_page);
 
@@ -417,6 +427,15 @@ int update_inode(struct inode *inode, struct page *node_page)
 						F2FS_I(inode)->i_projid);
 			ri->i_projid = cpu_to_le32(i_projid);
 		}
+
+		if (f2fs_sb_has_inode_crtime(F2FS_I_SB(inode)->sb) &&
+			F2FS_FITS_IN_INODE(ri, F2FS_I(inode)->i_extra_isize,
+								i_crtime)) {
+			ri->i_crtime =
+				cpu_to_le64(F2FS_I(inode)->i_crtime.tv_sec);
+			ri->i_crtime_nsec =
+				cpu_to_le32(F2FS_I(inode)->i_crtime.tv_nsec);
+		}
 	}
 
 	__set_inode_rdev(inode, ri);
@@ -426,14 +445,12 @@ int update_inode(struct inode *inode, struct page *node_page)
 	if (inode->i_nlink == 0)
 		clear_inline_node(node_page);
 
-	return set_page_dirty(node_page);
 }
 
-int update_inode_page(struct inode *inode)
+void update_inode_page(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct page *node_page;
-	int ret = 0;
 retry:
 	node_page = get_node_page(sbi, inode->i_ino);
 	if (IS_ERR(node_page)) {
@@ -444,11 +461,10 @@ int update_inode_page(struct inode *inode)
 		} else if (err != -ENOENT) {
 			f2fs_stop_checkpoint(sbi, false);
 		}
-		return 0;
+		return;
 	}
-	ret = update_inode(inode, node_page);
+	update_inode(inode, node_page);
 	f2fs_put_page(node_page, 1);
-	return ret;
 }
 
 int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)

fs/f2fs/namei.c

@@ -50,7 +50,8 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
 
 	inode->i_ino = ino;
 	inode->i_blocks = 0;
-	inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
+	inode->i_mtime = inode->i_atime = inode->i_ctime =
+			F2FS_I(inode)->i_crtime = current_time(inode);
 	inode->i_generation = sbi->s_next_generation++;
 
 	err = insert_inode_locked(inode);
@@ -74,12 +75,12 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
 	if (err)
 		goto fail_drop;
 
+	set_inode_flag(inode, FI_NEW_INODE);
+
 	/* If the directory encrypted, then we should encrypt the inode. */
 	if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode))
 		f2fs_set_encrypted_inode(inode);
 
-	set_inode_flag(inode, FI_NEW_INODE);
-
 	if (f2fs_sb_has_extra_attr(sbi->sb)) {
 		set_inode_flag(inode, FI_EXTRA_ATTR);
 		F2FS_I(inode)->i_extra_isize = F2FS_TOTAL_EXTRA_ATTR_SIZE;
@@ -240,9 +241,9 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
 	if (unlikely(f2fs_cp_error(sbi)))
 		return -EIO;
 
-	if (f2fs_encrypted_inode(dir) &&
-			!fscrypt_has_permitted_context(dir, inode))
-		return -EPERM;
+	err = fscrypt_prepare_link(old_dentry, dir, dentry);
+	if (err)
+		return err;
 
 	if (is_inode_flag_set(dir, FI_PROJ_INHERIT) &&
 			(!projid_eq(F2FS_I(dir)->i_projid,
@@ -357,20 +358,9 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
 
 	trace_f2fs_lookup_start(dir, dentry, flags);
 
-	if (f2fs_encrypted_inode(dir)) {
-		err = fscrypt_get_encryption_info(dir);
-
-		/*
-		 * DCACHE_ENCRYPTED_WITH_KEY is set if the dentry is
-		 * created while the directory was encrypted and we
-		 * don't have access to the key.
-		 */
-		if (fscrypt_has_encryption_key(dir))
-			fscrypt_set_encrypted_dentry(dentry);
-		fscrypt_set_d_op(dentry);
-		if (err && err != -ENOKEY)
-			goto out;
-	}
+	err = fscrypt_prepare_lookup(dir, dentry, flags);
+	if (err)
+		goto out;
 
 	if (dentry->d_name.len > F2FS_NAME_LEN) {
 		err = -ENAMETOOLONG;
@@ -544,7 +534,7 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
 		struct qstr istr = QSTR_INIT(symname, len);
 		struct fscrypt_str ostr;
 
-		sd = kzalloc(disk_link.len, GFP_NOFS);
+		sd = f2fs_kzalloc(sbi, disk_link.len, GFP_NOFS);
 		if (!sd) {
 			err = -ENOMEM;
 			goto err_out;
@@ -800,18 +790,6 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (unlikely(f2fs_cp_error(sbi)))
 		return -EIO;
 
-	if ((f2fs_encrypted_inode(old_dir) &&
-			!fscrypt_has_encryption_key(old_dir)) ||
-			(f2fs_encrypted_inode(new_dir) &&
-			!fscrypt_has_encryption_key(new_dir)))
-		return -ENOKEY;
-
-	if ((old_dir != new_dir) && f2fs_encrypted_inode(new_dir) &&
-			!fscrypt_has_permitted_context(new_dir, old_inode)) {
-		err = -EPERM;
-		goto out;
-	}
-
 	if (is_inode_flag_set(new_dir, FI_PROJ_INHERIT) &&
 			(!projid_eq(F2FS_I(new_dir)->i_projid,
 			F2FS_I(old_dentry->d_inode)->i_projid)))
@@ -958,6 +936,7 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		}
 		f2fs_i_links_write(old_dir, false);
 	}
+	add_ino_entry(sbi, new_dir->i_ino, TRANS_DIR_INO);
 
 	f2fs_unlock_op(sbi);
 
@@ -1002,18 +981,6 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (unlikely(f2fs_cp_error(sbi)))
 		return -EIO;
 
-	if ((f2fs_encrypted_inode(old_dir) &&
-			!fscrypt_has_encryption_key(old_dir)) ||
-			(f2fs_encrypted_inode(new_dir) &&
-			!fscrypt_has_encryption_key(new_dir)))
-		return -ENOKEY;
-
-	if ((f2fs_encrypted_inode(old_dir) || f2fs_encrypted_inode(new_dir)) &&
-			(old_dir != new_dir) &&
-			(!fscrypt_has_permitted_context(new_dir, old_inode) ||
-			 !fscrypt_has_permitted_context(old_dir, new_inode)))
-		return -EPERM;
-
 	if ((is_inode_flag_set(new_dir, FI_PROJ_INHERIT) &&
 			!projid_eq(F2FS_I(new_dir)->i_projid,
 			F2FS_I(old_dentry->d_inode)->i_projid)) ||
@@ -1124,6 +1091,9 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 	}
 	f2fs_mark_inode_dirty_sync(new_dir, false);
 
+	add_ino_entry(sbi, old_dir->i_ino, TRANS_DIR_INO);
+	add_ino_entry(sbi, new_dir->i_ino, TRANS_DIR_INO);
+
 	f2fs_unlock_op(sbi);
 
 	if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir))
@@ -1153,9 +1123,16 @@ static int f2fs_rename2(struct inode *old_dir, struct dentry *old_dentry,
 			struct inode *new_dir, struct dentry *new_dentry,
 			unsigned int flags)
 {
+	int err;
+
 	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
 		return -EINVAL;
 
+	err = fscrypt_prepare_rename(old_dir, old_dentry, new_dir, new_dentry,
+				     flags);
+	if (err)
+		return err;
+
 	if (flags & RENAME_EXCHANGE) {
 		return f2fs_cross_rename(old_dir, old_dentry,
 					 new_dir, new_dentry);

fs/f2fs/node.h

@@ -305,6 +305,10 @@ static inline bool is_recoverable_dnode(struct page *page)
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(F2FS_P_SB(page));
 	__u64 cp_ver = cur_cp_version(ckpt);
 
+	/* Don't care crc part, if fsck.f2fs sets it. */
+	if (__is_set_ckpt_flags(ckpt, CP_NOCRC_RECOVERY_FLAG))
+		return (cp_ver << 32) == (cpver_of_node(page) << 32);
+
 	if (__is_set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG))
 		cp_ver |= (cur_cp_crc(ckpt) << 32);
 

fs/f2fs/recovery.c

@@ -195,6 +195,20 @@ static int recover_dentry(struct inode *inode, struct page *ipage,
 	return err;
 }
 
+static void recover_inline_flags(struct inode *inode, struct f2fs_inode *ri)
+{
+	if (ri->i_inline & F2FS_PIN_FILE)
+		set_inode_flag(inode, FI_PIN_FILE);
+	else
+		clear_inode_flag(inode, FI_PIN_FILE);
+	if (ri->i_inline & F2FS_DATA_EXIST)
+		set_inode_flag(inode, FI_DATA_EXIST);
+	else
+		clear_inode_flag(inode, FI_DATA_EXIST);
+	if (!(ri->i_inline & F2FS_INLINE_DOTS))
+		clear_inode_flag(inode, FI_INLINE_DOTS);
+}
+
 static void recover_inode(struct inode *inode, struct page *page)
 {
 	struct f2fs_inode *raw = F2FS_INODE(page);
@@ -211,13 +225,16 @@ static void recover_inode(struct inode *inode, struct page *page)
 
 	F2FS_I(inode)->i_advise = raw->i_advise;
 
+	recover_inline_flags(inode, raw);
+
 	if (file_enc_name(inode))
 		name = "<encrypted>";
 	else
 		name = F2FS_INODE(page)->i_name;
 
-	f2fs_msg(inode->i_sb, KERN_NOTICE, "recover_inode: ino = %x, name = %s",
-			ino_of_node(page), name);
+	f2fs_msg(inode->i_sb, KERN_NOTICE,
+		"recover_inode: ino = %x, name = %s, inline = %x",
+			ino_of_node(page), name, raw->i_inline);
 }
 
 static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head,
@@ -404,7 +421,7 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
 }
 
 static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
-					struct page *page, block_t blkaddr)
+					struct page *page)
 {
 	struct dnode_of_data dn;
 	struct node_info ni;
@@ -415,7 +432,7 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 	if (IS_INODE(page)) {
 		recover_inline_xattr(inode, page);
 	} else if (f2fs_has_xattr_block(ofs_of_node(page))) {
-		err = recover_xattr_data(inode, page, blkaddr);
+		err = recover_xattr_data(inode, page);
 		if (!err)
 			recovered++;
 		goto out;
@@ -568,7 +585,7 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list,
 				break;
 			}
 		}
-		err = do_recover_data(sbi, entry->inode, page, blkaddr);
+		err = do_recover_data(sbi, entry->inode, page);
 		if (err) {
 			f2fs_put_page(page, 1);
 			break;

fs/f2fs/segment.h

@@ -348,16 +348,41 @@ static inline void seg_info_from_raw_sit(struct seg_entry *se,
 	se->mtime = le64_to_cpu(rs->mtime);
 }
 
-static inline void seg_info_to_raw_sit(struct seg_entry *se,
+static inline void __seg_info_to_raw_sit(struct seg_entry *se,
 					struct f2fs_sit_entry *rs)
 {
 	unsigned short raw_vblocks = (se->type << SIT_VBLOCKS_SHIFT) |
 					se->valid_blocks;
 	rs->vblocks = cpu_to_le16(raw_vblocks);
 	memcpy(rs->valid_map, se->cur_valid_map, SIT_VBLOCK_MAP_SIZE);
+	rs->mtime = cpu_to_le64(se->mtime);
+}
+
+static inline void seg_info_to_sit_page(struct f2fs_sb_info *sbi,
+				struct page *page, unsigned int start)
+{
+	struct f2fs_sit_block *raw_sit;
+	struct seg_entry *se;
+	struct f2fs_sit_entry *rs;
+	unsigned int end = min(start + SIT_ENTRY_PER_BLOCK,
+					(unsigned long)MAIN_SEGS(sbi));
+	int i;
+
+	raw_sit = (struct f2fs_sit_block *)page_address(page);
+	for (i = 0; i < end - start; i++) {
+		rs = &raw_sit->entries[i];
+		se = get_seg_entry(sbi, start + i);
+		__seg_info_to_raw_sit(se, rs);
+	}
+}
+
+static inline void seg_info_to_raw_sit(struct seg_entry *se,
+					struct f2fs_sit_entry *rs)
+{
+	__seg_info_to_raw_sit(se, rs);
+
 	memcpy(se->ckpt_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
 	se->ckpt_valid_blocks = se->valid_blocks;
-	rs->mtime = cpu_to_le64(se->mtime);
 }
 
 static inline unsigned int find_next_inuse(struct free_segmap_info *free_i,
@@ -580,47 +605,6 @@ enum {
 	F2FS_IPU_ASYNC,
 };
 
-static inline bool need_inplace_update_policy(struct inode *inode,
-				struct f2fs_io_info *fio)
-{
-	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	unsigned int policy = SM_I(sbi)->ipu_policy;
-
-	if (test_opt(sbi, LFS))
-		return false;
-
-	/* if this is cold file, we should overwrite to avoid fragmentation */
-	if (file_is_cold(inode))
-		return true;
-
-	if (policy & (0x1 << F2FS_IPU_FORCE))
-		return true;
-	if (policy & (0x1 << F2FS_IPU_SSR) && need_SSR(sbi))
-		return true;
-	if (policy & (0x1 << F2FS_IPU_UTIL) &&
-			utilization(sbi) > SM_I(sbi)->min_ipu_util)
-		return true;
-	if (policy & (0x1 << F2FS_IPU_SSR_UTIL) && need_SSR(sbi) &&
-			utilization(sbi) > SM_I(sbi)->min_ipu_util)
-		return true;
-
-	/*
-	 * IPU for rewrite async pages
-	 */
-	if (policy & (0x1 << F2FS_IPU_ASYNC) &&
-			fio && fio->op == REQ_OP_WRITE &&
-			!(fio->op_flags & REQ_SYNC) &&
-			!f2fs_encrypted_inode(inode))
-		return true;
-
-	/* this is only set during fdatasync */
-	if (policy & (0x1 << F2FS_IPU_FSYNC) &&
-			is_inode_flag_set(inode, FI_NEED_IPU))
-		return true;
-
-	return false;
-}
-
 static inline unsigned int curseg_segno(struct f2fs_sb_info *sbi,
 		int type)
 {
@@ -655,7 +639,7 @@ static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr)
 /*
  * Summary block is always treated as an invalid block
  */
-static inline void check_block_count(struct f2fs_sb_info *sbi,
+static inline int check_block_count(struct f2fs_sb_info *sbi,
 		int segno, struct f2fs_sit_entry *raw_sit)
 {
 #ifdef CONFIG_F2FS_CHECK_FS
@@ -677,11 +661,25 @@ static inline void check_block_count(struct f2fs_sb_info *sbi,
 		cur_pos = next_pos;
 		is_valid = !is_valid;
 	} while (cur_pos < sbi->blocks_per_seg);
-	BUG_ON(GET_SIT_VBLOCKS(raw_sit) != valid_blocks);
+
+	if (unlikely(GET_SIT_VBLOCKS(raw_sit) != valid_blocks)) {
+		f2fs_msg(sbi->sb, KERN_ERR,
+				"Mismatch valid blocks %d vs. %d",
+					GET_SIT_VBLOCKS(raw_sit), valid_blocks);
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
+		return -EINVAL;
+	}
 #endif
 	/* check segment usage, and check boundary of a given segment number */
-	f2fs_bug_on(sbi, GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg
-					|| segno > TOTAL_SEGS(sbi) - 1);
+	if (unlikely(GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg
+					|| segno > TOTAL_SEGS(sbi) - 1)) {
+		f2fs_msg(sbi->sb, KERN_ERR,
+				"Wrong valid blocks %d or segno %u",
+					GET_SIT_VBLOCKS(raw_sit), segno);
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
+		return -EINVAL;
+	}
+	return 0;
 }
 
 static inline pgoff_t current_sit_addr(struct f2fs_sb_info *sbi,

fs/f2fs/sysfs.c

@@ -113,6 +113,9 @@ static ssize_t features_show(struct f2fs_attr *a,
 	if (f2fs_sb_has_quota_ino(sb))
 		len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
 				len ? ", " : "", "quota_ino");
+	if (f2fs_sb_has_inode_crtime(sb))
+		len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+				len ? ", " : "", "inode_crtime");
 	len += snprintf(buf + len, PAGE_SIZE - len, "\n");
 	return len;
 }
@@ -162,7 +165,8 @@ static ssize_t f2fs_sbi_store(struct f2fs_attr *a,
 #endif
 	if (a->struct_type == RESERVED_BLOCKS) {
 		spin_lock(&sbi->stat_lock);
-		if (t > (unsigned long)sbi->user_block_count) {
+		if (t > (unsigned long)(sbi->user_block_count -
+					sbi->root_reserved_blocks)) {
 			spin_unlock(&sbi->stat_lock);
 			return -EINVAL;
 		}
@@ -231,6 +235,7 @@ enum feat_id {
 	FEAT_INODE_CHECKSUM,
 	FEAT_FLEXIBLE_INLINE_XATTR,
 	FEAT_QUOTA_INO,
+	FEAT_INODE_CRTIME,
 };
 
 static ssize_t f2fs_feature_show(struct f2fs_attr *a,
@@ -245,6 +250,7 @@ static ssize_t f2fs_feature_show(struct f2fs_attr *a,
 	case FEAT_INODE_CHECKSUM:
 	case FEAT_FLEXIBLE_INLINE_XATTR:
 	case FEAT_QUOTA_INO:
+	case FEAT_INODE_CRTIME:
 		return snprintf(buf, PAGE_SIZE, "supported\n");
 	}
 	return 0;
@@ -299,6 +305,8 @@ 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]);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, iostat_enable, iostat_enable);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, readdir_ra, readdir_ra);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_pin_file_thresh, gc_pin_file_threshold);
 #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);
@@ -320,6 +328,7 @@ F2FS_FEATURE_RO_ATTR(project_quota, FEAT_PROJECT_QUOTA);
 F2FS_FEATURE_RO_ATTR(inode_checksum, FEAT_INODE_CHECKSUM);
 F2FS_FEATURE_RO_ATTR(flexible_inline_xattr, FEAT_FLEXIBLE_INLINE_XATTR);
 F2FS_FEATURE_RO_ATTR(quota_ino, FEAT_QUOTA_INO);
+F2FS_FEATURE_RO_ATTR(inode_crtime, FEAT_INODE_CRTIME);
 
 #define ATTR_LIST(name) (&f2fs_attr_##name.attr)
 static struct attribute *f2fs_attrs[] = {
@@ -346,6 +355,8 @@ static struct attribute *f2fs_attrs[] = {
 	ATTR_LIST(cp_interval),
 	ATTR_LIST(idle_interval),
 	ATTR_LIST(iostat_enable),
+	ATTR_LIST(readdir_ra),
+	ATTR_LIST(gc_pin_file_thresh),
 #ifdef CONFIG_F2FS_FAULT_INJECTION
 	ATTR_LIST(inject_rate),
 	ATTR_LIST(inject_type),
@@ -371,6 +382,7 @@ static struct attribute *f2fs_feat_attrs[] = {
 	ATTR_LIST(inode_checksum),
 	ATTR_LIST(flexible_inline_xattr),
 	ATTR_LIST(quota_ino),
+	ATTR_LIST(inode_crtime),
 	NULL,
 };
 

fs/f2fs/trace.c

@@ -17,7 +17,7 @@
 #include "trace.h"
 
 static RADIX_TREE(pids, GFP_ATOMIC);
-static spinlock_t pids_lock;
+static struct mutex pids_lock;
 static struct last_io_info last_io;
 
 static inline void __print_last_io(void)
@@ -64,7 +64,7 @@ void f2fs_trace_pid(struct page *page)
 	if (radix_tree_preload(GFP_NOFS))
 		return;
 
-	spin_lock(&pids_lock);
+	mutex_lock(&pids_lock);
 	p = radix_tree_lookup(&pids, pid);
 	if (p == current)
 		goto out;
@@ -77,7 +77,7 @@ void f2fs_trace_pid(struct page *page)
 			MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev),
 			pid, current->comm);
 out:
-	spin_unlock(&pids_lock);
+	mutex_unlock(&pids_lock);
 	radix_tree_preload_end();
 }
 
@@ -122,7 +122,7 @@ void f2fs_trace_ios(struct f2fs_io_info *fio, int flush)
 
 void f2fs_build_trace_ios(void)
 {
-	spin_lock_init(&pids_lock);
+	mutex_init(&pids_lock);
 }
 
 #define PIDVEC_SIZE	128
@@ -150,7 +150,7 @@ void f2fs_destroy_trace_ios(void)
 	pid_t next_pid = 0;
 	unsigned int found;
 
-	spin_lock(&pids_lock);
+	mutex_lock(&pids_lock);
 	while ((found = gang_lookup_pids(pid, next_pid, PIDVEC_SIZE))) {
 		unsigned idx;
 
@@ -158,5 +158,5 @@ void f2fs_destroy_trace_ios(void)
 		for (idx = 0; idx < found; idx++)
 			radix_tree_delete(&pids, pid[idx]);
 	}
-	spin_unlock(&pids_lock);
+	mutex_unlock(&pids_lock);
 }

fs/f2fs/xattr.c

@@ -298,8 +298,8 @@ static int lookup_all_xattrs(struct inode *inode, struct page *ipage,
 	if (!size && !inline_size)
 		return -ENODATA;
 
-	txattr_addr = kzalloc(inline_size + size + XATTR_PADDING_SIZE,
-							GFP_F2FS_ZERO);
+	txattr_addr = f2fs_kzalloc(F2FS_I_SB(inode),
+			inline_size + size + XATTR_PADDING_SIZE, GFP_NOFS);
 	if (!txattr_addr)
 		return -ENOMEM;
 
@@ -351,8 +351,8 @@ static int read_all_xattrs(struct inode *inode, struct page *ipage,
 	void *txattr_addr;
 	int err;
 
-	txattr_addr = kzalloc(inline_size + size + XATTR_PADDING_SIZE,
-							GFP_F2FS_ZERO);
+	txattr_addr = f2fs_kzalloc(F2FS_I_SB(inode),
+			inline_size + size + XATTR_PADDING_SIZE, GFP_NOFS);
 	if (!txattr_addr)
 		return -ENOMEM;
 
@@ -433,6 +433,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
 	if (F2FS_I(inode)->i_xattr_nid) {
 		xpage = get_node_page(sbi, F2FS_I(inode)->i_xattr_nid);
 		if (IS_ERR(xpage)) {
+			err = PTR_ERR(xpage);
 			alloc_nid_failed(sbi, new_nid);
 			goto in_page_out;
 		}
@@ -443,6 +444,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
 		set_new_dnode(&dn, inode, NULL, NULL, new_nid);
 		xpage = new_node_page(&dn, XATTR_NODE_OFFSET);
 		if (IS_ERR(xpage)) {
+			err = PTR_ERR(xpage);
 			alloc_nid_failed(sbi, new_nid);
 			goto in_page_out;
 		}
@@ -598,7 +600,7 @@ static int __f2fs_setxattr(struct inode *inode, int index,
 			goto exit;
 		}
 
-		if (f2fs_xattr_value_same(here, value, size))
+		if (value && f2fs_xattr_value_same(here, value, size))
 			goto exit;
 	} else if ((flags & XATTR_REPLACE)) {
 		error = -ENODATA;

fs/posix_acl.c

@@ -43,7 +43,7 @@ struct posix_acl *get_cached_acl(struct inode *inode, int type)
 		rcu_read_lock();
 		acl = rcu_dereference(*p);
 		if (!acl || is_uncached_acl(acl) ||
-		    atomic_inc_not_zero(&acl->a_refcount))
+		    refcount_inc_not_zero(&acl->a_refcount))
 			break;
 		rcu_read_unlock();
 		cpu_relax();
@@ -164,7 +164,7 @@ EXPORT_SYMBOL(get_acl);
 void
 posix_acl_init(struct posix_acl *acl, int count)
 {
-	atomic_set(&acl->a_refcount, 1);
+	refcount_set(&acl->a_refcount, 1);
 	acl->a_count = count;
 }
 EXPORT_SYMBOL(posix_acl_init);
@@ -197,7 +197,7 @@ posix_acl_clone(const struct posix_acl *acl, gfp_t flags)
 		           sizeof(struct posix_acl_entry);
 		clone = kmemdup(acl, size, flags);
 		if (clone)
-			atomic_set(&clone->a_refcount, 1);
+			refcount_set(&clone->a_refcount, 1);
 	}
 	return clone;
 }

include/linux/f2fs_fs.h

@@ -117,6 +117,7 @@ struct f2fs_super_block {
 /*
  * For checkpoint
  */
+#define CP_NOCRC_RECOVERY_FLAG	0x00000200
 #define CP_TRIMMED_FLAG		0x00000100
 #define CP_NAT_BITS_FLAG	0x00000080
 #define CP_CRC_RECOVERY_FLAG	0x00000040
@@ -212,6 +213,7 @@ struct f2fs_extent {
 #define F2FS_DATA_EXIST		0x08	/* file inline data exist flag */
 #define F2FS_INLINE_DOTS	0x10	/* file having implicit dot dentries */
 #define F2FS_EXTRA_ATTR		0x20	/* file having extra attribute */
+#define F2FS_PIN_FILE		0x40	/* file should not be gced */
 
 struct f2fs_inode {
 	__le16 i_mode;			/* file mode */
@@ -229,7 +231,13 @@ struct f2fs_inode {
 	__le32 i_ctime_nsec;		/* change time in nano scale */
 	__le32 i_mtime_nsec;		/* modification time in nano scale */
 	__le32 i_generation;		/* file version (for NFS) */
-	__le32 i_current_depth;		/* only for directory depth */
+	union {
+		__le32 i_current_depth;	/* only for directory depth */
+		__le16 i_gc_failures;	/*
+					 * # of gc failures on pinned file.
+					 * only for regular files.
+					 */
+	};
 	__le32 i_xattr_nid;		/* nid to save xattr */
 	__le32 i_flags;			/* file attributes */
 	__le32 i_pino;			/* parent inode number */
@@ -245,8 +253,10 @@ struct f2fs_inode {
 			__le16 i_inline_xattr_size;	/* inline xattr size, unit: 4 bytes */
 			__le32 i_projid;	/* project id */
 			__le32 i_inode_checksum;/* inode meta checksum */
+			__le64 i_crtime;	/* creation time */
+			__le32 i_crtime_nsec;	/* creation time in nano scale */
 			__le32 i_extra_end[0];	/* for attribute size calculation */
-		};
+		} __packed;
 		__le32 i_addr[DEF_ADDRS_PER_INODE];	/* Pointers to data blocks */
 	};
 	__le32 i_nid[DEF_NIDS_PER_INODE];	/* direct(2), indirect(2),

include/linux/posix_acl.h

@@ -12,6 +12,7 @@
 #include <linux/bug.h>
 #include <linux/slab.h>
 #include <linux/rcupdate.h>
+#include <linux/refcount.h>
 #include <uapi/linux/posix_acl.h>
 
 struct posix_acl_entry {
@@ -24,7 +25,7 @@ struct posix_acl_entry {
 };
 
 struct posix_acl {
-	atomic_t		a_refcount;
+	refcount_t		a_refcount;
 	struct rcu_head		a_rcu;
 	unsigned int		a_count;
 	struct posix_acl_entry	a_entries[0];
@@ -41,7 +42,7 @@ static inline struct posix_acl *
 posix_acl_dup(struct posix_acl *acl)
 {
 	if (acl)
-		atomic_inc(&acl->a_refcount);
+		refcount_inc(&acl->a_refcount);
 	return acl;
 }
 
@@ -51,7 +52,7 @@ posix_acl_dup(struct posix_acl *acl)
 static inline void
 posix_acl_release(struct posix_acl *acl)
 {
-	if (acl && atomic_dec_and_test(&acl->a_refcount))
+	if (acl && refcount_dec_and_test(&acl->a_refcount))
 		kfree_rcu(acl, a_rcu);
 }
 

include/trace/events/f2fs.h

@@ -147,7 +147,8 @@ TRACE_DEFINE_ENUM(CP_TRIMMED);
 		{ CP_NO_SPC_ROLL,	"no space roll forward" },	\
 		{ CP_NODE_NEED_CP,	"node needs cp" },		\
 		{ CP_FASTBOOT_MODE,	"fastboot mode" },		\
-		{ CP_SPEC_LOG_NUM,	"log type is 2" })
+		{ CP_SPEC_LOG_NUM,	"log type is 2" },		\
+		{ CP_RECOVER_DIR,	"dir needs recovery" })
 
 struct victim_sel_policy;
 struct f2fs_map_blocks;