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
  ...

25 files changed, 1064 insertions, 452 deletions

diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs
index a7799c2fca28..d870b5514d15 100644
--- a/Documentation/ABI/testing/sysfs-fs-f2fs
+++ b/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.
diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index 2bb7c9fc5144..111824199a88 100644
--- a/fs/f2fs/acl.c
+++ b/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;
 }
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 4aa69bc1c70a..512dca8abc7d 100644
--- a/fs/f2fs/checkpoint.c
+++ b/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);
 }
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 455f086cce3d..7578ed1a85e0 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -111,8 +111,13 @@ static void f2fs_write_end_io(struct bio *bio)
 
 		if (unlikely(bio->bi_status)) {
 			mapping_set_error(page->mapping, -EIO);
-			f2fs_stop_checkpoint(sbi, true);
+			if (type == F2FS_WB_CP_DATA)
+				f2fs_stop_checkpoint(sbi, true);
 		}
+
+		f2fs_bug_on(sbi, page->mapping == NODE_MAPPING(sbi) &&
+					page->index != nid_of_node(page));
+
 		dec_page_count(sbi, type);
 		clear_cold_data(page);
 		end_page_writeback(page);
@@ -169,6 +174,7 @@ static bool __same_bdev(struct f2fs_sb_info *sbi,
  * Low-level block read/write IO operations.
  */
 static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr,
+				struct writeback_control *wbc,
 				int npages, bool is_read)
 {
 	struct bio *bio;
@@ -178,6 +184,8 @@ static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr,
 	f2fs_target_device(sbi, blk_addr, bio);
 	bio->bi_end_io = is_read ? f2fs_read_end_io : f2fs_write_end_io;
 	bio->bi_private = is_read ? NULL : sbi;
+	if (wbc)
+		wbc_init_bio(wbc, bio);
 
 	return bio;
 }
@@ -373,7 +381,8 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
 	f2fs_trace_ios(fio, 0);
 
 	/* Allocate a new bio */
-	bio = __bio_alloc(fio->sbi, fio->new_blkaddr, 1, is_read_io(fio->op));
+	bio = __bio_alloc(fio->sbi, fio->new_blkaddr, fio->io_wbc,
+				1, is_read_io(fio->op));
 
 	if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
 		bio_put(bio);
@@ -435,7 +444,7 @@ alloc_new:
 			dec_page_count(sbi, WB_DATA_TYPE(bio_page));
 			goto out_fail;
 		}
-		io->bio = __bio_alloc(sbi, fio->new_blkaddr,
+		io->bio = __bio_alloc(sbi, fio->new_blkaddr, fio->io_wbc,
 						BIO_MAX_PAGES, false);
 		io->fio = *fio;
 	}
@@ -445,6 +454,9 @@ alloc_new:
 		goto alloc_new;
 	}
 
+	if (fio->io_wbc)
+		wbc_account_io(fio->io_wbc, bio_page, PAGE_SIZE);
+
 	io->last_block_in_bio = fio->new_blkaddr;
 	f2fs_trace_ios(fio, 0);
 
@@ -783,7 +795,7 @@ got_it:
 	return page;
 }
 
-static int __allocate_data_block(struct dnode_of_data *dn)
+static int __allocate_data_block(struct dnode_of_data *dn, int seg_type)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
 	struct f2fs_summary sum;
@@ -808,7 +820,7 @@ alloc:
 	set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
 
 	allocate_data_block(sbi, NULL, dn->data_blkaddr, &dn->data_blkaddr,
-					&sum, CURSEG_WARM_DATA, NULL, false);
+					&sum, seg_type, NULL, false);
 	set_data_blkaddr(dn);
 
 	/* update i_size */
@@ -831,10 +843,12 @@ int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct inode *inode = file_inode(iocb->ki_filp);
 	struct f2fs_map_blocks map;
+	int flag;
 	int err = 0;
+	bool direct_io = iocb->ki_flags & IOCB_DIRECT;
 
 	/* convert inline data for Direct I/O*/
-	if (iocb->ki_flags & IOCB_DIRECT) {
+	if (direct_io) {
 		err = f2fs_convert_inline_inode(inode);
 		if (err)
 			return err;
@@ -851,19 +865,33 @@ int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
 		map.m_len = 0;
 
 	map.m_next_pgofs = NULL;
+	map.m_next_extent = NULL;
+	map.m_seg_type = NO_CHECK_TYPE;
 
-	if (iocb->ki_flags & IOCB_DIRECT)
-		return f2fs_map_blocks(inode, &map, 1,
-			__force_buffered_io(inode, WRITE) ?
-				F2FS_GET_BLOCK_PRE_AIO :
-				F2FS_GET_BLOCK_PRE_DIO);
+	if (direct_io) {
+		map.m_seg_type = rw_hint_to_seg_type(iocb->ki_hint);
+		flag = __force_buffered_io(inode, WRITE) ?
+					F2FS_GET_BLOCK_PRE_AIO :
+					F2FS_GET_BLOCK_PRE_DIO;
+		goto map_blocks;
+	}
 	if (iocb->ki_pos + iov_iter_count(from) > MAX_INLINE_DATA(inode)) {
 		err = f2fs_convert_inline_inode(inode);
 		if (err)
 			return err;
 	}
-	if (!f2fs_has_inline_data(inode))
-		return f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_AIO);
+	if (f2fs_has_inline_data(inode))
+		return err;
+
+	flag = F2FS_GET_BLOCK_PRE_AIO;
+
+map_blocks:
+	err = f2fs_map_blocks(inode, &map, 1, flag);
+	if (map.m_len > 0 && err == -ENOSPC) {
+		if (!direct_io)
+			set_inode_flag(inode, FI_NO_PREALLOC);
+		err = 0;
+	}
 	return err;
 }
 
@@ -904,6 +932,7 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
 	blkcnt_t prealloc;
 	struct extent_info ei = {0,0,0};
 	block_t blkaddr;
+	unsigned int start_pgofs;
 
 	if (!maxblocks)
 		return 0;
@@ -919,6 +948,8 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
 		map->m_pblk = ei.blk + pgofs - ei.fofs;
 		map->m_len = min((pgoff_t)maxblocks, ei.fofs + ei.len - pgofs);
 		map->m_flags = F2FS_MAP_MAPPED;
+		if (map->m_next_extent)
+			*map->m_next_extent = pgofs + map->m_len;
 		goto out;
 	}
 
@@ -937,10 +968,14 @@ next_dnode:
 			if (map->m_next_pgofs)
 				*map->m_next_pgofs =
 					get_next_page_offset(&dn, pgofs);
+			if (map->m_next_extent)
+				*map->m_next_extent =
+					get_next_page_offset(&dn, pgofs);
 		}
 		goto unlock_out;
 	}
 
+	start_pgofs = pgofs;
 	prealloc = 0;
 	last_ofs_in_node = ofs_in_node = dn.ofs_in_node;
 	end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
@@ -960,7 +995,8 @@ next_block:
 					last_ofs_in_node = dn.ofs_in_node;
 				}
 			} else {
-				err = __allocate_data_block(&dn);
+				err = __allocate_data_block(&dn,
+							map->m_seg_type);
 				if (!err)
 					set_inode_flag(inode, FI_APPEND_WRITE);
 			}
@@ -973,14 +1009,20 @@ next_block:
 				map->m_pblk = 0;
 				goto sync_out;
 			}
+			if (flag == F2FS_GET_BLOCK_PRECACHE)
+				goto sync_out;
 			if (flag == F2FS_GET_BLOCK_FIEMAP &&
 						blkaddr == NULL_ADDR) {
 				if (map->m_next_pgofs)
 					*map->m_next_pgofs = pgofs + 1;
+				goto sync_out;
 			}
-			if (flag != F2FS_GET_BLOCK_FIEMAP ||
-						blkaddr != NEW_ADDR)
+			if (flag != F2FS_GET_BLOCK_FIEMAP) {
+				/* for defragment case */
+				if (map->m_next_pgofs)
+					*map->m_next_pgofs = pgofs + 1;
 				goto sync_out;
+			}
 		}
 	}
 
@@ -1031,6 +1073,16 @@ skip:
 	else if (dn.ofs_in_node < end_offset)
 		goto next_block;
 
+	if (flag == F2FS_GET_BLOCK_PRECACHE) {
+		if (map->m_flags & F2FS_MAP_MAPPED) {
+			unsigned int ofs = start_pgofs - map->m_lblk;
+
+			f2fs_update_extent_cache_range(&dn,
+				start_pgofs, map->m_pblk + ofs,
+				map->m_len - ofs);
+		}
+	}
+
 	f2fs_put_dnode(&dn);
 
 	if (create) {
@@ -1040,6 +1092,17 @@ skip:
 	goto next_dnode;
 
 sync_out:
+	if (flag == F2FS_GET_BLOCK_PRECACHE) {
+		if (map->m_flags & F2FS_MAP_MAPPED) {
+			unsigned int ofs = start_pgofs - map->m_lblk;
+
+			f2fs_update_extent_cache_range(&dn,
+				start_pgofs, map->m_pblk + ofs,
+				map->m_len - ofs);
+		}
+		if (map->m_next_extent)
+			*map->m_next_extent = pgofs + 1;
+	}
 	f2fs_put_dnode(&dn);
 unlock_out:
 	if (create) {
@@ -1053,7 +1116,7 @@ out:
 
 static int __get_data_block(struct inode *inode, sector_t iblock,
 			struct buffer_head *bh, int create, int flag,
-			pgoff_t *next_pgofs)
+			pgoff_t *next_pgofs, int seg_type)
 {
 	struct f2fs_map_blocks map;
 	int err;
@@ -1061,6 +1124,8 @@ static int __get_data_block(struct inode *inode, sector_t iblock,
 	map.m_lblk = iblock;
 	map.m_len = bh->b_size >> inode->i_blkbits;
 	map.m_next_pgofs = next_pgofs;
+	map.m_next_extent = NULL;
+	map.m_seg_type = seg_type;
 
 	err = f2fs_map_blocks(inode, &map, create, flag);
 	if (!err) {
@@ -1076,14 +1141,17 @@ static int get_data_block(struct inode *inode, sector_t iblock,
 			pgoff_t *next_pgofs)
 {
 	return __get_data_block(inode, iblock, bh_result, create,
-							flag, next_pgofs);
+							flag, next_pgofs,
+							NO_CHECK_TYPE);
 }
 
 static int get_data_block_dio(struct inode *inode, sector_t iblock,
 			struct buffer_head *bh_result, int create)
 {
 	return __get_data_block(inode, iblock, bh_result, create,
-						F2FS_GET_BLOCK_DEFAULT, NULL);
+						F2FS_GET_BLOCK_DEFAULT, NULL,
+						rw_hint_to_seg_type(
+							inode->i_write_hint));
 }
 
 static int get_data_block_bmap(struct inode *inode, sector_t iblock,
@@ -1094,7 +1162,8 @@ static int get_data_block_bmap(struct inode *inode, sector_t iblock,
 		return -EFBIG;
 
 	return __get_data_block(inode, iblock, bh_result, create,
-						F2FS_GET_BLOCK_BMAP, NULL);
+						F2FS_GET_BLOCK_BMAP, NULL,
+						NO_CHECK_TYPE);
 }
 
 static inline sector_t logical_to_blk(struct inode *inode, loff_t offset)
@@ -1107,6 +1176,68 @@ static inline loff_t blk_to_logical(struct inode *inode, sector_t blk)
 	return (blk << inode->i_blkbits);
 }
 
+static int f2fs_xattr_fiemap(struct inode *inode,
+				struct fiemap_extent_info *fieinfo)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct page *page;
+	struct node_info ni;
+	__u64 phys = 0, len;
+	__u32 flags;
+	nid_t xnid = F2FS_I(inode)->i_xattr_nid;
+	int err = 0;
+
+	if (f2fs_has_inline_xattr(inode)) {
+		int offset;
+
+		page = f2fs_grab_cache_page(NODE_MAPPING(sbi),
+						inode->i_ino, false);
+		if (!page)
+			return -ENOMEM;
+
+		get_node_info(sbi, inode->i_ino, &ni);
+
+		phys = (__u64)blk_to_logical(inode, ni.blk_addr);
+		offset = offsetof(struct f2fs_inode, i_addr) +
+					sizeof(__le32) * (DEF_ADDRS_PER_INODE -
+					get_inline_xattr_addrs(inode));
+
+		phys += offset;
+		len = inline_xattr_size(inode);
+
+		f2fs_put_page(page, 1);
+
+		flags = FIEMAP_EXTENT_DATA_INLINE | FIEMAP_EXTENT_NOT_ALIGNED;
+
+		if (!xnid)
+			flags |= FIEMAP_EXTENT_LAST;
+
+		err = fiemap_fill_next_extent(fieinfo, 0, phys, len, flags);
+		if (err || err == 1)
+			return err;
+	}
+
+	if (xnid) {
+		page = f2fs_grab_cache_page(NODE_MAPPING(sbi), xnid, false);
+		if (!page)
+			return -ENOMEM;
+
+		get_node_info(sbi, xnid, &ni);
+
+		phys = (__u64)blk_to_logical(inode, ni.blk_addr);
+		len = inode->i_sb->s_blocksize;
+
+		f2fs_put_page(page, 1);
+
+		flags = FIEMAP_EXTENT_LAST;
+	}
+
+	if (phys)
+		err = fiemap_fill_next_extent(fieinfo, 0, phys, len, flags);
+
+	return (err < 0 ? err : 0);
+}
+
 int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		u64 start, u64 len)
 {
@@ -1117,18 +1248,29 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	u32 flags = 0;
 	int ret = 0;
 
-	ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC);
+	if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) {
+		ret = f2fs_precache_extents(inode);
+		if (ret)
+			return ret;
+	}
+
+	ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC | FIEMAP_FLAG_XATTR);
 	if (ret)
 		return ret;
 
+	inode_lock(inode);
+
+	if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) {
+		ret = f2fs_xattr_fiemap(inode, fieinfo);
+		goto out;
+	}
+
 	if (f2fs_has_inline_data(inode)) {
 		ret = f2fs_inline_data_fiemap(inode, fieinfo, start, len);
 		if (ret != -EAGAIN)
-			return ret;
+			goto out;
 	}
 
-	inode_lock(inode);
-
 	if (logical_to_blk(inode, len) == 0)
 		len = blk_to_logical(inode, 1);
 
@@ -1198,7 +1340,6 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
 			unsigned nr_pages)
 {
 	struct bio *bio = NULL;
-	unsigned page_idx;
 	sector_t last_block_in_bio = 0;
 	struct inode *inode = mapping->host;
 	const unsigned blkbits = inode->i_blkbits;
@@ -1214,9 +1355,10 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
 	map.m_len = 0;
 	map.m_flags = 0;
 	map.m_next_pgofs = NULL;
+	map.m_next_extent = NULL;
+	map.m_seg_type = NO_CHECK_TYPE;
 
-	for (page_idx = 0; nr_pages; page_idx++, nr_pages--) {
-
+	for (; nr_pages; nr_pages--) {
 		if (pages) {
 			page = list_last_entry(pages, struct page, lru);
 
@@ -1376,18 +1518,79 @@ retry_encrypt:
 	return PTR_ERR(fio->encrypted_page);
 }
 
+static inline bool check_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 (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;
+}
+
+bool should_update_inplace(struct inode *inode, struct f2fs_io_info *fio)
+{
+	if (f2fs_is_pinned_file(inode))
+		return true;
+
+	/* if this is cold file, we should overwrite to avoid fragmentation */
+	if (file_is_cold(inode))
+		return true;
+
+	return check_inplace_update_policy(inode, fio);
+}
+
+bool should_update_outplace(struct inode *inode, struct f2fs_io_info *fio)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+
+	if (test_opt(sbi, LFS))
+		return true;
+	if (S_ISDIR(inode->i_mode))
+		return true;
+	if (f2fs_is_atomic_file(inode))
+		return true;
+	if (fio) {
+		if (is_cold_data(fio->page))
+			return true;
+		if (IS_ATOMIC_WRITTEN_PAGE(fio->page))
+			return true;
+	}
+	return false;
+}
+
 static inline bool need_inplace_update(struct f2fs_io_info *fio)
 {
 	struct inode *inode = fio->page->mapping->host;
 
-	if (S_ISDIR(inode->i_mode) || f2fs_is_atomic_file(inode))
-		return false;
-	if (is_cold_data(fio->page))
-		return false;
-	if (IS_ATOMIC_WRITTEN_PAGE(fio->page))
+	if (should_update_outplace(inode, fio))
 		return false;
 
-	return need_inplace_update_policy(inode, fio);
+	return should_update_inplace(inode, fio);
 }
 
 static inline bool valid_ipu_blkaddr(struct f2fs_io_info *fio)
@@ -1508,10 +1711,17 @@ static int __write_data_page(struct page *page, bool *submitted,
 		.submitted = false,
 		.need_lock = LOCK_RETRY,
 		.io_type = io_type,
+		.io_wbc = wbc,
 	};
 
 	trace_f2fs_writepage(page, DATA);
 
+	/* we should bypass data pages to proceed the kworkder jobs */
+	if (unlikely(f2fs_cp_error(sbi))) {
+		mapping_set_error(page->mapping, -EIO);
+		goto out;
+	}
+
 	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
 		goto redirty_out;
 
@@ -1536,12 +1746,6 @@ write:
 			available_free_memory(sbi, BASE_CHECK))))
 		goto redirty_out;
 
-	/* we should bypass data pages to proceed the kworkder jobs */
-	if (unlikely(f2fs_cp_error(sbi))) {
-		mapping_set_error(page->mapping, -EIO);
-		goto out;
-	}
-
 	/* Dentry blocks are controlled by checkpoint */
 	if (S_ISDIR(inode->i_mode)) {
 		fio.need_lock = LOCK_DONE;
@@ -1571,10 +1775,14 @@ write:
 		}
 	}
 
-	down_write(&F2FS_I(inode)->i_sem);
-	if (F2FS_I(inode)->last_disk_size < psize)
-		F2FS_I(inode)->last_disk_size = psize;
-	up_write(&F2FS_I(inode)->i_sem);
+	if (err) {
+		file_set_keep_isize(inode);
+	} else {
+		down_write(&F2FS_I(inode)->i_sem);
+		if (F2FS_I(inode)->last_disk_size < psize)
+			F2FS_I(inode)->last_disk_size = psize;
+		up_write(&F2FS_I(inode)->i_sem);
+	}
 
 done:
 	if (err && err != -ENOENT)
@@ -1933,7 +2141,7 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct page *page = NULL;
 	pgoff_t index = ((unsigned long long) pos) >> PAGE_SHIFT;
-	bool need_balance = false;
+	bool need_balance = false, drop_atomic = false;
 	block_t blkaddr = NULL_ADDR;
 	int err = 0;
 
@@ -1942,6 +2150,7 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
 	if (f2fs_is_atomic_file(inode) &&
 			!available_free_memory(sbi, INMEM_PAGES)) {
 		err = -ENOMEM;
+		drop_atomic = true;
 		goto fail;
 	}
 
@@ -2022,7 +2231,7 @@ repeat:
 fail:
 	f2fs_put_page(page, 1);
 	f2fs_write_failed(mapping, pos + len);
-	if (f2fs_is_atomic_file(inode))
+	if (drop_atomic)
 		drop_inmem_pages_all(sbi);
 	return err;
 }
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index ecada8425268..a66107b5cfff 100644
--- a/fs/f2fs/debug.c
+++ b/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;
 
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 2d98d877c09d..f00b5ed8c011 100644
--- a/fs/f2fs/dir.c
+++ b/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;
 	}
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 6abf26c31d01..6300ac5bcbe4 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -19,6 +19,7 @@
 #include <linux/magic.h>
 #include <linux/kobject.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/vmalloc.h>
 #include <linux/bio.h>
 #include <linux/blkdev.h>
@@ -43,6 +44,7 @@
 #ifdef CONFIG_F2FS_FAULT_INJECTION
 enum {
 	FAULT_KMALLOC,
+	FAULT_KVMALLOC,
 	FAULT_PAGE_ALLOC,
 	FAULT_PAGE_GET,
 	FAULT_ALLOC_BIO,
@@ -94,6 +96,7 @@ extern char *fault_name[FAULT_MAX];
 #define F2FS_MOUNT_PRJQUOTA		0x00200000
 #define F2FS_MOUNT_QUOTA		0x00400000
 #define F2FS_MOUNT_INLINE_XATTR_SIZE	0x00800000
+#define F2FS_MOUNT_RESERVE_ROOT		0x01000000
 
 #define clear_opt(sbi, option)	((sbi)->mount_opt.opt &= ~F2FS_MOUNT_##option)
 #define set_opt(sbi, option)	((sbi)->mount_opt.opt |= F2FS_MOUNT_##option)
@@ -121,6 +124,7 @@ struct f2fs_mount_info {
 #define F2FS_FEATURE_INODE_CHKSUM	0x0020
 #define F2FS_FEATURE_FLEXIBLE_INLINE_XATTR	0x0040
 #define F2FS_FEATURE_QUOTA_INO		0x0080
+#define F2FS_FEATURE_INODE_CRTIME	0x0100
 
 #define F2FS_HAS_FEATURE(sb, mask)					\
 	((F2FS_SB(sb)->raw_super->feature & cpu_to_le32(mask)) != 0)
@@ -130,6 +134,12 @@ struct f2fs_mount_info {
 	(F2FS_SB(sb)->raw_super->feature &= ~cpu_to_le32(mask))
 
 /*
+ * Default values for user and/or group using reserved blocks
+ */
+#define	F2FS_DEF_RESUID		0
+#define	F2FS_DEF_RESGID		0
+
+/*
  * For checkpoint manager
  */
 enum {
@@ -179,6 +189,7 @@ enum {
 	ORPHAN_INO,		/* for orphan ino list */
 	APPEND_INO,		/* for append ino list */
 	UPDATE_INO,		/* for update ino list */
+	TRANS_DIR_INO,		/* for trasactions dir ino list */
 	FLUSH_INO,		/* for multiple device flushing */
 	MAX_INO_ENTRY,		/* max. list */
 };
@@ -264,7 +275,6 @@ struct discard_cmd_control {
 	struct task_struct *f2fs_issue_discard;	/* discard thread */
 	struct list_head entry_list;		/* 4KB discard entry list */
 	struct list_head pend_list[MAX_PLIST_NUM];/* store pending entries */
-	unsigned char pend_list_tag[MAX_PLIST_NUM];/* tag for pending entries */
 	struct list_head wait_list;		/* store on-flushing entries */
 	struct list_head fstrim_list;		/* in-flight discard from fstrim */
 	wait_queue_head_t discard_wait_queue;	/* waiting queue for wake-up */
@@ -347,6 +357,9 @@ static inline bool __has_cursum_space(struct f2fs_journal *journal,
 #define F2FS_IOC_GARBAGE_COLLECT_RANGE	_IOW(F2FS_IOCTL_MAGIC, 11,	\
 						struct f2fs_gc_range)
 #define F2FS_IOC_GET_FEATURES		_IOR(F2FS_IOCTL_MAGIC, 12, __u32)
+#define F2FS_IOC_SET_PIN_FILE		_IOW(F2FS_IOCTL_MAGIC, 13, __u32)
+#define F2FS_IOC_GET_PIN_FILE		_IOR(F2FS_IOCTL_MAGIC, 14, __u32)
+#define F2FS_IOC_PRECACHE_EXTENTS	_IO(F2FS_IOCTL_MAGIC, 15)
 
 #define F2FS_IOC_SET_ENCRYPTION_POLICY	FS_IOC_SET_ENCRYPTION_POLICY
 #define F2FS_IOC_GET_ENCRYPTION_POLICY	FS_IOC_GET_ENCRYPTION_POLICY
@@ -402,10 +415,9 @@ struct f2fs_flush_device {
 #define DEF_MIN_INLINE_SIZE		1
 static inline int get_extra_isize(struct inode *inode);
 static inline int get_inline_xattr_addrs(struct inode *inode);
-#define F2FS_INLINE_XATTR_ADDRS(inode)	get_inline_xattr_addrs(inode)
 #define MAX_INLINE_DATA(inode)	(sizeof(__le32) *			\
 				(CUR_ADDRS_PER_INODE(inode) -		\
-				F2FS_INLINE_XATTR_ADDRS(inode) -	\
+				get_inline_xattr_addrs(inode) -	\
 				DEF_INLINE_RESERVED_SIZE))
 
 /* for inline dir */
@@ -542,6 +554,8 @@ struct f2fs_map_blocks {
 	unsigned int m_len;
 	unsigned int m_flags;
 	pgoff_t *m_next_pgofs;		/* point next possible non-hole pgofs */
+	pgoff_t *m_next_extent;		/* point to next possible extent */
+	int m_seg_type;
 };
 
 /* for flag in get_data_block */
@@ -551,6 +565,7 @@ enum {
 	F2FS_GET_BLOCK_BMAP,
 	F2FS_GET_BLOCK_PRE_DIO,
 	F2FS_GET_BLOCK_PRE_AIO,
+	F2FS_GET_BLOCK_PRECACHE,
 };
 
 /*
@@ -583,7 +598,10 @@ struct f2fs_inode_info {
 	unsigned long i_flags;		/* keep an inode flags for ioctl */
 	unsigned char i_advise;		/* use to give file attribute hints */
 	unsigned char i_dir_level;	/* use for dentry level for large dir */
-	unsigned int i_current_depth;	/* use only in directory structure */
+	union {
+		unsigned int i_current_depth;	/* only for directory depth */
+		unsigned short i_gc_failures;	/* only for regular file */
+	};
 	unsigned int i_pino;		/* parent inode number */
 	umode_t i_acl_mode;		/* keep file acl mode temporarily */
 
@@ -618,6 +636,7 @@ struct f2fs_inode_info {
 	int i_extra_isize;		/* size of extra space located in i_addr */
 	kprojid_t i_projid;		/* id for project quota */
 	int i_inline_xattr_size;	/* inline xattr size */
+	struct timespec i_crtime;	/* inode creation time */
 };
 
 static inline void get_extent_info(struct extent_info *ext,
@@ -922,6 +941,7 @@ enum cp_reason_type {
 	CP_NODE_NEED_CP,
 	CP_FASTBOOT_MODE,
 	CP_SPEC_LOG_NUM,
+	CP_RECOVER_DIR,
 };
 
 enum iostat_type {
@@ -957,6 +977,7 @@ struct f2fs_io_info {
 	int need_lock;		/* indicate we need to lock cp_rwsem */
 	bool in_list;		/* indicate fio is in io_list */
 	enum iostat_type io_type;	/* io type */
+	struct writeback_control *io_wbc; /* writeback control */
 };
 
 #define is_read_io(rw) ((rw) == READ)
@@ -1093,6 +1114,7 @@ struct f2fs_sb_info {
 	int dir_level;				/* directory level */
 	int inline_xattr_size;			/* inline xattr size */
 	unsigned int trigger_ssr_threshold;	/* threshold to trigger ssr */
+	int readdir_ra;				/* readahead inode in readdir */
 
 	block_t user_block_count;		/* # of user blocks */
 	block_t total_valid_block_count;	/* # of valid blocks */
@@ -1100,6 +1122,11 @@ struct f2fs_sb_info {
 	block_t last_valid_block_count;		/* for recovery */
 	block_t reserved_blocks;		/* configurable reserved blocks */
 	block_t current_reserved_blocks;	/* current reserved blocks */
+	block_t root_reserved_blocks;		/* root reserved blocks */
+	kuid_t s_resuid;			/* reserved blocks for uid */
+	kgid_t s_resgid;			/* reserved blocks for gid */
+
+	unsigned int nquota_files;		/* # of quota sysfile */
 
 	u32 s_next_generation;			/* for NFS support */
 
@@ -1124,6 +1151,9 @@ struct f2fs_sb_info {
 	/* threshold for converting bg victims for fg */
 	u64 fggc_threshold;
 
+	/* threshold for gc trials on pinned files */
+	u64 gc_pin_file_threshold;
+
 	/* maximum # of trials to f