Merge tag 'for-f2fs-4.8' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "The major change in this version is mitigating cpu overheads on write
  paths by replacing redundant inode page updates with mark_inode_dirty
  calls.  And we tried to reduce lock contentions as well to improve
  filesystem scalability.  Other feature is setting F2FS automatically
  when detecting host-managed SMR.

  Enhancements:
   - ioctl to move a range of data between files
   - inject orphan inode errors
   - avoid flush commands congestion
   - support lazytime

  Bug fixes:
   - return proper results for some dentry operations
   - fix deadlock in add_link failure
   - disable extent_cache for fcollapse/finsert"

* tag 'for-f2fs-4.8' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (68 commits)
  f2fs: clean up coding style and redundancy
  f2fs: get victim segment again after new cp
  f2fs: handle error case with f2fs_bug_on
  f2fs: avoid data race when deciding checkpoin in f2fs_sync_file
  f2fs: support an ioctl to move a range of data blocks
  f2fs: fix to report error number of f2fs_find_entry
  f2fs: avoid memory allocation failure due to a long length
  f2fs: reset default idle interval value
  f2fs: use blk_plug in all the possible paths
  f2fs: fix to avoid data update racing between GC and DIO
  f2fs: add maximum prefree segments
  f2fs: disable extent_cache for fcollapse/finsert inodes
  f2fs: refactor __exchange_data_block for speed up
  f2fs: fix ERR_PTR returned by bio
  f2fs: avoid mark_inode_dirty
  f2fs: move i_size_write in f2fs_write_end
  f2fs: fix to avoid redundant discard during fstrim
  f2fs: avoid mismatching block range for discard
  f2fs: fix incorrect f_bfree calculation in ->statfs
  f2fs: use percpu_rw_semaphore
  ...

22 files changed, 1387 insertions, 750 deletions

diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt
index e1c9f0849da6..ecd808088362 100644
--- a/Documentation/filesystems/f2fs.txt
+++ b/Documentation/filesystems/f2fs.txt
@@ -109,7 +109,9 @@ background_gc=%s       Turn on/off cleaning operations, namely garbage
 disable_roll_forward   Disable the roll-forward recovery routine
 norecovery             Disable the roll-forward recovery routine, mounted read-
                        only (i.e., -o ro,disable_roll_forward)
-discard                Issue discard/TRIM commands when a segment is cleaned.
+discard/nodiscard      Enable/disable real-time discard in f2fs, if discard is
+                       enabled, f2fs will issue discard/TRIM commands when a
+		       segment is cleaned.
 no_heap                Disable heap-style segment allocation which finds free
                        segments for data from the beginning of main area, while
 		       for node from the end of main area.
@@ -151,6 +153,9 @@ noinline_data          Disable the inline data feature, inline data feature is
                        enabled by default.
 data_flush             Enable data flushing before checkpoint in order to
                        persist data of regular and symlink.
+mode=%s                Control block allocation mode which supports "adaptive"
+                       and "lfs". In "lfs" mode, there should be no random
+                       writes towards main area.
 
 ================================================================================
 DEBUGFS ENTRIES
diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index a31c7e859af6..4dcc9e28dc5c 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -201,7 +201,6 @@ struct posix_acl *f2fs_get_acl(struct inode *inode, int type)
 static int __f2fs_set_acl(struct inode *inode, int type,
 			struct posix_acl *acl, struct page *ipage)
 {
-	struct f2fs_inode_info *fi = F2FS_I(inode);
 	int name_index;
 	void *value = NULL;
 	size_t size = 0;
@@ -214,7 +213,7 @@ static int __f2fs_set_acl(struct inode *inode, int type,
 			error = posix_acl_equiv_mode(acl, &inode->i_mode);
 			if (error < 0)
 				return error;
-			set_acl_inode(fi, inode->i_mode);
+			set_acl_inode(inode, inode->i_mode);
 			if (error == 0)
 				acl = NULL;
 		}
@@ -233,7 +232,7 @@ static int __f2fs_set_acl(struct inode *inode, int type,
 	if (acl) {
 		value = f2fs_acl_to_disk(acl, &size);
 		if (IS_ERR(value)) {
-			clear_inode_flag(fi, FI_ACL_MODE);
+			clear_inode_flag(inode, FI_ACL_MODE);
 			return (int)PTR_ERR(value);
 		}
 	}
@@ -244,7 +243,7 @@ static int __f2fs_set_acl(struct inode *inode, int type,
 	if (!error)
 		set_cached_acl(inode, type, acl);
 
-	clear_inode_flag(fi, FI_ACL_MODE);
+	clear_inode_flag(inode, FI_ACL_MODE);
 	return error;
 }
 
@@ -385,6 +384,8 @@ int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage,
 	if (error)
 		return error;
 
+	f2fs_mark_inode_dirty_sync(inode);
+
 	if (default_acl) {
 		error = __f2fs_set_acl(inode, ACL_TYPE_DEFAULT, default_acl,
 				       ipage);
diff --git a/fs/f2fs/acl.h b/fs/f2fs/acl.h
index 997ca8edb6cb..b2334d11dae8 100644
--- a/fs/f2fs/acl.h
+++ b/fs/f2fs/acl.h
@@ -37,7 +37,7 @@ struct f2fs_acl_header {
 #ifdef CONFIG_F2FS_FS_POSIX_ACL
 
 extern struct posix_acl *f2fs_get_acl(struct inode *, int);
-extern int f2fs_set_acl(struct inode *inode, struct posix_acl *acl, int type);
+extern int f2fs_set_acl(struct inode *, struct posix_acl *, int);
 extern int f2fs_init_acl(struct inode *, struct inode *, struct page *,
 							struct page *);
 #else
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 124b4a3017b5..f94d01e7d001 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -48,7 +48,8 @@ repeat:
 		goto repeat;
 	}
 	f2fs_wait_on_page_writeback(page, META, true);
-	SetPageUptodate(page);
+	if (!PageUptodate(page))
+		SetPageUptodate(page);
 	return page;
 }
 
@@ -266,6 +267,7 @@ static int f2fs_write_meta_pages(struct address_space *mapping,
 				struct writeback_control *wbc)
 {
 	struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
+	struct blk_plug plug;
 	long diff, written;
 
 	/* collect a number of dirty meta pages and write together */
@@ -278,7 +280,9 @@ static int f2fs_write_meta_pages(struct address_space *mapping,
 	/* if mounting is failed, skip writing node pages */
 	mutex_lock(&sbi->cp_mutex);
 	diff = nr_pages_to_write(sbi, META, wbc);
+	blk_start_plug(&plug);
 	written = sync_meta_pages(sbi, META, wbc->nr_to_write);
+	blk_finish_plug(&plug);
 	mutex_unlock(&sbi->cp_mutex);
 	wbc->nr_to_write = max((long)0, wbc->nr_to_write - written - diff);
 	return 0;
@@ -366,9 +370,10 @@ static int f2fs_set_meta_page_dirty(struct page *page)
 {
 	trace_f2fs_set_page_dirty(page, META);
 
-	SetPageUptodate(page);
+	if (!PageUptodate(page))
+		SetPageUptodate(page);
 	if (!PageDirty(page)) {
-		__set_page_dirty_nobuffers(page);
+		f2fs_set_page_dirty_nobuffers(page);
 		inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_META);
 		SetPagePrivate(page);
 		f2fs_trace_pid(page);
@@ -510,10 +515,11 @@ void release_orphan_inode(struct f2fs_sb_info *sbi)
 	spin_unlock(&im->ino_lock);
 }
 
-void add_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
+void add_orphan_inode(struct inode *inode)
 {
 	/* add new orphan ino entry into list */
-	__add_ino_entry(sbi, ino, ORPHAN_INO);
+	__add_ino_entry(F2FS_I_SB(inode), inode->i_ino, ORPHAN_INO);
+	update_inode_page(inode);
 }
 
 void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
@@ -761,28 +767,25 @@ fail_no_cp:
 static void __add_dirty_inode(struct inode *inode, enum inode_type type)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct f2fs_inode_info *fi = F2FS_I(inode);
 	int flag = (type == DIR_INODE) ? FI_DIRTY_DIR : FI_DIRTY_FILE;
 
-	if (is_inode_flag_set(fi, flag))
+	if (is_inode_flag_set(inode, flag))
 		return;
 
-	set_inode_flag(fi, flag);
-	list_add_tail(&fi->dirty_list, &sbi->inode_list[type]);
+	set_inode_flag(inode, flag);
+	list_add_tail(&F2FS_I(inode)->dirty_list, &sbi->inode_list[type]);
 	stat_inc_dirty_inode(sbi, type);
 }
 
 static void __remove_dirty_inode(struct inode *inode, enum inode_type type)
 {
-	struct f2fs_inode_info *fi = F2FS_I(inode);
 	int flag = (type == DIR_INODE) ? FI_DIRTY_DIR : FI_DIRTY_FILE;
 
-	if (get_dirty_pages(inode) ||
-			!is_inode_flag_set(F2FS_I(inode), flag))
+	if (get_dirty_pages(inode) || !is_inode_flag_set(inode, flag))
 		return;
 
-	list_del_init(&fi->dirty_list);
-	clear_inode_flag(fi, flag);
+	list_del_init(&F2FS_I(inode)->dirty_list);
+	clear_inode_flag(inode, flag);
 	stat_dec_dirty_inode(F2FS_I_SB(inode), type);
 }
 
@@ -795,13 +798,12 @@ void update_dirty_page(struct inode *inode, struct page *page)
 			!S_ISLNK(inode->i_mode))
 		return;
 
-	if (type != FILE_INODE || test_opt(sbi, DATA_FLUSH)) {
-		spin_lock(&sbi->inode_lock[type]);
+	spin_lock(&sbi->inode_lock[type]);
+	if (type != FILE_INODE || test_opt(sbi, DATA_FLUSH))
 		__add_dirty_inode(inode, type);
-		spin_unlock(&sbi->inode_lock[type]);
-	}
-
 	inode_inc_dirty_pages(inode);
+	spin_unlock(&sbi->inode_lock[type]);
+
 	SetPagePrivate(page);
 	f2fs_trace_pid(page);
 }
@@ -864,6 +866,34 @@ retry:
 	goto retry;
 }
 
+int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi)
+{
+	struct list_head *head = &sbi->inode_list[DIRTY_META];
+	struct inode *inode;
+	struct f2fs_inode_info *fi;
+	s64 total = get_pages(sbi, F2FS_DIRTY_IMETA);
+
+	while (total--) {
+		if (unlikely(f2fs_cp_error(sbi)))
+			return -EIO;
+
+		spin_lock(&sbi->inode_lock[DIRTY_META]);
+		if (list_empty(head)) {
+			spin_unlock(&sbi->inode_lock[DIRTY_META]);
+			return 0;
+		}
+		fi = list_entry(head->next, struct f2fs_inode_info,
+							gdirty_list);
+		inode = igrab(&fi->vfs_inode);
+		spin_unlock(&sbi->inode_lock[DIRTY_META]);
+		if (inode) {
+			update_inode_page(inode);
+			iput(inode);
+		}
+	};
+	return 0;
+}
+
 /*
  * Freeze all the FS-operations for checkpoint.
  */
@@ -890,6 +920,14 @@ retry_flush_dents:
 		goto retry_flush_dents;
 	}
 
+	if (get_pages(sbi, F2FS_DIRTY_IMETA)) {
+		f2fs_unlock_all(sbi);
+		err = f2fs_sync_inode_meta(sbi);
+		if (err)
+			goto out;
+		goto retry_flush_dents;
+	}
+
 	/*
 	 * POR: we should ensure that there are no dirty node pages
 	 * until finishing nat/sit flush.
@@ -914,6 +952,8 @@ out:
 static void unblock_operations(struct f2fs_sb_info *sbi)
 {
 	up_write(&sbi->node_write);
+
+	build_free_nids(sbi);
 	f2fs_unlock_all(sbi);
 }
 
@@ -954,7 +994,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	 * This avoids to conduct wrong roll-forward operations and uses
 	 * metapages, so should be called prior to sync_meta_pages below.
 	 */
-	if (discard_next_dnode(sbi, discard_blk))
+	if (!test_opt(sbi, LFS) && discard_next_dnode(sbi, discard_blk))
 		invalidate = true;
 
 	/* Flush all the NAT/SIT pages */
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index ded224518978..e2624275d828 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -19,6 +19,8 @@
 #include <linux/bio.h>
 #include <linux/prefetch.h>
 #include <linux/uio.h>
+#include <linux/mm.h>
+#include <linux/memcontrol.h>
 #include <linux/cleancache.h>
 
 #include "f2fs.h"
@@ -45,7 +47,8 @@ static void f2fs_read_end_io(struct bio *bio)
 		struct page *page = bvec->bv_page;
 
 		if (!bio->bi_error) {
-			SetPageUptodate(page);
+			if (!PageUptodate(page))
+				SetPageUptodate(page);
 		} else {
 			ClearPageUptodate(page);
 			SetPageError(page);
@@ -97,10 +100,15 @@ 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, struct bio *bio)
+static inline void __submit_bio(struct f2fs_sb_info *sbi,
+				struct bio *bio, enum page_type type)
 {
-	if (!is_read_io(bio_op(bio)))
+	if (!is_read_io(bio_op(bio))) {
 		atomic_inc(&sbi->nr_wb_bios);
+		if (f2fs_sb_mounted_hmsmr(sbi->sb) &&
+			current->plug && (type == DATA || type == NODE))
+			blk_finish_plug(current->plug);
+	}
 	submit_bio(bio);
 }
 
@@ -118,7 +126,7 @@ static void __submit_merged_bio(struct f2fs_bio_info *io)
 
 	bio_set_op_attrs(io->bio, fio->op, fio->op_flags);
 
-	__submit_bio(io->sbi, io->bio);
+	__submit_bio(io->sbi, io->bio, fio->type);
 	io->bio = NULL;
 }
 
@@ -240,7 +248,7 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
 	bio->bi_rw = fio->op_flags;
 	bio_set_op_attrs(bio, fio->op, fio->op_flags);
 
-	__submit_bio(fio->sbi, bio);
+	__submit_bio(fio->sbi, bio, fio->type);
 	return 0;
 }
 
@@ -326,7 +334,7 @@ int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count)
 	if (!count)
 		return 0;
 
-	if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)))
+	if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC)))
 		return -EPERM;
 	if (unlikely(!inc_valid_block_count(sbi, dn->inode, &count)))
 		return -ENOSPC;
@@ -348,9 +356,6 @@ int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count)
 
 	if (set_page_dirty(dn->node_page))
 		dn->node_changed = true;
-
-	mark_inode_dirty(dn->inode);
-	sync_inode_page(dn);
 	return 0;
 }
 
@@ -446,7 +451,8 @@ got_it:
 	 */
 	if (dn.data_blkaddr == NEW_ADDR) {
 		zero_user_segment(page, 0, PAGE_SIZE);
-		SetPageUptodate(page);
+		if (!PageUptodate(page))
+			SetPageUptodate(page);
 		unlock_page(page);
 		return page;
 	}
@@ -505,14 +511,14 @@ repeat:
 
 	/* wait for read completion */
 	lock_page(page);
-	if (unlikely(!PageUptodate(page))) {
-		f2fs_put_page(page, 1);
-		return ERR_PTR(-EIO);
-	}
 	if (unlikely(page->mapping != mapping)) {
 		f2fs_put_page(page, 1);
 		goto repeat;
 	}
+	if (unlikely(!PageUptodate(page))) {
+		f2fs_put_page(page, 1);
+		return ERR_PTR(-EIO);
+	}
 	return page;
 }
 
@@ -557,7 +563,8 @@ struct page *get_new_data_page(struct inode *inode,
 
 	if (dn.data_blkaddr == NEW_ADDR) {
 		zero_user_segment(page, 0, PAGE_SIZE);
-		SetPageUptodate(page);
+		if (!PageUptodate(page))
+			SetPageUptodate(page);
 	} else {
 		f2fs_put_page(page, 1);
 
@@ -569,11 +576,8 @@ struct page *get_new_data_page(struct inode *inode,
 	}
 got_it:
 	if (new_i_size && i_size_read(inode) <
-				((loff_t)(index + 1) << PAGE_SHIFT)) {
-		i_size_write(inode, ((loff_t)(index + 1) << PAGE_SHIFT));
-		/* Only the directory inode sets new_i_size */
-		set_inode_flag(F2FS_I(inode), FI_UPDATE_DIR);
-	}
+				((loff_t)(index + 1) << PAGE_SHIFT))
+		f2fs_i_size_write(inode, ((loff_t)(index + 1) << PAGE_SHIFT));
 	return page;
 }
 
@@ -586,7 +590,7 @@ static int __allocate_data_block(struct dnode_of_data *dn)
 	pgoff_t fofs;
 	blkcnt_t count = 1;
 
-	if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)))
+	if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC)))
 		return -EPERM;
 
 	dn->data_blkaddr = datablock_addr(dn->node_page, dn->ofs_in_node);
@@ -611,7 +615,7 @@ alloc:
 	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) +
 							dn->ofs_in_node;
 	if (i_size_read(dn->inode) < ((loff_t)(fofs + 1) << PAGE_SHIFT))
-		i_size_write(dn->inode,
+		f2fs_i_size_write(dn->inode,
 				((loff_t)(fofs + 1) << PAGE_SHIFT));
 	return 0;
 }
@@ -660,7 +664,7 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
 	unsigned int maxblocks = map->m_len;
 	struct dnode_of_data dn;
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	int mode = create ? ALLOC_NODE : LOOKUP_NODE_RA;
+	int mode = create ? ALLOC_NODE : LOOKUP_NODE;
 	pgoff_t pgofs, end_offset, end;
 	int err = 0, ofs = 1;
 	unsigned int ofs_in_node, last_ofs_in_node;
@@ -723,8 +727,7 @@ next_block:
 			} else {
 				err = __allocate_data_block(&dn);
 				if (!err) {
-					set_inode_flag(F2FS_I(inode),
-							FI_APPEND_WRITE);
+					set_inode_flag(inode, FI_APPEND_WRITE);
 					allocated = true;
 				}
 			}
@@ -795,8 +798,6 @@ skip:
 	else if (dn.ofs_in_node < end_offset)
 		goto next_block;
 
-	if (allocated)
-		sync_inode_page(&dn);
 	f2fs_put_dnode(&dn);
 
 	if (create) {
@@ -807,8 +808,6 @@ skip:
 	goto next_dnode;
 
 sync_out:
-	if (allocated)
-		sync_inode_page(&dn);
 	f2fs_put_dnode(&dn);
 unlock_out:
 	if (create) {
@@ -968,6 +967,37 @@ out:
 	return ret;
 }
 
+struct bio *f2fs_grab_bio(struct inode *inode, block_t blkaddr,
+							unsigned nr_pages)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct fscrypt_ctx *ctx = NULL;
+	struct block_device *bdev = sbi->sb->s_bdev;
+	struct bio *bio;
+
+	if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
+		ctx = fscrypt_get_ctx(inode, GFP_NOFS);
+		if (IS_ERR(ctx))
+			return ERR_CAST(ctx);
+
+		/* wait the page to be moved by cleaning */
+		f2fs_wait_on_encrypted_page_writeback(sbi, blkaddr);
+	}
+
+	bio = bio_alloc(GFP_KERNEL, min_t(int, nr_pages, BIO_MAX_PAGES));
+	if (!bio) {
+		if (ctx)
+			fscrypt_release_ctx(ctx);
+		return ERR_PTR(-ENOMEM);
+	}
+	bio->bi_bdev = bdev;
+	bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(blkaddr);
+	bio->bi_end_io = f2fs_read_end_io;
+	bio->bi_private = ctx;
+
+	return bio;
+}
+
 /*
  * This function was originally taken from fs/mpage.c, and customized for f2fs.
  * Major change was from block_size == page_size in f2fs by default.
@@ -986,7 +1016,6 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
 	sector_t last_block;
 	sector_t last_block_in_file;
 	sector_t block_nr;
-	struct block_device *bdev = inode->i_sb->s_bdev;
 	struct f2fs_map_blocks map;
 
 	map.m_pblk = 0;
@@ -1047,7 +1076,8 @@ got_it:
 			}
 		} else {
 			zero_user_segment(page, 0, PAGE_SIZE);
-			SetPageUptodate(page);
+			if (!PageUptodate(page))
+				SetPageUptodate(page);
 			unlock_page(page);
 			goto next_page;
 		}
@@ -1058,35 +1088,15 @@ got_it:
 		 */
 		if (bio && (last_block_in_bio != block_nr - 1)) {
 submit_and_realloc:
-			__submit_bio(F2FS_I_SB(inode), bio);
+			__submit_bio(F2FS_I_SB(inode), bio, DATA);
 			bio = NULL;
 		}
 		if (bio == NULL) {
-			struct fscrypt_ctx *ctx = NULL;
-
-			if (f2fs_encrypted_inode(inode) &&
-					S_ISREG(inode->i_mode)) {
-
-				ctx = fscrypt_get_ctx(inode, GFP_NOFS);
-				if (IS_ERR(ctx))
-					goto set_error_page;
-
-				/* wait the page to be moved by cleaning */
-				f2fs_wait_on_encrypted_page_writeback(
-						F2FS_I_SB(inode), block_nr);
-			}
-
-			bio = bio_alloc(GFP_KERNEL,
-				min_t(int, nr_pages, BIO_MAX_PAGES));
-			if (!bio) {
-				if (ctx)
-					fscrypt_release_ctx(ctx);
+			bio = f2fs_grab_bio(inode, block_nr, nr_pages);
+			if (IS_ERR(bio)) {
+				bio = NULL;
 				goto set_error_page;
 			}
-			bio->bi_bdev = bdev;
-			bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(block_nr);
-			bio->bi_end_io = f2fs_read_end_io;
-			bio->bi_private = ctx;
 			bio_set_op_attrs(bio, REQ_OP_READ, 0);
 		}
 
@@ -1102,7 +1112,7 @@ set_error_page:
 		goto next_page;
 confused:
 		if (bio) {
-			__submit_bio(F2FS_I_SB(inode), bio);
+			__submit_bio(F2FS_I_SB(inode), bio, DATA);
 			bio = NULL;
 		}
 		unlock_page(page);
@@ -1112,7 +1122,7 @@ next_page:
 	}
 	BUG_ON(pages && !list_empty(pages));
 	if (bio)
-		__submit_bio(F2FS_I_SB(inode), bio);
+		__submit_bio(F2FS_I_SB(inode), bio, DATA);
 	return 0;
 }
 
@@ -1201,14 +1211,14 @@ retry_encrypt:
 			!IS_ATOMIC_WRITTEN_PAGE(page) &&
 			need_inplace_update(inode))) {
 		rewrite_data_page(fio);
-		set_inode_flag(F2FS_I(inode), FI_UPDATE_WRITE);
+		set_inode_flag(inode, FI_UPDATE_WRITE);
 		trace_f2fs_do_write_data_page(page, IPU);
 	} else {
 		write_data_page(&dn, fio);
 		trace_f2fs_do_write_data_page(page, OPU);
-		set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
+		set_inode_flag(inode, FI_APPEND_WRITE);
 		if (page->index == 0)
-			set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN);
+			set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN);
 	}
 out_writepage:
 	f2fs_put_dnode(&dn);
@@ -1223,6 +1233,7 @@ static int f2fs_write_data_page(struct page *page,
 	loff_t i_size = i_size_read(inode);
 	const pgoff_t end_index = ((unsigned long long) i_size)
 							>> PAGE_SHIFT;
+	loff_t psize = (page->index + 1) << PAGE_SHIFT;
 	unsigned offset = 0;
 	bool need_balance_fs = false;
 	int err = 0;
@@ -1260,20 +1271,18 @@ 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)) {
-		if (unlikely(f2fs_cp_error(sbi)))
-			goto redirty_out;
 		err = do_write_data_page(&fio);
 		goto done;
 	}
 
-	/* we should bypass data pages to proceed the kworkder jobs */
-	if (unlikely(f2fs_cp_error(sbi))) {
-		SetPageError(page);
-		goto out;
-	}
-
 	if (!wbc->for_reclaim)
 		need_balance_fs = true;
 	else if (has_not_enough_free_secs(sbi, 0))
@@ -1285,6 +1294,8 @@ write:
 		err = f2fs_write_inline_data(inode, page);
 	if (err == -EAGAIN)
 		err = do_write_data_page(&fio);
+	if (F2FS_I(inode)->last_disk_size < psize)
+		F2FS_I(inode)->last_disk_size = psize;
 	f2fs_unlock_op(sbi);
 done:
 	if (err && err != -ENOENT)
@@ -1311,16 +1322,8 @@ out:
 
 redirty_out:
 	redirty_page_for_writepage(wbc, page);
-	return AOP_WRITEPAGE_ACTIVATE;
-}
-
-static int __f2fs_writepage(struct page *page, struct writeback_control *wbc,
-			void *data)
-{
-	struct address_space *mapping = data;
-	int ret = mapping->a_ops->writepage(page, wbc);
-	mapping_set_error(mapping, ret);
-	return ret;
+	unlock_page(page);
+	return err;
 }
 
 /*
@@ -1329,8 +1332,7 @@ static int __f2fs_writepage(struct page *page, struct writeback_control *wbc,
  * warm/hot data page.
  */
 static int f2fs_write_cache_pages(struct address_space *mapping,
-			struct writeback_control *wbc, writepage_t writepage,
-			void *data)
+					struct writeback_control *wbc)
 {
 	int ret = 0;
 	int done = 0;
@@ -1343,10 +1345,9 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
 	int cycled;
 	int range_whole = 0;
 	int tag;
-	int step = 0;
 
 	pagevec_init(&pvec, 0);
-next:
+
 	if (wbc->range_cyclic) {
 		writeback_index = mapping->writeback_index; /* prev offset */
 		index = writeback_index;
@@ -1401,9 +1402,6 @@ continue_unlock:
 				goto continue_unlock;
 			}
 
-			if (step == is_cold_data(page))
-				goto continue_unlock;
-
 			if (PageWriteback(page)) {
 				if (wbc->sync_mode != WB_SYNC_NONE)
 					f2fs_wait_on_page_writeback(page,
@@ -1416,16 +1414,11 @@ continue_unlock:
 			if (!clear_page_dirty_for_io(page))
 				goto continue_unlock;
 
-			ret = (*writepage)(page, wbc, data);
+			ret = mapping->a_ops->writepage(page, wbc);
 			if (unlikely(ret)) {
-				if (ret == AOP_WRITEPAGE_ACTIVATE) {
-					unlock_page(page);
-					ret = 0;
-				} else {
-					done_index = page->index + 1;
-					done = 1;
-					break;
-				}
+				done_index = page->index + 1;
+				done = 1;
+				break;
 			}
 
 			if (--wbc->nr_to_write <= 0 &&
@@ -1438,11 +1431,6 @@ continue_unlock:
 		cond_resched();
 	}
 
-	if (step < 1) {
-		step++;
-		goto next;
-	}
-
 	if (!cycled && !done) {
 		cycled = 1;
 		index = 0;
@@ -1460,9 +1448,8 @@ static int f2fs_write_data_pages(struct address_space *mapping,
 {
 	struct inode *inode = mapping->host;
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	bool locked = false;
+	struct blk_plug plug;
 	int ret;
-	long diff;
 
 	/* deal with chardevs and other special file */
 	if (!mapping->a_ops->writepage)
@@ -1478,7 +1465,7 @@ static int f2fs_write_data_pages(struct address_space *mapping,
 		goto skip_write;
 
 	/* skip writing during file defragment */
-	if (is_inode_flag_set(F2FS_I(inode), FI_DO_DEFRAG))
+	if (is_inode_flag_set(inode, FI_DO_DEFRAG))
 		goto skip_write;
 
 	/* during POR, we don't need to trigger writepage at all. */
@@ -1487,20 +1474,16 @@ static int f2fs_write_data_pages(struct address_space *mapping,
 
 	trace_f2fs_writepages(mapping->host, wbc, DATA);
 
-	diff = nr_pages_to_write(sbi, DATA, wbc);
-
-	if (!S_ISDIR(inode->i_mode) && wbc->sync_mode == WB_SYNC_ALL) {
-		mutex_lock(&sbi->writepages);
-		locked = true;
-	}
-	ret = f2fs_write_cache_pages(mapping, wbc, __f2fs_writepage, mapping);
-	f2fs_submit_merged_bio_cond(sbi, inode, NULL, 0, DATA, WRITE);
-	if (locked)
-		mutex_unlock(&sbi->writepages);
+	blk_start_plug(&plug);
+	ret = f2fs_write_cache_pages(mapping, wbc);
+	blk_finish_plug(&plug);
+	/*
+	 * if some pages were truncated, we cannot guarantee its mapping->host
+	 * to detect pending bios.
+	 */
+	f2fs_submit_merged_bio(sbi, DATA, WRITE);
 
 	remove_dirty_inode(inode);
-
-	wbc->nr_to_write = max((long)0, wbc->nr_to_write - diff);
 	return ret;
 
 skip_write:
@@ -1558,7 +1541,7 @@ restart:
 	if (f2fs_has_inline_data(inode)) {
 		if (pos + len <= MAX_INLINE_DATA) {
 			read_inline_data(page, ipage);
-			set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
+			set_inode_flag(inode, FI_DATA_EXIST);
 			if (inode->i_nlink)
 				set_inline_node(ipage);
 		} else {
@@ -1668,39 +1651,35 @@ repeat:
 	if (blkaddr == NEW_ADDR) {
 		zero_user_segment(page, 0, PAGE_SIZE);
 	} else {
-		struct f2fs_io_info fio = {
-			.sbi = sbi,
-			.type = DATA,
-			.op = REQ_OP_READ,
-			.op_flags = READ_SYNC,
-			.old_blkaddr = blkaddr,
-			.new_blkaddr = blkaddr,
-			.page = page,
-			.encrypted_page = NULL,
-		};
-		err = f2fs_submit_page_bio(&fio);
-		if (err)
-			goto fail;
+		struct bio *bio;
 
-		lock_page(page);
-		if (unlikely(!PageUptodate(page))) {
-			err = -EIO;
+		bio = f2fs_grab_bio(inode, blkaddr, 1);
+		if (IS_ERR(bio)) {
+			err = PTR_ERR(bio);
 			goto fail;
 		}
+		bio_set_op_attrs(bio, REQ_OP_READ, READ_SYNC);
+		if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
+			bio_put(bio);
+			err = -EFAULT;
+			goto fail;
+		}
+
+		__submit_bio(sbi, bio, DATA);
+
+		lock_page(page);
 		if (unlikely(page->mapping != mapping)) {
 			f2fs_put_page(page, 1);
 			goto repeat;
 		}
-
-		/* avoid symlink page */
-		if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
-			err = fscrypt_decrypt_page(page);
-			if (err)
-				goto fail;
+		if (unlikely(!PageUptodate(page))) {
+			err = -EIO;
+			goto fail;
 		}
 	}
 out_update:
-	SetPageUptodate(page);
+	if (!PageUptodate(page))
+		SetPageUptodate(page);
 out_clear:
 	clear_cold_data(page);
 	return 0;
@@ -1721,13 +1700,11 @@ static int f2fs_write_end(struct file *file,
 	trace_f2fs_write_end(inode, pos, len, copied);
 
 	set_page_dirty(page);
+	f2fs_put_page(page, 1);
 
-	if (pos + copied > i_size_read(inode)) {
-		i_size_write(inode, pos + copied);
-		mark_inode_dirty(inode);
-	}
+	if (pos + copied > i_size_read(inode))
+		f2fs_i_size_write(inode, pos + copied);
 
-	f2fs_put_page(page, 1);
 	f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
 	return copied;
 }
@@ -1752,6 +1729,7 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	struct inode *inode = mapping->host;
 	size_t count = iov_iter_count(iter);
 	loff_t offset = iocb->ki_pos;
+	int rw = iov_iter_rw(iter);
 	int err;
 
 	err = check_direct_IO(inode, iter, offset);
@@ -1760,18 +1738,23 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 
 	if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
 		return 0;
+	if (test_opt(F2FS_I_SB(inode), LFS))
+		return 0;
 
-	trace_f2fs_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
+	trace_f2fs_direct_IO_enter(inode, offset, count, rw);
 
+	down_read(&F2FS_I(inode)->dio_rwsem[rw]);
 	err = blockdev_direct_IO(iocb, inode, iter, get_data_block_dio);
-	if (iov_iter_rw(iter) == WRITE) {
+	up_read(&F2FS_I(inode)->dio_rwsem[rw]);
+
+	if (rw == WRITE) {
 		if (err > 0)
-			set_inode_flag(F2FS_I(inode), FI_UPDATE_WRITE);
+			set_inode_flag(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);
+	trace_f2fs_direct_IO_exit(inode, offset, count, rw, err);
 
 	return err;
 }
@@ -1818,6 +1801,35 @@ int f2fs_release_page(struct page *page, gfp_t wait)
 	return 1;
 }
 
+/*
+ * This was copied from __set_page_dirty_buffers which gives higher performance
+ * in very high speed storages. (e.g., pmem)
+ */
+void f2fs_set_page_dirty_nobuffers(struct page *page)
+{
+	struct address_space *mapping = page->mapping;
+	unsigned long flags;
+
+	if (unlikely(!mapping))
+		return;
+
+	spin_lock(&mapping->private_lock);
+	lock_page_memcg(page);
+	SetPageDirty(page);
+	spin_unlock(&mapping->private_lock);
+
+	spin_lock_irqsave(&mapping->tree_l