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
  ...

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

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);

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

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 */

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_lock, flags);
+	WARN_ON_ONCE(!PageUptodate(page));
+	account_page_dirtied(page, mapping);
+	radix_tree_tag_set(&mapping->page_tree,
+			page_index(page), PAGECACHE_TAG_DIRTY);
+	spin_unlock_irqrestore(&mapping->tree_lock, flags);
+	unlock_page_memcg(page);
+
+	__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
+	return;
+}
+
 static int f2fs_set_data_page_dirty(struct page *page)
 {
 	struct address_space *mapping = page->mapping;
@@ -1825,7 +1837,8 @@ static int f2fs_set_data_page_dirty(struct page *page)
 
 	trace_f2fs_set_page_dirty(page, DATA);
 
-	SetPageUptodate(page);
+	if (!PageUptodate(page))
+		SetPageUptodate(page);
 
 	if (f2fs_is_atomic_file(inode)) {
 		if (!IS_ATOMIC_WRITTEN_PAGE(page)) {
@@ -1840,7 +1853,7 @@ static int f2fs_set_data_page_dirty(struct page *page)
 	}
 
 	if (!PageDirty(page)) {
-		__set_page_dirty_nobuffers(page);
+		f2fs_set_page_dirty_nobuffers(page);
 		update_dirty_page(inode, page);
 		return 1;
 	}

fs/f2fs/debug.c

@@ -47,6 +47,7 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 	si->ndirty_data = get_pages(sbi, F2FS_DIRTY_DATA);
 	si->ndirty_dirs = sbi->ndirty_inode[DIR_INODE];
 	si->ndirty_files = sbi->ndirty_inode[FILE_INODE];
+	si->ndirty_all = sbi->ndirty_inode[DIRTY_META];
 	si->inmem_pages = get_pages(sbi, F2FS_INMEM_PAGES);
 	si->wb_bios = atomic_read(&sbi->nr_wb_bios);
 	si->total_count = (int)sbi->user_block_count / sbi->blocks_per_seg;
@@ -304,8 +305,8 @@ static int stat_show(struct seq_file *s, void *v)
 			   si->inmem_pages, si->wb_bios);
 		seq_printf(s, "  - nodes: %4lld in %4d\n",
 			   si->ndirty_node, si->node_pages);
-		seq_printf(s, "  - dents: %4lld in dirs:%4d\n",
-			   si->ndirty_dent, si->ndirty_dirs);
+		seq_printf(s, "  - dents: %4lld in dirs:%4d (%4d)\n",
+			   si->ndirty_dent, si->ndirty_dirs, si->ndirty_all);
 		seq_printf(s, "  - datas: %4lld in files:%4d\n",
 			   si->ndirty_data, si->ndirty_files);
 		seq_printf(s, "  - meta: %4lld in %4d\n",

fs/f2fs/dir.c

@@ -185,8 +185,13 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
 		/* no need to allocate new dentry pages to all the indices */
 		dentry_page = find_data_page(dir, bidx);
 		if (IS_ERR(dentry_page)) {
-			room = true;
-			continue;
+			if (PTR_ERR(dentry_page) == -ENOENT) {
+				room = true;
+				continue;
+			} else {
+				*res_page = dentry_page;
+				break;
+			}
 		}
 
 		de = find_in_block(dentry_page, fname, namehash, &max_slots,
@@ -223,19 +228,22 @@ struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
 	struct fscrypt_name fname;
 	int err;
 
-	*res_page = NULL;
-
 	err = fscrypt_setup_filename(dir, child, 1, &fname);
-	if (err)
+	if (err) {
+		*res_page = ERR_PTR(err);
 		return NULL;
+	}
 
 	if (f2fs_has_inline_dentry(dir)) {
+		*res_page = NULL;
 		de = find_in_inline_dir(dir, &fname, res_page);
 		goto out;
 	}
 
-	if (npages == 0)
+	if (npages == 0) {
+		*res_page = NULL;
 		goto out;
+	}
 
 	max_depth = F2FS_I(dir)->i_current_depth;
 	if (unlikely(max_depth > MAX_DIR_HASH_DEPTH)) {
@@ -243,13 +251,13 @@ struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
 				"Corrupted max_depth of %lu: %u",
 				dir->i_ino, max_depth);
 		max_depth = MAX_DIR_HASH_DEPTH;
-		F2FS_I(dir)->i_current_depth = max_depth;
-		mark_inode_dirty(dir);
+		f2fs_i_depth_write(dir, max_depth);
 	}
 
 	for (level = 0; level < max_depth; level++) {
+		*res_page = NULL;
 		de = find_in_level(dir, level, &fname, res_page);
-		if (de)
+		if (de || IS_ERR(*res_page))
 			break;
 	}
 out:
@@ -259,35 +267,22 @@ out:
 
 struct f2fs_dir_entry *f2fs_parent_dir(struct inode *dir, struct page **p)
 {
-	struct page *page;
-	struct f2fs_dir_entry *de;
-	struct f2fs_dentry_block *dentry_blk;
-
-	if (f2fs_has_inline_dentry(dir))
-		return f2fs_parent_inline_dir(dir, p);
-
-	page = get_lock_data_page(dir, 0, false);
-	if (IS_ERR(page))
-		return NULL;
+	struct qstr dotdot = QSTR_INIT("..", 2);
 
-	dentry_blk = kmap(page);
-	de = &dentry_blk->dentry[1];
-	*p = page;
-	unlock_page(page);
-	return de;
+	return f2fs_find_entry(dir, &dotdot, p);
 }
 
-ino_t f2fs_inode_by_name(struct inode *dir, struct qstr *qstr)
+ino_t f2fs_inode_by_name(struct inode *dir, struct qstr *qstr,
+							struct page **page)
 {
 	ino_t res = 0;
 	struct f2fs_dir_entry *de;
-	struct page *page;
 
-	de = f2fs_find_entry(dir, qstr, &page);
+	de = f2fs_find_entry(dir, qstr, page);
 	if (de) {
 		res = le32_to_cpu(de->ino);
-		f2fs_dentry_kunmap(dir, page);
-		f2fs_put_page(page, 0);
+		f2fs_dentry_kunmap(dir, *page);
+		f2fs_put_page(*page, 0);
 	}
 
 	return res;
@@ -303,9 +298,9 @@ void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
 	set_de_type(de, inode->i_mode);
 	f2fs_dentry_kunmap(dir, page);
 	set_page_dirty(page);
-	dir->i_mtime = dir->i_ctime = CURRENT_TIME;
-	mark_inode_dirty(dir);
 
+	dir->i_mtime = dir->i_ctime = CURRENT_TIME;
+	f2fs_mark_inode_dirty_sync(dir);
 	f2fs_put_page(page, 1);
 }
 
@@ -385,7 +380,7 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
 	struct page *page;
 	int err;
 
-	if (is_inode_flag_set(F2FS_I(inode), FI_NEW_INODE)) {
+	if (is_inode_flag_set(inode, FI_NEW_INODE)) {
 		page = new_inode_page(inode);
 		if (IS_ERR(page))
 			return page;
@@ -429,7 +424,7 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
 	 * This file should be checkpointed during fsync.
 	 * We lost i_pino from now on.
 	 */
-	if (is_inode_flag_set(F2FS_I(inode), FI_INC_LINK)) {
+	if (is_inode_flag_set(inode, FI_INC_LINK)) {
 		file_lost_pino(inode);
 		/*
 		 * If link the tmpfile to alias through linkat path,
@@ -437,14 +432,11 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
 		 */
 		if (inode->i_nlink == 0)
 			remove_orphan_inode(F2FS_I_SB(dir), inode->i_ino);
-		inc_nlink(inode);
+		f2fs_i_links_write(inode, true);
 	}
 	return page;
 
 put_error:
-	/* truncate empty dir pages */
-	truncate_inode_pages(&inode->i_data, 0);
-
 	clear_nlink(inode);
 	update_inode(inode, page);
 	f2fs_put_page(page, 1);
@@ -454,23 +446,19 @@ put_error:
 void update_parent_metadata(struct inode *dir, struct inode *inode,
 						unsigned int current_depth)
 {
-	if (inode && is_inode_flag_set(F2FS_I(inode), FI_NEW_INODE)) {
-		if (S_ISDIR(inode->i_mode)) {
-			inc_nlink(dir);
-			set_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
-		}
-		clear_inode_flag(F2FS_I(inode), FI_NEW_INODE);
+	if (inode && is_inode_flag_set(inode, FI_NEW_INODE)) {
+		if (S_ISDIR(inode->i_mode))
+			f2fs_i_links_write(dir, true);
+		clear_inode_flag(inode, FI_NEW_INODE);
 	}
 	dir->i_mtime = dir->i_ctime = CURRENT_TIME;
-	mark_inode_dirty(dir);
+	f2fs_mark_inode_dirty_sync(dir);
 
-	if (F2FS_I(dir)->i_current_depth != current_depth) {
-		F2FS_I(dir)->i_current_depth = current_depth;
-		set_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
-	}
+	if (F2FS_I(dir)->i_current_depth != current_depth)
+		f2fs_i_depth_write(dir, current_depth);
 
-	if (inode && is_inode_flag_set(F2FS_I(inode), FI_INC_LINK))
-		clear_inode_flag(F2FS_I(inode), FI_INC_LINK);
+	if (inode && is_inode_flag_set(inode, FI_INC_LINK))
+		clear_inode_flag(inode, FI_INC_LINK);
 }
 
 int room_for_filename(const void *bitmap, int slots, int max_slots)
@@ -596,9 +584,7 @@ add_dentry:
 	set_page_dirty(dentry_page);
 
 	if (inode) {
-		/* we don't need to mark_inode_dirty now */
-		F2FS_I(inode)->i_pino = dir->i_ino;
-		update_inode(inode, page);
+		f2fs_i_pino_write(inode, dir->i_ino);
 		f2fs_put_page(page, 1);
 	}
 
@@ -607,10 +593,6 @@ fail:
 	if (inode)
 		up_write(&F2FS_I(inode)->i_sem);
 
-	if (is_inode_flag_set(F2FS_I(dir), FI_UPDATE_DIR)) {
-		update_inode_page(dir);
-		clear_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
-	}
 	kunmap(dentry_page);
 	f2fs_put_page(dentry_page, 1);
 
@@ -657,42 +639,34 @@ int f2fs_do_tmpfile(struct inode *inode, struct inode *dir)
 		err = PTR_ERR(page);
 		goto fail;
 	}
-	/* we don't need to mark_inode_dirty now */
-	update_inode(inode, page);
 	f2fs_put_page(page, 1);
 
-	clear_inode_flag(F2FS_I(inode), FI_NEW_INODE);
+	clear_inode_flag(inode, FI_NEW_INODE);
 fail:
 	up_write(&F2FS_I(inode)->i_sem);
 	f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
 	return err;
 }
 
-void f2fs_drop_nlink(struct inode *dir, struct inode *inode, struct page *page)
+void f2fs_drop_nlink(struct inode *dir, struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
 
 	down_write(&F2FS_I(inode)->i_sem);
 
-	if (S_ISDIR(inode->i_mode)) {
-		drop_nlink(dir);
-		if (page)
-			update_inode(dir, page);
-		else
-			update_inode_page(dir);
-	}
+	if (S_ISDIR(inode->i_mode))
+		f2fs_i_links_write(dir, false);
 	inode->i_ctime = CURRENT_TIME;
 
-	drop_nlink(inode);
+	f2fs_i_links_write(inode, false);
 	if (S_ISDIR(inode->i_mode)) {
-		drop_nlink(inode);
-		i_size_write(inode, 0);
+		f2fs_i_links_write(inode, false);
+		f2fs_i_size_write(inode, 0);
 	}
 	up_write(&F2FS_I(inode)->i_sem);
-	update_inode_page(inode);
 
 	if (inode->i_nlink == 0)
-		add_orphan_inode(sbi, inode->i_ino);
+		add_orphan_inode(inode);
 	else
 		release_orphan_inode(sbi);
 }
@@ -730,9 +704,10 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
 	set_page_dirty(page);
 
 	dir->i_ctime = dir->i_mtime = CURRENT_TIME;
+	f2fs_mark_inode_dirty_sync(dir);
 
 	if (inode)
-		f2fs_drop_nlink(dir, inode, NULL);
+		f2fs_drop_nlink(dir, inode);
 
 	if (bit_pos == NR_DENTRY_IN_BLOCK &&
 			!truncate_hole(dir, page->index, page->index + 1)) {

fs/f2fs/extent_cache.c

@@ -170,8 +170,10 @@ static void __drop_largest_extent(struct inode *inode,
 {
 	struct extent_info *largest = &F2FS_I(inode)->extent_tree->largest;
 
-	if (fofs < largest->fofs + largest->len && fofs + len > largest->fofs)
+	if (fofs < largest->fofs + largest->len && fofs + len > largest->fofs) {
 		largest->len = 0;
+		f2fs_mark_inode_dirty_sync(inode);
+	}
 }
 
 /* return true, if inode page is changed */
@@ -335,11 +337,12 @@ lookup_neighbors:
 	return en;
 }
 
-static struct extent_node *__try_merge_extent_node(struct f2fs_sb_info *sbi,
+static struct extent_node *__try_merge_extent_node(struct inode *inode,
 				struct extent_tree *et, struct extent_info *ei,
 				struct extent_node *prev_ex,
 				struct extent_node *next_ex)
 {
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct extent_node *en = NULL;
 
 	if (prev_ex && __is_back_mergeable(ei, &prev_ex->ei)) {
@@ -360,7 +363,7 @@ static struct extent_node *__try_merge_extent_node(struct f2fs_sb_info *sbi,
 	if (!en)
 		return NULL;
 
-	__try_update_largest_extent(et, en);
+	__try_update_largest_extent(inode, et, en);
 
 	spin_lock(&sbi->extent_lock);
 	if (!list_empty(&en->list)) {
@@ -371,11 +374,12 @@ static struct extent_node *__try_merge_extent_node(struct f2fs_sb_info *sbi,
 	return en;
 }
 
-static struct extent_node *__insert_extent_tree(struct f2fs_sb_info *sbi,
+static struct extent_node *__insert_extent_tree(struct inode *inode,
 				struct extent_tree *et, struct extent_info *ei,
 				struct rb_node **insert_p,
 				struct rb_node *insert_parent)
 {
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct rb_node **p = &et->root.rb_node;
 	struct rb_node *parent = NULL;
 	struct extent_node *en = NULL;
@@ -402,7 +406,7 @@ do_insert:
 	if (!en)
 		return NULL;
 
-	__try_update_largest_extent(et, en);
+	__try_update_largest_extent(inode, et, en);
 
 	/* update in global extent list */
 	spin_lock(&sbi->extent_lock);
@@ -431,7 +435,7 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
 
 	write_lock(&et->lock);
 
-	if (is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT)) {
+	if (is_inode_flag_set(inode, FI_NO_EXTENT)) {
 		write_unlock(&et->lock);
 		return false;
 	}
@@ -473,7 +477,7 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
 				set_extent_info(&ei, end,
 						end - dei.fofs + dei.blk,
 						org_end - end);
-				en1 = __insert_extent_tree(sbi, et, &ei,
+				en1 = __insert_extent_tree(inode, et, &ei,
 							NULL, NULL);
 				next_en = en1;
 			} else {
@@ -494,7 +498,7 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
 		}
 
 		if (parts)
-			__try_update_largest_extent(et, en);
+			__try_update_largest_extent(inode, et, en);
 		else
 			__release_extent_node(sbi, et, en);
 
@@ -514,20 +518,20 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
 	if (blkaddr) {
 
 		set_extent_info(&ei, fofs, blkaddr, len);
-		if (!__try_merge_extent_node(sbi, et, &ei, prev_en, next_en))
-			__insert_extent_tree(sbi, et, &ei,
+		if (!__try_merge_extent_node(inode, et, &ei, prev_en, next_en))
+			__insert_extent_tree(inode, et, &ei,
 						insert_p, insert_parent);
 
 		/* give up extent_cache, if split and small updates happen */
 		if (dei.len >= 1 &&
 				prev.len < F2FS_MIN_EXTENT_LEN &&
 				et->largest.len < F2FS_MIN_EXTENT_LEN) {
-			et->largest.len = 0;
-			set_inode_flag(F2FS_I(inode), FI_NO_EXTENT);
+			__drop_largest_extent(inode, 0, UINT_MAX);
+			set_inode_flag(inode, FI_NO_EXTENT);
 		}
 	}
 
-	if (is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT))
+	if (is_inode_flag_set(inode, FI_NO_EXTENT))
 		__free_extent_tree(sbi, et);
 
 	write_unlock(&et->lock);
@@ -627,6 +631,19 @@ unsigned int f2fs_destroy_extent_node(struct inode *inode)
 	return node_cnt;
 }
 
+void f2fs_drop_extent_tree(struct inode *inode)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct extent_tree *et = F2FS_I(inode)->extent_tree;
+
+	set_inode_flag(inode, FI_NO_EXTENT);
+
+	write_lock(&et->lock);
+	__free_extent_tree(sbi, et);
+	__drop_largest_extent(inode, 0, UINT_MAX);
+	write_unlock(&et->lock);
+}
+
 void f2fs_destroy_extent_tree(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -685,9 +702,7 @@ void f2fs_update_extent_cache(struct dnode_of_data *dn)
 
 	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) +
 								dn->ofs_in_node;
-
-	if (f2fs_update_extent_tree_range(dn->inode, fofs, blkaddr, 1))
-		sync_inode_page(dn);
+	f2fs_update_extent_tree_range(dn->inode, fofs, blkaddr, 1);
 }
 
 void f2fs_update_extent_cache_range(struct dnode_of_data *dn,
@@ -697,8 +712,7 @@ void f2fs_update_extent_cache_range(struct dnode_of_data *dn,
 	if (!f2fs_may_extent_tree(dn->inode))
 		return;
 
-	if (f2fs_update_extent_tree_range(dn->inode, fofs, blkaddr, len))
-		sync_inode_page(dn);
+	f2fs_update_extent_tree_range(dn->inode, fofs, blkaddr, len);
 }
 
 void init_extent_cache_info(struct f2fs_sb_info *sbi)

fs/f2fs/f2fs.h

@@ -45,6 +45,7 @@ enum {
 	FAULT_ORPHAN,
 	FAULT_BLOCK,
 	FAULT_DIR_DEPTH,
+	FAULT_EVICT_INODE,
 	FAULT_MAX,
 };
 
@@ -74,6 +75,8 @@ static inline bool time_to_inject(int type)
 		return false;
 	else if (type == FAULT_DIR_DEPTH && !IS_FAULT_SET(type))
 		return false;
+	else if (type == FAULT_EVICT_INODE && !IS_FAULT_SET(type))
+		return false;
 
 	atomic_inc(&f2fs_fault.inject_ops);
 	if (atomic_read(&f2fs_fault.inject_ops) >= f2fs_fault.inject_rate) {
@@ -108,6 +111,8 @@ static inline bool time_to_inject(int type)
 #define F2FS_MOUNT_FORCE_FG_GC		0x00004000
 #define F2FS_MOUNT_DATA_FLUSH		0x00008000
 #define F2FS_MOUNT_FAULT_INJECTION	0x00010000
+#define F2FS_MOUNT_ADAPTIVE		0x00020000
+#define F2FS_MOUNT_LFS			0x00040000
 
 #define clear_opt(sbi, option)	(sbi->mount_opt.opt &= ~F2FS_MOUNT_##option)
 #define set_opt(sbi, option)	(sbi->mount_opt.opt |= F2FS_MOUNT_##option)
@@ -128,6 +133,7 @@ struct f2fs_mount_info {
 };
 
 #define F2FS_FEATURE_ENCRYPT	0x0001
+#define F2FS_FEATURE_HMSMR	0x0002
 
 #define F2FS_HAS_FEATURE(sb, mask)					\
 	((F2FS_SB(sb)->raw_super->feature & cpu_to_le32(mask)) != 0)
@@ -158,7 +164,7 @@ enum {
 #define BATCHED_TRIM_BLOCKS(sbi)	\
 		(BATCHED_TRIM_SEGMENTS(sbi) << (sbi)->log_blocks_per_seg)
 #define DEF_CP_INTERVAL			60	/* 60 secs */
-#define DEF_IDLE_INTERVAL		120	/* 2 mins */
+#define DEF_IDLE_INTERVAL		5	/* 5 secs */
 
 struct cp_control {
 	int reason;
@@ -262,6 +268,8 @@ static inline bool __has_cursum_space(struct f2fs_journal *journal,
 #define F2FS_IOC_GARBAGE_COLLECT	_IO(F2FS_IOCTL_MAGIC, 6)
 #define F2FS_IOC_WRITE_CHECKPOINT	_IO(F2FS_IOCTL_MAGIC, 7)
 #define F2FS_IOC_DEFRAGMENT		_IO(F2FS_IOCTL_MAGIC, 8)
+#define F2FS_IOC_MOVE_RANGE		_IOWR(F2FS_IOCTL_MAGIC, 9,	\
+						struct f2fs_move_range)
 
 #define F2FS_IOC_SET_ENCRYPTION_POLICY	FS_IOC_SET_ENCRYPTION_POLICY
 #define F2FS_IOC_GET_ENCRYPTION_POLICY	FS_IOC_GET_ENCRYPTION_POLICY
@@ -291,6 +299,13 @@ struct f2fs_defragment {
 	u64 len;
 };
 
+struct f2fs_move_range {
+	u32 dst_fd;		/* destination fd */
+	u64 pos_in;		/* start position in src_fd */
+	u64 pos_out;		/* start position in dst_fd */
+	u64 len;		/* size to move */
+};
+
 /*
  * For INODE and NODE manager
  */
@@ -441,11 +456,14 @@ struct f2fs_inode_info {
 	unsigned int clevel;		/* maximum level of given file name */
 	nid_t i_xattr_nid;		/* node id that contains xattrs */
 	unsigned long long xattr_ver;	/* cp version of xattr modification */
+	loff_t	last_disk_size;		/* lastly written file size */
 
-	struct list_head dirty_list;	/* linked in global dirty list */
+	struct list_head dirty_list;	/* dirty list for dirs and files */
+	struct list_head gdirty_list;	/* linked in global dirty list */
 	struct list_head inmem_pages;	/* inmemory pages managed by f2fs */
 	struct mutex inmem_lock;	/* lock for inmemory pages */
 	struct extent_tree *extent_tree;	/* cached extent_tree entry */
+	struct rw_semaphore dio_rwsem[2];/* avoid racing between dio and gc */
 };
 
 static inline void get_extent_info(struct extent_info *ext,
@@ -498,11 +516,14 @@ static inline bool __is_front_mergeable(struct extent_info *cur,
 	return __is_extent_mergeable(cur, front);
 }
 
-static inline void __try_update_largest_extent(struct extent_tree *et,
-						struct extent_node *en)
+extern void f2fs_mark_inode_dirty_sync(struct inode *);
+static inline void __try_update_largest_extent(struct inode *inode,
+			struct extent_tree *et, struct extent_node *en)
 {
-	if (en->ei.len > et->largest.len)
+	if (en->ei.len > et->largest.len) {
 		et->largest = en->ei;
+		f2fs_mark_inode_dirty_sync(inode);
+	}
 }
 
 struct f2fs_nm_info {
@@ -517,7 +538,7 @@ struct f2fs_nm_info {
 	/* NAT cache management */
 	struct radix_tree_root nat_root;/* root of the nat entry cache */
 	struct radix_tree_root nat_set_root;/* root of the nat set cache */
-	struct rw_semaphore nat_tree_lock;	/* protect nat_tree_lock */
+	struct percpu_rw_semaphore nat_tree_lock;	/* protect nat_tree_lock */
 	struct list_head nat_entries;	/* cached nat entry list (clean) */
 	unsigned int nat_cnt;		/* the # of cached nat entries */
 	unsigned int dirty_nat_cnt;	/* total num of nat entries in set */
@@ -599,6 +620,7 @@ struct flush_cmd {
 struct flush_cmd_control {
 	struct task_struct *f2fs_issue_flush;	/* flush thread */
 	wait_queue_head_t flush_wait_queue;	/* waiting queue for wake-up */
+	atomic_t submit_flush;			/* # of issued flushes */
 	struct llist_head issue_list;		/* list for command issue */
 	struct llist_node *dispatch_list;	/* list for command dispatch */
 };
@@ -655,6 +677,7 @@ enum count_type {
 	F2FS_DIRTY_NODES,
 	F2FS_DIRTY_META,
 	F2FS_INMEM_PAGES,
+	F2FS_DIRTY_IMETA,
 	NR_COUNT_TYPE,
 };
 
@@ -706,6 +729,7 @@ struct f2fs_bio_info {
 enum inode_type {
 	DIR_INODE,			/* for dirty dir inode */
 	FILE_INODE,			/* for dirty regular/symlink inode */
+	DIRTY_META,			/* for all dirtied inode metadata */
 	NR_INODE_TYPE,
 };
 
@@ -757,14 +781,14 @@ struct f2fs_sb_info {
 	/* for bio operations */
 	struct f2fs_bio_info read_io;			/* for read bios */
 	struct f2fs_bio_info write_io[NR_PAGE_TYPE];	/* for write bios */
+	struct mutex wio_mutex[NODE + 1];	/* bio ordering for NODE/DATA */
 
 	/* for checkpoint */
 	struct f2fs_checkpoint *ckpt;		/* raw checkpoint pointer */
 	struct inode *meta_inode;		/* cache meta blocks */
 	struct mutex cp_mutex;			/* checkpoint procedure lock */
-	struct rw_semaphore cp_rwsem;		/* blocking FS operations */
+	struct percpu_rw_semaphore cp_rwsem;		/* blocking FS operations */
 	struct rw_semaphore node_write;		/* locking node writes */
-	struct mutex writepages;		/* mutex for writepages() */
 	wait_queue_head_t cp_wait;
 	unsigned long last_time[MAX_TIME];	/* to store time in jiffies */
 	long interval_time[MAX_TIME];		/* to store thresholds */
@@ -1050,22 +1074,22 @@ static inline void clear_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
 
 static inline void f2fs_lock_op(struct f2fs_sb_info *sbi)
 {
-	down_read(&sbi->cp_rwsem);
+	percpu_down_read(&sbi->cp_rwsem);
 }
 
 static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi)
 {
-	up_read(&sbi->cp_rwsem);
+	percpu_up_read(&sbi->cp_rwsem);
 }
 
 static inline void f2fs_lock_all(struct f2fs_sb_info *sbi)
 {
-	down_write(&sbi->cp_rwsem);
+	percpu_down_write(&sbi->cp_rwsem);
 }
 
 static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi)
 {
-	up_write(&sbi->cp_rwsem);
+	percpu_up_write(&sbi->cp_rwsem);
 }
 
 static inline int __get_cp_reason(struct f2fs_sb_info *sbi)
@@ -1120,34 +1144,37 @@ static inline bool f2fs_has_xattr_block(unsigned int ofs)
 	return ofs == XATTR_NODE_OFFSET;
 }
 
+static inline void f2fs_i_blocks_write(struct inode *, blkcnt_t, bool);
 static inline bool inc_valid_block_count(struct f2fs_sb_info *sbi,
 				 struct inode *inode, blkcnt_t *count)
 {
-	block_t	valid_block_count;
+	blkcnt_t diff;
 
-	spin_lock(&sbi->stat_lock);
 #ifdef CONFIG_F2FS_FAULT_INJECTION
-	if (time_to_inject(FAULT_BLOCK)) {
-		spin_unlock(&sbi->stat_lock);
+	if (time_to_inject(FAULT_BLOCK))
 		return false;
-	}
 #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;
+	/*
+	 * let's increase this in prior to actual block count change in order
+	 * for f2fs_sync_file to avoid data races when deciding checkpoint.
+	 */
+	percpu_counter_add(&sbi->alloc_valid_block_count, (*count));
+
+	spin_lock(&sbi->stat_lock);
+	sbi->total_valid_block_count += (block_t)(*count);
+	if (unlikely(sbi->total_valid_block_count > sbi->user_block_count)) {
+		diff = sbi->total_valid_block_count - sbi->user_block_count;
+		*count -= diff;
+		sbi->total_valid_block_count = sbi->user_block_count;
 		if (!*count) {
 			spin_unlock(&sbi->stat_lock);
+			percpu_counter_sub(&sbi->alloc_valid_block_count, diff);
 			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));
+	f2fs_i_blocks_write(inode, *count, true);
 	return true;
 }
 
@@ -1158,9 +1185,9 @@ static inline void dec_valid_block_count(struct f2fs_sb_info *sbi,
 	spin_lock(&sbi->stat_lock);
 	f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count);
 	f2fs_bug_on(sbi, inode->i_blocks < count);
-	inode->i_blocks -= count;
 	sbi->total_valid_block_count -= (block_t)count;
 	spin_unlock(&sbi->stat_lock);
+	f2fs_i_blocks_write(inode, count, false);
 }
 
 static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type)
@@ -1295,7 +1322,7 @@ static inline bool inc_valid_node_count(struct f2fs_sb_info *sbi,
 	}
 
 	if (inode)
-		inode->i_blocks++;
+		f2fs_i_blocks_write(inode, 1, true);
 
 	sbi->total_valid_node_count++;
 	sbi->total_valid_block_count++;
@@ -1314,7 +1341,7 @@ static inline void dec_valid_node_count(struct f2fs_sb_info *sbi,
 	f2fs_bug_on(sbi, !sbi->total_valid_node_count);
 	f2fs_bug_on(sbi, !inode->i_blocks);
 
-	inode->i_blocks--;
+	f2fs_i_blocks_write(inode, 1, false);
 	sbi->total_valid_node_count--;
 	sbi->total_valid_block_count--;
 
@@ -1511,12 +1538,12 @@ static inline void f2fs_change_bit(unsigned int nr, char *addr)
 enum {
 	FI_NEW_INODE,		/* indicate newly allocated inode */
 	FI_DIRTY_INODE,		/* indicate inode is dirty or not */
+	FI_AUTO_RECOVER,	/* indicate inode is recoverable */
 	FI_DIRTY_DIR,		/* indicate directory has dirty pages */
 	FI_INC_LINK,		/* need to increment i_nlink */
 	FI_ACL_MODE,		/* indicate acl mode */
 	FI_NO_ALLOC,		/* should not allocate any blocks */
 	FI_FREE_NID,		/* free allocated nide */
-	FI_UPDATE_DIR,		/* should update inode block for consistency */
 	FI_NO_EXTENT,		/* not to use the extent cache */
 	FI_INLINE_XATTR,	/* used for inline xattr */
 	FI_INLINE_DATA,		/* used for inline data*/
@@ -1534,64 +1561,143 @@ enum {
 	FI_DIRTY_FILE,		/* indicate regular/symlink has dirty pages */
 };
 
-static inline void set_inode_flag(struct f2fs_inode_info *fi, int flag)
+static inline void __mark_inode_dirty_flag(struct inode *inode,
+						int flag, bool set)
+{
+	switch (flag) {
+	case FI_INLINE_XATTR:
+	case FI_INLINE_DATA:
+	case FI_INLINE_DENTRY:
+		if (set)
+			return;
+	case FI_DATA_EXIST:
+	case FI_INLINE_DOTS:
+		f2fs_mark_inode_dirty_sync(inode);
+	}
+}
+
+static inline void set_inode_flag(struct inode *inode, int flag)
+{
+	if (!test_bit(flag, &F2FS_I(inode)->flags))
+		set_bit(flag, &F2FS_I(inode)->flags);
+	__mark_inode_dirty_flag(inode, flag, true);
+}
+
+static inline int is_inode_flag_set(struct inode *inode, int flag)
+{
+	return test_bit(flag, &F2FS_I(inode)->flags);
+}
+
+static inline void clear_inode_flag(struct inode *inode, int flag)
+{
+	if (test_bit(flag, &F2FS_I(inode)->flags))
+		clear_bit(flag, &F2FS_I(inode)->flags);
+	__mark_inode_dirty_flag(inode, flag, false);
+}
+
+static inline void set_acl_inode(struct inode *inode, umode_t mode)
 {
-	if (!test_bit(flag, &fi->flags))
-		set_bit(flag, &fi->flags);
+	F2FS_I(inode)->i_acl_mode = mode;
+	set_inode_flag(inode, FI_ACL_MODE);
+	f2fs_mark_inode_dirty_sync(inode);
 }
 
-static inline int is_inode_flag_set(struct f2fs_inode_info *fi, int flag)
+static inline void f2fs_i_links_write(struct inode *inode, bool inc)
 {
-	return test_bit(flag, &fi->flags);
+	if (inc)
+		inc_nlink(inode);
+	else
+		drop_nlink(inode);
+	f2fs_mark_inode_dirty_sync(inode);
+}
+
+static inline void f2fs_i_blocks_write(struct inode *inode,
+					blkcnt_t diff, bool add)
+{
+	bool clean = !is_inode_flag_set(inode, FI_DIRTY_INODE);
+	bool recover = is_inode_flag_set(inode, FI_AUTO_RECOVER);
+
+	inode->i_blocks = add ? inode->i_blocks + diff :
+				inode->i_blocks - diff;
+	f2fs_mark_inode_dirty_sync(inode);
+	if (clean || recover)
+		set_inode_flag(inode, FI_AUTO_RECOVER);
+}
+
+static inline void f2fs_i_size_write(struct inode *inode, loff_t i_size)
+{
+	bool clean = !is_inode_flag_set(inode, FI_DIRTY_INODE);
+	bool recover = is_inode_flag_set(inode, FI_AUTO_RECOVER);
+
+	if (i_size_read(inode) == i_size)
+		return;
+
+	i_size_write(inode, i_size);
+	f2fs_mark_inode_dirty_sync(inode);
+	if (clean || recover)
+		set_inode_flag(inode, FI_AUTO_RECOVER);
 }
 
-static inline void clear_inode_flag(struct f2fs_inode_info *fi, int flag)
+static inline bool f2fs_skip_inode_update(struct inode *inode)
 {
-	if (test_bit(flag, &fi->flags))
-		clear_bit(flag, &fi->flags);
+	if (!is_inode_flag_set(inode, FI_AUTO_RECOVER))
+		return false;
+	return F2FS_I(inode)->last_disk_size == i_size_read(inode);
 }
 
-static inline void set_acl_inode(struct f2fs_inode_info *fi, umode_t mode)
+static inline void f2fs_i_depth_write(struct inode *inode, unsigned int depth)
 {
-	fi->i_acl_mode = mode;
-	set_inode_flag(fi, FI_ACL_MODE);
+	F2FS_I(inode)->i_current_depth = depth;
+	f2fs_mark_inode_dirty_sync(inode);
 }
 
-static inline void get_inline_info(struct f2fs_inode_info *fi,
-					struct f2fs_inode *ri)
+static inline void f2fs_i_xnid_write(struct inode *inode, nid_t xnid)
 {
+	F2FS_I(inode)->i_xattr_nid = xnid;
+	f2fs_mark_inode_dirty_sync(inode);
+}
+
+static inline void f2fs_i_pino_write(struct inode *inode, nid_t pino)
+{
+	F2FS_I(inode)->i_pino = pino;
+	f2fs_mark_inode_dirty_sync(inode);
+}
+
+static inline void get_inline_info(struct inode *inode, struct f2fs_inode *ri)
+{
+	struct f2fs_inode_info *fi = F2FS_I(inode);
+
 	if (ri->i_inline & F2FS_INLINE_XATTR)
-		set_inode_flag(fi, FI_INLINE_XATTR);
+		set_bit(FI_INLINE_XATTR, &fi->flags);
 	if (ri->i_inline & F2FS_INLINE_DATA)
-		set_inode_flag(fi, FI_INLINE_DATA);
+		set_bit(FI_INLINE_DATA, &fi->flags);
 	if (ri->i_inline & F2FS_INLINE_DENTRY)
-		set_inode_flag(fi, FI_INLINE_DENTRY);
+		set_bit(FI_INLINE_DENTRY, &fi->flags);
 	if (ri->i_inline & F2FS_DATA_EXIST)
-		set_inode_flag(fi, FI_DATA_EXIST);
+		set_bit(FI_DATA_EXIST, &fi->flags);
 	if (ri->i_inline & F2FS_INLINE_DOTS)
-		set_inode_flag(fi, FI_INLINE_DOTS);
+		set_bit(FI_INLINE_DOTS, &fi->flags);
 }
 
-static inline void set_raw_inline(struct f2fs_inode_info *fi,
-					struct f2fs_inode *ri)
+static inline void set_raw_inline(struct inode *inode, struct f2fs_inode *ri)
 {
 	ri->i_inline = 0;
 
-	if (is_inode_flag_set(fi, FI_INLINE_XATTR))
+	if (is_inode_flag_set(inode, FI_INLINE_XATTR))
 		ri->i_inline |= F2FS_INLINE_XATTR;
-	if (is_inode_flag_set(fi, FI_INLINE_DATA))
+	if (is_inode_flag_set(inode, FI_INLINE_DATA))
 		ri->i_inline |= F2FS_INLINE_DATA;
-	if (is_inode_flag_set(fi, FI_INLINE_DENTRY))
+	if (is_inode_flag_set(inode, FI_INLINE_DENTRY))
 		ri->i_inline |= F2FS_INLINE_DENTRY;
-	if (is_inode_flag_set(fi, FI_DATA_EXIST))
+	if (is_inode_flag_set(inode, FI_DATA_EXIST))
 		ri->i_inline |= F2FS_DATA_EXIST;
-	if (is_inode_flag_set(fi, FI_INLINE_DOTS))
+	if (is_inode_flag_set(inode, FI_INLINE_DOTS))
 		ri->i_inline |= F2FS_INLINE_DOTS;
 }
 
 static inline int f2fs_has_inline_xattr(struct inode *inode)
 {
-	return is_inode_flag_set(F2FS_I(inode), FI_INLINE_XATTR);
+	return is_inode_flag_set(inode, FI_INLINE_XATTR);
 }
 
 static inline unsigned int addrs_per_inode(struct inode *inode)
@@ -1618,43 +1724,43 @@ static inline int inline_xattr_size(struct inode *inode)
 
 static inline int f2fs_has_inline_data(struct inode *inode)
 {
-	return is_inode_flag_set(F2FS_I(inode), FI_INLINE_DATA);
+	return is_inode_flag_set(inode, FI_INLINE_DATA);
 }
 
 static inline void f2fs_clear_inline_inode(struct inode *inode)
 {
-	clear_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
-	clear_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
+	clear_inode_flag(inode, FI_INLINE_DATA);
+	clear_inode_flag(inode, FI_DATA_EXIST);
 }
 
 static inline int f2fs_exist_data(struct inode *inode)
 {
-	return is_inode_flag_set(F2FS_I(inode), FI_DATA_EXIST);
+	return is_inode_flag_set(inode, FI_DATA_EXIST);
 }
 
 static inline int f2fs_has_inline_dots(struct inode *inode)
 {
-	return is_inode_flag_set(F2FS_I(inode), FI_INLINE_DOTS);
+	return is_inode_flag_set(inode, FI_INLINE_DOTS);
 }
 
 static inline bool f2fs_is_atomic_file(struct inode *inode)
 {
-	return is_inode_flag_set(F2FS_I(inode), FI_ATOMIC_FILE);
+	return is_inode_flag_set(inode, FI_ATOMIC_FILE);
 }
 
 static inline bool f2fs_is_volatile_file(struct inode *inode)
 {
-	return is_inode_flag_set(F2FS_I(inode), FI_VOLATILE_FILE);
+	return is_inode_flag_set(inode, FI_VOLATILE_FILE);
 }
 
 static inline bool f2fs_is_first_block_written(struct inode *inode)
 {
-	return is_inode_flag_set(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN);
+	return is_inode_flag_set(inode, FI_FIRST_BLOCK_WRITTEN);
 }
 
 static inline bool f2fs_is_drop_cache(struct inode *inode)
 {
-	return is_inode_flag_set(F2FS_I(inode), FI_DROP_CACHE);
+	return is_inode_flag_set(inode, FI_DROP_CACHE);
 }
 
 static inline void *inline_data_addr(struct page *page)
@@ -1665,7 +1771,7 @@ static inline void *inline_data_addr(struct page *page)
 
 static inline int f2fs_has_inline_dentry(struct inode *inode)
 {
-	return is_inode_flag_set(F2FS_I(inode), FI_INLINE_DENTRY);
+	return is_inode_flag_set(inode, FI_INLINE_DENTRY);
 }
 
 static inline void f2fs_dentry_kunmap(struct inode *dir, struct page *page)
@@ -1682,11 +1788,13 @@ static inline int is_file(struct inode *inode, int type)
 static inline void set_file(struct inode *inode, int type)
 {
 	F2FS_I(inode)->i_advise |= type;
+	f2fs_mark_inode_dirty_sync(inode);
 }
 
 static inline void clear_file(struct inode *inode, int type)
 {
 	F2FS_I(inode)->i_advise &= ~type;
+	f2fs_mark_inode_dirty_sync(inode);
 }
 
 static inline int f2fs_readonly(struct super_block *sb)
@@ -1713,7 +1821,7 @@ static inline bool is_dot_dotdot(const struct qstr *str)
 static inline bool f2fs_may_extent_tree(struct inode *inode)
 {
 	if (!test_opt(F2FS_I_SB(inode), EXTENT_CACHE) ||
-			is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT))
+			is_inode_flag_set(inode, FI_NO_EXTENT))
 		return false;
 
 	return S_ISREG(inode->i_mode);
@@ -1749,7 +1857,7 @@ static inline void *f2fs_kvzalloc(size_t size, gfp_t flags)
 }
 
 #define get_inode_mode(i) \
-	((is_inode_flag_set(F2FS_I(i), FI_ACL_MODE)) ? \
+	((is_inode_flag_set(i, FI_ACL_MODE)) ? \
 	 (F2FS_I(i)->i_acl_mode) : ((i)->i_mode))
 
 /* get offset of first page in next direct node */
@@ -1764,7 +1872,7 @@ static inline void *f2fs_kvzalloc(size_t size, gfp_t flags)
 int f2fs_sync_file(struct file *, loff_t, loff_t, int);
 void truncate_data_blocks(struct dnode_of_data *);
 int truncate_blocks(struct inode *, u64, bool);
-int f2fs_truncate(struct inode *, bool);
+int f2fs_truncate(struct inode *);
 int f2fs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
 int f2fs_setattr(struct dentry *, struct iattr *);
 int truncate_hole(struct inode *, pgoff_t, pgoff_t);
@@ -1805,11 +1913,11 @@ struct page *init_inode_metadata(struct inode *, struct inode *,
 			const struct qstr *, struct page *);
 void update_parent_metadata(struct inode *, struct inode *, unsigned int);
 int room_for_filename(const void *, int, int);
-void f2fs_drop_nlink(struct inode *, struct inode *, struct page *);
+void f2fs_drop_nlink(struct inode *, struct inode *);
 struct f2fs_dir_entry *f2fs_find_entry(struct inode *, struct qstr *,
 							struct page **);
 struct f2fs_dir_entry *f2fs_parent_dir(struct inode *, struct page **);
-ino_t f2fs_inode_by_name(struct inode *, struct qstr *);
+ino_t f2fs_inode_by_name(struct inode *, struct qstr *, struct page **);
 void f2fs_set_link(struct inode *, struct f2fs_dir_entry *,
 				struct page *, struct inode *);
 int update_dent_inode(struct inode *, struct inode *, const struct qstr *);
@@ -1833,6 +1941,8 @@ static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode)
 /*
  * super.c
  */
+int f2fs_inode_dirtied(struct inode *);
+void f2fs_inode_synced(struct inode *);
 int f2fs_commit_super(struct f2fs_sb_info *, bool);
 int f2fs_sync_fs(struct super_block *, int);
 extern __printf(3, 4)
@@ -1866,11 +1976,11 @@ struct page *new_node_page(struct dnode_of_data *, unsigned int, struct page *);
 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 *);
 void move_node_page(struct page *, int);
-int fsync_node_pages(struct f2fs_sb_info *, nid_t, struct writeback_control *,
-								bool);
+int fsync_node_pages(struct f2fs_sb_info *, struct inode *,
+			struct writeback_control *, bool);
 int sync_node_pages(struct f2fs_sb_info *, struct writeback_control *);
+void build_free_nids(struct f2fs_sb_info *);
 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);
@@ -1944,9 +2054,10 @@ 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 *, bool);
 bool exist_written_data(struct f2fs_sb_info *, nid_t, int);
+int f2fs_sync_inode_meta(struct f2fs_sb_info *);
 int acquire_orphan_inode(struct f2fs_sb_info *);
 void release_orphan_inode(struct f2fs_sb_info *);
-void add_orphan_inode(struct f2fs_sb_info *, nid_t);
+void add_orphan_inode(struct inode *);
 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 *);
@@ -1981,6 +2092,7 @@ struct page *get_new_data_page(struct inode *, struct page *, pgoff_t, bool);
 int do_write_data_page(struct f2fs_io_info *);
 int f2fs_map_blocks(struct inode *, struct f2fs_map_blocks *, int, int);
 int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *, u64, u64);
+void f2fs_set_page_dirty_nobuffers(struct page *);
 void f2fs_invalidate_page(struct page *, unsigned int, unsigned int);
 int f2fs_release_page(struct page *, gfp_t);
 
@@ -2012,7 +2124,7 @@ struct f2fs_stat_info {
 	unsigned long long hit_total, total_ext;
 	int ext_tree, zombie_tree, ext_node;
 	s64 ndirty_node, ndirty_dent, ndirty_meta, ndirty_data, inmem_pages;
-	unsigned int ndirty_dirs, ndirty_files;
+	unsigned int ndirty_dirs, ndirty_files, ndirty_all;
 	int nats, dirty_nats, sits, dirty_sits, fnids;
 	int total_count, utilization;
 	int bg_gc, wb_bios;
@@ -2181,7 +2293,6 @@ int f2fs_write_inline_data(struct inode *, struct page *);
 bool recover_inline_data(struct inode *, struct page *);
 struct f2fs_dir_entry *find_in_inline_dir(struct inode *,
 				struct fscrypt_name *, struct page **);
-struct f2fs_dir_entry *f2fs_parent_inline_dir(struct inode *, struct page **);
 int make_empty_inline_dir(struct inode *inode, struct inode *, struct page *);
 int f2fs_add_inline_entry(struct inode *, const struct qstr *, struct inode *,
 						nid_t, umode_t);
@@ -2206,6 +2317,7 @@ void f2fs_leave_shrinker(struct f2fs_sb_info *);
  */
 unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *, int);
 bool f2fs_init_extent_tree(struct inode *, struct f2fs_extent *);
+void f2fs_drop_extent_tree(struct inode *);
 unsigned int f2fs_destroy_extent_node(struct inode *);
 void f2fs_destroy_extent_tree(struct inode *);
 bool f2fs_lookup_extent_cache(struct inode *, pgoff_t, struct extent_info *);
@@ -2241,6 +2353,26 @@ static inline int f2fs_sb_has_crypto(struct super_block *sb)
 	return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_ENCRYPT);
 }
 
+static inline int f2fs_sb_mounted_hmsmr(struct super_block *sb)
+{
+	return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_HMSMR);
+}
+
+static inline void set_opt_mode(struct f2fs_sb_info *sbi, unsigned int mt)
+{
+	clear_opt(sbi, ADAPTIVE);
+	clear_opt(sbi, LFS);
+
+	switch (mt) {
+	case F2FS_MOUNT_ADAPTIVE:
+		set_opt(sbi, ADAPTIVE);
+		break;
+	case F2FS_MOUNT_LFS:
+		set_opt(sbi, LFS);
+		break;
+	}
+}
+
 static inline bool f2fs_may_encrypt(struct inode *inode)
 {
 #ifdef CONFIG_F2FS_FS_ENCRYPTION

fs/f2fs/file.c

@@ -21,6 +21,7 @@
 #include <linux/mount.h>
 #include <linux/pagevec.h>
 #include <linux/uuid.h>
+#include <linux/file.h>
 
 #include "f2fs.h"
 #include "node.h"
@@ -81,7 +82,8 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
 		zero_user_segment(page, offset, PAGE_SIZE);
 	}
 	set_page_dirty(page);
-	SetPageUptodate(page);
+	if (!PageUptodate(page))
+		SetPageUptodate(page);
 
 	trace_f2fs_vm_page_mkwrite(page, DATA);
 mapped:
@@ -171,22 +173,16 @@ static void try_to_fix_pino(struct inode *inode)
 	fi->xattr_ver = 0;
 	if (file_wrong_pino(inode) && inode->i_nlink == 1 &&
 			get_parent_ino(inode, &pino)) {
-		fi->i_pino = pino;
+		f2fs_i_pino_write(inode, pino);
 		file_got_pino(inode);
-		up_write(&fi->i_sem);
-
-		mark_inode_dirty_sync(inode);
-		f2fs_write_inode(inode, NULL);
-	} else {
-		up_write(&fi->i_sem);
 	}
+	up_write(&fi->i_sem);
 }
 
 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);
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	nid_t ino = inode->i_ino;
 	int ret = 0;
@@ -204,9 +200,9 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
 
 	/* if fdatasync is triggered, let's do in-place-update */
 	if (datasync || get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks)
-		set_inode_flag(fi, FI_NEED_IPU);
+		set_inode_flag(inode, FI_NEED_IPU);
 	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
-	clear_inode_flag(fi, FI_NEED_IPU);
+	clear_inode_flag(inode, FI_NEED_IPU);
 
 	if (ret) {
 		trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
@@ -214,7 +210,7 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
 	}
 
 	/* if the inode is dirty, let's recover all the time */
-	if (!datasync) {
+	if (!datasync && !f2fs_skip_inode_update(inode)) {
 		f2fs_write_inode(inode, NULL);
 		goto go_write;
 	}
@@ -222,14 +218,14 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
 	/*
 	 * if there is no written data, don't waste time to write recovery info.
 	 */
-	if (!is_inode_flag_set(fi, FI_APPEND_WRITE) &&
+	if (!is_inode_flag_set(inode, FI_APPEND_WRITE) &&
 			!exist_written_data(sbi, ino, APPEND_INO)) {
 
 		/* it may call write_inode just prior to fsync */
 		if (need_inode_page_update(sbi, ino))
 			goto go_write;
 
-		if (is_inode_flag_set(fi, FI_UPDATE_WRITE) ||
+		if (is_inode_flag_set(inode, FI_UPDATE_WRITE) ||
 				exist_written_data(sbi, ino, UPDATE_INO))
 			goto flush_out;
 		goto out;
@@ -239,9 +235,9 @@ go_write:
 	 * Both of fdatasync() and fsync() are able to be recovered from
 	 * sudden-power-off.
 	 */
-	down_read(&fi->i_sem);
+	down_read(&F2FS_I(inode)->i_sem);
 	need_cp = need_do_checkpoint(inode);
-	up_read(&fi->i_sem);
+	up_read(&F2FS_I(inode)->i_sem);
 
 	if (need_cp) {
 		/* all the dirty node pages should be flushed for POR */
@@ -252,12 +248,12 @@ go_write:
 		 * will be used only for fsynced inodes after checkpoint.
 		 */
 		try_to_fix_pino(inode);
-		clear_inode_flag(fi, FI_APPEND_WRITE);
-		clear_inode_flag(fi, FI_UPDATE_WRITE);
+		clear_inode_flag(inode, FI_APPEND_WRITE);
+		clear_inode_flag(inode, FI_UPDATE_WRITE);
 		goto out;
 	}
 sync_nodes:
-	ret = fsync_node_pages(sbi, ino, &wbc, atomic);
+	ret = fsync_node_pages(sbi, inode, &wbc, atomic);
 	if (ret)
 		goto out;
 
@@ -268,7 +264,7 @@ sync_nodes:
 	}
 
 	if (need_inode_block_update(sbi, ino)) {
-		mark_inode_dirty_sync(inode);
+		f2fs_mark_inode_dirty_sync(inode);
 		f2fs_write_inode(inode, NULL);
 		goto sync_nodes;
 	}
@@ -279,10 +275,10 @@ sync_nodes:
 
 	/* once recovery info is written, don't need to tack this */
 	remove_ino_entry(sbi, ino, APPEND_INO);
-	clear_inode_flag(fi, FI_APPEND_WRITE);
+	clear_inode_flag(inode, FI_APPEND_WRITE);
 flush_out:
 	remove_ino_entry(sbi, ino, UPDATE_INO);
-	clear_inode_flag(fi, FI_UPDATE_WRITE);
+	clear_inode_flag(inode, FI_UPDATE_WRITE);
 	ret = f2fs_issue_flush(sbi);
 	f2fs_update_time(sbi, REQ_TIME);
 out:
@@ -360,7 +356,7 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
 
 	for (; data_ofs < isize; data_ofs = (loff_t)pgofs << PAGE_SHIFT) {
 		set_new_dnode(&dn, inode, NULL, NULL, 0);
-		err = get_dnode_of_data(&dn, pgofs, LOOKUP_NODE_RA);
+		err = get_dnode_of_data(&dn, pgofs, LOOKUP_NODE);
 		if (err && err != -ENOENT) {
 			goto fail;
 		} else if (err == -ENOENT) {
@@ -487,8 +483,7 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
 		set_data_blkaddr(dn);
 		invalidate_blocks(sbi, blkaddr);
 		if (dn->ofs_in_node == 0 && IS_INODE(dn->node_page))
-			clear_inode_flag(F2FS_I(dn->inode),
-						FI_FIRST_BLOCK_WRITTEN);
+			clear_inode_flag(dn->inode, FI_FIRST_BLOCK_WRITTEN);
 		nr_free++;
 	}
 
@@ -502,7 +497,6 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
 							dn->inode) + ofs;
 		f2fs_update_extent_cache_range(dn, fofs, 0, len);
 		dec_valid_block_count(sbi, dn->inode, nr_free);
-		sync_inode_page(dn);
 	}
 	dn->ofs_in_node = ofs;
 
@@ -616,7 +610,7 @@ free_partial:
 	return err;
 }
 
-int f2fs_truncate(struct inode *inode, bool lock)
+int f2fs_truncate(struct inode *inode)
 {
 	int err;
 
@@ -633,12 +627,12 @@ int f2fs_truncate(struct inode *inode, bool lock)
 			return err;
 	}
 
-	err = truncate_blocks(inode, i_size_read(inode), lock);
+	err = truncate_blocks(inode, i_size_read(inode), true);
 	if (err)
 		return err;
 
 	inode->i_mtime = inode->i_ctime = CURRENT_TIME;
-	mark_inode_dirty(inode);
+	f2fs_mark_inode_dirty_sync(inode);
 	return 0;
 }
 
@@ -654,7 +648,6 @@ int f2fs_getattr(struct vfsmount *mnt,
 #ifdef CONFIG_F2FS_FS_POSIX_ACL
 static void __setattr_copy(struct inode *inode, const struct iattr *attr)
 {
-	struct f2fs_inode_info *fi = F2FS_I(inode);
 	unsigned int ia_valid = attr->ia_valid;
 
 	if (ia_valid & ATTR_UID)
@@ -675,7 +668,7 @@ static void __setattr_copy(struct inode *inode, const struct iattr *attr)
 
 		if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID))
 			mode &= ~S_ISGID;
-		set_acl_inode(fi, mode);
+		set_acl_inode(inode, mode);
 	}
 }
 #else
@@ -685,7 +678,6 @@ static void __setattr_copy(struct inode *inode, const struct iattr *attr)
 int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
 {
 	struct inode *inode = d_inode(dentry);
-	struct f2fs_inode_info *fi = F2FS_I(inode);
 	int err;
 
 	err = inode_change_ok(inode, attr);
@@ -699,7 +691,7 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
 
 		if (attr->ia_size <= i_size_read(inode)) {
 			truncate_setsize(inode, attr->ia_size);
-			err = f2fs_truncate(inode, true);
+			err = f2fs_truncate(inode);
 			if (err)
 				return err;
 			f2fs_balance_fs(F2FS_I_SB(inode), true);
@@ -724,13 +716,13 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
 
 	if (attr->ia_valid & ATTR_MODE) {
 		err = posix_acl_chmod(inode, get_inode_mode(inode));
-		if (err || is_inode_flag_set(fi, FI_ACL_MODE)) {
-			inode->i_mode = fi->i_acl_mode;
-			clear_inode_flag(fi, FI_ACL_MODE);
+		if (err || is_inode_flag_set(inode, FI_ACL_MODE)) {
+			inode->i_mode = F2FS_I(inode)->i_acl_mode;
+			clear_inode_flag(inode, FI_ACL_MODE);
 		}
 	}
 
-	mark_inode_dirty(inode);
+	f2fs_mark_inode_dirty_sync(inode);
 	return err;
 }
 
@@ -859,79 +851,199 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	return ret;
 }
 
-static int __exchange_data_block(struct inode *inode, pgoff_t src,
-					pgoff_t dst, bool full)
+static int __read_out_blkaddrs(struct inode *inode, block_t *blkaddr,
+				int *do_replace, pgoff_t off, pgoff_t len)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct dnode_of_data dn;
-	block_t new_addr;
-	bool do_replace = false;
-	int ret;
+	int ret, done, i;
 
+next_dnode:
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
-	ret = get_dnode_of_data(&dn, src, LOOKUP_NODE_RA);
+	ret = get_dnode_of_data(&dn, off, LOOKUP_NODE_RA);
 	if (ret && ret != -ENOENT) {
 		return ret;
 	} else if (ret == -ENOENT) {
-		new_addr = NULL_ADDR;
-	} else {
-		new_addr = dn.data_blkaddr;
-		if (!is_checkpointed_data(sbi, new_addr)) {
+		if (dn.max_level == 0)
+			return -ENOENT;
+		done = min((pgoff_t)ADDRS_PER_BLOCK - dn.ofs_in_node, len);
+		blkaddr += done;
+		do_replace += done;
+		goto next;
+	}
+
+	done = min((pgoff_t)ADDRS_PER_PAGE(dn.node_page, inode) -
+							dn.ofs_in_node, len);
+	for (i = 0; i < done; i++, blkaddr++, do_replace++, dn.ofs_in_node++) {
+		*blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
+		if (!is_checkpointed_data(sbi, *blkaddr)) {
+
+			if (test_opt(sbi, LFS)) {
+				f2fs_put_dnode(&dn);
+				return -ENOTSUPP;
+			}
+
 			/* do not invalidate this block address */
 			f2fs_update_data_blkaddr(&dn, NULL_ADDR);
-			do_replace = true;
+			*do_replace = 1;
 		}
-		f2fs_put_dnode(&dn);
 	}
+	f2fs_put_dnode(&dn);
+next:
+	len -= done;
+	off += done;
+	if (len)
+		goto next_dnode;
+	return 0;
+}
 
-	if (new_addr == NULL_ADDR)
-		return full ? truncate_hole(inode, dst, dst + 1) : 0;
+static int __roll_back_blkaddrs(struct inode *inode, block_t *blkaddr,
+				int *do_replace, pgoff_t off, int len)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct dnode_of_data dn;
+	int ret, i;
 
-	if (do_replace) {
-		struct page *ipage = get_node_page(sbi, inode->i_ino);
-		struct node_info ni;
+	for (i = 0; i < len; i++, do_replace++, blkaddr++) {
+		if (*do_replace == 0)
+			continue;
 
-		if (IS_ERR(ipage)) {
-			ret = PTR_ERR(ipage);
-			goto err_out;
+		set_new_dnode(&dn, inode, NULL, NULL, 0);
+		ret = get_dnode_of_data(&dn, off + i, LOOKUP_NODE_RA);
+		if (ret) {
+			dec_valid_block_count(sbi, inode, 1);
+			invalidate_blocks(sbi, *blkaddr);
+		} else {
+			f2fs_update_data_blkaddr(&dn, *blkaddr);
 		}
+		f2fs_put_dnode(&dn);
+	}
+	return 0;
+}
 
-		set_new_dnode(&dn, inode, ipage, NULL, 0);
-		ret = f2fs_reserve_block(&dn, dst);
-		if (ret)
-			goto err_out;
+static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode,
+			block_t *blkaddr, int *do_replace,
+			pgoff_t src, pgoff_t dst, pgoff_t len, bool full)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(src_inode);
+	pgoff_t i = 0;
+	int ret;
+
+	while (i < len) {
+		if (blkaddr[i] == NULL_ADDR && !full) {
+			i++;
+			continue;
+		}
 
-		truncate_data_blocks_range(&dn, 1);
+		if (do_replace[i] || blkaddr[i] == NULL_ADDR) {
+			struct dnode_of_data dn;
+			struct node_info ni;
+			size_t new_size;
+			pgoff_t ilen;
 
-		get_node_info(sbi, dn.nid, &ni);
-		f2fs_replace_block(sbi, &dn, dn.data_blkaddr, new_addr,
-				ni.version, true, false);
-		f2fs_put_dnode(&dn);
-	} else {
-		struct page *psrc, *pdst;
+			set_new_dnode(&dn, dst_inode, NULL, NULL, 0);
+			ret = get_dnode_of_data(&dn, dst + i, ALLOC_NODE);
+			if (ret)
+				return ret;
+
+			get_node_info(sbi, dn.nid, &ni);
+			ilen = min((pgoff_t)
+				ADDRS_PER_PAGE(dn.node_page, dst_inode) -
+						dn.ofs_in_node, len - i);
+			do {
+				dn.data_blkaddr = datablock_addr(dn.node_page,
+								dn.ofs_in_node);
+				truncate_data_blocks_range(&dn, 1);
+
+				if (do_replace[i]) {
+					f2fs_i_blocks_write(src_inode,
+								1, false);
+					f2fs_i_blocks_write(dst_inode,
+								1, true);
+					f2fs_replace_block(sbi, &dn, dn.data_blkaddr,
+					blkaddr[i], ni.version, true, false);
+
+					do_replace[i] = 0;
+				}
+				dn.ofs_in_node++;
+				i++;
+				new_size = (dst + i) << PAGE_SHIFT;
+				if (dst_inode->i_size < new_size)
+					f2fs_i_size_write(dst_inode, new_size);
+			} while ((do_replace[i] || blkaddr[i] == NULL_ADDR) && --ilen);
 
-		psrc = get_lock_data_page(inode, src, true);
-		if (IS_ERR(psrc))
-			return PTR_ERR(psrc);
-		pdst = get_new_data_page(inode, NULL, dst, true);
-		if (IS_ERR(pdst)) {
+			f2fs_put_dnode(&dn);
+		} else {
+			struct page *psrc, *pdst;
+
+			psrc = get_lock_data_page(src_inode, src + i, true);
+			if (IS_ERR(psrc))
+				return PTR_ERR(psrc);
+			pdst = get_new_data_page(dst_inode, NULL, dst + i,
+								true);
+			if (IS_ERR(pdst)) {
+				f2fs_put_page(psrc, 1);
+				return PTR_ERR(pdst);
+			}
+			f2fs_copy_page(psrc, pdst);
+			set_page_dirty(pdst);
+			f2fs_put_page(pdst, 1);
 			f2fs_put_page(psrc, 1);
-			return PTR_ERR(pdst);
-		}
-		f2fs_copy_page(psrc, pdst);
-		set_page_dirty(pdst);
-		f2fs_put_page(pdst, 1);
-		f2fs_put_page(psrc, 1);
 
-		return truncate_hole(inode, src, src + 1);
+			ret = truncate_hole(src_inode, src + i, src + i + 1);
+			if (ret)
+				return ret;
+			i++;
+		}
 	}
 	return 0;
+}
 
-err_out:
-	if (!get_dnode_of_data(&dn, src, LOOKUP_NODE)) {
-		f2fs_update_data_blkaddr(&dn, new_addr);
-		f2fs_put_dnode(&dn);
+static int __exchange_data_block(struct inode *src_inode,
+			struct inode *dst_inode, pgoff_t src, pgoff_t dst,
+			pgoff_t len, bool full)
+{
+	block_t *src_blkaddr;
+	int *do_replace;
+	pgoff_t olen;
+	int ret;
+
+	while (len) {
+		olen = min((pgoff_t)4 * ADDRS_PER_BLOCK, len);
+
+		src_blkaddr = f2fs_kvzalloc(sizeof(block_t) * olen, GFP_KERNEL);
+		if (!src_blkaddr)
+			return -ENOMEM;
+
+		do_replace = f2fs_kvzalloc(sizeof(int) * olen, GFP_KERNEL);
+		if (!do_replace) {
+			kvfree(src_blkaddr);
+			return -ENOMEM;
+		}
+
+		ret = __read_out_blkaddrs(src_inode, src_blkaddr,
+					do_replace, src, olen);
+		if (ret)
+			goto roll_back;
+
+		ret = __clone_blkaddrs(src_inode, dst_inode, src_blkaddr,
+					do_replace, src, dst, olen, full);
+		if (ret)
+			goto roll_back;
+
+		src += olen;
+		dst += olen;
+		len -= olen;
+
+		kvfree(src_blkaddr);
+		kvfree(do_replace);
 	}
+	return 0;
+
+roll_back:
+	__roll_back_blkaddrs(src_inode, src_blkaddr, do_replace, src, len);
+	kvfree(src_blkaddr);
+	kvfree(do_replace);
 	return ret;
 }
 
@@ -939,16 +1051,15 @@ static int f2fs_do_collapse(struct inode *inode, pgoff_t start, pgoff_t end)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	pgoff_t nrpages = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE;
-	int ret = 0;
+	int ret;
 
-	for (; end < nrpages; start++, end++) {
-		f2fs_balance_fs(sbi, true);
-		f2fs_lock_op(sbi);
-		ret = __exchange_data_block(inode, end, start, true);
-		f2fs_unlock_op(sbi);
-		if (ret)
-			break;
-	}
+	f2fs_balance_fs(sbi, true);
+	f2fs_lock_op(sbi);
+
+	f2fs_drop_extent_tree(inode);
+
+	ret = __exchange_data_block(inode, inode, end, start, nrpages - end, true);
+	f2fs_unlock_op(sbi);
 	return ret;
 }
 
@@ -992,7 +1103,7 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 
 	ret = truncate_blocks(inode, new_size, true);
 	if (!ret)
-		i_size_write(inode, new_size);
+		f2fs_i_size_write(inode, new_size);
 
 	return ret;
 }
@@ -1128,11 +1239,8 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
 	}
 
 out:
-	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);
-	}
+	if (!(mode & FALLOC_FL_KEEP_SIZE) && i_size_read(inode) < new_size)
+		f2fs_i_size_write(inode, new_size);
 
 	return ret;
 }
@@ -1140,7 +1248,7 @@ out:
 static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	pgoff_t pg_start, pg_end, delta, nrpages, idx;
+	pgoff_t nr, pg_start, pg_end, delta, idx;
 	loff_t new_size;
 	int ret = 0;
 
@@ -1175,14 +1283,20 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
 	pg_start = offset >> PAGE_SHIFT;
 	pg_end = (offset + len) >> PAGE_SHIFT;
 	delta = pg_end - pg_start;
-	nrpages = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE;
+	idx = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE;
+
+	while (!ret && idx > pg_start) {
+		nr = idx - pg_start;
+		if (nr > delta)
+			nr = delta;
+		idx -= nr;
 
-	for (idx = nrpages - 1; idx >= pg_start && idx != -1; idx--) {
 		f2fs_lock_op(sbi);
-		ret = __exchange_data_block(inode, idx, idx + delta, false);
+		f2fs_drop_extent_tree(inode);
+
+		ret = __exchange_data_block(inode, inode, idx,
+					idx + delta, nr, false);
 		f2fs_unlock_op(sbi);
-		if (ret)
-			break;
 	}
 
 	/* write out all moved pages, if possible */
@@ -1190,7 +1304,7 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
 	truncate_pagecache(inode, offset);
 
 	if (!ret)
-		i_size_write(inode, new_size);
+		f2fs_i_size_write(inode, new_size);
 	return ret;
 }
 
@@ -1238,11 +1352,8 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
 		new_size = ((loff_t)pg_end << PAGE_SHIFT) + off_end;
 	}
 
-	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);
-	}
+	if (!(mode & FALLOC_FL_KEEP_SIZE) && i_size_read(inode) < new_size)
+		f2fs_i_size_write(inode, new_size);
 
 	return ret;
 }
@@ -1285,7 +1396,7 @@ static long f2fs_fallocate(struct file *file, int mode,
 
 	if (!ret) {
 		inode->i_mtime = inode->i_ctime = CURRENT_TIME;
-		mark_inode_dirty(inode);
+		f2fs_mark_inode_dirty_sync(inode);
 		f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
 	}
 
@@ -1310,10 +1421,10 @@ static int f2fs_release_file(struct inode *inode, struct file *filp)
 	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);
+		clear_inode_flag(inode, FI_VOLATILE_FILE);
+		set_inode_flag(inode, FI_DROP_CACHE);
 		filemap_fdatawrite(inode->i_mapping);
-		clear_inode_flag(F2FS_I(inode), FI_DROP_CACHE);
+		clear_inode_flag(inode, FI_DROP_CACHE);
 	}
 	return 0;
 }
@@ -1376,9 +1487,8 @@ static int f2fs_ioc_setflags(struct file *filp, unsigned long arg)
 	fi->i_flags = flags;
 	inode_unlock(inode);
 
-	f2fs_set_inode_flags(inode);
 	inode->i_ctime = CURRENT_TIME;
-	mark_inode_dirty(inode);
+	f2fs_set_inode_flags(inode);
 out:
 	mnt_drop_write_file(filp);
 	return ret;
@@ -1412,7 +1522,7 @@ static int f2fs_ioc_start_atomic_write(struct file *filp)
 	if (ret)
 		goto out;
 
-	set_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
+	set_inode_flag(inode, FI_ATOMIC_FILE);
 	f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
 
 	if (!get_dirty_pages(inode))
@@ -1423,7 +1533,7 @@ static int f2fs_ioc_start_atomic_write(struct file *filp)
 					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);
+		clear_inode_flag(inode, FI_ATOMIC_FILE);
 out:
 	inode_unlock(inode);
 	mnt_drop_write_file(filp);
@@ -1448,10 +1558,10 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp)
 		goto err_out;
 
 	if (f2fs_is_atomic_file(inode)) {
-		clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
+		clear_inode_flag(inode, FI_ATOMIC_FILE);
 		ret = commit_inmem_pages(inode);
 		if (ret) {
-			set_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
+			set_inode_flag(inode, FI_ATOMIC_FILE);
 			goto err_out;
 		}
 	}
@@ -1484,7 +1594,7 @@ static int f2fs_ioc_start_volatile_write(struct file *filp)
 	if (ret)
 		goto out;
 
-	set_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
+	set_inode_flag(inode, FI_VOLATILE_FILE);
 	f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
 out:
 	inode_unlock(inode);
@@ -1538,7 +1648,7 @@ static int f2fs_ioc_abort_volatile_write(struct file *filp)
 	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);
+		clear_inode_flag(inode, FI_VOLATILE_FILE);
 		ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
 	}
 
@@ -1871,7 +1981,7 @@ do_map:
 			continue;
 		}
 
-		set_inode_flag(F2FS_I(inode), FI_DO_DEFRAG);
+		set_inode_flag(inode, FI_DO_DEFRAG);
 
 		idx = map.m_lblk;
 		while (idx < map.m_lblk + map.m_len && cnt < blk_per_seg) {
@@ -1896,14 +2006,14 @@ do_map:
 		if (idx < pg_end && cnt < blk_per_seg)
 			goto do_map;
 
-		clear_inode_flag(F2FS_I(inode), FI_DO_DEFRAG);
+		clear_inode_flag(inode, FI_DO_DEFRAG);
 
 		err = filemap_fdatawrite(inode->i_mapping);
 		if (err)
 			goto out;
 	}
 clear_out:
-	clear_inode_flag(F2FS_I(inode), FI_DO_DEFRAG);
+	clear_inode_flag(inode, FI_DO_DEFRAG);
 out:
 	inode_unlock(inode);
 	if (!err)
@@ -1959,6 +2069,133 @@ out:
 	return err;
 }
 
+static int f2fs_move_file_range(struct file *file_in, loff_t pos_in,
+			struct file *file_out, loff_t pos_out, size_t len)
+{
+	struct inode *src = file_inode(file_in);
+	struct inode *dst = file_inode(file_out);
+	struct f2fs_sb_info *sbi = F2FS_I_SB(src);
+	size_t olen = len, dst_max_i_size = 0;
+	size_t dst_osize;
+	int ret;
+
+	if (file_in->f_path.mnt != file_out->f_path.mnt ||
+				src->i_sb != dst->i_sb)
+		return -EXDEV;
+
+	if (unlikely(f2fs_readonly(src->i_sb)))
+		return -EROFS;
+
+	if (S_ISDIR(src->i_mode) || S_ISDIR(dst->i_mode))
+		return -EISDIR;
+
+	if (f2fs_encrypted_inode(src) || f2fs_encrypted_inode(dst))
+		return -EOPNOTSUPP;
+
+	inode_lock(src);
+	if (src != dst)
+		inode_lock(dst);
+
+	ret = -EINVAL;
+	if (pos_in + len > src->i_size || pos_in + len < pos_in)
+		goto out_unlock;
+	if (len == 0)
+		olen = len = src->i_size - pos_in;
+	if (pos_in + len == src->i_size)
+		len = ALIGN(src->i_size, F2FS_BLKSIZE) - pos_in;
+	if (len == 0) {
+		ret = 0;
+		goto out_unlock;
+	}
+
+	dst_osize = dst->i_size;
+	if (pos_out + olen > dst->i_size)
+		dst_max_i_size = pos_out + olen;
+
+	/* verify the end result is block aligned */
+	if (!IS_ALIGNED(pos_in, F2FS_BLKSIZE) ||
+			!IS_ALIGNED(pos_in + len, F2FS_BLKSIZE) ||
+			!IS_ALIGNED(pos_out, F2FS_BLKSIZE))
+		goto out_unlock;
+
+	ret = f2fs_convert_inline_inode(src);
+	if (ret)
+		goto out_unlock;
+
+	ret = f2fs_convert_inline_inode(dst);
+	if (ret)
+		goto out_unlock;
+
+	/* write out all dirty pages from offset */
+	ret = filemap_write_and_wait_range(src->i_mapping,
+					pos_in, pos_in + len);
+	if (ret)
+		goto out_unlock;
+
+	ret = filemap_write_and_wait_range(dst->i_mapping,
+					pos_out, pos_out + len);
+	if (ret)
+		goto out_unlock;
+
+	f2fs_balance_fs(sbi, true);
+	f2fs_lock_op(sbi);
+	ret = __exchange_data_block(src, dst, pos_in,
+				pos_out, len >> F2FS_BLKSIZE_BITS, false);
+
+	if (!ret) {
+		if (dst_max_i_size)
+			f2fs_i_size_write(dst, dst_max_i_size);
+		else if (dst_osize != dst->i_size)
+			f2fs_i_size_write(dst, dst_osize);
+	}
+	f2fs_unlock_op(sbi);
+out_unlock:
+	if (src != dst)
+		inode_unlock(dst);
+	inode_unlock(src);
+	return ret;
+}
+
+static int f2fs_ioc_move_range(struct file *filp, unsigned long arg)
+{
+	struct f2fs_move_range range;
+	struct fd dst;
+	int err;
+
+	if (!(filp->f_mode & FMODE_READ) ||
+			!(filp->f_mode & FMODE_WRITE))
+		return -EBADF;
+
+	if (copy_from_user(&range, (struct f2fs_move_range __user *)arg,
+							sizeof(range)))
+		return -EFAULT;
+
+	dst = fdget(range.dst_fd);
+	if (!dst.file)
+		return -EBADF;
+
+	if (!(dst.file->f_mode & FMODE_WRITE)) {
+		err = -EBADF;
+		goto err_out;
+	}
+
+	err = mnt_want_write_file(filp);
+	if (err)
+		goto err_out;
+
+	err = f2fs_move_file_range(filp, range.pos_in, dst.file,
+					range.pos_out, range.len);
+
+	mnt_drop_write_file(filp);
+
+	if (copy_to_user((struct f2fs_move_range __user *)arg,
+						&range, sizeof(range)))
+		err = -EFAULT;
+err_out:
+	fdput(dst);
+	return err;
+}
+
 long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	switch (cmd) {
@@ -1994,6 +2231,8 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		return f2fs_ioc_write_checkpoint(filp, arg);
 	case F2FS_IOC_DEFRAGMENT:
 		return f2fs_ioc_defragment(filp, arg);
+	case F2FS_IOC_MOVE_RANGE:
+		return f2fs_ioc_move_range(filp, arg);
 	default:
 		return -ENOTTY;
 	}
@@ -2003,6 +2242,7 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
+	struct blk_plug plug;
 	ssize_t ret;
 
 	if (f2fs_encrypted_inode(inode) &&
@@ -2014,8 +2254,11 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	ret = generic_write_checks(iocb, from);
 	if (ret > 0) {
 		ret = f2fs_preallocate_blocks(iocb, from);
-		if (!ret)
+		if (!ret) {
+			blk_start_plug(&plug);
 			ret = __generic_file_write_iter(iocb, from);
+			blk_finish_plug(&plug);
+		}
 	}
 	inode_unlock(inode);
 
@@ -2050,6 +2293,8 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case F2FS_IOC_WRITE_CHECKPOINT:
 	case F2FS_IOC_DEFRAGMENT:
 		break;
+	case F2FS_IOC_MOVE_RANGE:
+		break;
 	default:
 		return -ENOIOCTLCMD;
 	}

fs/f2fs/gc.c

@@ -594,11 +594,11 @@ static void move_encrypted_block(struct inode *inode, block_t bidx)
 	/* write page */
 	lock_page(fio.encrypted_page);
 
-	if (unlikely(!PageUptodate(fio.encrypted_page))) {
+	if (unlikely(fio.encrypted_page->mapping != META_MAPPING(fio.sbi))) {
 		err = -EIO;
 		goto put_page_out;
 	}
-	if (unlikely(fio.encrypted_page->mapping != META_MAPPING(fio.sbi))) {
+	if (unlikely(!PageUptodate(fio.encrypted_page))) {
 		err = -EIO;
 		goto put_page_out;
 	}
@@ -619,9 +619,9 @@ static void move_encrypted_block(struct inode *inode, block_t bidx)
 	f2fs_submit_page_mbio(&fio);
 
 	f2fs_update_data_blkaddr(&dn, newaddr);
-	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);
 put_page_out:
 	f2fs_put_page(fio.encrypted_page, 1);
 recover_block:
@@ -656,12 +656,23 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type)
 			.page = page,
 			.encrypted_page = NULL,
 		};
+		bool is_dirty = PageDirty(page);
+		int err;
+
+retry:
 		set_page_dirty(page);
 		f2fs_wait_on_page_writeback(page, DATA, true);
 		if (clear_page_dirty_for_io(page))
 			inode_dec_dirty_pages(inode);
+
 		set_cold_data(page);
-		do_write_data_page(&fio);
+
+		err = do_write_data_page(&fio);
+		if (err == -ENOMEM && is_dirty) {
+			congestion_wait(BLK_RW_ASYNC, HZ/50);
+			goto retry;
+		}
+
 		clear_cold_data(page);
 	}
 out:
@@ -748,12 +759,32 @@ next_step:
 		/* phase 3 */
 		inode = find_gc_inode(gc_list, dni.ino);
 		if (inode) {
+			struct f2fs_inode_info *fi = F2FS_I(inode);
+			bool locked = false;
+
+			if (S_ISREG(inode->i_mode)) {
+				if (!down_write_trylock(&fi->dio_rwsem[READ]))
+					continue;
+				if (!down_write_trylock(
+						&fi->dio_rwsem[WRITE])) {
+					up_write(&fi->dio_rwsem[READ]);
+					continue;
+				}
+				locked = true;
+			}
+
 			start_bidx = start_bidx_of_node(nofs, inode)
 								+ ofs_in_node;
 			if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
 				move_encrypted_block(inode, start_bidx);
 			else
 				move_data_page(inode, start_bidx, gc_type);
+
+			if (locked) {
+				up_write(&fi->dio_rwsem[WRITE]);
+				up_write(&fi->dio_rwsem[READ]);
+			}
+
 			stat_inc_data_blk_count(sbi, 1, gc_type);
 		}
 	}
@@ -802,6 +833,10 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi,
 	blk_start_plug(&plug);
 
 	for (segno = start_segno; segno < end_segno; segno++) {
+
+		if (get_valid_blocks(sbi, segno, 1) == 0)
+			continue;
+
 		/* find segment summary of victim */
 		sum_page = find_get_page(META_MAPPING(sbi),
 					GET_SUM_BLOCK(sbi, segno));
@@ -877,10 +912,13 @@ gc_more:
 		 * enough free sections, we should flush dent/node blocks and do
 		 * garbage collections.
 		 */
-		if (__get_victim(sbi, &segno, gc_type) || prefree_segments(sbi))
+		if (__get_victim(sbi, &segno, gc_type) ||
+						prefree_segments(sbi)) {
 			write_checkpoint(sbi, &cpc);
-		else if (has_not_enough_free_secs(sbi, 0))
+			segno = NULL_SEGNO;
+		} else if (has_not_enough_free_secs(sbi, 0)) {
 			write_checkpoint(sbi, &cpc);
+		}
 	}
 
 	if (segno == NULL_SEGNO && !__get_victim(sbi, &segno, gc_type))

fs/f2fs/inline.c

@@ -59,7 +59,8 @@ void read_inline_data(struct page *page, struct page *ipage)
 	memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
 	flush_dcache_page(page);
 	kunmap_atomic(dst_addr);
-	SetPageUptodate(page);
+	if (!PageUptodate(page))
+		SetPageUptodate(page);
 }
 
 bool truncate_inline_inode(struct page *ipage, u64 from)
@@ -73,7 +74,7 @@ bool truncate_inline_inode(struct page *ipage, u64 from)
 
 	f2fs_wait_on_page_writeback(ipage, NODE, true);
 	memset(addr + from, 0, MAX_INLINE_DATA - from);
-
+	set_page_dirty(ipage);
 	return true;
 }
 
@@ -97,7 +98,8 @@ int f2fs_read_inline_data(struct inode *inode, struct page *page)
 	else
 		read_inline_data(page, ipage);
 
-	SetPageUptodate(page);
+	if (!PageUptodate(page))
+		SetPageUptodate(page);
 	f2fs_put_page(ipage, 1);
 	unlock_page(page);
 	return 0;
@@ -139,7 +141,7 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
 		inode_dec_dirty_pages(dn->inode);
 
 	/* this converted inline_data should be recovered. */
-	set_inode_flag(F2FS_I(dn->inode), FI_APPEND_WRITE);
+	set_inode_flag(dn->inode, FI_APPEND_WRITE);
 
 	/* clear inline data and flag after data writeback */
 	truncate_inline_inode(dn->inode_page, 0);
@@ -147,7 +149,6 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
 clear_out:
 	stat_dec_inline_inode(dn->inode);
 	f2fs_clear_inline_inode(dn->inode);
-	sync_inode_page(dn);
 	f2fs_put_dnode(dn);
 	return 0;
 }
@@ -213,11 +214,11 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page)
 	dst_addr = inline_data_addr(dn.inode_page);
 	memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
 	kunmap_atomic(src_addr);
+	set_page_dirty(dn.inode_page);
 
-	set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
-	set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
+	set_inode_flag(inode, FI_APPEND_WRITE);
+	set_inode_flag(inode, FI_DATA_EXIST);
 
-	sync_inode_page(&dn);
 	clear_inline_node(dn.inode_page);
 	f2fs_put_dnode(&dn);
 	return 0;
@@ -253,10 +254,10 @@ process_inline:
 		dst_addr = inline_data_addr(ipage);
 		memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
 
-		set_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
-		set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
+		set_inode_flag(inode, FI_INLINE_DATA);
+		set_inode_flag(inode, FI_DATA_EXIST);
 
-		update_inode(inode, ipage);
+		set_page_dirty(ipage);
 		f2fs_put_page(ipage, 1);
 		return true;
 	}
@@ -267,7 +268,6 @@ process_inline:
 		if (!truncate_inline_inode(ipage, 0))
 			return false;
 		f2fs_clear_inline_inode(inode);
-		update_inode(inode, ipage);
 		f2fs_put_page(ipage, 1);
 	} else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) {
 		if (truncate_blocks(inode, 0, false))
@@ -289,8 +289,10 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
 	f2fs_hash_t namehash;
 
 	ipage = get_node_page(sbi, dir->i_ino);
-	if (IS_ERR(ipage))
+	if (IS_ERR(ipage)) {
+		*res_page = ipage;
 		return NULL;
+	}
 
 	namehash = f2fs_dentry_hash(&name);
 
@@ -307,25 +309,6 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
 	return de;
 }
 
-struct f2fs_dir_entry *f2fs_parent_inline_dir(struct inode *dir,
-							struct page **p)
-{
-	struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
-	struct page *ipage;
-	struct f2fs_dir_entry *de;
-	struct f2fs_inline_dentry *dentry_blk;
-
-	ipage = get_node_page(sbi, dir->i_ino);
-	if (IS_ERR(ipage))
-		return NULL;
-
-	dentry_blk = inline_data_addr(ipage);
-	de = &dentry_blk->dentry[1];
-	*p = ipage;
-	unlock_page(ipage);
-	return de;
-}
-
 int make_empty_inline_dir(struct inode *inode, struct inode *parent,
 							struct page *ipage)
 {
@@ -340,10 +323,8 @@ int make_empty_inline_dir(struct inode *inode, struct inode *parent,
 	set_page_dirty(ipage);
 
 	/* update i_size to MAX_INLINE_DATA */
-	if (i_size_read(inode) < MAX_INLINE_DATA) {
-		i_size_write(inode, MAX_INLINE_DATA);
-		set_inode_flag(F2FS_I(inode), FI_UPDATE_DIR);
-	}
+	if (i_size_read(inode) < MAX_INLINE_DATA)
+		f2fs_i_size_write(inode, MAX_INLINE_DATA);
 	return 0;
 }
 
@@ -392,22 +373,19 @@ static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage,
 					NR_INLINE_DENTRY * F2FS_SLOT_LEN);
 
 	kunmap_atomic(dentry_blk);
-	SetPageUptodate(page);
+	if (!PageUptodate(page))
+		SetPageUptodate(page);
 	set_page_dirty(page);
 
 	/* clear inline dir and flag after data writeback */
 	truncate_inline_inode(ipage, 0);
 
 	stat_dec_inline_dir(dir);
-	clear_inode_flag(F2FS_I(dir), FI_INLINE_DENTRY);
+	clear_inode_flag(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);
-	}
-
-	sync_inode_page(&dn);
+	f2fs_i_depth_write(dir, 1);
+	if (i_size_read(dir) < PAGE_SIZE)
+		f2fs_i_size_write(dir, PAGE_SIZE);
 out:
 	f2fs_put_page(page, 1);
 	return err;
@@ -465,7 +443,6 @@ 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),
@@ -487,16 +464,15 @@ static int f2fs_move_rehashed_dirents(struct inode *dir, struct page *ipage,
 	lock_page(ipage);
 
 	stat_dec_inline_dir(dir);
-	clear_inode_flag(fi, FI_INLINE_DENTRY);
-	update_inode(dir, ipage);
+	clear_inode_flag(dir, FI_INLINE_DENTRY);
 	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_i_depth_write(dir, 0);
+	f2fs_i_size_write(dir, MAX_INLINE_DATA);
+	set_page_dirty(ipage);
 	f2fs_put_page(ipage, 1);
 
 	kfree(backup_dentry);
@@ -560,8 +536,7 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *name,
 
 	/* we don't need to mark_inode_dirty now */
 	if (inode) {
-		F2FS_I(inode)->i_pino = dir->i_ino;
-		update_inode(inode, page);
+		f2fs_i_pino_write(inode, dir->i_ino);
 		f2fs_put_page(page, 1);
 	}
 
@@ -569,11 +544,6 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *name,
 fail:
 	if (inode)
 		up_write(&F2FS_I(inode)->i_sem);
-
-	if (is_inode_flag_set(F2FS_I(dir), FI_UPDATE_DIR)) {
-		update_inode(dir, ipage);
-		clear_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
-	}
 out:
 	f2fs_put_page(ipage, 1);
 	return err;
@@ -597,13 +567,13 @@ void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, struct page *page,
 				&inline_dentry->dentry_bitmap);
 
 	set_page_dirty(page);
+	f2fs_put_page(page, 1);
 
 	dir->i_ctime = dir->i_mtime = CURRENT_TIME;
+	f2fs_mark_inode_dirty_sync(dir);
 
 	if (inode)
-		f2fs_drop_nlink(dir, inode, page);
-
-	f2fs_put_page(page, 1);
+		f2fs_drop_nlink(dir, inode);
 }
 
 bool f2fs_empty_inline_dir(struct inode *dir)

fs/f2fs/inode.c

@@ -18,6 +18,13 @@
 
 #include <trace/events/f2fs.h>
 
+void f2fs_mark_inode_dirty_sync(struct inode *inode)
+{
+	if (f2fs_inode_dirtied(inode))
+		return;
+	mark_inode_dirty_sync(inode);
+}
+
 void f2fs_set_inode_flags(struct inode *inode)
 {
 	unsigned int flags = F2FS_I(inode)->i_flags;
@@ -35,6 +42,7 @@ void f2fs_set_inode_flags(struct inode *inode)
 		new_fl |= S_DIRSYNC;
 	inode_set_flags(inode, new_fl,
 			S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
+	f2fs_mark_inode_dirty_sync(inode);
 }
 
 static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
@@ -85,8 +93,8 @@ static void __recover_inline_status(struct inode *inode, struct page *ipage)
 		if (*start++) {
 			f2fs_wait_on_page_writeback(ipage, NODE, true);
 
-			set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
-			set_raw_inline(F2FS_I(inode), F2FS_INODE(ipage));
+			set_inode_flag(inode, FI_DATA_EXIST);
+			set_raw_inline(inode, F2FS_INODE(ipage));
 			set_page_dirty(ipage);
 			return;
 		}
@@ -141,7 +149,7 @@ static int do_read_inode(struct inode *inode)
 	if (f2fs_init_extent_tree(inode, &ri->i_ext))
 		set_page_dirty(node_page);
 
-	get_inline_info(fi, ri);
+	get_inline_info(inode, ri);
 
 	/* check data exist */
 	if (f2fs_has_inline_data(inode) && !f2fs_exist_data(inode))
@@ -151,7 +159,10 @@ static int do_read_inode(struct inode *inode)
 	__get_inode_rdev(inode, ri);
 
 	if (__written_first_block(ri))
-		set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN);
+		set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN);
+
+	if (!need_inode_block_update(sbi, inode->i_ino))
+		fi->last_disk_size = inode->i_size;
 
 	f2fs_put_page(node_page, 1);
 
@@ -227,6 +238,8 @@ int update_inode(struct inode *inode, struct page *node_page)
 {
 	struct f2fs_inode *ri;
 
+	f2fs_inode_synced(inode);
+
 	f2fs_wait_on_page_writeback(node_page, NODE, true);
 
 	ri = F2FS_INODE(node_page);
@@ -244,7 +257,7 @@ int update_inode(struct inode *inode, struct page *node_page)
 							&ri->i_ext);
 	else
 		memset(&ri->i_ext, 0, sizeof(ri->i_ext));
-	set_raw_inline(F2FS_I(inode), ri);
+	set_raw_inline(inode, ri);
 
 	ri->i_atime = cpu_to_le64(inode->i_atime.tv_sec);
 	ri->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec);
@@ -261,7 +274,6 @@ int update_inode(struct inode *inode, struct page *node_page)
 
 	__set_inode_rdev(inode, ri);
 	set_cold_node(inode, node_page);
-	clear_inode_flag(F2FS_I(inode), FI_DIRTY_INODE);
 
 	/* deleted inode */
 	if (inode->i_nlink == 0)
@@ -285,6 +297,7 @@ retry:
 		} else if (err != -ENOENT) {
 			f2fs_stop_checkpoint(sbi, false);
 		}
+		f2fs_inode_synced(inode);
 		return 0;
 	}
 	ret = update_inode(inode, node_page);
@@ -300,7 +313,7 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
 			inode->i_ino == F2FS_META_INO(sbi))
 		return 0;
 
-	if (!is_inode_flag_set(F2FS_I(inode), FI_DIRTY_INODE))
+	if (!is_inode_flag_set(inode, FI_DIRTY_INODE))
 		return 0;
 
 	/*
@@ -318,8 +331,7 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
 void f2fs_evict_inode(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct f2fs_inode_info *fi = F2FS_I(inode);
-	nid_t xnid = fi->i_xattr_nid;
+	nid_t xnid = F2FS_I(inode)->i_xattr_nid;
 	int err = 0;
 
 	/* some remained atomic pages should discarded */
@@ -341,12 +353,17 @@ void f2fs_evict_inode(struct inode *inode)
 	if (inode->i_nlink || is_bad_inode(inode))
 		goto no_delete;
 
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	if (time_to_inject(FAULT_EVICT_INODE))
+		goto no_delete;
+#endif
+
 	sb_start_intwrite(inode->i_sb);
-	set_inode_flag(fi, FI_NO_ALLOC);
+	set_inode_flag(inode, FI_NO_ALLOC);
 	i_size_write(inode, 0);
 retry:
 	if (F2FS_HAS_BLOCKS(inode))
-		err = f2fs_truncate(inode, true);
+		err = f2fs_truncate(inode);
 
 	if (!err) {
 		f2fs_lock_op(sbi);
@@ -360,6 +377,8 @@ retry:
 		goto retry;
 	}
 
+	if (err)
+		update_inode_page(inode);
 	sb_end_intwrite(inode->i_sb);
 no_delete:
 	stat_dec_inline_xattr(inode);
@@ -369,13 +388,13 @@ no_delete:
 	invalidate_mapping_pages(NODE_MAPPING(sbi), inode->i_ino, inode->i_ino);
 	if (xnid)
 		invalidate_mapping_pages(NODE_MAPPING(sbi), xnid, xnid);
-	if (is_inode_flag_set(fi, FI_APPEND_WRITE))
+	if (is_inode_flag_set(inode, FI_APPEND_WRITE))
 		add_ino_entry(sbi, inode->i_ino, APPEND_INO);
-	if (is_inode_flag_set(fi, FI_UPDATE_WRITE))
+	if (is_inode_flag_set(inode, FI_UPDATE_WRITE))
 		add_ino_entry(sbi, inode->i_ino, UPDATE_INO);
-	if (is_inode_flag_set(fi, FI_FREE_NID)) {
+	if (is_inode_flag_set(inode, FI_FREE_NID)) {
 		alloc_nid_failed(sbi, inode->i_ino);
-		clear_inode_flag(fi, FI_FREE_NID);
+		clear_inode_flag(inode, FI_FREE_NID);
 	}
 	f2fs_bug_on(sbi, err &&
 		!exist_written_data(sbi, inode->i_ino, ORPHAN_INO));
@@ -407,11 +426,11 @@ void handle_failed_inode(struct inode *inode)
 			f2fs_msg(sbi->sb, KERN_WARNING,
 				"Too many orphan inodes, run fsck to fix.");
 		} else {
-			add_orphan_inode(sbi, inode->i_ino);
+			add_orphan_inode(inode);
 		}
 		alloc_nid_done(sbi, inode->i_ino);
 	} else {
-		set_inode_flag(F2FS_I(inode), FI_FREE_NID);
+		set_inode_flag(inode, FI_FREE_NID);
 	}
 
 	f2fs_unlock_op(sbi);

fs/f2fs/namei.c

@@ -60,10 +60,14 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
 	if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode))
 		f2fs_set_encrypted_inode(inode);
 
+	set_inode_flag(inode, FI_NEW_INODE);
+
+	if (test_opt(sbi, INLINE_XATTR))
+		set_inode_flag(inode, FI_INLINE_XATTR);
 	if (test_opt(sbi, INLINE_DATA) && f2fs_may_inline_data(inode))
-		set_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
+		set_inode_flag(inode, FI_INLINE_DATA);
 	if (f2fs_may_inline_dentry(inode))
-		set_inode_flag(F2FS_I(inode), FI_INLINE_DENTRY);
+		set_inode_flag(inode, FI_INLINE_DENTRY);
 
 	f2fs_init_extent_tree(inode, NULL);
 
@@ -72,14 +76,13 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
 	stat_inc_inline_dir(inode);
 
 	trace_f2fs_new_inode(inode, 0);
-	mark_inode_dirty(inode);
 	return inode;
 
 fail:
 	trace_f2fs_new_inode(inode, err);
 	make_bad_inode(inode);
 	if (nid_free)
-		set_inode_flag(F2FS_I(inode), FI_FREE_NID);
+		set_inode_flag(inode, FI_FREE_NID);
 	iput(inode);
 	return ERR_PTR(err);
 }
@@ -177,7 +180,7 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
 	inode->i_ctime = CURRENT_TIME;
 	ihold(inode);
 
-	set_inode_flag(F2FS_I(inode), FI_INC_LINK);
+	set_inode_flag(inode, FI_INC_LINK);
 	f2fs_lock_op(sbi);
 	err = f2fs_add_link(dentry, inode);
 	if (err)
@@ -190,7 +193,7 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
 		f2fs_sync_fs(sbi->sb, 1);
 	return 0;
 out:
-	clear_inode_flag(F2FS_I(inode), FI_INC_LINK);
+	clear_inode_flag(inode, FI_INC_LINK);
 	iput(inode);
 	f2fs_unlock_op(sbi);
 	return err;
@@ -199,9 +202,13 @@ out:
 struct dentry *f2fs_get_parent(struct dentry *child)
 {
 	struct qstr dotdot = QSTR_INIT("..", 2);
-	unsigned long ino = f2fs_inode_by_name(d_inode(child), &dotdot);
-	if (!ino)
+	struct page *page;
+	unsigned long ino = f2fs_inode_by_name(d_inode(child), &dotdot, &page);
+	if (!ino) {
+		if (IS_ERR(page))
+			return ERR_CAST(page);
 		return ERR_PTR(-ENOENT);
+	}
 	return d_obtain_alias(f2fs_iget(child->d_sb, ino));
 }
 
@@ -229,6 +236,9 @@ static int __recover_dot_dentries(struct inode *dir, nid_t pino)
 	if (de) {
 		f2fs_dentry_kunmap(dir, page);
 		f2fs_put_page(page, 0);
+	} else if (IS_ERR(page)) {
+		err = PTR_ERR(page);
+		goto out;
 	} else {
 		err = __f2fs_add_link(dir, &dot, NULL, dir->i_ino, S_IFDIR);
 		if (err)
@@ -239,14 +249,14 @@ static int __recover_dot_dentries(struct inode *dir, nid_t pino)
 	if (de) {
 		f2fs_dentry_kunmap(dir, page);
 		f2fs_put_page(page, 0);
+	} else if (IS_ERR(page)) {
+		err = PTR_ERR(page);
 	} else {
 		err = __f2fs_add_link(dir, &dotdot, NULL, pino, S_IFDIR);
 	}
 out:
-	if (!err) {
-		clear_inode_flag(F2FS_I(dir), FI_INLINE_DOTS);
-		mark_inode_dirty(dir);
-	}
+	if (!err)
+		clear_inode_flag(dir, FI_INLINE_DOTS);
 
 	f2fs_unlock_op(sbi);
 	return err;
@@ -281,8 +291,11 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
 		return ERR_PTR(-ENAMETOOLONG);
 
 	de = f2fs_find_entry(dir, &dentry->d_name, &page);
-	if (!de)
+	if (!de) {
+		if (IS_ERR(page))
+			return (struct dentry *)page;
 		return d_splice_alias(inode, dentry);
+	}
 
 	ino = le32_to_cpu(de->ino);
 	f2fs_dentry_kunmap(dir, page);
@@ -329,8 +342,11 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
 	trace_f2fs_unlink_enter(dir, dentry);
 
 	de = f2fs_find_entry(dir, &dentry->d_name, &page);
-	if (!de)
+	if (!de) {
+		if (IS_ERR(page))
+			err = PTR_ERR(page);
 		goto fail;
+	}
 
 	f2fs_balance_fs(sbi, true);
 
@@ -345,9 +361,6 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
 	f2fs_delete_entry(de, page, dir, inode);
 	f2fs_unlock_op(sbi);
 
-	/* In order to evict this inode, we set it dirty */
-	mark_inode_dirty(inode);
-
 	if (IS_DIRSYNC(dir))
 		f2fs_sync_fs(sbi->sb, 1);
 fail:
@@ -492,7 +505,7 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 
 	f2fs_balance_fs(sbi, true);
 
-	set_inode_flag(F2FS_I(inode), FI_INC_LINK);
+	set_inode_flag(inode, FI_INC_LINK);
 	f2fs_lock_op(sbi);
 	err = f2fs_add_link(dentry, inode);
 	if (err)
@@ -509,7 +522,7 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	return 0;
 
 out_fail:
-	clear_inode_flag(F2FS_I(inode), FI_INC_LINK);
+	clear_inode_flag(inode, FI_INC_LINK);
 	handle_failed_inode(inode);
 	return err;
 }
@@ -592,17 +605,17 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry,
 	 * add this non-linked tmpfile to orphan list, in this way we could
 	 * remove all unused data of tmpfile after abnormal power-off.
 	 */
-	add_orphan_inode(sbi, inode->i_ino);
-	f2fs_unlock_op(sbi);
-
+	add_orphan_inode(inode);
 	alloc_nid_done(sbi, inode->i_ino);
 
 	if (whiteout) {
-		inode_dec_link_count(inode);
+		f2fs_i_links_write(inode, false);
 		*whiteout = inode;
 	} else {
 		d_tmpfile(dentry, inode);
 	}
+	/* link_count was changed by d_tmpfile as well. */
+	f2fs_unlock_op(sbi);
 	unlock_new_inode(inode);
 	return 0;
 
@@ -652,14 +665,19 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	}
 
 	old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
-	if (!old_entry)
+	if (!old_entry) {
+		if (IS_ERR(old_page))
+			err = PTR_ERR(old_page);
 		goto out;
+	}
 
 	if (S_ISDIR(old_inode->i_mode)) {
-		err = -EIO;
 		old_dir_entry = f2fs_parent_dir(old_inode, &old_dir_page);
-		if (!old_dir_entry)
+		if (!old_dir_entry) {
+			if (IS_ERR(old_dir_page))
+				err = PTR_ERR(old_dir_page);
 			goto out_old;
+		}
 	}
 
 	if (flags & RENAME_WHITEOUT) {
@@ -677,8 +695,11 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		err = -ENOENT;
 		new_entry = f2fs_find_entry(new_dir, &new_dentry->d_name,
 						&new_page);
-		if (!new_entry)
+		if (!new_entry) {
+			if (IS_ERR(new_page))
+				err = PTR_ERR(new_page);
 			goto out_whiteout;
+		}
 
 		f2fs_balance_fs(sbi, true);
 
@@ -700,19 +721,14 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		new_inode->i_ctime = CURRENT_TIME;
 		down_write(&F2FS_I(new_inode)->i_sem);
 		if (old_dir_entry)
-			drop_nlink(new_inode);
-		drop_nlink(new_inode);
+			f2fs_i_links_write(new_inode, false);
+		f2fs_i_links_write(new_inode, false);
 		up_write(&F2FS_I(new_inode)->i_sem);
 
-		mark_inode_dirty(new_inode);
-
 		if (!new_inode->i_nlink)
-			add_orphan_inode(sbi, new_inode->i_ino);
+			add_orphan_inode(new_inode);
 		else
 			release_orphan_inode(sbi);
-
-		update_inode_page(old_inode);
-		update_inode_page(new_inode);
 	} else {
 		f2fs_balance_fs(sbi, true);
 
@@ -724,10 +740,8 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 			goto out_whiteout;
 		}
 
-		if (old_dir_entry) {
-			inc_nlink(new_dir);
-			update_inode_page(new_dir);
-		}
+		if (old_dir_entry)
+			f2fs_i_links_write(new_dir, true);
 
 		/*
 		 * old entry and new entry can locate in the same inline
@@ -743,7 +757,9 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 			old_entry = f2fs_find_entry(old_dir,
 						&old_dentry->d_name, &old_page);
 			if (!old_entry) {
-				err = -EIO;
+				err = -ENOENT;
+				if (IS_ERR(old_page))
+					err = PTR_ERR(old_page);
 				f2fs_unlock_op(sbi);
 				goto out_whiteout;
 			}
@@ -757,13 +773,13 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	up_write(&F2FS_I(old_inode)->i_sem);
 
 	old_inode->i_ctime = CURRENT_TIME;
-	mark_inode_dirty(old_inode);
+	f2fs_mark_inode_dirty_sync(old_inode);
 
 	f2fs_delete_entry(old_entry, old_page, old_dir, NULL);
 
 	if (whiteout) {
 		whiteout->i_state |= I_LINKABLE;
-		set_inode_flag(F2FS_I(whiteout), FI_INC_LINK);
+		set_inode_flag(whiteout, FI_INC_LINK);
 		err = f2fs_add_link(old_dentry, whiteout);
 		if (err)
 			goto put_out_dir;
@@ -775,14 +791,11 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		if (old_dir != new_dir && !whiteout) {
 			f2fs_set_link(old_inode, old_dir_entry,
 						old_dir_page, new_dir);
-			update_inode_page(old_inode);
 		} else {
 			f2fs_dentry_kunmap(old_inode, old_dir_page);
 			f2fs_put_page(old_dir_page, 0);
 		}
-		drop_nlink(old_dir);
-		mark_inode_dirty(old_dir);
-		update_inode_page(old_dir);
+		f2fs_i_links_write(old_dir, false);
 	}
 
 	f2fs_unlock_op(sbi);
@@ -832,29 +845,39 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 		return -EPERM;
 
 	old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
-	if (!old_entry)
+	if (!old_entry) {
+		if (IS_ERR(old_page))
+			err = PTR_ERR(old_page);
 		goto out;
+	}
 
 	new_entry = f2fs_find_entry(new_dir, &new_dentry->d_name, &new_page);
-	if (!new_entry)
+	if (!new_entry) {
+		if (IS_ERR(new_page))
+			err = PTR_ERR(new_page);
 		goto out_old;
+	}
 
 	/* prepare for updating ".." directory entry info later */
 	if (old_dir != new_dir) {
 		if (S_ISDIR(old_inode->i_mode)) {
-			err = -EIO;
 			old_dir_entry = f2fs_parent_dir(old_inode,
 							&old_dir_page);
-			if (!old_dir_entry)
+			if (!old_dir_entry) {
+				if (IS_ERR(old_dir_page))
+					err = PTR_ERR(old_dir_page);
 				goto out_new;
+			}
 		}
 
 		if (S_ISDIR(new_inode->i_mode)) {
-			err = -EIO;
 			new_dir_entry = f2fs_parent_dir(new_inode,
 							&new_dir_page);
-			if (!new_dir_entry)
+			if (!new_dir_entry) {
+				if (IS_ERR(new_dir_page))
+					err = PTR_ERR(new_dir_page);
 				goto out_old_dir;
+			}
 		}
 	}
 
@@ -904,19 +927,13 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 	file_lost_pino(old_inode);
 	up_write(&F2FS_I(old_inode)->i_sem);
 
-	update_inode_page(old_inode);
-
 	old_dir->i_ctime = CURRENT_TIME;
 	if (old_nlink) {
 		down_write(&F2FS_I(old_dir)->i_sem);
-		if (old_nlink < 0)
-			drop_nlink(old_dir);
-		else
-			inc_nlink(old_dir);
+		f2fs_i_links_write(old_dir, old_nlink > 0);
 		up_write(&F2FS_I(old_dir)->i_sem);
 	}
-	mark_inode_dirty(old_dir);
-	update_inode_page(old_dir);
+	f2fs_mark_inode_dirty_sync(old_dir);
 
 	/* update directory entry info of new dir inode */
 	f2fs_set_link(new_dir, new_entry, new_page, old_inode);
@@ -925,19 +942,13 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 	file_lost_pino(new_inode);
 	up_write(&F2FS_I(new_inode)->i_sem);
 
-	update_inode_page(new_inode);
-
 	new_dir->i_ctime = CURRENT_TIME;
 	if (new_nlink) {
 		down_write(&F2FS_I(new_dir)->i_sem);
-		if (new_nlink < 0)
-			drop_nlink(new_dir);
-		else
-			inc_nlink(new_dir);
+		f2fs_i_links_write(new_dir, new_nlink > 0);
 		up_write(&F2FS_I(new_dir)->i_sem);
 	}
-	mark_inode_dirty(new_dir);
-	update_inode_page(new_dir);
+	f2fs_mark_inode_dirty_sync(new_dir);
 
 	f2fs_unlock_op(sbi);
 

fs/f2fs/node.c

@@ -52,6 +52,10 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type)
 		mem_size = (nm_i->nat_cnt * sizeof(struct nat_entry)) >>
 							PAGE_SHIFT;
 		res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2);
+		if (excess_cached_nats(sbi))
+			res = false;
+		if (nm_i->nat_cnt > DEF_NAT_CACHE_THRESHOLD)
+			res = false;
 	} else if (type == DIRTY_DENTS) {
 		if (sbi->sb->s_bdi->wb.dirty_exceeded)
 			return false;
@@ -202,14 +206,14 @@ int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid)
 	struct nat_entry *e;
 	bool need = false;
 
-	down_read(&nm_i->nat_tree_lock);
+	percpu_down_read(&nm_i->nat_tree_lock);
 	e = __lookup_nat_cache(nm_i, nid);
 	if (e) {
 		if (!get_nat_flag(e, IS_CHECKPOINTED) &&
 				!get_nat_flag(e, HAS_FSYNCED_INODE))
 			need = true;
 	}
-	up_read(&nm_i->nat_tree_lock);
+	percpu_up_read(&nm_i->nat_tree_lock);
 	return need;
 }
 
@@ -219,11 +223,11 @@ bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid)
 	struct nat_entry *e;
 	bool is_cp = true;
 
-	down_read(&nm_i->nat_tree_lock);
+	percpu_down_read(&nm_i->nat_tree_lock);
 	e = __lookup_nat_cache(nm_i, nid);
 	if (e && !get_nat_flag(e, IS_CHECKPOINTED))
 		is_cp = false;
-	up_read(&nm_i->nat_tree_lock);
+	percpu_up_read(&nm_i->nat_tree_lock);
 	return is_cp;
 }
 
@@ -233,13 +237,13 @@ bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino)
 	struct nat_entry *e;
 	bool need_update = true;
 
-	down_read(&nm_i->nat_tree_lock);
+	percpu_down_read(&nm_i->nat_tree_lock);
 	e = __lookup_nat_cache(nm_i, ino);
 	if (e && get_nat_flag(e, HAS_LAST_FSYNC) &&
 			(get_nat_flag(e, IS_CHECKPOINTED) ||
 			 get_nat_flag(e, HAS_FSYNCED_INODE)))
 		need_update = false;
-	up_read(&nm_i->nat_tree_lock);
+	percpu_up_read(&nm_i->nat_tree_lock);
 	return need_update;
 }
 
@@ -280,7 +284,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct nat_entry *e;
 
-	down_write(&nm_i->nat_tree_lock);
+	percpu_down_write(&nm_i->nat_tree_lock);
 	e = __lookup_nat_cache(nm_i, ni->nid);
 	if (!e) {
 		e = grab_nat_entry(nm_i, ni->nid);
@@ -330,7 +334,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
 			set_nat_flag(e, HAS_FSYNCED_INODE, true);
 		set_nat_flag(e, HAS_LAST_FSYNC, fsync_done);
 	}
-	up_write(&nm_i->nat_tree_lock);
+	percpu_up_write(&nm_i->nat_tree_lock);
 }
 
 int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink)
@@ -338,8 +342,7 @@ int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink)
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	int nr = nr_shrink;
 
-	if (!down_write_trylock(&nm_i->nat_tree_lock))
-		return 0;
+	percpu_down_write(&nm_i->nat_tree_lock);
 
 	while (nr_shrink && !list_empty(&nm_i->nat_entries)) {
 		struct nat_entry *ne;
@@ -348,7 +351,7 @@ int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink)
 		__del_from_nat_cache(nm_i, ne);
 		nr_shrink--;
 	}
-	up_write(&nm_i->nat_tree_lock);
+	percpu_up_write(&nm_i->nat_tree_lock);
 	return nr - nr_shrink;
 }
 
@@ -370,13 +373,13 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
 	ni->nid = nid;
 
 	/* Check nat cache */
-	down_read(&nm_i->nat_tree_lock);
+	percpu_down_read(&nm_i->nat_tree_lock);
 	e = __lookup_nat_cache(nm_i, nid);
 	if (e) {
 		ni->ino = nat_get_ino(e);
 		ni->blk_addr = nat_get_blkaddr(e);
 		ni->version = nat_get_version(e);
-		up_read(&nm_i->nat_tree_lock);
+		percpu_up_read(&nm_i->nat_tree_lock);
 		return;
 	}
 
@@ -400,11 +403,11 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
 	node_info_from_raw_nat(ni, &ne);
 	f2fs_put_page(page, 1);
 cache:
-	up_read(&nm_i->nat_tree_lock);
+	percpu_up_read(&nm_i->nat_tree_lock);
 	/* cache nat entry */
-	down_write(&nm_i->nat_tree_lock);
+	percpu_down_write(&nm_i->nat_tree_lock);
 	cache_nat_entry(sbi, nid, &ne);
-	up_write(&nm_i->nat_tree_lock);
+	percpu_up_write(&nm_i->nat_tree_lock);
 }
 
 /*
@@ -646,6 +649,7 @@ release_out:
 	if (err == -ENOENT) {
 		dn->cur_level = i;
 		dn->max_level = level;
+		dn->ofs_in_node = offset[level];
 	}
 	return err;
 }
@@ -670,8 +674,7 @@ static void truncate_node(struct dnode_of_data *dn)
 	if (dn->nid == dn->inode->i_ino) {
 		remove_orphan_inode(sbi, dn->nid);
 		dec_valid_inode_count(sbi);
-	} else {
-		sync_inode_page(dn);
+		f2fs_inode_synced(dn->inode);
 	}
 invalidate:
 	clear_node_page_dirty(dn->node_page);
@@ -953,7 +956,7 @@ int truncate_xattr_node(struct inode *inode, struct page *page)
 	if (IS_ERR(npage))
 		return PTR_ERR(npage);
 
-	F2FS_I(inode)->i_xattr_nid = 0;
+	f2fs_i_xnid_write(inode, 0);
 
 	/* need to do checkpoint during fsync */
 	F2FS_I(inode)->xattr_ver = cur_cp_version(F2FS_CKPT(sbi));
@@ -1019,7 +1022,7 @@ struct page *new_node_page(struct dnode_of_data *dn,
 	struct page *page;
 	int err;
 
-	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 ERR_PTR(-EPERM);
 
 	page = f2fs_grab_cache_page(NODE_MAPPING(sbi), dn->nid, false);
@@ -1042,21 +1045,16 @@ struct page *new_node_page(struct dnode_of_data *dn,
 	f2fs_wait_on_page_writeback(page, NODE, true);
 	fill_node_footer(page, dn->nid, dn->inode->i_ino, ofs, true);
 	set_cold_node(dn->inode, page);
-	SetPageUptodate(page);
+	if (!PageUptodate(page))
+		SetPageUptodate(page);
 	if (set_page_dirty(page))
 		dn->node_changed = true;
 
 	if (f2fs_has_xattr_block(ofs))
-		F2FS_I(dn->inode)->i_xattr_nid = dn->nid;
+		f2fs_i_xnid_write(dn->inode, dn->nid);
 
-	dn->node_page = page;
-	if (ipage)
-		update_inode(dn->inode, ipage);
-	else
-		sync_inode_page(dn);
 	if (ofs == 0)
 		inc_valid_inode_count(sbi);
-
 	return page;
 
 fail:
@@ -1083,6 +1081,9 @@ static int read_node_page(struct page *page, int op_flags)
 		.encrypted_page = NULL,
 	};
 
+	if (PageUptodate(page))
+		return LOCKED_PAGE;
+
 	get_node_info(sbi, page->index, &ni);
 
 	if (unlikely(ni.blk_addr == NULL_ADDR)) {
@@ -1090,9 +1091,6 @@ static int read_node_page(struct page *page, int op_flags)
 		return -ENOENT;
 	}
 
-	if (PageUptodate(page))
-		return LOCKED_PAGE;
-
 	fio.new_blkaddr = fio.old_blkaddr = ni.blk_addr;
 	return f2fs_submit_page_bio(&fio);
 }
@@ -1150,16 +1148,21 @@ repeat:
 
 	lock_page(page);
 
-	if (unlikely(!PageUptodate(page))) {
-		f2fs_put_page(page, 1);
-		return ERR_PTR(-EIO);
-	}
 	if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
 		f2fs_put_page(page, 1);
 		goto repeat;
 	}
+
+	if (unlikely(!PageUptodate(page)))
+		goto out_err;
 page_hit:
-	f2fs_bug_on(sbi, nid != nid_of_node(page));
+	if(unlikely(nid != nid_of_node(page))) {
+		f2fs_bug_on(sbi, 1);
+		ClearPageUptodate(page);
+out_err:
+		f2fs_put_page(page, 1);
+		return ERR_PTR(-EIO);
+	}
 	return page;
 }
 
@@ -1176,24 +1179,6 @@ struct page *get_node_page_ra(struct page *parent, int start)
 	return __get_node_page(sbi, nid, parent, start);
 }
 
-void sync_inode_page(struct dnode_of_data *dn)
-{
-	int ret = 0;
-
-	if (IS_INODE(dn->node_page) || dn->inode_page == dn->node_page) {
-		ret = update_inode(dn->inode, dn->node_page);
-	} else if (dn->inode_page) {
-		if (!dn->inode_page_locked)
-			lock_page(dn->inode_page);
-		ret = update_inode(dn->inode, dn->inode_page);
-		if (!dn->inode_page_locked)
-			unlock_page(dn->inode_page);
-	} else {
-		ret = update_inode_page(dn->inode);
-	}
-	dn->node_changed = ret ? true: false;
-}
-
 static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino)
 {
 	struct inode *inode;
@@ -1319,7 +1304,7 @@ continue_unlock:
 	return last_page;
 }
 
-int fsync_node_pages(struct f2fs_sb_info *sbi, nid_t ino,
+int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
 			struct writeback_control *wbc, bool atomic)
 {
 	pgoff_t index, end;
@@ -1327,6 +1312,7 @@ int fsync_node_pages(struct f2fs_sb_info *sbi, nid_t ino,
 	int ret = 0;
 	struct page *last_page = NULL;
 	bool marked = false;
+	nid_t ino = inode->i_ino;
 
 	if (atomic) {
 		last_page = last_fsync_dnode(sbi, ino);
@@ -1380,9 +1366,13 @@ continue_unlock:
 
 			if (!atomic || page == last_page) {
 				set_fsync_mark(page, 1);
-				if (IS_INODE(page))
+				if (IS_INODE(page)) {
+					if (is_inode_flag_set(inode,
+								FI_DIRTY_INODE))
+						update_inode(inode, page);
 					set_dentry_mark(page,
 						need_dentry_mark(sbi, ino));
+				}
 				/*  may be written by other thread */
 				if (!PageDirty(page))
 					set_page_dirty(page);
@@ -1630,6 +1620,7 @@ static int f2fs_write_node_pages(struct address_space *mapping,
 			    struct writeback_control *wbc)
 {
 	struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
+	struct blk_plug plug;
 	long diff;
 
 	/* balancing f2fs's metadata in background */
@@ -1643,7 +1634,9 @@ static int f2fs_write_node_pages(struct address_space *mapping,
 
 	diff = nr_pages_to_write(sbi, NODE, wbc);
 	wbc->sync_mode = WB_SYNC_NONE;
+	blk_start_plug(&plug);
 	sync_node_pages(sbi, wbc);
+	blk_finish_plug(&plug);
 	wbc->nr_to_write = max((long)0, wbc->nr_to_write - diff);
 	return 0;
 
@@ -1657,9 +1650,10 @@ static int f2fs_set_node_page_dirty(struct page *page)
 {
 	trace_f2fs_set_page_dirty(page, NODE);
 
-	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_NODES);
 		SetPagePrivate(page);
 		f2fs_trace_pid(page);
@@ -1778,7 +1772,7 @@ static void scan_nat_page(struct f2fs_sb_info *sbi,
 	}
 }
 
-static void build_free_nids(struct f2fs_sb_info *sbi)
+void build_free_nids(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
@@ -1787,14 +1781,14 @@ static void build_free_nids(struct f2fs_sb_info *sbi)
 	nid_t nid = nm_i->next_scan_nid;
 
 	/* Enough entries */
-	if (nm_i->fcnt > NAT_ENTRY_PER_BLOCK)
+	if (nm_i->fcnt >= NAT_ENTRY_PER_BLOCK)
 		return;
 
 	/* readahead nat pages to be scanned */
 	ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES,
 							META_NAT, true);
 
-	down_read(&nm_i->nat_tree_lock);
+	percpu_down_read(&nm_i->nat_tree_lock);
 
 	while (1) {
 		struct page *page = get_current_nat_page(sbi, nid);
@@ -1826,7 +1820,7 @@ static void build_free_nids(struct f2fs_sb_info *sbi)
 			remove_free_nid(nm_i, nid);
 	}
 	up_read(&curseg->journal_rwsem);
-	up_read(&nm_i->nat_tree_lock);
+	percpu_up_read(&nm_i->nat_tree_lock);
 
 	ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid),
 					nm_i->ra_nid_pages, META_NAT, false);
@@ -1925,12 +1919,15 @@ int try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink)
 	struct free_nid *i, *next;
 	int nr = nr_shrink;
 
+	if (nm_i->fcnt <= MAX_FREE_NIDS)
+		return 0;
+
 	if (!mutex_trylock(&nm_i->build_lock))
 		return 0;
 
 	spin_lock(&nm_i->free_nid_list_lock);
 	list_for_each_entry_safe(i, next, &nm_i->free_nid_list, list) {
-		if (nr_shrink <= 0 || nm_i->fcnt <= NAT_ENTRY_PER_BLOCK)
+		if (nr_shrink <= 0 || nm_i->fcnt <= MAX_FREE_NIDS)
 			break;
 		if (i->state == NID_ALLOC)
 			continue;
@@ -1957,7 +1954,7 @@ void recover_inline_xattr(struct inode *inode, struct page *page)
 
 	ri = F2FS_INODE(page);
 	if (!(ri->i_inline & F2FS_INLINE_XATTR)) {
-		clear_inode_flag(F2FS_I(inode), FI_INLINE_XATTR);
+		clear_inode_flag(inode, FI_INLINE_XATTR);
 		goto update_inode;
 	}
 
@@ -1999,13 +1996,11 @@ recover_xnid:
 	get_node_info(sbi, new_xnid, &ni);
 	ni.ino = inode->i_ino;
 	set_node_addr(sbi, &ni, NEW_ADDR, false);
-	F2FS_I(inode)->i_xattr_nid = new_xnid;
+	f2fs_i_xnid_write(inode, new_xnid);
 
 	/* 3: update xattr blkaddr */
 	refresh_sit_entry(sbi, NEW_ADDR, blkaddr);
 	set_node_addr(sbi, &ni, blkaddr, false);
-
-	update_inode_page(inode);
 }
 
 int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
@@ -2027,7 +2022,8 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
 	/* Should not use this inode from free nid list */
 	remove_free_nid(NM_I(sbi), ino);
 
-	SetPageUptodate(ipage);
+	if (!PageUptodate(ipage))
+		SetPageUptodate(ipage);
 	fill_node_footer(ipage, ino, ino, 0, true);
 
 	src = F2FS_INODE(page);
@@ -2213,7 +2209,7 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
 	if (!nm_i->dirty_nat_cnt)
 		return;
 
-	down_write(&nm_i->nat_tree_lock);
+	percpu_down_write(&nm_i->nat_tree_lock);
 
 	/*
 	 * if there are no enough space in journal to store dirty nat
@@ -2236,7 +2232,7 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
 	list_for_each_entry_safe(set, tmp, &sets, set_list)
 		__flush_nat_entry_set(sbi, set);
 
-	up_write(&nm_i->nat_tree_lock);
+	percpu_up_write(&nm_i->nat_tree_lock);
 
 	f2fs_bug_on(sbi, nm_i->dirty_nat_cnt);
 }
@@ -2272,7 +2268,8 @@ static int init_node_manager(struct f2fs_sb_info *sbi)
 
 	mutex_init(&nm_i->build_lock);
 	spin_lock_init(&nm_i->free_nid_list_lock);
-	init_rwsem(&nm_i->nat_tree_lock);
+	if (percpu_init_rwsem(&nm_i->nat_tree_lock))
+		return -ENOMEM;
 
 	nm_i->next_scan_nid = le32_to_cpu(sbi->ckpt->next_free_nid);
 	nm_i->bitmap_size = __bitmap_size(sbi, NAT_BITMAP);
@@ -2329,7 +2326,7 @@ void destroy_node_manager(struct f2fs_sb_info *sbi)
 	spin_unlock(&nm_i->free_nid_list_lock);
 
 	/* destroy nat cache */
-	down_write(&nm_i->nat_tree_lock);
+	percpu_down_write(&nm_i->nat_tree_lock);
 	while ((found = __gang_lookup_nat_cache(nm_i,
 					nid, NATVEC_SIZE, natvec))) {
 		unsigned idx;
@@ -2354,8 +2351,9 @@ void destroy_node_manager(struct f2fs_sb_info *sbi)
 			kmem_cache_free(nat_entry_set_slab, setvec[idx]);
 		}
 	}
-	up_write(&nm_i->nat_tree_lock);
+	percpu_up_write(&nm_i->nat_tree_lock);
 
+	percpu_free_rwsem(&nm_i->nat_tree_lock);
 	kfree(nm_i->nat_bitmap);
 	sbi->nm_info = NULL;
 	kfree(nm_i);

fs/f2fs/node.h

@@ -15,18 +15,21 @@
 #define	NAT_BLOCK_OFFSET(start_nid) (start_nid / NAT_ENTRY_PER_BLOCK)
 
 /* # of pages to perform synchronous readahead before building free nids */
-#define FREE_NID_PAGES 4
+#define FREE_NID_PAGES	8
+#define MAX_FREE_NIDS	(NAT_ENTRY_PER_BLOCK * FREE_NID_PAGES)
 
-#define DEF_RA_NID_PAGES	4	/* # of nid pages to be readaheaded */
+#define DEF_RA_NID_PAGES	0	/* # of nid pages to be readaheaded */
 
 /* maximum readahead size for node during getting data blocks */
 #define MAX_RA_NODE		128
 
 /* control the memory footprint threshold (10MB per 1GB ram) */
-#define DEF_RAM_THRESHOLD	10
+#define DEF_RAM_THRESHOLD	1
 
 /* control dirty nats ratio threshold (default: 10% over max nid count) */
 #define DEF_DIRTY_NAT_RATIO_THRESHOLD		10
+/* control total # of nats */
+#define DEF_NAT_CACHE_THRESHOLD			100000
 
 /* vector size for gang look-up from nat cache that consists of radix tree */
 #define NATVEC_SIZE	64
@@ -126,6 +129,11 @@ static inline bool excess_dirty_nats(struct f2fs_sb_info *sbi)
 					NM_I(sbi)->dirty_nats_ratio / 100;
 }
 
+static inline bool excess_cached_nats(struct f2fs_sb_info *sbi)
+{
+	return NM_I(sbi)->nat_cnt >= DEF_NAT_CACHE_THRESHOLD;
+}
+
 enum mem_type {
 	FREE_NIDS,	/* indicates the free nid list */
 	NAT_ENTRIES,	/* indicates the cached nat entry */

fs/f2fs/recovery.c

@@ -153,9 +153,12 @@ retry:
 		f2fs_delete_entry(de, page, dir, einode);
 		iput(einode);
 		goto retry;
+	} else if (IS_ERR(page)) {
+		err = PTR_ERR(page);
+	} else {
+		err = __f2fs_add_link(dir, &name, inode,
+					inode->i_ino, inode->i_mode);
 	}
-	err = __f2fs_add_link(dir, &name, inode, inode->i_ino, inode->i_mode);
-
 	goto out;
 
 out_unmap_put:
@@ -175,7 +178,7 @@ static void recover_inode(struct inode *inode, struct page *page)
 	char *name;
 
 	inode->i_mode = le16_to_cpu(raw->i_mode);
-	i_size_write(inode, le64_to_cpu(raw->i_size));
+	f2fs_i_size_write(inode, le64_to_cpu(raw->i_size));
 	inode->i_atime.tv_sec = le64_to_cpu(raw->i_mtime);
 	inode->i_ctime.tv_sec = le64_to_cpu(raw->i_ctime);
 	inode->i_mtime.tv_sec = le64_to_cpu(raw->i_mtime);
@@ -455,6 +458,9 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 			continue;
 		}
 
+		if ((start + 1) << PAGE_SHIFT > i_size_read(inode))
+			f2fs_i_size_write(inode, (start + 1) << PAGE_SHIFT);
+
 		/*
 		 * dest is reserved block, invalidate src block
 		 * and then reserve one new block in dnode page.
@@ -476,6 +482,8 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 #endif
 				/* We should not get -ENOSPC */
 				f2fs_bug_on(sbi, err);
+				if (err)
+					goto err;
 			}
 
 			/* Check the previous node page having this index */
@@ -490,9 +498,6 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 		}
 	}
 
-	if (IS_INODE(dn.node_page))
-		sync_inode_page(&dn);
-
 	copy_node_footer(dn.node_page, page);
 	fill_node_footer(dn.node_page, dn.nid, ni.ino,
 					ofs_of_node(page), false);
@@ -624,8 +629,12 @@ out:
 	if (err) {
 		bool invalidate = false;
 
-		if (discard_next_dnode(sbi, blkaddr))
+		if (test_opt(sbi, LFS)) {
+			update_meta_page(sbi, NULL, blkaddr);
+			invalidate = true;
+		} else if (discard_next_dnode(sbi, blkaddr)) {
 			invalidate = true;
+		}
 
 		/* Flush all the NAT/SIT pages */
 		while (get_pages(sbi, F2FS_DIRTY_META))

fs/f2fs/segment.c

@@ -241,7 +241,7 @@ void drop_inmem_pages(struct inode *inode)
 {
 	struct f2fs_inode_info *fi = F2FS_I(inode);
 
-	clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
+	clear_inode_flag(inode, FI_ATOMIC_FILE);
 
 	mutex_lock(&fi->inmem_lock);
 	__revoke_inmem_pages(inode, &fi->inmem_pages, true, false);
@@ -346,6 +346,11 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
 {
 	if (!need)
 		return;
+
+	/* balance_fs_bg is able to be pending */
+	if (excess_cached_nats(sbi))
+		f2fs_balance_fs_bg(sbi);
+
 	/*
 	 * We should do GC or end up with checkpoint, if there are so many dirty
 	 * dir/node pages without enough free segments.
@@ -367,7 +372,9 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
 		try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK);
 
 	if (!available_free_memory(sbi, FREE_NIDS))
-		try_to_free_nids(sbi, NAT_ENTRY_PER_BLOCK * FREE_NID_PAGES);
+		try_to_free_nids(sbi, MAX_FREE_NIDS);
+	else
+		build_free_nids(sbi);
 
 	/* checkpoint is the only way to shrink partial cached entries */
 	if (!available_free_memory(sbi, NAT_ENTRIES) ||
@@ -435,25 +442,29 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi)
 	if (test_opt(sbi, NOBARRIER))
 		return 0;
 
-	if (!test_opt(sbi, FLUSH_MERGE)) {
+	if (!test_opt(sbi, FLUSH_MERGE) || !atomic_read(&fcc->submit_flush)) {
 		struct bio *bio = f2fs_bio_alloc(0);
 		int ret;
 
+		atomic_inc(&fcc->submit_flush);
 		bio->bi_bdev = sbi->sb->s_bdev;
 		bio_set_op_attrs(bio, REQ_OP_WRITE, WRITE_FLUSH);
 		ret = submit_bio_wait(bio);
+		atomic_dec(&fcc->submit_flush);
 		bio_put(bio);
 		return ret;
 	}
 
 	init_completion(&cmd.wait);
 
+	atomic_inc(&fcc->submit_flush);
 	llist_add(&cmd.llnode, &fcc->issue_list);
 
 	if (!fcc->dispatch_list)
 		wake_up(&fcc->flush_wait_queue);
 
 	wait_for_completion(&cmd.wait);
+	atomic_dec(&fcc->submit_flush);
 
 	return cmd.ret;
 }
@@ -467,6 +478,7 @@ int create_flush_cmd_control(struct f2fs_sb_info *sbi)
 	fcc = kzalloc(sizeof(struct flush_cmd_control), GFP_KERNEL);
 	if (!fcc)
 		return -ENOMEM;
+	atomic_set(&fcc->submit_flush, 0);
 	init_waitqueue_head(&fcc->flush_wait_queue);
 	init_llist_head(&fcc->issue_list);
 	SM_I(sbi)->cmd_control_info = fcc;
@@ -668,6 +680,10 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 			break;
 
 		end = __find_rev_next_zero_bit(dmap, max_blocks, start + 1);
+		if (force && start && end != max_blocks
+					&& (end - start) < cpc->trim_minlen)
+			continue;
+
 		__add_discard_entry(sbi, cpc, se, start, end);
 	}
 }
@@ -705,6 +721,8 @@ void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
 	unsigned long *prefree_map = dirty_i->dirty_segmap[PRE];
 	unsigned int start = 0, end = -1;
+	unsigned int secno, start_segno;
+	bool force = (cpc->reason == CP_DISCARD);
 
 	mutex_lock(&dirty_i->seglist_lock);
 
@@ -721,17 +739,31 @@ void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 		dirty_i->nr_dirty[PRE] -= end - start;
 
-		if (!test_opt(sbi, DISCARD))
+		if (force || !test_opt(sbi, DISCARD))
 			continue;
 
-		f2fs_issue_discard(sbi, START_BLOCK(sbi, start),
+		if (!test_opt(sbi, LFS) || sbi->segs_per_sec == 1) {
+			f2fs_issue_discard(sbi, START_BLOCK(sbi, start),
 				(end - start) << sbi->log_blocks_per_seg);
+			continue;
+		}
+next:
+		secno = GET_SECNO(sbi, start);
+		start_segno = secno * sbi->segs_per_sec;
+		if (!IS_CURSEC(sbi, secno) &&
+			!get_valid_blocks(sbi, start, sbi->segs_per_sec))
+			f2fs_issue_discard(sbi, START_BLOCK(sbi, start_segno),
+				sbi->segs_per_sec << sbi->log_blocks_per_seg);
+
+		start = start_segno + sbi->segs_per_sec;
+		if (start < end)
+			goto next;
 	}
 	mutex_unlock(&dirty_i->seglist_lock);
 
 	/* send small discards */
 	list_for_each_entry_safe(entry, this, head, list) {
-		if (cpc->reason == CP_DISCARD && entry->len < cpc->trim_minlen)
+		if (force && entry->len < cpc->trim_minlen)
 			goto skip;
 		f2fs_issue_discard(sbi, entry->blkaddr, entry->len);
 		cpc->trimmed += entry->len;
@@ -1219,6 +1251,9 @@ void allocate_new_segments(struct f2fs_sb_info *sbi)
 {
 	int i;
 
+	if (test_opt(sbi, LFS))
+		return;
+
 	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++)
 		__allocate_new_segments(sbi, i);
 }
@@ -1392,11 +1427,17 @@ static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio)
 {
 	int type = __get_segment_type(fio->page, fio->type);
 
+	if (fio->type == NODE || fio->type == DATA)
+		mutex_lock(&fio->sbi->wio_mutex[fio->type]);
+
 	allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr,
 					&fio->new_blkaddr, sum, type);
 
 	/* writeout dirty page into bdev */
 	f2fs_submit_page_mbio(fio);
+
+	if (fio->type == NODE || fio->type == DATA)
+		mutex_unlock(&fio->sbi->wio_mutex[fio->type]);
 }
 
 void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
@@ -2377,7 +2418,11 @@ int build_segment_manager(struct f2fs_sb_info *sbi)
 	sm_info->ssa_blkaddr = le32_to_cpu(raw_super->ssa_blkaddr);
 	sm_info->rec_prefree_segments = sm_info->main_segments *
 					DEF_RECLAIM_PREFREE_SEGMENTS / 100;
-	sm_info->ipu_policy = 1 << F2FS_IPU_FSYNC;
+	if (sm_info->rec_prefree_segments > DEF_MAX_RECLAIM_PREFREE_SEGMENTS)
+		sm_info->rec_prefree_segments = DEF_MAX_RECLAIM_PREFREE_SEGMENTS;
+
+	if (!test_opt(sbi, LFS))
+		sm_info->ipu_policy = 1 << F2FS_IPU_FSYNC;
 	sm_info->min_ipu_util = DEF_MIN_IPU_UTIL;
 	sm_info->min_fsync_blocks = DEF_MIN_FSYNC_BLOCKS;
 

fs/f2fs/segment.h

@@ -16,6 +16,7 @@
 #define NULL_SECNO			((unsigned int)(~0))
 
 #define DEF_RECLAIM_PREFREE_SEGMENTS	5	/* 5% over total segments */
+#define DEF_MAX_RECLAIM_PREFREE_SEGMENTS	4096	/* 8GB in maximum */
 
 /* L: Logical segment # in volume, R: Relative segment # in main area */
 #define GET_L2R_SEGNO(free_i, segno)	(segno - free_i->start_segno)
@@ -470,6 +471,10 @@ static inline bool need_SSR(struct f2fs_sb_info *sbi)
 {
 	int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
 	int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
+
+	if (test_opt(sbi, LFS))
+		return false;
+
 	return free_sections(sbi) <= (node_secs + 2 * dent_secs +
 						reserved_sections(sbi) + 1);
 }
@@ -479,6 +484,8 @@ static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, int freed)
 	int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
 	int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
 
+	node_secs += get_blocktype_secs(sbi, F2FS_DIRTY_IMETA);
+
 	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
 		return false;
 
@@ -531,6 +538,9 @@ static inline bool need_inplace_update(struct inode *inode)
 	if (S_ISDIR(inode->i_mode) || f2fs_is_atomic_file(inode))
 		return false;
 
+	if (test_opt(sbi, LFS))
+		return false;
+
 	if (policy & (0x1 << F2FS_IPU_FORCE))
 		return true;
 	if (policy & (0x1 << F2FS_IPU_SSR) && need_SSR(sbi))
@@ -544,7 +554,7 @@ static inline bool need_inplace_update(struct inode *inode)
 
 	/* this is only set during fdatasync */
 	if (policy & (0x1 << F2FS_IPU_FSYNC) &&
-			is_inode_flag_set(F2FS_I(inode), FI_NEED_IPU))
+			is_inode_flag_set(inode, FI_NEED_IPU))
 		return true;
 
 	return false;
@@ -706,9 +716,9 @@ static inline int nr_pages_to_skip(struct f2fs_sb_info *sbi, int type)
 	if (type == DATA)
 		return sbi->blocks_per_seg;
 	else if (type == NODE)
-		return 3 * sbi->blocks_per_seg;
+		return 8 * sbi->blocks_per_seg;
 	else if (type == META)
-		return MAX_BIO_BLOCKS(sbi);
+		return 8 * MAX_BIO_BLOCKS(sbi);
 	else
 		return 0;
 }
@@ -726,10 +736,8 @@ static inline long nr_pages_to_write(struct f2fs_sb_info *sbi, int type,
 
 	nr_to_write = wbc->nr_to_write;
 
-	if (type == DATA)
-		desired = 4096;
-	else if (type == NODE)
-		desired = 3 * max_hw_blocks(sbi);
+	if (type == NODE)
+		desired = 2 * max_hw_blocks(sbi);
 	else
 		desired = MAX_BIO_BLOCKS(sbi);
 

fs/f2fs/shrinker.c

@@ -13,6 +13,7 @@
 #include <linux/f2fs_fs.h>
 
 #include "f2fs.h"
+#include "node.h"
 
 static LIST_HEAD(f2fs_list);
 static DEFINE_SPINLOCK(f2fs_list_lock);
@@ -25,8 +26,8 @@ static unsigned long __count_nat_entries(struct f2fs_sb_info *sbi)
 
 static unsigned long __count_free_nids(struct f2fs_sb_info *sbi)
 {
-	if (NM_I(sbi)->fcnt > NAT_ENTRY_PER_BLOCK)
-		return NM_I(sbi)->fcnt - NAT_ENTRY_PER_BLOCK;
+	if (NM_I(sbi)->fcnt > MAX_FREE_NIDS)
+		return NM_I(sbi)->fcnt - MAX_FREE_NIDS;
 	return 0;
 }
 

fs/f2fs/super.c

@@ -49,6 +49,7 @@ char *fault_name[FAULT_MAX] = {
 	[FAULT_ORPHAN]		= "orphan",
 	[FAULT_BLOCK]		= "no more block",
 	[FAULT_DIR_DEPTH]	= "too big dir depth",
+	[FAULT_EVICT_INODE]	= "evict_inode fail",
 };
 
 static void f2fs_build_fault_attr(unsigned int rate)
@@ -75,6 +76,7 @@ enum {
 	Opt_disable_roll_forward,
 	Opt_norecovery,
 	Opt_discard,
+	Opt_nodiscard,
 	Opt_noheap,
 	Opt_user_xattr,
 	Opt_nouser_xattr,
@@ -86,13 +88,17 @@ enum {
 	Opt_inline_data,
 	Opt_inline_dentry,
 	Opt_flush_merge,
+	Opt_noflush_merge,
 	Opt_nobarrier,
 	Opt_fastboot,
 	Opt_extent_cache,
 	Opt_noextent_cache,
 	Opt_noinline_data,
 	Opt_data_flush,
+	Opt_mode,
 	Opt_fault_injection,
+	Opt_lazytime,
+	Opt_nolazytime,
 	Opt_err,
 };
 
@@ -101,6 +107,7 @@ static match_table_t f2fs_tokens = {
 	{Opt_disable_roll_forward, "disable_roll_forward"},
 	{Opt_norecovery, "norecovery"},
 	{Opt_discard, "discard"},
+	{Opt_nodiscard, "nodiscard"},
 	{Opt_noheap, "no_heap"},
 	{Opt_user_xattr, "user_xattr"},
 	{Opt_nouser_xattr, "nouser_xattr"},
@@ -112,13 +119,17 @@ static match_table_t f2fs_tokens = {
 	{Opt_inline_data, "inline_data"},
 	{Opt_inline_dentry, "inline_dentry"},
 	{Opt_flush_merge, "flush_merge"},
+	{Opt_noflush_merge, "noflush_merge"},
 	{Opt_nobarrier, "nobarrier"},
 	{Opt_fastboot, "fastboot"},
 	{Opt_extent_cache, "extent_cache"},
 	{Opt_noextent_cache, "noextent_cache"},
 	{Opt_noinline_data, "noinline_data"},
 	{Opt_data_flush, "data_flush"},
+	{Opt_mode, "mode=%s"},
 	{Opt_fault_injection, "fault_injection=%u"},
+	{Opt_lazytime, "lazytime"},
+	{Opt_nolazytime, "nolazytime"},
 	{Opt_err, NULL},
 };
 
@@ -417,6 +428,8 @@ static int parse_options(struct super_block *sb, char *options)
 					"the device does not support discard");
 			}
 			break;
+		case Opt_nodiscard:
+			clear_opt(sbi, DISCARD);
 		case Opt_noheap:
 			set_opt(sbi, NOHEAP);
 			break;
@@ -478,6 +491,9 @@ static int parse_options(struct super_block *sb, char *options)
 		case Opt_flush_merge:
 			set_opt(sbi, FLUSH_MERGE);
 			break;
+		case Opt_noflush_merge:
+			clear_opt(sbi, FLUSH_MERGE);
+			break;
 		case Opt_nobarrier:
 			set_opt(sbi, NOBARRIER);
 			break;
@@ -496,6 +512,23 @@ static int parse_options(struct super_block *sb, char *options)
 		case Opt_data_flush:
 			set_opt(sbi, DATA_FLUSH);
 			break;
+		case Opt_mode:
+			name = match_strdup(&args[0]);
+
+			if (!name)
+				return -ENOMEM;
+			if (strlen(name) == 8 &&
+					!strncmp(name, "adaptive", 8)) {
+				set_opt_mode(sbi, F2FS_MOUNT_ADAPTIVE);
+			} else if (strlen(name) == 3 &&
+					!strncmp(name, "lfs", 3)) {
+				set_opt_mode(sbi, F2FS_MOUNT_LFS);
+			} else {
+				kfree(name);
+				return -EINVAL;
+			}
+			kfree(name);
+			break;
 		case Opt_fault_injection:
 			if (args->from && match_int(args, &arg))
 				return -EINVAL;
@@ -506,6 +539,12 @@ static int parse_options(struct super_block *sb, char *options)
 				"FAULT_INJECTION was not selected");
 #endif
 			break;
+		case Opt_lazytime:
+			sb->s_flags |= MS_LAZYTIME;
+			break;
+		case Opt_nolazytime:
+			sb->s_flags &= ~MS_LAZYTIME;
+			break;
 		default:
 			f2fs_msg(sb, KERN_ERR,
 				"Unrecognized mount option \"%s\" or missing value",
@@ -537,13 +576,11 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
 	fi->i_advise = 0;
 	init_rwsem(&fi->i_sem);
 	INIT_LIST_HEAD(&fi->dirty_list);
+	INIT_LIST_HEAD(&fi->gdirty_list);
 	INIT_LIST_HEAD(&fi->inmem_pages);
 	mutex_init(&fi->inmem_lock);
-
-	set_inode_flag(fi, FI_NEW_INODE);
-
-	if (test_opt(F2FS_SB(sb), INLINE_XATTR))
-		set_inode_flag(fi, FI_INLINE_XATTR);
+	init_rwsem(&fi->dio_rwsem[READ]);
+	init_rwsem(&fi->dio_rwsem[WRITE]);
 
 	/* Will be used by directory only */
 	fi->i_dir_level = F2FS_SB(sb)->dir_level;
@@ -559,7 +596,7 @@ static int f2fs_drop_inode(struct inode *inode)
 	 *    - f2fs_gc -> iput -> evict
 	 *       - inode_wait_for_writeback(inode)
 	 */
-	if (!inode_unhashed(inode) && inode->i_state & I_SYNC) {
+	if ((!inode_unhashed(inode) && inode->i_state & I_SYNC)) {
 		if (!inode->i_nlink && !is_bad_inode(inode)) {
 			/* to avoid evict_inode call simultaneously */
 			atomic_inc(&inode->i_count);
@@ -573,10 +610,10 @@ static int f2fs_drop_inode(struct inode *inode)
 			f2fs_destroy_extent_node(inode);
 
 			sb_start_intwrite(inode->i_sb);
-			i_size_write(inode, 0);
+			f2fs_i_size_write(inode, 0);
 
 			if (F2FS_HAS_BLOCKS(inode))
-				f2fs_truncate(inode, true);
+				f2fs_truncate(inode);
 
 			sb_end_intwrite(inode->i_sb);
 
@@ -586,9 +623,47 @@ static int f2fs_drop_inode(struct inode *inode)
 		}
 		return 0;
 	}
+
 	return generic_drop_inode(inode);
 }
 
+int f2fs_inode_dirtied(struct inode *inode)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+
+	spin_lock(&sbi->inode_lock[DIRTY_META]);
+	if (is_inode_flag_set(inode, FI_DIRTY_INODE)) {
+		spin_unlock(&sbi->inode_lock[DIRTY_META]);
+		return 1;
+	}
+
+	set_inode_flag(inode, FI_DIRTY_INODE);
+	list_add_tail(&F2FS_I(inode)->gdirty_list,
+				&sbi->inode_list[DIRTY_META]);
+	inc_page_count(sbi, F2FS_DIRTY_IMETA);
+	stat_inc_dirty_inode(sbi, DIRTY_META);
+	spin_unlock(&sbi->inode_lock[DIRTY_META]);
+
+	return 0;
+}
+
+void f2fs_inode_synced(struct inode *inode)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+
+	spin_lock(&sbi->inode_lock[DIRTY_META]);
+	if (!is_inode_flag_set(inode, FI_DIRTY_INODE)) {
+		spin_unlock(&sbi->inode_lock[DIRTY_META]);
+		return;
+	}
+	list_del_init(&F2FS_I(inode)->gdirty_list);
+	clear_inode_flag(inode, FI_DIRTY_INODE);
+	clear_inode_flag(inode, FI_AUTO_RECOVER);
+	dec_page_count(sbi, F2FS_DIRTY_IMETA);
+	stat_dec_dirty_inode(F2FS_I_SB(inode), DIRTY_META);
+	spin_unlock(&sbi->inode_lock[DIRTY_META]);
+}
+
 /*
  * f2fs_dirty_inode() is called from __mark_inode_dirty()
  *
@@ -596,7 +671,19 @@ static int f2fs_drop_inode(struct inode *inode)
  */
 static void f2fs_dirty_inode(struct inode *inode, int flags)
 {
-	set_inode_flag(F2FS_I(inode), FI_DIRTY_INODE);
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+
+	if (inode->i_ino == F2FS_NODE_INO(sbi) ||
+			inode->i_ino == F2FS_META_INO(sbi))
+		return;
+
+	if (flags == I_DIRTY_TIME)
+		return;
+
+	if (is_inode_flag_set(inode, FI_AUTO_RECOVER))
+		clear_inode_flag(inode, FI_AUTO_RECOVER);
+
+	f2fs_inode_dirtied(inode);
 }
 
 static void f2fs_i_callback(struct rcu_head *head)
@@ -619,6 +706,8 @@ static void destroy_percpu_info(struct f2fs_sb_info *sbi)
 		percpu_counter_destroy(&sbi->nr_pages[i]);
 	percpu_counter_destroy(&sbi->alloc_valid_block_count);
 	percpu_counter_destroy(&sbi->total_valid_inode_count);
+
+	percpu_free_rwsem(&sbi->cp_rwsem);
 }
 
 static void f2fs_put_super(struct super_block *sb)
@@ -738,7 +827,7 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bsize = sbi->blocksize;
 
 	buf->f_blocks = total_count - start_count;
-	buf->f_bfree = buf->f_blocks - valid_user_blocks(sbi) - ovp_count;
+	buf->f_bfree = user_block_count - valid_user_blocks(sbi) + ovp_count;
 	buf->f_bavail = user_block_count - valid_user_blocks(sbi);
 
 	buf->f_files = sbi->total_node_count - F2FS_RESERVED_NODE_NUM;
@@ -803,6 +892,12 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 		seq_puts(seq, ",noextent_cache");
 	if (test_opt(sbi, DATA_FLUSH))
 		seq_puts(seq, ",data_flush");
+
+	seq_puts(seq, ",mode=");
+	if (test_opt(sbi, ADAPTIVE))
+		seq_puts(seq, "adaptive");
+	else if (test_opt(sbi, LFS))
+		seq_puts(seq, "lfs");
 	seq_printf(seq, ",active_logs=%u", sbi->active_logs);
 
 	return 0;
@@ -884,6 +979,14 @@ static void default_options(struct f2fs_sb_info *sbi)
 	set_opt(sbi, BG_GC);
 	set_opt(sbi, INLINE_DATA);
 	set_opt(sbi, EXTENT_CACHE);
+	sbi->sb->s_flags |= MS_LAZYTIME;
+	set_opt(sbi, FLUSH_MERGE);
+	if (f2fs_sb_mounted_hmsmr(sbi->sb)) {
+		set_opt_mode(sbi, F2FS_MOUNT_LFS);
+		set_opt(sbi, DISCARD);
+	} else {
+		set_opt_mode(sbi, F2FS_MOUNT_ADAPTIVE);
+	}
 
 #ifdef CONFIG_F2FS_FS_XATTR
 	set_opt(sbi, XATTR_USER);
@@ -1367,6 +1470,8 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
 
 	INIT_LIST_HEAD(&sbi->s_list);
 	mutex_init(&sbi->umount_mutex);
+	mutex_init(&sbi->wio_mutex[NODE]);
+	mutex_init(&sbi->wio_mutex[DATA]);
 
 #ifdef CONFIG_F2FS_FS_ENCRYPTION
 	memcpy(sbi->key_prefix, F2FS_KEY_DESC_PREFIX,
@@ -1379,6 +1484,9 @@ static int init_percpu_info(struct f2fs_sb_info *sbi)
 {
 	int i, err;
 
+	if (percpu_init_rwsem(&sbi->cp_rwsem))
+		return -ENOMEM;
+
 	for (i = 0; i < NR_COUNT_TYPE; i++) {
 		err = percpu_counter_init(&sbi->nr_pages[i], 0, GFP_KERNEL);
 		if (err)
@@ -1530,6 +1638,8 @@ try_onemore:
 		goto free_sbi;
 
 	sb->s_fs_info = sbi;
+	sbi->raw_super = raw_super;
+
 	default_options(sbi);
 	/* parse mount options */
 	options = kstrdup((const char *)data, GFP_KERNEL);
@@ -1559,10 +1669,8 @@ try_onemore:
 	memcpy(sb->s_uuid, raw_super->uuid, sizeof(raw_super->uuid));
 
 	/* init f2fs-specific super block info */
-	sbi->raw_super = raw_super;
 	sbi->valid_super_block = valid_super_block;
 	mutex_init(&sbi->gc_mutex);
-	mutex_init(&sbi->writepages);
 	mutex_init(&sbi->cp_mutex);
 	init_rwsem(&sbi->node_write);
 
@@ -1579,7 +1687,6 @@ try_onemore:
 		sbi->write_io[i].bio = NULL;
 	}
 
-	init_rwsem(&sbi->cp_rwsem);
 	init_waitqueue_head(&sbi->cp_wait);
 	init_sb_info(sbi);
 
@@ -1762,6 +1869,7 @@ try_onemore:
 	return 0;
 
 free_kobj:
+	f2fs_sync_inode_meta(sbi);
 	kobject_del(&sbi->s_kobj);
 	kobject_put(&sbi->s_kobj);
 	wait_for_completion(&sbi->s_kobj_unregister);

fs/f2fs/xattr.c

@@ -106,7 +106,7 @@ static int f2fs_xattr_advise_set(const struct xattr_handler *handler,
 		return -EINVAL;
 
 	F2FS_I(inode)->i_advise |= *(char *)value;
-	mark_inode_dirty(inode);
+	f2fs_mark_inode_dirty_sync(inode);
 	return 0;
 }
 
@@ -299,6 +299,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
 		if (ipage) {
 			inline_addr = inline_xattr_addr(ipage);
 			f2fs_wait_on_page_writeback(ipage, NODE, true);
+			set_page_dirty(ipage);
 		} else {
 			page = get_node_page(sbi, inode->i_ino);
 			if (IS_ERR(page)) {
@@ -441,13 +442,12 @@ static int __f2fs_setxattr(struct inode *inode, int index,
 			const char *name, const void *value, size_t size,
 			struct page *ipage, int flags)
 {
-	struct f2fs_inode_info *fi = F2FS_I(inode);
 	struct f2fs_xattr_entry *here, *last;
 	void *base_addr;
 	int found, newsize;
 	size_t len;
 	__u32 new_hsize;
-	int error = -ENOMEM;
+	int error = 0;
 
 	if (name == NULL)
 		return -EINVAL;
@@ -465,7 +465,7 @@ static int __f2fs_setxattr(struct inode *inode, int index,
 
 	base_addr = read_all_xattrs(inode, ipage);
 	if (!base_addr)
-		goto exit;
+		return -ENOMEM;
 
 	/* find entry with wanted name. */
 	here = __find_xattr(base_addr, index, len, name);
@@ -539,19 +539,15 @@ static int __f2fs_setxattr(struct inode *inode, int index,
 	if (error)
 		goto exit;
 
-	if (is_inode_flag_set(fi, FI_ACL_MODE)) {
-		inode->i_mode = fi->i_acl_mode;
+	if (is_inode_flag_set(inode, FI_ACL_MODE)) {
+		inode->i_mode = F2FS_I(inode)->i_acl_mode;
 		inode->i_ctime = CURRENT_TIME;
-		clear_inode_flag(fi, FI_ACL_MODE);
+		clear_inode_flag(inode, FI_ACL_MODE);
 	}
 	if (index == F2FS_XATTR_INDEX_ENCRYPTION &&
 			!strcmp(name, F2FS_XATTR_NAME_ENCRYPTION_CONTEXT))
 		f2fs_set_encrypted_inode(inode);
-
-	if (ipage)
-		update_inode(inode, ipage);
-	else
-		update_inode_page(inode);
+	f2fs_mark_inode_dirty_sync(inode);
 exit:
 	kzfree(base_addr);
 	return error;