Merge tag 'f2fs-for-4.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this round, we introduce sysfile-based quota support which is
  required for Android by default. In addition, we allow that users are
  able to reserve some blocks in runtime to mitigate performance drops
  in low free space.

  Enhancements:
   - assign proper data segments according to write_hints given by user
   - issue cache_flush on dirty devices only among multiple devices
   - exploit cp_error flag and add more faults to enhance fault
     injection test
   - conduct more readaheads during f2fs_readdir
   - add a range for discard commands

  Bug fixes:
   - fix zero stat->st_blocks when inline_data is set
   - drop crypto key and free stale memory pointer while evict_inode is
     failing
   - fix some corner cases in free space and segment management
   - fix wrong last_disk_size

  This series includes lots of clean-ups and code enhancement in terms
  of xattr operations, discard/flush command control. In addition, it
  adds versatile debugfs entries to monitor f2fs status"

* tag 'f2fs-for-4.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (75 commits)
  f2fs: deny accessing encryption policy if encryption is off
  f2fs: inject fault in inc_valid_node_count
  f2fs: fix to clear FI_NO_PREALLOC
  f2fs: expose quota information in debugfs
  f2fs: separate nat entry mem alloc from nat_tree_lock
  f2fs: validate before set/clear free nat bitmap
  f2fs: avoid opened loop codes in __add_ino_entry
  f2fs: apply write hints to select the type of segments for buffered write
  f2fs: introduce scan_curseg_cache for cleanup
  f2fs: optimize the way of traversing free_nid_bitmap
  f2fs: keep scanning until enough free nids are acquired
  f2fs: trace checkpoint reason in fsync()
  f2fs: keep isize once block is reserved cross EOF
  f2fs: avoid race in between GC and block exchange
  f2fs: save a multiplication for last_nid calculation
  f2fs: fix summary info corruption
  f2fs: remove dead code in update_meta_page
  f2fs: remove unneeded semicolon
  f2fs: don't bother with inode->i_version
  f2fs: check curseg space before foreground GC
  ...

Documentation/ABI/testing/sysfs-fs-f2fs

@@ -51,6 +51,18 @@ Description:
 		 Controls the dirty page count condition for the in-place-update
 		 policies.
 
+What:		/sys/fs/f2fs/<disk>/min_hot_blocks
+Date:		March 2017
+Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
+Description:
+		 Controls the dirty page count condition for redefining hot data.
+
+What:		/sys/fs/f2fs/<disk>/min_ssr_sections
+Date:		October 2017
+Contact:	"Chao Yu" <yuchao0@huawei.com>
+Description:
+		 Controls the fee section threshold to trigger SSR allocation.
+
 What:		/sys/fs/f2fs/<disk>/max_small_discards
 Date:		November 2013
 Contact:	"Jaegeuk Kim" <jaegeuk.kim@samsung.com>
@@ -102,6 +114,12 @@ Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
 Description:
 		 Controls the idle timing.
 
+What:		/sys/fs/f2fs/<disk>/iostat_enable
+Date:		August 2017
+Contact:	"Chao Yu" <yuchao0@huawei.com>
+Description:
+		 Controls to enable/disable IO stat.
+
 What:		/sys/fs/f2fs/<disk>/ra_nid_pages
 Date:		October 2015
 Contact:	"Chao Yu" <chao2.yu@samsung.com>
@@ -122,6 +140,12 @@ Contact:	"Shuoran Liu" <liushuoran@huawei.com>
 Description:
 		 Shows total written kbytes issued to disk.
 
+What:		/sys/fs/f2fs/<disk>/feature
+Date:		July 2017
+Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
+Description:
+		 Shows all enabled features in current device.
+
 What:		/sys/fs/f2fs/<disk>/inject_rate
 Date:		May 2016
 Contact:	"Sheng Yong" <shengyong1@huawei.com>
@@ -138,7 +162,18 @@ What:		/sys/fs/f2fs/<disk>/reserved_blocks
 Date:		June 2017
 Contact:	"Chao Yu" <yuchao0@huawei.com>
 Description:
-		 Controls current reserved blocks in system.
+		 Controls target reserved blocks in system, the threshold
+		 is soft, it could exceed current available user space.
+
+What:		/sys/fs/f2fs/<disk>/current_reserved_blocks
+Date:		October 2017
+Contact:	"Yunlong Song" <yunlong.song@huawei.com>
+Contact:	"Chao Yu" <yuchao0@huawei.com>
+Description:
+		 Shows current reserved blocks in system, it may be temporarily
+		 smaller than target_reserved_blocks, but will gradually
+		 increase to target_reserved_blocks when more free blocks are
+		 freed by user later.
 
 What:		/sys/fs/f2fs/<disk>/gc_urgent
 Date:		August 2017

fs/f2fs/acl.c

@@ -250,6 +250,9 @@ static int __f2fs_set_acl(struct inode *inode, int type,
 
 int f2fs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 {
+	if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
+		return -EIO;
+
 	return __f2fs_set_acl(inode, type, acl, NULL);
 }
 

fs/f2fs/checkpoint.c

@@ -29,7 +29,6 @@ struct kmem_cache *inode_entry_slab;
 void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io)
 {
 	set_ckpt_flags(sbi, CP_ERROR_FLAG);
-	sbi->sb->s_flags |= MS_RDONLY;
 	if (!end_io)
 		f2fs_flush_merged_writes(sbi);
 }
@@ -398,24 +397,23 @@ const struct address_space_operations f2fs_meta_aops = {
 #endif
 };
 
-static void __add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
+static void __add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino,
+						unsigned int devidx, int type)
 {
 	struct inode_management *im = &sbi->im[type];
 	struct ino_entry *e, *tmp;
 
 	tmp = f2fs_kmem_cache_alloc(ino_entry_slab, GFP_NOFS);
-retry:
+
 	radix_tree_preload(GFP_NOFS | __GFP_NOFAIL);
 
 	spin_lock(&im->ino_lock);
 	e = radix_tree_lookup(&im->ino_root, ino);
 	if (!e) {
 		e = tmp;
-		if (radix_tree_insert(&im->ino_root, ino, e)) {
-			spin_unlock(&im->ino_lock);
-			radix_tree_preload_end();
-			goto retry;
-		}
+		if (unlikely(radix_tree_insert(&im->ino_root, ino, e)))
+			f2fs_bug_on(sbi, 1);
+
 		memset(e, 0, sizeof(struct ino_entry));
 		e->ino = ino;
 
@@ -423,6 +421,10 @@ static void __add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
 		if (type != ORPHAN_INO)
 			im->ino_num++;
 	}
+
+	if (type == FLUSH_INO)
+		f2fs_set_bit(devidx, (char *)&e->dirty_device);
+
 	spin_unlock(&im->ino_lock);
 	radix_tree_preload_end();
 
@@ -451,7 +453,7 @@ static void __remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
 void add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
 {
 	/* add new dirty ino entry into list */
-	__add_ino_entry(sbi, ino, type);
+	__add_ino_entry(sbi, ino, 0, type);
 }
 
 void remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
@@ -477,7 +479,7 @@ void release_ino_entry(struct f2fs_sb_info *sbi, bool all)
 	struct ino_entry *e, *tmp;
 	int i;
 
-	for (i = all ? ORPHAN_INO: APPEND_INO; i <= UPDATE_INO; i++) {
+	for (i = all ? ORPHAN_INO : APPEND_INO; i < MAX_INO_ENTRY; i++) {
 		struct inode_management *im = &sbi->im[i];
 
 		spin_lock(&im->ino_lock);
@@ -491,6 +493,27 @@ void release_ino_entry(struct f2fs_sb_info *sbi, bool all)
 	}
 }
 
+void set_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
+					unsigned int devidx, int type)
+{
+	__add_ino_entry(sbi, ino, devidx, type);
+}
+
+bool is_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
+					unsigned int devidx, int type)
+{
+	struct inode_management *im = &sbi->im[type];
+	struct ino_entry *e;
+	bool is_dirty = false;
+
+	spin_lock(&im->ino_lock);
+	e = radix_tree_lookup(&im->ino_root, ino);
+	if (e && f2fs_test_bit(devidx, (char *)&e->dirty_device))
+		is_dirty = true;
+	spin_unlock(&im->ino_lock);
+	return is_dirty;
+}
+
 int acquire_orphan_inode(struct f2fs_sb_info *sbi)
 {
 	struct inode_management *im = &sbi->im[ORPHAN_INO];
@@ -527,7 +550,7 @@ void release_orphan_inode(struct f2fs_sb_info *sbi)
 void add_orphan_inode(struct inode *inode)
 {
 	/* add new orphan ino entry into list */
-	__add_ino_entry(F2FS_I_SB(inode), inode->i_ino, ORPHAN_INO);
+	__add_ino_entry(F2FS_I_SB(inode), inode->i_ino, 0, ORPHAN_INO);
 	update_inode_page(inode);
 }
 
@@ -551,7 +574,7 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
 		return err;
 	}
 
-	__add_ino_entry(sbi, ino, ORPHAN_INO);
+	__add_ino_entry(sbi, ino, 0, ORPHAN_INO);
 
 	inode = f2fs_iget_retry(sbi->sb, ino);
 	if (IS_ERR(inode)) {
@@ -587,6 +610,9 @@ int recover_orphan_inodes(struct f2fs_sb_info *sbi)
 	block_t start_blk, orphan_blocks, i, j;
 	unsigned int s_flags = sbi->sb->s_flags;
 	int err = 0;
+#ifdef CONFIG_QUOTA
+	int quota_enabled;
+#endif
 
 	if (!is_set_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG))
 		return 0;
@@ -599,8 +625,9 @@ int recover_orphan_inodes(struct f2fs_sb_info *sbi)
 #ifdef CONFIG_QUOTA
 	/* Needed for iput() to work correctly and not trash data */
 	sbi->sb->s_flags |= MS_ACTIVE;
+
 	/* Turn on quotas so that they are updated correctly */
-	f2fs_enable_quota_files(sbi);
+	quota_enabled = f2fs_enable_quota_files(sbi, s_flags & MS_RDONLY);
 #endif
 
 	start_blk = __start_cp_addr(sbi) + 1 + __cp_payload(sbi);
@@ -628,6 +655,7 @@ int recover_orphan_inodes(struct f2fs_sb_info *sbi)
 out:
 #ifdef CONFIG_QUOTA
 	/* Turn quotas off */
+	if (quota_enabled)
 		f2fs_quota_off_umount(sbi->sb);
 #endif
 	sbi->sb->s_flags = s_flags; /* Restore MS_RDONLY status */
@@ -983,7 +1011,7 @@ int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi)
 				update_inode_page(inode);
 			iput(inode);
 		}
-	};
+	}
 	return 0;
 }
 
@@ -1143,6 +1171,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	struct super_block *sb = sbi->sb;
 	struct curseg_info *seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE);
 	u64 kbytes_written;
+	int err;
 
 	/* Flush all the NAT/SIT pages */
 	while (get_pages(sbi, F2FS_DIRTY_META)) {
@@ -1236,6 +1265,11 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	if (unlikely(f2fs_cp_error(sbi)))
 		return -EIO;
 
+	/* flush all device cache */
+	err = f2fs_flush_device_cache(sbi);
+	if (err)
+		return err;
+
 	/* write out checkpoint buffer at block 0 */
 	update_meta_page(sbi, ckpt, start_blk++);
 

fs/f2fs/data.c

@@ -173,7 +173,7 @@ static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr,
 {
 	struct bio *bio;
 
-	bio = f2fs_bio_alloc(npages);
+	bio = f2fs_bio_alloc(sbi, npages, true);
 
 	f2fs_target_device(sbi, blk_addr, bio);
 	bio->bi_end_io = is_read ? f2fs_read_end_io : f2fs_write_end_io;
@@ -418,8 +418,8 @@ int f2fs_submit_page_write(struct f2fs_io_info *fio)
 
 	bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page;
 
-	/* set submitted = 1 as a return value */
-	fio->submitted = 1;
+	/* set submitted = true as a return value */
+	fio->submitted = true;
 
 	inc_page_count(sbi, WB_DATA_TYPE(bio_page));
 
@@ -473,7 +473,7 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
 		f2fs_wait_on_block_writeback(sbi, blkaddr);
 	}
 
-	bio = bio_alloc(GFP_KERNEL, min_t(int, nr_pages, BIO_MAX_PAGES));
+	bio = f2fs_bio_alloc(sbi, min_t(int, nr_pages, BIO_MAX_PAGES), false);
 	if (!bio) {
 		if (ctx)
 			fscrypt_release_ctx(ctx);
@@ -833,6 +833,13 @@ int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
 	struct f2fs_map_blocks map;
 	int err = 0;
 
+	/* convert inline data for Direct I/O*/
+	if (iocb->ki_flags & IOCB_DIRECT) {
+		err = f2fs_convert_inline_inode(inode);
+		if (err)
+			return err;
+	}
+
 	if (is_inode_flag_set(inode, FI_NO_PREALLOC))
 		return 0;
 
@@ -845,15 +852,11 @@ int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
 
 	map.m_next_pgofs = NULL;
 
-	if (iocb->ki_flags & IOCB_DIRECT) {
-		err = f2fs_convert_inline_inode(inode);
-		if (err)
-			return err;
+	if (iocb->ki_flags & IOCB_DIRECT)
 		return f2fs_map_blocks(inode, &map, 1,
 			__force_buffered_io(inode, WRITE) ?
 				F2FS_GET_BLOCK_PRE_AIO :
 				F2FS_GET_BLOCK_PRE_DIO);
-	}
 	if (iocb->ki_pos + iov_iter_count(from) > MAX_INLINE_DATA(inode)) {
 		err = f2fs_convert_inline_inode(inode);
 		if (err)
@@ -1334,7 +1337,7 @@ static int f2fs_read_data_pages(struct file *file,
 			struct address_space *mapping,
 			struct list_head *pages, unsigned nr_pages)
 {
-	struct inode *inode = file->f_mapping->host;
+	struct inode *inode = mapping->host;
 	struct page *page = list_last_entry(pages, struct page, lru);
 
 	trace_f2fs_readpages(inode, page, nr_pages);
@@ -1495,6 +1498,7 @@ static int __write_data_page(struct page *page, bool *submitted,
 	int err = 0;
 	struct f2fs_io_info fio = {
 		.sbi = sbi,
+		.ino = inode->i_ino,
 		.type = DATA,
 		.op = REQ_OP_WRITE,
 		.op_flags = wbc_to_write_flags(wbc),
@@ -1566,8 +1570,11 @@ static int __write_data_page(struct page *page, bool *submitted,
 			err = do_write_data_page(&fio);
 		}
 	}
+
+	down_write(&F2FS_I(inode)->i_sem);
 	if (F2FS_I(inode)->last_disk_size < psize)
 		F2FS_I(inode)->last_disk_size = psize;
+	up_write(&F2FS_I(inode)->i_sem);
 
 done:
 	if (err && err != -ENOENT)
@@ -1932,6 +1939,12 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
 
 	trace_f2fs_write_begin(inode, pos, len, flags);
 
+	if (f2fs_is_atomic_file(inode) &&
+			!available_free_memory(sbi, INMEM_PAGES)) {
+		err = -ENOMEM;
+		goto fail;
+	}
+
 	/*
 	 * We should check this at this moment to avoid deadlock on inode page
 	 * and #0 page. The locking rule for inline_data conversion should be:
@@ -1947,7 +1960,7 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
 	 * Do not use grab_cache_page_write_begin() to avoid deadlock due to
 	 * wait_for_stable_page. Will wait that below with our IO control.
 	 */
-	page = pagecache_get_page(mapping, index,
+	page = f2fs_pagecache_get_page(mapping, index,
 				FGP_LOCK | FGP_WRITE | FGP_CREAT, GFP_NOFS);
 	if (!page) {
 		err = -ENOMEM;
@@ -2009,6 +2022,8 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
 fail:
 	f2fs_put_page(page, 1);
 	f2fs_write_failed(mapping, pos + len);
+	if (f2fs_is_atomic_file(inode))
+		drop_inmem_pages_all(sbi);
 	return err;
 }
 

fs/f2fs/debug.c

@@ -45,9 +45,18 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 	si->ndirty_dent = get_pages(sbi, F2FS_DIRTY_DENTS);
 	si->ndirty_meta = get_pages(sbi, F2FS_DIRTY_META);
 	si->ndirty_data = get_pages(sbi, F2FS_DIRTY_DATA);
+	si->ndirty_qdata = get_pages(sbi, F2FS_DIRTY_QDATA);
 	si->ndirty_imeta = get_pages(sbi, F2FS_DIRTY_IMETA);
 	si->ndirty_dirs = sbi->ndirty_inode[DIR_INODE];
 	si->ndirty_files = sbi->ndirty_inode[FILE_INODE];
+
+	si->nquota_files = 0;
+	if (f2fs_sb_has_quota_ino(sbi->sb)) {
+		for (i = 0; i < MAXQUOTAS; i++) {
+			if (f2fs_qf_ino(sbi->sb, i))
+				si->nquota_files++;
+		}
+	}
 	si->ndirty_all = sbi->ndirty_inode[DIRTY_META];
 	si->inmem_pages = get_pages(sbi, F2FS_INMEM_PAGES);
 	si->aw_cnt = atomic_read(&sbi->aw_cnt);
@@ -61,6 +70,8 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 			atomic_read(&SM_I(sbi)->fcc_info->issued_flush);
 		si->nr_flushing =
 			atomic_read(&SM_I(sbi)->fcc_info->issing_flush);
+		si->flush_list_empty =
+			llist_empty(&SM_I(sbi)->fcc_info->issue_list);
 	}
 	if (SM_I(sbi) && SM_I(sbi)->dcc_info) {
 		si->nr_discarded =
@@ -96,9 +107,9 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 	si->dirty_nats = NM_I(sbi)->dirty_nat_cnt;
 	si->sits = MAIN_SEGS(sbi);
 	si->dirty_sits = SIT_I(sbi)->dirty_sentries;
-	si->free_nids = NM_I(sbi)->nid_cnt[FREE_NID_LIST];
+	si->free_nids = NM_I(sbi)->nid_cnt[FREE_NID];
 	si->avail_nids = NM_I(sbi)->available_nids;
-	si->alloc_nids = NM_I(sbi)->nid_cnt[ALLOC_NID_LIST];
+	si->alloc_nids = NM_I(sbi)->nid_cnt[PREALLOC_NID];
 	si->bg_gc = sbi->bg_gc;
 	si->util_free = (int)(free_user_blocks(sbi) >> sbi->log_blocks_per_seg)
 		* 100 / (int)(sbi->user_block_count >> sbi->log_blocks_per_seg)
@@ -231,14 +242,14 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
 	}
 
 	/* free nids */
-	si->cache_mem += (NM_I(sbi)->nid_cnt[FREE_NID_LIST] +
-				NM_I(sbi)->nid_cnt[ALLOC_NID_LIST]) *
+	si->cache_mem += (NM_I(sbi)->nid_cnt[FREE_NID] +
+				NM_I(sbi)->nid_cnt[PREALLOC_NID]) *
 				sizeof(struct free_nid);
 	si->cache_mem += NM_I(sbi)->nat_cnt * sizeof(struct nat_entry);
 	si->cache_mem += NM_I(sbi)->dirty_nat_cnt *
 					sizeof(struct nat_entry_set);
 	si->cache_mem += si->inmem_pages * sizeof(struct inmem_pages);
-	for (i = 0; i <= ORPHAN_INO; i++)
+	for (i = 0; i < MAX_INO_ENTRY; i++)
 		si->cache_mem += sbi->im[i].ino_num * sizeof(struct ino_entry);
 	si->cache_mem += atomic_read(&sbi->total_ext_tree) *
 						sizeof(struct extent_tree);
@@ -262,9 +273,10 @@ static int stat_show(struct seq_file *s, void *v)
 	list_for_each_entry(si, &f2fs_stat_list, stat_list) {
 		update_general_status(si->sbi);
 
-		seq_printf(s, "\n=====[ partition info(%pg). #%d, %s]=====\n",
+		seq_printf(s, "\n=====[ partition info(%pg). #%d, %s, CP: %s]=====\n",
 			si->sbi->sb->s_bdev, i++,
-			f2fs_readonly(si->sbi->sb) ? "RO": "RW");
+			f2fs_readonly(si->sbi->sb) ? "RO": "RW",
+			f2fs_cp_error(si->sbi) ? "Error": "Good");
 		seq_printf(s, "[SB: 1] [CP: 2] [SIT: %d] [NAT: %d] ",
 			   si->sit_area_segs, si->nat_area_segs);
 		seq_printf(s, "[SSA: %d] [MAIN: %d",
@@ -349,10 +361,11 @@ static int stat_show(struct seq_file *s, void *v)
 		seq_printf(s, "  - Inner Struct Count: tree: %d(%d), node: %d\n",
 				si->ext_tree, si->zombie_tree, si->ext_node);
 		seq_puts(s, "\nBalancing F2FS Async:\n");
-		seq_printf(s, "  - IO (CP: %4d, Data: %4d, Flush: (%4d %4d), "
+		seq_printf(s, "  - IO (CP: %4d, Data: %4d, Flush: (%4d %4d %4d), "
 			"Discard: (%4d %4d)) cmd: %4d undiscard:%4u\n",
 			   si->nr_wb_cp_data, si->nr_wb_data,
 			   si->nr_flushing, si->nr_flushed,
+			   si->flush_list_empty,
 			   si->nr_discarding, si->nr_discarded,
 			   si->nr_discard_cmd, si->undiscard_blks);
 		seq_printf(s, "  - inmem: %4d, atomic IO: %4d (Max. %4d), "
@@ -365,6 +378,8 @@ static int stat_show(struct seq_file *s, void *v)
 			   si->ndirty_dent, si->ndirty_dirs, si->ndirty_all);
 		seq_printf(s, "  - datas: %4d in files:%4d\n",
 			   si->ndirty_data, si->ndirty_files);
+		seq_printf(s, "  - quota datas: %4d in quota files:%4d\n",
+			   si->ndirty_qdata, si->nquota_files);
 		seq_printf(s, "  - meta: %4d in %4d\n",
 			   si->ndirty_meta, si->meta_pages);
 		seq_printf(s, "  - imeta: %4d\n",

fs/f2fs/dir.c

@@ -10,10 +10,12 @@
  */
 #include <linux/fs.h>
 #include <linux/f2fs_fs.h>
+#include <linux/sched/signal.h>
 #include "f2fs.h"
 #include "node.h"
 #include "acl.h"
 #include "xattr.h"
+#include <trace/events/f2fs.h>
 
 static unsigned long dir_blocks(struct inode *inode)
 {
@@ -847,6 +849,7 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
 	struct f2fs_dentry_block *dentry_blk = NULL;
 	struct page *dentry_page = NULL;
 	struct file_ra_state *ra = &file->f_ra;
+	loff_t start_pos = ctx->pos;
 	unsigned int n = ((unsigned long)ctx->pos / NR_DENTRY_IN_BLOCK);
 	struct f2fs_dentry_ptr d;
 	struct fscrypt_str fstr = FSTR_INIT(NULL, 0);
@@ -855,24 +858,32 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
 	if (f2fs_encrypted_inode(inode)) {
 		err = fscrypt_get_encryption_info(inode);
 		if (err && err != -ENOKEY)
-			return err;
+			goto out;
 
 		err = fscrypt_fname_alloc_buffer(inode, F2FS_NAME_LEN, &fstr);
 		if (err < 0)
-			return err;
+			goto out;
 	}
 
 	if (f2fs_has_inline_dentry(inode)) {
 		err = f2fs_read_inline_dir(file, ctx, &fstr);
-		goto out;
+		goto out_free;
 	}
 
+	for (; n < npages; n++, ctx->pos = n * NR_DENTRY_IN_BLOCK) {
+
+		/* allow readdir() to be interrupted */
+		if (fatal_signal_pending(current)) {
+			err = -ERESTARTSYS;
+			goto out_free;
+		}
+		cond_resched();
+
 		/* readahead for multi pages of dir */
 		if (npages - n > 1 && !ra_has_index(ra, n))
 			page_cache_sync_readahead(inode->i_mapping, ra, file, n,
 				min(npages - n, (pgoff_t)MAX_DIR_RA_PAGES));
 
-	for (; n < npages; n++) {
 		dentry_page = get_lock_data_page(inode, n, false);
 		if (IS_ERR(dentry_page)) {
 			err = PTR_ERR(dentry_page);
@@ -880,7 +891,7 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
 				err = 0;
 				continue;
 			} else {
-				goto out;
+				goto out_free;
 			}
 		}
 
@@ -896,12 +907,13 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
 			break;
 		}
 
-		ctx->pos = (n + 1) * NR_DENTRY_IN_BLOCK;
 		kunmap(dentry_page);
 		f2fs_put_page(dentry_page, 1);
 	}
-out:
+out_free:
 	fscrypt_fname_free_buffer(&fstr);
+out:
+	trace_f2fs_readdir(inode, start_pos, ctx->pos, err);
 	return err < 0 ? err : 0;
 }
 

fs/f2fs/f2fs.h

@@ -44,6 +44,8 @@
 enum {
 	FAULT_KMALLOC,
 	FAULT_PAGE_ALLOC,
+	FAULT_PAGE_GET,
+	FAULT_ALLOC_BIO,
 	FAULT_ALLOC_NID,
 	FAULT_ORPHAN,
 	FAULT_BLOCK,
@@ -91,6 +93,7 @@ extern char *fault_name[FAULT_MAX];
 #define F2FS_MOUNT_GRPQUOTA		0x00100000
 #define F2FS_MOUNT_PRJQUOTA		0x00200000
 #define F2FS_MOUNT_QUOTA		0x00400000
+#define F2FS_MOUNT_INLINE_XATTR_SIZE	0x00800000
 
 #define clear_opt(sbi, option)	((sbi)->mount_opt.opt &= ~F2FS_MOUNT_##option)
 #define set_opt(sbi, option)	((sbi)->mount_opt.opt |= F2FS_MOUNT_##option)
@@ -116,6 +119,8 @@ struct f2fs_mount_info {
 #define F2FS_FEATURE_EXTRA_ATTR		0x0008
 #define F2FS_FEATURE_PRJQUOTA		0x0010
 #define F2FS_FEATURE_INODE_CHKSUM	0x0020
+#define F2FS_FEATURE_FLEXIBLE_INLINE_XATTR	0x0040
+#define F2FS_FEATURE_QUOTA_INO		0x0080
 
 #define F2FS_HAS_FEATURE(sb, mask)					\
 	((F2FS_SB(sb)->raw_super->feature & cpu_to_le32(mask)) != 0)
@@ -145,7 +150,7 @@ enum {
 #define BATCHED_TRIM_BLOCKS(sbi)	\
 		(BATCHED_TRIM_SEGMENTS(sbi) << (sbi)->log_blocks_per_seg)
 #define MAX_DISCARD_BLOCKS(sbi)		BLKS_PER_SEC(sbi)
-#define DISCARD_ISSUE_RATE		8
+#define DEF_MAX_DISCARD_REQUEST		8	/* issue 8 discards per round */
 #define DEF_MIN_DISCARD_ISSUE_TIME	50	/* 50 ms, if exists */
 #define DEF_MAX_DISCARD_ISSUE_TIME	60000	/* 60 s, if no candidates */
 #define DEF_CP_INTERVAL			60	/* 60 secs */
@@ -156,7 +161,6 @@ struct cp_control {
 	__u64 trim_start;
 	__u64 trim_end;
 	__u64 trim_minlen;
-	__u64 trimmed;
 };
 
 /*
@@ -175,12 +179,14 @@ enum {
 	ORPHAN_INO,		/* for orphan ino list */
 	APPEND_INO,		/* for append ino list */
 	UPDATE_INO,		/* for update ino list */
+	FLUSH_INO,		/* for multiple device flushing */
 	MAX_INO_ENTRY,		/* max. list */
 };
 
 struct ino_entry {
 	struct list_head list;		/* list head */
 	nid_t ino;			/* inode number */
+	unsigned int dirty_device;	/* dirty device bitmap */
 };
 
 /* for the list of inodes to be GCed */
@@ -204,10 +210,6 @@ struct discard_entry {
 #define plist_idx(blk_num)	((blk_num) >= MAX_PLIST_NUM ?		\
 					(MAX_PLIST_NUM - 1) : (blk_num - 1))
 
-#define P_ACTIVE	0x01
-#define P_TRIM		0x02
-#define plist_issue(tag)	(((tag) & P_ACTIVE) || ((tag) & P_TRIM))
-
 enum {
 	D_PREP,
 	D_SUBMIT,
@@ -239,12 +241,32 @@ struct discard_cmd {
 	int error;			/* bio error */
 };
 
+enum {
+	DPOLICY_BG,
+	DPOLICY_FORCE,
+	DPOLICY_FSTRIM,
+	DPOLICY_UMOUNT,
+	MAX_DPOLICY,
+};
+
+struct discard_policy {
+	int type;			/* type of discard */
+	unsigned int min_interval;	/* used for candidates exist */
+	unsigned int max_interval;	/* used for candidates not exist */
+	unsigned int max_requests;	/* # of discards issued per round */
+	unsigned int io_aware_gran;	/* minimum granularity discard not be aware of I/O */
+	bool io_aware;			/* issue discard in idle time */
+	bool sync;			/* submit discard with REQ_SYNC flag */
+	unsigned int granularity;	/* discard granularity */
+};
+
 struct discard_cmd_control {
 	struct task_struct *f2fs_issue_discard;	/* discard thread */
 	struct list_head entry_list;		/* 4KB discard entry list */
 	struct list_head pend_list[MAX_PLIST_NUM];/* store pending entries */
 	unsigned char pend_list_tag[MAX_PLIST_NUM];/* tag for pending entries */
 	struct list_head wait_list;		/* store on-flushing entries */
+	struct list_head fstrim_list;		/* in-flight discard from fstrim */
 	wait_queue_head_t discard_wait_queue;	/* waiting queue for wake-up */
 	unsigned int discard_wake;		/* to wake up discard thread */
 	struct mutex cmd_lock;
@@ -377,11 +399,14 @@ struct f2fs_flush_device {
 
 /* for inline stuff */
 #define DEF_INLINE_RESERVED_SIZE	1
+#define DEF_MIN_INLINE_SIZE		1
 static inline int get_extra_isize(struct inode *inode);
+static inline int get_inline_xattr_addrs(struct inode *inode);
+#define F2FS_INLINE_XATTR_ADDRS(inode)	get_inline_xattr_addrs(inode)
 #define MAX_INLINE_DATA(inode)	(sizeof(__le32) *			\
 				(CUR_ADDRS_PER_INODE(inode) -		\
-				DEF_INLINE_RESERVED_SIZE - \
-				F2FS_INLINE_XATTR_ADDRS))
+				F2FS_INLINE_XATTR_ADDRS(inode) -	\
+				DEF_INLINE_RESERVED_SIZE))
 
 /* for inline dir */
 #define NR_INLINE_DENTRY(inode)	(MAX_INLINE_DATA(inode) * BITS_PER_BYTE / \
@@ -581,6 +606,7 @@ struct f2fs_inode_info {
 #endif
 	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_ilist;	/* list for inmem inodes */
 	struct list_head inmem_pages;	/* inmemory pages managed by f2fs */
 	struct task_struct *inmem_task;	/* store inmemory task */
 	struct mutex inmem_lock;	/* lock for inmemory pages */
@@ -591,6 +617,7 @@ struct f2fs_inode_info {
 
 	int i_extra_isize;		/* size of extra space located in i_addr */
 	kprojid_t i_projid;		/* id for project quota */
+	int i_inline_xattr_size;	/* inline xattr size */
 };
 
 static inline void get_extent_info(struct extent_info *ext,
@@ -664,10 +691,13 @@ static inline void __try_update_largest_extent(struct inode *inode,
 	}
 }
 
-enum nid_list {
-	FREE_NID_LIST,
-	ALLOC_NID_LIST,
-	MAX_NID_LIST,
+/*
+ * For free nid management
+ */
+enum nid_state {
+	FREE_NID,		/* newly added to free nid list */
+	PREALLOC_NID,		/* it is preallocated */
+	MAX_NID_STATE,
 };
 
 struct f2fs_nm_info {
@@ -690,8 +720,8 @@ struct f2fs_nm_info {
 
 	/* free node ids management */
 	struct radix_tree_root free_nid_root;/* root of the free_nid cache */
-	struct list_head nid_list[MAX_NID_LIST];/* lists for free nids */
-	unsigned int nid_cnt[MAX_NID_LIST];	/* the number of free node id */
+	struct list_head free_nid_list;		/* list for free nids excluding preallocated nids */
+	unsigned int nid_cnt[MAX_NID_STATE];	/* the number of free node id */
 	spinlock_t nid_list_lock;	/* protect nid lists ops */
 	struct mutex build_lock;	/* lock for build free nids */
 	unsigned char (*free_nid_bitmap)[NAT_ENTRY_BITMAP_SIZE];
@@ -769,6 +799,7 @@ enum {
 struct flush_cmd {
 	struct completion wait;
 	struct llist_node llnode;
+	nid_t ino;
 	int ret;
 };
 
@@ -787,6 +818,8 @@ struct f2fs_sm_info {
 	struct dirty_seglist_info *dirty_info;	/* dirty segment information */
 	struct curseg_info *curseg_array;	/* active segment information */
 
+	struct rw_semaphore curseg_lock;	/* for preventing curseg change */
+
 	block_t seg0_blkaddr;		/* block address of 0'th segment */
 	block_t main_blkaddr;		/* start block address of main area */
 	block_t ssa_blkaddr;		/* start block address of SSA area */
@@ -808,6 +841,7 @@ struct f2fs_sm_info {
 	unsigned int min_ipu_util;	/* in-place-update threshold */
 	unsigned int min_fsync_blocks;	/* threshold for fsync */
 	unsigned int min_hot_blocks;	/* threshold for hot block allocation */
+	unsigned int min_ssr_sections;	/* threshold to trigger SSR allocation */
 
 	/* for flush command control */
 	struct flush_cmd_control *fcc_info;
@@ -829,6 +863,7 @@ struct f2fs_sm_info {
 enum count_type {
 	F2FS_DIRTY_DENTS,
 	F2FS_DIRTY_DATA,
+	F2FS_DIRTY_QDATA,
 	F2FS_DIRTY_NODES,
 	F2FS_DIRTY_META,
 	F2FS_INMEM_PAGES,
@@ -877,6 +912,18 @@ enum need_lock_type {
 	LOCK_RETRY,
 };
 
+enum cp_reason_type {
+	CP_NO_NEEDED,
+	CP_NON_REGULAR,
+	CP_HARDLINK,
+	CP_SB_NEED_CP,
+	CP_WRONG_PINO,
+	CP_NO_SPC_ROLL,
+	CP_NODE_NEED_CP,
+	CP_FASTBOOT_MODE,
+	CP_SPEC_LOG_NUM,
+};
+
 enum iostat_type {
 	APP_DIRECT_IO,			/* app direct IOs */
 	APP_BUFFERED_IO,		/* app buffered IOs */
@@ -896,6 +943,7 @@ enum iostat_type {
 
 struct f2fs_io_info {
 	struct f2fs_sb_info *sbi;	/* f2fs_sb_info pointer */
+	nid_t ino;		/* inode number */
 	enum page_type type;	/* contains DATA/NODE/META/META_FLUSH */
 	enum temp_type temp;	/* contains HOT/WARM/COLD */
 	int op;			/* contains REQ_OP_ */
@@ -940,6 +988,7 @@ enum inode_type {
 	DIR_INODE,			/* for dirty dir inode */
 	FILE_INODE,			/* for dirty regular/symlink inode */
 	DIRTY_META,			/* for all dirtied inode metadata */
+	ATOMIC_FILE,			/* for all atomic files */
 	NR_INODE_TYPE,
 };
 
@@ -1042,12 +1091,15 @@ struct f2fs_sb_info {
 	loff_t max_file_blocks;			/* max block index of file */
 	int active_logs;			/* # of active logs */
 	int dir_level;				/* directory level */
+	int inline_xattr_size;			/* inline xattr size */
+	unsigned int trigger_ssr_threshold;	/* threshold to trigger ssr */
 
 	block_t user_block_count;		/* # of user blocks */
 	block_t total_valid_block_count;	/* # of valid blocks */
 	block_t discard_blks;			/* discard command candidats */
 	block_t last_valid_block_count;		/* for recovery */
 	block_t reserved_blocks;		/* configurable reserved blocks */
+	block_t current_reserved_blocks;	/* current reserved blocks */
 
 	u32 s_next_generation;			/* for NFS support */
 
@@ -1113,6 +1165,8 @@ struct f2fs_sb_info {
 	struct list_head s_list;
 	int s_ndevs;				/* number of devices */
 	struct f2fs_dev_info *devs;		/* for device list */
+	unsigned int dirty_device;		/* for checkpoint data flush */
+	spinlock_t dev_lock;			/* protect dirty_device */
 	struct mutex umount_mutex;
 	unsigned int shrinker_run_no;
 
@@ -1176,8 +1230,7 @@ static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type)
 
 static inline bool f2fs_time_over(struct f2fs_sb_info *sbi, int type)
 {
-	struct timespec ts = {sbi->interval_time[type], 0};
-	unsigned long interval = timespec_to_jiffies(&ts);
+	unsigned long interval = sbi->interval_time[type] * HZ;
 
 	return time_after(jiffies, sbi->last_time[type] + interval);
 }
@@ -1344,6 +1397,13 @@ static inline unsigned long long cur_cp_version(struct f2fs_checkpoint *cp)
 	return le64_to_cpu(cp->checkpoint_ver);
 }
 
+static inline unsigned long f2fs_qf_ino(struct super_block *sb, int type)
+{
+	if (type < F2FS_MAX_QUOTAS)
+		return le32_to_cpu(F2FS_SB(sb)->raw_super->qf_ino[type]);
+	return 0;
+}
+
 static inline __u64 cur_cp_crc(struct f2fs_checkpoint *cp)
 {
 	size_t crc_offset = le32_to_cpu(cp->checksum_offset);
@@ -1522,7 +1582,8 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi,
 
 	spin_lock(&sbi->stat_lock);
 	sbi->total_valid_block_count += (block_t)(*count);
-	avail_user_block_count = sbi->user_block_count - sbi->reserved_blocks;
+	avail_user_block_count = sbi->user_block_count -
+					sbi->current_reserved_blocks;
 	if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) {
 		diff = sbi->total_valid_block_count - avail_user_block_count;
 		*count -= diff;
@@ -1556,6 +1617,10 @@ static inline void dec_valid_block_count(struct f2fs_sb_info *sbi,
 	f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count);
 	f2fs_bug_on(sbi, inode->i_blocks < sectors);
 	sbi->total_valid_block_count -= (block_t)count;
+	if (sbi->reserved_blocks &&
+		sbi->current_reserved_blocks < sbi->reserved_blocks)
+		sbi->current_reserved_blocks = min(sbi->reserved_blocks,
+					sbi->current_reserved_blocks + count);
 	spin_unlock(&sbi->stat_lock);
 	f2fs_i_blocks_write(inode, count, false, true);
 }
@@ -1576,6 +1641,8 @@ static inline void inode_inc_dirty_pages(struct inode *inode)
 	atomic_inc(&F2FS_I(inode)->dirty_pages);
 	inc_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ?
 				F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA);
+	if (IS_NOQUOTA(inode))
+		inc_page_count(F2FS_I_SB(inode), F2FS_DIRTY_QDATA);
 }
 
 static inline void dec_page_count(struct f2fs_sb_info *sbi, int count_type)
@@ -1592,6 +1659,8 @@ static inline void inode_dec_dirty_pages(struct inode *inode)
 	atomic_dec(&F2FS_I(inode)->dirty_pages);
 	dec_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ?
 				F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA);
+	if (IS_NOQUOTA(inode))
+		dec_page_count(F2FS_I_SB(inode), F2FS_DIRTY_QDATA);
 }
 
 static inline s64 get_pages(struct f2fs_sb_info *sbi, int count_type)
@@ -1699,10 +1768,17 @@ static inline int inc_valid_node_count(struct f2fs_sb_info *sbi,
 			return ret;
 	}
 
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	if (time_to_inject(sbi, FAULT_BLOCK)) {
+		f2fs_show_injection_info(FAULT_BLOCK);
+		goto enospc;
+	}
+#endif
+
 	spin_lock(&sbi->stat_lock);
 
 	valid_block_count = sbi->total_valid_block_count + 1;
-	if (unlikely(valid_block_count + sbi->reserved_blocks >
+	if (unlikely(valid_block_count + sbi->current_reserved_blocks >
 						sbi->user_block_count)) {
 		spin_unlock(&sbi->stat_lock);
 		goto enospc;
@@ -1745,6 +1821,9 @@ static inline void dec_valid_node_count(struct f2fs_sb_info *sbi,
 
 	sbi->total_valid_node_count--;
 	sbi->total_valid_block_count--;
+	if (sbi->reserved_blocks &&
+		sbi->current_reserved_blocks < sbi->reserved_blocks)
+		sbi->current_reserved_blocks++;
 
 	spin_unlock(&sbi->stat_lock);
 
@@ -1791,6 +1870,19 @@ static inline struct page *f2fs_grab_cache_page(struct address_space *mapping,
 	return grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS);
 }
 
+static inline struct page *f2fs_pagecache_get_page(
+				struct address_space *mapping, pgoff_t index,
+				int fgp_flags, gfp_t gfp_mask)
+{
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_GET)) {
+		f2fs_show_injection_info(FAULT_PAGE_GET);
+		return NULL;
+	}
+#endif
+	return pagecache_get_page(mapping, index, fgp_flags, gfp_mask);
+}
+
 static inline void f2fs_copy_page(struct page *src, struct page *dst)
 {
 	char *src_kaddr = kmap(src);
@@ -1840,15 +1932,25 @@ static inline void *f2fs_kmem_cache_alloc(struct kmem_cache *cachep,
 	return entry;
 }
 
-static inline struct bio *f2fs_bio_alloc(int npages)
+static inline struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi,
+						int npages, bool no_fail)
 {
 	struct bio *bio;
 
+	if (no_fail) {
 		/* No failure on bio allocation */
 		bio = bio_alloc(GFP_NOIO, npages);
 		if (!bio)
 			bio = bio_alloc(GFP_NOIO | __GFP_NOFAIL, npages);
 		return bio;
+	}
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	if (time_to_inject(sbi, FAULT_ALLOC_BIO)) {
+		f2fs_show_injection_info(FAULT_ALLOC_BIO);
+		return NULL;
+	}
+#endif
+	return bio_alloc(GFP_KERNEL, npages);
 }
 
 static inline void f2fs_radix_tree_insert(struct radix_tree_root *root,
@@ -2158,25 +2260,20 @@ static inline int f2fs_has_inline_xattr(struct inode *inode)
 
 static inline unsigned int addrs_per_inode(struct inode *inode)
 {
-	if (f2fs_has_inline_xattr(inode))
-		return CUR_ADDRS_PER_INODE(inode) - F2FS_INLINE_XATTR_ADDRS;
-	return CUR_ADDRS_PER_INODE(inode);
+	return CUR_ADDRS_PER_INODE(inode) - F2FS_INLINE_XATTR_ADDRS(inode);
 }
 
-static inline void *inline_xattr_addr(struct page *page)
+static inline void *inline_xattr_addr(struct inode *inode, struct page *page)
 {
 	struct f2fs_inode *ri = F2FS_INODE(page);
 
 	return (void *)&(ri->i_addr[DEF_ADDRS_PER_INODE -
-					F2FS_INLINE_XATTR_ADDRS]);
+					F2FS_INLINE_XATTR_ADDRS(inode)]);
 }
 
 static inline int inline_xattr_size(struct inode *inode)
 {
-	if (f2fs_has_inline_xattr(inode))
-		return F2FS_INLINE_XATTR_ADDRS << 2;
-	else
-		return 0;
+	return get_inline_xattr_addrs(inode) * sizeof(__le32);
 }
 
 static inline int f2fs_has_inline_data(struct inode *inode)
@@ -2257,9 +2354,10 @@ static inline void clear_file(struct inode *inode, int type)
 
 static inline bool f2fs_skip_inode_update(struct inode *inode, int dsync)
 {
+	bool ret;
+
 	if (dsync) {
 		struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-		bool ret;
 
 		spin_lock(&sbi->inode_lock[DIRTY_META]);
 		ret = list_empty(&F2FS_I(inode)->gdirty_list);
@@ -2270,7 +2368,12 @@ static inline bool f2fs_skip_inode_update(struct inode *inode, int dsync)
 			file_keep_isize(inode) ||
 			i_size_read(inode) & PAGE_MASK)
 		return false;
-	return F2FS_I(inode)->last_disk_size == i_size_read(inode);
+
+	down_read(&F2FS_I(inode)->i_sem);
+	ret = F2FS_I(inode)->last_disk_size == i_size_read(inode);
+	up_read(&F2FS_I(inode)->i_sem);
+
+	return ret;
 }
 
 static inline int f2fs_readonly(struct super_block *sb)
@@ -2320,6 +2423,12 @@ static inline int get_extra_isize(struct inode *inode)
 	return F2FS_I(inode)->i_extra_isize / sizeof(__le32);
 }
 
+static inline int f2fs_sb_has_flexible_inline_xattr(struct super_block *sb);
+static inline int get_inline_xattr_addrs(struct inode *inode)
+{
+	return F2FS_I(inode)->i_inline_xattr_size;
+}
+
 #define get_inode_mode(i) \
 	((is_inode_flag_set(i, FI_ACL_MODE)) ? \
 	 (F2FS_I(i)->i_acl_mode) : ((i)->i_mode))
@@ -2448,7 +2557,7 @@ static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode)
  */
 int f2fs_inode_dirtied(struct inode *inode, bool sync);
 void f2fs_inode_synced(struct inode *inode);
-void f2fs_enable_quota_files(struct f2fs_sb_info *sbi);
+int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly);
 void f2fs_quota_off_umount(struct super_block *sb);
 int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover);
 int f2fs_sync_fs(struct super_block *sb, int sync);
@@ -2476,7 +2585,7 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni);
 pgoff_t get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs);
 int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode);
 int truncate_inode_blocks(struct inode *inode, pgoff_t from);
-int truncate_xattr_node(struct inode *inode, struct page *page);
+int truncate_xattr_node(struct inode *inode);
 int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino);
 int remove_inode_page(struct inode *inode);
 struct page *new_inode_page(struct inode *inode);
@@ -2511,19 +2620,22 @@ void destroy_node_manager_caches(void);
  */
 bool need_SSR(struct f2fs_sb_info *sbi);
 void register_inmem_page(struct inode *inode, struct page *page);
+void drop_inmem_pages_all(struct f2fs_sb_info *sbi);
 void drop_inmem_pages(struct inode *inode);
 void drop_inmem_page(struct inode *inode, struct page *page);
 int commit_inmem_pages(struct inode *inode);
 void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need);
 void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi);
-int f2fs_issue_flush(struct f2fs_sb_info *sbi);
+int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino);
 int create_flush_cmd_control(struct f2fs_sb_info *sbi);
+int f2fs_flush_device_cache(struct f2fs_sb_info *sbi);
 void destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free);
 void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr);
 bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr);
-void refresh_sit_entry(struct f2fs_sb_info *sbi, block_t old, block_t new);
+void init_discard_policy(struct discard_policy *dpolicy, int discard_type,
+						unsigned int granularity);
 void stop_discard_thread(struct f2fs_sb_info *sbi);
-void f2fs_wait_discard_bios(struct f2fs_sb_info *sbi, bool umount);
+bool f2fs_wait_discard_bios(struct f2fs_sb_info *sbi);
 void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc);
 void release_discard_addrs(struct f2fs_sb_info *sbi);
 int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra);
@@ -2578,6 +2690,10 @@ void add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type);
 void remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type);
 void release_ino_entry(struct f2fs_sb_info *sbi, bool all);
 bool exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode);
+void set_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
+					unsigned int devidx, int type);
+bool is_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
+					unsigned int devidx, int type);
 int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi);
 int acquire_orphan_inode(struct f2fs_sb_info *sbi);
 void release_orphan_inode(struct f2fs_sb_info *sbi);
@@ -2665,14 +2781,16 @@ struct f2fs_stat_info {
 	unsigned long long hit_largest, hit_cached, hit_rbtree;
 	unsigned long long hit_total, total_ext;
 	int ext_tree, zombie_tree, ext_node;
-	int ndirty_node, ndirty_dent, ndirty_meta, ndirty_data, ndirty_imeta;
+	int ndirty_node, ndirty_dent, ndirty_meta, ndirty_imeta;
+	int ndirty_data, ndirty_qdata;
 	int inmem_pages;
-	unsigned int ndirty_dirs, ndirty_files, ndirty_all;
+	unsigned int ndirty_dirs, ndirty_files, nquota_files, ndirty_all;
 	int nats, dirty_nats, sits, dirty_sits;
 	int free_nids, avail_nids, alloc_nids;
 	int total_count, utilization;
 	int bg_gc, nr_wb_cp_data, nr_wb_data;
-	int nr_flushing, nr_flushed, nr_discarding, nr_discarded;
+	int nr_flushing, nr_flushed, flush_list_empty;
+	int nr_discarding, nr_discarded;
 	int nr_discard_cmd;
 	unsigned int undiscard_blks;
 	int inline_xattr, inline_inode, inline_dir, append, update, orphans;
@@ -2981,6 +3099,16 @@ static inline int f2fs_sb_has_inode_chksum(struct super_block *sb)
 	return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_INODE_CHKSUM);
 }
 
+static inline int f2fs_sb_has_flexible_inline_xattr(struct super_block *sb)
+{
+	return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_FLEXIBLE_INLINE_XATTR);
+}
+
+static inline int f2fs_sb_has_quota_ino(struct super_block *sb)
+{
+	return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_QUOTA_INO);
+}
+
 #ifdef CONFIG_BLK_DEV_ZONED
 static inline int get_blkz_type(struct f2fs_sb_info *sbi,
 			struct block_device *bdev, block_t blkaddr)

fs/f2fs/file.c

@@ -53,6 +53,11 @@ static int f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 	struct dnode_of_data dn;
 	int err;
 
+	if (unlikely(f2fs_cp_error(sbi))) {
+		err = -EIO;
+		goto err;
+	}
+
 	sb_start_pagefault(inode->i_sb);
 
 	f2fs_bug_on(sbi, f2fs_has_inline_data(inode));
@@ -114,6 +119,7 @@ static int f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 out:
 	sb_end_pagefault(inode->i_sb);
 	f2fs_update_time(sbi, REQ_TIME);
+err:
 	return block_page_mkwrite_return(err);
 }
 
@@ -138,27 +144,29 @@ static int get_parent_ino(struct inode *inode, nid_t *pino)
 	return 1;
 }
 
-static inline bool need_do_checkpoint(struct inode *inode)
+static inline enum cp_reason_type need_do_checkpoint(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	bool need_cp = false;
+	enum cp_reason_type cp_reason = CP_NO_NEEDED;
 
-	if (!S_ISREG(inode->i_mode) || inode->i_nlink != 1)
-		need_cp = true;
+	if (!S_ISREG(inode->i_mode))
+		cp_reason = CP_NON_REGULAR;
+	else if (inode->i_nlink != 1)
+		cp_reason = CP_HARDLINK;
 	else if (is_sbi_flag_set(sbi, SBI_NEED_CP))
-		need_cp = true;
+		cp_reason = CP_SB_NEED_CP;
 	else if (file_wrong_pino(inode))
-		need_cp = true;
+		cp_reason = CP_WRONG_PINO;
 	else if (!space_for_roll_forward(sbi))
-		need_cp = true;
+		cp_reason = CP_NO_SPC_ROLL;
 	else if (!is_checkpointed_node(sbi, F2FS_I(inode)->i_pino))
-		need_cp = true;
+		cp_reason = CP_NODE_NEED_CP;
 	else if (test_opt(sbi, FASTBOOT))
-		need_cp = true;
+		cp_reason = CP_FASTBOOT_MODE;
 	else if (sbi->active_logs == 2)
-		need_cp = true;
+		cp_reason = CP_SPEC_LOG_NUM;
 
-	return need_cp;
+	return cp_reason;
 }
 
 static bool need_inode_page_update(struct f2fs_sb_info *sbi, nid_t ino)
@@ -193,7 +201,7 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	nid_t ino = inode->i_ino;
 	int ret = 0;
-	bool need_cp = false;
+	enum cp_reason_type cp_reason = 0;
 	struct writeback_control wbc = {
 		.sync_mode = WB_SYNC_ALL,
 		.nr_to_write = LONG_MAX,
@@ -212,7 +220,7 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
 	clear_inode_flag(inode, FI_NEED_IPU);
 
 	if (ret) {
-		trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
+		trace_f2fs_sync_file_exit(inode, cp_reason, datasync, ret);
 		return ret;
 	}
 
@@ -243,10 +251,10 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
 	 * sudden-power-off.
 	 */
 	down_read(&F2FS_I(inode)->i_sem);
-	need_cp = need_do_checkpoint(inode);
+	cp_reason = need_do_checkpoint(inode);
 	up_read(&F2FS_I(inode)->i_sem);
 
-	if (need_cp) {
+	if (cp_reason) {
 		/* all the dirty node pages should be flushed for POR */
 		ret = f2fs_sync_fs(inode->i_sb, 1);
 
@@ -294,19 +302,24 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
 	remove_ino_entry(sbi, ino, APPEND_INO);
 	clear_inode_flag(inode, FI_APPEND_WRITE);
 flush_out:
+	if (!atomic)
+		ret = f2fs_issue_flush(sbi, inode->i_ino);
+	if (!ret) {
 		remove_ino_entry(sbi, ino, UPDATE_INO);
 		clear_inode_flag(inode, FI_UPDATE_WRITE);
-	if (!atomic)
-		ret = f2fs_issue_flush(sbi);
+		remove_ino_entry(sbi, ino, FLUSH_INO);
+	}
 	f2fs_update_time(sbi, REQ_TIME);
 out:
-	trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
+	trace_f2fs_sync_file_exit(inode, cp_reason, datasync, ret);
 	f2fs_trace_ios(NULL, 1);
 	return ret;
 }
 
 int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 {
+	if (unlikely(f2fs_cp_error(F2FS_I_SB(file_inode(file)))))
+		return -EIO;
 	return f2fs_do_sync_file(file, start, end, datasync, false);
 }
 
@@ -444,6 +457,9 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	struct inode *inode = file_inode(file);
 	int err;
 
+	if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
+		return -EIO;
+
 	/* we don't need to use inline_data strictly */
 	err = f2fs_convert_inline_inode(inode);
 	if (err)
@@ -630,6 +646,9 @@ int f2fs_truncate(struct inode *inode)
 {
 	int err;
 
+	if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
+		return -EIO;
+
 	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
 				S_ISLNK(inode->i_mode)))
 		return 0;
@@ -684,6 +703,12 @@ int f2fs_getattr(const struct path *path, struct kstat *stat,
 				  STATX_ATTR_NODUMP);
 
 	generic_fillattr(inode, stat);
+
+	/* we need to show initial sectors used for inline_data/dentries */
+	if ((S_ISREG(inode->i_mode) && f2fs_has_inline_data(inode)) ||
+					f2fs_has_inline_dentry(inode))
+		stat->blocks += (stat->size + 511) >> 9;
+
 	return 0;
 }
 
@@ -723,6 +748,9 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
 	int err;
 	bool size_changed = false;
 
+	if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
+		return -EIO;
+
 	err = setattr_prepare(dentry, attr);
 	if (err)
 		return err;
@@ -775,6 +803,10 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
 			inode->i_mtime = inode->i_ctime = current_time(inode);
 		}
 
+		down_write(&F2FS_I(inode)->i_sem);
+		F2FS_I(inode)->last_disk_size = i_size_read(inode);
+		up_write(&F2FS_I(inode)->i_sem);
+
 		size_changed = true;
 	}
 
@@ -845,7 +877,7 @@ int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
 		err = get_dnode_of_data(&dn, pg_start, LOOKUP_NODE);
 		if (err) {
 			if (err == -ENOENT) {
-				pg_start++;
+				pg_start = get_next_page_offset(&dn, pg_start);
 				continue;
 			}
 			return err;
@@ -1160,11 +1192,14 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 	if (ret)
 		goto out;
 
+	/* avoid gc operation during block exchange */
+	down_write(&F2FS_I(inode)->dio_rwsem[WRITE]);
+
 	truncate_pagecache(inode, offset);
 
 	ret = f2fs_do_collapse(inode, pg_start, pg_end);
 	if (ret)
-		goto out;
+		goto out_unlock;
 
 	/* write out all moved pages, if possible */
 	filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
@@ -1176,7 +1211,8 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 	ret = truncate_blocks(inode, new_size, true);
 	if (!ret)
 		f2fs_i_size_write(inode, new_size);
-
+out_unlock:
+	up_write(&F2FS_I(inode)->dio_rwsem[WRITE]);
 out:
 	up_write(&F2FS_I(inode)->i_mmap_sem);
 	return ret;
@@ -1359,6 +1395,9 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
 	if (ret)
 		goto out;
 
+	/* avoid gc operation during block exchange */
+	down_write(&F2FS_I(inode)->dio_rwsem[WRITE]);
+
 	truncate_pagecache(inode, offset);
 
 	pg_start = offset >> PAGE_SHIFT;
@@ -1386,6 +1425,8 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
 
 	if (!ret)
 		f2fs_i_size_write(inode, new_size);
+
+	up_write(&F2FS_I(inode)->dio_rwsem[WRITE]);
 out:
 	up_write(&F2FS_I(inode)->i_mmap_sem);
 	return ret;
@@ -1435,8 +1476,12 @@ 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)
+	if (new_size > i_size_read(inode)) {
+		if (mode & FALLOC_FL_KEEP_SIZE)
+			file_set_keep_isize(inode);
+		else
 			f2fs_i_size_write(inode, new_size);
+	}
 
 	return err;
 }
@@ -1447,6 +1492,9 @@ static long f2fs_fallocate(struct file *file, int mode,
 	struct inode *inode = file_inode(file);
 	long ret = 0;
 
+	if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
+		return -EIO;
+
 	/* f2fs only support ->fallocate for regular file */
 	if (!S_ISREG(inode->i_mode))
 		return -EINVAL;
@@ -1480,8 +1528,6 @@ static long f2fs_fallocate(struct file *file, int mode,
 	if (!ret) {
 		inode->i_mtime = inode->i_ctime = current_time(inode);
 		f2fs_mark_inode_dirty_sync(inode, false);
-		if (mode & FALLOC_FL_KEEP_SIZE)
-			file_set_keep_isize(inode);
 		f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
 	}
 
@@ -1883,6 +1929,9 @@ static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
 
+	if (!f2fs_sb_has_crypto(inode->i_sb))
+		return -EOPNOTSUPP;
+
 	f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
 
 	return fscrypt_ioctl_set_policy(filp, (const void __user *)arg);
@@ -1890,6 +1939,8 @@ static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg)
 
 static int f2fs_ioc_get_encryption_policy(struct file *filp, unsigned long arg)
 {
+	if (!f2fs_sb_has_crypto(file_inode(filp)->i_sb))
+		return -EOPNOTSUPP;
 	return fscrypt_ioctl_get_policy(filp, (void __user *)arg);
 }
 
@@ -2245,9 +2296,13 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in,
 	}
 
 	inode_lock(src);
+	down_write(&F2FS_I(src)->dio_rwsem[WRITE]);
 	if (src != dst) {
-		if (!inode_trylock(dst)) {
 		ret = -EBUSY;
+		if (!inode_trylock(dst))
+			goto out;
+		if (!down_write_trylock(&F2FS_I(dst)->dio_rwsem[WRITE])) {
+			inode_unlock(dst);
 			goto out;
 		}
 	}
@@ -2307,9 +2362,12 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in,
 	}
 	f2fs_unlock_op(sbi);
 out_unlock:
-	if (src != dst)
+	if (src != dst) {
+		up_write(&F2FS_I(dst)->dio_rwsem[WRITE]);
 		inode_unlock(dst);
+	}
 out:
+	up_write(&F2FS_I(src)->dio_rwsem[WRITE]);
 	inode_unlock(src);
 	return ret;
 }
@@ -2625,6 +2683,9 @@ static int f2fs_ioc_fssetxattr(struct file *filp, unsigned long arg)
 
 long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
+	if (unlikely(f2fs_cp_error(F2FS_I_SB(file_inode(filp)))))
+		return -EIO;
+
 	switch (cmd) {
 	case F2FS_IOC_GETFLAGS:
 		return f2fs_ioc_getflags(filp, arg);
@@ -2682,6 +2743,9 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct blk_plug plug;
 	ssize_t ret;
 
+	if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
+		return -EIO;
+
 	inode_lock(inode);
 	ret = generic_write_checks(iocb, from);
 	if (ret > 0) {
@@ -2692,6 +2756,7 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 
 		err = f2fs_preallocate_blocks(iocb, from);
 		if (err) {
+			clear_inode_flag(inode, FI_NO_PREALLOC);
 			inode_unlock(inode);
 			return err;
 		}

fs/f2fs/gc.c

@@ -267,16 +267,6 @@ static unsigned int get_cb_cost(struct f2fs_sb_info *sbi, unsigned int segno)
 	return UINT_MAX - ((100 * (100 - u) * age) / (100 + u));
 }
 
-static unsigned int get_greedy_cost(struct f2fs_sb_info *sbi,
-						unsigned int segno)
-{
-	unsigned int valid_blocks =
-			get_valid_blocks(sbi, segno, true);
-
-	return IS_DATASEG(get_seg_entry(sbi, segno)->type) ?
-				valid_blocks * 2 : valid_blocks;
-}
-
 static inline unsigned int get_gc_cost(struct f2fs_sb_info *sbi,
 			unsigned int segno, struct victim_sel_policy *p)
 {
@@ -285,7 +275,7 @@ static inline unsigned int get_gc_cost(struct f2fs_sb_info *sbi,
 
 	/* alloc_mode == LFS */
 	if (p->gc_mode == GC_GREEDY)
-		return get_greedy_cost(sbi, segno);
+		return get_valid_blocks(sbi, segno, true);
 	else
 		return get_cb_cost(sbi, segno);
 }
@@ -466,10 +456,10 @@ static int check_valid_map(struct f2fs_sb_info *sbi,
 	struct seg_entry *sentry;
 	int ret;
 
-	mutex_lock(&sit_i->sentry_lock);
+	down_read(&sit_i->sentry_lock);
 	sentry = get_seg_entry(sbi, segno);
 	ret = f2fs_test_bit(offset, sentry->cur_valid_map);
-	mutex_unlock(&sit_i->sentry_lock);
+	up_read(&sit_i->sentry_lock);
 	return ret;
 }
 
@@ -608,6 +598,7 @@ static void move_data_block(struct inode *inode, block_t bidx,
 {
 	struct f2fs_io_info fio = {
 		.sbi = F2FS_I_SB(inode),
+		.ino = inode->i_ino,
 		.type = DATA,
 		.temp = COLD,
 		.op = REQ_OP_READ,
@@ -659,8 +650,8 @@ static void move_data_block(struct inode *inode, block_t bidx,
 	allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr,
 					&sum, CURSEG_COLD_DATA, NULL, false);
 
-	fio.encrypted_page = pagecache_get_page(META_MAPPING(fio.sbi), newaddr,
-					FGP_LOCK | FGP_CREAT, GFP_NOFS);
+	fio.encrypted_page = f2fs_pagecache_get_page(META_MAPPING(fio.sbi),
+				newaddr, FGP_LOCK | FGP_CREAT, GFP_NOFS);
 	if (!fio.encrypted_page) {
 		err = -ENOMEM;
 		goto recover_block;
@@ -738,6 +729,7 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type,
 	} else {
 		struct f2fs_io_info fio = {
 			.sbi = F2FS_I_SB(inode),
+			.ino = inode->i_ino,
 			.type = DATA,
 			.temp = COLD,
 			.op = REQ_OP_WRITE,
@@ -840,10 +832,17 @@ static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 				continue;
 			}
 
+			if (!down_write_trylock(
+				&F2FS_I(inode)->dio_rwsem[WRITE])) {
+				iput(inode);
+				continue;
+			}
+
 			start_bidx = start_bidx_of_node(nofs, inode);
 			data_page = get_read_data_page(inode,
 					start_bidx + ofs_in_node, REQ_RAHEAD,
 					true);
+			up_write(&F2FS_I(inode)->dio_rwsem[WRITE]);
 			if (IS_ERR(data_page)) {
 				iput(inode);
 				continue;
@@ -901,10 +900,10 @@ static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim,
 	struct sit_info *sit_i = SIT_I(sbi);
 	int ret;
 
-	mutex_lock(&sit_i->sentry_lock);
+	down_write(&sit_i->sentry_lock);
 	ret = DIRTY_I(sbi)->v_ops->get_victim(sbi, victim, gc_type,
 					      NO_CHECK_TYPE, LFS);
-	mutex_unlock(&sit_i->sentry_lock);
+	up_write(&sit_i->sentry_lock);
 	return ret;
 }
 
@@ -952,8 +951,8 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi,
 		/*
 		 * this is to avoid deadlock:
 		 * - lock_page(sum_page)         - f2fs_replace_block
-		 *  - check_valid_map()            - mutex_lock(sentry_lock)
-		 *   - mutex_lock(sentry_lock)     - change_curseg()
+		 *  - check_valid_map()            - down_write(sentry_lock)
+		 *   - down_read(sentry_lock)     - change_curseg()
 		 *                                  - lock_page(sum_page)
 		 */
 		if (type == SUM_TYPE_NODE)

fs/f2fs/inline.c

@@ -112,6 +112,7 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
 {
 	struct f2fs_io_info fio = {
 		.sbi = F2FS_I_SB(dn->inode),
+		.ino = dn->inode->i_ino,
 		.type = DATA,
 		.op = REQ_OP_WRITE,
 		.op_flags = REQ_SYNC | REQ_PRIO,

fs/f2fs/inode.c

@@ -235,6 +235,23 @@ static int do_read_inode(struct inode *inode)
 	fi->i_extra_isize = f2fs_has_extra_attr(inode) ?
 					le16_to_cpu(ri->i_extra_isize) : 0;
 
+	if (f2fs_sb_has_flexible_inline_xattr(sbi->sb)) {
+		f2fs_bug_on(sbi, !f2fs_has_extra_attr(inode));
+		fi->i_inline_xattr_size = le16_to_cpu(ri->i_inline_xattr_size);
+	} else if (f2fs_has_inline_xattr(inode) ||
+				f2fs_has_inline_dentry(inode)) {
+		fi->i_inline_xattr_size = DEFAULT_INLINE_XATTR_ADDRS;
+	} else {
+
+		/*
+		 * Previous inline data or directory always reserved 200 bytes
+		 * in inode layout, even if inline_xattr is disabled. In order
+		 * to keep inline_dentry's structure for backward compatibility,
+		 * we get the space back only from inline_data.
+		 */
+		fi->i_inline_xattr_size = 0;
+	}
+
 	/* check data exist */
 	if (f2fs_has_inline_data(inode) && !f2fs_exist_data(inode))
 		__recover_inline_status(inode, node_page);
@@ -387,6 +404,10 @@ int update_inode(struct inode *inode, struct page *node_page)
 	if (f2fs_has_extra_attr(inode)) {
 		ri->i_extra_isize = cpu_to_le16(F2FS_I(inode)->i_extra_isize);
 
+		if (f2fs_sb_has_flexible_inline_xattr(F2FS_I_SB(inode)->sb))
+			ri->i_inline_xattr_size =
+				cpu_to_le16(F2FS_I(inode)->i_inline_xattr_size);
+
 		if (f2fs_sb_has_project_quota(F2FS_I_SB(inode)->sb) &&
 			F2FS_FITS_IN_INODE(ri, F2FS_I(inode)->i_extra_isize,
 								i_projid)) {
@@ -483,6 +504,7 @@ void f2fs_evict_inode(struct inode *inode)
 
 	remove_ino_entry(sbi, inode->i_ino, APPEND_INO);
 	remove_ino_entry(sbi, inode->i_ino, UPDATE_INO);
+	remove_ino_entry(sbi, inode->i_ino, FLUSH_INO);
 
 	sb_start_intwrite(inode->i_sb);
 	set_inode_flag(inode, FI_NO_ALLOC);
@@ -522,8 +544,10 @@ void f2fs_evict_inode(struct inode *inode)
 	stat_dec_inline_dir(inode);
 	stat_dec_inline_inode(inode);
 
-	if (!is_set_ckpt_flags(sbi, CP_ERROR_FLAG))
+	if (likely(!is_set_ckpt_flags(sbi, CP_ERROR_FLAG)))
 		f2fs_bug_on(sbi, is_inode_flag_set(inode, FI_DIRTY_INODE));
+	else
+		f2fs_inode_synced(inode);
 
 	/* ino == 0, if f2fs_new_inode() was failed t*/
 	if (inode->i_ino)

fs/f2fs/namei.c

@@ -29,6 +29,7 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
 	nid_t ino;
 	struct inode *inode;
 	bool nid_free = false;
+	int xattr_size = 0;
 	int err;
 
 	inode = new_inode(dir->i_sb);
@@ -86,11 +87,23 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
 
 	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(inode, FI_INLINE_DATA);
 	if (f2fs_may_inline_dentry(inode))
 		set_inode_flag(inode, FI_INLINE_DENTRY);
 
+	if (f2fs_sb_has_flexible_inline_xattr(sbi->sb)) {
+		f2fs_bug_on(sbi, !f2fs_has_extra_attr(inode));
+		if (f2fs_has_inline_xattr(inode))
+			xattr_size = sbi->inline_xattr_size;
+		/* Otherwise, will be 0 */
+	} else if (f2fs_has_inline_xattr(inode) ||
+				f2fs_has_inline_dentry(inode)) {
+		xattr_size = DEFAULT_INLINE_XATTR_ADDRS;
+	}
+	F2FS_I(inode)->i_inline_xattr_size = xattr_size;
+
 	f2fs_init_extent_tree(inode, NULL);
 
 	stat_inc_inline_xattr(inode);
@@ -177,6 +190,9 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 	nid_t ino = 0;
 	int err;
 
+	if (unlikely(f2fs_cp_error(sbi)))
+		return -EIO;
+
 	err = dquot_initialize(dir);
 	if (err)
 		return err;
@@ -221,6 +237,9 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
 	int err;
 
+	if (unlikely(f2fs_cp_error(sbi)))
+		return -EIO;
+
 	if (f2fs_encrypted_inode(dir) &&
 			!fscrypt_has_permitted_context(dir, inode))
 		return -EPERM;
@@ -331,12 +350,15 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
 	struct inode *inode = NULL;
 	struct f2fs_dir_entry *de;
 	struct page *page;
-	nid_t ino;
+	struct dentry *new;
+	nid_t ino = -1;
 	int err = 0;
 	unsigned int root_ino = F2FS_ROOT_INO(F2FS_I_SB(dir));
 
+	trace_f2fs_lookup_start(dir, dentry, flags);
+
 	if (f2fs_encrypted_inode(dir)) {
-		int res = fscrypt_get_encryption_info(dir);
+		err = fscrypt_get_encryption_info(dir);
 
 		/*
 		 * DCACHE_ENCRYPTED_WITH_KEY is set if the dentry is
@@ -346,18 +368,22 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
 		if (fscrypt_has_encryption_key(dir))
 			fscrypt_set_encrypted_dentry(dentry);
 		fscrypt_set_d_op(dentry);
-		if (res && res != -ENOKEY)
-			return ERR_PTR(res);
+		if (err && err != -ENOKEY)
+			goto out;
 	}
 
-	if (dentry->d_name.len > F2FS_NAME_LEN)
-		return ERR_PTR(-ENAMETOOLONG);
+	if (dentry->d_name.len > F2FS_NAME_LEN) {
+		err = -ENAMETOOLONG;
+		goto out;
+	}
 
 	de = f2fs_find_entry(dir, &dentry->d_name, &page);
 	if (!de) {
-		if (IS_ERR(page))
-			return (struct dentry *)page;
-		return d_splice_alias(inode, dentry);
+		if (IS_ERR(page)) {
+			err = PTR_ERR(page);
+			goto out;
+		}
+		goto out_splice;
 	}
 
 	ino = le32_to_cpu(de->ino);
@@ -365,19 +391,21 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
 	f2fs_put_page(page, 0);
 
 	inode = f2fs_iget(dir->i_sb, ino);
-	if (IS_ERR(inode))
-		return ERR_CAST(inode);
+	if (IS_ERR(inode)) {
+		err = PTR_ERR(inode);
+		goto out;
+	}
 
 	if ((dir->i_ino == root_ino) && f2fs_has_inline_dots(dir)) {
 		err = __recover_dot_dentries(dir, root_ino);
 		if (err)
-			goto err_out;
+			goto out_iput;
 	}
 
 	if (f2fs_has_inline_dots(inode)) {
 		err = __recover_dot_dentries(inode, dir->i_ino);
 		if (err)
-			goto err_out;
+			goto out_iput;
 	}
 	if (f2fs_encrypted_inode(dir) &&
 	    (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) &&
@@ -386,12 +414,18 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
 			 "Inconsistent encryption contexts: %lu/%lu",
 			 dir->i_ino, inode->i_ino);
 		err = -EPERM;
-		goto err_out;
+		goto out_iput;
 	}
-	return d_splice_alias(inode, dentry);
-
-err_out:
+out_splice:
+	new = d_splice_alias(inode, dentry);
+	if (IS_ERR(new))
+		err = PTR_ERR(new);
+	trace_f2fs_lookup_end(dir, dentry, ino, err);
+	return new;
+out_iput:
 	iput(inode);
+out:
+	trace_f2fs_lookup_end(dir, dentry, ino, err);
 	return ERR_PTR(err);
 }
 
@@ -405,7 +439,13 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
 
 	trace_f2fs_unlink_enter(dir, dentry);
 
+	if (unlikely(f2fs_cp_error(sbi)))
+		return -EIO;
+
 	err = dquot_initialize(dir);
+	if (err)
+		return err;
+	err = dquot_initialize(inode);
 	if (err)
 		return err;
 
@@ -460,6 +500,9 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
 	struct fscrypt_symlink_data *sd = NULL;
 	int err;
 
+	if (unlikely(f2fs_cp_error(sbi)))
+		return -EIO;
+
 	if (f2fs_encrypted_inode(dir)) {
 		err = fscrypt_get_encryption_info(dir);
 		if (err)
@@ -566,6 +609,9 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	struct inode *inode;
 	int err;
 
+	if (unlikely(f2fs_cp_error(sbi)))
+		return -EIO;
+
 	err = dquot_initialize(dir);
 	if (err)
 		return err;
@@ -618,6 +664,9 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
 	struct inode *inode;
 	int err = 0;
 
+	if (unlikely(f2fs_cp_error(sbi)))
+		return -EIO;
+
 	err = dquot_initialize(dir);
 	if (err)
 		return err;
@@ -712,6 +761,9 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry,
 
 static int f2fs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
 {
+	if (unlikely(f2fs_cp_error(F2FS_I_SB(dir))))
+		return -EIO;
+
 	if (f2fs_encrypted_inode(dir)) {
 		int err = fscrypt_get_encryption_info(dir);
 		if (err)
@@ -723,6 +775,9 @@ static int f2fs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
 
 static int f2fs_create_whiteout(struct inode *dir, struct inode **whiteout)
 {
+	if (unlikely(f2fs_cp_error(F2FS_I_SB(dir))))
+		return -EIO;
+
 	return __f2fs_tmpfile(dir, NULL, S_IFCHR | WHITEOUT_MODE, whiteout);
 }
 
@@ -742,6 +797,9 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	bool is_old_inline = f2fs_has_inline_dentry(old_dir);
 	int err = -ENOENT;
 
+	if (unlikely(f2fs_cp_error(sbi)))
+		return -EIO;
+
 	if ((f2fs_encrypted_inode(old_dir) &&
 			!fscrypt_has_encryption_key(old_dir)) ||
 			(f2fs_encrypted_inode(new_dir) &&
@@ -767,6 +825,12 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (err)
 		goto out;
 
+	if (new_inode) {
+		err = dquot_initialize(new_inode);
+		if (err)
+			goto out;
+	}
+
 	old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
 	if (!old_entry) {
 		if (IS_ERR(old_page))
@@ -935,6 +999,9 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 	int old_nlink = 0, new_nlink = 0;
 	int err = -ENOENT;
 
+	if (unlikely(f2fs_cp_error(sbi)))
+		return -EIO;
+
 	if ((f2fs_encrypted_inode(old_dir) &&
 			!fscrypt_has_encryption_key(old_dir)) ||
 			(f2fs_encrypted_inode(new_dir) &&

fs/f2fs/node.c

@@ -46,7 +46,7 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type)
 	 * give 25%, 25%, 50%, 50%, 50% memory for each components respectively
 	 */
 	if (type == FREE_NIDS) {
-		mem_size = (nm_i->nid_cnt[FREE_NID_LIST] *
+		mem_size = (nm_i->nid_cnt[FREE_NID] *
 				sizeof(struct free_nid)) >> PAGE_SHIFT;
 		res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2);
 	} else if (type == NAT_ENTRIES) {
@@ -63,7 +63,7 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type)
 	} else if (type == INO_ENTRIES) {
 		int i;
 
-		for (i = 0; i <= UPDATE_INO; i++)
+		for (i = 0; i < MAX_INO_ENTRY; i++)
 			mem_size += sbi->im[i].ino_num *
 						sizeof(struct ino_entry);
 		mem_size >>= PAGE_SHIFT;
@@ -74,6 +74,10 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type)
 				atomic_read(&sbi->total_ext_node) *
 				sizeof(struct extent_node)) >> PAGE_SHIFT;
 		res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1);
+	} else if (type == INMEM_PAGES) {
+		/* it allows 20% / total_ram for inmemory pages */
+		mem_size = get_pages(sbi, F2FS_INMEM_PAGES);
+		res = mem_size < (val.totalram / 5);
 	} else {
 		if (!sbi->sb->s_bdi->wb.dirty_exceeded)
 			return true;
@@ -134,6 +138,44 @@ static struct page *get_next_nat_page(struct f2fs_sb_info *sbi, nid_t nid)
 	return dst_page;
 }
 
+static struct nat_entry *__alloc_nat_entry(nid_t nid, bool no_fail)
+{
+	struct nat_entry *new;
+
+	if (no_fail)
+		new = f2fs_kmem_cache_alloc(nat_entry_slab,
+						GFP_NOFS | __GFP_ZERO);
+	else
+		new = kmem_cache_alloc(nat_entry_slab,
+						GFP_NOFS | __GFP_ZERO);
+	if (new) {
+		nat_set_nid(new, nid);
+		nat_reset_flag(new);
+	}
+	return new;
+}
+
+static void __free_nat_entry(struct nat_entry *e)
+{
+	kmem_cache_free(nat_entry_slab, e);
+}
+
+/* must be locked by nat_tree_lock */
+static struct nat_entry *__init_nat_entry(struct f2fs_nm_info *nm_i,
+	struct nat_entry *ne, struct f2fs_nat_entry *raw_ne, bool no_fail)
+{
+	if (no_fail)
+		f2fs_radix_tree_insert(&nm_i->nat_root, nat_get_nid(ne), ne);
+	else if (radix_tree_insert(&nm_i->nat_root, nat_get_nid(ne), ne))
+		return NULL;
+
+	if (raw_ne)
+		node_info_from_raw_nat(&ne->ni, raw_ne);
+	list_add_tail(&ne->list, &nm_i->nat_entries);
+	nm_i->nat_cnt++;
+	return ne;
+}
+
 static struct nat_entry *__lookup_nat_cache(struct f2fs_nm_info *nm_i, nid_t n)
 {
 	return radix_tree_lookup(&nm_i->nat_root, n);
@@ -150,7 +192,7 @@ static void __del_from_nat_cache(struct f2fs_nm_info *nm_i, struct nat_entry *e)
 	list_del(&e->list);
 	radix_tree_delete(&nm_i->nat_root, nat_get_nid(e));
 	nm_i->nat_cnt--;
-	kmem_cache_free(nat_entry_slab, e);
+	__free_nat_entry(e);
 }
 
 static void __set_nat_cache_dirty(struct f2fs_nm_info *nm_i,
@@ -246,49 +288,29 @@ bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino)
 	return need_update;
 }
 
-static struct nat_entry *grab_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid,
-								bool no_fail)
-{
-	struct nat_entry *new;
-
-	if (no_fail) {
-		new = f2fs_kmem_cache_alloc(nat_entry_slab, GFP_NOFS);
-		f2fs_radix_tree_insert(&nm_i->nat_root, nid, new);
-	} else {
-		new = kmem_cache_alloc(nat_entry_slab, GFP_NOFS);
-		if (!new)
-			return NULL;
-		if (radix_tree_insert(&nm_i->nat_root, nid, new)) {
-			kmem_cache_free(nat_entry_slab, new);
-			return NULL;
-		}
-	}
-
-	memset(new, 0, sizeof(struct nat_entry));
-	nat_set_nid(new, nid);
-	nat_reset_flag(new);
-	list_add_tail(&new->list, &nm_i->nat_entries);
-	nm_i->nat_cnt++;
-	return new;
-}
-
+/* must be locked by nat_tree_lock */
 static void cache_nat_entry(struct f2fs_sb_info *sbi, nid_t nid,
 						struct f2fs_nat_entry *ne)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
-	struct nat_entry *e;
+	struct nat_entry *new, *e;
+
+	new = __alloc_nat_entry(nid, false);
+	if (!new)
+		return;
 
+	down_write(&nm_i->nat_tree_lock);
 	e = __lookup_nat_cache(nm_i, nid);
-	if (!e) {
-		e = grab_nat_entry(nm_i, nid, false);
-		if (e)
-			node_info_from_raw_nat(&e->ni, ne);
-	} else {
+	if (!e)
+		e = __init_nat_entry(nm_i, new, ne, false);
+	else
 		f2fs_bug_on(sbi, nat_get_ino(e) != le32_to_cpu(ne->ino) ||
 				nat_get_blkaddr(e) !=
 					le32_to_cpu(ne->block_addr) ||
 				nat_get_version(e) != ne->version);
-	}
+	up_write(&nm_i->nat_tree_lock);
+	if (e != new)
+		__free_nat_entry(new);
 }
 
 static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
@@ -296,11 +318,12 @@ 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;
+	struct nat_entry *new = __alloc_nat_entry(ni->nid, true);
 
 	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, true);
+		e = __init_nat_entry(nm_i, new, NULL, true);
 		copy_node_info(&e->ni, ni);
 		f2fs_bug_on(sbi, ni->blk_addr == NEW_ADDR);
 	} else if (new_blkaddr == NEW_ADDR) {
@@ -312,6 +335,9 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
 		copy_node_info(&e->ni, ni);
 		f2fs_bug_on(sbi, ni->blk_addr != NULL_ADDR);
 	}
+	/* let's free early to reduce memory consumption */
+	if (e != new)
+		__free_nat_entry(new);
 
 	/* sanity check */
 	f2fs_bug_on(sbi, nat_get_blkaddr(e) != ni->blk_addr);
@@ -327,10 +353,6 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
 	if (nat_get_blkaddr(e) != NEW_ADDR && new_blkaddr == NULL_ADDR) {
 		unsigned char version = nat_get_version(e);
 		nat_set_version(e, inc_node_version(version));
-
-		/* in order to reuse the nid */
-		if (nm_i->next_scan_nid > ni->nid)
-			nm_i->next_scan_nid = ni->nid;
 	}
 
 	/* change address */
@@ -424,9 +446,7 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
 	f2fs_put_page(page, 1);
 cache:
 	/* cache nat entry */
-	down_write(&nm_i->nat_tree_lock);
 	cache_nat_entry(sbi, nid, &ne);
-	up_write(&nm_i->nat_tree_lock);
 }
 
 /*
@@ -962,7 +982,8 @@ int truncate_inode_blocks(struct inode *inode, pgoff_t from)
 	return err > 0 ? 0 : err;
 }
 
-int truncate_xattr_node(struct inode *inode, struct page *page)
+/* caller must lock inode page */
+int truncate_xattr_node(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	nid_t nid = F2FS_I(inode)->i_xattr_nid;
@@ -978,10 +999,7 @@ int truncate_xattr_node(struct inode *inode, struct page *page)
 
 	f2fs_i_xnid_write(inode, 0);
 
-	set_new_dnode(&dn, inode, page, npage, nid);
-
-	if (page)
-		dn.inode_page_locked = true;
+	set_new_dnode(&dn, inode, NULL, npage, nid);
 	truncate_node(&dn);
 	return 0;
 }
@@ -1000,7 +1018,7 @@ int remove_inode_page(struct inode *inode)
 	if (err)
 		return err;
 
-	err = truncate_xattr_node(inode, dn.inode_page);
+	err = truncate_xattr_node(inode);
 	if (err) {
 		f2fs_put_dnode(&dn);
 		return err;
@@ -1220,7 +1238,8 @@ static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino)
 	if (!inode)
 		return;
 
-	page = pagecache_get_page(inode->i_mapping, 0, FGP_LOCK|FGP_NOWAIT, 0);
+	page = f2fs_pagecache_get_page(inode->i_mapping, 0,
+					FGP_LOCK|FGP_NOWAIT, 0);
 	if (!page)
 		goto iput_out;
 
@@ -1244,37 +1263,6 @@ static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino)
 	iput(inode);
 }
 
-void move_node_page(struct page *node_page, int gc_type)
-{
-	if (gc_type == FG_GC) {
-		struct f2fs_sb_info *sbi = F2FS_P_SB(node_page);
-		struct writeback_control wbc = {
-			.sync_mode = WB_SYNC_ALL,
-			.nr_to_write = 1,
-			.for_reclaim = 0,
-		};
-
-		set_page_dirty(node_page);
-		f2fs_wait_on_page_writeback(node_page, NODE, true);
-
-		f2fs_bug_on(sbi, PageWriteback(node_page));
-		if (!clear_page_dirty_for_io(node_page))
-			goto out_page;
-
-		if (NODE_MAPPING(sbi)->a_ops->writepage(node_page, &wbc))
-			unlock_page(node_page);
-		goto release_page;
-	} else {
-		/* set page dirty and write it */
-		if (!PageWriteback(node_page))
-			set_page_dirty(node_page);
-	}
-out_page:
-	unlock_page(node_page);
-release_page:
-	f2fs_put_page(node_page, 0);
-}
-
 static struct page *last_fsync_dnode(struct f2fs_sb_info *sbi, nid_t ino)
 {
 	pgoff_t index;
@@ -1340,6 +1328,7 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
 	struct node_info ni;
 	struct f2fs_io_info fio = {
 		.sbi = sbi,
+		.ino = ino_of_node(page),
 		.type = NODE,
 		.op = REQ_OP_WRITE,
 		.op_flags = wbc_to_write_flags(wbc),
@@ -1412,6 +1401,37 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
 	return AOP_WRITEPAGE_ACTIVATE;
 }
 
+void move_node_page(struct page *node_page, int gc_type)
+{
+	if (gc_type == FG_GC) {
+		struct writeback_control wbc = {
+			.sync_mode = WB_SYNC_ALL,
+			.nr_to_write = 1,
+			.for_reclaim = 0,
+		};
+
+		set_page_dirty(node_page);
+		f2fs_wait_on_page_writeback(node_page, NODE, true);
+
+		f2fs_bug_on(F2FS_P_SB(node_page), PageWriteback(node_page));
+		if (!clear_page_dirty_for_io(node_page))
+			goto out_page;
+
+		if (__write_node_page(node_page, false, NULL,
+					&wbc, false, FS_GC_NODE_IO))
+			unlock_page(node_page);
+		goto release_page;
+	} else {
+		/* set page dirty and write it */
+		if (!PageWriteback(node_page))
+			set_page_dirty(node_page);
+	}
+out_page:
+	unlock_page(node_page);
+release_page:
+	f2fs_put_page(node_page, 0);
+}
+
 static int f2fs_write_node_page(struct page *page,
 				struct writeback_control *wbc)
 {
@@ -1742,37 +1762,56 @@ static struct free_nid *__lookup_free_nid_list(struct f2fs_nm_info *nm_i,
 	return radix_tree_lookup(&nm_i->free_nid_root, n);
 }
 
-static int __insert_nid_to_list(struct f2fs_sb_info *sbi,
-			struct free_nid *i, enum nid_list list, bool new)
+static int __insert_free_nid(struct f2fs_sb_info *sbi,
+			struct free_nid *i, enum nid_state state)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 
-	if (new) {
 	int err = radix_tree_insert(&nm_i->free_nid_root, i->nid, i);
 	if (err)
 		return err;
-	}
 
-	f2fs_bug_on(sbi, list == FREE_NID_LIST ? i->state != NID_NEW :
-						i->state != NID_ALLOC);
-	nm_i->nid_cnt[list]++;
-	list_add_tail(&i->list, &nm_i->nid_list[list]);
+	f2fs_bug_on(sbi, state != i->state);
+	nm_i->nid_cnt[state]++;
+	if (state == FREE_NID)
+		list_add_tail(&i->list, &nm_i->free_nid_list);
 	return 0;
 }
 
-static void __remove_nid_from_list(struct f2fs_sb_info *sbi,
-			struct free_nid *i, enum nid_list list, bool reuse)
+static void __remove_free_nid(struct f2fs_sb_info *sbi,
+			struct free_nid *i, enum nid_state state)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 
-	f2fs_bug_on(sbi, list == FREE_NID_LIST ? i->state != NID_NEW :
-						i->state != NID_ALLOC);
-	nm_i->nid_cnt[list]--;
+	f2fs_bug_on(sbi, state != i->state);
+	nm_i->nid_cnt[state]--;
+	if (state == FREE_NID)
 		list_del(&i->list);
-	if (!reuse)
 	radix_tree_delete(&nm_i->free_nid_root, i->nid);
 }
 
+static void __move_free_nid(struct f2fs_sb_info *sbi, struct free_nid *i,
+			enum nid_state org_state, enum nid_state dst_state)
+{
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
+
+	f2fs_bug_on(sbi, org_state != i->state);
+	i->state = dst_state;
+	nm_i->nid_cnt[org_state]--;
+	nm_i->nid_cnt[dst_state]++;
+
+	switch (dst_state) {
+	case PREALLOC_NID:
+		list_del(&i->list);
+		break;
+	case FREE_NID:
+		list_add_tail(&i->list, &nm_i->free_nid_list);
+		break;
+	default:
+		BUG_ON(1);
+	}
+}
+
 /* return if the nid is recognized as free */
 static bool add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
 {
@@ -1788,7 +1827,7 @@ static bool add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
 
 	i = f2fs_kmem_cache_alloc(free_nid_slab, GFP_NOFS);
 	i->nid = nid;
-	i->state = NID_NEW;
+	i->state = FREE_NID;
 
 	if (radix_tree_preload(GFP_NOFS))
 		goto err;
@@ -1801,7 +1840,7 @@ static bool add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
 		 *  - f2fs_create
 		 *   - f2fs_new_inode
 		 *    - alloc_nid
-		 *     - __insert_nid_to_list(ALLOC_NID_LIST)
+		 *     - __insert_nid_to_list(PREALLOC_NID)
 		 *                     - f2fs_balance_fs_bg
 		 *                      - build_free_nids
 		 *                       - __build_free_nids
@@ -1814,8 +1853,8 @@ static bool add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
 		 *     - new_node_page
 		 *      - set_node_addr
 		 *  - alloc_nid_done
-		 *   - __remove_nid_from_list(ALLOC_NID_LIST)
-		 *                         - __insert_nid_to_list(FREE_NID_LIST)
+		 *   - __remove_nid_from_list(PREALLOC_NID)
+		 *                         - __insert_nid_to_list(FREE_NID)
 		 */
 		ne = __lookup_nat_cache(nm_i, nid);
 		if (ne && (!get_nat_flag(ne, IS_CHECKPOINTED) ||
@@ -1824,13 +1863,13 @@ static bool add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
 
 		e = __lookup_free_nid_list(nm_i, nid);
 		if (e) {
-			if (e->state == NID_NEW)
+			if (e->state == FREE_NID)
 				ret = true;
 			goto err_out;
 		}
 	}
 	ret = true;
-	err = __insert_nid_to_list(sbi, i, FREE_NID_LIST, true);
+	err = __insert_free_nid(sbi, i, FREE_NID);
 err_out:
 	spin_unlock(&nm_i->nid_list_lock);
 	radix_tree_preload_end();
@@ -1848,8 +1887,8 @@ static void remove_free_nid(struct f2fs_sb_info *sbi, nid_t nid)
 
 	spin_lock(&nm_i->nid_list_lock);
 	i = __lookup_free_nid_list(nm_i, nid);
-	if (i && i->state == NID_NEW) {
-		__remove_nid_from_list(sbi, i, FREE_NID_LIST, false);
+	if (i && i->state == FREE_NID) {
+		__remove_free_nid(sbi, i, FREE_NID);
 		need_free = true;
 	}
 	spin_unlock(&nm_i->nid_list_lock);
@@ -1868,15 +1907,18 @@ static void update_free_nid_bitmap(struct f2fs_sb_info *sbi, nid_t nid,
 	if (!test_bit_le(nat_ofs, nm_i->nat_block_bitmap))
 		return;
 
-	if (set)
+	if (set) {
+		if (test_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]))
+			return;
 		__set_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]);
-	else
-		__clear_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]);
-
-	if (set)
 		nm_i->free_nid_count[nat_ofs]++;
-	else if (!build)
+	} else {
+		if (!test_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]))
+			return;
+		__clear_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]);
+		if (!build)
 			nm_i->free_nid_count[nat_ofs]--;
+	}
 }
 
 static void scan_nat_page(struct f2fs_sb_info *sbi,
@@ -1911,12 +1953,32 @@ static void scan_nat_page(struct f2fs_sb_info *sbi,
 	}
 }
 
-static void scan_free_nid_bits(struct f2fs_sb_info *sbi)
+static void scan_curseg_cache(struct f2fs_sb_info *sbi)
 {
-	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
 	struct f2fs_journal *journal = curseg->journal;
+	int i;
+
+	down_read(&curseg->journal_rwsem);
+	for (i = 0; i < nats_in_cursum(journal); i++) {
+		block_t addr;
+		nid_t nid;
+
+		addr = le32_to_cpu(nat_in_journal(journal, i).block_addr);
+		nid = le32_to_cpu(nid_in_journal(journal, i));
+		if (addr == NULL_ADDR)
+			add_free_nid(sbi, nid, true);
+		else
+			remove_free_nid(sbi, nid);
+	}
+	up_read(&curseg->journal_rwsem);
+}
+
+static void scan_free_nid_bits(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	unsigned int i, idx;
+	nid_t nid;
 
 	down_read(&nm_i->nat_tree_lock);
 
@@ -1926,40 +1988,27 @@ static void scan_free_nid_bits(struct f2fs_sb_info *sbi)
 		if (!nm_i->free_nid_count[i])
 			continue;
 		for (idx = 0; idx < NAT_ENTRY_PER_BLOCK; idx++) {
-			nid_t nid;
-
-			if (!test_bit_le(idx, nm_i->free_nid_bitmap[i]))
-				continue;
+			idx = find_next_bit_le(nm_i->free_nid_bitmap[i],
+						NAT_ENTRY_PER_BLOCK, idx);
+			if (idx >= NAT_ENTRY_PER_BLOCK)
+				break;
 
 			nid = i * NAT_ENTRY_PER_BLOCK + idx;
 			add_free_nid(sbi, nid, true);
 
-			if (nm_i->nid_cnt[FREE_NID_LIST] >= MAX_FREE_NIDS)
+			if (nm_i->nid_cnt[FREE_NID] >= MAX_FREE_NIDS)
 				goto out;
 		}
 	}
 out:
-	down_read(&curseg->journal_rwsem);
-	for (i = 0; i < nats_in_cursum(journal); i++) {
-		block_t addr;
-		nid_t nid;
+	scan_curseg_cache(sbi);
 
-		addr = le32_to_cpu(nat_in_journal(journal, i).block_addr);
-		nid = le32_to_cpu(nid_in_journal(journal, i));
-		if (addr == NULL_ADDR)
-			add_free_nid(sbi, nid, true);
-		else
-			remove_free_nid(sbi, nid);
-	}
-	up_read(&curseg->journal_rwsem);
 	up_read(&nm_i->nat_tree_lock);
 }
 
 static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
-	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
-	struct f2fs_journal *journal = curseg->journal;
 	int i = 0;
 	nid_t nid = nm_i->next_scan_nid;
 
@@ -1967,7 +2016,7 @@ static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount)
 		nid = 0;
 
 	/* Enough entries */
-	if (nm_i->nid_cnt[FREE_NID_LIST] >= NAT_ENTRY_PER_BLOCK)
+	if (nm_i->nid_cnt[FREE_NID] >= NAT_ENTRY_PER_BLOCK)
 		return;
 
 	if (!sync && !available_free_memory(sbi, FREE_NIDS))
@@ -1977,7 +2026,7 @@ static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount)
 		/* try to find free nids in free_nid_bitmap */
 		scan_free_nid_bits(sbi);
 
-		if (nm_i->nid_cnt[FREE_NID_LIST])
+		if (nm_i->nid_cnt[FREE_NID] >= NAT_ENTRY_PER_BLOCK)
 			return;
 	}
 
@@ -2005,18 +2054,8 @@ static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount)
 	nm_i->next_scan_nid = nid;
 
 	/* find free nids from current sum_pages */
-	down_read(&curseg->journal_rwsem);
-	for (i = 0; i < nats_in_cursum(journal); i++) {
-		block_t addr;
+	scan_curseg_cache(sbi);
 
-		addr = le32_to_cpu(nat_in_journal(journal, i).block_addr);
-		nid = le32_to_cpu(nid_in_journal(journal, i));
-		if (addr == NULL_ADDR)
-			add_free_nid(sbi, nid, true);
-		else
-			remove_free_nid(sbi, nid);
-	}
-	up_read(&curseg->journal_rwsem);
 	up_read(&nm_i->nat_tree_lock);
 
 	ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid),
@@ -2054,15 +2093,13 @@ bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid)
 	}
 
 	/* We should not use stale free nids created by build_free_nids */
-	if (nm_i->nid_cnt[FREE_NID_LIST] && !on_build_free_nids(nm_i)) {
-		f2fs_bug_on(sbi, list_empty(&nm_i->nid_list[FREE_NID_LIST]));
-		i = list_first_entry(&nm_i->nid_list[FREE_NID_LIST],
+	if (nm_i->nid_cnt[FREE_NID] && !on_build_free_nids(nm_i)) {
+		f2fs_bug_on(sbi, list_empty(&nm_i->free_nid_list));
+		i = list_first_entry(&nm_i->free_nid_list,
 					struct free_nid, list);
 		*nid = i->nid;
 
-		__remove_nid_from_list(sbi, i, FREE_NID_LIST, true);
-		i->state = NID_ALLOC;
-		__insert_nid_to_list(sbi, i, ALLOC_NID_LIST, false);
+		__move_free_nid(sbi, i, FREE_NID, PREALLOC_NID);
 		nm_i->available_nids--;
 
 		update_free_nid_bitmap(sbi, *nid, false, false);
@@ -2088,7 +2125,7 @@ void alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid)
 	spin_lock(&nm_i->nid_list_lock);
 	i = __lookup_free_nid_list(nm_i, nid);
 	f2fs_bug_on(sbi, !i);
-	__remove_nid_from_list(sbi, i, ALLOC_NID_LIST, false);
+	__remove_free_nid(sbi, i, PREALLOC_NID);
 	spin_unlock(&nm_i->nid_list_lock);
 
 	kmem_cache_free(free_nid_slab, i);
@@ -2111,12 +2148,10 @@ void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid)
 	f2fs_bug_on(sbi, !i);
 
 	if (!available_free_memory(sbi, FREE_NIDS)) {
-		__remove_nid_from_list(sbi, i, ALLOC_NID_LIST, false);
+		__remove_free_nid(sbi, i, PREALLOC_NID);
 		need_free = true;
 	} else {
-		__remove_nid_from_list(sbi, i, ALLOC_NID_LIST, true);
-		i->state = NID_NEW;
-		__insert_nid_to_list(sbi, i, FREE_NID_LIST, false);
+		__move_free_nid(sbi, i, PREALLOC_NID, FREE_NID);
 	}
 
 	nm_i->available_nids++;
@@ -2135,20 +2170,19 @@ 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->nid_cnt[FREE_NID_LIST] <= MAX_FREE_NIDS)
+	if (nm_i->nid_cnt[FREE_NID] <= MAX_FREE_NIDS)
 		return 0;
 
 	if (!mutex_trylock(&nm_i->build_lock))
 		return 0;
 
 	spin_lock(&nm_i->nid_list_lock);
-	list_for_each_entry_safe(i, next, &nm_i->nid_list[FREE_NID_LIST],
-									list) {
+	list_for_each_entry_safe(i, next, &nm_i->free_nid_list, list) {
 		if (nr_shrink <= 0 ||
-				nm_i->nid_cnt[FREE_NID_LIST] <= MAX_FREE_NIDS)
+				nm_i->nid_cnt[FREE_NID] <= MAX_FREE_NIDS)
 			break;
 
-		__remove_nid_from_list(sbi, i, FREE_NID_LIST, false);
+		__remove_free_nid(sbi, i, FREE_NID);
 		kmem_cache_free(free_nid_slab, i);
 		nr_shrink--;
 	}
@@ -2174,8 +2208,8 @@ void recover_inline_xattr(struct inode *inode, struct page *page)
 		goto update_inode;
 	}
 
-	dst_addr = inline_xattr_addr(ipage);
-	src_addr = inline_xattr_addr(page);
+	dst_addr = inline_xattr_addr(inode, ipage);
+	src_addr = inline_xattr_addr(inode, page);
 	inline_size = inline_xattr_size(inode);
 
 	f2fs_wait_on_page_writeback(ipage, NODE, true);
@@ -2264,6 +2298,12 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
 	dst->i_inline = src->i_inline & (F2FS_INLINE_XATTR | F2FS_EXTRA_ATTR);
 	if (dst->i_inline & F2FS_EXTRA_ATTR) {
 		dst->i_extra_isize = src->i_extra_isize;
+
+		if (f2fs_sb_has_flexible_inline_xattr(sbi->sb) &&
+			F2FS_FITS_IN_INODE(src, le16_to_cpu(src->i_extra_isize),
+							i_inline_xattr_size))
+			dst->i_inline_xattr_size = src->i_inline_xattr_size;
+
 		if (f2fs_sb_has_project_quota(sbi->sb) &&
 			F2FS_FITS_IN_INODE(src, le16_to_cpu(src->i_extra_isize),
 								i_projid))
@@ -2335,8 +2375,8 @@ static void remove_nats_in_journal(struct f2fs_sb_info *sbi)
 
 		ne = __lookup_nat_cache(nm_i, nid);
 		if (!ne) {
-			ne = grab_nat_entry(nm_i, nid, true);
-			node_info_from_raw_nat(&ne->ni, &raw_ne);
+			ne = __alloc_nat_entry(nid, true);
+			__init_nat_entry(nm_i, ne, &raw_ne, true);
 		}
 
 		/*
@@ -2382,15 +2422,17 @@ static void __update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid,
 	unsigned int nat_index = start_nid / NAT_ENTRY_PER_BLOCK;
 	struct f2fs_nat_block *nat_blk = page_address(page);
 	int valid = 0;
-	int i;
+	int i = 0;
 
 	if (!enabled_nat_bits(sbi, NULL))
 		return;
 
-	for (i = 0; i < NAT_ENTRY_PER_BLOCK; i++) {
-		if (start_nid == 0 && i == 0)
-			valid++;
-		if (nat_blk->entries[i].block_addr)
+	if (nat_index == 0) {
+		valid = 1;
+		i = 1;
+	}
+	for (; i < NAT_ENTRY_PER_BLOCK; i++) {
+		if (nat_blk->entries[i].block_addr != NULL_ADDR)
 			valid++;
 	}
 	if (valid == 0) {
@@ -2585,7 +2627,7 @@ static inline void load_free_nid_bitmap(struct f2fs_sb_info *sbi)
 		__set_bit_le(i, nm_i->nat_block_bitmap);
 
 		nid = i * NAT_ENTRY_PER_BLOCK;
-		last_nid = (i + 1) * NAT_ENTRY_PER_BLOCK;
+		last_nid = nid + NAT_ENTRY_PER_BLOCK;
 
 		spin_lock(&NM_I(sbi)->nid_list_lock);
 		for (; nid < last_nid; nid++)
@@ -2620,16 +2662,15 @@ static int init_node_manager(struct f2fs_sb_info *sbi)
 	/* not used nids: 0, node, meta, (and root counted as valid node) */
 	nm_i->available_nids = nm_i->max_nid - sbi->total_valid_node_count -
 							F2FS_RESERVED_NODE_NUM;
-	nm_i->nid_cnt[FREE_NID_LIST] = 0;
-	nm_i->nid_cnt[ALLOC_NID_LIST] = 0;
+	nm_i->nid_cnt[FREE_NID] = 0;
+	nm_i->nid_cnt[PREALLOC_NID] = 0;
 	nm_i->nat_cnt = 0;
 	nm_i->ram_thresh = DEF_RAM_THRESHOLD;
 	nm_i->ra_nid_pages = DEF_RA_NID_PAGES;
 	nm_i->dirty_nats_ratio = DEF_DIRTY_NAT_RATIO_THRESHOLD;
 
 	INIT_RADIX_TREE(&nm_i->free_nid_root, GFP_ATOMIC);
-	INIT_LIST_HEAD(&nm_i->nid_list[FREE_NID_LIST]);
-	INIT_LIST_HEAD(&nm_i->nid_list[ALLOC_NID_LIST]);
+	INIT_LIST_HEAD(&nm_i->free_nid_list);
 	INIT_RADIX_TREE(&nm_i->nat_root, GFP_NOIO);
 	INIT_RADIX_TREE(&nm_i->nat_set_root, GFP_NOIO);
 	INIT_LIST_HEAD(&nm_i->nat_entries);
@@ -2721,16 +2762,15 @@ void destroy_node_manager(struct f2fs_sb_info *sbi)
 
 	/* destroy free nid list */
 	spin_lock(&nm_i->nid_list_lock);
-	list_for_each_entry_safe(i, next_i, &nm_i->nid_list[FREE_NID_LIST],
-									list) {
-		__remove_nid_from_list(sbi, i, FREE_NID_LIST, false);
+	list_for_each_entry_safe(i, next_i, &nm_i->free_nid_list, list) {
+		__remove_free_nid(sbi, i, FREE_NID);
 		spin_unlock(&nm_i->nid_list_lock);
 		kmem_cache_free(free_nid_slab, i);
 		spin_lock(&nm_i->nid_list_lock);
 	}
-	f2fs_bug_on(sbi, nm_i->nid_cnt[FREE_NID_LIST]);
-	f2fs_bug_on(sbi, nm_i->nid_cnt[ALLOC_NID_LIST]);
-	f2fs_bug_on(sbi, !list_empty(&nm_i->nid_list[ALLOC_NID_LIST]));
+	f2fs_bug_on(sbi, nm_i->nid_cnt[FREE_NID]);
+	f2fs_bug_on(sbi, nm_i->nid_cnt[PREALLOC_NID]);
+	f2fs_bug_on(sbi, !list_empty(&nm_i->free_nid_list));
 	spin_unlock(&nm_i->nid_list_lock);
 
 	/* destroy nat cache */

fs/f2fs/node.h

@@ -140,6 +140,7 @@ enum mem_type {
 	DIRTY_DENTS,	/* indicates dirty dentry pages */
 	INO_ENTRIES,	/* indicates inode entries */
 	EXTENT_CACHE,	/* indicates extent cache */
+	INMEM_PAGES,	/* indicates inmemory pages */
 	BASE_CHECK,	/* check kernel status */
 };
 
@@ -150,18 +151,10 @@ struct nat_entry_set {
 	unsigned int entry_cnt;		/* the # of nat entries in set */
 };
 
-/*
- * For free nid mangement
- */
-enum nid_state {
-	NID_NEW,	/* newly added to free nid list */
-	NID_ALLOC	/* it is allocated */
-};
-
 struct free_nid {
 	struct list_head list;	/* for free node id list */
 	nid_t nid;		/* node id */
-	int state;		/* in use or not: NID_NEW or NID_ALLOC */
+	int state;		/* in use or not: FREE_NID or PREALLOC_NID */
 };
 
 static inline void next_free_nid(struct f2fs_sb_info *sbi, nid_t *nid)
@@ -170,12 +163,11 @@ static inline void next_free_nid(struct f2fs_sb_info *sbi, nid_t *nid)
 	struct free_nid *fnid;
 
 	spin_lock(&nm_i->nid_list_lock);
-	if (nm_i->nid_cnt[FREE_NID_LIST] <= 0) {
+	if (nm_i->nid_cnt[FREE_NID] <= 0) {
 		spin_unlock(&nm_i->nid_list_lock);
 		return;
 	}
-	fnid = list_first_entry(&nm_i->nid_list[FREE_NID_LIST],
-						struct free_nid, list);
+	fnid = list_first_entry(&nm_i->free_nid_list, struct free_nid, list);
 	*nid = fnid->nid;
 	spin_unlock(&nm_i->nid_list_lock);
 }

fs/f2fs/recovery.c

@@ -594,6 +594,9 @@ int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
 	int ret = 0;
 	unsigned long s_flags = sbi->sb->s_flags;
 	bool need_writecp = false;
+#ifdef CONFIG_QUOTA
+	int quota_enabled;
+#endif
 
 	if (s_flags & MS_RDONLY) {
 		f2fs_msg(sbi->sb, KERN_INFO, "orphan cleanup on readonly fs");
@@ -604,7 +607,7 @@ int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
 	/* Needed for iput() to work correctly and not trash data */
 	sbi->sb->s_flags |= MS_ACTIVE;
 	/* Turn on quotas so that they are updated correctly */
-	f2fs_enable_quota_files(sbi);
+	quota_enabled = f2fs_enable_quota_files(sbi, s_flags & MS_RDONLY);
 #endif
 
 	fsync_entry_slab = f2fs_kmem_cache_create("f2fs_fsync_inode_entry",
@@ -665,6 +668,7 @@ int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
 out:
 #ifdef CONFIG_QUOTA
 	/* Turn quotas off */
+	if (quota_enabled)
 		f2fs_quota_off_umount(sbi->sb);
 #endif
 	sbi->sb->s_flags = s_flags; /* Restore MS_RDONLY status */

fs/f2fs/segment.c

@@ -181,11 +181,12 @@ bool need_SSR(struct f2fs_sb_info *sbi)
 		return true;
 
 	return free_sections(sbi) <= (node_secs + 2 * dent_secs + imeta_secs +
-						2 * reserved_sections(sbi));
+			SM_I(sbi)->min_ssr_sections + reserved_sections(sbi));
 }
 
 void register_inmem_page(struct inode *inode, struct page *page)
 {
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct f2fs_inode_info *fi = F2FS_I(inode);
 	struct inmem_pages *new;
 
@@ -204,6 +205,10 @@ void register_inmem_page(struct inode *inode, struct page *page)
 	mutex_lock(&fi->inmem_lock);
 	get_page(page);
 	list_add_tail(&new->list, &fi->inmem_pages);
+	spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
+	if (list_empty(&fi->inmem_ilist))
+		list_add_tail(&fi->inmem_ilist, &sbi->inode_list[ATOMIC_FILE]);
+	spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
 	inc_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES);
 	mutex_unlock(&fi->inmem_lock);
 
@@ -262,12 +267,41 @@ static int __revoke_inmem_pages(struct inode *inode,
 	return err;
 }
 
+void drop_inmem_pages_all(struct f2fs_sb_info *sbi)
+{
+	struct list_head *head = &sbi->inode_list[ATOMIC_FILE];
+	struct inode *inode;
+	struct f2fs_inode_info *fi;
+next:
+	spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
+	if (list_empty(head)) {
+		spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
+		return;
+	}
+	fi = list_first_entry(head, struct f2fs_inode_info, inmem_ilist);
+	inode = igrab(&fi->vfs_inode);
+	spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
+
+	if (inode) {
+		drop_inmem_pages(inode);
+		iput(inode);
+	}
+	congestion_wait(BLK_RW_ASYNC, HZ/50);
+	cond_resched();
+	goto next;
+}
+
 void drop_inmem_pages(struct inode *inode)
 {
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct f2fs_inode_info *fi = F2FS_I(inode);
 
 	mutex_lock(&fi->inmem_lock);
 	__revoke_inmem_pages(inode, &fi->inmem_pages, true, false);
+	spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
+	if (!list_empty(&fi->inmem_ilist))
+		list_del_init(&fi->inmem_ilist);
+	spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
 	mutex_unlock(&fi->inmem_lock);
 
 	clear_inode_flag(inode, FI_ATOMIC_FILE);
@@ -313,6 +347,7 @@ static int __commit_inmem_pages(struct inode *inode,
 	struct inmem_pages *cur, *tmp;
 	struct f2fs_io_info fio = {
 		.sbi = sbi,
+		.ino = inode->i_ino,
 		.type = DATA,
 		.op = REQ_OP_WRITE,
 		.op_flags = REQ_SYNC | REQ_PRIO,
@@ -398,6 +433,10 @@ int commit_inmem_pages(struct inode *inode)
 		/* drop all uncommitted pages */
 		__revoke_inmem_pages(inode, &fi->inmem_pages, true, false);
 	}
+	spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
+	if (!list_empty(&fi->inmem_ilist))
+		list_del_init(&fi->inmem_ilist);
+	spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
 	mutex_unlock(&fi->inmem_lock);
 
 	clear_inode_flag(inode, FI_ATOMIC_COMMIT);
@@ -472,7 +511,7 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
 static int __submit_flush_wait(struct f2fs_sb_info *sbi,
 				struct block_device *bdev)
 {
-	struct bio *bio = f2fs_bio_alloc(0);
+	struct bio *bio = f2fs_bio_alloc(sbi, 0, true);
 	int ret;
 
 	bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH;
@@ -485,15 +524,17 @@ static int __submit_flush_wait(struct f2fs_sb_info *sbi,
 	return ret;
 }
 
-static int submit_flush_wait(struct f2fs_sb_info *sbi)
+static int submit_flush_wait(struct f2fs_sb_info *sbi, nid_t ino)
 {
-	int ret = __submit_flush_wait(sbi, sbi->sb->s_bdev);
+	int ret = 0;
 	int i;
 
-	if (!sbi->s_ndevs || ret)
-		return ret;
+	if (!sbi->s_ndevs)
+		return __submit_flush_wait(sbi, sbi->sb->s_bdev);
 
-	for (i = 1; i < sbi->s_ndevs; i++) {
+	for (i = 0; i < sbi->s_ndevs; i++) {
+		if (!is_dirty_device(sbi, ino, i, FLUSH_INO))
+			continue;
 		ret = __submit_flush_wait(sbi, FDEV(i).bdev);
 		if (ret)
 			break;
@@ -519,7 +560,9 @@ static int issue_flush_thread(void *data)
 		fcc->dispatch_list = llist_del_all(&fcc->issue_list);
 		fcc->dispatch_list = llist_reverse_order(fcc->dispatch_list);
 
-		ret = submit_flush_wait(sbi);
+		cmd = llist_entry(fcc->dispatch_list, struct flush_cmd, llnode);
+
+		ret = submit_flush_wait(sbi, cmd->ino);
 		atomic_inc(&fcc->issued_flush);
 
 		llist_for_each_entry_safe(cmd, next,
@@ -537,7 +580,7 @@ static int issue_flush_thread(void *data)
 	goto repeat;
 }
 
-int f2fs_issue_flush(struct f2fs_sb_info *sbi)
+int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino)
 {
 	struct flush_cmd_control *fcc = SM_I(sbi)->fcc_info;
 	struct flush_cmd cmd;
@@ -547,19 +590,20 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi)
 		return 0;
 
 	if (!test_opt(sbi, FLUSH_MERGE)) {
-		ret = submit_flush_wait(sbi);
+		ret = submit_flush_wait(sbi, ino);
 		atomic_inc(&fcc->issued_flush);
 		return ret;
 	}
 
-	if (atomic_inc_return(&fcc->issing_flush) == 1) {
-		ret = submit_flush_wait(sbi);
+	if (atomic_inc_return(&fcc->issing_flush) == 1 || sbi->s_ndevs > 1) {
+		ret = submit_flush_wait(sbi, ino);
 		atomic_dec(&fcc->issing_flush);
 
 		atomic_inc(&fcc->issued_flush);
 		return ret;
 	}
 
+	cmd.ino = ino;
 	init_completion(&cmd.wait);
 
 	llist_add(&cmd.llnode, &fcc->issue_list);
@@ -583,7 +627,7 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi)
 		} else {
 			struct flush_cmd *tmp, *next;
 
-			ret = submit_flush_wait(sbi);
+			ret = submit_flush_wait(sbi, ino);
 
 			llist_for_each_entry_safe(tmp, next, list, llnode) {
 				if (tmp == &cmd) {
@@ -653,6 +697,28 @@ void destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free)
 	}
 }
 
+int f2fs_flush_device_cache(struct f2fs_sb_info *sbi)
+{
+	int ret = 0, i;
+
+	if (!sbi->s_ndevs)
+		return 0;
+
+	for (i = 1; i < sbi->s_ndevs; i++) {
+		if (!f2fs_test_bit(i, (char *)&sbi->dirty_device))
+			continue;
+		ret = __submit_flush_wait(sbi, FDEV(i).bdev);
+		if (ret)
+			break;
+
+		spin_lock(&sbi->dev_lock);
+		f2fs_clear_bit(i, (char *)&sbi->dirty_device);
+		spin_unlock(&sbi->dev_lock);
+	}
+
+	return ret;
+}
+
 static void __locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
 		enum dirty_type dirty_type)
 {
@@ -794,6 +860,8 @@ static void __remove_discard_cmd(struct f2fs_sb_info *sbi,
 {
 	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
 
+	trace_f2fs_remove_discard(dc->bdev, dc->start, dc->len);
+
 	f2fs_bug_on(sbi, dc->ref);
 
 	if (dc->error == -EOPNOTSUPP)
@@ -845,10 +913,14 @@ void __check_sit_bitmap(struct f2fs_sb_info *sbi,
 
 /* this function is copied from blkdev_issue_discard from block/blk-lib.c */
 static void __submit_discard_cmd(struct f2fs_sb_info *sbi,
+						struct discard_policy *dpolicy,
 						struct discard_cmd *dc)
 {
 	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+	struct list_head *wait_list = (dpolicy->type == DPOLICY_FSTRIM) ?
+					&(dcc->fstrim_list) : &(dcc->wait_list);
 	struct bio *bio = NULL;
+	int flag = dpolicy->sync ? REQ_SYNC : 0;
 
 	if (dc->state != D_PREP)
 		return;
@@ -867,9 +939,9 @@ static void __submit_discard_cmd(struct f2fs_sb_info *sbi,
 		if (bio) {
 			bio->bi_private = dc;
 			bio->bi_end_io = f2fs_submit_discard_endio;
-			bio->bi_opf |= REQ_SYNC;
+			bio->bi_opf |= flag;
 			submit_bio(bio);
-			list_move_tail(&dc->list, &dcc->wait_list);
+			list_move_tail(&dc->list, wait_list);
 			__check_sit_bitmap(sbi, dc->start, dc->start + dc->len);
 
 			f2fs_update_iostat(sbi, FS_DISCARD, 1);
@@ -886,7 +958,7 @@ static struct discard_cmd *__insert_discard_tree(struct f2fs_sb_info *sbi,
 				struct rb_node *insert_parent)
 {
 	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
-	struct rb_node **p = &dcc->root.rb_node;
+	struct rb_node **p;
 	struct rb_node *parent = NULL;
 	struct discard_cmd *dc = NULL;
 
@@ -1054,71 +1126,121 @@ static int __queue_discard_cmd(struct f2fs_sb_info *sbi,
 	return 0;
 }
 
-static int __issue_discard_cmd(struct f2fs_sb_info *sbi, bool issue_cond)
+static void __issue_discard_cmd_range(struct f2fs_sb_info *sbi,
+					struct discard_policy *dpolicy,
+					unsigned int start, unsigned int end)
 {
 	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
-	struct list_head *pend_list;
-	struct discard_cmd *dc, *tmp;
+	struct discard_cmd *prev_dc = NULL, *next_dc = NULL;
+	struct rb_node **insert_p = NULL, *insert_parent = NULL;
+	struct discard_cmd *dc;
 	struct blk_plug plug;
-	int iter = 0, issued = 0;
-	int i;
-	bool io_interrupted = false;
+	int issued;
+
+next:
+	issued = 0;
 
 	mutex_lock(&dcc->cmd_lock);
-	f2fs_bug_on(sbi,
-		!__check_rb_tree_consistence(sbi, &dcc->root));
+	f2fs_bug_on(sbi, !__check_rb_tree_consistence(sbi, &dcc->root));
+
+	dc = (struct discard_cmd *)__lookup_rb_tree_ret(&dcc->root,
+					NULL, start,
+					(struct rb_entry **)&prev_dc,
+					(struct rb_entry **)&next_dc,
+					&insert_p, &insert_parent, true);
+	if (!dc)
+		dc = next_dc;
+
 	blk_start_plug(&plug);
-	for (i = MAX_PLIST_NUM - 1;
-			i >= 0 && plist_issue(dcc->pend_list_tag[i]); i--) {
-		pend_list = &dcc->pend_list[i];
-		list_for_each_entry_safe(dc, tmp, pend_list, list) {
-			f2fs_bug_on(sbi, dc->state != D_PREP);
 
-			/* Hurry up to finish fstrim */
-			if (dcc->pend_list_tag[i] & P_TRIM) {
-				__submit_discard_cmd(sbi, dc);
-				issued++;
+	while (dc && dc->lstart <= end) {
+		struct rb_node *node;
+
+		if (dc->len < dpolicy->granularity)
+			goto skip;
+
+		if (dc->state != D_PREP) {
+			list_move_tail(&dc->list, &dcc->fstrim_list);
+			goto skip;
+		}
+
+		__submit_discard_cmd(sbi, dpolicy, dc);
+
+		if (++issued >= dpolicy->max_requests) {
+			start = dc->lstart + dc->len;
+
+			blk_finish_plug(&plug);
+			mutex_unlock(&dcc->cmd_lock);
+
+			schedule();
+
+			goto next;
+		}
+skip:
+		node = rb_next(&dc->rb_node);
+		dc = rb_entry_safe(node, struct discard_cmd, rb_node);
 
 		if (fatal_signal_pending(current))
 			break;
-				continue;
 	}
 
-			if (!issue_cond) {
-				__submit_discard_cmd(sbi, dc);
-				issued++;
-				continue;
-			}
+	blk_finish_plug(&plug);
+	mutex_unlock(&dcc->cmd_lock);
+}
 
-			if (is_idle(sbi)) {
-				__submit_discard_cmd(sbi, dc);
-				issued++;
-			} else {
+static int __issue_discard_cmd(struct f2fs_sb_info *sbi,
+					struct discard_policy *dpolicy)
+{
+	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+	struct list_head *pend_list;
+	struct discard_cmd *dc, *tmp;
+	struct blk_plug plug;
+	int i, iter = 0, issued = 0;
+	bool io_interrupted = false;
+
+	for (i = MAX_PLIST_NUM - 1; i >= 0; i--) {
+		if (i + 1 < dpolicy->granularity)
+			break;
+		pend_list = &dcc->pend_list[i];
+
+		mutex_lock(&dcc->cmd_lock);
+		f2fs_bug_on(sbi, !__check_rb_tree_consistence(sbi, &dcc->root));
+		blk_start_plug(&plug);
+		list_for_each_entry_safe(dc, tmp, pend_list, list) {
+			f2fs_bug_on(sbi, dc->state != D_PREP);
+
+			if (dpolicy->io_aware && i < dpolicy->io_aware_gran &&
+								!is_idle(sbi)) {
 				io_interrupted = true;
+				goto skip;
 			}
 
-			if (++iter >= DISCARD_ISSUE_RATE)
-				goto out;
-		}
-		if (list_empty(pend_list) && dcc->pend_list_tag[i] & P_TRIM)
-			dcc->pend_list_tag[i] &= (~P_TRIM);
+			__submit_discard_cmd(sbi, dpolicy, dc);
+			issued++;
+skip:
+			if (++iter >= dpolicy->max_requests)
+				break;
 		}
-out:
 		blk_finish_plug(&plug);
 		mutex_unlock(&dcc->cmd_lock);
 
+		if (iter >= dpolicy->max_requests)
+			break;
+	}
+
 	if (!issued && io_interrupted)
 		issued = -1;
 
 	return issued;
 }
 
-static void __drop_discard_cmd(struct f2fs_sb_info *sbi)
+static bool __drop_discard_cmd(struct f2fs_sb_info *sbi)
 {
 	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
 	struct list_head *pend_list;
 	struct discard_cmd *dc, *tmp;
 	int i;
+	bool dropped = false;
 
 	mutex_lock(&dcc->cmd_lock);
 	for (i = MAX_PLIST_NUM - 1; i >= 0; i--) {
@@ -1126,39 +1248,58 @@ static void __drop_discard_cmd(struct f2fs_sb_info *sbi)
 		list_for_each_entry_safe(dc, tmp, pend_list, list) {
 			f2fs_bug_on(sbi, dc->state != D_PREP);
 			__remove_discard_cmd(sbi, dc);
+			dropped = true;
 		}
 	}
 	mutex_unlock(&dcc->cmd_lock);
+
+	return dropped;
 }
 
-static void __wait_one_discard_bio(struct f2fs_sb_info *sbi,
+static unsigned int __wait_one_discard_bio(struct f2fs_sb_info *sbi,
 							struct discard_cmd *dc)
 {
 	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+	unsigned int len = 0;
 
 	wait_for_completion_io(&dc->wait);
 	mutex_lock(&dcc->cmd_lock);
 	f2fs_bug_on(sbi, dc->state != D_DONE);
 	dc->ref--;
-	if (!dc->ref)
+	if (!dc->ref) {
+		if (!dc->error)
+			len = dc->len;
 		__remove_discard_cmd(sbi, dc);
+	}
 	mutex_unlock(&dcc->cmd_lock);
+
+	return len;
 }
 
-static void __wait_discard_cmd(struct f2fs_sb_info *sbi, bool wait_cond)
+static unsigned int __wait_discard_cmd_range(struct f2fs_sb_info *sbi,
+						struct discard_policy *dpolicy,
+						block_t start, block_t end)
 {
 	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
-	struct list_head *wait_list = &(dcc->wait_list);
+	struct list_head *wait_list = (dpolicy->type == DPOLICY_FSTRIM) ?
+					&(dcc->fstrim_list) : &(dcc->wait_list);
 	struct discard_cmd *dc, *tmp;
 	bool need_wait;
+	unsigned int trimmed = 0;
 
 next:
 	need_wait = false;
 
 	mutex_lock(&dcc->cmd_lock);
 	list_for_each_entry_safe(dc, tmp, wait_list, list) {
-		if (!wait_cond || (dc->state == D_DONE && !dc->ref)) {
+		if (dc->lstart + dc->len <= start || end <= dc->lstart)
+			continue;
+		if (dc->len < dpolicy->granularity)
+			continue;
+		if (dc->state == D_DONE && !dc->ref) {
 			wait_for_completion_io(&dc->wait);
+			if (!dc->error)
+				trimmed += dc->len;
 			__remove_discard_cmd(sbi, dc);
 		} else {
 			dc->ref++;
@@ -1169,9 +1310,17 @@ static void __wait_discard_cmd(struct f2fs_sb_info *sbi, bool wait_cond)
 	mutex_unlock(&dcc->cmd_lock);
 
 	if (need_wait) {
-		__wait_one_discard_bio(sbi, dc);
+		trimmed += __wait_one_discard_bio(sbi, dc);
 		goto next;
 	}
+
+	return trimmed;
+}
+
+static void __wait_all_discard_cmd(struct f2fs_sb_info *sbi,
+						struct discard_policy *dpolicy)
+{
+	__wait_discard_cmd_range(sbi, dpolicy, 0, UINT_MAX);
 }
 
 /* This should be covered by global mutex, &sit_i->sentry_lock */
@@ -1209,23 +1358,19 @@ void stop_discard_thread(struct f2fs_sb_info *sbi)
 	}
 }
 
-/* This comes from f2fs_put_super and f2fs_trim_fs */
-void f2fs_wait_discard_bios(struct f2fs_sb_info *sbi, bool umount)
-{
-	__issue_discard_cmd(sbi, false);
-	__drop_discard_cmd(sbi);
-	__wait_discard_cmd(sbi, !umount);
-}
-
-static void mark_discard_range_all(struct f2fs_sb_info *sbi)
+/* This comes from f2fs_put_super */
+bool f2fs_wait_discard_bios(struct f2fs_sb_info *sbi)
 {
 	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
-	int i;
+	struct discard_policy dpolicy;
+	bool dropped;
 
-	mutex_lock(&dcc->cmd_lock);
-	for (i = 0; i < MAX_PLIST_NUM; i++)
-		dcc->pend_list_tag[i] |= P_TRIM;
-	mutex_unlock(&dcc->cmd_lock);
+	init_discard_policy(&dpolicy, DPOLICY_UMOUNT, dcc->discard_granularity);
+	__issue_discard_cmd(sbi, &dpolicy);
+	dropped = __drop_discard_cmd(sbi);
+	__wait_all_discard_cmd(sbi, &dpolicy);
+
+	return dropped;
 }
 
 static int issue_discard_thread(void *data)
@@ -1233,12 +1378,16 @@ static int issue_discard_thread(void *data)
 	struct f2fs_sb_info *sbi = data;
 	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
 	wait_queue_head_t *q = &dcc->discard_wait_queue;
+	struct discard_policy dpolicy;
 	unsigned int wait_ms = DEF_MIN_DISCARD_ISSUE_TIME;
 	int issued;
 
 	set_freezable();
 
 	do {
+		init_discard_policy(&dpolicy, DPOLICY_BG,
+					dcc->discard_granularity);
+
 		wait_event_interruptible_timeout(*q,
 				kthread_should_stop() || freezing(current) ||
 				dcc->discard_wake,
@@ -1251,17 +1400,18 @@ static int issue_discard_thread(void *data)
 		if (dcc->discard_wake) {
 			dcc->discard_wake = 0;
 			if (sbi->gc_thread && sbi->gc_thread->gc_urgent)
-				mark_discard_range_all(sbi);
+				init_discard_policy(&dpolicy,
+							DPOLICY_FORCE, 1);
 		}
 
 		sb_start_intwrite(sbi->sb);
 
-		issued = __issue_discard_cmd(sbi, true);
+		issued = __issue_discard_cmd(sbi, &dpolicy);
 		if (issued) {
-			__wait_discard_cmd(sbi, true);
-			wait_ms = DEF_MIN_DISCARD_ISSUE_TIME;
+			__wait_all_discard_cmd(sbi, &dpolicy);
+			wait_ms = dpolicy.min_interval;
 		} else {
-			wait_ms = DEF_MAX_DISCARD_ISSUE_TIME;
+			wait_ms = dpolicy.max_interval;
 		}
 
 		sb_end_intwrite(sbi->sb);
@@ -1525,7 +1675,6 @@ void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 			f2fs_issue_discard(sbi, entry->start_blkaddr + cur_pos,
 									len);
-			cpc->trimmed += len;
 			total_len += len;
 		} else {
 			next_pos = find_next_bit_le(entry->discard_map,
@@ -1546,6 +1695,37 @@ void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	wake_up_discard_thread(sbi, false);
 }
 
+void init_discard_policy(struct discard_policy *dpolicy,
+				int discard_type, unsigned int granularity)
+{
+	/* common policy */
+	dpolicy->type = discard_type;
+	dpolicy->sync = true;
+	dpolicy->granularity = granularity;
+
+	if (discard_type == DPOLICY_BG) {
+		dpolicy->min_interval = DEF_MIN_DISCARD_ISSUE_TIME;
+		dpolicy->max_interval = DEF_MAX_DISCARD_ISSUE_TIME;
+		dpolicy->max_requests = DEF_MAX_DISCARD_REQUEST;
+		dpolicy->io_aware_gran = MAX_PLIST_NUM;
+		dpolicy->io_aware = true;
+	} else if (discard_type == DPOLICY_FORCE) {
+		dpolicy->min_interval = DEF_MIN_DISCARD_ISSUE_TIME;
+		dpolicy->max_interval = DEF_MAX_DISCARD_ISSUE_TIME;
+		dpolicy->max_requests = DEF_MAX_DISCARD_REQUEST;
+		dpolicy->io_aware_gran = MAX_PLIST_NUM;
+		dpolicy->io_aware = true;
+	} else if (discard_type == DPOLICY_FSTRIM) {
+		dpolicy->max_requests = DEF_MAX_DISCARD_REQUEST;
+		dpolicy->io_aware_gran = MAX_PLIST_NUM;
+		dpolicy->io_aware = false;
+	} else if (discard_type == DPOLICY_UMOUNT) {
+		dpolicy->max_requests = DEF_MAX_DISCARD_REQUEST;
+		dpolicy->io_aware_gran = MAX_PLIST_NUM;
+		dpolicy->io_aware = false;
+	}
+}
+
 static int create_discard_cmd_control(struct f2fs_sb_info *sbi)
 {
 	dev_t dev = sbi->sb->s_bdev->bd_dev;
@@ -1563,12 +1743,10 @@ static int create_discard_cmd_control(struct f2fs_sb_info *sbi)
 
 	dcc->discard_granularity = DEFAULT_DISCARD_GRANULARITY;
 	INIT_LIST_HEAD(&dcc->entry_list);
-	for (i = 0; i < MAX_PLIST_NUM; i++) {
+	for (i = 0; i < MAX_PLIST_NUM; i++)
 		INIT_LIST_HEAD(&dcc->pend_list[i]);
-		if (i >= dcc->discard_granularity - 1)
-			dcc->pend_list_tag[i] |= P_ACTIVE;
-	}
 	INIT_LIST_HEAD(&dcc->wait_list);
+	INIT_LIST_HEAD(&dcc->fstrim_list);
 	mutex_init(&dcc->cmd_lock);
 	atomic_set(&dcc->issued_discard, 0);
 	atomic_set(&dcc->issing_discard, 0);
@@ -1716,16 +1894,6 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
 		get_sec_entry(sbi, segno)->valid_blocks += del;
 }
 
-void refresh_sit_entry(struct f2fs_sb_info *sbi, block_t old, block_t new)
-{
-	update_sit_entry(sbi, new, 1);
-	if (GET_SEGNO(sbi, old) != NULL_SEGNO)
-		update_sit_entry(sbi, old, -1);
-
-	locate_dirty_segment(sbi, GET_SEGNO(sbi, old));
-	locate_dirty_segment(sbi, GET_SEGNO(sbi, new));
-}
-
 void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr)
 {
 	unsigned int segno = GET_SEGNO(sbi, addr);
@@ -1736,14 +1904,14 @@ void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr)
 		return;
 
 	/* add it into sit main buffer */
-	mutex_lock(&sit_i->sentry_lock);
+	down_write(&sit_i->sentry_lock);
 
 	update_sit_entry(sbi, addr, -1);
 
 	/* add it into dirty seglist */
 	locate_dirty_segment(sbi, segno);
 
-	mutex_unlock(&sit_i->sentry_lock);
+	up_write(&sit_i->sentry_lock);
 }
 
 bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr)
@@ -1756,7 +1924,7 @@ bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr)
 	if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR)
 		return true;
 
-	mutex_lock(&sit_i->sentry_lock);
+	down_read(&sit_i->sentry_lock);
 
 	segno = GET_SEGNO(sbi, blkaddr);
 	se = get_seg_entry(sbi, segno);
@@ -1765,7 +1933,7 @@ bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr)
 	if (f2fs_test_bit(offset, se->ckpt_valid_map))
 		is_cp = true;
 
-	mutex_unlock(&sit_i->sentry_lock);
+	up_read(&sit_i->sentry_lock);
 
 	return is_cp;
 }
@@ -1823,12 +1991,8 @@ struct page *get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno)
 void update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr)
 {
 	struct page *page = grab_meta_page(sbi, blk_addr);
-	void *dst = page_address(page);
 
-	if (src)
-		memcpy(dst, src, PAGE_SIZE);
-	else
-		memset(dst, 0, PAGE_SIZE);
+	memcpy(page_address(page), src, PAGE_SIZE);
 	set_page_dirty(page);
 	f2fs_put_page(page, 1);
 }
@@ -1927,7 +2091,6 @@ static void get_new_segment(struct f2fs_sb_info *sbi,
 	}
 	secno = left_start;
 skip_left:
-	hint = secno;
 	segno = GET_SEG_FROM_SEC(sbi, secno);
 	zoneno = GET_ZONE_FROM_SEC(sbi, secno);
 
@@ -2162,12 +2325,16 @@ void allocate_new_segments(struct f2fs_sb_info *sbi)
 	unsigned int old_segno;
 	int i;
 
+	down_write(&SIT_I(sbi)->sentry_lock);
+
 	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
 		curseg = CURSEG_I(sbi, i);
 		old_segno = curseg->segno;
 		SIT_I(sbi)->s_ops->allocate_segment(sbi, i, true);
 		locate_dirty_segment(sbi, old_segno);
 	}
+
+	up_write(&SIT_I(sbi)->sentry_lock);
 }
 
 static const struct segment_allocation default_salloc_ops = {
@@ -2179,14 +2346,14 @@ bool exist_trim_candidates(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	__u64 trim_start = cpc->trim_start;
 	bool has_candidate = false;
 
-	mutex_lock(&SIT_I(sbi)->sentry_lock);
+	down_write(&SIT_I(sbi)->sentry_lock);
 	for (; cpc->trim_start <= cpc->trim_end; cpc->trim_start++) {
 		if (add_discard_addrs(sbi, cpc, true)) {
 			has_candidate = true;
 			break;
 		}
 	}
-	mutex_unlock(&SIT_I(sbi)->sentry_lock);
+	up_write(&SIT_I(sbi)->sentry_lock);
 
 	cpc->trim_start = trim_start;
 	return has_candidate;
@@ -2196,14 +2363,16 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 {
 	__u64 start = F2FS_BYTES_TO_BLK(range->start);
 	__u64 end = start + F2FS_BYTES_TO_BLK(range->len) - 1;
-	unsigned int start_segno, end_segno;
+	unsigned int start_segno, end_segno, cur_segno;
+	block_t start_block, end_block;
 	struct cp_control cpc;
+	struct discard_policy dpolicy;
+	unsigned long long trimmed = 0;
 	int err = 0;
 
 	if (start >= MAX_BLKADDR(sbi) || range->len < sbi->blocksize)
 		return -EINVAL;
 
-	cpc.trimmed = 0;
 	if (end <= MAIN_BLKADDR(sbi))
 		goto out;
 
@@ -2217,12 +2386,14 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 	start_segno = (start <= MAIN_BLKADDR(sbi)) ? 0 : GET_SEGNO(sbi, start);
 	end_segno = (end >= MAX_BLKADDR(sbi)) ? MAIN_SEGS(sbi) - 1 :
 						GET_SEGNO(sbi, end);
+
 	cpc.reason = CP_DISCARD;
 	cpc.trim_minlen = max_t(__u64, 1, F2FS_BYTES_TO_BLK(range->minlen));
 
 	/* do checkpoint to issue discard commands safely */
-	for (; start_segno <= end_segno; start_segno = cpc.trim_end + 1) {
-		cpc.trim_start = start_segno;
+	for (cur_segno = start_segno; cur_segno <= end_segno;
+					cur_segno = cpc.trim_end + 1) {
+		cpc.trim_start = cur_segno;
 
 		if (sbi->discard_blks == 0)
 			break;
@@ -2230,7 +2401,7 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 			cpc.trim_end = end_segno;
 		else
 			cpc.trim_end = min_t(unsigned int,
-				rounddown(start_segno +
+				rounddown(cur_segno +
 				BATCHED_TRIM_SEGMENTS(sbi),
 				sbi->segs_per_sec) - 1, end_segno);
 
@@ -2242,11 +2413,16 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 
 		schedule();
 	}
-	/* It's time to issue all the filed discards */
-	mark_discard_range_all(sbi);
-	f2fs_wait_discard_bios(sbi, false);
+
+	start_block = START_BLOCK(sbi, start_segno);
+	end_block = START_BLOCK(sbi, min(cur_segno, end_segno) + 1);
+
+	init_discard_policy(&dpolicy, DPOLICY_FSTRIM, cpc.trim_minlen);
+	__issue_discard_cmd_range(sbi, &dpolicy, start_block, end_block);
+	trimmed = __wait_discard_cmd_range(sbi, &dpolicy,
+					start_block, end_block);
 out:
-	range->len = F2FS_BLK_TO_BYTES(cpc.trimmed);
+	range->len = F2FS_BLK_TO_BYTES(trimmed);
 	return err;
 }
 
@@ -2258,6 +2434,18 @@ static bool __has_curseg_space(struct f2fs_sb_info *sbi, int type)
 	return false;
 }
 
+int rw_hint_to_seg_type(enum rw_hint hint)
+{
+	switch (hint) {
+	case WRITE_LIFE_SHORT:
+		return CURSEG_HOT_DATA;
+	case WRITE_LIFE_EXTREME:
+		return CURSEG_COLD_DATA;
+	default:
+		return CURSEG_WARM_DATA;
+	}
+}
+
 static int __get_segment_type_2(struct f2fs_io_info *fio)
 {
 	if (fio->type == DATA)
@@ -2292,7 +2480,7 @@ static int __get_segment_type_6(struct f2fs_io_info *fio)
 			return CURSEG_COLD_DATA;
 		if (is_inode_flag_set(inode, FI_HOT_DATA))
 			return CURSEG_HOT_DATA;
-		return CURSEG_WARM_DATA;
+		return rw_hint_to_seg_type(inode->i_write_hint);
 	} else {
 		if (IS_DNODE(fio->page))
 			return is_cold_node(fio->page) ? CURSEG_WARM_NODE :
@@ -2336,8 +2524,10 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 	struct sit_info *sit_i = SIT_I(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, type);
 
+	down_read(&SM_I(sbi)->curseg_lock);
+
 	mutex_lock(&curseg->curseg_mutex);
-	mutex_lock(&sit_i->sentry_lock);
+	down_write(&sit_i->sentry_lock);
 
 	*new_blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
 
@@ -2354,15 +2544,26 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 
 	stat_inc_block_count(sbi, curseg);
 
+	/*
+	 * SIT information should be updated before segment allocation,
+	 * since SSR needs latest valid block information.
+	 */
+	update_sit_entry(sbi, *new_blkaddr, 1);
+	if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO)
+		update_sit_entry(sbi, old_blkaddr, -1);
+
 	if (!__has_curseg_space(sbi, type))
 		sit_i->s_ops->allocate_segment(sbi, type, false);
+
 	/*
-	 * SIT information should be updated after segment allocation,
-	 * since we need to keep dirty segments precisely under SSR.
+	 * segment dirty status should be updated after segment allocation,
+	 * so we just need to update status only one time after previous
+	 * segment being closed.
 	 */
-	refresh_sit_entry(sbi, old_blkaddr, *new_blkaddr);
+	locate_dirty_segment(sbi, GET_SEGNO(sbi, old_blkaddr));
+	locate_dirty_segment(sbi, GET_SEGNO(sbi, *new_blkaddr));
 
-	mutex_unlock(&sit_i->sentry_lock);
+	up_write(&sit_i->sentry_lock);
 
 	if (page && IS_NODESEG(type)) {
 		fill_node_footer_blkaddr(page, NEXT_FREE_BLKADDR(sbi, curseg));
@@ -2382,6 +2583,29 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 	}
 
 	mutex_unlock(&curseg->curseg_mutex);
+
+	up_read(&SM_I(sbi)->curseg_lock);
+}
+
+static void update_device_state(struct f2fs_io_info *fio)
+{
+	struct f2fs_sb_info *sbi = fio->sbi;
+	unsigned int devidx;
+
+	if (!sbi->s_ndevs)
+		return;
+
+	devidx = f2fs_target_device_index(sbi, fio->new_blkaddr);
+
+	/* update device state for fsync */
+	set_dirty_device(sbi, fio->ino, devidx, FLUSH_INO);
+
+	/* update device state for checkpoint */
+	if (!f2fs_test_bit(devidx, (char *)&sbi->dirty_device)) {
+		spin_lock(&sbi->dev_lock);
+		f2fs_set_bit(devidx, (char *)&sbi->dirty_device);
+		spin_unlock(&sbi->dev_lock);
+	}
 }
 
 static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio)
@@ -2398,6 +2622,8 @@ static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio)
 	if (err == -EAGAIN) {
 		fio->old_blkaddr = fio->new_blkaddr;
 		goto reallocate;
+	} else if (!err) {
+		update_device_state(fio);
 	}
 }
 
@@ -2458,12 +2684,26 @@ int rewrite_data_page(struct f2fs_io_info *fio)
 	stat_inc_inplace_blocks(fio->sbi);
 
 	err = f2fs_submit_page_bio(fio);
+	if (!err)
+		update_device_state(fio);
 
 	f2fs_update_iostat(fio->sbi, fio->io_type, F2FS_BLKSIZE);
 
 	return err;
 }
 
+static inline int __f2fs_get_curseg(struct f2fs_sb_info *sbi,
+						unsigned int segno)
+{
+	int i;
+
+	for (i = CURSEG_HOT_DATA; i < NO_CHECK_TYPE; i++) {
+		if (CURSEG_I(sbi, i)->segno == segno)
+			break;
+	}
+	return i;
+}
+
 void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 				block_t old_blkaddr, block_t new_blkaddr,
 				bool recover_curseg, bool recover_newaddr)
@@ -2479,6 +2719,8 @@ void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 	se = get_seg_entry(sbi, segno);
 	type = se->type;
 
+	down_write(&SM_I(sbi)->curseg_lock);
+
 	if (!recover_curseg) {
 		/* for recovery flow */
 		if (se->valid_blocks == 0 && !IS_CURSEG(sbi, segno)) {
@@ -2488,14 +2730,19 @@ void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 				type = CURSEG_WARM_DATA;
 		}
 	} else {
-		if (!IS_CURSEG(sbi, segno))
+		if (IS_CURSEG(sbi, segno)) {
+			/* se->type is volatile as SSR allocation */
+			type = __f2fs_get_curseg(sbi, segno);
+			f2fs_bug_on(sbi, type == NO_CHECK_TYPE);
+		} else {
 			type = CURSEG_WARM_DATA;
 		}
+	}
 
 	curseg = CURSEG_I(sbi, type);
 
 	mutex_lock(&curseg->curseg_mutex);
-	mutex_lock(&sit_i->sentry_lock);
+	down_write(&sit_i->sentry_lock);
 
 	old_cursegno = curseg->segno;
 	old_blkoff = curseg->next_blkoff;
@@ -2527,8 +2774,9 @@ void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 		curseg->next_blkoff = old_blkoff;
 	}
 
-	mutex_unlock(&sit_i->sentry_lock);
+	up_write(&sit_i->sentry_lock);
 	mutex_unlock(&curseg->curseg_mutex);
+	up_write(&SM_I(sbi)->curseg_lock);
 }
 
 void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn,
@@ -2982,7 +3230,7 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	bool to_journal = true;
 	struct seg_entry *se;
 
-	mutex_lock(&sit_i->sentry_lock);
+	down_write(&sit_i->sentry_lock);
 
 	if (!sit_i->dirty_sentries)
 		goto out;
@@ -3076,7 +3324,7 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 		cpc->trim_start = trim_start;
 	}
-	mutex_unlock(&sit_i->sentry_lock);
+	up_write(&sit_i->sentry_lock);
 
 	set_prefree_as_free_segments(sbi);
 }
@@ -3169,7 +3417,7 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
 	sit_i->sents_per_block = SIT_ENTRY_PER_BLOCK;
 	sit_i->elapsed_time = le64_to_cpu(sbi->ckpt->elapsed_time);
 	sit_i->mounted_time = ktime_get_real_seconds();
-	mutex_init(&sit_i->sentry_lock);
+	init_rwsem(&sit_i->sentry_lock);
 	return 0;
 }
 
@@ -3410,7 +3658,7 @@ static void init_min_max_mtime(struct f2fs_sb_info *sbi)
 	struct sit_info *sit_i = SIT_I(sbi);
 	unsigned int segno;
 
-	mutex_lock(&sit_i->sentry_lock);
+	down_write(&sit_i->sentry_lock);
 
 	sit_i->min_mtime = LLONG_MAX;
 
@@ -3427,7 +3675,7 @@ static void init_min_max_mtime(struct f2fs_sb_info *sbi)
 			sit_i->min_mtime = mtime;
 	}
 	sit_i->max_mtime = get_mtime(sbi);
-	mutex_unlock(&sit_i->sentry_lock);
+	up_write(&sit_i->sentry_lock);
 }
 
 int build_segment_manager(struct f2fs_sb_info *sbi)
@@ -3460,11 +3708,14 @@ int build_segment_manager(struct f2fs_sb_info *sbi)
 	sm_info->min_ipu_util = DEF_MIN_IPU_UTIL;
 	sm_info->min_fsync_blocks = DEF_MIN_FSYNC_BLOCKS;
 	sm_info->min_hot_blocks = DEF_MIN_HOT_BLOCKS;
+	sm_info->min_ssr_sections = reserved_sections(sbi);
 
 	sm_info->trim_sections = DEF_BATCHED_TRIM_SECTIONS;
 
 	INIT_LIST_HEAD(&sm_info->sit_entry_set);
 
+	init_rwsem(&sm_info->curseg_lock);
+
 	if (!f2fs_readonly(sbi->sb)) {
 		err = create_flush_cmd_control(sbi);
 		if (err)

fs/f2fs/segment.h

@@ -231,7 +231,7 @@ struct sit_info {
 	unsigned long *dirty_sentries_bitmap;	/* bitmap for dirty sentries */
 	unsigned int dirty_sentries;		/* # of dirty sentries */
 	unsigned int sents_per_block;		/* # of SIT entries per block */
-	struct mutex sentry_lock;		/* to protect SIT cache */
+	struct rw_semaphore sentry_lock;	/* to protect SIT cache */
 	struct seg_entry *sentries;		/* SIT segment-level cache */
 	struct sec_entry *sec_entries;		/* SIT section-level cache */
 
@@ -497,6 +497,33 @@ static inline int reserved_sections(struct f2fs_sb_info *sbi)
 	return GET_SEC_FROM_SEG(sbi, (unsigned int)reserved_segments(sbi));
 }
 
+static inline bool has_curseg_enough_space(struct f2fs_sb_info *sbi)
+{
+	unsigned int node_blocks = get_pages(sbi, F2FS_DIRTY_NODES) +
+					get_pages(sbi, F2FS_DIRTY_DENTS);
+	unsigned int dent_blocks = get_pages(sbi, F2FS_DIRTY_DENTS);
+	unsigned int segno, left_blocks;
+	int i;
+
+	/* check current node segment */
+	for (i = CURSEG_HOT_NODE; i <= CURSEG_COLD_NODE; i++) {
+		segno = CURSEG_I(sbi, i)->segno;
+		left_blocks = sbi->blocks_per_seg -
+			get_seg_entry(sbi, segno)->ckpt_valid_blocks;
+
+		if (node_blocks > left_blocks)
+			return false;
+	}
+
+	/* check current data segment */
+	segno = CURSEG_I(sbi, CURSEG_HOT_DATA)->segno;
+	left_blocks = sbi->blocks_per_seg -
+			get_seg_entry(sbi, segno)->ckpt_valid_blocks;
+	if (dent_blocks > left_blocks)
+		return false;
+	return true;
+}
+
 static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi,
 					int freed, int needed)
 {
@@ -507,6 +534,9 @@ static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi,
 	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
 		return false;
 
+	if (free_sections(sbi) + freed == reserved_sections(sbi) + needed &&
+			has_curseg_enough_space(sbi))
+		return false;
 	return (free_sections(sbi) + freed) <=
 		(node_secs + 2 * dent_secs + imeta_secs +
 		reserved_sections(sbi) + needed);
@@ -731,7 +761,7 @@ static inline block_t sum_blk_addr(struct f2fs_sb_info *sbi, int base, int type)
 static inline bool no_fggc_candidate(struct f2fs_sb_info *sbi,
 						unsigned int secno)
 {
-	if (get_valid_blocks(sbi, GET_SEG_FROM_SEC(sbi, secno), true) >=
+	if (get_valid_blocks(sbi, GET_SEG_FROM_SEC(sbi, secno), true) >
 						sbi->fggc_threshold)
 		return true;
 	return false;
@@ -796,8 +826,9 @@ static inline void wake_up_discard_thread(struct f2fs_sb_info *sbi, bool force)
 		goto wake_up;
 
 	mutex_lock(&dcc->cmd_lock);
-	for (i = MAX_PLIST_NUM - 1;
-			i >= 0 && plist_issue(dcc->pend_list_tag[i]); i--) {
+	for (i = MAX_PLIST_NUM - 1; i >= 0; i--) {
+		if (i + 1 < dcc->discard_granularity)
+			break;
 		if (!list_empty(&dcc->pend_list[i])) {
 			wakeup = true;
 			break;

fs/f2fs/shrinker.c

@@ -28,7 +28,7 @@ static unsigned long __count_nat_entries(struct f2fs_sb_info *sbi)
 
 static unsigned long __count_free_nids(struct f2fs_sb_info *sbi)
 {
-	long count = NM_I(sbi)->nid_cnt[FREE_NID_LIST] - MAX_FREE_NIDS;
+	long count = NM_I(sbi)->nid_cnt[FREE_NID] - MAX_FREE_NIDS;
 
 	return count > 0 ? count : 0;
 }

fs/f2fs/super.c

@@ -44,6 +44,8 @@ static struct kmem_cache *f2fs_inode_cachep;
 char *fault_name[FAULT_MAX] = {
 	[FAULT_KMALLOC]		= "kmalloc",
 	[FAULT_PAGE_ALLOC]	= "page alloc",
+	[FAULT_PAGE_GET]	= "page get",
+	[FAULT_ALLOC_BIO]	= "alloc bio",
 	[FAULT_ALLOC_NID]	= "alloc nid",
 	[FAULT_ORPHAN]		= "orphan",
 	[FAULT_BLOCK]		= "no more block",
@@ -92,6 +94,7 @@ enum {
 	Opt_disable_ext_identify,
 	Opt_inline_xattr,
 	Opt_noinline_xattr,
+	Opt_inline_xattr_size,
 	Opt_inline_data,
 	Opt_inline_dentry,
 	Opt_noinline_dentry,
@@ -141,6 +144,7 @@ static match_table_t f2fs_tokens = {
 	{Opt_disable_ext_identify, "disable_ext_identify"},
 	{Opt_inline_xattr, "inline_xattr"},
 	{Opt_noinline_xattr, "noinline_xattr"},
+	{Opt_inline_xattr_size, "inline_xattr_size=%u"},
 	{Opt_inline_data, "inline_data"},
 	{Opt_inline_dentry, "inline_dentry"},
 	{Opt_noinline_dentry, "noinline_dentry"},
@@ -209,6 +213,12 @@ static int f2fs_set_qf_name(struct super_block *sb, int qtype,
 			"quota options when quota turned on");
 		return -EINVAL;
 	}
+	if (f2fs_sb_has_quota_ino(sb)) {
+		f2fs_msg(sb, KERN_INFO,
+			"QUOTA feature is enabled, so ignore qf_name");
+		return 0;
+	}
+
 	qname = match_strdup(args);
 	if (!qname) {
 		f2fs_msg(sb, KERN_ERR,
@@ -287,6 +297,18 @@ static int f2fs_check_quota_options(struct f2fs_sb_info *sbi)
 			return -1;
 		}
 	}
+
+	if (f2fs_sb_has_quota_ino(sbi->sb) && sbi->s_jquota_fmt) {
+		f2fs_msg(sbi->sb, KERN_INFO,
+			"QUOTA feature is enabled, so ignore jquota_fmt");
+		sbi->s_jquota_fmt = 0;
+	}
+	if (f2fs_sb_has_quota_ino(sbi->sb) && sb_rdonly(sbi->sb)) {
+		f2fs_msg(sbi->sb, KERN_INFO,
+			 "Filesystem with quota feature cannot be mounted RDWR "
+			 "without CONFIG_QUOTA");
+		return -1;
+	}
 	return 0;
 }
 #endif
@@ -383,6 +405,12 @@ static int parse_options(struct super_block *sb, char *options)
 		case Opt_noinline_xattr:
 			clear_opt(sbi, INLINE_XATTR);
 			break;
+		case Opt_inline_xattr_size:
+			if (args->from && match_int(args, &arg))
+				return -EINVAL;
+			set_opt(sbi, INLINE_XATTR_SIZE);
+			sbi->inline_xattr_size = arg;
+			break;
 #else
 		case Opt_user_xattr:
 			f2fs_msg(sb, KERN_INFO,
@@ -604,6 +632,24 @@ static int parse_options(struct super_block *sb, char *options)
 				F2FS_IO_SIZE_KB(sbi));
 		return -EINVAL;
 	}
+
+	if (test_opt(sbi, INLINE_XATTR_SIZE)) {
+		if (!test_opt(sbi, INLINE_XATTR)) {
+			f2fs_msg(sb, KERN_ERR,
+					"inline_xattr_size option should be "
+					"set with inline_xattr option");
+			return -EINVAL;
+		}
+		if (!sbi->inline_xattr_size ||
+			sbi->inline_xattr_size >= DEF_ADDRS_PER_INODE -
+					F2FS_TOTAL_EXTRA_ATTR_SIZE -
+					DEF_INLINE_RESERVED_SIZE -
+					DEF_MIN_INLINE_SIZE) {
+			f2fs_msg(sb, KERN_ERR,
+					"inline xattr size is out of range");
+			return -EINVAL;
+		}
+	}
 	return 0;
 }
 
@@ -618,13 +664,13 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
 	init_once((void *) fi);
 
 	/* Initialize f2fs-specific inode info */
-	fi->vfs_inode.i_version = 1;
 	atomic_set(&fi->dirty_pages, 0);
 	fi->i_current_depth = 1;
 	fi->i_advise = 0;
 	init_rwsem(&fi->i_sem);
 	INIT_LIST_HEAD(&fi->dirty_list);
 	INIT_LIST_HEAD(&fi->gdirty_list);
+	INIT_LIST_HEAD(&fi->inmem_ilist);
 	INIT_LIST_HEAD(&fi->inmem_pages);
 	mutex_init(&fi->inmem_lock);
 	init_rwsem(&fi->dio_rwsem[READ]);
@@ -673,7 +719,6 @@ static int f2fs_drop_inode(struct inode *inode)
 
 			sb_end_intwrite(inode->i_sb);
 
-			fscrypt_put_encryption_info(inode, NULL);
 			spin_lock(&inode->i_lock);
 			atomic_dec(&inode->i_count);
 		}
@@ -781,6 +826,7 @@ static void f2fs_put_super(struct super_block *sb)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 	int i;
+	bool dropped;
 
 	f2fs_quota_off_umount(sb);
 
@@ -801,9 +847,9 @@ static void f2fs_put_super(struct super_block *sb)
 	}
 
 	/* be sure to wait for any on-going discard commands */
-	f2fs_wait_discard_bios(sbi, true);
+	dropped = f2fs_wait_discard_bios(sbi);
 
-	if (f2fs_discard_en(sbi) && !sbi->discard_blks) {
+	if (f2fs_discard_en(sbi) && !sbi->discard_blks && !dropped) {
 		struct cp_control cpc = {
 			.reason = CP_UMOUNT | CP_TRIMMED,
 		};
@@ -858,6 +904,9 @@ int f2fs_sync_fs(struct super_block *sb, int sync)
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 	int err = 0;
 
+	if (unlikely(f2fs_cp_error(sbi)))
+		return 0;
+
 	trace_f2fs_sync_fs(sb, sync);
 
 	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
@@ -957,7 +1006,7 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_blocks = total_count - start_count;
 	buf->f_bfree = user_block_count - valid_user_blocks(sbi) + ovp_count;
 	buf->f_bavail = user_block_count - valid_user_blocks(sbi) -
-						sbi->reserved_blocks;
+						sbi->current_reserved_blocks;
 
 	avail_node_count = sbi->total_node_count - F2FS_RESERVED_NODE_NUM;
 
@@ -1046,6 +1095,9 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 		seq_puts(seq, ",inline_xattr");
 	else
 		seq_puts(seq, ",noinline_xattr");
+	if (test_opt(sbi, INLINE_XATTR_SIZE))
+		seq_printf(seq, ",inline_xattr_size=%u",
+					sbi->inline_xattr_size);
 #endif
 #ifdef CONFIG_F2FS_FS_POSIX_ACL
 	if (test_opt(sbi, POSIX_ACL))
@@ -1108,6 +1160,7 @@ static void default_options(struct f2fs_sb_info *sbi)
 {
 	/* init some FS parameters */
 	sbi->active_logs = NR_CURSEG_TYPE;
+	sbi->inline_xattr_size = DEFAULT_INLINE_XATTR_ADDRS;
 
 	set_opt(sbi, BG_GC);
 	set_opt(sbi, INLINE_XATTR);
@@ -1136,6 +1189,9 @@ static void default_options(struct f2fs_sb_info *sbi)
 #endif
 }
 
+#ifdef CONFIG_QUOTA
+static int f2fs_enable_quotas(struct super_block *sb);
+#endif
 static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
@@ -1202,6 +1258,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	if (f2fs_readonly(sb) && (*flags & MS_RDONLY))
 		goto skip;
 
+#ifdef CONFIG_QUOTA
 	if (!f2fs_readonly(sb) && (*flags & MS_RDONLY)) {
 		err = dquot_suspend(sb, -1);
 		if (err < 0)
@@ -1209,9 +1266,15 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	} else {
 		/* dquot_resume needs RW */
 		sb->s_flags &= ~MS_RDONLY;
+		if (sb_any_quota_suspended(sb)) {
 			dquot_resume(sb, -1);
+		} else if (f2fs_sb_has_quota_ino(sb)) {
+			err = f2fs_enable_quotas(sb);
+			if (err)
+				goto restore_opts;
 		}
-
+	}
+#endif
 	/* disallow enable/disable extent_cache dynamically */
 	if (no_extent_cache == !!test_opt(sbi, EXTENT_CACHE)) {
 		err = -EINVAL;
@@ -1320,8 +1383,13 @@ static ssize_t f2fs_quota_read(struct super_block *sb, int type, char *data,
 		tocopy = min_t(unsigned long, sb->s_blocksize - offset, toread);
 repeat:
 		page = read_mapping_page(mapping, blkidx, NULL);
-		if (IS_ERR(page))
+		if (IS_ERR(page)) {
+			if (PTR_ERR(page) == -ENOMEM) {
+				congestion_wait(BLK_RW_ASYNC, HZ/50);
+				goto repeat;
+			}
 			return PTR_ERR(page);
+		}
 
 		lock_page(page);
 
@@ -1364,11 +1432,16 @@ static ssize_t f2fs_quota_write(struct super_block *sb, int type,
 	while (towrite > 0) {
 		tocopy = min_t(unsigned long, sb->s_blocksize - offset,
 								towrite);
-
+retry:
 		err = a_ops->write_begin(NULL, mapping, off, tocopy, 0,
 							&page, NULL);
-		if (unlikely(err))
+		if (unlikely(err)) {
+			if (err == -ENOMEM) {
+				congestion_wait(BLK_RW_ASYNC, HZ/50);
+				goto retry;
+			}
 			break;
+		}
 
 		kaddr = kmap_atomic(page);
 		memcpy(kaddr + offset, data, tocopy);
@@ -1385,8 +1458,7 @@ static ssize_t f2fs_quota_write(struct super_block *sb, int type,
 	}
 
 	if (len == towrite)
-		return 0;
-	inode->i_version++;
+		return err;
 	inode->i_mtime = inode->i_ctime = current_time(inode);
 	f2fs_mark_inode_dirty_sync(inode, false);
 	return len - towrite;
@@ -1408,19 +1480,91 @@ static int f2fs_quota_on_mount(struct f2fs_sb_info *sbi, int type)
 						sbi->s_jquota_fmt, type);
 }
 
-void f2fs_enable_quota_files(struct f2fs_sb_info *sbi)
+int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly)
 {
-	int i, ret;
+	int enabled = 0;
+	int i, err;
+
+	if (f2fs_sb_has_quota_ino(sbi->sb) && rdonly) {
+		err = f2fs_enable_quotas(sbi->sb);
+		if (err) {
+			f2fs_msg(sbi->sb, KERN_ERR,
+					"Cannot turn on quota_ino: %d", err);
+			return 0;
+		}
+		return 1;
+	}
 
 	for (i = 0; i < MAXQUOTAS; i++) {
 		if (sbi->s_qf_names[i]) {
-			ret = f2fs_quota_on_mount(sbi, i);
-			if (ret < 0)
+			err = f2fs_quota_on_mount(sbi, i);
+			if (!err) {
+				enabled = 1;
+				continue;
+			}
 			f2fs_msg(sbi->sb, KERN_ERR,
-					"Cannot turn on journaled "
-					"quota: error %d", ret);
+				"Cannot turn on quotas: %d on %d", err, i);
 		}
 	}
+	return enabled;
+}
+
+static int f2fs_quota_enable(struct super_block *sb, int type, int format_id,
+			     unsigned int flags)
+{
+	struct inode *qf_inode;
+	unsigned long qf_inum;
+	int err;
+
+	BUG_ON(!f2fs_sb_has_quota_ino(sb));
+
+	qf_inum = f2fs_qf_ino(sb, type);
+	if (!qf_inum)
+		return -EPERM;
+
+	qf_inode = f2fs_iget(sb, qf_inum);
+	if (IS_ERR(qf_inode)) {
+		f2fs_msg(sb, KERN_ERR,
+			"Bad quota inode %u:%lu", type, qf_inum);
+		return PTR_ERR(qf_inode);
+	}
+
+	/* Don't account quota for quota files to avoid recursion */
+	qf_inode->i_flags |= S_NOQUOTA;
+	err = dquot_enable(qf_inode, type, format_id, flags);
+	iput(qf_inode);
+	return err;
+}
+
+static int f2fs_enable_quotas(struct super_block *sb)
+{
+	int type, err = 0;
+	unsigned long qf_inum;
+	bool quota_mopt[MAXQUOTAS] = {
+		test_opt(F2FS_SB(sb), USRQUOTA),
+		test_opt(F2FS_SB(sb), GRPQUOTA),
+		test_opt(F2FS_SB(sb), PRJQUOTA),
+	};
+
+	sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE | DQUOT_NOLIST_DIRTY;
+	for (type = 0; type < MAXQUOTAS; type++) {
+		qf_inum = f2fs_qf_ino(sb, type);
+		if (qf_inum) {
+			err = f2fs_quota_enable(sb, type, QFMT_VFS_V1,
+				DQUOT_USAGE_ENABLED |
+				(quota_mopt[type] ? DQUOT_LIMITS_ENABLED : 0));
+			if (err) {
+				f2fs_msg(sb, KERN_ERR,
+					"Failed to enable quota tracking "
+					"(type=%d, err=%d). Please run "
+					"fsck to fix.", type, err);
+				for (type--; type >= 0; type--)
+					dquot_quota_off(sb, type);
+				return err;
+			}
+		}
+	}
+	return 0;
 }
 
 static int f2fs_quota_sync(struct super_block *sb, int type)
@@ -1491,7 +1635,7 @@ static int f2fs_quota_off(struct super_block *sb, int type)
 	f2fs_quota_sync(sb, type);
 
 	err = dquot_quota_off(sb, type);
-	if (err)
+	if (err || f2fs_sb_has_quota_ino(sb))
 		goto out_put;
 
 	inode_lock(inode);
@@ -1651,7 +1795,7 @@ static loff_t max_file_blocks(void)
 
 	/*
 	 * note: previously, result is equal to (DEF_ADDRS_PER_INODE -
-	 * F2FS_INLINE_XATTR_ADDRS), but now f2fs try to reserve more
+	 * DEFAULT_INLINE_XATTR_ADDRS), but now f2fs try to reserve more
 	 * space in inode.i_addr, it will be more safe to reassign
 	 * result as zero.
 	 */
@@ -1960,6 +2104,9 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
 		for (j = HOT; j < NR_TEMP_TYPE; j++)
 			mutex_init(&sbi->wio_mutex[i][j]);
 	spin_lock_init(&sbi->cp_lock);
+
+	sbi->dirty_device = 0;
+	spin_lock_init(&sbi->dev_lock);
 }
 
 static int init_percpu_info(struct f2fs_sb_info *sbi)
@@ -2310,6 +2457,9 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 
 #ifdef CONFIG_QUOTA
 	sb->dq_op = &f2fs_quota_operations;
+	if (f2fs_sb_has_quota_ino(sb))
+		sb->s_qcop = &dquot_quotactl_sysfile_ops;
+	else
 		sb->s_qcop = &f2fs_quotactl_ops;
 	sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP | QTYPE_MASK_PRJ;
 #endif
@@ -2408,6 +2558,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 				le64_to_cpu(sbi->ckpt->valid_block_count);
 	sbi->last_valid_block_count = sbi->total_valid_block_count;
 	sbi->reserved_blocks = 0;
+	sbi->current_reserved_blocks = 0;
 
 	for (i = 0; i < NR_INODE_TYPE; i++) {
 		INIT_LIST_HEAD(&sbi->inode_list[i]);
@@ -2482,10 +2633,24 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	if (err)
 		goto free_root_inode;
 
+#ifdef CONFIG_QUOTA
+	/*
+	 * Turn on quotas which were not enabled for read-only mounts if
+	 * filesystem has quota feature, so that they are updated correctly.
+	 */
+	if (f2fs_sb_has_quota_ino(sb) && !sb_rdonly(sb)) {
+		err = f2fs_enable_quotas(sb);
+		if (err) {
+			f2fs_msg(sb, KERN_ERR,
+				"Cannot turn on quotas: error %d", err);
+			goto free_sysfs;
+		}
+	}
+#endif
 	/* if there are nt orphan nodes free them */
 	err = recover_orphan_inodes(sbi);
 	if (err)
-		goto free_sysfs;
+		goto free_meta;
 
 	/* recover fsynced data */
 	if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) {
@@ -2519,7 +2684,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 			err = -EINVAL;
 			f2fs_msg(sb, KERN_ERR,
 				"Need to recover fsync data");
-			goto free_sysfs;
+			goto free_meta;
 		}
 	}
 skip_recovery:
@@ -2553,6 +2718,10 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	return 0;
 
 free_meta:
+#ifdef CONFIG_QUOTA
+	if (f2fs_sb_has_quota_ino(sb) && !sb_rdonly(sb))
+		f2fs_quota_off_umount(sbi->sb);
+#endif
 	f2fs_sync_inode_meta(sbi);
 	/*
 	 * Some dirty meta pages can be produced by recover_orphan_inodes()
@@ -2561,7 +2730,9 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	 * falls into an infinite loop in sync_meta_pages().
 	 */
 	truncate_inode_pages_final(META_MAPPING(sbi));
+#ifdef CONFIG_QUOTA
 free_sysfs:
+#endif
 	f2fs_unregister_sysfs(sbi);
 free_root_inode:
 	dput(sb->s_root);

fs/f2fs/sysfs.c

@@ -30,7 +30,7 @@ enum {
 	FAULT_INFO_RATE,	/* struct f2fs_fault_info */
 	FAULT_INFO_TYPE,	/* struct f2fs_fault_info */
 #endif
-	RESERVED_BLOCKS,
+	RESERVED_BLOCKS,	/* struct f2fs_sb_info */
 };
 
 struct f2fs_attr {
@@ -63,6 +63,13 @@ static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type)
 	return NULL;
 }
 
+static ssize_t dirty_segments_show(struct f2fs_attr *a,
+		struct f2fs_sb_info *sbi, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%llu\n",
+		(unsigned long long)(dirty_segments(sbi)));
+}
+
 static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a,
 		struct f2fs_sb_info *sbi, char *buf)
 {
@@ -100,10 +107,22 @@ static ssize_t features_show(struct f2fs_attr *a,
 	if (f2fs_sb_has_inode_chksum(sb))
 		len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
 				len ? ", " : "", "inode_checksum");
+	if (f2fs_sb_has_flexible_inline_xattr(sb))
+		len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+				len ? ", " : "", "flexible_inline_xattr");
+	if (f2fs_sb_has_quota_ino(sb))
+		len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+				len ? ", " : "", "quota_ino");
 	len += snprintf(buf + len, PAGE_SIZE - len, "\n");
 	return len;
 }
 
+static ssize_t current_reserved_blocks_show(struct f2fs_attr *a,
+					struct f2fs_sb_info *sbi, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%u\n", sbi->current_reserved_blocks);
+}
+
 static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
 			struct f2fs_sb_info *sbi, char *buf)
 {
@@ -143,34 +162,22 @@ static ssize_t f2fs_sbi_store(struct f2fs_attr *a,
 #endif
 	if (a->struct_type == RESERVED_BLOCKS) {
 		spin_lock(&sbi->stat_lock);
-		if ((unsigned long)sbi->total_valid_block_count + t >
-				(unsigned long)sbi->user_block_count) {
+		if (t > (unsigned long)sbi->user_block_count) {
 			spin_unlock(&sbi->stat_lock);
 			return -EINVAL;
 		}
 		*ui = t;
+		sbi->current_reserved_blocks = min(sbi->reserved_blocks,
+				sbi->user_block_count - valid_user_blocks(sbi));
 		spin_unlock(&sbi->stat_lock);
 		return count;
 	}
 
 	if (!strcmp(a->attr.name, "discard_granularity")) {
-		struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
-		int i;
-
 		if (t == 0 || t > MAX_PLIST_NUM)
 			return -EINVAL;
 		if (t == *ui)
 			return count;
-
-		mutex_lock(&dcc->cmd_lock);
-		for (i = 0; i < MAX_PLIST_NUM; i++) {
-			if (i >= t - 1)
-				dcc->pend_list_tag[i] |= P_ACTIVE;
-			else
-				dcc->pend_list_tag[i] &= (~P_ACTIVE);
-		}
-		mutex_unlock(&dcc->cmd_lock);
-
 		*ui = t;
 		return count;
 	}
@@ -222,6 +229,8 @@ enum feat_id {
 	FEAT_EXTRA_ATTR,
 	FEAT_PROJECT_QUOTA,
 	FEAT_INODE_CHECKSUM,
+	FEAT_FLEXIBLE_INLINE_XATTR,
+	FEAT_QUOTA_INO,
 };
 
 static ssize_t f2fs_feature_show(struct f2fs_attr *a,
@@ -234,6 +243,8 @@ static ssize_t f2fs_feature_show(struct f2fs_attr *a,
 	case FEAT_EXTRA_ATTR:
 	case FEAT_PROJECT_QUOTA:
 	case FEAT_INODE_CHECKSUM:
+	case FEAT_FLEXIBLE_INLINE_XATTR:
+	case FEAT_QUOTA_INO:
 		return snprintf(buf, PAGE_SIZE, "supported\n");
 	}
 	return 0;
@@ -279,6 +290,7 @@ F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, ipu_policy, ipu_policy);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_fsync_blocks, min_fsync_blocks);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_hot_blocks, min_hot_blocks);
+F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ssr_sections, min_ssr_sections);
 F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ram_thresh, ram_thresh);
 F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ra_nid_pages, ra_nid_pages);
 F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, dirty_nats_ratio, dirty_nats_ratio);
@@ -291,8 +303,10 @@ F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, iostat_enable, iostat_enable);
 F2FS_RW_ATTR(FAULT_INFO_RATE, f2fs_fault_info, inject_rate, inject_rate);
 F2FS_RW_ATTR(FAULT_INFO_TYPE, f2fs_fault_info, inject_type, inject_type);
 #endif
+F2FS_GENERAL_RO_ATTR(dirty_segments);
 F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes);
 F2FS_GENERAL_RO_ATTR(features);
+F2FS_GENERAL_RO_ATTR(current_reserved_blocks);
 
 #ifdef CONFIG_F2FS_FS_ENCRYPTION
 F2FS_FEATURE_RO_ATTR(encryption, FEAT_CRYPTO);
@@ -304,6 +318,8 @@ F2FS_FEATURE_RO_ATTR(atomic_write, FEAT_ATOMIC_WRITE);
 F2FS_FEATURE_RO_ATTR(extra_attr, FEAT_EXTRA_ATTR);
 F2FS_FEATURE_RO_ATTR(project_quota, FEAT_PROJECT_QUOTA);
 F2FS_FEATURE_RO_ATTR(inode_checksum, FEAT_INODE_CHECKSUM);
+F2FS_FEATURE_RO_ATTR(flexible_inline_xattr, FEAT_FLEXIBLE_INLINE_XATTR);
+F2FS_FEATURE_RO_ATTR(quota_ino, FEAT_QUOTA_INO);
 
 #define ATTR_LIST(name) (&f2fs_attr_##name.attr)
 static struct attribute *f2fs_attrs[] = {
@@ -321,6 +337,7 @@ static struct attribute *f2fs_attrs[] = {
 	ATTR_LIST(min_ipu_util),
 	ATTR_LIST(min_fsync_blocks),
 	ATTR_LIST(min_hot_blocks),
+	ATTR_LIST(min_ssr_sections),
 	ATTR_LIST(max_victim_search),
 	ATTR_LIST(dir_level),
 	ATTR_LIST(ram_thresh),
@@ -333,9 +350,11 @@ static struct attribute *f2fs_attrs[] = {
 	ATTR_LIST(inject_rate),
 	ATTR_LIST(inject_type),
 #endif
+	ATTR_LIST(dirty_segments),
 	ATTR_LIST(lifetime_write_kbytes),
 	ATTR_LIST(features),
 	ATTR_LIST(reserved_blocks),
+	ATTR_LIST(current_reserved_blocks),
 	NULL,
 };
 
@@ -350,6 +369,8 @@ static struct attribute *f2fs_feat_attrs[] = {
 	ATTR_LIST(extra_attr),
 	ATTR_LIST(project_quota),
 	ATTR_LIST(inode_checksum),
+	ATTR_LIST(flexible_inline_xattr),
+	ATTR_LIST(quota_ino),
 	NULL,
 };
 

fs/f2fs/xattr.c

@@ -217,12 +217,12 @@ static struct f2fs_xattr_entry *__find_xattr(void *base_addr, int index,
 	return entry;
 }
 
-static struct f2fs_xattr_entry *__find_inline_xattr(void *base_addr,
-					void **last_addr, int index,
+static struct f2fs_xattr_entry *__find_inline_xattr(struct inode *inode,
+				void *base_addr, void **last_addr, int index,
 				size_t len, const char *name)
 {
 	struct f2fs_xattr_entry *entry;
-	unsigned int inline_size = F2FS_INLINE_XATTR_ADDRS << 2;
+	unsigned int inline_size = inline_xattr_size(inode);
 
 	list_for_each_xattr(entry, base_addr) {
 		if ((void *)entry + sizeof(__u32) > base_addr + inline_size ||
@@ -241,12 +241,54 @@ static struct f2fs_xattr_entry *__find_inline_xattr(void *base_addr,
 	return entry;
 }
 
+static int read_inline_xattr(struct inode *inode, struct page *ipage,
+							void *txattr_addr)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	unsigned int inline_size = inline_xattr_size(inode);
+	struct page *page = NULL;
+	void *inline_addr;
+
+	if (ipage) {
+		inline_addr = inline_xattr_addr(inode, ipage);
+	} else {
+		page = get_node_page(sbi, inode->i_ino);
+		if (IS_ERR(page))
+			return PTR_ERR(page);
+
+		inline_addr = inline_xattr_addr(inode, page);
+	}
+	memcpy(txattr_addr, inline_addr, inline_size);
+	f2fs_put_page(page, 1);
+
+	return 0;
+}
+
+static int read_xattr_block(struct inode *inode, void *txattr_addr)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	nid_t xnid = F2FS_I(inode)->i_xattr_nid;
+	unsigned int inline_size = inline_xattr_size(inode);
+	struct page *xpage;
+	void *xattr_addr;
+
+	/* The inode already has an extended attribute block. */
+	xpage = get_node_page(sbi, xnid);
+	if (IS_ERR(xpage))
+		return PTR_ERR(xpage);
+
+	xattr_addr = page_address(xpage);
+	memcpy(txattr_addr + inline_size, xattr_addr, VALID_XATTR_BLOCK_SIZE);
+	f2fs_put_page(xpage, 1);
+
+	return 0;
+}
+
 static int lookup_all_xattrs(struct inode *inode, struct page *ipage,
 				unsigned int index, unsigned int len,
 				const char *name, struct f2fs_xattr_entry **xe,
 				void **base_addr)
 {
-	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	void *cur_addr, *txattr_addr, *last_addr = NULL;
 	nid_t xnid = F2FS_I(inode)->i_xattr_nid;
 	unsigned int size = xnid ? VALID_XATTR_BLOCK_SIZE : 0;
@@ -263,23 +305,11 @@ static int lookup_all_xattrs(struct inode *inode, struct page *ipage,
 
 	/* read from inline xattr */
 	if (inline_size) {
-		struct page *page = NULL;
-		void *inline_addr;
-
-		if (ipage) {
-			inline_addr = inline_xattr_addr(ipage);
-		} else {
-			page = get_node_page(sbi, inode->i_ino);
-			if (IS_ERR(page)) {
-				err = PTR_ERR(page);
+		err = read_inline_xattr(inode, ipage, txattr_addr);
+		if (err)
 			goto out;
-			}
-			inline_addr = inline_xattr_addr(page);
-		}
-		memcpy(txattr_addr, inline_addr, inline_size);
-		f2fs_put_page(page, 1);
 
-		*xe = __find_inline_xattr(txattr_addr, &last_addr,
+		*xe = __find_inline_xattr(inode, txattr_addr, &last_addr,
 						index, len, name);
 		if (*xe)
 			goto check;
@@ -287,21 +317,11 @@ static int lookup_all_xattrs(struct inode *inode, struct page *ipage,
 
 	/* read from xattr node block */
 	if (xnid) {
-		struct page *xpage;
-		void *xattr_addr;
-
-		/* The inode already has an extended attribute block. */
-		xpage = get_node_page(sbi, xnid);
-		if (IS_ERR(xpage)) {
-			err = PTR_ERR(xpage);
+		err = read_xattr_block(inode, txattr_addr);
+		if (err)
 			goto out;
 	}
 
-		xattr_addr = page_address(xpage);
-		memcpy(txattr_addr + inline_size, xattr_addr, size);
-		f2fs_put_page(xpage, 1);
-	}
-
 	if (last_addr)
 		cur_addr = XATTR_HDR(last_addr) - 1;
 	else
@@ -324,7 +344,6 @@ static int lookup_all_xattrs(struct inode *inode, struct page *ipage,
 static int read_all_xattrs(struct inode *inode, struct page *ipage,
 							void **base_addr)
 {
-	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct f2fs_xattr_header *header;
 	nid_t xnid = F2FS_I(inode)->i_xattr_nid;
 	unsigned int size = VALID_XATTR_BLOCK_SIZE;
@@ -339,40 +358,18 @@ static int read_all_xattrs(struct inode *inode, struct page *ipage,
 
 	/* read from inline xattr */
 	if (inline_size) {
-		struct page *page = NULL;
-		void *inline_addr;
-
-		if (ipage) {
-			inline_addr = inline_xattr_addr(ipage);
-		} else {
-			page = get_node_page(sbi, inode->i_ino);
-			if (IS_ERR(page)) {
-				err = PTR_ERR(page);
+		err = read_inline_xattr(inode, ipage, txattr_addr);
+		if (err)
 			goto fail;
 	}
-			inline_addr = inline_xattr_addr(page);
-		}
-		memcpy(txattr_addr, inline_addr, inline_size);
-		f2fs_put_page(page, 1);
-	}
 
 	/* read from xattr node block */
 	if (xnid) {
-		struct page *xpage;
-		void *xattr_addr;
-
-		/* The inode already has an extended attribute block. */
-		xpage = get_node_page(sbi, xnid);
-		if (IS_ERR(xpage)) {
-			err = PTR_ERR(xpage);
+		err = read_xattr_block(inode, txattr_addr);
+		if (err)
 			goto fail;
 	}
 
-		xattr_addr = page_address(xpage);
-		memcpy(txattr_addr + inline_size, xattr_addr, size);
-		f2fs_put_page(xpage, 1);
-	}
-
 	header = XATTR_HDR(txattr_addr);
 
 	/* never been allocated xattrs */
@@ -392,10 +389,12 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	size_t inline_size = inline_xattr_size(inode);
+	struct page *in_page = NULL;
 	void *xattr_addr;
+	void *inline_addr = NULL;
 	struct page *xpage;
 	nid_t new_nid = 0;
-	int err;
+	int err = 0;
 
 	if (hsize > inline_size && !F2FS_I(inode)->i_xattr_nid)
 		if (!alloc_nid(sbi, &new_nid))
@@ -403,31 +402,31 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
 
 	/* write to inline xattr */
 	if (inline_size) {
-		struct page *page = NULL;
-		void *inline_addr;
-
 		if (ipage) {
-			inline_addr = inline_xattr_addr(ipage);
-			f2fs_wait_on_page_writeback(ipage, NODE, true);
-			set_page_dirty(ipage);
+			inline_addr = inline_xattr_addr(inode, ipage);
 		} else {
-			page = get_node_page(sbi, inode->i_ino);
-			if (IS_ERR(page)) {
+			in_page = get_node_page(sbi, inode->i_ino);
+			if (IS_ERR(in_page)) {
 				alloc_nid_failed(sbi, new_nid);
-				return PTR_ERR(page);
+				return PTR_ERR(in_page);
 			}
-			inline_addr = inline_xattr_addr(page);
-			f2fs_wait_on_page_writeback(page, NODE, true);
+			inline_addr = inline_xattr_addr(inode, in_page);
 		}
-		memcpy(inline_addr, txattr_addr, inline_size);
-		f2fs_put_page(page, 1);
 
+		f2fs_wait_on_page_writeback(ipage ? ipage : in_page,
+							NODE, true);
 		/* no need to use xattr node block */
 		if (hsize <= inline_size) {
-			err = truncate_xattr_node(inode, ipage);
+			err = truncate_xattr_node(inode);
 			alloc_nid_failed(sbi, new_nid);
+			if (err) {
+				f2fs_put_page(in_page, 1);
 				return err;
 			}
+			memcpy(inline_addr, txattr_addr, inline_size);
+			set_page_dirty(ipage ? ipage : in_page);
+			goto in_page_out;
+		}
 	}
 
 	/* write to xattr node block */
@@ -435,7 +434,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
 		xpage = get_node_page(sbi, F2FS_I(inode)->i_xattr_nid);
 		if (IS_ERR(xpage)) {
 			alloc_nid_failed(sbi, new_nid);
-			return PTR_ERR(xpage);
+			goto in_page_out;
 		}
 		f2fs_bug_on(sbi, new_nid);
 		f2fs_wait_on_page_writeback(xpage, NODE, true);
@@ -445,17 +444,24 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
 		xpage = new_node_page(&dn, XATTR_NODE_OFFSET);
 		if (IS_ERR(xpage)) {
 			alloc_nid_failed(sbi, new_nid);
-			return PTR_ERR(xpage);
+			goto in_page_out;
 		}
 		alloc_nid_done(sbi, new_nid);
 	}
-
 	xattr_addr = page_address(xpage);
+
+	if (inline_size)
+		memcpy(inline_addr, txattr_addr, inline_size);
 	memcpy(xattr_addr, txattr_addr + inline_size, VALID_XATTR_BLOCK_SIZE);
+
+	if (inline_size)
+		set_page_dirty(ipage ? ipage : in_page);
 	set_page_dirty(xpage);
-	f2fs_put_page(xpage, 1);
 
-	return 0;
+	f2fs_put_page(xpage, 1);
+in_page_out:
+	f2fs_put_page(in_page, 1);
+	return err;
 }
 
 int f2fs_getxattr(struct inode *inode, int index, const char *name,
@@ -681,6 +687,10 @@ int f2fs_setxattr(struct inode *inode, int index, const char *name,
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	int err;
 
+	err = dquot_initialize(inode);
+	if (err)
+		return err;
+
 	/* this case is only from init_inode_metadata */
 	if (ipage)
 		return __f2fs_setxattr(inode, index, name, value,

include/linux/f2fs_fs.h

@@ -36,6 +36,8 @@
 #define F2FS_NODE_INO(sbi)	((sbi)->node_ino_num)
 #define F2FS_META_INO(sbi)	((sbi)->meta_ino_num)
 
+#define F2FS_MAX_QUOTAS		3
+
 #define F2FS_IO_SIZE(sbi)	(1 << (sbi)->write_io_size_bits) /* Blocks */
 #define F2FS_IO_SIZE_KB(sbi)	(1 << ((sbi)->write_io_size_bits + 2)) /* KB */
 #define F2FS_IO_SIZE_BYTES(sbi)	(1 << ((sbi)->write_io_size_bits + 12)) /* B */
@@ -108,7 +110,8 @@ struct f2fs_super_block {
 	__u8 encryption_level;		/* versioning level for encryption */
 	__u8 encrypt_pw_salt[16];	/* Salt used for string2key algorithm */
 	struct f2fs_device devs[MAX_DEVICES];	/* device list */
-	__u8 reserved[327];		/* valid reserved region */
+	__le32 qf_ino[F2FS_MAX_QUOTAS];	/* quota inode numbers */
+	__u8 reserved[315];		/* valid reserved region */
 } __packed;
 
 /*
@@ -184,7 +187,8 @@ struct f2fs_extent {
 } __packed;
 
 #define F2FS_NAME_LEN		255
-#define F2FS_INLINE_XATTR_ADDRS	50	/* 200 bytes for inline xattrs */
+/* 200 bytes for inline xattrs by default */
+#define DEFAULT_INLINE_XATTR_ADDRS	50
 #define DEF_ADDRS_PER_INODE	923	/* Address Pointers in an Inode */
 #define CUR_ADDRS_PER_INODE(inode)	(DEF_ADDRS_PER_INODE - \
 					get_extra_isize(inode))
@@ -238,7 +242,7 @@ struct f2fs_inode {
 	union {
 		struct {
 			__le16 i_extra_isize;	/* extra inode attribute size */
-			__le16 i_padding;	/* padding */
+			__le16 i_inline_xattr_size;	/* inline xattr size, unit: 4 bytes */
 			__le32 i_projid;	/* project id */
 			__le32 i_inode_checksum;/* inode meta checksum */
 			__le32 i_extra_end[0];	/* for attribute size calculation */

include/trace/events/f2fs.h

@@ -137,6 +137,18 @@ TRACE_DEFINE_ENUM(CP_TRIMMED);
 		{ CP_UMOUNT,	"Umount" },				\
 		{ CP_TRIMMED,	"Trimmed" })
 
+#define show_fsync_cpreason(type)					\
+	__print_symbolic(type,						\
+		{ CP_NO_NEEDED,		"no needed" },			\
+		{ CP_NON_REGULAR,	"non regular" },		\
+		{ CP_HARDLINK,		"hardlink" },			\
+		{ CP_SB_NEED_CP,	"sb needs cp" },		\
+		{ CP_WRONG_PINO,	"wrong pino" },			\
+		{ CP_NO_SPC_ROLL,	"no space roll forward" },	\
+		{ CP_NODE_NEED_CP,	"node needs cp" },		\
+		{ CP_FASTBOOT_MODE,	"fastboot mode" },		\
+		{ CP_SPEC_LOG_NUM,	"log type is 2" })
+
 struct victim_sel_policy;
 struct f2fs_map_blocks;
 
@@ -211,14 +223,14 @@ DEFINE_EVENT(f2fs__inode, f2fs_sync_file_enter,
 
 TRACE_EVENT(f2fs_sync_file_exit,
 
-	TP_PROTO(struct inode *inode, int need_cp, int datasync, int ret),
+	TP_PROTO(struct inode *inode, int cp_reason, int datasync, int ret),
 
-	TP_ARGS(inode, need_cp, datasync, ret),
+	TP_ARGS(inode, cp_reason, datasync, ret),
 
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
 		__field(ino_t,	ino)
-		__field(int,	need_cp)
+		__field(int,	cp_reason)
 		__field(int,	datasync)
 		__field(int,	ret)
 	),
@@ -226,15 +238,15 @@ TRACE_EVENT(f2fs_sync_file_exit,
 	TP_fast_assign(
 		__entry->dev		= inode->i_sb->s_dev;
 		__entry->ino		= inode->i_ino;
-		__entry->need_cp	= need_cp;
+		__entry->cp_reason	= cp_reason;
 		__entry->datasync	= datasync;
 		__entry->ret		= ret;
 	),
 
-	TP_printk("dev = (%d,%d), ino = %lu, checkpoint is %s, "
+	TP_printk("dev = (%d,%d), ino = %lu, cp_reason: %s, "
 		"datasync = %d, ret = %d",
 		show_dev_ino(__entry),
-		__entry->need_cp ? "needed" : "not needed",
+		show_fsync_cpreason(__entry->cp_reason),
 		__entry->datasync,
 		__entry->ret)
 );
@@ -729,6 +741,91 @@ TRACE_EVENT(f2fs_get_victim,
 		__entry->free)
 );
 
+TRACE_EVENT(f2fs_lookup_start,
+
+	TP_PROTO(struct inode *dir, struct dentry *dentry, unsigned int flags),
+
+	TP_ARGS(dir, dentry, flags),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(const char *,	name)
+		__field(unsigned int, flags)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= dir->i_sb->s_dev;
+		__entry->ino	= dir->i_ino;
+		__entry->name	= dentry->d_name.name;
+		__entry->flags	= flags;
+	),
+
+	TP_printk("dev = (%d,%d), pino = %lu, name:%s, flags:%u",
+		show_dev_ino(__entry),
+		__entry->name,
+		__entry->flags)
+);
+
+TRACE_EVENT(f2fs_lookup_end,
+
+	TP_PROTO(struct inode *dir, struct dentry *dentry, nid_t ino,
+		int err),
+
+	TP_ARGS(dir, dentry, ino, err),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(const char *,	name)
+		__field(nid_t,	cino)
+		__field(int,	err)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= dir->i_sb->s_dev;
+		__entry->ino	= dir->i_ino;
+		__entry->name	= dentry->d_name.name;
+		__entry->cino	= ino;
+		__entry->err	= err;
+	),
+
+	TP_printk("dev = (%d,%d), pino = %lu, name:%s, ino:%u, err:%d",
+		show_dev_ino(__entry),
+		__entry->name,
+		__entry->cino,
+		__entry->err)
+);
+
+TRACE_EVENT(f2fs_readdir,
+
+	TP_PROTO(struct inode *dir, loff_t start_pos, loff_t end_pos, int err),
+
+	TP_ARGS(dir, start_pos, end_pos, err),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(loff_t,	start)
+		__field(loff_t,	end)
+		__field(int,	err)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= dir->i_sb->s_dev;
+		__entry->ino	= dir->i_ino;
+		__entry->start	= start_pos;
+		__entry->end	= end_pos;
+		__entry->err	= err;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, start_pos:%llu, end_pos:%llu, err:%d",
+		show_dev_ino(__entry),
+		__entry->start,
+		__entry->end,
+		__entry->err)
+);
+
 TRACE_EVENT(f2fs_fallocate,
 
 	TP_PROTO(struct inode *inode, int mode,
@@ -1287,6 +1384,13 @@ DEFINE_EVENT(f2fs_discard, f2fs_issue_discard,
 	TP_ARGS(dev, blkstart, blklen)
 );
 
+DEFINE_EVENT(f2fs_discard, f2fs_remove_discard,
+
+	TP_PROTO(struct block_device *dev, block_t blkstart, block_t blklen),
+
+	TP_ARGS(dev, blkstart, blklen)
+);
+
 TRACE_EVENT(f2fs_issue_reset_zone,
 
 	TP_PROTO(struct block_device *dev, block_t blkstart),