Merge tag 'for-f2fs-4.11' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "This round introduces several interesting features such as on-disk NAT
  bitmaps, IO alignment, and a discard thread. And it includes a couple
  of major bug fixes as below.

  Enhancements:

   - introduce on-disk bitmaps to avoid scanning NAT blocks when getting
     free nids

   - support IO alignment to prepare open-channel SSD integration in
     future

   - introduce a discard thread to avoid long latency during checkpoint
     and fstrim

   - use SSR for warm node and enable inline_xattr by default

   - introduce in-memory bitmaps to check FS consistency for debugging

   - improve write_begin by avoiding needless read IO

  Bug fixes:

   - fix broken zone_reset behavior for SMR drive

   - fix wrong victim selection policy during GC

   - fix missing behavior when preparing discard commands

   - fix bugs in atomic write support and fiemap

   - workaround to handle multiple f2fs_add_link calls having same name

  ... and it includes a bunch of clean-up patches as well"

* tag 'for-f2fs-4.11' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (97 commits)
  f2fs: avoid to flush nat journal entries
  f2fs: avoid to issue redundant discard commands
  f2fs: fix a plint compile warning
  f2fs: add f2fs_drop_inode tracepoint
  f2fs: Fix zoned block device support
  f2fs: remove redundant set_page_dirty()
  f2fs: fix to enlarge size of write_io_dummy mempool
  f2fs: fix memory leak of write_io_dummy mempool during umount
  f2fs: fix to update F2FS_{CP_}WB_DATA count correctly
  f2fs: use MAX_FREE_NIDS for the free nids target
  f2fs: introduce free nid bitmap
  f2fs: new helper cur_cp_crc() getting crc in f2fs_checkpoint
  f2fs: update the comment of default nr_pages to skipping
  f2fs: drop the duplicate pval in f2fs_getxattr
  f2fs: Don't update the xattr data that same as the exist
  f2fs: kill __is_extent_same
  f2fs: avoid bggc->fggc when enough free segments are avaliable after cp
  f2fs: select target segment with closer temperature in SSR mode
  f2fs: show simple call stack in fault injection message
  f2fs: no need lock_op in f2fs_write_inline_data
  ...

Documentation/filesystems/f2fs.txt

@@ -125,13 +125,14 @@ active_logs=%u         Support configuring the number of active logs. In the
 disable_ext_identify   Disable the extension list configured by mkfs, so f2fs
                        does not aware of cold files such as media files.
 inline_xattr           Enable the inline xattrs feature.
+noinline_xattr         Disable the inline xattrs feature.
 inline_data            Enable the inline data feature: New created small(<~3.4k)
                        files can be written into inode block.
 inline_dentry          Enable the inline dir feature: data in new created
                        directory entries can be written into inode block. The
                        space of inode block which is used to store inline
                        dentries is limited to ~3.4k.
-noinline_dentry        Diable the inline dentry feature.
+noinline_dentry        Disable the inline dentry feature.
 flush_merge	       Merge concurrent cache_flush commands as much as possible
                        to eliminate redundant command issues. If the underlying
 		       device handles the cache_flush command relatively slowly,
@@ -157,6 +158,8 @@ data_flush             Enable data flushing before checkpoint in order to
 mode=%s                Control block allocation mode which supports "adaptive"
                        and "lfs". In "lfs" mode, there should be no random
                        writes towards main area.
+io_bits=%u             Set the bit size of write IO requests. It should be set
+                       with "mode=lfs".
 
 ================================================================================
 DEBUGFS ENTRIES
@@ -174,7 +177,7 @@ f2fs. Each file shows the whole f2fs information.
 SYSFS ENTRIES
 ================================================================================
 
-Information about mounted f2f2 file systems can be found in
+Information about mounted f2fs file systems can be found in
 /sys/fs/f2fs.  Each mounted filesystem will have a directory in
 /sys/fs/f2fs based on its device name (i.e., /sys/fs/f2fs/sda).
 The files in each per-device directory are shown in table below.

fs/f2fs/checkpoint.c

@@ -249,7 +249,8 @@ static int f2fs_write_meta_page(struct page *page,
 	dec_page_count(sbi, F2FS_DIRTY_META);
 
 	if (wbc->for_reclaim)
-		f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, META, WRITE);
+		f2fs_submit_merged_bio_cond(sbi, page->mapping->host,
+						0, page->index, META, WRITE);
 
 	unlock_page(page);
 
@@ -493,6 +494,7 @@ int acquire_orphan_inode(struct f2fs_sb_info *sbi)
 #ifdef CONFIG_F2FS_FAULT_INJECTION
 	if (time_to_inject(sbi, FAULT_ORPHAN)) {
 		spin_unlock(&im->ino_lock);
+		f2fs_show_injection_info(FAULT_ORPHAN);
 		return -ENOSPC;
 	}
 #endif
@@ -681,8 +683,7 @@ static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr,
 		return -EINVAL;
 	}
 
-	crc = le32_to_cpu(*((__le32 *)((unsigned char *)*cp_block
-							+ crc_offset)));
+	crc = cur_cp_crc(*cp_block);
 	if (!f2fs_crc_valid(sbi, crc, *cp_block, crc_offset)) {
 		f2fs_msg(sbi->sb, KERN_WARNING, "invalid crc value");
 		return -EINVAL;
@@ -891,7 +892,7 @@ int sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type)
 				F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA));
 		return 0;
 	}
-	fi = list_entry(head->next, struct f2fs_inode_info, dirty_list);
+	fi = list_first_entry(head, struct f2fs_inode_info, dirty_list);
 	inode = igrab(&fi->vfs_inode);
 	spin_unlock(&sbi->inode_lock[type]);
 	if (inode) {
@@ -924,7 +925,7 @@ int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi)
 			spin_unlock(&sbi->inode_lock[DIRTY_META]);
 			return 0;
 		}
-		fi = list_entry(head->next, struct f2fs_inode_info,
+		fi = list_first_entry(head, struct f2fs_inode_info,
 							gdirty_list);
 		inode = igrab(&fi->vfs_inode);
 		spin_unlock(&sbi->inode_lock[DIRTY_META]);
@@ -998,8 +999,6 @@ static int block_operations(struct f2fs_sb_info *sbi)
 static void unblock_operations(struct f2fs_sb_info *sbi)
 {
 	up_write(&sbi->node_write);
-
-	build_free_nids(sbi, false);
 	f2fs_unlock_all(sbi);
 }
 
@@ -1025,6 +1024,10 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	spin_lock(&sbi->cp_lock);
 
+	if (cpc->reason == CP_UMOUNT && ckpt->cp_pack_total_block_count >
+			sbi->blocks_per_seg - NM_I(sbi)->nat_bits_blocks)
+		disable_nat_bits(sbi, false);
+
 	if (cpc->reason == CP_UMOUNT)
 		__set_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
 	else
@@ -1137,6 +1140,28 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	start_blk = __start_cp_next_addr(sbi);
 
+	/* write nat bits */
+	if (enabled_nat_bits(sbi, cpc)) {
+		__u64 cp_ver = cur_cp_version(ckpt);
+		unsigned int i;
+		block_t blk;
+
+		cp_ver |= ((__u64)crc32 << 32);
+		*(__le64 *)nm_i->nat_bits = cpu_to_le64(cp_ver);
+
+		blk = start_blk + sbi->blocks_per_seg - nm_i->nat_bits_blocks;
+		for (i = 0; i < nm_i->nat_bits_blocks; i++)
+			update_meta_page(sbi, nm_i->nat_bits +
+					(i << F2FS_BLKSIZE_BITS), blk + i);
+
+		/* Flush all the NAT BITS pages */
+		while (get_pages(sbi, F2FS_DIRTY_META)) {
+			sync_meta_pages(sbi, META, LONG_MAX);
+			if (unlikely(f2fs_cp_error(sbi)))
+				return -EIO;
+		}
+	}
+
 	/* need to wait for end_io results */
 	wait_on_all_pages_writeback(sbi);
 	if (unlikely(f2fs_cp_error(sbi)))
@@ -1248,15 +1273,20 @@ int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	f2fs_flush_merged_bios(sbi);
 
 	/* this is the case of multiple fstrims without any changes */
-	if (cpc->reason == CP_DISCARD && !is_sbi_flag_set(sbi, SBI_IS_DIRTY)) {
-		f2fs_bug_on(sbi, NM_I(sbi)->dirty_nat_cnt);
-		f2fs_bug_on(sbi, SIT_I(sbi)->dirty_sentries);
-		f2fs_bug_on(sbi, prefree_segments(sbi));
-		flush_sit_entries(sbi, cpc);
-		clear_prefree_segments(sbi, cpc);
-		f2fs_wait_all_discard_bio(sbi);
-		unblock_operations(sbi);
-		goto out;
+	if (cpc->reason == CP_DISCARD) {
+		if (!exist_trim_candidates(sbi, cpc)) {
+			unblock_operations(sbi);
+			goto out;
+		}
+
+		if (NM_I(sbi)->dirty_nat_cnt == 0 &&
+				SIT_I(sbi)->dirty_sentries == 0 &&
+				prefree_segments(sbi) == 0) {
+			flush_sit_entries(sbi, cpc);
+			clear_prefree_segments(sbi, cpc);
+			unblock_operations(sbi);
+			goto out;
+		}
 	}
 
 	/*
@@ -1268,17 +1298,15 @@ int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	ckpt->checkpoint_ver = cpu_to_le64(++ckpt_ver);
 
 	/* write cached NAT/SIT entries to NAT/SIT area */
-	flush_nat_entries(sbi);
+	flush_nat_entries(sbi, cpc);
 	flush_sit_entries(sbi, cpc);
 
 	/* unlock all the fs_lock[] in do_checkpoint() */
 	err = do_checkpoint(sbi, cpc);
-	if (err) {
+	if (err)
 		release_discard_addrs(sbi);
-	} else {
+	else
 		clear_prefree_segments(sbi, cpc);
-		f2fs_wait_all_discard_bio(sbi);
-	}
 
 	unblock_operations(sbi);
 	stat_inc_cp_count(sbi->stat_info);

fs/f2fs/debug.c

@@ -50,8 +50,16 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 	si->ndirty_files = sbi->ndirty_inode[FILE_INODE];
 	si->ndirty_all = sbi->ndirty_inode[DIRTY_META];
 	si->inmem_pages = get_pages(sbi, F2FS_INMEM_PAGES);
+	si->aw_cnt = atomic_read(&sbi->aw_cnt);
+	si->max_aw_cnt = atomic_read(&sbi->max_aw_cnt);
 	si->nr_wb_cp_data = get_pages(sbi, F2FS_WB_CP_DATA);
 	si->nr_wb_data = get_pages(sbi, F2FS_WB_DATA);
+	if (SM_I(sbi) && SM_I(sbi)->fcc_info)
+		si->nr_flush =
+			atomic_read(&SM_I(sbi)->fcc_info->submit_flush);
+	if (SM_I(sbi) && SM_I(sbi)->dcc_info)
+		si->nr_discard =
+			atomic_read(&SM_I(sbi)->dcc_info->submit_discard);
 	si->total_count = (int)sbi->user_block_count / sbi->blocks_per_seg;
 	si->rsvd_segs = reserved_segments(sbi);
 	si->overp_segs = overprovision_segments(sbi);
@@ -62,6 +70,8 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 	si->inline_xattr = atomic_read(&sbi->inline_xattr);
 	si->inline_inode = atomic_read(&sbi->inline_inode);
 	si->inline_dir = atomic_read(&sbi->inline_dir);
+	si->append = sbi->im[APPEND_INO].ino_num;
+	si->update = sbi->im[UPDATE_INO].ino_num;
 	si->orphans = sbi->im[ORPHAN_INO].ino_num;
 	si->utilization = utilization(sbi);
 
@@ -183,6 +193,9 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
 	/* build nm */
 	si->base_mem += sizeof(struct f2fs_nm_info);
 	si->base_mem += __bitmap_size(sbi, NAT_BITMAP);
+	si->base_mem += (NM_I(sbi)->nat_bits_blocks << F2FS_BLKSIZE_BITS);
+	si->base_mem += NM_I(sbi)->nat_blocks * NAT_ENTRY_BITMAP_SIZE;
+	si->base_mem += NM_I(sbi)->nat_blocks / 8;
 
 get_cache:
 	si->cache_mem = 0;
@@ -192,8 +205,10 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
 		si->cache_mem += sizeof(struct f2fs_gc_kthread);
 
 	/* build merge flush thread */
-	if (SM_I(sbi)->cmd_control_info)
+	if (SM_I(sbi)->fcc_info)
 		si->cache_mem += sizeof(struct flush_cmd_control);
+	if (SM_I(sbi)->dcc_info)
+		si->cache_mem += sizeof(struct discard_cmd_control);
 
 	/* free nids */
 	si->cache_mem += (NM_I(sbi)->nid_cnt[FREE_NID_LIST] +
@@ -254,8 +269,8 @@ static int stat_show(struct seq_file *s, void *v)
 			   si->inline_inode);
 		seq_printf(s, "  - Inline_dentry Inode: %u\n",
 			   si->inline_dir);
-		seq_printf(s, "  - Orphan Inode: %u\n",
-			   si->orphans);
+		seq_printf(s, "  - Orphan/Append/Update Inode: %u, %u, %u\n",
+			   si->orphans, si->append, si->update);
 		seq_printf(s, "\nMain area: %d segs, %d secs %d zones\n",
 			   si->main_area_segs, si->main_area_sections,
 			   si->main_area_zones);
@@ -314,8 +329,11 @@ 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, "  - inmem: %4d, wb_cp_data: %4d, wb_data: %4d\n",
-			   si->inmem_pages, si->nr_wb_cp_data, si->nr_wb_data);
+		seq_printf(s, "  - IO (CP: %4d, Data: %4d, Flush: %4d, Discard: %4d)\n",
+			   si->nr_wb_cp_data, si->nr_wb_data,
+			   si->nr_flush, si->nr_discard);
+		seq_printf(s, "  - inmem: %4d, atomic IO: %4d (Max. %4d)\n",
+			   si->inmem_pages, si->aw_cnt, si->max_aw_cnt);
 		seq_printf(s, "  - nodes: %4d in %4d\n",
 			   si->ndirty_node, si->node_pages);
 		seq_printf(s, "  - dents: %4d in dirs:%4d (%4d)\n",
@@ -414,6 +432,9 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi)
 	atomic_set(&sbi->inline_dir, 0);
 	atomic_set(&sbi->inplace_count, 0);
 
+	atomic_set(&sbi->aw_cnt, 0);
+	atomic_set(&sbi->max_aw_cnt, 0);
+
 	mutex_lock(&f2fs_stat_mutex);
 	list_add_tail(&si->stat_list, &f2fs_stat_list);
 	mutex_unlock(&f2fs_stat_mutex);

fs/f2fs/dir.c

@@ -207,9 +207,13 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
 		f2fs_put_page(dentry_page, 0);
 	}
 
-	if (!de && room && F2FS_I(dir)->chash != namehash) {
-		F2FS_I(dir)->chash = namehash;
-		F2FS_I(dir)->clevel = level;
+	/* This is to increase the speed of f2fs_create */
+	if (!de && room) {
+		F2FS_I(dir)->task = current;
+		if (F2FS_I(dir)->chash != namehash) {
+			F2FS_I(dir)->chash = namehash;
+			F2FS_I(dir)->clevel = level;
+		}
 	}
 
 	return de;
@@ -548,8 +552,10 @@ int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name,
 
 start:
 #ifdef CONFIG_F2FS_FAULT_INJECTION
-	if (time_to_inject(F2FS_I_SB(dir), FAULT_DIR_DEPTH))
+	if (time_to_inject(F2FS_I_SB(dir), FAULT_DIR_DEPTH)) {
+		f2fs_show_injection_info(FAULT_DIR_DEPTH);
 		return -ENOSPC;
+	}
 #endif
 	if (unlikely(current_depth == MAX_DIR_HASH_DEPTH))
 		return -ENOSPC;
@@ -646,14 +652,34 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name,
 				struct inode *inode, nid_t ino, umode_t mode)
 {
 	struct fscrypt_name fname;
+	struct page *page = NULL;
+	struct f2fs_dir_entry *de = NULL;
 	int err;
 
 	err = fscrypt_setup_filename(dir, name, 0, &fname);
 	if (err)
 		return err;
 
-	err = __f2fs_do_add_link(dir, &fname, inode, ino, mode);
-
+	/*
+	 * An immature stakable filesystem shows a race condition between lookup
+	 * and create. If we have same task when doing lookup and create, it's
+	 * definitely fine as expected by VFS normally. Otherwise, let's just
+	 * verify on-disk dentry one more time, which guarantees filesystem
+	 * consistency more.
+	 */
+	if (current != F2FS_I(dir)->task) {
+		de = __f2fs_find_entry(dir, &fname, &page);
+		F2FS_I(dir)->task = NULL;
+	}
+	if (de) {
+		f2fs_dentry_kunmap(dir, page);
+		f2fs_put_page(page, 0);
+		err = -EEXIST;
+	} else if (IS_ERR(page)) {
+		err = PTR_ERR(page);
+	} else {
+		err = __f2fs_do_add_link(dir, &fname, inode, ino, mode);
+	}
 	fscrypt_free_filename(&fname);
 	return err;
 }

fs/f2fs/extent_cache.c

@@ -77,7 +77,7 @@ static struct extent_tree *__grab_extent_tree(struct inode *inode)
 	struct extent_tree *et;
 	nid_t ino = inode->i_ino;
 
-	down_write(&sbi->extent_tree_lock);
+	mutex_lock(&sbi->extent_tree_lock);
 	et = radix_tree_lookup(&sbi->extent_tree_root, ino);
 	if (!et) {
 		et = f2fs_kmem_cache_alloc(extent_tree_slab, GFP_NOFS);
@@ -94,7 +94,7 @@ static struct extent_tree *__grab_extent_tree(struct inode *inode)
 		atomic_dec(&sbi->total_zombie_tree);
 		list_del_init(&et->list);
 	}
-	up_write(&sbi->extent_tree_lock);
+	mutex_unlock(&sbi->extent_tree_lock);
 
 	/* never died until evict_inode */
 	F2FS_I(inode)->extent_tree = et;
@@ -311,28 +311,24 @@ static struct extent_node *__lookup_extent_tree_ret(struct extent_tree *et,
 	tmp_node = parent;
 	if (parent && fofs > en->ei.fofs)
 		tmp_node = rb_next(parent);
-	*next_ex = tmp_node ?
-		rb_entry(tmp_node, struct extent_node, rb_node) : NULL;
+	*next_ex = rb_entry_safe(tmp_node, struct extent_node, rb_node);
 
 	tmp_node = parent;
 	if (parent && fofs < en->ei.fofs)
 		tmp_node = rb_prev(parent);
-	*prev_ex = tmp_node ?
-		rb_entry(tmp_node, struct extent_node, rb_node) : NULL;
+	*prev_ex = rb_entry_safe(tmp_node, struct extent_node, rb_node);
 	return NULL;
 
 lookup_neighbors:
 	if (fofs == en->ei.fofs) {
 		/* lookup prev node for merging backward later */
 		tmp_node = rb_prev(&en->rb_node);
-		*prev_ex = tmp_node ?
-			rb_entry(tmp_node, struct extent_node, rb_node) : NULL;
+		*prev_ex = rb_entry_safe(tmp_node, struct extent_node, rb_node);
 	}
 	if (fofs == en->ei.fofs + en->ei.len - 1) {
 		/* lookup next node for merging frontward later */
 		tmp_node = rb_next(&en->rb_node);
-		*next_ex = tmp_node ?
-			rb_entry(tmp_node, struct extent_node, rb_node) : NULL;
+		*next_ex = rb_entry_safe(tmp_node, struct extent_node, rb_node);
 	}
 	return en;
 }
@@ -352,11 +348,12 @@ static struct extent_node *__try_merge_extent_node(struct inode *inode,
 	}
 
 	if (next_ex && __is_front_mergeable(ei, &next_ex->ei)) {
-		if (en)
-			__release_extent_node(sbi, et, prev_ex);
 		next_ex->ei.fofs = ei->fofs;
 		next_ex->ei.blk = ei->blk;
 		next_ex->ei.len += ei->len;
+		if (en)
+			__release_extent_node(sbi, et, prev_ex);
+
 		en = next_ex;
 	}
 
@@ -416,7 +413,7 @@ static struct extent_node *__insert_extent_tree(struct inode *inode,
 	return en;
 }
 
-static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
+static void f2fs_update_extent_tree_range(struct inode *inode,
 				pgoff_t fofs, block_t blkaddr, unsigned int len)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -429,7 +426,7 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
 	unsigned int pos = (unsigned int)fofs;
 
 	if (!et)
-		return false;
+		return;
 
 	trace_f2fs_update_extent_tree_range(inode, fofs, blkaddr, len);
 
@@ -437,7 +434,7 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
 
 	if (is_inode_flag_set(inode, FI_NO_EXTENT)) {
 		write_unlock(&et->lock);
-		return false;
+		return;
 	}
 
 	prev = et->largest;
@@ -492,9 +489,8 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
 		if (!next_en) {
 			struct rb_node *node = rb_next(&en->rb_node);
 
-			next_en = node ?
-				rb_entry(node, struct extent_node, rb_node)
-				: NULL;
+			next_en = rb_entry_safe(node, struct extent_node,
+						rb_node);
 		}
 
 		if (parts)
@@ -535,8 +531,6 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
 		__free_extent_tree(sbi, et);
 
 	write_unlock(&et->lock);
-
-	return !__is_extent_same(&prev, &et->largest);
 }
 
 unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
@@ -552,7 +546,7 @@ unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
 	if (!atomic_read(&sbi->total_zombie_tree))
 		goto free_node;
 
-	if (!down_write_trylock(&sbi->extent_tree_lock))
+	if (!mutex_trylock(&sbi->extent_tree_lock))
 		goto out;
 
 	/* 1. remove unreferenced extent tree */
@@ -574,11 +568,11 @@ unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
 			goto unlock_out;
 		cond_resched();
 	}
-	up_write(&sbi->extent_tree_lock);
+	mutex_unlock(&sbi->extent_tree_lock);
 
 free_node:
 	/* 2. remove LRU extent entries */
-	if (!down_write_trylock(&sbi->extent_tree_lock))
+	if (!mutex_trylock(&sbi->extent_tree_lock))
 		goto out;
 
 	remained = nr_shrink - (node_cnt + tree_cnt);
@@ -608,7 +602,7 @@ unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
 	spin_unlock(&sbi->extent_lock);
 
 unlock_out:
-	up_write(&sbi->extent_tree_lock);
+	mutex_unlock(&sbi->extent_tree_lock);
 out:
 	trace_f2fs_shrink_extent_tree(sbi, node_cnt, tree_cnt);
 
@@ -655,10 +649,10 @@ void f2fs_destroy_extent_tree(struct inode *inode)
 
 	if (inode->i_nlink && !is_bad_inode(inode) &&
 					atomic_read(&et->node_cnt)) {
-		down_write(&sbi->extent_tree_lock);
+		mutex_lock(&sbi->extent_tree_lock);
 		list_add_tail(&et->list, &sbi->zombie_list);
 		atomic_inc(&sbi->total_zombie_tree);
-		up_write(&sbi->extent_tree_lock);
+		mutex_unlock(&sbi->extent_tree_lock);
 		return;
 	}
 
@@ -666,12 +660,12 @@ void f2fs_destroy_extent_tree(struct inode *inode)
 	node_cnt = f2fs_destroy_extent_node(inode);
 
 	/* delete extent tree entry in radix tree */
-	down_write(&sbi->extent_tree_lock);
+	mutex_lock(&sbi->extent_tree_lock);
 	f2fs_bug_on(sbi, atomic_read(&et->node_cnt));
 	radix_tree_delete(&sbi->extent_tree_root, inode->i_ino);
 	kmem_cache_free(extent_tree_slab, et);
 	atomic_dec(&sbi->total_ext_tree);
-	up_write(&sbi->extent_tree_lock);
+	mutex_unlock(&sbi->extent_tree_lock);
 
 	F2FS_I(inode)->extent_tree = NULL;
 
@@ -718,7 +712,7 @@ void f2fs_update_extent_cache_range(struct dnode_of_data *dn,
 void init_extent_cache_info(struct f2fs_sb_info *sbi)
 {
 	INIT_RADIX_TREE(&sbi->extent_tree_root, GFP_NOIO);
-	init_rwsem(&sbi->extent_tree_lock);
+	mutex_init(&sbi->extent_tree_lock);
 	INIT_LIST_HEAD(&sbi->extent_list);
 	spin_lock_init(&sbi->extent_lock);
 	atomic_set(&sbi->total_ext_tree, 0);

fs/f2fs/file.c

@@ -20,6 +20,7 @@
 #include <linux/uaccess.h>
 #include <linux/mount.h>
 #include <linux/pagevec.h>
+#include <linux/uio.h>
 #include <linux/uuid.h>
 #include <linux/file.h>
 
@@ -140,8 +141,6 @@ static inline bool need_do_checkpoint(struct inode *inode)
 		need_cp = true;
 	else if (!is_checkpointed_node(sbi, F2FS_I(inode)->i_pino))
 		need_cp = true;
-	else if (F2FS_I(inode)->xattr_ver == cur_cp_version(F2FS_CKPT(sbi)))
-		need_cp = true;
 	else if (test_opt(sbi, FASTBOOT))
 		need_cp = true;
 	else if (sbi->active_logs == 2)
@@ -167,7 +166,6 @@ static void try_to_fix_pino(struct inode *inode)
 	nid_t pino;
 
 	down_write(&fi->i_sem);
-	fi->xattr_ver = 0;
 	if (file_wrong_pino(inode) && inode->i_nlink == 1 &&
 			get_parent_ino(inode, &pino)) {
 		f2fs_i_pino_write(inode, pino);
@@ -276,7 +274,8 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
 flush_out:
 	remove_ino_entry(sbi, ino, UPDATE_INO);
 	clear_inode_flag(inode, FI_UPDATE_WRITE);
-	ret = f2fs_issue_flush(sbi);
+	if (!atomic)
+		ret = f2fs_issue_flush(sbi);
 	f2fs_update_time(sbi, REQ_TIME);
 out:
 	trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
@@ -567,8 +566,9 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock)
 	}
 
 	if (f2fs_has_inline_data(inode)) {
-		if (truncate_inline_inode(ipage, from))
-			set_page_dirty(ipage);
+		truncate_inline_inode(ipage, from);
+		if (from == 0)
+			clear_inode_flag(inode, FI_DATA_EXIST);
 		f2fs_put_page(ipage, 1);
 		truncate_page = true;
 		goto out;
@@ -1541,6 +1541,8 @@ static int f2fs_ioc_start_atomic_write(struct file *filp)
 	if (ret)
 		clear_inode_flag(inode, FI_ATOMIC_FILE);
 out:
+	stat_inc_atomic_write(inode);
+	stat_update_max_atomic_write(inode);
 	inode_unlock(inode);
 	mnt_drop_write_file(filp);
 	return ret;
@@ -1564,15 +1566,18 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp)
 		goto err_out;
 
 	if (f2fs_is_atomic_file(inode)) {
-		clear_inode_flag(inode, FI_ATOMIC_FILE);
 		ret = commit_inmem_pages(inode);
-		if (ret) {
-			set_inode_flag(inode, FI_ATOMIC_FILE);
+		if (ret)
 			goto err_out;
+
+		ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
+		if (!ret) {
+			clear_inode_flag(inode, FI_ATOMIC_FILE);
+			stat_dec_atomic_write(inode);
 		}
+	} else {
+		ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
 	}
-
-	ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
 err_out:
 	inode_unlock(inode);
 	mnt_drop_write_file(filp);
@@ -1870,7 +1875,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
 {
 	struct inode *inode = file_inode(filp);
 	struct f2fs_map_blocks map = { .m_next_pgofs = NULL };
-	struct extent_info ei;
+	struct extent_info ei = {0,0,0};
 	pgoff_t pg_start, pg_end;
 	unsigned int blk_per_seg = sbi->blocks_per_seg;
 	unsigned int total = 0, sec_num;
@@ -2250,8 +2255,12 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	inode_lock(inode);
 	ret = generic_write_checks(iocb, from);
 	if (ret > 0) {
-		int err = f2fs_preallocate_blocks(iocb, from);
+		int err;
+
+		if (iov_iter_fault_in_readable(from, iov_iter_count(from)))
+			set_inode_flag(inode, FI_NO_PREALLOC);
 
+		err = f2fs_preallocate_blocks(iocb, from);
 		if (err) {
 			inode_unlock(inode);
 			return err;
@@ -2259,6 +2268,7 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		blk_start_plug(&plug);
 		ret = __generic_file_write_iter(iocb, from);
 		blk_finish_plug(&plug);
+		clear_inode_flag(inode, FI_NO_PREALLOC);
 	}
 	inode_unlock(inode);
 

fs/f2fs/gc.c

@@ -48,8 +48,10 @@ static int gc_thread_func(void *data)
 		}
 
 #ifdef CONFIG_F2FS_FAULT_INJECTION
-		if (time_to_inject(sbi, FAULT_CHECKPOINT))
+		if (time_to_inject(sbi, FAULT_CHECKPOINT)) {
+			f2fs_show_injection_info(FAULT_CHECKPOINT);
 			f2fs_stop_checkpoint(sbi, false);
+		}
 #endif
 
 		/*
@@ -166,7 +168,8 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type,
 		p->ofs_unit = sbi->segs_per_sec;
 	}
 
-	if (p->max_search > sbi->max_victim_search)
+	/* we need to check every dirty segments in the FG_GC case */
+	if (gc_type != FG_GC && p->max_search > sbi->max_victim_search)
 		p->max_search = sbi->max_victim_search;
 
 	p->offset = sbi->last_victim[p->gc_mode];
@@ -199,6 +202,10 @@ static unsigned int check_bg_victims(struct f2fs_sb_info *sbi)
 	for_each_set_bit(secno, dirty_i->victim_secmap, MAIN_SECS(sbi)) {
 		if (sec_usage_check(sbi, secno))
 			continue;
+
+		if (no_fggc_candidate(sbi, secno))
+			continue;
+
 		clear_bit(secno, dirty_i->victim_secmap);
 		return secno * sbi->segs_per_sec;
 	}
@@ -237,6 +244,16 @@ 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, sbi->segs_per_sec);
+
+	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)
 {
@@ -245,7 +262,7 @@ static inline unsigned int get_gc_cost(struct f2fs_sb_info *sbi,
 
 	/* alloc_mode == LFS */
 	if (p->gc_mode == GC_GREEDY)
-		return get_valid_blocks(sbi, segno, sbi->segs_per_sec);
+		return get_greedy_cost(sbi, segno);
 	else
 		return get_cb_cost(sbi, segno);
 }
@@ -322,13 +339,15 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
 			nsearched++;
 		}
 
-
 		secno = GET_SECNO(sbi, segno);
 
 		if (sec_usage_check(sbi, secno))
 			goto next;
 		if (gc_type == BG_GC && test_bit(secno, dirty_i->victim_secmap))
 			goto next;
+		if (gc_type == FG_GC && p.alloc_mode == LFS &&
+					no_fggc_candidate(sbi, secno))
+			goto next;
 
 		cost = get_gc_cost(sbi, segno, &p);
 
@@ -569,6 +588,9 @@ static void move_encrypted_block(struct inode *inode, block_t bidx,
 	if (!check_valid_map(F2FS_I_SB(inode), segno, off))
 		goto out;
 
+	if (f2fs_is_atomic_file(inode))
+		goto out;
+
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
 	err = get_dnode_of_data(&dn, bidx, LOOKUP_NODE);
 	if (err)
@@ -661,6 +683,9 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type,
 	if (!check_valid_map(F2FS_I_SB(inode), segno, off))
 		goto out;
 
+	if (f2fs_is_atomic_file(inode))
+		goto out;
+
 	if (gc_type == BG_GC) {
 		if (PageWriteback(page))
 			goto out;
@@ -921,8 +946,6 @@ int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, bool background)
 
 	cpc.reason = __get_cp_reason(sbi);
 gc_more:
-	segno = NULL_SEGNO;
-
 	if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE)))
 		goto stop;
 	if (unlikely(f2fs_cp_error(sbi))) {
@@ -930,30 +953,23 @@ int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, bool background)
 		goto stop;
 	}
 
-	if (gc_type == BG_GC && has_not_enough_free_secs(sbi, sec_freed, 0)) {
-		gc_type = FG_GC;
+	if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0)) {
 		/*
-		 * If there is no victim and no prefree segment but still not
-		 * enough free sections, we should flush dent/node blocks and do
-		 * garbage collections.
+		 * For example, if there are many prefree_segments below given
+		 * threshold, we can make them free by checkpoint. Then, we
+		 * secure free segments which doesn't need fggc any more.
 		 */
-		if (__get_victim(sbi, &segno, gc_type) ||
-						prefree_segments(sbi)) {
-			ret = write_checkpoint(sbi, &cpc);
-			if (ret)
-				goto stop;
-			segno = NULL_SEGNO;
-		} else if (has_not_enough_free_secs(sbi, 0, 0)) {
-			ret = write_checkpoint(sbi, &cpc);
-			if (ret)
-				goto stop;
-		}
-	} else if (gc_type == BG_GC && !background) {
-		/* f2fs_balance_fs doesn't need to do BG_GC in critical path. */
-		goto stop;
+		ret = write_checkpoint(sbi, &cpc);
+		if (ret)
+			goto stop;
+		if (has_not_enough_free_secs(sbi, 0, 0))
+			gc_type = FG_GC;
 	}
 
-	if (segno == NULL_SEGNO && !__get_victim(sbi, &segno, gc_type))
+	/* f2fs_balance_fs doesn't need to do BG_GC in critical path. */
+	if (gc_type == BG_GC && !background)
+		goto stop;
+	if (!__get_victim(sbi, &segno, gc_type))
 		goto stop;
 	ret = 0;
 
@@ -983,5 +999,16 @@ int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, bool background)
 
 void build_gc_manager(struct f2fs_sb_info *sbi)
 {
+	u64 main_count, resv_count, ovp_count, blocks_per_sec;
+
 	DIRTY_I(sbi)->v_ops = &default_v_ops;
+
+	/* threshold of # of valid blocks in a section for victims of FG_GC */
+	main_count = SM_I(sbi)->main_segments << sbi->log_blocks_per_seg;
+	resv_count = SM_I(sbi)->reserved_segments << sbi->log_blocks_per_seg;
+	ovp_count = SM_I(sbi)->ovp_segments << sbi->log_blocks_per_seg;
+	blocks_per_sec = sbi->blocks_per_seg * sbi->segs_per_sec;
+
+	sbi->fggc_threshold = div64_u64((main_count - ovp_count) * blocks_per_sec,
+					(main_count - resv_count));
 }

fs/f2fs/inode.c

@@ -373,8 +373,10 @@ void f2fs_evict_inode(struct inode *inode)
 		goto no_delete;
 
 #ifdef CONFIG_F2FS_FAULT_INJECTION
-	if (time_to_inject(sbi, FAULT_EVICT_INODE))
+	if (time_to_inject(sbi, FAULT_EVICT_INODE)) {
+		f2fs_show_injection_info(FAULT_EVICT_INODE);
 		goto no_delete;
+	}
 #endif
 
 	remove_ino_entry(sbi, inode->i_ino, APPEND_INO);

fs/f2fs/namei.c

@@ -321,9 +321,9 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
 		if (err)
 			goto err_out;
 	}
-	if (!IS_ERR(inode) && f2fs_encrypted_inode(dir) &&
-			(S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) &&
-			!fscrypt_has_permitted_context(dir, inode)) {
+	if (f2fs_encrypted_inode(dir) &&
+	    (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) &&
+	    !fscrypt_has_permitted_context(dir, inode)) {
 		bool nokey = f2fs_encrypted_inode(inode) &&
 			!fscrypt_has_encryption_key(inode);
 		err = nokey ? -ENOKEY : -EPERM;
@@ -663,6 +663,12 @@ 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 ((f2fs_encrypted_inode(old_dir) &&
+			!fscrypt_has_encryption_key(old_dir)) ||
+			(f2fs_encrypted_inode(new_dir) &&
+			!fscrypt_has_encryption_key(new_dir)))
+		return -ENOKEY;
+
 	if ((old_dir != new_dir) && f2fs_encrypted_inode(new_dir) &&
 			!fscrypt_has_permitted_context(new_dir, old_inode)) {
 		err = -EPERM;
@@ -843,6 +849,12 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 	int old_nlink = 0, new_nlink = 0;
 	int err = -ENOENT;
 
+	if ((f2fs_encrypted_inode(old_dir) &&
+			!fscrypt_has_encryption_key(old_dir)) ||
+			(f2fs_encrypted_inode(new_dir) &&
+			!fscrypt_has_encryption_key(new_dir)))
+		return -ENOKEY;
+
 	if ((f2fs_encrypted_inode(old_dir) || f2fs_encrypted_inode(new_dir)) &&
 			(old_dir != new_dir) &&
 			(!fscrypt_has_permitted_context(new_dir, old_inode) ||

fs/f2fs/node.h

@@ -174,7 +174,7 @@ static inline void next_free_nid(struct f2fs_sb_info *sbi, nid_t *nid)
 		spin_unlock(&nm_i->nid_list_lock);
 		return;
 	}
-	fnid = list_entry(nm_i->nid_list[FREE_NID_LIST].next,
+	fnid = list_first_entry(&nm_i->nid_list[FREE_NID_LIST],
 						struct free_nid, list);
 	*nid = fnid->nid;
 	spin_unlock(&nm_i->nid_list_lock);
@@ -186,6 +186,12 @@ static inline void next_free_nid(struct f2fs_sb_info *sbi, nid_t *nid)
 static inline void get_nat_bitmap(struct f2fs_sb_info *sbi, void *addr)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
+
+#ifdef CONFIG_F2FS_CHECK_FS
+	if (memcmp(nm_i->nat_bitmap, nm_i->nat_bitmap_mir,
+						nm_i->bitmap_size))
+		f2fs_bug_on(sbi, 1);
+#endif
 	memcpy(addr, nm_i->nat_bitmap, nm_i->bitmap_size);
 }
 
@@ -228,6 +234,9 @@ static inline void set_to_next_nat(struct f2fs_nm_info *nm_i, nid_t start_nid)
 	unsigned int block_off = NAT_BLOCK_OFFSET(start_nid);
 
 	f2fs_change_bit(block_off, nm_i->nat_bitmap);
+#ifdef CONFIG_F2FS_CHECK_FS
+	f2fs_change_bit(block_off, nm_i->nat_bitmap_mir);
+#endif
 }
 
 static inline nid_t ino_of_node(struct page *node_page)
@@ -291,14 +300,11 @@ static inline void fill_node_footer_blkaddr(struct page *page, block_t blkaddr)
 {
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(F2FS_P_SB(page));
 	struct f2fs_node *rn = F2FS_NODE(page);
-	size_t crc_offset = le32_to_cpu(ckpt->checksum_offset);
-	__u64 cp_ver = le64_to_cpu(ckpt->checkpoint_ver);
+	__u64 cp_ver = cur_cp_version(ckpt);
+
+	if (__is_set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG))
+		cp_ver |= (cur_cp_crc(ckpt) << 32);
 
-	if (__is_set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG)) {
-		__u64 crc = le32_to_cpu(*((__le32 *)
-				((unsigned char *)ckpt + crc_offset)));
-		cp_ver |= (crc << 32);
-	}
 	rn->footer.cp_ver = cpu_to_le64(cp_ver);
 	rn->footer.next_blkaddr = cpu_to_le32(blkaddr);
 }
@@ -306,14 +312,11 @@ static inline void fill_node_footer_blkaddr(struct page *page, block_t blkaddr)
 static inline bool is_recoverable_dnode(struct page *page)
 {
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(F2FS_P_SB(page));
-	size_t crc_offset = le32_to_cpu(ckpt->checksum_offset);
 	__u64 cp_ver = cur_cp_version(ckpt);
 
-	if (__is_set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG)) {
-		__u64 crc = le32_to_cpu(*((__le32 *)
-				((unsigned char *)ckpt + crc_offset)));
-		cp_ver |= (crc << 32);
-	}
+	if (__is_set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG))
+		cp_ver |= (cur_cp_crc(ckpt) << 32);
+
 	return cp_ver == cpver_of_node(page);
 }
 
@@ -343,7 +346,7 @@ static inline bool IS_DNODE(struct page *node_page)
 	unsigned int ofs = ofs_of_node(node_page);
 
 	if (f2fs_has_xattr_block(ofs))
-		return false;
+		return true;
 
 	if (ofs == 3 || ofs == 4 + NIDS_PER_BLOCK ||
 			ofs == 5 + 2 * NIDS_PER_BLOCK)

fs/f2fs/recovery.c

@@ -378,11 +378,9 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 	if (IS_INODE(page)) {
 		recover_inline_xattr(inode, page);
 	} else if (f2fs_has_xattr_block(ofs_of_node(page))) {
-		/*
-		 * Deprecated; xattr blocks should be found from cold log.
-		 * But, we should remain this for backward compatibility.
-		 */
-		recover_xattr_data(inode, page, blkaddr);
+		err = recover_xattr_data(inode, page, blkaddr);
+		if (!err)
+			recovered++;
 		goto out;
 	}
 
@@ -428,8 +426,9 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 		}
 
 		if (!file_keep_isize(inode) &&
-				(i_size_read(inode) <= (start << PAGE_SHIFT)))
-			f2fs_i_size_write(inode, (start + 1) << PAGE_SHIFT);
+			(i_size_read(inode) <= ((loff_t)start << PAGE_SHIFT)))
+			f2fs_i_size_write(inode,
+				(loff_t)(start + 1) << PAGE_SHIFT);
 
 		/*
 		 * dest is reserved block, invalidate src block
@@ -552,10 +551,8 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list,
 
 int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
 {
-	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
 	struct list_head inode_list;
 	struct list_head dir_list;
-	block_t blkaddr;
 	int err;
 	int ret = 0;
 	bool need_writecp = false;
@@ -571,8 +568,6 @@ int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
 	/* prevent checkpoint */
 	mutex_lock(&sbi->cp_mutex);
 
-	blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
-
 	/* step #1: find fsynced inode numbers */
 	err = find_fsync_dnodes(sbi, &inode_list);
 	if (err || list_empty(&inode_list))

fs/f2fs/segment.h

@@ -164,6 +164,9 @@ struct seg_entry {
 	unsigned int ckpt_valid_blocks:10;	/* # of valid blocks last cp */
 	unsigned int padding:6;		/* padding */
 	unsigned char *cur_valid_map;	/* validity bitmap of blocks */
+#ifdef CONFIG_F2FS_CHECK_FS
+	unsigned char *cur_valid_map_mir;	/* mirror of current valid bitmap */
+#endif
 	/*
 	 * # of valid blocks and the validity bitmap stored in the the last
 	 * checkpoint pack. This information is used by the SSR mode.
@@ -186,9 +189,12 @@ struct segment_allocation {
  * the page is atomically written, and it is in inmem_pages list.
  */
 #define ATOMIC_WRITTEN_PAGE		((unsigned long)-1)
+#define DUMMY_WRITTEN_PAGE		((unsigned long)-2)
 
 #define IS_ATOMIC_WRITTEN_PAGE(page)			\
 		(page_private(page) == (unsigned long)ATOMIC_WRITTEN_PAGE)
+#define IS_DUMMY_WRITTEN_PAGE(page)			\
+		(page_private(page) == (unsigned long)DUMMY_WRITTEN_PAGE)
 
 struct inmem_pages {
 	struct list_head list;
@@ -203,6 +209,9 @@ struct sit_info {
 	block_t sit_blocks;		/* # of blocks used by SIT area */
 	block_t written_valid_blocks;	/* # of valid blocks in main area */
 	char *sit_bitmap;		/* SIT bitmap pointer */
+#ifdef CONFIG_F2FS_CHECK_FS
+	char *sit_bitmap_mir;		/* SIT bitmap mirror */
+#endif
 	unsigned int bitmap_size;	/* SIT bitmap size */
 
 	unsigned long *tmp_map;			/* bitmap for temporal use */
@@ -317,6 +326,9 @@ static inline void seg_info_from_raw_sit(struct seg_entry *se,
 	se->ckpt_valid_blocks = GET_SIT_VBLOCKS(rs);
 	memcpy(se->cur_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
 	memcpy(se->ckpt_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
+#ifdef CONFIG_F2FS_CHECK_FS
+	memcpy(se->cur_valid_map_mir, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
+#endif
 	se->type = GET_SIT_TYPE(rs);
 	se->mtime = le64_to_cpu(rs->mtime);
 }
@@ -414,6 +426,12 @@ static inline void get_sit_bitmap(struct f2fs_sb_info *sbi,
 		void *dst_addr)
 {
 	struct sit_info *sit_i = SIT_I(sbi);
+
+#ifdef CONFIG_F2FS_CHECK_FS
+	if (memcmp(sit_i->sit_bitmap, sit_i->sit_bitmap_mir,
+						sit_i->bitmap_size))
+		f2fs_bug_on(sbi, 1);
+#endif
 	memcpy(dst_addr, sit_i->sit_bitmap, sit_i->bitmap_size);
 }
 
@@ -634,6 +652,12 @@ static inline pgoff_t current_sit_addr(struct f2fs_sb_info *sbi,
 
 	check_seg_range(sbi, start);
 
+#ifdef CONFIG_F2FS_CHECK_FS
+	if (f2fs_test_bit(offset, sit_i->sit_bitmap) !=
+			f2fs_test_bit(offset, sit_i->sit_bitmap_mir))
+		f2fs_bug_on(sbi, 1);
+#endif
+
 	/* calculate sit block address */
 	if (f2fs_test_bit(offset, sit_i->sit_bitmap))
 		blk_addr += sit_i->sit_blocks;
@@ -659,6 +683,9 @@ static inline void set_to_next_sit(struct sit_info *sit_i, unsigned int start)
 	unsigned int block_off = SIT_BLOCK_OFFSET(start);
 
 	f2fs_change_bit(block_off, sit_i->sit_bitmap);
+#ifdef CONFIG_F2FS_CHECK_FS
+	f2fs_change_bit(block_off, sit_i->sit_bitmap_mir);
+#endif
 }
 
 static inline unsigned long long get_mtime(struct f2fs_sb_info *sbi)
@@ -689,6 +716,15 @@ static inline block_t sum_blk_addr(struct f2fs_sb_info *sbi, int base, int type)
 				- (base + 1) + type;
 }
 
+static inline bool no_fggc_candidate(struct f2fs_sb_info *sbi,
+						unsigned int secno)
+{
+	if (get_valid_blocks(sbi, secno, sbi->segs_per_sec) >=
+						sbi->fggc_threshold)
+		return true;
+	return false;
+}
+
 static inline bool sec_usage_check(struct f2fs_sb_info *sbi, unsigned int secno)
 {
 	if (IS_CURSEC(sbi, secno) || (sbi->cur_victim_sec == secno))
@@ -700,8 +736,8 @@ static inline bool sec_usage_check(struct f2fs_sb_info *sbi, unsigned int secno)
  * It is very important to gather dirty pages and write at once, so that we can
  * submit a big bio without interfering other data writes.
  * By default, 512 pages for directory data,
- * 512 pages (2MB) * 3 for three types of nodes, and
- * max_bio_blocks for meta are set.
+ * 512 pages (2MB) * 8 for nodes, and
+ * 256 pages * 8 for meta are set.
  */
 static inline int nr_pages_to_skip(struct f2fs_sb_info *sbi, int type)
 {

fs/f2fs/xattr.c

@@ -217,6 +217,112 @@ 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,
+					size_t len, const char *name)
+{
+	struct f2fs_xattr_entry *entry;
+	unsigned int inline_size = F2FS_INLINE_XATTR_ADDRS << 2;
+
+	list_for_each_xattr(entry, base_addr) {
+		if ((void *)entry + sizeof(__u32) > base_addr + inline_size ||
+			(void *)XATTR_NEXT_ENTRY(entry) + sizeof(__u32) >
+			base_addr + inline_size) {
+			*last_addr = entry;
+			return NULL;
+		}
+		if (entry->e_name_index != index)
+			continue;
+		if (entry->e_name_len != len)
+			continue;
+		if (!memcmp(entry->e_name, name, len))
+			break;
+	}
+	return entry;
+}
+
+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;
+	unsigned int inline_size = 0;
+	int err = 0;
+
+	inline_size = inline_xattr_size(inode);
+
+	if (!size && !inline_size)
+		return -ENODATA;
+
+	txattr_addr = kzalloc(inline_size + size + sizeof(__u32),
+							GFP_F2FS_ZERO);
+	if (!txattr_addr)
+		return -ENOMEM;
+
+	/* 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);
+				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,
+						index, len, name);
+		if (*xe)
+			goto check;
+	}
+
+	/* 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);
+			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
+		cur_addr = txattr_addr;
+
+	*xe = __find_xattr(cur_addr, index, len, name);
+check:
+	if (IS_XATTR_LAST_ENTRY(*xe)) {
+		err = -ENODATA;
+		goto out;
+	}
+
+	*base_addr = txattr_addr;
+	return 0;
+out:
+	kzfree(txattr_addr);
+	return err;
+}
+
 static int read_all_xattrs(struct inode *inode, struct page *ipage,
 							void **base_addr)
 {
@@ -348,23 +454,20 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
 	}
 
 	xattr_addr = page_address(xpage);
-	memcpy(xattr_addr, txattr_addr + inline_size, PAGE_SIZE -
-						sizeof(struct node_footer));
+	memcpy(xattr_addr, txattr_addr + inline_size, MAX_XATTR_BLOCK_SIZE);
 	set_page_dirty(xpage);
 	f2fs_put_page(xpage, 1);
 
-	/* need to checkpoint during fsync */
-	F2FS_I(inode)->xattr_ver = cur_cp_version(F2FS_CKPT(sbi));
 	return 0;
 }
 
 int f2fs_getxattr(struct inode *inode, int index, const char *name,
 		void *buffer, size_t buffer_size, struct page *ipage)
 {
-	struct f2fs_xattr_entry *entry;
-	void *base_addr;
+	struct f2fs_xattr_entry *entry = NULL;
 	int error = 0;
-	size_t size, len;
+	unsigned int size, len;
+	void *base_addr = NULL;
 
 	if (name == NULL)
 		return -EINVAL;
@@ -373,21 +476,16 @@ int f2fs_getxattr(struct inode *inode, int index, const char *name,
 	if (len > F2FS_NAME_LEN)
 		return -ERANGE;
 
-	error = read_all_xattrs(inode, ipage, &base_addr);
+	error = lookup_all_xattrs(inode, ipage, index, len, name,
+				&entry, &base_addr);
 	if (error)
 		return error;
 
-	entry = __find_xattr(base_addr, index, len, name);
-	if (IS_XATTR_LAST_ENTRY(entry)) {
-		error = -ENODATA;
-		goto cleanup;
-	}
-
 	size = le16_to_cpu(entry->e_value_size);
 
 	if (buffer && size > buffer_size) {
 		error = -ERANGE;
-		goto cleanup;
+		goto out;
 	}
 
 	if (buffer) {
@@ -395,8 +493,7 @@ int f2fs_getxattr(struct inode *inode, int index, const char *name,
 		memcpy(buffer, pval, size);
 	}
 	error = size;
-
-cleanup:
+out:
 	kzfree(base_addr);
 	return error;
 }
@@ -445,6 +542,13 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
 	return error;
 }
 
+static bool f2fs_xattr_value_same(struct f2fs_xattr_entry *entry,
+					const void *value, size_t size)
+{
+	void *pval = entry->e_name + entry->e_name_len;
+	return (entry->e_value_size == size) && !memcmp(pval, value, size);
+}
+
 static int __f2fs_setxattr(struct inode *inode, int index,
 			const char *name, const void *value, size_t size,
 			struct page *ipage, int flags)
@@ -479,12 +583,17 @@ static int __f2fs_setxattr(struct inode *inode, int index,
 
 	found = IS_XATTR_LAST_ENTRY(here) ? 0 : 1;
 
-	if ((flags & XATTR_REPLACE) && !found) {
+	if (found) {
+		if ((flags & XATTR_CREATE)) {
+			error = -EEXIST;
+			goto exit;
+		}
+
+		if (f2fs_xattr_value_same(here, value, size))
+			goto exit;
+	} else if ((flags & XATTR_REPLACE)) {
 		error = -ENODATA;
 		goto exit;
-	} else if ((flags & XATTR_CREATE) && found) {
-		error = -EEXIST;
-		goto exit;
 	}
 
 	last = here;

fs/f2fs/xattr.h

@@ -72,9 +72,10 @@ struct f2fs_xattr_entry {
 		for (entry = XATTR_FIRST_ENTRY(addr);\
 				!IS_XATTR_LAST_ENTRY(entry);\
 				entry = XATTR_NEXT_ENTRY(entry))
-
-#define MIN_OFFSET(i)	XATTR_ALIGN(inline_xattr_size(i) + PAGE_SIZE -	\
-				sizeof(struct node_footer) - sizeof(__u32))
+#define MAX_XATTR_BLOCK_SIZE	(PAGE_SIZE - sizeof(struct node_footer))
+#define VALID_XATTR_BLOCK_SIZE	(MAX_XATTR_BLOCK_SIZE - sizeof(__u32))
+#define MIN_OFFSET(i)		XATTR_ALIGN(inline_xattr_size(i) +	\
+						VALID_XATTR_BLOCK_SIZE)
 
 #define MAX_VALUE_LEN(i)	(MIN_OFFSET(i) -			\
 				sizeof(struct f2fs_xattr_header) -	\

include/linux/f2fs_fs.h

@@ -36,6 +36,12 @@
 #define F2FS_NODE_INO(sbi)	(sbi->node_ino_num)
 #define F2FS_META_INO(sbi)	(sbi->meta_ino_num)
 
+#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 */
+#define F2FS_IO_SIZE_BITS(sbi)	((sbi)->write_io_size_bits) /* power of 2 */
+#define F2FS_IO_SIZE_MASK(sbi)	(F2FS_IO_SIZE(sbi) - 1)
+
 /* This flag is used by node and meta inodes, and by recovery */
 #define GFP_F2FS_ZERO		(GFP_NOFS | __GFP_ZERO)
 #define GFP_F2FS_HIGH_ZERO	(GFP_NOFS | __GFP_ZERO | __GFP_HIGHMEM)
@@ -108,6 +114,7 @@ struct f2fs_super_block {
 /*
  * For checkpoint
  */
+#define CP_NAT_BITS_FLAG	0x00000080
 #define CP_CRC_RECOVERY_FLAG	0x00000040
 #define CP_FASTBOOT_FLAG	0x00000020
 #define CP_FSCK_FLAG		0x00000010
@@ -272,6 +279,7 @@ struct f2fs_node {
  * For NAT entries
  */
 #define NAT_ENTRY_PER_BLOCK (PAGE_SIZE / sizeof(struct f2fs_nat_entry))
+#define NAT_ENTRY_BITMAP_SIZE	((NAT_ENTRY_PER_BLOCK + 7) / 8)
 
 struct f2fs_nat_entry {
 	__u8 version;		/* latest version of cached nat entry */