f2fs updates for v3.10

This patch-set includes the following major enhancement patches.
 o introduce a new gloabl lock scheme
 o add tracepoints on several major functions
 o fix the overall cleaning process focused on victim selection
 o apply the block plugging to merge IOs as much as possible
 o enhance management of free nids and its list
 o enhance the readahead mode for node pages
 o address several cretical deadlock conditions
 o reduce lock_page calls
 
 The other minor bug fixes and enhancements are as follows.
 o calculation mistakes: overflow
 o bio types: READ, READA, and READ_SYNC
 o fix the recovery flow, data races, and null pointer errors
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1.4.11 (GNU/Linux)
 
 iQIcBAABAgAGBQJRijCLAAoJEEAUqH6CSFDSg9kQAIqxmQzCUvCN3HcyVe8bGhKz
 8xhKrAY6ySRCKMuBbFRQsNrXUhckE3A44DgzYm5/gQikr/c8zhbqPVrtZ968eCKb
 wm3J+Re/uwZr5eOXlJEaHIiSkMDtERN7Cu2oYJWZi2B9wCSZcgvoWQ3c3LUVk6yF
 GFdi1Y00ll5tFKbEGbXSsfdul9P8jp0MmuMnWBBQZF3TrjETXMdThA5FXN0yTf9s
 XkcGE9vTCCPk8p7P3YmGGw6CwlaL8oallm0//iL4nMNpJzveq2C09IlY2BNrxU3L
 iTNXeIBdbhwXpnh2zq26Cy+cIEDIp0oXYui5BYdr/LWyWU3T/INa+hjUUszsESxF
 51LIUA1rA9nX/BSmj2QomswZ3lt4u5jl6rSBFKv3NG1KsFrAdb8S4tHukRSTSxAJ
 gzpY6kLT1+bgciA16F5W4yhzMYPN5hPa8s6hx4LHlpoqQICQsurjtS9KW7vncLFt
 ttmCMn8ehHcTzKRNNqYaBerCtSB3Z3G/uAy1y+DB7Zx2h2mqhCBXRalyRvs7RKvK
 d5OyYCpHntxuzDwVuivnr9Ddp30LUP1WqexxK+ykn99Ji3leMmffHP8Oari8w96b
 RxSbjoo8hOgoS5xZ4v3AaqtLDlBpxC6oWJzDaq/fJeKxOx22Z5BDFUM9mBGxrouJ
 AATl8b+cW/aTZ4l7WOPU
 =Hqii
 -----END PGP SIGNATURE-----

Merge tag 'f2fs-for-v3.10' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "This patch-set includes the following major enhancement patches.
   - introduce a new gloabl lock scheme
   - add tracepoints on several major functions
   - fix the overall cleaning process focused on victim selection
   - apply the block plugging to merge IOs as much as possible
   - enhance management of free nids and its list
   - enhance the readahead mode for node pages
   - address several cretical deadlock conditions
   - reduce lock_page calls

  The other minor bug fixes and enhancements are as follows.
   - calculation mistakes: overflow
   - bio types: READ, READA, and READ_SYNC
   - fix the recovery flow, data races, and null pointer errors"

* tag 'f2fs-for-v3.10' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (68 commits)
  f2fs: cover free_nid management with spin_lock
  f2fs: optimize scan_nat_page()
  f2fs: code cleanup for scan_nat_page() and build_free_nids()
  f2fs: bugfix for alloc_nid_failed()
  f2fs: recover when journal contains deleted files
  f2fs: continue to mount after failing recovery
  f2fs: avoid deadlock during evict after f2fs_gc
  f2fs: modify the number of issued pages to merge IOs
  f2fs: remove useless #include <linux/proc_fs.h> as we're now using sysfs as debug entry.
  f2fs: fix inconsistent using of NM_WOUT_THRESHOLD
  f2fs: check truncation of mapping after lock_page
  f2fs: enhance alloc_nid and build_free_nids flows
  f2fs: add a tracepoint on f2fs_new_inode
  f2fs: check nid == 0 in add_free_nid
  f2fs: add REQ_META about metadata requests for submit
  f2fs: give a chance to merge IOs by IO scheduler
  f2fs: avoid frequent background GC
  f2fs: add tracepoints to debug checkpoint request
  f2fs: add tracepoints for write page operations
  f2fs: add tracepoints to debug the block allocation
  ...

Documentation/filesystems/f2fs.txt

@@ -146,7 +146,7 @@ USAGE
 
 Format options
 --------------
--l [label]   : Give a volume label, up to 256 unicode name.
+-l [label]   : Give a volume label, up to 512 unicode name.
 -a [0 or 1]  : Split start location of each area for heap-based allocation.
                1 is set by default, which performs this.
 -o [int]     : Set overprovision ratio in percent over volume size.
@@ -156,6 +156,8 @@ Format options
 -z [int]     : Set the number of sections per zone.
                1 is set by default.
 -e [str]     : Set basic extension list. e.g. "mp3,gif,mov"
+-t [0 or 1]  : Disable discard command or not.
+               1 is set by default, which conducts discard.
 
 ================================================================================
 DESIGN

fs/f2fs/checkpoint.c

@@ -20,6 +20,7 @@
 #include "f2fs.h"
 #include "node.h"
 #include "segment.h"
+#include <trace/events/f2fs.h>
 
 static struct kmem_cache *orphan_entry_slab;
 static struct kmem_cache *inode_entry_slab;
@@ -57,13 +58,19 @@ repeat:
 		cond_resched();
 		goto repeat;
 	}
-	if (f2fs_readpage(sbi, page, index, READ_SYNC)) {
+	if (PageUptodate(page))
+		goto out;
+
+	if (f2fs_readpage(sbi, page, index, READ_SYNC))
+		goto repeat;
+
+	lock_page(page);
+	if (page->mapping != mapping) {
 		f2fs_put_page(page, 1);
 		goto repeat;
 	}
+out:
 	mark_page_accessed(page);
-
-	/* We do not allow returning an errorneous page */
 	return page;
 }
 
@@ -541,54 +548,44 @@ retry:
  */
 static void block_operations(struct f2fs_sb_info *sbi)
 {
-	int t;
 	struct writeback_control wbc = {
 		.sync_mode = WB_SYNC_ALL,
 		.nr_to_write = LONG_MAX,
 		.for_reclaim = 0,
 	};
+	struct blk_plug plug;
 
-	/* Stop renaming operation */
+	blk_start_plug(&plug);
-	mutex_lock_op(sbi, RENAME);
+
-	mutex_lock_op(sbi, DENTRY_OPS);
+retry_flush_dents:
+	mutex_lock_all(sbi);
 
-retry_dents:
 	/* write all the dirty dentry pages */
-	sync_dirty_dir_inodes(sbi);
-
-	mutex_lock_op(sbi, DATA_WRITE);
 	if (get_pages(sbi, F2FS_DIRTY_DENTS)) {
-		mutex_unlock_op(sbi, DATA_WRITE);
+		mutex_unlock_all(sbi);
-		goto retry_dents;
+		sync_dirty_dir_inodes(sbi);
+		goto retry_flush_dents;
 	}
 
-	/* block all the operations */
-	for (t = DATA_NEW; t <= NODE_TRUNC; t++)
-		mutex_lock_op(sbi, t);
-
-	mutex_lock(&sbi->write_inode);
-
 	/*
 	 * POR: we should ensure that there is no dirty node pages
 	 * until finishing nat/sit flush.
 	 */
-retry:
+retry_flush_nodes:
-	sync_node_pages(sbi, 0, &wbc);
+	mutex_lock(&sbi->node_write);
-
-	mutex_lock_op(sbi, NODE_WRITE);
 
 	if (get_pages(sbi, F2FS_DIRTY_NODES)) {
-		mutex_unlock_op(sbi, NODE_WRITE);
+		mutex_unlock(&sbi->node_write);
-		goto retry;
+		sync_node_pages(sbi, 0, &wbc);
+		goto retry_flush_nodes;
 	}
-	mutex_unlock(&sbi->write_inode);
+	blk_finish_plug(&plug);
 }
 
 static void unblock_operations(struct f2fs_sb_info *sbi)
 {
-	int t;
+	mutex_unlock(&sbi->node_write);
-	for (t = NODE_WRITE; t >= RENAME; t--)
+	mutex_unlock_all(sbi);
-		mutex_unlock_op(sbi, t);
 }
 
 static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
@@ -727,9 +724,13 @@ void write_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
 	unsigned long long ckpt_ver;
 
+	trace_f2fs_write_checkpoint(sbi->sb, is_umount, "start block_ops");
+
 	mutex_lock(&sbi->cp_mutex);
 	block_operations(sbi);
 
+	trace_f2fs_write_checkpoint(sbi->sb, is_umount, "finish block_ops");
+
 	f2fs_submit_bio(sbi, DATA, true);
 	f2fs_submit_bio(sbi, NODE, true);
 	f2fs_submit_bio(sbi, META, true);
@@ -746,13 +747,13 @@ void write_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
 	flush_nat_entries(sbi);
 	flush_sit_entries(sbi);
 
-	reset_victim_segmap(sbi);
-
 	/* unlock all the fs_lock[] in do_checkpoint() */
 	do_checkpoint(sbi, is_umount);
 
 	unblock_operations(sbi);
 	mutex_unlock(&sbi->cp_mutex);
+
+	trace_f2fs_write_checkpoint(sbi->sb, is_umount, "finish checkpoint");
 }
 
 void init_orphan_info(struct f2fs_sb_info *sbi)

fs/f2fs/data.c

@@ -22,6 +22,7 @@
 #include "f2fs.h"
 #include "node.h"
 #include "segment.h"
+#include <trace/events/f2fs.h>
 
 /*
  * Lock ordering for the change of data block address:
@@ -55,6 +56,8 @@ int reserve_new_block(struct dnode_of_data *dn)
 	if (!inc_valid_block_count(sbi, dn->inode, 1))
 		return -ENOSPC;
 
+	trace_f2fs_reserve_new_block(dn->inode, dn->nid, dn->ofs_in_node);
+
 	__set_data_blkaddr(dn, NEW_ADDR);
 	dn->data_blkaddr = NEW_ADDR;
 	sync_inode_page(dn);
@@ -134,7 +137,7 @@ void update_extent_cache(block_t blk_addr, struct dnode_of_data *dn)
 		goto end_update;
 	}
 
-	/* Frone merge */
+	/* Front merge */
 	if (fofs == start_fofs - 1 && blk_addr == start_blkaddr - 1) {
 		fi->ext.fofs--;
 		fi->ext.blk_addr--;
@@ -170,7 +173,7 @@ end_update:
 	return;
 }
 
-struct page *find_data_page(struct inode *inode, pgoff_t index)
+struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
 	struct address_space *mapping = inode->i_mapping;
@@ -184,7 +187,7 @@ struct page *find_data_page(struct inode *inode, pgoff_t index)
 	f2fs_put_page(page, 0);
 
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
-	err = get_dnode_of_data(&dn, index, RDONLY_NODE);
+	err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
 	if (err)
 		return ERR_PTR(err);
 	f2fs_put_dnode(&dn);
@@ -200,12 +203,20 @@ struct page *find_data_page(struct inode *inode, pgoff_t index)
 	if (!page)
 		return ERR_PTR(-ENOMEM);
 
-	err = f2fs_readpage(sbi, page, dn.data_blkaddr, READ_SYNC);
+	if (PageUptodate(page)) {
-	if (err) {
+		unlock_page(page);
-		f2fs_put_page(page, 1);
+		return page;
-		return ERR_PTR(err);
+	}
+
+	err = f2fs_readpage(sbi, page, dn.data_blkaddr,
+					sync ? READ_SYNC : READA);
+	if (sync) {
+		wait_on_page_locked(page);
+		if (!PageUptodate(page)) {
+			f2fs_put_page(page, 0);
+			return ERR_PTR(-EIO);
+		}
 	}
-	unlock_page(page);
 	return page;
 }
 
@@ -223,14 +234,14 @@ struct page *get_lock_data_page(struct inode *inode, pgoff_t index)
 	int err;
 
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
-	err = get_dnode_of_data(&dn, index, RDONLY_NODE);
+	err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
 	if (err)
 		return ERR_PTR(err);
 	f2fs_put_dnode(&dn);
 
 	if (dn.data_blkaddr == NULL_ADDR)
 		return ERR_PTR(-ENOENT);
-
+repeat:
 	page = grab_cache_page(mapping, index);
 	if (!page)
 		return ERR_PTR(-ENOMEM);
@@ -242,9 +253,17 @@ struct page *get_lock_data_page(struct inode *inode, pgoff_t index)
 	BUG_ON(dn.data_blkaddr == NULL_ADDR);
 
 	err = f2fs_readpage(sbi, page, dn.data_blkaddr, READ_SYNC);
-	if (err) {
+	if (err)
-		f2fs_put_page(page, 1);
 		return ERR_PTR(err);
+
+	lock_page(page);
+	if (!PageUptodate(page)) {
+		f2fs_put_page(page, 1);
+		return ERR_PTR(-EIO);
+	}
+	if (page->mapping != mapping) {
+		f2fs_put_page(page, 1);
+		goto repeat;
 	}
 	return page;
 }
@@ -252,6 +271,9 @@ struct page *get_lock_data_page(struct inode *inode, pgoff_t index)
 /*
  * Caller ensures that this data page is never allocated.
  * A new zero-filled data page is allocated in the page cache.
+ *
+ * Also, caller should grab and release a mutex by calling mutex_lock_op() and
+ * mutex_unlock_op().
  */
 struct page *get_new_data_page(struct inode *inode, pgoff_t index,
 						bool new_i_size)
@@ -263,7 +285,7 @@ struct page *get_new_data_page(struct inode *inode, pgoff_t index,
 	int err;
 
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
-	err = get_dnode_of_data(&dn, index, 0);
+	err = get_dnode_of_data(&dn, index, ALLOC_NODE);
 	if (err)
 		return ERR_PTR(err);
 
@@ -274,7 +296,7 @@ struct page *get_new_data_page(struct inode *inode, pgoff_t index,
 		}
 	}
 	f2fs_put_dnode(&dn);
-
+repeat:
 	page = grab_cache_page(mapping, index);
 	if (!page)
 		return ERR_PTR(-ENOMEM);
@@ -284,14 +306,21 @@ struct page *get_new_data_page(struct inode *inode, pgoff_t index,
 
 	if (dn.data_blkaddr == NEW_ADDR) {
 		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
+		SetPageUptodate(page);
 	} else {
 		err = f2fs_readpage(sbi, page, dn.data_blkaddr, READ_SYNC);
-		if (err) {
+		if (err)
-			f2fs_put_page(page, 1);
 			return ERR_PTR(err);
+		lock_page(page);
+		if (!PageUptodate(page)) {
+			f2fs_put_page(page, 1);
+			return ERR_PTR(-EIO);
+		}
+		if (page->mapping != mapping) {
+			f2fs_put_page(page, 1);
+			goto repeat;
 		}
 	}
-	SetPageUptodate(page);
 
 	if (new_i_size &&
 		i_size_read(inode) < ((index + 1) << PAGE_CACHE_SHIFT)) {
@@ -326,21 +355,15 @@ static void read_end_io(struct bio *bio, int err)
 
 /*
  * Fill the locked page with data located in the block address.
- * Read operation is synchronous, and caller must unlock the page.
+ * Return unlocked page.
  */
 int f2fs_readpage(struct f2fs_sb_info *sbi, struct page *page,
 					block_t blk_addr, int type)
 {
 	struct block_device *bdev = sbi->sb->s_bdev;
-	bool sync = (type == READ_SYNC);
 	struct bio *bio;
 
-	/* This page can be already read by other threads */
+	trace_f2fs_readpage(page, blk_addr, type);
-	if (PageUptodate(page)) {
-		if (!sync)
-			unlock_page(page);
-		return 0;
-	}
 
 	down_read(&sbi->bio_sem);
 
@@ -355,18 +378,12 @@ int f2fs_readpage(struct f2fs_sb_info *sbi, struct page *page,
 		kfree(bio->bi_private);
 		bio_put(bio);
 		up_read(&sbi->bio_sem);
+		f2fs_put_page(page, 1);
 		return -EFAULT;
 	}
 
 	submit_bio(type, bio);
 	up_read(&sbi->bio_sem);
-
-	/* wait for read completion if sync */
-	if (sync) {
-		lock_page(page);
-		if (PageError(page))
-			return -EIO;
-	}
 	return 0;
 }
 
@@ -388,14 +405,18 @@ static int get_data_block_ro(struct inode *inode, sector_t iblock,
 	/* Get the page offset from the block offset(iblock) */
 	pgofs =	(pgoff_t)(iblock >> (PAGE_CACHE_SHIFT - blkbits));
 
-	if (check_extent_cache(inode, pgofs, bh_result))
+	if (check_extent_cache(inode, pgofs, bh_result)) {
+		trace_f2fs_get_data_block(inode, iblock, bh_result, 0);
 		return 0;
+	}
 
 	/* When reading holes, we need its node page */
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
-	err = get_dnode_of_data(&dn, pgofs, RDONLY_NODE);
+	err = get_dnode_of_data(&dn, pgofs, LOOKUP_NODE_RA);
-	if (err)
+	if (err) {
+		trace_f2fs_get_data_block(inode, iblock, bh_result, err);
 		return (err == -ENOENT) ? 0 : err;
+	}
 
 	/* It does not support data allocation */
 	BUG_ON(create);
@@ -420,6 +441,7 @@ static int get_data_block_ro(struct inode *inode, sector_t iblock,
 		bh_result->b_size = (i << blkbits);
 	}
 	f2fs_put_dnode(&dn);
+	trace_f2fs_get_data_block(inode, iblock, bh_result, 0);
 	return 0;
 }
 
@@ -438,13 +460,12 @@ static int f2fs_read_data_pages(struct file *file,
 int do_write_data_page(struct page *page)
 {
 	struct inode *inode = page->mapping->host;
-	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
 	block_t old_blk_addr, new_blk_addr;
 	struct dnode_of_data dn;
 	int err = 0;
 
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
-	err = get_dnode_of_data(&dn, page->index, RDONLY_NODE);
+	err = get_dnode_of_data(&dn, page->index, LOOKUP_NODE);
 	if (err)
 		return err;
 
@@ -468,8 +489,6 @@ int do_write_data_page(struct page *page)
 		write_data_page(inode, page, &dn,
 				old_blk_addr, &new_blk_addr);
 		update_extent_cache(new_blk_addr, &dn);
-		F2FS_I(inode)->data_version =
-			le64_to_cpu(F2FS_CKPT(sbi)->checkpoint_ver);
 	}
 out_writepage:
 	f2fs_put_dnode(&dn);
@@ -485,10 +504,11 @@ static int f2fs_write_data_page(struct page *page,
 	const pgoff_t end_index = ((unsigned long long) i_size)
 							>> PAGE_CACHE_SHIFT;
 	unsigned offset;
+	bool need_balance_fs = false;
 	int err = 0;
 
 	if (page->index < end_index)
-		goto out;
+		goto write;
 
 	/*
 	 * If the offset is out-of-range of file size,
@@ -500,50 +520,46 @@ static int f2fs_write_data_page(struct page *page,
 			dec_page_count(sbi, F2FS_DIRTY_DENTS);
 			inode_dec_dirty_dents(inode);
 		}
-		goto unlock_out;
+		goto out;
 	}
 
 	zero_user_segment(page, offset, PAGE_CACHE_SIZE);
-out:
+write:
-	if (sbi->por_doing)
+	if (sbi->por_doing) {
+		err = AOP_WRITEPAGE_ACTIVATE;
 		goto redirty_out;
+	}
 
-	if (wbc->for_reclaim && !S_ISDIR(inode->i_mode) && !is_cold_data(page))
+	/* Dentry blocks are controlled by checkpoint */
-		goto redirty_out;
-
-	mutex_lock_op(sbi, DATA_WRITE);
 	if (S_ISDIR(inode->i_mode)) {
 		dec_page_count(sbi, F2FS_DIRTY_DENTS);
 		inode_dec_dirty_dents(inode);
+		err = do_write_data_page(page);
+	} else {
+		int ilock = mutex_lock_op(sbi);
+		err = do_write_data_page(page);
+		mutex_unlock_op(sbi, ilock);
+		need_balance_fs = true;
 	}
-	err = do_write_data_page(page);
+	if (err == -ENOENT)
-	if (err && err != -ENOENT) {
+		goto out;
-		wbc->pages_skipped++;
+	else if (err)
-		set_page_dirty(page);
+		goto redirty_out;
-	}
-	mutex_unlock_op(sbi, DATA_WRITE);
 
 	if (wbc->for_reclaim)
 		f2fs_submit_bio(sbi, DATA, true);
 
-	if (err == -ENOENT)
-		goto unlock_out;
-
 	clear_cold_data(page);
+out:
 	unlock_page(page);
-
+	if (need_balance_fs)
-	if (!wbc->for_reclaim && !S_ISDIR(inode->i_mode))
 		f2fs_balance_fs(sbi);
 	return 0;
 
-unlock_out:
-	unlock_page(page);
-	return (err == -ENOENT) ? 0 : err;
-
 redirty_out:
 	wbc->pages_skipped++;
 	set_page_dirty(page);
-	return AOP_WRITEPAGE_ACTIVATE;
+	return err;
 }
 
 #define MAX_DESIRED_PAGES_WP	4096
@@ -562,19 +578,26 @@ static int f2fs_write_data_pages(struct address_space *mapping,
 {
 	struct inode *inode = mapping->host;
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	bool locked = false;
 	int ret;
 	long excess_nrtw = 0, desired_nrtw;
 
+	/* deal with chardevs and other special file */
+	if (!mapping->a_ops->writepage)
+		return 0;
+
 	if (wbc->nr_to_write < MAX_DESIRED_PAGES_WP) {
 		desired_nrtw = MAX_DESIRED_PAGES_WP;
 		excess_nrtw = desired_nrtw - wbc->nr_to_write;
 		wbc->nr_to_write = desired_nrtw;
 	}
 
-	if (!S_ISDIR(inode->i_mode))
+	if (!S_ISDIR(inode->i_mode)) {
 		mutex_lock(&sbi->writepages);
+		locked = true;
+	}
 	ret = write_cache_pages(mapping, wbc, __f2fs_writepage, mapping);
-	if (!S_ISDIR(inode->i_mode))
+	if (locked)
 		mutex_unlock(&sbi->writepages);
 	f2fs_submit_bio(sbi, DATA, (wbc->sync_mode == WB_SYNC_ALL));
 
@@ -594,39 +617,33 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
 	pgoff_t index = ((unsigned long long) pos) >> PAGE_CACHE_SHIFT;
 	struct dnode_of_data dn;
 	int err = 0;
+	int ilock;
 
 	/* for nobh_write_end */
 	*fsdata = NULL;
 
 	f2fs_balance_fs(sbi);
-
+repeat:
 	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (!page)
 		return -ENOMEM;
 	*pagep = page;
 
-	mutex_lock_op(sbi, DATA_NEW);
+	ilock = mutex_lock_op(sbi);
 
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
-	err = get_dnode_of_data(&dn, index, 0);
+	err = get_dnode_of_data(&dn, index, ALLOC_NODE);
-	if (err) {
+	if (err)
-		mutex_unlock_op(sbi, DATA_NEW);
+		goto err;
-		f2fs_put_page(page, 1);
-		return err;
-	}
 
-	if (dn.data_blkaddr == NULL_ADDR) {
+	if (dn.data_blkaddr == NULL_ADDR)
 		err = reserve_new_block(&dn);
-		if (err) {
-			f2fs_put_dnode(&dn);
-			mutex_unlock_op(sbi, DATA_NEW);
-			f2fs_put_page(page, 1);
-			return err;
-		}
-	}
-	f2fs_put_dnode(&dn);
 
-	mutex_unlock_op(sbi, DATA_NEW);
+	f2fs_put_dnode(&dn);
+	if (err)
+		goto err;
+
+	mutex_unlock_op(sbi, ilock);
 
 	if ((len == PAGE_CACHE_SIZE) || PageUptodate(page))
 		return 0;
@@ -637,21 +654,34 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
 
 		/* Reading beyond i_size is simple: memset to zero */
 		zero_user_segments(page, 0, start, end, PAGE_CACHE_SIZE);
-		return 0;
+		goto out;
 	}
 
 	if (dn.data_blkaddr == NEW_ADDR) {
 		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
 	} else {
 		err = f2fs_readpage(sbi, page, dn.data_blkaddr, READ_SYNC);
-		if (err) {
+		if (err)
-			f2fs_put_page(page, 1);
 			return err;
+		lock_page(page);
+		if (!PageUptodate(page)) {
+			f2fs_put_page(page, 1);
+			return -EIO;
+		}
+		if (page->mapping != mapping) {
+			f2fs_put_page(page, 1);
+			goto repeat;
 		}
 	}
+out:
 	SetPageUptodate(page);
 	clear_cold_data(page);
 	return 0;
+
+err:
+	mutex_unlock_op(sbi, ilock);
+	f2fs_put_page(page, 1);
+	return err;
 }
 
 static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb,
@@ -682,7 +712,7 @@ static void f2fs_invalidate_data_page(struct page *page, unsigned long offset)
 static int f2fs_release_data_page(struct page *page, gfp_t wait)
 {
 	ClearPagePrivate(page);
-	return 0;
+	return 1;
 }
 
 static int f2fs_set_data_page_dirty(struct page *page)

fs/f2fs/debug.c

@@ -13,7 +13,6 @@
 
 #include <linux/fs.h>
 #include <linux/backing-dev.h>
-#include <linux/proc_fs.h>
 #include <linux/f2fs_fs.h>
 #include <linux/blkdev.h>
 #include <linux/debugfs.h>
@@ -106,7 +105,7 @@ static void update_sit_info(struct f2fs_sb_info *sbi)
 		}
 	}
 	mutex_unlock(&sit_i->sentry_lock);
-	dist = sbi->total_sections * hblks_per_sec * hblks_per_sec / 100;
+	dist = TOTAL_SECS(sbi) * hblks_per_sec * hblks_per_sec / 100;
 	si->bimodal = bimodal / dist;
 	if (si->dirty_count)
 		si->avg_vblocks = total_vblocks / ndirty;
@@ -138,14 +137,13 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
 	si->base_mem += f2fs_bitmap_size(TOTAL_SEGS(sbi));
 	si->base_mem += 2 * SIT_VBLOCK_MAP_SIZE * TOTAL_SEGS(sbi);
 	if (sbi->segs_per_sec > 1)
-		si->base_mem += sbi->total_sections *
+		si->base_mem += TOTAL_SECS(sbi) * sizeof(struct sec_entry);
-			sizeof(struct sec_entry);
 	si->base_mem += __bitmap_size(sbi, SIT_BITMAP);
 
 	/* build free segmap */
 	si->base_mem += sizeof(struct free_segmap_info);
 	si->base_mem += f2fs_bitmap_size(TOTAL_SEGS(sbi));
-	si->base_mem += f2fs_bitmap_size(sbi->total_sections);
+	si->base_mem += f2fs_bitmap_size(TOTAL_SECS(sbi));
 
 	/* build curseg */
 	si->base_mem += sizeof(struct curseg_info) * NR_CURSEG_TYPE;
@@ -154,7 +152,7 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
 	/* build dirty segmap */
 	si->base_mem += sizeof(struct dirty_seglist_info);
 	si->base_mem += NR_DIRTY_TYPE * f2fs_bitmap_size(TOTAL_SEGS(sbi));
-	si->base_mem += 2 * f2fs_bitmap_size(TOTAL_SEGS(sbi));
+	si->base_mem += f2fs_bitmap_size(TOTAL_SECS(sbi));
 
 	/* buld nm */
 	si->base_mem += sizeof(struct f2fs_nm_info);

fs/f2fs/dir.c

@@ -148,7 +148,7 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
 
 	for (; bidx < end_block; bidx++) {
 		/* no need to allocate new dentry pages to all the indices */
-		dentry_page = find_data_page(dir, bidx);
+		dentry_page = find_data_page(dir, bidx, true);
 		if (IS_ERR(dentry_page)) {
 			room = true;
 			continue;
@@ -189,6 +189,9 @@ struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
 	unsigned int max_depth;
 	unsigned int level;
 
+	if (namelen > F2FS_NAME_LEN)
+		return NULL;
+
 	if (npages == 0)
 		return NULL;
 
@@ -246,9 +249,6 @@ ino_t f2fs_inode_by_name(struct inode *dir, struct qstr *qstr)
 void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
 		struct page *page, struct inode *inode)
 {
-	struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
-
-	mutex_lock_op(sbi, DENTRY_OPS);
 	lock_page(page);
 	wait_on_page_writeback(page);
 	de->ino = cpu_to_le32(inode->i_ino);
@@ -262,7 +262,6 @@ void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
 	F2FS_I(inode)->i_pino = dir->i_ino;
 
 	f2fs_put_page(page, 1);
-	mutex_unlock_op(sbi, DENTRY_OPS);
 }
 
 void init_dent_inode(const struct qstr *name, struct page *ipage)
@@ -281,6 +280,43 @@ void init_dent_inode(const struct qstr *name, struct page *ipage)
 	set_page_dirty(ipage);
 }
 
+static int make_empty_dir(struct inode *inode, struct inode *parent)
+{
+	struct page *dentry_page;
+	struct f2fs_dentry_block *dentry_blk;
+	struct f2fs_dir_entry *de;
+	void *kaddr;
+
+	dentry_page = get_new_data_page(inode, 0, true);
+	if (IS_ERR(dentry_page))
+		return PTR_ERR(dentry_page);
+
+	kaddr = kmap_atomic(dentry_page);
+	dentry_blk = (struct f2fs_dentry_block *)kaddr;
+
+	de = &dentry_blk->dentry[0];
+	de->name_len = cpu_to_le16(1);
+	de->hash_code = 0;
+	de->ino = cpu_to_le32(inode->i_ino);
+	memcpy(dentry_blk->filename[0], ".", 1);
+	set_de_type(de, inode);
+
+	de = &dentry_blk->dentry[1];
+	de->hash_code = 0;
+	de->name_len = cpu_to_le16(2);
+	de->ino = cpu_to_le32(parent->i_ino);
+	memcpy(dentry_blk->filename[1], "..", 2);
+	set_de_type(de, inode);
+
+	test_and_set_bit_le(0, &dentry_blk->dentry_bitmap);
+	test_and_set_bit_le(1, &dentry_blk->dentry_bitmap);
+	kunmap_atomic(kaddr);
+
+	set_page_dirty(dentry_page);
+	f2fs_put_page(dentry_page, 1);
+	return 0;
+}
+
 static int init_inode_metadata(struct inode *inode,
 		struct inode *dir, const struct qstr *name)
 {
@@ -291,7 +327,7 @@ static int init_inode_metadata(struct inode *inode,
 			return err;
 
 		if (S_ISDIR(inode->i_mode)) {
-			err = f2fs_make_empty(inode, dir);
+			err = make_empty_dir(inode, dir);
 			if (err) {
 				remove_inode_page(inode);
 				return err;
@@ -314,7 +350,7 @@ static int init_inode_metadata(struct inode *inode,
 	}
 	if (is_inode_flag_set(F2FS_I(inode), FI_INC_LINK)) {
 		inc_nlink(inode);
-		f2fs_write_inode(inode, NULL);
+		update_inode_page(inode);
 	}
 	return 0;
 }
@@ -338,7 +374,7 @@ static void update_parent_metadata(struct inode *dir, struct inode *inode,
 	}
 
 	if (need_dir_update)
-		f2fs_write_inode(dir, NULL);
+		update_inode_page(dir);
 	else
 		mark_inode_dirty(dir);
 
@@ -370,6 +406,10 @@ next:
 	goto next;
 }
 
+/*
+ * Caller should grab and release a mutex by calling mutex_lock_op() and
+ * mutex_unlock_op().
+ */
 int __f2fs_add_link(struct inode *dir, const struct qstr *name, struct inode *inode)
 {
 	unsigned int bit_pos;
@@ -379,7 +419,6 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name, struct inode *in
 	f2fs_hash_t dentry_hash;
 	struct f2fs_dir_entry *de;
 	unsigned int nbucket, nblock;
-	struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
 	size_t namelen = name->len;
 	struct page *dentry_page = NULL;
 	struct f2fs_dentry_block *dentry_blk = NULL;
@@ -409,12 +448,9 @@ start:
 	bidx = dir_block_index(level, (le32_to_cpu(dentry_hash) % nbucket));
 
 	for (block = bidx; block <= (bidx + nblock - 1); block++) {
-		mutex_lock_op(sbi, DENTRY_OPS);
 		dentry_page = get_new_data_page(dir, block, true);
-		if (IS_ERR(dentry_page)) {
+		if (IS_ERR(dentry_page))
-			mutex_unlock_op(sbi, DENTRY_OPS);
 			return PTR_ERR(dentry_page);
-		}
 
 		dentry_blk = kmap(dentry_page);
 		bit_pos = room_for_filename(dentry_blk, slots);
@@ -423,7 +459,6 @@ start:
 
 		kunmap(dentry_page);
 		f2fs_put_page(dentry_page, 1);
-		mutex_unlock_op(sbi, DENTRY_OPS);
 	}
 
 	/* Move to next level to find the empty slot for new dentry */
@@ -453,7 +488,6 @@ add_dentry:
 fail:
 	kunmap(dentry_page);
 	f2fs_put_page(dentry_page, 1);
-	mutex_unlock_op(sbi, DENTRY_OPS);
 	return err;
 }
 
@@ -473,8 +507,6 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
 	void *kaddr = page_address(page);
 	int i;
 
-	mutex_lock_op(sbi, DENTRY_OPS);
-
 	lock_page(page);
 	wait_on_page_writeback(page);
 
@@ -494,7 +526,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
 
 	if (inode && S_ISDIR(inode->i_mode)) {
 		drop_nlink(dir);
-		f2fs_write_inode(dir, NULL);
+		update_inode_page(dir);
 	} else {
 		mark_inode_dirty(dir);
 	}
@@ -506,7 +538,8 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
 			drop_nlink(inode);
 			i_size_write(inode, 0);
 		}
-		f2fs_write_inode(inode, NULL);
+		update_inode_page(inode);
+
 		if (inode->i_nlink == 0)
 			add_orphan_inode(sbi, inode->i_ino);
 	}
@@ -519,45 +552,6 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
 		inode_dec_dirty_dents(dir);
 	}
 	f2fs_put_page(page, 1);
-
-	mutex_unlock_op(sbi, DENTRY_OPS);
-}
-
-int f2fs_make_empty(struct inode *inode, struct inode *parent)
-{
-	struct page *dentry_page;
-	struct f2fs_dentry_block *dentry_blk;
-	struct f2fs_dir_entry *de;
-	void *kaddr;
-
-	dentry_page = get_new_data_page(inode, 0, true);
-	if (IS_ERR(dentry_page))
-		return PTR_ERR(dentry_page);
-
-	kaddr = kmap_atomic(dentry_page);
-	dentry_blk = (struct f2fs_dentry_block *)kaddr;
-
-	de = &dentry_blk->dentry[0];
-	de->name_len = cpu_to_le16(1);
-	de->hash_code = f2fs_dentry_hash(".", 1);
-	de->ino = cpu_to_le32(inode->i_ino);
-	memcpy(dentry_blk->filename[0], ".", 1);
-	set_de_type(de, inode);
-
-	de = &dentry_blk->dentry[1];
-	de->hash_code = f2fs_dentry_hash("..", 2);
-	de->name_len = cpu_to_le16(2);
-	de->ino = cpu_to_le32(parent->i_ino);
-	memcpy(dentry_blk->filename[1], "..", 2);
-	set_de_type(de, inode);
-
-	test_and_set_bit_le(0, &dentry_blk->dentry_bitmap);
-	test_and_set_bit_le(1, &dentry_blk->dentry_bitmap);
-	kunmap_atomic(kaddr);
-
-	set_page_dirty(dentry_page);
-	f2fs_put_page(dentry_page, 1);
-	return 0;
 }
 
 bool f2fs_empty_dir(struct inode *dir)

fs/f2fs/f2fs.h

@@ -125,11 +125,15 @@ static inline int update_sits_in_cursum(struct f2fs_summary_block *rs, int i)
 					 * file keeping -1 as its node offset to
 					 * distinguish from index node blocks.
 					 */
-#define RDONLY_NODE		1	/*
+enum {
-					 * specify a read-only mode when getting
+	ALLOC_NODE,			/* allocate a new node page if needed */
-					 * a node block. 0 is read-write mode.
+	LOOKUP_NODE,			/* look up a node without readahead */
-					 * used by get_dnode_of_data().
+	LOOKUP_NODE_RA,			/*
+					 * look up a node with readahead called
+					 * by get_datablock_ro.
 					 */
+};
+
 #define F2FS_LINK_MAX		32000	/* maximum link count per file */
 
 /* for in-memory extent cache entry */
@@ -144,6 +148,7 @@ struct extent_info {
  * i_advise uses FADVISE_XXX_BIT. We can add additional hints later.
  */
 #define FADVISE_COLD_BIT	0x01
+#define FADVISE_CP_BIT		0x02
 
 struct f2fs_inode_info {
 	struct inode vfs_inode;		/* serve a vfs inode */
@@ -155,7 +160,6 @@ struct f2fs_inode_info {
 
 	/* Use below internally in f2fs*/
 	unsigned long flags;		/* use to pass per-file flags */
-	unsigned long long data_version;/* latest version of data for fsync */
 	atomic_t dirty_dents;		/* # of dirty dentry pages */
 	f2fs_hash_t chash;		/* hash value of given file name */
 	unsigned int clevel;		/* maximum level of given file name */
@@ -186,7 +190,6 @@ static inline void set_raw_extent(struct extent_info *ext,
 struct f2fs_nm_info {
 	block_t nat_blkaddr;		/* base disk address of NAT */
 	nid_t max_nid;			/* maximum possible node ids */
-	nid_t init_scan_nid;		/* the first nid to be scanned */
 	nid_t next_scan_nid;		/* the next nid to be scanned */
 
 	/* NAT cache management */
@@ -305,23 +308,12 @@ enum count_type {
 };
 
 /*
- * FS_LOCK nesting subclasses for the lock validator:
+ * Uses as sbi->fs_lock[NR_GLOBAL_LOCKS].
- *
+ * The checkpoint procedure blocks all the locks in this fs_lock array.
- * The locking order between these classes is
+ * Some FS operations grab free locks, and if there is no free lock,
- * RENAME -> DENTRY_OPS -> DATA_WRITE -> DATA_NEW
+ * then wait to grab a lock in a round-robin manner.
- *    -> DATA_TRUNC -> NODE_WRITE -> NODE_NEW -> NODE_TRUNC
  */
-enum lock_type {
+#define NR_GLOBAL_LOCKS	8
-	RENAME,		/* for renaming operations */
-	DENTRY_OPS,	/* for directory operations */
-	DATA_WRITE,	/* for data write */
-	DATA_NEW,	/* for data allocation */
-	DATA_TRUNC,	/* for data truncate */
-	NODE_NEW,	/* for node allocation */
-	NODE_TRUNC,	/* for node truncate */
-	NODE_WRITE,	/* for node write */
-	NR_LOCK_TYPE,
-};
 
 /*
  * The below are the page types of bios used in submti_bio().
@@ -361,11 +353,13 @@ struct f2fs_sb_info {
 	/* for checkpoint */
 	struct f2fs_checkpoint *ckpt;		/* raw checkpoint pointer */
 	struct inode *meta_inode;		/* cache meta blocks */
-	struct mutex cp_mutex;			/* for checkpoint procedure */
+	struct mutex cp_mutex;			/* checkpoint procedure lock */
-	struct mutex fs_lock[NR_LOCK_TYPE];	/* for blocking FS operations */
+	struct mutex fs_lock[NR_GLOBAL_LOCKS];	/* blocking FS operations */
-	struct mutex write_inode;		/* mutex for write inode */
+	struct mutex node_write;		/* locking node writes */
 	struct mutex writepages;		/* mutex for writepages() */
+	unsigned char next_lock_num;		/* round-robin global locks */
 	int por_doing;				/* recovery is doing or not */
+	int on_build_free_nids;			/* build_free_nids is doing */
 
 	/* for orphan inode management */
 	struct list_head orphan_inode_list;	/* orphan inode list */
@@ -406,6 +400,7 @@ struct f2fs_sb_info {
 	/* for cleaning operations */
 	struct mutex gc_mutex;			/* mutex for GC */
 	struct f2fs_gc_kthread	*gc_thread;	/* GC thread */
+	unsigned int cur_victim_sec;		/* current victim section num */
 
 	/*
 	 * for stat information.
@@ -498,22 +493,51 @@ static inline void clear_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
 	cp->ckpt_flags = cpu_to_le32(ckpt_flags);
 }
 
-static inline void mutex_lock_op(struct f2fs_sb_info *sbi, enum lock_type t)
+static inline void mutex_lock_all(struct f2fs_sb_info *sbi)
 {
-	mutex_lock_nested(&sbi->fs_lock[t], t);
+	int i = 0;
+	for (; i < NR_GLOBAL_LOCKS; i++)
+		mutex_lock(&sbi->fs_lock[i]);
 }
 
-static inline void mutex_unlock_op(struct f2fs_sb_info *sbi, enum lock_type t)
+static inline void mutex_unlock_all(struct f2fs_sb_info *sbi)
 {
-	mutex_unlock(&sbi->fs_lock[t]);
+	int i = 0;
+	for (; i < NR_GLOBAL_LOCKS; i++)
+		mutex_unlock(&sbi->fs_lock[i]);
+}
+
+static inline int mutex_lock_op(struct f2fs_sb_info *sbi)
+{
+	unsigned char next_lock = sbi->next_lock_num % NR_GLOBAL_LOCKS;
+	int i = 0;
+
+	for (; i < NR_GLOBAL_LOCKS; i++)
+		if (mutex_trylock(&sbi->fs_lock[i]))
+			return i;
+
+	mutex_lock(&sbi->fs_lock[next_lock]);
+	sbi->next_lock_num++;
+	return next_lock;
+}
+
+static inline void mutex_unlock_op(struct f2fs_sb_info *sbi, int ilock)
+{
+	if (ilock < 0)
+		return;
+	BUG_ON(ilock >= NR_GLOBAL_LOCKS);
+	mutex_unlock(&sbi->fs_lock[ilock]);
 }
 
 /*
  * Check whether the given nid is within node id range.
  */
-static inline void check_nid_range(struct f2fs_sb_info *sbi, nid_t nid)
+static inline int check_nid_range(struct f2fs_sb_info *sbi, nid_t nid)
 {
-	BUG_ON((nid >= NM_I(sbi)->max_nid));
+	WARN_ON((nid >= NM_I(sbi)->max_nid));
+	if (nid >= NM_I(sbi)->max_nid)
+		return -EINVAL;
+	return 0;
 }
 
 #define F2FS_DEFAULT_ALLOCATED_BLOCKS	1
@@ -819,7 +843,6 @@ static inline int f2fs_clear_bit(unsigned int nr, char *addr)
 /* used for f2fs_inode_info->flags */
 enum {
 	FI_NEW_INODE,		/* indicate newly allocated inode */
-	FI_NEED_CP,		/* need to do checkpoint during fsync */
 	FI_INC_LINK,		/* need to increment i_nlink */
 	FI_ACL_MODE,		/* indicate acl mode */
 	FI_NO_ALLOC,		/* should not allocate any blocks */
@@ -872,6 +895,7 @@ long f2fs_compat_ioctl(struct file *, unsigned int, unsigned long);
 void f2fs_set_inode_flags(struct inode *);
 struct inode *f2fs_iget(struct super_block *, unsigned long);
 void update_inode(struct inode *, struct page *);
+int update_inode_page(struct inode *);
 int f2fs_write_inode(struct inode *, struct writeback_control *);
 void f2fs_evict_inode(struct inode *);
 
@@ -973,7 +997,6 @@ int lookup_journal_in_cursum(struct f2fs_summary_block *,
 					int, unsigned int, int);
 void flush_sit_entries(struct f2fs_sb_info *);
 int build_segment_manager(struct f2fs_sb_info *);
-void reset_victim_segmap(struct f2fs_sb_info *);
 void destroy_segment_manager(struct f2fs_sb_info *);
 
 /*
@@ -1000,7 +1023,7 @@ void destroy_checkpoint_caches(void);
  */
 int reserve_new_block(struct dnode_of_data *);
 void update_extent_cache(block_t, struct dnode_of_data *);
-struct page *find_data_page(struct inode *, pgoff_t);
+struct page *find_data_page(struct inode *, pgoff_t, bool);
 struct page *get_lock_data_page(struct inode *, pgoff_t);
 struct page *get_new_data_page(struct inode *, pgoff_t, bool);
 int f2fs_readpage(struct f2fs_sb_info *, struct page *, block_t, int);
@@ -1020,7 +1043,7 @@ void destroy_gc_caches(void);
 /*
  * recovery.c
  */
-void recover_fsync_data(struct f2fs_sb_info *);
+int recover_fsync_data(struct f2fs_sb_info *);
 bool space_for_roll_forward(struct f2fs_sb_info *);
 
 /*

fs/f2fs/file.c

@@ -13,6 +13,7 @@
 #include <linux/stat.h>
 #include <linux/buffer_head.h>
 #include <linux/writeback.h>
+#include <linux/blkdev.h>
 #include <linux/falloc.h>
 #include <linux/types.h>
 #include <linux/compat.h>
@@ -24,6 +25,7 @@
 #include "segment.h"
 #include "xattr.h"
 #include "acl.h"
+#include <trace/events/f2fs.h>
 
 static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
 						struct vm_fault *vmf)
@@ -33,19 +35,18 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
 	block_t old_blk_addr;
 	struct dnode_of_data dn;
-	int err;
+	int err, ilock;
 
 	f2fs_balance_fs(sbi);
 
 	sb_start_pagefault(inode->i_sb);
 
-	mutex_lock_op(sbi, DATA_NEW);
-
 	/* block allocation */
+	ilock = mutex_lock_op(sbi);
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
-	err = get_dnode_of_data(&dn, page->index, 0);
+	err = get_dnode_of_data(&dn, page->index, ALLOC_NODE);
 	if (err) {
-		mutex_unlock_op(sbi, DATA_NEW);
+		mutex_unlock_op(sbi, ilock);
 		goto out;
 	}
 
@@ -55,13 +56,12 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
 		err = reserve_new_block(&dn);
 		if (err) {
 			f2fs_put_dnode(&dn);
-			mutex_unlock_op(sbi, DATA_NEW);
+			mutex_unlock_op(sbi, ilock);
 			goto out;
 		}
 	}
 	f2fs_put_dnode(&dn);
-
+	mutex_unlock_op(sbi, ilock);
-	mutex_unlock_op(sbi, DATA_NEW);
 
 	lock_page(page);
 	if (page->mapping != inode->i_mapping ||
@@ -102,28 +102,10 @@ static const struct vm_operations_struct f2fs_file_vm_ops = {
 	.remap_pages	= generic_file_remap_pages,
 };
 
-static int need_to_sync_dir(struct f2fs_sb_info *sbi, struct inode *inode)
-{
-	struct dentry *dentry;
-	nid_t pino;
-
-	inode = igrab(inode);
-	dentry = d_find_any_alias(inode);
-	if (!dentry) {
-		iput(inode);
-		return 0;
-	}
-	pino = dentry->d_parent->d_inode->i_ino;
-	dput(dentry);
-	iput(inode);
-	return !is_checkpointed_node(sbi, pino);
-}
-
 int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 {
 	struct inode *inode = file->f_mapping->host;
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
-	unsigned long long cur_version;
 	int ret = 0;
 	bool need_cp = false;
 	struct writeback_control wbc = {
@@ -135,9 +117,12 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	if (inode->i_sb->s_flags & MS_RDONLY)
 		return 0;
 
+	trace_f2fs_sync_file_enter(inode);
 	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
-	if (ret)
+	if (ret) {
+		trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
 		return ret;
+	}
 
 	/* guarantee free sections for fsync */
 	f2fs_balance_fs(sbi);
@@ -147,28 +132,18 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
 		goto out;
 
-	mutex_lock(&sbi->cp_mutex);
-	cur_version = le64_to_cpu(F2FS_CKPT(sbi)->checkpoint_ver);
-	mutex_unlock(&sbi->cp_mutex);
-
-	if (F2FS_I(inode)->data_version != cur_version &&
-					!(inode->i_state & I_DIRTY))
-		goto out;
-	F2FS_I(inode)->data_version--;
-
 	if (!S_ISREG(inode->i_mode) || inode->i_nlink != 1)
 		need_cp = true;
-	else if (is_inode_flag_set(F2FS_I(inode), FI_NEED_CP))
+	else if (is_cp_file(inode))
 		need_cp = true;
 	else if (!space_for_roll_forward(sbi))
 		need_cp = true;
-	else if (need_to_sync_dir(sbi, inode))
+	else if (!is_checkpointed_node(sbi, F2FS_I(inode)->i_pino))
 		need_cp = true;
 
 	if (need_cp) {
 		/* all the dirty node pages should be flushed for POR */
 		ret = f2fs_sync_fs(inode->i_sb, 1);
-		clear_inode_flag(F2FS_I(inode), FI_NEED_CP);
 	} else {
 		/* if there is no written node page, write its inode page */
 		while (!sync_node_pages(sbi, inode->i_ino, &wbc)) {
@@ -178,9 +153,11 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 		}
 		filemap_fdatawait_range(sbi->node_inode->i_mapping,
 							0, LONG_MAX);
+		ret = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
 	}
 out:
 	mutex_unlock(&inode->i_mutex);
+	trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
 	return ret;
 }
 
@@ -216,6 +193,9 @@ static int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
 		sync_inode_page(dn);
 	}
 	dn->ofs_in_node = ofs;
+
+	trace_f2fs_truncate_data_blocks_range(dn->inode, dn->nid,
+					 dn->ofs_in_node, nr_free);
 	return nr_free;
 }
 
@@ -232,11 +212,15 @@ static void truncate_partial_data_page(struct inode *inode, u64 from)
 	if (!offset)
 		return;
 
-	page = find_data_page(inode, from >> PAGE_CACHE_SHIFT);
+	page = find_data_page(inode, from >> PAGE_CACHE_SHIFT, false);
 	if (IS_ERR(page))
 		return;
 
 	lock_page(page);
+	if (page->mapping != inode->i_mapping) {
+		f2fs_put_page(page, 1);
+		return;
+	}
 	wait_on_page_writeback(page);
 	zero_user(page, offset, PAGE_CACHE_SIZE - offset);
 	set_page_dirty(page);
@@ -249,20 +233,22 @@ static int truncate_blocks(struct inode *inode, u64 from)
 	unsigned int blocksize = inode->i_sb->s_blocksize;
 	struct dnode_of_data dn;
 	pgoff_t free_from;
-	int count = 0;
+	int count = 0, ilock = -1;
 	int err;
 
+	trace_f2fs_truncate_blocks_enter(inode, from);
+
 	free_from = (pgoff_t)
 			((from + blocksize - 1) >> (sbi->log_blocksize));
 
-	mutex_lock_op(sbi, DATA_TRUNC);
+	ilock = mutex_lock_op(sbi);
-
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
-	err = get_dnode_of_data(&dn, free_from, RDONLY_NODE);
+	err = get_dnode_of_data(&dn, free_from, LOOKUP_NODE);
 	if (err) {
 		if (err == -ENOENT)
 			goto free_next;
-		mutex_unlock_op(sbi, DATA_TRUNC);
+		mutex_unlock_op(sbi, ilock);
+		trace_f2fs_truncate_blocks_exit(inode, err);
 		return err;
 	}
 
@@ -273,6 +259,7 @@ static int truncate_blocks(struct inode *inode, u64 from)
 
 	count -= dn.ofs_in_node;
 	BUG_ON(count < 0);
+
 	if (dn.ofs_in_node || IS_INODE(dn.node_page)) {
 		truncate_data_blocks_range(&dn, count);
 		free_from += count;
@@ -281,11 +268,12 @@ static int truncate_blocks(struct inode *inode, u64 from)
 	f2fs_put_dnode(&dn);
 free_next:
 	err = truncate_inode_blocks(inode, free_from);
-	mutex_unlock_op(sbi, DATA_TRUNC);
+	mutex_unlock_op(sbi, ilock);
 
 	/* lastly zero out the first data page */
 	truncate_partial_data_page(inode, from);
 
+	trace_f2fs_truncate_blocks_exit(inode, err);
 	return err;
 }
 
@@ -295,6 +283,8 @@ void f2fs_truncate(struct inode *inode)
 				S_ISLNK(inode->i_mode)))
 		return;
 
+	trace_f2fs_truncate(inode);
+
 	if (!truncate_blocks(inode, i_size_read(inode))) {
 		inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 		mark_inode_dirty(inode);
@@ -389,15 +379,16 @@ static void fill_zero(struct inode *inode, pgoff_t index,
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
 	struct page *page;
+	int ilock;
 
 	if (!len)
 		return;
 
 	f2fs_balance_fs(sbi);
 
-	mutex_lock_op(sbi, DATA_NEW);
+	ilock = mutex_lock_op(sbi);
 	page = get_new_data_page(inode, index, false);
-	mutex_unlock_op(sbi, DATA_NEW);
+	mutex_unlock_op(sbi, ilock);
 
 	if (!IS_ERR(page)) {
 		wait_on_page_writeback(page);
@@ -414,15 +405,10 @@ int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
 
 	for (index = pg_start; index < pg_end; index++) {
 		struct dnode_of_data dn;
-		struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
 
-		f2fs_balance_fs(sbi);
-
-		mutex_lock_op(sbi, DATA_TRUNC);
 		set_new_dnode(&dn, inode, NULL, NULL, 0);
-		err = get_dnode_of_data(&dn, index, RDONLY_NODE);
+		err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
 		if (err) {
-			mutex_unlock_op(sbi, DATA_TRUNC);
 			if (err == -ENOENT)
 				continue;
 			return err;
@@ -431,7 +417,6 @@ int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
 		if (dn.data_blkaddr != NULL_ADDR)
 			truncate_data_blocks_range(&dn, 1);
 		f2fs_put_dnode(&dn);
-		mutex_unlock_op(sbi, DATA_TRUNC);
 	}
 	return 0;
 }
@@ -461,12 +446,19 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len, int mode)
 		if (pg_start < pg_end) {
 			struct address_space *mapping = inode->i_mapping;
 			loff_t blk_start, blk_end;
+			struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+			int ilock;
+
+			f2fs_balance_fs(sbi);
 
 			blk_start = pg_start << PAGE_CACHE_SHIFT;
 			blk_end = pg_end << PAGE_CACHE_SHIFT;
 			truncate_inode_pages_range(mapping, blk_start,
 					blk_end - 1);
+
+			ilock = mutex_lock_op(sbi);
 			ret = truncate_hole(inode, pg_start, pg_end);
+			mutex_unlock_op(sbi, ilock);
 		}
 	}
 
@@ -500,13 +492,13 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
 
 	for (index = pg_start; index <= pg_end; index++) {
 		struct dnode_of_data dn;
+		int ilock;
 
-		mutex_lock_op(sbi, DATA_NEW);
+		ilock = mutex_lock_op(sbi);
-
 		set_new_dnode(&dn, inode, NULL, NULL, 0);
-		ret = get_dnode_of_data(&dn, index, 0);
+		ret = get_dnode_of_data(&dn, index, ALLOC_NODE);
 		if (ret) {
-			mutex_unlock_op(sbi, DATA_NEW);
+			mutex_unlock_op(sbi, ilock);
 			break;
 		}
 
@@ -514,13 +506,12 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
 			ret = reserve_new_block(&dn);
 			if (ret) {
 				f2fs_put_dnode(&dn);
-				mutex_unlock_op(sbi, DATA_NEW);
+				mutex_unlock_op(sbi, ilock);
 				break;
 			}
 		}
 		f2fs_put_dnode(&dn);
-
+		mutex_unlock_op(sbi, ilock);
-		mutex_unlock_op(sbi, DATA_NEW);
 
 		if (pg_start == pg_end)
 			new_size = offset + len;
@@ -559,6 +550,7 @@ static long f2fs_fallocate(struct file *file, int mode,
 		inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 		mark_inode_dirty(inode);
 	}
+	trace_f2fs_fallocate(inode, mode, offset, len, ret);
 	return ret;
 }
 

fs/f2fs/gc.c

@@ -11,7 +11,6 @@
 #include <linux/fs.h>
 #include <linux/module.h>
 #include <linux/backing-dev.h>
-#include <linux/proc_fs.h>
 #include <linux/init.h>
 #include <linux/f2fs_fs.h>
 #include <linux/kthread.h>
@@ -23,6 +22,7 @@
 #include "node.h"
 #include "segment.h"
 #include "gc.h"
+#include <trace/events/f2fs.h>
 
 static struct kmem_cache *winode_slab;
 
@@ -81,9 +81,6 @@ static int gc_thread_func(void *data)
 		/* if return value is not zero, no victim was selected */
 		if (f2fs_gc(sbi))
 			wait_ms = GC_THREAD_NOGC_SLEEP_TIME;
-		else if (wait_ms == GC_THREAD_NOGC_SLEEP_TIME)
-			wait_ms = GC_THREAD_MAX_SLEEP_TIME;
-
 	} while (!kthread_should_stop());
 	return 0;
 }
@@ -131,7 +128,7 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type,
 {
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
 
-	if (p->alloc_mode) {
+	if (p->alloc_mode == SSR) {
 		p->gc_mode = GC_GREEDY;
 		p->dirty_segmap = dirty_i->dirty_segmap[type];
 		p->ofs_unit = 1;
@@ -160,18 +157,21 @@ static unsigned int get_max_cost(struct f2fs_sb_info *sbi,
 static unsigned int check_bg_victims(struct f2fs_sb_info *sbi)
 {
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
-	unsigned int segno;
+	unsigned int hint = 0;
+	unsigned int secno;
 
 	/*
 	 * If the gc_type is FG_GC, we can select victim segments
 	 * selected by background GC before.
 	 * Those segments guarantee they have small valid blocks.
 	 */
-	segno = find_next_bit(dirty_i->victim_segmap[BG_GC],
+next:
-						TOTAL_SEGS(sbi), 0);
+	secno = find_next_bit(dirty_i->victim_secmap, TOTAL_SECS(sbi), hint++);
-	if (segno < TOTAL_SEGS(sbi)) {
+	if (secno < TOTAL_SECS(sbi)) {
-		clear_bit(segno, dirty_i->victim_segmap[BG_GC]);
+		if (sec_usage_check(sbi, secno))
-		return segno;
+			goto next;
+		clear_bit(secno, dirty_i->victim_secmap);
+		return secno * sbi->segs_per_sec;
 	}
 	return NULL_SEGNO;
 }
@@ -234,7 +234,7 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
 {
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
 	struct victim_sel_policy p;
-	unsigned int segno;
+	unsigned int secno;
 	int nsearched = 0;
 
 	p.alloc_mode = alloc_mode;
@@ -253,6 +253,7 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
 
 	while (1) {
 		unsigned long cost;
+		unsigned int segno;
 
 		segno = find_next_bit(p.dirty_segmap,
 						TOTAL_SEGS(sbi), p.offset);
@@ -265,13 +266,11 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
 			break;
 		}
 		p.offset = ((segno / p.ofs_unit) * p.ofs_unit) + p.ofs_unit;
+		secno = GET_SECNO(sbi, segno);
 
-		if (test_bit(segno, dirty_i->victim_segmap[FG_GC]))
+		if (sec_usage_check(sbi, secno))
 			continue;
-		if (gc_type == BG_GC &&
+		if (gc_type == BG_GC && test_bit(secno, dirty_i->victim_secmap))
-				test_bit(segno, dirty_i->victim_segmap[BG_GC]))
-			continue;
-		if (IS_CURSEC(sbi, GET_SECNO(sbi, segno)))
 			continue;
 
 		cost = get_gc_cost(sbi, segno, &p);
@@ -291,13 +290,18 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
 	}
 got_it:
 	if (p.min_segno != NULL_SEGNO) {
-		*result = (p.min_segno / p.ofs_unit) * p.ofs_unit;
 		if (p.alloc_mode == LFS) {
-			int i;
+			secno = GET_SECNO(sbi, p.min_segno);
-			for (i = 0; i < p.ofs_unit; i++)
+			if (gc_type == FG_GC)
-				set_bit(*result + i,
+				sbi->cur_victim_sec = secno;
-					dirty_i->victim_segmap[gc_type]);
+			else
+				set_bit(secno, dirty_i->victim_secmap);
 		}
+		*result = (p.min_segno / p.ofs_unit) * p.ofs_unit;
+
+		trace_f2fs_get_victim(sbi->sb, type, gc_type, &p,
+				sbi->cur_victim_sec,
+				prefree_segments(sbi), free_segments(sbi));
 	}
 	mutex_unlock(&dirty_i->seglist_lock);
 
@@ -381,6 +385,7 @@ static void gc_node_segment(struct f2fs_sb_info *sbi,
 
 next_step:
 	entry = sum;
+
 	for (off = 0; off < sbi->blocks_per_seg; off++, entry++) {
 		nid_t nid = le32_to_cpu(entry->nid);
 		struct page *node_page;
@@ -401,11 +406,18 @@ next_step:
 			continue;
 
 		/* set page dirty and write it */
-		if (!PageWriteback(node_page))
+		if (gc_type == FG_GC) {
+			f2fs_submit_bio(sbi, NODE, true);
+			wait_on_page_writeback(node_page);
 			set_page_dirty(node_page);
+		} else {
+			if (!PageWriteback(node_page))
+				set_page_dirty(node_page);
+		}
 		f2fs_put_page(node_page, 1);
 		stat_inc_node_blk_count(sbi, 1);
 	}
+
 	if (initial) {
 		initial = false;
 		goto next_step;
@@ -418,6 +430,13 @@ next_step:
 			.for_reclaim = 0,
 		};
 		sync_node_pages(sbi, 0, &wbc);
+
+		/*
+		 * In the case of FG_GC, it'd be better to reclaim this victim
+		 * completely.
+		 */
+		if (get_valid_blocks(sbi, segno, 1) != 0)
+			goto next_step;
 	}
 }
 
@@ -481,21 +500,19 @@ static int check_dnode(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 
 static void move_data_page(struct inode *inode, struct page *page, int gc_type)
 {
-	if (page->mapping != inode->i_mapping)
-		goto out;
-
-	if (inode != page->mapping->host)
-		goto out;
-
-	if (PageWriteback(page))
-		goto out;
-
 	if (gc_type == BG_GC) {
+		if (PageWriteback(page))
+			goto out;
 		set_page_dirty(page);
 		set_cold_data(page);
 	} else {
 		struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
-		mutex_lock_op(sbi, DATA_WRITE);
+
+		if (PageWriteback(page)) {
+			f2fs_submit_bio(sbi, DATA, true);
+			wait_on_page_writeback(page);
+		}
+
 		if (clear_page_dirty_for_io(page) &&
 			S_ISDIR(inode->i_mode)) {
 			dec_page_count(sbi, F2FS_DIRTY_DENTS);
@@ -503,7 +520,6 @@ static void move_data_page(struct inode *inode, struct page *page, int gc_type)
 		}
 		set_cold_data(page);
 		do_write_data_page(page);
-		mutex_unlock_op(sbi, DATA_WRITE);
 		clear_cold_data(page);
 	}
 out:
@@ -530,6 +546,7 @@ static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 
 next_step:
 	entry = sum;
+
 	for (off = 0; off < sbi->blocks_per_seg; off++, entry++) {
 		struct page *data_page;
 		struct inode *inode;
@@ -567,7 +584,7 @@ next_step:
 				continue;
 
 			data_page = find_data_page(inode,
-					start_bidx + ofs_in_node);
+					start_bidx + ofs_in_node, false);
 			if (IS_ERR(data_page))
 				goto next_iput;
 
@@ -588,11 +605,22 @@ next_step:
 next_iput:
 		iput(inode);
 	}
+
 	if (++phase < 4)
 		goto next_step;
 
-	if (gc_type == FG_GC)
+	if (gc_type == FG_GC) {
 		f2fs_submit_bio(sbi, DATA, true);
+
+		/*
+		 * In the case of FG_GC, it'd be better to reclaim this victim
+		 * completely.
+		 */
+		if (get_valid_blocks(sbi, segno, 1) != 0) {
+			phase = 2;
+			goto next_step;
+		}
+	}
 }
 
 static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim,
@@ -611,18 +639,15 @@ static void do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno,
 {
 	struct page *sum_page;
 	struct f2fs_summary_block *sum;
+	struct blk_plug plug;
 
 	/* read segment summary of victim */
 	sum_page = get_sum_page(sbi, segno);
 	if (IS_ERR(sum_page))
 		return;
 
-	/*
+	blk_start_plug(&plug);
-	 * CP needs to lock sum_page. In this time, we don't need
+
-	 * to lock this page, because this summary page is not gone anywhere.
-	 * Also, this page is not gonna be updated before GC is done.
-	 */
-	unlock_page(sum_page);
 	sum = page_address(sum_page);
 
 	switch (GET_SUM_TYPE((&sum->footer))) {
@@ -633,10 +658,12 @@ static void do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno,
 		gc_data_segment(sbi, sum->entries, ilist, segno, gc_type);
 		break;
 	}
+	blk_finish_plug(&plug);
+
 	stat_inc_seg_count(sbi, GET_SUM_TYPE((&sum->footer)));
 	stat_inc_call_count(sbi->stat_info);
 
-	f2fs_put_page(sum_page, 0);
+	f2fs_put_page(sum_page, 1);
 }
 
 int f2fs_gc(struct f2fs_sb_info *sbi)
@@ -652,8 +679,10 @@ gc_more:
 	if (!(sbi->sb->s_flags & MS_ACTIVE))
 		goto stop;
 
-	if (gc_type == BG_GC && has_not_enough_free_secs(sbi, nfree))
+	if (gc_type == BG_GC && has_not_enough_free_secs(sbi, nfree)) {
 		gc_type = FG_GC;
+		write_checkpoint(sbi, false);
+	}
 
 	if (!__get_victim(sbi, &segno, gc_type, NO_CHECK_TYPE))
 		goto stop;
@@ -662,9 +691,11 @@ gc_more:
 	for (i = 0; i < sbi->segs_per_sec; i++)
 		do_garbage_collect(sbi, segno + i, &ilist, gc_type);
 
-	if (gc_type == FG_GC &&
+	if (gc_type == FG_GC) {
-			get_valid_blocks(sbi, segno, sbi->segs_per_sec) == 0)
+		sbi->cur_victim_sec = NULL_SEGNO;
 		nfree++;
+		WARN_ON(get_valid_blocks(sbi, segno, sbi->segs_per_sec));
+	}
 
 	if (has_not_enough_free_secs(sbi, nfree))
 		goto gc_more;

fs/f2fs/gc.h

@@ -13,9 +13,9 @@
 						 * whether IO subsystem is idle
 						 * or not
 						 */
-#define GC_THREAD_MIN_SLEEP_TIME	10000 /* milliseconds */
+#define GC_THREAD_MIN_SLEEP_TIME	30000	/* milliseconds */
-#define GC_THREAD_MAX_SLEEP_TIME	30000
+#define GC_THREAD_MAX_SLEEP_TIME	60000
-#define GC_THREAD_NOGC_SLEEP_TIME	10000
+#define GC_THREAD_NOGC_SLEEP_TIME	300000	/* wait 5 min */
 #define LIMIT_INVALID_BLOCK	40 /* percentage over total user space */
 #define LIMIT_FREE_BLOCK	40 /* percentage over invalid + free space */
 
@@ -58,6 +58,9 @@ static inline block_t limit_free_user_blocks(struct f2fs_sb_info *sbi)
 
 static inline long increase_sleep_time(long wait)
 {
+	if (wait == GC_THREAD_NOGC_SLEEP_TIME)
+		return wait;
+
 	wait += GC_THREAD_MIN_SLEEP_TIME;
 	if (wait > GC_THREAD_MAX_SLEEP_TIME)
 		wait = GC_THREAD_MAX_SLEEP_TIME;
@@ -66,6 +69,9 @@ static inline long increase_sleep_time(long wait)
 
 static inline long decrease_sleep_time(long wait)
 {
+	if (wait == GC_THREAD_NOGC_SLEEP_TIME)
+		wait = GC_THREAD_MAX_SLEEP_TIME;
+
 	wait -= GC_THREAD_MIN_SLEEP_TIME;
 	if (wait <= GC_THREAD_MIN_SLEEP_TIME)
 		wait = GC_THREAD_MIN_SLEEP_TIME;

fs/f2fs/inode.c

@@ -16,6 +16,8 @@
 #include "f2fs.h"
 #include "node.h"
 
+#include <trace/events/f2fs.h>
+
 void f2fs_set_inode_flags(struct inode *inode)
 {
 	unsigned int flags = F2FS_I(inode)->i_flags;
@@ -44,7 +46,11 @@ static int do_read_inode(struct inode *inode)
 	struct f2fs_inode *ri;
 
 	/* Check if ino is within scope */
-	check_nid_range(sbi, inode->i_ino);
+	if (check_nid_range(sbi, inode->i_ino)) {
+		f2fs_msg(inode->i_sb, KERN_ERR, "bad inode number: %lu",
+			 (unsigned long) inode->i_ino);
+		return -EINVAL;
+	}
 
 	node_page = get_node_page(sbi, inode->i_ino);
 	if (IS_ERR(node_page))
@@ -76,7 +82,6 @@ static int do_read_inode(struct inode *inode)
 	fi->i_xattr_nid = le32_to_cpu(ri->i_xattr_nid);
 	fi->i_flags = le32_to_cpu(ri->i_flags);
 	fi->flags = 0;
-	fi->data_version = le64_to_cpu(F2FS_CKPT(sbi)->checkpoint_ver) - 1;
 	fi->i_advise = ri->i_advise;
 	fi->i_pino = le32_to_cpu(ri->i_pino);
 	get_extent_info(&fi->ext, ri->i_ext);
@@ -88,13 +93,16 @@ struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 	struct inode *inode;
-	int ret;
+	int ret = 0;
 
 	inode = iget_locked(sb, ino);
 	if (!inode)
 		return ERR_PTR(-ENOMEM);
-	if (!(inode->i_state & I_NEW))
+
+	if (!(inode->i_state & I_NEW)) {
+		trace_f2fs_iget(inode);
 		return inode;
+	}
 	if (ino == F2FS_NODE_INO(sbi) || ino == F2FS_META_INO(sbi))
 		goto make_now;
 
@@ -136,11 +144,12 @@ make_now:
 		goto bad_inode;
 	}
 	unlock_new_inode(inode);
-
+	trace_f2fs_iget(inode);
 	return inode;
 
 bad_inode:
 	iget_failed(inode);
+	trace_f2fs_iget_exit(inode, ret);
 	return ERR_PTR(ret);
 }
 
@@ -192,11 +201,24 @@ void update_inode(struct inode *inode, struct page *node_page)
 	set_page_dirty(node_page);
 }
 
-int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
+int update_inode_page(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
 	struct page *node_page;
-	bool need_lock = false;
+
+	node_page = get_node_page(sbi, inode->i_ino);
+	if (IS_ERR(node_page))
+		return PTR_ERR(node_page);
+
+	update_inode(inode, node_page);
+	f2fs_put_page(node_page, 1);
+	return 0;
+}
+
+int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	int ret, ilock;
 
 	if (inode->i_ino == F2FS_NODE_INO(sbi) ||
 			inode->i_ino == F2FS_META_INO(sbi))
@@ -205,25 +227,14 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
 	if (wbc)
 		f2fs_balance_fs(sbi);
 
-	node_page = get_node_page(sbi, inode->i_ino);
+	/*
-	if (IS_ERR(node_page))
+	 * We need to lock here to prevent from producing dirty node pages
-		return PTR_ERR(node_page);
+	 * during the urgent cleaning time when runing out of free sections.
-
+	 */
-	if (!PageDirty(node_page)) {
+	ilock = mutex_lock_op(sbi);
-		need_lock = true;
+	ret = update_inode_page(inode);
-		f2fs_put_page(node_page, 1);
+	mutex_unlock_op(sbi, ilock);
-		mutex_lock(&sbi->write_inode);
+	return ret;
-		node_page = get_node_page(sbi, inode->i_ino);
-		if (IS_ERR(node_page)) {
-			mutex_unlock(&sbi->write_inode);
-			return PTR_ERR(node_page);
-		}
-	}
-	update_inode(inode, node_page);
-	f2fs_put_page(node_page, 1);
-	if (need_lock)
-		mutex_unlock(&sbi->write_inode);
-	return 0;
 }
 
 /*
@@ -232,7 +243,9 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
 void f2fs_evict_inode(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	int ilock;
 
+	trace_f2fs_evict_inode(inode);
 	truncate_inode_pages(&inode->i_data, 0);
 
 	if (inode->i_ino == F2FS_NODE_INO(sbi) ||
@@ -252,7 +265,10 @@ void f2fs_evict_inode(struct inode *inode)
 	if (F2FS_HAS_BLOCKS(inode))
 		f2fs_truncate(inode);
 
+	ilock = mutex_lock_op(sbi);
 	remove_inode_page(inode);
+	mutex_unlock_op(sbi, ilock);
+
 	sb_end_intwrite(inode->i_sb);
 no_delete:
 	clear_inode(inode);

fs/f2fs/namei.c

@@ -15,8 +15,10 @@
 #include <linux/ctype.h>
 
 #include "f2fs.h"
+#include "node.h"
 #include "xattr.h"
 #include "acl.h"
+#include <trace/events/f2fs.h>
 
 static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
 {
@@ -25,19 +27,19 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
 	nid_t ino;
 	struct inode *inode;
 	bool nid_free = false;
-	int err;
+	int err, ilock;
 
 	inode = new_inode(sb);
 	if (!inode)
 		return ERR_PTR(-ENOMEM);
 
-	mutex_lock_op(sbi, NODE_NEW);
+	ilock = mutex_lock_op(sbi);
 	if (!alloc_nid(sbi, &ino)) {
-		mutex_unlock_op(sbi, NODE_NEW);
+		mutex_unlock_op(sbi, ilock);
 		err = -ENOSPC;
 		goto fail;
 	}
-	mutex_unlock_op(sbi, NODE_NEW);
+	mutex_unlock_op(sbi, ilock);
 
 	inode->i_uid = current_fsuid();
 
@@ -61,7 +63,7 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
 		nid_free = true;
 		goto out;
 	}
-
+	trace_f2fs_new_inode(inode, 0);
 	mark_inode_dirty(inode);
 	return inode;
 
@@ -69,6 +71,8 @@ out:
 	clear_nlink(inode);
 	unlock_new_inode(inode);
 fail:
+	trace_f2fs_new_inode(inode, err);
+	make_bad_inode(inode);
 	iput(inode);
 	if (nid_free)
 		alloc_nid_failed(sbi, ino);
@@ -82,7 +86,7 @@ static int is_multimedia_file(const unsigned char *s, const char *sub)
 	int ret;
 
 	if (sublen > slen)
-		return 1;
+		return 0;
 
 	ret = memcmp(s + slen - sublen, sub, sublen);
 	if (ret) {	/* compare upper case */
@@ -90,16 +94,16 @@ static int is_multimedia_file(const unsigned char *s, const char *sub)
 		char upper_sub[8];
 		for (i = 0; i < sublen && i < sizeof(upper_sub); i++)
 			upper_sub[i] = toupper(sub[i]);
-		return memcmp(s + slen - sublen, upper_sub, sublen);
+		return !memcmp(s + slen - sublen, upper_sub, sublen);
 	}
 
-	return ret;
+	return !ret;
 }
 
 /*
  * Set multimedia files as cold files for hot/cold data separation
  */
-static inline void set_cold_file(struct f2fs_sb_info *sbi, struct inode *inode,
+static inline void set_cold_files(struct f2fs_sb_info *sbi, struct inode *inode,
 		const unsigned char *name)
 {
 	int i;
@@ -107,8 +111,8 @@ static inline void set_cold_file(struct f2fs_sb_info *sbi, struct inode *inode,
 
 	int count = le32_to_cpu(sbi->raw_super->extension_count);
 	for (i = 0; i < count; i++) {
-		if (!is_multimedia_file(name, extlist[i])) {
+		if (is_multimedia_file(name, extlist[i])) {
-			F2FS_I(inode)->i_advise |= FADVISE_COLD_BIT;
+			set_cold_file(inode);
 			break;
 		}
 	}
@@ -121,7 +125,7 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 	struct inode *inode;
 	nid_t ino = 0;
-	int err;
+	int err, ilock;
 
 	f2fs_balance_fs(sbi);
 
@@ -130,14 +134,16 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 		return PTR_ERR(inode);
 
 	if (!test_opt(sbi, DISABLE_EXT_IDENTIFY))
-		set_cold_file(sbi, inode, dentry->d_name.name);
+		set_cold_files(sbi, inode, dentry->d_name.name);
 
 	inode->i_op = &f2fs_file_inode_operations;
 	inode->i_fop = &f2fs_file_operations;
 	inode->i_mapping->a_ops = &f2fs_dblock_aops;
 	ino = inode->i_ino;
 
+	ilock = mutex_lock_op(sbi);
 	err = f2fs_add_link(dentry, inode);
+	mutex_unlock_op(sbi, ilock);
 	if (err)
 		goto out;
 
@@ -150,6 +156,7 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 out:
 	clear_nlink(inode);
 	unlock_new_inode(inode);
+	make_bad_inode(inode);
 	iput(inode);
 	alloc_nid_failed(sbi, ino);
 	return err;
@@ -161,7 +168,7 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
 	struct inode *inode = old_dentry->d_inode;
 	struct super_block *sb = dir->i_sb;
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
-	int err;
+	int err, ilock;
 
 	f2fs_balance_fs(sbi);
 
@@ -169,14 +176,23 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
 	atomic_inc(&inode->i_count);
 
 	set_inode_flag(F2FS_I(inode), FI_INC_LINK);
+	ilock = mutex_lock_op(sbi);
 	err = f2fs_add_link(dentry, inode);
+	mutex_unlock_op(sbi, ilock);
 	if (err)
 		goto out;
 
+	/*
+	 * This file should be checkpointed during fsync.
+	 * We lost i_pino from now on.
+	 */
+	set_cp_file(inode);
+
 	d_instantiate(dentry, inode);
 	return 0;
 out:
 	clear_inode_flag(F2FS_I(inode), FI_INC_LINK);
+	make_bad_inode(inode);
 	iput(inode);
 	return err;
 }
@@ -197,7 +213,7 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
 	struct f2fs_dir_entry *de;
 	struct page *page;
 
-	if (dentry->d_name.len > F2FS_MAX_NAME_LEN)
+	if (dentry->d_name.len > F2FS_NAME_LEN)
 		return ERR_PTR(-ENAMETOOLONG);
 
 	de = f2fs_find_entry(dir, &dentry->d_name, &page);
@@ -222,7 +238,9 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
 	struct f2fs_dir_entry *de;
 	struct page *page;
 	int err = -ENOENT;
+	int ilock;
 
+	trace_f2fs_unlink_enter(dir, dentry);
 	f2fs_balance_fs(sbi);
 
 	de = f2fs_find_entry(dir, &dentry->d_name, &page);
@@ -236,11 +254,14 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
 		goto fail;
 	}
 
+	ilock = mutex_lock_op(sbi);
 	f2fs_delete_entry(de, page, inode);
+	mutex_unlock_op(sbi, ilock);
 
 	/* In order to evict this inode,  we set it dirty */
 	mark_inode_dirty(inode);
 fail:
+	trace_f2fs_unlink_exit(inode, err);
 	return err;
 }
 
@@ -251,7 +272,7 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 	struct inode *inode;
 	size_t symlen = strlen(symname) + 1;
-	int err;
+	int err, ilock;
 
 	f2fs_balance_fs(sbi);
 
@@ -262,7 +283,9 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
 	inode->i_op = &f2fs_symlink_inode_operations;
 	inode->i_mapping->a_ops = &f2fs_dblock_aops;
 
+	ilock = mutex_lock_op(sbi);
 	err = f2fs_add_link(dentry, inode);
+	mutex_unlock_op(sbi, ilock);
 	if (err)
 		goto out;
 
@@ -275,6 +298,7 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
 out:
 	clear_nlink(inode);
 	unlock_new_inode(inode);
+	make_bad_inode(inode);
 	iput(inode);
 	alloc_nid_failed(sbi, inode->i_ino);
 	return err;
@@ -284,7 +308,7 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
 	struct inode *inode;
-	int err;
+	int err, ilock;
 
 	f2fs_balance_fs(sbi);
 
@@ -298,7 +322,9 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO);
 
 	set_inode_flag(F2FS_I(inode), FI_INC_LINK);
+	ilock = mutex_lock_op(sbi);
 	err = f2fs_add_link(dentry, inode);
+	mutex_unlock_op(sbi, ilock);
 	if (err)
 		goto out_fail;
 
@@ -313,6 +339,7 @@ out_fail:
 	clear_inode_flag(F2FS_I(inode), FI_INC_LINK);
 	clear_nlink(inode);
 	unlock_new_inode(inode);
+	make_bad_inode(inode);
 	iput(inode);
 	alloc_nid_failed(sbi, inode->i_ino);
 	return err;
@@ -333,6 +360,7 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 	struct inode *inode;
 	int err = 0;
+	int ilock;
 
 	if (!new_valid_dev(rdev))
 		return -EINVAL;
@@ -346,7 +374,9 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
 	init_special_inode(inode, inode->i_mode, rdev);
 	inode->i_op = &f2fs_special_inode_operations;
 
+	ilock = mutex_lock_op(sbi);
 	err = f2fs_add_link(dentry, inode);
+	mutex_unlock_op(sbi, ilock);
 	if (err)
 		goto out;
 
@@ -357,6 +387,7 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
 out:
 	clear_nlink(inode);
 	unlock_new_inode(inode);
+	make_bad_inode(inode);
 	iput(inode);
 	alloc_nid_failed(sbi, inode->i_ino);
 	return err;
@@ -374,7 +405,7 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct f2fs_dir_entry *old_dir_entry = NULL;
 	struct f2fs_dir_entry *old_entry;
 	struct f2fs_dir_entry *new_entry;
-	int err = -ENOENT;
+	int err = -ENOENT, ilock = -1;
 
 	f2fs_balance_fs(sbi);
 
@@ -389,7 +420,7 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 			goto out_old;
 	}
 
-	mutex_lock_op(sbi, RENAME);
+	ilock = mutex_lock_op(sbi);
 
 	if (new_inode) {
 		struct page *new_page;
@@ -412,7 +443,7 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		drop_nlink(new_inode);
 		if (!new_inode->i_nlink)
 			add_orphan_inode(sbi, new_inode->i_ino);
-		f2fs_write_inode(new_inode, NULL);
+		update_inode_page(new_inode);
 	} else {
 		err = f2fs_add_link(new_dentry, old_inode);
 		if (err)
@@ -420,12 +451,11 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 		if (old_dir_entry) {
 			inc_nlink(new_dir);
-			f2fs_write_inode(new_dir, NULL);
+			update_inode_page(new_dir);
 		}
 	}
 
 	old_inode->i_ctime = CURRENT_TIME;
-	set_inode_flag(F2FS_I(old_inode), FI_NEED_CP);
 	mark_inode_dirty(old_inode);
 
 	f2fs_delete_entry(old_entry, old_page, NULL);
@@ -439,10 +469,10 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 			f2fs_put_page(old_dir_page, 0);
 		}
 		drop_nlink(old_dir);
-		f2fs_write_inode(old_dir, NULL);
+		update_inode_page(old_dir);
 	}
 
-	mutex_unlock_op(sbi, RENAME);
+	mutex_unlock_op(sbi, ilock);
 	return 0;
 
 out_dir:
@@ -450,7 +480,7 @@ out_dir:
 		kunmap(old_dir_page);
 		f2fs_put_page(old_dir_page, 0);
 	}
-	mutex_unlock_op(sbi, RENAME);
+	mutex_unlock_op(sbi, ilock);
 out_old:
 	kunmap(old_page);
 	f2fs_put_page(old_page, 0);

fs/f2fs/node.c

@@ -19,6 +19,7 @@
 #include "f2fs.h"
 #include "node.h"
 #include "segment.h"
+#include <trace/events/f2fs.h>
 
 static struct kmem_cache *nat_entry_slab;
 static struct kmem_cache *free_nid_slab;
@@ -88,10 +89,13 @@ static void ra_nat_pages(struct f2fs_sb_info *sbi, int nid)
 {
 	struct address_space *mapping = sbi->meta_inode->i_mapping;
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
+	struct blk_plug plug;
 	struct page *page;
 	pgoff_t index;
 	int i;
 
+	blk_start_plug(&plug);
+
 	for (i = 0; i < FREE_NID_PAGES; i++, nid += NAT_ENTRY_PER_BLOCK) {
 		if (nid >= nm_i->max_nid)
 			nid = 0;
@@ -100,12 +104,16 @@ static void ra_nat_pages(struct f2fs_sb_info *sbi, int nid)
 		page = grab_cache_page(mapping, index);
 		if (!page)
 			continue;
-		if (f2fs_readpage(sbi, page, index, READ)) {
+		if (PageUptodate(page)) {
 			f2fs_put_page(page, 1);
 			continue;
 		}
+		if (f2fs_readpage(sbi, page, index, READ))
+			continue;
+
 		f2fs_put_page(page, 0);
 	}
+	blk_finish_plug(&plug);
 }
 
 static struct nat_entry *__lookup_nat_cache(struct f2fs_nm_info *nm_i, nid_t n)
@@ -236,7 +244,7 @@ static int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 
-	if (nm_i->nat_cnt < 2 * NM_WOUT_THRESHOLD)
+	if (nm_i->nat_cnt <= NM_WOUT_THRESHOLD)
 		return 0;
 
 	write_lock(&nm_i->nat_tree_lock);
@@ -320,15 +328,14 @@ static int get_node_path(long block, int offset[4], unsigned int noffset[4])
 	noffset[0] = 0;
 
 	if (block < direct_index) {
-		offset[n++] = block;
+		offset[n] = block;
-		level = 0;
 		goto got;
 	}
 	block -= direct_index;
 	if (block < direct_blks) {
 		offset[n++] = NODE_DIR1_BLOCK;
 		noffset[n] = 1;
-		offset[n++] = block;
+		offset[n] = block;
 		level = 1;
 		goto got;
 	}
@@ -336,7 +343,7 @@ static int get_node_path(long block, int offset[4], unsigned int noffset[4])
 	if (block < direct_blks) {
 		offset[n++] = NODE_DIR2_BLOCK;
 		noffset[n] = 2;
-		offset[n++] = block;
+		offset[n] = block;
 		level = 1;
 		goto got;
 	}
@@ -346,7 +353,7 @@ static int get_node_path(long block, int offset[4], unsigned int noffset[4])
 		noffset[n] = 3;
 		offset[n++] = block / direct_blks;
 		noffset[n] = 4 + offset[n - 1];
-		offset[n++] = block % direct_blks;
+		offset[n] = block % direct_blks;
 		level = 2;
 		goto got;
 	}
@@ -356,7 +363,7 @@ static int get_node_path(long block, int offset[4], unsigned int noffset[4])
 		noffset[n] = 4 + dptrs_per_blk;
 		offset[n++] = block / direct_blks;
 		noffset[n] = 5 + dptrs_per_blk + offset[n - 1];
-		offset[n++] = block % direct_blks;
+		offset[n] = block % direct_blks;
 		level = 2;
 		goto got;
 	}
@@ -371,7 +378,7 @@ static int get_node_path(long block, int offset[4], unsigned int noffset[4])
 		noffset[n] = 7 + (dptrs_per_blk * 2) +
 			      offset[n - 2] * (dptrs_per_blk + 1) +
 			      offset[n - 1];
-		offset[n++] = block % direct_blks;
+		offset[n] = block % direct_blks;
 		level = 3;
 		goto got;
 	} else {
@@ -383,8 +390,11 @@ got:
 
 /*
  * Caller should call f2fs_put_dnode(dn).
+ * Also, it should grab and release a mutex by calling mutex_lock_op() and
+ * mutex_unlock_op() only if ro is not set RDONLY_NODE.
+ * In the case of RDONLY_NODE, we don't need to care about mutex.
  */
-int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int ro)
+int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
 	struct page *npage[4];
@@ -403,7 +413,8 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int ro)
 		return PTR_ERR(npage[0]);
 
 	parent = npage[0];
-	nids[1] = get_nid(parent, offset[0], true);
+	if (level != 0)
+		nids[1] = get_nid(parent, offset[0], true);
 	dn->inode_page = npage[0];
 	dn->inode_page_locked = true;
 
@@ -411,12 +422,9 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int ro)
 	for (i = 1; i <= level; i++) {
 		bool done = false;
 
-		if (!nids[i] && !ro) {
+		if (!nids[i] && mode == ALLOC_NODE) {
-			mutex_lock_op(sbi, NODE_NEW);
-
 			/* alloc new node */
 			if (!alloc_nid(sbi, &(nids[i]))) {
-				mutex_unlock_op(sbi, NODE_NEW);
 				err = -ENOSPC;
 				goto release_pages;
 			}
@@ -425,16 +433,14 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int ro)
 			npage[i] = new_node_page(dn, noffset[i]);
 			if (IS_ERR(npage[i])) {
 				alloc_nid_failed(sbi, nids[i]);
-				mutex_unlock_op(sbi, NODE_NEW);
 				err = PTR_ERR(npage[i]);
 				goto release_pages;
 			}
 
 			set_nid(parent, offset[i - 1], nids[i], i == 1);
 			alloc_nid_done(sbi, nids[i]);
-			mutex_unlock_op(sbi, NODE_NEW);
 			done = true;
-		} else if (ro && i == level && level > 1) {
+		} else if (mode == LOOKUP_NODE_RA && i == level && level > 1) {
 			npage[i] = get_node_page_ra(parent, offset[i - 1]);
 			if (IS_ERR(npage[i])) {
 				err = PTR_ERR(npage[i]);
@@ -507,6 +513,7 @@ invalidate:
 
 	f2fs_put_page(dn->node_page, 1);
 	dn->node_page = NULL;
+	trace_f2fs_truncate_node(dn->inode, dn->nid, ni.blk_addr);
 }
 
 static int truncate_dnode(struct dnode_of_data *dn)
@@ -547,9 +554,13 @@ static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs,
 	if (dn->nid == 0)
 		return NIDS_PER_BLOCK + 1;
 
+	trace_f2fs_truncate_nodes_enter(dn->inode, dn->nid, dn->data_blkaddr);
+
 	page = get_node_page(sbi, dn->nid);
-	if (IS_ERR(page))
+	if (IS_ERR(page)) {
+		trace_f2fs_truncate_nodes_exit(dn->inode, PTR_ERR(page));
 		return PTR_ERR(page);
+	}
 
 	rn = (struct f2fs_node *)page_address(page);
 	if (depth < 3) {
@@ -591,10 +602,12 @@ static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs,
 	} else {
 		f2fs_put_page(page, 1);
 	}
+	trace_f2fs_truncate_nodes_exit(dn->inode, freed);
 	return freed;
 
 out_err:
 	f2fs_put_page(page, 1);
+	trace_f2fs_truncate_nodes_exit(dn->inode, ret);
 	return ret;
 }
 
@@ -649,6 +662,9 @@ static int truncate_partial_nodes(struct dnode_of_data *dn,
 fail:
 	for (i = depth - 3; i >= 0; i--)
 		f2fs_put_page(pages[i], 1);
+
+	trace_f2fs_truncate_partial_nodes(dn->inode, nid, depth, err);
+
 	return err;
 }
 
@@ -658,6 +674,7 @@ fail:
 int truncate_inode_blocks(struct inode *inode, pgoff_t from)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	struct address_space *node_mapping = sbi->node_inode->i_mapping;
 	int err = 0, cont = 1;
 	int level, offset[4], noffset[4];
 	unsigned int nofs = 0;
@@ -665,11 +682,15 @@ int truncate_inode_blocks(struct inode *inode, pgoff_t from)
 	struct dnode_of_data dn;
 	struct page *page;
 
-	level = get_node_path(from, offset, noffset);
+	trace_f2fs_truncate_inode_blocks_enter(inode, from);
 
+	level = get_node_path(from, offset, noffset);
+restart:
 	page = get_node_page(sbi, inode->i_ino);
-	if (IS_ERR(page))
+	if (IS_ERR(page)) {
+		trace_f2fs_truncate_inode_blocks_exit(inode, PTR_ERR(page));
 		return PTR_ERR(page);
+	}
 
 	set_new_dnode(&dn, inode, page, NULL, 0);
 	unlock_page(page);
@@ -728,6 +749,10 @@ skip_partial:
 		if (offset[1] == 0 &&
 				rn->i.i_nid[offset[0] - NODE_DIR1_BLOCK]) {
 			lock_page(page);
+			if (page->mapping != node_mapping) {
+				f2fs_put_page(page, 1);
+				goto restart;
+			}
 			wait_on_page_writeback(page);
 			rn->i.i_nid[offset[0] - NODE_DIR1_BLOCK] = 0;
 			set_page_dirty(page);
@@ -739,9 +764,14 @@ skip_partial:
 	}
 fail:
 	f2fs_put_page(page, 0);
+	trace_f2fs_truncate_inode_blocks_exit(inode, err);
 	return err > 0 ? 0 : err;
 }
 
+/*
+ * Caller should grab and release a mutex by calling mutex_lock_op() and
+ * mutex_unlock_op().
+ */
 int remove_inode_page(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
@@ -749,21 +779,16 @@ int remove_inode_page(struct inode *inode)
 	nid_t ino = inode->i_ino;
 	struct dnode_of_data dn;
 
-	mutex_lock_op(sbi, NODE_TRUNC);
 	page = get_node_page(sbi, ino);
-	if (IS_ERR(page)) {
+	if (IS_ERR(page))
-		mutex_unlock_op(sbi, NODE_TRUNC);
 		return PTR_ERR(page);
-	}
 
 	if (F2FS_I(inode)->i_xattr_nid) {
 		nid_t nid = F2FS_I(inode)->i_xattr_nid;
 		struct page *npage = get_node_page(sbi, nid);
 
-		if (IS_ERR(npage)) {
+		if (IS_ERR(npage))
-			mutex_unlock_op(sbi, NODE_TRUNC);
 			return PTR_ERR(npage);
-		}
 
 		F2FS_I(inode)->i_xattr_nid = 0;
 		set_new_dnode(&dn, inode, page, npage, nid);
@@ -775,23 +800,18 @@ int remove_inode_page(struct inode *inode)
 	BUG_ON(inode->i_blocks != 0 && inode->i_blocks != 1);
 	set_new_dnode(&dn, inode, page, page, ino);
 	truncate_node(&dn);
-
-	mutex_unlock_op(sbi, NODE_TRUNC);
 	return 0;
 }
 
 int new_inode_page(struct inode *inode, const struct qstr *name)
 {
-	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
 	struct page *page;
 	struct dnode_of_data dn;
 
 	/* allocate inode page for new inode */
 	set_new_dnode(&dn, inode, NULL, NULL, inode->i_ino);
-	mutex_lock_op(sbi, NODE_NEW);
 	page = new_node_page(&dn, 0);
 	init_dent_inode(name, page);
-	mutex_unlock_op(sbi, NODE_NEW);
 	if (IS_ERR(page))
 		return PTR_ERR(page);
 	f2fs_put_page(page, 1);
@@ -844,6 +864,12 @@ fail:
 	return ERR_PTR(err);
 }
 
+/*
+ * Caller should do after getting the following values.
+ * 0: f2fs_put_page(page, 0)
+ * LOCKED_PAGE: f2fs_put_page(page, 1)
+ * error: nothing
+ */
 static int read_node_page(struct page *page, int type)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb);
@@ -851,8 +877,14 @@ static int read_node_page(struct page *page, int type)
 
 	get_node_info(sbi, page->index, &ni);
 
-	if (ni.blk_addr == NULL_ADDR)
+	if (ni.blk_addr == NULL_ADDR) {
+		f2fs_put_page(page, 1);
 		return -ENOENT;
+	}
+
+	if (PageUptodate(page))
+		return LOCKED_PAGE;
+
 	return f2fs_readpage(sbi, page, ni.blk_addr, type);
 }
 
@@ -863,40 +895,53 @@ void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid)
 {
 	struct address_space *mapping = sbi->node_inode->i_mapping;
 	struct page *apage;
+	int err;
 
 	apage = find_get_page(mapping, nid);
-	if (apage && PageUptodate(apage))
+	if (apage && PageUptodate(apage)) {
-		goto release_out;
+		f2fs_put_page(apage, 0);
+		return;
+	}
 	f2fs_put_page(apage, 0);
 
 	apage = grab_cache_page(mapping, nid);
 	if (!apage)
 		return;
 
-	if (read_node_page(apage, READA))
+	err = read_node_page(apage, READA);
-		unlock_page(apage);
+	if (err == 0)
-
+		f2fs_put_page(apage, 0);
-release_out:
+	else if (err == LOCKED_PAGE)
-	f2fs_put_page(apage, 0);
+		f2fs_put_page(apage, 1);
 	return;
 }
 
 struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid)
 {
-	int err;
-	struct page *page;
 	struct address_space *mapping = sbi->node_inode->i_mapping;
-
+	struct page *page;
+	int err;
+repeat:
 	page = grab_cache_page(mapping, nid);
 	if (!page)
 		return ERR_PTR(-ENOMEM);
 
 	err = read_node_page(page, READ_SYNC);
-	if (err) {
+	if (err < 0)
-		f2fs_put_page(page, 1);
 		return ERR_PTR(err);
-	}
+	else if (err == LOCKED_PAGE)
+		goto got_it;
 
+	lock_page(page);
+	if (!PageUptodate(page)) {
+		f2fs_put_page(page, 1);
+		return ERR_PTR(-EIO);
+	}
+	if (page->mapping != mapping) {
+		f2fs_put_page(page, 1);
+		goto repeat;
+	}
+got_it:
 	BUG_ON(nid != nid_of_node(page));
 	mark_page_accessed(page);
 	return page;
@@ -910,31 +955,27 @@ struct page *get_node_page_ra(struct page *parent, int start)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(parent->mapping->host->i_sb);
 	struct address_space *mapping = sbi->node_inode->i_mapping;
-	int i, end;
+	struct blk_plug plug;
-	int err = 0;
-	nid_t nid;
 	struct page *page;
+	int err, i, end;
+	nid_t nid;
 
 	/* First, try getting the desired direct node. */
 	nid = get_nid(parent, start, false);
 	if (!nid)
 		return ERR_PTR(-ENOENT);
-
-	page = find_get_page(mapping, nid);
-	if (page && PageUptodate(page))
-		goto page_hit;
-	f2fs_put_page(page, 0);
-
 repeat:
 	page = grab_cache_page(mapping, nid);
 	if (!page)
 		return ERR_PTR(-ENOMEM);
 
-	err = read_node_page(page, READA);
+	err = read_node_page(page, READ_SYNC);
-	if (err) {
+	if (err < 0)
-		f2fs_put_page(page, 1);
 		return ERR_PTR(err);
-	}
+	else if (err == LOCKED_PAGE)
+		goto page_hit;
+
+	blk_start_plug(&plug);
 
 	/* Then, try readahead for siblings of the desired node */
 	end = start + MAX_RA_NODE;
@@ -946,18 +987,19 @@ repeat:
 		ra_node_page(sbi, nid);
 	}
 
-page_hit:
+	blk_finish_plug(&plug);
-	lock_page(page);
-	if (PageError(page)) {
-		f2fs_put_page(page, 1);
-		return ERR_PTR(-EIO);
-	}
 
-	/* Has the page been truncated? */
+	lock_page(page);
 	if (page->mapping != mapping) {
 		f2fs_put_page(page, 1);
 		goto repeat;
 	}
+page_hit:
+	if (!PageUptodate(page)) {
+		f2fs_put_page(page, 1);
+		return ERR_PTR(-EIO);
+	}
+	mark_page_accessed(page);
 	return page;
 }
 
@@ -972,7 +1014,7 @@ void sync_inode_page(struct dnode_of_data *dn)
 		if (!dn->inode_page_locked)
 			unlock_page(dn->inode_page);
 	} else {
-		f2fs_write_inode(dn->inode, NULL);
+		update_inode_page(dn->inode);
 	}
 }
 
@@ -1087,17 +1129,8 @@ static int f2fs_write_node_page(struct page *page,
 	block_t new_addr;
 	struct node_info ni;
 
-	if (wbc->for_reclaim) {
-		dec_page_count(sbi, F2FS_DIRTY_NODES);
-		wbc->pages_skipped++;
-		set_page_dirty(page);
-		return AOP_WRITEPAGE_ACTIVATE;
-	}
-
 	wait_on_page_writeback(page);
 
-	mutex_lock_op(sbi, NODE_WRITE);
-
 	/* get old block addr of this node page */
 	nid = nid_of_node(page);
 	BUG_ON(page->index != nid);
@@ -1105,17 +1138,25 @@ static int f2fs_write_node_page(struct page *page,
 	get_node_info(sbi, nid, &ni);
 
 	/* This page is already truncated */
-	if (ni.blk_addr == NULL_ADDR)
+	if (ni.blk_addr == NULL_ADDR) {
+		dec_page_count(sbi, F2FS_DIRTY_NODES);
+		unlock_page(page);
 		return 0;
+	}
 
+	if (wbc->for_reclaim) {
+		dec_page_count(sbi, F2FS_DIRTY_NODES);
+		wbc->pages_skipped++;
+		set_page_dirty(page);
+		return AOP_WRITEPAGE_ACTIVATE;
+	}
+
+	mutex_lock(&sbi->node_write);
 	set_page_writeback(page);
-
-	/* insert node offset */
 	write_node_page(sbi, page, nid, ni.blk_addr, &new_addr);
 	set_node_addr(sbi, &ni, new_addr);
 	dec_page_count(sbi, F2FS_DIRTY_NODES);
-
+	mutex_unlock(&sbi->node_write);
-	mutex_unlock_op(sbi, NODE_WRITE);
 	unlock_page(page);
 	return 0;
 }
@@ -1130,12 +1171,11 @@ static int f2fs_write_node_pages(struct address_space *mapping,
 			    struct writeback_control *wbc)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb);
-	struct block_device *bdev = sbi->sb->s_bdev;
 	long nr_to_write = wbc->nr_to_write;
 
 	/* First check balancing cached NAT entries */
 	if (try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK)) {
-		write_checkpoint(sbi, false);
+		f2fs_sync_fs(sbi->sb, true);
 		return 0;
 	}
 
@@ -1144,10 +1184,9 @@ static int f2fs_write_node_pages(struct address_space *mapping,
 		return 0;
 
 	/* if mounting is failed, skip writing node pages */
-	wbc->nr_to_write = bio_get_nr_vecs(bdev);
+	wbc->nr_to_write = max_hw_blocks(sbi);
 	sync_node_pages(sbi, 0, wbc);
-	wbc->nr_to_write = nr_to_write -
+	wbc->nr_to_write = nr_to_write - (max_hw_blocks(sbi) - wbc->nr_to_write);
-		(bio_get_nr_vecs(bdev) - wbc->nr_to_write);
 	return 0;
 }
 
@@ -1178,7 +1217,7 @@ static void f2fs_invalidate_node_page(struct page *page, unsigned long offset)
 static int f2fs_release_node_page(struct page *page, gfp_t wait)
 {
 	ClearPagePrivate(page);
-	return 0;
+	return 1;
 }
 
 /*
@@ -1195,14 +1234,13 @@ const struct address_space_operations f2fs_node_aops = {
 static struct free_nid *__lookup_free_nid_list(nid_t n, struct list_head *head)
 {
 	struct list_head *this;
-	struct free_nid *i = NULL;
+	struct free_nid *i;
 	list_for_each(this, head) {
 		i = list_entry(this, struct free_nid, list);
 		if (i->nid == n)
-			break;
+			return i;
-		i = NULL;
 	}
-	return i;
+	return NULL;
 }
 
 static void __del_from_free_nid_list(struct free_nid *i)
@@ -1211,11 +1249,29 @@ static void __del_from_free_nid_list(struct free_nid *i)
 	kmem_cache_free(free_nid_slab, i);
 }
 
-static int add_free_nid(struct f2fs_nm_info *nm_i, nid_t nid)
+static int add_free_nid(struct f2fs_nm_info *nm_i, nid_t nid, bool build)
 {
 	struct free_nid *i;
+	struct nat_entry *ne;
+	bool allocated = false;
 
 	if (nm_i->fcnt > 2 * MAX_FREE_NIDS)
+		return -1;
+
+	/* 0 nid should not be used */
+	if (nid == 0)
+		return 0;
+
+	if (!build)
+		goto retry;
+
+	/* do not add allocated nids */
+	read_lock(&nm_i->nat_tree_lock);
+	ne = __lookup_nat_cache(nm_i, nid);
+	if (ne && nat_get_blkaddr(ne) != NULL_ADDR)
+		allocated = true;
+	read_unlock(&nm_i->nat_tree_lock);
+	if (allocated)
 		return 0;
 retry:
 	i = kmem_cache_alloc(free_nid_slab, GFP_NOFS);
@@ -1250,63 +1306,59 @@ static void remove_free_nid(struct f2fs_nm_info *nm_i, nid_t nid)
 	spin_unlock(&nm_i->free_nid_list_lock);
 }
 
-static int scan_nat_page(struct f2fs_nm_info *nm_i,
+static void scan_nat_page(struct f2fs_nm_info *nm_i,
 			struct page *nat_page, nid_t start_nid)
 {
 	struct f2fs_nat_block *nat_blk = page_address(nat_page);
 	block_t blk_addr;
-	int fcnt = 0;
 	int i;
 
-	/* 0 nid should not be used */
-	if (start_nid == 0)
-		++start_nid;
-
 	i = start_nid % NAT_ENTRY_PER_BLOCK;
 
 	for (; i < NAT_ENTRY_PER_BLOCK; i++, start_nid++) {
-		blk_addr  = le32_to_cpu(nat_blk->entries[i].block_addr);
+
+		if (start_nid >= nm_i->max_nid)
+			break;
+
+		blk_addr = le32_to_cpu(nat_blk->entries[i].block_addr);
 		BUG_ON(blk_addr == NEW_ADDR);
-		if (blk_addr == NULL_ADDR)
+		if (blk_addr == NULL_ADDR) {
-			fcnt += add_free_nid(nm_i, start_nid);
+			if (add_free_nid(nm_i, start_nid, true) < 0)
+				break;
+		}
 	}
-	return fcnt;
 }
 
 static void build_free_nids(struct f2fs_sb_info *sbi)
 {
-	struct free_nid *fnid, *next_fnid;
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
 	struct f2fs_summary_block *sum = curseg->sum_blk;
-	nid_t nid = 0;
+	int i = 0;
-	bool is_cycled = false;
+	nid_t nid = nm_i->next_scan_nid;
-	int fcnt = 0;
-	int i;
 
-	nid = nm_i->next_scan_nid;
+	/* Enough entries */
-	nm_i->init_scan_nid = nid;
+	if (nm_i->fcnt > NAT_ENTRY_PER_BLOCK)
+		return;
 
+	/* readahead nat pages to be scanned */
 	ra_nat_pages(sbi, nid);
 
 	while (1) {
 		struct page *page = get_current_nat_page(sbi, nid);
 
-		fcnt += scan_nat_page(nm_i, page, nid);
+		scan_nat_page(nm_i, page, nid);
 		f2fs_put_page(page, 1);
 
 		nid += (NAT_ENTRY_PER_BLOCK - (nid % NAT_ENTRY_PER_BLOCK));
-
+		if (nid >= nm_i->max_nid)
-		if (nid >= nm_i->max_nid) {
 			nid = 0;
-			is_cycled = true;
+
-		}
+		if (i++ == FREE_NID_PAGES)
-		if (fcnt > MAX_FREE_NIDS)
-			break;
-		if (is_cycled && nm_i->init_scan_nid <= nid)
 			break;
 	}
 
+	/* go to the next free nat pages to find free nids abundantly */
 	nm_i->next_scan_nid = nid;
 
 	/* find free nids from current sum_pages */
@@ -1315,22 +1367,11 @@ static void build_free_nids(struct f2fs_sb_info *sbi)
 		block_t addr = le32_to_cpu(nat_in_journal(sum, i).block_addr);
 		nid = le32_to_cpu(nid_in_journal(sum, i));
 		if (addr == NULL_ADDR)
-			add_free_nid(nm_i, nid);
+			add_free_nid(nm_i, nid, true);
 		else
 			remove_free_nid(nm_i, nid);
 	}
 	mutex_unlock(&curseg->curseg_mutex);
-
-	/* remove the free nids from current allocated nids */
-	list_for_each_entry_safe(fnid, next_fnid, &nm_i->free_nid_list, list) {
-		struct nat_entry *ne;
-
-		read_lock(&nm_i->nat_tree_lock);
-		ne = __lookup_nat_cache(nm_i, fnid->nid);
-		if (ne && nat_get_blkaddr(ne) != NULL_ADDR)
-			remove_free_nid(nm_i, fnid->nid);
-		read_unlock(&nm_i->nat_tree_lock);
-	}
 }
 
 /*
@@ -1344,41 +1385,36 @@ bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid)
 	struct free_nid *i = NULL;
 	struct list_head *this;
 retry:
-	mutex_lock(&nm_i->build_lock);
+	if (sbi->total_valid_node_count + 1 >= nm_i->max_nid)
-	if (!nm_i->fcnt) {
+		return false;
-		/* scan NAT in order to build free nid list */
-		build_free_nids(sbi);
-		if (!nm_i->fcnt) {
-			mutex_unlock(&nm_i->build_lock);
-			return false;
-		}
-	}
-	mutex_unlock(&nm_i->build_lock);
 
-	/*
-	 * We check fcnt again since previous check is racy as
-	 * we didn't hold free_nid_list_lock. So other thread
-	 * could consume all of free nids.
-	 */
 	spin_lock(&nm_i->free_nid_list_lock);
-	if (!nm_i->fcnt) {
+
+	/* We should not use stale free nids created by build_free_nids */
+	if (nm_i->fcnt && !sbi->on_build_free_nids) {
+		BUG_ON(list_empty(&nm_i->free_nid_list));
+		list_for_each(this, &nm_i->free_nid_list) {
+			i = list_entry(this, struct free_nid, list);
+			if (i->state == NID_NEW)
+				break;
+		}
+
+		BUG_ON(i->state != NID_NEW);
+		*nid = i->nid;
+		i->state = NID_ALLOC;
+		nm_i->fcnt--;
 		spin_unlock(&nm_i->free_nid_list_lock);
-		goto retry;
+		return true;
 	}
-
-	BUG_ON(list_empty(&nm_i->free_nid_list));
-	list_for_each(this, &nm_i->free_nid_list) {
-		i = list_entry(this, struct free_nid, list);
-		if (i->state == NID_NEW)
-			break;
-	}
-
-	BUG_ON(i->state != NID_NEW);
-	*nid = i->nid;
-	i->state = NID_ALLOC;
-	nm_i->fcnt--;
 	spin_unlock(&nm_i->free_nid_list_lock);
-	return true;
+
+	/* Let's scan nat pages and its caches to get free nids */
+	mutex_lock(&nm_i->build_lock);
+	sbi->on_build_free_nids = 1;
+	build_free_nids(sbi);
+	sbi->on_build_free_nids = 0;
+	mutex_unlock(&nm_i->build_lock);
+	goto retry;
 }
 
 /*
@@ -1391,10 +1427,8 @@ void alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid)
 
 	spin_lock(&nm_i->free_nid_list_lock);
 	i = __lookup_free_nid_list(nid, &nm_i->free_nid_list);
-	if (i) {
+	BUG_ON(!i || i->state != NID_ALLOC);
-		BUG_ON(i->state != NID_ALLOC);
+	__del_from_free_nid_list(i);
-		__del_from_free_nid_list(i);
-	}
 	spin_unlock(&nm_i->free_nid_list_lock);
 }
 
@@ -1403,8 +1437,19 @@ void alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid)
  */
 void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid)
 {
-	alloc_nid_done(sbi, nid);
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
-	add_free_nid(NM_I(sbi), nid);
+	struct free_nid *i;
+
+	spin_lock(&nm_i->free_nid_list_lock);
+	i = __lookup_free_nid_list(nid, &nm_i->free_nid_list);
+	BUG_ON(!i || i->state != NID_ALLOC);
+	if (nm_i->fcnt > 2 * MAX_FREE_NIDS) {
+		__del_from_free_nid_list(i);
+	} else {
+		i->state = NID_NEW;
+		nm_i->fcnt++;
+	}
+	spin_unlock(&nm_i->free_nid_list_lock);
 }
 
 void recover_node_page(struct f2fs_sb_info *sbi, struct page *page,
@@ -1475,23 +1520,24 @@ int restore_node_summary(struct f2fs_sb_info *sbi,
 	sum_entry = &sum->entries[0];
 
 	for (i = 0; i < last_offset; i++, sum_entry++) {
-		if (f2fs_readpage(sbi, page, addr, READ_SYNC))
-			goto out;
-
-		rn = (struct f2fs_node *)page_address(page);
-		sum_entry->nid = rn->footer.nid;
-		sum_entry->version = 0;
-		sum_entry->ofs_in_node = 0;
-		addr++;
-
 		/*
 		 * In order to read next node page,
 		 * we must clear PageUptodate flag.
 		 */
 		ClearPageUptodate(page);
+
+		if (f2fs_readpage(sbi, page, addr, READ_SYNC))
+			goto out;
+
+		lock_page(page);
+		rn = (struct f2fs_node *)page_address(page);
+		sum_entry->nid = rn->footer.nid;
+		sum_entry->version = 0;
+		sum_entry->ofs_in_node = 0;
+		addr++;
 	}
-out:
 	unlock_page(page);
+out:
 	__free_pages(page, 0);
 	return 0;
 }
@@ -1614,13 +1660,11 @@ flush_now:
 			nid_in_journal(sum, offset) = cpu_to_le32(nid);
 		}
 
-		if (nat_get_blkaddr(ne) == NULL_ADDR) {
+		if (nat_get_blkaddr(ne) == NULL_ADDR &&
+				add_free_nid(NM_I(sbi), nid, false) <= 0) {
 			write_lock(&nm_i->nat_tree_lock);
 			__del_from_nat_cache(nm_i, ne);
 			write_unlock(&nm_i->nat_tree_lock);
-
-			/* We can reuse this freed nid at this point */
-			add_free_nid(NM_I(sbi), nid);
 		} else {
 			write_lock(&nm_i->nat_tree_lock);
 			__clear_nat_cache_dirty(nm_i, ne);
@@ -1661,19 +1705,16 @@ static int init_node_manager(struct f2fs_sb_info *sbi)
 	spin_lock_init(&nm_i->free_nid_list_lock);
 	rwlock_init(&nm_i->nat_tree_lock);
 
-	nm_i->bitmap_size = __bitmap_size(sbi, NAT_BITMAP);
-	nm_i->init_scan_nid = le32_to_cpu(sbi->ckpt->next_free_nid);
 	nm_i->next_scan_nid = le32_to_cpu(sbi->ckpt->next_free_nid);
-
+	nm_i->bitmap_size = __bitmap_size(sbi, NAT_BITMAP);
-	nm_i->nat_bitmap = kzalloc(nm_i->bitmap_size, GFP_KERNEL);
-	if (!nm_i->nat_bitmap)
-		return -ENOMEM;
 	version_bitmap = __bitmap_ptr(sbi, NAT_BITMAP);
 	if (!version_bitmap)
 		return -EFAULT;
 
-	/* copy version bitmap */
+	nm_i->nat_bitmap = kmemdup(version_bitmap, nm_i->bitmap_size,
-	memcpy(nm_i->nat_bitmap, version_bitmap, nm_i->bitmap_size);
+					GFP_KERNEL);
+	if (!nm_i->nat_bitmap)
+		return -ENOMEM;
 	return 0;
 }
 

fs/f2fs/node.h

@@ -29,6 +29,9 @@
 /* vector size for gang look-up from nat cache that consists of radix tree */
 #define NATVEC_SIZE	64
 
+/* return value for read_node_page */
+#define LOCKED_PAGE	1
+
 /*
  * For node information
  */
@@ -239,7 +242,7 @@ static inline bool IS_DNODE(struct page *node_page)
 		return false;
 	if (ofs >= 6 + 2 * NIDS_PER_BLOCK) {
 		ofs -= 6 + 2 * NIDS_PER_BLOCK;
-		if ((long int)ofs % (NIDS_PER_BLOCK + 1))
+		if (!((long int)ofs % (NIDS_PER_BLOCK + 1)))
 			return false;
 	}
 	return true;
@@ -277,6 +280,21 @@ static inline int is_cold_file(struct inode *inode)
 	return F2FS_I(inode)->i_advise & FADVISE_COLD_BIT;
 }
 
+static inline void set_cold_file(struct inode *inode)
+{
+	F2FS_I(inode)->i_advise |= FADVISE_COLD_BIT;
+}
+
+static inline int is_cp_file(struct inode *inode)
+{
+	return F2FS_I(inode)->i_advise & FADVISE_CP_BIT;
+}
+
+static inline void set_cp_file(struct inode *inode)
+{
+	F2FS_I(inode)->i_advise |= FADVISE_CP_BIT;
+}
+
 static inline int is_cold_data(struct page *page)
 {
 	return PageChecked(page);

fs/f2fs/recovery.c

@@ -53,7 +53,7 @@ static int recover_dentry(struct page *ipage, struct inode *inode)
 
 	dir = f2fs_iget(inode->i_sb, le32_to_cpu(raw_inode->i_pino));
 	if (IS_ERR(dir)) {
-		err = -EINVAL;
+		err = PTR_ERR(dir);
 		goto out;
 	}
 
@@ -112,11 +112,14 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
 	while (1) {
 		struct fsync_inode_entry *entry;
 
-		if (f2fs_readpage(sbi, page, blkaddr, READ_SYNC))
+		err = f2fs_readpage(sbi, page, blkaddr, READ_SYNC);
+		if (err)
 			goto out;
 
+		lock_page(page);
+
 		if (cp_ver != cpver_of_node(page))
-			goto out;
+			goto unlock_out;
 
 		if (!is_fsync_dnode(page))
 			goto next;
@@ -129,24 +132,23 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
 							FI_INC_LINK);
 		} else {
 			if (IS_INODE(page) && is_dent_dnode(page)) {
-				if (recover_inode_page(sbi, page)) {
+				err = recover_inode_page(sbi, page);
-					err = -ENOMEM;
+				if (err)
-					goto out;
+					goto unlock_out;
-				}
 			}
 
 			/* add this fsync inode to the list */
 			entry = kmem_cache_alloc(fsync_entry_slab, GFP_NOFS);
 			if (!entry) {
 				err = -ENOMEM;
-				goto out;
+				goto unlock_out;
 			}
 
 			entry->inode = f2fs_iget(sbi->sb, ino_of_node(page));
 			if (IS_ERR(entry->inode)) {
 				err = PTR_ERR(entry->inode);
 				kmem_cache_free(fsync_entry_slab, entry);
-				goto out;
+				goto unlock_out;
 			}
 
 			list_add_tail(&entry->list, head);
@@ -154,16 +156,20 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
 		}
 		if (IS_INODE(page)) {
 			err = recover_inode(entry->inode, page);
-			if (err)
+			if (err == -ENOENT) {
-				goto out;
+				goto next;
+			} else if (err) {
+				err = -EINVAL;
+				goto unlock_out;
+			}
 		}
 next:
 		/* check next segment */
 		blkaddr = next_blkaddr_of_node(page);
-		ClearPageUptodate(page);
 	}
-out:
+unlock_out:
 	unlock_page(page);
+out:
 	__free_pages(page, 0);
 	return err;
 }
@@ -232,13 +238,15 @@ static void check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
 	iput(inode);
 }
 
-static void do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
+static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 					struct page *page, block_t blkaddr)
 {
 	unsigned int start, end;
 	struct dnode_of_data dn;
 	struct f2fs_summary sum;
 	struct node_info ni;
+	int err = 0;
+	int ilock;
 
 	start = start_bidx_of_node(ofs_of_node(page));
 	if (IS_INODE(page))
@@ -246,9 +254,14 @@ static void do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 	else
 		end = start + ADDRS_PER_BLOCK;
 
+	ilock = mutex_lock_op(sbi);
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
-	if (get_dnode_of_data(&dn, start, 0))
+
-		return;
+	err = get_dnode_of_data(&dn, start, ALLOC_NODE);
+	if (err) {
+		mutex_unlock_op(sbi, ilock);
+		return err;
+	}
 
 	wait_on_page_writeback(dn.node_page);
 
@@ -293,14 +306,17 @@ static void do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 
 	recover_node_page(sbi, dn.node_page, &sum, &ni, blkaddr);
 	f2fs_put_dnode(&dn);
+	mutex_unlock_op(sbi, ilock);
+	return 0;
 }
 
-static void recover_data(struct f2fs_sb_info *sbi,
+static int recover_data(struct f2fs_sb_info *sbi,
 				struct list_head *head, int type)
 {
 	unsigned long long cp_ver = le64_to_cpu(sbi->ckpt->checkpoint_ver);
 	struct curseg_info *curseg;
 	struct page *page;
+	int err = 0;
 	block_t blkaddr;
 
 	/* get node pages in the current segment */
@@ -310,23 +326,29 @@ static void recover_data(struct f2fs_sb_info *sbi,
 	/* read node page */
 	page = alloc_page(GFP_NOFS | __GFP_ZERO);
 	if (IS_ERR(page))
-		return;
+		return -ENOMEM;
+
 	lock_page(page);
 
 	while (1) {
 		struct fsync_inode_entry *entry;
 
-		if (f2fs_readpage(sbi, page, blkaddr, READ_SYNC))
+		err = f2fs_readpage(sbi, page, blkaddr, READ_SYNC);
+		if (err)
 			goto out;
 
+		lock_page(page);
+
 		if (cp_ver != cpver_of_node(page))
-			goto out;
+			goto unlock_out;
 
 		entry = get_fsync_inode(head, ino_of_node(page));
 		if (!entry)
 			goto next;
 
-		do_recover_data(sbi, entry->inode, page, blkaddr);
+		err = do_recover_data(sbi, entry->inode, page, blkaddr);
+		if (err)
+			goto out;
 
 		if (entry->blkaddr == blkaddr) {
 			iput(entry->inode);
@@ -336,28 +358,32 @@ static void recover_data(struct f2fs_sb_info *sbi,
 next:
 		/* check next segment */
 		blkaddr = next_blkaddr_of_node(page);
-		ClearPageUptodate(page);
 	}
-out:
+unlock_out:
 	unlock_page(page);
+out:
 	__free_pages(page, 0);
 
-	allocate_new_segments(sbi);
+	if (!err)
+		allocate_new_segments(sbi);
+	return err;
 }
 
-void recover_fsync_data(struct f2fs_sb_info *sbi)
+int recover_fsync_data(struct f2fs_sb_info *sbi)
 {
 	struct list_head inode_list;
+	int err;
 
 	fsync_entry_slab = f2fs_kmem_cache_create("f2fs_fsync_inode_entry",
 			sizeof(struct fsync_inode_entry), NULL);
 	if (unlikely(!fsync_entry_slab))
-		return;
+		return -ENOMEM;
 
 	INIT_LIST_HEAD(&inode_list);
 
 	/* step #1: find fsynced inode numbers */
-	if (find_fsync_dnodes(sbi, &inode_list))
+	err = find_fsync_dnodes(sbi, &inode_list);
+	if (err)
 		goto out;
 
 	if (list_empty(&inode_list))
@@ -365,11 +391,12 @@ void recover_fsync_data(struct f2fs_sb_info *sbi)
 
 	/* step #2: recover data */
 	sbi->por_doing = 1;
-	recover_data(sbi, &inode_list, CURSEG_WARM_NODE);
+	err = recover_data(sbi, &inode_list, CURSEG_WARM_NODE);
 	sbi->por_doing = 0;
 	BUG_ON(!list_empty(&inode_list));
 out:
 	destroy_fsync_dnodes(sbi, &inode_list);
 	kmem_cache_destroy(fsync_entry_slab);
 	write_checkpoint(sbi, false);
+	return err;
 }

fs/f2fs/segment.c

@@ -18,6 +18,7 @@
 #include "f2fs.h"
 #include "segment.h"
 #include "node.h"
+#include <trace/events/f2fs.h>
 
 /*
  * This function balances dirty node and dentry pages.
@@ -49,9 +50,20 @@ static void __locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
 
 	if (dirty_type == DIRTY) {
 		struct seg_entry *sentry = get_seg_entry(sbi, segno);
+		enum dirty_type t = DIRTY_HOT_DATA;
+
 		dirty_type = sentry->type;
+
 		if (!test_and_set_bit(segno, dirty_i->dirty_segmap[dirty_type]))
 			dirty_i->nr_dirty[dirty_type]++;
+
+		/* Only one bitmap should be set */
+		for (; t <= DIRTY_COLD_NODE; t++) {
+			if (t == dirty_type)
+				continue;
+			if (test_and_clear_bit(segno, dirty_i->dirty_segmap[t]))
+				dirty_i->nr_dirty[t]--;
+		}
 	}
 }
 
@@ -64,13 +76,16 @@ static void __remove_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
 		dirty_i->nr_dirty[dirty_type]--;
 
 	if (dirty_type == DIRTY) {
-		struct seg_entry *sentry = get_seg_entry(sbi, segno);
+		enum dirty_type t = DIRTY_HOT_DATA;
-		dirty_type = sentry->type;
+
-		if (test_and_clear_bit(segno,
+		/* clear all the bitmaps */
-					dirty_i->dirty_segmap[dirty_type]))
+		for (; t <= DIRTY_COLD_NODE; t++)
-			dirty_i->nr_dirty[dirty_type]--;
+			if (test_and_clear_bit(segno, dirty_i->dirty_segmap[t]))
-		clear_bit(segno, dirty_i->victim_segmap[FG_GC]);
+				dirty_i->nr_dirty[t]--;
-		clear_bit(segno, dirty_i->victim_segmap[BG_GC]);
+
+		if (get_valid_blocks(sbi, segno, sbi->segs_per_sec) == 0)
+			clear_bit(GET_SECNO(sbi, segno),
+						dirty_i->victim_secmap);
 	}
 }
 
@@ -296,13 +311,12 @@ static void write_sum_page(struct f2fs_sb_info *sbi,
 	f2fs_put_page(page, 1);
 }
 
-static unsigned int check_prefree_segments(struct f2fs_sb_info *sbi,
+static unsigned int check_prefree_segments(struct f2fs_sb_info *sbi, int type)
-					int ofs_unit, int type)
 {
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
 	unsigned long *prefree_segmap = dirty_i->dirty_segmap[PRE];
-	unsigned int segno, next_segno, i;
+	unsigned int segno;
-	int ofs = 0;
+	unsigned int ofs = 0;
 
 	/*
 	 * If there is not enough reserved sections,
@@ -318,28 +332,46 @@ static unsigned int check_prefree_segments(struct f2fs_sb_info *sbi,
 	if (IS_NODESEG(type))
 		return NULL_SEGNO;
 next:
-	segno = find_next_bit(prefree_segmap, TOTAL_SEGS(sbi), ofs++);
+	segno = find_next_bit(prefree_segmap, TOTAL_SEGS(sbi), ofs);
-	ofs = ((segno / ofs_unit) * ofs_unit) + ofs_unit;
+	ofs += sbi->segs_per_sec;
+
 	if (segno < TOTAL_SEGS(sbi)) {
+		int i;
+
 		/* skip intermediate segments in a section */
-		if (segno % ofs_unit)
+		if (segno % sbi->segs_per_sec)
+			goto next;
+
+		/* skip if the section is currently used */
+		if (sec_usage_check(sbi, GET_SECNO(sbi, segno)))
 			goto next;
 
 		/* skip if whole section is not prefree */
-		next_segno = find_next_zero_bit(prefree_segmap,
+		for (i = 1; i < sbi->segs_per_sec; i++)
-						TOTAL_SEGS(sbi), segno + 1);
+			if (!test_bit(segno + i, prefree_segmap))
-		if (next_segno - segno < ofs_unit)
+				goto next;
-			goto next;
 
 		/* skip if whole section was not free at the last checkpoint */
-		for (i = 0; i < ofs_unit; i++)
+		for (i = 0; i < sbi->segs_per_sec; i++)
-			if (get_seg_entry(sbi, segno)->ckpt_valid_blocks)
+			if (get_seg_entry(sbi, segno + i)->ckpt_valid_blocks)
 				goto next;
+
 		return segno;
 	}
 	return NULL_SEGNO;
 }
 
+static int is_next_segment_free(struct f2fs_sb_info *sbi, int type)
+{
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
+	unsigned int segno = curseg->segno;
+	struct free_segmap_info *free_i = FREE_I(sbi);
+
+	if (segno + 1 < TOTAL_SEGS(sbi) && (segno + 1) % sbi->segs_per_sec)
+		return !test_bit(segno + 1, free_i->free_segmap);
+	return 0;
+}
+
 /*
  * Find a new segment from the free segments bitmap to right order
  * This function should be returned with success, otherwise BUG
@@ -348,9 +380,8 @@ static void get_new_segment(struct f2fs_sb_info *sbi,
 			unsigned int *newseg, bool new_sec, int dir)
 {
 	struct free_segmap_info *free_i = FREE_I(sbi);
-	unsigned int total_secs = sbi->total_sections;
 	unsigned int segno, secno, zoneno;
-	unsigned int total_zones = sbi->total_sections / sbi->secs_per_zone;
+	unsigned int total_zones = TOTAL_SECS(sbi) / sbi->secs_per_zone;
 	unsigned int hint = *newseg / sbi->segs_per_sec;
 	unsigned int old_zoneno = GET_ZONENO_FROM_SEGNO(sbi, *newseg);
 	unsigned int left_start = hint;
@@ -363,16 +394,17 @@ static void get_new_segment(struct f2fs_sb_info *sbi,
 	if (!new_sec && ((*newseg + 1) % sbi->segs_per_sec)) {
 		segno = find_next_zero_bit(free_i->free_segmap,
 					TOTAL_SEGS(sbi), *newseg + 1);
-		if (segno < TOTAL_SEGS(sbi))
+		if (segno - *newseg < sbi->segs_per_sec -
+					(*newseg % sbi->segs_per_sec))
 			goto got_it;
 	}
 find_other_zone:
-	secno = find_next_zero_bit(free_i->free_secmap, total_secs, hint);
+	secno = find_next_zero_bit(free_i->free_secmap, TOTAL_SECS(sbi), hint);
-	if (secno >= total_secs) {
+	if (secno >= TOTAL_SECS(sbi)) {
 		if (dir == ALLOC_RIGHT) {
 			secno = find_next_zero_bit(free_i->free_secmap,
-						total_secs, 0);
+							TOTAL_SECS(sbi), 0);
-			BUG_ON(secno >= total_secs);
+			BUG_ON(secno >= TOTAL_SECS(sbi));
 		} else {
 			go_left = 1;
 			left_start = hint - 1;
@@ -387,8 +419,8 @@ find_other_zone:
 			continue;
 		}
 		left_start = find_next_zero_bit(free_i->free_secmap,
-						total_secs, 0);
+							TOTAL_SECS(sbi), 0);
-		BUG_ON(left_start >= total_secs);
+		BUG_ON(left_start >= TOTAL_SECS(sbi));
 		break;
 	}
 	secno = left_start;
@@ -561,20 +593,20 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi,
 						int type, bool force)
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, type);
-	unsigned int ofs_unit;
 
 	if (force) {
 		new_curseg(sbi, type, true);
 		goto out;
 	}
 
-	ofs_unit = need_SSR(sbi) ? 1 : sbi->segs_per_sec;
+	curseg->next_segno = check_prefree_segments(sbi, type);
-	curseg->next_segno = check_prefree_segments(sbi, ofs_unit, type);
 
 	if (curseg->next_segno != NULL_SEGNO)
 		change_curseg(sbi, type, false);
 	else if (type == CURSEG_WARM_NODE)
 		new_curseg(sbi, type, false);
+	else if (curseg->alloc_type == LFS && is_next_segment_free(sbi, type))
+		new_curseg(sbi, type, false);
 	else if (need_SSR(sbi) && get_ssr_segment(sbi, type))
 		change_curseg(sbi, type, true);
 	else
@@ -656,10 +688,16 @@ static void do_submit_bio(struct f2fs_sb_info *sbi,
 	if (type >= META_FLUSH)
 		rw = WRITE_FLUSH_FUA;
 
+	if (btype == META)
+		rw |= REQ_META;
+
 	if (sbi->bio[btype]) {
 		struct bio_private *p = sbi->bio[btype]->bi_private;
 		p->sbi = sbi;
 		sbi->bio[btype]->bi_end_io = f2fs_end_io_write;
+
+		trace_f2fs_do_submit_bio(sbi->sb, btype, sync, sbi->bio[btype]);
+
 		if (type == META_FLUSH) {
 			DECLARE_COMPLETION_ONSTACK(wait);
 			p->is_sync = true;
@@ -696,7 +734,7 @@ static void submit_write_page(struct f2fs_sb_info *sbi, struct page *page,
 		do_submit_bio(sbi, type, false);
 alloc_new:
 	if (sbi->bio[type] == NULL) {
-		sbi->bio[type] = f2fs_bio_alloc(bdev, bio_get_nr_vecs(bdev));
+		sbi->bio[type] = f2fs_bio_alloc(bdev, max_hw_blocks(sbi));
 		sbi->bio[type]->bi_sector = SECTOR_FROM_BLOCK(sbi, blk_addr);
 		/*
 		 * The end_io will be assigned at the sumbission phase.
@@ -714,6 +752,7 @@ alloc_new:
 	sbi->last_block_in_bio[type] = blk_addr;
 
 	up_write(&sbi->bio_sem);
+	trace_f2fs_submit_write_page(page, blk_addr, type);
 }
 
 static bool __has_curseg_space(struct f2fs_sb_info *sbi, int type)
@@ -1390,7 +1429,7 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
 	}
 
 	if (sbi->segs_per_sec > 1) {
-		sit_i->sec_entries = vzalloc(sbi->total_sections *
+		sit_i->sec_entries = vzalloc(TOTAL_SECS(sbi) *
 					sizeof(struct sec_entry));
 		if (!sit_i->sec_entries)
 			return -ENOMEM;
@@ -1403,10 +1442,9 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
 	bitmap_size = __bitmap_size(sbi, SIT_BITMAP);
 	src_bitmap = __bitmap_ptr(sbi, SIT_BITMAP);
 
-	dst_bitmap = kzalloc(bitmap_size, GFP_KERNEL);
+	dst_bitmap = kmemdup(src_bitmap, bitmap_size, GFP_KERNEL);
 	if (!dst_bitmap)
 		return -ENOMEM;
-	memcpy(dst_bitmap, src_bitmap, bitmap_size);
 
 	/* init SIT information */
 	sit_i->s_ops = &default_salloc_ops;
@@ -1442,7 +1480,7 @@ static int build_free_segmap(struct f2fs_sb_info *sbi)
 	if (!free_i->free_segmap)
 		return -ENOMEM;
 
-	sec_bitmap_size = f2fs_bitmap_size(sbi->total_sections);
+	sec_bitmap_size = f2fs_bitmap_size(TOTAL_SECS(sbi));
 	free_i->free_secmap = kmalloc(sec_bitmap_size, GFP_KERNEL);
 	if (!free_i->free_secmap)
 		return -ENOMEM;
@@ -1559,14 +1597,13 @@ static void init_dirty_segmap(struct f2fs_sb_info *sbi)
 	}
 }
 
-static int init_victim_segmap(struct f2fs_sb_info *sbi)
+static int init_victim_secmap(struct f2fs_sb_info *sbi)
 {
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
-	unsigned int bitmap_size = f2fs_bitmap_size(TOTAL_SEGS(sbi));
+	unsigned int bitmap_size = f2fs_bitmap_size(TOTAL_SECS(sbi));
 
-	dirty_i->victim_segmap[FG_GC] = kzalloc(bitmap_size, GFP_KERNEL);
+	dirty_i->victim_secmap = kzalloc(bitmap_size, GFP_KERNEL);
-	dirty_i->victim_segmap[BG_GC] = kzalloc(bitmap_size, GFP_KERNEL);
+	if (!dirty_i->victim_secmap)
-	if (!dirty_i->victim_segmap[FG_GC] || !dirty_i->victim_segmap[BG_GC])
 		return -ENOMEM;
 	return 0;
 }
@@ -1593,7 +1630,7 @@ static int build_dirty_segmap(struct f2fs_sb_info *sbi)
 	}
 
 	init_dirty_segmap(sbi);
-	return init_victim_segmap(sbi);
+	return init_victim_secmap(sbi);
 }
 
 /*
@@ -1680,18 +1717,10 @@ static void discard_dirty_segmap(struct f2fs_sb_info *sbi,
 	mutex_unlock(&dirty_i->seglist_lock);
 }
 
-void reset_victim_segmap(struct f2fs_sb_info *sbi)
+static void destroy_victim_secmap(struct f2fs_sb_info *sbi)
-{
-	unsigned int bitmap_size = f2fs_bitmap_size(TOTAL_SEGS(sbi));
-	memset(DIRTY_I(sbi)->victim_segmap[FG_GC], 0, bitmap_size);
-}
-
-static void destroy_victim_segmap(struct f2fs_sb_info *sbi)
 {
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
-
+	kfree(dirty_i->victim_secmap);
-	kfree(dirty_i->victim_segmap[FG_GC]);
-	kfree(dirty_i->victim_segmap[BG_GC]);
 }
 
 static void destroy_dirty_segmap(struct f2fs_sb_info *sbi)
@@ -1706,7 +1735,7 @@ static void destroy_dirty_segmap(struct f2fs_sb_info *sbi)
 	for (i = 0; i < NR_DIRTY_TYPE; i++)
 		discard_dirty_segmap(sbi, i);
 
-	destroy_victim_segmap(sbi);
+	destroy_victim_secmap(sbi);
 	SM_I(sbi)->dirty_info = NULL;
 	kfree(dirty_i);
 }

fs/f2fs/segment.h

@@ -8,10 +8,13 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+#include <linux/blkdev.h>
+
 /* constant macro */
 #define NULL_SEGNO			((unsigned int)(~0))
+#define NULL_SECNO			((unsigned int)(~0))
 
-/* V: Logical segment # in volume, R: Relative segment # in main area */
+/* L: Logical segment # in volume, R: Relative segment # in main area */
 #define GET_L2R_SEGNO(free_i, segno)	(segno - free_i->start_segno)
 #define GET_R2L_SEGNO(free_i, segno)	(segno + free_i->start_segno)
 
@@ -23,13 +26,13 @@
 	((t == CURSEG_HOT_NODE) || (t == CURSEG_COLD_NODE) ||		\
 	(t == CURSEG_WARM_NODE))
 
-#define IS_CURSEG(sbi, segno)						\
+#define IS_CURSEG(sbi, seg)						\
-	((segno == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno) ||	\
+	((seg == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno) ||	\
-	 (segno == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno) ||	\
+	 (seg == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno) ||	\
-	 (segno == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno) ||	\
+	 (seg == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno) ||	\
-	 (segno == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno) ||	\
+	 (seg == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno) ||	\
-	 (segno == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno) ||	\
+	 (seg == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno) ||	\
-	 (segno == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno))
+	 (seg == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno))
 
 #define IS_CURSEC(sbi, secno)						\
 	((secno == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno /		\
@@ -81,9 +84,12 @@
 #define f2fs_bitmap_size(nr)			\
 	(BITS_TO_LONGS(nr) * sizeof(unsigned long))
 #define TOTAL_SEGS(sbi)	(SM_I(sbi)->main_segments)
+#define TOTAL_SECS(sbi)	(sbi->total_sections)
 
 #define SECTOR_FROM_BLOCK(sbi, blk_addr)				\
 	(blk_addr << ((sbi)->log_blocksize - F2FS_LOG_SECTOR_SIZE))
+#define SECTOR_TO_BLOCK(sbi, sectors)					\
+	(sectors >> ((sbi)->log_blocksize - F2FS_LOG_SECTOR_SIZE))
 
 /* during checkpoint, bio_private is used to synchronize the last bio */
 struct bio_private {
@@ -213,7 +219,7 @@ struct dirty_seglist_info {
 	unsigned long *dirty_segmap[NR_DIRTY_TYPE];
 	struct mutex seglist_lock;		/* lock for segment bitmaps */
 	int nr_dirty[NR_DIRTY_TYPE];		/* # of dirty segments */
-	unsigned long *victim_segmap[2];	/* BG_GC, FG_GC */
+	unsigned long *victim_secmap;		/* background GC victims */
 };
 
 /* victim selection function for cleaning and SSR */
@@ -464,8 +470,7 @@ static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, int freed)
 
 static inline int utilization(struct f2fs_sb_info *sbi)
 {
-	return (long int)valid_user_blocks(sbi) * 100 /
+	return div_u64(valid_user_blocks(sbi) * 100, sbi->user_block_count);
-			(long int)sbi->user_block_count;
 }
 
 /*
@@ -616,3 +621,17 @@ static inline block_t sum_blk_addr(struct f2fs_sb_info *sbi, int base, int type)
 		le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_total_block_count)
 				- (base + 1) + type;
 }
+
+static inline bool sec_usage_check(struct f2fs_sb_info *sbi, unsigned int secno)
+{
+	if (IS_CURSEC(sbi, secno) || (sbi->cur_victim_sec == secno))
+		return true;
+	return false;
+}
+
+static inline unsigned int max_hw_blocks(struct f2fs_sb_info *sbi)
+{
+	struct block_device *bdev = sbi->sb->s_bdev;
+	struct request_queue *q = bdev_get_queue(bdev);
+	return SECTOR_TO_BLOCK(sbi, queue_max_sectors(q));
+}

fs/f2fs/super.c

@@ -12,7 +12,6 @@
 #include <linux/init.h>
 #include <linux/fs.h>
 #include <linux/statfs.h>
-#include <linux/proc_fs.h>
 #include <linux/buffer_head.h>
 #include <linux/backing-dev.h>
 #include <linux/kthread.h>
@@ -21,12 +20,17 @@
 #include <linux/seq_file.h>
 #include <linux/random.h>
 #include <linux/exportfs.h>
+#include <linux/blkdev.h>
 #include <linux/f2fs_fs.h>
 
 #include "f2fs.h"
 #include "node.h"
+#include "segment.h"
 #include "xattr.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/f2fs.h>
+
 static struct kmem_cache *f2fs_inode_cachep;
 
 enum {
@@ -94,6 +98,20 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
 	return &fi->vfs_inode;
 }
 
+static int f2fs_drop_inode(struct inode *inode)
+{
+	/*
+	 * This is to avoid a deadlock condition like below.
+	 * writeback_single_inode(inode)
+	 *  - f2fs_write_data_page
+	 *    - f2fs_gc -> iput -> evict
+	 *       - inode_wait_for_writeback(inode)
+	 */
+	if (!inode_unhashed(inode) && inode->i_state & I_SYNC)
+		return 0;
+	return generic_drop_inode(inode);
+}
+
 static void f2fs_i_callback(struct rcu_head *head)
 {
 	struct inode *inode = container_of(head, struct inode, i_rcu);
@@ -132,13 +150,18 @@ int f2fs_sync_fs(struct super_block *sb, int sync)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 
+	trace_f2fs_sync_fs(sb, sync);
+
 	if (!sbi->s_dirty && !get_pages(sbi, F2FS_DIRTY_NODES))
 		return 0;
 
-	if (sync)
+	if (sync) {
+		mutex_lock(&sbi->gc_mutex);
 		write_checkpoint(sbi, false);
-	else
+		mutex_unlock(&sbi->gc_mutex);
+	} else {
 		f2fs_balance_fs(sbi);
+	}
 
 	return 0;
 }
@@ -180,7 +203,7 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_files = sbi->total_node_count;
 	buf->f_ffree = sbi->total_node_count - valid_inode_count(sbi);
 
-	buf->f_namelen = F2FS_MAX_NAME_LEN;
+	buf->f_namelen = F2FS_NAME_LEN;
 	buf->f_fsid.val[0] = (u32)id;
 	buf->f_fsid.val[1] = (u32)(id >> 32);
 
@@ -223,6 +246,7 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 
 static struct super_operations f2fs_sops = {
 	.alloc_inode	= f2fs_alloc_inode,
+	.drop_inode	= f2fs_drop_inode,
 	.destroy_inode	= f2fs_destroy_inode,
 	.write_inode	= f2fs_write_inode,
 	.show_options	= f2fs_show_options,
@@ -457,6 +481,7 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
 	sbi->root_ino_num = le32_to_cpu(raw_super->root_ino);
 	sbi->node_ino_num = le32_to_cpu(raw_super->node_ino);
 	sbi->meta_ino_num = le32_to_cpu(raw_super->meta_ino);
+	sbi->cur_victim_sec = NULL_SECNO;
 
 	for (i = 0; i < NR_COUNT_TYPE; i++)
 		atomic_set(&sbi->nr_pages[i], 0);
@@ -473,7 +498,7 @@ static int validate_superblock(struct super_block *sb,
 	if (!*raw_super_buf) {
 		f2fs_msg(sb, KERN_ERR, "unable to read %s superblock",
 				super);
-		return 1;
+		return -EIO;
 	}
 
 	*raw_super = (struct f2fs_super_block *)
@@ -485,7 +510,7 @@ static int validate_superblock(struct super_block *sb,
 
 	f2fs_msg(sb, KERN_ERR, "Can't find a valid F2FS filesystem "
 				"in %s superblock", super);
-	return 1;
+	return -EINVAL;
 }
 
 static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
@@ -508,9 +533,12 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 		goto free_sbi;
 	}
 
-	if (validate_superblock(sb, &raw_super, &raw_super_buf, 0)) {
+	err = validate_superblock(sb, &raw_super, &raw_super_buf, 0);
+	if (err) {
 		brelse(raw_super_buf);
-		if (validate_superblock(sb, &raw_super, &raw_super_buf, 1))
+		/* check secondary superblock when primary failed */
+		err = validate_superblock(sb, &raw_super, &raw_super_buf, 1);
+		if (err)
 			goto free_sb_buf;
 	}
 	/* init some FS parameters */
@@ -525,7 +553,8 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	set_opt(sbi, POSIX_ACL);
 #endif
 	/* parse mount options */
-	if (parse_options(sb, sbi, (char *)data))
+	err = parse_options(sb, sbi, (char *)data);
+	if (err)
 		goto free_sb_buf;
 
 	sb->s_maxbytes = max_file_size(le32_to_cpu(raw_super->log_blocksize));
@@ -547,11 +576,11 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->raw_super = raw_super;
 	sbi->raw_super_buf = raw_super_buf;
 	mutex_init(&sbi->gc_mutex);
-	mutex_init(&sbi->write_inode);
 	mutex_init(&sbi->writepages);
 	mutex_init(&sbi->cp_mutex);
-	for (i = 0; i < NR_LOCK_TYPE; i++)
+	for (i = 0; i < NR_GLOBAL_LOCKS; i++)
 		mutex_init(&sbi->fs_lock[i]);
+	mutex_init(&sbi->node_write);
 	sbi->por_doing = 0;
 	spin_lock_init(&sbi->stat_lock);
 	init_rwsem(&sbi->bio_sem);
@@ -638,8 +667,12 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	}
 
 	/* recover fsynced data */
-	if (!test_opt(sbi, DISABLE_ROLL_FORWARD))
+	if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) {
-		recover_fsync_data(sbi);
+		err = recover_fsync_data(sbi);
+		if (err)
+			f2fs_msg(sb, KERN_ERR,
+				"Cannot recover all fsync data errno=%ld", err);
+	}
 
 	/* After POR, we can run background GC thread */
 	err = start_gc_thread(sbi);
@@ -650,6 +683,14 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	if (err)
 		goto fail;
 
+	if (test_opt(sbi, DISCARD)) {
+		struct request_queue *q = bdev_get_queue(sb->s_bdev);
+		if (!blk_queue_discard(q))
+			f2fs_msg(sb, KERN_WARNING,
+					"mounting with \"discard\" option, but "
+					"the device does not support discard");
+	}
+
 	return 0;
 fail:
 	stop_gc_thread(sbi);

fs/f2fs/xattr.c

@@ -307,27 +307,30 @@ int f2fs_setxattr(struct inode *inode, int name_index, const char *name,
 	int error, found, free, newsize;
 	size_t name_len;
 	char *pval;
+	int ilock;
 
 	if (name == NULL)
 		return -EINVAL;
-	name_len = strlen(name);
 
 	if (value == NULL)
 		value_len = 0;
 
-	if (name_len > 255 || value_len > MAX_VALUE_LEN)
+	name_len = strlen(name);
+
+	if (name_len > F2FS_NAME_LEN || value_len > MAX_VALUE_LEN)
 		return -ERANGE;
 
 	f2fs_balance_fs(sbi);
 
-	mutex_lock_op(sbi, NODE_NEW);
+	ilock = mutex_lock_op(sbi);
+
 	if (!fi->i_xattr_nid) {
 		/* Allocate new attribute block */
 		struct dnode_of_data dn;
 
 		if (!alloc_nid(sbi, &fi->i_xattr_nid)) {
-			mutex_unlock_op(sbi, NODE_NEW);
+			error = -ENOSPC;
-			return -ENOSPC;
+			goto exit;
 		}
 		set_new_dnode(&dn, inode, NULL, NULL, fi->i_xattr_nid);
 		mark_inode_dirty(inode);
@@ -336,8 +339,8 @@ int f2fs_setxattr(struct inode *inode, int name_index, const char *name,
 		if (IS_ERR(page)) {
 			alloc_nid_failed(sbi, fi->i_xattr_nid);
 			fi->i_xattr_nid = 0;
-			mutex_unlock_op(sbi, NODE_NEW);
+			error = PTR_ERR(page);
-			return PTR_ERR(page);
+			goto exit;
 		}
 
 		alloc_nid_done(sbi, fi->i_xattr_nid);
@@ -349,8 +352,8 @@ int f2fs_setxattr(struct inode *inode, int name_index, const char *name,
 		/* The inode already has an extended attribute block. */
 		page = get_node_page(sbi, fi->i_xattr_nid);
 		if (IS_ERR(page)) {
-			mutex_unlock_op(sbi, NODE_NEW);
+			error = PTR_ERR(page);
-			return PTR_ERR(page);
+			goto exit;
 		}
 
 		base_addr = page_address(page);
@@ -432,12 +435,13 @@ int f2fs_setxattr(struct inode *inode, int name_index, const char *name,
 		inode->i_ctime = CURRENT_TIME;
 		clear_inode_flag(fi, FI_ACL_MODE);
 	}
-	f2fs_write_inode(inode, NULL);
+	update_inode_page(inode);
-	mutex_unlock_op(sbi, NODE_NEW);
+	mutex_unlock_op(sbi, ilock);
 
 	return 0;
 cleanup:
 	f2fs_put_page(page, 1);
-	mutex_unlock_op(sbi, NODE_NEW);
+exit:
+	mutex_unlock_op(sbi, ilock);
 	return error;
 }

include/linux/f2fs_fs.h

@@ -139,7 +139,7 @@ struct f2fs_extent {
 	__le32 len;		/* lengh of the extent */
 } __packed;
 
-#define F2FS_MAX_NAME_LEN	256
+#define F2FS_NAME_LEN		255
 #define ADDRS_PER_INODE         923	/* Address Pointers in an Inode */
 #define ADDRS_PER_BLOCK         1018	/* Address Pointers in a Direct Block */
 #define NIDS_PER_BLOCK          1018	/* Node IDs in an Indirect Block */
@@ -165,7 +165,8 @@ struct f2fs_inode {
 	__le32 i_flags;			/* file attributes */
 	__le32 i_pino;			/* parent inode number */
 	__le32 i_namelen;		/* file name length */
-	__u8 i_name[F2FS_MAX_NAME_LEN];	/* file name for SPOR */
+	__u8 i_name[F2FS_NAME_LEN];	/* file name for SPOR */
+	__u8 i_reserved2;		/* for backward compatibility */
 
 	struct f2fs_extent i_ext;	/* caching a largest extent */
 
@@ -362,10 +363,10 @@ struct f2fs_summary_block {
 typedef __le32	f2fs_hash_t;
 
 /* One directory entry slot covers 8bytes-long file name */
-#define F2FS_NAME_LEN		8
+#define F2FS_SLOT_LEN		8
-#define F2FS_NAME_LEN_BITS	3
+#define F2FS_SLOT_LEN_BITS	3
 
-#define GET_DENTRY_SLOTS(x)	((x + F2FS_NAME_LEN - 1) >> F2FS_NAME_LEN_BITS)
+#define GET_DENTRY_SLOTS(x)	((x + F2FS_SLOT_LEN - 1) >> F2FS_SLOT_LEN_BITS)
 
 /* the number of dentry in a block */
 #define NR_DENTRY_IN_BLOCK	214
@@ -377,10 +378,10 @@ typedef __le32	f2fs_hash_t;
 #define SIZE_OF_DENTRY_BITMAP	((NR_DENTRY_IN_BLOCK + BITS_PER_BYTE - 1) / \
 					BITS_PER_BYTE)
 #define SIZE_OF_RESERVED	(PAGE_SIZE - ((SIZE_OF_DIR_ENTRY + \
-				F2FS_NAME_LEN) * \
+				F2FS_SLOT_LEN) * \
 				NR_DENTRY_IN_BLOCK + SIZE_OF_DENTRY_BITMAP))
 
-/* One directory entry slot representing F2FS_NAME_LEN-sized file name */
+/* One directory entry slot representing F2FS_SLOT_LEN-sized file name */
 struct f2fs_dir_entry {
 	__le32 hash_code;	/* hash code of file name */
 	__le32 ino;		/* inode number */
@@ -394,7 +395,7 @@ struct f2fs_dentry_block {
 	__u8 dentry_bitmap[SIZE_OF_DENTRY_BITMAP];
 	__u8 reserved[SIZE_OF_RESERVED];
 	struct f2fs_dir_entry dentry[NR_DENTRY_IN_BLOCK];
-	__u8 filename[NR_DENTRY_IN_BLOCK][F2FS_NAME_LEN];
+	__u8 filename[NR_DENTRY_IN_BLOCK][F2FS_SLOT_LEN];
 } __packed;
 
 /* file types used in inode_info->flags */

include/trace/events/f2fs.h

@@ -0,0 +1,682 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM f2fs
+
+#if !defined(_TRACE_F2FS_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_F2FS_H
+
+#include <linux/tracepoint.h>
+
+#define show_dev(entry)		MAJOR(entry->dev), MINOR(entry->dev)
+#define show_dev_ino(entry)	show_dev(entry), (unsigned long)entry->ino
+
+#define show_block_type(type)						\
+	__print_symbolic(type,						\
+		{ NODE,		"NODE" },				\
+		{ DATA,		"DATA" },				\
+		{ META,		"META" },				\
+		{ META_FLUSH,	"META_FLUSH" })
+
+#define show_bio_type(type)						\
+	__print_symbolic(type,						\
+		{ READ, 	"READ" },				\
+		{ READA, 	"READAHEAD" },				\
+		{ READ_SYNC, 	"READ_SYNC" },				\
+		{ WRITE, 	"WRITE" },				\
+		{ WRITE_SYNC, 	"WRITE_SYNC" },				\
+		{ WRITE_FLUSH,	"WRITE_FLUSH" },			\
+		{ WRITE_FUA, 	"WRITE_FUA" })
+
+#define show_data_type(type)						\
+	__print_symbolic(type,						\
+		{ CURSEG_HOT_DATA, 	"Hot DATA" },			\
+		{ CURSEG_WARM_DATA, 	"Warm DATA" },			\
+		{ CURSEG_COLD_DATA, 	"Cold DATA" },			\
+		{ CURSEG_HOT_NODE, 	"Hot NODE" },			\
+		{ CURSEG_WARM_NODE, 	"Warm NODE" },			\
+		{ CURSEG_COLD_NODE, 	"Cold NODE" },			\
+		{ NO_CHECK_TYPE, 	"No TYPE" })
+
+#define show_gc_type(type)						\
+	__print_symbolic(type,						\
+		{ FG_GC,	"Foreground GC" },			\
+		{ BG_GC,	"Background GC" })
+
+#define show_alloc_mode(type)						\
+	__print_symbolic(type,						\
+		{ LFS,	"LFS-mode" },					\
+		{ SSR,	"SSR-mode" })
+
+#define show_victim_policy(type)					\
+	__print_symbolic(type,						\
+		{ GC_GREEDY,	"Greedy" },				\
+		{ GC_CB,	"Cost-Benefit" })
+
+struct victim_sel_policy;
+
+DECLARE_EVENT_CLASS(f2fs__inode,
+
+	TP_PROTO(struct inode *inode),
+
+	TP_ARGS(inode),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(ino_t,	pino)
+		__field(umode_t, mode)
+		__field(loff_t,	size)
+		__field(unsigned int, nlink)
+		__field(blkcnt_t, blocks)
+		__field(__u8,	advise)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->pino	= F2FS_I(inode)->i_pino;
+		__entry->mode	= inode->i_mode;
+		__entry->nlink	= inode->i_nlink;
+		__entry->size	= inode->i_size;
+		__entry->blocks	= inode->i_blocks;
+		__entry->advise	= F2FS_I(inode)->i_advise;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, pino = %lu, i_mode = 0x%hx, "
+		"i_size = %lld, i_nlink = %u, i_blocks = %llu, i_advise = 0x%x",
+		show_dev_ino(__entry),
+		(unsigned long)__entry->pino,
+		__entry->mode,
+		__entry->size,
+		(unsigned int)__entry->nlink,
+		(unsigned long long)__entry->blocks,
+		(unsigned char)__entry->advise)
+);
+
+DECLARE_EVENT_CLASS(f2fs__inode_exit,
+
+	TP_PROTO(struct inode *inode, int ret),
+
+	TP_ARGS(inode, ret),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(int,	ret)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->ret	= ret;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, ret = %d",
+		show_dev_ino(__entry),
+		__entry->ret)
+);
+
+DEFINE_EVENT(f2fs__inode, f2fs_sync_file_enter,
+
+	TP_PROTO(struct inode *inode),
+
+	TP_ARGS(inode)
+);
+
+TRACE_EVENT(f2fs_sync_file_exit,
+
+	TP_PROTO(struct inode *inode, bool need_cp, int datasync, int ret),
+
+	TP_ARGS(inode, need_cp, datasync, ret),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(bool,	need_cp)
+		__field(int,	datasync)
+		__field(int,	ret)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= inode->i_sb->s_dev;
+		__entry->ino		= inode->i_ino;
+		__entry->need_cp	= need_cp;
+		__entry->datasync	= datasync;
+		__entry->ret		= ret;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, checkpoint is %s, "
+		"datasync = %d, ret = %d",
+		show_dev_ino(__entry),
+		__entry->need_cp ? "needed" : "not needed",
+		__entry->datasync,
+		__entry->ret)
+);
+
+TRACE_EVENT(f2fs_sync_fs,
+
+	TP_PROTO(struct super_block *sb, int wait),
+
+	TP_ARGS(sb, wait),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(int,	dirty)
+		__field(int,	wait)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= sb->s_dev;
+		__entry->dirty	= F2FS_SB(sb)->s_dirty;
+		__entry->wait	= wait;
+	),
+
+	TP_printk("dev = (%d,%d), superblock is %s, wait = %d",
+		show_dev(__entry),
+		__entry->dirty ? "dirty" : "not dirty",
+		__entry->wait)
+);
+
+DEFINE_EVENT(f2fs__inode, f2fs_iget,
+
+	TP_PROTO(struct inode *inode),
+
+	TP_ARGS(inode)
+);
+
+DEFINE_EVENT(f2fs__inode_exit, f2fs_iget_exit,
+
+	TP_PROTO(struct inode *inode, int ret),
+
+	TP_ARGS(inode, ret)
+);
+
+DEFINE_EVENT(f2fs__inode, f2fs_evict_inode,
+
+	TP_PROTO(struct inode *inode),
+
+	TP_ARGS(inode)
+);
+
+DEFINE_EVENT(f2fs__inode_exit, f2fs_new_inode,
+
+	TP_PROTO(struct inode *inode, int ret),
+
+	TP_ARGS(inode, ret)
+);
+
+TRACE_EVENT(f2fs_unlink_enter,
+
+	TP_PROTO(struct inode *dir, struct dentry *dentry),
+
+	TP_ARGS(dir, dentry),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(loff_t,	size)
+		__field(blkcnt_t, blocks)
+		__field(const char *,	name)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= dir->i_sb->s_dev;
+		__entry->ino	= dir->i_ino;
+		__entry->size	= dir->i_size;
+		__entry->blocks	= dir->i_blocks;
+		__entry->name	= dentry->d_name.name;
+	),
+
+	TP_printk("dev = (%d,%d), dir ino = %lu, i_size = %lld, "
+		"i_blocks = %llu, name = %s",
+		show_dev_ino(__entry),
+		__entry->size,
+		(unsigned long long)__entry->blocks,
+		__entry->name)
+);
+
+DEFINE_EVENT(f2fs__inode_exit, f2fs_unlink_exit,
+
+	TP_PROTO(struct inode *inode, int ret),
+
+	TP_ARGS(inode, ret)
+);
+
+DEFINE_EVENT(f2fs__inode, f2fs_truncate,
+
+	TP_PROTO(struct inode *inode),
+
+	TP_ARGS(inode)
+);
+
+TRACE_EVENT(f2fs_truncate_data_blocks_range,
+
+	TP_PROTO(struct inode *inode, nid_t nid, unsigned int ofs, int free),
+
+	TP_ARGS(inode, nid,  ofs, free),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(nid_t,	nid)
+		__field(unsigned int,	ofs)
+		__field(int,	free)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->nid	= nid;
+		__entry->ofs	= ofs;
+		__entry->free	= free;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, nid = %u, offset = %u, freed = %d",
+		show_dev_ino(__entry),
+		(unsigned int)__entry->nid,
+		__entry->ofs,
+		__entry->free)
+);
+
+DECLARE_EVENT_CLASS(f2fs__truncate_op,
+
+	TP_PROTO(struct inode *inode, u64 from),
+
+	TP_ARGS(inode, from),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(loff_t,	size)
+		__field(blkcnt_t, blocks)
+		__field(u64,	from)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->size	= inode->i_size;
+		__entry->blocks	= inode->i_blocks;
+		__entry->from	= from;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, i_size = %lld, i_blocks = %llu, "
+		"start file offset = %llu",
+		show_dev_ino(__entry),
+		__entry->size,
+		(unsigned long long)__entry->blocks,
+		(unsigned long long)__entry->from)
+);
+
+DEFINE_EVENT(f2fs__truncate_op, f2fs_truncate_blocks_enter,
+
+	TP_PROTO(struct inode *inode, u64 from),
+
+	TP_ARGS(inode, from)
+);
+
+DEFINE_EVENT(f2fs__inode_exit, f2fs_truncate_blocks_exit,
+
+	TP_PROTO(struct inode *inode, int ret),
+
+	TP_ARGS(inode, ret)
+);
+
+DEFINE_EVENT(f2fs__truncate_op, f2fs_truncate_inode_blocks_enter,
+
+	TP_PROTO(struct inode *inode, u64 from),
+
+	TP_ARGS(inode, from)
+);
+
+DEFINE_EVENT(f2fs__inode_exit, f2fs_truncate_inode_blocks_exit,
+
+	TP_PROTO(struct inode *inode, int ret),
+
+	TP_ARGS(inode, ret)
+);
+
+DECLARE_EVENT_CLASS(f2fs__truncate_node,
+
+	TP_PROTO(struct inode *inode, nid_t nid, block_t blk_addr),
+
+	TP_ARGS(inode, nid, blk_addr),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(nid_t,	nid)
+		__field(block_t,	blk_addr)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= inode->i_sb->s_dev;
+		__entry->ino		= inode->i_ino;
+		__entry->nid		= nid;
+		__entry->blk_addr	= blk_addr;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, nid = %u, block_address = 0x%llx",
+		show_dev_ino(__entry),
+		(unsigned int)__entry->nid,
+		(unsigned long long)__entry->blk_addr)
+);
+
+DEFINE_EVENT(f2fs__truncate_node, f2fs_truncate_nodes_enter,
+
+	TP_PROTO(struct inode *inode, nid_t nid, block_t blk_addr),
+
+	TP_ARGS(inode, nid, blk_addr)
+);
+
+DEFINE_EVENT(f2fs__inode_exit, f2fs_truncate_nodes_exit,
+
+	TP_PROTO(struct inode *inode, int ret),
+
+	TP_ARGS(inode, ret)
+);
+
+DEFINE_EVENT(f2fs__truncate_node, f2fs_truncate_node,
+
+	TP_PROTO(struct inode *inode, nid_t nid, block_t blk_addr),
+
+	TP_ARGS(inode, nid, blk_addr)
+);
+
+TRACE_EVENT(f2fs_truncate_partial_nodes,
+
+	TP_PROTO(struct inode *inode, nid_t nid[], int depth, int err),
+
+	TP_ARGS(inode, nid, depth, err),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(nid_t,	nid[3])
+		__field(int,	depth)
+		__field(int,	err)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->nid[0]	= nid[0];
+		__entry->nid[1]	= nid[1];
+		__entry->nid[2]	= nid[2];
+		__entry->depth	= depth;
+		__entry->err	= err;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, "
+		"nid[0] = %u, nid[1] = %u, nid[2] = %u, depth = %d, err = %d",
+		show_dev_ino(__entry),
+		(unsigned int)__entry->nid[0],
+		(unsigned int)__entry->nid[1],
+		(unsigned int)__entry->nid[2],
+		__entry->depth,
+		__entry->err)
+);
+
+TRACE_EVENT_CONDITION(f2fs_readpage,
+
+	TP_PROTO(struct page *page, sector_t blkaddr, int type),
+
+	TP_ARGS(page, blkaddr, type),
+
+	TP_CONDITION(page->mapping),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(pgoff_t,	index)
+		__field(sector_t,	blkaddr)
+		__field(int,	type)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= page->mapping->host->i_sb->s_dev;
+		__entry->ino		= page->mapping->host->i_ino;
+		__entry->index		= page->index;
+		__entry->blkaddr	= blkaddr;
+		__entry->type		= type;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, page_index = 0x%lx, "
+		"blkaddr = 0x%llx, bio_type = %s",
+		show_dev_ino(__entry),
+		(unsigned long)__entry->index,
+		(unsigned long long)__entry->blkaddr,
+		show_bio_type(__entry->type))
+);
+
+TRACE_EVENT(f2fs_get_data_block,
+	TP_PROTO(struct inode *inode, sector_t iblock,
+				struct buffer_head *bh, int ret),
+
+	TP_ARGS(inode, iblock, bh, ret),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(sector_t,	iblock)
+		__field(sector_t,	bh_start)
+		__field(size_t,	bh_size)
+		__field(int,	ret)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= inode->i_sb->s_dev;
+		__entry->ino		= inode->i_ino;
+		__entry->iblock		= iblock;
+		__entry->bh_start	= bh->b_blocknr;
+		__entry->bh_size	= bh->b_size;
+		__entry->ret		= ret;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, file offset = %llu, "
+		"start blkaddr = 0x%llx, len = 0x%llx bytes, err = %d",
+		show_dev_ino(__entry),
+		(unsigned long long)__entry->iblock,
+		(unsigned long long)__entry->bh_start,
+		(unsigned long long)__entry->bh_size,
+		__entry->ret)
+);
+
+TRACE_EVENT(f2fs_get_victim,
+
+	TP_PROTO(struct super_block *sb, int type, int gc_type,
+			struct victim_sel_policy *p, unsigned int pre_victim,
+			unsigned int prefree, unsigned int free),
+
+	TP_ARGS(sb, type, gc_type, p, pre_victim, prefree, free),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(int,	type)
+		__field(int,	gc_type)
+		__field(int,	alloc_mode)
+		__field(int,	gc_mode)
+		__field(unsigned int,	victim)
+		__field(unsigned int,	ofs_unit)
+		__field(unsigned int,	pre_victim)
+		__field(unsigned int,	prefree)
+		__field(unsigned int,	free)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= sb->s_dev;
+		__entry->type		= type;
+		__entry->gc_type	= gc_type;
+		__entry->alloc_mode	= p->alloc_mode;
+		__entry->gc_mode	= p->gc_mode;
+		__entry->victim		= p->min_segno;
+		__entry->ofs_unit	= p->ofs_unit;
+		__entry->pre_victim	= pre_victim;
+		__entry->prefree	= prefree;
+		__entry->free		= free;
+	),
+
+	TP_printk("dev = (%d,%d), type = %s, policy = (%s, %s, %s), victim = %u "
+		"ofs_unit = %u, pre_victim_secno = %d, prefree = %u, free = %u",
+		show_dev(__entry),
+		show_data_type(__entry->type),
+		show_gc_type(__entry->gc_type),
+		show_alloc_mode(__entry->alloc_mode),
+		show_victim_policy(__entry->gc_mode),
+		__entry->victim,
+		__entry->ofs_unit,
+		(int)__entry->pre_victim,
+		__entry->prefree,
+		__entry->free)
+);
+
+TRACE_EVENT(f2fs_fallocate,
+
+	TP_PROTO(struct inode *inode, int mode,
+				loff_t offset, loff_t len, int ret),
+
+	TP_ARGS(inode, mode, offset, len, ret),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(int,	mode)
+		__field(loff_t,	offset)
+		__field(loff_t,	len)
+		__field(loff_t, size)
+		__field(blkcnt_t, blocks)
+		__field(int,	ret)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->mode	= mode;
+		__entry->offset	= offset;
+		__entry->len	= len;
+		__entry->size	= inode->i_size;
+		__entry->blocks = inode->i_blocks;
+		__entry->ret	= ret;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, mode = %x, offset = %lld, "
+		"len = %lld,  i_size = %lld, i_blocks = %llu, ret = %d",
+		show_dev_ino(__entry),
+		__entry->mode,
+		(unsigned long long)__entry->offset,
+		(unsigned long long)__entry->len,
+		(unsigned long long)__entry->size,
+		(unsigned long long)__entry->blocks,
+		__entry->ret)
+);
+
+TRACE_EVENT(f2fs_reserve_new_block,
+
+	TP_PROTO(struct inode *inode, nid_t nid, unsigned int ofs_in_node),
+
+	TP_ARGS(inode, nid, ofs_in_node),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(nid_t, nid)
+		__field(unsigned int, ofs_in_node)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->nid	= nid;
+		__entry->ofs_in_node = ofs_in_node;
+	),
+
+	TP_printk("dev = (%d,%d), nid = %u, ofs_in_node = %u",
+		show_dev(__entry),
+		(unsigned int)__entry->nid,
+		__entry->ofs_in_node)
+);
+
+TRACE_EVENT(f2fs_do_submit_bio,
+
+	TP_PROTO(struct super_block *sb, int btype, bool sync, struct bio *bio),
+
+	TP_ARGS(sb, btype, sync, bio),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(int,	btype)
+		__field(bool,	sync)
+		__field(sector_t,	sector)
+		__field(unsigned int,	size)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= sb->s_dev;
+		__entry->btype		= btype;
+		__entry->sync		= sync;
+		__entry->sector		= bio->bi_sector;
+		__entry->size		= bio->bi_size;
+	),
+
+	TP_printk("dev = (%d,%d), type = %s, io = %s, sector = %lld, size = %u",
+		show_dev(__entry),
+		show_block_type(__entry->btype),
+		__entry->sync ? "sync" : "no sync",
+		(unsigned long long)__entry->sector,
+		__entry->size)
+);
+
+TRACE_EVENT(f2fs_submit_write_page,
+
+	TP_PROTO(struct page *page, block_t blk_addr, int type),
+
+	TP_ARGS(page, blk_addr, type),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(int, type)
+		__field(pgoff_t, index)
+		__field(block_t, block)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= page->mapping->host->i_sb->s_dev;
+		__entry->ino	= page->mapping->host->i_ino;
+		__entry->type	= type;
+		__entry->index	= page->index;
+		__entry->block	= blk_addr;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, %s, index = %lu, blkaddr = 0x%llx",
+		show_dev_ino(__entry),
+		show_block_type(__entry->type),
+		(unsigned long)__entry->index,
+		(unsigned long long)__entry->block)
+);
+
+TRACE_EVENT(f2fs_write_checkpoint,
+
+	TP_PROTO(struct super_block *sb, bool is_umount, char *msg),
+
+	TP_ARGS(sb, is_umount, msg),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(bool,	is_umount)
+		__field(char *,	msg)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= sb->s_dev;
+		__entry->is_umount	= is_umount;
+		__entry->msg		= msg;
+	),
+
+	TP_printk("dev = (%d,%d), checkpoint for %s, state = %s",
+		show_dev(__entry),
+		__entry->is_umount ? "clean umount" : "consistency",
+		__entry->msg)
+);
+
+#endif /* _TRACE_F2FS_H */
+
+ /* This part must be outside protection */
+#include <trace/define_trace.h>