Commit f9a03ae1 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge tag 'for-f2fs-4.5' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs 

Pull f2fs updates from Jaegeuk Kim:
 "This series adds two ioctls to control cached data and fragmented
  files.  Most of the rest fixes missing error cases and bugs that we
  have not covered so far.  Summary:

  Enhancements:
   - support an ioctl to execute online file defragmentation
   - support an ioctl to flush cached data
   - speed up shrinking of extent_cache entries
   - handle broken superblock
   - refector dirty inode management infra
   - revisit f2fs_map_blocks to handle more cases
   - reduce global lock coverage
   - add detecting user's idle time

  Major bug fixes:
   - fix data race condition on cached nat entries
   - fix error cases of volatile and atomic writes"

* tag 'for-f2fs-4.5' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (87 commits)
  f2fs: should unset atomic flag after successful commit
  f2fs: fix wrong memory condition check
  f2fs: monitor the number of background checkpoint
  f2fs: detect idle time depending on user behavior
  f2fs: introduce time and interval facility
  f2fs: skip releasing nodes in chindless extent tree
  f2fs: use atomic type for node count in extent tree
  f2fs: recognize encrypted data in f2fs_fiemap
  f2fs: clean up f2fs_balance_fs
  f2fs: remove redundant calls
  f2fs: avoid unnecessary f2fs_balance_fs calls
  f2fs: check the page status filled from disk
  f2fs: introduce __get_node_page to reuse common code
  f2fs: check node id earily when readaheading node page
  f2fs: read isize while holding i_mutex in fiemap
  Revert "f2fs: check the node block address of newly allocated nid"
  f2fs: cover more area with nat_tree_lock
  f2fs: introduce max_file_blocks in sbi
  f2fs crypto: check CONFIG_F2FS_FS_XATTR for encrypted symlink
  f2fs: introduce zombie list for fast shrinking extent trees
  ...
parents 1289ace5 447135a8

Documentation/ABI/testing/sysfs-fs-f2fs

+6 −0
Original line number Diff line number Diff line
@@ -87,6 +87,12 @@ Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 
Description:

		 Controls the checkpoint timing.



What:		/sys/fs/f2fs/<disk>/idle_interval

Date:		January 2016

Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>

Description:

		 Controls the idle timing.



What:		/sys/fs/f2fs/<disk>/ra_nid_pages

Date:		October 2015

Contact:	"Chao Yu" <chao2.yu@samsung.com>

Documentation/filesystems/f2fs.txt

+6 −4
Original line number Diff line number Diff line
@@ -102,7 +102,7 @@ background_gc=%s Turn on/off cleaning operations, namely garbage 
                       collection, triggered in background when I/O subsystem is

                       idle. If background_gc=on, it will turn on the garbage

                       collection and if background_gc=off, garbage collection

                       will be truned off. If background_gc=sync, it will turn

                       will be turned off. If background_gc=sync, it will turn

                       on synchronous garbage collection running in background.

                       Default value for this option is on. So garbage

                       collection is on by default.
@@ -145,10 +145,12 @@ extent_cache Enable an extent cache based on rb-tree, it can cache 
                       as many as extent which map between contiguous logical

                       address and physical address per inode, resulting in

                       increasing the cache hit ratio. Set by default.

noextent_cache         Diable an extent cache based on rb-tree explicitly, see

noextent_cache         Disable an extent cache based on rb-tree explicitly, see

                       the above extent_cache mount option.

noinline_data          Disable the inline data feature, inline data feature is

                       enabled by default.

data_flush             Enable data flushing before checkpoint in order to

                       persist data of regular and symlink.



================================================================================

DEBUGFS ENTRIES
@@ -192,7 +194,7 @@ Files in /sys/fs/f2fs/<devname> 
                              policy for garbage collection. Setting gc_idle = 0

                              (default) will disable this option. Setting

                              gc_idle = 1 will select the Cost Benefit approach

                              & setting gc_idle = 2 will select the greedy aproach.

                              & setting gc_idle = 2 will select the greedy approach.



 reclaim_segments             This parameter controls the number of prefree

                              segments to be reclaimed. If the number of prefree
@@ -298,7 +300,7 @@ The dump.f2fs shows the information of specific inode and dumps SSA and SIT to 
file. Each file is dump_ssa and dump_sit.



The dump.f2fs is used to debug on-disk data structures of the f2fs filesystem.

It shows on-disk inode information reconized by a given inode number, and is

It shows on-disk inode information recognized by a given inode number, and is

able to dump all the SSA and SIT entries into predefined files, ./dump_ssa and

./dump_sit respectively.

fs/f2fs/checkpoint.c

+87 −90
Original line number Diff line number Diff line
@@ -237,7 +237,7 @@ static int f2fs_write_meta_page(struct page *page, 
	dec_page_count(sbi, F2FS_DIRTY_META);

	unlock_page(page);



	if (wbc->for_reclaim)

	if (wbc->for_reclaim || unlikely(f2fs_cp_error(sbi)))

		f2fs_submit_merged_bio(sbi, META, WRITE);

	return 0;
@@ -410,13 +410,13 @@ static void __remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) 
	spin_unlock(&im->ino_lock);

}



void add_dirty_inode(struct f2fs_sb_info *sbi, nid_t ino, int type)

void add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)

{

	/* add new dirty ino entry into list */

	__add_ino_entry(sbi, ino, type);

}



void remove_dirty_inode(struct f2fs_sb_info *sbi, nid_t ino, int type)

void remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)

{

	/* remove dirty ino entry from list */

	__remove_ino_entry(sbi, ino, type);
@@ -434,7 +434,7 @@ bool exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode) 
	return e ? true : false;

}



void release_dirty_inode(struct f2fs_sb_info *sbi)

void release_ino_entry(struct f2fs_sb_info *sbi)

{

	struct ino_entry *e, *tmp;

	int i;
@@ -722,47 +722,48 @@ fail_no_cp: 
	return -EINVAL;

}



static int __add_dirty_inode(struct inode *inode, struct inode_entry *new)

static void __add_dirty_inode(struct inode *inode, enum inode_type type)

{

	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);

	struct f2fs_inode_info *fi = F2FS_I(inode);

	int flag = (type == DIR_INODE) ? FI_DIRTY_DIR : FI_DIRTY_FILE;



	if (is_inode_flag_set(F2FS_I(inode), FI_DIRTY_DIR))

		return -EEXIST;

	if (is_inode_flag_set(fi, flag))

		return;



	set_inode_flag(F2FS_I(inode), FI_DIRTY_DIR);

	F2FS_I(inode)->dirty_dir = new;

	list_add_tail(&new->list, &sbi->dir_inode_list);

	stat_inc_dirty_dir(sbi);

	return 0;

	set_inode_flag(fi, flag);

	list_add_tail(&fi->dirty_list, &sbi->inode_list[type]);

	stat_inc_dirty_inode(sbi, type);

}



static void __remove_dirty_inode(struct inode *inode, enum inode_type type)

{

	struct f2fs_inode_info *fi = F2FS_I(inode);

	int flag = (type == DIR_INODE) ? FI_DIRTY_DIR : FI_DIRTY_FILE;



	if (get_dirty_pages(inode) ||

			!is_inode_flag_set(F2FS_I(inode), flag))

		return;



	list_del_init(&fi->dirty_list);

	clear_inode_flag(fi, flag);

	stat_dec_dirty_inode(F2FS_I_SB(inode), type);

}



void update_dirty_page(struct inode *inode, struct page *page)

{

	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);

	struct inode_entry *new;

	int ret = 0;

	enum inode_type type = S_ISDIR(inode->i_mode) ? DIR_INODE : FILE_INODE;



	if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) &&

			!S_ISLNK(inode->i_mode))

		return;



	if (!S_ISDIR(inode->i_mode)) {

		inode_inc_dirty_pages(inode);

		goto out;

	}



	new = f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS);

	new->inode = inode;

	INIT_LIST_HEAD(&new->list);



	spin_lock(&sbi->dir_inode_lock);

	ret = __add_dirty_inode(inode, new);

	spin_lock(&sbi->inode_lock[type]);

	__add_dirty_inode(inode, type);

	inode_inc_dirty_pages(inode);

	spin_unlock(&sbi->dir_inode_lock);

	spin_unlock(&sbi->inode_lock[type]);



	if (ret)

		kmem_cache_free(inode_entry_slab, new);

out:

	SetPagePrivate(page);

	f2fs_trace_pid(page);

}
@@ -770,70 +771,60 @@ out: 
void add_dirty_dir_inode(struct inode *inode)

{

	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);

	struct inode_entry *new =

			f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS);

	int ret = 0;



	new->inode = inode;

	INIT_LIST_HEAD(&new->list);



	spin_lock(&sbi->dir_inode_lock);

	ret = __add_dirty_inode(inode, new);

	spin_unlock(&sbi->dir_inode_lock);



	if (ret)

		kmem_cache_free(inode_entry_slab, new);

	spin_lock(&sbi->inode_lock[DIR_INODE]);

	__add_dirty_inode(inode, DIR_INODE);

	spin_unlock(&sbi->inode_lock[DIR_INODE]);

}



void remove_dirty_dir_inode(struct inode *inode)

void remove_dirty_inode(struct inode *inode)

{

	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);

	struct inode_entry *entry;



	if (!S_ISDIR(inode->i_mode))

		return;

	struct f2fs_inode_info *fi = F2FS_I(inode);

	enum inode_type type = S_ISDIR(inode->i_mode) ? DIR_INODE : FILE_INODE;



	spin_lock(&sbi->dir_inode_lock);

	if (get_dirty_pages(inode) ||

			!is_inode_flag_set(F2FS_I(inode), FI_DIRTY_DIR)) {

		spin_unlock(&sbi->dir_inode_lock);

	if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) &&

			!S_ISLNK(inode->i_mode))

		return;

	}



	entry = F2FS_I(inode)->dirty_dir;

	list_del(&entry->list);

	F2FS_I(inode)->dirty_dir = NULL;

	clear_inode_flag(F2FS_I(inode), FI_DIRTY_DIR);

	stat_dec_dirty_dir(sbi);

	spin_unlock(&sbi->dir_inode_lock);

	kmem_cache_free(inode_entry_slab, entry);

	spin_lock(&sbi->inode_lock[type]);

	__remove_dirty_inode(inode, type);

	spin_unlock(&sbi->inode_lock[type]);



	/* Only from the recovery routine */

	if (is_inode_flag_set(F2FS_I(inode), FI_DELAY_IPUT)) {

		clear_inode_flag(F2FS_I(inode), FI_DELAY_IPUT);

	if (is_inode_flag_set(fi, FI_DELAY_IPUT)) {

		clear_inode_flag(fi, FI_DELAY_IPUT);

		iput(inode);

	}

}



void sync_dirty_dir_inodes(struct f2fs_sb_info *sbi)

int sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type)

{

	struct list_head *head;

	struct inode_entry *entry;

	struct inode *inode;

	struct f2fs_inode_info *fi;

	bool is_dir = (type == DIR_INODE);



	trace_f2fs_sync_dirty_inodes_enter(sbi->sb, is_dir,

				get_pages(sbi, is_dir ?

				F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA));

retry:

	if (unlikely(f2fs_cp_error(sbi)))

		return;

		return -EIO;



	spin_lock(&sbi->dir_inode_lock);

	spin_lock(&sbi->inode_lock[type]);



	head = &sbi->dir_inode_list;

	head = &sbi->inode_list[type];

	if (list_empty(head)) {

		spin_unlock(&sbi->dir_inode_lock);

		return;

		spin_unlock(&sbi->inode_lock[type]);

		trace_f2fs_sync_dirty_inodes_exit(sbi->sb, is_dir,

				get_pages(sbi, is_dir ?

				F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA));

		return 0;

	}

	entry = list_entry(head->next, struct inode_entry, list);

	inode = igrab(entry->inode);

	spin_unlock(&sbi->dir_inode_lock);

	fi = list_entry(head->next, struct f2fs_inode_info, dirty_list);

	inode = igrab(&fi->vfs_inode);

	spin_unlock(&sbi->inode_lock[type]);

	if (inode) {

		filemap_fdatawrite(inode->i_mapping);

		iput(inode);
@@ -868,11 +859,9 @@ retry_flush_dents: 
	/* write all the dirty dentry pages */

	if (get_pages(sbi, F2FS_DIRTY_DENTS)) {

		f2fs_unlock_all(sbi);

		sync_dirty_dir_inodes(sbi);

		if (unlikely(f2fs_cp_error(sbi))) {

			err = -EIO;

		err = sync_dirty_inodes(sbi, DIR_INODE);

		if (err)

			goto out;

		}

		goto retry_flush_dents;

	}
@@ -885,10 +874,9 @@ retry_flush_nodes: 


	if (get_pages(sbi, F2FS_DIRTY_NODES)) {

		up_write(&sbi->node_write);

		sync_node_pages(sbi, 0, &wbc);

		if (unlikely(f2fs_cp_error(sbi))) {

		err = sync_node_pages(sbi, 0, &wbc);

		if (err) {

			f2fs_unlock_all(sbi);

			err = -EIO;

			goto out;

		}

		goto retry_flush_nodes;
@@ -919,7 +907,7 @@ static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi) 
	finish_wait(&sbi->cp_wait, &wait);

}



static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)

static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)

{

	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);

	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
@@ -945,7 +933,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) 
	while (get_pages(sbi, F2FS_DIRTY_META)) {

		sync_meta_pages(sbi, META, LONG_MAX);

		if (unlikely(f2fs_cp_error(sbi)))

			return;

			return -EIO;

	}



	next_free_nid(sbi, &last_nid);
@@ -1030,7 +1018,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) 
	/* need to wait for end_io results */

	wait_on_all_pages_writeback(sbi);

	if (unlikely(f2fs_cp_error(sbi)))

		return;

		return -EIO;



	/* write out checkpoint buffer at block 0 */

	update_meta_page(sbi, ckpt, start_blk++);
@@ -1058,7 +1046,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) 
	wait_on_all_pages_writeback(sbi);



	if (unlikely(f2fs_cp_error(sbi)))

		return;

		return -EIO;



	filemap_fdatawait_range(NODE_MAPPING(sbi), 0, LONG_MAX);

	filemap_fdatawait_range(META_MAPPING(sbi), 0, LONG_MAX);
@@ -1081,22 +1069,25 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) 
		invalidate_mapping_pages(META_MAPPING(sbi), discard_blk,

								discard_blk);



	release_dirty_inode(sbi);

	release_ino_entry(sbi);



	if (unlikely(f2fs_cp_error(sbi)))

		return;

		return -EIO;



	clear_prefree_segments(sbi, cpc);

	clear_sbi_flag(sbi, SBI_IS_DIRTY);



	return 0;

}



/*

 * We guarantee that this checkpoint procedure will not fail.

 */

void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)

int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)

{

	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);

	unsigned long long ckpt_ver;

	int err = 0;



	mutex_lock(&sbi->cp_mutex);
@@ -1104,14 +1095,19 @@ void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) 
		(cpc->reason == CP_FASTBOOT || cpc->reason == CP_SYNC ||

		(cpc->reason == CP_DISCARD && !sbi->discard_blks)))

		goto out;

	if (unlikely(f2fs_cp_error(sbi)))

	if (unlikely(f2fs_cp_error(sbi))) {

		err = -EIO;

		goto out;

	if (f2fs_readonly(sbi->sb))

	}

	if (f2fs_readonly(sbi->sb)) {

		err = -EROFS;

		goto out;

	}



	trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "start block_ops");



	if (block_operations(sbi))

	err = block_operations(sbi);

	if (err)

		goto out;



	trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish block_ops");
@@ -1133,7 +1129,7 @@ void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) 
	flush_sit_entries(sbi, cpc);



	/* unlock all the fs_lock[] in do_checkpoint() */

	do_checkpoint(sbi, cpc);

	err = do_checkpoint(sbi, cpc);



	unblock_operations(sbi);

	stat_inc_cp_count(sbi->stat_info);
@@ -1143,10 +1139,11 @@ void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) 
			"checkpoint: version = %llx", ckpt_ver);



	/* do checkpoint periodically */

	sbi->cp_expires = round_jiffies_up(jiffies + HZ * sbi->cp_interval);

	f2fs_update_time(sbi, CP_TIME);

	trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish checkpoint");

out:

	mutex_unlock(&sbi->cp_mutex);

	trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish checkpoint");

	return err;

}



void init_ino_entry_info(struct f2fs_sb_info *sbi)

fs/f2fs/data.c

+215 −162
Original line number Diff line number Diff line
@@ -225,7 +225,8 @@ void set_data_blkaddr(struct dnode_of_data *dn) 
	/* Get physical address of data block */

	addr_array = blkaddr_in_node(rn);

	addr_array[ofs_in_node] = cpu_to_le32(dn->data_blkaddr);

	set_page_dirty(node_page);

	if (set_page_dirty(node_page))

		dn->node_changed = true;

}



int reserve_new_block(struct dnode_of_data *dn)
@@ -412,7 +413,7 @@ struct page *get_new_data_page(struct inode *inode, 
	struct page *page;

	struct dnode_of_data dn;

	int err;

repeat:



	page = f2fs_grab_cache_page(mapping, index, true);

	if (!page) {

		/*
@@ -441,12 +442,11 @@ repeat: 
	} else {

		f2fs_put_page(page, 1);



		page = get_read_data_page(inode, index, READ_SYNC, true);

		/* if ipage exists, blkaddr should be NEW_ADDR */

		f2fs_bug_on(F2FS_I_SB(inode), ipage);

		page = get_lock_data_page(inode, index, true);

		if (IS_ERR(page))

			goto repeat;



		/* wait for read completion */

		lock_page(page);

			return page;

	}

got_it:

	if (new_i_size && i_size_read(inode) <
@@ -494,14 +494,10 @@ alloc: 
	if (i_size_read(dn->inode) < ((loff_t)(fofs + 1) << PAGE_CACHE_SHIFT))

		i_size_write(dn->inode,

				((loff_t)(fofs + 1) << PAGE_CACHE_SHIFT));



	/* direct IO doesn't use extent cache to maximize the performance */

	f2fs_drop_largest_extent(dn->inode, fofs);



	return 0;

}



static void __allocate_data_blocks(struct inode *inode, loff_t offset,

static int __allocate_data_blocks(struct inode *inode, loff_t offset,

							size_t count)

{

	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -510,14 +506,15 @@ static void __allocate_data_blocks(struct inode *inode, loff_t offset, 
	u64 len = F2FS_BYTES_TO_BLK(count);

	bool allocated;

	u64 end_offset;

	int err = 0;



	while (len) {

		f2fs_balance_fs(sbi);

		f2fs_lock_op(sbi);



		/* When reading holes, we need its node page */

		set_new_dnode(&dn, inode, NULL, NULL, 0);

		if (get_dnode_of_data(&dn, start, ALLOC_NODE))

		err = get_dnode_of_data(&dn, start, ALLOC_NODE);

		if (err)

			goto out;



		allocated = false;
@@ -526,12 +523,15 @@ static void __allocate_data_blocks(struct inode *inode, loff_t offset, 
		while (dn.ofs_in_node < end_offset && len) {

			block_t blkaddr;



			if (unlikely(f2fs_cp_error(sbi)))

			if (unlikely(f2fs_cp_error(sbi))) {

				err = -EIO;

				goto sync_out;

			}



			blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);

			if (blkaddr == NULL_ADDR || blkaddr == NEW_ADDR) {

				if (__allocate_data_block(&dn))

				err = __allocate_data_block(&dn);

				if (err)

					goto sync_out;

				allocated = true;

			}
@@ -545,8 +545,10 @@ static void __allocate_data_blocks(struct inode *inode, loff_t offset, 


		f2fs_put_dnode(&dn);

		f2fs_unlock_op(sbi);



		f2fs_balance_fs(sbi, dn.node_changed);

	}

	return;

	return err;



sync_out:

	if (allocated)
@@ -554,7 +556,8 @@ sync_out: 
	f2fs_put_dnode(&dn);

out:

	f2fs_unlock_op(sbi);

	return;

	f2fs_balance_fs(sbi, dn.node_changed);

	return err;

}



/*
@@ -566,7 +569,7 @@ out: 
 *     b. do not use extent cache for better performance

 *     c. give the block addresses to blockdev

 */

static int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,

int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,

						int create, int flag)

{

	unsigned int maxblocks = map->m_len;
@@ -577,6 +580,7 @@ static int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, 
	int err = 0, ofs = 1;

	struct extent_info ei;

	bool allocated = false;

	block_t blkaddr;



	map->m_len = 0;

	map->m_flags = 0;
@@ -592,7 +596,7 @@ static int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, 
	}



	if (create)

		f2fs_lock_op(F2FS_I_SB(inode));

		f2fs_lock_op(sbi);



	/* When reading holes, we need its node page */

	set_new_dnode(&dn, inode, NULL, NULL, 0);
@@ -640,12 +644,21 @@ static int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, 
	pgofs++;



get_next:

	if (map->m_len >= maxblocks)

		goto sync_out;



	if (dn.ofs_in_node >= end_offset) {

		if (allocated)

			sync_inode_page(&dn);

		allocated = false;

		f2fs_put_dnode(&dn);



		if (create) {

			f2fs_unlock_op(sbi);

			f2fs_balance_fs(sbi, dn.node_changed);

			f2fs_lock_op(sbi);

		}



		set_new_dnode(&dn, inode, NULL, NULL, 0);

		err = get_dnode_of_data(&dn, pgofs, mode);

		if (err) {
@@ -657,8 +670,7 @@ get_next: 
		end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));

	}



	if (maxblocks > map->m_len) {

		block_t blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);

	blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);



	if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR) {

		if (create) {
@@ -694,15 +706,17 @@ get_next: 
		map->m_len++;

		goto get_next;

	}

	}



sync_out:

	if (allocated)

		sync_inode_page(&dn);

put_out:

	f2fs_put_dnode(&dn);

unlock_out:

	if (create)

		f2fs_unlock_op(F2FS_I_SB(inode));

	if (create) {

		f2fs_unlock_op(sbi);

		f2fs_balance_fs(sbi, dn.node_changed);

	}

out:

	trace_f2fs_map_blocks(inode, map, err);

	return err;
@@ -742,6 +756,10 @@ static int get_data_block_dio(struct inode *inode, sector_t iblock, 
static int get_data_block_bmap(struct inode *inode, sector_t iblock,

			struct buffer_head *bh_result, int create)

{

	/* Block number less than F2FS MAX BLOCKS */

	if (unlikely(iblock >= F2FS_I_SB(inode)->max_file_blocks))

		return -EFBIG;



	return __get_data_block(inode, iblock, bh_result, create,

						F2FS_GET_BLOCK_BMAP);

}
@@ -761,10 +779,9 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, 
{

	struct buffer_head map_bh;

	sector_t start_blk, last_blk;

	loff_t isize = i_size_read(inode);

	loff_t isize;

	u64 logical = 0, phys = 0, size = 0;

	u32 flags = 0;

	bool past_eof = false, whole_file = false;

	int ret = 0;



	ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC);
@@ -779,16 +796,19 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, 


	mutex_lock(&inode->i_mutex);



	if (len >= isize) {

		whole_file = true;

		len = isize;

	}

	isize = i_size_read(inode);

	if (start >= isize)

		goto out;



	if (start + len > isize)

		len = isize - start;



	if (logical_to_blk(inode, len) == 0)

		len = blk_to_logical(inode, 1);



	start_blk = logical_to_blk(inode, start);

	last_blk = logical_to_blk(inode, start + len - 1);



next:

	memset(&map_bh, 0, sizeof(struct buffer_head));

	map_bh.b_size = len;
@@ -800,41 +820,26 @@ next: 


	/* HOLE */

	if (!buffer_mapped(&map_bh)) {

		start_blk++;



		if (!past_eof && blk_to_logical(inode, start_blk) >= isize)

			past_eof = 1;



		if (past_eof && size) {

		/* Go through holes util pass the EOF */

		if (blk_to_logical(inode, start_blk++) < isize)

			goto prep_next;

		/* Found a hole beyond isize means no more extents.

		 * Note that the premise is that filesystems don't

		 * punch holes beyond isize and keep size unchanged.

		 */

		flags |= FIEMAP_EXTENT_LAST;

			ret = fiemap_fill_next_extent(fieinfo, logical,

					phys, size, flags);

		} else if (size) {

			ret = fiemap_fill_next_extent(fieinfo, logical,

					phys, size, flags);

			size = 0;

	}



		/* if we have holes up to/past EOF then we're done */

		if (start_blk > last_blk || past_eof || ret)

			goto out;

	} else {

		if (start_blk > last_blk && !whole_file) {

	if (size) {

		if (f2fs_encrypted_inode(inode))

			flags |= FIEMAP_EXTENT_DATA_ENCRYPTED;



		ret = fiemap_fill_next_extent(fieinfo, logical,

				phys, size, flags);

			goto out;

	}



		/*

		 * if size != 0 then we know we already have an extent

		 * to add, so add it.

		 */

		if (size) {

			ret = fiemap_fill_next_extent(fieinfo, logical,

					phys, size, flags);

			if (ret)

	if (start_blk > last_blk || ret)

		goto out;

		}



	logical = blk_to_logical(inode, start_blk);

	phys = blk_to_logical(inode, map_bh.b_blocknr);
@@ -845,14 +850,7 @@ next: 


	start_blk += logical_to_blk(inode, size);



		/*

		 * If we are past the EOF, then we need to make sure as

		 * soon as we find a hole that the last extent we found

		 * is marked with FIEMAP_EXTENT_LAST

		 */

		if (!past_eof && logical + size >= isize)

			past_eof = true;

	}

prep_next:

	cond_resched();

	if (fatal_signal_pending(current))

		ret = -EINTR;
@@ -1083,6 +1081,7 @@ int do_write_data_page(struct f2fs_io_info *fio) 
	 */

	if (unlikely(fio->blk_addr != NEW_ADDR &&

			!is_cold_data(page) &&

			!IS_ATOMIC_WRITTEN_PAGE(page) &&

			need_inplace_update(inode))) {

		rewrite_data_page(fio);

		set_inode_flag(F2FS_I(inode), FI_UPDATE_WRITE);
@@ -1179,10 +1178,11 @@ out: 
	if (err)

		ClearPageUptodate(page);

	unlock_page(page);

	if (need_balance_fs)

		f2fs_balance_fs(sbi);

	if (wbc->for_reclaim)

	f2fs_balance_fs(sbi, need_balance_fs);

	if (wbc->for_reclaim || unlikely(f2fs_cp_error(sbi))) {

		f2fs_submit_merged_bio(sbi, DATA, WRITE);

		remove_dirty_inode(inode);

	}

	return 0;



redirty_out:
@@ -1354,6 +1354,10 @@ static int f2fs_write_data_pages(struct address_space *mapping, 
			available_free_memory(sbi, DIRTY_DENTS))

		goto skip_write;



	/* skip writing during file defragment */

	if (is_inode_flag_set(F2FS_I(inode), FI_DO_DEFRAG))

		goto skip_write;



	/* during POR, we don't need to trigger writepage at all. */

	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))

		goto skip_write;
@@ -1369,7 +1373,7 @@ static int f2fs_write_data_pages(struct address_space *mapping, 
	if (locked)

		mutex_unlock(&sbi->writepages);



	remove_dirty_dir_inode(inode);

	remove_dirty_inode(inode);



	wbc->nr_to_write = max((long)0, wbc->nr_to_write - diff);

	return ret;
@@ -1382,11 +1386,83 @@ skip_write: 
static void f2fs_write_failed(struct address_space *mapping, loff_t to)

{

	struct inode *inode = mapping->host;

	loff_t i_size = i_size_read(inode);



	if (to > i_size) {

		truncate_pagecache(inode, i_size);

		truncate_blocks(inode, i_size, true);

	}

}



static int prepare_write_begin(struct f2fs_sb_info *sbi,

			struct page *page, loff_t pos, unsigned len,

			block_t *blk_addr, bool *node_changed)

{

	struct inode *inode = page->mapping->host;

	pgoff_t index = page->index;

	struct dnode_of_data dn;

	struct page *ipage;

	bool locked = false;

	struct extent_info ei;

	int err = 0;



	if (to > inode->i_size) {

		truncate_pagecache(inode, inode->i_size);

		truncate_blocks(inode, inode->i_size, true);

	if (f2fs_has_inline_data(inode) ||

			(pos & PAGE_CACHE_MASK) >= i_size_read(inode)) {

		f2fs_lock_op(sbi);

		locked = true;

	}

restart:

	/* check inline_data */

	ipage = get_node_page(sbi, inode->i_ino);

	if (IS_ERR(ipage)) {

		err = PTR_ERR(ipage);

		goto unlock_out;

	}



	set_new_dnode(&dn, inode, ipage, ipage, 0);



	if (f2fs_has_inline_data(inode)) {

		if (pos + len <= MAX_INLINE_DATA) {

			read_inline_data(page, ipage);

			set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);

			sync_inode_page(&dn);

		} else {

			err = f2fs_convert_inline_page(&dn, page);

			if (err)

				goto out;

			if (dn.data_blkaddr == NULL_ADDR)

				err = f2fs_get_block(&dn, index);

		}

	} else if (locked) {

		err = f2fs_get_block(&dn, index);

	} else {

		if (f2fs_lookup_extent_cache(inode, index, &ei)) {

			dn.data_blkaddr = ei.blk + index - ei.fofs;

		} else {

			bool restart = false;



			/* hole case */

			err = get_dnode_of_data(&dn, index, LOOKUP_NODE);

			if (err || (!err && dn.data_blkaddr == NULL_ADDR))

				restart = true;

			if (restart) {

				f2fs_put_dnode(&dn);

				f2fs_lock_op(sbi);

				locked = true;

				goto restart;

			}

		}

	}



	/* convert_inline_page can make node_changed */

	*blk_addr = dn.data_blkaddr;

	*node_changed = dn.node_changed;

out:

	f2fs_put_dnode(&dn);

unlock_out:

	if (locked)

		f2fs_unlock_op(sbi);

	return err;

}



static int f2fs_write_begin(struct file *file, struct address_space *mapping,
@@ -1396,15 +1472,13 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping, 
	struct inode *inode = mapping->host;

	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);

	struct page *page = NULL;

	struct page *ipage;

	pgoff_t index = ((unsigned long long) pos) >> PAGE_CACHE_SHIFT;

	struct dnode_of_data dn;

	bool need_balance = false;

	block_t blkaddr = NULL_ADDR;

	int err = 0;



	trace_f2fs_write_begin(inode, pos, len, flags);



	f2fs_balance_fs(sbi);



	/*

	 * We should check this at this moment to avoid deadlock on inode page

	 * and #0 page. The locking rule for inline_data conversion should be:
@@ -1424,41 +1498,27 @@ repeat: 


	*pagep = page;



	f2fs_lock_op(sbi);



	/* check inline_data */

	ipage = get_node_page(sbi, inode->i_ino);

	if (IS_ERR(ipage)) {

		err = PTR_ERR(ipage);

		goto unlock_fail;

	}



	set_new_dnode(&dn, inode, ipage, ipage, 0);

	err = prepare_write_begin(sbi, page, pos, len,

					&blkaddr, &need_balance);

	if (err)

		goto fail;



	if (f2fs_has_inline_data(inode)) {

		if (pos + len <= MAX_INLINE_DATA) {

			read_inline_data(page, ipage);

			set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);

			sync_inode_page(&dn);

			goto put_next;

	if (need_balance && has_not_enough_free_secs(sbi, 0)) {

		unlock_page(page);

		f2fs_balance_fs(sbi, true);

		lock_page(page);

		if (page->mapping != mapping) {

			/* The page got truncated from under us */

			f2fs_put_page(page, 1);

			goto repeat;

		}

		err = f2fs_convert_inline_page(&dn, page);

		if (err)

			goto put_fail;

	}



	err = f2fs_get_block(&dn, index);

	if (err)

		goto put_fail;

put_next:

	f2fs_put_dnode(&dn);

	f2fs_unlock_op(sbi);



	f2fs_wait_on_page_writeback(page, DATA);



	/* wait for GCed encrypted page writeback */

	if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))

		f2fs_wait_on_encrypted_page_writeback(sbi, dn.data_blkaddr);

		f2fs_wait_on_encrypted_page_writeback(sbi, blkaddr);



	if (len == PAGE_CACHE_SIZE)

		goto out_update;
@@ -1474,14 +1534,14 @@ put_next: 
		goto out_update;

	}



	if (dn.data_blkaddr == NEW_ADDR) {

	if (blkaddr == NEW_ADDR) {

		zero_user_segment(page, 0, PAGE_CACHE_SIZE);

	} else {

		struct f2fs_io_info fio = {

			.sbi = sbi,

			.type = DATA,

			.rw = READ_SYNC,

			.blk_addr = dn.data_blkaddr,

			.blk_addr = blkaddr,

			.page = page,

			.encrypted_page = NULL,

		};
@@ -1512,10 +1572,6 @@ out_clear: 
	clear_cold_data(page);

	return 0;



put_fail:

	f2fs_put_dnode(&dn);

unlock_fail:

	f2fs_unlock_op(sbi);

fail:

	f2fs_put_page(page, 1);

	f2fs_write_failed(mapping, pos + len);
@@ -1540,6 +1596,7 @@ static int f2fs_write_end(struct file *file, 
	}



	f2fs_put_page(page, 1);

	f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);

	return copied;

}
@@ -1567,11 +1624,9 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, 
	int err;



	/* we don't need to use inline_data strictly */

	if (f2fs_has_inline_data(inode)) {

	err = f2fs_convert_inline_inode(inode);

	if (err)

		return err;

	}



	if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))

		return 0;
@@ -1583,12 +1638,10 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, 
	trace_f2fs_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));



	if (iov_iter_rw(iter) == WRITE) {

		__allocate_data_blocks(inode, offset, count);

		if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) {

			err = -EIO;

		err = __allocate_data_blocks(inode, offset, count);

		if (err)

			goto out;

	}

	}



	err = blockdev_direct_IO(iocb, inode, iter, offset, get_data_block_dio);

out:

fs/f2fs/debug.c

+19 −10

File changed.

Preview size limit exceeded, changes collapsed.

CRA Git | Maintained and supported by SUSTech CRA and CCSE