Merge tag 'f2fs-for-5.10-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this round, we've added new features such as zone capacity for ZNS
  and a new GC policy, ATGC, along with in-memory segment management. In
  addition, we could improve the decompression speed significantly by
  changing virtual mapping method. Even though we've fixed lots of small
  bugs in compression support, I feel that it becomes more stable so
  that I could give it a try in production.

  Enhancements:
   - suport zone capacity in NVMe Zoned Namespace devices
   - introduce in-memory current segment management
   - add standart casefolding support
   - support age threshold based garbage collection
   - improve decompression speed by changing virtual mapping method

  Bug fixes:
   - fix condition checks in some ioctl() such as compression, move_range, etc
   - fix 32/64bits support in data structures
   - fix memory allocation in zstd decompress
   - add some boundary checks to avoid kernel panic on corrupted image
   - fix disallowing compression for non-empty file
   - fix slab leakage of compressed block writes

  In addition, it includes code refactoring for better readability and
  minor bug fixes for compression and zoned device support"

* tag 'f2fs-for-5.10-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (51 commits)
  f2fs: code cleanup by removing unnecessary check
  f2fs: wait for sysfs kobject removal before freeing f2fs_sb_info
  f2fs: fix writecount false positive in releasing compress blocks
  f2fs: introduce check_swap_activate_fast()
  f2fs: don't issue flush in f2fs_flush_device_cache() for nobarrier case
  f2fs: handle errors of f2fs_get_meta_page_nofail
  f2fs: fix to set SBI_NEED_FSCK flag for inconsistent inode
  f2fs: reject CASEFOLD inode flag without casefold feature
  f2fs: fix memory alignment to support 32bit
  f2fs: fix slab leak of rpages pointer
  f2fs: compress: fix to disallow enabling compress on non-empty file
  f2fs: compress: introduce cic/dic slab cache
  f2fs: compress: introduce page array slab cache
  f2fs: fix to do sanity check on segment/section count
  f2fs: fix to check segment boundary during SIT page readahead
  f2fs: fix uninit-value in f2fs_lookup
  f2fs: remove unneeded parameter in find_in_block()
  f2fs: fix wrong total_sections check and fsmeta check
  f2fs: remove duplicated code in sanity_check_area_boundary
  f2fs: remove unused check on version_bitmap
  ...

Documentation/ABI/testing/sysfs-fs-f2fs

@@ -22,7 +22,8 @@ Contact:	"Namjae Jeon" <namjae.jeon@samsung.com>
 Description:	Controls the victim selection 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 approach.
+		gc_idle = 2 will select the greedy approach & setting
+		gc_idle = 3 will select the age-threshold based approach.
 
 What:		/sys/fs/f2fs/<disk>/reclaim_segments
 Date:		October 2013

Documentation/filesystems/f2fs.rst

@@ -127,14 +127,14 @@ active_logs=%u		 Support configuring the number of active logs. In the
 			 current design, f2fs supports only 2, 4, and 6 logs.
 			 Default number is 6.
 disable_ext_identify	 Disable the extension list configured by mkfs, so f2fs
-			 does not aware of cold files such as media files.
+			 is not aware of cold files such as media files.
 inline_xattr		 Enable the inline xattrs feature.
 noinline_xattr		 Disable the inline xattrs feature.
 inline_xattr_size=%u	 Support configuring inline xattr size, it depends on
 			 flexible inline xattr feature.
-inline_data		 Enable the inline data feature: New created small(<~3.4k)
+inline_data		 Enable the inline data feature: Newly created small (<~3.4k)
 			 files can be written into inode block.
-inline_dentry		 Enable the inline dir feature: data in new created
+inline_dentry		 Enable the inline dir feature: data in newly created
 			 directory entries can be written into inode block. The
 			 space of inode block which is used to store inline
 			 dentries is limited to ~3.4k.
@@ -203,9 +203,9 @@ usrjquota=<file>	 Appoint specified file and type during mount, so that quota
 grpjquota=<file>	 information can be properly updated during recovery flow,
 prjjquota=<file>	 <quota file>: must be in root directory;
 jqfmt=<quota type>	 <quota type>: [vfsold,vfsv0,vfsv1].
-offusrjquota		 Turn off user journelled quota.
-offgrpjquota		 Turn off group journelled quota.
-offprjjquota		 Turn off project journelled quota.
+offusrjquota		 Turn off user journalled quota.
+offgrpjquota		 Turn off group journalled quota.
+offprjjquota		 Turn off project journalled quota.
 quota			 Enable plain user disk quota accounting.
 noquota			 Disable all plain disk quota option.
 whint_mode=%s		 Control which write hints are passed down to block
@@ -266,6 +266,8 @@ inlinecrypt		 When possible, encrypt/decrypt the contents of encrypted
 			 inline encryption hardware. The on-disk format is
 			 unaffected. For more details, see
 			 Documentation/block/inline-encryption.rst.
+atgc			 Enable age-threshold garbage collection, it provides high
+			 effectiveness and efficiency on background GC.
 ======================== ============================================================
 
 Debugfs Entries
@@ -301,7 +303,7 @@ Usage
 
 	# insmod f2fs.ko
 
-3. Create a directory trying to mount::
+3. Create a directory to use when mounting::
 
 	# mkdir /mnt/f2fs
 
@@ -315,7 +317,7 @@ mkfs.f2fs
 The mkfs.f2fs is for the use of formatting a partition as the f2fs filesystem,
 which builds a basic on-disk layout.
 
-The options consist of:
+The quick options consist of:
 
 ===============    ===========================================================
 ``-l [label]``     Give a volume label, up to 512 unicode name.
@@ -337,6 +339,8 @@ The options consist of:
                    1 is set by default, which conducts discard.
 ===============    ===========================================================
 
+Note: please refer to the manpage of mkfs.f2fs(8) to get full option list.
+
 fsck.f2fs
 ---------
 The fsck.f2fs is a tool to check the consistency of an f2fs-formatted
@@ -344,10 +348,12 @@ partition, which examines whether the filesystem metadata and user-made data
 are cross-referenced correctly or not.
 Note that, initial version of the tool does not fix any inconsistency.
 
-The options consist of::
+The quick options consist of::
 
   -d debug level [default:0]
 
+Note: please refer to the manpage of fsck.f2fs(8) to get full option list.
+
 dump.f2fs
 ---------
 The dump.f2fs shows the information of specific inode and dumps SSA and SIT to
@@ -371,6 +377,37 @@ Examples::
     # dump.f2fs -s 0~-1 /dev/sdx (SIT dump)
     # dump.f2fs -a 0~-1 /dev/sdx (SSA dump)
 
+Note: please refer to the manpage of dump.f2fs(8) to get full option list.
+
+sload.f2fs
+----------
+The sload.f2fs gives a way to insert files and directories in the exisiting disk
+image. This tool is useful when building f2fs images given compiled files.
+
+Note: please refer to the manpage of sload.f2fs(8) to get full option list.
+
+resize.f2fs
+-----------
+The resize.f2fs lets a user resize the f2fs-formatted disk image, while preserving
+all the files and directories stored in the image.
+
+Note: please refer to the manpage of resize.f2fs(8) to get full option list.
+
+defrag.f2fs
+-----------
+The defrag.f2fs can be used to defragment scattered written data as well as
+filesystem metadata across the disk. This can improve the write speed by giving
+more free consecutive space.
+
+Note: please refer to the manpage of defrag.f2fs(8) to get full option list.
+
+f2fs_io
+-------
+The f2fs_io is a simple tool to issue various filesystem APIs as well as
+f2fs-specific ones, which is very useful for QA tests.
+
+Note: please refer to the manpage of f2fs_io(8) to get full option list.
+
 Design
 ======
 
@@ -383,7 +420,7 @@ consists of a set of sections. By default, section and zone sizes are set to one
 segment size identically, but users can easily modify the sizes by mkfs.
 
 F2FS splits the entire volume into six areas, and all the areas except superblock
-consists of multiple segments as described below::
+consist of multiple segments as described below::
 
                                             align with the zone size <-|
                  |-> align with the segment size
@@ -486,7 +523,7 @@ one inode block (i.e., a file) covers::
 			              `- direct node (1018)
 	                                         `- data (1018)
 
-Note that, all the node blocks are mapped by NAT which means the location of
+Note that all the node blocks are mapped by NAT which means the location of
 each node is translated by the NAT table. In the consideration of the wandering
 tree problem, F2FS is able to cut off the propagation of node updates caused by
 leaf data writes.
@@ -566,7 +603,7 @@ When F2FS finds a file name in a directory, at first a hash value of the file
 name is calculated. Then, F2FS scans the hash table in level #0 to find the
 dentry consisting of the file name and its inode number. If not found, F2FS
 scans the next hash table in level #1. In this way, F2FS scans hash tables in
-each levels incrementally from 1 to N. In each levels F2FS needs to scan only
+each levels incrementally from 1 to N. In each level F2FS needs to scan only
 one bucket determined by the following equation, which shows O(log(# of files))
 complexity::
 
@@ -707,7 +744,7 @@ WRITE_LIFE_LONG       "                        WRITE_LIFE_LONG
 Fallocate(2) Policy
 -------------------
 
-The default policy follows the below posix rule.
+The default policy follows the below POSIX rule.
 
 Allocating disk space
     The default operation (i.e., mode is zero) of fallocate() allocates
@@ -720,7 +757,7 @@ Allocating disk space
     as a method of optimally implementing that function.
 
 However, once F2FS receives ioctl(fd, F2FS_IOC_SET_PIN_FILE) in prior to
-fallocate(fd, DEFAULT_MODE), it allocates on-disk blocks addressess having
+fallocate(fd, DEFAULT_MODE), it allocates on-disk block addressess having
 zero or random data, which is useful to the below scenario where:
 
  1. create(fd)
@@ -739,7 +776,7 @@ Compression implementation
   cluster can be compressed or not.
 
 - In cluster metadata layout, one special block address is used to indicate
-  cluster is compressed one or normal one, for compressed cluster, following
+  a cluster is a compressed one or normal one; for compressed cluster, following
   metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs
   stores data including compress header and compressed data.
 
@@ -772,3 +809,18 @@ Compress metadata layout::
 	+-------------+-------------+----------+----------------------------+
 	| data length | data chksum | reserved |      compressed data       |
 	+-------------+-------------+----------+----------------------------+
+
+NVMe Zoned Namespace devices
+----------------------------
+
+- ZNS defines a per-zone capacity which can be equal or less than the
+  zone-size. Zone-capacity is the number of usable blocks in the zone.
+  F2FS checks if zone-capacity is less than zone-size, if it is, then any
+  segment which starts after the zone-capacity is marked as not-free in
+  the free segment bitmap at initial mount time. These segments are marked
+  as permanently used so they are not allocated for writes and
+  consequently are not needed to be garbage collected. In case the
+  zone-capacity is not aligned to default segment size(2MB), then a segment
+  can start before the zone-capacity and span across zone-capacity boundary.
+  Such spanning segments are also considered as usable segments. All blocks
+  past the zone-capacity are considered unusable in these segments.

fs/f2fs/acl.c

@@ -160,7 +160,7 @@ static void *f2fs_acl_to_disk(struct f2fs_sb_info *sbi,
 	return (void *)f2fs_acl;
 
 fail:
-	kvfree(f2fs_acl);
+	kfree(f2fs_acl);
 	return ERR_PTR(-EINVAL);
 }
 
@@ -190,7 +190,7 @@ static struct posix_acl *__f2fs_get_acl(struct inode *inode, int type,
 		acl = NULL;
 	else
 		acl = ERR_PTR(retval);
-	kvfree(value);
+	kfree(value);
 
 	return acl;
 }
@@ -240,7 +240,7 @@ static int __f2fs_set_acl(struct inode *inode, int type,
 
 	error = f2fs_setxattr(inode, name_index, "", value, size, ipage, 0);
 
-	kvfree(value);
+	kfree(value);
 	if (!error)
 		set_cached_acl(inode, type, acl);
 

fs/f2fs/checkpoint.c

@@ -107,7 +107,7 @@ struct page *f2fs_get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
 	return __get_meta_page(sbi, index, true);
 }
 
-struct page *f2fs_get_meta_page_nofail(struct f2fs_sb_info *sbi, pgoff_t index)
+struct page *f2fs_get_meta_page_retry(struct f2fs_sb_info *sbi, pgoff_t index)
 {
 	struct page *page;
 	int count = 0;
@@ -243,6 +243,8 @@ int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
 					blkno * NAT_ENTRY_PER_BLOCK);
 			break;
 		case META_SIT:
+			if (unlikely(blkno >= TOTAL_SEGS(sbi)))
+				goto out;
 			/* get sit block addr */
 			fio.new_blkaddr = current_sit_addr(sbi,
 					blkno * SIT_ENTRY_PER_BLOCK);
@@ -1047,8 +1049,12 @@ int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type)
 				get_pages(sbi, is_dir ?
 				F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA));
 retry:
-	if (unlikely(f2fs_cp_error(sbi)))
+	if (unlikely(f2fs_cp_error(sbi))) {
+		trace_f2fs_sync_dirty_inodes_exit(sbi->sb, is_dir,
+				get_pages(sbi, is_dir ?
+				F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA));
 		return -EIO;
+	}
 
 	spin_lock(&sbi->inode_lock[type]);
 
@@ -1619,11 +1625,16 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	f2fs_flush_sit_entries(sbi, cpc);
 
+	/* save inmem log status */
+	f2fs_save_inmem_curseg(sbi);
+
 	err = do_checkpoint(sbi, cpc);
 	if (err)
 		f2fs_release_discard_addrs(sbi);
 	else
 		f2fs_clear_prefree_segments(sbi, cpc);
+
+	f2fs_restore_inmem_curseg(sbi);
 stop:
 	unblock_operations(sbi);
 	stat_inc_cp_count(sbi->stat_info);
@@ -1654,7 +1665,7 @@ void f2fs_init_ino_entry_info(struct f2fs_sb_info *sbi)
 	}
 
 	sbi->max_orphans = (sbi->blocks_per_seg - F2FS_CP_PACKS -
-			NR_CURSEG_TYPE - __cp_payload(sbi)) *
+			NR_CURSEG_PERSIST_TYPE - __cp_payload(sbi)) *
 				F2FS_ORPHANS_PER_BLOCK;
 }
 

fs/f2fs/data.c

@@ -202,7 +202,7 @@ static void f2fs_verify_bio(struct bio *bio)
 		dic = (struct decompress_io_ctx *)page_private(page);
 
 		if (dic) {
-			if (refcount_dec_not_one(&dic->ref))
+			if (atomic_dec_return(&dic->pending_pages))
 				continue;
 			f2fs_verify_pages(dic->rpages,
 						dic->cluster_size);
@@ -517,7 +517,7 @@ static inline void __submit_bio(struct f2fs_sb_info *sbi,
 
 			zero_user_segment(page, 0, PAGE_SIZE);
 			SetPagePrivate(page);
-			set_page_private(page, (unsigned long)DUMMY_WRITTEN_PAGE);
+			set_page_private(page, DUMMY_WRITTEN_PAGE);
 			lock_page(page);
 			if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE)
 				f2fs_bug_on(sbi, 1);
@@ -1416,7 +1416,7 @@ static int __allocate_data_block(struct dnode_of_data *dn, int seg_type)
 	set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
 	old_blkaddr = dn->data_blkaddr;
 	f2fs_allocate_data_block(sbi, NULL, old_blkaddr, &dn->data_blkaddr,
-					&sum, seg_type, NULL);
+				&sum, seg_type, NULL);
 	if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO)
 		invalidate_mapping_pages(META_MAPPING(sbi),
 					old_blkaddr, old_blkaddr);
@@ -1803,10 +1803,6 @@ 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, NULL,
 						NO_CHECK_TYPE, create);
@@ -2272,8 +2268,8 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
 			if (IS_ERR(bio)) {
 				ret = PTR_ERR(bio);
 				dic->failed = true;
-				if (refcount_sub_and_test(dic->nr_cpages - i,
-							&dic->ref)) {
+				if (!atomic_sub_return(dic->nr_cpages - i,
+							&dic->pending_pages)) {
 					f2fs_decompress_end_io(dic->rpages,
 							cc->cluster_size, true,
 							false);
@@ -3133,6 +3129,8 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
 			retry = 0;
 		}
 	}
+	if (f2fs_compressed_file(inode))
+		f2fs_destroy_compress_ctx(&cc);
 #endif
 	if (retry) {
 		index = 0;
@@ -3574,7 +3572,7 @@ static void f2fs_dio_end_io(struct bio *bio)
 	bio->bi_private = dio->orig_private;
 	bio->bi_end_io = dio->orig_end_io;
 
-	kvfree(dio);
+	kfree(dio);
 
 	bio_endio(bio);
 }
@@ -3673,12 +3671,18 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 									err);
 			if (!do_opu)
 				set_inode_flag(inode, FI_UPDATE_WRITE);
+		} else if (err == -EIOCBQUEUED) {
+			f2fs_update_iostat(F2FS_I_SB(inode), APP_DIRECT_IO,
+						count - iov_iter_count(iter));
 		} else if (err < 0) {
 			f2fs_write_failed(mapping, offset + count);
 		}
 	} else {
 		if (err > 0)
 			f2fs_update_iostat(sbi, APP_DIRECT_READ_IO, err);
+		else if (err == -EIOCBQUEUED)
+			f2fs_update_iostat(F2FS_I_SB(inode), APP_DIRECT_READ_IO,
+						count - iov_iter_count(iter));
 	}
 
 out:
@@ -3807,11 +3811,16 @@ static sector_t f2fs_bmap(struct address_space *mapping, sector_t block)
 	if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
 		filemap_write_and_wait(mapping);
 
-	if (f2fs_compressed_file(inode))
-		blknr = f2fs_bmap_compress(inode, block);
+	/* Block number less than F2FS MAX BLOCKS */
+	if (unlikely(block >= F2FS_I_SB(inode)->max_file_blocks))
+		goto out;
 
-	if (!get_data_block_bmap(inode, block, &tmp, 0))
-		blknr = tmp.b_blocknr;
+	if (f2fs_compressed_file(inode)) {
+		blknr = f2fs_bmap_compress(inode, block);
+	} else {
+		if (!get_data_block_bmap(inode, block, &tmp, 0))
+			blknr = tmp.b_blocknr;
+	}
 out:
 	trace_f2fs_bmap(inode, block, blknr);
 	return blknr;
@@ -3874,6 +3883,83 @@ int f2fs_migrate_page(struct address_space *mapping,
 #endif
 
 #ifdef CONFIG_SWAP
+static int check_swap_activate_fast(struct swap_info_struct *sis,
+				struct file *swap_file, sector_t *span)
+{
+	struct address_space *mapping = swap_file->f_mapping;
+	struct inode *inode = mapping->host;
+	sector_t cur_lblock;
+	sector_t last_lblock;
+	sector_t pblock;
+	sector_t lowest_pblock = -1;
+	sector_t highest_pblock = 0;
+	int nr_extents = 0;
+	unsigned long nr_pblocks;
+	unsigned long len;
+	int ret;
+
+	/*
+	 * Map all the blocks into the extent list.  This code doesn't try
+	 * to be very smart.
+	 */
+	cur_lblock = 0;
+	last_lblock = logical_to_blk(inode, i_size_read(inode));
+	len = i_size_read(inode);
+
+	while (cur_lblock <= last_lblock && cur_lblock < sis->max) {
+		struct buffer_head map_bh;
+		pgoff_t next_pgofs;
+
+		cond_resched();
+
+		memset(&map_bh, 0, sizeof(struct buffer_head));
+		map_bh.b_size = len - cur_lblock;
+
+		ret = get_data_block(inode, cur_lblock, &map_bh, 0,
+					F2FS_GET_BLOCK_FIEMAP, &next_pgofs);
+		if (ret)
+			goto err_out;
+
+		/* hole */
+		if (!buffer_mapped(&map_bh))
+			goto err_out;
+
+		pblock = map_bh.b_blocknr;
+		nr_pblocks = logical_to_blk(inode, map_bh.b_size);
+
+		if (cur_lblock + nr_pblocks >= sis->max)
+			nr_pblocks = sis->max - cur_lblock;
+
+		if (cur_lblock) {	/* exclude the header page */
+			if (pblock < lowest_pblock)
+				lowest_pblock = pblock;
+			if (pblock + nr_pblocks - 1 > highest_pblock)
+				highest_pblock = pblock + nr_pblocks - 1;
+		}
+
+		/*
+		 * We found a PAGE_SIZE-length, PAGE_SIZE-aligned run of blocks
+		 */
+		ret = add_swap_extent(sis, cur_lblock, nr_pblocks, pblock);
+		if (ret < 0)
+			goto out;
+		nr_extents += ret;
+		cur_lblock += nr_pblocks;
+	}
+	ret = nr_extents;
+	*span = 1 + highest_pblock - lowest_pblock;
+	if (cur_lblock == 0)
+		cur_lblock = 1;	/* force Empty message */
+	sis->max = cur_lblock;
+	sis->pages = cur_lblock - 1;
+	sis->highest_bit = cur_lblock - 1;
+out:
+	return ret;
+err_out:
+	pr_err("swapon: swapfile has holes\n");
+	return -EINVAL;
+}
+
 /* Copied from generic_swapfile_activate() to check any holes */
 static int check_swap_activate(struct swap_info_struct *sis,
 				struct file *swap_file, sector_t *span)
@@ -3890,6 +3976,9 @@ static int check_swap_activate(struct swap_info_struct *sis,
 	int nr_extents = 0;
 	int ret;
 
+	if (PAGE_SIZE == F2FS_BLKSIZE)
+		return check_swap_activate_fast(sis, swap_file, span);
+
 	blkbits = inode->i_blkbits;
 	blocks_per_page = PAGE_SIZE >> blkbits;
 
@@ -3989,7 +4078,7 @@ static int f2fs_swap_activate(struct swap_info_struct *sis, struct file *file,
 	if (ret)
 		return ret;
 
-	if (f2fs_disable_compressed_file(inode))
+	if (!f2fs_disable_compressed_file(inode))
 		return -EINVAL;
 
 	ret = check_swap_activate(sis, file, span);

fs/f2fs/debug.c

@@ -131,7 +131,7 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 	si->inline_inode = atomic_read(&sbi->inline_inode);
 	si->inline_dir = atomic_read(&sbi->inline_dir);
 	si->compr_inode = atomic_read(&sbi->compr_inode);
-	si->compr_blocks = atomic_read(&sbi->compr_blocks);
+	si->compr_blocks = atomic64_read(&sbi->compr_blocks);
 	si->append = sbi->im[APPEND_INO].ino_num;
 	si->update = sbi->im[UPDATE_INO].ino_num;
 	si->orphans = sbi->im[ORPHAN_INO].ino_num;
@@ -164,7 +164,7 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 		* 100 / (int)(sbi->user_block_count >> sbi->log_blocks_per_seg)
 		/ 2;
 	si->util_invalid = 50 - si->util_free - si->util_valid;
-	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_NODE; i++) {
+	for (i = CURSEG_HOT_DATA; i < NO_CHECK_TYPE; i++) {
 		struct curseg_info *curseg = CURSEG_I(sbi, i);
 		si->curseg[i] = curseg->segno;
 		si->cursec[i] = GET_SEC_FROM_SEG(sbi, curseg->segno);
@@ -342,7 +342,7 @@ static int stat_show(struct seq_file *s, void *v)
 			   si->inline_inode);
 		seq_printf(s, "  - Inline_dentry Inode: %u\n",
 			   si->inline_dir);
-		seq_printf(s, "  - Compressed Inode: %u, Blocks: %u\n",
+		seq_printf(s, "  - Compressed Inode: %u, Blocks: %llu\n",
 			   si->compr_inode, si->compr_blocks);
 		seq_printf(s, "  - Orphan/Append/Update Inode: %u, %u, %u\n",
 			   si->orphans, si->append, si->update);
@@ -393,6 +393,14 @@ static int stat_show(struct seq_file *s, void *v)
 			   si->dirty_seg[CURSEG_COLD_NODE],
 			   si->full_seg[CURSEG_COLD_NODE],
 			   si->valid_blks[CURSEG_COLD_NODE]);
+		seq_printf(s, "  - Pinned file: %8d %8d %8d\n",
+			   si->curseg[CURSEG_COLD_DATA_PINNED],
+			   si->cursec[CURSEG_COLD_DATA_PINNED],
+			   si->curzone[CURSEG_COLD_DATA_PINNED]);
+		seq_printf(s, "  - ATGC   data: %8d %8d %8d\n",
+			   si->curseg[CURSEG_ALL_DATA_ATGC],
+			   si->cursec[CURSEG_ALL_DATA_ATGC],
+			   si->curzone[CURSEG_ALL_DATA_ATGC]);
 		seq_printf(s, "\n  - Valid: %d\n  - Dirty: %d\n",
 			   si->main_area_segs - si->dirty_count -
 			   si->prefree_count - si->free_segs,
@@ -542,7 +550,7 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi)
 	atomic_set(&sbi->inline_inode, 0);
 	atomic_set(&sbi->inline_dir, 0);
 	atomic_set(&sbi->compr_inode, 0);
-	atomic_set(&sbi->compr_blocks, 0);
+	atomic64_set(&sbi->compr_blocks, 0);
 	atomic_set(&sbi->inplace_count, 0);
 	for (i = META_CP; i < META_MAX; i++)
 		atomic_set(&sbi->meta_count[i], 0);
@@ -566,7 +574,7 @@ void f2fs_destroy_stats(struct f2fs_sb_info *sbi)
 	list_del(&si->stat_list);
 	mutex_unlock(&f2fs_stat_mutex);
 
-	kvfree(si);
+	kfree(si);
 }
 
 void __init f2fs_create_root_stats(void)

fs/f2fs/dir.c

@@ -75,21 +75,22 @@ int f2fs_init_casefolded_name(const struct inode *dir,
 			      struct f2fs_filename *fname)
 {
 #ifdef CONFIG_UNICODE
-	struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
+	struct super_block *sb = dir->i_sb;
+	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 
 	if (IS_CASEFOLDED(dir)) {
 		fname->cf_name.name = f2fs_kmalloc(sbi, F2FS_NAME_LEN,
 						   GFP_NOFS);
 		if (!fname->cf_name.name)
 			return -ENOMEM;
-		fname->cf_name.len = utf8_casefold(sbi->s_encoding,
+		fname->cf_name.len = utf8_casefold(sb->s_encoding,
 						   fname->usr_fname,
 						   fname->cf_name.name,
 						   F2FS_NAME_LEN);
 		if ((int)fname->cf_name.len <= 0) {
 			kfree(fname->cf_name.name);
 			fname->cf_name.name = NULL;
-			if (f2fs_has_strict_mode(sbi))
+			if (sb_has_strict_encoding(sb))
 				return -EINVAL;
 			/* fall back to treating name as opaque byte sequence */
 		}
@@ -190,21 +191,15 @@ static unsigned long dir_block_index(unsigned int level,
 static struct f2fs_dir_entry *find_in_block(struct inode *dir,
 				struct page *dentry_page,
 				const struct f2fs_filename *fname,
-				int *max_slots,
-				struct page **res_page)
+				int *max_slots)
 {
 	struct f2fs_dentry_block *dentry_blk;
-	struct f2fs_dir_entry *de;
 	struct f2fs_dentry_ptr d;
 
 	dentry_blk = (struct f2fs_dentry_block *)page_address(dentry_page);
 
 	make_dentry_ptr_block(dir, &d, dentry_blk);
-	de = f2fs_find_target_dentry(&d, fname, max_slots);
-	if (de)
-		*res_page = dentry_page;
-
-	return de;
+	return f2fs_find_target_dentry(&d, fname, max_slots);
 }
 
 #ifdef CONFIG_UNICODE
@@ -215,8 +210,8 @@ static struct f2fs_dir_entry *find_in_block(struct inode *dir,
 static bool f2fs_match_ci_name(const struct inode *dir, const struct qstr *name,
 			       const u8 *de_name, u32 de_name_len)
 {
-	const struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
-	const struct unicode_map *um = sbi->s_encoding;
+	const struct super_block *sb = dir->i_sb;
+	const struct unicode_map *um = sb->s_encoding;
 	struct qstr entry = QSTR_INIT(de_name, de_name_len);
 	int res;
 
@@ -226,7 +221,7 @@ static bool f2fs_match_ci_name(const struct inode *dir, const struct qstr *name,
 		 * In strict mode, ignore invalid names.  In non-strict mode,
 		 * fall back to treating them as opaque byte sequences.
 		 */
-		if (f2fs_has_strict_mode(sbi) || name->len != entry.len)
+		if (sb_has_strict_encoding(sb) || name->len != entry.len)
 			return false;
 		return !memcmp(name->name, entry.name, name->len);
 	}
@@ -330,10 +325,11 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
 			}
 		}
 
-		de = find_in_block(dir, dentry_page, fname, &max_slots,
-				   res_page);
-		if (de)
+		de = find_in_block(dir, dentry_page, fname, &max_slots);
+		if (de) {
+			*res_page = dentry_page;
 			break;
+		}
 
 		if (max_slots >= s)
 			room = true;
@@ -357,16 +353,15 @@ struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir,
 	unsigned int max_depth;
 	unsigned int level;
 
+	*res_page = NULL;
+
 	if (f2fs_has_inline_dentry(dir)) {
-		*res_page = NULL;
 		de = f2fs_find_in_inline_dir(dir, fname, res_page);
 		goto out;
 	}
 
-	if (npages == 0) {
-		*res_page = NULL;
+	if (npages == 0)
 		goto out;
-	}
 
 	max_depth = F2FS_I(dir)->i_current_depth;
 	if (unlikely(max_depth > MAX_DIR_HASH_DEPTH)) {
@@ -377,7 +372,6 @@ struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir,
 	}
 
 	for (level = 0; level < max_depth; level++) {
-		*res_page = NULL;
 		de = find_in_level(dir, level, fname, res_page);
 		if (de || IS_ERR(*res_page))
 			break;
@@ -1107,75 +1101,8 @@ const struct file_operations f2fs_dir_operations = {
 };
 
 #ifdef CONFIG_UNICODE
-static int f2fs_d_compare(const struct dentry *dentry, unsigned int len,
-			  const char *str, const struct qstr *name)
-{
-	const struct dentry *parent = READ_ONCE(dentry->d_parent);
-	const struct inode *dir = READ_ONCE(parent->d_inode);
-	const struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
-	struct qstr entry = QSTR_INIT(str, len);
-	char strbuf[DNAME_INLINE_LEN];
-	int res;
-
-	if (!dir || !IS_CASEFOLDED(dir))
-		goto fallback;
-
-	/*
-	 * If the dentry name is stored in-line, then it may be concurrently
-	 * modified by a rename.  If this happens, the VFS will eventually retry
-	 * the lookup, so it doesn't matter what ->d_compare() returns.
-	 * However, it's unsafe to call utf8_strncasecmp() with an unstable
-	 * string.  Therefore, we have to copy the name into a temporary buffer.
-	 */
-	if (len <= DNAME_INLINE_LEN - 1) {
-		memcpy(strbuf, str, len);
-		strbuf[len] = 0;
-		entry.name = strbuf;
-		/* prevent compiler from optimizing out the temporary buffer */
-		barrier();
-	}
-
-	res = utf8_strncasecmp(sbi->s_encoding, name, &entry);
-	if (res >= 0)
-		return res;
-
-	if (f2fs_has_strict_mode(sbi))
-		return -EINVAL;
-fallback:
-	if (len != name->len)
-		return 1;
-	return !!memcmp(str, name->name, len);
-}
-
-static int f2fs_d_hash(const struct dentry *dentry, struct qstr *str)
-{
-	struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
-	const struct unicode_map *um = sbi->s_encoding;
-	const struct inode *inode = READ_ONCE(dentry->d_inode);
-	unsigned char *norm;
-	int len, ret = 0;
-
-	if (!inode || !IS_CASEFOLDED(inode))
-		return 0;
-
-	norm = f2fs_kmalloc(sbi, PATH_MAX, GFP_ATOMIC);
-	if (!norm)
-		return -ENOMEM;
-
-	len = utf8_casefold(um, str, norm, PATH_MAX);
-	if (len < 0) {
-		if (f2fs_has_strict_mode(sbi))
-			ret = -EINVAL;
-		goto out;
-	}
-	str->hash = full_name_hash(dentry, norm, len);
-out:
-	kvfree(norm);
-	return ret;
-}
-
 const struct dentry_operations f2fs_dentry_ops = {
-	.d_hash = f2fs_d_hash,
-	.d_compare = f2fs_d_compare,
+	.d_hash = generic_ci_d_hash,
+	.d_compare = generic_ci_d_compare,
 };
 #endif

fs/f2fs/extent_cache.c

@@ -58,6 +58,29 @@ struct rb_entry *f2fs_lookup_rb_tree(struct rb_root_cached *root,
 	return re;
 }
 
+struct rb_node **f2fs_lookup_rb_tree_ext(struct f2fs_sb_info *sbi,
+					struct rb_root_cached *root,
+					struct rb_node **parent,
+					unsigned long long key, bool *leftmost)
+{
+	struct rb_node **p = &root->rb_root.rb_node;
+	struct rb_entry *re;
+
+	while (*p) {
+		*parent = *p;
+		re = rb_entry(*parent, struct rb_entry, rb_node);
+
+		if (key < re->key) {
+			p = &(*p)->rb_left;
+		} else {
+			p = &(*p)->rb_right;
+			*leftmost = false;
+		}
+	}
+
+	return p;
+}
+
 struct rb_node **f2fs_lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi,
 				struct rb_root_cached *root,
 				struct rb_node **parent,
@@ -166,7 +189,7 @@ struct rb_entry *f2fs_lookup_rb_tree_ret(struct rb_root_cached *root,
 }
 
 bool f2fs_check_rb_tree_consistence(struct f2fs_sb_info *sbi,
-						struct rb_root_cached *root)
+				struct rb_root_cached *root, bool check_key)
 {
 #ifdef CONFIG_F2FS_CHECK_FS
 	struct rb_node *cur = rb_first_cached(root), *next;
@@ -183,13 +206,23 @@ bool f2fs_check_rb_tree_consistence(struct f2fs_sb_info *sbi,
 		cur_re = rb_entry(cur, struct rb_entry, rb_node);
 		next_re = rb_entry(next, struct rb_entry, rb_node);
 
+		if (check_key) {
+			if (cur_re->key > next_re->key) {
+				f2fs_info(sbi, "inconsistent rbtree, "
+					"cur(%llu) next(%llu)",
+					cur_re->key, next_re->key);
+				return false;
+			}
+			goto next;
+		}
+
 		if (cur_re->ofs + cur_re->len > next_re->ofs) {
 			f2fs_info(sbi, "inconsistent rbtree, cur(%u, %u) next(%u, %u)",
 				  cur_re->ofs, cur_re->len,
 				  next_re->ofs, next_re->len);
 			return false;
 		}
-
+next:
 		cur = next;
 	}
 #endif

fs/f2fs/file.c

@@ -376,32 +376,15 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	return f2fs_do_sync_file(file, start, end, datasync, false);
 }
 
-static pgoff_t __get_first_dirty_index(struct address_space *mapping,
-						pgoff_t pgofs, int whence)
-{
-	struct page *page;
-	int nr_pages;
-
-	if (whence != SEEK_DATA)
-		return 0;
-
-	/* find first dirty page index */
-	nr_pages = find_get_pages_tag(mapping, &pgofs, PAGECACHE_TAG_DIRTY,
-				      1, &page);
-	if (!nr_pages)
-		return ULONG_MAX;
-	pgofs = page->index;
-	put_page(page);
-	return pgofs;
-}
-
-static bool __found_offset(struct f2fs_sb_info *sbi, block_t blkaddr,
-				pgoff_t dirty, pgoff_t pgofs, int whence)
+static bool __found_offset(struct address_space *mapping, block_t blkaddr,
+				pgoff_t index, int whence)
 {
 	switch (whence) {
 	case SEEK_DATA:
-		if ((blkaddr == NEW_ADDR && dirty == pgofs) ||
-			__is_valid_data_blkaddr(blkaddr))
+		if (__is_valid_data_blkaddr(blkaddr))
+			return true;
+		if (blkaddr == NEW_ADDR &&
+		    xa_get_mark(&mapping->i_pages, index, PAGECACHE_TAG_DIRTY))
 			return true;
 		break;
 	case SEEK_HOLE:
@@ -417,7 +400,7 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
 	struct inode *inode = file->f_mapping->host;
 	loff_t maxbytes = inode->i_sb->s_maxbytes;
 	struct dnode_of_data dn;
-	pgoff_t pgofs, end_offset, dirty;
+	pgoff_t pgofs, end_offset;
 	loff_t data_ofs = offset;
 	loff_t isize;
 	int err = 0;
@@ -429,16 +412,13 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
 		goto fail;
 
 	/* handle inline data case */
-	if (f2fs_has_inline_data(inode) || f2fs_has_inline_dentry(inode)) {
-		if (whence == SEEK_HOLE)
-			data_ofs = isize;
+	if (f2fs_has_inline_data(inode) && whence == SEEK_HOLE) {
+		data_ofs = isize;
 		goto found;
 	}
 
 	pgofs = (pgoff_t)(offset >> PAGE_SHIFT);
 
-	dirty = __get_first_dirty_index(inode->i_mapping, pgofs, whence);
-
 	for (; data_ofs < isize; data_ofs = (loff_t)pgofs << PAGE_SHIFT) {
 		set_new_dnode(&dn, inode, NULL, NULL, 0);
 		err = f2fs_get_dnode_of_data(&dn, pgofs, LOOKUP_NODE);
@@ -471,7 +451,7 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
 				goto fail;
 			}
 
-			if (__found_offset(F2FS_I_SB(inode), blkaddr, dirty,
+			if (__found_offset(file->f_mapping, blkaddr,
 							pgofs, whence)) {
 				f2fs_put_dnode(&dn);
 				goto found;
@@ -564,7 +544,7 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count)
 	bool compressed_cluster = false;
 	int cluster_index = 0, valid_blocks = 0;
 	int cluster_size = F2FS_I(dn->inode)->i_cluster_size;
-	bool released = !F2FS_I(dn->inode)->i_compr_blocks;
+	bool released = !atomic_read(&F2FS_I(dn->inode)->i_compr_blocks);
 
 	if (IS_INODE(dn->node_page) && f2fs_has_extra_attr(dn->inode))
 		base = get_extra_isize(dn->inode);
@@ -753,11 +733,14 @@ int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock)
 		return err;
 
 #ifdef CONFIG_F2FS_FS_COMPRESSION
-	if (from != free_from)
+	if (from != free_from) {
 		err = f2fs_truncate_partial_cluster(inode, from, lock);
+		if (err)
+			return err;
+	}
 #endif
 
-	return err;
+	return 0;
 }
 
 int f2fs_truncate(struct inode *inode)
@@ -1656,13 +1639,14 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
 		}
 
 		down_write(&sbi->pin_sem);
-		map.m_seg_type = CURSEG_COLD_DATA_PINNED;
 
 		f2fs_lock_op(sbi);
-		f2fs_allocate_new_segment(sbi, CURSEG_COLD_DATA);
+		f2fs_allocate_new_segment(sbi, CURSEG_COLD_DATA_PINNED);
 		f2fs_unlock_op(sbi);
 
+		map.m_seg_type = CURSEG_COLD_DATA_PINNED;
 		err = f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_DIO);
+
 		up_write(&sbi->pin_sem);
 
 		done += map.m_len;
@@ -1828,7 +1812,7 @@ static int f2fs_setflags_common(struct inode *inode, u32 iflags, u32 mask)
 
 	if ((iflags ^ masked_flags) & F2FS_COMPR_FL) {
 		if (masked_flags & F2FS_COMPR_FL) {
-			if (f2fs_disable_compressed_file(inode))
+			if (!f2fs_disable_compressed_file(inode))
 				return -EINVAL;
 		}
 		if (iflags & F2FS_NOCOMP_FL)
@@ -1836,6 +1820,8 @@ static int f2fs_setflags_common(struct inode *inode, u32 iflags, u32 mask)
 		if (iflags & F2FS_COMPR_FL) {
 			if (!f2fs_may_compress(inode))
 				return -EINVAL;
+			if (S_ISREG(inode->i_mode) && inode->i_size)
+				return -EINVAL;
 
 			set_compress_context(inode);
 		}
@@ -2783,6 +2769,9 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in,
 	if (IS_ENCRYPTED(src) || IS_ENCRYPTED(dst))
 		return -EOPNOTSUPP;
 
+	if (pos_out < 0 || pos_in < 0)
+		return -EINVAL;
+
 	if (src == dst) {
 		if (pos_in == pos_out)
 			return 0;
@@ -3258,7 +3247,7 @@ static int f2fs_ioc_set_pin_file(struct file *filp, unsigned long arg)
 	if (ret)
 		goto out;
 
-	if (f2fs_disable_compressed_file(inode)) {
+	if (!f2fs_disable_compressed_file(inode)) {
 		ret = -EOPNOTSUPP;
 		goto out;
 	}
@@ -3385,7 +3374,7 @@ static int f2fs_ioc_getfslabel(struct file *filp, unsigned long arg)
 				min(FSLABEL_MAX, count)))
 		err = -EFAULT;
 
-	kvfree(vbuf);
+	kfree(vbuf);
 	return err;
 }
 
@@ -3436,7 +3425,7 @@ static int f2fs_get_compress_blocks(struct file *filp, unsigned long arg)
 	if (!f2fs_compressed_file(inode))
 		return -EINVAL;
 
-	blocks = F2FS_I(inode)->i_compr_blocks;
+	blocks = atomic_read(&F2FS_I(inode)->i_compr_blocks);
 	return put_user(blocks, (u64 __user *)arg);
 }
 
@@ -3521,7 +3510,8 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg)
 	inode_lock(inode);
 
 	writecount = atomic_read(&inode->i_writecount);
-	if ((filp->f_mode & FMODE_WRITE && writecount != 1) || writecount) {
+	if ((filp->f_mode & FMODE_WRITE && writecount != 1) ||
+			(!(filp->f_mode & FMODE_WRITE) && writecount)) {
 		ret = -EBUSY;
 		goto out;
 	}
@@ -3540,7 +3530,7 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg)
 	inode->i_ctime = current_time(inode);
 	f2fs_mark_inode_dirty_sync(inode, true);
 
-	if (!F2FS_I(inode)->i_compr_blocks)
+	if (!atomic_read(&F2FS_I(inode)->i_compr_blocks))
 		goto out;
 
 	down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
@@ -3588,14 +3578,15 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg)
 
 	if (ret >= 0) {
 		ret = put_user(released_blocks, (u64 __user *)arg);
-	} else if (released_blocks && F2FS_I(inode)->i_compr_blocks) {
+	} else if (released_blocks &&
+			atomic_read(&F2FS_I(inode)->i_compr_blocks)) {
 		set_sbi_flag(sbi, SBI_NEED_FSCK);
 		f2fs_warn(sbi, "%s: partial blocks were released i_ino=%lx "
-			"iblocks=%llu, released=%u, compr_blocks=%llu, "
+			"iblocks=%llu, released=%u, compr_blocks=%u, "
 			"run fsck to fix.",
 			__func__, inode->i_ino, inode->i_blocks,
 			released_blocks,
-			F2FS_I(inode)->i_compr_blocks);
+			atomic_read(&F2FS_I(inode)->i_compr_blocks));
 	}
 
 	return ret;
@@ -3683,7 +3674,7 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
 	if (ret)
 		return ret;
 
-	if (F2FS_I(inode)->i_compr_blocks)
+	if (atomic_read(&F2FS_I(inode)->i_compr_blocks))
 		goto out;
 
 	f2fs_balance_fs(F2FS_I_SB(inode), true);
@@ -3747,14 +3738,15 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
 
 	if (ret >= 0) {
 		ret = put_user(reserved_blocks, (u64 __user *)arg);
-	} else if (reserved_blocks && F2FS_I(inode)->i_compr_blocks) {
+	} else if (reserved_blocks &&
+			atomic_read(&F2FS_I(inode)->i_compr_blocks)) {
 		set_sbi_flag(sbi, SBI_NEED_FSCK);
 		f2fs_warn(sbi, "%s: partial blocks were released i_ino=%lx "
-			"iblocks=%llu, reserved=%u, compr_blocks=%llu, "
+			"iblocks=%llu, reserved=%u, compr_blocks=%u, "
 			"run fsck to fix.",
 			__func__, inode->i_ino, inode->i_blocks,
 			reserved_blocks,
-			F2FS_I(inode)->i_compr_blocks);
+			atomic_read(&F2FS_I(inode)->i_compr_blocks));
 	}
 
 	return ret;

fs/f2fs/gc.h

@@ -14,6 +14,14 @@
 #define DEF_GC_THREAD_MIN_SLEEP_TIME	30000	/* milliseconds */
 #define DEF_GC_THREAD_MAX_SLEEP_TIME	60000
 #define DEF_GC_THREAD_NOGC_SLEEP_TIME	300000	/* wait 5 min */
+
+/* choose candidates from sections which has age of more than 7 days */
+#define DEF_GC_THREAD_AGE_THRESHOLD		(60 * 60 * 24 * 7)
+#define DEF_GC_THREAD_CANDIDATE_RATIO		20	/* select 20% oldest sections as candidates */
+#define DEF_GC_THREAD_MAX_CANDIDATE_COUNT	10	/* select at most 10 sections as candidates */
+#define DEF_GC_THREAD_AGE_WEIGHT		60	/* age weight */
+#define DEFAULT_ACCURACY_CLASS			10000	/* accuracy class */
+
 #define LIMIT_INVALID_BLOCK	40 /* percentage over total user space */
 #define LIMIT_FREE_BLOCK	40 /* percentage over invalid + free space */
 
@@ -41,16 +49,69 @@ struct gc_inode_list {
 	struct radix_tree_root iroot;
 };
 
+struct victim_info {
+	unsigned long long mtime;	/* mtime of section */
+	unsigned int segno;		/* section No. */
+};
+
+struct victim_entry {
+	struct rb_node rb_node;		/* rb node located in rb-tree */
+	union {
+		struct {
+			unsigned long long mtime;	/* mtime of section */
+			unsigned int segno;		/* segment No. */
+		};
+		struct victim_info vi;	/* victim info */
+	};
+	struct list_head list;
+};
+
 /*
  * inline functions
  */
+
+/*
+ * On a Zoned device zone-capacity can be less than zone-size and if
+ * zone-capacity is not aligned to f2fs segment size(2MB), then the segment
+ * starting just before zone-capacity has some blocks spanning across the
+ * zone-capacity, these blocks are not usable.
+ * Such spanning segments can be in free list so calculate the sum of usable
+ * blocks in currently free segments including normal and spanning segments.
+ */
+static inline block_t free_segs_blk_count_zoned(struct f2fs_sb_info *sbi)
+{
+	block_t free_seg_blks = 0;
+	struct free_segmap_info *free_i = FREE_I(sbi);
+	int j;
+
+	spin_lock(&free_i->segmap_lock);
+	for (j = 0; j < MAIN_SEGS(sbi); j++)
+		if (!test_bit(j, free_i->free_segmap))
+			free_seg_blks += f2fs_usable_blks_in_seg(sbi, j);
+	spin_unlock(&free_i->segmap_lock);
+
+	return free_seg_blks;
+}
+
+static inline block_t free_segs_blk_count(struct f2fs_sb_info *sbi)
+{
+	if (f2fs_sb_has_blkzoned(sbi))
+		return free_segs_blk_count_zoned(sbi);
+
+	return free_segments(sbi) << sbi->log_blocks_per_seg;
+}
+
 static inline block_t free_user_blocks(struct f2fs_sb_info *sbi)
 {
-	if (free_segments(sbi) < overprovision_segments(sbi))
+	block_t free_blks, ovp_blks;
+
+	free_blks = free_segs_blk_count(sbi);
+	ovp_blks = overprovision_segments(sbi) << sbi->log_blocks_per_seg;
+
+	if (free_blks < ovp_blks)
 		return 0;
-	else
-		return (free_segments(sbi) - overprovision_segments(sbi))
-			<< sbi->log_blocks_per_seg;
+
+	return free_blks - ovp_blks;
 }
 
 static inline block_t limit_invalid_user_blocks(struct f2fs_sb_info *sbi)

fs/f2fs/inline.c

@@ -524,7 +524,7 @@ static int f2fs_move_rehashed_dirents(struct inode *dir, struct page *ipage,
 			!f2fs_has_inline_xattr(dir))
 		F2FS_I(dir)->i_inline_xattr_size = 0;
 
-	kvfree(backup_dentry);
+	kfree(backup_dentry);
 	return 0;
 recover:
 	lock_page(ipage);
@@ -535,7 +535,7 @@ static int f2fs_move_rehashed_dirents(struct inode *dir, struct page *ipage,
 	set_page_dirty(ipage);
 	f2fs_put_page(ipage, 1);
 
-	kvfree(backup_dentry);
+	kfree(backup_dentry);
 	return err;
 }
 

fs/f2fs/inode.c

@@ -287,11 +287,19 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
 		return false;
 	}
 
+	if ((fi->i_flags & F2FS_CASEFOLD_FL) && !f2fs_sb_has_casefold(sbi)) {
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
+		f2fs_warn(sbi, "%s: inode (ino=%lx) has casefold flag, but casefold feature is off",
+			  __func__, inode->i_ino);
+		return false;
+	}
+
 	if (f2fs_has_extra_attr(inode) && f2fs_sb_has_compression(sbi) &&
 			fi->i_flags & F2FS_COMPR_FL &&
 			F2FS_FITS_IN_INODE(ri, fi->i_extra_isize,
 						i_log_cluster_size)) {
 		if (ri->i_compress_algorithm >= COMPRESS_MAX) {
+			set_sbi_flag(sbi, SBI_NEED_FSCK);
 			f2fs_warn(sbi, "%s: inode (ino=%lx) has unsupported "
 				"compress algorithm: %u, run fsck to fix",
 				  __func__, inode->i_ino,
@@ -300,6 +308,7 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
 		}
 		if (le64_to_cpu(ri->i_compr_blocks) >
 				SECTOR_TO_BLOCK(inode->i_blocks)) {
+			set_sbi_flag(sbi, SBI_NEED_FSCK);
 			f2fs_warn(sbi, "%s: inode (ino=%lx) has inconsistent "
 				"i_compr_blocks:%llu, i_blocks:%llu, run fsck to fix",
 				  __func__, inode->i_ino,
@@ -309,6 +318,7 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
 		}
 		if (ri->i_log_cluster_size < MIN_COMPRESS_LOG_SIZE ||
 			ri->i_log_cluster_size > MAX_COMPRESS_LOG_SIZE) {
+			set_sbi_flag(sbi, SBI_NEED_FSCK);
 			f2fs_warn(sbi, "%s: inode (ino=%lx) has unsupported "
 				"log cluster size: %u, run fsck to fix",
 				  __func__, inode->i_ino,
@@ -442,7 +452,8 @@ static int do_read_inode(struct inode *inode)
 					(fi->i_flags & F2FS_COMPR_FL)) {
 		if (F2FS_FITS_IN_INODE(ri, fi->i_extra_isize,
 					i_log_cluster_size)) {
-			fi->i_compr_blocks = le64_to_cpu(ri->i_compr_blocks);
+			atomic_set(&fi->i_compr_blocks,
+					le64_to_cpu(ri->i_compr_blocks));
 			fi->i_compress_algorithm = ri->i_compress_algorithm;
 			fi->i_log_cluster_size = ri->i_log_cluster_size;
 			fi->i_cluster_size = 1 << fi->i_log_cluster_size;
@@ -460,7 +471,7 @@ static int do_read_inode(struct inode *inode)
 	stat_inc_inline_inode(inode);
 	stat_inc_inline_dir(inode);
 	stat_inc_compr_inode(inode);
-	stat_add_compr_blocks(inode, F2FS_I(inode)->i_compr_blocks);
+	stat_add_compr_blocks(inode, atomic_read(&fi->i_compr_blocks));
 
 	return 0;
 }
@@ -619,7 +630,8 @@ void f2fs_update_inode(struct inode *inode, struct page *node_page)
 			F2FS_FITS_IN_INODE(ri, F2FS_I(inode)->i_extra_isize,
 							i_log_cluster_size)) {
 			ri->i_compr_blocks =
-				cpu_to_le64(F2FS_I(inode)->i_compr_blocks);
+				cpu_to_le64(atomic_read(
+					&F2FS_I(inode)->i_compr_blocks));
 			ri->i_compress_algorithm =
 				F2FS_I(inode)->i_compress_algorithm;
 			ri->i_log_cluster_size =
@@ -768,7 +780,8 @@ void f2fs_evict_inode(struct inode *inode)
 	stat_dec_inline_dir(inode);
 	stat_dec_inline_inode(inode);
 	stat_dec_compr_inode(inode);
-	stat_sub_compr_blocks(inode, F2FS_I(inode)->i_compr_blocks);
+	stat_sub_compr_blocks(inode,
+			atomic_read(&F2FS_I(inode)->i_compr_blocks));
 
 	if (likely(!f2fs_cp_error(sbi) &&
 				!is_sbi_flag_set(sbi, SBI_CP_DISABLED)))

fs/f2fs/namei.c

@@ -712,7 +712,7 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
 	f2fs_handle_failed_inode(inode);
 out_free_encrypted_link:
 	if (disk_link.name != (unsigned char *)symname)
-		kvfree(disk_link.name);
+		kfree(disk_link.name);
 	return err;
 }
 

fs/f2fs/node.c

@@ -109,7 +109,7 @@ static void clear_node_page_dirty(struct page *page)
 
 static struct page *get_current_nat_page(struct f2fs_sb_info *sbi, nid_t nid)
 {
-	return f2fs_get_meta_page_nofail(sbi, current_nat_addr(sbi, nid));
+	return f2fs_get_meta_page(sbi, current_nat_addr(sbi, nid));
 }
 
 static struct page *get_next_nat_page(struct f2fs_sb_info *sbi, nid_t nid)
@@ -3105,9 +3105,6 @@ static int init_node_manager(struct f2fs_sb_info *sbi)
 	nm_i->next_scan_nid = le32_to_cpu(sbi->ckpt->next_free_nid);
 	nm_i->bitmap_size = __bitmap_size(sbi, NAT_BITMAP);
 	version_bitmap = __bitmap_ptr(sbi, NAT_BITMAP);
-	if (!version_bitmap)
-		return -EFAULT;
-
 	nm_i->nat_bitmap = kmemdup(version_bitmap, nm_i->bitmap_size,
 					GFP_KERNEL);
 	if (!nm_i->nat_bitmap)
@@ -3257,7 +3254,7 @@ void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi)
 	kvfree(nm_i->nat_bitmap_mir);
 #endif
 	sbi->nm_info = NULL;
-	kvfree(nm_i);
+	kfree(nm_i);
 }
 
 int __init f2fs_create_node_manager_caches(void)

fs/f2fs/segment.h

@@ -16,13 +16,20 @@
 #define DEF_MAX_RECLAIM_PREFREE_SEGMENTS	4096	/* 8GB in maximum */
 
 #define F2FS_MIN_SEGMENTS	9 /* SB + 2 (CP + SIT + NAT) + SSA + MAIN */
+#define F2FS_MIN_META_SEGMENTS	8 /* SB + 2 (CP + SIT + NAT) + SSA */
 
 /* 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)
 
 #define IS_DATASEG(t)	((t) <= CURSEG_COLD_DATA)
-#define IS_NODESEG(t)	((t) >= CURSEG_HOT_NODE)
+#define IS_NODESEG(t)	((t) >= CURSEG_HOT_NODE && (t) <= CURSEG_COLD_NODE)
+
+static inline void sanity_check_seg_type(struct f2fs_sb_info *sbi,
+						unsigned short seg_type)
+{
+	f2fs_bug_on(sbi, seg_type >= NR_PERSISTENT_LOG);
+}
 
 #define IS_HOT(t)	((t) == CURSEG_HOT_NODE || (t) == CURSEG_HOT_DATA)
 #define IS_WARM(t)	((t) == CURSEG_WARM_NODE || (t) == CURSEG_WARM_DATA)
@@ -34,7 +41,9 @@
 	 ((seg) == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno) ||	\
 	 ((seg) == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno) ||	\
 	 ((seg) == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno) ||	\
-	 ((seg) == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno))
+	 ((seg) == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno) ||	\
+	 ((seg) == CURSEG_I(sbi, CURSEG_COLD_DATA_PINNED)->segno) ||	\
+	 ((seg) == CURSEG_I(sbi, CURSEG_ALL_DATA_ATGC)->segno))
 
 #define IS_CURSEC(sbi, secno)						\
 	(((secno) == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno /		\
@@ -48,7 +57,11 @@
 	 ((secno) == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno /		\
 	  (sbi)->segs_per_sec) ||	\
 	 ((secno) == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno /		\
-	  (sbi)->segs_per_sec))	\
+	  (sbi)->segs_per_sec) ||	\
+	 ((secno) == CURSEG_I(sbi, CURSEG_COLD_DATA_PINNED)->segno /	\
+	  (sbi)->segs_per_sec) ||	\
+	 ((secno) == CURSEG_I(sbi, CURSEG_ALL_DATA_ATGC)->segno /	\
+	  (sbi)->segs_per_sec))
 
 #define MAIN_BLKADDR(sbi)						\
 	(SM_I(sbi) ? SM_I(sbi)->main_blkaddr : 				\
@@ -132,20 +145,25 @@ enum {
  * In the victim_sel_policy->alloc_mode, there are two block allocation modes.
  * LFS writes data sequentially with cleaning operations.
  * SSR (Slack Space Recycle) reuses obsolete space without cleaning operations.
+ * AT_SSR (Age Threshold based Slack Space Recycle) merges fragments into
+ * fragmented segment which has similar aging degree.
  */
 enum {
 	LFS = 0,
-	SSR
+	SSR,
+	AT_SSR,
 };
 
 /*
  * In the victim_sel_policy->gc_mode, there are two gc, aka cleaning, modes.
  * GC_CB is based on cost-benefit algorithm.
  * GC_GREEDY is based on greedy algorithm.
+ * GC_AT is based on age-threshold algorithm.
  */
 enum {
 	GC_CB = 0,
 	GC_GREEDY,
+	GC_AT,
 	ALLOC_NEXT,
 	FLUSH_DEVICE,
 	MAX_GC_POLICY,
@@ -174,7 +192,10 @@ struct victim_sel_policy {
 	unsigned int offset;		/* last scanned bitmap offset */
 	unsigned int ofs_unit;		/* bitmap search unit */
 	unsigned int min_cost;		/* minimum cost */
+	unsigned long long oldest_age;	/* oldest age of segments having the same min cost */
 	unsigned int min_segno;		/* segment # having min. cost */
+	unsigned long long age;		/* mtime of GCed section*/
+	unsigned long long age_threshold;/* age threshold */
 };
 
 struct seg_entry {
@@ -240,6 +261,8 @@ struct sit_info {
 	unsigned long long mounted_time;	/* mount time */
 	unsigned long long min_mtime;		/* min. modification time */
 	unsigned long long max_mtime;		/* max. modification time */
+	unsigned long long dirty_min_mtime;	/* rerange candidates in GC_AT */
+	unsigned long long dirty_max_mtime;	/* rerange candidates in GC_AT */
 
 	unsigned int last_victim[MAX_GC_POLICY]; /* last victim segment # */
 };
@@ -278,7 +301,7 @@ struct dirty_seglist_info {
 /* victim selection function for cleaning and SSR */
 struct victim_selection {
 	int (*get_victim)(struct f2fs_sb_info *, unsigned int *,
-							int, int, char);
+					int, int, char, unsigned long long);
 };
 
 /* for active log information */
@@ -288,10 +311,12 @@ struct curseg_info {
 	struct rw_semaphore journal_rwsem;	/* protect journal area */
 	struct f2fs_journal *journal;		/* cached journal info */
 	unsigned char alloc_type;		/* current allocation type */
+	unsigned short seg_type;		/* segment type like CURSEG_XXX_TYPE */
 	unsigned int segno;			/* current segment number */
 	unsigned short next_blkoff;		/* next block offset to write */
 	unsigned int zone;			/* current zone number */
 	unsigned int next_segno;		/* preallocated segment */
+	bool inited;				/* indicate inmem log is inited */
 };
 
 struct sit_entry_set {
@@ -305,8 +330,6 @@ struct sit_entry_set {
  */
 static inline struct curseg_info *CURSEG_I(struct f2fs_sb_info *sbi, int type)
 {
-	if (type == CURSEG_COLD_DATA_PINNED)
-		type = CURSEG_COLD_DATA;
 	return (struct curseg_info *)(SM_I(sbi)->curseg_array + type);
 }
 
@@ -411,6 +434,7 @@ static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno)
 	unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
 	unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno);
 	unsigned int next;
+	unsigned int usable_segs = f2fs_usable_segs_in_sec(sbi, segno);
 
 	spin_lock(&free_i->segmap_lock);
 	clear_bit(segno, free_i->free_segmap);
@@ -418,7 +442,7 @@ static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno)
 
 	next = find_next_bit(free_i->free_segmap,
 			start_segno + sbi->segs_per_sec, start_segno);
-	if (next >= start_segno + sbi->segs_per_sec) {
+	if (next >= start_segno + usable_segs) {
 		clear_bit(secno, free_i->free_secmap);
 		free_i->free_sections++;
 	}
@@ -438,22 +462,23 @@ static inline void __set_inuse(struct f2fs_sb_info *sbi,
 }
 
 static inline void __set_test_and_free(struct f2fs_sb_info *sbi,
-		unsigned int segno)
+		unsigned int segno, bool inmem)
 {
 	struct free_segmap_info *free_i = FREE_I(sbi);
 	unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
 	unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno);
 	unsigned int next;
+	unsigned int usable_segs = f2fs_usable_segs_in_sec(sbi, segno);
 
 	spin_lock(&free_i->segmap_lock);
 	if (test_and_clear_bit(segno, free_i->free_segmap)) {
 		free_i->free_segments++;
 
-		if (IS_CURSEC(sbi, secno))
+		if (!inmem && IS_CURSEC(sbi, secno))
 			goto skip_free;
 		next = find_next_bit(free_i->free_segmap,
 				start_segno + sbi->segs_per_sec, start_segno);
-		if (next >= start_segno + sbi->segs_per_sec) {
+		if (next >= start_segno + usable_segs) {
 			if (test_and_clear_bit(secno, free_i->free_secmap))
 				free_i->free_sections++;
 		}
@@ -500,7 +525,7 @@ static inline unsigned int free_segments(struct f2fs_sb_info *sbi)
 	return FREE_I(sbi)->free_segments;
 }
 
-static inline int reserved_segments(struct f2fs_sb_info *sbi)
+static inline unsigned int reserved_segments(struct f2fs_sb_info *sbi)
 {
 	return SM_I(sbi)->reserved_segments;
 }
@@ -532,7 +557,7 @@ static inline int overprovision_segments(struct f2fs_sb_info *sbi)
 
 static inline int reserved_sections(struct f2fs_sb_info *sbi)
 {
-	return GET_SEC_FROM_SEG(sbi, (unsigned int)reserved_segments(sbi));
+	return GET_SEC_FROM_SEG(sbi, reserved_segments(sbi));
 }
 
 static inline bool has_curseg_enough_space(struct f2fs_sb_info *sbi)
@@ -546,8 +571,8 @@ static inline bool has_curseg_enough_space(struct f2fs_sb_info *sbi)
 	/* check current node segment */
 	for (i = CURSEG_HOT_NODE; i <= CURSEG_COLD_NODE; i++) {
 		segno = CURSEG_I(sbi, i)->segno;
-		left_blocks = sbi->blocks_per_seg -
-			get_seg_entry(sbi, segno)->ckpt_valid_blocks;
+		left_blocks = f2fs_usable_blks_in_seg(sbi, segno) -
+				get_seg_entry(sbi, segno)->ckpt_valid_blocks;
 
 		if (node_blocks > left_blocks)
 			return false;
@@ -555,7 +580,7 @@ static inline bool has_curseg_enough_space(struct f2fs_sb_info *sbi)
 
 	/* check current data segment */
 	segno = CURSEG_I(sbi, CURSEG_HOT_DATA)->segno;
-	left_blocks = sbi->blocks_per_seg -
+	left_blocks = f2fs_usable_blks_in_seg(sbi, segno) -
 			get_seg_entry(sbi, segno)->ckpt_valid_blocks;
 	if (dent_blocks > left_blocks)
 		return false;
@@ -677,21 +702,22 @@ static inline int check_block_count(struct f2fs_sb_info *sbi,
 	bool is_valid  = test_bit_le(0, raw_sit->valid_map) ? true : false;
 	int valid_blocks = 0;
 	int cur_pos = 0, next_pos;
+	unsigned int usable_blks_per_seg = f2fs_usable_blks_in_seg(sbi, segno);
 
 	/* check bitmap with valid block count */
 	do {
 		if (is_valid) {
 			next_pos = find_next_zero_bit_le(&raw_sit->valid_map,
-					sbi->blocks_per_seg,
+					usable_blks_per_seg,
 					cur_pos);
 			valid_blocks += next_pos - cur_pos;
 		} else
 			next_pos = find_next_bit_le(&raw_sit->valid_map,
-					sbi->blocks_per_seg,
+					usable_blks_per_seg,
 					cur_pos);
 		cur_pos = next_pos;
 		is_valid = !is_valid;
-	} while (cur_pos < sbi->blocks_per_seg);
+	} while (cur_pos < usable_blks_per_seg);
 
 	if (unlikely(GET_SIT_VBLOCKS(raw_sit) != valid_blocks)) {
 		f2fs_err(sbi, "Mismatch valid blocks %d vs. %d",
@@ -700,8 +726,13 @@ static inline int check_block_count(struct f2fs_sb_info *sbi,
 		return -EFSCORRUPTED;
 	}
 
+	if (usable_blks_per_seg < sbi->blocks_per_seg)
+		f2fs_bug_on(sbi, find_next_bit_le(&raw_sit->valid_map,
+				sbi->blocks_per_seg,
+				usable_blks_per_seg) != sbi->blocks_per_seg);
+
 	/* check segment usage, and check boundary of a given segment number */
-	if (unlikely(GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg
+	if (unlikely(GET_SIT_VBLOCKS(raw_sit) > usable_blks_per_seg
 					|| segno > TOTAL_SEGS(sbi) - 1)) {
 		f2fs_err(sbi, "Wrong valid blocks %d or segno %u",
 			 GET_SIT_VBLOCKS(raw_sit), segno);

fs/f2fs/sysfs.c

@@ -176,12 +176,14 @@ static ssize_t encoding_show(struct f2fs_attr *a,
 		struct f2fs_sb_info *sbi, char *buf)
 {
 #ifdef CONFIG_UNICODE
+	struct super_block *sb = sbi->sb;
+
 	if (f2fs_sb_has_casefold(sbi))
 		return snprintf(buf, PAGE_SIZE, "%s (%d.%d.%d)\n",
-			sbi->s_encoding->charset,
-			(sbi->s_encoding->version >> 16) & 0xff,
-			(sbi->s_encoding->version >> 8) & 0xff,
-			sbi->s_encoding->version & 0xff);
+			sb->s_encoding->charset,
+			(sb->s_encoding->version >> 16) & 0xff,
+			(sb->s_encoding->version >> 8) & 0xff,
+			sb->s_encoding->version & 0xff);
 #endif
 	return sprintf(buf, "(none)");
 }
@@ -375,12 +377,17 @@ static ssize_t __sbi_store(struct f2fs_attr *a,
 		return count;
 	}
 	if (!strcmp(a->attr.name, "gc_idle")) {
-		if (t == GC_IDLE_CB)
+		if (t == GC_IDLE_CB) {
 			sbi->gc_mode = GC_IDLE_CB;
-		else if (t == GC_IDLE_GREEDY)
+		} else if (t == GC_IDLE_GREEDY) {
 			sbi->gc_mode = GC_IDLE_GREEDY;
-		else
+		} else if (t == GC_IDLE_AT) {
+			if (!sbi->am.atgc_enabled)
+				return -EINVAL;
+			sbi->gc_mode = GC_AT;
+		} else {
 			sbi->gc_mode = GC_NORMAL;
+		}
 		return count;
 	}
 
@@ -968,4 +975,5 @@ void f2fs_unregister_sysfs(struct f2fs_sb_info *sbi)
 	}
 	kobject_del(&sbi->s_kobj);
 	kobject_put(&sbi->s_kobj);
+	wait_for_completion(&sbi->s_kobj_unregister);
 }

fs/f2fs/xattr.c

@@ -39,7 +39,7 @@ static void xattr_free(struct f2fs_sb_info *sbi, void *xattr_addr,
 	if (is_inline)
 		kmem_cache_free(sbi->inline_xattr_slab, xattr_addr);
 	else
-		kvfree(xattr_addr);
+		kfree(xattr_addr);
 }
 
 static int f2fs_xattr_generic_get(const struct xattr_handler *handler,
@@ -425,7 +425,7 @@ static int read_all_xattrs(struct inode *inode, struct page *ipage,
 	*base_addr = txattr_addr;
 	return 0;
 fail:
-	kvfree(txattr_addr);
+	kfree(txattr_addr);
 	return err;
 }
 
@@ -610,7 +610,7 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
 	}
 	error = buffer_size - rest;
 cleanup:
-	kvfree(base_addr);
+	kfree(base_addr);
 	return error;
 }
 
@@ -750,7 +750,7 @@ static int __f2fs_setxattr(struct inode *inode, int index,
 	if (!error && S_ISDIR(inode->i_mode))
 		set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_CP);
 exit:
-	kvfree(base_addr);
+	kfree(base_addr);
 	return error;
 }
 

fs/libfs.c

@@ -20,6 +20,8 @@
 #include <linux/fs_context.h>
 #include <linux/pseudo_fs.h>
 #include <linux/fsnotify.h>
+#include <linux/unicode.h>
+#include <linux/fscrypt.h>
 
 #include <linux/uaccess.h>
 
@@ -1363,3 +1365,88 @@ bool is_empty_dir_inode(struct inode *inode)
 	return (inode->i_fop == &empty_dir_operations) &&
 		(inode->i_op == &empty_dir_inode_operations);
 }
+
+#ifdef CONFIG_UNICODE
+/*
+ * Determine if the name of a dentry should be casefolded.
+ *
+ * Return: if names will need casefolding
+ */
+static bool needs_casefold(const struct inode *dir)
+{
+	return IS_CASEFOLDED(dir) && dir->i_sb->s_encoding;
+}
+
+/**
+ * generic_ci_d_compare - generic d_compare implementation for casefolding filesystems
+ * @dentry:	dentry whose name we are checking against
+ * @len:	len of name of dentry
+ * @str:	str pointer to name of dentry
+ * @name:	Name to compare against
+ *
+ * Return: 0 if names match, 1 if mismatch, or -ERRNO
+ */
+int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
+			  const char *str, const struct qstr *name)
+{
+	const struct dentry *parent = READ_ONCE(dentry->d_parent);
+	const struct inode *dir = READ_ONCE(parent->d_inode);
+	const struct super_block *sb = dentry->d_sb;
+	const struct unicode_map *um = sb->s_encoding;
+	struct qstr qstr = QSTR_INIT(str, len);
+	char strbuf[DNAME_INLINE_LEN];
+	int ret;
+
+	if (!dir || !needs_casefold(dir))
+		goto fallback;
+	/*
+	 * If the dentry name is stored in-line, then it may be concurrently
+	 * modified by a rename.  If this happens, the VFS will eventually retry
+	 * the lookup, so it doesn't matter what ->d_compare() returns.
+	 * However, it's unsafe to call utf8_strncasecmp() with an unstable
+	 * string.  Therefore, we have to copy the name into a temporary buffer.
+	 */
+	if (len <= DNAME_INLINE_LEN - 1) {
+		memcpy(strbuf, str, len);
+		strbuf[len] = 0;
+		qstr.name = strbuf;
+		/* prevent compiler from optimizing out the temporary buffer */
+		barrier();
+	}
+	ret = utf8_strncasecmp(um, name, &qstr);
+	if (ret >= 0)
+		return ret;
+
+	if (sb_has_strict_encoding(sb))
+		return -EINVAL;
+fallback:
+	if (len != name->len)
+		return 1;
+	return !!memcmp(str, name->name, len);
+}
+EXPORT_SYMBOL(generic_ci_d_compare);
+
+/**
+ * generic_ci_d_hash - generic d_hash implementation for casefolding filesystems
+ * @dentry:	dentry of the parent directory
+ * @str:	qstr of name whose hash we should fill in
+ *
+ * Return: 0 if hash was successful or unchanged, and -EINVAL on error
+ */
+int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str)
+{
+	const struct inode *dir = READ_ONCE(dentry->d_inode);
+	struct super_block *sb = dentry->d_sb;
+	const struct unicode_map *um = sb->s_encoding;
+	int ret = 0;
+
+	if (!dir || !needs_casefold(dir))
+		return 0;
+
+	ret = utf8_casefold_hash(um, dentry, str);
+	if (ret < 0 && sb_has_strict_encoding(sb))
+		return -EINVAL;
+	return 0;
+}
+EXPORT_SYMBOL(generic_ci_d_hash);
+#endif

fs/unicode/utf8-core.c

@@ -6,6 +6,7 @@
 #include <linux/parser.h>
 #include <linux/errno.h>
 #include <linux/unicode.h>
+#include <linux/stringhash.h>
 
 #include "utf8n.h"
 
@@ -122,9 +123,29 @@ int utf8_casefold(const struct unicode_map *um, const struct qstr *str,
 	}
 	return -EINVAL;
 }
-
 EXPORT_SYMBOL(utf8_casefold);
 
+int utf8_casefold_hash(const struct unicode_map *um, const void *salt,
+		       struct qstr *str)
+{
+	const struct utf8data *data = utf8nfdicf(um->version);
+	struct utf8cursor cur;
+	int c;
+	unsigned long hash = init_name_hash(salt);
+
+	if (utf8ncursor(&cur, data, str->name, str->len) < 0)
+		return -EINVAL;
+
+	while ((c = utf8byte(&cur))) {
+		if (c < 0)
+			return -EINVAL;
+		hash = partial_name_hash((unsigned char)c, hash);
+	}
+	str->hash = end_name_hash(hash);
+	return 0;
+}
+EXPORT_SYMBOL(utf8_casefold_hash);
+
 int utf8_normalize(const struct unicode_map *um, const struct qstr *str,
 		   unsigned char *dest, size_t dlen)
 {

include/linux/f2fs_fs.h

@@ -38,9 +38,6 @@
 #define F2FS_MAX_QUOTAS		3
 
 #define F2FS_ENC_UTF8_12_1	1
-#define F2FS_ENC_STRICT_MODE_FL	(1 << 0)
-#define f2fs_has_strict_mode(sbi) \
-	(sbi->s_encoding_flags & F2FS_ENC_STRICT_MODE_FL)
 
 #define F2FS_IO_SIZE(sbi)	(1 << F2FS_OPTION(sbi).write_io_size_bits) /* Blocks */
 #define F2FS_IO_SIZE_KB(sbi)	(1 << (F2FS_OPTION(sbi).write_io_size_bits + 2)) /* KB */

include/linux/fs.h

@@ -1366,6 +1366,12 @@ extern int send_sigurg(struct fown_struct *fown);
 #define SB_ACTIVE	(1<<30)
 #define SB_NOUSER	(1<<31)
 
+/* These flags relate to encoding and casefolding */
+#define SB_ENC_STRICT_MODE_FL	(1 << 0)
+
+#define sb_has_strict_encoding(sb) \
+	(sb->s_encoding_flags & SB_ENC_STRICT_MODE_FL)
+
 /*
  *	Umount options
  */
@@ -1435,6 +1441,10 @@ struct super_block {
 #endif
 #ifdef CONFIG_FS_VERITY
 	const struct fsverity_operations *s_vop;
+#endif
+#ifdef CONFIG_UNICODE
+	struct unicode_map *s_encoding;
+	__u16 s_encoding_flags;
 #endif
 	struct hlist_bl_head	s_roots;	/* alternate root dentries for NFS */
 	struct list_head	s_mounts;	/* list of mounts; _not_ for fs use */
@@ -3189,6 +3199,12 @@ extern int generic_file_fsync(struct file *, loff_t, loff_t, int);
 
 extern int generic_check_addressable(unsigned, u64);
 
+#ifdef CONFIG_UNICODE
+extern int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str);
+extern int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
+				const char *str, const struct qstr *name);
+#endif
+
 #ifdef CONFIG_MIGRATION
 extern int buffer_migrate_page(struct address_space *,
 				struct page *, struct page *,

include/linux/unicode.h

@@ -27,6 +27,9 @@ int utf8_normalize(const struct unicode_map *um, const struct qstr *str,
 int utf8_casefold(const struct unicode_map *um, const struct qstr *str,
 		  unsigned char *dest, size_t dlen);
 
+int utf8_casefold_hash(const struct unicode_map *um, const void *salt,
+		       struct qstr *str);
+
 struct unicode_map *utf8_load(const char *version);
 void utf8_unload(struct unicode_map *um);
 

include/trace/events/f2fs.h

@@ -111,13 +111,15 @@ TRACE_DEFINE_ENUM(CP_RESIZE);
 
 #define show_alloc_mode(type)						\
 	__print_symbolic(type,						\
-		{ LFS,	"LFS-mode" },					\
-		{ SSR,	"SSR-mode" })
+		{ LFS,		"LFS-mode" },				\
+		{ SSR,		"SSR-mode" },				\
+		{ AT_SSR,	"AT_SSR-mode" })
 
 #define show_victim_policy(type)					\
 	__print_symbolic(type,						\
 		{ GC_GREEDY,	"Greedy" },				\
-		{ GC_CB,	"Cost-Benefit" })
+		{ GC_CB,	"Cost-Benefit" },			\
+		{ GC_AT,	"Age-threshold" })
 
 #define show_cpreason(type)						\
 	__print_flags(type, "|",					\
@@ -134,7 +136,7 @@ TRACE_DEFINE_ENUM(CP_RESIZE);
 	__print_symbolic(type,						\
 		{ CP_NO_NEEDED,		"no needed" },			\
 		{ CP_NON_REGULAR,	"non regular" },		\
-		{ CP_COMPRESSED,	"compreesed" },			\
+		{ CP_COMPRESSED,	"compressed" },			\
 		{ CP_HARDLINK,		"hardlink" },			\
 		{ CP_SB_NEED_CP,	"sb needs cp" },		\
 		{ CP_WRONG_PINO,	"wrong pino" },			\