f2fs-for-5.16-rc1

In this cycle, we've applied relatively small number of patches which fix subtle
 corner cases mainly, while introducing a new mount option to be able to fragment
 the disk intentionally for performance tests.
 
 Enhancement:
  - add a mount option to fragmente on-disk layout to understand the performance
  - support direct IO for multi-partitions
  - add a fault injection of dquot_initialize
 
 Bug fix:
  - address some lockdep complaints
  - fix a deadlock issue with quota
  - fix a memory tuning condition
  - fix compression condition to improve the ratio
  - fix disabling compression on the non-empty compressed file
  - invalidate cached pages before IPU/DIO writes
 
 And, we've added some minor clean-ups as usual.
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEE00UqedjCtOrGVvQiQBSofoJIUNIFAmGMILwACgkQQBSofoJI
 UNJDRA/+KPyCXdY0OqL26BuGKj+z7hW6bz7tlh6h3wdnPdsR/W3ehbqQEr3GBb+q
 yokmD75/in7vZwGsDHGowFWMAfWOHYEqHz5UAq91sHjhfZzLDNUgLFWJedBX2XJb
 UoEAa7KzRt9M9K2p/5vSTs07RN3okUiRkFhVBBQJIaL7xi6MpadN/XAqpyoBqsiP
 pAV6J3GF6WNF19P/hkN1CJI8rV+PFrvY6C23lMkP7mnsWh03jMSgDDuhLHMQpAba
 EJYq7QbSatsLDRdR+jUQwIfMucvvzN7M6ja9+NTGlbeACvND8vXKYXOwngCq9+je
 2PIU4J8zNqnEkLsPn8STm4zwZHCA7VFdeCobCZcaVZCZFBzVqCkVYE9wqFVaQmr1
 bCrRFvEb+D1pkHYFujVXwCAfPlO6twiAInFNMa3WQ3FduJq2nhc8OLCJJ46D1KT2
 ZzzLv2EIIlncxPvgLIhiEE9DgPOyV56PQAO3OTsBZcvycU32aHo4hyexju1ubKiD
 CZFEHLnPbxX8Ulh3NX4uUxqPAEVhM/aw4l4e8xhmVRY3uj75geY7M6rt1vD+Y5Et
 EwbUE8XbLy+GhqbbO/SX9G38pftOiIquH1J0RuhuVNNmkIDkQvnSNp8WqHTdjEJE
 NiHZ5bkRkii34Wfrax9UccqGDswh/gjHAXEfGD8nFfcQZwLP1n8=
 =KGQ3
 -----END PGP SIGNATURE-----

Merge tag 'f2fs-for-5.16-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this cycle, we've applied relatively small number of patches which
  fix subtle corner cases mainly, while introducing a new mount option
  to be able to fragment the disk intentionally for performance tests.

  Enhancements:

   - add a mount option to fragmente on-disk layout to understand the
     performance

   - support direct IO for multi-partitions

   - add a fault injection of dquot_initialize

  Bug fixes:

   - address some lockdep complaints

   - fix a deadlock issue with quota

   - fix a memory tuning condition

   - fix compression condition to improve the ratio

   - fix disabling compression on the non-empty compressed file

   - invalidate cached pages before IPU/DIO writes

  And, we've added some minor clean-ups as usual"

* tag 'f2fs-for-5.16-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs:
  f2fs: fix UAF in f2fs_available_free_memory
  f2fs: invalidate META_MAPPING before IPU/DIO write
  f2fs: support fault injection for dquot_initialize()
  f2fs: fix incorrect return value in f2fs_sanity_check_ckpt()
  f2fs: compress: disallow disabling compress on non-empty compressed file
  f2fs: compress: fix overwrite may reduce compress ratio unproperly
  f2fs: multidevice: support direct IO
  f2fs: introduce fragment allocation mode mount option
  f2fs: replace snprintf in show functions with sysfs_emit
  f2fs: include non-compressed blocks in compr_written_block
  f2fs: fix wrong condition to trigger background checkpoint correctly
  f2fs: fix to use WHINT_MODE
  f2fs: fix up f2fs_lookup tracepoints
  f2fs: set SBI_NEED_FSCK flag when inconsistent node block found
  f2fs: introduce excess_dirty_threshold()
  f2fs: avoid attaching SB_ACTIVE flag during mount
  f2fs: quota: fix potential deadlock
  f2fs: should use GFP_NOFS for directory inodes

Documentation/ABI/testing/sysfs-fs-f2fs

@@ -512,3 +512,19 @@ Date:		July 2021
 Contact:	"Daeho Jeong" <daehojeong@google.com>
 Description:	You can	control the multiplier value of	bdi device readahead window size
 		between 2 (default) and 256 for POSIX_FADV_SEQUENTIAL advise option.
+
+What:		/sys/fs/f2fs/<disk>/max_fragment_chunk
+Date:		August 2021
+Contact:	"Daeho Jeong" <daehojeong@google.com>
+Description:	With "mode=fragment:block" mount options, we can scatter block allocation.
+		f2fs will allocate 1..<max_fragment_chunk> blocks in a chunk and make a hole
+		in the length of 1..<max_fragment_hole> by turns. This value can be set
+		between 1..512 and the default value is 4.
+
+What:		/sys/fs/f2fs/<disk>/max_fragment_hole
+Date:		August 2021
+Contact:	"Daeho Jeong" <daehojeong@google.com>
+Description:	With "mode=fragment:block" mount options, we can scatter block allocation.
+		f2fs will allocate 1..<max_fragment_chunk> blocks in a chunk and make a hole
+		in the length of 1..<max_fragment_hole> by turns. This value can be set
+		between 1..512 and the default value is 4.

Documentation/filesystems/f2fs.rst

@@ -197,10 +197,29 @@ fault_type=%d		 Support configuring fault injection type, should be
 			 FAULT_DISCARD		  0x000002000
 			 FAULT_WRITE_IO		  0x000004000
 			 FAULT_SLAB_ALLOC	  0x000008000
+			 FAULT_DQUOT_INIT	  0x000010000
 			 ===================	  ===========
 mode=%s			 Control block allocation mode which supports "adaptive"
 			 and "lfs". In "lfs" mode, there should be no random
 			 writes towards main area.
+			 "fragment:segment" and "fragment:block" are newly added here.
+			 These are developer options for experiments to simulate filesystem
+			 fragmentation/after-GC situation itself. The developers use these
+			 modes to understand filesystem fragmentation/after-GC condition well,
+			 and eventually get some insights to handle them better.
+			 In "fragment:segment", f2fs allocates a new segment in ramdom
+			 position. With this, we can simulate the after-GC condition.
+			 In "fragment:block", we can scatter block allocation with
+			 "max_fragment_chunk" and "max_fragment_hole" sysfs nodes.
+			 We added some randomness to both chunk and hole size to make
+			 it close to realistic IO pattern. So, in this mode, f2fs will allocate
+			 1..<max_fragment_chunk> blocks in a chunk and make a hole in the
+			 length of 1..<max_fragment_hole> by turns. With this, the newly
+			 allocated blocks will be scattered throughout the whole partition.
+			 Note that "fragment:block" implicitly enables "fragment:segment"
+			 option for more randomness.
+			 Please, use these options for your experiments and we strongly
+			 recommend to re-format the filesystem after using these options.
 io_bits=%u		 Set the bit size of write IO requests. It should be set
 			 with "mode=lfs".
 usrquota		 Enable plain user disk quota accounting.

fs/f2fs/checkpoint.c

@@ -653,7 +653,7 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
 		return PTR_ERR(inode);
 	}
 
-	err = dquot_initialize(inode);
+	err = f2fs_dquot_initialize(inode);
 	if (err) {
 		iput(inode);
 		goto err_out;
@@ -705,9 +705,6 @@ int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi)
 	}
 
 #ifdef CONFIG_QUOTA
-	/* Needed for iput() to work correctly and not trash data */
-	sbi->sb->s_flags |= SB_ACTIVE;
-
 	/*
 	 * Turn on quotas which were not enabled for read-only mounts if
 	 * filesystem has quota feature, so that they are updated correctly.
@@ -1162,7 +1159,8 @@ static bool __need_flush_quota(struct f2fs_sb_info *sbi)
 	if (!is_journalled_quota(sbi))
 		return false;
 
-	down_write(&sbi->quota_sem);
+	if (!down_write_trylock(&sbi->quota_sem))
+		return true;
 	if (is_sbi_flag_set(sbi, SBI_QUOTA_SKIP_FLUSH)) {
 		ret = false;
 	} else if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_REPAIR)) {

fs/f2fs/compress.c

@@ -882,6 +882,25 @@ bool f2fs_cluster_can_merge_page(struct compress_ctx *cc, pgoff_t index)
 	return is_page_in_cluster(cc, index);
 }
 
+bool f2fs_all_cluster_page_loaded(struct compress_ctx *cc, struct pagevec *pvec,
+				int index, int nr_pages)
+{
+	unsigned long pgidx;
+	int i;
+
+	if (nr_pages - index < cc->cluster_size)
+		return false;
+
+	pgidx = pvec->pages[index]->index;
+
+	for (i = 1; i < cc->cluster_size; i++) {
+		if (pvec->pages[index + i]->index != pgidx + i)
+			return false;
+	}
+
+	return true;
+}
+
 static bool cluster_has_invalid_data(struct compress_ctx *cc)
 {
 	loff_t i_size = i_size_read(cc->inode);
@@ -1531,6 +1550,7 @@ int f2fs_write_multi_pages(struct compress_ctx *cc,
 	if (cluster_may_compress(cc)) {
 		err = f2fs_compress_pages(cc);
 		if (err == -EAGAIN) {
+			add_compr_block_stat(cc->inode, cc->cluster_size);
 			goto write;
 		} else if (err) {
 			f2fs_put_rpages_wbc(cc, wbc, true, 1);

fs/f2fs/data.c

@@ -1465,10 +1465,15 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
 	struct extent_info ei = {0, };
 	block_t blkaddr;
 	unsigned int start_pgofs;
+	int bidx = 0;
 
 	if (!maxblocks)
 		return 0;
 
+	map->m_bdev = inode->i_sb->s_bdev;
+	map->m_multidev_dio =
+		f2fs_allow_multi_device_dio(F2FS_I_SB(inode), flag);
+
 	map->m_len = 0;
 	map->m_flags = 0;
 
@@ -1491,6 +1496,21 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
 		if (flag == F2FS_GET_BLOCK_DIO)
 			f2fs_wait_on_block_writeback_range(inode,
 						map->m_pblk, map->m_len);
+
+		if (map->m_multidev_dio) {
+			block_t blk_addr = map->m_pblk;
+
+			bidx = f2fs_target_device_index(sbi, map->m_pblk);
+
+			map->m_bdev = FDEV(bidx).bdev;
+			map->m_pblk -= FDEV(bidx).start_blk;
+			map->m_len = min(map->m_len,
+				FDEV(bidx).end_blk + 1 - map->m_pblk);
+
+			if (map->m_may_create)
+				f2fs_update_device_state(sbi, inode->i_ino,
+							blk_addr, map->m_len);
+		}
 		goto out;
 	}
 
@@ -1609,6 +1629,9 @@ next_block:
 	if (flag == F2FS_GET_BLOCK_PRE_AIO)
 		goto skip;
 
+	if (map->m_multidev_dio)
+		bidx = f2fs_target_device_index(sbi, blkaddr);
+
 	if (map->m_len == 0) {
 		/* preallocated unwritten block should be mapped for fiemap. */
 		if (blkaddr == NEW_ADDR)
@@ -1617,10 +1640,15 @@ next_block:
 
 		map->m_pblk = blkaddr;
 		map->m_len = 1;
+
+		if (map->m_multidev_dio)
+			map->m_bdev = FDEV(bidx).bdev;
 	} else if ((map->m_pblk != NEW_ADDR &&
 			blkaddr == (map->m_pblk + ofs)) ||
 			(map->m_pblk == NEW_ADDR && blkaddr == NEW_ADDR) ||
 			flag == F2FS_GET_BLOCK_PRE_DIO) {
+		if (map->m_multidev_dio && map->m_bdev != FDEV(bidx).bdev)
+			goto sync_out;
 		ofs++;
 		map->m_len++;
 	} else {
@@ -1673,10 +1701,32 @@ skip:
 
 sync_out:
 
-	/* for hardware encryption, but to avoid potential issue in future */
+	if (flag == F2FS_GET_BLOCK_DIO && map->m_flags & F2FS_MAP_MAPPED) {
-	if (flag == F2FS_GET_BLOCK_DIO && map->m_flags & F2FS_MAP_MAPPED)
+		/*
+		 * for hardware encryption, but to avoid potential issue
+		 * in future
+		 */
 		f2fs_wait_on_block_writeback_range(inode,
 						map->m_pblk, map->m_len);
+		invalidate_mapping_pages(META_MAPPING(sbi),
+						map->m_pblk, map->m_pblk);
+
+		if (map->m_multidev_dio) {
+			block_t blk_addr = map->m_pblk;
+
+			bidx = f2fs_target_device_index(sbi, map->m_pblk);
+
+			map->m_bdev = FDEV(bidx).bdev;
+			map->m_pblk -= FDEV(bidx).start_blk;
+
+			if (map->m_may_create)
+				f2fs_update_device_state(sbi, inode->i_ino,
+							blk_addr, map->m_len);
+
+			f2fs_bug_on(sbi, blk_addr + map->m_len >
+						FDEV(bidx).end_blk + 1);
+		}
+	}
 
 	if (flag == F2FS_GET_BLOCK_PRECACHE) {
 		if (map->m_flags & F2FS_MAP_MAPPED) {
@@ -1696,7 +1746,7 @@ unlock_out:
 		f2fs_balance_fs(sbi, dn.node_changed);
 	}
 out:
-	trace_f2fs_map_blocks(inode, map, err);
+	trace_f2fs_map_blocks(inode, map, create, flag, err);
 	return err;
 }
 
@@ -1755,6 +1805,9 @@ static int __get_data_block(struct inode *inode, sector_t iblock,
 		map_bh(bh, inode->i_sb, map.m_pblk);
 		bh->b_state = (bh->b_state & ~F2FS_MAP_FLAGS) | map.m_flags;
 		bh->b_size = blks_to_bytes(inode, map.m_len);
+
+		if (map.m_multidev_dio)
+			bh->b_bdev = map.m_bdev;
 	}
 	return err;
 }
@@ -2989,6 +3042,10 @@ readd:
 			need_readd = false;
 #ifdef CONFIG_F2FS_FS_COMPRESSION
 			if (f2fs_compressed_file(inode)) {
+				void *fsdata = NULL;
+				struct page *pagep;
+				int ret2;
+
 				ret = f2fs_init_compress_ctx(&cc);
 				if (ret) {
 					done = 1;
@@ -3007,27 +3064,23 @@ readd:
 				if (unlikely(f2fs_cp_error(sbi)))
 					goto lock_page;
 
-				if (f2fs_cluster_is_empty(&cc)) {
+				if (!f2fs_cluster_is_empty(&cc))
-					void *fsdata = NULL;
+					goto lock_page;
-					struct page *pagep;
-					int ret2;
 
-					ret2 = f2fs_prepare_compress_overwrite(
+				ret2 = f2fs_prepare_compress_overwrite(
 							inode, &pagep,
 							page->index, &fsdata);
-					if (ret2 < 0) {
+				if (ret2 < 0) {
-						ret = ret2;
+					ret = ret2;
-						done = 1;
+					done = 1;
-						break;
+					break;
-					} else if (ret2 &&
+				} else if (ret2 &&
-						!f2fs_compress_write_end(inode,
+					(!f2fs_compress_write_end(inode,
-								fsdata, page->index,
+						fsdata, page->index, 1) ||
-								1)) {
+					 !f2fs_all_cluster_page_loaded(&cc,
-						retry = 1;
+						&pvec, i, nr_pages))) {
-						break;
+					retry = 1;
-					}
+					break;
-				} else {
-					goto lock_page;
 				}
 			}
 #endif

fs/f2fs/f2fs.h

@@ -55,6 +55,7 @@ enum {
 	FAULT_DISCARD,
 	FAULT_WRITE_IO,
 	FAULT_SLAB_ALLOC,
+	FAULT_DQUOT_INIT,
 	FAULT_MAX,
 };
 
@@ -561,6 +562,9 @@ enum {
 
 #define MAX_DIR_RA_PAGES	4	/* maximum ra pages of dir */
 
+/* dirty segments threshold for triggering CP */
+#define DEFAULT_DIRTY_THRESHOLD		4
+
 /* for in-memory extent cache entry */
 #define F2FS_MIN_EXTENT_LEN	64	/* minimum extent length */
 
@@ -617,6 +621,7 @@ struct extent_tree {
 				F2FS_MAP_UNWRITTEN)
 
 struct f2fs_map_blocks {
+	struct block_device *m_bdev;	/* for multi-device dio */
 	block_t m_pblk;
 	block_t m_lblk;
 	unsigned int m_len;
@@ -625,6 +630,7 @@ struct f2fs_map_blocks {
 	pgoff_t *m_next_extent;		/* point to next possible extent */
 	int m_seg_type;
 	bool m_may_create;		/* indicate it is from write path */
+	bool m_multidev_dio;		/* indicate it allows multi-device dio */
 };
 
 /* for flag in get_data_block */
@@ -1284,8 +1290,10 @@ enum {
 };
 
 enum {
-	FS_MODE_ADAPTIVE,	/* use both lfs/ssr allocation */
+	FS_MODE_ADAPTIVE,		/* use both lfs/ssr allocation */
-	FS_MODE_LFS,		/* use lfs allocation only */
+	FS_MODE_LFS,			/* use lfs allocation only */
+	FS_MODE_FRAGMENT_SEG,		/* segment fragmentation mode */
+	FS_MODE_FRAGMENT_BLK,		/* block fragmentation mode */
 };
 
 enum {
@@ -1728,12 +1736,15 @@ struct f2fs_sb_info {
 
 	/* For shrinker support */
 	struct list_head s_list;
+	struct mutex umount_mutex;
+	unsigned int shrinker_run_no;
+
+	/* For multi devices */
 	int s_ndevs;				/* number of devices */
 	struct f2fs_dev_info *devs;		/* for device list */
 	unsigned int dirty_device;		/* for checkpoint data flush */
 	spinlock_t dev_lock;			/* protect dirty_device */
-	struct mutex umount_mutex;
+	bool aligned_blksize;			/* all devices has the same logical blksize */
-	unsigned int shrinker_run_no;
 
 	/* For write statistics */
 	u64 sectors_written_start;
@@ -1756,6 +1767,9 @@ struct f2fs_sb_info {
 
 	unsigned long seq_file_ra_mul;		/* multiplier for ra_pages of seq. files in fadvise */
 
+	int max_fragment_chunk;			/* max chunk size for block fragmentation mode */
+	int max_fragment_hole;			/* max hole size for block fragmentation mode */
+
 #ifdef CONFIG_F2FS_FS_COMPRESSION
 	struct kmem_cache *page_array_slab;	/* page array entry */
 	unsigned int page_array_slab_size;	/* default page array slab size */
@@ -3363,6 +3377,7 @@ static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode)
  */
 int f2fs_inode_dirtied(struct inode *inode, bool sync);
 void f2fs_inode_synced(struct inode *inode);
+int f2fs_dquot_initialize(struct inode *inode);
 int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly);
 int f2fs_quota_sync(struct super_block *sb, int type);
 loff_t max_file_blocks(struct inode *inode);
@@ -3492,6 +3507,8 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 			block_t old_blkaddr, block_t *new_blkaddr,
 			struct f2fs_summary *sum, int type,
 			struct f2fs_io_info *fio);
+void f2fs_update_device_state(struct f2fs_sb_info *sbi, nid_t ino,
+					block_t blkaddr, unsigned int blkcnt);
 void f2fs_wait_on_page_writeback(struct page *page,
 			enum page_type type, bool ordered, bool locked);
 void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr);
@@ -3516,6 +3533,16 @@ unsigned int f2fs_usable_segs_in_sec(struct f2fs_sb_info *sbi,
 unsigned int f2fs_usable_blks_in_seg(struct f2fs_sb_info *sbi,
 			unsigned int segno);
 
+#define DEF_FRAGMENT_SIZE	4
+#define MIN_FRAGMENT_SIZE	1
+#define MAX_FRAGMENT_SIZE	512
+
+static inline bool f2fs_need_rand_seg(struct f2fs_sb_info *sbi)
+{
+	return F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_SEG ||
+		F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_BLK;
+}
+
 /*
  * checkpoint.c
  */
@@ -4027,6 +4054,8 @@ void f2fs_end_read_compressed_page(struct page *page, bool failed,
 							block_t blkaddr);
 bool f2fs_cluster_is_empty(struct compress_ctx *cc);
 bool f2fs_cluster_can_merge_page(struct compress_ctx *cc, pgoff_t index);
+bool f2fs_all_cluster_page_loaded(struct compress_ctx *cc, struct pagevec *pvec,
+				int index, int nr_pages);
 bool f2fs_sanity_check_cluster(struct dnode_of_data *dn);
 void f2fs_compress_ctx_add_page(struct compress_ctx *cc, struct page *page);
 int f2fs_write_multi_pages(struct compress_ctx *cc,
@@ -4152,8 +4181,7 @@ static inline bool f2fs_disable_compressed_file(struct inode *inode)
 
 	if (!f2fs_compressed_file(inode))
 		return true;
-	if (S_ISREG(inode->i_mode) &&
+	if (S_ISREG(inode->i_mode) && F2FS_HAS_BLOCKS(inode))
-		(get_dirty_pages(inode) || atomic_read(&fi->i_compr_blocks)))
 		return false;
 
 	fi->i_flags &= ~F2FS_COMPR_FL;
@@ -4302,6 +4330,16 @@ static inline int block_unaligned_IO(struct inode *inode,
 	return align & blocksize_mask;
 }
 
+static inline bool f2fs_allow_multi_device_dio(struct f2fs_sb_info *sbi,
+								int flag)
+{
+	if (!f2fs_is_multi_device(sbi))
+		return false;
+	if (flag != F2FS_GET_BLOCK_DIO)
+		return false;
+	return sbi->aligned_blksize;
+}
+
 static inline bool f2fs_force_buffered_io(struct inode *inode,
 				struct kiocb *iocb, struct iov_iter *iter)
 {
@@ -4310,7 +4348,9 @@ static inline bool f2fs_force_buffered_io(struct inode *inode,
 
 	if (f2fs_post_read_required(inode))
 		return true;
-	if (f2fs_is_multi_device(sbi))
+
+	/* disallow direct IO if any of devices has unaligned blksize */
+	if (f2fs_is_multi_device(sbi) && !sbi->aligned_blksize)
 		return true;
 	/*
 	 * for blkzoned device, fallback direct IO to buffered IO, so

fs/f2fs/file.c

@@ -786,7 +786,7 @@ int f2fs_truncate(struct inode *inode)
 		return -EIO;
 	}
 
-	err = dquot_initialize(inode);
+	err = f2fs_dquot_initialize(inode);
 	if (err)
 		return err;
 
@@ -916,7 +916,7 @@ int f2fs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 		return err;
 
 	if (is_quota_modification(inode, attr)) {
-		err = dquot_initialize(inode);
+		err = f2fs_dquot_initialize(inode);
 		if (err)
 			return err;
 	}
@@ -3020,7 +3020,7 @@ static int f2fs_ioc_setproject(struct inode *inode, __u32 projid)
 	}
 	f2fs_put_page(ipage, 1);
 
-	err = dquot_initialize(inode);
+	err = f2fs_dquot_initialize(inode);
 	if (err)
 		return err;
 

fs/f2fs/gc.c

@@ -14,6 +14,7 @@
 #include <linux/delay.h>
 #include <linux/freezer.h>
 #include <linux/sched/signal.h>
+#include <linux/random.h>
 
 #include "f2fs.h"
 #include "node.h"
@@ -257,7 +258,9 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type,
 		p->max_search = sbi->max_victim_search;
 
 	/* let's select beginning hot/small space first in no_heap mode*/
-	if (test_opt(sbi, NOHEAP) &&
+	if (f2fs_need_rand_seg(sbi))
+		p->offset = prandom_u32() % (MAIN_SECS(sbi) * sbi->segs_per_sec);
+	else if (test_opt(sbi, NOHEAP) &&
 		(type == CURSEG_HOT_DATA || IS_NODESEG(type)))
 		p->offset = 0;
 	else

fs/f2fs/inline.c

@@ -192,7 +192,7 @@ int f2fs_convert_inline_inode(struct inode *inode)
 			f2fs_hw_is_readonly(sbi) || f2fs_readonly(sbi->sb))
 		return 0;
 
-	err = dquot_initialize(inode);
+	err = f2fs_dquot_initialize(inode);
 	if (err)
 		return err;
 

fs/f2fs/inode.c

@@ -527,7 +527,7 @@ make_now:
 		inode->i_op = &f2fs_dir_inode_operations;
 		inode->i_fop = &f2fs_dir_operations;
 		inode->i_mapping->a_ops = &f2fs_dblock_aops;
-		inode_nohighmem(inode);
+		mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
 	} else if (S_ISLNK(inode->i_mode)) {
 		if (file_is_encrypt(inode))
 			inode->i_op = &f2fs_encrypted_symlink_inode_operations;
@@ -754,7 +754,7 @@ void f2fs_evict_inode(struct inode *inode)
 	if (inode->i_nlink || is_bad_inode(inode))
 		goto no_delete;
 
-	err = dquot_initialize(inode);
+	err = f2fs_dquot_initialize(inode);
 	if (err) {
 		err = 0;
 		set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR);

fs/f2fs/namei.c

@@ -74,7 +74,7 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
 	if (err)
 		goto fail_drop;
 
-	err = dquot_initialize(inode);
+	err = f2fs_dquot_initialize(inode);
 	if (err)
 		goto fail_drop;
 
@@ -345,7 +345,7 @@ static int f2fs_create(struct user_namespace *mnt_userns, struct inode *dir,
 	if (!f2fs_is_checkpoint_ready(sbi))
 		return -ENOSPC;
 
-	err = dquot_initialize(dir);
+	err = f2fs_dquot_initialize(dir);
 	if (err)
 		return err;
 
@@ -404,7 +404,7 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
 			F2FS_I(old_dentry->d_inode)->i_projid)))
 		return -EXDEV;
 
-	err = dquot_initialize(dir);
+	err = f2fs_dquot_initialize(dir);
 	if (err)
 		return err;
 
@@ -460,7 +460,7 @@ static int __recover_dot_dentries(struct inode *dir, nid_t pino)
 		return 0;
 	}
 
-	err = dquot_initialize(dir);
+	err = f2fs_dquot_initialize(dir);
 	if (err)
 		return err;
 
@@ -598,10 +598,10 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
 		goto fail;
 	}
 
-	err = dquot_initialize(dir);
+	err = f2fs_dquot_initialize(dir);
 	if (err)
 		goto fail;
-	err = dquot_initialize(inode);
+	err = f2fs_dquot_initialize(inode);
 	if (err)
 		goto fail;
 
@@ -675,7 +675,7 @@ static int f2fs_symlink(struct user_namespace *mnt_userns, struct inode *dir,
 	if (err)
 		return err;
 
-	err = dquot_initialize(dir);
+	err = f2fs_dquot_initialize(dir);
 	if (err)
 		return err;
 
@@ -746,7 +746,7 @@ static int f2fs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
 	if (unlikely(f2fs_cp_error(sbi)))
 		return -EIO;
 
-	err = dquot_initialize(dir);
+	err = f2fs_dquot_initialize(dir);
 	if (err)
 		return err;
 
@@ -757,7 +757,7 @@ static int f2fs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
 	inode->i_op = &f2fs_dir_inode_operations;
 	inode->i_fop = &f2fs_dir_operations;
 	inode->i_mapping->a_ops = &f2fs_dblock_aops;
-	inode_nohighmem(inode);
+	mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
 
 	set_inode_flag(inode, FI_INC_LINK);
 	f2fs_lock_op(sbi);
@@ -803,7 +803,7 @@ static int f2fs_mknod(struct user_namespace *mnt_userns, struct inode *dir,
 	if (!f2fs_is_checkpoint_ready(sbi))
 		return -ENOSPC;
 
-	err = dquot_initialize(dir);
+	err = f2fs_dquot_initialize(dir);
 	if (err)
 		return err;
 
@@ -841,7 +841,7 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry,
 	struct inode *inode;
 	int err;
 
-	err = dquot_initialize(dir);
+	err = f2fs_dquot_initialize(dir);
 	if (err)
 		return err;
 
@@ -965,16 +965,16 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 			return err;
 	}
 
-	err = dquot_initialize(old_dir);
+	err = f2fs_dquot_initialize(old_dir);
 	if (err)
 		goto out;
 
-	err = dquot_initialize(new_dir);
+	err = f2fs_dquot_initialize(new_dir);
 	if (err)
 		goto out;
 
 	if (new_inode) {
-		err = dquot_initialize(new_inode);
+		err = f2fs_dquot_initialize(new_inode);
 		if (err)
 			goto out;
 	}
@@ -1138,11 +1138,11 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 			F2FS_I(new_dentry->d_inode)->i_projid)))
 		return -EXDEV;
 
-	err = dquot_initialize(old_dir);
+	err = f2fs_dquot_initialize(old_dir);
 	if (err)
 		goto out;
 
-	err = dquot_initialize(new_dir);
+	err = f2fs_dquot_initialize(new_dir);
 	if (err)
 		goto out;
 

fs/f2fs/node.c

@@ -1443,6 +1443,7 @@ page_hit:
 			  nid, nid_of_node(page), ino_of_node(page),
 			  ofs_of_node(page), cpver_of_node(page),
 			  next_blkaddr_of_node(page));
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
 		err = -EINVAL;
 out_err:
 		ClearPageUptodate(page);

fs/f2fs/node.h

@@ -138,11 +138,6 @@ static inline bool excess_cached_nats(struct f2fs_sb_info *sbi)
 	return NM_I(sbi)->nat_cnt[TOTAL_NAT] >= DEF_NAT_CACHE_THRESHOLD;
 }
 
-static inline bool excess_dirty_nodes(struct f2fs_sb_info *sbi)
-{
-	return get_pages(sbi, F2FS_DIRTY_NODES) >= sbi->blocks_per_seg * 8;
-}
-
 enum mem_type {
 	FREE_NIDS,	/* indicates the free nid list */
 	NAT_ENTRIES,	/* indicates the cached nat entry */

fs/f2fs/recovery.c

@@ -81,7 +81,7 @@ static struct fsync_inode_entry *add_fsync_inode(struct f2fs_sb_info *sbi,
 	if (IS_ERR(inode))
 		return ERR_CAST(inode);
 
-	err = dquot_initialize(inode);
+	err = f2fs_dquot_initialize(inode);
 	if (err)
 		goto err_out;
 
@@ -203,7 +203,7 @@ retry:
 			goto out_put;
 		}
 
-		err = dquot_initialize(einode);
+		err = f2fs_dquot_initialize(einode);
 		if (err) {
 			iput(einode);
 			goto out_put;
@@ -508,7 +508,7 @@ got_it:
 		if (IS_ERR(inode))
 			return PTR_ERR(inode);
 
-		ret = dquot_initialize(inode);
+		ret = f2fs_dquot_initialize(inode);
 		if (ret) {
 			iput(inode);
 			return ret;
@@ -787,8 +787,6 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
 	}
 
 #ifdef CONFIG_QUOTA
-	/* Needed for iput() to work correctly and not trash data */
-	sbi->sb->s_flags |= SB_ACTIVE;
 	/* Turn on quotas so that they are updated correctly */
 	quota_enabled = f2fs_enable_quota_files(sbi, s_flags & SB_RDONLY);
 #endif
@@ -816,10 +814,8 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
 	err = recover_data(sbi, &inode_list, &tmp_inode_list, &dir_list);
 	if (!err)
 		f2fs_bug_on(sbi, !list_empty(&inode_list));
-	else {
+	else
-		/* restore s_flags to let iput() trash data */
+		f2fs_bug_on(sbi, sbi->sb->s_flags & SB_ACTIVE);
-		sbi->sb->s_flags = s_flags;
-	}
 skip:
 	fix_curseg_write_pointer = !check_only || list_empty(&inode_list);
 

fs/f2fs/segment.c

@@ -15,6 +15,7 @@
 #include <linux/timer.h>
 #include <linux/freezer.h>
 #include <linux/sched/signal.h>
+#include <linux/random.h>
 
 #include "f2fs.h"
 #include "segment.h"
@@ -529,6 +530,25 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
 	}
 }
 
+static inline bool excess_dirty_threshold(struct f2fs_sb_info *sbi)
+{
+	int factor = rwsem_is_locked(&sbi->cp_rwsem) ? 3 : 2;
+	unsigned int dents = get_pages(sbi, F2FS_DIRTY_DENTS);
+	unsigned int qdata = get_pages(sbi, F2FS_DIRTY_QDATA);
+	unsigned int nodes = get_pages(sbi, F2FS_DIRTY_NODES);
+	unsigned int meta = get_pages(sbi, F2FS_DIRTY_META);
+	unsigned int imeta = get_pages(sbi, F2FS_DIRTY_IMETA);
+	unsigned int threshold = sbi->blocks_per_seg * factor *
+					DEFAULT_DIRTY_THRESHOLD;
+	unsigned int global_threshold = threshold * 3 / 2;
+
+	if (dents >= threshold || qdata >= threshold ||
+		nodes >= threshold || meta >= threshold ||
+		imeta >= threshold)
+		return true;
+	return dents + qdata + nodes + meta + imeta >  global_threshold;
+}
+
 void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi, bool from_bg)
 {
 	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
@@ -547,8 +567,8 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi, bool from_bg)
 	else
 		f2fs_build_free_nids(sbi, false, false);
 
-	if (excess_dirty_nats(sbi) || excess_dirty_nodes(sbi) ||
+	if (excess_dirty_nats(sbi) || excess_dirty_threshold(sbi) ||
-		excess_prefree_segs(sbi))
+		excess_prefree_segs(sbi) || !f2fs_space_for_roll_forward(sbi))
 		goto do_sync;
 
 	/* there is background inflight IO or foreground operation recently */
@@ -561,7 +581,7 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi, bool from_bg)
 		goto do_sync;
 
 	/* checkpoint is the only way to shrink partial cached entries */
-	if (f2fs_available_free_memory(sbi, NAT_ENTRIES) ||
+	if (f2fs_available_free_memory(sbi, NAT_ENTRIES) &&
 		f2fs_available_free_memory(sbi, INO_ENTRIES))
 		return;
 
@@ -2630,6 +2650,8 @@ static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type)
 	unsigned short seg_type = curseg->seg_type;
 
 	sanity_check_seg_type(sbi, seg_type);
+	if (f2fs_need_rand_seg(sbi))
+		return prandom_u32() % (MAIN_SECS(sbi) * sbi->segs_per_sec);
 
 	/* if segs_per_sec is large than 1, we need to keep original policy. */
 	if (__is_large_section(sbi))
@@ -2681,6 +2703,9 @@ static void new_curseg(struct f2fs_sb_info *sbi, int type, bool new_sec)
 	curseg->next_segno = segno;
 	reset_curseg(sbi, type, 1);
 	curseg->alloc_type = LFS;
+	if (F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_BLK)
+		curseg->fragment_remained_chunk =
+				prandom_u32() % sbi->max_fragment_chunk + 1;
 }
 
 static int __next_free_blkoff(struct f2fs_sb_info *sbi,
@@ -2707,12 +2732,22 @@ static int __next_free_blkoff(struct f2fs_sb_info *sbi,
 static void __refresh_next_blkoff(struct f2fs_sb_info *sbi,
 				struct curseg_info *seg)
 {
-	if (seg->alloc_type == SSR)
+	if (seg->alloc_type == SSR) {
 		seg->next_blkoff =
 			__next_free_blkoff(sbi, seg->segno,
 						seg->next_blkoff + 1);
-	else
+	} else {
 		seg->next_blkoff++;
+		if (F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_BLK) {
+			/* To allocate block chunks in different sizes, use random number */
+			if (--seg->fragment_remained_chunk <= 0) {
+				seg->fragment_remained_chunk =
+				   prandom_u32() % sbi->max_fragment_chunk + 1;
+				seg->next_blkoff +=
+				   prandom_u32() % sbi->max_fragment_hole + 1;
+			}
+		}
+	}
 }
 
 bool f2fs_segment_has_free_slot(struct f2fs_sb_info *sbi, int segno)
@@ -3485,24 +3520,30 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 	up_read(&SM_I(sbi)->curseg_lock);
 }
 
-static void update_device_state(struct f2fs_io_info *fio)
+void f2fs_update_device_state(struct f2fs_sb_info *sbi, nid_t ino,
+					block_t blkaddr, unsigned int blkcnt)
 {
-	struct f2fs_sb_info *sbi = fio->sbi;
-	unsigned int devidx;
-
 	if (!f2fs_is_multi_device(sbi))
 		return;
 
-	devidx = f2fs_target_device_index(sbi, fio->new_blkaddr);
+	while (1) {
+		unsigned int devidx = f2fs_target_device_index(sbi, blkaddr);
+		unsigned int blks = FDEV(devidx).end_blk - blkaddr + 1;
 
-	/* update device state for fsync */
+		/* update device state for fsync */
-	f2fs_set_dirty_device(sbi, fio->ino, devidx, FLUSH_INO);
+		f2fs_set_dirty_device(sbi, ino, devidx, FLUSH_INO);
 
-	/* update device state for checkpoint */
+		/* update device state for checkpoint */
-	if (!f2fs_test_bit(devidx, (char *)&sbi->dirty_device)) {
+		if (!f2fs_test_bit(devidx, (char *)&sbi->dirty_device)) {
-		spin_lock(&sbi->dev_lock);
+			spin_lock(&sbi->dev_lock);
-		f2fs_set_bit(devidx, (char *)&sbi->dirty_device);
+			f2fs_set_bit(devidx, (char *)&sbi->dirty_device);
-		spin_unlock(&sbi->dev_lock);
+			spin_unlock(&sbi->dev_lock);
+		}
+
+		if (blkcnt <= blks)
+			break;
+		blkcnt -= blks;
+		blkaddr += blks;
 	}
 }
 
@@ -3529,7 +3570,7 @@ reallocate:
 		goto reallocate;
 	}
 
-	update_device_state(fio);
+	f2fs_update_device_state(fio->sbi, fio->ino, fio->new_blkaddr, 1);
 
 	if (keep_order)
 		up_read(&fio->sbi->io_order_lock);
@@ -3611,6 +3652,9 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio)
 		goto drop_bio;
 	}
 
+	invalidate_mapping_pages(META_MAPPING(sbi),
+				fio->new_blkaddr, fio->new_blkaddr);
+
 	stat_inc_inplace_blocks(fio->sbi);
 
 	if (fio->bio && !(SM_I(sbi)->ipu_policy & (1 << F2FS_IPU_NOCACHE)))
@@ -3618,7 +3662,8 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio)
 	else
 		err = f2fs_submit_page_bio(fio);
 	if (!err) {
-		update_device_state(fio);
+		f2fs_update_device_state(fio->sbi, fio->ino,
+						fio->new_blkaddr, 1);
 		f2fs_update_iostat(fio->sbi, fio->io_type, F2FS_BLKSIZE);
 	}
 

fs/f2fs/segment.h

@@ -314,6 +314,7 @@ struct curseg_info {
 	unsigned short next_blkoff;		/* next block offset to write */
 	unsigned int zone;			/* current zone number */
 	unsigned int next_segno;		/* preallocated segment */
+	int fragment_remained_chunk;		/* remained block size in a chunk for block fragmentation mode */
 	bool inited;				/* indicate inmem log is inited */
 };
 

fs/f2fs/super.c

@@ -58,6 +58,7 @@ const char *f2fs_fault_name[FAULT_MAX] = {
 	[FAULT_DISCARD]		= "discard error",
 	[FAULT_WRITE_IO]	= "write IO error",
 	[FAULT_SLAB_ALLOC]	= "slab alloc",
+	[FAULT_DQUOT_INIT]	= "dquot initialize",
 };
 
 void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate,
@@ -817,6 +818,10 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
 				F2FS_OPTION(sbi).fs_mode = FS_MODE_ADAPTIVE;
 			} else if (!strcmp(name, "lfs")) {
 				F2FS_OPTION(sbi).fs_mode = FS_MODE_LFS;
+			} else if (!strcmp(name, "fragment:segment")) {
+				F2FS_OPTION(sbi).fs_mode = FS_MODE_FRAGMENT_SEG;
+			} else if (!strcmp(name, "fragment:block")) {
+				F2FS_OPTION(sbi).fs_mode = FS_MODE_FRAGMENT_BLK;
 			} else {
 				kfree(name);
 				return -EINVAL;
@@ -1292,7 +1297,7 @@ default_check:
 	/* Not pass down write hints if the number of active logs is lesser
 	 * than NR_CURSEG_PERSIST_TYPE.
 	 */
-	if (F2FS_OPTION(sbi).active_logs != NR_CURSEG_TYPE)
+	if (F2FS_OPTION(sbi).active_logs != NR_CURSEG_PERSIST_TYPE)
 		F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF;
 
 	if (f2fs_sb_has_readonly(sbi) && !f2fs_readonly(sbi->sb)) {
@@ -1896,6 +1901,10 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 		seq_puts(seq, "adaptive");
 	else if (F2FS_OPTION(sbi).fs_mode == FS_MODE_LFS)
 		seq_puts(seq, "lfs");
+	else if (F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_SEG)
+		seq_puts(seq, "fragment:segment");
+	else if (F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_BLK)
+		seq_puts(seq, "fragment:block");
 	seq_printf(seq, ",active_logs=%u", F2FS_OPTION(sbi).active_logs);
 	if (test_opt(sbi, RESERVE_ROOT))
 		seq_printf(seq, ",reserve_root=%u,resuid=%u,resgid=%u",
@@ -2491,6 +2500,16 @@ retry:
 	return len - towrite;
 }
 
+int f2fs_dquot_initialize(struct inode *inode)
+{
+	if (time_to_inject(F2FS_I_SB(inode), FAULT_DQUOT_INIT)) {
+		f2fs_show_injection_info(F2FS_I_SB(inode), FAULT_DQUOT_INIT);
+		return -ESRCH;
+	}
+
+	return dquot_initialize(inode);
+}
+
 static struct dquot **f2fs_get_dquots(struct inode *inode)
 {
 	return F2FS_I(inode)->i_dquot;
@@ -2875,6 +2894,11 @@ static const struct quotactl_ops f2fs_quotactl_ops = {
 	.get_nextdqblk	= dquot_get_next_dqblk,
 };
 #else
+int f2fs_dquot_initialize(struct inode *inode)
+{
+	return 0;
+}
+
 int f2fs_quota_sync(struct super_block *sb, int type)
 {
 	return 0;
@@ -3486,7 +3510,7 @@ skip_cross:
 		NR_CURSEG_PERSIST_TYPE + nat_bits_blocks >= blocks_per_seg)) {
 		f2fs_warn(sbi, "Insane cp_payload: %u, nat_bits_blocks: %u)",
 			  cp_payload, nat_bits_blocks);
-		return -EFSCORRUPTED;
+		return 1;
 	}
 
 	if (unlikely(f2fs_cp_error(sbi))) {
@@ -3522,6 +3546,8 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
 	sbi->max_victim_search = DEF_MAX_VICTIM_SEARCH;
 	sbi->migration_granularity = sbi->segs_per_sec;
 	sbi->seq_file_ra_mul = MIN_RA_MUL;
+	sbi->max_fragment_chunk = DEF_FRAGMENT_SIZE;
+	sbi->max_fragment_hole = DEF_FRAGMENT_SIZE;
 
 	sbi->dir_level = DEF_DIR_LEVEL;
 	sbi->interval_time[CP_TIME] = DEF_CP_INTERVAL;
@@ -3746,6 +3772,7 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
 	unsigned int max_devices = MAX_DEVICES;
+	unsigned int logical_blksize;
 	int i;
 
 	/* Initialize single device information */
@@ -3766,6 +3793,9 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 	if (!sbi->devs)
 		return -ENOMEM;
 
+	logical_blksize = bdev_logical_block_size(sbi->sb->s_bdev);
+	sbi->aligned_blksize = true;
+
 	for (i = 0; i < max_devices; i++) {
 
 		if (i > 0 && !RDEV(i).path[0])
@@ -3802,6 +3832,9 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 		/* to release errored devices */
 		sbi->s_ndevs = i + 1;
 
+		if (logical_blksize != bdev_logical_block_size(FDEV(i).bdev))
+			sbi->aligned_blksize = false;
+
 #ifdef CONFIG_BLK_DEV_ZONED
 		if (bdev_zoned_model(FDEV(i).bdev) == BLK_ZONED_HM &&
 				!f2fs_sb_has_blkzoned(sbi)) {
@@ -4351,6 +4384,8 @@ free_node_inode:
 free_stats:
 	f2fs_destroy_stats(sbi);
 free_nm:
+	/* stop discard thread before destroying node manager */
+	f2fs_stop_discard_thread(sbi);
 	f2fs_destroy_node_manager(sbi);
 free_sm:
 	f2fs_destroy_segment_manager(sbi);

fs/f2fs/sysfs.c

@@ -196,7 +196,7 @@ static ssize_t encoding_show(struct f2fs_attr *a,
 	struct super_block *sb = sbi->sb;
 
 	if (f2fs_sb_has_casefold(sbi))
-		return snprintf(buf, PAGE_SIZE, "%s (%d.%d.%d)\n",
+		return sysfs_emit(buf, "%s (%d.%d.%d)\n",
 			sb->s_encoding->charset,
 			(sb->s_encoding->version >> 16) & 0xff,
 			(sb->s_encoding->version >> 8) & 0xff,
@@ -245,7 +245,7 @@ static ssize_t avg_vblocks_show(struct f2fs_attr *a,
 static ssize_t main_blkaddr_show(struct f2fs_attr *a,
 				struct f2fs_sb_info *sbi, char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "%llu\n",
+	return sysfs_emit(buf, "%llu\n",
 			(unsigned long long)MAIN_BLKADDR(sbi));
 }
 
@@ -551,6 +551,22 @@ out:
 		return count;
 	}
 
+	if (!strcmp(a->attr.name, "max_fragment_chunk")) {
+		if (t >= MIN_FRAGMENT_SIZE && t <= MAX_FRAGMENT_SIZE)
+			sbi->max_fragment_chunk = t;
+		else
+			return -EINVAL;
+		return count;
+	}
+
+	if (!strcmp(a->attr.name, "max_fragment_hole")) {
+		if (t >= MIN_FRAGMENT_SIZE && t <= MAX_FRAGMENT_SIZE)
+			sbi->max_fragment_hole = t;
+		else
+			return -EINVAL;
+		return count;
+	}
+
 	*ui = (unsigned int)t;
 
 	return count;
@@ -781,6 +797,8 @@ F2FS_RW_ATTR(ATGC_INFO, atgc_management, atgc_age_threshold, age_threshold);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, seq_file_ra_mul, seq_file_ra_mul);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_segment_mode, gc_segment_mode);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_reclaimed_segments, gc_reclaimed_segs);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_fragment_chunk, max_fragment_chunk);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_fragment_hole, max_fragment_hole);
 
 #define ATTR_LIST(name) (&f2fs_attr_##name.attr)
 static struct attribute *f2fs_attrs[] = {
@@ -859,6 +877,8 @@ static struct attribute *f2fs_attrs[] = {
 	ATTR_LIST(seq_file_ra_mul),
 	ATTR_LIST(gc_segment_mode),
 	ATTR_LIST(gc_reclaimed_segments),
+	ATTR_LIST(max_fragment_chunk),
+	ATTR_LIST(max_fragment_hole),
 	NULL,
 };
 ATTRIBUTE_GROUPS(f2fs);

fs/f2fs/verity.c

@@ -136,7 +136,7 @@ static int f2fs_begin_enable_verity(struct file *filp)
 	 * here and not rely on ->open() doing it.  This must be done before
 	 * evicting the inline data.
 	 */
-	err = dquot_initialize(inode);
+	err = f2fs_dquot_initialize(inode);
 	if (err)
 		return err;
 

fs/f2fs/xattr.c

@@ -773,7 +773,7 @@ int f2fs_setxattr(struct inode *inode, int index, const char *name,
 	if (!f2fs_is_checkpoint_ready(sbi))
 		return -ENOSPC;
 
-	err = dquot_initialize(inode);
+	err = f2fs_dquot_initialize(inode);
 	if (err)
 		return err;
 

include/trace/events/f2fs.h

@@ -570,9 +570,10 @@ TRACE_EVENT(f2fs_file_write_iter,
 );
 
 TRACE_EVENT(f2fs_map_blocks,
-	TP_PROTO(struct inode *inode, struct f2fs_map_blocks *map, int ret),
+	TP_PROTO(struct inode *inode, struct f2fs_map_blocks *map,
+				int create, int flag, int ret),
 
-	TP_ARGS(inode, map, ret),
+	TP_ARGS(inode, map, create, flag, ret),
 
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
@@ -583,11 +584,14 @@ TRACE_EVENT(f2fs_map_blocks,
 		__field(unsigned int,	m_flags)
 		__field(int,	m_seg_type)
 		__field(bool,	m_may_create)
+		__field(bool,	m_multidev_dio)
+		__field(int,	create)
+		__field(int,	flag)
 		__field(int,	ret)
 	),
 
 	TP_fast_assign(
-		__entry->dev		= inode->i_sb->s_dev;
+		__entry->dev		= map->m_bdev->bd_dev;
 		__entry->ino		= inode->i_ino;
 		__entry->m_lblk		= map->m_lblk;
 		__entry->m_pblk		= map->m_pblk;
@@ -595,12 +599,16 @@ TRACE_EVENT(f2fs_map_blocks,
 		__entry->m_flags	= map->m_flags;
 		__entry->m_seg_type	= map->m_seg_type;
 		__entry->m_may_create	= map->m_may_create;
+		__entry->m_multidev_dio	= map->m_multidev_dio;
+		__entry->create		= create;
+		__entry->flag		= flag;
 		__entry->ret		= ret;
 	),
 
 	TP_printk("dev = (%d,%d), ino = %lu, file offset = %llu, "
-		"start blkaddr = 0x%llx, len = 0x%llx, flags = %u,"
+		"start blkaddr = 0x%llx, len = 0x%llx, flags = %u, "
-		"seg_type = %d, may_create = %d, err = %d",
+		"seg_type = %d, may_create = %d, multidevice = %d, "
+		"create = %d, flag = %d, err = %d",
 		show_dev_ino(__entry),
 		(unsigned long long)__entry->m_lblk,
 		(unsigned long long)__entry->m_pblk,
@@ -608,6 +616,9 @@ TRACE_EVENT(f2fs_map_blocks,
 		__entry->m_flags,
 		__entry->m_seg_type,
 		__entry->m_may_create,
+		__entry->m_multidev_dio,
+		__entry->create,
+		__entry->flag,
 		__entry->ret)
 );
 
@@ -807,20 +818,20 @@ TRACE_EVENT(f2fs_lookup_start,
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
 		__field(ino_t,	ino)
-		__field(const char *,	name)
+		__string(name,	dentry->d_name.name)
 		__field(unsigned int, flags)
 	),
 
 	TP_fast_assign(
 		__entry->dev	= dir->i_sb->s_dev;
 		__entry->ino	= dir->i_ino;
-		__entry->name	= dentry->d_name.name;
+		__assign_str(name, dentry->d_name.name);
 		__entry->flags	= flags;
 	),
 
 	TP_printk("dev = (%d,%d), pino = %lu, name:%s, flags:%u",
 		show_dev_ino(__entry),
-		__entry->name,
+		__get_str(name),
 		__entry->flags)
 );
 
@@ -834,7 +845,7 @@ TRACE_EVENT(f2fs_lookup_end,
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
 		__field(ino_t,	ino)
-		__field(const char *,	name)
+		__string(name,	dentry->d_name.name)
 		__field(nid_t,	cino)
 		__field(int,	err)
 	),
@@ -842,14 +853,14 @@ TRACE_EVENT(f2fs_lookup_end,
 	TP_fast_assign(
 		__entry->dev	= dir->i_sb->s_dev;
 		__entry->ino	= dir->i_ino;
-		__entry->name	= dentry->d_name.name;
+		__assign_str(name, dentry->d_name.name);
 		__entry->cino	= ino;
 		__entry->err	= err;
 	),
 
 	TP_printk("dev = (%d,%d), pino = %lu, name:%s, ino:%u, err:%d",
 		show_dev_ino(__entry),
-		__entry->name,
+		__get_str(name),
 		__entry->cino,
 		__entry->err)
 );