Merge tag 'f2fs-for-5.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this round, we've made more work into per-file compression support.

  For example, F2FS_IOC_GET | SET_COMPRESS_OPTION provides a way to
  change the algorithm or cluster size per file. F2FS_IOC_COMPRESS |
  DECOMPRESS_FILE provides a way to compress and decompress the existing
  normal files manually.

  There is also a new mount option, compress_mode=fs|user, which can
  control who compresses the data.

  Chao also added a checksum feature with a mount option so that
  we are able to detect any corrupted cluster.

  In addition, Daniel contributed casefolding with encryption patch,
  which will be used for Android devices.

  Summary:

  Enhancements:
   - add ioctls and mount option to manage per-file compression feature
   - support casefolding with encryption
   - support checksum for compressed cluster
   - avoid IO starvation by replacing mutex with rwsem
   - add sysfs, max_io_bytes, to control max bio size

  Bug fixes:
   - fix use-after-free issue when compression and fsverity are enabled
   - fix consistency corruption during fault injection test
   - fix data offset for lseek
   - get rid of buffer_head which has 32bits limit in fiemap
   - fix some bugs in multi-partitions support
   - fix nat entry count calculation in shrinker
   - fix some stat information

  And, we've refactored some logics and fix minor bugs as well"

* tag 'f2fs-for-5.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (36 commits)
  f2fs: compress: fix compression chksum
  f2fs: fix shift-out-of-bounds in sanity_check_raw_super()
  f2fs: fix race of pending_pages in decompression
  f2fs: fix to account inline xattr correctly during recovery
  f2fs: inline: fix wrong inline inode stat
  f2fs: inline: correct comment in f2fs_recover_inline_data
  f2fs: don't check PAGE_SIZE again in sanity_check_raw_super()
  f2fs: convert to F2FS_*_INO macro
  f2fs: introduce max_io_bytes, a sysfs entry, to limit bio size
  f2fs: don't allow any writes on readonly mount
  f2fs: avoid race condition for shrinker count
  f2fs: add F2FS_IOC_DECOMPRESS_FILE and F2FS_IOC_COMPRESS_FILE
  f2fs: add compress_mode mount option
  f2fs: Remove unnecessary unlikely()
  f2fs: init dirty_secmap incorrectly
  f2fs: remove buffer_head which has 32bits limit
  f2fs: fix wrong block count instead of bytes
  f2fs: use new conversion functions between blks and bytes
  f2fs: rename logical_to_blk and blk_to_logical
  f2fs: fix kbytes written stat for multi-device case
  ...

1 files changed, 75 insertions, 106 deletions

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 9f793923dabe..bb11759191dc 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -33,10 +33,8 @@
 #else
 #define f2fs_bug_on(sbi, condition)					\
 	do {								\
-		if (unlikely(condition)) {				\
-			WARN_ON(1);					\
+		if (WARN_ON(condition))					\
 			set_sbi_flag(sbi, SBI_NEED_FSCK);		\
-		}							\
 	} while (0)
 #endif
 
@@ -147,8 +145,10 @@ struct f2fs_mount_info {
 
 	/* For compression */
 	unsigned char compress_algorithm;	/* algorithm type */
-	unsigned compress_log_size;		/* cluster log size */
+	unsigned char compress_log_size;	/* cluster log size */
+	bool compress_chksum;			/* compressed data chksum */
 	unsigned char compress_ext_cnt;		/* extension count */
+	int compress_mode;			/* compression mode */
 	unsigned char extensions[COMPRESS_EXT_NUM][F2FS_EXTENSION_LEN];	/* extensions */
 };
 
@@ -402,85 +402,6 @@ static inline bool __has_cursum_space(struct f2fs_journal *journal,
 	return size <= MAX_SIT_JENTRIES(journal);
 }
 
-/*
- * f2fs-specific ioctl commands
- */
-#define F2FS_IOCTL_MAGIC		0xf5
-#define F2FS_IOC_START_ATOMIC_WRITE	_IO(F2FS_IOCTL_MAGIC, 1)
-#define F2FS_IOC_COMMIT_ATOMIC_WRITE	_IO(F2FS_IOCTL_MAGIC, 2)
-#define F2FS_IOC_START_VOLATILE_WRITE	_IO(F2FS_IOCTL_MAGIC, 3)
-#define F2FS_IOC_RELEASE_VOLATILE_WRITE	_IO(F2FS_IOCTL_MAGIC, 4)
-#define F2FS_IOC_ABORT_VOLATILE_WRITE	_IO(F2FS_IOCTL_MAGIC, 5)
-#define F2FS_IOC_GARBAGE_COLLECT	_IOW(F2FS_IOCTL_MAGIC, 6, __u32)
-#define F2FS_IOC_WRITE_CHECKPOINT	_IO(F2FS_IOCTL_MAGIC, 7)
-#define F2FS_IOC_DEFRAGMENT		_IOWR(F2FS_IOCTL_MAGIC, 8,	\
-						struct f2fs_defragment)
-#define F2FS_IOC_MOVE_RANGE		_IOWR(F2FS_IOCTL_MAGIC, 9,	\
-						struct f2fs_move_range)
-#define F2FS_IOC_FLUSH_DEVICE		_IOW(F2FS_IOCTL_MAGIC, 10,	\
-						struct f2fs_flush_device)
-#define F2FS_IOC_GARBAGE_COLLECT_RANGE	_IOW(F2FS_IOCTL_MAGIC, 11,	\
-						struct f2fs_gc_range)
-#define F2FS_IOC_GET_FEATURES		_IOR(F2FS_IOCTL_MAGIC, 12, __u32)
-#define F2FS_IOC_SET_PIN_FILE		_IOW(F2FS_IOCTL_MAGIC, 13, __u32)
-#define F2FS_IOC_GET_PIN_FILE		_IOR(F2FS_IOCTL_MAGIC, 14, __u32)
-#define F2FS_IOC_PRECACHE_EXTENTS	_IO(F2FS_IOCTL_MAGIC, 15)
-#define F2FS_IOC_RESIZE_FS		_IOW(F2FS_IOCTL_MAGIC, 16, __u64)
-#define F2FS_IOC_GET_COMPRESS_BLOCKS	_IOR(F2FS_IOCTL_MAGIC, 17, __u64)
-#define F2FS_IOC_RELEASE_COMPRESS_BLOCKS				\
-					_IOR(F2FS_IOCTL_MAGIC, 18, __u64)
-#define F2FS_IOC_RESERVE_COMPRESS_BLOCKS				\
-					_IOR(F2FS_IOCTL_MAGIC, 19, __u64)
-#define F2FS_IOC_SEC_TRIM_FILE		_IOW(F2FS_IOCTL_MAGIC, 20,	\
-						struct f2fs_sectrim_range)
-
-/*
- * should be same as XFS_IOC_GOINGDOWN.
- * Flags for going down operation used by FS_IOC_GOINGDOWN
- */
-#define F2FS_IOC_SHUTDOWN	_IOR('X', 125, __u32)	/* Shutdown */
-#define F2FS_GOING_DOWN_FULLSYNC	0x0	/* going down with full sync */
-#define F2FS_GOING_DOWN_METASYNC	0x1	/* going down with metadata */
-#define F2FS_GOING_DOWN_NOSYNC		0x2	/* going down */
-#define F2FS_GOING_DOWN_METAFLUSH	0x3	/* going down with meta flush */
-#define F2FS_GOING_DOWN_NEED_FSCK	0x4	/* going down to trigger fsck */
-
-/*
- * Flags used by F2FS_IOC_SEC_TRIM_FILE
- */
-#define F2FS_TRIM_FILE_DISCARD		0x1	/* send discard command */
-#define F2FS_TRIM_FILE_ZEROOUT		0x2	/* zero out */
-#define F2FS_TRIM_FILE_MASK		0x3
-
-struct f2fs_gc_range {
-	u32 sync;
-	u64 start;
-	u64 len;
-};
-
-struct f2fs_defragment {
-	u64 start;
-	u64 len;
-};
-
-struct f2fs_move_range {
-	u32 dst_fd;		/* destination fd */
-	u64 pos_in;		/* start position in src_fd */
-	u64 pos_out;		/* start position in dst_fd */
-	u64 len;		/* size to move */
-};
-
-struct f2fs_flush_device {
-	u32 dev_num;		/* device number to flush */
-	u32 segments;		/* # of segments to flush */
-};
-
-struct f2fs_sectrim_range {
-	u64 start;
-	u64 len;
-	u64 flags;
-};
-
 /* for inline stuff */
 #define DEF_INLINE_RESERVED_SIZE	1
 static inline int get_extra_isize(struct inode *inode);
@@ -533,9 +454,11 @@ struct f2fs_filename {
 #ifdef CONFIG_UNICODE
 	/*
 	 * For casefolded directories: the casefolded name, but it's left NULL
-	 * if the original name is not valid Unicode or if the filesystem is
-	 * doing an internal operation where usr_fname is also NULL.  In these
-	 * cases we fall back to treating the name as an opaque byte sequence.
+	 * if the original name is not valid Unicode, if the directory is both
+	 * casefolded and encrypted and its encryption key is unavailable, or if
+	 * the filesystem is doing an internal operation where usr_fname is also
+	 * NULL.  In all these cases we fall back to treating the name as an
+	 * opaque byte sequence.
 	 */
 	struct fscrypt_str cf_name;
 #endif
@@ -753,7 +676,9 @@ enum {
 	FI_ATOMIC_REVOKE_REQUEST, /* request to drop atomic data */
 	FI_VERITY_IN_PROGRESS,	/* building fs-verity Merkle tree */
 	FI_COMPRESSED_FILE,	/* indicate file's data can be compressed */
+	FI_COMPRESS_CORRUPT,	/* indicate compressed cluster is corrupted */
 	FI_MMAP_FILE,		/* indicate file was mmapped */
+	FI_ENABLE_COMPRESS,	/* enable compression in "user" compression mode */
 	FI_MAX,			/* max flag, never be used */
 };
 
@@ -810,6 +735,7 @@ struct f2fs_inode_info {
 	atomic_t i_compr_blocks;		/* # of compressed blocks */
 	unsigned char i_compress_algorithm;	/* algorithm type */
 	unsigned char i_log_cluster_size;	/* log of cluster size */
+	unsigned short i_compress_flag;		/* compress flag */
 	unsigned int i_cluster_size;		/* cluster size */
 };
 
@@ -894,6 +820,13 @@ enum nid_state {
 	MAX_NID_STATE,
 };
 
+enum nat_state {
+	TOTAL_NAT,
+	DIRTY_NAT,
+	RECLAIMABLE_NAT,
+	MAX_NAT_STATE,
+};
+
 struct f2fs_nm_info {
 	block_t nat_blkaddr;		/* base disk address of NAT */
 	nid_t max_nid;			/* maximum possible node ids */
@@ -909,8 +842,7 @@ struct f2fs_nm_info {
 	struct rw_semaphore nat_tree_lock;	/* protect nat_tree_lock */
 	struct list_head nat_entries;	/* cached nat entry list (clean) */
 	spinlock_t nat_list_lock;	/* protect clean nat entry list */
-	unsigned int nat_cnt;		/* the # of cached nat entries */
-	unsigned int dirty_nat_cnt;	/* total num of nat entries in set */
+	unsigned int nat_cnt[MAX_NAT_STATE]; /* the # of cached nat entries */
 	unsigned int nat_blocks;	/* # of nat blocks */
 
 	/* free node ids management */
@@ -1320,6 +1252,18 @@ enum fsync_mode {
 	FSYNC_MODE_NOBARRIER,	/* fsync behaves nobarrier based on posix */
 };
 
+enum {
+	COMPR_MODE_FS,		/*
+				 * automatically compress compression
+				 * enabled files
+				 */
+	COMPR_MODE_USER,	/*
+				 * automatical compression is disabled.
+				 * user can control the file compression
+				 * using ioctls
+				 */
+};
+
 /*
  * this value is set in page as a private data which indicate that
  * the page is atomically written, and it is in inmem_pages list.
@@ -1349,9 +1293,15 @@ enum compress_algorithm_type {
 	COMPRESS_MAX,
 };
 
-#define COMPRESS_DATA_RESERVED_SIZE		5
+enum compress_flag {
+	COMPRESS_CHKSUM,
+	COMPRESS_MAX_FLAG,
+};
+
+#define COMPRESS_DATA_RESERVED_SIZE		4
 struct compress_data {
 	__le32 clen;			/* compressed data size */
+	__le32 chksum;			/* compressed data chksum */
 	__le32 reserved[COMPRESS_DATA_RESERVED_SIZE];	/* reserved */
 	u8 cdata[];			/* compressed data */
 };
@@ -1404,6 +1354,7 @@ struct decompress_io_ctx {
 	size_t rlen;			/* valid data length in rbuf */
 	size_t clen;			/* valid data length in cbuf */
 	atomic_t pending_pages;		/* in-flight compressed page count */
+	atomic_t verity_pages;		/* in-flight page count for verity */
 	bool failed;			/* indicate IO error during decompression */
 	void *private;			/* payload buffer for specified decompression algorithm */
 	void *private2;			/* extra payload buffer */
@@ -1446,7 +1397,7 @@ struct f2fs_sb_info {
 	int cur_cp_pack;			/* remain current cp pack */
 	spinlock_t cp_lock;			/* for flag in ckpt */
 	struct inode *meta_inode;		/* cache meta blocks */
-	struct mutex cp_mutex;			/* checkpoint procedure lock */
+	struct rw_semaphore cp_global_sem;	/* checkpoint procedure lock */
 	struct rw_semaphore cp_rwsem;		/* blocking FS operations */
 	struct rw_semaphore node_write;		/* locking node writes */
 	struct rw_semaphore node_change;	/* locking node change */
@@ -1496,6 +1447,7 @@ struct f2fs_sb_info {
 	loff_t max_file_blocks;			/* max block index of file */
 	int dir_level;				/* directory level */
 	int readdir_ra;				/* readahead inode in readdir */
+	u64 max_io_bytes;			/* max io bytes to merge IOs */
 
 	block_t user_block_count;		/* # of user blocks */
 	block_t total_valid_block_count;	/* # of valid blocks */
@@ -1671,13 +1623,6 @@ static inline bool f2fs_is_multi_device(struct f2fs_sb_info *sbi)
 	return sbi->s_ndevs > 1;
 }
 
-/* For write statistics. Suppose sector size is 512 bytes,
- * and the return value is in kbytes. s is of struct f2fs_sb_info.
- */
-#define BD_PART_WRITTEN(s)						 \
-	(((u64)part_stat_read((s)->sb->s_bdev, sectors[STAT_WRITE]) -   \
-		(s)->sectors_written_start) >> 1)
-
 static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type)
 {
 	unsigned long now = jiffies;
@@ -2477,24 +2422,31 @@ static inline void *f2fs_kmem_cache_alloc(struct kmem_cache *cachep,
 	return entry;
 }
 
-static inline bool is_idle(struct f2fs_sb_info *sbi, int type)
+static inline bool is_inflight_io(struct f2fs_sb_info *sbi, int type)
 {
-	if (sbi->gc_mode == GC_URGENT_HIGH)
-		return true;
-
 	if (get_pages(sbi, F2FS_RD_DATA) || get_pages(sbi, F2FS_RD_NODE) ||
 		get_pages(sbi, F2FS_RD_META) || get_pages(sbi, F2FS_WB_DATA) ||
 		get_pages(sbi, F2FS_WB_CP_DATA) ||
 		get_pages(sbi, F2FS_DIO_READ) ||
 		get_pages(sbi, F2FS_DIO_WRITE))
-		return false;
+		return true;
 
 	if (type != DISCARD_TIME && SM_I(sbi) && SM_I(sbi)->dcc_info &&
 			atomic_read(&SM_I(sbi)->dcc_info->queued_discard))
-		return false;
+		return true;
 
 	if (SM_I(sbi) && SM_I(sbi)->fcc_info &&
 			atomic_read(&SM_I(sbi)->fcc_info->queued_flush))
+		return true;
+	return false;
+}
+
+static inline bool is_idle(struct f2fs_sb_info *sbi, int type)
+{
+	if (sbi->gc_mode == GC_URGENT_HIGH)
+		return true;
+
+	if (is_inflight_io(sbi, type))
 		return false;
 
 	if (sbi->gc_mode == GC_URGENT_LOW &&
@@ -2829,6 +2781,22 @@ static inline int f2fs_compressed_file(struct inode *inode)
 		is_inode_flag_set(inode, FI_COMPRESSED_FILE);
 }
 
+static inline bool f2fs_need_compress_data(struct inode *inode)
+{
+	int compress_mode = F2FS_OPTION(F2FS_I_SB(inode)).compress_mode;
+
+	if (!f2fs_compressed_file(inode))
+		return false;
+
+	if (compress_mode == COMPR_MODE_FS)
+		return true;
+	else if (compress_mode == COMPR_MODE_USER &&
+			is_inode_flag_set(inode, FI_ENABLE_COMPRESS))
+		return true;
+
+	return false;
+}
+
 static inline unsigned int addrs_per_inode(struct inode *inode)
 {
 	unsigned int addrs = CUR_ADDRS_PER_INODE(inode) -
@@ -3445,6 +3413,7 @@ void f2fs_update_dirty_page(struct inode *inode, struct page *page);
 void f2fs_remove_dirty_inode(struct inode *inode);
 int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type);
 void f2fs_wait_on_all_pages(struct f2fs_sb_info *sbi, int type);
+u64 f2fs_get_sectors_written(struct f2fs_sb_info *sbi);
 int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc);
 void f2fs_init_ino_entry_info(struct f2fs_sb_info *sbi);
 int __init f2fs_create_checkpoint_caches(void);
@@ -3769,9 +3738,6 @@ static inline void f2fs_update_sit_info(struct f2fs_sb_info *sbi) {}
 #endif
 
 extern const struct file_operations f2fs_dir_operations;
-#ifdef CONFIG_UNICODE
-extern const struct dentry_operations f2fs_dentry_ops;
-#endif
 extern const struct file_operations f2fs_file_operations;
 extern const struct inode_operations f2fs_file_inode_operations;
 extern const struct address_space_operations f2fs_dblock_aops;
@@ -3963,6 +3929,9 @@ static inline void set_compress_context(struct inode *inode)
 			F2FS_OPTION(sbi).compress_algorithm;
 	F2FS_I(inode)->i_log_cluster_size =
 			F2FS_OPTION(sbi).compress_log_size;
+	F2FS_I(inode)->i_compress_flag =
+			F2FS_OPTION(sbi).compress_chksum ?
+				1 << COMPRESS_CHKSUM : 0;
 	F2FS_I(inode)->i_cluster_size =
 			1 << F2FS_I(inode)->i_log_cluster_size;
 	F2FS_I(inode)->i_flags |= F2FS_COMPR_FL;