Merge tag 'f2fs-for-5.8' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this round, we've added some knobs to enhance compression feature
  and harden testing environment. In addition, we've fixed several bugs
  reported from Android devices such as long discarding latency, device
  hanging during quota_sync, etc.

  Enhancements:
   - support lzo-rle algorithm
   - add two ioctls to release and reserve blocks for compression
   - support partial truncation/fiemap on compressed file
   - introduce sysfs entries to attach IO flags explicitly
   - add iostat trace point along with read io stat

  Bug fixes:
   - fix long discard latency
   - flush quota data by f2fs_quota_sync correctly
   - fix to recover parent inode number for power-cut recovery
   - fix lz4/zstd output buffer budget
   - parse checkpoint mount option correctly
   - avoid inifinite loop to wait for flushing node/meta pages
   - manage discard space correctly

  And some refactoring and clean up patches were added"

* tag 'f2fs-for-5.8' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (51 commits)
  f2fs: attach IO flags to the missing cases
  f2fs: add node_io_flag for bio flags likewise data_io_flag
  f2fs: remove unused parameter of f2fs_put_rpages_mapping()
  f2fs: handle readonly filesystem in f2fs_ioc_shutdown()
  f2fs: avoid utf8_strncasecmp() with unstable name
  f2fs: don't return vmalloc() memory from f2fs_kmalloc()
  f2fs: fix retry logic in f2fs_write_cache_pages()
  f2fs: fix wrong discard space
  f2fs: compress: don't compress any datas after cp stop
  f2fs: remove unneeded return value of __insert_discard_tree()
  f2fs: fix wrong value of tracepoint parameter
  f2fs: protect new segment allocation in expand_inode_data
  f2fs: code cleanup by removing ifdef macro surrounding
  f2fs: avoid inifinite loop to wait for flushing node pages at cp_error
  f2fs: flush dirty meta pages when flushing them
  f2fs: fix checkpoint=disable:%u%%
  f2fs: compress: fix zstd data corruption
  f2fs: add compressed/gc data read IO stat
  f2fs: fix potential use-after-free issue
  f2fs: compress: don't handle non-compressed data in workqueue
  ...

1 files changed, 126 insertions, 45 deletions

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 5c0149d2f46a..b35a50f4953c 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * fs/f2fs/f2fs.h
  *
@@ -139,6 +139,7 @@ struct f2fs_mount_info {
 	int fs_mode;			/* fs mode: LFS or ADAPTIVE */
 	int bggc_mode;			/* bggc mode: off, on or sync */
 	struct fscrypt_dummy_context dummy_enc_ctx; /* test dummy encryption */
+	block_t unusable_cap_perc;	/* percentage for cap */
 	block_t unusable_cap;		/* Amount of space allowed to be
 					 * unusable when disabling checkpoint
 					 */
@@ -194,6 +195,7 @@ enum {
 #define	CP_DISCARD	0x00000010
 #define CP_TRIMMED	0x00000020
 #define CP_PAUSE	0x00000040
+#define CP_RESIZE 	0x00000080
 
 #define MAX_DISCARD_BLOCKS(sbi)		BLKS_PER_SEC(sbi)
 #define DEF_MAX_DISCARD_REQUEST		8	/* issue 8 discards per round */
@@ -428,6 +430,10 @@ static inline bool __has_cursum_space(struct f2fs_journal *journal,
 #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_GET_VOLUME_NAME	FS_IOC_GETFSLABEL
 #define F2FS_IOC_SET_VOLUME_NAME	FS_IOC_SETFSLABEL
@@ -506,6 +512,42 @@ static inline int get_inline_xattr_addrs(struct inode *inode);
  * For INODE and NODE manager
  */
 /* for directory operations */
+
+struct f2fs_filename {
+	/*
+	 * The filename the user specified.  This is NULL for some
+	 * filesystem-internal operations, e.g. converting an inline directory
+	 * to a non-inline one, or roll-forward recovering an encrypted dentry.
+	 */
+	const struct qstr *usr_fname;
+
+	/*
+	 * The on-disk filename.  For encrypted directories, this is encrypted.
+	 * This may be NULL for lookups in an encrypted dir without the key.
+	 */
+	struct fscrypt_str disk_name;
+
+	/* The dirhash of this filename */
+	f2fs_hash_t hash;
+
+#ifdef CONFIG_FS_ENCRYPTION
+	/*
+	 * For lookups in encrypted directories: either the buffer backing
+	 * disk_name, or a buffer that holds the decoded no-key name.
+	 */
+	struct fscrypt_str crypto_buf;
+#endif
+#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.
+	 */
+	struct fscrypt_str cf_name;
+#endif
+};
+
 struct f2fs_dentry_ptr {
 	struct inode *inode;
 	void *bitmap;
@@ -1088,8 +1130,9 @@ enum cp_reason_type {
 };
 
 enum iostat_type {
-	APP_DIRECT_IO,			/* app direct IOs */
-	APP_BUFFERED_IO,		/* app buffered IOs */
+	/* WRITE IO */
+	APP_DIRECT_IO,			/* app direct write IOs */
+	APP_BUFFERED_IO,		/* app buffered write IOs */
 	APP_WRITE_IO,			/* app write IOs */
 	APP_MAPPED_IO,			/* app mapped IOs */
 	FS_DATA_IO,			/* data IOs from kworker/fsync/reclaimer */
@@ -1100,6 +1143,19 @@ enum iostat_type {
 	FS_CP_DATA_IO,			/* data IOs from checkpoint */
 	FS_CP_NODE_IO,			/* node IOs from checkpoint */
 	FS_CP_META_IO,			/* meta IOs from checkpoint */
+
+	/* READ IO */
+	APP_DIRECT_READ_IO,		/* app direct read IOs */
+	APP_BUFFERED_READ_IO,		/* app buffered read IOs */
+	APP_READ_IO,			/* app read IOs */
+	APP_MAPPED_READ_IO,		/* app mapped read IOs */
+	FS_DATA_READ_IO,		/* data read IOs */
+	FS_GDATA_READ_IO,		/* data read IOs from background gc */
+	FS_CDATA_READ_IO,		/* compressed data read IOs */
+	FS_NODE_READ_IO,		/* node read IOs */
+	FS_META_READ_IO,		/* meta read IOs */
+
+	/* other */
 	FS_DISCARD,			/* discard */
 	NR_IO_TYPE,
 };
@@ -1269,6 +1325,7 @@ enum compress_algorithm_type {
 	COMPRESS_LZO,
 	COMPRESS_LZ4,
 	COMPRESS_ZSTD,
+	COMPRESS_LZORLE,
 	COMPRESS_MAX,
 };
 
@@ -1418,7 +1475,6 @@ struct f2fs_sb_info {
 	unsigned int segs_per_sec;		/* segments per section */
 	unsigned int secs_per_zone;		/* sections per zone */
 	unsigned int total_sections;		/* total section count */
-	struct mutex resize_mutex;		/* for resize exclusion */
 	unsigned int total_node_count;		/* total node block count */
 	unsigned int total_valid_node_count;	/* valid node block count */
 	loff_t max_file_blocks;			/* max block index of file */
@@ -1504,8 +1560,15 @@ struct f2fs_sb_info {
 
 	/* For app/fs IO statistics */
 	spinlock_t iostat_lock;
-	unsigned long long write_iostat[NR_IO_TYPE];
+	unsigned long long rw_iostat[NR_IO_TYPE];
+	unsigned long long prev_rw_iostat[NR_IO_TYPE];
 	bool iostat_enable;
+	unsigned long iostat_next_period;
+	unsigned int iostat_period_ms;
+
+	/* to attach REQ_META|REQ_FUA flags */
+	unsigned int data_io_flag;
+	unsigned int node_io_flag;
 
 	/* For sysfs suppport */
 	struct kobject s_kobj;
@@ -2902,12 +2965,12 @@ static inline bool f2fs_cp_error(struct f2fs_sb_info *sbi)
 	return is_set_ckpt_flags(sbi, CP_ERROR_FLAG);
 }
 
-static inline bool is_dot_dotdot(const struct qstr *str)
+static inline bool is_dot_dotdot(const u8 *name, size_t len)
 {
-	if (str->len == 1 && str->name[0] == '.')
+	if (len == 1 && name[0] == '.')
 		return true;
 
-	if (str->len == 2 && str->name[0] == '.' && str->name[1] == '.')
+	if (len == 2 && name[0] == '.' && name[1] == '.')
 		return true;
 
 	return false;
@@ -2935,18 +2998,12 @@ static inline bool f2fs_may_extent_tree(struct inode *inode)
 static inline void *f2fs_kmalloc(struct f2fs_sb_info *sbi,
 					size_t size, gfp_t flags)
 {
-	void *ret;
-
 	if (time_to_inject(sbi, FAULT_KMALLOC)) {
 		f2fs_show_injection_info(sbi, FAULT_KMALLOC);
 		return NULL;
 	}
 
-	ret = kmalloc(size, flags);
-	if (ret)
-		return ret;
-
-	return kvmalloc(size, flags);
+	return kmalloc(size, flags);
 }
 
 static inline void *f2fs_kzalloc(struct f2fs_sb_info *sbi,
@@ -2996,29 +3053,45 @@ static inline int get_inline_xattr_addrs(struct inode *inode)
 		sizeof((f2fs_inode)->field))			\
 		<= (F2FS_OLD_ATTRIBUTE_SIZE + (extra_isize)))	\
 
+#define DEFAULT_IOSTAT_PERIOD_MS	3000
+#define MIN_IOSTAT_PERIOD_MS		100
+/* maximum period of iostat tracing is 1 day */
+#define MAX_IOSTAT_PERIOD_MS		8640000
+
 static inline void f2fs_reset_iostat(struct f2fs_sb_info *sbi)
 {
 	int i;
 
 	spin_lock(&sbi->iostat_lock);
-	for (i = 0; i < NR_IO_TYPE; i++)
-		sbi->write_iostat[i] = 0;
+	for (i = 0; i < NR_IO_TYPE; i++) {
+		sbi->rw_iostat[i] = 0;
+		sbi->prev_rw_iostat[i] = 0;
+	}
 	spin_unlock(&sbi->iostat_lock);
 }
 
+extern void f2fs_record_iostat(struct f2fs_sb_info *sbi);
+
 static inline void f2fs_update_iostat(struct f2fs_sb_info *sbi,
 			enum iostat_type type, unsigned long long io_bytes)
 {
 	if (!sbi->iostat_enable)
 		return;
 	spin_lock(&sbi->iostat_lock);
-	sbi->write_iostat[type] += io_bytes;
+	sbi->rw_iostat[type] += io_bytes;
 
 	if (type == APP_WRITE_IO || type == APP_DIRECT_IO)
-		sbi->write_iostat[APP_BUFFERED_IO] =
-			sbi->write_iostat[APP_WRITE_IO] -
-			sbi->write_iostat[APP_DIRECT_IO];
+		sbi->rw_iostat[APP_BUFFERED_IO] =
+			sbi->rw_iostat[APP_WRITE_IO] -
+			sbi->rw_iostat[APP_DIRECT_IO];
+
+	if (type == APP_READ_IO || type == APP_DIRECT_READ_IO)
+		sbi->rw_iostat[APP_BUFFERED_READ_IO] =
+			sbi->rw_iostat[APP_READ_IO] -
+			sbi->rw_iostat[APP_DIRECT_READ_IO];
 	spin_unlock(&sbi->iostat_lock);
+
+	f2fs_record_iostat(sbi);
 }
 
 #define __is_large_section(sbi)		((sbi)->segs_per_sec > 1)
@@ -3064,6 +3137,7 @@ static inline void f2fs_clear_page_private(struct page *page)
  */
 int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync);
 void f2fs_truncate_data_blocks(struct dnode_of_data *dn);
+int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock);
 int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock);
 int f2fs_truncate(struct inode *inode);
 int f2fs_getattr(const struct path *path, struct kstat *stat,
@@ -3099,31 +3173,32 @@ int f2fs_update_extension_list(struct f2fs_sb_info *sbi, const char *name,
 							bool hot, bool set);
 struct dentry *f2fs_get_parent(struct dentry *child);
 
-extern int f2fs_ci_compare(const struct inode *parent,
-			   const struct qstr *name,
-			   const struct qstr *entry,
-			   bool quick);
-
 /*
  * dir.c
  */
 unsigned char f2fs_get_de_type(struct f2fs_dir_entry *de);
-struct f2fs_dir_entry *f2fs_find_target_dentry(struct fscrypt_name *fname,
-			f2fs_hash_t namehash, int *max_slots,
-			struct f2fs_dentry_ptr *d);
+int f2fs_init_casefolded_name(const struct inode *dir,
+			      struct f2fs_filename *fname);
+int f2fs_setup_filename(struct inode *dir, const struct qstr *iname,
+			int lookup, struct f2fs_filename *fname);
+int f2fs_prepare_lookup(struct inode *dir, struct dentry *dentry,
+			struct f2fs_filename *fname);
+void f2fs_free_filename(struct f2fs_filename *fname);
+struct f2fs_dir_entry *f2fs_find_target_dentry(const struct f2fs_dentry_ptr *d,
+			const struct f2fs_filename *fname, int *max_slots);
 int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
 			unsigned int start_pos, struct fscrypt_str *fstr);
 void f2fs_do_make_empty_dir(struct inode *inode, struct inode *parent,
 			struct f2fs_dentry_ptr *d);
 struct page *f2fs_init_inode_metadata(struct inode *inode, struct inode *dir,
-			const struct qstr *new_name,
-			const struct qstr *orig_name, struct page *dpage);
+			const struct f2fs_filename *fname, struct page *dpage);
 void f2fs_update_parent_metadata(struct inode *dir, struct inode *inode,
 			unsigned int current_depth);
 int f2fs_room_for_filename(const void *bitmap, int slots, int max_slots);
 void f2fs_drop_nlink(struct inode *dir, struct inode *inode);
 struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir,
-			struct fscrypt_name *fname, struct page **res_page);
+					 const struct f2fs_filename *fname,
+					 struct page **res_page);
 struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
 			const struct qstr *child, struct page **res_page);
 struct f2fs_dir_entry *f2fs_parent_dir(struct inode *dir, struct page **p);
@@ -3132,14 +3207,13 @@ ino_t f2fs_inode_by_name(struct inode *dir, const struct qstr *qstr,
 void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
 			struct page *page, struct inode *inode);
 bool f2fs_has_enough_room(struct inode *dir, struct page *ipage,
-			struct fscrypt_name *fname);
+			  const struct f2fs_filename *fname);
 void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d,
-			const struct qstr *name, f2fs_hash_t name_hash,
+			const struct fscrypt_str *name, f2fs_hash_t name_hash,
 			unsigned int bit_pos);
-int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name,
-			const struct qstr *orig_name,
+int f2fs_add_regular_entry(struct inode *dir, const struct f2fs_filename *fname,
 			struct inode *inode, nid_t ino, umode_t mode);
-int f2fs_add_dentry(struct inode *dir, struct fscrypt_name *fname,
+int f2fs_add_dentry(struct inode *dir, const struct f2fs_filename *fname,
 			struct inode *inode, nid_t ino, umode_t mode);
 int f2fs_do_add_link(struct inode *dir, const struct qstr *name,
 			struct inode *inode, nid_t ino, umode_t mode);
@@ -3169,8 +3243,7 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi);
 /*
  * hash.c
  */
-f2fs_hash_t f2fs_dentry_hash(const struct inode *dir,
-		const struct qstr *name_info, struct fscrypt_name *fname);
+void f2fs_hash_filename(const struct inode *dir, struct f2fs_filename *fname);
 
 /*
  * node.c
@@ -3202,6 +3275,7 @@ void f2fs_ra_node_page(struct f2fs_sb_info *sbi, nid_t nid);
 struct page *f2fs_get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid);
 struct page *f2fs_get_node_page_ra(struct page *parent, int start);
 int f2fs_move_node_page(struct page *node_page, int gc_type);
+int f2fs_flush_inline_data(struct f2fs_sb_info *sbi);
 int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
 			struct writeback_control *wbc, bool atomic,
 			unsigned int *seq_id);
@@ -3645,7 +3719,7 @@ static inline int f2fs_build_stats(struct f2fs_sb_info *sbi) { return 0; }
 static inline void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { }
 static inline void __init f2fs_create_root_stats(void) { }
 static inline void f2fs_destroy_root_stats(void) { }
-static inline void update_sit_info(struct f2fs_sb_info *sbi) {}
+static inline void f2fs_update_sit_info(struct f2fs_sb_info *sbi) {}
 #endif
 
 extern const struct file_operations f2fs_dir_operations;
@@ -3678,11 +3752,11 @@ int f2fs_try_convert_inline_dir(struct inode *dir, struct dentry *dentry);
 int f2fs_write_inline_data(struct inode *inode, struct page *page);
 bool f2fs_recover_inline_data(struct inode *inode, struct page *npage);
 struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir,
-			struct fscrypt_name *fname, struct page **res_page);
+					const struct f2fs_filename *fname,
+					struct page **res_page);
 int f2fs_make_empty_inline_dir(struct inode *inode, struct inode *parent,
 			struct page *ipage);
-int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
-			const struct qstr *orig_name,
+int f2fs_add_inline_entry(struct inode *dir, const struct f2fs_filename *fname,
 			struct inode *inode, nid_t ino, umode_t mode);
 void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry,
 				struct page *page, struct inode *dir,
@@ -3781,8 +3855,11 @@ int f2fs_prepare_compress_overwrite(struct inode *inode,
 			struct page **pagep, pgoff_t index, void **fsdata);
 bool f2fs_compress_write_end(struct inode *inode, void *fsdata,
 					pgoff_t index, unsigned copied);
+int f2fs_truncate_partial_cluster(struct inode *inode, u64 from, bool lock);
 void f2fs_compress_write_end_io(struct bio *bio, struct page *page);
 bool f2fs_is_compress_backend_ready(struct inode *inode);
+int f2fs_init_compress_mempool(void);
+void f2fs_destroy_compress_mempool(void);
 void f2fs_decompress_pages(struct bio *bio, struct page *page, bool verity);
 bool f2fs_cluster_is_empty(struct compress_ctx *cc);
 bool f2fs_cluster_can_merge_page(struct compress_ctx *cc, pgoff_t index);
@@ -3816,6 +3893,8 @@ static inline struct page *f2fs_compress_control_page(struct page *page)
 	WARN_ON_ONCE(1);
 	return ERR_PTR(-EINVAL);
 }
+static inline int f2fs_init_compress_mempool(void) { return 0; }
+static inline void f2fs_destroy_compress_mempool(void) { }
 #endif
 
 static inline void set_compress_context(struct inode *inode)
@@ -3962,6 +4041,10 @@ static inline void f2fs_i_compr_blocks_update(struct inode *inode,
 {
 	int diff = F2FS_I(inode)->i_cluster_size - blocks;
 
+	/* don't update i_compr_blocks if saved blocks were released */
+	if (!add && !F2FS_I(inode)->i_compr_blocks)
+		return;
+
 	if (add) {
 		F2FS_I(inode)->i_compr_blocks += diff;
 		stat_add_compr_blocks(inode, diff);
@@ -4003,8 +4086,6 @@ static inline bool f2fs_force_buffered_io(struct inode *inode,
 		return true;
 	if (f2fs_is_multi_device(sbi))
 		return true;
-	if (f2fs_compressed_file(inode))
-		return true;
 	/*
 	 * for blkzoned device, fallback direct IO to buffered IO, so
 	 * all IOs can be serialized by log-structured write.