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
  ...

1 files changed, 84 insertions, 34 deletions

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 7c089ff7ff94..cb700d797296 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -98,6 +98,7 @@ extern const char *f2fs_fault_name[FAULT_MAX];
 #define F2FS_MOUNT_RESERVE_ROOT		0x01000000
 #define F2FS_MOUNT_DISABLE_CHECKPOINT	0x02000000
 #define F2FS_MOUNT_NORECOVERY		0x04000000
+#define F2FS_MOUNT_ATGC			0x08000000
 
 #define F2FS_OPTION(sbi)	((sbi)->mount_opt)
 #define clear_opt(sbi, option)	(F2FS_OPTION(sbi).opt &= ~F2FS_MOUNT_##option)
@@ -612,8 +613,13 @@ enum {
 
 struct rb_entry {
 	struct rb_node rb_node;		/* rb node located in rb-tree */
-	unsigned int ofs;		/* start offset of the entry */
-	unsigned int len;		/* length of the entry */
+	union {
+		struct {
+			unsigned int ofs;	/* start offset of the entry */
+			unsigned int len;	/* length of the entry */
+		};
+		unsigned long long key;		/* 64-bits key */
+	} __packed;
 };
 
 struct extent_info {
@@ -801,7 +807,7 @@ struct f2fs_inode_info {
 	struct timespec64 i_disk_time[4];/* inode disk times */
 
 	/* for file compress */
-	u64 i_compr_blocks;			/* # of compressed blocks */
+	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 int i_cluster_size;		/* cluster size */
@@ -973,7 +979,9 @@ static inline void set_new_dnode(struct dnode_of_data *dn, struct inode *inode,
  */
 #define	NR_CURSEG_DATA_TYPE	(3)
 #define NR_CURSEG_NODE_TYPE	(3)
-#define NR_CURSEG_TYPE	(NR_CURSEG_DATA_TYPE + NR_CURSEG_NODE_TYPE)
+#define NR_CURSEG_INMEM_TYPE	(2)
+#define NR_CURSEG_PERSIST_TYPE	(NR_CURSEG_DATA_TYPE + NR_CURSEG_NODE_TYPE)
+#define NR_CURSEG_TYPE		(NR_CURSEG_INMEM_TYPE + NR_CURSEG_PERSIST_TYPE)
 
 enum {
 	CURSEG_HOT_DATA	= 0,	/* directory entry blocks */
@@ -982,8 +990,11 @@ enum {
 	CURSEG_HOT_NODE,	/* direct node blocks of directory files */
 	CURSEG_WARM_NODE,	/* direct node blocks of normal files */
 	CURSEG_COLD_NODE,	/* indirect node blocks */
-	NO_CHECK_TYPE,
-	CURSEG_COLD_DATA_PINNED,/* cold data for pinned file */
+	NR_PERSISTENT_LOG,	/* number of persistent log */
+	CURSEG_COLD_DATA_PINNED = NR_PERSISTENT_LOG,
+				/* pinned file that needs consecutive block address */
+	CURSEG_ALL_DATA_ATGC,	/* SSR alloctor in hot/warm/cold data area */
+	NO_CHECK_TYPE,		/* number of persistent & inmem log */
 };
 
 struct flush_cmd {
@@ -1209,6 +1220,7 @@ struct f2fs_dev_info {
 #ifdef CONFIG_BLK_DEV_ZONED
 	unsigned int nr_blkz;		/* Total number of zones */
 	unsigned long *blkz_seq;	/* Bitmap indicating sequential zones */
+	block_t *zone_capacity_blocks;  /* Array of zone capacity in blks */
 #endif
 };
 
@@ -1228,6 +1240,18 @@ struct inode_management {
 	unsigned long ino_num;			/* number of entries */
 };
 
+/* for GC_AT */
+struct atgc_management {
+	bool atgc_enabled;			/* ATGC is enabled or not */
+	struct rb_root_cached root;		/* root of victim rb-tree */
+	struct list_head victim_list;		/* linked with all victim entries */
+	unsigned int victim_count;		/* victim count in rb-tree */
+	unsigned int candidate_ratio;		/* candidate ratio */
+	unsigned int max_candidate_count;	/* max candidate count */
+	unsigned int age_weight;		/* age weight, vblock_weight = 100 - age_weight */
+	unsigned long long age_threshold;	/* age threshold */
+};
+
 /* For s_flag in struct f2fs_sb_info */
 enum {
 	SBI_IS_DIRTY,				/* dirty flag for checkpoint */
@@ -1260,6 +1284,7 @@ enum {
 	GC_NORMAL,
 	GC_IDLE_CB,
 	GC_IDLE_GREEDY,
+	GC_IDLE_AT,
 	GC_URGENT_HIGH,
 	GC_URGENT_LOW,
 };
@@ -1303,9 +1328,9 @@ enum fsync_mode {
 #define DUMMY_WRITTEN_PAGE		((unsigned long)-2)
 
 #define IS_ATOMIC_WRITTEN_PAGE(page)			\
-		(page_private(page) == (unsigned long)ATOMIC_WRITTEN_PAGE)
+		(page_private(page) == ATOMIC_WRITTEN_PAGE)
 #define IS_DUMMY_WRITTEN_PAGE(page)			\
-		(page_private(page) == (unsigned long)DUMMY_WRITTEN_PAGE)
+		(page_private(page) == DUMMY_WRITTEN_PAGE)
 
 #ifdef CONFIG_F2FS_IO_TRACE
 #define IS_IO_TRACED_PAGE(page)			\
@@ -1359,7 +1384,7 @@ struct compress_io_ctx {
 	struct inode *inode;		/* inode the context belong to */
 	struct page **rpages;		/* pages store raw data in cluster */
 	unsigned int nr_rpages;		/* total page number in rpages */
-	refcount_t ref;			/* referrence count of raw page */
+	atomic_t pending_pages;		/* in-flight compressed page count */
 };
 
 /* decompress io context for read IO path */
@@ -1378,7 +1403,7 @@ struct decompress_io_ctx {
 	struct compress_data *cbuf;	/* virtual mapped address on cpages */
 	size_t rlen;			/* valid data length in rbuf */
 	size_t clen;			/* valid data length in cbuf */
-	refcount_t ref;			/* referrence count of compressed page */
+	atomic_t pending_pages;		/* in-flight compressed page count */
 	bool failed;			/* indicate IO error during decompression */
 	void *private;			/* payload buffer for specified decompression algorithm */
 	void *private2;			/* extra payload buffer */
@@ -1387,7 +1412,7 @@ struct decompress_io_ctx {
 #define NULL_CLUSTER			((unsigned int)(~0))
 #define MIN_COMPRESS_LOG_SIZE		2
 #define MAX_COMPRESS_LOG_SIZE		8
-#define MAX_COMPRESS_WINDOW_SIZE	((PAGE_SIZE) << MAX_COMPRESS_LOG_SIZE)
+#define MAX_COMPRESS_WINDOW_SIZE(log_size)	((PAGE_SIZE) << (log_size))
 
 struct f2fs_sb_info {
 	struct super_block *sb;			/* pointer to VFS super block */
@@ -1397,10 +1422,6 @@ struct f2fs_sb_info {
 	int valid_super_block;			/* valid super block no */
 	unsigned long s_flag;				/* flags for sbi */
 	struct mutex writepages;		/* mutex for writepages() */
-#ifdef CONFIG_UNICODE
-	struct unicode_map *s_encoding;
-	__u16 s_encoding_flags;
-#endif
 
 #ifdef CONFIG_BLK_DEV_ZONED
 	unsigned int blocks_per_blkz;		/* F2FS blocks per zone */
@@ -1508,6 +1529,7 @@ struct f2fs_sb_info {
 						 * race between GC and GC or CP
 						 */
 	struct f2fs_gc_kthread	*gc_thread;	/* GC thread */
+	struct atgc_management am;		/* atgc management */
 	unsigned int cur_victim_sec;		/* current victim section num */
 	unsigned int gc_mode;			/* current GC state */
 	unsigned int next_victim_seg[2];	/* next segment in victim section */
@@ -1544,7 +1566,7 @@ struct f2fs_sb_info {
 	atomic_t inline_inode;			/* # of inline_data inodes */
 	atomic_t inline_dir;			/* # of inline_dentry inodes */
 	atomic_t compr_inode;			/* # of compressed inodes */
-	atomic_t compr_blocks;			/* # of compressed blocks */
+	atomic64_t compr_blocks;		/* # of compressed blocks */
 	atomic_t vw_cnt;			/* # of volatile writes */
 	atomic_t max_aw_cnt;			/* max # of atomic writes */
 	atomic_t max_vw_cnt;			/* max # of volatile writes */
@@ -1593,6 +1615,11 @@ struct f2fs_sb_info {
 
 	struct kmem_cache *inline_xattr_slab;	/* inline xattr entry */
 	unsigned int inline_xattr_slab_size;	/* default inline xattr slab size */
+
+#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 */
+#endif
 };
 
 struct f2fs_private_dio {
@@ -3325,6 +3352,11 @@ block_t f2fs_get_unusable_blocks(struct f2fs_sb_info *sbi);
 int f2fs_disable_cp_again(struct f2fs_sb_info *sbi, block_t unusable);
 void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi);
 int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra);
+void f2fs_init_inmem_curseg(struct f2fs_sb_info *sbi);
+void f2fs_save_inmem_curseg(struct f2fs_sb_info *sbi);
+void f2fs_restore_inmem_curseg(struct f2fs_sb_info *sbi);
+void f2fs_get_new_segment(struct f2fs_sb_info *sbi,
+			unsigned int *newseg, bool new_sec, int dir);
 void f2fs_allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type,
 					unsigned int start, unsigned int end);
 void f2fs_allocate_new_segment(struct f2fs_sb_info *sbi, int type);
@@ -3343,7 +3375,8 @@ void f2fs_outplace_write_data(struct dnode_of_data *dn,
 int f2fs_inplace_write_data(struct f2fs_io_info *fio);
 void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 			block_t old_blkaddr, block_t new_blkaddr,
-			bool recover_curseg, bool recover_newaddr);
+			bool recover_curseg, bool recover_newaddr,
+			bool from_gc);
 void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn,
 			block_t old_addr, block_t new_addr,
 			unsigned char version, bool recover_curseg,
@@ -3371,6 +3404,10 @@ void f2fs_destroy_segment_manager_caches(void);
 int f2fs_rw_hint_to_seg_type(enum rw_hint hint);
 enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi,
 			enum page_type type, enum temp_type temp);
+unsigned int f2fs_usable_segs_in_sec(struct f2fs_sb_info *sbi,
+			unsigned int segno);
+unsigned int f2fs_usable_blks_in_seg(struct f2fs_sb_info *sbi,
+			unsigned int segno);
 
 /*
  * checkpoint.c
@@ -3378,7 +3415,7 @@ enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi,
 void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io);
 struct page *f2fs_grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index);
 struct page *f2fs_get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index);
-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 *f2fs_get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index);
 bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
 					block_t blkaddr, int type);
@@ -3486,6 +3523,8 @@ int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, bool background,
 			unsigned int segno);
 void f2fs_build_gc_manager(struct f2fs_sb_info *sbi);
 int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count);
+int __init f2fs_create_garbage_collection_cache(void);
+void f2fs_destroy_garbage_collection_cache(void);
 
 /*
  * recovery.c
@@ -3521,7 +3560,8 @@ struct f2fs_stat_info {
 	int nr_discard_cmd;
 	unsigned int undiscard_blks;
 	int inline_xattr, inline_inode, inline_dir, append, update, orphans;
-	int compr_inode, compr_blocks;
+	int compr_inode;
+	unsigned long long compr_blocks;
 	int aw_cnt, max_aw_cnt, vw_cnt, max_vw_cnt;
 	unsigned int valid_count, valid_node_count, valid_inode_count, discard_blks;
 	unsigned int bimodal, avg_vblocks;
@@ -3606,9 +3646,9 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
 			(atomic_dec(&F2FS_I_SB(inode)->compr_inode));	\
 	} while (0)
 #define stat_add_compr_blocks(inode, blocks)				\
-		(atomic_add(blocks, &F2FS_I_SB(inode)->compr_blocks))
+		(atomic64_add(blocks, &F2FS_I_SB(inode)->compr_blocks))
 #define stat_sub_compr_blocks(inode, blocks)				\
-		(atomic_sub(blocks, &F2FS_I_SB(inode)->compr_blocks))
+		(atomic64_sub(blocks, &F2FS_I_SB(inode)->compr_blocks))
 #define stat_inc_meta_count(sbi, blkaddr)				\
 	do {								\
 		if (blkaddr < SIT_I(sbi)->sit_base_addr)		\
@@ -3787,6 +3827,10 @@ void f2fs_leave_shrinker(struct f2fs_sb_info *sbi);
  */
 struct rb_entry *f2fs_lookup_rb_tree(struct rb_root_cached *root,
 				struct rb_entry *cached_re, unsigned int ofs);
+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 *left_most);
 struct rb_node **f2fs_lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi,
 				struct rb_root_cached *root,
 				struct rb_node **parent,
@@ -3797,7 +3841,7 @@ struct rb_entry *f2fs_lookup_rb_tree_ret(struct rb_root_cached *root,
 		struct rb_node ***insert_p, struct rb_node **insert_parent,
 		bool force, bool *leftmost);
 bool f2fs_check_rb_tree_consistence(struct f2fs_sb_info *sbi,
-						struct rb_root_cached *root);
+				struct rb_root_cached *root, bool check_key);
 unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink);
 void f2fs_init_extent_tree(struct inode *inode, struct page *ipage);
 void f2fs_drop_extent_tree(struct inode *inode);
@@ -3883,6 +3927,10 @@ void f2fs_decompress_end_io(struct page **rpages,
 int f2fs_init_compress_ctx(struct compress_ctx *cc);
 void f2fs_destroy_compress_ctx(struct compress_ctx *cc);
 void f2fs_init_compress_info(struct f2fs_sb_info *sbi);
+int f2fs_init_page_array_cache(struct f2fs_sb_info *sbi);
+void f2fs_destroy_page_array_cache(struct f2fs_sb_info *sbi);
+int __init f2fs_init_compress_cache(void);
+void f2fs_destroy_compress_cache(void);
 #else
 static inline bool f2fs_is_compressed_page(struct page *page) { return false; }
 static inline bool f2fs_is_compress_backend_ready(struct inode *inode)
@@ -3899,6 +3947,10 @@ static inline struct page *f2fs_compress_control_page(struct page *page)
 }
 static inline int f2fs_init_compress_mempool(void) { return 0; }
 static inline void f2fs_destroy_compress_mempool(void) { }
+static inline int f2fs_init_page_array_cache(struct f2fs_sb_info *sbi) { return 0; }
+static inline void f2fs_destroy_page_array_cache(struct f2fs_sb_info *sbi) { }
+static inline int __init f2fs_init_compress_cache(void) { return 0; }
+static inline void f2fs_destroy_compress_cache(void) { }
 #endif
 
 static inline void set_compress_context(struct inode *inode)
@@ -3917,24 +3969,21 @@ static inline void set_compress_context(struct inode *inode)
 	f2fs_mark_inode_dirty_sync(inode, true);
 }
 
-static inline u64 f2fs_disable_compressed_file(struct inode *inode)
+static inline bool f2fs_disable_compressed_file(struct inode *inode)
 {
 	struct f2fs_inode_info *fi = F2FS_I(inode);
 
 	if (!f2fs_compressed_file(inode))
-		return 0;
-	if (S_ISREG(inode->i_mode)) {
-		if (get_dirty_pages(inode))
-			return 1;
-		if (fi->i_compr_blocks)
-			return fi->i_compr_blocks;
-	}
+		return true;
+	if (S_ISREG(inode->i_mode) &&
+		(get_dirty_pages(inode) || atomic_read(&fi->i_compr_blocks)))
+		return false;
 
 	fi->i_flags &= ~F2FS_COMPR_FL;
 	stat_dec_compr_inode(inode);
 	clear_inode_flag(inode, FI_COMPRESSED_FILE);
 	f2fs_mark_inode_dirty_sync(inode, true);
-	return 0;
+	return true;
 }
 
 #define F2FS_FEATURE_FUNCS(name, flagname) \
@@ -4028,16 +4077,17 @@ static inline void f2fs_i_compr_blocks_update(struct inode *inode,
 						u64 blocks, bool add)
 {
 	int diff = F2FS_I(inode)->i_cluster_size - blocks;
+	struct f2fs_inode_info *fi = F2FS_I(inode);
 
 	/* don't update i_compr_blocks if saved blocks were released */
-	if (!add && !F2FS_I(inode)->i_compr_blocks)
+	if (!add && !atomic_read(&fi->i_compr_blocks))
 		return;
 
 	if (add) {
-		F2FS_I(inode)->i_compr_blocks += diff;
+		atomic_add(diff, &fi->i_compr_blocks);
 		stat_add_compr_blocks(inode, diff);
 	} else {
-		F2FS_I(inode)->i_compr_blocks -= diff;
+		atomic_sub(diff, &fi->i_compr_blocks);
 		stat_sub_compr_blocks(inode, diff);
 	}
 	f2fs_mark_inode_dirty_sync(inode, true);