Merge tag 'f2fs-for-5.12-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "We've added two major features: 1) compression level and 2)
  checkpoint_merge, in this round.

  Compression level expands 'compress_algorithm' mount option to accept
  parameter as format of <algorithm>:<level>, by this way, it gives a
  way to allow user to do more specified config on lz4 and zstd
  compression level, then f2fs compression can provide higher compress
  ratio.

  checkpoint_merge creates a kernel daemon and makes it to merge
  concurrent checkpoint requests as much as possible to eliminate
  redundant checkpoint issues. Plus, we can eliminate the sluggish issue
  caused by slow checkpoint operation when the checkpoint is done in a
  process context in a cgroup having low i/o budget and cpu shares.

  Enhancements:
   - add compress level for lz4 and zstd in mount option
   - checkpoint_merge mount option
   - deprecate f2fs_trace_io

  Bug fixes:
   - flush data when enabling checkpoint back
   - handle corner cases of mount options
   - missing ACL update and lock for I_LINKABLE flag
   - attach FIEMAP_EXTENT_MERGED in f2fs_fiemap
   - fix potential deadlock in compression flow
   - fix wrong submit_io condition

  As usual, we've cleaned up many code flows and fixed minor bugs"

* tag 'f2fs-for-5.12-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (32 commits)
  Documentation: f2fs: fix typo s/automaic/automatic
  f2fs: give a warning only for readonly partition
  f2fs: don't grab superblock freeze for flush/ckpt thread
  f2fs: add ckpt_thread_ioprio sysfs node
  f2fs: introduce checkpoint_merge mount option
  f2fs: relocate inline conversion from mmap() to mkwrite()
  f2fs: fix a wrong condition in __submit_bio
  f2fs: remove unnecessary initialization in xattr.c
  f2fs: fix to avoid inconsistent quota data
  f2fs: flush data when enabling checkpoint back
  f2fs: deprecate f2fs_trace_io
  f2fs: Remove readahead collision detection
  f2fs: remove unused stat_{inc, dec}_atomic_write
  f2fs: introduce sb_status sysfs node
  f2fs: fix to use per-inode maxbytes
  f2fs: compress: fix potential deadlock
  libfs: unexport generic_ci_d_compare() and generic_ci_d_hash()
  f2fs: fix to set/clear I_LINKABLE under i_lock
  f2fs: fix null page reference in redirty_blocks
  f2fs: clean up post-read processing
  ...

1 files changed, 90 insertions, 14 deletions

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index bb11759191dc..2860003a09ed 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -97,6 +97,7 @@ extern const char *f2fs_fault_name[FAULT_MAX];
 #define F2FS_MOUNT_DISABLE_CHECKPOINT	0x02000000
 #define F2FS_MOUNT_NORECOVERY		0x04000000
 #define F2FS_MOUNT_ATGC			0x08000000
+#define F2FS_MOUNT_MERGE_CHECKPOINT	0x10000000
 
 #define F2FS_OPTION(sbi)	((sbi)->mount_opt)
 #define clear_opt(sbi, option)	(F2FS_OPTION(sbi).opt &= ~F2FS_MOUNT_##option)
@@ -146,6 +147,7 @@ struct f2fs_mount_info {
 	/* For compression */
 	unsigned char compress_algorithm;	/* algorithm type */
 	unsigned char compress_log_size;	/* cluster log size */
+	unsigned char compress_level;		/* compress level */
 	bool compress_chksum;			/* compressed data chksum */
 	unsigned char compress_ext_cnt;		/* extension count */
 	int compress_mode;			/* compression mode */
@@ -266,6 +268,26 @@ struct fsync_node_entry {
 	unsigned int seq_id;	/* sequence id */
 };
 
+struct ckpt_req {
+	struct completion wait;		/* completion for checkpoint done */
+	struct llist_node llnode;	/* llist_node to be linked in wait queue */
+	int ret;			/* return code of checkpoint */
+	ktime_t queue_time;		/* request queued time */
+};
+
+struct ckpt_req_control {
+	struct task_struct *f2fs_issue_ckpt;	/* checkpoint task */
+	int ckpt_thread_ioprio;			/* checkpoint merge thread ioprio */
+	wait_queue_head_t ckpt_wait_queue;	/* waiting queue for wake-up */
+	atomic_t issued_ckpt;		/* # of actually issued ckpts */
+	atomic_t total_ckpt;		/* # of total ckpts */
+	atomic_t queued_ckpt;		/* # of queued ckpts */
+	struct llist_head issue_list;	/* list for command issue */
+	spinlock_t stat_lock;		/* lock for below checkpoint time stats */
+	unsigned int cur_time;		/* cur wait time in msec for currently issued checkpoint */
+	unsigned int peak_time;		/* peak wait time in msec until now */
+};
+
 /* for the bitmap indicate blocks to be discarded */
 struct discard_entry {
 	struct list_head list;	/* list head */
@@ -717,7 +739,6 @@ struct f2fs_inode_info {
 	struct list_head inmem_pages;	/* inmemory pages managed by f2fs */
 	struct task_struct *inmem_task;	/* store inmemory task */
 	struct mutex inmem_lock;	/* lock for inmemory pages */
-	pgoff_t ra_offset;		/* ongoing readahead offset */
 	struct extent_tree *extent_tree;	/* cached extent_tree entry */
 
 	/* avoid racing between foreground op and gc */
@@ -735,6 +756,7 @@ 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 char i_compress_level;		/* compress level (lz4hc,zstd) */
 	unsigned short i_compress_flag;		/* compress flag */
 	unsigned int i_cluster_size;		/* cluster size */
 };
@@ -1310,6 +1332,8 @@ struct compress_data {
 
 #define F2FS_COMPRESSED_PAGE_MAGIC	0xF5F2C000
 
+#define	COMPRESS_LEVEL_OFFSET	8
+
 /* compress context */
 struct compress_ctx {
 	struct inode *inode;		/* inode the context belong to */
@@ -1337,7 +1361,7 @@ struct compress_io_ctx {
 	atomic_t pending_pages;		/* in-flight compressed page count */
 };
 
-/* decompress io context for read IO path */
+/* Context for decompressing one cluster on the read IO path */
 struct decompress_io_ctx {
 	u32 magic;			/* magic number to indicate page is compressed */
 	struct inode *inode;		/* inode the context belong to */
@@ -1353,11 +1377,37 @@ 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 */
-	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 */
+
+	/*
+	 * The number of compressed pages remaining to be read in this cluster.
+	 * This is initially nr_cpages.  It is decremented by 1 each time a page
+	 * has been read (or failed to be read).  When it reaches 0, the cluster
+	 * is decompressed (or an error is reported).
+	 *
+	 * If an error occurs before all the pages have been submitted for I/O,
+	 * then this will never reach 0.  In this case the I/O submitter is
+	 * responsible for calling f2fs_decompress_end_io() instead.
+	 */
+	atomic_t remaining_pages;
+
+	/*
+	 * Number of references to this decompress_io_ctx.
+	 *
+	 * One reference is held for I/O completion.  This reference is dropped
+	 * after the pagecache pages are updated and unlocked -- either after
+	 * decompression (and verity if enabled), or after an error.
+	 *
+	 * In addition, each compressed page holds a reference while it is in a
+	 * bio.  These references are necessary prevent compressed pages from
+	 * being freed while they are still in a bio.
+	 */
+	refcount_t refcnt;
+
+	bool failed;			/* IO error occurred before decompression? */
+	bool need_verity;		/* need fs-verity verification after decompression? */
 	void *private;			/* payload buffer for specified decompression algorithm */
 	void *private2;			/* extra payload buffer */
+	struct work_struct verity_work;	/* work to verify the decompressed pages */
 };
 
 #define NULL_CLUSTER			((unsigned int)(~0))
@@ -1404,6 +1454,7 @@ struct f2fs_sb_info {
 	wait_queue_head_t cp_wait;
 	unsigned long last_time[MAX_TIME];	/* to store time in jiffies */
 	long interval_time[MAX_TIME];		/* to store thresholds */
+	struct ckpt_req_control cprc_info;	/* for checkpoint request control */
 
 	struct inode_management im[MAX_INO_ENTRY];	/* manage inode cache */
 
@@ -1444,7 +1495,6 @@ struct f2fs_sb_info {
 	unsigned int total_sections;		/* total section count */
 	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 */
 	int dir_level;				/* directory level */
 	int readdir_ra;				/* readahead inode in readdir */
 	u64 max_io_bytes;			/* max io bytes to merge IOs */
@@ -1541,9 +1591,12 @@ struct f2fs_sb_info {
 	unsigned int node_io_flag;
 
 	/* For sysfs suppport */
-	struct kobject s_kobj;
+	struct kobject s_kobj;			/* /sys/fs/f2fs/<devname> */
 	struct completion s_kobj_unregister;
 
+	struct kobject s_stat_kobj;		/* /sys/fs/f2fs/<devname>/stat */
+	struct completion s_stat_kobj_unregister;
+
 	/* For shrinker support */
 	struct list_head s_list;
 	int s_ndevs;				/* number of devices */
@@ -3232,6 +3285,7 @@ int f2fs_inode_dirtied(struct inode *inode, bool sync);
 void f2fs_inode_synced(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);
 void f2fs_quota_off_umount(struct super_block *sb);
 int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover);
 int f2fs_sync_fs(struct super_block *sb, int sync);
@@ -3418,6 +3472,10 @@ 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);
 void f2fs_destroy_checkpoint_caches(void);
+int f2fs_issue_checkpoint(struct f2fs_sb_info *sbi);
+int f2fs_start_ckpt_thread(struct f2fs_sb_info *sbi);
+void f2fs_stop_ckpt_thread(struct f2fs_sb_info *sbi);
+void f2fs_init_ckpt_req_control(struct f2fs_sb_info *sbi);
 
 /*
  * data.c
@@ -3469,7 +3527,7 @@ int f2fs_write_single_data_page(struct page *page, int *submitted,
 				struct bio **bio, sector_t *last_block,
 				struct writeback_control *wbc,
 				enum iostat_type io_type,
-				int compr_blocks);
+				int compr_blocks, bool allow_balance);
 void f2fs_invalidate_page(struct page *page, unsigned int offset,
 			unsigned int length);
 int f2fs_release_page(struct page *page, gfp_t wait);
@@ -3530,6 +3588,8 @@ struct f2fs_stat_info {
 	int nr_discarding, nr_discarded;
 	int nr_discard_cmd;
 	unsigned int undiscard_blks;
+	int nr_issued_ckpt, nr_total_ckpt, nr_queued_ckpt;
+	unsigned int cur_ckpt_time, peak_ckpt_time;
 	int inline_xattr, inline_inode, inline_dir, append, update, orphans;
 	int compr_inode;
 	unsigned long long compr_blocks;
@@ -3715,8 +3775,6 @@ void f2fs_update_sit_info(struct f2fs_sb_info *sbi);
 #define stat_dec_compr_inode(inode)			do { } while (0)
 #define stat_add_compr_blocks(inode, blocks)		do { } while (0)
 #define stat_sub_compr_blocks(inode, blocks)		do { } while (0)
-#define stat_inc_atomic_write(inode)			do { } while (0)
-#define stat_dec_atomic_write(inode)			do { } while (0)
 #define stat_update_max_atomic_write(inode)		do { } while (0)
 #define stat_inc_volatile_write(inode)			do { } while (0)
 #define stat_dec_volatile_write(inode)			do { } while (0)
@@ -3876,7 +3934,7 @@ 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);
+void f2fs_end_read_compressed_page(struct page *page, bool failed);
 bool f2fs_cluster_is_empty(struct compress_ctx *cc);
 bool f2fs_cluster_can_merge_page(struct compress_ctx *cc, pgoff_t index);
 void f2fs_compress_ctx_add_page(struct compress_ctx *cc, struct page *page);
@@ -3889,9 +3947,8 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
 				unsigned nr_pages, sector_t *last_block_in_bio,
 				bool is_readahead, bool for_write);
 struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc);
-void f2fs_free_dic(struct decompress_io_ctx *dic);
-void f2fs_decompress_end_io(struct page **rpages,
-			unsigned int cluster_size, bool err, bool verity);
+void f2fs_decompress_end_io(struct decompress_io_ctx *dic, bool failed);
+void f2fs_put_page_dic(struct page *page);
 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);
@@ -3915,6 +3972,14 @@ 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 void f2fs_end_read_compressed_page(struct page *page, bool failed)
+{
+	WARN_ON_ONCE(1);
+}
+static inline void f2fs_put_page_dic(struct page *page)
+{
+	WARN_ON_ONCE(1);
+}
 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; }
@@ -3934,6 +3999,11 @@ static inline void set_compress_context(struct inode *inode)
 				1 << COMPRESS_CHKSUM : 0;
 	F2FS_I(inode)->i_cluster_size =
 			1 << F2FS_I(inode)->i_log_cluster_size;
+	if (F2FS_I(inode)->i_compress_algorithm == COMPRESS_LZ4 &&
+			F2FS_OPTION(sbi).compress_level)
+		F2FS_I(inode)->i_compress_flag |=
+				F2FS_OPTION(sbi).compress_level <<
+				COMPRESS_LEVEL_OFFSET;
 	F2FS_I(inode)->i_flags |= F2FS_COMPR_FL;
 	set_inode_flag(inode, FI_COMPRESSED_FILE);
 	stat_inc_compr_inode(inode);
@@ -4114,6 +4184,12 @@ static inline bool f2fs_force_buffered_io(struct inode *inode,
 	return false;
 }
 
+static inline bool f2fs_need_verity(const struct inode *inode, pgoff_t idx)
+{
+	return fsverity_active(inode) &&
+	       idx < DIV_ROUND_UP(inode->i_size, PAGE_SIZE);
+}
+
 #ifdef CONFIG_F2FS_FAULT_INJECTION
 extern void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate,
 							unsigned int type);