Merge tag 'f2fs-for-5.18' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this cycle, f2fs has some performance improvements for Android
  workloads such as using read-unfair rwsems and adding some sysfs
  entries to control GCs and discard commands in more details. In
  addtiion, it has some tunings to improve the recovery speed after
  sudden power-cut.

  Enhancement:
   - add reader-unfair rwsems with F2FS_UNFAIR_RWSEM: will replace with
     generic API support
   - adjust to make the readahead/recovery flow more efficiently
   - sysfs entries to control issue speeds of GCs and Discard commands
   - enable idmapped mounts

  Bug fix:
   - correct wrong error handling routines
   - fix missing conditions in quota
   - fix a potential deadlock between writeback and block plug routines
   - fix a deadlock btween freezefs and evict_inode

  We've added some boundary checks to avoid kernel panics on corrupted
  images, and several minor code clean-ups"

* tag 'f2fs-for-5.18' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (27 commits)
  f2fs: fix to do sanity check on .cp_pack_total_block_count
  f2fs: make gc_urgent and gc_segment_mode sysfs node readable
  f2fs: use aggressive GC policy during f2fs_disable_checkpoint()
  f2fs: fix compressed file start atomic write may cause data corruption
  f2fs: initialize sbi->gc_mode explicitly
  f2fs: introduce gc_urgent_mid mode
  f2fs: compress: fix to print raw data size in error path of lz4 decompression
  f2fs: remove redundant parameter judgment
  f2fs: use spin_lock to avoid hang
  f2fs: don't get FREEZE lock in f2fs_evict_inode in frozen fs
  f2fs: remove unnecessary read for F2FS_FITS_IN_INODE
  f2fs: introduce F2FS_UNFAIR_RWSEM to support unfair rwsem
  f2fs: avoid an infinite loop in f2fs_sync_dirty_inodes
  f2fs: fix to do sanity check on curseg->alloc_type
  f2fs: fix to avoid potential deadlock
  f2fs: quota: fix loop condition at f2fs_quota_sync()
  f2fs: Restore rwsem lockdep support
  f2fs: fix missing free nid in f2fs_handle_failed_inode
  f2fs: support idmapped mounts
  f2fs: add a way to limit roll forward recovery time
  ...

1 files changed, 131 insertions, 23 deletions

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index c2c89b03df1e..9c72a91912ae 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -123,6 +123,20 @@ typedef u32 nid_t;
 
 #define COMPRESS_EXT_NUM		16
 
+/*
+ * An implementation of an rwsem that is explicitly unfair to readers. This
+ * prevents priority inversion when a low-priority reader acquires the read lock
+ * while sleeping on the write lock but the write lock is needed by
+ * higher-priority clients.
+ */
+
+struct f2fs_rwsem {
+        struct rw_semaphore internal_rwsem;
+#ifdef CONFIG_F2FS_UNFAIR_RWSEM
+        wait_queue_head_t read_waiters;
+#endif
+};
+
 struct f2fs_mount_info {
 	unsigned int opt;
 	int write_io_size_bits;		/* Write IO size bits */
@@ -386,6 +400,10 @@ struct discard_cmd_control {
 	struct mutex cmd_lock;
 	unsigned int nr_discards;		/* # of discards in the list */
 	unsigned int max_discards;		/* max. discards to be issued */
+	unsigned int max_discard_request;	/* max. discard request per round */
+	unsigned int min_discard_issue_time;	/* min. interval between discard issue */
+	unsigned int mid_discard_issue_time;	/* mid. interval between discard issue */
+	unsigned int max_discard_issue_time;	/* max. interval between discard issue */
 	unsigned int discard_granularity;	/* discard granularity */
 	unsigned int undiscard_blks;		/* # of undiscard blocks */
 	unsigned int next_pos;			/* next discard position */
@@ -561,6 +579,9 @@ enum {
 /* maximum retry quota flush count */
 #define DEFAULT_RETRY_QUOTA_FLUSH_COUNT		8
 
+/* maximum retry of EIO'ed meta page */
+#define MAX_RETRY_META_PAGE_EIO			100
+
 #define F2FS_LINK_MAX	0xffffffff	/* maximum link count per file */
 
 #define MAX_DIR_RA_PAGES	4	/* maximum ra pages of dir */
@@ -574,6 +595,9 @@ enum {
 /* number of extent info in extent cache we try to shrink */
 #define EXTENT_CACHE_SHRINK_NUMBER	128
 
+#define RECOVERY_MAX_RA_BLOCKS		BIO_MAX_VECS
+#define RECOVERY_MIN_RA_BLOCKS		1
+
 struct rb_entry {
 	struct rb_node rb_node;		/* rb node located in rb-tree */
 	union {
@@ -721,7 +745,8 @@ enum {
 	FI_DROP_CACHE,		/* drop dirty page cache */
 	FI_DATA_EXIST,		/* indicate data exists */
 	FI_INLINE_DOTS,		/* indicate inline dot dentries */
-	FI_DO_DEFRAG,		/* indicate defragment is running */
+	FI_SKIP_WRITES,		/* should skip data page writeback */
+	FI_OPU_WRITE,		/* used for opu per file */
 	FI_DIRTY_FILE,		/* indicate regular/symlink has dirty pages */
 	FI_PREALLOCATED_ALL,	/* all blocks for write were preallocated */
 	FI_HOT_DATA,		/* indicate file is hot */
@@ -752,7 +777,7 @@ struct f2fs_inode_info {
 
 	/* Use below internally in f2fs*/
 	unsigned long flags[BITS_TO_LONGS(FI_MAX)];	/* use to pass per-file flags */
-	struct rw_semaphore i_sem;	/* protect fi info */
+	struct f2fs_rwsem i_sem;	/* protect fi info */
 	atomic_t dirty_pages;		/* # of dirty pages */
 	f2fs_hash_t chash;		/* hash value of given file name */
 	unsigned int clevel;		/* maximum level of given file name */
@@ -777,8 +802,8 @@ struct f2fs_inode_info {
 	struct extent_tree *extent_tree;	/* cached extent_tree entry */
 
 	/* avoid racing between foreground op and gc */
-	struct rw_semaphore i_gc_rwsem[2];
-	struct rw_semaphore i_xattr_sem; /* avoid racing between reading and changing EAs */
+	struct f2fs_rwsem i_gc_rwsem[2];
+	struct f2fs_rwsem i_xattr_sem; /* avoid racing between reading and changing EAs */
 
 	int i_extra_isize;		/* size of extra space located in i_addr */
 	kprojid_t i_projid;		/* id for project quota */
@@ -897,6 +922,7 @@ struct f2fs_nm_info {
 	nid_t max_nid;			/* maximum possible node ids */
 	nid_t available_nids;		/* # of available node ids */
 	nid_t next_scan_nid;		/* the next nid to be scanned */
+	nid_t max_rf_node_blocks;	/* max # of nodes for recovery */
 	unsigned int ram_thresh;	/* control the memory footprint */
 	unsigned int ra_nid_pages;	/* # of nid pages to be readaheaded */
 	unsigned int dirty_nats_ratio;	/* control dirty nats ratio threshold */
@@ -904,7 +930,7 @@ struct f2fs_nm_info {
 	/* NAT cache management */
 	struct radix_tree_root nat_root;/* root of the nat entry cache */
 	struct radix_tree_root nat_set_root;/* root of the nat set cache */
-	struct rw_semaphore nat_tree_lock;	/* protect nat entry tree */
+	struct f2fs_rwsem nat_tree_lock;	/* protect nat entry tree */
 	struct list_head nat_entries;	/* cached nat entry list (clean) */
 	spinlock_t nat_list_lock;	/* protect clean nat entry list */
 	unsigned int nat_cnt[MAX_NAT_STATE]; /* the # of cached nat entries */
@@ -1017,7 +1043,7 @@ struct f2fs_sm_info {
 	struct dirty_seglist_info *dirty_info;	/* dirty segment information */
 	struct curseg_info *curseg_array;	/* active segment information */
 
-	struct rw_semaphore curseg_lock;	/* for preventing curseg change */
+	struct f2fs_rwsem curseg_lock;	/* for preventing curseg change */
 
 	block_t seg0_blkaddr;		/* block address of 0'th segment */
 	block_t main_blkaddr;		/* start block address of main area */
@@ -1201,11 +1227,11 @@ struct f2fs_bio_info {
 	struct bio *bio;		/* bios to merge */
 	sector_t last_block_in_bio;	/* last block number */
 	struct f2fs_io_info fio;	/* store buffered io info. */
-	struct rw_semaphore io_rwsem;	/* blocking op for bio */
+	struct f2fs_rwsem io_rwsem;	/* blocking op for bio */
 	spinlock_t io_lock;		/* serialize DATA/NODE IOs */
 	struct list_head io_list;	/* track fios */
 	struct list_head bio_list;	/* bio entry list head */
-	struct rw_semaphore bio_list_lock;	/* lock to protect bio entry list */
+	struct f2fs_rwsem bio_list_lock;	/* lock to protect bio entry list */
 };
 
 #define FDEV(i)				(sbi->devs[i])
@@ -1267,6 +1293,7 @@ enum {
 	SBI_QUOTA_SKIP_FLUSH,			/* skip flushing quota in current CP */
 	SBI_QUOTA_NEED_REPAIR,			/* quota file may be corrupted */
 	SBI_IS_RESIZEFS,			/* resizefs is in process */
+	SBI_IS_FREEZING,			/* freezefs is in process */
 };
 
 enum {
@@ -1286,6 +1313,7 @@ enum {
 	GC_IDLE_AT,
 	GC_URGENT_HIGH,
 	GC_URGENT_LOW,
+	GC_URGENT_MID,
 	MAX_GC_MODE,
 };
 
@@ -1571,7 +1599,7 @@ struct f2fs_sb_info {
 	struct super_block *sb;			/* pointer to VFS super block */
 	struct proc_dir_entry *s_proc;		/* proc entry */
 	struct f2fs_super_block *raw_super;	/* raw super block pointer */
-	struct rw_semaphore sb_lock;		/* lock for raw super block */
+	struct f2fs_rwsem sb_lock;		/* lock for raw super block */
 	int valid_super_block;			/* valid super block no */
 	unsigned long s_flag;				/* flags for sbi */
 	struct mutex writepages;		/* mutex for writepages() */
@@ -1591,18 +1619,20 @@ struct f2fs_sb_info {
 	/* for bio operations */
 	struct f2fs_bio_info *write_io[NR_PAGE_TYPE];	/* for write bios */
 	/* keep migration IO order for LFS mode */
-	struct rw_semaphore io_order_lock;
+	struct f2fs_rwsem io_order_lock;
 	mempool_t *write_io_dummy;		/* Dummy pages */
+	pgoff_t metapage_eio_ofs;		/* EIO page offset */
+	int metapage_eio_cnt;			/* EIO count */
 
 	/* for checkpoint */
 	struct f2fs_checkpoint *ckpt;		/* raw checkpoint pointer */
 	int cur_cp_pack;			/* remain current cp pack */
 	spinlock_t cp_lock;			/* for flag in ckpt */
 	struct inode *meta_inode;		/* cache meta blocks */
-	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 */
+	struct f2fs_rwsem cp_global_sem;	/* checkpoint procedure lock */
+	struct f2fs_rwsem cp_rwsem;		/* blocking FS operations */
+	struct f2fs_rwsem node_write;		/* locking node writes */
+	struct f2fs_rwsem node_change;	/* locking node change */
 	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 */
@@ -1662,12 +1692,14 @@ struct f2fs_sb_info {
 	block_t unusable_block_count;		/* # of blocks saved by last cp */
 
 	unsigned int nquota_files;		/* # of quota sysfile */
-	struct rw_semaphore quota_sem;		/* blocking cp for flags */
+	struct f2fs_rwsem quota_sem;		/* blocking cp for flags */
 
 	/* # of pages, see count_type */
 	atomic_t nr_pages[NR_COUNT_TYPE];
 	/* # of allocated blocks */
 	struct percpu_counter alloc_valid_block_count;
+	/* # of node block writes as roll forward recovery */
+	struct percpu_counter rf_node_block_count;
 
 	/* writeback control */
 	atomic_t wb_sync_req[META];	/* count # of WB_SYNC threads */
@@ -1678,7 +1710,7 @@ struct f2fs_sb_info {
 	struct f2fs_mount_info mount_opt;	/* mount options */
 
 	/* for cleaning operations */
-	struct rw_semaphore gc_lock;		/*
+	struct f2fs_rwsem gc_lock;		/*
 						 * semaphore for GC, avoid
 						 * race between GC and GC or CP
 						 */
@@ -1698,7 +1730,7 @@ struct f2fs_sb_info {
 
 	/* threshold for gc trials on pinned files */
 	u64 gc_pin_file_threshold;
-	struct rw_semaphore pin_sem;
+	struct f2fs_rwsem pin_sem;
 
 	/* maximum # of trials to find a victim segment for SSR and GC */
 	unsigned int max_victim_search;
@@ -2092,9 +2124,81 @@ static inline void clear_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f)
 	spin_unlock_irqrestore(&sbi->cp_lock, flags);
 }
 
+#define init_f2fs_rwsem(sem)					\
+do {								\
+	static struct lock_class_key __key;			\
+								\
+	__init_f2fs_rwsem((sem), #sem, &__key);			\
+} while (0)
+
+static inline void __init_f2fs_rwsem(struct f2fs_rwsem *sem,
+		const char *sem_name, struct lock_class_key *key)
+{
+	__init_rwsem(&sem->internal_rwsem, sem_name, key);
+#ifdef CONFIG_F2FS_UNFAIR_RWSEM
+	init_waitqueue_head(&sem->read_waiters);
+#endif
+}
+
+static inline int f2fs_rwsem_is_locked(struct f2fs_rwsem *sem)
+{
+	return rwsem_is_locked(&sem->internal_rwsem);
+}
+
+static inline int f2fs_rwsem_is_contended(struct f2fs_rwsem *sem)
+{
+	return rwsem_is_contended(&sem->internal_rwsem);
+}
+
+static inline void f2fs_down_read(struct f2fs_rwsem *sem)
+{
+#ifdef CONFIG_F2FS_UNFAIR_RWSEM
+	wait_event(sem->read_waiters, down_read_trylock(&sem->internal_rwsem));
+#else
+	down_read(&sem->internal_rwsem);
+#endif
+}
+
+static inline int f2fs_down_read_trylock(struct f2fs_rwsem *sem)
+{
+	return down_read_trylock(&sem->internal_rwsem);
+}
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+static inline void f2fs_down_read_nested(struct f2fs_rwsem *sem, int subclass)
+{
+	down_read_nested(&sem->internal_rwsem, subclass);
+}
+#else
+#define f2fs_down_read_nested(sem, subclass) f2fs_down_read(sem)
+#endif
+
+static inline void f2fs_up_read(struct f2fs_rwsem *sem)
+{
+	up_read(&sem->internal_rwsem);
+}
+
+static inline void f2fs_down_write(struct f2fs_rwsem *sem)
+{
+	down_write(&sem->internal_rwsem);
+}
+
+static inline int f2fs_down_write_trylock(struct f2fs_rwsem *sem)
+{
+	return down_write_trylock(&sem->internal_rwsem);
+}
+
+static inline void f2fs_up_write(struct f2fs_rwsem *sem)
+{
+	up_write(&sem->internal_rwsem);
+#ifdef CONFIG_F2FS_UNFAIR_RWSEM
+	wake_up_all(&sem->read_waiters);
+#endif
+}
+
 static inline void f2fs_lock_op(struct f2fs_sb_info *sbi)
 {
-	down_read(&sbi->cp_rwsem);
+	f2fs_down_read(&sbi->cp_rwsem);
 }
 
 static inline int f2fs_trylock_op(struct f2fs_sb_info *sbi)
@@ -2103,22 +2207,22 @@ static inline int f2fs_trylock_op(struct f2fs_sb_info *sbi)
 		f2fs_show_injection_info(sbi, FAULT_LOCK_OP);
 		return 0;
 	}
-	return down_read_trylock(&sbi->cp_rwsem);
+	return f2fs_down_read_trylock(&sbi->cp_rwsem);
 }
 
 static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi)
 {
-	up_read(&sbi->cp_rwsem);
+	f2fs_up_read(&sbi->cp_rwsem);
 }
 
 static inline void f2fs_lock_all(struct f2fs_sb_info *sbi)
 {
-	down_write(&sbi->cp_rwsem);
+	f2fs_down_write(&sbi->cp_rwsem);
 }
 
 static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi)
 {
-	up_write(&sbi->cp_rwsem);
+	f2fs_up_write(&sbi->cp_rwsem);
 }
 
 static inline int __get_cp_reason(struct f2fs_sb_info *sbi)
@@ -2681,6 +2785,9 @@ static inline bool is_idle(struct f2fs_sb_info *sbi, int type)
 	if (is_inflight_io(sbi, type))
 		return false;
 
+	if (sbi->gc_mode == GC_URGENT_MID)
+		return true;
+
 	if (sbi->gc_mode == GC_URGENT_LOW &&
 			(type == DISCARD_TIME || type == GC_TIME))
 		return true;
@@ -3579,7 +3686,8 @@ bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
 					block_t blkaddr, int type);
 int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
 			int type, bool sync);
-void f2fs_ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index);
+void f2fs_ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index,
+							unsigned int ra_blocks);
 long f2fs_sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
 			long nr_to_write, enum iostat_type io_type);
 void f2fs_add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type);