Merge tag 'f2fs-for-5.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this cycle, we've addressed some performance issues such as lock
  contention, misbehaving compress_cache, allowing extent_cache for
  compressed files, and new sysfs to adjust ra_size for fadvise.

  In order to diagnose the performance issues quickly, we also added an
  iostat which shows the IO latencies periodically.

  On the stability side, we've found two memory leakage cases in the
  error path in compression flow. And, we've also fixed various corner
  cases in fiemap, quota, checkpoint=disable, zstd, and so on.

  Enhancements:
   - avoid long checkpoint latency by releasing nat_tree_lock
   - collect and show iostats periodically
   - support extent_cache for compressed files
   - add a sysfs entry to manage ra_size given fadvise(POSIX_FADV_SEQUENTIAL)
   - report f2fs GC status via sysfs
   - add discard_unit=%s in mount option to handle zoned device

  Bug fixes:
   - fix two memory leakages when an error happens in the compressed IO flow
   - fix commpress_cache to get the right LBA
   - fix fiemap to deal with compressed case correctly
   - fix wrong EIO returns due to SBI_NEED_FSCK
   - fix missing writes when enabling checkpoint back
   - fix quota deadlock
   - fix zstd level mount option

  In addition to the above major updates, we've cleaned up several code
  paths such as dio, unnecessary operations, debugfs/f2fs/status, sanity
  check, and typos"

* tag 'f2fs-for-5.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (46 commits)
  f2fs: should put a page beyond EOF when preparing a write
  f2fs: deallocate compressed pages when error happens
  f2fs: enable realtime discard iff device supports discard
  f2fs: guarantee to write dirty data when enabling checkpoint back
  f2fs: fix to unmap pages from userspace process in punch_hole()
  f2fs: fix unexpected ENOENT comes from f2fs_map_blocks()
  f2fs: fix to account missing .skipped_gc_rwsem
  f2fs: adjust unlock order for cleanup
  f2fs: Don't create discard thread when device doesn't support realtime discard
  f2fs: rebuild nat_bits during umount
  f2fs: introduce periodic iostat io latency traces
  f2fs: separate out iostat feature
  f2fs: compress: do sanity check on cluster
  f2fs: fix description about main_blkaddr node
  f2fs: convert S_IRUGO to 0444
  f2fs: fix to keep compatibility of fault injection interface
  f2fs: support fault injection for f2fs_kmem_cache_alloc()
  f2fs: compress: allow write compress released file after truncate to zero
  f2fs: correct comment in segment.h
  f2fs: improve sbi status info in debugfs/f2fs/status
  ...

1 files changed, 85 insertions, 92 deletions

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 906b2c4b50e7..b339ae89c1ad 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -43,6 +43,7 @@ enum {
 	FAULT_KVMALLOC,
 	FAULT_PAGE_ALLOC,
 	FAULT_PAGE_GET,
+	FAULT_ALLOC_BIO,	/* it's obsolete due to bio_alloc() will never fail */
 	FAULT_ALLOC_NID,
 	FAULT_ORPHAN,
 	FAULT_BLOCK,
@@ -53,6 +54,7 @@ enum {
 	FAULT_CHECKPOINT,
 	FAULT_DISCARD,
 	FAULT_WRITE_IO,
+	FAULT_SLAB_ALLOC,
 	FAULT_MAX,
 };
 
@@ -139,6 +141,11 @@ struct f2fs_mount_info {
 	int fsync_mode;			/* fsync policy */
 	int fs_mode;			/* fs mode: LFS or ADAPTIVE */
 	int bggc_mode;			/* bggc mode: off, on or sync */
+	int discard_unit;		/*
+					 * discard command's offset/size should
+					 * be aligned to this unit: block,
+					 * segment or section
+					 */
 	struct fscrypt_dummy_policy dummy_enc_policy; /* test dummy encryption */
 	block_t unusable_cap_perc;	/* percentage for cap */
 	block_t unusable_cap;		/* Amount of space allowed to be
@@ -542,7 +549,7 @@ enum {
 					 */
 };
 
-#define DEFAULT_RETRY_IO_COUNT	8	/* maximum retry read IO count */
+#define DEFAULT_RETRY_IO_COUNT	8	/* maximum retry read IO or flush count */
 
 /* congestion wait timeout value, default: 20ms */
 #define	DEFAULT_IO_TIMEOUT	(msecs_to_jiffies(20))
@@ -575,6 +582,9 @@ struct extent_info {
 	unsigned int fofs;		/* start offset in a file */
 	unsigned int len;		/* length of the extent */
 	u32 blk;			/* start block address of the extent */
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+	unsigned int c_len;		/* physical extent length of compressed blocks */
+#endif
 };
 
 struct extent_node {
@@ -793,6 +803,9 @@ static inline void set_extent_info(struct extent_info *ei, unsigned int fofs,
 	ei->fofs = fofs;
 	ei->blk = blk;
 	ei->len = len;
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+	ei->c_len = 0;
+#endif
 }
 
 static inline bool __is_discard_mergeable(struct discard_info *back,
@@ -817,6 +830,12 @@ static inline bool __is_discard_front_mergeable(struct discard_info *cur,
 static inline bool __is_extent_mergeable(struct extent_info *back,
 						struct extent_info *front)
 {
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+	if (back->c_len && back->len != back->c_len)
+		return false;
+	if (front->c_len && front->len != front->c_len)
+		return false;
+#endif
 	return (back->fofs + back->len == front->fofs &&
 			back->blk + back->len == front->blk);
 }
@@ -1252,6 +1271,7 @@ enum {
 	GC_IDLE_AT,
 	GC_URGENT_HIGH,
 	GC_URGENT_LOW,
+	MAX_GC_MODE,
 };
 
 enum {
@@ -1297,6 +1317,12 @@ enum {
 				 */
 };
 
+enum {
+	DISCARD_UNIT_BLOCK,	/* basic discard unit is block */
+	DISCARD_UNIT_SEGMENT,	/* basic discard unit is segment */
+	DISCARD_UNIT_SECTION,	/* basic discard unit is section */
+};
+
 static inline int f2fs_test_bit(unsigned int nr, char *addr);
 static inline void f2fs_set_bit(unsigned int nr, char *addr);
 static inline void f2fs_clear_bit(unsigned int nr, char *addr);
@@ -1686,14 +1712,6 @@ struct f2fs_sb_info {
 #endif
 	spinlock_t stat_lock;			/* lock for stat operations */
 
-	/* For app/fs IO statistics */
-	spinlock_t iostat_lock;
-	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;
@@ -1732,6 +1750,12 @@ struct f2fs_sb_info {
 	struct kmem_cache *inline_xattr_slab;	/* inline xattr entry */
 	unsigned int inline_xattr_slab_size;	/* default inline xattr slab size */
 
+	/* For reclaimed segs statistics per each GC mode */
+	unsigned int gc_segment_mode;		/* GC state for reclaimed segments */
+	unsigned int gc_reclaimed_segs[MAX_GC_MODE];	/* Reclaimed segs for each mode */
+
+	unsigned long seq_file_ra_mul;		/* multiplier for ra_pages of seq. files in fadvise */
+
 #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 */
@@ -1747,6 +1771,20 @@ struct f2fs_sb_info {
 	unsigned int compress_watermark;	/* cache page watermark */
 	atomic_t compress_page_hit;		/* cache hit count */
 #endif
+
+#ifdef CONFIG_F2FS_IOSTAT
+	/* For app/fs IO statistics */
+	spinlock_t iostat_lock;
+	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;
+
+	/* For io latency related statistics info in one iostat period */
+	spinlock_t iostat_lat_lock;
+	struct iostat_lat_info *iostat_io_lat;
+#endif
 };
 
 struct f2fs_private_dio {
@@ -2034,36 +2072,6 @@ static inline void clear_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f)
 	spin_unlock_irqrestore(&sbi->cp_lock, flags);
 }
 
-static inline void disable_nat_bits(struct f2fs_sb_info *sbi, bool lock)
-{
-	unsigned long flags;
-	unsigned char *nat_bits;
-
-	/*
-	 * In order to re-enable nat_bits we need to call fsck.f2fs by
-	 * set_sbi_flag(sbi, SBI_NEED_FSCK). But it may give huge cost,
-	 * so let's rely on regular fsck or unclean shutdown.
-	 */
-
-	if (lock)
-		spin_lock_irqsave(&sbi->cp_lock, flags);
-	__clear_ckpt_flags(F2FS_CKPT(sbi), CP_NAT_BITS_FLAG);
-	nat_bits = NM_I(sbi)->nat_bits;
-	NM_I(sbi)->nat_bits = NULL;
-	if (lock)
-		spin_unlock_irqrestore(&sbi->cp_lock, flags);
-
-	kvfree(nat_bits);
-}
-
-static inline bool enabled_nat_bits(struct f2fs_sb_info *sbi,
-					struct cp_control *cpc)
-{
-	bool set = is_set_ckpt_flags(sbi, CP_NAT_BITS_FLAG);
-
-	return (cpc) ? (cpc->reason & CP_UMOUNT) && set : set;
-}
-
 static inline void f2fs_lock_op(struct f2fs_sb_info *sbi)
 {
 	down_read(&sbi->cp_rwsem);
@@ -2587,7 +2595,7 @@ static inline struct kmem_cache *f2fs_kmem_cache_create(const char *name,
 	return kmem_cache_create(name, size, 0, SLAB_RECLAIM_ACCOUNT, NULL);
 }
 
-static inline void *f2fs_kmem_cache_alloc(struct kmem_cache *cachep,
+static inline void *f2fs_kmem_cache_alloc_nofail(struct kmem_cache *cachep,
 						gfp_t flags)
 {
 	void *entry;
@@ -2598,6 +2606,20 @@ static inline void *f2fs_kmem_cache_alloc(struct kmem_cache *cachep,
 	return entry;
 }
 
+static inline void *f2fs_kmem_cache_alloc(struct kmem_cache *cachep,
+			gfp_t flags, bool nofail, struct f2fs_sb_info *sbi)
+{
+	if (nofail)
+		return f2fs_kmem_cache_alloc_nofail(cachep, flags);
+
+	if (time_to_inject(sbi, FAULT_SLAB_ALLOC)) {
+		f2fs_show_injection_info(sbi, FAULT_SLAB_ALLOC);
+		return NULL;
+	}
+
+	return kmem_cache_alloc(cachep, flags);
+}
+
 static inline bool is_inflight_io(struct f2fs_sb_info *sbi, int type)
 {
 	if (get_pages(sbi, F2FS_RD_DATA) || get_pages(sbi, F2FS_RD_NODE) ||
@@ -3210,47 +3232,6 @@ 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->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->rw_iostat[type] += io_bytes;
-
-	if (type == APP_WRITE_IO || type == 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)
 
 #define __is_meta_io(fio) (PAGE_TYPE_OF_BIO((fio)->type) == META)
@@ -3417,6 +3398,7 @@ int f2fs_truncate_inode_blocks(struct inode *inode, pgoff_t from);
 int f2fs_truncate_xattr_node(struct inode *inode);
 int f2fs_wait_on_node_pages_writeback(struct f2fs_sb_info *sbi,
 					unsigned int seq_id);
+bool f2fs_nat_bitmap_enabled(struct f2fs_sb_info *sbi);
 int f2fs_remove_inode_page(struct inode *inode);
 struct page *f2fs_new_inode_page(struct inode *inode);
 struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs);
@@ -3441,6 +3423,7 @@ int f2fs_recover_xattr_data(struct inode *inode, struct page *page);
 int f2fs_recover_inode_page(struct f2fs_sb_info *sbi, struct page *page);
 int f2fs_restore_node_summary(struct f2fs_sb_info *sbi,
 			unsigned int segno, struct f2fs_summary_block *sum);
+void f2fs_enable_nat_bits(struct f2fs_sb_info *sbi);
 int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
 int f2fs_build_node_manager(struct f2fs_sb_info *sbi);
 void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi);
@@ -3464,6 +3447,7 @@ int f2fs_flush_device_cache(struct f2fs_sb_info *sbi);
 void f2fs_destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free);
 void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr);
 bool f2fs_is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr);
+int f2fs_start_discard_thread(struct f2fs_sb_info *sbi);
 void f2fs_drop_discard_cmd(struct f2fs_sb_info *sbi);
 void f2fs_stop_discard_thread(struct f2fs_sb_info *sbi);
 bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi);
@@ -3986,6 +3970,9 @@ void f2fs_destroy_extent_cache(void);
 /*
  * sysfs.c
  */
+#define MIN_RA_MUL	2
+#define MAX_RA_MUL	256
+
 int __init f2fs_init_sysfs(void);
 void f2fs_exit_sysfs(void);
 int f2fs_register_sysfs(struct f2fs_sb_info *sbi);
@@ -4040,18 +4027,23 @@ void f2fs_end_read_compressed_page(struct page *page, bool failed,
 							block_t blkaddr);
 bool f2fs_cluster_is_empty(struct compress_ctx *cc);
 bool f2fs_cluster_can_merge_page(struct compress_ctx *cc, pgoff_t index);
+bool f2fs_sanity_check_cluster(struct dnode_of_data *dn);
 void f2fs_compress_ctx_add_page(struct compress_ctx *cc, struct page *page);
 int f2fs_write_multi_pages(struct compress_ctx *cc,
 						int *submitted,
 						struct writeback_control *wbc,
 						enum iostat_type io_type);
 int f2fs_is_compressed_cluster(struct inode *inode, pgoff_t index);
+void f2fs_update_extent_tree_range_compressed(struct inode *inode,
+				pgoff_t fofs, block_t blkaddr, unsigned int llen,
+				unsigned int c_len);
 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_decompress_end_io(struct decompress_io_ctx *dic, bool failed);
 void f2fs_put_page_dic(struct page *page);
+unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn);
 int f2fs_init_compress_ctx(struct compress_ctx *cc);
 void f2fs_destroy_compress_ctx(struct compress_ctx *cc, bool reuse);
 void f2fs_init_compress_info(struct f2fs_sb_info *sbi);
@@ -4106,6 +4098,8 @@ static inline void f2fs_put_page_dic(struct page *page)
 {
 	WARN_ON_ONCE(1);
 }
+static inline unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn) { return 0; }
+static inline bool f2fs_sanity_check_cluster(struct dnode_of_data *dn) { return false; }
 static inline int f2fs_init_compress_inode(struct f2fs_sb_info *sbi) { return 0; }
 static inline void f2fs_destroy_compress_inode(struct f2fs_sb_info *sbi) { }
 static inline int f2fs_init_page_array_cache(struct f2fs_sb_info *sbi) { return 0; }
@@ -4121,6 +4115,9 @@ static inline bool f2fs_load_compressed_page(struct f2fs_sb_info *sbi,
 static inline void f2fs_invalidate_compress_pages(struct f2fs_sb_info *sbi,
 							nid_t ino) { }
 #define inc_compr_inode_stat(inode)		do { } while (0)
+static inline void f2fs_update_extent_tree_range_compressed(struct inode *inode,
+				pgoff_t fofs, block_t blkaddr, unsigned int llen,
+				unsigned int c_len) { }
 #endif
 
 static inline void set_compress_context(struct inode *inode)
@@ -4136,7 +4133,8 @@ 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 &&
+	if ((F2FS_I(inode)->i_compress_algorithm == COMPRESS_LZ4 ||
+		F2FS_I(inode)->i_compress_algorithm == COMPRESS_ZSTD) &&
 			F2FS_OPTION(sbi).compress_level)
 		F2FS_I(inode)->i_compress_flag |=
 				F2FS_OPTION(sbi).compress_level <<
@@ -4304,16 +4302,6 @@ static inline int block_unaligned_IO(struct inode *inode,
 	return align & blocksize_mask;
 }
 
-static inline int allow_outplace_dio(struct inode *inode,
-				struct kiocb *iocb, struct iov_iter *iter)
-{
-	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	int rw = iov_iter_rw(iter);
-
-	return (f2fs_lfs_mode(sbi) && (rw == WRITE) &&
-				!block_unaligned_IO(inode, iocb, iter));
-}
-
 static inline bool f2fs_force_buffered_io(struct inode *inode,
 				struct kiocb *iocb, struct iov_iter *iter)
 {
@@ -4368,6 +4356,11 @@ static inline bool is_journalled_quota(struct f2fs_sb_info *sbi)
 	return false;
 }
 
+static inline bool f2fs_block_unit_discard(struct f2fs_sb_info *sbi)
+{
+	return F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_BLOCK;
+}
+
 #define EFSBADCRC	EBADMSG		/* Bad CRC detected */
 #define EFSCORRUPTED	EUCLEAN		/* Filesystem is corrupted */