Merge tag 'f2fs-for-6.2-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 two features: F2FS_IOC_START_ATOMIC_REPLACE
  and a per-block age-based extent cache.

  F2FS_IOC_START_ATOMIC_REPLACE is a variant of the previous atomic
  write feature which guarantees a per-file atomicity. It would be more
  efficient than AtomicFile implementation in Android framework.

  The per-block age-based extent cache implements another type of extent
  cache in memory which keeps the per-block age in a file, so that block
  allocator could split the hot and cold data blocks more accurately.

  Enhancements:
   - introduce F2FS_IOC_START_ATOMIC_REPLACE
   - refactor extent_cache to add a new per-block-age-based extent cache support
   - introduce discard_urgent_util, gc_mode, max_ordered_discard sysfs knobs
   - add proc entry to show discard_plist info
   - optimize iteration over sparse directories
   - add barrier mount option

  Bug fixes:
   - avoid victim selection from previous victim section
   - fix to enable compress for newly created file if extension matches
   - set zstd compress level correctly
   - initialize locks early in f2fs_fill_super() to fix bugs reported by syzbot
   - correct i_size change for atomic writes
   - allow to read node block after shutdown
   - allow to set compression for inlined file
   - fix gc mode when gc_urgent_high_remaining is 1
   - should put a page when checking the summary info

  Minor fixes and various clean-ups in GC, discard, debugfs, sysfs, and
  doc"

* tag 'f2fs-for-6.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (63 commits)
  f2fs: reset wait_ms to default if any of the victims have been selected
  f2fs: fix some format WARNING in debug.c and sysfs.c
  f2fs: don't call f2fs_issue_discard_timeout() when discard_cmd_cnt is 0 in f2fs_put_super()
  f2fs: fix iostat parameter for discard
  f2fs: Fix spelling mistake in label: free_bio_enrty_cache -> free_bio_entry_cache
  f2fs: add block_age-based extent cache
  f2fs: allocate the extent_cache by default
  f2fs: refactor extent_cache to support for read and more
  f2fs: remove unnecessary __init_extent_tree
  f2fs: move internal functions into extent_cache.c
  f2fs: specify extent cache for read explicitly
  f2fs: introduce f2fs_is_readonly() for readability
  f2fs: remove F2FS_SET_FEATURE() and F2FS_CLEAR_FEATURE() macro
  f2fs: do some cleanup for f2fs module init
  MAINTAINERS: Add f2fs bug tracker link
  f2fs: remove the unused flush argument to change_curseg
  f2fs: open code allocate_segment_by_default
  f2fs: remove struct segment_allocation default_salloc_ops
  f2fs: introduce discard_urgent_util sysfs node
  f2fs: define MIN_DISCARD_GRANULARITY macro
  ...

2 files changed, 136 insertions, 41 deletions

diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index c6b372401c27..31d994e6b4ca 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -48,6 +48,8 @@ TRACE_DEFINE_ENUM(CP_DISCARD);
 TRACE_DEFINE_ENUM(CP_TRIMMED);
 TRACE_DEFINE_ENUM(CP_PAUSE);
 TRACE_DEFINE_ENUM(CP_RESIZE);
+TRACE_DEFINE_ENUM(EX_READ);
+TRACE_DEFINE_ENUM(EX_BLOCK_AGE);
 
 #define show_block_type(type)						\
 	__print_symbolic(type,						\
@@ -154,6 +156,11 @@ TRACE_DEFINE_ENUM(CP_RESIZE);
 		{ COMPRESS_ZSTD,	"ZSTD" },			\
 		{ COMPRESS_LZORLE,	"LZO-RLE" })
 
+#define show_extent_type(type)						\
+	__print_symbolic(type,						\
+		{ EX_READ,	"Read" },				\
+		{ EX_BLOCK_AGE,	"Block Age" })
+
 struct f2fs_sb_info;
 struct f2fs_io_info;
 struct extent_info;
@@ -322,7 +329,7 @@ TRACE_EVENT(f2fs_unlink_enter,
 		__field(ino_t,	ino)
 		__field(loff_t,	size)
 		__field(blkcnt_t, blocks)
-		__field(const char *,	name)
+		__string(name,  dentry->d_name.name)
 	),
 
 	TP_fast_assign(
@@ -330,7 +337,7 @@ TRACE_EVENT(f2fs_unlink_enter,
 		__entry->ino	= dir->i_ino;
 		__entry->size	= dir->i_size;
 		__entry->blocks	= dir->i_blocks;
-		__entry->name	= dentry->d_name.name;
+		__assign_str(name, dentry->d_name.name);
 	),
 
 	TP_printk("dev = (%d,%d), dir ino = %lu, i_size = %lld, "
@@ -338,7 +345,7 @@ TRACE_EVENT(f2fs_unlink_enter,
 		show_dev_ino(__entry),
 		__entry->size,
 		(unsigned long long)__entry->blocks,
-		__entry->name)
+		__get_str(name))
 );
 
 DEFINE_EVENT(f2fs__inode_exit, f2fs_unlink_exit,
@@ -940,25 +947,29 @@ TRACE_EVENT(f2fs_direct_IO_enter,
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
 		__field(ino_t,	ino)
-		__field(struct kiocb *,	iocb)
+		__field(loff_t,	ki_pos)
+		__field(int,	ki_flags)
+		__field(u16,	ki_ioprio)
 		__field(unsigned long,	len)
 		__field(int,	rw)
 	),
 
 	TP_fast_assign(
-		__entry->dev	= inode->i_sb->s_dev;
-		__entry->ino	= inode->i_ino;
-		__entry->iocb	= iocb;
-		__entry->len	= len;
-		__entry->rw	= rw;
+		__entry->dev		= inode->i_sb->s_dev;
+		__entry->ino		= inode->i_ino;
+		__entry->ki_pos		= iocb->ki_pos;
+		__entry->ki_flags	= iocb->ki_flags;
+		__entry->ki_ioprio	= iocb->ki_ioprio;
+		__entry->len		= len;
+		__entry->rw		= rw;
 	),
 
 	TP_printk("dev = (%d,%d), ino = %lu pos = %lld len = %lu ki_flags = %x ki_ioprio = %x rw = %d",
 		show_dev_ino(__entry),
-		__entry->iocb->ki_pos,
+		__entry->ki_pos,
 		__entry->len,
-		__entry->iocb->ki_flags,
-		__entry->iocb->ki_ioprio,
+		__entry->ki_flags,
+		__entry->ki_ioprio,
 		__entry->rw)
 );
 
@@ -1400,26 +1411,26 @@ TRACE_EVENT(f2fs_readpages,
 
 TRACE_EVENT(f2fs_write_checkpoint,
 
-	TP_PROTO(struct super_block *sb, int reason, char *msg),
+	TP_PROTO(struct super_block *sb, int reason, const char *msg),
 
 	TP_ARGS(sb, reason, msg),
 
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
 		__field(int,	reason)
-		__field(char *,	msg)
+		__string(dest_msg, msg)
 	),
 
 	TP_fast_assign(
 		__entry->dev		= sb->s_dev;
 		__entry->reason		= reason;
-		__entry->msg		= msg;
+		__assign_str(dest_msg, msg);
 	),
 
 	TP_printk("dev = (%d,%d), checkpoint for %s, state = %s",
 		show_dev(__entry->dev),
 		show_cpreason(__entry->reason),
-		__entry->msg)
+		__get_str(dest_msg))
 );
 
 DECLARE_EVENT_CLASS(f2fs_discard,
@@ -1518,28 +1529,31 @@ TRACE_EVENT(f2fs_issue_flush,
 
 TRACE_EVENT(f2fs_lookup_extent_tree_start,
 
-	TP_PROTO(struct inode *inode, unsigned int pgofs),
+	TP_PROTO(struct inode *inode, unsigned int pgofs, enum extent_type type),
 
-	TP_ARGS(inode, pgofs),
+	TP_ARGS(inode, pgofs, type),
 
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
 		__field(ino_t,	ino)
 		__field(unsigned int, pgofs)
+		__field(enum extent_type, type)
 	),
 
 	TP_fast_assign(
 		__entry->dev = inode->i_sb->s_dev;
 		__entry->ino = inode->i_ino;
 		__entry->pgofs = pgofs;
+		__entry->type = type;
 	),
 
-	TP_printk("dev = (%d,%d), ino = %lu, pgofs = %u",
+	TP_printk("dev = (%d,%d), ino = %lu, pgofs = %u, type = %s",
 		show_dev_ino(__entry),
-		__entry->pgofs)
+		__entry->pgofs,
+		show_extent_type(__entry->type))
 );
 
-TRACE_EVENT_CONDITION(f2fs_lookup_extent_tree_end,
+TRACE_EVENT_CONDITION(f2fs_lookup_read_extent_tree_end,
 
 	TP_PROTO(struct inode *inode, unsigned int pgofs,
 						struct extent_info *ei),
@@ -1553,8 +1567,8 @@ TRACE_EVENT_CONDITION(f2fs_lookup_extent_tree_end,
 		__field(ino_t,	ino)
 		__field(unsigned int, pgofs)
 		__field(unsigned int, fofs)
-		__field(u32, blk)
 		__field(unsigned int, len)
+		__field(u32, blk)
 	),
 
 	TP_fast_assign(
@@ -1562,26 +1576,65 @@ TRACE_EVENT_CONDITION(f2fs_lookup_extent_tree_end,
 		__entry->ino = inode->i_ino;
 		__entry->pgofs = pgofs;
 		__entry->fofs = ei->fofs;
+		__entry->len = ei->len;
 		__entry->blk = ei->blk;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, pgofs = %u, "
+		"read_ext_info(fofs: %u, len: %u, blk: %u)",
+		show_dev_ino(__entry),
+		__entry->pgofs,
+		__entry->fofs,
+		__entry->len,
+		__entry->blk)
+);
+
+TRACE_EVENT_CONDITION(f2fs_lookup_age_extent_tree_end,
+
+	TP_PROTO(struct inode *inode, unsigned int pgofs,
+						struct extent_info *ei),
+
+	TP_ARGS(inode, pgofs, ei),
+
+	TP_CONDITION(ei),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(unsigned int, pgofs)
+		__field(unsigned int, fofs)
+		__field(unsigned int, len)
+		__field(unsigned long long, age)
+		__field(unsigned long long, blocks)
+	),
+
+	TP_fast_assign(
+		__entry->dev = inode->i_sb->s_dev;
+		__entry->ino = inode->i_ino;
+		__entry->pgofs = pgofs;
+		__entry->fofs = ei->fofs;
 		__entry->len = ei->len;
+		__entry->age = ei->age;
+		__entry->blocks = ei->last_blocks;
 	),
 
 	TP_printk("dev = (%d,%d), ino = %lu, pgofs = %u, "
-		"ext_info(fofs: %u, blk: %u, len: %u)",
+		"age_ext_info(fofs: %u, len: %u, age: %llu, blocks: %llu)",
 		show_dev_ino(__entry),
 		__entry->pgofs,
 		__entry->fofs,
-		__entry->blk,
-		__entry->len)
+		__entry->len,
+		__entry->age,
+		__entry->blocks)
 );
 
-TRACE_EVENT(f2fs_update_extent_tree_range,
+TRACE_EVENT(f2fs_update_read_extent_tree_range,
 
-	TP_PROTO(struct inode *inode, unsigned int pgofs, block_t blkaddr,
-						unsigned int len,
+	TP_PROTO(struct inode *inode, unsigned int pgofs, unsigned int len,
+						block_t blkaddr,
 						unsigned int c_len),
 
-	TP_ARGS(inode, pgofs, blkaddr, len, c_len),
+	TP_ARGS(inode, pgofs, len, blkaddr, c_len),
 
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
@@ -1596,67 +1649,108 @@ TRACE_EVENT(f2fs_update_extent_tree_range,
 		__entry->dev = inode->i_sb->s_dev;
 		__entry->ino = inode->i_ino;
 		__entry->pgofs = pgofs;
-		__entry->blk = blkaddr;
 		__entry->len = len;
+		__entry->blk = blkaddr;
 		__entry->c_len = c_len;
 	),
 
 	TP_printk("dev = (%d,%d), ino = %lu, pgofs = %u, "
-					"blkaddr = %u, len = %u, "
-					"c_len = %u",
+				"len = %u, blkaddr = %u, c_len = %u",
 		show_dev_ino(__entry),
 		__entry->pgofs,
-		__entry->blk,
 		__entry->len,
+		__entry->blk,
 		__entry->c_len)
 );
 
+TRACE_EVENT(f2fs_update_age_extent_tree_range,
+
+	TP_PROTO(struct inode *inode, unsigned int pgofs, unsigned int len,
+					unsigned long long age,
+					unsigned long long last_blks),
+
+	TP_ARGS(inode, pgofs, len, age, last_blks),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(unsigned int, pgofs)
+		__field(unsigned int, len)
+		__field(unsigned long long, age)
+		__field(unsigned long long, blocks)
+	),
+
+	TP_fast_assign(
+		__entry->dev = inode->i_sb->s_dev;
+		__entry->ino = inode->i_ino;
+		__entry->pgofs = pgofs;
+		__entry->len = len;
+		__entry->age = age;
+		__entry->blocks = last_blks;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, pgofs = %u, "
+				"len = %u, age = %llu, blocks = %llu",
+		show_dev_ino(__entry),
+		__entry->pgofs,
+		__entry->len,
+		__entry->age,
+		__entry->blocks)
+);
+
 TRACE_EVENT(f2fs_shrink_extent_tree,
 
 	TP_PROTO(struct f2fs_sb_info *sbi, unsigned int node_cnt,
-						unsigned int tree_cnt),
+			unsigned int tree_cnt, enum extent_type type),
 
-	TP_ARGS(sbi, node_cnt, tree_cnt),
+	TP_ARGS(sbi, node_cnt, tree_cnt, type),
 
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
 		__field(unsigned int, node_cnt)
 		__field(unsigned int, tree_cnt)
+		__field(enum extent_type, type)
 	),
 
 	TP_fast_assign(
 		__entry->dev = sbi->sb->s_dev;
 		__entry->node_cnt = node_cnt;
 		__entry->tree_cnt = tree_cnt;
+		__entry->type = type;
 	),
 
-	TP_printk("dev = (%d,%d), shrunk: node_cnt = %u, tree_cnt = %u",
+	TP_printk("dev = (%d,%d), shrunk: node_cnt = %u, tree_cnt = %u, type = %s",
 		show_dev(__entry->dev),
 		__entry->node_cnt,
-		__entry->tree_cnt)
+		__entry->tree_cnt,
+		show_extent_type(__entry->type))
 );
 
 TRACE_EVENT(f2fs_destroy_extent_tree,
 
-	TP_PROTO(struct inode *inode, unsigned int node_cnt),
+	TP_PROTO(struct inode *inode, unsigned int node_cnt,
+				enum extent_type type),
 
-	TP_ARGS(inode, node_cnt),
+	TP_ARGS(inode, node_cnt, type),
 
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
 		__field(ino_t,	ino)
 		__field(unsigned int, node_cnt)
+		__field(enum extent_type, type)
 	),
 
 	TP_fast_assign(
 		__entry->dev = inode->i_sb->s_dev;
 		__entry->ino = inode->i_ino;
 		__entry->node_cnt = node_cnt;
+		__entry->type = type;
 	),
 
-	TP_printk("dev = (%d,%d), ino = %lu, destroyed: node_cnt = %u",
+	TP_printk("dev = (%d,%d), ino = %lu, destroyed: node_cnt = %u, type = %s",
 		show_dev_ino(__entry),
-		__entry->node_cnt)
+		__entry->node_cnt,
+		show_extent_type(__entry->type))
 );
 
 DECLARE_EVENT_CLASS(f2fs_sync_dirty_inodes,
diff --git a/include/uapi/linux/f2fs.h b/include/uapi/linux/f2fs.h
index 3121d127d5aa..955d440be104 100644
--- a/include/uapi/linux/f2fs.h
+++ b/include/uapi/linux/f2fs.h
@@ -42,6 +42,7 @@
 						struct f2fs_comp_option)
 #define F2FS_IOC_DECOMPRESS_FILE	_IO(F2FS_IOCTL_MAGIC, 23)
 #define F2FS_IOC_COMPRESS_FILE		_IO(F2FS_IOCTL_MAGIC, 24)
+#define F2FS_IOC_START_ATOMIC_REPLACE	_IO(F2FS_IOCTL_MAGIC, 25)
 
 /*
  * should be same as XFS_IOC_GOINGDOWN.