Merge tag 'f2fs-for-7.3-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this round, key enhancements focus on reducing inode management
  memory overhead, introducing resizable tail sections with unified
  pinned allocation, and boosting I/O throughput via parallel
  multi-device flushes and asynchronous f2fs_write_end_io() execution.
  We also add dynamic device alias reservations to allow on-the-fly
  space donation from user partitions.

  Alongside these features, critical bug fixes resolve folio race
  conditions, lingering dirty flags, dentry and block counter leaks, and
  potential deadloops in f2fs_fsync_node_pages(). Additional stability
  patches address error-path handling across symlink, sync, and
  rename/unlink operations, prevent pinned file fragmentation, and
  correct segment migration and free section accounting in
  free_segment_range.

  Enhancements:
   - reduce memory footprint of ino management
   - support dynamic reserve/release for device aliasing
   - issue multi-device flushes in parallel
   - add a way to run f2fs_write_end_io() asynchronously
   - support resizable tail section and unify pinned allocation

  Bug fixes:
   - fix to pass folio->index to f2fs_sanity_check_node_footer()
   - fix folio_nr_pages() race after put in large folio invalidate
   - fix to clear dirty flag on folio in error path
   - accurately adjust free_sections during free_segment_range
   - fix to avoid potential deadloop in f2fs_fsync_node_pages()
   - fix the error path in symlink, device alias in rename/unlink,
     f2fs_sync_fs
   - fix to migrate all curseg types during free_segment_range
   - fix to avoid pinfile fragment on fragment:{block, segment} mode
   - fix valid block count leak on data block allocation failure
   - fix dentry folio leak in find_in_level
   - reject overlapping move range after len expansion
   - fix some bugs related to file pinning, GC functions, i_size

  And, the series includes a number of minor bug fixes"

* tag 'f2fs-for-7.3-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (51 commits)
  f2fs: support resizable tail section and unify pinned allocation
  f2fs: don't leave the hashed inode while it's unlinked
  f2fs: accurately adjust free_sections during free_segment_range
  f2fs: fix to avoid potential deadloop in f2fs_fsync_node_pages()
  f2fs: use adjusted write range after f2fs_write_checks()
  f2fs: fix to propagate error from f2fs_sync_fs()
  f2fs: return symlink writeback errors
  f2fs: fix error handling on device alias check in rename and unlink
  f2fs: fix to reset all pinned status during fggc
  f2fs: use f2fs_{down, up}_(read, write}_trace() for nat_tree_lock
  f2fs: reduce memory footprint of ino management
  f2fs: fix i_size when pinned fallocate partially fails
  f2fs: fix to migrate all curseg types during free_segment_range
  f2fs: avoid setting SBI_NEED_FSCK on transient resize failure
  f2fs: fix to avoid pinfile fragment on fragment:{block, segment} mode
  f2fs: cleanup w/ f2fs_need_rand_{blk, seg, seg_blk}
  f2fs: fix to shrink gc_lock coverage in f2fs_gc_range()
  f2fs: fix to reclaim space in f2fs_allocate_pinning_section()
  f2fs: unify add/remove ino entry API for all ino types
  f2fs: fix to zero post-EOF data when extending file size
  ...

2 files changed, 25 insertions, 5 deletions

diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index 270c1a2c24c4..d53be932df01 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -191,7 +191,8 @@ TRACE_DEFINE_ENUM(CP_PHASE_FINISH_CHECKPOINT);
 		{ LOCK_NAME_NODE_WRITE,		"node_write" },		\
 		{ LOCK_NAME_GC_LOCK,		"gc_lock" },		\
 		{ LOCK_NAME_CP_GLOBAL,		"cp_global" },		\
-		{ LOCK_NAME_IO_RWSEM,		"io_rwsem" })
+		{ LOCK_NAME_IO_RWSEM,		"io_rwsem" },		\
+		{ LOCK_NAME_NAT_TREE_LOCK,	"nat_tree_lock" })
 
 struct f2fs_sb_info;
 struct f2fs_io_info;
@@ -2114,6 +2115,14 @@ DEFINE_EVENT(f2fs_zip_end, f2fs_decompress_pages_end,
 );
 
 #ifdef CONFIG_F2FS_IOSTAT
+/*
+ * Number of read folio order buckets emitted by the f2fs_iostat tracepoint.
+ * TP_printk() cannot loop, so the field count is fixed here and must be >=
+ * the largest possible NR_PAGE_ORDERS (14 on arm64 with 64K pages). The
+ * BUILD_BUG_ON() in f2fs_update_read_folio_count() enforces this.
+ */
+#define F2FS_IOSTAT_RD_FOLIO_ORDERS	16
+
 TRACE_EVENT(f2fs_iostat,
 
 	TP_PROTO(struct f2fs_sb_info *sbi, unsigned long long *iostat,
@@ -2151,7 +2160,7 @@ TRACE_EVENT(f2fs_iostat,
 		__field(unsigned long long,	fs_mrio)
 		__field(unsigned long long,	fs_discard)
 		__field(unsigned long long,	fs_reset_zone)
-		__array(unsigned long long,	read_folio_count, 11)
+		__array(unsigned long long,	read_folio_count, F2FS_IOSTAT_RD_FOLIO_ORDERS)
 	),
 
 	TP_fast_assign(
@@ -2186,7 +2195,8 @@ TRACE_EVENT(f2fs_iostat,
 		__entry->fs_reset_zone	= iostat[FS_ZONE_RESET_IO];
 		memset(__entry->read_folio_count, 0, sizeof(__entry->read_folio_count));
 		memcpy(__entry->read_folio_count, read_folio_count,
-				sizeof(unsigned long long) * min_t(int, NR_PAGE_ORDERS, 11));
+				sizeof(unsigned long long) *
+				min_t(int, NR_PAGE_ORDERS, F2FS_IOSTAT_RD_FOLIO_ORDERS));
 	),
 
 	TP_printk("dev = (%d,%d), "
@@ -2201,7 +2211,8 @@ TRACE_EVENT(f2fs_iostat,
 		"fs [data=%llu, (gc_data=%llu, cdata=%llu), "
 		"node=%llu, meta=%llu], "
 		"read_folio_count [0=%llu, 1=%llu, 2=%llu, 3=%llu, 4=%llu, "
-		"5=%llu, 6=%llu, 7=%llu, 8=%llu, 9=%llu, 10=%llu]",
+		"5=%llu, 6=%llu, 7=%llu, 8=%llu, 9=%llu, 10=%llu, 11=%llu, "
+		"12=%llu, 13=%llu, 14=%llu, 15=%llu]",
 		show_dev(__entry->dev), __entry->app_wio, __entry->app_dio,
 		__entry->app_bio, __entry->app_mio, __entry->app_bcdio,
 		__entry->app_mcdio, __entry->fs_dio, __entry->fs_cdio,
@@ -2218,7 +2229,9 @@ TRACE_EVENT(f2fs_iostat,
 		__entry->read_folio_count[4], __entry->read_folio_count[5],
 		__entry->read_folio_count[6], __entry->read_folio_count[7],
 		__entry->read_folio_count[8], __entry->read_folio_count[9],
-		__entry->read_folio_count[10])
+		__entry->read_folio_count[10], __entry->read_folio_count[11],
+		__entry->read_folio_count[12], __entry->read_folio_count[13],
+		__entry->read_folio_count[14], __entry->read_folio_count[15])
 );
 
 #ifndef __F2FS_IOSTAT_LATENCY_TYPE
diff --git a/include/uapi/linux/f2fs.h b/include/uapi/linux/f2fs.h
index 795e26258355..4409ada2fecb 100644
--- a/include/uapi/linux/f2fs.h
+++ b/include/uapi/linux/f2fs.h
@@ -45,6 +45,9 @@
 #define F2FS_IOC_START_ATOMIC_REPLACE	_IO(F2FS_IOCTL_MAGIC, 25)
 #define F2FS_IOC_GET_DEV_ALIAS_FILE	_IOR(F2FS_IOCTL_MAGIC, 26, __u32)
 #define F2FS_IOC_IO_PRIO		_IOW(F2FS_IOCTL_MAGIC, 27, __u32)
+#define F2FS_IOC_RESERVE_DEV_ALIAS	_IO(F2FS_IOCTL_MAGIC, 28)
+#define F2FS_IOC_RELEASE_DEV_ALIAS	_IO(F2FS_IOCTL_MAGIC, 29)
+#define F2FS_IOC_GET_DEV_ALIAS_STATUS	_IOR(F2FS_IOCTL_MAGIC, 30, __u32)
 
 /*
  * should be same as XFS_IOC_GOINGDOWN.
@@ -70,6 +73,10 @@ enum {
 	F2FS_IOPRIO_MAX,
 };
 
+/* for F2FS_IOC_GET_DEV_ALIAS_STATUS */
+#define F2FS_DEV_ALIAS_STATUS_RELEASED	0
+#define F2FS_DEV_ALIAS_STATUS_RESERVED	1
+
 struct f2fs_gc_range {
 	__u32 sync;
 	__u64 start;