Merge tag 'for-5.19-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "Features:

   - subpage:
      - support for PAGE_SIZE > 4K (previously only 64K)
      - make it work with raid56

   - repair super block num_devices automatically if it does not match
     the number of device items

   - defrag can convert inline extents to regular extents, up to now
     inline files were skipped but the setting of mount option
     max_inline could affect the decision logic

   - zoned:
      - minimal accepted zone size is explicitly set to 4MiB
      - make zone reclaim less aggressive and don't reclaim if there are
        enough free zones
      - add per-profile sysfs tunable of the reclaim threshold

   - allow automatic block group reclaim for non-zoned filesystems, with
     sysfs tunables

   - tree-checker: new check, compare extent buffer owner against owner
     rootid

  Performance:

   - avoid blocking on space reservation when doing nowait direct io
     writes (+7% throughput for reads and writes)

   - NOCOW write throughput improvement due to refined locking (+3%)

   - send: reduce pressure to page cache by dropping extent pages right
     after they're processed

  Core:

   - convert all radix trees to xarray

   - add iterators for b-tree node items

   - support printk message index

   - user bulk page allocation for extent buffers

   - switch to bio_alloc API, use on-stack bios where convenient, other
     bio cleanups

   - use rw lock for block groups to favor concurrent reads

   - simplify workques, don't allocate high priority threads for all
     normal queues as we need only one

   - refactor scrub, process chunks based on their constraints and
     similarity

   - allocate direct io structures on stack and pass around only
     pointers, avoids allocation and reduces potential error handling

  Fixes:

   - fix count of reserved transaction items for various inode
     operations

   - fix deadlock between concurrent dio writes when low on free data
     space

   - fix a few cases when zones need to be finished

  VFS, iomap:

   - add helper to check if sb write has started (usable for assertions)

   - new helper iomap_dio_alloc_bio, export iomap_dio_bio_end_io"

* tag 'for-5.19-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (173 commits)
  btrfs: zoned: introduce a minimal zone size 4M and reject mount
  btrfs: allow defrag to convert inline extents to regular extents
  btrfs: add "0x" prefix for unsupported optional features
  btrfs: do not account twice for inode ref when reserving metadata units
  btrfs: zoned: fix comparison of alloc_offset vs meta_write_pointer
  btrfs: send: avoid trashing the page cache
  btrfs: send: keep the current inode open while processing it
  btrfs: allocate the btrfs_dio_private as part of the iomap dio bio
  btrfs: move struct btrfs_dio_private to inode.c
  btrfs: remove the disk_bytenr in struct btrfs_dio_private
  btrfs: allocate dio_data on stack
  iomap: add per-iomap_iter private data
  iomap: allow the file system to provide a bio_set for direct I/O
  btrfs: add a btrfs_dio_rw wrapper
  btrfs: zoned: zone finish unused block group
  btrfs: zoned: properly finish block group on metadata write
  btrfs: zoned: finish block group when there are no more allocatable bytes left
  btrfs: zoned: consolidate zone finish functions
  btrfs: zoned: introduce btrfs_zoned_bg_is_full
  btrfs: improve error reporting in lookup_inline_extent_backref
  ...

4 files changed, 31 insertions, 33 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 87b5af1d9fbe..02e7f60638b8 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1708,6 +1708,11 @@ static inline bool __sb_start_write_trylock(struct super_block *sb, int level)
 #define __sb_writers_release(sb, lev)	\
 	percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_)
 
+static inline bool sb_write_started(const struct super_block *sb)
+{
+	return lockdep_is_held_type(sb->s_writers.rw_sem + SB_FREEZE_WRITE - 1, 1);
+}
+
 /**
  * sb_end_write - drop write access to a superblock
  * @sb: the super we wrote to
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index b76f0dd149fb..5b6f64f4d771 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -188,6 +188,7 @@ struct iomap_iter {
 	unsigned flags;
 	struct iomap iomap;
 	struct iomap srcmap;
+	void *private;
 };
 
 int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops);
@@ -320,6 +321,16 @@ struct iomap_dio_ops {
 		      unsigned flags);
 	void (*submit_io)(const struct iomap_iter *iter, struct bio *bio,
 		          loff_t file_offset);
+
+	/*
+	 * Filesystems wishing to attach private information to a direct io bio
+	 * must provide a ->submit_io method that attaches the additional
+	 * information to the bio and changes the ->bi_end_io callback to a
+	 * custom function.  This function should, at a minimum, perform any
+	 * relevant post-processing of the bio and end with a call to
+	 * iomap_dio_bio_end_io.
+	 */
+	struct bio_set *bio_set;
 };
 
 /*
@@ -344,11 +355,12 @@ struct iomap_dio_ops {
 
 ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
-		unsigned int dio_flags, size_t done_before);
+		unsigned int dio_flags, void *private, size_t done_before);
 struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
-		unsigned int dio_flags, size_t done_before);
+		unsigned int dio_flags, void *private, size_t done_before);
 ssize_t iomap_dio_complete(struct iomap_dio *dio);
+void iomap_dio_bio_end_io(struct bio *bio);
 
 #ifdef CONFIG_SWAP
 struct file;
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index f068ff30d654..290f07eb050a 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -24,7 +24,7 @@ struct btrfs_free_cluster;
 struct map_lookup;
 struct extent_buffer;
 struct btrfs_work;
-struct __btrfs_workqueue;
+struct btrfs_workqueue;
 struct btrfs_qgroup_extent_record;
 struct btrfs_qgroup;
 struct extent_io_tree;
@@ -1457,42 +1457,36 @@ DEFINE_EVENT(btrfs__work, btrfs_ordered_sched,
 	TP_ARGS(work)
 );
 
-DECLARE_EVENT_CLASS(btrfs__workqueue,
+DECLARE_EVENT_CLASS(btrfs_workqueue,
 
-	TP_PROTO(const struct __btrfs_workqueue *wq,
-		 const char *name, int high),
+	TP_PROTO(const struct btrfs_workqueue *wq, const char *name),
 
-	TP_ARGS(wq, name, high),
+	TP_ARGS(wq, name),
 
 	TP_STRUCT__entry_btrfs(
 		__field(	const void *,	wq			)
 		__string(	name,	name			)
-		__field(	int ,	high			)
 	),
 
 	TP_fast_assign_btrfs(btrfs_workqueue_owner(wq),
 		__entry->wq		= wq;
 		__assign_str(name, name);
-		__entry->high		= high;
 	),
 
-	TP_printk_btrfs("name=%s%s wq=%p", __get_str(name),
-		  __print_flags(__entry->high, "",
-				{(WQ_HIGHPRI),	"-high"}),
+	TP_printk_btrfs("name=%s wq=%p", __get_str(name),
 		  __entry->wq)
 );
 
-DEFINE_EVENT(btrfs__workqueue, btrfs_workqueue_alloc,
+DEFINE_EVENT(btrfs_workqueue, btrfs_workqueue_alloc,
 
-	TP_PROTO(const struct __btrfs_workqueue *wq,
-		 const char *name, int high),
+	TP_PROTO(const struct btrfs_workqueue *wq, const char *name),
 
-	TP_ARGS(wq, name, high)
+	TP_ARGS(wq, name)
 );
 
-DECLARE_EVENT_CLASS(btrfs__workqueue_done,
+DECLARE_EVENT_CLASS(btrfs_workqueue_done,
 
-	TP_PROTO(const struct __btrfs_workqueue *wq),
+	TP_PROTO(const struct btrfs_workqueue *wq),
 
 	TP_ARGS(wq),
 
@@ -1507,9 +1501,9 @@ DECLARE_EVENT_CLASS(btrfs__workqueue_done,
 	TP_printk_btrfs("wq=%p", __entry->wq)
 );
 
-DEFINE_EVENT(btrfs__workqueue_done, btrfs_workqueue_destroy,
+DEFINE_EVENT(btrfs_workqueue_done, btrfs_workqueue_destroy,
 
-	TP_PROTO(const struct __btrfs_workqueue *wq),
+	TP_PROTO(const struct btrfs_workqueue *wq),
 
 	TP_ARGS(wq)
 );
diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h
index b069752a8ecf..d4117152d907 100644
--- a/include/uapi/linux/btrfs_tree.h
+++ b/include/uapi/linux/btrfs_tree.h
@@ -880,19 +880,6 @@ struct btrfs_dev_replace_item {
 #define BTRFS_BLOCK_GROUP_RESERVED	(BTRFS_AVAIL_ALLOC_BIT_SINGLE | \
 					 BTRFS_SPACE_INFO_GLOBAL_RSV)
 
-enum btrfs_raid_types {
-	BTRFS_RAID_RAID10,
-	BTRFS_RAID_RAID1,
-	BTRFS_RAID_DUP,
-	BTRFS_RAID_RAID0,
-	BTRFS_RAID_SINGLE,
-	BTRFS_RAID_RAID5,
-	BTRFS_RAID_RAID6,
-	BTRFS_RAID_RAID1C3,
-	BTRFS_RAID_RAID1C4,
-	BTRFS_NR_RAID_TYPES
-};
-
 #define BTRFS_BLOCK_GROUP_TYPE_MASK	(BTRFS_BLOCK_GROUP_DATA |    \
 					 BTRFS_BLOCK_GROUP_SYSTEM |  \
 					 BTRFS_BLOCK_GROUP_METADATA)