Merge tag 'for-6.2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "This round there are a lot of cleanups and moved code so the diffstat
  looks huge, otherwise there are some nice performance improvements and
  an update to raid56 reliability.

  User visible features:

   - raid56 reliability vs performance trade off:
      - fix destructive RMW for raid5 data (raid6 still needs work): do
        full checksum verification for all data during RMW cycle, this
        should prevent rewriting potentially corrupted data without
        notice
      - stripes are cached in memory which should reduce the performance
        impact but still can hurt some workloads
      - checksums are verified after repair again
      - this is the last option without introducing additional features
        (write intent bitmap, journal, another tree), the extra checksum
        read/verification was supposed to be avoided by the original
        implementation exactly for performance reasons but that caused
        all the reliability problems

   - discard=async by default for devices that support it

   - implement emergency flush reserve to avoid almost all unnecessary
     transaction aborts due to ENOSPC in cases where there are too many
     delayed refs or delayed allocation

   - skip block group synchronization if there's no change in used
     bytes, can reduce transaction commit count for some workloads

  Performance improvements:

   - fiemap and lseek:
      - overall speedup due to skipping unnecessary or duplicate
        searches (-40% run time)
      - cache some data structures and sharedness of extents (-30% run
        time)

   - send:
      - faster backref resolution when finding clones
      - cached leaf to root mapping for faster backref walking
      - improved clone/sharing detection
      - overall run time improvements (-70%)

  Core:

   - module initialization converted to a table of function pointers run
     in a sequence

   - preparation for fscrypt, extend passing file names across calls,
     dir item can store encryption status

   - raid56 updates:
      - more accurate error tracking of sectors within stripe
      - simplify recovery path and remove dedicated endio worker kthread
      - simplify scrub call paths
      - refactoring to support the extra data checksum verification
        during RMW cycle

   - tree block parentness checks consolidated and done at metadata read
     time

   - improved error handling

   - cleanups:
      - move a lot of code for better synchronization between kernel and
        user space sources, split big files
      - enum cleanups
      - GFP flag cleanups
      - header file cleanups, prototypes, dependencies
      - redundant parameter cleanups
      - inline extent handling simplifications
      - inode parameter conversion
      - data structure cleanups, reductions, renames, merges"

* tag 'for-6.2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (249 commits)
  btrfs: print transaction aborted messages with an error level
  btrfs: sync some cleanups from progs into uapi/btrfs.h
  btrfs: do not BUG_ON() on ENOMEM when dropping extent items for a range
  btrfs: fix extent map use-after-free when handling missing device in read_one_chunk
  btrfs: remove outdated logic from overwrite_item() and add assertion
  btrfs: unify overwrite_item() and do_overwrite_item()
  btrfs: replace strncpy() with strscpy()
  btrfs: fix uninitialized variable in find_first_clear_extent_bit
  btrfs: fix uninitialized parent in insert_state
  btrfs: add might_sleep() annotations
  btrfs: add stack helpers for a few btrfs items
  btrfs: add nr_global_roots to the super block definition
  btrfs: remove BTRFS_LEAF_DATA_OFFSET
  btrfs: add helpers for manipulating leaf items and data
  btrfs: add eb to btrfs_node_key_ptr_offset
  btrfs: pass the extent buffer for the btrfs_item_nr helpers
  btrfs: move the csum helpers into ctree.h
  btrfs: move eb offset helpers into extent_io.h
  btrfs: move file_extent_item helpers into file-item.h
  btrfs: move leaf_data_end into ctree.c
  ...

1 files changed, 76 insertions, 0 deletions

diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h
index 490c7a79e995..11c2269b4b6f 100644
--- a/fs/btrfs/locking.h
+++ b/fs/btrfs/locking.h
@@ -78,6 +78,82 @@ enum btrfs_lock_nesting {
 	BTRFS_NESTING_MAX,
 };
 
+enum btrfs_lockdep_trans_states {
+	BTRFS_LOCKDEP_TRANS_COMMIT_START,
+	BTRFS_LOCKDEP_TRANS_UNBLOCKED,
+	BTRFS_LOCKDEP_TRANS_SUPER_COMMITTED,
+	BTRFS_LOCKDEP_TRANS_COMPLETED,
+};
+
+/*
+ * Lockdep annotation for wait events.
+ *
+ * @owner:  The struct where the lockdep map is defined
+ * @lock:   The lockdep map corresponding to a wait event
+ *
+ * This macro is used to annotate a wait event. In this case a thread acquires
+ * the lockdep map as writer (exclusive lock) because it has to block until all
+ * the threads that hold the lock as readers signal the condition for the wait
+ * event and release their locks.
+ */
+#define btrfs_might_wait_for_event(owner, lock)					\
+	do {									\
+		rwsem_acquire(&owner->lock##_map, 0, 0, _THIS_IP_);		\
+		rwsem_release(&owner->lock##_map, _THIS_IP_);			\
+	} while (0)
+
+/*
+ * Protection for the resource/condition of a wait event.
+ *
+ * @owner:  The struct where the lockdep map is defined
+ * @lock:   The lockdep map corresponding to a wait event
+ *
+ * Many threads can modify the condition for the wait event at the same time
+ * and signal the threads that block on the wait event. The threads that modify
+ * the condition and do the signaling acquire the lock as readers (shared
+ * lock).
+ */
+#define btrfs_lockdep_acquire(owner, lock)					\
+	rwsem_acquire_read(&owner->lock##_map, 0, 0, _THIS_IP_)
+
+/*
+ * Used after signaling the condition for a wait event to release the lockdep
+ * map held by a reader thread.
+ */
+#define btrfs_lockdep_release(owner, lock)					\
+	rwsem_release(&owner->lock##_map, _THIS_IP_)
+
+/*
+ * Macros for the transaction states wait events, similar to the generic wait
+ * event macros.
+ */
+#define btrfs_might_wait_for_state(owner, i)					\
+	do {									\
+		rwsem_acquire(&owner->btrfs_state_change_map[i], 0, 0, _THIS_IP_); \
+		rwsem_release(&owner->btrfs_state_change_map[i], _THIS_IP_);	\
+	} while (0)
+
+#define btrfs_trans_state_lockdep_acquire(owner, i)				\
+	rwsem_acquire_read(&owner->btrfs_state_change_map[i], 0, 0, _THIS_IP_)
+
+#define btrfs_trans_state_lockdep_release(owner, i)				\
+	rwsem_release(&owner->btrfs_state_change_map[i], _THIS_IP_)
+
+/* Initialization of the lockdep map */
+#define btrfs_lockdep_init_map(owner, lock)					\
+	do {									\
+		static struct lock_class_key lock##_key;			\
+		lockdep_init_map(&owner->lock##_map, #lock, &lock##_key, 0);	\
+	} while (0)
+
+/* Initialization of the transaction states lockdep maps. */
+#define btrfs_state_lockdep_init_map(owner, lock, state)			\
+	do {									\
+		static struct lock_class_key lock##_key;			\
+		lockdep_init_map(&owner->btrfs_state_change_map[state], #lock,	\
+				 &lock##_key, 0);				\
+	} while (0)
+
 static_assert(BTRFS_NESTING_MAX <= MAX_LOCKDEP_SUBCLASSES,
 	      "too many lock subclasses defined");