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, 27 insertions, 89 deletions

diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 099def5613b8..6b7a05f6cf82 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -6,10 +6,12 @@
 #ifndef BTRFS_VOLUMES_H
 #define BTRFS_VOLUMES_H
 
-#include <linux/bio.h>
 #include <linux/sort.h>
 #include <linux/btrfs.h>
 #include "async-thread.h"
+#include "messages.h"
+#include "tree-checker.h"
+#include "rcu-string.h"
 
 #define BTRFS_MAX_DATA_CHUNK_SIZE	(10ULL * SZ_1G)
 
@@ -354,6 +356,8 @@ struct btrfs_fs_devices {
 	 * nonrot flag set
 	 */
 	bool rotating;
+	/* Devices support TRIM/discard commands */
+	bool discardable;
 
 	struct btrfs_fs_info *fs_info;
 	/* sysfs kobjects */
@@ -368,8 +372,6 @@ struct btrfs_fs_devices {
 	enum btrfs_read_policy read_policy;
 };
 
-#define BTRFS_BIO_INLINE_CSUM_SIZE	64
-
 #define BTRFS_MAX_DEVS(info) ((BTRFS_MAX_ITEM_SIZE(info)	\
 			- sizeof(struct btrfs_chunk))		\
 			/ sizeof(struct btrfs_stripe) + 1)
@@ -379,89 +381,6 @@ struct btrfs_fs_devices {
 				- 2 * sizeof(struct btrfs_chunk))	\
 				/ sizeof(struct btrfs_stripe) + 1)
 
-/*
- * Maximum number of sectors for a single bio to limit the size of the
- * checksum array.  This matches the number of bio_vecs per bio and thus the
- * I/O size for buffered I/O.
- */
-#define BTRFS_MAX_BIO_SECTORS				(256)
-
-typedef void (*btrfs_bio_end_io_t)(struct btrfs_bio *bbio);
-
-/*
- * Additional info to pass along bio.
- *
- * Mostly for btrfs specific features like csum and mirror_num.
- */
-struct btrfs_bio {
-	unsigned int mirror_num;
-	struct bvec_iter iter;
-
-	/* for direct I/O */
-	u64 file_offset;
-
-	/* @device is for stripe IO submission. */
-	struct btrfs_device *device;
-	u8 *csum;
-	u8 csum_inline[BTRFS_BIO_INLINE_CSUM_SIZE];
-
-	/* End I/O information supplied to btrfs_bio_alloc */
-	btrfs_bio_end_io_t end_io;
-	void *private;
-
-	/* For read end I/O handling */
-	struct work_struct end_io_work;
-
-	/*
-	 * This member must come last, bio_alloc_bioset will allocate enough
-	 * bytes for entire btrfs_bio but relies on bio being last.
-	 */
-	struct bio bio;
-};
-
-static inline struct btrfs_bio *btrfs_bio(struct bio *bio)
-{
-	return container_of(bio, struct btrfs_bio, bio);
-}
-
-int __init btrfs_bioset_init(void);
-void __cold btrfs_bioset_exit(void);
-
-struct bio *btrfs_bio_alloc(unsigned int nr_vecs, blk_opf_t opf,
-			    btrfs_bio_end_io_t end_io, void *private);
-struct bio *btrfs_bio_clone_partial(struct bio *orig, u64 offset, u64 size,
-				    btrfs_bio_end_io_t end_io, void *private);
-
-static inline void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status)
-{
-	bbio->bio.bi_status = status;
-	bbio->end_io(bbio);
-}
-
-static inline void btrfs_bio_free_csum(struct btrfs_bio *bbio)
-{
-	if (bbio->csum != bbio->csum_inline) {
-		kfree(bbio->csum);
-		bbio->csum = NULL;
-	}
-}
-
-/*
- * Iterate through a btrfs_bio (@bbio) on a per-sector basis.
- *
- * bvl        - struct bio_vec
- * bbio       - struct btrfs_bio
- * iters      - struct bvec_iter
- * bio_offset - unsigned int
- */
-#define btrfs_bio_for_each_sector(fs_info, bvl, bbio, iter, bio_offset)	\
-	for ((iter) = (bbio)->iter, (bio_offset) = 0;			\
-	     (iter).bi_size &&					\
-	     (((bvl) = bio_iter_iovec((&(bbio)->bio), (iter))), 1);	\
-	     (bio_offset) += fs_info->sectorsize,			\
-	     bio_advance_iter_single(&(bbio)->bio, &(iter),		\
-	     (fs_info)->sectorsize))
-
 struct btrfs_io_stripe {
 	struct btrfs_device *dev;
 	union {
@@ -603,6 +522,13 @@ static inline enum btrfs_map_op btrfs_op(struct bio *bio)
 	}
 }
 
+static inline unsigned long btrfs_chunk_item_size(int num_stripes)
+{
+	ASSERT(num_stripes);
+	return sizeof(struct btrfs_chunk) +
+		sizeof(struct btrfs_stripe) * (num_stripes - 1);
+}
+
 void btrfs_get_bioc(struct btrfs_io_context *bioc);
 void btrfs_put_bioc(struct btrfs_io_context *bioc);
 int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
@@ -611,6 +537,11 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 int btrfs_map_sblock(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 		     u64 logical, u64 *length,
 		     struct btrfs_io_context **bioc_ret);
+int __btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
+		      u64 logical, u64 *length,
+		      struct btrfs_io_context **bioc_ret,
+		      struct btrfs_io_stripe *smap, int *mirror_num_ret,
+		      int need_raid_map);
 struct btrfs_discard_stripe *btrfs_map_discard(struct btrfs_fs_info *fs_info,
 					       u64 logical, u64 *length_ret,
 					       u32 *num_stripes);
@@ -622,7 +553,6 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info);
 struct btrfs_block_group *btrfs_create_chunk(struct btrfs_trans_handle *trans,
 					    u64 type);
 void btrfs_mapping_tree_free(struct extent_map_tree *tree);
-void btrfs_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio, int mirror_num);
 int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 		       fmode_t flags, void *holder);
 struct btrfs_device *btrfs_scan_one_device(const char *path,
@@ -639,8 +569,8 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info,
 				 struct btrfs_dev_lookup_args *args,
 				 const char *path);
 struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
-					const u64 *devid,
-					const u8 *uuid);
+					const u64 *devid, const u8 *uuid,
+					const char *path);
 void btrfs_put_dev_args_from_path(struct btrfs_dev_lookup_args *args);
 void btrfs_free_device(struct btrfs_device *device);
 int btrfs_rm_device(struct btrfs_fs_info *fs_info,
@@ -741,6 +671,14 @@ static inline void btrfs_dev_stat_set(struct btrfs_device *dev,
 	atomic_inc(&dev->dev_stats_ccnt);
 }
 
+static inline const char *btrfs_dev_name(const struct btrfs_device *device)
+{
+	if (!device || test_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state))
+		return "<missing disk>";
+	else
+		return rcu_str_deref(device->name);
+}
+
 void btrfs_commit_device_sizes(struct btrfs_transaction *trans);
 
 struct list_head * __attribute_const__ btrfs_get_fs_uuids(void);