Merge tag 'for-5.4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "This continues with work on code refactoring, sanity checks and space
  handling. There are some less user visible changes, nothing that would
  particularly stand out.

  User visible changes:
   - tree checker, more sanity checks of:
       - ROOT_ITEM (key, size, generation, level, alignment, flags)
       - EXTENT_ITEM and METADATA_ITEM checks (key, size, offset,
         alignment, refs)
       - tree block reference items
       - EXTENT_DATA_REF (key, hash, offset)

   - deprecate flag BTRFS_SUBVOL_CREATE_ASYNC for subvolume creation
     ioctl, scheduled removal in 5.7

   - delete stale and unused UAPI definitions
     BTRFS_DEV_REPLACE_ITEM_STATE_*

   - improved export of debugging information available via existing
     sysfs directory structure

   - try harder to delete relations between qgroups and allow to delete
     orphan entries

   - remove unreliable space checks before relocation starts

  Core:
   - space handling:
       - improved ticket reservations and other high level logic in
         order to remove special cases
       - factor flushing infrastructure and use it for different
         contexts, allows to remove some special case handling
       - reduce metadata reservation when only updating inodes
       - reduce global block reserve minimum size (affects small
         filesystems)
       - improved overcommit logic wrt global block reserve

   - tests:
       - fix memory leaks in extent IO tree
       - catch all TRIM range

  Fixes:
   - fix ENOSPC errors, leading to transaction aborts, when cloning
     extents

   - several fixes for inode number cache (mount option inode_cache)

   - fix potential soft lockups during send when traversing large trees

   - fix unaligned access to space cache pages with SLUB debug on
     (PowerPC)

  Other:
   - refactoring public/private functions, moving to new or more
     appropriate files

   - defines converted to enums

   - error handling improvements

   - more assertions and comments

   - old code deletion"

* tag 'for-5.4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (138 commits)
  btrfs: Relinquish CPUs in btrfs_compare_trees
  btrfs: Don't assign retval of btrfs_try_tree_write_lock/btrfs_tree_read_lock_atomic
  btrfs: create structure to encode checksum type and length
  btrfs: turn checksum type define into an enum
  btrfs: add enospc debug messages for ticket failure
  btrfs: do not account global reserve in can_overcommit
  btrfs: use btrfs_try_granting_tickets in update_global_rsv
  btrfs: always reserve our entire size for the global reserve
  btrfs: change the minimum global reserve size
  btrfs: rename btrfs_space_info_add_old_bytes
  btrfs: remove orig_bytes from reserve_ticket
  btrfs: fix may_commit_transaction to deal with no partial filling
  btrfs: rework wake_all_tickets
  btrfs: refactor the ticket wakeup code
  btrfs: stop partially refilling tickets when releasing space
  btrfs: add space reservation tracepoint for reserved bytes
  btrfs: roll tracepoint into btrfs_space_info_update helper
  btrfs: do not allow reservations if we have pending tickets
  btrfs: stop clearing EXTENT_DIRTY in inode I/O tree
  btrfs: treat RWF_{,D}SYNC writes as sync for CRCs
  ...

fs/btrfs/Makefile

@@ -11,7 +11,7 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \
 	   compression.o delayed-ref.o relocation.o delayed-inode.o scrub.o \
 	   reada.o backref.o ulist.o qgroup.o send.o dev-replace.o raid56.o \
 	   uuid-tree.o props.o free-space-tree.o tree-checker.o space-info.o \
-	   block-rsv.o delalloc-space.o
+	   block-rsv.o delalloc-space.o block-group.o
 
 btrfs-$(CONFIG_BTRFS_FS_POSIX_ACL) += acl.o
 btrfs-$(CONFIG_BTRFS_FS_CHECK_INTEGRITY) += check-integrity.o

fs/btrfs/async-thread.c

@@ -12,9 +12,11 @@
 #include "async-thread.h"
 #include "ctree.h"
 
-#define WORK_DONE_BIT 0
-#define WORK_ORDER_DONE_BIT 1
-#define WORK_HIGH_PRIO_BIT 2
+enum {
+	WORK_DONE_BIT,
+	WORK_ORDER_DONE_BIT,
+	WORK_HIGH_PRIO_BIT,
+};
 
 #define NO_THRESHOLD (-1)
 #define DFT_THRESHOLD (32)

fs/btrfs/block-group.h

+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef BTRFS_BLOCK_GROUP_H
+#define BTRFS_BLOCK_GROUP_H
+
+#include "free-space-cache.h"
+
+enum btrfs_disk_cache_state {
+	BTRFS_DC_WRITTEN,
+	BTRFS_DC_ERROR,
+	BTRFS_DC_CLEAR,
+	BTRFS_DC_SETUP,
+};
+
+/*
+ * Control flags for do_chunk_alloc's force field CHUNK_ALLOC_NO_FORCE means to
+ * only allocate a chunk if we really need one.
+ *
+ * CHUNK_ALLOC_LIMITED means to only try and allocate one if we have very few
+ * chunks already allocated.  This is used as part of the clustering code to
+ * help make sure we have a good pool of storage to cluster in, without filling
+ * the FS with empty chunks
+ *
+ * CHUNK_ALLOC_FORCE means it must try to allocate one
+ */
+enum btrfs_chunk_alloc_enum {
+	CHUNK_ALLOC_NO_FORCE,
+	CHUNK_ALLOC_LIMITED,
+	CHUNK_ALLOC_FORCE,
+};
+
+struct btrfs_caching_control {
+	struct list_head list;
+	struct mutex mutex;
+	wait_queue_head_t wait;
+	struct btrfs_work work;
+	struct btrfs_block_group_cache *block_group;
+	u64 progress;
+	refcount_t count;
+};
+
+/* Once caching_thread() finds this much free space, it will wake up waiters. */
+#define CACHING_CTL_WAKE_UP SZ_2M
+
+struct btrfs_block_group_cache {
+	struct btrfs_key key;
+	struct btrfs_block_group_item item;
+	struct btrfs_fs_info *fs_info;
+	struct inode *inode;
+	spinlock_t lock;
+	u64 pinned;
+	u64 reserved;
+	u64 delalloc_bytes;
+	u64 bytes_super;
+	u64 flags;
+	u64 cache_generation;
+
+	/*
+	 * If the free space extent count exceeds this number, convert the block
+	 * group to bitmaps.
+	 */
+	u32 bitmap_high_thresh;
+
+	/*
+	 * If the free space extent count drops below this number, convert the
+	 * block group back to extents.
+	 */
+	u32 bitmap_low_thresh;
+
+	/*
+	 * It is just used for the delayed data space allocation because
+	 * only the data space allocation and the relative metadata update
+	 * can be done cross the transaction.
+	 */
+	struct rw_semaphore data_rwsem;
+
+	/* For raid56, this is a full stripe, without parity */
+	unsigned long full_stripe_len;
+
+	unsigned int ro;
+	unsigned int iref:1;
+	unsigned int has_caching_ctl:1;
+	unsigned int removed:1;
+
+	int disk_cache_state;
+
+	/* Cache tracking stuff */
+	int cached;
+	struct btrfs_caching_control *caching_ctl;
+	u64 last_byte_to_unpin;
+
+	struct btrfs_space_info *space_info;
+
+	/* Free space cache stuff */
+	struct btrfs_free_space_ctl *free_space_ctl;
+
+	/* Block group cache stuff */
+	struct rb_node cache_node;
+
+	/* For block groups in the same raid type */
+	struct list_head list;
+
+	/* Usage count */
+	atomic_t count;
+
+	/*
+	 * List of struct btrfs_free_clusters for this block group.
+	 * Today it will only have one thing on it, but that may change
+	 */
+	struct list_head cluster_list;
+
+	/* For delayed block group creation or deletion of empty block groups */
+	struct list_head bg_list;
+
+	/* For read-only block groups */
+	struct list_head ro_list;
+
+	atomic_t trimming;
+
+	/* For dirty block groups */
+	struct list_head dirty_list;
+	struct list_head io_list;
+
+	struct btrfs_io_ctl io_ctl;
+
+	/*
+	 * Incremented when doing extent allocations and holding a read lock
+	 * on the space_info's groups_sem semaphore.
+	 * Decremented when an ordered extent that represents an IO against this
+	 * block group's range is created (after it's added to its inode's
+	 * root's list of ordered extents) or immediately after the allocation
+	 * if it's a metadata extent or fallocate extent (for these cases we
+	 * don't create ordered extents).
+	 */
+	atomic_t reservations;
+
+	/*
+	 * Incremented while holding the spinlock *lock* by a task checking if
+	 * it can perform a nocow write (incremented if the value for the *ro*
+	 * field is 0). Decremented by such tasks once they create an ordered
+	 * extent or before that if some error happens before reaching that step.
+	 * This is to prevent races between block group relocation and nocow
+	 * writes through direct IO.
+	 */
+	atomic_t nocow_writers;
+
+	/* Lock for free space tree operations. */
+	struct mutex free_space_lock;
+
+	/*
+	 * Does the block group need to be added to the free space tree?
+	 * Protected by free_space_lock.
+	 */
+	int needs_free_space;
+
+	/* Record locked full stripes for RAID5/6 block group */
+	struct btrfs_full_stripe_locks_tree full_stripe_locks_root;
+};
+
+#ifdef CONFIG_BTRFS_DEBUG
+static inline int btrfs_should_fragment_free_space(
+		struct btrfs_block_group_cache *block_group)
+{
+	struct btrfs_fs_info *fs_info = block_group->fs_info;
+
+	return (btrfs_test_opt(fs_info, FRAGMENT_METADATA) &&
+		block_group->flags & BTRFS_BLOCK_GROUP_METADATA) ||
+	       (btrfs_test_opt(fs_info, FRAGMENT_DATA) &&
+		block_group->flags &  BTRFS_BLOCK_GROUP_DATA);
+}
+#endif
+
+struct btrfs_block_group_cache *btrfs_lookup_first_block_group(
+		struct btrfs_fs_info *info, u64 bytenr);
+struct btrfs_block_group_cache *btrfs_lookup_block_group(
+		struct btrfs_fs_info *info, u64 bytenr);
+struct btrfs_block_group_cache *btrfs_next_block_group(
+		struct btrfs_block_group_cache *cache);
+void btrfs_get_block_group(struct btrfs_block_group_cache *cache);
+void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
+void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info,
+					const u64 start);
+void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg);
+bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr);
+void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr);
+void btrfs_wait_nocow_writers(struct btrfs_block_group_cache *bg);
+void btrfs_wait_block_group_cache_progress(struct btrfs_block_group_cache *cache,
+				           u64 num_bytes);
+int btrfs_wait_block_group_cache_done(struct btrfs_block_group_cache *cache);
+int btrfs_cache_block_group(struct btrfs_block_group_cache *cache,
+			    int load_cache_only);
+void btrfs_put_caching_control(struct btrfs_caching_control *ctl);
+struct btrfs_caching_control *btrfs_get_caching_control(
+		struct btrfs_block_group_cache *cache);
+u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
+		       u64 start, u64 end);
+struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
+				struct btrfs_fs_info *fs_info,
+				const u64 chunk_offset);
+int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
+			     u64 group_start, struct extent_map *em);
+void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info);
+void btrfs_mark_bg_unused(struct btrfs_block_group_cache *bg);
+int btrfs_read_block_groups(struct btrfs_fs_info *info);
+int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used,
+			   u64 type, u64 chunk_offset, u64 size);
+void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans);
+int btrfs_inc_block_group_ro(struct btrfs_block_group_cache *cache);
+void btrfs_dec_block_group_ro(struct btrfs_block_group_cache *cache);
+int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans);
+int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans);
+int btrfs_setup_space_cache(struct btrfs_trans_handle *trans);
+int btrfs_update_block_group(struct btrfs_trans_handle *trans,
+			     u64 bytenr, u64 num_bytes, int alloc);
+int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache,
+			     u64 ram_bytes, u64 num_bytes, int delalloc);
+void btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache,
+			       u64 num_bytes, int delalloc);
+int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
+		      enum btrfs_chunk_alloc_enum force);
+int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans, u64 type);
+void check_system_chunk(struct btrfs_trans_handle *trans, const u64 type);
+u64 btrfs_get_alloc_profile(struct btrfs_fs_info *fs_info, u64 orig_flags);
+void btrfs_put_block_group_cache(struct btrfs_fs_info *info);
+int btrfs_free_block_groups(struct btrfs_fs_info *info);
+
+static inline u64 btrfs_data_alloc_profile(struct btrfs_fs_info *fs_info)
+{
+	return btrfs_get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_DATA);
+}
+
+static inline u64 btrfs_metadata_alloc_profile(struct btrfs_fs_info *fs_info)
+{
+	return btrfs_get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_METADATA);
+}
+
+static inline u64 btrfs_system_alloc_profile(struct btrfs_fs_info *fs_info)
+{
+	return btrfs_get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_SYSTEM);
+}
+
+static inline int btrfs_block_group_cache_done(
+		struct btrfs_block_group_cache *cache)
+{
+	smp_mb();
+	return cache->cached == BTRFS_CACHE_FINISHED ||
+		cache->cached == BTRFS_CACHE_ERROR;
+}
+
+#endif /* BTRFS_BLOCK_GROUP_H */

fs/btrfs/block-rsv.c

 // SPDX-License-Identifier: GPL-2.0
 
+#include "misc.h"
 #include "ctree.h"
 #include "block-rsv.h"
 #include "space-info.h"
-#include "math.h"
 #include "transaction.h"
 
 static u64 block_rsv_release_bytes(struct btrfs_fs_info *fs_info,
@@ -54,8 +54,9 @@ static u64 block_rsv_release_bytes(struct btrfs_fs_info *fs_info,
 			spin_unlock(&dest->lock);
 		}
 		if (num_bytes)
-			btrfs_space_info_add_old_bytes(fs_info, space_info,
-						       num_bytes);
+			btrfs_space_info_free_bytes_may_use(fs_info,
+							    space_info,
+							    num_bytes);
 	}
 	if (qgroup_to_release_ret)
 		*qgroup_to_release_ret = qgroup_to_release;
@@ -258,6 +259,7 @@ void btrfs_update_global_block_rsv(struct btrfs_fs_info *fs_info)
 	struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv;
 	struct btrfs_space_info *sinfo = block_rsv->space_info;
 	u64 num_bytes;
+	unsigned min_items;
 
 	/*
 	 * The global block rsv is based on the size of the extent tree, the
@@ -267,7 +269,26 @@ void btrfs_update_global_block_rsv(struct btrfs_fs_info *fs_info)
 	num_bytes = btrfs_root_used(&fs_info->extent_root->root_item) +
 		btrfs_root_used(&fs_info->csum_root->root_item) +
 		btrfs_root_used(&fs_info->tree_root->root_item);
-	num_bytes = max_t(u64, num_bytes, SZ_16M);
+
+	/*
+	 * We at a minimum are going to modify the csum root, the tree root, and
+	 * the extent root.
+	 */
+	min_items = 3;
+
+	/*
+	 * But we also want to reserve enough space so we can do the fallback
+	 * global reserve for an unlink, which is an additional 5 items (see the
+	 * comment in __unlink_start_trans for what we're modifying.)
+	 *
+	 * But we also need space for the delayed ref updates from the unlink,
+	 * so its 10, 5 for the actual operation, and 5 for the delayed ref
+	 * updates.
+	 */
+	min_items += 10;
+
+	num_bytes = max_t(u64, num_bytes,
+			  btrfs_calc_insert_metadata_size(fs_info, min_items));
 
 	spin_lock(&sinfo->lock);
 	spin_lock(&block_rsv->lock);
@@ -275,25 +296,16 @@ void btrfs_update_global_block_rsv(struct btrfs_fs_info *fs_info)
 	block_rsv->size = min_t(u64, num_bytes, SZ_512M);
 
 	if (block_rsv->reserved < block_rsv->size) {
-		num_bytes = btrfs_space_info_used(sinfo, true);
-		if (sinfo->total_bytes > num_bytes) {
-			num_bytes = sinfo->total_bytes - num_bytes;
-			num_bytes = min(num_bytes,
-					block_rsv->size - block_rsv->reserved);
-			block_rsv->reserved += num_bytes;
-			btrfs_space_info_update_bytes_may_use(fs_info, sinfo,
-							      num_bytes);
-			trace_btrfs_space_reservation(fs_info, "space_info",
-						      sinfo->flags, num_bytes,
-						      1);
-		}
+		num_bytes = block_rsv->size - block_rsv->reserved;
+		block_rsv->reserved += num_bytes;
+		btrfs_space_info_update_bytes_may_use(fs_info, sinfo,
+						      num_bytes);
 	} else if (block_rsv->reserved > block_rsv->size) {
 		num_bytes = block_rsv->reserved - block_rsv->size;
 		btrfs_space_info_update_bytes_may_use(fs_info, sinfo,
 						      -num_bytes);
-		trace_btrfs_space_reservation(fs_info, "space_info",
-				      sinfo->flags, num_bytes, 0);
 		block_rsv->reserved = block_rsv->size;
+		btrfs_try_granting_tickets(fs_info, sinfo);
 	}
 
 	if (block_rsv->reserved == block_rsv->size)

fs/btrfs/check-integrity.c

@@ -940,7 +940,7 @@ static void btrfsic_stack_frame_free(struct btrfsic_stack_frame *sf)
 	kfree(sf);
 }
 
-static int btrfsic_process_metablock(
+static noinline_for_stack int btrfsic_process_metablock(
 		struct btrfsic_state *state,
 		struct btrfsic_block *const first_block,
 		struct btrfsic_block_data_ctx *const first_block_ctx,
@@ -1706,8 +1706,9 @@ static void btrfsic_dump_database(struct btrfsic_state *state)
  * Test whether the disk block contains a tree block (leaf or node)
  * (note that this test fails for the super block)
  */
-static int btrfsic_test_for_metadata(struct btrfsic_state *state,
-				     char **datav, unsigned int num_pages)
+static noinline_for_stack int btrfsic_test_for_metadata(
+		struct btrfsic_state *state,
+		char **datav, unsigned int num_pages)
 {
 	struct btrfs_fs_info *fs_info = state->fs_info;
 	SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);

fs/btrfs/compression.c

@@ -18,6 +18,7 @@
 #include <linux/sched/mm.h>
 #include <linux/log2.h>
 #include <crypto/hash.h>
+#include "misc.h"
 #include "ctree.h"
 #include "disk-io.h"
 #include "transaction.h"
@@ -1039,7 +1040,7 @@ int btrfs_compress_pages(unsigned int type_level, struct address_space *mapping,
 	struct list_head *workspace;
 	int ret;
 
-	level = btrfs_compress_op[type]->set_level(level);
+	level = btrfs_compress_set_level(type, level);
 	workspace = get_workspace(type, level);
 	ret = btrfs_compress_op[type]->compress_pages(workspace, mapping,
 						      start, pages,
@@ -1611,7 +1612,23 @@ unsigned int btrfs_compress_str2level(unsigned int type, const char *str)
 			level = 0;
 	}
 
-	level = btrfs_compress_op[type]->set_level(level);
+	level = btrfs_compress_set_level(type, level);
+
+	return level;
+}
+
+/*
+ * Adjust @level according to the limits of the compression algorithm or
+ * fallback to default
+ */
+unsigned int btrfs_compress_set_level(int type, unsigned level)
+{
+	const struct btrfs_compress_op *ops = btrfs_compress_op[type];
+
+	if (level == 0)
+		level = ops->default_level;
+	else
+		level = min(level, ops->max_level);
 
 	return level;
 }

fs/btrfs/compression.h

@@ -156,12 +156,9 @@ struct btrfs_compress_op {
 			  unsigned long start_byte,
 			  size_t srclen, size_t destlen);
 
-	/*
-	 * This bounds the level set by the user to be within range of a
-	 * particular compression type.  It returns the level that will be used
-	 * if the level is out of bounds or the default if 0 is passed in.
-	 */
-	unsigned int (*set_level)(unsigned int level);
+	/* Maximum level supported by the compression algorithm */
+	unsigned int max_level;
+	unsigned int default_level;
 };
 
 /* The heuristic workspaces are managed via the 0th workspace manager */
@@ -175,6 +172,8 @@ extern const struct btrfs_compress_op btrfs_zstd_compress;
 const char* btrfs_compress_type2str(enum btrfs_compression_type type);
 bool btrfs_compress_is_valid_type(const char *str, size_t len);
 
+unsigned int btrfs_compress_set_level(int type, unsigned level);
+
 int btrfs_compress_heuristic(struct inode *inode, u64 start, u64 end);
 
 #endif

fs/btrfs/dedupe.h

-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (C) 2016 Fujitsu.  All rights reserved.
- */
-
-#ifndef BTRFS_DEDUPE_H
-#define BTRFS_DEDUPE_H
-
-/* later in-band dedupe will expand this struct */
-struct btrfs_dedupe_hash;
-
-#endif

fs/btrfs/delalloc-space.c

@@ -7,6 +7,7 @@
 #include "space-info.h"
 #include "transaction.h"
 #include "qgroup.h"
+#include "block-group.h"
 
 int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes)
 {
@@ -129,8 +130,6 @@ int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes)
 		return -ENOSPC;
 	}
 	btrfs_space_info_update_bytes_may_use(fs_info, data_sinfo, bytes);
-	trace_btrfs_space_reservation(fs_info, "space_info",
-				      data_sinfo->flags, bytes, 1);
 	spin_unlock(&data_sinfo->lock);
 
 	return 0;
@@ -182,8 +181,6 @@ void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start,
 	data_sinfo = fs_info->data_sinfo;
 	spin_lock(&data_sinfo->lock);
 	btrfs_space_info_update_bytes_may_use(fs_info, data_sinfo, -len);
-	trace_btrfs_space_reservation(fs_info, "space_info",
-				      data_sinfo->flags, len, 0);
 	spin_unlock(&data_sinfo->lock);
 }
 
@@ -254,13 +251,20 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
 
 	lockdep_assert_held(&inode->lock);
 	outstanding_extents = inode->outstanding_extents;
-	if (outstanding_extents)
-		reserve_size = btrfs_calc_trans_metadata_size(fs_info,
-						outstanding_extents + 1);
+
+	/*
+	 * Insert size for the number of outstanding extents, 1 normal size for
+	 * updating the inode.
+	 */
+	if (outstanding_extents) {
+		reserve_size = btrfs_calc_insert_metadata_size(fs_info,
+						outstanding_extents);
+		reserve_size += btrfs_calc_metadata_size(fs_info, 1);
+	}
 	csum_leaves = btrfs_csum_bytes_to_leaves(fs_info,
 						 inode->csum_bytes);
-	reserve_size += btrfs_calc_trans_metadata_size(fs_info,
-						       csum_leaves);
+	reserve_size += btrfs_calc_insert_metadata_size(fs_info,
+							csum_leaves);
 	/*
 	 * For qgroup rsv, the calculation is very simple:
 	 * account one nodesize for each outstanding extent
@@ -281,10 +285,16 @@ static void calc_inode_reservations(struct btrfs_fs_info *fs_info,
 {
 	u64 nr_extents = count_max_extents(num_bytes);
 	u64 csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, num_bytes);
+	u64 inode_update = btrfs_calc_metadata_size(fs_info, 1);
 
-	/* We add one for the inode update at finish ordered time */
-	*meta_reserve = btrfs_calc_trans_metadata_size(fs_info,
-						nr_extents + csum_leaves + 1);
+	*meta_reserve = btrfs_calc_insert_metadata_size(fs_info,
+						nr_extents + csum_leaves);
+
+	/*
+	 * finish_ordered_io has to update the inode, so add the space required
+	 * for an inode update.
+	 */
+	*meta_reserve += inode_update;
 	*qgroup_reserve = nr_extents * fs_info->nodesize;
 }
 

fs/btrfs/dev-replace.c

@@ -9,6 +9,7 @@
 #include <linux/blkdev.h>
 #include <linux/kthread.h>
 #include <linux/math64.h>
+#include "misc.h"
 #include "ctree.h"
 #include "extent_map.h"
 #include "disk-io.h"
@@ -56,7 +57,7 @@ int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info)
 no_valid_dev_replace_entry_found:
 		ret = 0;
 		dev_replace->replace_state =
-			BTRFS_DEV_REPLACE_ITEM_STATE_NEVER_STARTED;
+			BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED;
 		dev_replace->cont_reading_from_srcdev_mode =
 		    BTRFS_DEV_REPLACE_ITEM_CONT_READING_FROM_SRCDEV_MODE_ALWAYS;
 		dev_replace->time_started = 0;

fs/btrfs/disk-io.h

@@ -45,8 +45,6 @@ struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr,
 				      u64 parent_transid, int level,
 				      struct btrfs_key *first_key);
 void readahead_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr);
-int reada_tree_block_flagged(struct btrfs_fs_info *fs_info, u64 bytenr,
-			 int mirror_num, struct extent_buffer **eb);
 struct extent_buffer *btrfs_find_create_tree_block(
 						struct btrfs_fs_info *fs_info,
 						u64 bytenr);