Merge tag 'for-6.7-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "New features:

   - raid-stripe-tree

     New tree for logical file extent mapping where the physical mapping
     may not match on multiple devices. This is now used in zoned mode
     to implement RAID0/RAID1* profiles, but can be used in non-zoned
     mode as well. The support for RAID56 is in development and will
     eventually fix the problems with the current implementation. This
     is a backward incompatible feature and has to be enabled at mkfs
     time.

   - simple quota accounting (squota)

     A simplified mode of qgroup that accounts all space on the initial
     extent owners (a subvolume), the snapshots are then cheap to create
     and delete. The deletion of snapshots in fully accounting qgroups
     is a known CPU/IO performance bottleneck.

     The squota is not suitable for the general use case but works well
     for containers where the original subvolume exists for the whole
     time. This is a backward incompatible feature as it needs extending
     some structures, but can be enabled on an existing filesystem.

   - temporary filesystem fsid (temp_fsid)

     The fsid identifies a filesystem and is hard coded in the
     structures, which disallows mounting the same fsid found on
     different devices.

     For a single device filesystem this is not strictly necessary, a
     new temporary fsid can be generated on mount e.g. after a device is
     cloned. This will be used by Steam Deck for root partition A/B
     testing, or can be used for VM root images.

  Other user visible changes:

   - filesystems with partially finished metadata_uuid conversion cannot
     be mounted anymore and the uuid fixup has to be done by btrfs-progs
     (btrfstune).

  Performance improvements:

   - reduce reservations for checksum deletions (with enabled free space
     tree by factor of 4), on a sample workload on file with many
     extents the deletion time decreased by 12%

   - make extent state merges more efficient during insertions, reduce
     rb-tree iterations (run time of critical functions reduced by 5%)

  Core changes:

   - the integrity check functionality has been removed, this was a
     debugging feature and removal does not affect other integrity
     checks like checksums or tree-checker

   - space reservation changes:

      - more efficient delayed ref reservations, this avoids building up
        too much work or overusing or exhausting the global block
        reserve in some situations

      - move delayed refs reservation to the transaction start time,
        this prevents some ENOSPC corner cases related to exhaustion of
        global reserve

      - improvements in reducing excessive reservations for block group
        items

      - adjust overcommit logic in near full situations, account for one
        more chunk to eventually allocate metadata chunk, this is mostly
        relevant for small filesystems (<10GiB)

   - single device filesystems are scanned but not registered (except
     seed devices), this allows temp_fsid to work

   - qgroup iterations do not need GFP_ATOMIC allocations anymore

   - cleanups, refactoring, reduced data structure size, function
     parameter simplifications, error handling fixes"

* tag 'for-6.7-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (156 commits)
  btrfs: open code timespec64 in struct btrfs_inode
  btrfs: remove redundant log root tree index assignment during log sync
  btrfs: remove redundant initialization of variable dirty in btrfs_update_time()
  btrfs: sysfs: show temp_fsid feature
  btrfs: disable the device add feature for temp-fsid
  btrfs: disable the seed feature for temp-fsid
  btrfs: update comment for temp-fsid, fsid, and metadata_uuid
  btrfs: remove pointless empty log context list check when syncing log
  btrfs: update comment for struct btrfs_inode::lock
  btrfs: remove pointless barrier from btrfs_sync_file()
  btrfs: add and use helpers for reading and writing last_trans_committed
  btrfs: add and use helpers for reading and writing fs_info->generation
  btrfs: add and use helpers for reading and writing log_transid
  btrfs: add and use helpers for reading and writing last_log_commit
  btrfs: support cloned-device mount capability
  btrfs: add helper function find_fsid_by_disk
  btrfs: stop reserving excessive space for block group item insertions
  btrfs: stop reserving excessive space for block group item updates
  btrfs: reorder btrfs_inode to fill gaps
  btrfs: open code btrfs_ordered_inode_tree in btrfs_inode
  ...

1 files changed, 81 insertions, 61 deletions

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index ff40acd63a37..196c005c31f6 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -6,37 +6,10 @@
 #ifndef BTRFS_CTREE_H
 #define BTRFS_CTREE_H
 
-#include <linux/mm.h>
-#include <linux/sched/signal.h>
-#include <linux/highmem.h>
-#include <linux/fs.h>
-#include <linux/rwsem.h>
-#include <linux/semaphore.h>
-#include <linux/completion.h>
-#include <linux/backing-dev.h>
-#include <linux/wait.h>
-#include <linux/slab.h>
-#include <trace/events/btrfs.h>
-#include <asm/unaligned.h>
 #include <linux/pagemap.h>
-#include <linux/btrfs.h>
-#include <linux/btrfs_tree.h>
-#include <linux/workqueue.h>
-#include <linux/security.h>
-#include <linux/sizes.h>
-#include <linux/dynamic_debug.h>
-#include <linux/refcount.h>
-#include <linux/crc32c.h>
-#include <linux/iomap.h>
-#include <linux/fscrypt.h>
-#include "extent-io-tree.h"
-#include "extent_io.h"
-#include "extent_map.h"
-#include "async-thread.h"
-#include "block-rsv.h"
 #include "locking.h"
-#include "misc.h"
 #include "fs.h"
+#include "accessors.h"
 
 struct btrfs_trans_handle;
 struct btrfs_transaction;
@@ -218,10 +191,22 @@ struct btrfs_root {
 	atomic_t log_commit[2];
 	/* Used only for log trees of subvolumes, not for the log root tree */
 	atomic_t log_batch;
+	/*
+	 * Protected by the 'log_mutex' lock but can be read without holding
+	 * that lock to avoid unnecessary lock contention, in which case it
+	 * should be read using btrfs_get_root_log_transid() except if it's a
+	 * log tree in which case it can be directly accessed. Updates to this
+	 * field should always use btrfs_set_root_log_transid(), except for log
+	 * trees where the field can be updated directly.
+	 */
 	int log_transid;
 	/* No matter the commit succeeds or not*/
 	int log_transid_committed;
-	/* Just be updated when the commit succeeds. */
+	/*
+	 * Just be updated when the commit succeeds. Use
+	 * btrfs_get_root_last_log_commit() and btrfs_set_root_last_log_commit()
+	 * to access this field.
+	 */
 	int last_log_commit;
 	pid_t log_start_pid;
 
@@ -326,6 +311,9 @@ struct btrfs_root {
 	/* Used only by log trees, when logging csum items */
 	struct extent_io_tree log_csum_range;
 
+	/* Used in simple quotas, track root during relocation. */
+	u64 relocation_src_root;
+
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 	u64 alloc_bytenr;
 #endif
@@ -352,6 +340,26 @@ static inline u64 btrfs_root_id(const struct btrfs_root *root)
 	return root->root_key.objectid;
 }
 
+static inline int btrfs_get_root_log_transid(const struct btrfs_root *root)
+{
+	return READ_ONCE(root->log_transid);
+}
+
+static inline void btrfs_set_root_log_transid(struct btrfs_root *root, int log_transid)
+{
+	WRITE_ONCE(root->log_transid, log_transid);
+}
+
+static inline int btrfs_get_root_last_log_commit(const struct btrfs_root *root)
+{
+	return READ_ONCE(root->last_log_commit);
+}
+
+static inline void btrfs_set_root_last_log_commit(struct btrfs_root *root, int commit_id)
+{
+	WRITE_ONCE(root->last_log_commit, commit_id);
+}
+
 /*
  * Structure that conveys information about an extent that is going to replace
  * all the extents in a file range.
@@ -470,30 +478,6 @@ static inline u32 BTRFS_MAX_XATTR_SIZE(const struct btrfs_fs_info *info)
 #define BTRFS_BYTES_TO_BLKS(fs_info, bytes) \
 				((bytes) >> (fs_info)->sectorsize_bits)
 
-static inline u32 btrfs_crc32c(u32 crc, const void *address, unsigned length)
-{
-	return crc32c(crc, address, length);
-}
-
-static inline void btrfs_crc32c_final(u32 crc, u8 *result)
-{
-	put_unaligned_le32(~crc, result);
-}
-
-static inline u64 btrfs_name_hash(const char *name, int len)
-{
-       return crc32c((u32)~1, name, len);
-}
-
-/*
- * Figure the key offset of an extended inode ref
- */
-static inline u64 btrfs_extref_hash(u64 parent_objectid, const char *name,
-                                   int len)
-{
-       return (u64) crc32c(parent_objectid, name, len);
-}
-
 static inline gfp_t btrfs_alloc_write_mask(struct address_space *mapping)
 {
 	return mapping_gfp_constraint(mapping, ~__GFP_FS);
@@ -513,12 +497,42 @@ int btrfs_bin_search(struct extent_buffer *eb, int first_slot,
 		     const struct btrfs_key *key, int *slot);
 
 int __pure btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2);
+
+#ifdef __LITTLE_ENDIAN
+
+/*
+ * Compare two keys, on little-endian the disk order is same as CPU order and
+ * we can avoid the conversion.
+ */
+static inline int btrfs_comp_keys(const struct btrfs_disk_key *disk_key,
+				  const struct btrfs_key *k2)
+{
+	const struct btrfs_key *k1 = (const struct btrfs_key *)disk_key;
+
+	return btrfs_comp_cpu_keys(k1, k2);
+}
+
+#else
+
+/* Compare two keys in a memcmp fashion. */
+static inline int btrfs_comp_keys(const struct btrfs_disk_key *disk,
+				  const struct btrfs_key *k2)
+{
+	struct btrfs_key k1;
+
+	btrfs_disk_key_to_cpu(&k1, disk);
+
+	return btrfs_comp_cpu_keys(&k1, k2);
+}
+
+#endif
+
 int btrfs_previous_item(struct btrfs_root *root,
 			struct btrfs_path *path, u64 min_objectid,
 			int type);
 int btrfs_previous_extent_item(struct btrfs_root *root,
 			struct btrfs_path *path, u64 min_objectid);
-void btrfs_set_item_key_safe(struct btrfs_fs_info *fs_info,
+void btrfs_set_item_key_safe(struct btrfs_trans_handle *trans,
 			     struct btrfs_path *path,
 			     const struct btrfs_key *new_key);
 struct extent_buffer *btrfs_root_node(struct btrfs_root *root);
@@ -536,6 +550,13 @@ int btrfs_cow_block(struct btrfs_trans_handle *trans,
 		    struct extent_buffer *parent, int parent_slot,
 		    struct extent_buffer **cow_ret,
 		    enum btrfs_lock_nesting nest);
+int btrfs_force_cow_block(struct btrfs_trans_handle *trans,
+			  struct btrfs_root *root,
+			  struct extent_buffer *buf,
+			  struct extent_buffer *parent, int parent_slot,
+			  struct extent_buffer **cow_ret,
+			  u64 search_start, u64 empty_size,
+			  enum btrfs_lock_nesting nest);
 int btrfs_copy_root(struct btrfs_trans_handle *trans,
 		      struct btrfs_root *root,
 		      struct extent_buffer *buf,
@@ -545,8 +566,10 @@ int btrfs_block_can_be_shared(struct btrfs_trans_handle *trans,
 			      struct extent_buffer *buf);
 int btrfs_del_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		  struct btrfs_path *path, int level, int slot);
-void btrfs_extend_item(struct btrfs_path *path, u32 data_size);
-void btrfs_truncate_item(struct btrfs_path *path, u32 new_size, int from_end);
+void btrfs_extend_item(struct btrfs_trans_handle *trans,
+		       struct btrfs_path *path, u32 data_size);
+void btrfs_truncate_item(struct btrfs_trans_handle *trans,
+			 struct btrfs_path *path, u32 new_size, int from_end);
 int btrfs_split_item(struct btrfs_trans_handle *trans,
 		     struct btrfs_root *root,
 		     struct btrfs_path *path,
@@ -567,10 +590,6 @@ int btrfs_search_slot_for_read(struct btrfs_root *root,
 			       const struct btrfs_key *key,
 			       struct btrfs_path *p, int find_higher,
 			       int return_any);
-int btrfs_realloc_node(struct btrfs_trans_handle *trans,
-		       struct btrfs_root *root, struct extent_buffer *parent,
-		       int start_slot, u64 *last_ret,
-		       struct btrfs_key *progress);
 void btrfs_release_path(struct btrfs_path *p);
 struct btrfs_path *btrfs_alloc_path(void);
 void btrfs_free_path(struct btrfs_path *p);
@@ -610,7 +629,8 @@ struct btrfs_item_batch {
 	int nr;
 };
 
-void btrfs_setup_item_for_insert(struct btrfs_root *root,
+void btrfs_setup_item_for_insert(struct btrfs_trans_handle *trans,
+				 struct btrfs_root *root,
 				 struct btrfs_path *path,
 				 const struct btrfs_key *key,
 				 u32 data_size);