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, 32 insertions, 29 deletions

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 278a4ea651e1..f47731c45bb5 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -17,6 +17,7 @@
 #include <linux/uio.h>
 #include <linux/iversion.h>
 #include <linux/fsverity.h>
+#include <linux/iomap.h>
 #include "ctree.h"
 #include "disk-io.h"
 #include "transaction.h"
@@ -368,12 +369,13 @@ next_slot:
 			btrfs_set_file_extent_offset(leaf, fi, extent_offset);
 			btrfs_set_file_extent_num_bytes(leaf, fi,
 							extent_end - args->start);
-			btrfs_mark_buffer_dirty(leaf);
+			btrfs_mark_buffer_dirty(trans, leaf);
 
 			if (update_refs && disk_bytenr > 0) {
 				btrfs_init_generic_ref(&ref,
 						BTRFS_ADD_DELAYED_REF,
-						disk_bytenr, num_bytes, 0);
+						disk_bytenr, num_bytes, 0,
+						root->root_key.objectid);
 				btrfs_init_data_ref(&ref,
 						root->root_key.objectid,
 						new_key.objectid,
@@ -405,13 +407,13 @@ next_slot:
 
 			memcpy(&new_key, &key, sizeof(new_key));
 			new_key.offset = args->end;
-			btrfs_set_item_key_safe(fs_info, path, &new_key);
+			btrfs_set_item_key_safe(trans, path, &new_key);
 
 			extent_offset += args->end - key.offset;
 			btrfs_set_file_extent_offset(leaf, fi, extent_offset);
 			btrfs_set_file_extent_num_bytes(leaf, fi,
 							extent_end - args->end);
-			btrfs_mark_buffer_dirty(leaf);
+			btrfs_mark_buffer_dirty(trans, leaf);
 			if (update_refs && disk_bytenr > 0)
 				args->bytes_found += args->end - key.offset;
 			break;
@@ -431,7 +433,7 @@ next_slot:
 
 			btrfs_set_file_extent_num_bytes(leaf, fi,
 							args->start - key.offset);
-			btrfs_mark_buffer_dirty(leaf);
+			btrfs_mark_buffer_dirty(trans, leaf);
 			if (update_refs && disk_bytenr > 0)
 				args->bytes_found += extent_end - args->start;
 			if (args->end == extent_end)
@@ -463,7 +465,8 @@ delete_extent_item:
 			} else if (update_refs && disk_bytenr > 0) {
 				btrfs_init_generic_ref(&ref,
 						BTRFS_DROP_DELAYED_REF,
-						disk_bytenr, num_bytes, 0);
+						disk_bytenr, num_bytes, 0,
+						root->root_key.objectid);
 				btrfs_init_data_ref(&ref,
 						root->root_key.objectid,
 						key.objectid,
@@ -536,7 +539,8 @@ delete_extent_item:
 			if (btrfs_comp_cpu_keys(&key, &slot_key) > 0)
 				path->slots[0]++;
 		}
-		btrfs_setup_item_for_insert(root, path, &key, args->extent_item_size);
+		btrfs_setup_item_for_insert(trans, root, path, &key,
+					    args->extent_item_size);
 		args->extent_inserted = true;
 	}
 
@@ -593,7 +597,6 @@ static int extent_mergeable(struct extent_buffer *leaf, int slot,
 int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
 			      struct btrfs_inode *inode, u64 start, u64 end)
 {
-	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *root = inode->root;
 	struct extent_buffer *leaf;
 	struct btrfs_path *path;
@@ -664,7 +667,7 @@ again:
 				     ino, bytenr, orig_offset,
 				     &other_start, &other_end)) {
 			new_key.offset = end;
-			btrfs_set_item_key_safe(fs_info, path, &new_key);
+			btrfs_set_item_key_safe(trans, path, &new_key);
 			fi = btrfs_item_ptr(leaf, path->slots[0],
 					    struct btrfs_file_extent_item);
 			btrfs_set_file_extent_generation(leaf, fi,
@@ -679,7 +682,7 @@ again:
 							 trans->transid);
 			btrfs_set_file_extent_num_bytes(leaf, fi,
 							end - other_start);
-			btrfs_mark_buffer_dirty(leaf);
+			btrfs_mark_buffer_dirty(trans, leaf);
 			goto out;
 		}
 	}
@@ -698,7 +701,7 @@ again:
 							 trans->transid);
 			path->slots[0]++;
 			new_key.offset = start;
-			btrfs_set_item_key_safe(fs_info, path, &new_key);
+			btrfs_set_item_key_safe(trans, path, &new_key);
 
 			fi = btrfs_item_ptr(leaf, path->slots[0],
 					    struct btrfs_file_extent_item);
@@ -708,7 +711,7 @@ again:
 							other_end - start);
 			btrfs_set_file_extent_offset(leaf, fi,
 						     start - orig_offset);
-			btrfs_mark_buffer_dirty(leaf);
+			btrfs_mark_buffer_dirty(trans, leaf);
 			goto out;
 		}
 	}
@@ -742,10 +745,10 @@ again:
 		btrfs_set_file_extent_offset(leaf, fi, split - orig_offset);
 		btrfs_set_file_extent_num_bytes(leaf, fi,
 						extent_end - split);
-		btrfs_mark_buffer_dirty(leaf);
+		btrfs_mark_buffer_dirty(trans, leaf);
 
 		btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF, bytenr,
-				       num_bytes, 0);
+				       num_bytes, 0, root->root_key.objectid);
 		btrfs_init_data_ref(&ref, root->root_key.objectid, ino,
 				    orig_offset, 0, false);
 		ret = btrfs_inc_extent_ref(trans, &ref);
@@ -771,7 +774,7 @@ again:
 	other_start = end;
 	other_end = 0;
 	btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, bytenr,
-			       num_bytes, 0);
+			       num_bytes, 0, root->root_key.objectid);
 	btrfs_init_data_ref(&ref, root->root_key.objectid, ino, orig_offset,
 			    0, false);
 	if (extent_mergeable(leaf, path->slots[0] + 1,
@@ -814,7 +817,7 @@ again:
 		btrfs_set_file_extent_type(leaf, fi,
 					   BTRFS_FILE_EXTENT_REG);
 		btrfs_set_file_extent_generation(leaf, fi, trans->transid);
-		btrfs_mark_buffer_dirty(leaf);
+		btrfs_mark_buffer_dirty(trans, leaf);
 	} else {
 		fi = btrfs_item_ptr(leaf, del_slot - 1,
 			   struct btrfs_file_extent_item);
@@ -823,7 +826,7 @@ again:
 		btrfs_set_file_extent_generation(leaf, fi, trans->transid);
 		btrfs_set_file_extent_num_bytes(leaf, fi,
 						extent_end - key.offset);
-		btrfs_mark_buffer_dirty(leaf);
+		btrfs_mark_buffer_dirty(trans, leaf);
 
 		ret = btrfs_del_items(trans, root, path, del_slot, del_nr);
 		if (ret < 0) {
@@ -1747,7 +1750,7 @@ static inline bool skip_inode_logging(const struct btrfs_log_ctx *ctx)
 	struct btrfs_inode *inode = BTRFS_I(ctx->inode);
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 
-	if (btrfs_inode_in_log(inode, fs_info->generation) &&
+	if (btrfs_inode_in_log(inode, btrfs_get_fs_generation(fs_info)) &&
 	    list_empty(&ctx->ordered_extents))
 		return true;
 
@@ -1758,7 +1761,7 @@ static inline bool skip_inode_logging(const struct btrfs_log_ctx *ctx)
 	 * and for a fast fsync we don't wait for that, we only wait for the
 	 * writeback to complete.
 	 */
-	if (inode->last_trans <= fs_info->last_trans_committed &&
+	if (inode->last_trans <= btrfs_get_last_trans_committed(fs_info) &&
 	    (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags) ||
 	     list_empty(&ctx->ordered_extents)))
 		return true;
@@ -1887,7 +1890,6 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 
 	atomic_inc(&root->log_batch);
 
-	smp_mb();
 	if (skip_inode_logging(&ctx)) {
 		/*
 		 * We've had everything committed since the last time we were
@@ -2105,7 +2107,7 @@ static int fill_holes(struct btrfs_trans_handle *trans,
 		btrfs_set_file_extent_ram_bytes(leaf, fi, num_bytes);
 		btrfs_set_file_extent_offset(leaf, fi, 0);
 		btrfs_set_file_extent_generation(leaf, fi, trans->transid);
-		btrfs_mark_buffer_dirty(leaf);
+		btrfs_mark_buffer_dirty(trans, leaf);
 		goto out;
 	}
 
@@ -2113,7 +2115,7 @@ static int fill_holes(struct btrfs_trans_handle *trans,
 		u64 num_bytes;
 
 		key.offset = offset;
-		btrfs_set_item_key_safe(fs_info, path, &key);
+		btrfs_set_item_key_safe(trans, path, &key);
 		fi = btrfs_item_ptr(leaf, path->slots[0],
 				    struct btrfs_file_extent_item);
 		num_bytes = btrfs_file_extent_num_bytes(leaf, fi) + end -
@@ -2122,7 +2124,7 @@ static int fill_holes(struct btrfs_trans_handle *trans,
 		btrfs_set_file_extent_ram_bytes(leaf, fi, num_bytes);
 		btrfs_set_file_extent_offset(leaf, fi, 0);
 		btrfs_set_file_extent_generation(leaf, fi, trans->transid);
-		btrfs_mark_buffer_dirty(leaf);
+		btrfs_mark_buffer_dirty(trans, leaf);
 		goto out;
 	}
 	btrfs_release_path(path);
@@ -2274,7 +2276,7 @@ static int btrfs_insert_replace_extent(struct btrfs_trans_handle *trans,
 	btrfs_set_file_extent_num_bytes(leaf, extent, replace_len);
 	if (extent_info->is_new_extent)
 		btrfs_set_file_extent_generation(leaf, extent, trans->transid);
-	btrfs_mark_buffer_dirty(leaf);
+	btrfs_mark_buffer_dirty(trans, leaf);
 	btrfs_release_path(path);
 
 	ret = btrfs_inode_set_file_extent_range(inode, extent_info->file_offset,
@@ -2304,7 +2306,8 @@ static int btrfs_insert_replace_extent(struct btrfs_trans_handle *trans,
 
 		btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF,
 				       extent_info->disk_offset,
-				       extent_info->disk_len, 0);
+				       extent_info->disk_len, 0,
+				       root->root_key.objectid);
 		ref_offset = extent_info->file_offset - extent_info->data_offset;
 		btrfs_init_data_ref(&ref, root->root_key.objectid,
 				    btrfs_ino(inode), ref_offset, 0, false);
@@ -2477,7 +2480,7 @@ int btrfs_replace_file_extents(struct btrfs_inode *inode,
 			inode_set_mtime_to_ts(&inode->vfs_inode,
 					      inode_set_ctime_current(&inode->vfs_inode));
 
-		ret = btrfs_update_inode(trans, root, inode);
+		ret = btrfs_update_inode(trans, inode);
 		if (ret)
 			break;
 
@@ -2717,7 +2720,7 @@ static int btrfs_punch_hole(struct file *file, loff_t offset, loff_t len)
 	ASSERT(trans != NULL);
 	inode_inc_iversion(inode);
 	inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
-	ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
+	ret = btrfs_update_inode(trans, BTRFS_I(inode));
 	updated_inode = true;
 	btrfs_end_transaction(trans);
 	btrfs_btree_balance_dirty(fs_info);
@@ -2743,7 +2746,7 @@ out_only_mutex:
 		} else {
 			int ret2;
 
-			ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
+			ret = btrfs_update_inode(trans, BTRFS_I(inode));
 			ret2 = btrfs_end_transaction(trans);
 			if (!ret)
 				ret = ret2;
@@ -2810,7 +2813,7 @@ static int btrfs_fallocate_update_isize(struct inode *inode,
 	inode_set_ctime_current(inode);
 	i_size_write(inode, end);
 	btrfs_inode_safe_disk_i_size_write(BTRFS_I(inode), 0);
-	ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
+	ret = btrfs_update_inode(trans, BTRFS_I(inode));
 	ret2 = btrfs_end_transaction(trans);
 
 	return ret ? ret : ret2;