Merge tag 'for-6.1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "There's a bunch of performance improvements, most notably the FIEMAP
  speedup, the new block group tree to speed up mount on large
  filesystems, more io_uring integration, some sysfs exports and the
  usual fixes and core updates.

  Summary:

  Performance:

   - outstanding FIEMAP speed improvement
      - algorithmic change how extents are enumerated leads to orders of
        magnitude speed boost (uncached and cached)
      - extent sharing check speedup (2.2x uncached, 3x cached)
      - add more cancellation points, allowing to interrupt seeking in
        files with large number of extents
      - more efficient hole and data seeking (4x uncached, 1.3x cached)
      - sample results:
	    256M, 32K extents:   4s ->  29ms  (~150x)
	    512M, 64K extents:  30s ->  59ms  (~550x)
	    1G,  128K extents: 225s -> 120ms (~1800x)

   - improved inode logging, especially for directories (on dbench
     workload throughput +25%, max latency -21%)

   - improved buffered IO, remove redundant extent state tracking,
     lowering memory consumption and avoiding rb tree traversal

   - add sysfs tunable to let qgroup temporarily skip exact accounting
     when deleting snapshot, leading to a speedup but requiring a rescan
     after that, will be used by snapper

   - support io_uring and buffered writes, until now it was just for
     direct IO, with the no-wait semantics implemented in the buffered
     write path it now works and leads to speed improvement in IOPS
     (2x), throughput (2.2x), latency (depends, 2x to 150x)

   - small performance improvements when dropping and searching for
     extent maps as well as when flushing delalloc in COW mode
     (throughput +5MB/s)

  User visible changes:

   - new incompatible feature block-group-tree adding a dedicated tree
     for tracking block groups, this allows a much faster load during
     mount and avoids seeking unlike when it's scattered in the extent
     tree items
      - this reduces mount time for many-terabyte sized filesystems
      - conversion tool will be provided so existing filesystem can also
        be updated in place
      - to reduce test matrix and feature combinations requires no-holes
        and free-space-tree (mkfs defaults since 5.15)

   - improved reporting of super block corruption detected by scrub

   - scrub also tries to repair super block and does not wait until next
     commit

   - discard stats and tunables are exported in sysfs
     (/sys/fs/btrfs/FSID/discard)

   - qgroup status is exported in sysfs
     (/sys/sys/fs/btrfs/FSID/qgroups/)

   - verify that super block was not modified when thawing filesystem

  Fixes:

   - FIEMAP fixes
      - fix extent sharing status, does not depend on the cached status
        where merged
      - flush delalloc so compressed extents are reported correctly

   - fix alignment of VMA for memory mapped files on THP

   - send: fix failures when processing inodes with no links (orphan
     files and directories)

   - fix race between quota enable and quota rescan ioctl

   - handle more corner cases for read-only compat feature verification

   - fix missed extent on fsync after dropping extent maps

  Core:

   - lockdep annotations to validate various transactions states and
     state transitions

   - preliminary support for fs-verity in send

   - more effective memory use in scrub for subpage where sector is
     smaller than page

   - block group caching progress logic has been removed, load is now
     synchronous

   - simplify end IO callbacks and bio handling, use chained bios
     instead of own tracking

   - add no-wait semantics to several functions (tree search, nocow,
     flushing, buffered write

   - cleanups and refactoring

  MM changes:

   - export balance_dirty_pages_ratelimited_flags"

* tag 'for-6.1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (177 commits)
  btrfs: set generation before calling btrfs_clean_tree_block in btrfs_init_new_buffer
  btrfs: drop extent map range more efficiently
  btrfs: avoid pointless extent map tree search when flushing delalloc
  btrfs: remove unnecessary next extent map search
  btrfs: remove unnecessary NULL pointer checks when searching extent maps
  btrfs: assert tree is locked when clearing extent map from logging
  btrfs: remove unnecessary extent map initializations
  btrfs: remove the refcount warning/check at free_extent_map()
  btrfs: add helper to replace extent map range with a new extent map
  btrfs: move open coded extent map tree deletion out of inode eviction
  btrfs: use cond_resched_rwlock_write() during inode eviction
  btrfs: use extent_map_end() at btrfs_drop_extent_map_range()
  btrfs: move btrfs_drop_extent_cache() to extent_map.c
  btrfs: fix missed extent on fsync after dropping extent maps
  btrfs: remove stale prototype of btrfs_write_inode
  btrfs: enable nowait async buffered writes
  btrfs: assert nowait mode is not used for some btree search functions
  btrfs: make btrfs_buffered_write nowait compatible
  btrfs: plumb NOWAIT through the write path
  btrfs: make lock_and_cleanup_extent_if_need nowait compatible
  ...

1 files changed, 90 insertions, 22 deletions

diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index f89beac3c665..9be4fd2db0f4 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -346,12 +346,14 @@ void __cold btrfs_err_32bit_limit(struct btrfs_fs_info *fs_info)
 __cold
 void __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
 			       const char *function,
-			       unsigned int line, int errno)
+			       unsigned int line, int errno, bool first_hit)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
 
 	WRITE_ONCE(trans->aborted, errno);
 	WRITE_ONCE(trans->transaction->aborted, errno);
+	if (first_hit && errno == -ENOSPC)
+		btrfs_dump_space_info_for_trans_abort(fs_info);
 	/* Wake up anybody who may be waiting on this transaction */
 	wake_up(&fs_info->transaction_wait);
 	wake_up(&fs_info->transaction_blocked_wait);
@@ -626,6 +628,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 	int saved_compress_level;
 	bool saved_compress_force;
 	int no_compress = 0;
+	const bool remounting = test_bit(BTRFS_FS_STATE_REMOUNTING, &info->fs_state);
 
 	if (btrfs_fs_compat_ro(info, FREE_SPACE_TREE))
 		btrfs_set_opt(info->mount_opt, FREE_SPACE_TREE);
@@ -1137,10 +1140,12 @@ out:
 	}
 	if (!ret)
 		ret = btrfs_check_mountopts_zoned(info);
-	if (!ret && btrfs_test_opt(info, SPACE_CACHE))
-		btrfs_info(info, "disk space caching is enabled");
-	if (!ret && btrfs_test_opt(info, FREE_SPACE_TREE))
-		btrfs_info(info, "using free space tree");
+	if (!ret && !remounting) {
+		if (btrfs_test_opt(info, SPACE_CACHE))
+			btrfs_info(info, "disk space caching is enabled");
+		if (btrfs_test_opt(info, FREE_SPACE_TREE))
+			btrfs_info(info, "using free space tree");
+	}
 	return ret;
 }
 
@@ -2009,14 +2014,10 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 	if (ret)
 		goto restore;
 
-	/* V1 cache is not supported for subpage mount. */
-	if (fs_info->sectorsize < PAGE_SIZE && btrfs_test_opt(fs_info, SPACE_CACHE)) {
-		btrfs_warn(fs_info,
-	"v1 space cache is not supported for page size %lu with sectorsize %u",
-			   PAGE_SIZE, fs_info->sectorsize);
-		ret = -EINVAL;
+	ret = btrfs_check_features(fs_info, sb);
+	if (ret < 0)
 		goto restore;
-	}
+
 	btrfs_remount_begin(fs_info, old_opts, *flags);
 	btrfs_resize_thread_pool(fs_info,
 		fs_info->thread_pool_size, old_thread_pool_size);
@@ -2550,11 +2551,71 @@ static int btrfs_freeze(struct super_block *sb)
 	return btrfs_commit_transaction(trans);
 }
 
+static int check_dev_super(struct btrfs_device *dev)
+{
+	struct btrfs_fs_info *fs_info = dev->fs_info;
+	struct btrfs_super_block *sb;
+	int ret = 0;
+
+	/* This should be called with fs still frozen. */
+	ASSERT(test_bit(BTRFS_FS_FROZEN, &fs_info->flags));
+
+	/* Missing dev, no need to check. */
+	if (!dev->bdev)
+		return 0;
+
+	/* Only need to check the primary super block. */
+	sb = btrfs_read_dev_one_super(dev->bdev, 0, true);
+	if (IS_ERR(sb))
+		return PTR_ERR(sb);
+
+	/* Btrfs_validate_super() includes fsid check against super->fsid. */
+	ret = btrfs_validate_super(fs_info, sb, 0);
+	if (ret < 0)
+		goto out;
+
+	if (btrfs_super_generation(sb) != fs_info->last_trans_committed) {
+		btrfs_err(fs_info, "transid mismatch, has %llu expect %llu",
+			btrfs_super_generation(sb),
+			fs_info->last_trans_committed);
+		ret = -EUCLEAN;
+		goto out;
+	}
+out:
+	btrfs_release_disk_super(sb);
+	return ret;
+}
+
 static int btrfs_unfreeze(struct super_block *sb)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
+	struct btrfs_device *device;
+	int ret = 0;
 
+	/*
+	 * Make sure the fs is not changed by accident (like hibernation then
+	 * modified by other OS).
+	 * If we found anything wrong, we mark the fs error immediately.
+	 *
+	 * And since the fs is frozen, no one can modify the fs yet, thus
+	 * we don't need to hold device_list_mutex.
+	 */
+	list_for_each_entry(device, &fs_info->fs_devices->devices, dev_list) {
+		ret = check_dev_super(device);
+		if (ret < 0) {
+			btrfs_handle_fs_error(fs_info, ret,
+				"super block on devid %llu got modified unexpectedly",
+				device->devid);
+			break;
+		}
+	}
 	clear_bit(BTRFS_FS_FROZEN, &fs_info->flags);
+
+	/*
+	 * We still return 0, to allow VFS layer to unfreeze the fs even the
+	 * above checks failed. Since the fs is either fine or read-only, we're
+	 * safe to continue, without causing further damage.
+	 */
 	return 0;
 }
 
@@ -2662,17 +2723,21 @@ static int __init init_btrfs_fs(void)
 	if (err)
 		goto free_compress;
 
-	err = extent_io_init();
+	err = extent_state_init_cachep();
 	if (err)
 		goto free_cachep;
 
-	err = extent_state_cache_init();
+	err = extent_buffer_init_cachep();
+	if (err)
+		goto free_extent_cachep;
+
+	err = btrfs_bioset_init();
 	if (err)
-		goto free_extent_io;
+		goto free_eb_cachep;
 
 	err = extent_map_init();
 	if (err)
-		goto free_extent_state_cache;
+		goto free_bioset;
 
 	err = ordered_data_init();
 	if (err)
@@ -2724,10 +2789,12 @@ free_ordered_data:
 	ordered_data_exit();
 free_extent_map:
 	extent_map_exit();
-free_extent_state_cache:
-	extent_state_cache_exit();
-free_extent_io:
-	extent_io_exit();
+free_bioset:
+	btrfs_bioset_exit();
+free_eb_cachep:
+	extent_buffer_free_cachep();
+free_extent_cachep:
+	extent_state_free_cachep();
 free_cachep:
 	btrfs_destroy_cachep();
 free_compress:
@@ -2746,8 +2813,9 @@ static void __exit exit_btrfs_fs(void)
 	btrfs_prelim_ref_exit();
 	ordered_data_exit();
 	extent_map_exit();
-	extent_state_cache_exit();
-	extent_io_exit();
+	btrfs_bioset_exit();
+	extent_state_free_cachep();
+	extent_buffer_free_cachep();
 	btrfs_interface_exit();
 	unregister_filesystem(&btrfs_fs_type);
 	btrfs_exit_sysfs();