Merge tag 'for-5.17-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "This end of the year branch is intentionally not that exciting. Most
  of the changes are under the hood, but there are some minor user
  visible improvements and several performance improvements too.

  Features:

   - make send work with concurrent block group relocation.

     We're not allowed to prevent send failing or silently producing
     some bad stream but with more fine grained locking and checks it's
     possible. The send vs deduplication exclusion could reuse the same
     logic in the future.

   - new exclusive operation 'balance paused' to allow adding a device
     to filesystem with paused balance

   - new sysfs file for fsid stored in the per-device directory to help
     distinguish devices when seeding is enabled, the fsid may differ
     from the one reported by the filesystem

  Performance improvements:

   - less metadata needed for directory logging, directory deletion is
     20-40% faster

   - in zoned mode, cache zone information during mount to speed up
     repeated queries (about 50% speedup)

   - free space tree entries get indexed and searched by size (latency
     -30%, search run time -30%)

   - less contention in tree node locking when inserting a key and no
     splits are needed (files/sec in fsmark improves by 1-20%)

  Fixes:

   - fix ENOSPC failure when attempting direct IO write into NOCOW range

   - fix deadlock between quota enable and other quota operations

   - global reserve minimum calculations fixed to account for free space
     tree

   - in zoned mode, fix condition for chunk allocation that may not find
     the right zone for reuse and could lead to early ENOSPC

  Core:

   - global reserve stealing got simplified and cleaned up in evict

   - remove async transaction commit based on manual transaction refs,
     reuse existing kthread and mechanisms to let it commit transaction
     before timeout

   - preparatory work for extent tree v2, add wrappers for global tree
     roots, truncation path cleanups

   - remove readahead framework, it's a bit overengineered and used only
     for scrub, and yet it does not cover all its needs, there is
     another readahead built in the b-tree search that is now used,
     performance drop on HDD is about 5% which is acceptable and scrub
     is often throttled anyway, on SSDs there's no reported drop but
     slight improvement

   - self tests report extent tree state when error occurs

   - replace assert with debugging information when an uncommitted
     transaction is found at unmount time

  Other:

   - error handling improvements

   - other cleanups and refactoring"

* tag 'for-5.17-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (115 commits)
  btrfs: output more debug messages for uncommitted transaction
  btrfs: respect the max size in the header when activating swap file
  btrfs: fix argument list that the kdoc format and script verified
  btrfs: remove unnecessary parameter type from compression_decompress_bio
  btrfs: selftests: dump extent io tree if extent-io-tree test failed
  btrfs: scrub: cleanup the argument list of scrub_stripe()
  btrfs: scrub: cleanup the argument list of scrub_chunk()
  btrfs: remove reada infrastructure
  btrfs: scrub: use btrfs_path::reada for extent tree readahead
  btrfs: scrub: remove the unnecessary path parameter for scrub_raid56_parity()
  btrfs: refactor unlock_up
  btrfs: skip transaction commit after failure to create subvolume
  btrfs: zoned: fix chunk allocation condition for zoned allocator
  btrfs: add extent allocator hook to decide to allocate chunk or not
  btrfs: zoned: unset dedicated block group on allocation failure
  btrfs: zoned: drop redundant check for REQ_OP_ZONE_APPEND and btrfs_is_zoned
  btrfs: zoned: sink zone check into btrfs_repair_one_zone
  btrfs: zoned: simplify btrfs_check_meta_write_pointer
  btrfs: zoned: encapsulate inode locking for zoned relocation
  btrfs: sysfs: add devinfo/fsid to retrieve actual fsid from the device
  ...

1 files changed, 80 insertions, 41 deletions

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index fd0ced829edb..b07d382d53a8 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -34,6 +34,10 @@
 #include "discard.h"
 #include "zoned.h"
 
+#define BTRFS_BLOCK_GROUP_STRIPE_MASK	(BTRFS_BLOCK_GROUP_RAID0 | \
+					 BTRFS_BLOCK_GROUP_RAID10 | \
+					 BTRFS_BLOCK_GROUP_RAID56_MASK)
+
 const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
 	[BTRFS_RAID_RAID10] = {
 		.sub_stripes	= 2,
@@ -1162,7 +1166,6 @@ static void btrfs_close_one_device(struct btrfs_device *device)
 	ASSERT(!test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state));
 	ASSERT(list_empty(&device->dev_alloc_list));
 	ASSERT(list_empty(&device->post_commit_list));
-	ASSERT(atomic_read(&device->reada_in_flight) == 0);
 }
 
 static void close_fs_devices(struct btrfs_fs_devices *fs_devices)
@@ -2146,8 +2149,6 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,
 	}
 
 	ret = btrfs_shrink_device(device, 0);
-	if (!ret)
-		btrfs_reada_remove_dev(device);
 	if (ret)
 		goto error_undo;
 
@@ -2245,7 +2246,6 @@ out:
 	return ret;
 
 error_undo:
-	btrfs_reada_undo_remove_dev(device);
 	if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
 		mutex_lock(&fs_info->chunk_mutex);
 		list_add(&device->dev_alloc_list,
@@ -2431,21 +2431,15 @@ struct btrfs_device *btrfs_find_device_by_devspec(
 	return device;
 }
 
-/*
- * does all the dirty work required for changing file system's UUID.
- */
-static int btrfs_prepare_sprout(struct btrfs_fs_info *fs_info)
+static struct btrfs_fs_devices *btrfs_init_sprout(struct btrfs_fs_info *fs_info)
 {
 	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
 	struct btrfs_fs_devices *old_devices;
 	struct btrfs_fs_devices *seed_devices;
-	struct btrfs_super_block *disk_super = fs_info->super_copy;
-	struct btrfs_device *device;
-	u64 super_flags;
 
 	lockdep_assert_held(&uuid_mutex);
 	if (!fs_devices->seeding)
-		return -EINVAL;
+		return ERR_PTR(-EINVAL);
 
 	/*
 	 * Private copy of the seed devices, anchored at
@@ -2453,7 +2447,7 @@ static int btrfs_prepare_sprout(struct btrfs_fs_info *fs_info)
 	 */
 	seed_devices = alloc_fs_devices(NULL, NULL);
 	if (IS_ERR(seed_devices))
-		return PTR_ERR(seed_devices);
+		return seed_devices;
 
 	/*
 	 * It's necessary to retain a copy of the original seed fs_devices in
@@ -2464,7 +2458,7 @@ static int btrfs_prepare_sprout(struct btrfs_fs_info *fs_info)
 	old_devices = clone_fs_devices(fs_devices);
 	if (IS_ERR(old_devices)) {
 		kfree(seed_devices);
-		return PTR_ERR(old_devices);
+		return old_devices;
 	}
 
 	list_add(&old_devices->fs_list, &fs_uuids);
@@ -2475,7 +2469,41 @@ static int btrfs_prepare_sprout(struct btrfs_fs_info *fs_info)
 	INIT_LIST_HEAD(&seed_devices->alloc_list);
 	mutex_init(&seed_devices->device_list_mutex);
 
-	mutex_lock(&fs_devices->device_list_mutex);
+	return seed_devices;
+}
+
+/*
+ * Splice seed devices into the sprout fs_devices.
+ * Generate a new fsid for the sprouted read-write filesystem.
+ */
+static void btrfs_setup_sprout(struct btrfs_fs_info *fs_info,
+			       struct btrfs_fs_devices *seed_devices)
+{
+	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
+	struct btrfs_super_block *disk_super = fs_info->super_copy;
+	struct btrfs_device *device;
+	u64 super_flags;
+
+	/*
+	 * We are updating the fsid, the thread leading to device_list_add()
+	 * could race, so uuid_mutex is needed.
+	 */
+	lockdep_assert_held(&uuid_mutex);
+
+	/*
+	 * The threads listed below may traverse dev_list but can do that without
+	 * device_list_mutex:
+	 * - All device ops and balance - as we are in btrfs_exclop_start.
+	 * - Various dev_list readers - are using RCU.
+	 * - btrfs_ioctl_fitrim() - is using RCU.
+	 *
+	 * For-read threads as below are using device_list_mutex:
+	 * - Readonly scrub btrfs_scrub_dev()
+	 * - Readonly scrub btrfs_scrub_progress()
+	 * - btrfs_get_dev_stats()
+	 */
+	lockdep_assert_held(&fs_devices->device_list_mutex);
+
 	list_splice_init_rcu(&fs_devices->devices, &seed_devices->devices,
 			      synchronize_rcu);
 	list_for_each_entry(device, &seed_devices->devices, dev_list)
@@ -2491,13 +2519,10 @@ static int btrfs_prepare_sprout(struct btrfs_fs_info *fs_info)
 	generate_random_uuid(fs_devices->fsid);
 	memcpy(fs_devices->metadata_uuid, fs_devices->fsid, BTRFS_FSID_SIZE);
 	memcpy(disk_super->fsid, fs_devices->fsid, BTRFS_FSID_SIZE);
-	mutex_unlock(&fs_devices->device_list_mutex);
 
 	super_flags = btrfs_super_flags(disk_super) &
 		      ~BTRFS_SUPER_FLAG_SEEDING;
 	btrfs_set_super_flags(disk_super, super_flags);
-
-	return 0;
 }
 
 /*
@@ -2588,10 +2613,11 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	struct super_block *sb = fs_info->sb;
 	struct rcu_string *name;
 	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
+	struct btrfs_fs_devices *seed_devices;
 	u64 orig_super_total_bytes;
 	u64 orig_super_num_devices;
-	int seeding_dev = 0;
 	int ret = 0;
+	bool seeding_dev = false;
 	bool locked = false;
 
 	if (sb_rdonly(sb) && !fs_devices->seeding)
@@ -2608,7 +2634,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	}
 
 	if (fs_devices->seeding) {
-		seeding_dev = 1;
+		seeding_dev = true;
 		down_write(&sb->s_umount);
 		mutex_lock(&uuid_mutex);
 		locked = true;
@@ -2643,7 +2669,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	device->fs_info = fs_info;
 	device->bdev = bdev;
 
-	ret = btrfs_get_dev_zone_info(device);
+	ret = btrfs_get_dev_zone_info(device, false);
 	if (ret)
 		goto error_free_device;
 
@@ -2671,18 +2697,25 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 
 	if (seeding_dev) {
 		btrfs_clear_sb_rdonly(sb);
-		ret = btrfs_prepare_sprout(fs_info);
-		if (ret) {
+
+		/* GFP_KERNEL allocation must not be under device_list_mutex */
+		seed_devices = btrfs_init_sprout(fs_info);
+		if (IS_ERR(seed_devices)) {
+			ret = PTR_ERR(seed_devices);
 			btrfs_abort_transaction(trans, ret);
 			goto error_trans;
 		}
+	}
+
+	mutex_lock(&fs_devices->device_list_mutex);
+	if (seeding_dev) {
+		btrfs_setup_sprout(fs_info, seed_devices);
 		btrfs_assign_next_active_device(fs_info->fs_devices->latest_dev,
 						device);
 	}
 
 	device->fs_devices = fs_devices;
 
-	mutex_lock(&fs_devices->device_list_mutex);
 	mutex_lock(&fs_info->chunk_mutex);
 	list_add_rcu(&device->dev_list, &fs_devices->devices);
 	list_add(&device->dev_alloc_list, &fs_devices->alloc_list);
@@ -2744,7 +2777,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 
 		/*
 		 * fs_devices now represents the newly sprouted filesystem and
-		 * its fsid has been changed by btrfs_prepare_sprout
+		 * its fsid has been changed by btrfs_sprout_splice().
 		 */
 		btrfs_sysfs_update_sprout_fsid(fs_devices);
 	}
@@ -4357,8 +4390,10 @@ int btrfs_balance(struct btrfs_fs_info *fs_info,
 	ret = __btrfs_balance(fs_info);
 
 	mutex_lock(&fs_info->balance_mutex);
-	if (ret == -ECANCELED && atomic_read(&fs_info->balance_pause_req))
+	if (ret == -ECANCELED && atomic_read(&fs_info->balance_pause_req)) {
 		btrfs_info(fs_info, "balance: paused");
+		btrfs_exclop_balance(fs_info, BTRFS_EXCLOP_BALANCE_PAUSED);
+	}
 	/*
 	 * Balance can be canceled by:
 	 *
@@ -4434,6 +4469,10 @@ int btrfs_resume_balance_async(struct btrfs_fs_info *fs_info)
 		return 0;
 	}
 
+	spin_lock(&fs_info->super_lock);
+	ASSERT(fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE_PAUSED);
+	fs_info->exclusive_operation = BTRFS_EXCLOP_BALANCE;
+	spin_unlock(&fs_info->super_lock);
 	/*
 	 * A ro->rw remount sequence should continue with the paused balance
 	 * regardless of who pauses it, system or the user as of now, so set
@@ -4502,7 +4541,7 @@ int btrfs_recover_balance(struct btrfs_fs_info *fs_info)
 	 * is in a paused state and must have fs_info::balance_ctl properly
 	 * set up.
 	 */
-	if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_BALANCE))
+	if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_BALANCE_PAUSED))
 		btrfs_warn(fs_info,
 	"balance: cannot set exclusive op status, resume manually");
 
@@ -4643,7 +4682,7 @@ int btrfs_uuid_scan_kthread(void *data)
 
 		eb = path->nodes[0];
 		slot = path->slots[0];
-		item_size = btrfs_item_size_nr(eb, slot);
+		item_size = btrfs_item_size(eb, slot);
 		if (item_size < sizeof(root_item))
 			goto skip;
 
@@ -5504,7 +5543,6 @@ int btrfs_chunk_alloc_add_chunk_item(struct btrfs_trans_handle *trans,
 				     struct btrfs_block_group *bg)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
-	struct btrfs_root *extent_root = fs_info->extent_root;
 	struct btrfs_root *chunk_root = fs_info->chunk_root;
 	struct btrfs_key key;
 	struct btrfs_chunk *chunk;
@@ -5576,7 +5614,7 @@ int btrfs_chunk_alloc_add_chunk_item(struct btrfs_trans_handle *trans,
 	}
 
 	btrfs_set_stack_chunk_length(chunk, bg->length);
-	btrfs_set_stack_chunk_owner(chunk, extent_root->root_key.objectid);
+	btrfs_set_stack_chunk_owner(chunk, BTRFS_EXTENT_TREE_OBJECTID);
 	btrfs_set_stack_chunk_stripe_len(chunk, map->stripe_len);
 	btrfs_set_stack_chunk_type(chunk, map->type);
 	btrfs_set_stack_chunk_num_stripes(chunk, map->num_stripes);
@@ -6314,7 +6352,8 @@ int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, struct extent_map *em,
 	stripe_offset = offset - stripe_offset;
 	data_stripes = nr_data_stripes(map);
 
-	if (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
+	/* Only stripe based profiles needs to check against stripe length. */
+	if (map->type & BTRFS_BLOCK_GROUP_STRIPE_MASK) {
 		u64 max_len = stripe_len - stripe_offset;
 
 		/*
@@ -6937,11 +6976,8 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
 	INIT_LIST_HEAD(&dev->dev_alloc_list);
 	INIT_LIST_HEAD(&dev->post_commit_list);
 
-	atomic_set(&dev->reada_in_flight, 0);
 	atomic_set(&dev->dev_stats_ccnt, 0);
 	btrfs_device_data_ordered_init(dev);
-	INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
-	INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
 	extent_io_tree_init(fs_info, &dev->alloc_state,
 			    IO_TREE_DEVICE_ALLOC_STATE, NULL);
 
@@ -7730,7 +7766,7 @@ static int btrfs_device_init_dev_stats(struct btrfs_device *device,
 	}
 	slot = path->slots[0];
 	eb = path->nodes[0];
-	item_size = btrfs_item_size_nr(eb, slot);
+	item_size = btrfs_item_size(eb, slot);
 
 	ptr = btrfs_item_ptr(eb, slot, struct btrfs_dev_stats_item);
 
@@ -7808,7 +7844,7 @@ static int update_dev_stat_item(struct btrfs_trans_handle *trans,
 	}
 
 	if (ret == 0 &&
-	    btrfs_item_size_nr(path->nodes[0], path->slots[0]) < sizeof(*ptr)) {
+	    btrfs_item_size(path->nodes[0], path->slots[0]) < sizeof(*ptr)) {
 		/* need to delete old one and insert a new one */
 		ret = btrfs_del_item(trans, dev_root, path);
 		if (ret != 0) {
@@ -8298,23 +8334,26 @@ out:
 	return ret;
 }
 
-int btrfs_repair_one_zone(struct btrfs_fs_info *fs_info, u64 logical)
+bool btrfs_repair_one_zone(struct btrfs_fs_info *fs_info, u64 logical)
 {
 	struct btrfs_block_group *cache;
 
+	if (!btrfs_is_zoned(fs_info))
+		return false;
+
 	/* Do not attempt to repair in degraded state */
 	if (btrfs_test_opt(fs_info, DEGRADED))
-		return 0;
+		return true;
 
 	cache = btrfs_lookup_block_group(fs_info, logical);
 	if (!cache)
-		return 0;
+		return true;
 
 	spin_lock(&cache->lock);
 	if (cache->relocating_repair) {
 		spin_unlock(&cache->lock);
 		btrfs_put_block_group(cache);
-		return 0;
+		return true;
 	}
 	cache->relocating_repair = 1;
 	spin_unlock(&cache->lock);
@@ -8322,5 +8361,5 @@ int btrfs_repair_one_zone(struct btrfs_fs_info *fs_info, u64 logical)
 	kthread_run(relocating_repair_kthread, cache,
 		    "btrfs-relocating-repair");
 
-	return 0;
+	return true;
 }