Update bcachefs sources to 54de30ef9de8 bcachefs: Kill unused tracepoints

30 files changed, 411 insertions, 270 deletions

diff --git a/.bcachefs_revision b/.bcachefs_revision
index e4007c01..4a0284df 100644
--- a/.bcachefs_revision
+++ b/.bcachefs_revision
@@ -1 +1 @@
-5e40e376e242076ba1148c100993e99f339c2391
+54de30ef9de88c274997d8f78d21297d356c7bc0
diff --git a/libbcachefs/bcachefs.h b/libbcachefs/bcachefs.h
index d0d3a686..5a1cede2 100644
--- a/libbcachefs/bcachefs.h
+++ b/libbcachefs/bcachefs.h
@@ -862,7 +862,7 @@ struct bch_fs {
 	DARRAY(enum bcachefs_metadata_version)
 				incompat_versions_requested;
 
-#if IS_ENABLED(CONFIG_UNICODE)
+#ifdef CONFIG_UNICODE
 	struct unicode_map	*cf_encoding;
 #endif
 
diff --git a/libbcachefs/btree_gc.c b/libbcachefs/btree_gc.c
index ebd2be54..e92cf392 100644
--- a/libbcachefs/btree_gc.c
+++ b/libbcachefs/btree_gc.c
@@ -442,7 +442,8 @@ again:
 
 	if (!ret && !IS_ERR_OR_NULL(prev)) {
 		BUG_ON(cur);
-		ret = btree_repair_node_end(trans, b, prev, pulled_from_scan);
+		ret = lockrestart_do(trans,
+			btree_repair_node_end(trans, b, prev, pulled_from_scan));
 		if (ret == DID_FILL_FROM_SCAN) {
 			new_pass = true;
 			ret = 0;
diff --git a/libbcachefs/btree_io.c b/libbcachefs/btree_io.c
index 6787d5b9..d8f3c4c6 100644
--- a/libbcachefs/btree_io.c
+++ b/libbcachefs/btree_io.c
@@ -741,16 +741,22 @@ static int validate_bset(struct bch_fs *c, struct bch_dev *ca,
 		     BCH_VERSION_MAJOR(version),
 		     BCH_VERSION_MINOR(version));
 
-	if (btree_err_on(version < c->sb.version_min,
+	if (c->recovery.curr_pass != BCH_RECOVERY_PASS_scan_for_btree_nodes &&
+	    btree_err_on(version < c->sb.version_min,
 			 -BCH_ERR_btree_node_read_err_fixable,
 			 c, NULL, b, i, NULL,
 			 btree_node_bset_older_than_sb_min,
 			 "bset version %u older than superblock version_min %u",
 			 version, c->sb.version_min)) {
-		mutex_lock(&c->sb_lock);
-		c->disk_sb.sb->version_min = cpu_to_le16(version);
-		bch2_write_super(c);
-		mutex_unlock(&c->sb_lock);
+		if (bch2_version_compatible(version)) {
+			mutex_lock(&c->sb_lock);
+			c->disk_sb.sb->version_min = cpu_to_le16(version);
+			bch2_write_super(c);
+			mutex_unlock(&c->sb_lock);
+		} else {
+			/* We have no idea what's going on: */
+			i->version = cpu_to_le16(c->sb.version);
+		}
 	}
 
 	if (btree_err_on(BCH_VERSION_MAJOR(version) >
diff --git a/libbcachefs/btree_iter.c b/libbcachefs/btree_iter.c
index b7840337..06160399 100644
--- a/libbcachefs/btree_iter.c
+++ b/libbcachefs/btree_iter.c
@@ -2076,14 +2076,14 @@ inline bool bch2_btree_iter_rewind(struct btree_trans *trans, struct btree_iter
 
 static noinline
 void bch2_btree_trans_peek_prev_updates(struct btree_trans *trans, struct btree_iter *iter,
-					struct bkey_s_c *k)
+					struct bpos search_key, struct bkey_s_c *k)
 {
 	struct bpos end = path_l(btree_iter_path(trans, iter))->b->data->min_key;
 
 	trans_for_each_update(trans, i)
 		if (!i->key_cache_already_flushed &&
 		    i->btree_id == iter->btree_id &&
-		    bpos_le(i->k->k.p, iter->pos) &&
+		    bpos_le(i->k->k.p, search_key) &&
 		    bpos_ge(i->k->k.p, k->k ? k->k->p : end)) {
 			iter->k = i->k->k;
 			*k = bkey_i_to_s_c(i->k);
@@ -2092,6 +2092,7 @@ void bch2_btree_trans_peek_prev_updates(struct btree_trans *trans, struct btree_
 
 static noinline
 void bch2_btree_trans_peek_updates(struct btree_trans *trans, struct btree_iter *iter,
+				   struct bpos search_key,
 				   struct bkey_s_c *k)
 {
 	struct btree_path *path = btree_iter_path(trans, iter);
@@ -2100,7 +2101,7 @@ void bch2_btree_trans_peek_updates(struct btree_trans *trans, struct btree_iter
 	trans_for_each_update(trans, i)
 		if (!i->key_cache_already_flushed &&
 		    i->btree_id == iter->btree_id &&
-		    bpos_ge(i->k->k.p, path->pos) &&
+		    bpos_ge(i->k->k.p, search_key) &&
 		    bpos_le(i->k->k.p, k->k ? k->k->p : end)) {
 			iter->k = i->k->k;
 			*k = bkey_i_to_s_c(i->k);
@@ -2122,13 +2123,14 @@ void bch2_btree_trans_peek_slot_updates(struct btree_trans *trans, struct btree_
 
 static struct bkey_i *bch2_btree_journal_peek(struct btree_trans *trans,
 					      struct btree_iter *iter,
+					      struct bpos search_pos,
 					      struct bpos end_pos)
 {
 	struct btree_path *path = btree_iter_path(trans, iter);
 
 	return bch2_journal_keys_peek_max(trans->c, iter->btree_id,
 					   path->level,
-					   path->pos,
+					   search_pos,
 					   end_pos,
 					   &iter->journal_idx);
 }
@@ -2138,7 +2140,7 @@ struct bkey_s_c btree_trans_peek_slot_journal(struct btree_trans *trans,
 					      struct btree_iter *iter)
 {
 	struct btree_path *path = btree_iter_path(trans, iter);
-	struct bkey_i *k = bch2_btree_journal_peek(trans, iter, path->pos);
+	struct bkey_i *k = bch2_btree_journal_peek(trans, iter, path->pos, path->pos);
 
 	if (k) {
 		iter->k = k->k;
@@ -2151,11 +2153,12 @@ struct bkey_s_c btree_trans_peek_slot_journal(struct btree_trans *trans,
 static noinline
 void btree_trans_peek_journal(struct btree_trans *trans,
 			      struct btree_iter *iter,
+			      struct bpos search_key,
 			      struct bkey_s_c *k)
 {
 	struct btree_path *path = btree_iter_path(trans, iter);
 	struct bkey_i *next_journal =
-		bch2_btree_journal_peek(trans, iter,
+		bch2_btree_journal_peek(trans, iter, search_key,
 				k->k ? k->k->p : path_l(path)->b->key.k.p);
 	if (next_journal) {
 		iter->k = next_journal->k;
@@ -2165,13 +2168,14 @@ void btree_trans_peek_journal(struct btree_trans *trans,
 
 static struct bkey_i *bch2_btree_journal_peek_prev(struct btree_trans *trans,
 					      struct btree_iter *iter,
+					      struct bpos search_key,
 					      struct bpos end_pos)
 {
 	struct btree_path *path = btree_iter_path(trans, iter);
 
 	return bch2_journal_keys_peek_prev_min(trans->c, iter->btree_id,
 					   path->level,
-					   path->pos,
+					   search_key,
 					   end_pos,
 					   &iter->journal_idx);
 }
@@ -2179,11 +2183,12 @@ static struct bkey_i *bch2_btree_journal_peek_prev(struct btree_trans *trans,
 static noinline
 void btree_trans_peek_prev_journal(struct btree_trans *trans,
 				   struct btree_iter *iter,
+				   struct bpos search_key,
 				   struct bkey_s_c *k)
 {
 	struct btree_path *path = btree_iter_path(trans, iter);
 	struct bkey_i *next_journal =
-		bch2_btree_journal_peek_prev(trans, iter,
+		bch2_btree_journal_peek_prev(trans, iter, search_key,
 				k->k ? k->k->p : path_l(path)->b->key.k.p);
 
 	if (next_journal) {
@@ -2292,11 +2297,11 @@ static struct bkey_s_c __bch2_btree_iter_peek(struct btree_trans *trans, struct
 		}
 
 		if (unlikely(iter->flags & BTREE_ITER_with_journal))
-			btree_trans_peek_journal(trans, iter, &k);
+			btree_trans_peek_journal(trans, iter, search_key, &k);
 
 		if (unlikely((iter->flags & BTREE_ITER_with_updates) &&
 			     trans->nr_updates))
-			bch2_btree_trans_peek_updates(trans, iter, &k);
+			bch2_btree_trans_peek_updates(trans, iter, search_key, &k);
 
 		if (k.k && bkey_deleted(k.k)) {
 			/*
@@ -2326,6 +2331,20 @@ static struct bkey_s_c __bch2_btree_iter_peek(struct btree_trans *trans, struct
 	}
 
 	bch2_btree_iter_verify(trans, iter);
+
+	if (trace___btree_iter_peek_enabled()) {
+		CLASS(printbuf, buf)();
+
+		int ret = bkey_err(k);
+		if (ret)
+			prt_str(&buf, bch2_err_str(ret));
+		else if (k.k)
+			bch2_bkey_val_to_text(&buf, trans->c, k);
+		else
+			prt_str(&buf, "(null)");
+		trace___btree_iter_peek(trans->c, buf.buf);
+	}
+
 	return k;
 }
 
@@ -2484,6 +2503,19 @@ out_no_locked:
 
 	bch2_btree_iter_verify_entry_exit(iter);
 
+	if (trace_btree_iter_peek_max_enabled()) {
+		CLASS(printbuf, buf)();
+
+		int ret = bkey_err(k);
+		if (ret)
+			prt_str(&buf, bch2_err_str(ret));
+		else if (k.k)
+			bch2_bkey_val_to_text(&buf, trans->c, k);
+		else
+			prt_str(&buf, "(null)");
+		trace_btree_iter_peek_max(trans->c, buf.buf);
+	}
+
 	return k;
 end:
 	bch2_btree_iter_set_pos(trans, iter, end);
@@ -2557,11 +2589,11 @@ static struct bkey_s_c __bch2_btree_iter_peek_prev(struct btree_trans *trans, st
 		}
 
 		if (unlikely(iter->flags & BTREE_ITER_with_journal))
-			btree_trans_peek_prev_journal(trans, iter, &k);
+			btree_trans_peek_prev_journal(trans, iter, search_key, &k);
 
 		if (unlikely((iter->flags & BTREE_ITER_with_updates) &&
 			     trans->nr_updates))
-			bch2_btree_trans_peek_prev_updates(trans, iter, &k);
+			bch2_btree_trans_peek_prev_updates(trans, iter, search_key, &k);
 
 		if (likely(k.k && !bkey_deleted(k.k))) {
 			break;
@@ -2724,6 +2756,19 @@ out_no_locked:
 
 	bch2_btree_iter_verify_entry_exit(iter);
 	bch2_btree_iter_verify(trans, iter);
+
+	if (trace_btree_iter_peek_prev_min_enabled()) {
+		CLASS(printbuf, buf)();
+
+		int ret = bkey_err(k);
+		if (ret)
+			prt_str(&buf, bch2_err_str(ret));
+		else if (k.k)
+			bch2_bkey_val_to_text(&buf, trans->c, k);
+		else
+			prt_str(&buf, "(null)");
+		trace_btree_iter_peek_prev_min(trans->c, buf.buf);
+	}
 	return k;
 end:
 	bch2_btree_iter_set_pos(trans, iter, end);
@@ -2767,8 +2812,10 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_trans *trans, struct btre
 	/* extents can't span inode numbers: */
 	if ((iter->flags & BTREE_ITER_is_extents) &&
 	    unlikely(iter->pos.offset == KEY_OFFSET_MAX)) {
-		if (iter->pos.inode == KEY_INODE_MAX)
-			return bkey_s_c_null;
+		if (iter->pos.inode == KEY_INODE_MAX) {
+			k = bkey_s_c_null;
+			goto out2;
+		}
 
 		bch2_btree_iter_set_pos(trans, iter, bpos_nosnap_successor(iter->pos));
 	}
@@ -2785,8 +2832,10 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_trans *trans, struct btre
 	}
 
 	struct btree_path *path = btree_iter_path(trans, iter);
-	if (unlikely(!btree_path_node(path, path->level)))
-		return bkey_s_c_null;
+	if (unlikely(!btree_path_node(path, path->level))) {
+		k = bkey_s_c_null;
+		goto out2;
+	}
 
 	btree_path_set_should_be_locked(trans, path);
 
@@ -2879,7 +2928,20 @@ out:
 	bch2_btree_iter_verify(trans, iter);
 	ret = bch2_btree_iter_verify_ret(trans, iter, k);
 	if (unlikely(ret))
-		return bkey_s_c_err(ret);
+		k = bkey_s_c_err(ret);
+out2:
+	if (trace_btree_iter_peek_slot_enabled()) {
+		CLASS(printbuf, buf)();
+
+		int ret = bkey_err(k);
+		if (ret)
+			prt_str(&buf, bch2_err_str(ret));
+		else if (k.k)
+			bch2_bkey_val_to_text(&buf, trans->c, k);
+		else
+			prt_str(&buf, "(null)");
+		trace_btree_iter_peek_slot(trans->c, buf.buf);
+	}
 
 	return k;
 }
@@ -3159,46 +3221,32 @@ void *__bch2_trans_kmalloc(struct btree_trans *trans, size_t size, unsigned long
 		mutex_unlock(&s->lock);
 	}
 
-	if (trans->used_mempool) {
-		if (trans->mem_bytes >= new_bytes)
-			goto out_change_top;
-
-		/* No more space from mempool item, need malloc new one */
-		new_mem = kmalloc(new_bytes, GFP_NOWAIT|__GFP_NOWARN);
-		if (unlikely(!new_mem)) {
-			bch2_trans_unlock(trans);
-
-			new_mem = kmalloc(new_bytes, GFP_KERNEL);
-			if (!new_mem)
-				return ERR_PTR(-BCH_ERR_ENOMEM_trans_kmalloc);
+	if (trans->used_mempool || new_bytes > BTREE_TRANS_MEM_MAX) {
+		EBUG_ON(trans->mem_bytes >= new_bytes);
+		return ERR_PTR(-BCH_ERR_ENOMEM_trans_kmalloc);
+	}
 
-			ret = bch2_trans_relock(trans);
-			if (ret) {
-				kfree(new_mem);
-				return ERR_PTR(ret);
-			}
-		}
-		memcpy(new_mem, trans->mem, trans->mem_top);
-		trans->used_mempool = false;
-		mempool_free(trans->mem, &c->btree_trans_mem_pool);
-		goto out_new_mem;
+	if (old_bytes) {
+		trans->realloc_bytes_required = new_bytes;
+		trace_and_count(c, trans_restart_mem_realloced, trans, _RET_IP_, new_bytes);
+		return ERR_PTR(btree_trans_restart_ip(trans,
+					BCH_ERR_transaction_restart_mem_realloced, _RET_IP_));
 	}
 
-	new_mem = krealloc(trans->mem, new_bytes, GFP_NOWAIT|__GFP_NOWARN);
+	EBUG_ON(trans->mem);
+
+	new_mem = kmalloc(new_bytes, GFP_NOWAIT|__GFP_NOWARN);
 	if (unlikely(!new_mem)) {
 		bch2_trans_unlock(trans);
 
-		new_mem = krealloc(trans->mem, new_bytes, GFP_KERNEL);
+		new_mem = kmalloc(new_bytes, GFP_KERNEL);
 		if (!new_mem && new_bytes <= BTREE_TRANS_MEM_MAX) {
 			new_mem = mempool_alloc(&c->btree_trans_mem_pool, GFP_KERNEL);
 			new_bytes = BTREE_TRANS_MEM_MAX;
-			memcpy(new_mem, trans->mem, trans->mem_top);
 			trans->used_mempool = true;
-			kfree(trans->mem);
 		}
 
-		if (!new_mem)
-			return ERR_PTR(-BCH_ERR_ENOMEM_trans_kmalloc);
+		EBUG_ON(!new_mem);
 
 		trans->mem = new_mem;
 		trans->mem_bytes = new_bytes;
@@ -3207,18 +3255,10 @@ void *__bch2_trans_kmalloc(struct btree_trans *trans, size_t size, unsigned long
 		if (ret)
 			return ERR_PTR(ret);
 	}
-out_new_mem:
+
 	trans->mem = new_mem;
 	trans->mem_bytes = new_bytes;
 
-	if (old_bytes) {
-		trace_and_count(c, trans_restart_mem_realloced, trans, _RET_IP_, new_bytes);
-		return ERR_PTR(btree_trans_restart_ip(trans,
-					BCH_ERR_transaction_restart_mem_realloced, _RET_IP_));
-	}
-out_change_top:
-	bch2_trans_kmalloc_trace(trans, size, ip);
-
 	p = trans->mem + trans->mem_top;
 	trans->mem_top += size;
 	memset(p, 0, size);
@@ -3279,6 +3319,27 @@ u32 bch2_trans_begin(struct btree_trans *trans)
 	trans->restart_count++;
 	trans->mem_top			= 0;
 
+	if (trans->restarted == BCH_ERR_transaction_restart_mem_realloced) {
+		EBUG_ON(!trans->mem || !trans->mem_bytes);
+		unsigned new_bytes = trans->realloc_bytes_required;
+		void *new_mem = krealloc(trans->mem, new_bytes, GFP_NOWAIT|__GFP_NOWARN);
+		if (unlikely(!new_mem)) {
+			bch2_trans_unlock(trans);
+			new_mem = krealloc(trans->mem, new_bytes, GFP_KERNEL);
+
+			EBUG_ON(new_bytes > BTREE_TRANS_MEM_MAX);
+
+			if (!new_mem) {
+				new_mem = mempool_alloc(&trans->c->btree_trans_mem_pool, GFP_KERNEL);
+				new_bytes = BTREE_TRANS_MEM_MAX;
+				trans->used_mempool = true;
+				kfree(trans->mem);
+			}
+                }
+		trans->mem = new_mem;
+		trans->mem_bytes = new_bytes;
+	}
+
 	trans_for_each_path(trans, path, i) {
 		path->should_be_locked = false;
 
diff --git a/libbcachefs/btree_journal_iter.c b/libbcachefs/btree_journal_iter.c
index cf739875..8f94c3bd 100644
--- a/libbcachefs/btree_journal_iter.c
+++ b/libbcachefs/btree_journal_iter.c
@@ -141,8 +141,8 @@ search:
 	if (!*idx)
 		*idx = __bch2_journal_key_search(keys, btree_id, level, pos);
 
-	while (*idx &&
-	       __journal_key_cmp(btree_id, level, end_pos, idx_to_key(keys, *idx - 1)) <= 0) {
+	while (*idx < keys->nr &&
+	       __journal_key_cmp(btree_id, level, end_pos, idx_to_key(keys, *idx - 1)) >= 0) {
 		(*idx)++;
 		iters++;
 		if (iters == 10) {
@@ -641,10 +641,11 @@ static int journal_sort_key_cmp(const void *_l, const void *_r)
 {
 	const struct journal_key *l = _l;
 	const struct journal_key *r = _r;
+	int rewind = l->rewind && r->rewind ? -1 : 1;
 
 	return  journal_key_cmp(l, r) ?:
-		cmp_int(l->journal_seq, r->journal_seq) ?:
-		cmp_int(l->journal_offset, r->journal_offset);
+		((cmp_int(l->journal_seq, r->journal_seq) ?:
+		  cmp_int(l->journal_offset, r->journal_offset)) * rewind);
 }
 
 void bch2_journal_keys_put(struct bch_fs *c)
@@ -712,37 +713,59 @@ int bch2_journal_keys_sort(struct bch_fs *c)
 	struct journal_replay *i, **_i;
 	struct journal_keys *keys = &c->journal_keys;
 	size_t nr_read = 0;
+	u64 nr_entries = 0, nr_non_ignored = 0;
+
+	u64 rewind_seq = c->opts.journal_rewind ?: U64_MAX;
 
 	genradix_for_each(&c->journal_entries, iter, _i) {
 		i = *_i;
 
+		nr_entries += i != NULL;
+
 		if (journal_replay_ignore(i))
 			continue;
 
+		nr_non_ignored++;
+
 		cond_resched();
 
-		for_each_jset_key(k, entry, &i->j) {
-			struct journal_key n = (struct journal_key) {
-				.btree_id	= entry->btree_id,
-				.level		= entry->level,
-				.k		= k,
-				.journal_seq	= le64_to_cpu(i->j.seq),
-				.journal_offset	= k->_data - i->j._data,
-			};
-
-			if (darray_push(keys, n)) {
-				__journal_keys_sort(keys);
-
-				if (keys->nr * 8 > keys->size * 7) {
-					bch_err(c, "Too many journal keys for slowpath; have %zu compacted, buf size %zu, processed %zu keys at seq %llu",
-						keys->nr, keys->size, nr_read, le64_to_cpu(i->j.seq));
-					return bch_err_throw(c, ENOMEM_journal_keys_sort);
+		vstruct_for_each(&i->j, entry) {
+			bool rewind = !entry->level &&
+				!btree_id_is_alloc(entry->btree_id) &&
+				le64_to_cpu(i->j.seq) >= rewind_seq;
+
+			if (entry->type != (rewind
+					    ? BCH_JSET_ENTRY_overwrite
+					    : BCH_JSET_ENTRY_btree_keys))
+				continue;
+
+			if (!rewind && le64_to_cpu(i->j.seq) < c->journal_replay_seq_start)
+				continue;
+
+			jset_entry_for_each_key(entry, k) {
+				struct journal_key n = (struct journal_key) {
+					.btree_id	= entry->btree_id,
+					.level		= entry->level,
+					.rewind		= rewind,
+					.k		= k,
+					.journal_seq	= le64_to_cpu(i->j.seq),
+					.journal_offset	= k->_data - i->j._data,
+				};
+
+				if (darray_push(keys, n)) {
+					__journal_keys_sort(keys);
+
+					if (keys->nr * 8 > keys->size * 7) {
+						bch_err(c, "Too many journal keys for slowpath; have %zu compacted, buf size %zu, processed %zu keys at seq %llu",
+							keys->nr, keys->size, nr_read, le64_to_cpu(i->j.seq));
+						return bch_err_throw(c, ENOMEM_journal_keys_sort);
+					}
+
+					BUG_ON(darray_push(keys, n));
 				}
 
-				BUG_ON(darray_push(keys, n));
+				nr_read++;
 			}
-
-			nr_read++;
 		}
 	}
 
diff --git a/libbcachefs/btree_journal_iter_types.h b/libbcachefs/btree_journal_iter_types.h
index 8b773823..86aacb25 100644
--- a/libbcachefs/btree_journal_iter_types.h
+++ b/libbcachefs/btree_journal_iter_types.h
@@ -11,8 +11,9 @@ struct journal_key {
 	u32			journal_offset;
 	enum btree_id		btree_id:8;
 	unsigned		level:8;
-	bool			allocated;
-	bool			overwritten;
+	bool			allocated:1;
+	bool			overwritten:1;
+	bool			rewind:1;
 	struct journal_key_range_overwritten __rcu *
 				overwritten_range;
 	struct bkey_i		*k;
diff --git a/libbcachefs/btree_locking.h b/libbcachefs/btree_locking.h
index 9adca77e..f2173a33 100644
--- a/libbcachefs/btree_locking.h
+++ b/libbcachefs/btree_locking.h
@@ -417,8 +417,10 @@ static inline void btree_path_set_should_be_locked(struct btree_trans *trans, st
 	EBUG_ON(!btree_node_locked(path, path->level));
 	EBUG_ON(path->uptodate);
 
-	path->should_be_locked = true;
-	trace_btree_path_should_be_locked(trans, path);
+	if (!path->should_be_locked) {
+		path->should_be_locked = true;
+		trace_btree_path_should_be_locked(trans, path);
+	}
 }
 
 static inline void __btree_path_set_level_up(struct btree_trans *trans,
diff --git a/libbcachefs/btree_trans_commit.c b/libbcachefs/btree_trans_commit.c
index d9710801..639ef75b 100644
--- a/libbcachefs/btree_trans_commit.c
+++ b/libbcachefs/btree_trans_commit.c
@@ -595,12 +595,13 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags,
 	int ret = 0;
 
 	bch2_trans_verify_not_unlocked_or_in_restart(trans);
-
+#if 0
+	/* todo: bring back dynamic fault injection */
 	if (race_fault()) {
 		trace_and_count(c, trans_restart_fault_inject, trans, trace_ip);
 		return btree_trans_restart(trans, BCH_ERR_transaction_restart_fault_inject);
 	}
-
+#endif
 	/*
 	 * Check if the insert will fit in the leaf node with the write lock
 	 * held, otherwise another thread could write the node changing the
@@ -757,6 +758,8 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags,
 				  btree_trans_journal_entries_start(trans),
 				  trans->journal_entries.u64s);
 
+		EBUG_ON(trans->journal_res.u64s < trans->journal_entries.u64s);
+
 		trans->journal_res.offset	+= trans->journal_entries.u64s;
 		trans->journal_res.u64s		-= trans->journal_entries.u64s;
 
@@ -1003,6 +1006,7 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags)
 {
 	struct btree_insert_entry *errored_at = NULL;
 	struct bch_fs *c = trans->c;
+	unsigned journal_u64s = 0;
 	int ret = 0;
 
 	bch2_trans_verify_not_unlocked_or_in_restart(trans);
@@ -1031,10 +1035,10 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags)
 
 	EBUG_ON(test_bit(BCH_FS_clean_shutdown, &c->flags));
 
-	trans->journal_u64s		= trans->journal_entries.u64s + jset_u64s(trans->accounting.u64s);
+	journal_u64s = jset_u64s(trans->accounting.u64s);
 	trans->journal_transaction_names = READ_ONCE(c->opts.journal_transaction_names);
 	if (trans->journal_transaction_names)
-		trans->journal_u64s += jset_u64s(JSET_ENTRY_LOG_U64s);
+		journal_u64s += jset_u64s(JSET_ENTRY_LOG_U64s);
 
 	trans_for_each_update(trans, i) {
 		struct btree_path *path = trans->paths + i->path;
@@ -1054,11 +1058,11 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags)
 			continue;
 
 		/* we're going to journal the key being updated: */
-		trans->journal_u64s += jset_u64s(i->k->k.u64s);
+		journal_u64s += jset_u64s(i->k->k.u64s);
 
 		/* and we're also going to log the overwrite: */
 		if (trans->journal_transaction_names)
-			trans->journal_u64s += jset_u64s(i->old_k.u64s);
+			journal_u64s += jset_u64s(i->old_k.u64s);
 	}
 
 	if (trans->extra_disk_res) {
@@ -1076,6 +1080,8 @@ retry:
 		memset(&trans->journal_res, 0, sizeof(trans->journal_res));
 	memset(&trans->fs_usage_delta, 0, sizeof(trans->fs_usage_delta));
 
+	trans->journal_u64s = journal_u64s + trans->journal_entries.u64s;
+
 	ret = do_bch2_trans_commit(trans, flags, &errored_at, _RET_IP_);
 
 	/* make sure we didn't drop or screw up locks: */
diff --git a/libbcachefs/btree_types.h b/libbcachefs/btree_types.h
index 3aa4a602..112170fd 100644
--- a/libbcachefs/btree_types.h
+++ b/libbcachefs/btree_types.h
@@ -497,6 +497,7 @@ struct btree_trans {
 	void			*mem;
 	unsigned		mem_top;
 	unsigned		mem_bytes;
+	unsigned		realloc_bytes_required;
 #ifdef CONFIG_BCACHEFS_TRANS_KMALLOC_TRACE
 	darray_trans_kmalloc_trace trans_kmalloc_trace;
 #endif
diff --git a/libbcachefs/btree_update_interior.c b/libbcachefs/btree_update_interior.c
index 9e281d18..e7758460 100644
--- a/libbcachefs/btree_update_interior.c
+++ b/libbcachefs/btree_update_interior.c
@@ -290,6 +290,8 @@ static struct btree *__bch2_btree_node_alloc(struct btree_trans *trans,
 	struct bch_fs *c = trans->c;
 	struct write_point *wp;
 	struct btree *b;
+	BKEY_PADDED_ONSTACK(k, BKEY_BTREE_PTR_VAL_U64s_MAX) tmp;
+	struct open_buckets obs = { .nr = 0 };
 	struct bch_devs_list devs_have = (struct bch_devs_list) { 0 };
 	enum bch_watermark watermark = flags & BCH_WATERMARK_MASK;
 	unsigned nr_reserve = watermark < BCH_WATERMARK_reclaim
@@ -308,8 +310,8 @@ static struct btree *__bch2_btree_node_alloc(struct btree_trans *trans,
 		struct btree_alloc *a =
 			&c->btree_reserve_cache[--c->btree_reserve_cache_nr];
 
-		bkey_copy(&b->key, &a->k);
-		b->ob = a->ob;
+		obs = a->ob;
+		bkey_copy(&tmp.k, &a->k);
 		mutex_unlock(&c->btree_reserve_cache_lock);
 		goto out;
 	}
@@ -343,12 +345,14 @@ retry:
 		goto retry;
 	}
 
-	bkey_btree_ptr_v2_init(&b->key);
-	bch2_alloc_sectors_append_ptrs(c, wp, &b->key, btree_sectors(c), false);
+	bkey_btree_ptr_v2_init(&tmp.k);
+	bch2_alloc_sectors_append_ptrs(c, wp, &tmp.k, btree_sectors(c), false);
 
-	bch2_open_bucket_get(c, wp, &b->ob);
+	bch2_open_bucket_get(c, wp, &obs);
 	bch2_alloc_sectors_done(c, wp);
 out:
+	bkey_copy(&b->key, &tmp.k);
+	b->ob = obs;
 	six_unlock_write(&b->c.lock);
 	six_unlock_intent(&b->c.lock);
 
@@ -509,25 +513,30 @@ static int bch2_btree_reserve_get(struct btree_trans *trans,
 				  unsigned flags,
 				  struct closure *cl)
 {
+	struct btree *b;
+	unsigned interior;
+	int ret = 0;
+
 	BUG_ON(nr_nodes[0] + nr_nodes[1] > BTREE_RESERVE_MAX);
 
 	/*
 	 * Protects reaping from the btree node cache and using the btree node
 	 * open bucket reserve:
 	 */
-	int ret = bch2_btree_cache_cannibalize_lock(trans, cl);
+	ret = bch2_btree_cache_cannibalize_lock(trans, cl);
 	if (ret)
 		return ret;
 
-	for (unsigned interior = 0; interior < 2; interior++) {
+	for (interior = 0; interior < 2; interior++) {
 		struct prealloc_nodes *p = as->prealloc_nodes + interior;
 
 		while (p->nr < nr_nodes[interior]) {
-			struct btree *b = __bch2_btree_node_alloc(trans, &as->disk_res,
-							cl, interior, target, flags);
-			ret = PTR_ERR_OR_ZERO(b);
-			if (ret)
+			b = __bch2_btree_node_alloc(trans, &as->disk_res, cl,
+						    interior, target, flags);
+			if (IS_ERR(b)) {
+				ret = PTR_ERR(b);
 				goto err;
+			}
 
 			p->b[p->nr++] = b;
 		}
diff --git a/libbcachefs/btree_write_buffer.c b/libbcachefs/btree_write_buffer.c
index 90b21e61..21b5c03d 100644
--- a/libbcachefs/btree_write_buffer.c
+++ b/libbcachefs/btree_write_buffer.c
@@ -676,6 +676,9 @@ int bch2_btree_write_buffer_maybe_flush(struct btree_trans *trans,
 			goto err;
 
 		bch2_bkey_buf_copy(last_flushed, c, tmp.k);
+
+		/* can we avoid the unconditional restart? */
+		trace_and_count(c, trans_restart_write_buffer_flush, trans, _RET_IP_);
 		ret = bch_err_throw(c, transaction_restart_write_buffer_flush);
 	}
 err:
diff --git a/libbcachefs/dirent.c b/libbcachefs/dirent.c
index 5c3df997..300f7cc8 100644
--- a/libbcachefs/dirent.c
+++ b/libbcachefs/dirent.c
@@ -18,7 +18,7 @@ int bch2_casefold(struct btree_trans *trans, const struct bch_hash_info *info,
 {
 	*out_cf = (struct qstr) QSTR_INIT(NULL, 0);
 
-#if IS_ENABLED(CONFIG_UNICODE)
+#ifdef CONFIG_UNICODE
 	unsigned char *buf = bch2_trans_kmalloc(trans, BCH_NAME_MAX + 1);
 	int ret = PTR_ERR_OR_ZERO(buf);
 	if (ret)
diff --git a/libbcachefs/errcode.h b/libbcachefs/errcode.h
index ac326413..86a842f1 100644
--- a/libbcachefs/errcode.h
+++ b/libbcachefs/errcode.h
@@ -137,7 +137,6 @@
 	x(BCH_ERR_transaction_restart,	transaction_restart_relock)		\
 	x(BCH_ERR_transaction_restart,	transaction_restart_relock_path)	\
 	x(BCH_ERR_transaction_restart,	transaction_restart_relock_path_intent)	\
-	x(BCH_ERR_transaction_restart,	transaction_restart_relock_after_fill)	\
 	x(BCH_ERR_transaction_restart,	transaction_restart_too_many_iters)	\
 	x(BCH_ERR_transaction_restart,	transaction_restart_lock_node_reused)	\
 	x(BCH_ERR_transaction_restart,	transaction_restart_fill_relock)	\
@@ -148,11 +147,8 @@
 	x(BCH_ERR_transaction_restart,	transaction_restart_would_deadlock_write)\
 	x(BCH_ERR_transaction_restart,	transaction_restart_deadlock_recursion_limit)\
 	x(BCH_ERR_transaction_restart,	transaction_restart_upgrade)		\
-	x(BCH_ERR_transaction_restart,	transaction_restart_key_cache_upgrade)	\
 	x(BCH_ERR_transaction_restart,	transaction_restart_key_cache_fill)	\
 	x(BCH_ERR_transaction_restart,	transaction_restart_key_cache_raced)	\
-	x(BCH_ERR_transaction_restart,	transaction_restart_key_cache_realloced)\
-	x(BCH_ERR_transaction_restart,	transaction_restart_journal_preres_get)	\
 	x(BCH_ERR_transaction_restart,	transaction_restart_split_race)		\
 	x(BCH_ERR_transaction_restart,	transaction_restart_write_buffer_flush)	\
 	x(BCH_ERR_transaction_restart,	transaction_restart_nested)		\
@@ -241,7 +237,6 @@
 	x(BCH_ERR_journal_res_blocked,	journal_buf_enomem)			\
 	x(BCH_ERR_journal_res_blocked,	journal_stuck)				\
 	x(BCH_ERR_journal_res_blocked,	journal_retry_open)			\
-	x(BCH_ERR_journal_res_blocked,	journal_preres_get_blocked)		\
 	x(BCH_ERR_journal_res_blocked,	bucket_alloc_blocked)			\
 	x(BCH_ERR_journal_res_blocked,	stripe_alloc_blocked)			\
 	x(BCH_ERR_invalid,		invalid_sb)				\
diff --git a/libbcachefs/extent_update.c b/libbcachefs/extent_update.c
index b899ee75..e76e58a5 100644
--- a/libbcachefs/extent_update.c
+++ b/libbcachefs/extent_update.c
@@ -139,6 +139,17 @@ int bch2_extent_trim_atomic(struct btree_trans *trans,
 	if (ret)
 		return ret;
 
-	bch2_cut_back(end, k);
+	/* tracepoint */
+
+	if (bpos_lt(end, k->k.p)) {
+		if (trace_extent_trim_atomic_enabled()) {
+			CLASS(printbuf, buf)();
+			bch2_bpos_to_text(&buf, end);
+			prt_newline(&buf);
+			bch2_bkey_val_to_text(&buf, trans->c, bkey_i_to_s_c(k));
+			trace_extent_trim_atomic(trans->c, buf.buf);
+		}
+		bch2_cut_back(end, k);
+	}
 	return 0;
 }
diff --git a/libbcachefs/fs.c b/libbcachefs/fs.c
index 40b633cd..3063a8dd 100644
--- a/libbcachefs/fs.c
+++ b/libbcachefs/fs.c
@@ -722,7 +722,7 @@ static struct dentry *bch2_lookup(struct inode *vdir, struct dentry *dentry,
 	if (IS_ERR(inode))
 		inode = NULL;
 
-#if IS_ENABLED(CONFIG_UNICODE)
+#ifdef CONFIG_UNICODE
 	if (!inode && IS_CASEFOLDED(vdir)) {
 		/*
 		 * Do not cache a negative dentry in casefolded directories
@@ -2564,7 +2564,7 @@ got_sb:
 
 	sb->s_shrink->seeks = 0;
 
-#if IS_ENABLED(CONFIG_UNICODE)
+#ifdef CONFIG_UNICODE
 	sb->s_encoding = c->cf_encoding;
 #endif
 	generic_set_sb_d_ops(sb);
diff --git a/libbcachefs/fsck.c b/libbcachefs/fsck.c
index 7736103f..48810a8e 100644
--- a/libbcachefs/fsck.c
+++ b/libbcachefs/fsck.c
@@ -806,7 +806,7 @@ static int add_inode(struct bch_fs *c, struct inode_walker *w,
 	if (!n->whiteout) {
 		return bch2_inode_unpack(inode, &n->inode);
 	} else {
-		n->inode.bi_inum	= inode.k->p.inode;
+		n->inode.bi_inum	= inode.k->p.offset;
 		n->inode.bi_snapshot	= inode.k->p.snapshot;
 		return 0;
 	}
@@ -903,17 +903,15 @@ lookup_inode_for_snapshot(struct btree_trans *trans, struct inode_walker *w, str
 			 w->last_pos.inode, k.k->p.snapshot, i->inode.bi_snapshot,
 			 (bch2_bkey_val_to_text(&buf, c, k),
 			  buf.buf))) {
-		struct bch_inode_unpacked new = i->inode;
-		struct bkey_i whiteout;
-
-		new.bi_snapshot = k.k->p.snapshot;
-
 		if (!i->whiteout) {
+			struct bch_inode_unpacked new = i->inode;
+			new.bi_snapshot = k.k->p.snapshot;
 			ret = __bch2_fsck_write_inode(trans, &new);
 		} else {
+			struct bkey_i whiteout;
 			bkey_init(&whiteout.k);
 			whiteout.k.type = KEY_TYPE_whiteout;
-			whiteout.k.p = SPOS(0, i->inode.bi_inum, i->inode.bi_snapshot);
+			whiteout.k.p = SPOS(0, i->inode.bi_inum, k.k->p.snapshot);
 			ret = bch2_btree_insert_nonextent(trans, BTREE_ID_inodes,
 							  &whiteout,
 							  BTREE_UPDATE_internal_snapshot_node);
@@ -1822,18 +1820,39 @@ static int check_extent(struct btree_trans *trans, struct btree_iter *iter,
 			    !key_visible_in_snapshot(c, s, i->inode.bi_snapshot, k.k->p.snapshot))
 				continue;
 
-			if (fsck_err_on(k.k->p.offset > round_up(i->inode.bi_size, block_bytes(c)) >> 9 &&
+			u64 last_block = round_up(i->inode.bi_size, block_bytes(c)) >> 9;
+
+			if (fsck_err_on(k.k->p.offset > last_block &&
 					!bkey_extent_is_reservation(k),
 					trans, extent_past_end_of_inode,
 					"extent type past end of inode %llu:%u, i_size %llu\n%s",
 					i->inode.bi_inum, i->inode.bi_snapshot, i->inode.bi_size,
 					(bch2_bkey_val_to_text(&buf, c, k), buf.buf))) {
-				struct btree_iter iter2;
+				struct bkey_i *whiteout = bch2_trans_kmalloc(trans, sizeof(*whiteout));
+				ret = PTR_ERR_OR_ZERO(whiteout);
+				if (ret)
+					goto err;
+
+				bkey_init(&whiteout->k);
+				whiteout->k.p = SPOS(k.k->p.inode,
+						     last_block,
+						     i->inode.bi_snapshot);
+				bch2_key_resize(&whiteout->k,
+						min(KEY_SIZE_MAX & (~0 << c->block_bits),
+						    U64_MAX - whiteout->k.p.offset));
+
 
-				bch2_trans_copy_iter(trans, &iter2, iter);
-				bch2_btree_iter_set_snapshot(trans, &iter2, i->inode.bi_snapshot);
+				/*
+				 * Need a normal (not BTREE_ITER_all_snapshots)
+				 * iterator, if we're deleting in a different
+				 * snapshot and need to emit a whiteout
+				 */
+				struct btree_iter iter2;
+				bch2_trans_iter_init(trans, &iter2, BTREE_ID_extents,
+						     bkey_start_pos(&whiteout->k),
+						     BTREE_ITER_intent);
 				ret =   bch2_btree_iter_traverse(trans, &iter2) ?:
-					bch2_btree_delete_at(trans, &iter2,
+					bch2_trans_update(trans, &iter2, whiteout,
 						BTREE_UPDATE_internal_snapshot_node);
 				bch2_trans_iter_exit(trans, &iter2);
 				if (ret)
@@ -2184,7 +2203,7 @@ static int check_dirent(struct btree_trans *trans, struct btree_iter *iter,
 		*hash_info = bch2_hash_info_init(c, &i->inode);
 	dir->first_this_inode = false;
 
-#if IS_ENABLED(CONFIG_UNICODE)
+#ifdef CONFIG_UNICODE
 	hash_info->cf_encoding = bch2_inode_casefold(c, &i->inode) ? c->cf_encoding : NULL;
 #endif
 
@@ -2474,6 +2493,14 @@ int bch2_check_root(struct bch_fs *c)
 	return ret;
 }
 
+static bool darray_u32_has(darray_u32 *d, u32 v)
+{
+	darray_for_each(*d, i)
+		if (*i == v)
+			return true;
+	return false;
+}
+
 static int check_subvol_path(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k)
 {
 	struct bch_fs *c = trans->c;
@@ -2501,7 +2528,7 @@ static int check_subvol_path(struct btree_trans *trans, struct btree_iter *iter,
 
 		u32 parent = le32_to_cpu(s.v->fs_path_parent);
 
-		if (darray_find(subvol_path, parent)) {
+		if (darray_u32_has(&subvol_path, parent)) {
 			printbuf_reset(&buf);
 			prt_printf(&buf, "subvolume loop:\n");
 
diff --git a/libbcachefs/inode.c b/libbcachefs/inode.c
index ceed2eb7..53e5dc1f 100644
--- a/libbcachefs/inode.c
+++ b/libbcachefs/inode.c
@@ -1265,7 +1265,7 @@ int bch2_inode_set_casefold(struct btree_trans *trans, subvol_inum inum,
 {
 	struct bch_fs *c = trans->c;
 
-#if IS_ENABLED(CONFIG_UNICODE)
+#ifdef CONFIG_UNICODE
 	int ret = 0;
 	/* Not supported on individual files. */
 	if (!S_ISDIR(bi->bi_mode))
diff --git a/libbcachefs/journal.c b/libbcachefs/journal.c
index dda802a6..df71af00 100644
--- a/libbcachefs/journal.c
+++ b/libbcachefs/journal.c
@@ -1474,14 +1474,13 @@ void bch2_fs_journal_stop(struct journal *j)
 		clear_bit(JOURNAL_running, &j->flags);
 }
 
-int bch2_fs_journal_start(struct journal *j, u64 cur_seq)
+int bch2_fs_journal_start(struct journal *j, u64 last_seq, u64 cur_seq)
 {
 	struct bch_fs *c = container_of(j, struct bch_fs, journal);
 	struct journal_entry_pin_list *p;
 	struct journal_replay *i, **_i;
 	struct genradix_iter iter;
 	bool had_entries = false;
-	u64 last_seq = cur_seq, nr, seq;
 
 	/*
 	 *
@@ -1495,17 +1494,11 @@ int bch2_fs_journal_start(struct journal *j, u64 cur_seq)
 		return -EINVAL;
 	}
 
-	genradix_for_each_reverse(&c->journal_entries, iter, _i) {
-		i = *_i;
-
-		if (journal_replay_ignore(i))
-			continue;
+	/* Clean filesystem? */
+	if (!last_seq)
+		last_seq = cur_seq;
 
-		last_seq = le64_to_cpu(i->j.last_seq);
-		break;
-	}
-
-	nr = cur_seq - last_seq;
+	u64 nr = cur_seq - last_seq;
 
 	/*
 	 * Extra fudge factor, in case we crashed when the journal pin fifo was
@@ -1532,6 +1525,7 @@ int bch2_fs_journal_start(struct journal *j, u64 cur_seq)
 	j->pin.back		= cur_seq;
 	atomic64_set(&j->seq, cur_seq - 1);
 
+	u64 seq;
 	fifo_for_each_entry_ptr(p, &j->pin, seq)
 		journal_pin_list_init(p, 1);
 
diff --git a/libbcachefs/journal.h b/libbcachefs/journal.h
index 83734fe4..97790703 100644
--- a/libbcachefs/journal.h
+++ b/libbcachefs/journal.h
@@ -453,7 +453,7 @@ int bch2_fs_journal_alloc(struct bch_fs *);
 void bch2_dev_journal_stop(struct journal *, struct bch_dev *);
 
 void bch2_fs_journal_stop(struct journal *);
-int bch2_fs_journal_start(struct journal *, u64);
+int bch2_fs_journal_start(struct journal *, u64, u64);
 void bch2_journal_set_replay_done(struct journal *);
 
 void bch2_dev_journal_exit(struct bch_dev *);
diff --git a/libbcachefs/journal_io.c b/libbcachefs/journal_io.c
index 0b15d71a..afbf12e8 100644
--- a/libbcachefs/journal_io.c
+++ b/libbcachefs/journal_io.c
@@ -160,6 +160,9 @@ static int journal_entry_add(struct bch_fs *c, struct bch_dev *ca,
 	struct printbuf buf = PRINTBUF;
 	int ret = JOURNAL_ENTRY_ADD_OK;
 
+	if (last_seq && c->opts.journal_rewind)
+		last_seq = min(last_seq, c->opts.journal_rewind);
+
 	if (!c->journal.oldest_seq_found_ondisk ||
 	    le64_to_cpu(j->seq) < c->journal.oldest_seq_found_ondisk)
 		c->journal.oldest_seq_found_ondisk = le64_to_cpu(j->seq);
@@ -1430,11 +1433,21 @@ int bch2_journal_read(struct bch_fs *c,
 	printbuf_reset(&buf);
 	prt_printf(&buf, "journal read done, replaying entries %llu-%llu",
 		   *last_seq, *blacklist_seq - 1);
+
+	/*
+	 * Drop blacklisted entries and entries older than last_seq (or start of
+	 * journal rewind:
+	 */
+	u64 drop_before = *last_seq;
+	if (c->opts.journal_rewind) {
+		drop_before = min(drop_before, c->opts.journal_rewind);
+		prt_printf(&buf, " (rewinding from %llu)", c->opts.journal_rewind);
+	}
+
+	*last_seq = drop_before;
 	if (*start_seq != *blacklist_seq)
 		prt_printf(&buf, " (unflushed %llu-%llu)", *blacklist_seq, *start_seq - 1);
 	bch_info(c, "%s", buf.buf);
-
-	/* Drop blacklisted entries and entries older than last_seq: */
 	genradix_for_each(&c->journal_entries, radix_iter, _i) {
 		i = *_i;
 
@@ -1442,7 +1455,7 @@ int bch2_journal_read(struct bch_fs *c,
 			continue;
 
 		seq = le64_to_cpu(i->j.seq);
-		if (seq < *last_seq) {
+		if (seq < drop_before) {
 			journal_replay_free(c, i, false);
 			continue;
 		}
@@ -1455,7 +1468,7 @@ int bch2_journal_read(struct bch_fs *c,
 		}
 	}
 
-	ret = bch2_journal_check_for_missing(c, *last_seq, *blacklist_seq - 1);
+	ret = bch2_journal_check_for_missing(c, drop_before, *blacklist_seq - 1);
 	if (ret)
 		goto err;
 
diff --git a/libbcachefs/namei.c b/libbcachefs/namei.c
index 24120037..779c22eb 100644
--- a/libbcachefs/namei.c
+++ b/libbcachefs/namei.c
@@ -175,6 +175,16 @@ int bch2_create_trans(struct btree_trans *trans,
 		new_inode->bi_dir_offset	= dir_offset;
 	}
 
+	if (S_ISDIR(mode)) {
+		ret = bch2_maybe_propagate_has_case_insensitive(trans,
+				(subvol_inum) {
+					new_inode->bi_subvol ?: dir.subvol,
+					new_inode->bi_inum },
+				new_inode);
+		if (ret)
+			goto err;
+	}
+
 	if (S_ISDIR(mode) &&
 	    !new_inode->bi_subvol)
 		new_inode->bi_depth = dir_u->bi_depth + 1;
diff --git a/libbcachefs/opts.h b/libbcachefs/opts.h
index 2a026062..b0a76bd6 100644
--- a/libbcachefs/opts.h
+++ b/libbcachefs/opts.h
@@ -379,6 +379,11 @@ enum fsck_err_opts {
 	  OPT_BOOL(),							\
 	  BCH2_NO_SB_OPT,		false,				\
 	  NULL,		"Exit recovery immediately prior to journal replay")\
+	x(journal_rewind,		u64,				\
+	  OPT_FS|OPT_MOUNT,						\
+	  OPT_UINT(0, U64_MAX),						\
+	  BCH2_NO_SB_OPT,		0,				\
+	  NULL,		"Rewind journal")				\
 	x(recovery_passes,		u64,				\
 	  OPT_FS|OPT_MOUNT,						\
 	  OPT_BITFIELD(bch2_recovery_passes),				\
diff --git a/libbcachefs/recovery.c b/libbcachefs/recovery.c
index 0b21fa6f..37f2cc1e 100644
--- a/libbcachefs/recovery.c
+++ b/libbcachefs/recovery.c
@@ -692,7 +692,7 @@ static bool check_version_upgrade(struct bch_fs *c)
 		ret = true;
 	}
 
-	if (new_version > c->sb.version_incompat &&
+	if (new_version > c->sb.version_incompat_allowed &&
 	    c->opts.version_upgrade == BCH_VERSION_UPGRADE_incompatible) {
 		struct printbuf buf = PRINTBUF;
 
@@ -757,6 +757,11 @@ int bch2_fs_recovery(struct bch_fs *c)
 	if (c->opts.nochanges)
 		c->opts.read_only = true;
 
+	if (c->opts.journal_rewind) {
+		bch_info(c, "rewinding journal, fsck required");
+		c->opts.fsck = true;
+	}
+
 	mutex_lock(&c->sb_lock);
 	struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext);
 	bool write_sb = false;
@@ -965,7 +970,7 @@ use_clean:
 
 	ret =   bch2_journal_log_msg(c, "starting journal at entry %llu, replaying %llu-%llu",
 				     journal_seq, last_seq, blacklist_seq - 1) ?:
-		bch2_fs_journal_start(&c->journal, journal_seq);
+		bch2_fs_journal_start(&c->journal, last_seq, journal_seq);
 	if (ret)
 		goto err;
 
@@ -1181,7 +1186,7 @@ int bch2_fs_initialize(struct bch_fs *c)
 	 * journal_res_get() will crash if called before this has
 	 * set up the journal.pin FIFO and journal.cur pointer:
 	 */
-	ret = bch2_fs_journal_start(&c->journal, 1);
+	ret = bch2_fs_journal_start(&c->journal, 1, 1);
 	if (ret)
 		goto err;
 
diff --git a/libbcachefs/sb-errors_format.h b/libbcachefs/sb-errors_format.h
index d06e7388..82ecee3d 100644
--- a/libbcachefs/sb-errors_format.h
+++ b/libbcachefs/sb-errors_format.h
@@ -217,7 +217,7 @@ enum bch_fsck_flags {
 	x(inode_str_hash_invalid,				194,	0)		\
 	x(inode_v3_fields_start_bad,				195,	0)		\
 	x(inode_snapshot_mismatch,				196,	0)		\
-	x(snapshot_key_missing_inode_snapshot,			314,	0)		\
+	x(snapshot_key_missing_inode_snapshot,			314,	FSCK_AUTOFIX)	\
 	x(inode_unlinked_but_clean,				197,	0)		\
 	x(inode_unlinked_but_nlink_nonzero,			198,	0)		\
 	x(inode_unlinked_and_not_open,				281,	0)		\
@@ -253,7 +253,7 @@ enum bch_fsck_flags {
 	x(extent_overlapping,					215,	0)		\
 	x(key_in_missing_inode,					216,	0)		\
 	x(key_in_wrong_inode_type,				217,	0)		\
-	x(extent_past_end_of_inode,				218,	0)		\
+	x(extent_past_end_of_inode,				218,	FSCK_AUTOFIX)	\
 	x(dirent_empty_name,					219,	0)		\
 	x(dirent_val_too_big,					220,	0)		\
 	x(dirent_name_too_long,					221,	0)		\
diff --git a/libbcachefs/sb-members.c b/libbcachefs/sb-members.c
index 363eb0c6..6245e342 100644
--- a/libbcachefs/sb-members.c
+++ b/libbcachefs/sb-members.c
@@ -325,9 +325,17 @@ static void bch2_sb_members_v1_to_text(struct printbuf *out, struct bch_sb *sb,
 {
 	struct bch_sb_field_members_v1 *mi = field_to_type(f, members_v1);
 	struct bch_sb_field_disk_groups *gi = bch2_sb_field_get(sb, disk_groups);
-	unsigned i;
 
-	for (i = 0; i < sb->nr_devices; i++)
+	if (vstruct_end(&mi->field) <= (void *) &mi->_members[0]) {
+		prt_printf(out, "field ends before start of entries");
+		return;
+	}
+
+	unsigned nr = (vstruct_end(&mi->field) - (void *) &mi->_members[0]) / sizeof(mi->_members[0]);
+	if (nr != sb->nr_devices)
+		prt_printf(out, "nr_devices mismatch: have %i entries, should be %u", nr, sb->nr_devices);
+
+	for (unsigned i = 0; i < min(sb->nr_devices, nr); i++)
 		member_to_text(out, members_v1_get(mi, i), gi, sb, i);
 }
 
@@ -341,9 +349,27 @@ static void bch2_sb_members_v2_to_text(struct printbuf *out, struct bch_sb *sb,
 {
 	struct bch_sb_field_members_v2 *mi = field_to_type(f, members_v2);
 	struct bch_sb_field_disk_groups *gi = bch2_sb_field_get(sb, disk_groups);
-	unsigned i;
 
-	for (i = 0; i < sb->nr_devices; i++)
+	if (vstruct_end(&mi->field) <= (void *) &mi->_members[0]) {
+		prt_printf(out, "field ends before start of entries");
+		return;
+	}
+
+	if (!le16_to_cpu(mi->member_bytes)) {
+		prt_printf(out, "member_bytes 0");
+		return;
+	}
+
+	unsigned nr = (vstruct_end(&mi->field) - (void *) &mi->_members[0]) / le16_to_cpu(mi->member_bytes);
+	if (nr != sb->nr_devices)
+		prt_printf(out, "nr_devices mismatch: have %i entries, should be %u", nr, sb->nr_devices);
+
+	/*
+	 * We call to_text() on superblock sections that haven't passed
+	 * validate, so we can't trust sb->nr_devices.
+	 */
+
+	for (unsigned i = 0; i < min(sb->nr_devices, nr); i++)
 		member_to_text(out, members_v2_get(mi, i), gi, sb, i);
 }
 
diff --git a/libbcachefs/snapshot.c b/libbcachefs/snapshot.c
index 23a332d7..38aeaa12 100644
--- a/libbcachefs/snapshot.c
+++ b/libbcachefs/snapshot.c
@@ -135,7 +135,9 @@ static bool test_ancestor_bitmap(struct snapshot_table *t, u32 id, u32 ancestor)
 
 bool __bch2_snapshot_is_ancestor(struct bch_fs *c, u32 id, u32 ancestor)
 {
-	bool ret;
+#ifdef CONFIG_BCACHEFS_DEBUG
+	u32 orig_id = id;
+#endif
 
 	guard(rcu)();
 	struct snapshot_table *t = rcu_dereference(c->snapshots);
@@ -147,11 +149,11 @@ bool __bch2_snapshot_is_ancestor(struct bch_fs *c, u32 id, u32 ancestor)
 		while (id && id < ancestor - IS_ANCESTOR_BITMAP)
 			id = get_ancestor_below(t, id, ancestor);
 
-	ret = id && id < ancestor
+	bool ret = id && id < ancestor
 		? test_ancestor_bitmap(t, id, ancestor)
 		: id == ancestor;
 
-	EBUG_ON(ret != __bch2_snapshot_is_ancestor_early(t, id, ancestor));
+	EBUG_ON(ret != __bch2_snapshot_is_ancestor_early(t, orig_id, ancestor));
 	return ret;
 }
 
diff --git a/libbcachefs/str_hash.h b/libbcachefs/str_hash.h
index a49376df..79d51aef 100644
--- a/libbcachefs/str_hash.h
+++ b/libbcachefs/str_hash.h
@@ -48,7 +48,7 @@ bch2_hash_info_init(struct bch_fs *c, const struct bch_inode_unpacked *bi)
 	struct bch_hash_info info = {
 		.inum_snapshot	= bi->bi_snapshot,
 		.type		= INODE_STR_HASH(bi),
-#if IS_ENABLED(CONFIG_UNICODE)
+#ifdef CONFIG_UNICODE
 		.cf_encoding	= bch2_inode_casefold(c, bi) ? c->cf_encoding : NULL,
 #endif
 		.siphash_key	= { .k0 = bi->bi_hash_seed }
diff --git a/libbcachefs/super.c b/libbcachefs/super.c
index 61ef897c..a5b97c9c 100644
--- a/libbcachefs/super.c
+++ b/libbcachefs/super.c
@@ -586,7 +586,7 @@ static void __bch2_fs_free(struct bch_fs *c)
 	for (unsigned i = 0; i < BCH_TIME_STAT_NR; i++)
 		bch2_time_stats_exit(&c->times[i]);
 
-#if IS_ENABLED(CONFIG_UNICODE)
+#ifdef CONFIG_UNICODE
 	utf8_unload(c->cf_encoding);
 #endif
 
@@ -1015,7 +1015,7 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts *opts,
 	if (ret)
 		goto err;
 
-#if IS_ENABLED(CONFIG_UNICODE)
+#ifdef CONFIG_UNICODE
 	/* Default encoding until we can potentially have more as an option. */
 	c->cf_encoding = utf8_load(BCH_FS_DEFAULT_UTF8_ENCODING);
 	if (IS_ERR(c->cf_encoding)) {
@@ -1067,12 +1067,13 @@ noinline_for_stack
 static void print_mount_opts(struct bch_fs *c)
 {
 	enum bch_opt_id i;
-	struct printbuf p = PRINTBUF;
-	bool first = true;
+	CLASS(printbuf, p)();
+	bch2_log_msg_start(c, &p);
 
 	prt_str(&p, "starting version ");
 	bch2_version_to_text(&p, c->sb.version);
 
+	bool first = true;
 	for (i = 0; i < bch2_opts_nr; i++) {
 		const struct bch_option *opt = &bch2_opt_table[i];
 		u64 v = bch2_opt_get_by_id(&c->opts, i);
@@ -1089,17 +1090,24 @@ static void print_mount_opts(struct bch_fs *c)
 	}
 
 	if (c->sb.version_incompat_allowed != c->sb.version) {
-		prt_printf(&p, "\n  allowing incompatible features above ");
+		prt_printf(&p, "\nallowing incompatible features above ");
 		bch2_version_to_text(&p, c->sb.version_incompat_allowed);
 	}
 
 	if (c->opts.verbose) {
-		prt_printf(&p, "\n  features: ");
+		prt_printf(&p, "\nfeatures: ");
 		prt_bitflags(&p, bch2_sb_features, c->sb.features);
 	}
 
-	bch_info(c, "%s", p.buf);
-	printbuf_exit(&p);
+	if (c->sb.multi_device) {
+		prt_printf(&p, "\nwith devices");
+		for_each_online_member(c, ca, BCH_DEV_READ_REF_bch2_online_devs) {
+			prt_char(&p, ' ');
+			prt_str(&p, ca->name);
+		}
+	}
+
+	bch2_print_str(c, KERN_INFO, p.buf);
 }
 
 static bool bch2_fs_may_start(struct bch_fs *c)
@@ -1143,11 +1151,12 @@ int bch2_fs_start(struct bch_fs *c)
 
 	print_mount_opts(c);
 
-	if (IS_ENABLED(CONFIG_UNICODE))
-		bch_info(c, "Using encoding defined by superblock: utf8-%u.%u.%u",
-			 unicode_major(BCH_FS_DEFAULT_UTF8_ENCODING),
-			 unicode_minor(BCH_FS_DEFAULT_UTF8_ENCODING),
-			 unicode_rev(BCH_FS_DEFAULT_UTF8_ENCODING));
+#ifdef CONFIG_UNICODE
+	bch_info(c, "Using encoding defined by superblock: utf8-%u.%u.%u",
+		 unicode_major(BCH_FS_DEFAULT_UTF8_ENCODING),
+		 unicode_minor(BCH_FS_DEFAULT_UTF8_ENCODING),
+		 unicode_rev(BCH_FS_DEFAULT_UTF8_ENCODING));
+#endif
 
 	if (!bch2_fs_may_start(c))
 		return bch_err_throw(c, insufficient_devices_to_start);
diff --git a/libbcachefs/trace.h b/libbcachefs/trace.h
index dc095327..9c5a9c55 100644
--- a/libbcachefs/trace.h
+++ b/libbcachefs/trace.h
@@ -1080,34 +1080,14 @@ TRACE_EVENT(trans_blocked_journal_reclaim,
 		  __entry->must_wait)
 );
 
-TRACE_EVENT(trans_restart_journal_preres_get,
-	TP_PROTO(struct btree_trans *trans,
-		 unsigned long caller_ip,
-		 unsigned flags),
-	TP_ARGS(trans, caller_ip, flags),
-
-	TP_STRUCT__entry(
-		__array(char,			trans_fn, 32	)
-		__field(unsigned long,		caller_ip	)
-		__field(unsigned,		flags		)
-	),
-
-	TP_fast_assign(
-		strscpy(__entry->trans_fn, trans->fn, sizeof(__entry->trans_fn));
-		__entry->caller_ip		= caller_ip;
-		__entry->flags			= flags;
-	),
-
-	TP_printk("%s %pS %x", __entry->trans_fn,
-		  (void *) __entry->caller_ip,
-		  __entry->flags)
-);
-
+#if 0
+/* todo: bring back dynamic fault injection */
 DEFINE_EVENT(transaction_event,	trans_restart_fault_inject,
 	TP_PROTO(struct btree_trans *trans,
 		 unsigned long caller_ip),
 	TP_ARGS(trans, caller_ip)
 );
+#endif
 
 DEFINE_EVENT(transaction_event,	trans_traverse_all,
 	TP_PROTO(struct btree_trans *trans,
@@ -1195,19 +1175,6 @@ DEFINE_EVENT(transaction_restart_iter,	trans_restart_relock_parent_for_fill,
 	TP_ARGS(trans, caller_ip, path)
 );
 
-DEFINE_EVENT(transaction_restart_iter,	trans_restart_relock_after_fill,
-	TP_PROTO(struct btree_trans *trans,
-		 unsigned long caller_ip,
-		 struct btree_path *path),
-	TP_ARGS(trans, caller_ip, path)
-);
-
-DEFINE_EVENT(transaction_event,	trans_restart_key_cache_upgrade,
-	TP_PROTO(struct btree_trans *trans,
-		 unsigned long caller_ip),
-	TP_ARGS(trans, caller_ip)
-);
-
 DEFINE_EVENT(transaction_restart_iter,	trans_restart_relock_key_cache_fill,
 	TP_PROTO(struct btree_trans *trans,
 		 unsigned long caller_ip,
@@ -1229,13 +1196,6 @@ DEFINE_EVENT(transaction_restart_iter,	trans_restart_relock_path_intent,
 	TP_ARGS(trans, caller_ip, path)
 );
 
-DEFINE_EVENT(transaction_restart_iter,	trans_restart_traverse,
-	TP_PROTO(struct btree_trans *trans,
-		 unsigned long caller_ip,
-		 struct btree_path *path),
-	TP_ARGS(trans, caller_ip, path)
-);
-
 DEFINE_EVENT(transaction_restart_iter,	trans_restart_memory_allocation_failure,
 	TP_PROTO(struct btree_trans *trans,
 		 unsigned long caller_ip,
@@ -1294,44 +1254,6 @@ TRACE_EVENT(trans_restart_mem_realloced,
 		  __entry->bytes)
 );
 
-TRACE_EVENT(trans_restart_key_cache_key_realloced,
-	TP_PROTO(struct btree_trans *trans,
-		 unsigned long caller_ip,
-		 struct btree_path *path,
-		 unsigned old_u64s,
-		 unsigned new_u64s),
-	TP_ARGS(trans, caller_ip, path, old_u64s, new_u64s),
-
-	TP_STRUCT__entry(
-		__array(char,			trans_fn, 32	)
-		__field(unsigned long,		caller_ip	)
-		__field(enum btree_id,		btree_id	)
-		TRACE_BPOS_entries(pos)
-		__field(u32,			old_u64s	)
-		__field(u32,			new_u64s	)
-	),
-
-	TP_fast_assign(
-		strscpy(__entry->trans_fn, trans->fn, sizeof(__entry->trans_fn));
-		__entry->caller_ip		= caller_ip;
-
-		__entry->btree_id	= path->btree_id;
-		TRACE_BPOS_assign(pos, path->pos);
-		__entry->old_u64s	= old_u64s;
-		__entry->new_u64s	= new_u64s;
-	),
-
-	TP_printk("%s %pS btree %s pos %llu:%llu:%u old_u64s %u new_u64s %u",
-		  __entry->trans_fn,
-		  (void *) __entry->caller_ip,
-		  bch2_btree_id_str(__entry->btree_id),
-		  __entry->pos_inode,
-		  __entry->pos_offset,
-		  __entry->pos_snapshot,
-		  __entry->old_u64s,
-		  __entry->new_u64s)
-);
-
 DEFINE_EVENT(transaction_event,	trans_restart_write_buffer_flush,
 	TP_PROTO(struct btree_trans *trans,
 		 unsigned long caller_ip),
@@ -1490,6 +1412,31 @@ DEFINE_EVENT(fs_str, io_move_evacuate_bucket,
 	TP_ARGS(c, str)
 );
 
+DEFINE_EVENT(fs_str, extent_trim_atomic,
+	TP_PROTO(struct bch_fs *c, const char *str),
+	TP_ARGS(c, str)
+);
+
+DEFINE_EVENT(fs_str, btree_iter_peek_slot,
+	TP_PROTO(struct bch_fs *c, const char *str),
+	TP_ARGS(c, str)
+);
+
+DEFINE_EVENT(fs_str, __btree_iter_peek,
+	TP_PROTO(struct bch_fs *c, const char *str),
+	TP_ARGS(c, str)
+);
+
+DEFINE_EVENT(fs_str, btree_iter_peek_max,
+	TP_PROTO(struct bch_fs *c, const char *str),
+	TP_ARGS(c, str)
+);
+
+DEFINE_EVENT(fs_str, btree_iter_peek_prev_min,
+	TP_PROTO(struct bch_fs *c, const char *str),
+	TP_ARGS(c, str)
+);
+
 #ifdef CONFIG_BCACHEFS_PATH_TRACEPOINTS
 
 TRACE_EVENT(update_by_path,
@@ -1902,21 +1849,6 @@ TRACE_EVENT(btree_path_free,
 		  __entry->dup_locked)
 );
 
-TRACE_EVENT(btree_path_free_trans_begin,
-	TP_PROTO(btree_path_idx_t path),
-	TP_ARGS(path),
-
-	TP_STRUCT__entry(
-		__field(btree_path_idx_t,	idx		)
-	),
-
-	TP_fast_assign(
-		__entry->idx			= path;
-	),
-
-	TP_printk("   path %3u", __entry->idx)
-);
-
 #else /* CONFIG_BCACHEFS_PATH_TRACEPOINTS */
 #ifndef _TRACE_BCACHEFS_H
 
@@ -1934,7 +1866,6 @@ static inline void trace_btree_path_traverse_start(struct btree_trans *trans, st
 static inline void trace_btree_path_traverse_end(struct btree_trans *trans, struct btree_path *path) {}
 static inline void trace_btree_path_set_pos(struct btree_trans *trans, struct btree_path *path, struct bpos *new_pos) {}
 static inline void trace_btree_path_free(struct btree_trans *trans, btree_path_idx_t path, struct btree_path *dup) {}
-static inline void trace_btree_path_free_trans_begin(btree_path_idx_t path) {}
 
 #endif
 #endif /* CONFIG_BCACHEFS_PATH_TRACEPOINTS */