Merge tag 'bcachefs-2025-06-26' of git://evilpiepirate.org/bcachefs

6f2a71a9 · Linus Torvalds <[email protected]> · 2025-06-26 19:49:12 -07:00

Pull bcachefs fixes from Kent Overstreet:

 - Lots of small check/repair fixes, primarily in subvol loop and
   directory structure loop (when involving snapshots).

 - Fix a few 6.16 regressions: rare UAF in the foreground allocator path
   when taking a transaction restart from the transaction bump
   allocator, and some small fallout from the change to log the error
   being corrected in the journal when repairing errors, also some
   fallout from the btree node read error logging improvements.

   (Alan, Bharadwaj)

 - New option: journal_rewind

   This lets the entire filesystem be reset to an earlier point in time.

   Note that this is only a disaster recovery tool, and right now there
   are major caveats to using it (discards should be disabled, in
   particular), but it successfully restored the filesystem of one of
   the users who was bit by the subvolume deletion bug and didn't have
   backups. I'll likely be making some changes to the discard path in
   the future to make this a reliable recovery tool.

 - Some new btree iterator tracepoints, for tracking down some
   livelock-ish behaviour we've been seeing in the main data write path.

* tag 'bcachefs-2025-06-26' of git://evilpiepirate.org/bcachefs: (51 commits)
  bcachefs: Plumb correct ip to trans_relock_fail tracepoint
  bcachefs: Ensure we rewind to run recovery passes
  bcachefs: Ensure btree node scan runs before checking for scanned nodes
  bcachefs: btree_root_unreadable_and_scan_found_nothing should not be autofix
  bcachefs: fix bch2_journal_keys_peek_prev_min() underflow
  bcachefs: Use wait_on_allocator() when allocating journal
  bcachefs: Check for bad write buffer key when moving from journal
  bcachefs: Don't unlock the trans if ret doesn't match BCH_ERR_operation_blocked
  bcachefs: Fix range in bch2_lookup_indirect_extent() error path
  bcachefs: fix spurious error_throw
  bcachefs: Add missing bch2_err_class() to fileattr_set()
  bcachefs: Add missing key type checks to check_snapshot_exists()
  bcachefs: Don't log fsck err in the journal if doing repair elsewhere
  bcachefs: Fix *__bch2_trans_subbuf_alloc() error path
  bcachefs: Fix missing newlines before ero
  bcachefs: fix spurious error in read_btree_roots()
  bcachefs: fsck: Fix oops in key_visible_in_snapshot()
  bcachefs: fsck: fix unhandled restart in topology repair
  bcachefs: fsck: Fix check_directory_structure when no check_dirents
  bcachefs: Fix restart handling in btree_node_scrub_work()
  ...

Commit: 6f2a71a99ebd5dfaa7948a2e9c59eae94b741bd8
Parents: 8a20830f · ef6fac0f

Merge commit. Changes below are compared with the first parent: 8a20830f.

Changes

42 files changed · +734 −451

File	Status	Add	Del	Content
fs/bcachefs/alloc_background.c	modified	+9	−4	View file
fs/bcachefs/backpointers.c	modified	+1	−1	View file
fs/bcachefs/bcachefs.h	modified	+2	−1	View file
fs/bcachefs/btree_gc.c	modified	+25	−12	View file
fs/bcachefs/btree_io.c	modified	+31	−43	View file
fs/bcachefs/btree_iter.c	modified	+119	−54	View file
fs/bcachefs/btree_journal_iter.c	modified	+55	−27	View file
fs/bcachefs/btree_journal_iter_types.h	modified	+3	−2	View file
fs/bcachefs/btree_locking.c	modified	+6	−6	View file
fs/bcachefs/btree_node_scan.c	modified	+5	−1	View file
fs/bcachefs/btree_node_scan.h	modified	+1	−1	View file
fs/bcachefs/btree_trans_commit.c	modified	+12	−6	View file
fs/bcachefs/btree_types.h	modified	+1	−0	View file
fs/bcachefs/btree_update.c	modified	+11	−5	View file
fs/bcachefs/btree_update.h	modified	+2	−3	View file
fs/bcachefs/btree_update_interior.c	modified	+8	−8	View file
fs/bcachefs/btree_update_interior.h	modified	+3	−0	View file
fs/bcachefs/btree_write_buffer.c	modified	+5	−3	View file
fs/bcachefs/btree_write_buffer.h	modified	+6	−0	View file
fs/bcachefs/chardev.c	modified	+22	−7	View file
fs/bcachefs/data_update.c	modified	+1	−0	View file
fs/bcachefs/errcode.h	modified	+0	−5	View file
fs/bcachefs/error.c	modified	+3	−1	View file
fs/bcachefs/extent_update.c	modified	+12	−1	View file
fs/bcachefs/fs.c	modified	+2	−1	View file
fs/bcachefs/fsck.c	modified	+218	−99	View file
fs/bcachefs/inode.h	modified	+5	−0	View file
fs/bcachefs/io_read.c	modified	+6	−1	View file
fs/bcachefs/journal.c	modified	+7	−13	View file
fs/bcachefs/journal.h	modified	+1	−1	View file
fs/bcachefs/journal_io.c	modified	+20	−6	View file
fs/bcachefs/namei.c	modified	+23	−7	View file
fs/bcachefs/opts.h	modified	+5	−0	View file
fs/bcachefs/recovery.c	modified	+20	−4	View file
fs/bcachefs/recovery_passes.c	modified	+9	−10	View file
fs/bcachefs/recovery_passes.h	modified	+9	−0	View file
fs/bcachefs/reflink.c	modified	+7	−5	View file
fs/bcachefs/sb-errors_format.h	modified	+10	−9	View file
fs/bcachefs/snapshot.c	modified	+9	−5	View file
fs/bcachefs/super.c	modified	+11	−2	View file
fs/bcachefs/super.h	modified	+1	−0	View file
fs/bcachefs/trace.h	modified	+28	−97	View file

Only the first 600 diff lines are shown. Download the complete patch.

fs/bcachefs/alloc_background.c

View file

diff --git a/fs/bcachefs/alloc_background.c b/fs/bcachefs/alloc_background.c
index b228a5a..66de463 100644
--- a/fs/bcachefs/alloc_background.c
+++ b/fs/bcachefs/alloc_background.c
@@ -1406,6 +1406,9 @@ int bch2_check_discard_freespace_key(struct btree_trans *trans, struct btree_ite
 		: BCH_DATA_free;
 	struct printbuf buf = PRINTBUF;
 
+	unsigned fsck_flags = (async_repair ? FSCK_ERR_NO_LOG : 0)|
+		FSCK_CAN_FIX|FSCK_CAN_IGNORE;
+
 	struct bpos bucket = iter->pos;
 	bucket.offset &= ~(~0ULL << 56);
 	u64 genbits = iter->pos.offset & (~0ULL << 56);
@@ -1419,9 +1422,10 @@ int bch2_check_discard_freespace_key(struct btree_trans *trans, struct btree_ite
 		return ret;
 
 	if (!bch2_dev_bucket_exists(c, bucket)) {
-		if (fsck_err(trans, need_discard_freespace_key_to_invalid_dev_bucket,
-			     "entry in %s btree for nonexistant dev:bucket %llu:%llu",
-			     bch2_btree_id_str(iter->btree_id), bucket.inode, bucket.offset))
+		if (__fsck_err(trans, fsck_flags,
+			       need_discard_freespace_key_to_invalid_dev_bucket,
+			       "entry in %s btree for nonexistant dev:bucket %llu:%llu",
+			       bch2_btree_id_str(iter->btree_id), bucket.inode, bucket.offset))
 			goto delete;
 		ret = 1;
 		goto out;
@@ -1433,7 +1437,8 @@ int bch2_check_discard_freespace_key(struct btree_trans *trans, struct btree_ite
 	if (a->data_type != state ||
 	    (state == BCH_DATA_free &&
 	     genbits != alloc_freespace_genbits(*a))) {
-		if (fsck_err(trans, need_discard_freespace_key_bad,
+		if (__fsck_err(trans, fsck_flags,
+			       need_discard_freespace_key_bad,
 			     "%s\nincorrectly set at %s:%llu:%llu:0 (free %u, genbits %llu should be %llu)",
 			     (bch2_bkey_val_to_text(&buf, c, alloc_k), buf.buf),
 			     bch2_btree_id_str(iter->btree_id),

fs/bcachefs/backpointers.c

View file

diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c
index e76809e..77d93be 100644
--- a/fs/bcachefs/backpointers.c
+++ b/fs/bcachefs/backpointers.c
@@ -353,7 +353,7 @@ static struct bkey_s_c __bch2_backpointer_get_key(struct btree_trans *trans,
 		return ret ? bkey_s_c_err(ret) : bkey_s_c_null;
 	} else {
 		struct btree *b = __bch2_backpointer_get_node(trans, bp, iter, last_flushed, commit);
-		if (b == ERR_PTR(bch_err_throw(c, backpointer_to_overwritten_btree_node)))
+		if (b == ERR_PTR(-BCH_ERR_backpointer_to_overwritten_btree_node))
 			return bkey_s_c_null;
 		if (IS_ERR_OR_NULL(b))
 			return ((struct bkey_s_c) { .k = ERR_CAST(b) });

fs/bcachefs/bcachefs.h

View file

diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h
index 5a1cede..8043943 100644
--- a/fs/bcachefs/bcachefs.h
+++ b/fs/bcachefs/bcachefs.h
@@ -767,7 +767,8 @@ struct btree_trans_buf {
 	x(sysfs)							\
 	x(btree_write_buffer)						\
 	x(btree_node_scrub)						\
-	x(async_recovery_passes)
+	x(async_recovery_passes)					\
+	x(ioctl_data)
 
 enum bch_write_ref {
 #define x(n) BCH_WRITE_REF_##n,

fs/bcachefs/btree_gc.c

View file

diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c
index e92cf39..bac108e 100644
--- a/fs/bcachefs/btree_gc.c
+++ b/fs/bcachefs/btree_gc.c
@@ -503,8 +503,14 @@ again:
 	prt_newline(&buf);
 	bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key));
 
+	/*
+	 * XXX: we're not passing the trans object here because we're not set up
+	 * to handle a transaction restart - this code needs to be rewritten
+	 * when we start doing online topology repair
+	 */
+	bch2_trans_unlock_long(trans);
 	if (mustfix_fsck_err_on(!have_child,
-			trans, btree_node_topology_interior_node_empty,
+			c, btree_node_topology_interior_node_empty,
 			"empty interior btree node at %s", buf.buf))
 		ret = DROP_THIS_NODE;
 err:
@@ -528,32 +534,39 @@ fsck_err:
 	return ret;
 }
 
-static int bch2_check_root(struct btree_trans *trans, enum btree_id i,
+static int bch2_check_root(struct btree_trans *trans, enum btree_id btree,
 			   bool *reconstructed_root)
 {
 	struct bch_fs *c = trans->c;
-	struct btree_root *r = bch2_btree_id_root(c, i);
+	struct btree_root *r = bch2_btree_id_root(c, btree);
 	struct printbuf buf = PRINTBUF;
 	int ret = 0;
 
-	bch2_btree_id_to_text(&buf, i);
+	bch2_btree_id_to_text(&buf, btree);
 
 	if (r->error) {
 		bch_info(c, "btree root %s unreadable, must recover from scan", buf.buf);
 
-		r->alive = false;
-		r->error = 0;
+		ret = bch2_btree_has_scanned_nodes(c, btree);
+		if (ret < 0)
+			goto err;
 
-		if (!bch2_btree_has_scanned_nodes(c, i)) {
+		if (!ret) {
 			__fsck_err(trans,
-				   FSCK_CAN_FIX|(!btree_id_important(i) ? FSCK_AUTOFIX : 0),
+				   FSCK_CAN_FIX|(!btree_id_important(btree) ? FSCK_AUTOFIX : 0),
 				   btree_root_unreadable_and_scan_found_nothing,
 				   "no nodes found for btree %s, continue?", buf.buf);
-			bch2_btree_root_alloc_fake_trans(trans, i, 0);
+
+			r->alive = false;
+			r->error = 0;
+			bch2_btree_root_alloc_fake_trans(trans, btree, 0);
 		} else {
-			bch2_btree_root_alloc_fake_trans(trans, i, 1);
-			bch2_shoot_down_journal_keys(c, i, 1, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX);
-			ret = bch2_get_scanned_nodes(c, i, 0, POS_MIN, SPOS_MAX);
+			r->alive = false;
+			r->error = 0;
+			bch2_btree_root_alloc_fake_trans(trans, btree, 1);
+
+			bch2_shoot_down_journal_keys(c, btree, 1, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX);
+			ret = bch2_get_scanned_nodes(c, btree, 0, POS_MIN, SPOS_MAX);
 			if (ret)
 				goto err;
 		}

fs/bcachefs/btree_io.c

View file

diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c
index d8f3c4c..08b22bd 100644
--- a/fs/bcachefs/btree_io.c
+++ b/fs/bcachefs/btree_io.c
@@ -557,7 +557,9 @@ static int __btree_err(int ret,
 		       const char *fmt, ...)
 {
 	if (c->recovery.curr_pass == BCH_RECOVERY_PASS_scan_for_btree_nodes)
-		return bch_err_throw(c, fsck_fix);
+		return ret == -BCH_ERR_btree_node_read_err_fixable
+			? bch_err_throw(c, fsck_fix)
+			: ret;
 
 	bool have_retry = false;
 	int ret2;
@@ -723,12 +725,11 @@ void bch2_btree_node_drop_keys_outside_node(struct btree *b)
 
 static int validate_bset(struct bch_fs *c, struct bch_dev *ca,
 			 struct btree *b, struct bset *i,
-			 unsigned offset, unsigned sectors, int write,
+			 unsigned offset, int write,
 			 struct bch_io_failures *failed,
 			 struct printbuf *err_msg)
 {
 	unsigned version = le16_to_cpu(i->version);
-	unsigned ptr_written = btree_ptr_sectors_written(bkey_i_to_s_c(&b->key));
 	struct printbuf buf1 = PRINTBUF;
 	struct printbuf buf2 = PRINTBUF;
 	int ret = 0;
@@ -778,15 +779,6 @@ static int validate_bset(struct bch_fs *c, struct bch_dev *ca,
 		     btree_node_unsupported_version,
 		     "BSET_SEPARATE_WHITEOUTS no longer supported");
 
-	if (!write &&
-	    btree_err_on(offset + sectors > (ptr_written ?: btree_sectors(c)),
-			 -BCH_ERR_btree_node_read_err_fixable,
-			 c, ca, b, i, NULL,
-			 bset_past_end_of_btree_node,
-			 "bset past end of btree node (offset %u len %u but written %zu)",
-			 offset, sectors, ptr_written ?: btree_sectors(c)))
-		i->u64s = 0;
-
 	btree_err_on(offset && !i->u64s,
 		     -BCH_ERR_btree_node_read_err_fixable,
 		     c, ca, b, i, NULL,
@@ -1151,6 +1143,14 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 			     "unknown checksum type %llu", BSET_CSUM_TYPE(i));
 
 		if (first) {
+			sectors = vstruct_sectors(b->data, c->block_bits);
+			if (btree_err_on(b->written + sectors > (ptr_written ?: btree_sectors(c)),
+					 -BCH_ERR_btree_node_read_err_fixable,
+					 c, ca, b, i, NULL,
+					 bset_past_end_of_btree_node,
+					 "bset past end of btree node (offset %u len %u but written %zu)",
+					 b->written, sectors, ptr_written ?: btree_sectors(c)))
+				i->u64s = 0;
 			if (good_csum_type) {
 				struct bch_csum csum = csum_vstruct(c, BSET_CSUM_TYPE(i), nonce, b->data);
 				bool csum_bad = bch2_crc_cmp(b->data->csum, csum);
@@ -1178,9 +1178,15 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 				     c, NULL, b, NULL, NULL,
 				     btree_node_unsupported_version,
 				     "btree node does not have NEW_EXTENT_OVERWRITE set");
-
-			sectors = vstruct_sectors(b->data, c->block_bits);
 		} else {
+			sectors = vstruct_sectors(bne, c->block_bits);
+			if (btree_err_on(b->written + sectors > (ptr_written ?: btree_sectors(c)),
+					 -BCH_ERR_btree_node_read_err_fixable,
+					 c, ca, b, i, NULL,
+					 bset_past_end_of_btree_node,
+					 "bset past end of btree node (offset %u len %u but written %zu)",
+					 b->written, sectors, ptr_written ?: btree_sectors(c)))
+				i->u64s = 0;
 			if (good_csum_type) {
 				struct bch_csum csum = csum_vstruct(c, BSET_CSUM_TYPE(i), nonce, bne);
 				bool csum_bad = bch2_crc_cmp(bne->csum, csum);
@@ -1201,14 +1207,12 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 						"decrypting btree node: %s", bch2_err_str(ret)))
 					goto fsck_err;
 			}
-
-			sectors = vstruct_sectors(bne, c->block_bits);
 		}
 
 		b->version_ondisk = min(b->version_ondisk,
 					le16_to_cpu(i->version));
 
-		ret = validate_bset(c, ca, b, i, b->written, sectors, READ, failed, err_msg);
+		ret = validate_bset(c, ca, b, i, b->written, READ, failed, err_msg);
 		if (ret)
 			goto fsck_err;
 
@@ -1982,28 +1986,12 @@ static void btree_node_scrub_work(struct work_struct *work)
 	prt_newline(&err);
 
 	if (!btree_node_scrub_check(c, scrub->buf, scrub->written, &err)) {
-		struct btree_trans *trans = bch2_trans_get(c);
-
-		struct btree_iter iter;
-		bch2_trans_node_iter_init(trans, &iter, scrub->btree,
-					  scrub->key.k->k.p, 0, scrub->level - 1, 0);
-
-		struct btree *b;
-		int ret = lockrestart_do(trans,
-			PTR_ERR_OR_ZERO(b = bch2_btree_iter_peek_node(trans, &iter)));
-		if (ret)
-			goto err;
-
-		if (bkey_i_to_btree_ptr_v2(&b->key)->v.seq == scrub->seq) {
-			bch_err(c, "error validating btree node during scrub on %s at btree %s",
-				scrub->ca->name, err.buf);
-
-			ret = bch2_btree_node_rewrite(trans, &iter, b, 0, 0);
-		}
-err:
-		bch2_trans_iter_exit(trans, &iter);
-		bch2_trans_begin(trans);
-		bch2_trans_put(trans);
+		int ret = bch2_trans_do(c,
+			bch2_btree_node_rewrite_key(trans, scrub->btree, scrub->level - 1,
+						    scrub->key.k, 0));
+		if (!bch2_err_matches(ret, ENOENT) &&
+		    !bch2_err_matches(ret, EROFS))
+			bch_err_fn_ratelimited(c, ret);
 	}
 
 	printbuf_exit(&err);
@@ -2267,7 +2255,7 @@ static void btree_node_write_endio(struct bio *bio)
 }
 
 static int validate_bset_for_write(struct bch_fs *c, struct btree *b,
-				   struct bset *i, unsigned sectors)
+				   struct bset *i)
 {
 	int ret = bch2_bkey_validate(c, bkey_i_to_s_c(&b->key),
 				     (struct bkey_validate_context) {
@@ -2282,7 +2270,7 @@ static int validate_bset_for_write(struct bch_fs *c, struct btree *b,
 	}
 
 	ret = validate_bset_keys(c, b, i, WRITE, NULL, NULL) ?:
-		validate_bset(c, NULL, b, i, b->written, sectors, WRITE, NULL, NULL);
+		validate_bset(c, NULL, b, i, b->written, WRITE, NULL, NULL);
 	if (ret) {
 		bch2_inconsistent_error(c);
 		dump_stack();
@@ -2475,7 +2463,7 @@ do_write:
 
 	/* if we're going to be encrypting, check metadata validity first: */
 	if (validate_before_checksum &&
-	    validate_bset_for_write(c, b, i, sectors_to_write))
+	    validate_bset_for_write(c, b, i))
 		goto err;
 
 	ret = bset_encrypt(c, i, b->written << 9);
@@ -2492,7 +2480,7 @@ do_write:
 
 	/* if we're not encrypting, check metadata after checksumming: */
 	if (!validate_before_checksum &&
-	    validate_bset_for_write(c, b, i, sectors_to_write))
+	    validate_bset_for_write(c, b, i))
 		goto err;
 
 	/*

fs/bcachefs/btree_iter.c

View file

diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c
index b784033..352f9cd 100644
--- a/fs/bcachefs/btree_iter.c
+++ b/fs/bcachefs/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;
 }
@@ -3132,6 +3194,10 @@ void *__bch2_trans_kmalloc(struct btree_trans *trans, size_t size, unsigned long
 	if (WARN_ON_ONCE(new_bytes > BTREE_TRANS_MEM_MAX)) {
 #ifdef CONFIG_BCACHEFS_TRANS_KMALLOC_TRACE
 		struct printbuf buf = PRINTBUF;
+		bch2_log_msg_start(c, &buf);
+		prt_printf(&buf, "bump allocator exceeded BTREE_TRANS_MEM_MAX (%u)\n",
+			   BTREE_TRANS_MEM_MAX);
+
 		bch2_trans_kmalloc_trace_to_text(&buf, &trans->trans_kmalloc_trace);
 		bch2_print_str(c, KERN_ERR, buf.buf);
 		printbuf_exit(&buf);
@@ -3159,46 +3225,32 @@ 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);