Adding upstream version 6.8.9.upstream/6.8.9

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

1 files changed, 176 insertions, 236 deletions

diff --git a/fs/bcachefs/btree_iter.h b/fs/bcachefs/btree_iter.h
index eaffced4c1..24772538e4 100644
--- a/fs/bcachefs/btree_iter.h
+++ b/fs/bcachefs/btree_iter.h
@@ -63,60 +63,57 @@ static inline void btree_trans_sort_paths(struct btree_trans *trans)
 	__bch2_btree_trans_sort_paths(trans);
 }
 
-static inline struct btree_path *
-__trans_next_path(struct btree_trans *trans, unsigned idx)
+static inline unsigned long *trans_paths_nr(struct btree_path *paths)
 {
-	u64 l;
-
-	if (idx == BTREE_ITER_MAX)
-		return NULL;
-
-	l = trans->paths_allocated >> idx;
-	if (!l)
-		return NULL;
-
-	idx += __ffs64(l);
-	EBUG_ON(idx >= BTREE_ITER_MAX);
-	EBUG_ON(trans->paths[idx].idx != idx);
-	return &trans->paths[idx];
+	return &container_of(paths, struct btree_trans_paths, paths[0])->nr_paths;
 }
 
-#define trans_for_each_path_from(_trans, _path, _start)			\
-	for (_path = __trans_next_path((_trans), _start);		\
-	     (_path);							\
-	     _path = __trans_next_path((_trans), (_path)->idx + 1))
-
-#define trans_for_each_path(_trans, _path)				\
-	trans_for_each_path_from(_trans, _path, 0)
-
-static inline struct btree_path *
-__trans_next_path_safe(struct btree_trans *trans, unsigned *idx)
+static inline unsigned long *trans_paths_allocated(struct btree_path *paths)
 {
-	u64 l;
+	unsigned long *v = trans_paths_nr(paths);
+	return v - BITS_TO_LONGS(*v);
+}
 
-	if (*idx == BTREE_ITER_MAX)
-		return NULL;
+#define trans_for_each_path_idx_from(_paths_allocated, _nr, _idx, _start)\
+	for (_idx = _start;						\
+	     (_idx = find_next_bit(_paths_allocated, _nr, _idx)) < _nr;	\
+	     _idx++)
 
-	l = trans->paths_allocated >> *idx;
-	if (!l)
-		return NULL;
+static inline struct btree_path *
+__trans_next_path(struct btree_trans *trans, unsigned *idx)
+{
+	unsigned long *w = trans->paths_allocated + *idx / BITS_PER_LONG;
+	/*
+	 * Open coded find_next_bit(), because
+	 *  - this is fast path, we can't afford the function call
+	 *  - and we know that nr_paths is a multiple of BITS_PER_LONG,
+	 */
+	while (*idx < trans->nr_paths) {
+		unsigned long v = *w >> (*idx & (BITS_PER_LONG - 1));
+		if (v) {
+			*idx += __ffs(v);
+			return trans->paths + *idx;
+		}
+
+		*idx += BITS_PER_LONG;
+		*idx &= ~(BITS_PER_LONG - 1);
+		w++;
+	}
 
-	*idx += __ffs64(l);
-	EBUG_ON(*idx >= BTREE_ITER_MAX);
-	return &trans->paths[*idx];
+	return NULL;
 }
 
 /*
  * This version is intended to be safe for use on a btree_trans that is owned by
  * another thread, for bch2_btree_trans_to_text();
  */
-#define trans_for_each_path_safe_from(_trans, _path, _idx, _start)	\
+#define trans_for_each_path_from(_trans, _path, _idx, _start)		\
 	for (_idx = _start;						\
-	     (_path = __trans_next_path_safe((_trans), &_idx));		\
+	     (_path = __trans_next_path((_trans), &_idx));		\
 	     _idx++)
 
-#define trans_for_each_path_safe(_trans, _path, _idx)			\
-	trans_for_each_path_safe_from(_trans, _path, _idx, 0)
+#define trans_for_each_path(_trans, _path, _idx)			\
+	trans_for_each_path_from(_trans, _path, _idx, 1)
 
 static inline struct btree_path *next_btree_path(struct btree_trans *trans, struct btree_path *path)
 {
@@ -138,10 +135,23 @@ static inline struct btree_path *prev_btree_path(struct btree_trans *trans, stru
 		: NULL;
 }
 
-#define trans_for_each_path_inorder(_trans, _path, _i)			\
-	for (_i = 0;							\
-	     ((_path) = (_trans)->paths + trans->sorted[_i]), (_i) < (_trans)->nr_sorted;\
-	     _i++)
+#define trans_for_each_path_idx_inorder(_trans, _iter)			\
+	for (_iter = (struct trans_for_each_path_inorder_iter) { 0 };	\
+	     (_iter.path_idx = trans->sorted[_iter.sorted_idx],		\
+	      _iter.sorted_idx < (_trans)->nr_sorted);			\
+	     _iter.sorted_idx++)
+
+struct trans_for_each_path_inorder_iter {
+	btree_path_idx_t	sorted_idx;
+	btree_path_idx_t	path_idx;
+};
+
+#define trans_for_each_path_inorder(_trans, _path, _iter)		\
+	for (_iter = (struct trans_for_each_path_inorder_iter) { 0 };	\
+	     (_iter.path_idx = trans->sorted[_iter.sorted_idx],		\
+	      _path = (_trans)->paths + _iter.path_idx,			\
+	      _iter.sorted_idx < (_trans)->nr_sorted);			\
+	     _iter.sorted_idx++)
 
 #define trans_for_each_path_inorder_reverse(_trans, _path, _i)		\
 	for (_i = trans->nr_sorted - 1;					\
@@ -157,67 +167,65 @@ static inline bool __path_has_node(const struct btree_path *path,
 
 static inline struct btree_path *
 __trans_next_path_with_node(struct btree_trans *trans, struct btree *b,
-			    unsigned idx)
+			    unsigned *idx)
 {
-	struct btree_path *path = __trans_next_path(trans, idx);
+	struct btree_path *path;
 
-	while (path && !__path_has_node(path, b))
-		path = __trans_next_path(trans, path->idx + 1);
+	while ((path = __trans_next_path(trans, idx)) &&
+		!__path_has_node(path, b))
+	       (*idx)++;
 
 	return path;
 }
 
-#define trans_for_each_path_with_node(_trans, _b, _path)		\
-	for (_path = __trans_next_path_with_node((_trans), (_b), 0);	\
-	     (_path);							\
-	     _path = __trans_next_path_with_node((_trans), (_b),	\
-						 (_path)->idx + 1))
+#define trans_for_each_path_with_node(_trans, _b, _path, _iter)		\
+	for (_iter = 1;							\
+	     (_path = __trans_next_path_with_node((_trans), (_b), &_iter));\
+	     _iter++)
 
-struct btree_path *__bch2_btree_path_make_mut(struct btree_trans *, struct btree_path *,
-			 bool, unsigned long);
+btree_path_idx_t __bch2_btree_path_make_mut(struct btree_trans *, btree_path_idx_t,
+					    bool, unsigned long);
 
-static inline struct btree_path * __must_check
+static inline btree_path_idx_t __must_check
 bch2_btree_path_make_mut(struct btree_trans *trans,
-			 struct btree_path *path, bool intent,
+			 btree_path_idx_t path, bool intent,
 			 unsigned long ip)
 {
-	if (path->ref > 1 || path->preserve)
+	if (trans->paths[path].ref > 1 ||
+	    trans->paths[path].preserve)
 		path = __bch2_btree_path_make_mut(trans, path, intent, ip);
-	path->should_be_locked = false;
+	trans->paths[path].should_be_locked = false;
 	return path;
 }
 
-struct btree_path * __must_check
-__bch2_btree_path_set_pos(struct btree_trans *, struct btree_path *,
-			struct bpos, bool, unsigned long, int);
+btree_path_idx_t __must_check
+__bch2_btree_path_set_pos(struct btree_trans *, btree_path_idx_t,
+			  struct bpos, bool, unsigned long);
 
-static inline struct btree_path * __must_check
+static inline btree_path_idx_t __must_check
 bch2_btree_path_set_pos(struct btree_trans *trans,
-		   struct btree_path *path, struct bpos new_pos,
-		   bool intent, unsigned long ip)
+			btree_path_idx_t path, struct bpos new_pos,
+			bool intent, unsigned long ip)
 {
-	int cmp = bpos_cmp(new_pos, path->pos);
-
-	return cmp
-		? __bch2_btree_path_set_pos(trans, path, new_pos, intent, ip, cmp)
+	return !bpos_eq(new_pos, trans->paths[path].pos)
+		? __bch2_btree_path_set_pos(trans, path, new_pos, intent, ip)
 		: path;
 }
 
-int __must_check bch2_btree_path_traverse_one(struct btree_trans *, struct btree_path *,
+int __must_check bch2_btree_path_traverse_one(struct btree_trans *,
+					      btree_path_idx_t,
 					      unsigned, unsigned long);
 
 static inline int __must_check bch2_btree_path_traverse(struct btree_trans *trans,
-					  struct btree_path *path, unsigned flags)
+					  btree_path_idx_t path, unsigned flags)
 {
-	if (path->uptodate < BTREE_ITER_NEED_RELOCK)
+	if (trans->paths[path].uptodate < BTREE_ITER_NEED_RELOCK)
 		return 0;
 
 	return bch2_btree_path_traverse_one(trans, path, flags, _RET_IP_);
 }
 
-int __must_check bch2_btree_path_traverse(struct btree_trans *,
-					  struct btree_path *, unsigned);
-struct btree_path *bch2_path_get(struct btree_trans *, enum btree_id, struct bpos,
+btree_path_idx_t bch2_path_get(struct btree_trans *, enum btree_id, struct bpos,
 				 unsigned, unsigned, unsigned, unsigned long);
 struct bkey_s_c bch2_btree_path_peek_slot(struct btree_path *, struct bkey *);
 
@@ -269,7 +277,7 @@ void bch2_btree_node_iter_fix(struct btree_trans *trans, struct btree_path *,
 
 int bch2_btree_path_relock_intent(struct btree_trans *, struct btree_path *);
 
-void bch2_path_put(struct btree_trans *, struct btree_path *, bool);
+void bch2_path_put(struct btree_trans *, btree_path_idx_t, bool);
 
 int bch2_trans_relock(struct btree_trans *);
 int bch2_trans_relock_notrace(struct btree_trans *);
@@ -335,7 +343,7 @@ static inline void bch2_btree_path_downgrade(struct btree_trans *trans,
 
 void bch2_trans_downgrade(struct btree_trans *);
 
-void bch2_trans_node_add(struct btree_trans *trans, struct btree *);
+void bch2_trans_node_add(struct btree_trans *trans, struct btree_path *, struct btree *);
 void bch2_trans_node_reinit_iter(struct btree_trans *, struct btree *);
 
 int __must_check __bch2_btree_iter_traverse(struct btree_iter *iter);
@@ -348,8 +356,6 @@ struct btree *bch2_btree_iter_next_node(struct btree_iter *);
 struct bkey_s_c bch2_btree_iter_peek_upto(struct btree_iter *, struct bpos);
 struct bkey_s_c bch2_btree_iter_next(struct btree_iter *);
 
-struct bkey_s_c bch2_btree_iter_peek_all_levels(struct btree_iter *);
-
 static inline struct bkey_s_c bch2_btree_iter_peek(struct btree_iter *iter)
 {
 	return bch2_btree_iter_peek_upto(iter, SPOS_MAX);
@@ -376,10 +382,12 @@ static inline void __bch2_btree_iter_set_pos(struct btree_iter *iter, struct bpo
 
 static inline void bch2_btree_iter_set_pos(struct btree_iter *iter, struct bpos new_pos)
 {
+	struct btree_trans *trans = iter->trans;
+
 	if (unlikely(iter->update_path))
-		bch2_path_put(iter->trans, iter->update_path,
+		bch2_path_put(trans, iter->update_path,
 			      iter->flags & BTREE_ITER_INTENT);
-	iter->update_path = NULL;
+	iter->update_path = 0;
 
 	if (!(iter->flags & BTREE_ITER_ALL_SNAPSHOTS))
 		new_pos.snapshot = iter->snapshot;
@@ -408,9 +416,6 @@ static inline unsigned __bch2_btree_iter_flags(struct btree_trans *trans,
 					       unsigned btree_id,
 					       unsigned flags)
 {
-	if (flags & BTREE_ITER_ALL_LEVELS)
-		flags |= BTREE_ITER_ALL_SNAPSHOTS|__BTREE_ITER_ALL_SNAPSHOTS;
-
 	if (!(flags & (BTREE_ITER_ALL_SNAPSHOTS|BTREE_ITER_NOT_EXTENTS)) &&
 	    btree_id_is_extents(btree_id))
 		flags |= BTREE_ITER_IS_EXTENTS;
@@ -450,14 +455,16 @@ static inline void bch2_trans_iter_init_common(struct btree_trans *trans,
 					  unsigned flags,
 					  unsigned long ip)
 {
-	memset(iter, 0, sizeof(*iter));
-	iter->trans	= trans;
-	iter->btree_id	= btree_id;
-	iter->flags	= flags;
-	iter->snapshot	= pos.snapshot;
-	iter->pos	= pos;
-	iter->k.p	= pos;
-
+	iter->trans		= trans;
+	iter->update_path	= 0;
+	iter->key_cache_path	= 0;
+	iter->btree_id		= btree_id;
+	iter->min_depth		= 0;
+	iter->flags		= flags;
+	iter->snapshot		= pos.snapshot;
+	iter->pos		= pos;
+	iter->k			= POS_KEY(pos);
+	iter->journal_idx	= 0;
 #ifdef CONFIG_BCACHEFS_DEBUG
 	iter->ip_allocated = ip;
 #endif
@@ -489,8 +496,10 @@ void bch2_trans_copy_iter(struct btree_iter *, struct btree_iter *);
 
 static inline void set_btree_iter_dontneed(struct btree_iter *iter)
 {
-	if (!iter->trans->restarted)
-		iter->path->preserve = false;
+	struct btree_trans *trans = iter->trans;
+
+	if (!trans->restarted)
+		btree_iter_path(trans, iter)->preserve = false;
 }
 
 void *__bch2_trans_kmalloc(struct btree_trans *, size_t);
@@ -512,7 +521,7 @@ static inline void *bch2_trans_kmalloc(struct btree_trans *trans, size_t size)
 
 static inline void *bch2_trans_kmalloc_nomemzero(struct btree_trans *trans, size_t size)
 {
-	size = roundup(size, 8);
+	size = round_up(size, 8);
 
 	if (likely(trans->mem_top + size <= trans->mem_bytes)) {
 		void *p = trans->mem + trans->mem_top;
@@ -581,7 +590,6 @@ static inline int __bch2_bkey_get_val_typed(struct btree_trans *trans,
 				  KEY_TYPE_##_type, sizeof(*_val), _val)
 
 void bch2_trans_srcu_unlock(struct btree_trans *);
-void bch2_trans_srcu_lock(struct btree_trans *);
 
 u32 bch2_trans_begin(struct btree_trans *);
 
@@ -606,8 +614,6 @@ u32 bch2_trans_begin(struct btree_trans *);
 static inline struct bkey_s_c bch2_btree_iter_peek_prev_type(struct btree_iter *iter,
 							     unsigned flags)
 {
-	BUG_ON(flags & BTREE_ITER_ALL_LEVELS);
-
 	return  flags & BTREE_ITER_SLOTS      ? bch2_btree_iter_peek_slot(iter) :
 						bch2_btree_iter_peek_prev(iter);
 }
@@ -615,8 +621,7 @@ static inline struct bkey_s_c bch2_btree_iter_peek_prev_type(struct btree_iter *
 static inline struct bkey_s_c bch2_btree_iter_peek_type(struct btree_iter *iter,
 							unsigned flags)
 {
-	return  flags & BTREE_ITER_ALL_LEVELS ? bch2_btree_iter_peek_all_levels(iter) :
-		flags & BTREE_ITER_SLOTS      ? bch2_btree_iter_peek_slot(iter) :
+	return  flags & BTREE_ITER_SLOTS      ? bch2_btree_iter_peek_slot(iter) :
 						bch2_btree_iter_peek(iter);
 }
 
@@ -633,61 +638,34 @@ static inline struct bkey_s_c bch2_btree_iter_peek_upto_type(struct btree_iter *
 	return bch2_btree_iter_peek_slot(iter);
 }
 
+int __bch2_btree_trans_too_many_iters(struct btree_trans *);
+
 static inline int btree_trans_too_many_iters(struct btree_trans *trans)
 {
-	if (hweight64(trans->paths_allocated) > BTREE_ITER_MAX - 8) {
-		trace_and_count(trans->c, trans_restart_too_many_iters, trans, _THIS_IP_);
-		return btree_trans_restart(trans, BCH_ERR_transaction_restart_too_many_iters);
-	}
+	if (bitmap_weight(trans->paths_allocated, trans->nr_paths) > BTREE_ITER_INITIAL - 8)
+		return __bch2_btree_trans_too_many_iters(trans);
 
 	return 0;
 }
 
-struct bkey_s_c bch2_btree_iter_peek_and_restart_outlined(struct btree_iter *);
-
-static inline struct bkey_s_c
-__bch2_btree_iter_peek_and_restart(struct btree_trans *trans,
-				   struct btree_iter *iter, unsigned flags)
-{
-	struct bkey_s_c k;
-
-	while (btree_trans_too_many_iters(trans) ||
-	       (k = bch2_btree_iter_peek_type(iter, flags),
-		bch2_err_matches(bkey_err(k), BCH_ERR_transaction_restart)))
-		bch2_trans_begin(trans);
-
-	return k;
-}
-
-static inline struct bkey_s_c
-__bch2_btree_iter_peek_upto_and_restart(struct btree_trans *trans,
-					struct btree_iter *iter,
-					struct bpos end,
-					unsigned flags)
-{
-	struct bkey_s_c k;
-
-	while (btree_trans_too_many_iters(trans) ||
-	       (k = bch2_btree_iter_peek_upto_type(iter, end, flags),
-		bch2_err_matches(bkey_err(k), BCH_ERR_transaction_restart)))
-		bch2_trans_begin(trans);
-
-	return k;
-}
-
+/*
+ * goto instead of loop, so that when used inside for_each_btree_key2()
+ * break/continue work correctly
+ */
 #define lockrestart_do(_trans, _do)					\
 ({									\
+	__label__ transaction_restart;					\
 	u32 _restart_count;						\
 	int _ret2;							\
+transaction_restart:							\
+	_restart_count = bch2_trans_begin(_trans);			\
+	_ret2 = (_do);							\
 									\
-	do {								\
-		_restart_count = bch2_trans_begin(_trans);		\
-		_ret2 = (_do);						\
-	} while (bch2_err_matches(_ret2, BCH_ERR_transaction_restart));	\
+	if (bch2_err_matches(_ret2, BCH_ERR_transaction_restart))	\
+		goto transaction_restart;				\
 									\
 	if (!_ret2)							\
 		bch2_trans_verify_not_restarted(_trans, _restart_count);\
-									\
 	_ret2;								\
 })
 
@@ -716,91 +694,56 @@ __bch2_btree_iter_peek_upto_and_restart(struct btree_trans *trans,
 	_ret2 ?: trans_was_restarted(_trans, _restart_count);		\
 })
 
-#define for_each_btree_key2(_trans, _iter, _btree_id,			\
-			    _start, _flags, _k, _do)			\
+#define for_each_btree_key_upto(_trans, _iter, _btree_id,		\
+				_start, _end, _flags, _k, _do)		\
 ({									\
+	struct btree_iter _iter;					\
+	struct bkey_s_c _k;						\
 	int _ret3 = 0;							\
 									\
 	bch2_trans_iter_init((_trans), &(_iter), (_btree_id),		\
 			     (_start), (_flags));			\
 									\
-	while (1) {							\
-		u32 _restart_count = bch2_trans_begin(_trans);		\
-									\
-		_ret3 = 0;						\
-		(_k) = bch2_btree_iter_peek_type(&(_iter), (_flags));	\
-		if (!(_k).k)						\
-			break;						\
+	do {								\
+		_ret3 = lockrestart_do(_trans, ({			\
+			(_k) = bch2_btree_iter_peek_upto_type(&(_iter),	\
+						_end, (_flags));	\
+			if (!(_k).k)					\
+				break;					\
 									\
-		_ret3 = bkey_err(_k) ?: (_do);				\
-		if (bch2_err_matches(_ret3, BCH_ERR_transaction_restart))\
-			continue;					\
-		if (_ret3)						\
-			break;						\
-		bch2_trans_verify_not_restarted(_trans, _restart_count);\
-		if (!bch2_btree_iter_advance(&(_iter)))			\
-			break;						\
-	}								\
+			bkey_err(_k) ?: (_do);				\
+		}));							\
+	} while (!_ret3 && bch2_btree_iter_advance(&(_iter)));		\
 									\
 	bch2_trans_iter_exit((_trans), &(_iter));			\
 	_ret3;								\
 })
 
-#define for_each_btree_key2_upto(_trans, _iter, _btree_id,		\
-			    _start, _end, _flags, _k, _do)		\
-({									\
-	int _ret3 = 0;							\
-									\
-	bch2_trans_iter_init((_trans), &(_iter), (_btree_id),		\
-			     (_start), (_flags));			\
-									\
-	while (1) {							\
-		u32 _restart_count = bch2_trans_begin(_trans);		\
-									\
-		_ret3 = 0;						\
-		(_k) = bch2_btree_iter_peek_upto_type(&(_iter), _end, (_flags));\
-		if (!(_k).k)						\
-			break;						\
-									\
-		_ret3 = bkey_err(_k) ?: (_do);				\
-		if (bch2_err_matches(_ret3, BCH_ERR_transaction_restart))\
-			continue;					\
-		if (_ret3)						\
-			break;						\
-		bch2_trans_verify_not_restarted(_trans, _restart_count);\
-		if (!bch2_btree_iter_advance(&(_iter)))			\
-			break;						\
-	}								\
-									\
-	bch2_trans_iter_exit((_trans), &(_iter));			\
-	_ret3;								\
-})
+#define for_each_btree_key(_trans, _iter, _btree_id,			\
+			   _start, _flags, _k, _do)			\
+	for_each_btree_key_upto(_trans, _iter, _btree_id, _start,	\
+				 SPOS_MAX, _flags, _k, _do)
 
 #define for_each_btree_key_reverse(_trans, _iter, _btree_id,		\
 				   _start, _flags, _k, _do)		\
 ({									\
+	struct btree_iter _iter;					\
+	struct bkey_s_c _k;						\
 	int _ret3 = 0;							\
 									\
 	bch2_trans_iter_init((_trans), &(_iter), (_btree_id),		\
 			     (_start), (_flags));			\
 									\
-	while (1) {							\
-		u32 _restart_count = bch2_trans_begin(_trans);		\
-		(_k) = bch2_btree_iter_peek_prev_type(&(_iter), (_flags));\
-		if (!(_k).k) {						\
-			_ret3 = 0;					\
-			break;						\
-		}							\
+	do {								\
+		_ret3 = lockrestart_do(_trans, ({			\
+			(_k) = bch2_btree_iter_peek_prev_type(&(_iter),	\
+							(_flags));	\
+			if (!(_k).k)					\
+				break;					\
 									\
-		_ret3 = bkey_err(_k) ?: (_do);				\
-		if (bch2_err_matches(_ret3, BCH_ERR_transaction_restart))\
-			continue;					\
-		if (_ret3)						\
-			break;						\
-		bch2_trans_verify_not_restarted(_trans, _restart_count);\
-		if (!bch2_btree_iter_rewind(&(_iter)))			\
-			break;						\
-	}								\
+			bkey_err(_k) ?: (_do);				\
+		}));							\
+	} while (!_ret3 && bch2_btree_iter_rewind(&(_iter)));		\
 									\
 	bch2_trans_iter_exit((_trans), &(_iter));			\
 	_ret3;								\
@@ -810,7 +753,7 @@ __bch2_btree_iter_peek_upto_and_restart(struct btree_trans *trans,
 				  _start, _iter_flags, _k,		\
 				  _disk_res, _journal_seq, _commit_flags,\
 				  _do)					\
-	for_each_btree_key2(_trans, _iter, _btree_id, _start, _iter_flags, _k,\
+	for_each_btree_key(_trans, _iter, _btree_id, _start, _iter_flags, _k,\
 			    (_do) ?: bch2_trans_commit(_trans, (_disk_res),\
 					(_journal_seq), (_commit_flags)))
 
@@ -826,32 +769,31 @@ __bch2_btree_iter_peek_upto_and_restart(struct btree_trans *trans,
 				  _start, _end, _iter_flags, _k,	\
 				  _disk_res, _journal_seq, _commit_flags,\
 				  _do)					\
-	for_each_btree_key2_upto(_trans, _iter, _btree_id, _start, _end, _iter_flags, _k,\
+	for_each_btree_key_upto(_trans, _iter, _btree_id, _start, _end, _iter_flags, _k,\
 			    (_do) ?: bch2_trans_commit(_trans, (_disk_res),\
 					(_journal_seq), (_commit_flags)))
 
-#define for_each_btree_key(_trans, _iter, _btree_id,			\
-			   _start, _flags, _k, _ret)			\
-	for (bch2_trans_iter_init((_trans), &(_iter), (_btree_id),	\
-				  (_start), (_flags));			\
-	     (_k) = __bch2_btree_iter_peek_and_restart((_trans), &(_iter), _flags),\
-	     !((_ret) = bkey_err(_k)) && (_k).k;			\
-	     bch2_btree_iter_advance(&(_iter)))
+struct bkey_s_c bch2_btree_iter_peek_and_restart_outlined(struct btree_iter *);
 
-#define for_each_btree_key_upto(_trans, _iter, _btree_id,		\
-				_start, _end, _flags, _k, _ret)		\
-	for (bch2_trans_iter_init((_trans), &(_iter), (_btree_id),	\
-				  (_start), (_flags));			\
-	     (_k) = __bch2_btree_iter_peek_upto_and_restart((_trans),	\
-						&(_iter), _end, _flags),\
-	     !((_ret) = bkey_err(_k)) && (_k).k;			\
-	     bch2_btree_iter_advance(&(_iter)))
+static inline struct bkey_s_c
+__bch2_btree_iter_peek_and_restart(struct btree_trans *trans,
+				   struct btree_iter *iter, unsigned flags)
+{
+	struct bkey_s_c k;
 
-#define for_each_btree_key_norestart(_trans, _iter, _btree_id,		\
+	while (btree_trans_too_many_iters(trans) ||
+	       (k = bch2_btree_iter_peek_type(iter, flags),
+		bch2_err_matches(bkey_err(k), BCH_ERR_transaction_restart)))
+		bch2_trans_begin(trans);
+
+	return k;
+}
+
+#define for_each_btree_key_old(_trans, _iter, _btree_id,		\
 			   _start, _flags, _k, _ret)			\
 	for (bch2_trans_iter_init((_trans), &(_iter), (_btree_id),	\
 				  (_start), (_flags));			\
-	     (_k) = bch2_btree_iter_peek_type(&(_iter), _flags),	\
+	     (_k) = __bch2_btree_iter_peek_and_restart((_trans), &(_iter), _flags),\
 	     !((_ret) = bkey_err(_k)) && (_k).k;			\
 	     bch2_btree_iter_advance(&(_iter)))
 
@@ -863,24 +805,25 @@ __bch2_btree_iter_peek_upto_and_restart(struct btree_trans *trans,
 	     !((_ret) = bkey_err(_k)) && (_k).k;			\
 	     bch2_btree_iter_advance(&(_iter)))
 
-#define for_each_btree_key_continue(_trans, _iter, _flags, _k, _ret)	\
-	for (;								\
-	     (_k) = __bch2_btree_iter_peek_and_restart((_trans), &(_iter), _flags),\
-	     !((_ret) = bkey_err(_k)) && (_k).k;			\
-	     bch2_btree_iter_advance(&(_iter)))
-
-#define for_each_btree_key_continue_norestart(_iter, _flags, _k, _ret)	\
-	for (;								\
-	     (_k) = bch2_btree_iter_peek_type(&(_iter), _flags),	\
-	     !((_ret) = bkey_err(_k)) && (_k).k;			\
-	     bch2_btree_iter_advance(&(_iter)))
-
 #define for_each_btree_key_upto_continue_norestart(_iter, _end, _flags, _k, _ret)\
 	for (;									\
 	     (_k) = bch2_btree_iter_peek_upto_type(&(_iter), _end, _flags),	\
 	     !((_ret) = bkey_err(_k)) && (_k).k;				\
 	     bch2_btree_iter_advance(&(_iter)))
 
+#define for_each_btree_key_norestart(_trans, _iter, _btree_id,		\
+			   _start, _flags, _k, _ret)			\
+	for_each_btree_key_upto_norestart(_trans, _iter, _btree_id, _start,\
+					  SPOS_MAX, _flags, _k, _ret)
+
+#define for_each_btree_key_continue_norestart(_iter, _flags, _k, _ret)	\
+	for_each_btree_key_upto_continue_norestart(_iter, SPOS_MAX, _flags, _k, _ret)
+
+/*
+ * This should not be used in a fastpath, without first trying _do in
+ * nonblocking mode - it will cause excessive transaction restarts and
+ * potentially livelocking:
+ */
 #define drop_locks_do(_trans, _do)					\
 ({									\
 	bch2_trans_unlock(_trans);					\
@@ -912,10 +855,7 @@ __bch2_btree_iter_peek_upto_and_restart(struct btree_trans *trans,
 	_p;								\
 })
 
-/* new multiple iterator interface: */
-
 void bch2_trans_updates_to_text(struct printbuf *, struct btree_trans *);
-void bch2_btree_path_to_text(struct printbuf *, struct btree_path *);
 void bch2_trans_paths_to_text(struct printbuf *, struct btree_trans *);
 void bch2_dump_trans_updates(struct btree_trans *);
 void bch2_dump_trans_paths_updates(struct btree_trans *);