Update bcachefs sources to d267e10a43b2 bcachefs: __bch2_sb_field_to_text()

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

.bcachefs_revision

@@ -1 +1 @@
-2a6125decb436ddc5e022c2428f64cf68dc974de
+d267e10a43b2e9ab37da6c9c991ca021142f6324

libbcachefs/alloc_background.c

@@ -749,25 +749,25 @@ static noinline int bch2_bucket_gen_update(struct btree_trans *trans,
 	return ret;
 }
 
-int bch2_trans_mark_alloc(struct btree_trans *trans,
+int bch2_trigger_alloc(struct btree_trans *trans,
-			  enum btree_id btree_id, unsigned level,
+		       enum btree_id btree, unsigned level,
-			  struct bkey_s_c old, struct bkey_i *new,
+		       struct bkey_s_c old, struct bkey_s new,
 		       unsigned flags)
 {
 	struct bch_fs *c = trans->c;
-	struct bch_alloc_v4 old_a_convert, *new_a;
-	const struct bch_alloc_v4 *old_a;
-	u64 old_lru, new_lru;
 	int ret = 0;
 
-	/*
+	if (bch2_trans_inconsistent_on(!bch2_dev_bucket_exists(c, new.k->p), trans,
-	 * Deletion only happens in the device removal path, with
+				       "alloc key for invalid device or bucket"))
-	 * BTREE_TRIGGER_NORUN:
+		return -EIO;
-	 */
-	BUG_ON(new->k.type != KEY_TYPE_alloc_v4);
 
-	old_a = bch2_alloc_to_v4(old, &old_a_convert);
+	struct bch_dev *ca = bch_dev_bkey_exists(c, new.k->p.inode);
-	new_a = &bkey_i_to_alloc_v4(new)->v;
+
+	struct bch_alloc_v4 old_a_convert;
+	const struct bch_alloc_v4 *old_a = bch2_alloc_to_v4(old, &old_a_convert);
+
+	if (flags & BTREE_TRIGGER_TRANSACTIONAL) {
+		struct bch_alloc_v4 *new_a = bkey_s_to_alloc_v4(new).v;
 
 		new_a->data_type = alloc_data_type(*new_a, new_a->data_type);
 
@@ -780,7 +780,7 @@ int bch2_trans_mark_alloc(struct btree_trans *trans,
 
 		if (data_type_is_empty(new_a->data_type) &&
 		    BCH_ALLOC_V4_NEED_INC_GEN(new_a) &&
-	    !bch2_bucket_is_open_safe(c, new->k.p.inode, new->k.p.offset)) {
+		    !bch2_bucket_is_open_safe(c, new.k->p.inode, new.k->p.offset)) {
 			new_a->gen++;
 			SET_BCH_ALLOC_V4_NEED_INC_GEN(new_a, false);
 		}
@@ -789,7 +789,7 @@ int bch2_trans_mark_alloc(struct btree_trans *trans,
 		    (new_a->data_type == BCH_DATA_free &&
 		     alloc_freespace_genbits(*old_a) != alloc_freespace_genbits(*new_a))) {
 			ret =   bch2_bucket_do_index(trans, old, old_a, false) ?:
-			bch2_bucket_do_index(trans, bkey_i_to_s_c(new), new_a, true);
+				bch2_bucket_do_index(trans, new.s_c, new_a, true);
 			if (ret)
 				return ret;
 		}
@@ -798,31 +798,29 @@ int bch2_trans_mark_alloc(struct btree_trans *trans,
 		    !new_a->io_time[READ])
 			new_a->io_time[READ] = max_t(u64, 1, atomic64_read(&c->io_clock[READ].now));
 
-	old_lru = alloc_lru_idx_read(*old_a);
+		u64 old_lru = alloc_lru_idx_read(*old_a);
-	new_lru = alloc_lru_idx_read(*new_a);
+		u64 new_lru = alloc_lru_idx_read(*new_a);
-
 		if (old_lru != new_lru) {
-		ret = bch2_lru_change(trans, new->k.p.inode,
+			ret = bch2_lru_change(trans, new.k->p.inode,
-				      bucket_to_u64(new->k.p),
+					      bucket_to_u64(new.k->p),
 					      old_lru, new_lru);
 			if (ret)
 				return ret;
 		}
 
 		new_a->fragmentation_lru = alloc_lru_idx_fragmentation(*new_a,
-					bch_dev_bkey_exists(c, new->k.p.inode));
+						bch_dev_bkey_exists(c, new.k->p.inode));
-
 		if (old_a->fragmentation_lru != new_a->fragmentation_lru) {
 			ret = bch2_lru_change(trans,
 					BCH_LRU_FRAGMENTATION_START,
-				bucket_to_u64(new->k.p),
+					bucket_to_u64(new.k->p),
 					old_a->fragmentation_lru, new_a->fragmentation_lru);
 			if (ret)
 				return ret;
 		}
 
 		if (old_a->gen != new_a->gen) {
-		ret = bch2_bucket_gen_update(trans, new->k.p, new_a->gen);
+			ret = bch2_bucket_gen_update(trans, new.k->p, new_a->gen);
 			if (ret)
 				return ret;
 		}
@@ -834,11 +832,95 @@ int bch2_trans_mark_alloc(struct btree_trans *trans,
 
 		if ((flags & BTREE_TRIGGER_BUCKET_INVALIDATE) &&
 		    old_a->cached_sectors) {
-		ret = bch2_update_cached_sectors_list(trans, new->k.p.inode,
+			ret = bch2_update_cached_sectors_list(trans, new.k->p.inode,
 							      -((s64) old_a->cached_sectors));
 			if (ret)
 				return ret;
 		}
+	}
+
+	if (!(flags & BTREE_TRIGGER_TRANSACTIONAL) && (flags & BTREE_TRIGGER_INSERT)) {
+		struct bch_alloc_v4 *new_a = bkey_s_to_alloc_v4(new).v;
+		u64 journal_seq = trans->journal_res.seq;
+		u64 bucket_journal_seq = new_a->journal_seq;
+
+		if ((flags & BTREE_TRIGGER_INSERT) &&
+		    data_type_is_empty(old_a->data_type) !=
+		    data_type_is_empty(new_a->data_type) &&
+		    new.k->type == KEY_TYPE_alloc_v4) {
+			struct bch_alloc_v4 *v = bkey_s_to_alloc_v4(new).v;
+
+			/*
+			 * If the btree updates referring to a bucket weren't flushed
+			 * before the bucket became empty again, then the we don't have
+			 * to wait on a journal flush before we can reuse the bucket:
+			 */
+			v->journal_seq = bucket_journal_seq =
+				data_type_is_empty(new_a->data_type) &&
+				(journal_seq == v->journal_seq ||
+				 bch2_journal_noflush_seq(&c->journal, v->journal_seq))
+				? 0 : journal_seq;
+		}
+
+		if (!data_type_is_empty(old_a->data_type) &&
+		    data_type_is_empty(new_a->data_type) &&
+		    bucket_journal_seq) {
+			ret = bch2_set_bucket_needs_journal_commit(&c->buckets_waiting_for_journal,
+					c->journal.flushed_seq_ondisk,
+					new.k->p.inode, new.k->p.offset,
+					bucket_journal_seq);
+			if (ret) {
+				bch2_fs_fatal_error(c,
+					"error setting bucket_needs_journal_commit: %i", ret);
+				return ret;
+			}
+		}
+
+		percpu_down_read(&c->mark_lock);
+		if (new_a->gen != old_a->gen)
+			*bucket_gen(ca, new.k->p.offset) = new_a->gen;
+
+		bch2_dev_usage_update(c, ca, old_a, new_a, journal_seq, false);
+
+		if (new_a->data_type == BCH_DATA_free &&
+		    (!new_a->journal_seq || new_a->journal_seq < c->journal.flushed_seq_ondisk))
+			closure_wake_up(&c->freelist_wait);
+
+		if (new_a->data_type == BCH_DATA_need_discard &&
+		    (!bucket_journal_seq || bucket_journal_seq < c->journal.flushed_seq_ondisk))
+			bch2_do_discards(c);
+
+		if (old_a->data_type != BCH_DATA_cached &&
+		    new_a->data_type == BCH_DATA_cached &&
+		    should_invalidate_buckets(ca, bch2_dev_usage_read(ca)))
+			bch2_do_invalidates(c);
+
+		if (new_a->data_type == BCH_DATA_need_gc_gens)
+			bch2_do_gc_gens(c);
+		percpu_up_read(&c->mark_lock);
+	}
+
+	if ((flags & BTREE_TRIGGER_GC) &&
+	    (flags & BTREE_TRIGGER_BUCKET_INVALIDATE)) {
+		struct bch_alloc_v4 new_a_convert;
+		const struct bch_alloc_v4 *new_a = bch2_alloc_to_v4(new.s_c, &new_a_convert);
+
+		percpu_down_read(&c->mark_lock);
+		struct bucket *g = gc_bucket(ca, new.k->p.offset);
+
+		bucket_lock(g);
+
+		g->gen_valid		= 1;
+		g->gen			= new_a->gen;
+		g->data_type		= new_a->data_type;
+		g->stripe		= new_a->stripe;
+		g->stripe_redundancy	= new_a->stripe_redundancy;
+		g->dirty_sectors	= new_a->dirty_sectors;
+		g->cached_sectors	= new_a->cached_sectors;
+
+		bucket_unlock(g);
+		percpu_up_read(&c->mark_lock);
+	}
 
 	return 0;
 }
@@ -1150,9 +1232,6 @@ int bch2_check_alloc_hole_bucket_gens(struct btree_trans *trans,
 	unsigned i, gens_offset, gens_end_offset;
 	int ret;
 
-	if (c->sb.version < bcachefs_metadata_version_bucket_gens)
-		return 0;
-
 	bch2_btree_iter_set_pos(bucket_gens_iter, alloc_gens_pos(start, &gens_offset));
 
 	k = bch2_btree_iter_peek_slot(bucket_gens_iter);

libbcachefs/alloc_background.h

@@ -182,24 +182,21 @@ void bch2_alloc_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c);
 #define bch2_bkey_ops_alloc ((struct bkey_ops) {	\
 	.key_invalid	= bch2_alloc_v1_invalid,	\
 	.val_to_text	= bch2_alloc_to_text,		\
-	.trans_trigger	= bch2_trans_mark_alloc,	\
+	.trigger	= bch2_trigger_alloc,		\
-	.atomic_trigger	= bch2_mark_alloc,		\
 	.min_val_size	= 8,				\
 })
 
 #define bch2_bkey_ops_alloc_v2 ((struct bkey_ops) {	\
 	.key_invalid	= bch2_alloc_v2_invalid,	\
 	.val_to_text	= bch2_alloc_to_text,		\
-	.trans_trigger	= bch2_trans_mark_alloc,	\
+	.trigger	= bch2_trigger_alloc,		\
-	.atomic_trigger	= bch2_mark_alloc,		\
 	.min_val_size	= 8,				\
 })
 
 #define bch2_bkey_ops_alloc_v3 ((struct bkey_ops) {	\
 	.key_invalid	= bch2_alloc_v3_invalid,	\
 	.val_to_text	= bch2_alloc_to_text,		\
-	.trans_trigger	= bch2_trans_mark_alloc,	\
+	.trigger	= bch2_trigger_alloc,		\
-	.atomic_trigger	= bch2_mark_alloc,		\
 	.min_val_size	= 16,				\
 })
 
@@ -207,8 +204,7 @@ void bch2_alloc_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c);
 	.key_invalid	= bch2_alloc_v4_invalid,	\
 	.val_to_text	= bch2_alloc_to_text,		\
 	.swab		= bch2_alloc_v4_swab,		\
-	.trans_trigger	= bch2_trans_mark_alloc,	\
+	.trigger	= bch2_trigger_alloc,		\
-	.atomic_trigger	= bch2_mark_alloc,		\
 	.min_val_size	= 48,				\
 })
 
@@ -232,8 +228,8 @@ static inline bool bkey_is_alloc(const struct bkey *k)
 
 int bch2_alloc_read(struct bch_fs *);
 
-int bch2_trans_mark_alloc(struct btree_trans *, enum btree_id, unsigned,
+int bch2_trigger_alloc(struct btree_trans *, enum btree_id, unsigned,
-			  struct bkey_s_c, struct bkey_i *, unsigned);
+		       struct bkey_s_c, struct bkey_s, unsigned);
 int bch2_check_alloc_info(struct bch_fs *);
 int bch2_check_alloc_to_lru_refs(struct bch_fs *);
 void bch2_do_discards(struct bch_fs *);

libbcachefs/backpointers.c

@@ -467,8 +467,7 @@ missing:
 	prt_printf(&buf, "\nbp pos ");
 	bch2_bpos_to_text(&buf, bp_iter.pos);
 
-	if (c->sb.version_upgrade_complete < bcachefs_metadata_version_backpointers ||
+	if (c->opts.reconstruct_alloc ||
-	    c->opts.reconstruct_alloc ||
 	    fsck_err(c, ptr_to_missing_backpointer, "%s", buf.buf))
 		ret = bch2_bucket_backpointer_mod(trans, bucket, bp, orig_k, true);
 

libbcachefs/bcachefs.h

@@ -425,6 +425,7 @@ BCH_DEBUG_PARAMS_DEBUG()
 	x(btree_node_merge)			\
 	x(btree_node_sort)			\
 	x(btree_node_read)			\
+	x(btree_node_read_done)			\
 	x(btree_interior_update_foreground)	\
 	x(btree_interior_update_total)		\
 	x(btree_gc)				\
@@ -464,6 +465,7 @@ enum bch_time_stats {
 #include "replicas_types.h"
 #include "subvolume_types.h"
 #include "super_types.h"
+#include "thread_with_file_types.h"
 
 /* Number of nodes btree coalesce will try to coalesce at once */
 #define GC_MERGE_NODES		4U
@@ -478,12 +480,6 @@ enum bch_time_stats {
 
 struct btree;
 
-struct log_output {
-	spinlock_t		lock;
-	wait_queue_head_t	wait;
-	struct printbuf		buf;
-};
-
 enum gc_phase {
 	GC_PHASE_NOT_RUNNING,
 	GC_PHASE_START,
@@ -607,9 +603,6 @@ struct bch_dev {
 };
 
 /*
- * fsck_done - kill?
- *
- * replace with something more general from enumated fsck passes/errors:
  * initial_gc_unfixed
  * error
  * topology error
@@ -625,7 +618,7 @@ struct bch_dev {
 	x(going_ro)			\
 	x(write_disable_complete)	\
 	x(clean_shutdown)		\
-	x(fsck_done)			\
+	x(fsck_running)			\
 	x(initial_gc_unfixed)		\
 	x(need_another_gc)		\
 	x(need_delete_dead_snapshots)	\
@@ -739,8 +732,8 @@ struct bch_fs {
 	struct super_block	*vfs_sb;
 	dev_t			dev;
 	char			name[40];
-	struct log_output	*output;
+	struct stdio_redirect	*stdio;
-	struct task_struct	*output_filter;
+	struct task_struct	*stdio_filter;
 
 	/* ro/rw, add/remove/resize devices: */
 	struct rw_semaphore	state_lock;
@@ -1252,6 +1245,15 @@ static inline bool bch2_dev_exists2(const struct bch_fs *c, unsigned dev)
 	return dev < c->sb.nr_devices && c->devs[dev];
 }
 
+static inline struct stdio_redirect *bch2_fs_stdio_redirect(struct bch_fs *c)
+{
+	struct stdio_redirect *stdio = c->stdio;
+
+	if (c->stdio_filter && c->stdio_filter != current)
+		stdio = NULL;
+	return stdio;
+}
+
 #define BKEY_PADDED_ONSTACK(key, pad)				\
 	struct { struct bkey_i key; __u64 key ## _pad[pad]; }
 

libbcachefs/bcachefs_format.h

@@ -1672,73 +1672,41 @@ struct bch_sb_field_downgrade {
 #define BCH_VERSION_MINOR(_v)		((__u16) ((_v) & ~(~0U << 10)))
 #define BCH_VERSION(_major, _minor)	(((_major) << 10)|(_minor) << 0)
 
-#define RECOVERY_PASS_ALL_FSCK		(1ULL << 63)
-
 /*
  * field 1:		version name
  * field 2:		BCH_VERSION(major, minor)
  * field 3:		recovery passess required on upgrade
  */
 #define BCH_METADATA_VERSIONS()						\
-	x(bkey_renumber,		BCH_VERSION(0, 10),		\
+	x(bkey_renumber,		BCH_VERSION(0, 10))		\
-	  RECOVERY_PASS_ALL_FSCK)					\
+	x(inode_btree_change,		BCH_VERSION(0, 11))		\
-	x(inode_btree_change,		BCH_VERSION(0, 11),		\
+	x(snapshot,			BCH_VERSION(0, 12))		\
-	  RECOVERY_PASS_ALL_FSCK)					\
+	x(inode_backpointers,		BCH_VERSION(0, 13))		\
-	x(snapshot,			BCH_VERSION(0, 12),		\
+	x(btree_ptr_sectors_written,	BCH_VERSION(0, 14))		\
-	  RECOVERY_PASS_ALL_FSCK)					\
+	x(snapshot_2,			BCH_VERSION(0, 15))		\
-	x(inode_backpointers,		BCH_VERSION(0, 13),		\
+	x(reflink_p_fix,		BCH_VERSION(0, 16))		\
-	  RECOVERY_PASS_ALL_FSCK)					\
+	x(subvol_dirent,		BCH_VERSION(0, 17))		\
-	x(btree_ptr_sectors_written,	BCH_VERSION(0, 14),		\
+	x(inode_v2,			BCH_VERSION(0, 18))		\
-	  RECOVERY_PASS_ALL_FSCK)					\
+	x(freespace,			BCH_VERSION(0, 19))		\
-	x(snapshot_2,			BCH_VERSION(0, 15),		\
+	x(alloc_v4,			BCH_VERSION(0, 20))		\
-	  BIT_ULL(BCH_RECOVERY_PASS_fs_upgrade_for_subvolumes)|		\
+	x(new_data_types,		BCH_VERSION(0, 21))		\
-	  BIT_ULL(BCH_RECOVERY_PASS_initialize_subvolumes)|		\
+	x(backpointers,			BCH_VERSION(0, 22))		\
-	  RECOVERY_PASS_ALL_FSCK)					\
+	x(inode_v3,			BCH_VERSION(0, 23))		\
-	x(reflink_p_fix,		BCH_VERSION(0, 16),		\
+	x(unwritten_extents,		BCH_VERSION(0, 24))		\
-	  BIT_ULL(BCH_RECOVERY_PASS_fix_reflink_p))			\
+	x(bucket_gens,			BCH_VERSION(0, 25))		\
-	x(subvol_dirent,		BCH_VERSION(0, 17),		\
+	x(lru_v2,			BCH_VERSION(0, 26))		\
-	  RECOVERY_PASS_ALL_FSCK)					\
+	x(fragmentation_lru,		BCH_VERSION(0, 27))		\
-	x(inode_v2,			BCH_VERSION(0, 18),		\
+	x(no_bps_in_alloc_keys,		BCH_VERSION(0, 28))		\
-	  RECOVERY_PASS_ALL_FSCK)					\
+	x(snapshot_trees,		BCH_VERSION(0, 29))		\
-	x(freespace,			BCH_VERSION(0, 19),		\
+	x(major_minor,			BCH_VERSION(1,  0))		\
-	  RECOVERY_PASS_ALL_FSCK)					\
+	x(snapshot_skiplists,		BCH_VERSION(1,  1))		\
-	x(alloc_v4,			BCH_VERSION(0, 20),		\
+	x(deleted_inodes,		BCH_VERSION(1,  2))		\
-	  RECOVERY_PASS_ALL_FSCK)					\
+	x(rebalance_work,		BCH_VERSION(1,  3))		\
-	x(new_data_types,		BCH_VERSION(0, 21),		\
+	x(member_seq,			BCH_VERSION(1,  4))
-	  RECOVERY_PASS_ALL_FSCK)					\
-	x(backpointers,			BCH_VERSION(0, 22),		\
-	  RECOVERY_PASS_ALL_FSCK)					\
-	x(inode_v3,			BCH_VERSION(0, 23),		\
-	  RECOVERY_PASS_ALL_FSCK)					\
-	x(unwritten_extents,		BCH_VERSION(0, 24),		\
-	  RECOVERY_PASS_ALL_FSCK)					\
-	x(bucket_gens,			BCH_VERSION(0, 25),		\
-	  BIT_ULL(BCH_RECOVERY_PASS_bucket_gens_init)|			\
-	  RECOVERY_PASS_ALL_FSCK)					\
-	x(lru_v2,			BCH_VERSION(0, 26),		\
-	  RECOVERY_PASS_ALL_FSCK)					\
-	x(fragmentation_lru,		BCH_VERSION(0, 27),		\
-	  RECOVERY_PASS_ALL_FSCK)					\
-	x(no_bps_in_alloc_keys,		BCH_VERSION(0, 28),		\
-	  RECOVERY_PASS_ALL_FSCK)					\
-	x(snapshot_trees,		BCH_VERSION(0, 29),		\
-	  RECOVERY_PASS_ALL_FSCK)					\
-	x(major_minor,			BCH_VERSION(1,  0),		\
-	  0)								\
-	x(snapshot_skiplists,		BCH_VERSION(1,  1),		\
-	  BIT_ULL(BCH_RECOVERY_PASS_check_snapshots))			\
-	x(deleted_inodes,		BCH_VERSION(1,  2),		\
-	  BIT_ULL(BCH_RECOVERY_PASS_check_inodes))			\
-	x(rebalance_work,		BCH_VERSION(1,  3),		\
-	  BIT_ULL(BCH_RECOVERY_PASS_set_fs_needs_rebalance))		\
-	x(member_seq,			BCH_VERSION(1,  4),		\
-	  0)								\
-	x(disk_accounting_v2,		BCH_VERSION(1,  5),		\
-	  BIT_ULL(BCH_RECOVERY_PASS_check_alloc_info))
 
 enum bcachefs_metadata_version {
 	bcachefs_metadata_version_min = 9,
-#define x(t, n, upgrade_passes)	bcachefs_metadata_version_##t = n,
+#define x(t, n)	bcachefs_metadata_version_##t = n,
 	BCH_METADATA_VERSIONS()
 #undef x
 	bcachefs_metadata_version_max

libbcachefs/bkey_methods.h

@@ -28,10 +28,8 @@ struct bkey_ops {
 	void		(*swab)(struct bkey_s);
 	bool		(*key_normalize)(struct bch_fs *, struct bkey_s);
 	bool		(*key_merge)(struct bch_fs *, struct bkey_s, struct bkey_s_c);
-	int		(*trans_trigger)(struct btree_trans *, enum btree_id, unsigned,
+	int		(*trigger)(struct btree_trans *, enum btree_id, unsigned,
-					 struct bkey_s_c, struct bkey_i *, unsigned);
+				   struct bkey_s_c, struct bkey_s, unsigned);
-	int		(*atomic_trigger)(struct btree_trans *, enum btree_id, unsigned,
-					  struct bkey_s_c, struct bkey_s_c, unsigned);
 	void		(*compat)(enum btree_id id, unsigned version,
 				  unsigned big_endian, int write,
 				  struct bkey_s);
@@ -78,59 +76,63 @@ static inline bool bch2_bkey_maybe_mergable(const struct bkey *l, const struct b
 
 bool bch2_bkey_merge(struct bch_fs *, struct bkey_s, struct bkey_s_c);
 
-static inline int bch2_mark_key(struct btree_trans *trans,
-		enum btree_id btree, unsigned level,
-		struct bkey_s_c old, struct bkey_s_c new,
-		unsigned flags)
-{
-	const struct bkey_ops *ops = bch2_bkey_type_ops(old.k->type ?: new.k->type);
-
-	return ops->atomic_trigger
-		? ops->atomic_trigger(trans, btree, level, old, new, flags)
-		: 0;
-}
-
 enum btree_update_flags {
 	__BTREE_UPDATE_INTERNAL_SNAPSHOT_NODE = __BTREE_ITER_FLAGS_END,
 	__BTREE_UPDATE_NOJOURNAL,
 	__BTREE_UPDATE_KEY_CACHE_RECLAIM,
 
-	__BTREE_TRIGGER_NORUN,		/* Don't run triggers at all */
+	__BTREE_TRIGGER_NORUN,
-
+	__BTREE_TRIGGER_TRANSACTIONAL,
 	__BTREE_TRIGGER_INSERT,
 	__BTREE_TRIGGER_OVERWRITE,
-
 	__BTREE_TRIGGER_GC,
 	__BTREE_TRIGGER_BUCKET_INVALIDATE,
-	__BTREE_TRIGGER_NOATOMIC,
 };
 
 #define BTREE_UPDATE_INTERNAL_SNAPSHOT_NODE (1U << __BTREE_UPDATE_INTERNAL_SNAPSHOT_NODE)
 #define BTREE_UPDATE_NOJOURNAL		(1U << __BTREE_UPDATE_NOJOURNAL)
 #define BTREE_UPDATE_KEY_CACHE_RECLAIM	(1U << __BTREE_UPDATE_KEY_CACHE_RECLAIM)
 
+/* Don't run triggers at all */
 #define BTREE_TRIGGER_NORUN		(1U << __BTREE_TRIGGER_NORUN)
 
+/*
+ * If set, we're running transactional triggers as part of a transaction commit:
+ * triggers may generate new updates
+ *
+ * If cleared, and either BTREE_TRIGGER_INSERT|BTREE_TRIGGER_OVERWRITE are set,
+ * we're running atomic triggers during a transaction commit: we have our
+ * journal reservation, we're holding btree node write locks, and we know the
+ * transaction is going to commit (returning an error here is a fatal error,
+ * causing us to go emergency read-only)
+ */
+#define BTREE_TRIGGER_TRANSACTIONAL	(1U << __BTREE_TRIGGER_TRANSACTIONAL)
+
+/* @new is entering the btree */
 #define BTREE_TRIGGER_INSERT		(1U << __BTREE_TRIGGER_INSERT)
+
+/* @old is leaving the btree */
 #define BTREE_TRIGGER_OVERWRITE		(1U << __BTREE_TRIGGER_OVERWRITE)
 
+/* We're in gc/fsck: running triggers to recalculate e.g. disk usage */
 #define BTREE_TRIGGER_GC		(1U << __BTREE_TRIGGER_GC)
-#define BTREE_TRIGGER_BUCKET_INVALIDATE	(1U << __BTREE_TRIGGER_BUCKET_INVALIDATE)
-#define BTREE_TRIGGER_NOATOMIC		(1U << __BTREE_TRIGGER_NOATOMIC)
 
-static inline int bch2_trans_mark_key(struct btree_trans *trans,
+/* signal from bucket invalidate path to alloc trigger */
-				      enum btree_id btree_id, unsigned level,
+#define BTREE_TRIGGER_BUCKET_INVALIDATE	(1U << __BTREE_TRIGGER_BUCKET_INVALIDATE)
-				      struct bkey_s_c old, struct bkey_i *new,
+
+static inline int bch2_key_trigger(struct btree_trans *trans,
+		enum btree_id btree, unsigned level,
+		struct bkey_s_c old, struct bkey_s new,
 		unsigned flags)
 {
-	const struct bkey_ops *ops = bch2_bkey_type_ops(old.k->type ?: new->k.type);
+	const struct bkey_ops *ops = bch2_bkey_type_ops(old.k->type ?: new.k->type);
 
-	return ops->trans_trigger
+	return ops->trigger
-		? ops->trans_trigger(trans, btree_id, level, old, new, flags)
+		? ops->trigger(trans, btree, level, old, new, flags)
 		: 0;
 }
 
-static inline int bch2_trans_mark_old(struct btree_trans *trans,
+static inline int bch2_key_trigger_old(struct btree_trans *trans,
 				       enum btree_id btree_id, unsigned level,
 				       struct bkey_s_c old, unsigned flags)
 {
@@ -139,20 +141,20 @@ static inline int bch2_trans_mark_old(struct btree_trans *trans,
 	bkey_init(&deleted.k);
 	deleted.k.p = old.k->p;
 
-	return bch2_trans_mark_key(trans, btree_id, level, old, &deleted,
+	return bch2_key_trigger(trans, btree_id, level, old, bkey_i_to_s(&deleted),
 				BTREE_TRIGGER_OVERWRITE|flags);
 }
 
-static inline int bch2_trans_mark_new(struct btree_trans *trans,
+static inline int bch2_key_trigger_new(struct btree_trans *trans,
 				       enum btree_id btree_id, unsigned level,
-				      struct bkey_i *new, unsigned flags)
+				       struct bkey_s new, unsigned flags)
 {
 	struct bkey_i deleted;
 
 	bkey_init(&deleted.k);
-	deleted.k.p = new->k.p;
+	deleted.k.p = new.k->p;
 
-	return bch2_trans_mark_key(trans, btree_id, level, bkey_i_to_s_c(&deleted), new,
+	return bch2_key_trigger(trans, btree_id, level, bkey_i_to_s_c(&deleted), new,
 				BTREE_TRIGGER_INSERT|flags);
 }
 

libbcachefs/btree_cache.c

@@ -719,12 +719,6 @@ static noinline struct btree *bch2_btree_node_fill(struct btree_trans *trans,
 	if (IS_ERR(b))
 		return b;
 
-	/*
-	 * Btree nodes read in from disk should not have the accessed bit set
-	 * initially, so that linear scans don't thrash the cache:
-	 */
-	clear_btree_node_accessed(b);
-
 	bkey_copy(&b->key, k);
 	if (bch2_btree_node_hash_insert(bc, b, level, btree_id)) {
 		/* raced with another fill: */

libbcachefs/btree_gc.c

@@ -41,6 +41,14 @@
 #define DROP_THIS_NODE		10
 #define DROP_PREV_NODE		11
 
+static struct bkey_s unsafe_bkey_s_c_to_s(struct bkey_s_c k)
+{
+	return (struct bkey_s) {{{
+		(struct bkey *) k.k,
+		(struct bch_val *) k.v
+	}}};
+}
+
 static bool should_restart_for_topology_repair(struct bch_fs *c)
 {
 	return c->opts.fix_errors != FSCK_FIX_no &&
@@ -805,9 +813,6 @@ static int bch2_gc_mark_key(struct btree_trans *trans, enum btree_id btree_id,
 	struct bch_fs *c = trans->c;
 	struct bkey deleted = KEY(0, 0, 0);
 	struct bkey_s_c old = (struct bkey_s_c) { &deleted, NULL };
-	unsigned flags =
-		BTREE_TRIGGER_GC|
-		(initial ? BTREE_TRIGGER_NOATOMIC : 0);
 	int ret = 0;
 
 	deleted.p = k->k->p;
@@ -829,7 +834,7 @@ static int bch2_gc_mark_key(struct btree_trans *trans, enum btree_id btree_id,
 	}
 
 	ret = commit_do(trans, NULL, NULL, 0,
-			bch2_mark_key(trans, btree_id, level, old, *k, flags));
+			bch2_key_trigger(trans, btree_id, level, old, unsafe_bkey_s_c_to_s(*k), BTREE_TRIGGER_GC));
 fsck_err:
 err:
 	bch_err_fn(c, ret);
@@ -1589,7 +1594,7 @@ static int bch2_gc_write_reflink_key(struct btree_trans *trans,
 		if (!r->refcount)
 			new->k.type = KEY_TYPE_deleted;
 		else
-			*bkey_refcount(new) = cpu_to_le64(r->refcount);
+			*bkey_refcount(bkey_i_to_s(new)) = cpu_to_le64(r->refcount);
 	}
 fsck_err:
 	printbuf_exit(&buf);

libbcachefs/btree_io.c

@@ -942,6 +942,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 	unsigned ptr_written = btree_ptr_sectors_written(&b->key);
 	struct printbuf buf = PRINTBUF;
 	int ret = 0, retry_read = 0, write = READ;
+	u64 start_time = local_clock();
 
 	b->version_ondisk = U16_MAX;
 	/* We might get called multiple times on read retry: */
@@ -1209,6 +1210,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 out:
 	mempool_free(iter, &c->fill_iter);
 	printbuf_exit(&buf);
+	bch2_time_stats_update(&c->times[BCH_TIME_btree_node_read_done], start_time);
 	return retry_read;
 fsck_err:
 	if (ret == -BCH_ERR_btree_node_read_err_want_retry ||
@@ -1645,7 +1647,7 @@ void bch2_btree_node_read(struct btree_trans *trans, struct btree *b,
 
 		if (sync) {
 			submit_bio_wait(bio);
-
+			bch2_latency_acct(ca, rb->start_time, READ);
 			btree_node_read_work(&rb->work);
 		} else {
 			submit_bio(bio);

libbcachefs/btree_iter.c

@@ -897,7 +897,8 @@ static noinline int btree_node_iter_and_journal_peek(struct btree_trans *trans,
 
 	bch2_bkey_buf_reassemble(out, c, k);
 
-	if (flags & BTREE_ITER_PREFETCH)
+	if ((flags & BTREE_ITER_PREFETCH) &&
+	    c->opts.btree_node_prefetch)
 		ret = btree_path_prefetch_j(trans, path, &jiter);
 
 	bch2_btree_and_journal_iter_exit(&jiter);
@@ -929,7 +930,8 @@ static __always_inline int btree_path_down(struct btree_trans *trans,
 		bch2_bkey_buf_unpack(&tmp, c, l->b,
 				 bch2_btree_node_iter_peek(&l->iter, l->b));
 
-		if (flags & BTREE_ITER_PREFETCH) {
+		if ((flags & BTREE_ITER_PREFETCH) &&
+		    c->opts.btree_node_prefetch) {
 			ret = btree_path_prefetch(trans, path);
 			if (ret)
 				goto err;
@@ -2816,11 +2818,34 @@ void *__bch2_trans_kmalloc(struct btree_trans *trans, size_t size)
 	return p;
 }
 
+#include "sb-members.h"
+
 static inline void check_srcu_held_too_long(struct btree_trans *trans)
 {
+	if (trans->srcu_held && time_after(jiffies, trans->srcu_lock_time + HZ * 10)) {
+		struct printbuf buf = PRINTBUF;
+
+		prt_str(&buf, "btree node read time:\n");
+		bch2_time_stats_to_text(&buf, &trans->c->times[BCH_TIME_btree_node_read]);
+
+		prt_str(&buf, "btree node read_done time:\n");
+		bch2_time_stats_to_text(&buf, &trans->c->times[BCH_TIME_btree_node_read_done]);
+
+		for_each_member_device(trans->c, ca) {
+			prt_printf(&buf, "device %u read time:\n", ca->dev_idx);
+			bch2_time_stats_to_text(&buf, &ca->io_latency[READ]);
+		}
+
+		struct btree_transaction_stats *s = btree_trans_stats(trans);
+		prt_str(&buf, "transaction duration:\n");
+		bch2_time_stats_to_text(&buf, &s->duration);
+
 		WARN(trans->srcu_held && time_after(jiffies, trans->srcu_lock_time + HZ * 10),
 		     "btree trans held srcu lock (delaying memory reclaim) for %lu seconds",
 		     (jiffies - trans->srcu_lock_time) / HZ);
+		bch2_print_string_as_lines(KERN_ERR, buf.buf);
+		printbuf_exit(&buf);
+	}
 }
 
 void bch2_trans_srcu_unlock(struct btree_trans *trans)

libbcachefs/btree_locking.c

@@ -86,8 +86,14 @@ static noinline void print_cycle(struct printbuf *out, struct lock_graph *g)
 	prt_printf(out, "Found lock cycle (%u entries):", g->nr);
 	prt_newline(out);
 
-	for (i = g->g; i < g->g + g->nr; i++)
+	for (i = g->g; i < g->g + g->nr; i++) {
+		struct task_struct *task = READ_ONCE(i->trans->locking_wait.task);
+		if (!task)
+			continue;
+
 		bch2_btree_trans_to_text(out, i->trans);
+		bch2_prt_task_backtrace(out, task, i == g->g ? 5 : 1);
+	}
 }
 
 static noinline void print_chain(struct printbuf *out, struct lock_graph *g)
@@ -144,8 +150,7 @@ static bool lock_graph_remove_non_waiters(struct lock_graph *g)
 	return false;
 }
 
-static void trace_would_deadlock(struct lock_graph *g, struct btree_trans *trans,
+static void trace_would_deadlock(struct lock_graph *g, struct btree_trans *trans)
-				 unsigned long ip)
 {
 	struct bch_fs *c = trans->c;
 
@@ -157,7 +162,7 @@ static void trace_would_deadlock(struct lock_graph *g, struct btree_trans *trans
 		buf.atomic++;
 		print_cycle(&buf, g);
 
-		trace_trans_restart_would_deadlock(trans, ip, buf.buf);
+		trace_trans_restart_would_deadlock(trans, buf.buf);
 		printbuf_exit(&buf);
 	}
 }
@@ -165,7 +170,7 @@ static void trace_would_deadlock(struct lock_graph *g, struct btree_trans *trans
 static int abort_lock(struct lock_graph *g, struct trans_waiting_for_lock *i)
 {
 	if (i == g->g) {
-		trace_would_deadlock(g, i->trans, _RET_IP_);
+		trace_would_deadlock(g, i->trans);
 		return btree_trans_restart(i->trans, BCH_ERR_transaction_restart_would_deadlock);
 	} else {
 		i->trans->lock_must_abort = true;
@@ -222,7 +227,7 @@ static noinline int break_cycle(struct lock_graph *g, struct printbuf *cycle)
 			prt_printf(&buf, "backtrace:");
 			prt_newline(&buf);
 			printbuf_indent_add(&buf, 2);
-			bch2_prt_task_backtrace(&buf, trans->locking_wait.task);
+			bch2_prt_task_backtrace(&buf, trans->locking_wait.task, 2);
 			printbuf_indent_sub(&buf, 2);
 			prt_newline(&buf);
 		}
@@ -291,7 +296,7 @@ int bch2_check_for_deadlock(struct btree_trans *trans, struct printbuf *cycle)
 		if (cycle)
 			return -1;
 
-		trace_would_deadlock(&g, trans, _RET_IP_);
+		trace_would_deadlock(&g, trans);
 		return btree_trans_restart(trans, BCH_ERR_transaction_restart_would_deadlock);
 	}
 

libbcachefs/btree_trans_commit.c

@@ -451,20 +451,15 @@ static int run_one_mem_trigger(struct btree_trans *trans,
 	if (!btree_node_type_needs_gc(__btree_node_type(i->level, i->btree_id)))
 		return 0;
 
-	if (old_ops->atomic_trigger == new_ops->atomic_trigger) {
+	if (old_ops->trigger == new_ops->trigger) {
-		ret   = bch2_mark_key(trans, i->btree_id, i->level,
+		ret   = bch2_key_trigger(trans, i->btree_id, i->level,
-				old, bkey_i_to_s_c(new),
+				old, bkey_i_to_s(new),
 				BTREE_TRIGGER_INSERT|BTREE_TRIGGER_OVERWRITE|flags);
 	} else {
-		struct bkey		_deleted = POS_KEY((trans->paths + i->path)->pos);
+		ret   = bch2_key_trigger_new(trans, i->btree_id, i->level,
-		struct bkey_s_c		deleted = (struct bkey_s_c) { &_deleted, NULL };
+				bkey_i_to_s(new), flags) ?:
-
+			bch2_key_trigger_old(trans, i->btree_id, i->level,
-		ret   = bch2_mark_key(trans, i->btree_id, i->level,
+				old, flags);
-				deleted, bkey_i_to_s_c(new),
-				BTREE_TRIGGER_INSERT|flags) ?:
-			bch2_mark_key(trans, i->btree_id, i->level,
-				old, deleted,
-				BTREE_TRIGGER_OVERWRITE|flags);
 	}
 
 	return ret;
@@ -482,6 +477,7 @@ static int run_one_trans_trigger(struct btree_trans *trans, struct btree_insert_
 	struct bkey_s_c old = { &old_k, i->old_v };
 	const struct bkey_ops *old_ops = bch2_bkey_type_ops(old.k->type);
 	const struct bkey_ops *new_ops = bch2_bkey_type_ops(i->k->k.type);
+	unsigned flags = i->flags|BTREE_TRIGGER_TRANSACTIONAL;
 
 	verify_update_old_key(trans, i);
 
@@ -491,19 +487,18 @@ static int run_one_trans_trigger(struct btree_trans *trans, struct btree_insert_
 
 	if (!i->insert_trigger_run &&
 	    !i->overwrite_trigger_run &&
-	    old_ops->trans_trigger == new_ops->trans_trigger) {
+	    old_ops->trigger == new_ops->trigger) {
 		i->overwrite_trigger_run = true;
 		i->insert_trigger_run = true;
-		return bch2_trans_mark_key(trans, i->btree_id, i->level, old, i->k,
+		return bch2_key_trigger(trans, i->btree_id, i->level, old, bkey_i_to_s(i->k),
 					BTREE_TRIGGER_INSERT|
-					   BTREE_TRIGGER_OVERWRITE|
+					BTREE_TRIGGER_OVERWRITE|flags) ?: 1;
-					   i->flags) ?: 1;
 	} else if (overwrite && !i->overwrite_trigger_run) {
 		i->overwrite_trigger_run = true;
-		return bch2_trans_mark_old(trans, i->btree_id, i->level, old, i->flags) ?: 1;
+		return bch2_key_trigger_old(trans, i->btree_id, i->level, old, flags) ?: 1;
 	} else if (!overwrite && !i->insert_trigger_run) {
 		i->insert_trigger_run = true;
-		return bch2_trans_mark_new(trans, i->btree_id, i->level, i->k, i->flags) ?: 1;
+		return bch2_key_trigger_new(trans, i->btree_id, i->level, bkey_i_to_s(i->k), flags) ?: 1;
 	} else {
 		return 0;
 	}

libbcachefs/btree_update_interior.c

@@ -568,7 +568,8 @@ static int btree_update_nodes_written_trans(struct btree_trans *trans,
 	for_each_keylist_key(&as->old_keys, k) {
 		unsigned level = bkey_i_to_btree_ptr_v2(k)->v.mem_ptr;
 
-		ret = bch2_trans_mark_old(trans, as->btree_id, level, bkey_i_to_s_c(k), 0);
+		ret = bch2_key_trigger_old(trans, as->btree_id, level, bkey_i_to_s_c(k),
+					   BTREE_TRIGGER_TRANSACTIONAL);
 		if (ret)
 			return ret;
 	}
@@ -576,7 +577,8 @@ static int btree_update_nodes_written_trans(struct btree_trans *trans,
 	for_each_keylist_key(&as->new_keys, k) {
 		unsigned level = bkey_i_to_btree_ptr_v2(k)->v.mem_ptr;
 
-		ret = bch2_trans_mark_new(trans, as->btree_id, level, k, 0);
+		ret = bch2_key_trigger_new(trans, as->btree_id, level, bkey_i_to_s(k),
+					   BTREE_TRIGGER_TRANSACTIONAL);
 		if (ret)
 			return ret;
 	}
@@ -2156,13 +2158,12 @@ static int __bch2_btree_node_update_key(struct btree_trans *trans,
 	int ret;
 
 	if (!skip_triggers) {
-		ret = bch2_trans_mark_old(trans, b->c.btree_id, b->c.level + 1,
+		ret   = bch2_key_trigger_old(trans, b->c.btree_id, b->c.level + 1,
-					  bkey_i_to_s_c(&b->key), 0);
+					     bkey_i_to_s_c(&b->key),
-		if (ret)
+					     BTREE_TRIGGER_TRANSACTIONAL) ?:
-			return ret;
+			bch2_key_trigger_new(trans, b->c.btree_id, b->c.level + 1,
-
+					     bkey_i_to_s(new_key),
-		ret = bch2_trans_mark_new(trans, b->c.btree_id, b->c.level + 1,
+					     BTREE_TRIGGER_TRANSACTIONAL);
-					  new_key, 0);
 		if (ret)
 			return ret;
 	}

libbcachefs/buckets.h

@@ -302,6 +302,12 @@ u64 bch2_fs_sectors_used(struct bch_fs *, struct bch_fs_usage_online *);
 struct bch_fs_usage_short
 bch2_fs_usage_read_short(struct bch_fs *);
 
+void bch2_dev_usage_update(struct bch_fs *, struct bch_dev *,
+			   const struct bch_alloc_v4 *,
+			   const struct bch_alloc_v4 *, u64, bool);
+void bch2_dev_usage_update_m(struct bch_fs *, struct bch_dev *,
+			     struct bucket *, struct bucket *);
+
 /* key/bucket marking: */
 
 static inline struct bch_fs_usage *fs_usage_ptr(struct bch_fs *c,
@@ -316,6 +322,9 @@ static inline struct bch_fs_usage *fs_usage_ptr(struct bch_fs *c,
 			    : c->usage[journal_seq & JOURNAL_BUF_MASK]);
 }
 
+int bch2_update_replicas(struct bch_fs *, struct bkey_s_c,
+			 struct bch_replicas_entry_v1 *, s64,
+			 unsigned, bool);
 int bch2_update_replicas_list(struct btree_trans *,
 			 struct bch_replicas_entry_v1 *, s64);
 int bch2_update_cached_sectors_list(struct btree_trans *, unsigned, s64);
@@ -323,36 +332,30 @@ int bch2_replicas_deltas_realloc(struct btree_trans *, unsigned);
 
 void bch2_fs_usage_initialize(struct bch_fs *);
 
+int bch2_check_bucket_ref(struct btree_trans *, struct bkey_s_c,
+			  const struct bch_extent_ptr *,
+			  s64, enum bch_data_type, u8, u8, u32);
+
 int bch2_mark_metadata_bucket(struct bch_fs *, struct bch_dev *,
 			      size_t, enum bch_data_type, unsigned,
 			      struct gc_pos, unsigned);
 
-int bch2_mark_alloc(struct btree_trans *, enum btree_id, unsigned,
+int bch2_trigger_extent(struct btree_trans *, enum btree_id, unsigned,
-		    struct bkey_s_c, struct bkey_s_c, unsigned);
+			struct bkey_s_c, struct bkey_s, unsigned);
-int bch2_mark_extent(struct btree_trans *, enum btree_id, unsigned,
+int bch2_trigger_reservation(struct btree_trans *, enum btree_id, unsigned,
-		     struct bkey_s_c, struct bkey_s_c, unsigned);
+			  struct bkey_s_c, struct bkey_s, unsigned);
-int bch2_mark_stripe(struct btree_trans *, enum btree_id, unsigned,
-		     struct bkey_s_c, struct bkey_s_c, unsigned);
-int bch2_mark_reservation(struct btree_trans *, enum btree_id, unsigned,
-			  struct bkey_s_c, struct bkey_s_c, unsigned);
 
-int bch2_trans_mark_extent(struct btree_trans *, enum btree_id, unsigned, struct bkey_s_c, struct bkey_i *, unsigned);
+#define trigger_run_overwrite_then_insert(_fn, _trans, _btree_id, _level, _old, _new, _flags)\
-int bch2_trans_mark_stripe(struct btree_trans *, enum btree_id, unsigned, struct bkey_s_c, struct bkey_i *, unsigned);
-int bch2_trans_mark_reservation(struct btree_trans *, enum btree_id, unsigned, struct bkey_s_c, struct bkey_i *, unsigned);
-#define mem_trigger_run_overwrite_then_insert(_fn, _trans, _btree_id, _level, _old, _new, _flags)\
 ({												\
 	int ret = 0;										\
 												\
 	if (_old.k->type)									\
 		ret = _fn(_trans, _btree_id, _level, _old, _flags & ~BTREE_TRIGGER_INSERT);	\
 	if (!ret && _new.k->type)								\
-		ret = _fn(_trans, _btree_id, _level, _new, _flags & ~BTREE_TRIGGER_OVERWRITE);	\
+		ret = _fn(_trans, _btree_id, _level, _new.s_c, _flags & ~BTREE_TRIGGER_OVERWRITE);\
 	ret;											\
 })
 
-#define trigger_run_overwrite_then_insert(_fn, _trans, _btree_id, _level, _old, _new, _flags)	\
-	mem_trigger_run_overwrite_then_insert(_fn, _trans, _btree_id, _level, _old, bkey_i_to_s_c(_new), _flags)
-
 void bch2_trans_fs_usage_revert(struct btree_trans *, struct replicas_delta_list *);
 int bch2_trans_fs_usage_apply(struct btree_trans *, struct replicas_delta_list *);
 

libbcachefs/chardev.c

@@ -11,16 +11,13 @@
 #include "replicas.h"
 #include "super.h"
 #include "super-io.h"
+#include "thread_with_file.h"
 
-#include <linux/anon_inodes.h>
 #include <linux/cdev.h>
 #include <linux/device.h>
-#include <linux/file.h>
 #include <linux/fs.h>
 #include <linux/ioctl.h>
-#include <linux/kthread.h>
 #include <linux/major.h>
-#include <linux/poll.h>
 #include <linux/sched/task.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
@@ -31,65 +28,6 @@ static int copy_to_user_errcode(void __user *to, const void *from, unsigned long
 	return copy_to_user(to, from, n) ? -EFAULT : 0;
 }
 
-struct thread_with_file {
-	struct task_struct	*task;
-	int			ret;
-	bool			done;
-};
-
-static void thread_with_file_exit(struct thread_with_file *thr)
-{
-	if (thr->task) {
-		kthread_stop(thr->task);
-		put_task_struct(thr->task);
-	}
-}
-
-__printf(4, 0)
-static int run_thread_with_file(struct thread_with_file *thr,
-				const struct file_operations *fops,
-				int (*fn)(void *), const char *fmt, ...)
-{
-	va_list args;
-	struct file *file = NULL;
-	int ret, fd = -1;
-	struct printbuf name = PRINTBUF;
-	unsigned fd_flags = O_RDONLY|O_CLOEXEC|O_NONBLOCK;
-
-	va_start(args, fmt);
-	prt_vprintf(&name, fmt, args);
-	va_end(args);
-
-	thr->ret = 0;
-	thr->task = kthread_create(fn, thr, name.buf);
-	ret = PTR_ERR_OR_ZERO(thr->task);
-	if (ret)
-		goto err;
-
-	ret = get_unused_fd_flags(fd_flags);
-	if (ret < 0)
-		goto err_stop_task;
-	fd = ret;
-
-	file = anon_inode_getfile(name.buf, fops, thr, fd_flags);
-	ret = PTR_ERR_OR_ZERO(file);
-	if (ret)
-		goto err_put_fd;
-
-	fd_install(fd, file);
-	get_task_struct(thr->task);
-	wake_up_process(thr->task);
-	printbuf_exit(&name);
-	return fd;
-err_put_fd:
-	put_unused_fd(fd);
-err_stop_task:
-	kthread_stop(thr->task);
-err:
-	printbuf_exit(&name);
-	return ret;
-}
-
 /* returns with ref on ca->ref */
 static struct bch_dev *bch2_device_lookup(struct bch_fs *c, u64 dev,
 					  unsigned flags)
@@ -200,132 +138,33 @@ static long bch2_ioctl_incremental(struct bch_ioctl_incremental __user *user_arg
 #endif
 
 struct fsck_thread {
-	struct thread_with_file	thr;
+	struct thread_with_stdio thr;
-	struct printbuf		buf;
 	struct bch_fs		*c;
 	char			**devs;
 	size_t			nr_devs;
 	struct bch_opts		opts;
-
-	struct log_output	output;
-	DARRAY(char)		output2;
 };
 
-static void bch2_fsck_thread_free(struct fsck_thread *thr)
+static void bch2_fsck_thread_exit(struct thread_with_stdio *_thr)
 {
-	thread_with_file_exit(&thr->thr);
+	struct fsck_thread *thr = container_of(_thr, struct fsck_thread, thr);
 	if (thr->devs)
 		for (size_t i = 0; i < thr->nr_devs; i++)
 			kfree(thr->devs[i]);
-	darray_exit(&thr->output2);
-	printbuf_exit(&thr->output.buf);
 	kfree(thr->devs);
 	kfree(thr);
 }
 
-static int bch2_fsck_thread_release(struct inode *inode, struct file *file)
-{
-	struct fsck_thread *thr = container_of(file->private_data, struct fsck_thread, thr);
-
-	bch2_fsck_thread_free(thr);
-	return 0;
-}
-
-static bool fsck_thread_ready(struct fsck_thread *thr)
-{
-	return thr->output.buf.pos ||
-		thr->output2.nr ||
-		thr->thr.done;
-}
-
-static ssize_t bch2_fsck_thread_read(struct file *file, char __user *buf,
-				     size_t len, loff_t *ppos)
-{
-	struct fsck_thread *thr = container_of(file->private_data, struct fsck_thread, thr);
-	size_t copied = 0, b;
-	int ret = 0;
-
-	if ((file->f_flags & O_NONBLOCK) &&
-	    !fsck_thread_ready(thr))
-		return -EAGAIN;
-
-	ret = wait_event_interruptible(thr->output.wait,
-			fsck_thread_ready(thr));
-	if (ret)
-		return ret;
-
-	if (thr->thr.done)
-		return 0;
-
-	while (len) {
-		ret = darray_make_room(&thr->output2, thr->output.buf.pos);
-		if (ret)
-			break;
-
-		spin_lock_irq(&thr->output.lock);
-		b = min_t(size_t, darray_room(thr->output2), thr->output.buf.pos);
-
-		memcpy(&darray_top(thr->output2), thr->output.buf.buf, b);
-		memmove(thr->output.buf.buf,
-			thr->output.buf.buf + b,
-			thr->output.buf.pos - b);
-
-		thr->output2.nr += b;
-		thr->output.buf.pos -= b;
-		spin_unlock_irq(&thr->output.lock);
-
-		b = min(len, thr->output2.nr);
-		if (!b)
-			break;
-
-		b -= copy_to_user(buf, thr->output2.data, b);
-		if (!b) {
-			ret = -EFAULT;
-			break;
-		}
-
-		copied	+= b;
-		buf	+= b;
-		len	-= b;
-
-		memmove(thr->output2.data,
-			thr->output2.data + b,
-			thr->output2.nr - b);
-		thr->output2.nr -= b;
-	}
-
-	return copied ?: ret;
-}
-
-static __poll_t bch2_fsck_thread_poll(struct file *file, struct poll_table_struct *wait)
-{
-	struct fsck_thread *thr = container_of(file->private_data, struct fsck_thread, thr);
-
-	poll_wait(file, &thr->output.wait, wait);
-
-	return fsck_thread_ready(thr)
-		? EPOLLIN|EPOLLHUP
-		: 0;
-}
-
-static const struct file_operations fsck_thread_ops = {
-	.release	= bch2_fsck_thread_release,
-	.read		= bch2_fsck_thread_read,
-	.poll		= bch2_fsck_thread_poll,
-	.llseek		= no_llseek,
-};
-
 static int bch2_fsck_offline_thread_fn(void *arg)
 {
 	struct fsck_thread *thr = container_of(arg, struct fsck_thread, thr);
 	struct bch_fs *c = bch2_fs_open(thr->devs, thr->nr_devs, thr->opts);
 
-	thr->thr.ret = PTR_ERR_OR_ZERO(c);
+	thr->thr.thr.ret = PTR_ERR_OR_ZERO(c);
-	if (!thr->thr.ret)
+	if (!thr->thr.thr.ret)
 		bch2_fs_stop(c);
 
-	thr->thr.done = true;
+	thread_with_stdio_done(&thr->thr);
-	wake_up(&thr->output.wait);
 	return 0;
 }
 
@@ -354,11 +193,6 @@ static long bch2_ioctl_fsck_offline(struct bch_ioctl_fsck_offline __user *user_a
 
 	thr->opts = bch2_opts_empty();
 	thr->nr_devs = arg.nr_devs;
-	thr->output.buf	= PRINTBUF;
-	thr->output.buf.atomic++;
-	spin_lock_init(&thr->output.lock);
-	init_waitqueue_head(&thr->output.wait);
-	darray_init(&thr->output2);
 
 	if (copy_from_user(devs, &user_arg->devs[0],
 			   array_size(sizeof(user_arg->devs[0]), arg.nr_devs))) {
@@ -384,16 +218,15 @@ static long bch2_ioctl_fsck_offline(struct bch_ioctl_fsck_offline __user *user_a
 			goto err;
 	}
 
-	opt_set(thr->opts, log_output, (u64)(unsigned long)&thr->output);
+	opt_set(thr->opts, stdio, (u64)(unsigned long)&thr->thr.stdio);
 
-	ret = run_thread_with_file(&thr->thr,
+	ret = bch2_run_thread_with_stdio(&thr->thr,
-				   &fsck_thread_ops,
+			bch2_fsck_thread_exit,
-				   bch2_fsck_offline_thread_fn,
+			bch2_fsck_offline_thread_fn);
-				   "bch-fsck");
 err:
 	if (ret < 0) {
 		if (thr)
-			bch2_fsck_thread_free(thr);
+			bch2_fsck_thread_exit(&thr->thr);
 		pr_err("ret %s", bch2_err_str(ret));
 	}
 	kfree(devs);
@@ -592,7 +425,7 @@ static int bch2_data_job_release(struct inode *inode, struct file *file)
 {
 	struct bch_data_ctx *ctx = container_of(file->private_data, struct bch_data_ctx, thr);
 
-	thread_with_file_exit(&ctx->thr);
+	bch2_thread_with_file_exit(&ctx->thr);
 	kfree(ctx);
 	return 0;
 }
@@ -642,10 +475,9 @@ static long bch2_ioctl_data(struct bch_fs *c,
 	ctx->c = c;
 	ctx->arg = arg;
 
-	ret = run_thread_with_file(&ctx->thr,
+	ret = bch2_run_thread_with_file(&ctx->thr,
 			&bcachefs_data_ops,
-				   bch2_data_thread,
+			bch2_data_thread);
-				   "bch-data/%s", c->name);
 	if (ret < 0)
 		kfree(ctx);
 	return ret;
@@ -936,24 +768,32 @@ static int bch2_fsck_online_thread_fn(void *arg)
 	struct fsck_thread *thr = container_of(arg, struct fsck_thread, thr);
 	struct bch_fs *c = thr->c;
 
-	c->output_filter = current;
+	c->stdio_filter = current;
-	c->output = &thr->output;
+	c->stdio = &thr->thr.stdio;
 
 	/*
 	 * XXX: can we figure out a way to do this without mucking with c->opts?
 	 */
+	unsigned old_fix_errors = c->opts.fix_errors;
 	if (opt_defined(thr->opts, fix_errors))
 		c->opts.fix_errors = thr->opts.fix_errors;
+	else
+		c->opts.fix_errors = FSCK_FIX_ask;
+
 	c->opts.fsck = true;
+	set_bit(BCH_FS_fsck_running, &c->flags);
 
 	c->curr_recovery_pass = BCH_RECOVERY_PASS_check_alloc_info;
-	bch2_run_online_recovery_passes(c);
+	int ret = bch2_run_online_recovery_passes(c);
 
-	c->output = NULL;
+	clear_bit(BCH_FS_fsck_running, &c->flags);
-	c->output_filter = NULL;
+	bch_err_fn(c, ret);
 
-	thr->thr.done = true;
+	c->stdio = NULL;
-	wake_up(&thr->output.wait);
+	c->stdio_filter = NULL;
+	c->opts.fix_errors = old_fix_errors;
+
+	thread_with_stdio_done(&thr->thr);
 
 	up(&c->online_fsck_mutex);
 	bch2_ro_ref_put(c);
@@ -988,11 +828,6 @@ static long bch2_ioctl_fsck_online(struct bch_fs *c,
 
 	thr->c = c;
 	thr->opts = bch2_opts_empty();
-	thr->output.buf	= PRINTBUF;
-	thr->output.buf.atomic++;
-	spin_lock_init(&thr->output.lock);
-	init_waitqueue_head(&thr->output.wait);
-	darray_init(&thr->output2);
 
 	if (arg.opts) {
 		char *optstr = strndup_user((char __user *)(unsigned long) arg.opts, 1 << 16);
@@ -1005,15 +840,14 @@ static long bch2_ioctl_fsck_online(struct bch_fs *c,
 			goto err;
 	}
 
-	ret = run_thread_with_file(&thr->thr,
+	ret = bch2_run_thread_with_stdio(&thr->thr,
-				   &fsck_thread_ops,
+			bch2_fsck_thread_exit,
-				   bch2_fsck_online_thread_fn,
+			bch2_fsck_online_thread_fn);
-				   "bch-fsck");
 err:
 	if (ret < 0) {
 		bch_err_fn(c, ret);
 		if (thr)
-			bch2_fsck_thread_free(thr);
+			bch2_fsck_thread_exit(&thr->thr);
 		up(&c->online_fsck_mutex);
 		bch2_ro_ref_put(c);
 	}

libbcachefs/debug.c

@@ -627,7 +627,7 @@ restart:
 		prt_printf(&i->buf, "backtrace:");
 		prt_newline(&i->buf);
 		printbuf_indent_add(&i->buf, 2);
-		bch2_prt_task_backtrace(&i->buf, task);
+		bch2_prt_task_backtrace(&i->buf, task, 0);
 		printbuf_indent_sub(&i->buf, 2);
 		prt_newline(&i->buf);
 
@@ -930,8 +930,6 @@ void bch2_debug_exit(void)
 
 int __init bch2_debug_init(void)
 {
-	int ret = 0;
-
 	bch_debug = debugfs_create_dir("bcachefs", NULL);
-	return ret;
+	return 0;
 }

libbcachefs/disk_groups.c

@@ -557,7 +557,7 @@ void bch2_target_to_text(struct printbuf *out, struct bch_fs *c, unsigned v)
 			: NULL;
 
 		if (ca && percpu_ref_tryget(&ca->io_ref)) {
-			prt_printf(out, "/dev/%pg", ca->disk_sb.bdev);
+			prt_printf(out, "/dev/%s", ca->name);
 			percpu_ref_put(&ca->io_ref);
 		} else if (ca) {
 			prt_printf(out, "offline device %u", t.dev);

libbcachefs/ec.c

@@ -3,6 +3,7 @@
 /* erasure coding */
 
 #include "bcachefs.h"
+#include "alloc_background.h"
 #include "alloc_foreground.h"
 #include "backpointers.h"
 #include "bkey_buf.h"
@@ -156,6 +157,306 @@ void bch2_stripe_to_text(struct printbuf *out, struct bch_fs *c,
 	}
 }
 
+/* Triggers: */
+
+static int bch2_trans_mark_stripe_bucket(struct btree_trans *trans,
+					 struct bkey_s_c_stripe s,
+					 unsigned idx, bool deleting)
+{
+	struct bch_fs *c = trans->c;
+	const struct bch_extent_ptr *ptr = &s.v->ptrs[idx];
+	struct btree_iter iter;
+	struct bkey_i_alloc_v4 *a;
+	enum bch_data_type data_type = idx >= s.v->nr_blocks - s.v->nr_redundant
+		? BCH_DATA_parity : 0;
+	s64 sectors = data_type ? le16_to_cpu(s.v->sectors) : 0;
+	int ret = 0;
+
+	if (deleting)
+		sectors = -sectors;
+
+	a = bch2_trans_start_alloc_update(trans, &iter, PTR_BUCKET_POS(c, ptr));
+	if (IS_ERR(a))
+		return PTR_ERR(a);
+
+	ret = bch2_check_bucket_ref(trans, s.s_c, ptr, sectors, data_type,
+				    a->v.gen, a->v.data_type,
+				    a->v.dirty_sectors);
+	if (ret)
+		goto err;
+
+	if (!deleting) {
+		if (bch2_trans_inconsistent_on(a->v.stripe ||
+					       a->v.stripe_redundancy, trans,
+				"bucket %llu:%llu gen %u data type %s dirty_sectors %u: multiple stripes using same bucket (%u, %llu)",
+				iter.pos.inode, iter.pos.offset, a->v.gen,
+				bch2_data_types[a->v.data_type],
+				a->v.dirty_sectors,
+				a->v.stripe, s.k->p.offset)) {
+			ret = -EIO;
+			goto err;
+		}
+
+		if (bch2_trans_inconsistent_on(data_type && a->v.dirty_sectors, trans,
+				"bucket %llu:%llu gen %u data type %s dirty_sectors %u: data already in stripe bucket %llu",
+				iter.pos.inode, iter.pos.offset, a->v.gen,
+				bch2_data_types[a->v.data_type],
+				a->v.dirty_sectors,
+				s.k->p.offset)) {
+			ret = -EIO;
+			goto err;
+		}
+
+		a->v.stripe		= s.k->p.offset;
+		a->v.stripe_redundancy	= s.v->nr_redundant;
+		a->v.data_type		= BCH_DATA_stripe;
+	} else {
+		if (bch2_trans_inconsistent_on(a->v.stripe != s.k->p.offset ||
+					       a->v.stripe_redundancy != s.v->nr_redundant, trans,
+				"bucket %llu:%llu gen %u: not marked as stripe when deleting stripe %llu (got %u)",
+				iter.pos.inode, iter.pos.offset, a->v.gen,
+				s.k->p.offset, a->v.stripe)) {
+			ret = -EIO;
+			goto err;
+		}
+
+		a->v.stripe		= 0;
+		a->v.stripe_redundancy	= 0;
+		a->v.data_type		= alloc_data_type(a->v, BCH_DATA_user);
+	}
+
+	a->v.dirty_sectors += sectors;
+	if (data_type)
+		a->v.data_type = !deleting ? data_type : 0;
+
+	ret = bch2_trans_update(trans, &iter, &a->k_i, 0);
+	if (ret)
+		goto err;
+err:
+	bch2_trans_iter_exit(trans, &iter);
+	return ret;
+}
+
+static int mark_stripe_bucket(struct btree_trans *trans,
+			      struct bkey_s_c k,
+			      unsigned ptr_idx,
+			      unsigned flags)
+{
+	struct bch_fs *c = trans->c;
+	const struct bch_stripe *s = bkey_s_c_to_stripe(k).v;
+	unsigned nr_data = s->nr_blocks - s->nr_redundant;
+	bool parity = ptr_idx >= nr_data;
+	enum bch_data_type data_type = parity ? BCH_DATA_parity : BCH_DATA_stripe;
+	s64 sectors = parity ? le16_to_cpu(s->sectors) : 0;
+	const struct bch_extent_ptr *ptr = s->ptrs + ptr_idx;
+	struct bch_dev *ca = bch_dev_bkey_exists(c, ptr->dev);
+	struct bucket old, new, *g;
+	struct printbuf buf = PRINTBUF;
+	int ret = 0;
+
+	BUG_ON(!(flags & BTREE_TRIGGER_GC));
+
+	/* * XXX doesn't handle deletion */
+
+	percpu_down_read(&c->mark_lock);
+	g = PTR_GC_BUCKET(ca, ptr);
+
+	if (g->dirty_sectors ||
+	    (g->stripe && g->stripe != k.k->p.offset)) {
+		bch2_fs_inconsistent(c,
+			      "bucket %u:%zu gen %u: multiple stripes using same bucket\n%s",
+			      ptr->dev, PTR_BUCKET_NR(ca, ptr), g->gen,
+			      (bch2_bkey_val_to_text(&buf, c, k), buf.buf));
+		ret = -EINVAL;
+		goto err;
+	}
+
+	bucket_lock(g);
+	old = *g;
+
+	ret = bch2_check_bucket_ref(trans, k, ptr, sectors, data_type,
+				    g->gen, g->data_type,
+				    g->dirty_sectors);
+	if (ret)
+		goto err;
+
+	g->data_type = data_type;
+	g->dirty_sectors += sectors;
+
+	g->stripe		= k.k->p.offset;
+	g->stripe_redundancy	= s->nr_redundant;
+	new = *g;
+err:
+	bucket_unlock(g);
+	if (!ret)
+		bch2_dev_usage_update_m(c, ca, &old, &new);
+	percpu_up_read(&c->mark_lock);
+	printbuf_exit(&buf);
+	return ret;
+}
+
+int bch2_trigger_stripe(struct btree_trans *trans,
+			enum btree_id btree_id, unsigned level,
+			struct bkey_s_c old, struct bkey_s _new,
+			unsigned flags)
+{
+	struct bkey_s_c new = _new.s_c;
+	struct bch_fs *c = trans->c;
+	u64 idx = new.k->p.offset;
+	const struct bch_stripe *old_s = old.k->type == KEY_TYPE_stripe
+		? bkey_s_c_to_stripe(old).v : NULL;
+	const struct bch_stripe *new_s = new.k->type == KEY_TYPE_stripe
+		? bkey_s_c_to_stripe(new).v : NULL;
+
+	if (flags & BTREE_TRIGGER_TRANSACTIONAL) {
+		/*
+		 * If the pointers aren't changing, we don't need to do anything:
+		 */
+		if (new_s && old_s &&
+		    new_s->nr_blocks	== old_s->nr_blocks &&
+		    new_s->nr_redundant	== old_s->nr_redundant &&
+		    !memcmp(old_s->ptrs, new_s->ptrs,
+			    new_s->nr_blocks * sizeof(struct bch_extent_ptr)))
+			return 0;
+
+		BUG_ON(new_s && old_s &&
+		       (new_s->nr_blocks	!= old_s->nr_blocks ||
+			new_s->nr_redundant	!= old_s->nr_redundant));
+
+		if (new_s) {
+			s64 sectors = le16_to_cpu(new_s->sectors);
+
+			struct bch_replicas_padded r;
+			bch2_bkey_to_replicas(&r.e, new);
+			int ret = bch2_update_replicas_list(trans, &r.e, sectors * new_s->nr_redundant);
+			if (ret)
+				return ret;
+		}
+
+		if (old_s) {
+			s64 sectors = -((s64) le16_to_cpu(old_s->sectors));
+
+			struct bch_replicas_padded r;
+			bch2_bkey_to_replicas(&r.e, old);
+			int ret = bch2_update_replicas_list(trans, &r.e, sectors * old_s->nr_redundant);
+			if (ret)
+				return ret;
+		}
+
+		unsigned nr_blocks = new_s ? new_s->nr_blocks : old_s->nr_blocks;
+		for (unsigned i = 0; i < nr_blocks; i++) {
+			if (new_s && old_s &&
+			    !memcmp(&new_s->ptrs[i],
+				    &old_s->ptrs[i],
+				    sizeof(new_s->ptrs[i])))
+				continue;
+
+			if (new_s) {
+				int ret = bch2_trans_mark_stripe_bucket(trans,
+						bkey_s_c_to_stripe(new), i, false);
+				if (ret)
+					return ret;
+			}
+
+			if (old_s) {
+				int ret = bch2_trans_mark_stripe_bucket(trans,
+						bkey_s_c_to_stripe(old), i, true);
+				if (ret)
+					return ret;
+			}
+		}
+	}
+
+	if (!(flags & (BTREE_TRIGGER_TRANSACTIONAL|BTREE_TRIGGER_GC))) {
+		struct stripe *m = genradix_ptr(&c->stripes, idx);
+
+		if (!m) {
+			struct printbuf buf1 = PRINTBUF;
+			struct printbuf buf2 = PRINTBUF;
+
+			bch2_bkey_val_to_text(&buf1, c, old);
+			bch2_bkey_val_to_text(&buf2, c, new);
+			bch_err_ratelimited(c, "error marking nonexistent stripe %llu while marking\n"
+					    "old %s\n"
+					    "new %s", idx, buf1.buf, buf2.buf);
+			printbuf_exit(&buf2);
+			printbuf_exit(&buf1);
+			bch2_inconsistent_error(c);
+			return -1;
+		}
+
+		if (!new_s) {
+			bch2_stripes_heap_del(c, m, idx);
+
+			memset(m, 0, sizeof(*m));
+		} else {
+			m->sectors	= le16_to_cpu(new_s->sectors);
+			m->algorithm	= new_s->algorithm;
+			m->nr_blocks	= new_s->nr_blocks;
+			m->nr_redundant	= new_s->nr_redundant;
+			m->blocks_nonempty = 0;
+
+			for (unsigned i = 0; i < new_s->nr_blocks; i++)
+				m->blocks_nonempty += !!stripe_blockcount_get(new_s, i);
+
+			if (!old_s)
+				bch2_stripes_heap_insert(c, m, idx);
+			else
+				bch2_stripes_heap_update(c, m, idx);
+		}
+	}
+
+	if (flags & BTREE_TRIGGER_GC) {
+		struct gc_stripe *m =
+			genradix_ptr_alloc(&c->gc_stripes, idx, GFP_KERNEL);
+
+		if (!m) {
+			bch_err(c, "error allocating memory for gc_stripes, idx %llu",
+				idx);
+			return -BCH_ERR_ENOMEM_mark_stripe;
+		}
+		/*
+		 * This will be wrong when we bring back runtime gc: we should
+		 * be unmarking the old key and then marking the new key
+		 */
+		m->alive	= true;
+		m->sectors	= le16_to_cpu(new_s->sectors);
+		m->nr_blocks	= new_s->nr_blocks;
+		m->nr_redundant	= new_s->nr_redundant;
+
+		for (unsigned i = 0; i < new_s->nr_blocks; i++)
+			m->ptrs[i] = new_s->ptrs[i];
+
+		bch2_bkey_to_replicas(&m->r.e, new);
+
+		/*
+		 * gc recalculates this field from stripe ptr
+		 * references:
+		 */
+		memset(m->block_sectors, 0, sizeof(m->block_sectors));
+
+		for (unsigned i = 0; i < new_s->nr_blocks; i++) {
+			int ret = mark_stripe_bucket(trans, new, i, flags);
+			if (ret)
+				return ret;
+		}
+
+		int ret = bch2_update_replicas(c, new, &m->r.e,
+				      ((s64) m->sectors * m->nr_redundant),
+				      0, true);
+		if (ret) {
+			struct printbuf buf = PRINTBUF;
+
+			bch2_bkey_val_to_text(&buf, c, new);
+			bch2_fs_fatal_error(c, "no replicas entry for %s", buf.buf);
+			printbuf_exit(&buf);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
 /* returns blocknr in stripe that we matched: */
 static const struct bch_extent_ptr *bkey_matches_stripe(struct bch_stripe *s,
 						struct bkey_s_c k, unsigned *block)

libbcachefs/ec.h

@@ -12,13 +12,14 @@ int bch2_stripe_invalid(struct bch_fs *, struct bkey_s_c,
 			enum bkey_invalid_flags, struct printbuf *);
 void bch2_stripe_to_text(struct printbuf *, struct bch_fs *,
 			 struct bkey_s_c);
+int bch2_trigger_stripe(struct btree_trans *, enum btree_id, unsigned,
+			struct bkey_s_c, struct bkey_s, unsigned);
 
 #define bch2_bkey_ops_stripe ((struct bkey_ops) {	\
 	.key_invalid	= bch2_stripe_invalid,		\
 	.val_to_text	= bch2_stripe_to_text,		\
 	.swab		= bch2_ptr_swab,		\
-	.trans_trigger	= bch2_trans_mark_stripe,	\
+	.trigger	= bch2_trigger_stripe,		\
-	.atomic_trigger	= bch2_mark_stripe,		\
 	.min_val_size	= 8,				\
 })
 

libbcachefs/error.c

@@ -2,6 +2,7 @@
 #include "bcachefs.h"
 #include "error.h"
 #include "super.h"
+#include "thread_with_file.h"
 
 #define FSCK_ERR_RATELIMIT_NR	10
 
@@ -27,7 +28,7 @@ bool bch2_inconsistent_error(struct bch_fs *c)
 void bch2_topology_error(struct bch_fs *c)
 {
 	set_bit(BCH_FS_topology_error, &c->flags);
-	if (test_bit(BCH_FS_fsck_done, &c->flags))
+	if (!test_bit(BCH_FS_fsck_running, &c->flags))
 		bch2_inconsistent_error(c);
 }
 
@@ -69,29 +70,11 @@ enum ask_yn {
 	YN_ALLYES,
 };
 
-#ifdef __KERNEL__
+static enum ask_yn parse_yn_response(char *buf)
-#define bch2_fsck_ask_yn()	YN_NO
-#else
-
-#include "tools-util.h"
-
-enum ask_yn bch2_fsck_ask_yn(void)
 {
-	char *buf = NULL;
+	buf = strim(buf);
-	size_t buflen = 0;
-	bool ret;
-
-	while (true) {
-		fputs(" (y,n, or Y,N for all errors of this type) ", stdout);
-		fflush(stdout);
-
-		if (getline(&buf, &buflen, stdin) < 0)
-			die("error reading from standard input");
-
-		strim(buf);
-		if (strlen(buf) != 1)
-			continue;
 
+	if (strlen(buf) == 1)
 		switch (buf[0]) {
 		case 'n':
 			return YN_NO;
@@ -102,7 +85,51 @@ enum ask_yn bch2_fsck_ask_yn(void)
 		case 'Y':
 			return YN_ALLYES;
 		}
-	}
+	return -1;
+}
+
+#ifdef __KERNEL__
+static enum ask_yn bch2_fsck_ask_yn(struct bch_fs *c)
+{
+	struct stdio_redirect *stdio = c->stdio;
+
+	if (c->stdio_filter && c->stdio_filter != current)
+		stdio = NULL;
+
+	if (!stdio)
+		return YN_NO;
+
+	char buf[100];
+	int ret;
+
+	do {
+		bch2_print(c, " (y,n, or Y,N for all errors of this type) ");
+
+		int r = bch2_stdio_redirect_readline(stdio, buf, sizeof(buf) - 1);
+		if (r < 0)
+			return YN_NO;
+		buf[r] = '\0';
+	} while ((ret = parse_yn_response(buf)) < 0);
+
+	return ret;
+}
+#else
+
+#include "tools-util.h"
+
+static enum ask_yn bch2_fsck_ask_yn(struct bch_fs *c)
+{
+	char *buf = NULL;
+	size_t buflen = 0;
+	int ret;
+
+	do {
+		fputs(" (y,n, or Y,N for all errors of this type) ", stdout);
+		fflush(stdout);
+
+		if (getline(&buf, &buflen, stdin) < 0)
+			die("error reading from standard input");
+	} while ((ret = parse_yn_response(buf)) < 0);
 
 	free(buf);
 	return ret;
@@ -114,7 +141,7 @@ static struct fsck_err_state *fsck_err_get(struct bch_fs *c, const char *fmt)
 {
 	struct fsck_err_state *s;
 
-	if (test_bit(BCH_FS_fsck_done, &c->flags))
+	if (!test_bit(BCH_FS_fsck_running, &c->flags))
 		return NULL;
 
 	list_for_each_entry(s, &c->fsck_error_msgs, list)
@@ -152,7 +179,8 @@ int bch2_fsck_err(struct bch_fs *c,
 	struct printbuf buf = PRINTBUF, *out = &buf;
 	int ret = -BCH_ERR_fsck_ignore;
 
-	if (test_bit(err, c->sb.errors_silent))
+	if ((flags & FSCK_CAN_FIX) &&
+	    test_bit(err, c->sb.errors_silent))
 		return -BCH_ERR_fsck_fix;
 
 	bch2_sb_error_count(c, err);
@@ -196,7 +224,7 @@ int bch2_fsck_err(struct bch_fs *c,
 		prt_printf(out, bch2_log_msg(c, ""));
 #endif
 
-	if (test_bit(BCH_FS_fsck_done, &c->flags)) {
+	if (!test_bit(BCH_FS_fsck_running, &c->flags)) {
 		if (c->opts.errors != BCH_ON_ERROR_continue ||
 		    !(flags & (FSCK_CAN_FIX|FSCK_CAN_IGNORE))) {
 			prt_str(out, ", shutting down");
@@ -221,10 +249,13 @@ int bch2_fsck_err(struct bch_fs *c,
 			int ask;
 
 			prt_str(out, ": fix?");
+			if (bch2_fs_stdio_redirect(c))
+				bch2_print(c, "%s", out->buf);
+			else
 				bch2_print_string_as_lines(KERN_ERR, out->buf);
 			print = false;
 
-			ask = bch2_fsck_ask_yn();
+			ask = bch2_fsck_ask_yn(c);
 
 			if (ask >= YN_ALLNO && s)
 				s->fix = ask == YN_ALLNO
@@ -253,10 +284,14 @@ int bch2_fsck_err(struct bch_fs *c,
 	     !(flags & FSCK_CAN_IGNORE)))
 		ret = -BCH_ERR_fsck_errors_not_fixed;
 
-	if (print)
+	if (print) {
+		if (bch2_fs_stdio_redirect(c))
+			bch2_print(c, "%s\n", out->buf);
+		else
 			bch2_print_string_as_lines(KERN_ERR, out->buf);
+	}
 
-	if (!test_bit(BCH_FS_fsck_done, &c->flags) &&
+	if (test_bit(BCH_FS_fsck_running, &c->flags) &&
 	    (ret != -BCH_ERR_fsck_fix &&
 	     ret != -BCH_ERR_fsck_ignore))
 		bch_err(c, "Unable to continue, halting");

libbcachefs/extents.h

@@ -415,8 +415,7 @@ void bch2_btree_ptr_v2_compat(enum btree_id, unsigned, unsigned,
 	.key_invalid	= bch2_btree_ptr_invalid,		\
 	.val_to_text	= bch2_btree_ptr_to_text,		\
 	.swab		= bch2_ptr_swab,			\
-	.trans_trigger	= bch2_trans_mark_extent,		\
+	.trigger	= bch2_trigger_extent,			\
-	.atomic_trigger	= bch2_mark_extent,			\
 })
 
 #define bch2_bkey_ops_btree_ptr_v2 ((struct bkey_ops) {		\
@@ -424,8 +423,7 @@ void bch2_btree_ptr_v2_compat(enum btree_id, unsigned, unsigned,
 	.val_to_text	= bch2_btree_ptr_v2_to_text,		\
 	.swab		= bch2_ptr_swab,			\
 	.compat		= bch2_btree_ptr_v2_compat,		\
-	.trans_trigger	= bch2_trans_mark_extent,		\
+	.trigger	= bch2_trigger_extent,			\
-	.atomic_trigger	= bch2_mark_extent,			\
 	.min_val_size	= 40,					\
 })
 
@@ -439,8 +437,7 @@ bool bch2_extent_merge(struct bch_fs *, struct bkey_s, struct bkey_s_c);
 	.swab		= bch2_ptr_swab,			\
 	.key_normalize	= bch2_extent_normalize,		\
 	.key_merge	= bch2_extent_merge,			\
-	.trans_trigger	= bch2_trans_mark_extent,		\
+	.trigger	= bch2_trigger_extent,			\
-	.atomic_trigger	= bch2_mark_extent,			\
 })
 
 /* KEY_TYPE_reservation: */
@@ -454,8 +451,7 @@ bool bch2_reservation_merge(struct bch_fs *, struct bkey_s, struct bkey_s_c);
 	.key_invalid	= bch2_reservation_invalid,		\
 	.val_to_text	= bch2_reservation_to_text,		\
 	.key_merge	= bch2_reservation_merge,		\
-	.trans_trigger	= bch2_trans_mark_reservation,		\
+	.trigger	= bch2_trigger_reservation,		\
-	.atomic_trigger	= bch2_mark_reservation,		\
 	.min_val_size	= 8,					\
 })
 

libbcachefs/fs-common.c

@@ -166,11 +166,9 @@ int bch2_create_trans(struct btree_trans *trans,
 		if (ret)
 			goto err;
 
-		if (c->sb.version >= bcachefs_metadata_version_inode_backpointers) {
 		new_inode->bi_dir		= dir_u->bi_inum;
 		new_inode->bi_dir_offset	= dir_offset;
 	}
-	}
 
 	inode_iter.flags &= ~BTREE_ITER_ALL_SNAPSHOTS;
 	bch2_btree_iter_set_snapshot(&inode_iter, snapshot);
@@ -228,10 +226,8 @@ int bch2_link_trans(struct btree_trans *trans,
 	if (ret)
 		goto err;
 
-	if (c->sb.version >= bcachefs_metadata_version_inode_backpointers) {
 	inode_u->bi_dir		= dir.inum;
 	inode_u->bi_dir_offset	= dir_offset;
-	}
 
 	ret =   bch2_inode_write(trans, &dir_iter, dir_u) ?:
 		bch2_inode_write(trans, &inode_iter, inode_u);
@@ -414,7 +410,6 @@ int bch2_rename_trans(struct btree_trans *trans,
 			goto err;
 	}
 
-	if (c->sb.version >= bcachefs_metadata_version_inode_backpointers) {
 	src_inode_u->bi_dir		= dst_dir_u->bi_inum;
 	src_inode_u->bi_dir_offset	= dst_offset;
 
@@ -429,7 +424,6 @@ int bch2_rename_trans(struct btree_trans *trans,
 		dst_inode_u->bi_dir		= 0;
 		dst_inode_u->bi_dir_offset	= 0;
 	}
-	}
 
 	if (mode == BCH_RENAME_OVERWRITE) {
 		if (S_ISDIR(src_inode_u->bi_mode) !=

libbcachefs/fs-io.c

@@ -194,6 +194,16 @@ int bch2_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	struct bch_fs *c = inode->v.i_sb->s_fs_info;
 	int ret;
 
+	/*
+	 * check if unlinked, disable/defer until relink
+	 */
+
+	/*
+	 * also: add a mode where a file is a tmpfile until fully,
+	 * asynchronously written
+	 */
+
+
 	ret = file_write_and_wait_range(file, start, end);
 	if (ret)
 		goto out;

libbcachefs/fsck.c

@@ -870,8 +870,7 @@ static int check_inode(struct btree_trans *trans,
 		return 0;
 	}
 
-	if (u.bi_flags & BCH_INODE_unlinked &&
+	if (u.bi_flags & BCH_INODE_unlinked) {
-	    c->sb.version >= bcachefs_metadata_version_deleted_inodes) {
 		ret = check_inode_deleted_list(trans, k.k->p);
 		if (ret < 0)
 			return ret;
@@ -1594,13 +1593,12 @@ static int check_dirent_target(struct btree_trans *trans,
 		d = dirent_i_to_s_c(n);
 	}
 
-	if (d.v->d_type == DT_SUBVOL &&
+	if (fsck_err_on(d.v->d_type == DT_SUBVOL &&
-	    target->bi_parent_subvol != le32_to_cpu(d.v->d_parent_subvol) &&
+			target->bi_parent_subvol != le32_to_cpu(d.v->d_parent_subvol),
-	    (c->sb.version < bcachefs_metadata_version_subvol_dirent ||
+			c, dirent_d_parent_subvol_wrong,
-	     fsck_err(c, dirent_d_parent_subvol_wrong,
 			"dirent has wrong d_parent_subvol field: got %u, should be %u",
 			le32_to_cpu(d.v->d_parent_subvol),
-		      target->bi_parent_subvol))) {
+			target->bi_parent_subvol)) {
 		n = bch2_trans_kmalloc(trans, bkey_bytes(d.k));
 		ret = PTR_ERR_OR_ZERO(n);
 		if (ret)

libbcachefs/inode.c

@@ -561,64 +561,46 @@ static inline bool bkey_is_deleted_inode(struct bkey_s_c k)
 	return bkey_inode_flags(k) & BCH_INODE_unlinked;
 }
 
-int bch2_trans_mark_inode(struct btree_trans *trans,
+int bch2_trigger_inode(struct btree_trans *trans,
 		       enum btree_id btree_id, unsigned level,
 		       struct bkey_s_c old,
-			  struct bkey_i *new,
+		       struct bkey_s new,
 		       unsigned flags)
 {
-	int nr = bkey_is_inode(&new->k) - bkey_is_inode(old.k);
+	s64 nr = bkey_is_inode(new.k) - bkey_is_inode(old.k);
-	bool old_deleted = bkey_is_deleted_inode(old);
-	bool new_deleted = bkey_is_deleted_inode(bkey_i_to_s_c(new));
 
+	if (flags & BTREE_TRIGGER_TRANSACTIONAL) {
 		if (nr) {
 			int ret = bch2_replicas_deltas_realloc(trans, 0);
-		struct replicas_delta_list *d = trans->fs_usage_deltas;
-
 			if (ret)
 				return ret;
 
-		d->nr_inodes += nr;
+			trans->fs_usage_deltas->nr_inodes += nr;
 		}
 
+		bool old_deleted = bkey_is_deleted_inode(old);
+		bool new_deleted = bkey_is_deleted_inode(new.s_c);
 		if (old_deleted != new_deleted) {
-		int ret = bch2_btree_bit_mod(trans, BTREE_ID_deleted_inodes, new->k.p, new_deleted);
+			int ret = bch2_btree_bit_mod(trans, BTREE_ID_deleted_inodes, new.k->p, new_deleted);
 			if (ret)
 				return ret;
 		}
+	}
 
-	return 0;
+	if (!(flags & BTREE_TRIGGER_TRANSACTIONAL) && (flags & BTREE_TRIGGER_INSERT)) {
-}
+		BUG_ON(!trans->journal_res.seq);
 
-int bch2_mark_inode(struct btree_trans *trans,
+		bkey_s_to_inode_v3(new).v->bi_journal_seq = cpu_to_le64(trans->journal_res.seq);
-		    enum btree_id btree_id, unsigned level,
-		    struct bkey_s_c old, struct bkey_s_c new,
-		    unsigned flags)
-{
-	struct bch_fs *c = trans->c;
-	struct bch_fs_usage *fs_usage;
-	u64 journal_seq = trans->journal_res.seq;
-
-	if (flags & BTREE_TRIGGER_INSERT) {
-		struct bch_inode_v3 *v = (struct bch_inode_v3 *) new.v;
-
-		BUG_ON(!journal_seq);
-		BUG_ON(new.k->type != KEY_TYPE_inode_v3);
-
-		v->bi_journal_seq = cpu_to_le64(journal_seq);
 	}
 
 	if (flags & BTREE_TRIGGER_GC) {
+		struct bch_fs *c = trans->c;
+
 		percpu_down_read(&c->mark_lock);
-		preempt_disable();
+		this_cpu_add(c->usage_gc->nr_inodes, nr);
-
-		fs_usage = fs_usage_ptr(c, journal_seq, flags & BTREE_TRIGGER_GC);
-		fs_usage->nr_inodes += bkey_is_inode(new.k);
-		fs_usage->nr_inodes -= bkey_is_inode(old.k);
-
-		preempt_enable();
 		percpu_up_read(&c->mark_lock);
 	}
+
 	return 0;
 }
 

libbcachefs/inode.h

@@ -17,32 +17,27 @@ int bch2_inode_v3_invalid(struct bch_fs *, struct bkey_s_c,
 			  enum bkey_invalid_flags, struct printbuf *);
 void bch2_inode_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c);
 
-int bch2_trans_mark_inode(struct btree_trans *, enum btree_id, unsigned,
+int bch2_trigger_inode(struct btree_trans *, enum btree_id, unsigned,
-			  struct bkey_s_c, struct bkey_i *, unsigned);
+			  struct bkey_s_c, struct bkey_s, unsigned);
-int bch2_mark_inode(struct btree_trans *, enum btree_id, unsigned,
-		    struct bkey_s_c, struct bkey_s_c, unsigned);
 
 #define bch2_bkey_ops_inode ((struct bkey_ops) {	\
 	.key_invalid	= bch2_inode_invalid,		\
 	.val_to_text	= bch2_inode_to_text,		\
-	.trans_trigger	= bch2_trans_mark_inode,	\
+	.trigger	= bch2_trigger_inode,		\
-	.atomic_trigger	= bch2_mark_inode,		\
 	.min_val_size	= 16,				\
 })
 
 #define bch2_bkey_ops_inode_v2 ((struct bkey_ops) {	\
 	.key_invalid	= bch2_inode_v2_invalid,	\
 	.val_to_text	= bch2_inode_to_text,		\
-	.trans_trigger	= bch2_trans_mark_inode,	\
+	.trigger	= bch2_trigger_inode,		\
-	.atomic_trigger	= bch2_mark_inode,		\
 	.min_val_size	= 32,				\
 })
 
 #define bch2_bkey_ops_inode_v3 ((struct bkey_ops) {	\
 	.key_invalid	= bch2_inode_v3_invalid,	\
 	.val_to_text	= bch2_inode_to_text,		\
-	.trans_trigger	= bch2_trans_mark_inode,	\
+	.trigger	= bch2_trigger_inode,		\
-	.atomic_trigger	= bch2_mark_inode,		\
 	.min_val_size	= 48,				\
 })
 

libbcachefs/opts.h

@@ -414,11 +414,11 @@ enum fsck_err_opts {
 	  OPT_BOOL(),							\
 	  BCH2_NO_SB_OPT,		false,				\
 	  NULL,		"Allocate the buckets_nouse bitmap")		\
-	x(log_output,			u64,				\
+	x(stdio,			u64,				\
 	  0,								\
 	  OPT_UINT(0, S64_MAX),						\
 	  BCH2_NO_SB_OPT,		false,				\
-	  NULL,		"Pointer to a struct log_output")		\
+	  NULL,		"Pointer to a struct stdio_redirect")		\
 	x(project,			u8,				\
 	  OPT_INODE,							\
 	  OPT_BOOL(),							\
@@ -458,7 +458,13 @@ enum fsck_err_opts {
 	  OPT_UINT(0, BCH_REPLICAS_MAX),				\
 	  BCH2_NO_SB_OPT,		1,				\
 	  "n",		"Data written to this device will be considered\n"\
-			"to have already been replicated n times")
+			"to have already been replicated n times")	\
+	x(btree_node_prefetch,		u8,				\
+	  OPT_FS|OPT_MOUNT|OPT_RUNTIME,					\
+	  OPT_BOOL(),							\
+	  BCH2_NO_SB_OPT,		true,				\
+	  NULL,		"BTREE_ITER_PREFETCH casuse btree nodes to be\n"\
+	  " prefetched sequentially")
 
 struct bch_opts {
 #define x(_name, _bits, ...)	unsigned _name##_defined:1;

libbcachefs/printbuf.c

@@ -1,8 +1,8 @@
 // SPDX-License-Identifier: LGPL-2.1+
 /* Copyright (C) 2022 Kent Overstreet */
 
-#include <linux/err.h>
 #include <linux/bitmap.h>
+#include <linux/err.h>
 #include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>

libbcachefs/recovery.c

@@ -575,7 +575,7 @@ u64 bch2_recovery_passes_from_stable(u64 v)
 	return ret;
 }
 
-static u64 check_version_upgrade(struct bch_fs *c)
+static bool check_version_upgrade(struct bch_fs *c)
 {
 	unsigned latest_compatible = bch2_latest_compatible_version(c->sb.version);
 	unsigned latest_version	= bcachefs_metadata_version_current;
@@ -624,10 +624,15 @@ static u64 check_version_upgrade(struct bch_fs *c)
 		bch2_version_to_text(&buf, new_version);
 		prt_newline(&buf);
 
-		u64 recovery_passes = bch2_upgrade_recovery_passes(c, old_version, new_version);
+		struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext);
-		if (recovery_passes) {
+		__le64 passes = ext->recovery_passes_required[0];
+		bch2_sb_set_upgrade(c, old_version, new_version);
+		passes = ext->recovery_passes_required[0] & ~passes;
+
+		if (passes) {
 			prt_str(&buf, "  running recovery passes: ");
-			prt_bitflags(&buf, bch2_recovery_passes, recovery_passes);
+			prt_bitflags(&buf, bch2_recovery_passes,
+				     bch2_recovery_passes_from_stable(le64_to_cpu(passes)));
 		}
 
 		bch_info(c, "%s", buf.buf);
@@ -635,10 +640,6 @@ static u64 check_version_upgrade(struct bch_fs *c)
 		bch2_sb_upgrade(c, new_version);
 
 		printbuf_exit(&buf);
-
-		struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext);
-		ext->recovery_passes_required[0] |=
-			cpu_to_le64(bch2_recovery_passes_to_stable(recovery_passes));
 		return true;
 	}
 
@@ -795,23 +796,17 @@ int bch2_fs_recovery(struct bch_fs *c)
 			prt_bitflags(&buf, bch2_recovery_passes, sb_passes);
 			bch_info(c, "%s", buf.buf);
 			printbuf_exit(&buf);
-			c->recovery_passes_explicit |= sb_passes;
 		}
 
-		if (bcachefs_metadata_version_current < c->sb.version) {
+		if (bch2_check_version_downgrade(c)) {
 			struct printbuf buf = PRINTBUF;
 
 			prt_str(&buf, "Version downgrade required:\n");
 
-			u64 passes = ext->recovery_passes_required[0];
+			__le64 passes = ext->recovery_passes_required[0];
-			ret = bch2_sb_set_downgrade(c,
+			bch2_sb_set_downgrade(c,
 					BCH_VERSION_MINOR(bcachefs_metadata_version_current),
 					BCH_VERSION_MINOR(c->sb.version));
-			if (ret) {
-				mutex_unlock(&c->sb_lock);
-				goto err;
-			}
-
 			passes = ext->recovery_passes_required[0] & ~passes;
 			if (passes) {
 				prt_str(&buf, "  running recovery passes: ");
@@ -821,8 +816,6 @@ int bch2_fs_recovery(struct bch_fs *c)
 
 			bch_info(c, "%s", buf.buf);
 			printbuf_exit(&buf);
-
-			bch2_sb_maybe_downgrade(c);
 			write_sb = true;
 		}
 
@@ -839,6 +832,9 @@ int bch2_fs_recovery(struct bch_fs *c)
 	if (c->opts.fsck && IS_ENABLED(CONFIG_BCACHEFS_DEBUG))
 		c->recovery_passes_explicit |= BIT_ULL(BCH_RECOVERY_PASS_check_topology);
 
+	if (c->opts.fsck)
+		set_bit(BCH_FS_fsck_running, &c->flags);
+
 	ret = bch2_blacklist_table_initialize(c);
 	if (ret) {
 		bch_err(c, "error initializing blacklist table");
@@ -979,6 +975,8 @@ use_clean:
 	if (ret)
 		goto err;
 
+	clear_bit(BCH_FS_fsck_running, &c->flags);
+
 	/* If we fixed errors, verify that fs is actually clean now: */
 	if (IS_ENABLED(CONFIG_BCACHEFS_DEBUG) &&
 	    test_bit(BCH_FS_errors_fixed, &c->flags) &&
@@ -1073,7 +1071,6 @@ use_clean:
 
 	ret = 0;
 out:
-	set_bit(BCH_FS_fsck_done, &c->flags);
 	bch2_flush_fsck_errs(c);
 
 	if (!c->opts.keep_journal &&
@@ -1109,7 +1106,7 @@ int bch2_fs_initialize(struct bch_fs *c)
 	c->disk_sb.sb->compat[0] |= cpu_to_le64(1ULL << BCH_COMPAT_extents_above_btree_updates_done);
 	c->disk_sb.sb->compat[0] |= cpu_to_le64(1ULL << BCH_COMPAT_bformat_overflow_done);
 
-	bch2_sb_maybe_downgrade(c);
+	bch2_check_version_downgrade(c);
 
 	if (c->opts.version_upgrade != BCH_VERSION_UPGRADE_none) {
 		bch2_sb_upgrade(c, bcachefs_metadata_version_current);
@@ -1120,7 +1117,6 @@ int bch2_fs_initialize(struct bch_fs *c)
 
 	c->curr_recovery_pass = ARRAY_SIZE(recovery_pass_fns);
 	set_bit(BCH_FS_may_go_rw, &c->flags);
-	set_bit(BCH_FS_fsck_done, &c->flags);
 
 	for (unsigned i = 0; i < BTREE_ID_NR; i++)
 		bch2_btree_root_alloc(c, i);

libbcachefs/reflink.c

@@ -34,15 +34,14 @@ int bch2_reflink_p_invalid(struct bch_fs *c, struct bkey_s_c k,
 			   struct printbuf *err)
 {
 	struct bkey_s_c_reflink_p p = bkey_s_c_to_reflink_p(k);
+	int ret = 0;
 
-	if (c->sb.version >= bcachefs_metadata_version_reflink_p_fix &&
+	bkey_fsck_err_on(le64_to_cpu(p.v->idx) < le32_to_cpu(p.v->front_pad),
-	    le64_to_cpu(p.v->idx) < le32_to_cpu(p.v->front_pad)) {
+			 c, err, reflink_p_front_pad_bad,
-		prt_printf(err, "idx < front_pad (%llu < %u)",
+			 "idx < front_pad (%llu < %u)",
 			 le64_to_cpu(p.v->idx), le32_to_cpu(p.v->front_pad));
-		return -EINVAL;
+fsck_err:
-	}
+	return ret;
-
-	return 0;
 }
 
 void bch2_reflink_p_to_text(struct printbuf *out, struct bch_fs *c,
@@ -74,7 +73,7 @@ bool bch2_reflink_p_merge(struct bch_fs *c, struct bkey_s _l, struct bkey_s_c _r
 	return true;
 }
 
-static int trans_mark_reflink_p_segment(struct btree_trans *trans,
+static int trans_trigger_reflink_p_segment(struct btree_trans *trans,
 			struct bkey_s_c_reflink_p p,
 			u64 *idx, unsigned flags)
 {
@@ -93,7 +92,7 @@ static int trans_mark_reflink_p_segment(struct btree_trans *trans,
 	if (ret)
 		goto err;
 
-	refcount = bkey_refcount(k);
+	refcount = bkey_refcount(bkey_i_to_s(k));
 	if (!refcount) {
 		bch2_bkey_val_to_text(&buf, c, p.s_c);
 		bch2_trans_inconsistent(trans,
@@ -141,47 +140,16 @@ err:
 	return ret;
 }
 
-static int __trans_mark_reflink_p(struct btree_trans *trans,
+static s64 gc_trigger_reflink_p_segment(struct btree_trans *trans,
-				enum btree_id btree_id, unsigned level,
-				struct bkey_s_c k, unsigned flags)
-{
-	struct bkey_s_c_reflink_p p = bkey_s_c_to_reflink_p(k);
-	u64 idx, end_idx;
-	int ret = 0;
-
-	idx	= le64_to_cpu(p.v->idx) - le32_to_cpu(p.v->front_pad);
-	end_idx = le64_to_cpu(p.v->idx) + p.k->size +
-		le32_to_cpu(p.v->back_pad);
-
-	while (idx < end_idx && !ret)
-		ret = trans_mark_reflink_p_segment(trans, p, &idx, flags);
-	return ret;
-}
-
-int bch2_trans_mark_reflink_p(struct btree_trans *trans,
-			      enum btree_id btree_id, unsigned level,
-			      struct bkey_s_c old,
-			      struct bkey_i *new,
-			      unsigned flags)
-{
-	if (flags & BTREE_TRIGGER_INSERT) {
-		struct bch_reflink_p *v = &bkey_i_to_reflink_p(new)->v;
-
-		v->front_pad = v->back_pad = 0;
-	}
-
-	return trigger_run_overwrite_then_insert(__trans_mark_reflink_p, trans, btree_id, level, old, new, flags);
-}
-
-static s64 __bch2_mark_reflink_p(struct btree_trans *trans,
 				struct bkey_s_c_reflink_p p,
-				 u64 start, u64 end,
 				u64 *idx, unsigned flags, size_t r_idx)
 {
 	struct bch_fs *c = trans->c;
 	struct reflink_gc *r;
 	int add = !(flags & BTREE_TRIGGER_OVERWRITE) ? 1 : -1;
-	u64 next_idx = end;
+	u64 start = le64_to_cpu(p.v->idx);
+	u64 end = le64_to_cpu(p.v->idx) + p.k->size;
+	u64 next_idx = end + le32_to_cpu(p.v->back_pad);
 	s64 ret = 0;
 	struct printbuf buf = PRINTBUF;
 
@@ -205,20 +173,24 @@ not_found:
 		     "  missing range %llu-%llu",
 		     (bch2_bkey_val_to_text(&buf, c, p.s_c), buf.buf),
 		     *idx, next_idx)) {
-		struct bkey_i_error *new;
+		struct bkey_i *update = bch2_bkey_make_mut_noupdate(trans, p.s_c);
-
+		ret = PTR_ERR_OR_ZERO(update);
-		new = bch2_trans_kmalloc(trans, sizeof(*new));
-		ret = PTR_ERR_OR_ZERO(new);
 		if (ret)
 			goto err;
 
-		bkey_init(&new->k);
+		if (next_idx <= start) {
-		new->k.type	= KEY_TYPE_error;
+			bkey_i_to_reflink_p(update)->v.front_pad = cpu_to_le32(start - next_idx);
-		new->k.p		= bkey_start_pos(p.k);
+		} else if (*idx >= end) {
-		new->k.p.offset += *idx - start;
+			bkey_i_to_reflink_p(update)->v.back_pad = cpu_to_le32(*idx - end);
-		bch2_key_resize(&new->k, next_idx - *idx);
+		} else {
-		ret = bch2_btree_insert_trans(trans, BTREE_ID_extents, &new->k_i,
+			bkey_error_init(update);
-					  BTREE_TRIGGER_NORUN);
+			update->k.p		= p.k->p;
+			update->k.p.offset	= next_idx;
+			update->k.size		= next_idx - *idx;
+			set_bkey_val_u64s(&update->k, 0);
+		}
+
+		ret = bch2_btree_insert_trans(trans, BTREE_ID_extents, update, BTREE_TRIGGER_NORUN);
 	}
 
 	*idx = next_idx;
@@ -228,31 +200,28 @@ fsck_err:
 	return ret;
 }
 
-static int __mark_reflink_p(struct btree_trans *trans,
+static int __trigger_reflink_p(struct btree_trans *trans,
 			    enum btree_id btree_id, unsigned level,
 			    struct bkey_s_c k, unsigned flags)
 {
 	struct bch_fs *c = trans->c;
 	struct bkey_s_c_reflink_p p = bkey_s_c_to_reflink_p(k);
-	struct reflink_gc *ref;
-	size_t l, r, m;
-	u64 idx = le64_to_cpu(p.v->idx), start = idx;
-	u64 end = le64_to_cpu(p.v->idx) + p.k->size;
 	int ret = 0;
 
-	BUG_ON(!(flags & BTREE_TRIGGER_GC));
+	u64 idx = le64_to_cpu(p.v->idx) - le32_to_cpu(p.v->front_pad);
+	u64 end = le64_to_cpu(p.v->idx) + p.k->size + le32_to_cpu(p.v->back_pad);
 
-	if (c->sb.version_upgrade_complete >= bcachefs_metadata_version_reflink_p_fix) {
+	if (flags & BTREE_TRIGGER_TRANSACTIONAL) {
-		idx -= le32_to_cpu(p.v->front_pad);
+		while (idx < end && !ret)
-		end += le32_to_cpu(p.v->back_pad);
+			ret = trans_trigger_reflink_p_segment(trans, p, &idx, flags);
 	}
 
-	l = 0;
+	if (flags & BTREE_TRIGGER_GC) {
-	r = c->reflink_gc_nr;
+		size_t l = 0, r = c->reflink_gc_nr;
-	while (l < r) {
-		m = l + (r - l) / 2;
 
-		ref = genradix_ptr(&c->reflink_gc_table, m);
+		while (l < r) {
+			size_t m = l + (r - l) / 2;
+			struct reflink_gc *ref = genradix_ptr(&c->reflink_gc_table, m);
 			if (ref->offset <= idx)
 				l = m + 1;
 			else
@@ -260,18 +229,26 @@ static int __mark_reflink_p(struct btree_trans *trans,
 		}
 
 		while (idx < end && !ret)
-		ret = __bch2_mark_reflink_p(trans, p, start, end,
+			ret = gc_trigger_reflink_p_segment(trans, p, &idx, flags, l++);
-					    &idx, flags, l++);
+	}
 
 	return ret;
 }
 
-int bch2_mark_reflink_p(struct btree_trans *trans,
+int bch2_trigger_reflink_p(struct btree_trans *trans,
 			   enum btree_id btree_id, unsigned level,
-			struct bkey_s_c old, struct bkey_s_c new,
+			   struct bkey_s_c old,
+			   struct bkey_s new,
 			   unsigned flags)
 {
-	return mem_trigger_run_overwrite_then_insert(__mark_reflink_p, trans, btree_id, level, old, new, flags);
+	if ((flags & BTREE_TRIGGER_TRANSACTIONAL) &&
+	    (flags & BTREE_TRIGGER_INSERT)) {
+		struct bch_reflink_p *v = bkey_s_to_reflink_p(new).v;
+
+		v->front_pad = v->back_pad = 0;
+	}
+
+	return trigger_run_overwrite_then_insert(__trigger_reflink_p, trans, btree_id, level, old, new, flags);
 }
 
 /* indirect extents */
@@ -305,32 +282,34 @@ bool bch2_reflink_v_merge(struct bch_fs *c, struct bkey_s _l, struct bkey_s_c _r
 }
 #endif
 
-static inline void check_indirect_extent_deleting(struct bkey_i *new, unsigned *flags)
+static inline void check_indirect_extent_deleting(struct bkey_s new, unsigned *flags)
 {
 	if ((*flags & BTREE_TRIGGER_INSERT) && !*bkey_refcount(new)) {
-		new->k.type = KEY_TYPE_deleted;
+		new.k->type = KEY_TYPE_deleted;
-		new->k.size = 0;
+		new.k->size = 0;
-		set_bkey_val_u64s(&new->k, 0);
+		set_bkey_val_u64s(new.k, 0);
 		*flags &= ~BTREE_TRIGGER_INSERT;
 	}
 }
 
 int bch2_trans_mark_reflink_v(struct btree_trans *trans,
 			      enum btree_id btree_id, unsigned level,
-			      struct bkey_s_c old, struct bkey_i *new,
+			      struct bkey_s_c old, struct bkey_s new,
 			      unsigned flags)
 {
+	if ((flags & BTREE_TRIGGER_TRANSACTIONAL) &&
+	    (flags & BTREE_TRIGGER_INSERT))
 		check_indirect_extent_deleting(new, &flags);
 
 	if (old.k->type == KEY_TYPE_reflink_v &&
-	    new->k.type == KEY_TYPE_reflink_v &&
+	    new.k->type == KEY_TYPE_reflink_v &&
-	    old.k->u64s == new->k.u64s &&
+	    old.k->u64s == new.k->u64s &&
 	    !memcmp(bkey_s_c_to_reflink_v(old).v->start,
-		    bkey_i_to_reflink_v(new)->v.start,
+		    bkey_s_to_reflink_v(new).v->start,
-		    bkey_val_bytes(&new->k) - 8))
+		    bkey_val_bytes(new.k) - 8))
 		return 0;
 
-	return bch2_trans_mark_extent(trans, btree_id, level, old, new, flags);
+	return bch2_trigger_extent(trans, btree_id, level, old, new, flags);
 }
 
 /* indirect inline data */
@@ -355,7 +334,7 @@ void bch2_indirect_inline_data_to_text(struct printbuf *out,
 
 int bch2_trans_mark_indirect_inline_data(struct btree_trans *trans,
 			      enum btree_id btree_id, unsigned level,
-			      struct bkey_s_c old, struct bkey_i *new,
+			      struct bkey_s_c old, struct bkey_s new,
 			      unsigned flags)
 {
 	check_indirect_extent_deleting(new, &flags);
@@ -398,7 +377,7 @@ static int bch2_make_extent_indirect(struct btree_trans *trans,
 
 	set_bkey_val_bytes(&r_v->k, sizeof(__le64) + bkey_val_bytes(&orig->k));
 
-	refcount	= bkey_refcount(r_v);
+	refcount	= bkey_refcount(bkey_i_to_s(r_v));
 	*refcount	= 0;
 	memcpy(refcount + 1, &orig->v, bkey_val_bytes(&orig->k));
 

libbcachefs/reflink.h

@@ -9,17 +9,14 @@ int bch2_reflink_p_invalid(struct bch_fs *, struct bkey_s_c,
 void bch2_reflink_p_to_text(struct printbuf *, struct bch_fs *,
 			    struct bkey_s_c);
 bool bch2_reflink_p_merge(struct bch_fs *, struct bkey_s, struct bkey_s_c);
-int bch2_trans_mark_reflink_p(struct btree_trans *, enum btree_id, unsigned,
+int bch2_trigger_reflink_p(struct btree_trans *, enum btree_id, unsigned,
-			      struct bkey_s_c, struct bkey_i *, unsigned);
+			   struct bkey_s_c, struct bkey_s, unsigned);
-int bch2_mark_reflink_p(struct btree_trans *, enum btree_id, unsigned,
-			struct bkey_s_c, struct bkey_s_c, unsigned);
 
 #define bch2_bkey_ops_reflink_p ((struct bkey_ops) {		\
 	.key_invalid	= bch2_reflink_p_invalid,		\
 	.val_to_text	= bch2_reflink_p_to_text,		\
 	.key_merge	= bch2_reflink_p_merge,			\
-	.trans_trigger	= bch2_trans_mark_reflink_p,		\
+	.trigger	= bch2_trigger_reflink_p,		\
-	.atomic_trigger	= bch2_mark_reflink_p,			\
 	.min_val_size	= 16,					\
 })
 
@@ -28,14 +25,13 @@ int bch2_reflink_v_invalid(struct bch_fs *, struct bkey_s_c,
 void bch2_reflink_v_to_text(struct printbuf *, struct bch_fs *,
 			    struct bkey_s_c);
 int bch2_trans_mark_reflink_v(struct btree_trans *, enum btree_id, unsigned,
-			      struct bkey_s_c, struct bkey_i *, unsigned);
+			      struct bkey_s_c, struct bkey_s, unsigned);
 
 #define bch2_bkey_ops_reflink_v ((struct bkey_ops) {		\
 	.key_invalid	= bch2_reflink_v_invalid,		\
 	.val_to_text	= bch2_reflink_v_to_text,		\
 	.swab		= bch2_ptr_swab,			\
-	.trans_trigger	= bch2_trans_mark_reflink_v,		\
+	.trigger	= bch2_trans_mark_reflink_v,		\
-	.atomic_trigger	= bch2_mark_extent,			\
 	.min_val_size	= 8,					\
 })
 
@@ -45,13 +41,13 @@ void bch2_indirect_inline_data_to_text(struct printbuf *,
 				struct bch_fs *, struct bkey_s_c);
 int bch2_trans_mark_indirect_inline_data(struct btree_trans *,
 					 enum btree_id, unsigned,
-			      struct bkey_s_c, struct bkey_i *,
+			      struct bkey_s_c, struct bkey_s,
 			      unsigned);
 
 #define bch2_bkey_ops_indirect_inline_data ((struct bkey_ops) {	\
 	.key_invalid	= bch2_indirect_inline_data_invalid,	\
 	.val_to_text	= bch2_indirect_inline_data_to_text,	\
-	.trans_trigger	= bch2_trans_mark_indirect_inline_data,	\
+	.trigger	= bch2_trans_mark_indirect_inline_data,	\
 	.min_val_size	= 8,					\
 })
 
@@ -67,13 +63,13 @@ static inline const __le64 *bkey_refcount_c(struct bkey_s_c k)
 	}
 }
 
-static inline __le64 *bkey_refcount(struct bkey_i *k)
+static inline __le64 *bkey_refcount(struct bkey_s k)
 {
-	switch (k->k.type) {
+	switch (k.k->type) {
 	case KEY_TYPE_reflink_v:
-		return &bkey_i_to_reflink_v(k)->v.refcount;
+		return &bkey_s_to_reflink_v(k).v->refcount;
 	case KEY_TYPE_indirect_inline_data:
-		return &bkey_i_to_indirect_inline_data(k)->v.refcount;
+		return &bkey_s_to_indirect_inline_data(k).v->refcount;
 	default:
 		return NULL;
 	}

libbcachefs/sb-downgrade.c

@@ -12,36 +12,105 @@
 #include "sb-errors.h"
 #include "super-io.h"
 
+#define RECOVERY_PASS_ALL_FSCK		BIT_ULL(63)
+
 /*
- * Downgrade table:
+ * Upgrade, downgrade tables - run certain recovery passes, fix certain errors
- * When dowgrading past certain versions, we need to run certain recovery passes
- * and fix certain errors:
  *
  * x(version, recovery_passes, errors...)
  */
+#define UPGRADE_TABLE()						\
+	x(backpointers,						\
+	  RECOVERY_PASS_ALL_FSCK)				\
+	x(inode_v3,						\
+	  RECOVERY_PASS_ALL_FSCK)				\
+	x(unwritten_extents,					\
+	  RECOVERY_PASS_ALL_FSCK)				\
+	x(bucket_gens,						\
+	  BIT_ULL(BCH_RECOVERY_PASS_bucket_gens_init)|		\
+	  RECOVERY_PASS_ALL_FSCK)				\
+	x(lru_v2,						\
+	  RECOVERY_PASS_ALL_FSCK)				\
+	x(fragmentation_lru,					\
+	  RECOVERY_PASS_ALL_FSCK)				\
+	x(no_bps_in_alloc_keys,					\
+	  RECOVERY_PASS_ALL_FSCK)				\
+	x(snapshot_trees,					\
+	  RECOVERY_PASS_ALL_FSCK)				\
+	x(snapshot_skiplists,					\
+	  BIT_ULL(BCH_RECOVERY_PASS_check_snapshots),		\
+	  BCH_FSCK_ERR_snapshot_bad_depth,			\
+	  BCH_FSCK_ERR_snapshot_bad_skiplist)			\
+	x(deleted_inodes,					\
+	  BIT_ULL(BCH_RECOVERY_PASS_check_inodes),		\
+	  BCH_FSCK_ERR_unlinked_inode_not_on_deleted_list)	\
+	x(rebalance_work,					\
+	  BIT_ULL(BCH_RECOVERY_PASS_set_fs_needs_rebalance))
 
-#define DOWNGRADE_TABLE()					\
+#define DOWNGRADE_TABLE()
-	x(disk_accounting_v2,					\
-	  BIT_ULL(BCH_RECOVERY_PASS_check_alloc_info),		\
-	  BCH_FSCK_ERR_dev_usage_buckets_wrong)
 
-struct downgrade_entry {
+struct upgrade_downgrade_entry {
 	u64		recovery_passes;
 	u16		version;
 	u16		nr_errors;
 	const u16	*errors;
 };
 
-#define x(ver, passes, ...) static const u16 ver_##errors[] = { __VA_ARGS__ };
+#define x(ver, passes, ...) static const u16 upgrade_##ver##_errors[] = { __VA_ARGS__ };
-DOWNGRADE_TABLE()
+UPGRADE_TABLE()
 #undef x
 
-static const struct downgrade_entry downgrade_table[] = {
+static const struct upgrade_downgrade_entry upgrade_table[] = {
 #define x(ver, passes, ...) {					\
 	.recovery_passes	= passes,			\
 	.version		= bcachefs_metadata_version_##ver,\
-	.nr_errors		= ARRAY_SIZE(ver_##errors),	\
+	.nr_errors		= ARRAY_SIZE(upgrade_##ver##_errors),	\
-	.errors			= ver_##errors,			\
+	.errors			= upgrade_##ver##_errors,	\
+},
+UPGRADE_TABLE()
+#undef x
+};
+
+void bch2_sb_set_upgrade(struct bch_fs *c,
+			 unsigned old_version,
+			 unsigned new_version)
+{
+	lockdep_assert_held(&c->sb_lock);
+
+	struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext);
+
+	for (const struct upgrade_downgrade_entry *i = upgrade_table;
+	     i < upgrade_table + ARRAY_SIZE(upgrade_table);
+	     i++)
+		if (i->version > old_version && i->version <= new_version) {
+			u64 passes = i->recovery_passes;
+
+			if (passes & RECOVERY_PASS_ALL_FSCK)
+				passes |= bch2_fsck_recovery_passes();
+			passes &= ~RECOVERY_PASS_ALL_FSCK;
+
+			ext->recovery_passes_required[0] |=
+				cpu_to_le64(bch2_recovery_passes_to_stable(passes));
+
+			for (const u16 *e = i->errors;
+			     e < i->errors + i->nr_errors;
+			     e++) {
+				__set_bit(*e, c->sb.errors_silent);
+				ext->errors_silent[*e / 64] |= cpu_to_le64(BIT_ULL(*e % 64));
+			}
+		}
+}
+
+#define x(ver, passes, ...) static const u16 downgrade_ver_##errors[] = { __VA_ARGS__ };
+DOWNGRADE_TABLE()
+#undef x
+
+static const struct upgrade_downgrade_entry downgrade_table[] = {
+#define x(ver, passes, ...) {					\
+	.recovery_passes	= passes,			\
+	.version		= bcachefs_metadata_version_##ver,\
+	.nr_errors		= ARRAY_SIZE(downgrade_##ver##_errors),	\
+	.errors			= downgrade_##ver##_errors,	\
 },
 DOWNGRADE_TABLE()
 #undef x
@@ -59,12 +128,6 @@ downgrade_entry_next_c(const struct bch_sb_field_downgrade_entry *e)
 	     (void *) &_i->errors[0] < vstruct_end(&(_d)->field);			\
 	     _i = downgrade_entry_next_c(_i))
 
-static inline unsigned bch2_sb_field_downgrade_u64s(unsigned nr)
-{
-	return (sizeof(struct bch_sb_field_downgrade) +
-		sizeof(struct bch_sb_field_downgrade_entry) * nr) / sizeof(u64);
-}
-
 static int bch2_sb_downgrade_validate(struct bch_sb *sb, struct bch_sb_field *f,
 				      struct printbuf *err)
 {
@@ -127,7 +190,7 @@ int bch2_sb_downgrade_update(struct bch_fs *c)
 	darray_char table = {};
 	int ret = 0;
 
-	for (const struct downgrade_entry *src = downgrade_table;
+	for (const struct upgrade_downgrade_entry *src = downgrade_table;
 	     src < downgrade_table + ARRAY_SIZE(downgrade_table);
 	     src++) {
 		if (BCH_VERSION_MAJOR(src->version) != BCH_VERSION_MAJOR(le16_to_cpu(c->disk_sb.sb->version)))
@@ -171,11 +234,11 @@ out:
 	return ret;
 }
 
-int bch2_sb_set_downgrade(struct bch_fs *c, unsigned new_minor, unsigned old_minor)
+void bch2_sb_set_downgrade(struct bch_fs *c, unsigned new_minor, unsigned old_minor)
 {
 	struct bch_sb_field_downgrade *d = bch2_sb_field_get(c->disk_sb.sb, downgrade);
 	if (!d)
-		return 0;
+		return;
 
 	struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext);
 
@@ -194,6 +257,4 @@ int bch2_sb_set_downgrade(struct bch_fs *c, unsigned new_minor, unsigned old_min
 			}
 		}
 	}
-
-	return 0;
 }

libbcachefs/sb-downgrade.h

@@ -5,6 +5,7 @@
 extern const struct bch_sb_field_ops bch_sb_field_ops_downgrade;
 
 int bch2_sb_downgrade_update(struct bch_fs *);
-int bch2_sb_set_downgrade(struct bch_fs *, unsigned, unsigned);
+void bch2_sb_set_upgrade(struct bch_fs *, unsigned, unsigned);
+void bch2_sb_set_downgrade(struct bch_fs *, unsigned, unsigned);
 
 #endif /* _BCACHEFS_SB_DOWNGRADE_H */

libbcachefs/sb-errors_types.h

@@ -249,7 +249,8 @@
 	x(dir_loop,						241)	\
 	x(hash_table_key_duplicate,				242)	\
 	x(hash_table_key_wrong_offset,				243)	\
-	x(unlinked_inode_not_on_deleted_list,			244)
+	x(unlinked_inode_not_on_deleted_list,			244)	\
+	x(reflink_p_front_pad_bad,				245)
 
 enum bch_sb_error_id {
 #define x(t, n) BCH_FSCK_ERR_##t = n,

libbcachefs/sb-members.c

@@ -266,7 +266,7 @@ static void member_to_text(struct printbuf *out,
 
 	prt_str(out, "Durability:");
 	prt_tab(out);
-	prt_printf(out, "%llu", BCH_MEMBER_DURABILITY(&m));
+	prt_printf(out, "%llu", BCH_MEMBER_DURABILITY(&m) ? BCH_MEMBER_DURABILITY(&m) - 1 : 1);
 	prt_newline(out);
 
 	prt_printf(out, "Discard:");

libbcachefs/snapshot.c

@@ -276,7 +276,7 @@ static void set_is_ancestor_bitmap(struct bch_fs *c, u32 id)
 	mutex_unlock(&c->snapshot_table_lock);
 }
 
-int bch2_mark_snapshot(struct btree_trans *trans,
+static int __bch2_mark_snapshot(struct btree_trans *trans,
 		       enum btree_id btree, unsigned level,
 		       struct bkey_s_c old, struct bkey_s_c new,
 		       unsigned flags)
@@ -330,6 +330,14 @@ err:
 	return ret;
 }
 
+int bch2_mark_snapshot(struct btree_trans *trans,
+		       enum btree_id btree, unsigned level,
+		       struct bkey_s_c old, struct bkey_s new,
+		       unsigned flags)
+{
+	return __bch2_mark_snapshot(trans, btree, level, old, new.s_c, flags);
+}
+
 int bch2_snapshot_lookup(struct btree_trans *trans, u32 id,
 			 struct bch_snapshot *s)
 {
@@ -806,11 +814,10 @@ static int check_snapshot(struct btree_trans *trans,
 
 	real_depth = bch2_snapshot_depth(c, parent_id);
 
-	if (le32_to_cpu(s.depth) != real_depth &&
+	if (fsck_err_on(le32_to_cpu(s.depth) != real_depth,
-	    (c->sb.version_upgrade_complete < bcachefs_metadata_version_snapshot_skiplists ||
+			c, snapshot_bad_depth,
-	     fsck_err(c, snapshot_bad_depth,
 			"snapshot with incorrect depth field, should be %u:\n  %s",
-		      real_depth, (bch2_bkey_val_to_text(&buf, c, k), buf.buf)))) {
+			real_depth, (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) {
 		u = bch2_bkey_make_mut_typed(trans, iter, &k, 0, snapshot);
 		ret = PTR_ERR_OR_ZERO(u);
 		if (ret)
@@ -824,11 +831,9 @@ static int check_snapshot(struct btree_trans *trans,
 	if (ret < 0)
 		goto err;
 
-	if (!ret &&
+	if (fsck_err_on(!ret, c, snapshot_bad_skiplist,
-	    (c->sb.version_upgrade_complete < bcachefs_metadata_version_snapshot_skiplists ||
-	     fsck_err(c, snapshot_bad_skiplist,
 			"snapshot with bad skiplist field:\n  %s",
-		      (bch2_bkey_val_to_text(&buf, c, k), buf.buf)))) {
+			(bch2_bkey_val_to_text(&buf, c, k), buf.buf))) {
 		u = bch2_bkey_make_mut_typed(trans, iter, &k, 0, snapshot);
 		ret = PTR_ERR_OR_ZERO(u);
 		if (ret)
@@ -1055,7 +1060,7 @@ static int create_snapids(struct btree_trans *trans, u32 parent, u32 tree,
 		bubble_sort(n->v.skip, ARRAY_SIZE(n->v.skip), cmp_le32);
 		SET_BCH_SNAPSHOT_SUBVOL(&n->v, true);
 
-		ret = bch2_mark_snapshot(trans, BTREE_ID_snapshots, 0,
+		ret = __bch2_mark_snapshot(trans, BTREE_ID_snapshots, 0,
 					 bkey_s_c_null, bkey_i_to_s_c(&n->k_i), 0);
 		if (ret)
 			goto err;
@@ -1664,7 +1669,7 @@ int bch2_snapshots_read(struct bch_fs *c)
 	int ret = bch2_trans_run(c,
 		for_each_btree_key(trans, iter, BTREE_ID_snapshots,
 				   POS_MIN, 0, k,
-			bch2_mark_snapshot(trans, BTREE_ID_snapshots, 0, bkey_s_c_null, k, 0) ?:
+			__bch2_mark_snapshot(trans, BTREE_ID_snapshots, 0, bkey_s_c_null, k, 0) ?:
 			bch2_snapshot_set_equiv(trans, k) ?:
 			bch2_check_snapshot_needs_deletion(trans, k)) ?:
 		for_each_btree_key(trans, iter, BTREE_ID_snapshots,

libbcachefs/snapshot.h

@@ -22,12 +22,12 @@ void bch2_snapshot_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c);
 int bch2_snapshot_invalid(struct bch_fs *, struct bkey_s_c,
 			  enum bkey_invalid_flags, struct printbuf *);
 int bch2_mark_snapshot(struct btree_trans *, enum btree_id, unsigned,
-		       struct bkey_s_c, struct bkey_s_c, unsigned);
+		       struct bkey_s_c, struct bkey_s, unsigned);
 
 #define bch2_bkey_ops_snapshot ((struct bkey_ops) {		\
 	.key_invalid	= bch2_snapshot_invalid,		\
 	.val_to_text	= bch2_snapshot_to_text,		\
-	.atomic_trigger	= bch2_mark_snapshot,			\
+	.trigger	= bch2_mark_snapshot,			\
 	.min_val_size	= 24,					\
 })
 

libbcachefs/super-io.c

@@ -30,14 +30,12 @@ static const struct blk_holder_ops bch2_sb_handle_bdev_ops = {
 struct bch2_metadata_version {
 	u16		version;
 	const char	*name;
-	u64		recovery_passes;
 };
 
 static const struct bch2_metadata_version bch2_metadata_versions[] = {
-#define x(n, v, _recovery_passes) {		\
+#define x(n, v) {		\
 	.version = v,				\
 	.name = #n,				\
-	.recovery_passes = _recovery_passes,	\
 },
 	BCH_METADATA_VERSIONS()
 #undef x
@@ -70,24 +68,6 @@ unsigned bch2_latest_compatible_version(unsigned v)
 	return v;
 }
 
-u64 bch2_upgrade_recovery_passes(struct bch_fs *c,
-				 unsigned old_version,
-				 unsigned new_version)
-{
-	u64 ret = 0;
-
-	for (const struct bch2_metadata_version *i = bch2_metadata_versions;
-	     i < bch2_metadata_versions + ARRAY_SIZE(bch2_metadata_versions);
-	     i++)
-		if (i->version > old_version && i->version <= new_version) {
-			if (i->recovery_passes & RECOVERY_PASS_ALL_FSCK)
-				ret |= bch2_fsck_recovery_passes();
-			ret |= i->recovery_passes;
-		}
-
-	return ret &= ~RECOVERY_PASS_ALL_FSCK;
-}
-
 const char * const bch2_sb_fields[] = {
 #define x(name, nr)	#name,
 	BCH_SB_FIELDS()
@@ -190,8 +170,12 @@ int bch2_sb_realloc(struct bch_sb_handle *sb, unsigned u64s)
 		u64 max_bytes = 512 << sb->sb->layout.sb_max_size_bits;
 
 		if (new_bytes > max_bytes) {
-			pr_err("%pg: superblock too big: want %zu but have %llu",
+			struct printbuf buf = PRINTBUF;
-			       sb->bdev, new_bytes, max_bytes);
+
+			prt_bdevname(&buf, sb->bdev);
+			prt_printf(&buf, ": superblock too big: want %zu but have %llu", new_bytes, max_bytes);
+			pr_err("%s", buf.buf);
+			printbuf_exit(&buf);
 			return -BCH_ERR_ENOSPC_sb;
 		}
 	}
@@ -1095,8 +1079,10 @@ void __bch2_check_set_feature(struct bch_fs *c, unsigned feat)
 }
 
 /* Downgrade if superblock is at a higher version than currently supported: */
-void bch2_sb_maybe_downgrade(struct bch_fs *c)
+bool bch2_check_version_downgrade(struct bch_fs *c)
 {
+	bool ret = bcachefs_metadata_version_current < c->sb.version;
+
 	lockdep_assert_held(&c->sb_lock);
 
 	/*
@@ -1110,6 +1096,7 @@ void bch2_sb_maybe_downgrade(struct bch_fs *c)
 	if (c->sb.version_min > bcachefs_metadata_version_current)
 		c->disk_sb.sb->version_min = cpu_to_le16(bcachefs_metadata_version_current);
 	c->disk_sb.sb->compat[0] &= cpu_to_le64((1ULL << BCH_COMPAT_NR) - 1);
+	return ret;
 }
 
 void bch2_sb_upgrade(struct bch_fs *c, unsigned new_version)
@@ -1200,7 +1187,7 @@ static int bch2_sb_field_validate(struct bch_sb *sb, struct bch_sb_field *f,
 	return ret;
 }
 
-void bch2_sb_field_to_text(struct printbuf *out, struct bch_sb *sb,
+void __bch2_sb_field_to_text(struct printbuf *out, struct bch_sb *sb,
 			     struct bch_sb_field *f)
 {
 	unsigned type = le32_to_cpu(f->type);
@@ -1209,6 +1196,15 @@ void bch2_sb_field_to_text(struct printbuf *out, struct bch_sb *sb,
 	if (!out->nr_tabstops)
 		printbuf_tabstop_push(out, 32);
 
+	if (ops->to_text)
+		ops->to_text(out, sb, f);
+}
+
+void bch2_sb_field_to_text(struct printbuf *out, struct bch_sb *sb,
+			   struct bch_sb_field *f)
+{
+	unsigned type = le32_to_cpu(f->type);
+
 	if (type < BCH_SB_FIELD_NR)
 		prt_printf(out, "%s", bch2_sb_fields[type]);
 	else
@@ -1217,11 +1213,7 @@ void bch2_sb_field_to_text(struct printbuf *out, struct bch_sb *sb,
 	prt_printf(out, " (size %zu):", vstruct_bytes(f));
 	prt_newline(out);
 
-	if (ops->to_text) {
+	__bch2_sb_field_to_text(out, sb, f);
-		printbuf_indent_add(out, 2);
-		ops->to_text(out, sb, f);
-		printbuf_indent_sub(out, 2);
-	}
 }
 
 void bch2_sb_layout_to_text(struct printbuf *out, struct bch_sb_layout *l)

libbcachefs/super-io.h

@@ -19,10 +19,6 @@ static inline bool bch2_version_compatible(u16 version)
 void bch2_version_to_text(struct printbuf *, unsigned);
 unsigned bch2_latest_compatible_version(unsigned);
 
-u64 bch2_upgrade_recovery_passes(struct bch_fs *c,
-				 unsigned,
-				 unsigned);
-
 static inline size_t bch2_sb_field_bytes(struct bch_sb_field *f)
 {
 	return le32_to_cpu(f->u64s) * sizeof(u64);
@@ -94,9 +90,11 @@ static inline void bch2_check_set_feature(struct bch_fs *c, unsigned feat)
 		__bch2_check_set_feature(c, feat);
 }
 
-void bch2_sb_maybe_downgrade(struct bch_fs *);
+bool bch2_check_version_downgrade(struct bch_fs *);
 void bch2_sb_upgrade(struct bch_fs *, unsigned);
 
+void __bch2_sb_field_to_text(struct printbuf *, struct bch_sb *,
+			     struct bch_sb_field *);
 void bch2_sb_field_to_text(struct printbuf *, struct bch_sb *,
 			   struct bch_sb_field *);
 void bch2_sb_layout_to_text(struct printbuf *, struct bch_sb_layout *);

libbcachefs/super.c

@@ -88,14 +88,11 @@ const char * const bch2_fs_flag_strs[] = {
 
 void __bch2_print(struct bch_fs *c, const char *fmt, ...)
 {
-	struct log_output *output = c->output;
+	struct stdio_redirect *stdio = bch2_fs_stdio_redirect(c);
+
 	va_list args;
-
-	if (c->output_filter && c->output_filter != current)
-		output = NULL;
-
 	va_start(args, fmt);
-	if (likely(!output)) {
+	if (likely(!stdio)) {
 		vprintk(fmt, args);
 	} else {
 		unsigned long flags;
@@ -103,11 +100,11 @@ void __bch2_print(struct bch_fs *c, const char *fmt, ...)
 		if (fmt[0] == KERN_SOH[0])
 			fmt += 2;
 
-		spin_lock_irqsave(&output->lock, flags);
+		spin_lock_irqsave(&stdio->output_lock, flags);
-		prt_vprintf(&output->buf, fmt, args);
+		prt_vprintf(&stdio->output_buf, fmt, args);
-		spin_unlock_irqrestore(&output->lock, flags);
+		spin_unlock_irqrestore(&stdio->output_lock, flags);
 
-		wake_up(&output->wait);
+		wake_up(&stdio->output_wait);
 	}
 	va_end(args);
 }
@@ -724,7 +721,7 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts)
 		goto out;
 	}
 
-	c->output = (void *)(unsigned long) opts.log_output;
+	c->stdio = (void *)(unsigned long) opts.stdio;
 
 	__module_get(THIS_MODULE);
 
@@ -871,7 +868,7 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts)
 	    !(c->copygc_wq = alloc_workqueue("bcachefs_copygc",
 				WQ_FREEZABLE|WQ_MEM_RECLAIM|WQ_CPU_INTENSIVE, 1)) ||
 	    !(c->io_complete_wq = alloc_workqueue("bcachefs_io",
-				WQ_FREEZABLE|WQ_HIGHPRI|WQ_MEM_RECLAIM, 1)) ||
+				WQ_FREEZABLE|WQ_HIGHPRI|WQ_MEM_RECLAIM, 512)) ||
 	    !(c->write_ref_wq = alloc_workqueue("bcachefs_write_ref",
 				WQ_FREEZABLE, 0)) ||
 #ifndef BCH_WRITE_REF_DEBUG
@@ -1086,17 +1083,22 @@ static int bch2_dev_in_fs(struct bch_sb_handle *fs,
 	    fs->sb->write_time != sb->sb->write_time) {
 		struct printbuf buf = PRINTBUF;
 
-		prt_printf(&buf, "Split brain detected between %pg and %pg:",
+		prt_str(&buf, "Split brain detected between ");
-			   sb->bdev, fs->bdev);
+		prt_bdevname(&buf, sb->bdev);
+		prt_str(&buf, " and ");
+		prt_bdevname(&buf, fs->bdev);
+		prt_char(&buf, ':');
 		prt_newline(&buf);
 		prt_printf(&buf, "seq=%llu but write_time different, got", le64_to_cpu(sb->sb->seq));
 		prt_newline(&buf);
 
-		prt_printf(&buf, "%pg ", fs->bdev);
+		prt_bdevname(&buf, fs->bdev);
+		prt_char(&buf, ' ');
 		bch2_prt_datetime(&buf, le64_to_cpu(fs->sb->write_time));;
 		prt_newline(&buf);
 
-		prt_printf(&buf, "%pg ", sb->bdev);
+		prt_bdevname(&buf, sb->bdev);
+		prt_char(&buf, ' ');
 		bch2_prt_datetime(&buf, le64_to_cpu(sb->sb->write_time));;
 		prt_newline(&buf);
 
@@ -1112,13 +1114,26 @@ static int bch2_dev_in_fs(struct bch_sb_handle *fs,
 	u64 seq_from_member	= le64_to_cpu(sb->sb->seq);
 
 	if (seq_from_fs && seq_from_fs < seq_from_member) {
-		pr_err("Split brain detected between %pg and %pg:\n"
+		struct printbuf buf = PRINTBUF;
-		       "%pg believes seq of %pg to be %llu, but %pg has %llu\n"
+
-		       "Not using %pg",
+		prt_str(&buf, "Split brain detected between ");
-		       sb->bdev, fs->bdev,
+		prt_bdevname(&buf, sb->bdev);
-		       fs->bdev, sb->bdev, seq_from_fs,
+		prt_str(&buf, " and ");
-		       sb->bdev, seq_from_member,
+		prt_bdevname(&buf, fs->bdev);
-		       sb->bdev);
+		prt_char(&buf, ':');
+		prt_newline(&buf);
+
+		prt_bdevname(&buf, fs->bdev);
+		prt_str(&buf, "believes seq of ");
+		prt_bdevname(&buf, sb->bdev);
+		prt_printf(&buf, " to be %llu, but ", seq_from_fs);
+		prt_bdevname(&buf, sb->bdev);
+		prt_printf(&buf, " has %llu\n", seq_from_member);
+		prt_str(&buf, "Not using ");
+		prt_bdevname(&buf, sb->bdev);
+
+		pr_err("%s", buf.buf);
+		printbuf_exit(&buf);
 		return -BCH_ERR_device_splitbrain;
 	}
 
@@ -1367,9 +1382,14 @@ static int bch2_dev_attach_bdev(struct bch_fs *c, struct bch_sb_handle *sb)
 
 	bch2_dev_sysfs_online(c, ca);
 
+	struct printbuf name = PRINTBUF;
+	prt_bdevname(&name, ca->disk_sb.bdev);
+
 	if (c->sb.nr_devices == 1)
-		snprintf(c->name, sizeof(c->name), "%pg", ca->disk_sb.bdev);
+		strlcpy(c->name, name.buf, sizeof(c->name));
-	snprintf(ca->name, sizeof(ca->name), "%pg", ca->disk_sb.bdev);
+	strlcpy(ca->name, name.buf, sizeof(ca->name));
+
+	printbuf_exit(&name);
 
 	rebalance_wakeup(c);
 	return 0;

libbcachefs/thread_with_file.c

@@ -0,0 +1,299 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef NO_BCACHEFS_FS
+
+#include "bcachefs.h"
+#include "printbuf.h"
+#include "thread_with_file.h"
+
+#include <linux/anon_inodes.h>
+#include <linux/file.h>
+#include <linux/kthread.h>
+#include <linux/pagemap.h>
+#include <linux/poll.h>
+
+void bch2_thread_with_file_exit(struct thread_with_file *thr)
+{
+	if (thr->task) {
+		kthread_stop(thr->task);
+		put_task_struct(thr->task);
+	}
+}
+
+int bch2_run_thread_with_file(struct thread_with_file *thr,
+			      const struct file_operations *fops,
+			      int (*fn)(void *))
+{
+	struct file *file = NULL;
+	int ret, fd = -1;
+	unsigned fd_flags = O_CLOEXEC;
+
+	if (fops->read && fops->write)
+		fd_flags |= O_RDWR;
+	else if (fops->read)
+		fd_flags |= O_RDONLY;
+	else if (fops->write)
+		fd_flags |= O_WRONLY;
+
+	char name[TASK_COMM_LEN];
+	get_task_comm(name, current);
+
+	thr->ret = 0;
+	thr->task = kthread_create(fn, thr, "%s", name);
+	ret = PTR_ERR_OR_ZERO(thr->task);
+	if (ret)
+		return ret;
+
+	ret = get_unused_fd_flags(fd_flags);
+	if (ret < 0)
+		goto err;
+	fd = ret;
+
+	file = anon_inode_getfile(name, fops, thr, fd_flags);
+	ret = PTR_ERR_OR_ZERO(file);
+	if (ret)
+		goto err;
+
+	fd_install(fd, file);
+	get_task_struct(thr->task);
+	wake_up_process(thr->task);
+	return fd;
+err:
+	if (fd >= 0)
+		put_unused_fd(fd);
+	if (thr->task)
+		kthread_stop(thr->task);
+	return ret;
+}
+
+static inline bool thread_with_stdio_has_output(struct thread_with_stdio *thr)
+{
+	return thr->stdio.output_buf.pos ||
+		thr->output2.nr ||
+		thr->thr.done;
+}
+
+static ssize_t thread_with_stdio_read(struct file *file, char __user *buf,
+				      size_t len, loff_t *ppos)
+{
+	struct thread_with_stdio *thr =
+		container_of(file->private_data, struct thread_with_stdio, thr);
+	size_t copied = 0, b;
+	int ret = 0;
+
+	if ((file->f_flags & O_NONBLOCK) &&
+	    !thread_with_stdio_has_output(thr))
+		return -EAGAIN;
+
+	ret = wait_event_interruptible(thr->stdio.output_wait,
+		thread_with_stdio_has_output(thr));
+	if (ret)
+		return ret;
+
+	if (thr->thr.done)
+		return 0;
+
+	while (len) {
+		ret = darray_make_room(&thr->output2, thr->stdio.output_buf.pos);
+		if (ret)
+			break;
+
+		spin_lock_irq(&thr->stdio.output_lock);
+		b = min_t(size_t, darray_room(thr->output2), thr->stdio.output_buf.pos);
+
+		memcpy(&darray_top(thr->output2), thr->stdio.output_buf.buf, b);
+		memmove(thr->stdio.output_buf.buf,
+			thr->stdio.output_buf.buf + b,
+			thr->stdio.output_buf.pos - b);
+
+		thr->output2.nr += b;
+		thr->stdio.output_buf.pos -= b;
+		spin_unlock_irq(&thr->stdio.output_lock);
+
+		b = min(len, thr->output2.nr);
+		if (!b)
+			break;
+
+		b -= copy_to_user(buf, thr->output2.data, b);
+		if (!b) {
+			ret = -EFAULT;
+			break;
+		}
+
+		copied	+= b;
+		buf	+= b;
+		len	-= b;
+
+		memmove(thr->output2.data,
+			thr->output2.data + b,
+			thr->output2.nr - b);
+		thr->output2.nr -= b;
+	}
+
+	return copied ?: ret;
+}
+
+static int thread_with_stdio_release(struct inode *inode, struct file *file)
+{
+	struct thread_with_stdio *thr =
+		container_of(file->private_data, struct thread_with_stdio, thr);
+
+	bch2_thread_with_file_exit(&thr->thr);
+	printbuf_exit(&thr->stdio.input_buf);
+	printbuf_exit(&thr->stdio.output_buf);
+	darray_exit(&thr->output2);
+	thr->exit(thr);
+	return 0;
+}
+
+#define WRITE_BUFFER		4096
+
+static inline bool thread_with_stdio_has_input_space(struct thread_with_stdio *thr)
+{
+	return thr->stdio.input_buf.pos < WRITE_BUFFER || thr->thr.done;
+}
+
+static ssize_t thread_with_stdio_write(struct file *file, const char __user *ubuf,
+				       size_t len, loff_t *ppos)
+{
+	struct thread_with_stdio *thr =
+		container_of(file->private_data, struct thread_with_stdio, thr);
+	struct printbuf *buf = &thr->stdio.input_buf;
+	size_t copied = 0;
+	ssize_t ret = 0;
+
+	while (len) {
+		if (thr->thr.done) {
+			ret = -EPIPE;
+			break;
+		}
+
+		size_t b = len - fault_in_readable(ubuf, len);
+		if (!b) {
+			ret = -EFAULT;
+			break;
+		}
+
+		spin_lock(&thr->stdio.input_lock);
+		if (buf->pos < WRITE_BUFFER)
+			bch2_printbuf_make_room(buf, min(b, WRITE_BUFFER - buf->pos));
+		b = min(len, printbuf_remaining_size(buf));
+
+		if (b && !copy_from_user_nofault(&buf->buf[buf->pos], ubuf, b)) {
+			ubuf += b;
+			len -= b;
+			copied += b;
+			buf->pos += b;
+		}
+		spin_unlock(&thr->stdio.input_lock);
+
+		if (b) {
+			wake_up(&thr->stdio.input_wait);
+		} else {
+			if ((file->f_flags & O_NONBLOCK)) {
+				ret = -EAGAIN;
+				break;
+			}
+
+			ret = wait_event_interruptible(thr->stdio.input_wait,
+					thread_with_stdio_has_input_space(thr));
+			if (ret)
+				break;
+		}
+	}
+
+	return copied ?: ret;
+}
+
+static __poll_t thread_with_stdio_poll(struct file *file, struct poll_table_struct *wait)
+{
+	struct thread_with_stdio *thr =
+		container_of(file->private_data, struct thread_with_stdio, thr);
+
+	poll_wait(file, &thr->stdio.output_wait, wait);
+	poll_wait(file, &thr->stdio.input_wait, wait);
+
+	__poll_t mask = 0;
+
+	if (thread_with_stdio_has_output(thr))
+		mask |= EPOLLIN;
+	if (thread_with_stdio_has_input_space(thr))
+		mask |= EPOLLOUT;
+	if (thr->thr.done)
+		mask |= EPOLLHUP|EPOLLERR;
+	return mask;
+}
+
+static const struct file_operations thread_with_stdio_fops = {
+	.release	= thread_with_stdio_release,
+	.read		= thread_with_stdio_read,
+	.write		= thread_with_stdio_write,
+	.poll		= thread_with_stdio_poll,
+	.llseek		= no_llseek,
+};
+
+int bch2_run_thread_with_stdio(struct thread_with_stdio *thr,
+			       void (*exit)(struct thread_with_stdio *),
+			       int (*fn)(void *))
+{
+	thr->stdio.input_buf = PRINTBUF;
+	thr->stdio.input_buf.atomic++;
+	spin_lock_init(&thr->stdio.input_lock);
+	init_waitqueue_head(&thr->stdio.input_wait);
+
+	thr->stdio.output_buf = PRINTBUF;
+	thr->stdio.output_buf.atomic++;
+	spin_lock_init(&thr->stdio.output_lock);
+	init_waitqueue_head(&thr->stdio.output_wait);
+
+	darray_init(&thr->output2);
+	thr->exit = exit;
+
+	return bch2_run_thread_with_file(&thr->thr, &thread_with_stdio_fops, fn);
+}
+
+int bch2_stdio_redirect_read(struct stdio_redirect *stdio, char *buf, size_t len)
+{
+	wait_event(stdio->input_wait,
+		   stdio->input_buf.pos || stdio->done);
+
+	if (stdio->done)
+		return -1;
+
+	spin_lock(&stdio->input_lock);
+	int ret = min(len, stdio->input_buf.pos);
+	stdio->input_buf.pos -= ret;
+	memcpy(buf, stdio->input_buf.buf, ret);
+	memmove(stdio->input_buf.buf,
+		stdio->input_buf.buf + ret,
+		stdio->input_buf.pos);
+	spin_unlock(&stdio->input_lock);
+
+	wake_up(&stdio->input_wait);
+	return ret;
+}
+
+int bch2_stdio_redirect_readline(struct stdio_redirect *stdio, char *buf, size_t len)
+{
+	wait_event(stdio->input_wait,
+		   stdio->input_buf.pos || stdio->done);
+
+	if (stdio->done)
+		return -1;
+
+	spin_lock(&stdio->input_lock);
+	int ret = min(len, stdio->input_buf.pos);
+	char *n = memchr(stdio->input_buf.buf, '\n', ret);
+	if (n)
+		ret = min(ret, n + 1 - stdio->input_buf.buf);
+	stdio->input_buf.pos -= ret;
+	memcpy(buf, stdio->input_buf.buf, ret);
+	memmove(stdio->input_buf.buf,
+		stdio->input_buf.buf + ret,
+		stdio->input_buf.pos);
+	spin_unlock(&stdio->input_lock);
+
+	wake_up(&stdio->input_wait);
+	return ret;
+}
+
+#endif /* NO_BCACHEFS_FS */

libbcachefs/thread_with_file.h

@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_THREAD_WITH_FILE_H
+#define _BCACHEFS_THREAD_WITH_FILE_H
+
+#include "thread_with_file_types.h"
+
+struct task_struct;
+
+struct thread_with_file {
+	struct task_struct	*task;
+	int			ret;
+	bool			done;
+};
+
+void bch2_thread_with_file_exit(struct thread_with_file *);
+int bch2_run_thread_with_file(struct thread_with_file *,
+			      const struct file_operations *,
+			      int (*fn)(void *));
+
+struct thread_with_stdio {
+	struct thread_with_file	thr;
+	struct stdio_redirect	stdio;
+	DARRAY(char)		output2;
+	void			(*exit)(struct thread_with_stdio *);
+};
+
+static inline void thread_with_stdio_done(struct thread_with_stdio *thr)
+{
+	thr->thr.done = true;
+	thr->stdio.done = true;
+	wake_up(&thr->stdio.input_wait);
+	wake_up(&thr->stdio.output_wait);
+}
+
+int bch2_run_thread_with_stdio(struct thread_with_stdio *,
+			       void (*exit)(struct thread_with_stdio *),
+			       int (*fn)(void *));
+int bch2_stdio_redirect_read(struct stdio_redirect *, char *, size_t);
+int bch2_stdio_redirect_readline(struct stdio_redirect *, char *, size_t);
+
+#endif /* _BCACHEFS_THREAD_WITH_FILE_H */

libbcachefs/thread_with_file_types.h

@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_THREAD_WITH_FILE_TYPES_H
+#define _BCACHEFS_THREAD_WITH_FILE_TYPES_H
+
+struct stdio_redirect {
+	spinlock_t		output_lock;
+	wait_queue_head_t	output_wait;
+	struct printbuf		output_buf;
+
+	spinlock_t		input_lock;
+	wait_queue_head_t	input_wait;
+	struct printbuf		input_buf;
+	bool			done;
+};
+
+#endif /* _BCACHEFS_THREAD_WITH_FILE_TYPES_H */

libbcachefs/trace.h

@@ -72,6 +72,27 @@ DECLARE_EVENT_CLASS(trans_str,
 		  __entry->trans_fn, (void *) __entry->caller_ip, __get_str(str))
 );
 
+DECLARE_EVENT_CLASS(trans_str_nocaller,
+	TP_PROTO(struct btree_trans *trans, const char *str),
+	TP_ARGS(trans, str),
+
+	TP_STRUCT__entry(
+		__field(dev_t,		dev			)
+		__array(char,		trans_fn, 32		)
+		__string(str,		str			)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= trans->c->dev;
+		strscpy(__entry->trans_fn, trans->fn, sizeof(__entry->trans_fn));
+		__assign_str(str, str);
+	),
+
+	TP_printk("%d,%d %s %s",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->trans_fn, __get_str(str))
+);
+
 DECLARE_EVENT_CLASS(btree_node_nofs,
 	TP_PROTO(struct bch_fs *c, struct btree *b),
 	TP_ARGS(c, b),
@@ -1243,11 +1264,10 @@ DEFINE_EVENT(transaction_restart_iter,	trans_restart_memory_allocation_failure,
 	TP_ARGS(trans, caller_ip, path)
 );
 
-DEFINE_EVENT(trans_str, trans_restart_would_deadlock,
+DEFINE_EVENT(trans_str_nocaller, trans_restart_would_deadlock,
 	TP_PROTO(struct btree_trans *trans,
-		 unsigned long caller_ip,
 		 const char *cycle),
-	TP_ARGS(trans, caller_ip, cycle)
+	TP_ARGS(trans, cycle)
 );
 
 DEFINE_EVENT(transaction_event,	trans_restart_would_deadlock_recursion_limit,

libbcachefs/util.c

@@ -267,7 +267,7 @@ void bch2_print_string_as_lines(const char *prefix, const char *lines)
 	console_unlock();
 }
 
-int bch2_save_backtrace(bch_stacktrace *stack, struct task_struct *task)
+int bch2_save_backtrace(bch_stacktrace *stack, struct task_struct *task, unsigned skipnr)
 {
 #ifdef CONFIG_STACKTRACE
 	unsigned nr_entries = 0;
@@ -282,7 +282,7 @@ int bch2_save_backtrace(bch_stacktrace *stack, struct task_struct *task)
 		return -1;
 
 	do {
-		nr_entries = stack_trace_save_tsk(task, stack->data, stack->size, 0);
+		nr_entries = stack_trace_save_tsk(task, stack->data, stack->size, skipnr + 1);
 	} while (nr_entries == stack->size &&
 		 !(ret = darray_make_room(stack, stack->size * 2)));
 
@@ -303,10 +303,10 @@ void bch2_prt_backtrace(struct printbuf *out, bch_stacktrace *stack)
 	}
 }
 
-int bch2_prt_task_backtrace(struct printbuf *out, struct task_struct *task)
+int bch2_prt_task_backtrace(struct printbuf *out, struct task_struct *task, unsigned skipnr)
 {
 	bch_stacktrace stack = { 0 };
-	int ret = bch2_save_backtrace(&stack, task);
+	int ret = bch2_save_backtrace(&stack, task, skipnr + 1);
 
 	bch2_prt_backtrace(out, &stack);
 	darray_exit(&stack);

libbcachefs/util.h

@@ -347,9 +347,18 @@ void bch2_prt_u64_binary(struct printbuf *, u64, unsigned);
 void bch2_print_string_as_lines(const char *prefix, const char *lines);
 
 typedef DARRAY(unsigned long) bch_stacktrace;
-int bch2_save_backtrace(bch_stacktrace *stack, struct task_struct *);
+int bch2_save_backtrace(bch_stacktrace *stack, struct task_struct *, unsigned);
 void bch2_prt_backtrace(struct printbuf *, bch_stacktrace *);
-int bch2_prt_task_backtrace(struct printbuf *, struct task_struct *);
+int bch2_prt_task_backtrace(struct printbuf *, struct task_struct *, unsigned);
+
+static inline void prt_bdevname(struct printbuf *out, struct block_device *bdev)
+{
+#ifdef __KERNEL__
+	prt_printf(out, "%pg", bdev);
+#else
+	prt_str(out, bdev->name);
+#endif
+}
 
 #define NR_QUANTILES	15
 #define QUANTILE_IDX(i)	inorder_to_eytzinger0(i, NR_QUANTILES)