bcachefs: Online fsck can now fix errors

BCH_FS_fsck_done -> BCH_FS_fsck_running; set when we might be fixing
fsck errors. Also; set fix_errors to ask by default when fsck is
running.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

fs/bcachefs/bcachefs.h

@@ -602,9 +602,6 @@ struct bch_dev {
 };
 
 /*
- * fsck_done - kill?
- *
- * replace with something more general from enumated fsck passes/errors:
  * initial_gc_unfixed
  * error
  * topology error
@@ -620,7 +617,7 @@ 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)	\

fs/bcachefs/chardev.c

@@ -774,15 +774,24 @@ static int bch2_fsck_online_thread_fn(void *arg)
 	/*
 	 * 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);
+
+	clear_bit(BCH_FS_fsck_running, &c->flags);
+	bch_err_fn(c, ret);
 
 	c->stdio = NULL;
 	c->stdio_filter = NULL;
+	c->opts.fix_errors = old_fix_errors;
 
 	thread_with_stdio_done(&thr->thr);
 

fs/bcachefs/error.c

@@ -28,7 +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);
 }
 
@@ -141,7 +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)
@@ -223,7 +223,7 @@ 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");
@@ -290,7 +290,7 @@ int bch2_fsck_err(struct bch_fs *c,
 			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");

fs/bcachefs/recovery.c

@@ -832,6 +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");
@@ -972,6 +975,8 @@ int bch2_fs_recovery(struct bch_fs *c)
 	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) &&
@@ -1066,7 +1071,6 @@ int bch2_fs_recovery(struct bch_fs *c)
 
 	ret = 0;
 out:
-	set_bit(BCH_FS_fsck_done, &c->flags);
 	bch2_flush_fsck_errs(c);
 
 	if (!c->opts.keep_journal &&
@@ -1113,7 +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);