bcachefs: BCH_IOCTL_FSCK_ONLINE

This adds a new ioctl for running fsck on a mounted, in use filesystem.

This reuses the fsck_thread code from the previous patch for running
fsck on an offline, unmounted filesystem, so that log messages for the
fsck thread are redirected to userspace.

Only one running fsck instance is allowed at a time; a new semaphore
(since the lock will be taken by one thread and released by another) is
added for this.

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

4 files changed, 107 insertions, 2 deletions

diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h
index 18bc1bbef918..b42e3854c51f 100644
--- a/fs/bcachefs/bcachefs.h
+++ b/fs/bcachefs/bcachefs.h
@@ -1058,6 +1058,7 @@ struct bch_fs {
 	/* bitmap of explicitly enabled recovery passes: */
 	u64			recovery_passes_explicit;
 	u64			recovery_passes_complete;
+	struct semaphore	online_fsck_mutex;
 
 	/* DEBUG JUNK */
 	struct dentry		*fs_debug_dir;
diff --git a/fs/bcachefs/bcachefs_ioctl.h b/fs/bcachefs/bcachefs_ioctl.h
index 07c490851742..21f81b16f24e 100644
--- a/fs/bcachefs/bcachefs_ioctl.h
+++ b/fs/bcachefs/bcachefs_ioctl.h
@@ -83,7 +83,8 @@ struct bch_ioctl_incremental {
 
 #define BCH_IOCTL_DEV_USAGE_V2	_IOWR(0xbc,	18, struct bch_ioctl_dev_usage_v2)
 
-#define BCH_IOCTL_FSCK_OFFLINE		_IOW(0xbc,	19,  struct bch_ioctl_fsck_offline)
+#define BCH_IOCTL_FSCK_OFFLINE	_IOW(0xbc,	19,  struct bch_ioctl_fsck_offline)
+#define BCH_IOCTL_FSCK_ONLINE	_IOW(0xbc,	20,  struct bch_ioctl_fsck_online)
 
 /* ioctl below act on a particular file, not the filesystem as a whole: */
 
@@ -399,4 +400,13 @@ struct bch_ioctl_fsck_offline {
 	__u64			devs[0];
 };
 
+/*
+ * BCH_IOCTL_FSCK_ONLINE: run fsck from the 'bcachefs fsck' userspace command,
+ * but with the kernel's implementation of fsck:
+ */
+struct bch_ioctl_fsck_online {
+	__u64			flags;
+	__u64			opts;		/* string */
+};
+
 #endif /* _BCACHEFS_IOCTL_H */
diff --git a/fs/bcachefs/chardev.c b/fs/bcachefs/chardev.c
index 78bcfa4cb48f..08922f7e380a 100644
--- a/fs/bcachefs/chardev.c
+++ b/fs/bcachefs/chardev.c
@@ -7,6 +7,7 @@
 #include "chardev.h"
 #include "journal.h"
 #include "move.h"
+#include "recovery.h"
 #include "replicas.h"
 #include "super.h"
 #include "super-io.h"
@@ -201,6 +202,7 @@ static long bch2_ioctl_incremental(struct bch_ioctl_incremental __user *user_arg
 struct fsck_thread {
 	struct thread_with_file	thr;
 	struct printbuf		buf;
+	struct bch_fs		*c;
 	char			**devs;
 	size_t			nr_devs;
 	struct bch_opts		opts;
@@ -350,6 +352,7 @@ static long bch2_ioctl_fsck_offline(struct bch_ioctl_fsck_offline __user *user_a
 		goto err;
 	}
 
+	thr->opts = bch2_opts_empty();
 	thr->nr_devs = arg.nr_devs;
 	thr->output.buf	= PRINTBUF;
 	thr->output.buf.atomic++;
@@ -929,6 +932,95 @@ static long bch2_ioctl_disk_resize_journal(struct bch_fs *c,
 	return ret;
 }
 
+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->output = &thr->output;
+
+	/*
+	 * XXX: can we figure out a way to do this without mucking with c->opts?
+	 */
+	if (opt_defined(thr->opts, fix_errors))
+		c->opts.fix_errors = thr->opts.fix_errors;
+	c->opts.fsck = true;
+
+	c->curr_recovery_pass = BCH_RECOVERY_PASS_check_alloc_info;
+	bch2_run_online_recovery_passes(c);
+
+	c->output = NULL;
+	c->output_filter = NULL;
+
+	thr->thr.done = true;
+	wake_up(&thr->output.wait);
+
+	up(&c->online_fsck_mutex);
+	bch2_ro_ref_put(c);
+	return 0;
+}
+
+static long bch2_ioctl_fsck_online(struct bch_fs *c,
+				   struct bch_ioctl_fsck_online arg)
+{
+	struct fsck_thread *thr = NULL;
+	long ret = 0;
+
+	if (arg.flags)
+		return -EINVAL;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (!bch2_ro_ref_tryget(c))
+		return -EROFS;
+
+	if (down_trylock(&c->online_fsck_mutex)) {
+		bch2_ro_ref_put(c);
+		return -EAGAIN;
+	}
+
+	thr = kzalloc(sizeof(*thr), GFP_KERNEL);
+	if (!thr) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	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);
+
+		ret =   PTR_ERR_OR_ZERO(optstr) ?:
+			bch2_parse_mount_opts(c, &thr->opts, optstr);
+		kfree(optstr);
+
+		if (ret)
+			goto err;
+	}
+
+	ret = run_thread_with_file(&thr->thr,
+				   &fsck_thread_ops,
+				   bch2_fsck_online_thread_fn,
+				   "bch-fsck");
+err:
+	if (ret < 0) {
+		bch_err_fn(c, ret);
+		if (thr)
+			bch2_fsck_thread_free(thr);
+		up(&c->online_fsck_mutex);
+		bch2_ro_ref_put(c);
+	}
+	return ret;
+}
+
 #define BCH_IOCTL(_name, _argtype)					\
 do {									\
 	_argtype i;							\
@@ -984,7 +1076,8 @@ long bch2_fs_ioctl(struct bch_fs *c, unsigned cmd, void __user *arg)
 		BCH_IOCTL(disk_resize, struct bch_ioctl_disk_resize);
 	case BCH_IOCTL_DISK_RESIZE_JOURNAL:
 		BCH_IOCTL(disk_resize_journal, struct bch_ioctl_disk_resize_journal);
-
+	case BCH_IOCTL_FSCK_ONLINE:
+		BCH_IOCTL(fsck_online, struct bch_ioctl_fsck_online);
 	default:
 		return -ENOTTY;
 	}
diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index 83e5423fd005..c7c7d4a11eb9 100644
--- a/fs/bcachefs/super.c
+++ b/fs/bcachefs/super.c
@@ -762,6 +762,7 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts)
 
 	refcount_set(&c->ro_ref, 1);
 	init_waitqueue_head(&c->ro_ref_wait);
+	sema_init(&c->online_fsck_mutex, 1);
 
 	init_rwsem(&c->gc_lock);
 	mutex_init(&c->gc_gens_lock);