X-Git-Url: https://git.sesse.net/?a=blobdiff_plain;f=libbcachefs%2Fchardev.c;h=226b39c176673a374f50ab06ad5f6d3e0a4858d8;hb=b5fd066153c40a70a29caa1ea7987723ab687763;hp=ac1ec5f62cea06c4b4bef44ef108af4d4ef03179;hpb=a10a41fa2b1a917b0f3b34d20175867f968b2d12;p=bcachefs-tools-debian

diff --git a/libbcachefs/chardev.c b/libbcachefs/chardev.c
index ac1ec5f..226b39c 100644
--- a/libbcachefs/chardev.c
+++ b/libbcachefs/chardev.c
@@ -1,25 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0
 #ifndef NO_BCACHEFS_CHARDEV
 
 #include "bcachefs.h"
 #include "bcachefs_ioctl.h"
 #include "buckets.h"
 #include "chardev.h"
+#include "journal.h"
 #include "move.h"
+#include "recovery.h"
+#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/sched/task.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
 
+__must_check
+static int copy_to_user_errcode(void __user *to, const void *from, unsigned long n)
+{
+	return copy_to_user(to, from, n) ? -EFAULT : 0;
+}
+
 /* returns with ref on ca->ref */
 static struct bch_dev *bch2_device_lookup(struct bch_fs *c, u64 dev,
 					  unsigned flags)
@@ -83,10 +91,9 @@ static long bch2_ioctl_assemble(struct bch_ioctl_assemble __user *user_arg)
 		devs[i] = strndup_user((const char __user *)(unsigned long)
 				       user_devs[i],
 				       PATH_MAX);
-		if (!devs[i]) {
-			ret = -ENOMEM;
+		ret= PTR_ERR_OR_ZERO(devs[i]);
+		if (ret)
 			goto err;
-		}
 	}
 
 	c = bch2_fs_open(devs, arg.nr_devs, bch2_opts_empty());
@@ -114,8 +121,9 @@ static long bch2_ioctl_incremental(struct bch_ioctl_incremental __user *user_arg
 		return -EINVAL;
 
 	path = strndup_user((const char __user *)(unsigned long) arg.dev, PATH_MAX);
-	if (!path)
-		return -ENOMEM;
+	ret = PTR_ERR_OR_ZERO(path);
+	if (ret)
+		return ret;
 
 	err = bch2_fs_open_incremental(path);
 	kfree(path);
@@ -129,8 +137,106 @@ static long bch2_ioctl_incremental(struct bch_ioctl_incremental __user *user_arg
 }
 #endif
 
+struct fsck_thread {
+	struct thread_with_stdio thr;
+	struct bch_fs		*c;
+	char			**devs;
+	size_t			nr_devs;
+	struct bch_opts		opts;
+};
+
+static void bch2_fsck_thread_exit(struct thread_with_stdio *_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]);
+	kfree(thr->devs);
+	kfree(thr);
+}
+
+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.thr.ret = PTR_ERR_OR_ZERO(c);
+	if (!thr->thr.thr.ret)
+		bch2_fs_stop(c);
+
+	thread_with_stdio_done(&thr->thr);
+	return 0;
+}
+
+static long bch2_ioctl_fsck_offline(struct bch_ioctl_fsck_offline __user *user_arg)
+{
+	struct bch_ioctl_fsck_offline arg;
+	struct fsck_thread *thr = NULL;
+	u64 *devs = NULL;
+	long ret = 0;
+
+	if (copy_from_user(&arg, user_arg, sizeof(arg)))
+		return -EFAULT;
+
+	if (arg.flags)
+		return -EINVAL;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (!(devs = kcalloc(arg.nr_devs, sizeof(*devs), GFP_KERNEL)) ||
+	    !(thr = kzalloc(sizeof(*thr), GFP_KERNEL)) ||
+	    !(thr->devs = kcalloc(arg.nr_devs, sizeof(*thr->devs), GFP_KERNEL))) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	thr->opts = bch2_opts_empty();
+	thr->nr_devs = arg.nr_devs;
+
+	if (copy_from_user(devs, &user_arg->devs[0],
+			   array_size(sizeof(user_arg->devs[0]), arg.nr_devs))) {
+		ret = -EINVAL;
+		goto err;
+	}
+
+	for (size_t i = 0; i < arg.nr_devs; i++) {
+		thr->devs[i] = strndup_user((char __user *)(unsigned long) devs[i], PATH_MAX);
+		ret = PTR_ERR_OR_ZERO(thr->devs[i]);
+		if (ret)
+			goto err;
+	}
+
+	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(NULL, &thr->opts, optstr);
+		kfree(optstr);
+
+		if (ret)
+			goto err;
+	}
+
+	opt_set(thr->opts, stdio, (u64)(unsigned long)&thr->thr.stdio);
+
+	ret = bch2_run_thread_with_stdio(&thr->thr,
+			bch2_fsck_thread_exit,
+			bch2_fsck_offline_thread_fn);
+err:
+	if (ret < 0) {
+		if (thr)
+			bch2_fsck_thread_exit(&thr->thr);
+		pr_err("ret %s", bch2_err_str(ret));
+	}
+	kfree(devs);
+	return ret;
+}
+
 static long bch2_global_ioctl(unsigned cmd, void __user *arg)
 {
+	long ret;
+
 	switch (cmd) {
 #if 0
 	case BCH_IOCTL_ASSEMBLE:
@@ -138,30 +244,44 @@ static long bch2_global_ioctl(unsigned cmd, void __user *arg)
 	case BCH_IOCTL_INCREMENTAL:
 		return bch2_ioctl_incremental(arg);
 #endif
+	case BCH_IOCTL_FSCK_OFFLINE: {
+		ret = bch2_ioctl_fsck_offline(arg);
+		break;
+	}
 	default:
-		return -ENOTTY;
+		ret = -ENOTTY;
+		break;
 	}
+
+	if (ret < 0)
+		ret = bch2_err_class(ret);
+	return ret;
 }
 
 static long bch2_ioctl_query_uuid(struct bch_fs *c,
 			struct bch_ioctl_query_uuid __user *user_arg)
 {
-	return copy_to_user(&user_arg->uuid,
-			    &c->sb.user_uuid,
-			    sizeof(c->sb.user_uuid));
+	return copy_to_user_errcode(&user_arg->uuid, &c->sb.user_uuid,
+				    sizeof(c->sb.user_uuid));
 }
 
 #if 0
 static long bch2_ioctl_start(struct bch_fs *c, struct bch_ioctl_start arg)
 {
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	if (arg.flags || arg.pad)
 		return -EINVAL;
 
-	return bch2_fs_start(c) ? -EIO : 0;
+	return bch2_fs_start(c);
 }
 
 static long bch2_ioctl_stop(struct bch_fs *c)
 {
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	bch2_fs_stop(c);
 	return 0;
 }
@@ -172,12 +292,16 @@ static long bch2_ioctl_disk_add(struct bch_fs *c, struct bch_ioctl_disk arg)
 	char *path;
 	int ret;
 
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	if (arg.flags || arg.pad)
 		return -EINVAL;
 
 	path = strndup_user((const char __user *)(unsigned long) arg.dev, PATH_MAX);
-	if (!path)
-		return -ENOMEM;
+	ret = PTR_ERR_OR_ZERO(path);
+	if (ret)
+		return ret;
 
 	ret = bch2_dev_add(c, path);
 	kfree(path);
@@ -189,6 +313,9 @@ static long bch2_ioctl_disk_remove(struct bch_fs *c, struct bch_ioctl_disk arg)
 {
 	struct bch_dev *ca;
 
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	if ((arg.flags & ~(BCH_FORCE_IF_DATA_LOST|
 			   BCH_FORCE_IF_METADATA_LOST|
 			   BCH_FORCE_IF_DEGRADED|
@@ -208,12 +335,16 @@ static long bch2_ioctl_disk_online(struct bch_fs *c, struct bch_ioctl_disk arg)
 	char *path;
 	int ret;
 
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	if (arg.flags || arg.pad)
 		return -EINVAL;
 
 	path = strndup_user((const char __user *)(unsigned long) arg.dev, PATH_MAX);
-	if (!path)
-		return -ENOMEM;
+	ret = PTR_ERR_OR_ZERO(path);
+	if (ret)
+		return ret;
 
 	ret = bch2_dev_online(c, path);
 	kfree(path);
@@ -225,6 +356,9 @@ static long bch2_ioctl_disk_offline(struct bch_fs *c, struct bch_ioctl_disk arg)
 	struct bch_dev *ca;
 	int ret;
 
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	if ((arg.flags & ~(BCH_FORCE_IF_DATA_LOST|
 			   BCH_FORCE_IF_METADATA_LOST|
 			   BCH_FORCE_IF_DEGRADED|
@@ -247,11 +381,15 @@ static long bch2_ioctl_disk_set_state(struct bch_fs *c,
 	struct bch_dev *ca;
 	int ret;
 
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	if ((arg.flags & ~(BCH_FORCE_IF_DATA_LOST|
 			   BCH_FORCE_IF_METADATA_LOST|
 			   BCH_FORCE_IF_DEGRADED|
 			   BCH_BY_INDEX)) ||
-	    arg.pad[0] || arg.pad[1] || arg.pad[2])
+	    arg.pad[0] || arg.pad[1] || arg.pad[2] ||
+	    arg.new_state >= BCH_MEMBER_STATE_NR)
 		return -EINVAL;
 
 	ca = bch2_device_lookup(c, arg.dev, arg.flags);
@@ -259,37 +397,35 @@ static long bch2_ioctl_disk_set_state(struct bch_fs *c,
 		return PTR_ERR(ca);
 
 	ret = bch2_dev_set_state(c, ca, arg.new_state, arg.flags);
+	if (ret)
+		bch_err(c, "Error setting device state: %s", bch2_err_str(ret));
 
 	percpu_ref_put(&ca->ref);
 	return ret;
 }
 
 struct bch_data_ctx {
+	struct thread_with_file		thr;
+
 	struct bch_fs			*c;
 	struct bch_ioctl_data		arg;
 	struct bch_move_stats		stats;
-
-	int				ret;
-
-	struct task_struct		*thread;
 };
 
 static int bch2_data_thread(void *arg)
 {
-	struct bch_data_ctx *ctx = arg;
-
-	ctx->ret = bch2_data_job(ctx->c, &ctx->stats, ctx->arg);
+	struct bch_data_ctx *ctx = container_of(arg, struct bch_data_ctx, thr);
 
+	ctx->thr.ret = bch2_data_job(ctx->c, &ctx->stats, ctx->arg);
 	ctx->stats.data_type = U8_MAX;
 	return 0;
 }
 
 static int bch2_data_job_release(struct inode *inode, struct file *file)
 {
-	struct bch_data_ctx *ctx = file->private_data;
+	struct bch_data_ctx *ctx = container_of(file->private_data, struct bch_data_ctx, thr);
 
-	kthread_stop(ctx->thread);
-	put_task_struct(ctx->thread);
+	bch2_thread_with_file_exit(&ctx->thr);
 	kfree(ctx);
 	return 0;
 }
@@ -297,13 +433,13 @@ static int bch2_data_job_release(struct inode *inode, struct file *file)
 static ssize_t bch2_data_job_read(struct file *file, char __user *buf,
 				  size_t len, loff_t *ppos)
 {
-	struct bch_data_ctx *ctx = file->private_data;
+	struct bch_data_ctx *ctx = container_of(file->private_data, struct bch_data_ctx, thr);
 	struct bch_fs *c = ctx->c;
 	struct bch_ioctl_data_event e = {
 		.type			= BCH_DATA_EVENT_PROGRESS,
 		.p.data_type		= ctx->stats.data_type,
-		.p.btree_id		= ctx->stats.iter.btree_id,
-		.p.pos			= ctx->stats.iter.pos,
+		.p.btree_id		= ctx->stats.pos.btree,
+		.p.pos			= ctx->stats.pos.pos,
 		.p.sectors_done		= atomic64_read(&ctx->stats.sectors_seen),
 		.p.sectors_total	= bch2_fs_usage_read_short(c).used,
 	};
@@ -311,7 +447,7 @@ static ssize_t bch2_data_job_read(struct file *file, char __user *buf,
 	if (len < sizeof(e))
 		return -EINVAL;
 
-	return copy_to_user(buf, &e, sizeof(e)) ?: sizeof(e);
+	return copy_to_user_errcode(buf, &e, sizeof(e)) ?: sizeof(e);
 }
 
 static const struct file_operations bcachefs_data_ops = {
@@ -323,10 +459,11 @@ static const struct file_operations bcachefs_data_ops = {
 static long bch2_ioctl_data(struct bch_fs *c,
 			    struct bch_ioctl_data arg)
 {
-	struct bch_data_ctx *ctx = NULL;
-	struct file *file = NULL;
-	unsigned flags = O_RDONLY|O_CLOEXEC|O_NONBLOCK;
-	int ret, fd = -1;
+	struct bch_data_ctx *ctx;
+	int ret;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
 
 	if (arg.op >= BCH_DATA_OP_NR || arg.flags)
 		return -EINVAL;
@@ -338,111 +475,180 @@ static long bch2_ioctl_data(struct bch_fs *c,
 	ctx->c = c;
 	ctx->arg = arg;
 
-	ctx->thread = kthread_create(bch2_data_thread, ctx, "[bcachefs]");
-	if (IS_ERR(ctx->thread)) {
-		ret = PTR_ERR(ctx->thread);
+	ret = bch2_run_thread_with_file(&ctx->thr,
+			&bcachefs_data_ops,
+			bch2_data_thread);
+	if (ret < 0)
+		kfree(ctx);
+	return ret;
+}
+
+static long bch2_ioctl_fs_usage(struct bch_fs *c,
+				struct bch_ioctl_fs_usage __user *user_arg)
+{
+	struct bch_ioctl_fs_usage *arg = NULL;
+	struct bch_replicas_usage *dst_e, *dst_end;
+	struct bch_fs_usage_online *src;
+	u32 replica_entries_bytes;
+	unsigned i;
+	int ret = 0;
+
+	if (!test_bit(BCH_FS_started, &c->flags))
+		return -EINVAL;
+
+	if (get_user(replica_entries_bytes, &user_arg->replica_entries_bytes))
+		return -EFAULT;
+
+	arg = kzalloc(size_add(sizeof(*arg), replica_entries_bytes), GFP_KERNEL);
+	if (!arg)
+		return -ENOMEM;
+
+	src = bch2_fs_usage_read(c);
+	if (!src) {
+		ret = -ENOMEM;
 		goto err;
 	}
 
-	ret = get_unused_fd_flags(flags);
-	if (ret < 0)
-		goto err;
-	fd = ret;
+	arg->capacity		= c->capacity;
+	arg->used		= bch2_fs_sectors_used(c, src);
+	arg->online_reserved	= src->online_reserved;
 
-	file = anon_inode_getfile("[bcachefs]", &bcachefs_data_ops, ctx, flags);
-	if (IS_ERR(file)) {
-		ret = PTR_ERR(file);
-		goto err;
+	for (i = 0; i < BCH_REPLICAS_MAX; i++)
+		arg->persistent_reserved[i] = src->u.persistent_reserved[i];
+
+	dst_e	= arg->replicas;
+	dst_end = (void *) arg->replicas + replica_entries_bytes;
+
+	for (i = 0; i < c->replicas.nr; i++) {
+		struct bch_replicas_entry_v1 *src_e =
+			cpu_replicas_entry(&c->replicas, i);
+
+		/* check that we have enough space for one replicas entry */
+		if (dst_e + 1 > dst_end) {
+			ret = -ERANGE;
+			break;
+		}
+
+		dst_e->sectors		= src->u.replicas[i];
+		dst_e->r		= *src_e;
+
+		/* recheck after setting nr_devs: */
+		if (replicas_usage_next(dst_e) > dst_end) {
+			ret = -ERANGE;
+			break;
+		}
+
+		memcpy(dst_e->r.devs, src_e->devs, src_e->nr_devs);
+
+		dst_e = replicas_usage_next(dst_e);
 	}
 
-	fd_install(fd, file);
+	arg->replica_entries_bytes = (void *) dst_e - (void *) arg->replicas;
 
-	get_task_struct(ctx->thread);
-	wake_up_process(ctx->thread);
+	percpu_up_read(&c->mark_lock);
+	kfree(src);
 
-	return fd;
+	if (ret)
+		goto err;
+
+	ret = copy_to_user_errcode(user_arg, arg,
+			sizeof(*arg) + arg->replica_entries_bytes);
 err:
-	if (fd >= 0)
-		put_unused_fd(fd);
-	if (!IS_ERR_OR_NULL(ctx->thread))
-		kthread_stop(ctx->thread);
-	kfree(ctx);
+	kfree(arg);
 	return ret;
 }
 
-static long bch2_ioctl_usage(struct bch_fs *c,
-			     struct bch_ioctl_usage __user *user_arg)
+/* obsolete, didn't allow for new data types: */
+static long bch2_ioctl_dev_usage(struct bch_fs *c,
+				 struct bch_ioctl_dev_usage __user *user_arg)
 {
-	struct bch_ioctl_usage arg;
+	struct bch_ioctl_dev_usage arg;
+	struct bch_dev_usage src;
 	struct bch_dev *ca;
-	unsigned i, j;
-	int ret;
+	unsigned i;
 
-	if (!test_bit(BCH_FS_STARTED, &c->flags))
+	if (!test_bit(BCH_FS_started, &c->flags))
 		return -EINVAL;
 
 	if (copy_from_user(&arg, user_arg, sizeof(arg)))
 		return -EFAULT;
 
-	for (i = 0; i < arg.nr_devices; i++) {
-		struct bch_ioctl_dev_usage dst = { .alive = 0 };
+	if ((arg.flags & ~BCH_BY_INDEX) ||
+	    arg.pad[0] ||
+	    arg.pad[1] ||
+	    arg.pad[2])
+		return -EINVAL;
 
-		ret = copy_to_user(&user_arg->devs[i], &dst, sizeof(dst));
-		if (ret)
-			return ret;
+	ca = bch2_device_lookup(c, arg.dev, arg.flags);
+	if (IS_ERR(ca))
+		return PTR_ERR(ca);
+
+	src = bch2_dev_usage_read(ca);
+
+	arg.state		= ca->mi.state;
+	arg.bucket_size		= ca->mi.bucket_size;
+	arg.nr_buckets		= ca->mi.nbuckets - ca->mi.first_bucket;
+
+	for (i = 0; i < BCH_DATA_NR; i++) {
+		arg.d[i].buckets	= src.d[i].buckets;
+		arg.d[i].sectors	= src.d[i].sectors;
+		arg.d[i].fragmented	= src.d[i].fragmented;
 	}
 
-	{
-		struct bch_fs_usage src = bch2_fs_usage_read(c);
-		struct bch_ioctl_fs_usage dst = {
-			.capacity		= c->capacity,
-			.used			= bch2_fs_sectors_used(c, src),
-			.online_reserved	= src.s.online_reserved,
-		};
+	percpu_ref_put(&ca->ref);
 
-		for (i = 0; i < BCH_REPLICAS_MAX; i++) {
-			dst.persistent_reserved[i] =
-				src.replicas[i].persistent_reserved;
+	return copy_to_user_errcode(user_arg, &arg, sizeof(arg));
+}
 
-			for (j = 0; j < BCH_DATA_NR; j++)
-				dst.sectors[j][i] = src.replicas[i].data[j];
-		}
+static long bch2_ioctl_dev_usage_v2(struct bch_fs *c,
+				 struct bch_ioctl_dev_usage_v2 __user *user_arg)
+{
+	struct bch_ioctl_dev_usage_v2 arg;
+	struct bch_dev_usage src;
+	struct bch_dev *ca;
+	int ret = 0;
 
-		ret = copy_to_user(&user_arg->fs, &dst, sizeof(dst));
-		if (ret)
-			return ret;
-	}
+	if (!test_bit(BCH_FS_started, &c->flags))
+		return -EINVAL;
 
-	for_each_member_device(ca, c, i) {
-		struct bch_dev_usage src = bch2_dev_usage_read(c, ca);
-		struct bch_ioctl_dev_usage dst = {
-			.alive		= 1,
-			.state		= ca->mi.state,
-			.bucket_size	= ca->mi.bucket_size,
-			.nr_buckets	= ca->mi.nbuckets - ca->mi.first_bucket,
-		};
+	if (copy_from_user(&arg, user_arg, sizeof(arg)))
+		return -EFAULT;
 
-		if (ca->dev_idx >= arg.nr_devices) {
-			percpu_ref_put(&ca->ref);
-			return -ERANGE;
-		}
+	if ((arg.flags & ~BCH_BY_INDEX) ||
+	    arg.pad[0] ||
+	    arg.pad[1] ||
+	    arg.pad[2])
+		return -EINVAL;
 
-		if (percpu_ref_tryget(&ca->io_ref)) {
-			dst.dev = huge_encode_dev(ca->disk_sb.bdev->bd_dev);
-			percpu_ref_put(&ca->io_ref);
-		}
+	ca = bch2_device_lookup(c, arg.dev, arg.flags);
+	if (IS_ERR(ca))
+		return PTR_ERR(ca);
 
-		for (j = 0; j < BCH_DATA_NR; j++) {
-			dst.buckets[j] = src.buckets[j];
-			dst.sectors[j] = src.sectors[j];
-		}
+	src = bch2_dev_usage_read(ca);
+
+	arg.state		= ca->mi.state;
+	arg.bucket_size		= ca->mi.bucket_size;
+	arg.nr_data_types	= min(arg.nr_data_types, BCH_DATA_NR);
+	arg.nr_buckets		= ca->mi.nbuckets - ca->mi.first_bucket;
+
+	ret = copy_to_user_errcode(user_arg, &arg, sizeof(arg));
+	if (ret)
+		goto err;
 
-		ret = copy_to_user(&user_arg->devs[i], &dst, sizeof(dst));
+	for (unsigned i = 0; i < arg.nr_data_types; i++) {
+		struct bch_ioctl_dev_usage_type t = {
+			.buckets	= src.d[i].buckets,
+			.sectors	= src.d[i].sectors,
+			.fragmented	= src.d[i].fragmented,
+		};
+
+		ret = copy_to_user_errcode(&user_arg->d[i], &t, sizeof(t));
 		if (ret)
-			return ret;
+			goto err;
 	}
-
-	return 0;
+err:
+	percpu_ref_put(&ca->ref);
+	return ret;
 }
 
 static long bch2_ioctl_read_super(struct bch_fs *c,
@@ -452,6 +658,9 @@ static long bch2_ioctl_read_super(struct bch_fs *c,
 	struct bch_sb *sb;
 	int ret = 0;
 
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	if ((arg.flags & ~(BCH_BY_INDEX|BCH_READ_DEV)) ||
 	    arg.pad)
 		return -EINVAL;
@@ -476,10 +685,10 @@ static long bch2_ioctl_read_super(struct bch_fs *c,
 		goto err;
 	}
 
-	ret = copy_to_user((void __user *)(unsigned long)arg.sb,
-			   sb, vstruct_bytes(sb));
+	ret = copy_to_user_errcode((void __user *)(unsigned long)arg.sb, sb,
+				   vstruct_bytes(sb));
 err:
-	if (ca)
+	if (!IS_ERR_OR_NULL(ca))
 		percpu_ref_put(&ca->ref);
 	mutex_unlock(&c->sb_lock);
 	return ret;
@@ -489,16 +698,20 @@ static long bch2_ioctl_disk_get_idx(struct bch_fs *c,
 				    struct bch_ioctl_disk_get_idx arg)
 {
 	dev_t dev = huge_decode_dev(arg.dev);
-	struct bch_dev *ca;
-	unsigned i;
 
-	for_each_online_member(ca, c, i)
-		if (ca->disk_sb.bdev->bd_dev == dev) {
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (!dev)
+		return -EINVAL;
+
+	for_each_online_member(c, ca)
+		if (ca->dev == dev) {
 			percpu_ref_put(&ca->io_ref);
-			return i;
+			return ca->dev_idx;
 		}
 
-	return -ENOENT;
+	return -BCH_ERR_ENOENT_dev_idx_not_found;
 }
 
 static long bch2_ioctl_disk_resize(struct bch_fs *c,
@@ -507,6 +720,9 @@ static long bch2_ioctl_disk_resize(struct bch_fs *c,
 	struct bch_dev *ca;
 	int ret;
 
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	if ((arg.flags & ~BCH_BY_INDEX) ||
 	    arg.pad)
 		return -EINVAL;
@@ -521,29 +737,146 @@ static long bch2_ioctl_disk_resize(struct bch_fs *c,
 	return ret;
 }
 
+static long bch2_ioctl_disk_resize_journal(struct bch_fs *c,
+				   struct bch_ioctl_disk_resize_journal arg)
+{
+	struct bch_dev *ca;
+	int ret;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if ((arg.flags & ~BCH_BY_INDEX) ||
+	    arg.pad)
+		return -EINVAL;
+
+	if (arg.nbuckets > U32_MAX)
+		return -EINVAL;
+
+	ca = bch2_device_lookup(c, arg.dev, arg.flags);
+	if (IS_ERR(ca))
+		return PTR_ERR(ca);
+
+	ret = bch2_set_nr_journal_buckets(c, ca, arg.nbuckets);
+
+	percpu_ref_put(&ca->ref);
+	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->stdio_filter = current;
+	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;
+	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);
+
+	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();
+
+	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 = bch2_run_thread_with_stdio(&thr->thr,
+			bch2_fsck_thread_exit,
+			bch2_fsck_online_thread_fn);
+err:
+	if (ret < 0) {
+		bch_err_fn(c, ret);
+		if (thr)
+			bch2_fsck_thread_exit(&thr->thr);
+		up(&c->online_fsck_mutex);
+		bch2_ro_ref_put(c);
+	}
+	return ret;
+}
+
 #define BCH_IOCTL(_name, _argtype)					\
 do {									\
 	_argtype i;							\
 									\
 	if (copy_from_user(&i, arg, sizeof(i)))				\
 		return -EFAULT;						\
-	return bch2_ioctl_##_name(c, i);				\
+	ret = bch2_ioctl_##_name(c, i);					\
+	goto out;							\
 } while (0)
 
 long bch2_fs_ioctl(struct bch_fs *c, unsigned cmd, void __user *arg)
 {
-	/* ioctls that don't require admin cap: */
+	long ret;
+
 	switch (cmd) {
 	case BCH_IOCTL_QUERY_UUID:
 		return bch2_ioctl_query_uuid(c, arg);
-	case BCH_IOCTL_USAGE:
-		return bch2_ioctl_usage(c, arg);
-	}
-
-	if (!capable(CAP_SYS_ADMIN))
-		return -EPERM;
-
-	switch (cmd) {
+	case BCH_IOCTL_FS_USAGE:
+		return bch2_ioctl_fs_usage(c, arg);
+	case BCH_IOCTL_DEV_USAGE:
+		return bch2_ioctl_dev_usage(c, arg);
+	case BCH_IOCTL_DEV_USAGE_V2:
+		return bch2_ioctl_dev_usage_v2(c, arg);
 #if 0
 	case BCH_IOCTL_START:
 		BCH_IOCTL(start, struct bch_ioctl_start);
@@ -556,10 +889,9 @@ long bch2_fs_ioctl(struct bch_fs *c, unsigned cmd, void __user *arg)
 		BCH_IOCTL(disk_get_idx, struct bch_ioctl_disk_get_idx);
 	}
 
-	if (!test_bit(BCH_FS_STARTED, &c->flags))
+	if (!test_bit(BCH_FS_started, &c->flags))
 		return -EINVAL;
 
-	/* ioctls that do require admin cap: */
 	switch (cmd) {
 	case BCH_IOCTL_DISK_ADD:
 		BCH_IOCTL(disk_add, struct bch_ioctl_disk);
@@ -575,10 +907,17 @@ long bch2_fs_ioctl(struct bch_fs *c, unsigned cmd, void __user *arg)
 		BCH_IOCTL(data, struct bch_ioctl_data);
 	case BCH_IOCTL_DISK_RESIZE:
 		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;
 	}
+out:
+	if (ret < 0)
+		ret = bch2_err_class(ret);
+	return ret;
 }
 
 static DEFINE_IDR(bch_chardev_minor);
@@ -644,7 +983,7 @@ int __init bch2_chardev_init(void)
 	if (bch_chardev_major < 0)
 		return bch_chardev_major;
 
-	bch_chardev_class = class_create(THIS_MODULE, "bcachefs");
+	bch_chardev_class = class_create("bcachefs");
 	if (IS_ERR(bch_chardev_class))
 		return PTR_ERR(bch_chardev_class);