diff --git a/fs/filesystems.c b/fs/filesystems.c
index 3083d904df9b..9429844bf6bf 100644
--- a/fs/filesystems.c
+++ b/fs/filesystems.c
@@ -18,6 +18,7 @@
#include <linux/uaccess.h>
#include <linux/fs_parser.h>
#include <linux/rculist.h>
+#include "internal.h"
/*
* Read-mostly filesystem drivers list.
@@ -390,6 +391,20 @@ static struct file_system_type *__get_fs_type(const char *name, int len)
return fs;
}
+struct file_system_type *get_fs_type_noload(const char *name)
+{
+ struct file_system_type *fs;
+ const char *dot = strchr(name, '.');
+ int len = dot ? dot - name : strlen(name);
+
+ fs = __get_fs_type(name, len);
+ if (dot && fs && !(fs->fs_flags & FS_HAS_SUBTYPE)) {
+ put_filesystem(fs);
+ fs = NULL;
+ }
+ return fs;
+}
+
struct file_system_type *get_fs_type(const char *name)
{
struct file_system_type *fs;diff --git a/fs/fs_context.c b/fs/fs_context.c
index a50584df97be..542dede2f864 100644
--- a/fs/fs_context.c
+++ b/fs/fs_context.c
@@ -259,7 +259,8 @@ static struct fs_context *alloc_fs_context(struct file_system_type *fs_type,
struct dentry *reference,
unsigned int sb_flags,
unsigned int sb_flags_mask,
- enum fs_context_purpose purpose)
+ enum fs_context_purpose purpose,
+ bool init)
{
struct fs_context *fc;
int ret = -ENOMEM;@@ -292,6 +293,9 @@ static struct fs_context *alloc_fs_context(struct file_system_type *fs_type,
break;
}
+ if (!init)
+ return fc;
+
ret = fc->fs_type->init_fs_context(fc);
if (ret < 0)
goto err_fc;
@@ -307,10 +311,16 @@ struct fs_context *fs_context_for_mount(struct file_system_type *fs_type,
unsigned int sb_flags)
{
return alloc_fs_context(fs_type, NULL, sb_flags, 0,
- FS_CONTEXT_FOR_MOUNT);
+ FS_CONTEXT_FOR_MOUNT, true);
}
EXPORT_SYMBOL(fs_context_for_mount);
+struct fs_context *fs_context_for_unpriv_mount(struct file_system_type *fs_type)
+{
+ return alloc_fs_context(fs_type, NULL, 0, 0,
+ FS_CONTEXT_FOR_MOUNT, false);
+}
+
struct fs_context *fs_context_for_reconfigure(struct dentry *dentry,
unsigned int sb_flags,
unsigned int sb_flags_mask)@@ -320,7 +330,8 @@ struct fs_context *fs_context_for_reconfigure(struct dentry *dentry,
return ERR_PTR(-EINVAL);
return alloc_fs_context(dentry->d_sb->s_type, dentry, sb_flags,
- sb_flags_mask, FS_CONTEXT_FOR_RECONFIGURE);
+ sb_flags_mask, FS_CONTEXT_FOR_RECONFIGURE,
+ true);
}
/**
@@ -337,7 +348,8 @@ struct fs_context *fs_context_for_submount(struct file_system_type *type,
struct fs_context *fc;
int ret;
- fc = alloc_fs_context(type, reference, 0, 0, FS_CONTEXT_FOR_SUBMOUNT);
+ fc = alloc_fs_context(type, reference, 0, 0, FS_CONTEXT_FOR_SUBMOUNT,
+ true);
if (IS_ERR(fc))
return fc;
diff --git a/fs/fsopen.c b/fs/fsopen.c
index 70024870fefa..3e36270baadb 100644
--- a/fs/fsopen.c
+++ b/fs/fsopen.c
@@ -13,9 +13,14 @@
#include <linux/security.h>
#include <linux/anon_inodes.h>
#include <linux/namei.h>
+#include <linux/capability.h>
+#include <linux/nsproxy.h>
+#include <linux/rootns.h>
+#include <linux/user_namespace.h>
#include <linux/file.h>
#include <uapi/linux/mount.h>
#include <linux/audit.h>
+#include <net/net_namespace.h>
#include "internal.h"
#include "mount.h"
@@ -41,6 +46,76 @@ static inline const char *fetch_message_locked(struct fc_log *log, size_t len,
return p;
}
+/**
+ * DOC: FSCONFIG_SET_ROOTNS
+ *
+ * ``fsconfig(fsfd, FSCONFIG_SET_ROOTNS, NULL, NULL, rootnsfd)`` binds a newly
+ * opened filesystem context to ``rootnsfd`` once before any parameters are
+ * supplied (subsequent calls fail with ``-EBUSY``).
+ *
+ * The caller must hold ``CAP_SYS_ADMIN`` in the target ``rootns`` user
+ * namespace, allowing unprivileged callers to configure ``FS_USERNS_MOUNT``
+ * filesystems without entering the user namespace first.
+ *
+ * The context is initialized against the ``rootns`` network namespace,
+ * ``fc->user_ns`` is delegated to the ``rootns`` user namespace for
+ * ``FS_USERNS_MOUNT`` and ``FS_USERNS_DELEGATABLE`` filesystems when the
+ * mounter ``fsuid``/``fsgid`` map into it or the caller lacks
+ * ``CAP_SYS_ADMIN`` in its own user namespace, and ``proc`` and ``mqueue``
+ * contexts bind to the target ``rootns`` PID and IPC namespaces.
+ */
+static int fsconfig_set_rootns(struct fs_context *fc, struct fs_parameter *param)
+{
+ struct user_namespace *user_ns;
+ struct rootns *c;
+ int ret;
+
+ if (!is_rootns_file(param->file))
+ return -EINVAL;
+
+ c = param->file->private_data;
+ user_ns = c->user_ns;
+ if (!ns_capable(user_ns, CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (fc->need_free && fc->ops && fc->ops->free)
+ fc->ops->free(fc);
+ fc->need_free = false;
+ fc->fs_private = NULL;
+ fc->s_fs_info = NULL;
+ fc->ops = NULL;
+ fc->sb_flags = 0;
+ fc->global = false;
+ security_free_mnt_opts(&fc->security);
+
+ put_net(fc->net_ns);
+ fc->net_ns = get_net(c->ns->net_ns);
+ put_user_ns(fc->user_ns);
+ if ((fc->fs_type->fs_flags & (FS_USERNS_MOUNT | FS_USERNS_DELEGATABLE)) &&
+ ((kuid_has_mapping(user_ns, fc->cred->fsuid) &&
+ kgid_has_mapping(user_ns, fc->cred->fsgid)) ||
+ !ns_capable(fc->cred->user_ns, CAP_SYS_ADMIN)))
+ fc->user_ns = get_user_ns(user_ns);
+ else
+ fc->user_ns = get_user_ns(fc->cred->user_ns);
+
+ ret = fc->fs_type->init_fs_context(fc);
+ if (ret < 0) {
+ fc->phase = FS_CONTEXT_FAILED;
+ return ret;
+ }
+ fc->need_free = true;
+
+ if (fc->ops->set_rootns) {
+ ret = fc->ops->set_rootns(fc, c);
+ if (ret < 0)
+ return ret;
+ }
+ fc->rootns_bound = true;
+ fc->phase = FS_CONTEXT_CREATE_PARAMS;
+ return 0;
+}
+
/*
* Allow the user to read back any error, warning or informational messages.
* Only one message is returned for each read(2) call.@@ -123,9 +198,11 @@ SYSCALL_DEFINE2(fsopen, const char __user *, _fs_name, unsigned int, flags)
struct file_system_type *fs_type;
struct fs_context *fc;
const char *fs_name;
+ bool priv;
int ret;
- if (!may_mount())
+ priv = may_mount();
+ if (!priv && !IS_ENABLED(CONFIG_ROOTNS))
return -EPERM;
if (flags & ~FSOPEN_CLOEXEC)
@@ -137,17 +214,23 @@ SYSCALL_DEFINE2(fsopen, const char __user *, _fs_name, unsigned int, flags)
audit_log_fsopen(fs_name);
- fs_type = get_fs_type(fs_name);
+ fs_type = priv ? get_fs_type(fs_name) : get_fs_type_noload(fs_name);
kfree(fs_name);
if (!fs_type)
- return -ENODEV;
+ return priv ? -ENODEV : -EPERM;
- fc = fs_context_for_mount(fs_type, 0);
+ if (!priv && !(fs_type->fs_flags & FS_USERNS_MOUNT)) {
+ put_filesystem(fs_type);
+ return -EPERM;
+ }
+
+ fc = priv ? fs_context_for_mount(fs_type, 0) :
+ fs_context_for_unpriv_mount(fs_type);
put_filesystem(fs_type);
if (IS_ERR(fc))
return PTR_ERR(fc);
- fc->phase = FS_CONTEXT_CREATE_PARAMS;
+ fc->phase = priv ? FS_CONTEXT_CREATE_NS : FS_CONTEXT_AWAITING_NS;
ret = fscontext_alloc_log(fc);
if (ret < 0)@@ -222,7 +305,8 @@ static int vfs_cmd_create(struct fs_context *fc, bool exclusive)
struct super_block *sb;
int ret;
- if (fc->phase != FS_CONTEXT_CREATE_PARAMS)
+ if (fc->phase != FS_CONTEXT_CREATE_NS &&
+ fc->phase != FS_CONTEXT_CREATE_PARAMS)
return -EBUSY;
if (!mount_capable(fc))
@@ -291,6 +375,8 @@ static int vfs_fsconfig_locked(struct fs_context *fc, int cmd,
ret = finish_clean_context(fc);
if (ret)
return ret;
+ if (fc->phase == FS_CONTEXT_AWAITING_NS && cmd != FSCONFIG_SET_ROOTNS)
+ return -EPERM;
switch (cmd) {
case FSCONFIG_CMD_CREATE:
return vfs_cmd_create(fc, false);@@ -298,9 +384,17 @@ static int vfs_fsconfig_locked(struct fs_context *fc, int cmd,
return vfs_cmd_create(fc, true);
case FSCONFIG_CMD_RECONFIGURE:
return vfs_cmd_reconfigure(fc);
+ case FSCONFIG_SET_ROOTNS:
+ if (fc->phase != FS_CONTEXT_AWAITING_NS &&
+ fc->phase != FS_CONTEXT_CREATE_NS)
+ return -EBUSY;
+ return fsconfig_set_rootns(fc, param);
+
default:
- if (fc->phase != FS_CONTEXT_CREATE_PARAMS &&
- fc->phase != FS_CONTEXT_RECONF_PARAMS)
+ if (fc->phase == FS_CONTEXT_CREATE_NS)
+ fc->phase = FS_CONTEXT_CREATE_PARAMS;
+ else if (fc->phase != FS_CONTEXT_CREATE_PARAMS &&
+ fc->phase != FS_CONTEXT_RECONF_PARAMS)
return -EBUSY;
return vfs_parse_fs_param(fc, param);
@@ -390,6 +484,10 @@ SYSCALL_DEFINE5(fsconfig,
if (!_key || _value || aux < 0)
return -EINVAL;
break;
+ case FSCONFIG_SET_ROOTNS:
+ if (_key || _value || aux < 0)
+ return -EINVAL;
+ break;
case FSCONFIG_CMD_CREATE:
case FSCONFIG_CMD_CREATE_EXCL:
case FSCONFIG_CMD_RECONFIGURE:
@@ -457,6 +555,12 @@ SYSCALL_DEFINE5(fsconfig,
goto out_key;
param.dirfd = aux;
break;
+ case FSCONFIG_SET_ROOTNS:
+ ret = -EBADF;
+ param.file = fget(aux);
+ if (!param.file)
+ goto out_key;
+ break;
default:
break;
}
@@ -482,6 +586,7 @@ SYSCALL_DEFINE5(fsconfig,
putname(param.name);
break;
case FSCONFIG_SET_FD:
+ case FSCONFIG_SET_ROOTNS:
if (param.file)
fput(param.file);
break;
diff --git a/fs/internal.h b/fs/internal.h
index 3f2fbac40f8e..d6815bf6ea9b 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -40,12 +40,18 @@ int __block_write_begin_int(struct folio *folio, loff_t pos, unsigned len,
*/
extern void __init chrdev_init(void);
+/*
+ * filesystems.c
+ */
+struct file_system_type *get_fs_type_noload(const char *name);
+
/*
* fs_context.c
*/
extern int parse_monolithic_mount_data(struct fs_context *, void *);
extern void vfs_clean_context(struct fs_context *fc);
extern int finish_clean_context(struct fs_context *fc);
+struct fs_context *fs_context_for_unpriv_mount(struct file_system_type *fs_type);
/*
* namei.c
diff --git a/fs/namespace.c b/fs/namespace.c
index 781380945d78..a6c0a31e275a 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -4623,7 +4623,8 @@ SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags,
!ns_capable(current_user_ns(), CAP_SYS_ADMIN))
return -EPERM;
- if (!(flags & FSMOUNT_NAMESPACE) && !may_mount())
+ if (!(flags & FSMOUNT_NAMESPACE) && !IS_ENABLED(CONFIG_ROOTNS) &&
+ !may_mount())
return -EPERM;
if (attr_flags & ~FSMOUNT_VALID_FLAGS)
@@ -4658,6 +4659,16 @@ SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags,
if (ret)
return ret;
+ if (!(flags & FSMOUNT_NAMESPACE)) {
+ if (fc->rootns_bound) {
+ if (!ns_capable(fc->user_ns, CAP_SYS_ADMIN) &&
+ !may_mount())
+ return -EPERM;
+ } else if (!may_mount()) {
+ return -EPERM;
+ }
+ }
+
/* There must be a valid superblock or we can't mount it */
ret = -EINVAL;
if (!fc->root)@@ -4699,7 +4710,8 @@ SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags,
return FD_ADD((flags & FSMOUNT_CLOEXEC) ? O_CLOEXEC : 0,
open_new_namespace(&new_path, MOUNT_COPY_NEW));
- ns = alloc_mnt_ns(current->nsproxy->mnt_ns->user_ns, true);
+ ns = alloc_mnt_ns(fc->rootns_bound ? fc->user_ns :
+ current->nsproxy->mnt_ns->user_ns, true);
if (IS_ERR(ns))
return PTR_ERR(ns);
mnt = real_mount(new_path.mnt);
@@ -6582,6 +6594,7 @@ static bool mnt_already_visible(struct mnt_namespace *ns,
const struct super_block *sb,
int *new_mnt_flags)
{
+ bool foreign_ns = !ns_capable_noaudit(ns->user_ns, CAP_SYS_ADMIN);
int new_flags = *new_mnt_flags;
struct mount *mnt;
@@ -6611,6 +6624,11 @@ static bool mnt_already_visible(struct mnt_namespace *ns,
/* Don't miss readonly hidden in the superblock flags */
if (sb_rdonly(mnt->mnt.mnt_sb))
mnt_flags |= MNT_LOCK_READONLY;
+ if (foreign_ns) {
+ if (mnt_flags & MNT_READONLY)
+ mnt_flags |= MNT_LOCK_READONLY;
+ mnt_flags |= MNT_LOCK_ATIME;
+ }
/* Verify the mount flags are equal to or more permissive
* than the proposed new mount.@@ -6629,7 +6647,7 @@ static bool mnt_already_visible(struct mnt_namespace *ns,
list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
struct inode *inode = child->mnt_mountpoint->d_inode;
/* Only worry about locked mounts */
- if (!(child->mnt.mnt_flags & MNT_LOCKED))
+ if (!foreign_ns && !(child->mnt.mnt_flags & MNT_LOCKED))
continue;
/* Is the directory permanently empty? */
if (!is_empty_dir_inode(inode))@@ -6650,13 +6668,18 @@ static bool mount_too_revealing(const struct super_block *sb, int *new_mnt_flags
struct mnt_namespace *ns = current->nsproxy->mnt_ns;
unsigned long s_iflags;
- if (ns->user_ns == &init_user_ns)
- return false;
-
/* Can this filesystem be too revealing? */
if (!(sb->s_type->fs_flags & FS_USERNS_MOUNT_RESTRICTED))
return false;
+ if (ns->user_ns == &init_user_ns &&
+ ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN))
+ return false;
+
+ if (!ns_capable_noaudit(ns->user_ns, CAP_SYS_ADMIN) &&
+ current_chrooted())
+ return true;
+
s_iflags = sb->s_iflags;
if ((s_iflags & required_iflags) != required_iflags) {
WARN_ONCE(1, "Expected s_iflags to contain 0x%lx\n",diff --git a/fs/proc/root.c b/fs/proc/root.c
index 7fbbe92bf73a..323296b03089 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -15,6 +15,8 @@
#include <linux/sched/stat.h>
#include <linux/module.h>
#include <linux/bitops.h>
+#include <linux/nsproxy.h>
+#include <linux/rootns.h>
#include <linux/user_namespace.h>
#include <linux/fs_context.h>
#include <linux/mount.h>
@@ -323,6 +325,21 @@ static int proc_get_tree(struct fs_context *fc)
return get_tree_nodev(fc, proc_fill_super);
}
+static int proc_set_rootns(struct fs_context *fc, struct rootns *rootns)
+{
+ struct proc_fs_context *ctx = fc->fs_private;
+ struct pid_namespace *target = rootns->ns->pid_ns_for_children;
+
+ if (!pidns_is_ancestor(target, task_active_pid_ns(current)))
+ return invalfc(fc, "cannot set pidns to non-descendant pidns");
+
+ put_pid_ns(ctx->pid_ns);
+ ctx->pid_ns = get_pid_ns(target);
+ put_user_ns(fc->user_ns);
+ fc->user_ns = get_user_ns(ctx->pid_ns->user_ns);
+ return 0;
+}
+
static void proc_fs_context_free(struct fs_context *fc)
{
struct proc_fs_context *ctx = fc->fs_private;@@ -334,6 +351,7 @@ static void proc_fs_context_free(struct fs_context *fc)
static const struct fs_context_operations proc_fs_context_ops = {
.free = proc_fs_context_free,
.parse_param = proc_parse_param,
+ .set_rootns = proc_set_rootns,
.get_tree = proc_get_tree,
.reconfigure = proc_reconfigure,
};diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h
index d1727dffecc5..b1adcd6ed693 100644
--- a/include/linux/fs_context.h
+++ b/include/linux/fs_context.h
@@ -21,6 +21,7 @@ struct file_system_type;
struct mnt_namespace;
struct net;
struct pid_namespace;
+struct rootns;
struct super_block;
struct user_namespace;
struct vfsmount;
@@ -36,6 +37,8 @@ enum fs_context_purpose {
* Userspace usage phase for fsopen/fspick.
*/
enum fs_context_phase {
+ FS_CONTEXT_AWAITING_NS, /* Unprivileged context awaiting target ns */
+ FS_CONTEXT_CREATE_NS, /* Set namespaces for sb creation */
FS_CONTEXT_CREATE_PARAMS, /* Loading params for sb creation */
FS_CONTEXT_CREATING, /* A superblock is being created */
FS_CONTEXT_AWAITING_MOUNT, /* Superblock created, awaiting fsmount() */@@ -110,6 +113,7 @@ struct fs_context {
bool global:1; /* Goes into &init_user_ns */
bool oldapi:1; /* Coming from mount(2) */
bool exclusive:1; /* create new superblock, reject existing one */
+ bool rootns_bound:1; /* Bound via FSCONFIG_SET_ROOTNS */
};
struct fs_context_operations {@@ -117,6 +121,7 @@ struct fs_context_operations {
int (*dup)(struct fs_context *fc, struct fs_context *src_fc);
int (*parse_param)(struct fs_context *fc, struct fs_parameter *param);
int (*parse_monolithic)(struct fs_context *fc, void *data);
+ int (*set_rootns)(struct fs_context *fc, struct rootns *rootns);
int (*get_tree)(struct fs_context *fc);
int (*reconfigure)(struct fs_context *fc);
};diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h
index ac865edac517..cb55cfcfc92e 100644
--- a/include/uapi/linux/mount.h
+++ b/include/uapi/linux/mount.h
@@ -105,6 +105,7 @@ enum fsconfig_command {
FSCONFIG_CMD_CREATE = 6, /* Create new or reuse existing superblock */
FSCONFIG_CMD_RECONFIGURE = 7, /* Invoke superblock reconfiguration */
FSCONFIG_CMD_CREATE_EXCL = 8, /* Create new superblock, fail if reusing existing superblock */
+ FSCONFIG_SET_ROOTNS = 9, /* Set a rootns, supplied by fd */
};
/*diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index 322c3dd98c44..f94e9b566bd0 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -32,6 +32,7 @@
#include <linux/mutex.h>
#include <linux/nsproxy.h>
#include <linux/pid.h>
+#include <linux/rootns.h>
#include <linux/ipc_namespace.h>
#include <linux/user_namespace.h>
#include <linux/slab.h>
@@ -400,6 +401,17 @@ static struct inode *mqueue_get_inode(struct super_block *sb,
return ERR_PTR(ret);
}
+static int mqueue_set_rootns(struct fs_context *fc, struct rootns *rootns)
+{
+ struct mqueue_fs_context *ctx = fc->fs_private;
+
+ put_ipc_ns(ctx->ipc_ns);
+ ctx->ipc_ns = get_ipc_ns(rootns->ns->ipc_ns);
+ put_user_ns(fc->user_ns);
+ fc->user_ns = get_user_ns(ctx->ipc_ns->user_ns);
+ return 0;
+}
+
static int mqueue_fill_super(struct super_block *sb, struct fs_context *fc)
{
struct inode *inode;@@ -1613,6 +1625,7 @@ static const struct super_operations mqueue_super_ops = {
static const struct fs_context_operations mqueue_fs_context_ops = {
.free = mqueue_fs_context_free,
+ .set_rootns = mqueue_set_rootns,
.get_tree = mqueue_get_tree,
};
--
2.47.3