FUSE mounts from non-init user namespaces
Subsystems (14)
PATCH v8 5/6 fuse: Support fuse filesystems outside of init_user_ns
In reply to a message not in the archiveIn order to support mounts from namespaces other than init_user_ns, fuse must translate uids and gids to/from the userns of the process servicing requests on /dev/fuse. This patch does that, with a couple of restrictions on the namespace:
- The userns for the fuse connection is fixed to the namespace from which /dev/fuse is opened.
- The namespace must be the same as s_user_ns.
These restrictions simplify the implementation by avoiding the need to pass around userns references and by allowing fuse to rely on the checks in setattr_prepare for ownership changes. Either restriction could be relaxed in the future if needed.
For cuse the userns used is the opener of /dev/cuse. Semantically the cuse support does not appear safe for unprivileged users. Practically the permissions on /dev/cuse only make it accessible to the global root user. If something slips through the cracks in a user namespace the only users who will be able to use the cuse device are those users mapped into the user namespace.
Translation in the posix acl is updated to use the uuser namespace of the filesystem. Avoiding cases which might bypass this translation is handled in a following change.
This change is stronlgy based on a similar change from Seth Forshee and Dongsu Park.
--- fs/fuse/acl.c | 4 ++-- fs/fuse/cuse.c | 7 ++++++- fs/fuse/dev.c | 4 ++-- fs/fuse/dir.c | 14 +++++++------- fs/fuse/fuse_i.h | 6 +++++- fs/fuse/inode.c | 31 +++++++++++++++++++------------ 6 files changed, 41 insertions(+), 25 deletions(-)
fs/fuse/acl.c +2 -2
@@ -34,7 +34,7 @@ struct posix_acl *fuse_get_acl(struct inode *inode, int type)return ERR_PTR (-ENOMEM ); size =fuse_getxattr (inode, name, value,PAGE_SIZE );if (size >0 ) - acl =posix_acl_from_xattr (&init_user_ns, value, size); + acl =posix_acl_from_xattr (fc->user_ns, value, size);else if ((size ==0 ) || (size == -ENODATA ) || (size == -EOPNOTSUPP && fc->no_getxattr)) acl =NULL ;
@@ -83,7 +83,7 @@ int fuse_set_acl(struct inode *inode, struct posix_acl *acl, int type)if (!value)return -ENOMEM ; - ret =posix_acl_to_xattr (&init_user_ns, acl, value, size); + ret =posix_acl_to_xattr (fc->user_ns, acl, value, size);if (ret <0 ) {kfree (value);return ret;
fs/fuse/cuse.c +6 -1
@@ -48,6 +48,7 @@#include <linux/stat.h> #include <linux/module.h> #include <linux/uio.h> +#include <linux/user_namespace.h> #include "fuse_i.h"
@@ -498,7 +499,11 @@ static int cuse_channel_open(struct inode *inode, struct file *file)if (!cc)return -ENOMEM ; -fuse_conn_init (&cc->fc); +/* +* Limit the cuse channel to requests that can +* be represented in file->f_cred->user_ns. +*/ +fuse_conn_init (&cc->fc, file->f_cred->user_ns); fud =fuse_dev_alloc (&cc->fc);if (!fud) {
fs/fuse/dev.c +2 -2
@@ -114,8 +114,8 @@ static void __fuse_put_request(struct fuse_req *req)static bool fuse_req_init_context (struct fuse_conn *fc,struct fuse_req *req) { - req->in.h.uid =from_kuid (&init_user_ns,current_fsuid ()); - req->in.h.gid =from_kgid (&init_user_ns,current_fsgid ()); + req->in.h.uid =from_kuid (fc->user_ns,current_fsuid ()); + req->in.h.gid =from_kgid (fc->user_ns,current_fsgid ()); req->in.h.pid =pid_nr_ns (task_pid (current), fc->pid_ns);return (req->in.h.uid != ((uid_t)-1 )) && (req->in.h.gid != ((gid_t)-1 ));
fs/fuse/dir.c +7 -7
@@ -858,8 +858,8 @@ static void fuse_fillattr(struct inode *inode, struct fuse_attr *attr, stat->ino = attr->ino; stat->mode = (inode->i_mode &S_IFMT ) | (attr->mode &07777 ); stat->nlink = attr->nlink; - stat->uid =make_kuid (&init_user_ns, attr->uid); - stat->gid =make_kgid (&init_user_ns, attr->gid); + stat->uid =make_kuid (fc->user_ns, attr->uid); + stat->gid =make_kgid (fc->user_ns, attr->gid); stat->rdev = inode->i_rdev; stat->atime.tv_sec = attr->atime; stat->atime.tv_nsec = attr->atimensec;
@@ -1475,17 +1475,17 @@ static bool update_mtime(unsigned ivalid, bool trust_local_mtime)return true; } -static void iattr_to_fattr (struct iattr *iattr,struct fuse_setattr_in *arg, -bool trust_local_cmtime) +static void iattr_to_fattr (struct fuse_conn *fc,struct iattr *iattr, +struct fuse_setattr_in *arg,bool trust_local_cmtime) {unsigned ivalid = iattr->ia_valid;if (ivalid &ATTR_MODE ) arg->valid |=FATTR_MODE , arg->mode = iattr->ia_mode;if (ivalid &ATTR_UID ) - arg->valid |=FATTR_UID , arg->uid =from_kuid (&init_user_ns, iattr->ia_uid); + arg->valid |=FATTR_UID , arg->uid =from_kuid (fc->user_ns, iattr->ia_uid);if (ivalid &ATTR_GID ) - arg->valid |=FATTR_GID , arg->gid =from_kgid (&init_user_ns, iattr->ia_gid); + arg->valid |=FATTR_GID , arg->gid =from_kgid (fc->user_ns, iattr->ia_gid);if (ivalid &ATTR_SIZE ) arg->valid |=FATTR_SIZE , arg->size = iattr->ia_size;if (ivalid &ATTR_ATIME ) {
@@ -1646,7 +1646,7 @@ int fuse_do_setattr(struct dentry *dentry, struct iattr *attr,memset (&inarg,0 ,sizeof (inarg));memset (&outarg,0 ,sizeof (outarg)); -iattr_to_fattr (attr, &inarg, trust_local_cmtime); +iattr_to_fattr (fc, attr, &inarg, trust_local_cmtime);if (file) {struct fuse_file *ff = file->private_data; inarg.valid |=FATTR_FH ;
fs/fuse/fuse_i.h +5 -1
@@ -26,6 +26,7 @@#include <linux/xattr.h> #include <linux/pid_namespace.h> #include <linux/refcount.h> +#include <linux/user_namespace.h> /** Max number of pages that can be used in a single read request */ #define FUSE_MAX_PAGES_PER_REQ 32
@@ -466,6 +467,9 @@ struct fuse_conn {/** The pid namespace for this mount */ struct pid_namespace *pid_ns; +/** The user namespace for this mount */ +struct user_namespace *user_ns; +/** Maximum read size */ unsigned max_read;
@@ -870,7 +874,7 @@ struct fuse_conn *fuse_conn_get(struct fuse_conn *fc);/** * Initialize fuse_conn */ -void fuse_conn_init (struct fuse_conn *fc); +void fuse_conn_init (struct fuse_conn *fc,struct user_namespace *user_ns);/** * Release reference to fuse_conn
fs/fuse/inode.c +19 -12
@@ -171,8 +171,8 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr, inode->i_ino =fuse_squash_ino (attr->ino); inode->i_mode = (inode->i_mode &S_IFMT ) | (attr->mode &07777 );set_nlink (inode, attr->nlink); - inode->i_uid =make_kuid (&init_user_ns, attr->uid); - inode->i_gid =make_kgid (&init_user_ns, attr->gid); + inode->i_uid =make_kuid (fc->user_ns, attr->uid); + inode->i_gid =make_kgid (fc->user_ns, attr->gid); inode->i_blocks = attr->blocks; inode->i_atime.tv_sec = attr->atime; inode->i_atime.tv_nsec = attr->atimensec;
@@ -477,7 +477,8 @@ static int fuse_match_uint(substring_t *s, unsigned int *res)return err; } -static int parse_fuse_opt (char *opt,struct fuse_mount_data *d,int is_bdev) +static int parse_fuse_opt (char *opt,struct fuse_mount_data *d,int is_bdev, +struct user_namespace *user_ns) {char *p;memset (d,0 ,sizeof (struct fuse_mount_data ));
@@ -513,7 +514,7 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)case OPT_USER_ID :if (fuse_match_uint (&args[0 ], &uv))return 0 ; - d->user_id =make_kuid (current_user_ns (), uv); + d->user_id =make_kuid (user_ns, uv);if (!uid_valid (d->user_id))return 0 ; d->user_id_present =1 ;
@@ -522,7 +523,7 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)case OPT_GROUP_ID :if (fuse_match_uint (&args[0 ], &uv))return 0 ; - d->group_id =make_kgid (current_user_ns (), uv); + d->group_id =make_kgid (user_ns, uv);if (!gid_valid (d->group_id))return 0 ; d->group_id_present =1 ;
@@ -565,8 +566,8 @@ static int fuse_show_options(struct seq_file *m, struct dentry *root)struct super_block *sb = root->d_sb;struct fuse_conn *fc =get_fuse_conn_super (sb); -seq_printf (m,",user_id=%u" ,from_kuid_munged (&init_user_ns, fc->user_id)); -seq_printf (m,",group_id=%u" ,from_kgid_munged (&init_user_ns, fc->group_id)); +seq_printf (m,",user_id=%u" ,from_kuid_munged (fc->user_ns, fc->user_id)); +seq_printf (m,",group_id=%u" ,from_kgid_munged (fc->user_ns, fc->group_id));if (fc->default_permissions)seq_puts (m,",default_permissions" );if (fc->allow_other)
@@ -597,7 +598,7 @@ static void fuse_pqueue_init(struct fuse_pqueue *fpq) fpq->connected =1 ; } -void fuse_conn_init (struct fuse_conn *fc) +void fuse_conn_init (struct fuse_conn *fc,struct user_namespace *user_ns) {memset (fc,0 ,sizeof (*fc));spin_lock_init (&fc->lock);
@@ -621,6 +622,7 @@ void fuse_conn_init(struct fuse_conn *fc) fc->attr_version =1 ;get_random_bytes (&fc->scramble_key,sizeof (fc->scramble_key)); fc->pid_ns =get_pid_ns (task_active_pid_ns (current)); + fc->user_ns =get_user_ns (user_ns); }EXPORT_SYMBOL_GPL (fuse_conn_init);
@@ -630,6 +632,7 @@ void fuse_conn_put(struct fuse_conn *fc)if (fc->destroy_req)fuse_request_free (fc->destroy_req);put_pid_ns (fc->pid_ns); +put_user_ns (fc->user_ns); fc->release (fc); } }
@@ -1060,7 +1063,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) sb->s_flags &= ~(SB_NOSEC |SB_I_VERSION ); -if (!parse_fuse_opt (data, &d, is_bdev)) +if (!parse_fuse_opt (data, &d, is_bdev, sb->s_user_ns)) goto err;if (is_bdev) {
@@ -1085,8 +1088,12 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)if (!file) goto err; -if ((file->f_op != &fuse_dev_operations) || - (file->f_cred->user_ns != &init_user_ns)) +/* +* Require mount to happen from the same user namespace which +* opened /dev/fuse to prevent potential attacks. +*/ +if (file->f_op != &fuse_dev_operations || + file->f_cred->user_ns != sb->s_user_ns) goto err_fput; fc =kmalloc (sizeof (*fc),GFP_KERNEL );
@@ -1094,7 +1101,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)if (!fc) goto err_fput; -fuse_conn_init (fc); +fuse_conn_init (fc, sb->s_user_ns); fc->release = fuse_free_conn; fud =fuse_dev_alloc (fc);
Signature · 1 line
2.14.1
PATCH v8 5/6 fuse: Support fuse filesystems outside of init_user_ns
In reply to Eric W. BiedermanIn order to support mounts from namespaces other than init_user_ns, fuse must translate uids and gids to/from the userns of the process servicing requests on /dev/fuse. This patch does that, with a couple of restrictions on the namespace:
- The userns for the fuse connection is fixed to the namespace from which /dev/fuse is opened.
- The namespace must be the same as s_user_ns.
These restrictions simplify the implementation by avoiding the need to pass around userns references and by allowing fuse to rely on the checks in setattr_prepare for ownership changes. Either restriction could be relaxed in the future if needed.
For cuse the userns used is the opener of /dev/cuse. Semantically the cuse support does not appear safe for unprivileged users. Practically the permissions on /dev/cuse only make it accessible to the global root user. If something slips through the cracks in a user namespace the only users who will be able to use the cuse device are those users mapped into the user namespace.
Translation in the posix acl is updated to use the uuser namespace of the filesystem. Avoiding cases which might bypass this translation is handled in a following change.
This change is stronlgy based on a similar change from Seth Forshee and Dongsu Park.
--- fs/fuse/acl.c | 4 ++-- fs/fuse/cuse.c | 7 ++++++- fs/fuse/dev.c | 4 ++-- fs/fuse/dir.c | 14 +++++++------- fs/fuse/fuse_i.h | 6 +++++- fs/fuse/inode.c | 31 +++++++++++++++++++------------ 6 files changed, 41 insertions(+), 25 deletions(-)
fs/fuse/acl.c +2 -2
@@ -34,7 +34,7 @@ struct posix_acl *fuse_get_acl(struct inode *inode, int type)return ERR_PTR (-ENOMEM ); size =fuse_getxattr (inode, name, value,PAGE_SIZE );if (size >0 ) - acl =posix_acl_from_xattr (&init_user_ns, value, size); + acl =posix_acl_from_xattr (fc->user_ns, value, size);else if ((size ==0 ) || (size == -ENODATA ) || (size == -EOPNOTSUPP && fc->no_getxattr)) acl =NULL ;
@@ -83,7 +83,7 @@ int fuse_set_acl(struct inode *inode, struct posix_acl *acl, int type)if (!value)return -ENOMEM ; - ret =posix_acl_to_xattr (&init_user_ns, acl, value, size); + ret =posix_acl_to_xattr (fc->user_ns, acl, value, size);if (ret <0 ) {kfree (value);return ret;
fs/fuse/cuse.c +6 -1
@@ -48,6 +48,7 @@#include <linux/stat.h> #include <linux/module.h> #include <linux/uio.h> +#include <linux/user_namespace.h> #include "fuse_i.h"
@@ -498,7 +499,11 @@ static int cuse_channel_open(struct inode *inode, struct file *file)if (!cc)return -ENOMEM ; -fuse_conn_init (&cc->fc); +/* +* Limit the cuse channel to requests that can +* be represented in file->f_cred->user_ns. +*/ +fuse_conn_init (&cc->fc, file->f_cred->user_ns); fud =fuse_dev_alloc (&cc->fc);if (!fud) {
fs/fuse/dev.c +2 -2
@@ -114,8 +114,8 @@ static void __fuse_put_request(struct fuse_req *req)static bool fuse_req_init_context (struct fuse_conn *fc,struct fuse_req *req) { - req->in.h.uid =from_kuid (&init_user_ns,current_fsuid ()); - req->in.h.gid =from_kgid (&init_user_ns,current_fsgid ()); + req->in.h.uid =from_kuid (fc->user_ns,current_fsuid ()); + req->in.h.gid =from_kgid (fc->user_ns,current_fsgid ()); req->in.h.pid =pid_nr_ns (task_pid (current), fc->pid_ns);return (req->in.h.uid != ((uid_t)-1 )) && (req->in.h.gid != ((gid_t)-1 ));
fs/fuse/dir.c +7 -7
@@ -858,8 +858,8 @@ static void fuse_fillattr(struct inode *inode, struct fuse_attr *attr, stat->ino = attr->ino; stat->mode = (inode->i_mode &S_IFMT ) | (attr->mode &07777 ); stat->nlink = attr->nlink; - stat->uid =make_kuid (&init_user_ns, attr->uid); - stat->gid =make_kgid (&init_user_ns, attr->gid); + stat->uid =make_kuid (fc->user_ns, attr->uid); + stat->gid =make_kgid (fc->user_ns, attr->gid); stat->rdev = inode->i_rdev; stat->atime.tv_sec = attr->atime; stat->atime.tv_nsec = attr->atimensec;
@@ -1475,17 +1475,17 @@ static bool update_mtime(unsigned ivalid, bool trust_local_mtime)return true; } -static void iattr_to_fattr (struct iattr *iattr,struct fuse_setattr_in *arg, -bool trust_local_cmtime) +static void iattr_to_fattr (struct fuse_conn *fc,struct iattr *iattr, +struct fuse_setattr_in *arg,bool trust_local_cmtime) {unsigned ivalid = iattr->ia_valid;if (ivalid &ATTR_MODE ) arg->valid |=FATTR_MODE , arg->mode = iattr->ia_mode;if (ivalid &ATTR_UID ) - arg->valid |=FATTR_UID , arg->uid =from_kuid (&init_user_ns, iattr->ia_uid); + arg->valid |=FATTR_UID , arg->uid =from_kuid (fc->user_ns, iattr->ia_uid);if (ivalid &ATTR_GID ) - arg->valid |=FATTR_GID , arg->gid =from_kgid (&init_user_ns, iattr->ia_gid); + arg->valid |=FATTR_GID , arg->gid =from_kgid (fc->user_ns, iattr->ia_gid);if (ivalid &ATTR_SIZE ) arg->valid |=FATTR_SIZE , arg->size = iattr->ia_size;if (ivalid &ATTR_ATIME ) {
@@ -1646,7 +1646,7 @@ int fuse_do_setattr(struct dentry *dentry, struct iattr *attr,memset (&inarg,0 ,sizeof (inarg));memset (&outarg,0 ,sizeof (outarg)); -iattr_to_fattr (attr, &inarg, trust_local_cmtime); +iattr_to_fattr (fc, attr, &inarg, trust_local_cmtime);if (file) {struct fuse_file *ff = file->private_data; inarg.valid |=FATTR_FH ;
fs/fuse/fuse_i.h +5 -1
@@ -26,6 +26,7 @@#include <linux/xattr.h> #include <linux/pid_namespace.h> #include <linux/refcount.h> +#include <linux/user_namespace.h> /** Max number of pages that can be used in a single read request */ #define FUSE_MAX_PAGES_PER_REQ 32
@@ -466,6 +467,9 @@ struct fuse_conn {/** The pid namespace for this mount */ struct pid_namespace *pid_ns; +/** The user namespace for this mount */ +struct user_namespace *user_ns; +/** Maximum read size */ unsigned max_read;
@@ -870,7 +874,7 @@ struct fuse_conn *fuse_conn_get(struct fuse_conn *fc);/** * Initialize fuse_conn */ -void fuse_conn_init (struct fuse_conn *fc); +void fuse_conn_init (struct fuse_conn *fc,struct user_namespace *user_ns);/** * Release reference to fuse_conn
fs/fuse/inode.c +19 -12
@@ -171,8 +171,8 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr, inode->i_ino =fuse_squash_ino (attr->ino); inode->i_mode = (inode->i_mode &S_IFMT ) | (attr->mode &07777 );set_nlink (inode, attr->nlink); - inode->i_uid =make_kuid (&init_user_ns, attr->uid); - inode->i_gid =make_kgid (&init_user_ns, attr->gid); + inode->i_uid =make_kuid (fc->user_ns, attr->uid); + inode->i_gid =make_kgid (fc->user_ns, attr->gid); inode->i_blocks = attr->blocks; inode->i_atime.tv_sec = attr->atime; inode->i_atime.tv_nsec = attr->atimensec;
@@ -477,7 +477,8 @@ static int fuse_match_uint(substring_t *s, unsigned int *res)return err; } -static int parse_fuse_opt (char *opt,struct fuse_mount_data *d,int is_bdev) +static int parse_fuse_opt (char *opt,struct fuse_mount_data *d,int is_bdev, +struct user_namespace *user_ns) {char *p;memset (d,0 ,sizeof (struct fuse_mount_data ));
@@ -513,7 +514,7 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)case OPT_USER_ID :if (fuse_match_uint (&args[0 ], &uv))return 0 ; - d->user_id =make_kuid (current_user_ns (), uv); + d->user_id =make_kuid (user_ns, uv);if (!uid_valid (d->user_id))return 0 ; d->user_id_present =1 ;
@@ -522,7 +523,7 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)case OPT_GROUP_ID :if (fuse_match_uint (&args[0 ], &uv))return 0 ; - d->group_id =make_kgid (current_user_ns (), uv); + d->group_id =make_kgid (user_ns, uv);if (!gid_valid (d->group_id))return 0 ; d->group_id_present =1 ;
@@ -565,8 +566,8 @@ static int fuse_show_options(struct seq_file *m, struct dentry *root)struct super_block *sb = root->d_sb;struct fuse_conn *fc =get_fuse_conn_super (sb); -seq_printf (m,",user_id=%u" ,from_kuid_munged (&init_user_ns, fc->user_id)); -seq_printf (m,",group_id=%u" ,from_kgid_munged (&init_user_ns, fc->group_id)); +seq_printf (m,",user_id=%u" ,from_kuid_munged (fc->user_ns, fc->user_id)); +seq_printf (m,",group_id=%u" ,from_kgid_munged (fc->user_ns, fc->group_id));if (fc->default_permissions)seq_puts (m,",default_permissions" );if (fc->allow_other)
@@ -597,7 +598,7 @@ static void fuse_pqueue_init(struct fuse_pqueue *fpq) fpq->connected =1 ; } -void fuse_conn_init (struct fuse_conn *fc) +void fuse_conn_init (struct fuse_conn *fc,struct user_namespace *user_ns) {memset (fc,0 ,sizeof (*fc));spin_lock_init (&fc->lock);
@@ -621,6 +622,7 @@ void fuse_conn_init(struct fuse_conn *fc) fc->attr_version =1 ;get_random_bytes (&fc->scramble_key,sizeof (fc->scramble_key)); fc->pid_ns =get_pid_ns (task_active_pid_ns (current)); + fc->user_ns =get_user_ns (user_ns); }EXPORT_SYMBOL_GPL (fuse_conn_init);
@@ -630,6 +632,7 @@ void fuse_conn_put(struct fuse_conn *fc)if (fc->destroy_req)fuse_request_free (fc->destroy_req);put_pid_ns (fc->pid_ns); +put_user_ns (fc->user_ns); fc->release (fc); } }
@@ -1060,7 +1063,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) sb->s_flags &= ~(SB_NOSEC |SB_I_VERSION ); -if (!parse_fuse_opt (data, &d, is_bdev)) +if (!parse_fuse_opt (data, &d, is_bdev, sb->s_user_ns)) goto err;if (is_bdev) {
@@ -1085,8 +1088,12 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)if (!file) goto err; -if ((file->f_op != &fuse_dev_operations) || - (file->f_cred->user_ns != &init_user_ns)) +/* +* Require mount to happen from the same user namespace which +* opened /dev/fuse to prevent potential attacks. +*/ +if (file->f_op != &fuse_dev_operations || + file->f_cred->user_ns != sb->s_user_ns) goto err_fput; fc =kmalloc (sizeof (*fc),GFP_KERNEL );
@@ -1094,7 +1101,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)if (!fc) goto err_fput; -fuse_conn_init (fc); +fuse_conn_init (fc, sb->s_user_ns); fc->release = fuse_free_conn; fud =fuse_dev_alloc (fc);
Signature · 1 line
2.14.1
PATCH v8 6/6 fuse: Restrict allow_other to the superblock's namespace or a descendant
In reply to Eric W. BiedermanFrom: Seth Forshee <[email protected]>
Unprivileged users are normally restricted from mounting with the allow_other option by system policy, but this could be bypassed for a mount done with user namespace root permissions. In such cases allow_other should not allow users outside the userns to access the mount as doing so would give the unprivileged user the ability to manipulate processes it would otherwise be unable to manipulate. Restrict allow_other to apply to users in the same userns used at mount or a descendant of that namespace. Also export current_in_userns() for use by fuse when built as a module.
--- fs/fuse/dir.c | 2 +- kernel/user_namespace.c | 1 + 2 files changed, 2 insertions(+), 1 deletion(-)
fs/fuse/dir.c +1 -1
@@ -1030,7 +1030,7 @@ int fuse_allow_current_process(struct fuse_conn *fc)const struct cred *cred;if (fc->allow_other) -return 1 ; +return current_in_userns (fc->user_ns); cred =current_cred (); if (uid_eq(cred->euid, fc->user_id) &&
kernel/user_namespace.c +1 -0
@@ -1235,6 +1235,7 @@ bool current_in_userns(const struct user_namespace *target_ns) {return in_userns (target_ns,current_user_ns ()); } +EXPORT_SYMBOL (current_in_userns);static inline struct user_namespace *to_user_ns (struct ns_common *ns) {
Signature · 1 line
2.14.1
v9 cover fuse: mounts from non-init user namespaces
In reply to Eric W. BiedermanThis patchset builds on the work by Donsu Park and Seth Forshee and is reduced to the set of patches that just affect fuse. The non-fuse vfs patches are far enough along we can ignore them except possibly for the question of when does FS_USERNS_MOUNT get set in fuse_fs_type.
Fuse with a block device has been left as an exercise for a later time.
Since v5 I changed the core of this patchset around as the previous patches were showing signs of bitrot. Some important explanations were missing, some important functionality was missing, and xattr handling was completely absent.
Since v6 I have:
- Removed the failure case from fuse_get_req_nofail_nopages that I added.
- Updated fuse to always to use posix_acl_access_xattr_handler, and posix_acl_default_xattr_handler, by teaching fuse to set ACL_DONT_CACHE when FUSE_POSIX_ACL is not set.
Since v7 I have:
- Rethought and reworked how I am unifying the cached and the non-cached posix acl case so the code is cleaner and simpler.
- I have dropped enhancements to caching negative acls when
fc->no_getxattr is set.
- Removed the need to wrap forget_all_cached_acls in fuse.
- Reorder the patches so the posix acl work comes first
Since v8 I have:
- Dropped and postponed the unification of the uncached and the cached posix acls case. The code is not hard but tricky enough it needs to be considered on it's own on it's own merits.
Miklos can you take a look and see what you think?
Miklos if you could pick these up I would appreciate it. If not I can merge these through the userns tree.
These changes are also available at:
git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace.git userns-fuse-v9
Eric W. Biederman (3):
fuse: Remove the buggy retranslation of pids in fuse_dev_do_read
fuse: Fail all requests with invalid uids or gids
fuse: Support fuse filesystems outside of init_user_ns
Seth Forshee (1):
fuse: Restrict allow_other to the superblock's namespace or a descendant
fs/fuse/acl.c | 4 ++-- fs/fuse/cuse.c | 7 ++++++- fs/fuse/dev.c | 30 +++++++++++++++++------------- fs/fuse/dir.c | 16 ++++++++-------- fs/fuse/fuse_i.h | 6 +++++- fs/fuse/inode.c | 31 +++++++++++++++++++------------ kernel/user_namespace.c | 1 + 7 files changed, 58 insertions(+), 37 deletions(-)
A message that is not in the archive (sent off-list or not yet received): 87ina6ntx0.fsf_-_-aS9lmoZGLiVWk0Htik3J/[email protected]
PATCH v9 1/4 fuse: Remove the buggy retranslation of pids in fuse_dev_do_read
At the point of fuse_dev_do_read the user space process that initiated the action on the fuse filesystem may no longer exist. The process have been killed or may have fired an asynchronous request and exited.
If the initial process has exited the code "pid_vnr(find_pid_ns(in->h.pid, fc->pid_ns)" will either return a pid of 0, or in the unlikely event that the pid has been reallocated it can return practically any pid. Any pid is possible as the pid allocator allocates pid numbers in different pid namespaces independently.
The only way to make translation in fuse_dev_do_read reliable is to call get_pid in fuse_req_init_context, and pid_vnr followed by put_pid in fuse_dev_do_read. That reference counting in other contexts has been shown to bounce cache lines between processors and in general be slow. So that is not desirable.
The only known user of running the fuse server in a different pid namespace from the filesystem does not care what the pids are in the fuse messages so removing this code should not matter.
Getting the translation to a server running outside of the pid namespace of a container can still be achieved by playing setns games at mount time. It is also possible to add an option to pass a pid namespace into the fuse filesystem at mount time.
--- fs/fuse/dev.c | 6 ------ 1 file changed, 6 deletions(-)
fs/fuse/dev.c +0 -6
@@ -1260,12 +1260,6 @@ static ssize_t fuse_dev_do_read(struct fuse_dev *fud, struct file *file, in = &req->in; reqsize = in->h.len; -if (task_active_pid_ns (current) != fc->pid_ns) { -rcu_read_lock (); - in->h.pid =pid_vnr (find_pid_ns (in->h.pid, fc->pid_ns)); -rcu_read_unlock (); - } -/* If request is too large, reply with an error and restart the read */ if (nbytes < reqsize) { req->out.h.error = -EIO ;
Signature · 1 line
2.14.1
PATCH v9 3/4 fuse: Support fuse filesystems outside of init_user_ns
In reply to a message not in the archiveIn order to support mounts from namespaces other than init_user_ns, fuse must translate uids and gids to/from the userns of the process servicing requests on /dev/fuse. This patch does that, with a couple of restrictions on the namespace:
- The userns for the fuse connection is fixed to the namespace from which /dev/fuse is opened.
- The namespace must be the same as s_user_ns.
These restrictions simplify the implementation by avoiding the need to pass around userns references and by allowing fuse to rely on the checks in setattr_prepare for ownership changes. Either restriction could be relaxed in the future if needed.
For cuse the userns used is the opener of /dev/cuse. Semantically the cuse support does not appear safe for unprivileged users. Practically the permissions on /dev/cuse only make it accessible to the global root user. If something slips through the cracks in a user namespace the only users who will be able to use the cuse device are those users mapped into the user namespace.
Translation in the posix acl is updated to use the uuser namespace of the filesystem. Avoiding cases which might bypass this translation is handled in a following change.
This change is stronlgy based on a similar change from Seth Forshee and Dongsu Park.
--- fs/fuse/acl.c | 4 ++-- fs/fuse/cuse.c | 7 ++++++- fs/fuse/dev.c | 4 ++-- fs/fuse/dir.c | 14 +++++++------- fs/fuse/fuse_i.h | 6 +++++- fs/fuse/inode.c | 31 +++++++++++++++++++------------ 6 files changed, 41 insertions(+), 25 deletions(-)
fs/fuse/acl.c +2 -2
@@ -34,7 +34,7 @@ struct posix_acl *fuse_get_acl(struct inode *inode, int type)return ERR_PTR (-ENOMEM ); size =fuse_getxattr (inode, name, value,PAGE_SIZE );if (size >0 ) - acl =posix_acl_from_xattr (&init_user_ns, value, size); + acl =posix_acl_from_xattr (fc->user_ns, value, size);else if ((size ==0 ) || (size == -ENODATA ) || (size == -EOPNOTSUPP && fc->no_getxattr)) acl =NULL ;
@@ -81,7 +81,7 @@ int fuse_set_acl(struct inode *inode, struct posix_acl *acl, int type)if (!value)return -ENOMEM ; - ret =posix_acl_to_xattr (&init_user_ns, acl, value, size); + ret =posix_acl_to_xattr (fc->user_ns, acl, value, size);if (ret <0 ) {kfree (value);return ret;
fs/fuse/cuse.c +6 -1
@@ -48,6 +48,7 @@#include <linux/stat.h> #include <linux/module.h> #include <linux/uio.h> +#include <linux/user_namespace.h> #include "fuse_i.h"
@@ -498,7 +499,11 @@ static int cuse_channel_open(struct inode *inode, struct file *file)if (!cc)return -ENOMEM ; -fuse_conn_init (&cc->fc); +/* +* Limit the cuse channel to requests that can +* be represented in file->f_cred->user_ns. +*/ +fuse_conn_init (&cc->fc, file->f_cred->user_ns); fud =fuse_dev_alloc (&cc->fc);if (!fud) {
fs/fuse/dev.c +2 -2
@@ -114,8 +114,8 @@ static void __fuse_put_request(struct fuse_req *req)static bool fuse_req_init_context (struct fuse_conn *fc,struct fuse_req *req) { - req->in.h.uid =from_kuid (&init_user_ns,current_fsuid ()); - req->in.h.gid =from_kgid (&init_user_ns,current_fsgid ()); + req->in.h.uid =from_kuid (fc->user_ns,current_fsuid ()); + req->in.h.gid =from_kgid (fc->user_ns,current_fsgid ()); req->in.h.pid =pid_nr_ns (task_pid (current), fc->pid_ns);return (req->in.h.uid != ((uid_t)-1 )) && (req->in.h.gid != ((gid_t)-1 ));
fs/fuse/dir.c +7 -7
@@ -858,8 +858,8 @@ static void fuse_fillattr(struct inode *inode, struct fuse_attr *attr, stat->ino = attr->ino; stat->mode = (inode->i_mode &S_IFMT ) | (attr->mode &07777 ); stat->nlink = attr->nlink; - stat->uid =make_kuid (&init_user_ns, attr->uid); - stat->gid =make_kgid (&init_user_ns, attr->gid); + stat->uid =make_kuid (fc->user_ns, attr->uid); + stat->gid =make_kgid (fc->user_ns, attr->gid); stat->rdev = inode->i_rdev; stat->atime.tv_sec = attr->atime; stat->atime.tv_nsec = attr->atimensec;
@@ -1475,17 +1475,17 @@ static bool update_mtime(unsigned ivalid, bool trust_local_mtime)return true; } -static void iattr_to_fattr (struct iattr *iattr,struct fuse_setattr_in *arg, -bool trust_local_cmtime) +static void iattr_to_fattr (struct fuse_conn *fc,struct iattr *iattr, +struct fuse_setattr_in *arg,bool trust_local_cmtime) {unsigned ivalid = iattr->ia_valid;if (ivalid &ATTR_MODE ) arg->valid |=FATTR_MODE , arg->mode = iattr->ia_mode;if (ivalid &ATTR_UID ) - arg->valid |=FATTR_UID , arg->uid =from_kuid (&init_user_ns, iattr->ia_uid); + arg->valid |=FATTR_UID , arg->uid =from_kuid (fc->user_ns, iattr->ia_uid);if (ivalid &ATTR_GID ) - arg->valid |=FATTR_GID , arg->gid =from_kgid (&init_user_ns, iattr->ia_gid); + arg->valid |=FATTR_GID , arg->gid =from_kgid (fc->user_ns, iattr->ia_gid);if (ivalid &ATTR_SIZE ) arg->valid |=FATTR_SIZE , arg->size = iattr->ia_size;if (ivalid &ATTR_ATIME ) {
@@ -1646,7 +1646,7 @@ int fuse_do_setattr(struct dentry *dentry, struct iattr *attr,memset (&inarg,0 ,sizeof (inarg));memset (&outarg,0 ,sizeof (outarg)); -iattr_to_fattr (attr, &inarg, trust_local_cmtime); +iattr_to_fattr (fc, attr, &inarg, trust_local_cmtime);if (file) {struct fuse_file *ff = file->private_data; inarg.valid |=FATTR_FH ;
fs/fuse/fuse_i.h +5 -1
@@ -26,6 +26,7 @@#include <linux/xattr.h> #include <linux/pid_namespace.h> #include <linux/refcount.h> +#include <linux/user_namespace.h> /** Max number of pages that can be used in a single read request */ #define FUSE_MAX_PAGES_PER_REQ 32
@@ -466,6 +467,9 @@ struct fuse_conn {/** The pid namespace for this mount */ struct pid_namespace *pid_ns; +/** The user namespace for this mount */ +struct user_namespace *user_ns; +/** Maximum read size */ unsigned max_read;
@@ -870,7 +874,7 @@ struct fuse_conn *fuse_conn_get(struct fuse_conn *fc);/** * Initialize fuse_conn */ -void fuse_conn_init (struct fuse_conn *fc); +void fuse_conn_init (struct fuse_conn *fc,struct user_namespace *user_ns);/** * Release reference to fuse_conn
fs/fuse/inode.c +19 -12
@@ -171,8 +171,8 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr, inode->i_ino =fuse_squash_ino (attr->ino); inode->i_mode = (inode->i_mode &S_IFMT ) | (attr->mode &07777 );set_nlink (inode, attr->nlink); - inode->i_uid =make_kuid (&init_user_ns, attr->uid); - inode->i_gid =make_kgid (&init_user_ns, attr->gid); + inode->i_uid =make_kuid (fc->user_ns, attr->uid); + inode->i_gid =make_kgid (fc->user_ns, attr->gid); inode->i_blocks = attr->blocks; inode->i_atime.tv_sec = attr->atime; inode->i_atime.tv_nsec = attr->atimensec;
@@ -477,7 +477,8 @@ static int fuse_match_uint(substring_t *s, unsigned int *res)return err; } -static int parse_fuse_opt (char *opt,struct fuse_mount_data *d,int is_bdev) +static int parse_fuse_opt (char *opt,struct fuse_mount_data *d,int is_bdev, +struct user_namespace *user_ns) {char *p;memset (d,0 ,sizeof (struct fuse_mount_data ));
@@ -513,7 +514,7 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)case OPT_USER_ID :if (fuse_match_uint (&args[0 ], &uv))return 0 ; - d->user_id =make_kuid (current_user_ns (), uv); + d->user_id =make_kuid (user_ns, uv);if (!uid_valid (d->user_id))return 0 ; d->user_id_present =1 ;
@@ -522,7 +523,7 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)case OPT_GROUP_ID :if (fuse_match_uint (&args[0 ], &uv))return 0 ; - d->group_id =make_kgid (current_user_ns (), uv); + d->group_id =make_kgid (user_ns, uv);if (!gid_valid (d->group_id))return 0 ; d->group_id_present =1 ;
@@ -565,8 +566,8 @@ static int fuse_show_options(struct seq_file *m, struct dentry *root)struct super_block *sb = root->d_sb;struct fuse_conn *fc =get_fuse_conn_super (sb); -seq_printf (m,",user_id=%u" ,from_kuid_munged (&init_user_ns, fc->user_id)); -seq_printf (m,",group_id=%u" ,from_kgid_munged (&init_user_ns, fc->group_id)); +seq_printf (m,",user_id=%u" ,from_kuid_munged (fc->user_ns, fc->user_id)); +seq_printf (m,",group_id=%u" ,from_kgid_munged (fc->user_ns, fc->group_id));if (fc->default_permissions)seq_puts (m,",default_permissions" );if (fc->allow_other)
@@ -597,7 +598,7 @@ static void fuse_pqueue_init(struct fuse_pqueue *fpq) fpq->connected =1 ; } -void fuse_conn_init (struct fuse_conn *fc) +void fuse_conn_init (struct fuse_conn *fc,struct user_namespace *user_ns) {memset (fc,0 ,sizeof (*fc));spin_lock_init (&fc->lock);
@@ -621,6 +622,7 @@ void fuse_conn_init(struct fuse_conn *fc) fc->attr_version =1 ;get_random_bytes (&fc->scramble_key,sizeof (fc->scramble_key)); fc->pid_ns =get_pid_ns (task_active_pid_ns (current)); + fc->user_ns =get_user_ns (user_ns); }EXPORT_SYMBOL_GPL (fuse_conn_init);
@@ -630,6 +632,7 @@ void fuse_conn_put(struct fuse_conn *fc)if (fc->destroy_req)fuse_request_free (fc->destroy_req);put_pid_ns (fc->pid_ns); +put_user_ns (fc->user_ns); fc->release (fc); } }
@@ -1061,7 +1064,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) sb->s_flags &= ~(SB_NOSEC |SB_I_VERSION ); -if (!parse_fuse_opt (data, &d, is_bdev)) +if (!parse_fuse_opt (data, &d, is_bdev, sb->s_user_ns)) goto err;if (is_bdev) {
@@ -1086,8 +1089,12 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)if (!file) goto err; -if ((file->f_op != &fuse_dev_operations) || - (file->f_cred->user_ns != &init_user_ns)) +/* +* Require mount to happen from the same user namespace which +* opened /dev/fuse to prevent potential attacks. +*/ +if (file->f_op != &fuse_dev_operations || + file->f_cred->user_ns != sb->s_user_ns) goto err_fput; fc =kmalloc (sizeof (*fc),GFP_KERNEL );
@@ -1095,7 +1102,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)if (!fc) goto err_fput; -fuse_conn_init (fc); +fuse_conn_init (fc, sb->s_user_ns); fc->release = fuse_free_conn; fud =fuse_dev_alloc (fc);
Signature · 1 line
2.14.1
PATCH v9 4/4 fuse: Restrict allow_other to the superblock's namespace or a descendant
In reply to a message not in the archiveFrom: Seth Forshee <[email protected]>
Unprivileged users are normally restricted from mounting with the allow_other option by system policy, but this could be bypassed for a mount done with user namespace root permissions. In such cases allow_other should not allow users outside the userns to access the mount as doing so would give the unprivileged user the ability to manipulate processes it would otherwise be unable to manipulate. Restrict allow_other to apply to users in the same userns used at mount or a descendant of that namespace. Also export current_in_userns() for use by fuse when built as a module.
--- fs/fuse/dir.c | 2 +- kernel/user_namespace.c | 1 + 2 files changed, 2 insertions(+), 1 deletion(-)
fs/fuse/dir.c +1 -1
@@ -1030,7 +1030,7 @@ int fuse_allow_current_process(struct fuse_conn *fc)const struct cred *cred;if (fc->allow_other) -return 1 ; +return current_in_userns (fc->user_ns); cred =current_cred (); if (uid_eq(cred->euid, fc->user_id) &&
kernel/user_namespace.c +1 -0
@@ -1235,6 +1235,7 @@ bool current_in_userns(const struct user_namespace *target_ns) {return in_userns (target_ns,current_user_ns ()); } +EXPORT_SYMBOL (current_in_userns);static inline struct user_namespace *to_user_ns (struct ns_common *ns) {
Signature · 1 line
2.14.1
Re: [PATCH v9 0/4] fuse: mounts from non-init user namespaces
In reply to a message not in the archiveQuoted 33 lines · Eric W. Biederman
This patchset builds on the work by Donsu Park and Seth Forshee and is reduced to the set of patches that just affect fuse. The non-fuse vfs patches are far enough along we can ignore them except possibly for the question of when does
FS_USERNS_MOUNTget set infuse_fs_type.Fuse with a block device has been left as an exercise for a later time.
Since v5 I changed the core of this patchset around as the previous patches were showing signs of bitrot. Some important explanations were missing, some important functionality was missing, and xattr handling was completely absent.
Since v6 I have:
- Removed the failure case fromfuse_get_req_nofail_nopagesthat I added.
- Updated fuse to always to useposix_acl_access_xattr_handler, andposix_acl_default_xattr_handler, by teaching fuse to setACL_DONT_CACHEwhenFUSE_POSIX_ACLis not set.Since v7 I have:
- Rethought and reworked how I am unifying the cached and the non-cached posix acl case so the code is cleaner and simpler.
- I have dropped enhancements to caching negative acls whenfc->no_getxattr is set.- Removed the need to wrap
forget_all_cached_aclsin fuse.
- Reorder the patches so the posix acl work comes firstSince v8 I have:
- Dropped and postponed the unification of the uncached and the cached posix acls case. The code is not hard but tricky enough it needs to be considered on it's own on it's own merits.
Quoted 4 lines
Miklos can you take a look and see what you think?
Miklos if you could pick these up I would appreciate it. If not I can merge these through the userns tree.
Thank you Eric for moving this along. Patches pushed to:
git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse.git for-next
I did just one modification to "fuse: Fail all requests with invalid uids or gids": instead of zeroing out the context for the nofail case, continue to use the "_munged" variants. I don't think this hurts and is better for backward compatibility (I guess the only relevant use would be for debugging output, but we don't want to regress even for that if not necessary).
Thanks,
Miklos
PATCH v9 1/4 fuse: Remove the buggy retranslation of pids in fuse_dev_do_read
In reply to Eric W. BiedermanAt the point of fuse_dev_do_read the user space process that initiated the action on the fuse filesystem may no longer exist. The process have been killed or may have fired an asynchronous request and exited.
If the initial process has exited the code "pid_vnr(find_pid_ns(in->h.pid, fc->pid_ns)" will either return a pid of 0, or in the unlikely event that the pid has been reallocated it can return practically any pid. Any pid is possible as the pid allocator allocates pid numbers in different pid namespaces independently.
The only way to make translation in fuse_dev_do_read reliable is to call get_pid in fuse_req_init_context, and pid_vnr followed by put_pid in fuse_dev_do_read. That reference counting in other contexts has been shown to bounce cache lines between processors and in general be slow. So that is not desirable.
The only known user of running the fuse server in a different pid namespace from the filesystem does not care what the pids are in the fuse messages so removing this code should not matter.
Getting the translation to a server running outside of the pid namespace of a container can still be achieved by playing setns games at mount time. It is also possible to add an option to pass a pid namespace into the fuse filesystem at mount time.
--- fs/fuse/dev.c | 6 ------ 1 file changed, 6 deletions(-)
fs/fuse/dev.c +0 -6
@@ -1260,12 +1260,6 @@ static ssize_t fuse_dev_do_read(struct fuse_dev *fud, struct file *file, in = &req->in; reqsize = in->h.len; -if (task_active_pid_ns (current) != fc->pid_ns) { -rcu_read_lock (); - in->h.pid =pid_vnr (find_pid_ns (in->h.pid, fc->pid_ns)); -rcu_read_unlock (); - } -/* If request is too large, reply with an error and restart the read */ if (nbytes < reqsize) { req->out.h.error = -EIO ;
Signature · 1 line
2.14.1
PATCH v9 2/4 fuse: Fail all requests with invalid uids or gids
In reply to Eric W. BiedermanUpon a cursory examinination the uid and gid of a fuse request are necessary for correct operation. Failing a fuse request where those values are not reliable seems a straight forward and reliable means of ensuring that fuse requests with bad data are not sent or processed.
In most cases the vfs will avoid actions it suspects will cause an inode write back of an inode with an invalid uid or gid. But that does not map precisely to what fuse is doing, so test for this and solve this at the fuse level as well.
Performing this work in fuse_req_init_context is cheap as the code is already performing the translation here and only needs to check the result of the translation to see if things are not representable in a form the fuse server can handle.
--- fs/fuse/dev.c | 24 +++++++++++++++++------- 1 file changed, 17 insertions(+), 7 deletions(-)
fs/fuse/dev.c +17 -7
@@ -112,11 +112,20 @@ static void __fuse_put_request(struct fuse_req *req)refcount_dec (&req->count); } -static void fuse_req_init_context (struct fuse_conn *fc,struct fuse_req *req) +static bool fuse_req_init_context (struct fuse_conn *fc,struct fuse_req *req) { - req->in.h.uid =from_kuid_munged (&init_user_ns,current_fsuid ()); - req->in.h.gid =from_kgid_munged (&init_user_ns,current_fsgid ()); + req->in.h.uid =from_kuid (&init_user_ns,current_fsuid ()); + req->in.h.gid =from_kgid (&init_user_ns,current_fsgid ()); req->in.h.pid =pid_nr_ns (task_pid (current), fc->pid_ns); + +return (req->in.h.uid != ((uid_t)-1 )) && (req->in.h.gid != ((gid_t)-1 )); +} + +static void fuse_req_init_context_nofail (struct fuse_req *req) +{ + req->in.h.uid =0 ; + req->in.h.gid =0 ; + req->in.h.pid =0 ; }void fuse_set_initialized (struct fuse_conn *fc)
@@ -162,12 +171,13 @@ static struct fuse_req *__fuse_get_req(struct fuse_conn *fc, unsigned npages,wake_up (&fc->blocked_waitq); goto out; } - -fuse_req_init_context (fc, req);__set_bit (FR_WAITING , &req->flags);if (for_background)__set_bit (FR_BACKGROUND , &req->flags); - +if (unlikely (!fuse_req_init_context (fc, req))) { +fuse_put_request (fc, req); +return ERR_PTR (-EOVERFLOW ); + }return req; out:
@@ -256,7 +266,7 @@ struct fuse_req *fuse_get_req_nofail_nopages(struct fuse_conn *fc,if (!req) req =get_reserved_req (fc, file); -fuse_req_init_context (fc, req); +fuse_req_init_context_nofail (req);__set_bit (FR_WAITING , &req->flags);__clear_bit (FR_BACKGROUND , &req->flags);return req;
Signature · 1 line
2.14.1
PATCH v9 3/4 fuse: Support fuse filesystems outside of init_user_ns
In reply to Eric W. BiedermanIn order to support mounts from namespaces other than init_user_ns, fuse must translate uids and gids to/from the userns of the process servicing requests on /dev/fuse. This patch does that, with a couple of restrictions on the namespace:
- The userns for the fuse connection is fixed to the namespace from which /dev/fuse is opened.
- The namespace must be the same as s_user_ns.
These restrictions simplify the implementation by avoiding the need to pass around userns references and by allowing fuse to rely on the checks in setattr_prepare for ownership changes. Either restriction could be relaxed in the future if needed.
For cuse the userns used is the opener of /dev/cuse. Semantically the cuse support does not appear safe for unprivileged users. Practically the permissions on /dev/cuse only make it accessible to the global root user. If something slips through the cracks in a user namespace the only users who will be able to use the cuse device are those users mapped into the user namespace.
Translation in the posix acl is updated to use the uuser namespace of the filesystem. Avoiding cases which might bypass this translation is handled in a following change.
This change is stronlgy based on a similar change from Seth Forshee and Dongsu Park.
--- fs/fuse/acl.c | 4 ++-- fs/fuse/cuse.c | 7 ++++++- fs/fuse/dev.c | 4 ++-- fs/fuse/dir.c | 14 +++++++------- fs/fuse/fuse_i.h | 6 +++++- fs/fuse/inode.c | 31 +++++++++++++++++++------------ 6 files changed, 41 insertions(+), 25 deletions(-)
fs/fuse/acl.c +2 -2
@@ -34,7 +34,7 @@ struct posix_acl *fuse_get_acl(struct inode *inode, int type)return ERR_PTR (-ENOMEM ); size =fuse_getxattr (inode, name, value,PAGE_SIZE );if (size >0 ) - acl =posix_acl_from_xattr (&init_user_ns, value, size); + acl =posix_acl_from_xattr (fc->user_ns, value, size);else if ((size ==0 ) || (size == -ENODATA ) || (size == -EOPNOTSUPP && fc->no_getxattr)) acl =NULL ;
@@ -81,7 +81,7 @@ int fuse_set_acl(struct inode *inode, struct posix_acl *acl, int type)if (!value)return -ENOMEM ; - ret =posix_acl_to_xattr (&init_user_ns, acl, value, size); + ret =posix_acl_to_xattr (fc->user_ns, acl, value, size);if (ret <0 ) {kfree (value);return ret;
fs/fuse/cuse.c +6 -1
@@ -48,6 +48,7 @@#include <linux/stat.h> #include <linux/module.h> #include <linux/uio.h> +#include <linux/user_namespace.h> #include "fuse_i.h"
@@ -498,7 +499,11 @@ static int cuse_channel_open(struct inode *inode, struct file *file)if (!cc)return -ENOMEM ; -fuse_conn_init (&cc->fc); +/* +* Limit the cuse channel to requests that can +* be represented in file->f_cred->user_ns. +*/ +fuse_conn_init (&cc->fc, file->f_cred->user_ns); fud =fuse_dev_alloc (&cc->fc);if (!fud) {
fs/fuse/dev.c +2 -2
@@ -114,8 +114,8 @@ static void __fuse_put_request(struct fuse_req *req)static bool fuse_req_init_context (struct fuse_conn *fc,struct fuse_req *req) { - req->in.h.uid =from_kuid (&init_user_ns,current_fsuid ()); - req->in.h.gid =from_kgid (&init_user_ns,current_fsgid ()); + req->in.h.uid =from_kuid (fc->user_ns,current_fsuid ()); + req->in.h.gid =from_kgid (fc->user_ns,current_fsgid ()); req->in.h.pid =pid_nr_ns (task_pid (current), fc->pid_ns);return (req->in.h.uid != ((uid_t)-1 )) && (req->in.h.gid != ((gid_t)-1 ));
fs/fuse/dir.c +7 -7
@@ -858,8 +858,8 @@ static void fuse_fillattr(struct inode *inode, struct fuse_attr *attr, stat->ino = attr->ino; stat->mode = (inode->i_mode &S_IFMT ) | (attr->mode &07777 ); stat->nlink = attr->nlink; - stat->uid =make_kuid (&init_user_ns, attr->uid); - stat->gid =make_kgid (&init_user_ns, attr->gid); + stat->uid =make_kuid (fc->user_ns, attr->uid); + stat->gid =make_kgid (fc->user_ns, attr->gid); stat->rdev = inode->i_rdev; stat->atime.tv_sec = attr->atime; stat->atime.tv_nsec = attr->atimensec;
@@ -1475,17 +1475,17 @@ static bool update_mtime(unsigned ivalid, bool trust_local_mtime)return true; } -static void iattr_to_fattr (struct iattr *iattr,struct fuse_setattr_in *arg, -bool trust_local_cmtime) +static void iattr_to_fattr (struct fuse_conn *fc,struct iattr *iattr, +struct fuse_setattr_in *arg,bool trust_local_cmtime) {unsigned ivalid = iattr->ia_valid;if (ivalid &ATTR_MODE ) arg->valid |=FATTR_MODE , arg->mode = iattr->ia_mode;if (ivalid &ATTR_UID ) - arg->valid |=FATTR_UID , arg->uid =from_kuid (&init_user_ns, iattr->ia_uid); + arg->valid |=FATTR_UID , arg->uid =from_kuid (fc->user_ns, iattr->ia_uid);if (ivalid &ATTR_GID ) - arg->valid |=FATTR_GID , arg->gid =from_kgid (&init_user_ns, iattr->ia_gid); + arg->valid |=FATTR_GID , arg->gid =from_kgid (fc->user_ns, iattr->ia_gid);if (ivalid &ATTR_SIZE ) arg->valid |=FATTR_SIZE , arg->size = iattr->ia_size;if (ivalid &ATTR_ATIME ) {
@@ -1646,7 +1646,7 @@ int fuse_do_setattr(struct dentry *dentry, struct iattr *attr,memset (&inarg,0 ,sizeof (inarg));memset (&outarg,0 ,sizeof (outarg)); -iattr_to_fattr (attr, &inarg, trust_local_cmtime); +iattr_to_fattr (fc, attr, &inarg, trust_local_cmtime);if (file) {struct fuse_file *ff = file->private_data; inarg.valid |=FATTR_FH ;
fs/fuse/fuse_i.h +5 -1
@@ -26,6 +26,7 @@#include <linux/xattr.h> #include <linux/pid_namespace.h> #include <linux/refcount.h> +#include <linux/user_namespace.h> /** Max number of pages that can be used in a single read request */ #define FUSE_MAX_PAGES_PER_REQ 32
@@ -466,6 +467,9 @@ struct fuse_conn {/** The pid namespace for this mount */ struct pid_namespace *pid_ns; +/** The user namespace for this mount */ +struct user_namespace *user_ns; +/** Maximum read size */ unsigned max_read;
@@ -870,7 +874,7 @@ struct fuse_conn *fuse_conn_get(struct fuse_conn *fc);/** * Initialize fuse_conn */ -void fuse_conn_init (struct fuse_conn *fc); +void fuse_conn_init (struct fuse_conn *fc,struct user_namespace *user_ns);/** * Release reference to fuse_conn
fs/fuse/inode.c +19 -12
@@ -171,8 +171,8 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr, inode->i_ino =fuse_squash_ino (attr->ino); inode->i_mode = (inode->i_mode &S_IFMT ) | (attr->mode &07777 );set_nlink (inode, attr->nlink); - inode->i_uid =make_kuid (&init_user_ns, attr->uid); - inode->i_gid =make_kgid (&init_user_ns, attr->gid); + inode->i_uid =make_kuid (fc->user_ns, attr->uid); + inode->i_gid =make_kgid (fc->user_ns, attr->gid); inode->i_blocks = attr->blocks; inode->i_atime.tv_sec = attr->atime; inode->i_atime.tv_nsec = attr->atimensec;
@@ -477,7 +477,8 @@ static int fuse_match_uint(substring_t *s, unsigned int *res)return err; } -static int parse_fuse_opt (char *opt,struct fuse_mount_data *d,int is_bdev) +static int parse_fuse_opt (char *opt,struct fuse_mount_data *d,int is_bdev, +struct user_namespace *user_ns) {char *p;memset (d,0 ,sizeof (struct fuse_mount_data ));
@@ -513,7 +514,7 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)case OPT_USER_ID :if (fuse_match_uint (&args[0 ], &uv))return 0 ; - d->user_id =make_kuid (current_user_ns (), uv); + d->user_id =make_kuid (user_ns, uv);if (!uid_valid (d->user_id))return 0 ; d->user_id_present =1 ;
@@ -522,7 +523,7 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)case OPT_GROUP_ID :if (fuse_match_uint (&args[0 ], &uv))return 0 ; - d->group_id =make_kgid (current_user_ns (), uv); + d->group_id =make_kgid (user_ns, uv);if (!gid_valid (d->group_id))return 0 ; d->group_id_present =1 ;
@@ -565,8 +566,8 @@ static int fuse_show_options(struct seq_file *m, struct dentry *root)struct super_block *sb = root->d_sb;struct fuse_conn *fc =get_fuse_conn_super (sb); -seq_printf (m,",user_id=%u" ,from_kuid_munged (&init_user_ns, fc->user_id)); -seq_printf (m,",group_id=%u" ,from_kgid_munged (&init_user_ns, fc->group_id)); +seq_printf (m,",user_id=%u" ,from_kuid_munged (fc->user_ns, fc->user_id)); +seq_printf (m,",group_id=%u" ,from_kgid_munged (fc->user_ns, fc->group_id));if (fc->default_permissions)seq_puts (m,",default_permissions" );if (fc->allow_other)
@@ -597,7 +598,7 @@ static void fuse_pqueue_init(struct fuse_pqueue *fpq) fpq->connected =1 ; } -void fuse_conn_init (struct fuse_conn *fc) +void fuse_conn_init (struct fuse_conn *fc,struct user_namespace *user_ns) {memset (fc,0 ,sizeof (*fc));spin_lock_init (&fc->lock);
@@ -621,6 +622,7 @@ void fuse_conn_init(struct fuse_conn *fc) fc->attr_version =1 ;get_random_bytes (&fc->scramble_key,sizeof (fc->scramble_key)); fc->pid_ns =get_pid_ns (task_active_pid_ns (current)); + fc->user_ns =get_user_ns (user_ns); }EXPORT_SYMBOL_GPL (fuse_conn_init);
@@ -630,6 +632,7 @@ void fuse_conn_put(struct fuse_conn *fc)if (fc->destroy_req)fuse_request_free (fc->destroy_req);put_pid_ns (fc->pid_ns); +put_user_ns (fc->user_ns); fc->release (fc); } }
@@ -1061,7 +1064,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) sb->s_flags &= ~(SB_NOSEC |SB_I_VERSION ); -if (!parse_fuse_opt (data, &d, is_bdev)) +if (!parse_fuse_opt (data, &d, is_bdev, sb->s_user_ns)) goto err;if (is_bdev) {
@@ -1086,8 +1089,12 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)if (!file) goto err; -if ((file->f_op != &fuse_dev_operations) || - (file->f_cred->user_ns != &init_user_ns)) +/* +* Require mount to happen from the same user namespace which +* opened /dev/fuse to prevent potential attacks. +*/ +if (file->f_op != &fuse_dev_operations || + file->f_cred->user_ns != sb->s_user_ns) goto err_fput; fc =kmalloc (sizeof (*fc),GFP_KERNEL );
@@ -1095,7 +1102,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)if (!fc) goto err_fput; -fuse_conn_init (fc); +fuse_conn_init (fc, sb->s_user_ns); fc->release = fuse_free_conn; fud =fuse_dev_alloc (fc);
Signature · 1 line
2.14.1
PATCH v9 4/4 fuse: Restrict allow_other to the superblock's namespace or a descendant
In reply to Eric W. BiedermanFrom: Seth Forshee <[email protected]>
Unprivileged users are normally restricted from mounting with the allow_other option by system policy, but this could be bypassed for a mount done with user namespace root permissions. In such cases allow_other should not allow users outside the userns to access the mount as doing so would give the unprivileged user the ability to manipulate processes it would otherwise be unable to manipulate. Restrict allow_other to apply to users in the same userns used at mount or a descendant of that namespace. Also export current_in_userns() for use by fuse when built as a module.
--- fs/fuse/dir.c | 2 +- kernel/user_namespace.c | 1 + 2 files changed, 2 insertions(+), 1 deletion(-)
fs/fuse/dir.c +1 -1
@@ -1030,7 +1030,7 @@ int fuse_allow_current_process(struct fuse_conn *fc)const struct cred *cred;if (fc->allow_other) -return 1 ; +return current_in_userns (fc->user_ns); cred =current_cred (); if (uid_eq(cred->euid, fc->user_id) &&
kernel/user_namespace.c +1 -0
@@ -1235,6 +1235,7 @@ bool current_in_userns(const struct user_namespace *target_ns) {return in_userns (target_ns,current_user_ns ()); } +EXPORT_SYMBOL (current_in_userns);static inline struct user_namespace *to_user_ns (struct ns_common *ns) {
Signature · 1 line
2.14.1
Re: [PATCH v9 0/4] fuse: mounts from non-init user namespaces
In reply to Eric W. BiedermanQuoted 33 lines · Eric W. Biederman
This patchset builds on the work by Donsu Park and Seth Forshee and is reduced to the set of patches that just affect fuse. The non-fuse vfs patches are far enough along we can ignore them except possibly for the question of when does
FS_USERNS_MOUNTget set infuse_fs_type.Fuse with a block device has been left as an exercise for a later time.
Since v5 I changed the core of this patchset around as the previous patches were showing signs of bitrot. Some important explanations were missing, some important functionality was missing, and xattr handling was completely absent.
Since v6 I have:
- Removed the failure case fromfuse_get_req_nofail_nopagesthat I added.
- Updated fuse to always to useposix_acl_access_xattr_handler, andposix_acl_default_xattr_handler, by teaching fuse to setACL_DONT_CACHEwhenFUSE_POSIX_ACLis not set.Since v7 I have:
- Rethought and reworked how I am unifying the cached and the non-cached posix acl case so the code is cleaner and simpler.
- I have dropped enhancements to caching negative acls whenfc->no_getxattr is set.- Removed the need to wrap
forget_all_cached_aclsin fuse.
- Reorder the patches so the posix acl work comes firstSince v8 I have:
- Dropped and postponed the unification of the uncached and the cached posix acls case. The code is not hard but tricky enough it needs to be considered on it's own on it's own merits.
Quoted 4 lines
Miklos can you take a look and see what you think?
Miklos if you could pick these up I would appreciate it. If not I can merge these through the userns tree.
Thank you Eric for moving this along. Patches pushed to:
git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse.git for-next
I did just one modification to "fuse: Fail all requests with invalid uids or gids": instead of zeroing out the context for the nofail case, continue to use the "_munged" variants. I don't think this hurts and is better for backward compatibility (I guess the only relevant use would be for debugging output, but we don't want to regress even for that if not necessary).
Thanks,
Miklos
Re: [PATCH v9 0/4] fuse: mounts from non-init user namespaces
Quoted 42 lines · Miklos Szeredi
Quoted 33 lines · Eric W. Biederman
This patchset builds on the work by Donsu Park and Seth Forshee and is reduced to the set of patches that just affect fuse. The non-fuse vfs patches are far enough along we can ignore them except possibly for the question of when does
FS_USERNS_MOUNTget set infuse_fs_type.Fuse with a block device has been left as an exercise for a later time.
Since v5 I changed the core of this patchset around as the previous patches were showing signs of bitrot. Some important explanations were missing, some important functionality was missing, and xattr handling was completely absent.
Since v6 I have:
- Removed the failure case fromfuse_get_req_nofail_nopagesthat I added.
- Updated fuse to always to useposix_acl_access_xattr_handler, andposix_acl_default_xattr_handler, by teaching fuse to setACL_DONT_CACHEwhenFUSE_POSIX_ACLis not set.Since v7 I have:
- Rethought and reworked how I am unifying the cached and the non-cached posix acl case so the code is cleaner and simpler.
- I have dropped enhancements to caching negative acls whenfc->no_getxattr is set.- Removed the need to wrap
forget_all_cached_aclsin fuse.
- Reorder the patches so the posix acl work comes firstSince v8 I have:
- Dropped and postponed the unification of the uncached and the cached posix acls case. The code is not hard but tricky enough it needs to be considered on it's own on it's own merits.Quoted 4 lines
Miklos can you take a look and see what you think?
Miklos if you could pick these up I would appreciate it. If not I can merge these through the userns tree.
Thank you Eric for moving this along. Patches pushed to:
Quoted 8 lines
git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse.gitfor-nextI did just one modification to "fuse: Fail all requests with invalid uids or gids": instead of zeroing out the context for the nofail case, continue to use the "
_munged" variants. I don't think this hurts and is better for backward compatibility (I guess the only relevant use would be for debugging output, but we don't want to regress even for that if not necessary)
Hmm...
The thing is the failure doesn't come in the difference between the _munged and the normal variants. The difference between munged and non-munged variants is how they handled failure ((uid16_t)-2) aka 0xfffe for munged and -1 for the non-munged case.
The failures are introduced by changing &init_user_ns to fc->user_ns.
The operations in question are iop->flush and fuse_force_forget (on an
error). I don't know what value having ids on those paths will do
they are operations that must succeed, and they should not change the on-disk ids. I was thinking saying the most privileged id was asking for the oepration would seem to make sense.
With the munged variants we will get (uid16_t)-2 aka 0xfffe aka nobody asking for the operation if things don't map. In practice the don't map case is new.
Since the id's should not be looked at anyway I don't see it makes much difference which ids we use so the munged case seems at least plausible.
It might be better to use the non-munghed variant and do:
if (req->in.h.uid == (uid_t)-1)
req.in.h.uid = 0;
if (req->in.h.gid == (gid_t)-1)
req.in.h.gid = 0;That might be less surprising to userspace. As I don't think the unmapped case has ever occurred in practice yet. The vfs will work hard to keep the unmapped case from happening but only in the context of i_uid and i_gid not current_fsuid and current_fsgid.
Eric
A message that is not in the archive (sent off-list or not yet received): 87tvta38lu.fsf-aS9lmoZGLiVWk0Htik3J/[email protected]
Re: [PATCH v9 0/4] fuse: mounts from non-init user namespaces
Quoted 9 lines · Eric W. Biederman
Quoted 6 lines · Miklos Szeredi
I did just one modification to "fuse: Fail all requests with invalid uids or gids": instead of zeroing out the context for the nofail case, continue to use the "
_munged" variants. I don't think this hurts and is better for backward compatibility (I guess the only relevant use would be for debugging output, but we don't want to regress even for that if not necessary)
Quoted 8 lines
Hmm...
The thing is the failure doesn't come in the difference between the
_mungedand the normal variants. The difference between munged and non-munged variants is how they handled failure ((uid16_t)-2) aka0xfffefor munged and -1 for the non-munged case.The failures are introduced by changing
&init_user_nstofc->user_ns.
Right.
Quoted 5 lines
The operations in question are
iop->flushandfuse_force_forget(on an
error). I don't know what value having ids on those paths will do
they are operations that must succeed, and they should not change the on-disk ids. I was thinking saying the most privileged id was asking for the oepration would seem to make sense.
I don't think anybody should actually *care* about the id's in flush, but I'd still not change the current behavior for change's sake.
Quoted 9 lines
With the munged variants we will get (uid16_t)-2 aka
0xfffeaka nobody asking for the operation if things don't map. In practice the don't map case is new.Since the id's should not be looked at anyway I don't see it makes much difference which ids we use so the munged case seems at least plausible.
Quoted 8 lines
It might be better to use the non-munghed variant and do:
if (req->in.h.uid == (uid_t)-1) req.in.h.uid = 0; if (req->in.h.gid == (gid_t)-1) req.in.h.gid = 0;That might be less surprising to userspace. As I don't think the unmapped case has ever occurred in practice yet.
Right, that would work too, but I don't think it actually matters, so unless you can think of an actual security issue arising from using the munged variants, I'd just leave it as it is.
Thanks,
Miklos
Re: [PATCH v9 0/4] fuse: mounts from non-init user namespaces
In reply to Eric W. BiedermanQuoted 9 lines · Eric W. Biederman
Quoted 6 lines · Miklos Szeredi
I did just one modification to "fuse: Fail all requests with invalid uids or gids": instead of zeroing out the context for the nofail case, continue to use the "
_munged" variants. I don't think this hurts and is better for backward compatibility (I guess the only relevant use would be for debugging output, but we don't want to regress even for that if not necessary)
Quoted 8 lines
Hmm...
The thing is the failure doesn't come in the difference between the
_mungedand the normal variants. The difference between munged and non-munged variants is how they handled failure ((uid16_t)-2) aka0xfffefor munged and -1 for the non-munged case.The failures are introduced by changing
&init_user_nstofc->user_ns.
Right.
Quoted 5 lines
The operations in question are
iop->flushandfuse_force_forget(on an
error). I don't know what value having ids on those paths will do
they are operations that must succeed, and they should not change the on-disk ids. I was thinking saying the most privileged id was asking for the oepration would seem to make sense.
I don't think anybody should actually *care* about the id's in flush, but I'd still not change the current behavior for change's sake.
Quoted 9 lines
With the munged variants we will get (uid16_t)-2 aka
0xfffeaka nobody asking for the operation if things don't map. In practice the don't map case is new.Since the id's should not be looked at anyway I don't see it makes much difference which ids we use so the munged case seems at least plausible.
Quoted 8 lines
It might be better to use the non-munghed variant and do:
if (req->in.h.uid == (uid_t)-1) req.in.h.uid = 0; if (req->in.h.gid == (gid_t)-1) req.in.h.gid = 0;That might be less surprising to userspace. As I don't think the unmapped case has ever occurred in practice yet.
Right, that would work too, but I don't think it actually matters, so unless you can think of an actual security issue arising from using the munged variants, I'd just leave it as it is.
Thanks,
Miklos