int (*get)(const struct xattr_handler *handler, struct dentry *dentry,
struct inode *inode, const char *name, void *buffer,
size_t size);
- int (*set)(const struct xattr_handler *handler, struct dentry *dentry,
- struct inode *inode, const char *name, const void *buffer,
- size_t size, int flags);
+ int (*set)(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct inode *inode, const char *name,
+ const void *buffer, size_t size, int flags);
locking rules:
all may block
**mandatory**
->setxattr() and xattr_handler.set() get dentry and inode passed separately.
+The xattr_handler.set() gets passed the user namespace of the mount the inode
+is seen from so filesystems can idmap the i_uid and i_gid accordingly.
dentry might be yet to be attached to inode, so do _not_ use its ->d_inode
in the instances. Rationale: !@#!@# security_d_instantiate() needs to be
called before we attach dentry to inode and !@#!@##!@$!$#!@#$!@$!@$ smack
.. code-block:: c
struct inode_operations {
- int (*create) (struct inode *,struct dentry *, umode_t, bool);
+ int (*create) (struct user_namespace *, struct inode *,struct dentry *, umode_t, bool);
struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
int (*link) (struct dentry *,struct inode *,struct dentry *);
int (*unlink) (struct inode *,struct dentry *);
- int (*symlink) (struct inode *,struct dentry *,const char *);
- int (*mkdir) (struct inode *,struct dentry *,umode_t);
+ int (*symlink) (struct user_namespace *, struct inode *,struct dentry *,const char *);
+ int (*mkdir) (struct user_namespace *, struct inode *,struct dentry *,umode_t);
int (*rmdir) (struct inode *,struct dentry *);
- int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t);
- int (*rename) (struct inode *, struct dentry *,
+ int (*mknod) (struct user_namespace *, struct inode *,struct dentry *,umode_t,dev_t);
+ int (*rename) (struct user_namespace *, struct inode *, struct dentry *,
struct inode *, struct dentry *, unsigned int);
int (*readlink) (struct dentry *, char __user *,int);
const char *(*get_link) (struct dentry *, struct inode *,
struct delayed_call *);
- int (*permission) (struct inode *, int);
+ int (*permission) (struct user_namespace *, struct inode *, int);
int (*get_acl)(struct inode *, int);
- int (*setattr) (struct dentry *, struct iattr *);
- int (*getattr) (const struct path *, struct kstat *, u32, unsigned int);
+ int (*setattr) (struct user_namespace *, struct dentry *, struct iattr *);
+ int (*getattr) (struct user_namespace *, const struct path *, struct kstat *, u32, unsigned int);
ssize_t (*listxattr) (struct dentry *, char *, size_t);
void (*update_time)(struct inode *, struct timespec *, int);
int (*atomic_open)(struct inode *, struct dentry *, struct file *,
unsigned open_flag, umode_t create_mode);
- int (*tmpfile) (struct inode *, struct dentry *, umode_t);
+ int (*tmpfile) (struct user_namespace *, struct inode *, struct dentry *, umode_t);
+ int (*set_acl)(struct user_namespace *, struct inode *, struct posix_acl *, int);
};
Again, all methods are called without any locks being held, unless
549 common faccessat2 sys_faccessat2
550 common process_madvise sys_process_madvise
551 common epoll_pwait2 sys_epoll_pwait2
+552 common mount_setattr sys_mount_setattr
439 common faccessat2 sys_faccessat2
440 common process_madvise sys_process_madvise
441 common epoll_pwait2 sys_epoll_pwait2
+442 common mount_setattr sys_mount_setattr
#define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5)
#define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800)
-#define __NR_compat_syscalls 442
+#define __NR_compat_syscalls 443
#endif
#define __ARCH_WANT_SYS_CLONE
__SYSCALL(__NR_process_madvise, sys_process_madvise)
#define __NR_epoll_pwait2 441
__SYSCALL(__NR_epoll_pwait2, compat_sys_epoll_pwait2)
+#define __NR_mount_setattr 442
+__SYSCALL(__NR_mount_setattr, sys_mount_setattr)
/*
* Please add new compat syscalls above this comment and update
439 common faccessat2 sys_faccessat2
440 common process_madvise sys_process_madvise
441 common epoll_pwait2 sys_epoll_pwait2
+442 common mount_setattr sys_mount_setattr
439 common faccessat2 sys_faccessat2
440 common process_madvise sys_process_madvise
441 common epoll_pwait2 sys_epoll_pwait2
+442 common mount_setattr sys_mount_setattr
439 common faccessat2 sys_faccessat2
440 common process_madvise sys_process_madvise
441 common epoll_pwait2 sys_epoll_pwait2
+442 common mount_setattr sys_mount_setattr
439 n32 faccessat2 sys_faccessat2
440 n32 process_madvise sys_process_madvise
441 n32 epoll_pwait2 compat_sys_epoll_pwait2
+442 n32 mount_setattr sys_mount_setattr
439 n64 faccessat2 sys_faccessat2
440 n64 process_madvise sys_process_madvise
441 n64 epoll_pwait2 sys_epoll_pwait2
+442 n64 mount_setattr sys_mount_setattr
439 o32 faccessat2 sys_faccessat2
440 o32 process_madvise sys_process_madvise
441 o32 epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2
+442 o32 mount_setattr sys_mount_setattr
439 common faccessat2 sys_faccessat2
440 common process_madvise sys_process_madvise
441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2
+442 common mount_setattr sys_mount_setattr
439 common faccessat2 sys_faccessat2
440 common process_madvise sys_process_madvise
441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2
+442 common mount_setattr sys_mount_setattr
}
static int
-spufs_setattr(struct dentry *dentry, struct iattr *attr)
+spufs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
if ((attr->ia_valid & ATTR_SIZE) &&
(attr->ia_size != inode->i_size))
return -EINVAL;
- setattr_copy(inode, attr);
+ setattr_copy(&init_user_ns, inode, attr);
mark_inode_dirty(inode);
return 0;
}
439 common faccessat2 sys_faccessat2 sys_faccessat2
440 common process_madvise sys_process_madvise sys_process_madvise
441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2
+442 common mount_setattr sys_mount_setattr sys_mount_setattr
439 common faccessat2 sys_faccessat2
440 common process_madvise sys_process_madvise
441 common epoll_pwait2 sys_epoll_pwait2
+442 common mount_setattr sys_mount_setattr
439 common faccessat2 sys_faccessat2
440 common process_madvise sys_process_madvise
441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2
+442 common mount_setattr sys_mount_setattr
439 i386 faccessat2 sys_faccessat2
440 i386 process_madvise sys_process_madvise
441 i386 epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2
+442 i386 mount_setattr sys_mount_setattr
439 common faccessat2 sys_faccessat2
440 common process_madvise sys_process_madvise
441 common epoll_pwait2 sys_epoll_pwait2
+442 common mount_setattr sys_mount_setattr
#
# Due to a historical design error, certain syscalls are numbered differently
439 common faccessat2 sys_faccessat2
440 common process_madvise sys_process_madvise
441 common epoll_pwait2 sys_epoll_pwait2
+442 common mount_setattr sys_mount_setattr
return info->control_dentry == dentry;
}
-static int binderfs_rename(struct inode *old_dir, struct dentry *old_dentry,
+static int binderfs_rename(struct user_namespace *mnt_userns,
+ struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
is_binderfs_control_device(new_dentry))
return -EPERM;
- return simple_rename(old_dir, old_dentry, new_dir, new_dentry, flags);
+ return simple_rename(&init_user_ns, old_dir, old_dentry, new_dir,
+ new_dentry, flags);
}
static int binderfs_unlink(struct inode *dir, struct dentry *dentry)
if (IS_ERR(dentry))
return PTR_ERR(dentry);
- err = vfs_mkdir(d_inode(path.dentry), dentry, mode);
+ err = vfs_mkdir(&init_user_ns, d_inode(path.dentry), dentry, mode);
if (!err)
/* mark as kernel-created inode */
d_inode(dentry)->i_private = &thread;
if (IS_ERR(dentry))
return PTR_ERR(dentry);
- err = vfs_mknod(d_inode(path.dentry), dentry, mode, dev->devt);
+ err = vfs_mknod(&init_user_ns, d_inode(path.dentry), dentry, mode,
+ dev->devt);
if (!err) {
struct iattr newattrs;
newattrs.ia_gid = gid;
newattrs.ia_valid = ATTR_MODE|ATTR_UID|ATTR_GID;
inode_lock(d_inode(dentry));
- notify_change(dentry, &newattrs, NULL);
+ notify_change(&init_user_ns, dentry, &newattrs, NULL);
inode_unlock(d_inode(dentry));
/* mark as kernel-created inode */
return PTR_ERR(dentry);
if (d_really_is_positive(dentry)) {
if (d_inode(dentry)->i_private == &thread)
- err = vfs_rmdir(d_inode(parent.dentry), dentry);
+ err = vfs_rmdir(&init_user_ns, d_inode(parent.dentry),
+ dentry);
else
err = -EPERM;
} else {
newattrs.ia_valid =
ATTR_UID|ATTR_GID|ATTR_MODE;
inode_lock(d_inode(dentry));
- notify_change(dentry, &newattrs, NULL);
+ notify_change(&init_user_ns, dentry, &newattrs, NULL);
inode_unlock(d_inode(dentry));
- err = vfs_unlink(d_inode(parent.dentry), dentry, NULL);
+ err = vfs_unlink(&init_user_ns, d_inode(parent.dentry),
+ dentry, NULL);
if (!err || err == -ENOENT)
deleted = 1;
}
}
static int v9fs_xattr_set_acl(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *dentry, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
if (S_ISLNK(inode->i_mode))
return -EOPNOTSUPP;
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(&init_user_ns, inode))
return -EPERM;
if (value) {
/* update the cached acl value */
struct iattr iattr = { 0 };
struct posix_acl *old_acl = acl;
- retval = posix_acl_update_mode(inode, &iattr.ia_mode, &acl);
+ retval = posix_acl_update_mode(&init_user_ns, inode,
+ &iattr.ia_mode, &acl);
if (retval)
goto err_out;
if (!acl) {
* What is the following setxattr update the
* mode ?
*/
- v9fs_vfs_setattr_dotl(dentry, &iattr);
+ v9fs_vfs_setattr_dotl(&init_user_ns, dentry, &iattr);
}
break;
case ACL_TYPE_DEFAULT:
unsigned int flags);
extern int v9fs_vfs_unlink(struct inode *i, struct dentry *d);
extern int v9fs_vfs_rmdir(struct inode *i, struct dentry *d);
-extern int v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
+extern int v9fs_vfs_rename(struct user_namespace *mnt_userns,
+ struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags);
extern struct inode *v9fs_inode_from_fid(struct v9fs_session_info *v9ses,
int v9fs_uflags2omode(int uflags, int extended);
void v9fs_blank_wstat(struct p9_wstat *wstat);
-int v9fs_vfs_setattr_dotl(struct dentry *, struct iattr *);
+int v9fs_vfs_setattr_dotl(struct user_namespace *, struct dentry *,
+ struct iattr *);
int v9fs_file_fsync_dotl(struct file *filp, loff_t start, loff_t end,
int datasync);
int v9fs_refresh_inode(struct p9_fid *fid, struct inode *inode);
{
int err = 0;
- inode_init_owner(inode, NULL, mode);
+ inode_init_owner(&init_user_ns,inode, NULL, mode);
inode->i_blocks = 0;
inode->i_rdev = rdev;
inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
*/
static int
-v9fs_vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- bool excl)
+v9fs_vfs_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool excl)
{
struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dir);
u32 perm = unixmode2p9mode(v9ses, mode);
*
*/
-static int v9fs_vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int v9fs_vfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
int err;
u32 perm;
*/
int
-v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry,
- unsigned int flags)
+v9fs_vfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
+ struct dentry *old_dentry, struct inode *new_dir,
+ struct dentry *new_dentry, unsigned int flags)
{
int retval;
struct inode *old_inode;
*/
static int
-v9fs_vfs_getattr(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int flags)
+v9fs_vfs_getattr(struct user_namespace *mnt_userns, const struct path *path,
+ struct kstat *stat, u32 request_mask, unsigned int flags)
{
struct dentry *dentry = path->dentry;
struct v9fs_session_info *v9ses;
p9_debug(P9_DEBUG_VFS, "dentry: %p\n", dentry);
v9ses = v9fs_dentry2v9ses(dentry);
if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) {
- generic_fillattr(d_inode(dentry), stat);
+ generic_fillattr(&init_user_ns, d_inode(dentry), stat);
return 0;
}
fid = v9fs_fid_lookup(dentry);
return PTR_ERR(st);
v9fs_stat2inode(st, d_inode(dentry), dentry->d_sb, 0);
- generic_fillattr(d_inode(dentry), stat);
+ generic_fillattr(&init_user_ns, d_inode(dentry), stat);
p9stat_free(st);
kfree(st);
*
*/
-static int v9fs_vfs_setattr(struct dentry *dentry, struct iattr *iattr)
+static int v9fs_vfs_setattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct iattr *iattr)
{
int retval, use_dentry = 0;
struct v9fs_session_info *v9ses;
struct p9_wstat wstat;
p9_debug(P9_DEBUG_VFS, "\n");
- retval = setattr_prepare(dentry, iattr);
+ retval = setattr_prepare(&init_user_ns, dentry, iattr);
if (retval)
return retval;
v9fs_invalidate_inode_attr(d_inode(dentry));
- setattr_copy(d_inode(dentry), iattr);
+ setattr_copy(&init_user_ns, d_inode(dentry), iattr);
mark_inode_dirty(d_inode(dentry));
return 0;
}
*/
static int
-v9fs_vfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
+v9fs_vfs_symlink(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, const char *symname)
{
p9_debug(P9_DEBUG_VFS, " %lu,%pd,%s\n",
dir->i_ino, dentry, symname);
*/
static int
-v9fs_vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev)
+v9fs_vfs_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, dev_t rdev)
{
struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dir);
int retval;
#include "acl.h"
static int
-v9fs_vfs_mknod_dotl(struct inode *dir, struct dentry *dentry, umode_t omode,
- dev_t rdev);
+v9fs_vfs_mknod_dotl(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t omode, dev_t rdev);
/**
* v9fs_get_fsgid_for_create - Helper function to get the gid for creating a
*/
static int
-v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, umode_t omode,
- bool excl)
+v9fs_vfs_create_dotl(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t omode, bool excl)
{
- return v9fs_vfs_mknod_dotl(dir, dentry, omode, 0);
+ return v9fs_vfs_mknod_dotl(mnt_userns, dir, dentry, omode, 0);
}
static int
*
*/
-static int v9fs_vfs_mkdir_dotl(struct inode *dir,
- struct dentry *dentry, umode_t omode)
+static int v9fs_vfs_mkdir_dotl(struct user_namespace *mnt_userns,
+ struct inode *dir, struct dentry *dentry,
+ umode_t omode)
{
int err;
struct v9fs_session_info *v9ses;
}
static int
-v9fs_vfs_getattr_dotl(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int flags)
+v9fs_vfs_getattr_dotl(struct user_namespace *mnt_userns,
+ const struct path *path, struct kstat *stat,
+ u32 request_mask, unsigned int flags)
{
struct dentry *dentry = path->dentry;
struct v9fs_session_info *v9ses;
p9_debug(P9_DEBUG_VFS, "dentry: %p\n", dentry);
v9ses = v9fs_dentry2v9ses(dentry);
if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) {
- generic_fillattr(d_inode(dentry), stat);
+ generic_fillattr(&init_user_ns, d_inode(dentry), stat);
return 0;
}
fid = v9fs_fid_lookup(dentry);
return PTR_ERR(st);
v9fs_stat2inode_dotl(st, d_inode(dentry), 0);
- generic_fillattr(d_inode(dentry), stat);
+ generic_fillattr(&init_user_ns, d_inode(dentry), stat);
/* Change block size to what the server returned */
stat->blksize = st->st_blksize;
*
*/
-int v9fs_vfs_setattr_dotl(struct dentry *dentry, struct iattr *iattr)
+int v9fs_vfs_setattr_dotl(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct iattr *iattr)
{
int retval, use_dentry = 0;
struct p9_fid *fid = NULL;
p9_debug(P9_DEBUG_VFS, "\n");
- retval = setattr_prepare(dentry, iattr);
+ retval = setattr_prepare(&init_user_ns, dentry, iattr);
if (retval)
return retval;
truncate_setsize(inode, iattr->ia_size);
v9fs_invalidate_inode_attr(inode);
- setattr_copy(inode, iattr);
+ setattr_copy(&init_user_ns, inode, iattr);
mark_inode_dirty(inode);
if (iattr->ia_valid & ATTR_MODE) {
/* We also want to update ACL when we update mode bits */
}
static int
-v9fs_vfs_symlink_dotl(struct inode *dir, struct dentry *dentry,
- const char *symname)
+v9fs_vfs_symlink_dotl(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, const char *symname)
{
int err;
kgid_t gid;
*
*/
static int
-v9fs_vfs_mknod_dotl(struct inode *dir, struct dentry *dentry, umode_t omode,
- dev_t rdev)
+v9fs_vfs_mknod_dotl(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t omode, dev_t rdev)
{
int err;
kgid_t gid;
}
static int v9fs_xattr_handler_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *dentry, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
/* Inode stuff */
struct inode *adfs_iget(struct super_block *sb, struct object_info *obj);
int adfs_write_inode(struct inode *inode, struct writeback_control *wbc);
-int adfs_notify_change(struct dentry *dentry, struct iattr *attr);
+int adfs_notify_change(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr);
/* map.c */
int adfs_map_lookup(struct super_block *sb, u32 frag_id, unsigned int offset);
* later.
*/
int
-adfs_notify_change(struct dentry *dentry, struct iattr *attr)
+adfs_notify_change(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
struct super_block *sb = inode->i_sb;
unsigned int ia_valid = attr->ia_valid;
int error;
- error = setattr_prepare(dentry, attr);
+ error = setattr_prepare(&init_user_ns, dentry, attr);
/*
* we can't change the UID or GID of any file -
extern int affs_hash_name(struct super_block *sb, const u8 *name, unsigned int len);
extern struct dentry *affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int);
extern int affs_unlink(struct inode *dir, struct dentry *dentry);
-extern int affs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool);
-extern int affs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode);
+extern int affs_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool);
+extern int affs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode);
extern int affs_rmdir(struct inode *dir, struct dentry *dentry);
extern int affs_link(struct dentry *olddentry, struct inode *dir,
struct dentry *dentry);
-extern int affs_symlink(struct inode *dir, struct dentry *dentry,
- const char *symname);
-extern int affs_rename2(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry,
- unsigned int flags);
+extern int affs_symlink(struct user_namespace *mnt_userns,
+ struct inode *dir, struct dentry *dentry,
+ const char *symname);
+extern int affs_rename2(struct user_namespace *mnt_userns,
+ struct inode *old_dir, struct dentry *old_dentry,
+ struct inode *new_dir, struct dentry *new_dentry,
+ unsigned int flags);
/* inode.c */
extern struct inode *affs_new_inode(struct inode *dir);
-extern int affs_notify_change(struct dentry *dentry, struct iattr *attr);
+extern int affs_notify_change(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct iattr *attr);
extern void affs_evict_inode(struct inode *inode);
extern struct inode *affs_iget(struct super_block *sb,
unsigned long ino);
extern int affs_write_inode(struct inode *inode,
struct writeback_control *wbc);
-extern int affs_add_entry(struct inode *dir, struct inode *inode, struct dentry *dentry, s32 type);
+extern int affs_add_entry(struct inode *dir, struct inode *inode,
+ struct dentry *dentry, s32 type);
/* file.c */
}
int
-affs_notify_change(struct dentry *dentry, struct iattr *attr)
+affs_notify_change(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
int error;
pr_debug("notify_change(%lu,0x%x)\n", inode->i_ino, attr->ia_valid);
- error = setattr_prepare(dentry, attr);
+ error = setattr_prepare(&init_user_ns, dentry, attr);
if (error)
goto out;
affs_truncate(inode);
}
- setattr_copy(inode, attr);
+ setattr_copy(&init_user_ns, inode, attr);
mark_inode_dirty(inode);
if (attr->ia_valid & ATTR_MODE)
}
int
-affs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl)
+affs_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool excl)
{
struct super_block *sb = dir->i_sb;
struct inode *inode;
}
int
-affs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+affs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
struct inode *inode;
int error;
}
int
-affs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
+affs_symlink(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, const char *symname)
{
struct super_block *sb = dir->i_sb;
struct buffer_head *bh;
return retval;
}
-int affs_rename2(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry,
- unsigned int flags)
+int affs_rename2(struct user_namespace *mnt_userns, struct inode *old_dir,
+ struct dentry *old_dentry, struct inode *new_dir,
+ struct dentry *new_dentry, unsigned int flags)
{
if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE))
loff_t fpos, u64 ino, unsigned dtype);
static int afs_lookup_filldir(struct dir_context *ctx, const char *name, int nlen,
loff_t fpos, u64 ino, unsigned dtype);
-static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- bool excl);
-static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode);
+static int afs_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool excl);
+static int afs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode);
static int afs_rmdir(struct inode *dir, struct dentry *dentry);
static int afs_unlink(struct inode *dir, struct dentry *dentry);
static int afs_link(struct dentry *from, struct inode *dir,
struct dentry *dentry);
-static int afs_symlink(struct inode *dir, struct dentry *dentry,
- const char *content);
-static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry,
- unsigned int flags);
+static int afs_symlink(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, const char *content);
+static int afs_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
+ struct dentry *old_dentry, struct inode *new_dir,
+ struct dentry *new_dentry, unsigned int flags);
static int afs_dir_releasepage(struct page *page, gfp_t gfp_flags);
static void afs_dir_invalidatepage(struct page *page, unsigned int offset,
unsigned int length);
/*
* create a directory on an AFS filesystem
*/
-static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int afs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
struct afs_operation *op;
struct afs_vnode *dvnode = AFS_FS_I(dir);
/*
* create a regular file on an AFS filesystem
*/
-static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- bool excl)
+static int afs_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool excl)
{
struct afs_operation *op;
struct afs_vnode *dvnode = AFS_FS_I(dir);
/*
* create a symlink in an AFS filesystem
*/
-static int afs_symlink(struct inode *dir, struct dentry *dentry,
- const char *content)
+static int afs_symlink(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, const char *content)
{
struct afs_operation *op;
struct afs_vnode *dvnode = AFS_FS_I(dir);
/*
* rename a file in an AFS filesystem and/or move it between directories
*/
-static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry,
- unsigned int flags)
+static int afs_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
+ struct dentry *old_dentry, struct inode *new_dir,
+ struct dentry *new_dentry, unsigned int flags)
{
struct afs_operation *op;
struct afs_vnode *orig_dvnode, *new_dvnode, *vnode;
/*
* read the attributes of an inode
*/
-int afs_getattr(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int query_flags)
+int afs_getattr(struct user_namespace *mnt_userns, const struct path *path,
+ struct kstat *stat, u32 request_mask, unsigned int query_flags)
{
struct inode *inode = d_inode(path->dentry);
struct afs_vnode *vnode = AFS_FS_I(inode);
do {
read_seqbegin_or_lock(&vnode->cb_lock, &seq);
- generic_fillattr(inode, stat);
+ generic_fillattr(&init_user_ns, inode, stat);
if (test_bit(AFS_VNODE_SILLY_DELETED, &vnode->flags) &&
stat->nlink > 0)
stat->nlink -= 1;
/*
* set the attributes of an inode
*/
-int afs_setattr(struct dentry *dentry, struct iattr *attr)
+int afs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr)
{
struct afs_operation *op;
struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry));
extern struct inode *afs_root_iget(struct super_block *, struct key *);
extern bool afs_check_validity(struct afs_vnode *);
extern int afs_validate(struct afs_vnode *, struct key *);
-extern int afs_getattr(const struct path *, struct kstat *, u32, unsigned int);
-extern int afs_setattr(struct dentry *, struct iattr *);
+extern int afs_getattr(struct user_namespace *mnt_userns, const struct path *,
+ struct kstat *, u32, unsigned int);
+extern int afs_setattr(struct user_namespace *mnt_userns, struct dentry *, struct iattr *);
extern void afs_evict_inode(struct inode *);
extern int afs_drop_inode(struct inode *);
extern struct key *afs_request_key(struct afs_cell *);
extern struct key *afs_request_key_rcu(struct afs_cell *);
extern int afs_check_permit(struct afs_vnode *, struct key *, afs_access_t *);
-extern int afs_permission(struct inode *, int);
+extern int afs_permission(struct user_namespace *, struct inode *, int);
extern void __exit afs_clean_up_permit_cache(void);
/*
* - AFS ACLs are attached to directories only, and a file is controlled by its
* parent directory's ACL
*/
-int afs_permission(struct inode *inode, int mask)
+int afs_permission(struct user_namespace *mnt_userns, struct inode *inode,
+ int mask)
{
struct afs_vnode *vnode = AFS_FS_I(inode);
afs_access_t access;
* Set a file's AFS3 ACL.
*/
static int afs_xattr_set_acl(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *dentry,
struct inode *inode, const char *name,
const void *buffer, size_t size, int flags)
* Set a file's YFS ACL.
*/
static int afs_xattr_set_yfs(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *dentry,
struct inode *inode, const char *name,
const void *buffer, size_t size, int flags)
#include <linux/evm.h>
#include <linux/ima.h>
-static bool chown_ok(const struct inode *inode, kuid_t uid)
+/**
+ * chown_ok - verify permissions to chown inode
+ * @mnt_userns: user namespace of the mount @inode was found from
+ * @inode: inode to check permissions on
+ * @uid: uid to chown @inode to
+ *
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then
+ * take care to map the inode according to @mnt_userns before checking
+ * permissions. On non-idmapped mounts or if permission checking is to be
+ * performed on the raw inode simply passs init_user_ns.
+ */
+static bool chown_ok(struct user_namespace *mnt_userns,
+ const struct inode *inode,
+ kuid_t uid)
{
- if (uid_eq(current_fsuid(), inode->i_uid) &&
- uid_eq(uid, inode->i_uid))
+ kuid_t kuid = i_uid_into_mnt(mnt_userns, inode);
+ if (uid_eq(current_fsuid(), kuid) && uid_eq(uid, kuid))
return true;
- if (capable_wrt_inode_uidgid(inode, CAP_CHOWN))
+ if (capable_wrt_inode_uidgid(mnt_userns, inode, CAP_CHOWN))
return true;
- if (uid_eq(inode->i_uid, INVALID_UID) &&
+ if (uid_eq(kuid, INVALID_UID) &&
ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN))
return true;
return false;
}
-static bool chgrp_ok(const struct inode *inode, kgid_t gid)
+/**
+ * chgrp_ok - verify permissions to chgrp inode
+ * @mnt_userns: user namespace of the mount @inode was found from
+ * @inode: inode to check permissions on
+ * @gid: gid to chown @inode to
+ *
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then
+ * take care to map the inode according to @mnt_userns before checking
+ * permissions. On non-idmapped mounts or if permission checking is to be
+ * performed on the raw inode simply passs init_user_ns.
+ */
+static bool chgrp_ok(struct user_namespace *mnt_userns,
+ const struct inode *inode, kgid_t gid)
{
- if (uid_eq(current_fsuid(), inode->i_uid) &&
- (in_group_p(gid) || gid_eq(gid, inode->i_gid)))
+ kgid_t kgid = i_gid_into_mnt(mnt_userns, inode);
+ if (uid_eq(current_fsuid(), i_uid_into_mnt(mnt_userns, inode)) &&
+ (in_group_p(gid) || gid_eq(gid, kgid)))
return true;
- if (capable_wrt_inode_uidgid(inode, CAP_CHOWN))
+ if (capable_wrt_inode_uidgid(mnt_userns, inode, CAP_CHOWN))
return true;
- if (gid_eq(inode->i_gid, INVALID_GID) &&
+ if (gid_eq(kgid, INVALID_GID) &&
ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN))
return true;
return false;
/**
* setattr_prepare - check if attribute changes to a dentry are allowed
+ * @mnt_userns: user namespace of the mount the inode was found from
* @dentry: dentry to check
* @attr: attributes to change
*
* SGID bit from mode if user is not allowed to set it. Also file capabilities
* and IMA extended attributes are cleared if ATTR_KILL_PRIV is set.
*
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then
+ * take care to map the inode according to @mnt_userns before checking
+ * permissions. On non-idmapped mounts or if permission checking is to be
+ * performed on the raw inode simply passs init_user_ns.
+ *
* Should be called as the first thing in ->setattr implementations,
* possibly after taking additional locks.
*/
-int setattr_prepare(struct dentry *dentry, struct iattr *attr)
+int setattr_prepare(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
unsigned int ia_valid = attr->ia_valid;
goto kill_priv;
/* Make sure a caller can chown. */
- if ((ia_valid & ATTR_UID) && !chown_ok(inode, attr->ia_uid))
+ if ((ia_valid & ATTR_UID) && !chown_ok(mnt_userns, inode, attr->ia_uid))
return -EPERM;
/* Make sure caller can chgrp. */
- if ((ia_valid & ATTR_GID) && !chgrp_ok(inode, attr->ia_gid))
+ if ((ia_valid & ATTR_GID) && !chgrp_ok(mnt_userns, inode, attr->ia_gid))
return -EPERM;
/* Make sure a caller can chmod. */
if (ia_valid & ATTR_MODE) {
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(mnt_userns, inode))
return -EPERM;
/* Also check the setgid bit! */
- if (!in_group_p((ia_valid & ATTR_GID) ? attr->ia_gid :
- inode->i_gid) &&
- !capable_wrt_inode_uidgid(inode, CAP_FSETID))
+ if (!in_group_p((ia_valid & ATTR_GID) ? attr->ia_gid :
+ i_gid_into_mnt(mnt_userns, inode)) &&
+ !capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FSETID))
attr->ia_mode &= ~S_ISGID;
}
/* Check for setting the inode time. */
if (ia_valid & (ATTR_MTIME_SET | ATTR_ATIME_SET | ATTR_TIMES_SET)) {
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(mnt_userns, inode))
return -EPERM;
}
if (ia_valid & ATTR_KILL_PRIV) {
int error;
- error = security_inode_killpriv(dentry);
+ error = security_inode_killpriv(mnt_userns, dentry);
if (error)
return error;
}
/**
* setattr_copy - copy simple metadata updates into the generic inode
+ * @mnt_userns: user namespace of the mount the inode was found from
* @inode: the inode to be updated
* @attr: the new attributes
*
* setattr_copy must be called with i_mutex held.
*
* setattr_copy updates the inode's metadata with that specified
- * in attr. Noticeably missing is inode size update, which is more complex
+ * in attr on idmapped mounts. If file ownership is changed setattr_copy
+ * doesn't map ia_uid and ia_gid. It will asssume the caller has already
+ * provided the intended values. Necessary permission checks to determine
+ * whether or not the S_ISGID property needs to be removed are performed with
+ * the correct idmapped mount permission helpers.
+ * Noticeably missing is inode size update, which is more complex
* as it requires pagecache updates.
*
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then
+ * take care to map the inode according to @mnt_userns before checking
+ * permissions. On non-idmapped mounts or if permission checking is to be
+ * performed on the raw inode simply passs init_user_ns.
+ *
* The inode is not marked as dirty after this operation. The rationale is
* that for "simple" filesystems, the struct inode is the inode storage.
* The caller is free to mark the inode dirty afterwards if needed.
*/
-void setattr_copy(struct inode *inode, const struct iattr *attr)
+void setattr_copy(struct user_namespace *mnt_userns, struct inode *inode,
+ const struct iattr *attr)
{
unsigned int ia_valid = attr->ia_valid;
inode->i_ctime = attr->ia_ctime;
if (ia_valid & ATTR_MODE) {
umode_t mode = attr->ia_mode;
-
- if (!in_group_p(inode->i_gid) &&
- !capable_wrt_inode_uidgid(inode, CAP_FSETID))
+ kgid_t kgid = i_gid_into_mnt(mnt_userns, inode);
+ if (!in_group_p(kgid) &&
+ !capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FSETID))
mode &= ~S_ISGID;
inode->i_mode = mode;
}
/**
* notify_change - modify attributes of a filesytem object
+ * @mnt_userns: user namespace of the mount the inode was found from
* @dentry: object affected
* @attr: new attributes
* @delegated_inode: returns inode, if the inode is delegated
* retry. Because breaking a delegation may take a long time, the
* caller should drop the i_mutex before doing so.
*
+ * If file ownership is changed notify_change() doesn't map ia_uid and
+ * ia_gid. It will asssume the caller has already provided the intended values.
+ *
* Alternatively, a caller may pass NULL for delegated_inode. This may
* be appropriate for callers that expect the underlying filesystem not
* to be NFS exported. Also, passing NULL is fine for callers holding
* the file open for write, as there can be no conflicting delegation in
* that case.
+ *
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then
+ * take care to map the inode according to @mnt_userns before checking
+ * permissions. On non-idmapped mounts or if permission checking is to be
+ * performed on the raw inode simply passs init_user_ns.
*/
-int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **delegated_inode)
+int notify_change(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr, struct inode **delegated_inode)
{
struct inode *inode = dentry->d_inode;
umode_t mode = inode->i_mode;
if (IS_IMMUTABLE(inode))
return -EPERM;
- if (!inode_owner_or_capable(inode)) {
- error = inode_permission(inode, MAY_WRITE);
+ if (!inode_owner_or_capable(mnt_userns, inode)) {
+ error = inode_permission(mnt_userns, inode, MAY_WRITE);
if (error)
return error;
}
/* Don't allow modifications of files with invalid uids or
* gids unless those uids & gids are being made valid.
*/
- if (!(ia_valid & ATTR_UID) && !uid_valid(inode->i_uid))
+ if (!(ia_valid & ATTR_UID) &&
+ !uid_valid(i_uid_into_mnt(mnt_userns, inode)))
return -EOVERFLOW;
- if (!(ia_valid & ATTR_GID) && !gid_valid(inode->i_gid))
+ if (!(ia_valid & ATTR_GID) &&
+ !gid_valid(i_gid_into_mnt(mnt_userns, inode)))
return -EOVERFLOW;
error = security_inode_setattr(dentry, attr);
return error;
if (inode->i_op->setattr)
- error = inode->i_op->setattr(dentry, attr);
+ error = inode->i_op->setattr(mnt_userns, dentry, attr);
else
- error = simple_setattr(dentry, attr);
+ error = simple_setattr(mnt_userns, dentry, attr);
if (!error) {
fsnotify_change(dentry, ia_valid);
- ima_inode_post_setattr(dentry);
+ ima_inode_post_setattr(mnt_userns, dentry);
evm_inode_post_setattr(dentry, ia_valid);
}
#include "autofs_i.h"
-static int autofs_dir_symlink(struct inode *, struct dentry *, const char *);
+static int autofs_dir_symlink(struct user_namespace *, struct inode *,
+ struct dentry *, const char *);
static int autofs_dir_unlink(struct inode *, struct dentry *);
static int autofs_dir_rmdir(struct inode *, struct dentry *);
-static int autofs_dir_mkdir(struct inode *, struct dentry *, umode_t);
+static int autofs_dir_mkdir(struct user_namespace *, struct inode *,
+ struct dentry *, umode_t);
static long autofs_root_ioctl(struct file *, unsigned int, unsigned long);
#ifdef CONFIG_COMPAT
static long autofs_root_compat_ioctl(struct file *,
return NULL;
}
-static int autofs_dir_symlink(struct inode *dir,
- struct dentry *dentry,
- const char *symname)
+static int autofs_dir_symlink(struct user_namespace *mnt_userns,
+ struct inode *dir, struct dentry *dentry,
+ const char *symname)
{
struct autofs_sb_info *sbi = autofs_sbi(dir->i_sb);
struct autofs_info *ino = autofs_dentry_ino(dentry);
return 0;
}
-static int autofs_dir_mkdir(struct inode *dir,
- struct dentry *dentry, umode_t mode)
+static int autofs_dir_mkdir(struct user_namespace *mnt_userns,
+ struct inode *dir, struct dentry *dentry,
+ umode_t mode)
{
struct autofs_sb_info *sbi = autofs_sbi(dir->i_sb);
struct autofs_info *ino = autofs_dentry_ino(dentry);
.open = bad_file_open,
};
-static int bad_inode_create (struct inode *dir, struct dentry *dentry,
- umode_t mode, bool excl)
+static int bad_inode_create(struct user_namespace *mnt_userns,
+ struct inode *dir, struct dentry *dentry,
+ umode_t mode, bool excl)
{
return -EIO;
}
return -EIO;
}
-static int bad_inode_symlink (struct inode *dir, struct dentry *dentry,
- const char *symname)
+static int bad_inode_symlink(struct user_namespace *mnt_userns,
+ struct inode *dir, struct dentry *dentry,
+ const char *symname)
{
return -EIO;
}
-static int bad_inode_mkdir(struct inode *dir, struct dentry *dentry,
- umode_t mode)
+static int bad_inode_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
return -EIO;
}
return -EIO;
}
-static int bad_inode_mknod (struct inode *dir, struct dentry *dentry,
- umode_t mode, dev_t rdev)
+static int bad_inode_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, dev_t rdev)
{
return -EIO;
}
-static int bad_inode_rename2(struct inode *old_dir, struct dentry *old_dentry,
+static int bad_inode_rename2(struct user_namespace *mnt_userns,
+ struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
return -EIO;
}
-static int bad_inode_permission(struct inode *inode, int mask)
+static int bad_inode_permission(struct user_namespace *mnt_userns,
+ struct inode *inode, int mask)
{
return -EIO;
}
-static int bad_inode_getattr(const struct path *path, struct kstat *stat,
+static int bad_inode_getattr(struct user_namespace *mnt_userns,
+ const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int query_flags)
{
return -EIO;
}
-static int bad_inode_setattr(struct dentry *direntry, struct iattr *attrs)
+static int bad_inode_setattr(struct user_namespace *mnt_userns,
+ struct dentry *direntry, struct iattr *attrs)
{
return -EIO;
}
return -EIO;
}
-static int bad_inode_tmpfile(struct inode *inode, struct dentry *dentry,
+static int bad_inode_tmpfile(struct user_namespace *mnt_userns,
+ struct inode *inode, struct dentry *dentry,
umode_t mode)
{
return -EIO;
}
-static int bad_inode_set_acl(struct inode *inode, struct posix_acl *acl,
+static int bad_inode_set_acl(struct user_namespace *mnt_userns,
+ struct inode *inode, struct posix_acl *acl,
int type)
{
return -EIO;
.llseek = generic_file_llseek,
};
-static int bfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- bool excl)
+static int bfs_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool excl)
{
int err;
struct inode *inode;
}
set_bit(ino, info->si_imap);
info->si_freei--;
- inode_init_owner(inode, dir, mode);
+ inode_init_owner(&init_user_ns, inode, dir, mode);
inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
inode->i_blocks = 0;
inode->i_op = &bfs_file_inops;
return error;
}
-static int bfs_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry,
- unsigned int flags)
+static int bfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
+ struct dentry *old_dentry, struct inode *new_dir,
+ struct dentry *new_dentry, unsigned int flags)
{
struct inode *old_inode, *new_inode;
struct buffer_head *old_bh, *new_bh;
return ret;
}
-int btrfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+int btrfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
+ struct posix_acl *acl, int type)
{
int ret;
umode_t old_mode = inode->i_mode;
if (type == ACL_TYPE_ACCESS && acl) {
- ret = posix_acl_update_mode(inode, &inode->i_mode, &acl);
+ ret = posix_acl_update_mode(&init_user_ns, inode,
+ &inode->i_mode, &acl);
if (ret)
return ret;
}
/* acl.c */
#ifdef CONFIG_BTRFS_FS_POSIX_ACL
struct posix_acl *btrfs_get_acl(struct inode *inode, int type);
-int btrfs_set_acl(struct inode *inode, struct posix_acl *acl, int type);
+int btrfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
+ struct posix_acl *acl, int type);
int btrfs_init_acl(struct btrfs_trans_handle *trans,
struct inode *inode, struct inode *dir);
#else
return ret;
}
-static int btrfs_setattr(struct dentry *dentry, struct iattr *attr)
+static int btrfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
struct btrfs_root *root = BTRFS_I(inode)->root;
if (btrfs_root_readonly(root))
return -EROFS;
- err = setattr_prepare(dentry, attr);
+ err = setattr_prepare(&init_user_ns, dentry, attr);
if (err)
return err;
}
if (attr->ia_valid) {
- setattr_copy(inode, attr);
+ setattr_copy(&init_user_ns, inode, attr);
inode_inc_iversion(inode);
err = btrfs_dirty_inode(inode);
if (!err && attr->ia_valid & ATTR_MODE)
- err = posix_acl_chmod(inode, inode->i_mode);
+ err = posix_acl_chmod(&init_user_ns, inode,
+ inode->i_mode);
}
return err;
if (ret != 0)
goto fail_unlock;
- inode_init_owner(inode, dir, mode);
+ inode_init_owner(&init_user_ns, inode, dir, mode);
inode_set_bytes(inode, 0);
inode->i_mtime = current_time(inode);
return err;
}
-static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
- umode_t mode, dev_t rdev)
+static int btrfs_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, dev_t rdev)
{
struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
struct btrfs_trans_handle *trans;
return err;
}
-static int btrfs_create(struct inode *dir, struct dentry *dentry,
- umode_t mode, bool excl)
+static int btrfs_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool excl)
{
struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
struct btrfs_trans_handle *trans;
return err;
}
-static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int btrfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
struct inode *inode = NULL;
return -ENOMEM;
}
-static int btrfs_getattr(const struct path *path, struct kstat *stat,
+static int btrfs_getattr(struct user_namespace *mnt_userns,
+ const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int flags)
{
u64 delalloc_bytes;
STATX_ATTR_IMMUTABLE |
STATX_ATTR_NODUMP);
- generic_fillattr(inode, stat);
+ generic_fillattr(&init_user_ns, inode, stat);
stat->dev = BTRFS_I(inode)->root->anon_dev;
spin_lock(&BTRFS_I(inode)->lock);
return ret;
}
-static int btrfs_rename2(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry,
- unsigned int flags)
+static int btrfs_rename2(struct user_namespace *mnt_userns, struct inode *old_dir,
+ struct dentry *old_dentry, struct inode *new_dir,
+ struct dentry *new_dentry, unsigned int flags)
{
if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
return -EINVAL;
return ret;
}
-static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
- const char *symname)
+static int btrfs_symlink(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, const char *symname)
{
struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
struct btrfs_trans_handle *trans;
return __set_page_dirty_nobuffers(page);
}
-static int btrfs_permission(struct inode *inode, int mask)
+static int btrfs_permission(struct user_namespace *mnt_userns,
+ struct inode *inode, int mask)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
umode_t mode = inode->i_mode;
if (BTRFS_I(inode)->flags & BTRFS_INODE_READONLY)
return -EACCES;
}
- return generic_permission(inode, mask);
+ return generic_permission(&init_user_ns, inode, mask);
}
-static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int btrfs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
struct btrfs_trans_handle *trans;
const char *comp = NULL;
u32 binode_flags;
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(&init_user_ns, inode))
return -EPERM;
if (btrfs_root_readonly(root))
unsigned old_i_flags;
int ret = 0;
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(&init_user_ns, inode))
return -EPERM;
if (btrfs_root_readonly(root))
BUG_ON(d_inode(victim->d_parent) != dir);
audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE);
- error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
+ error = inode_permission(&init_user_ns, dir, MAY_WRITE | MAY_EXEC);
if (error)
return error;
if (IS_APPEND(dir))
return -EPERM;
- if (check_sticky(dir, d_inode(victim)) || IS_APPEND(d_inode(victim)) ||
- IS_IMMUTABLE(d_inode(victim)) || IS_SWAPFILE(d_inode(victim)))
+ if (check_sticky(&init_user_ns, dir, d_inode(victim)) ||
+ IS_APPEND(d_inode(victim)) || IS_IMMUTABLE(d_inode(victim)) ||
+ IS_SWAPFILE(d_inode(victim)))
return -EPERM;
if (isdir) {
if (!d_is_dir(victim))
return -EEXIST;
if (IS_DEADDIR(dir))
return -ENOENT;
- return inode_permission(dir, MAY_WRITE | MAY_EXEC);
+ return inode_permission(&init_user_ns, dir, MAY_WRITE | MAY_EXEC);
}
/*
btrfs_info(BTRFS_I(file_inode(file))->root->fs_info,
"Snapshot src from another FS");
ret = -EXDEV;
- } else if (!inode_owner_or_capable(src_inode)) {
+ } else if (!inode_owner_or_capable(&init_user_ns, src_inode)) {
/*
* Subvolume creation is not restricted, but snapshots
* are limited to own subvolumes only
u64 flags;
int ret = 0;
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(&init_user_ns, inode))
return -EPERM;
ret = mnt_want_write_file(file);
ret = PTR_ERR(temp_inode);
goto out_put;
}
- ret = inode_permission(temp_inode, MAY_READ | MAY_EXEC);
+ ret = inode_permission(&init_user_ns, temp_inode,
+ MAY_READ | MAY_EXEC);
iput(temp_inode);
if (ret) {
ret = -EACCES;
if (root == dest)
goto out_dput;
- err = inode_permission(inode, MAY_WRITE | MAY_EXEC);
+ err = inode_permission(&init_user_ns, inode,
+ MAY_WRITE | MAY_EXEC);
if (err)
goto out_dput;
}
* running and allows defrag on files open in read-only mode.
*/
if (!capable(CAP_SYS_ADMIN) &&
- inode_permission(inode, MAY_WRITE)) {
+ inode_permission(&init_user_ns, inode, MAY_WRITE)) {
ret = -EPERM;
goto out;
}
int ret = 0;
int received_uuid_changed;
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(&init_user_ns, inode))
return -EPERM;
ret = mnt_want_write_file(file);
BTRFS_I(inode)->location.type = BTRFS_INODE_ITEM_KEY;
BTRFS_I(inode)->location.objectid = BTRFS_FIRST_FREE_OBJECTID;
BTRFS_I(inode)->location.offset = 0;
- inode_init_owner(inode, NULL, S_IFREG);
+ inode_init_owner(&init_user_ns, inode, NULL, S_IFREG);
return inode;
}
}
static int btrfs_xattr_handler_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *name, const void *buffer,
size_t size, int flags)
}
static int btrfs_xattr_handler_set_prop(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
_debug("discard tail %llx", oi_size);
newattrs.ia_valid = ATTR_SIZE;
newattrs.ia_size = oi_size & PAGE_MASK;
- ret = notify_change(object->backer, &newattrs, NULL);
+ ret = notify_change(&init_user_ns, object->backer, &newattrs, NULL);
if (ret < 0)
goto truncate_failed;
}
newattrs.ia_valid = ATTR_SIZE;
newattrs.ia_size = ni_size;
- ret = notify_change(object->backer, &newattrs, NULL);
+ ret = notify_change(&init_user_ns, object->backer, &newattrs, NULL);
truncate_failed:
inode_unlock(d_inode(object->backer));
cachefiles_io_error(cache, "Unlink security error");
} else {
trace_cachefiles_unlink(object, rep, why);
- ret = vfs_unlink(d_inode(dir), rep, NULL);
+ ret = vfs_unlink(&init_user_ns, d_inode(dir), rep,
+ NULL);
if (preemptive)
cachefiles_mark_object_buried(cache, rep, why);
if (ret < 0) {
cachefiles_io_error(cache, "Rename security error %d", ret);
} else {
+ struct renamedata rd = {
+ .old_mnt_userns = &init_user_ns,
+ .old_dir = d_inode(dir),
+ .old_dentry = rep,
+ .new_mnt_userns = &init_user_ns,
+ .new_dir = d_inode(cache->graveyard),
+ .new_dentry = grave,
+ };
trace_cachefiles_rename(object, rep, grave, why);
- ret = vfs_rename(d_inode(dir), rep,
- d_inode(cache->graveyard), grave, NULL, 0);
+ ret = vfs_rename(&rd);
if (ret != 0 && ret != -ENOMEM)
cachefiles_io_error(cache,
"Rename failed with error %d", ret);
if (ret < 0)
goto create_error;
start = jiffies;
- ret = vfs_mkdir(d_inode(dir), next, 0);
+ ret = vfs_mkdir(&init_user_ns, d_inode(dir), next, 0);
cachefiles_hist(cachefiles_mkdir_histogram, start);
if (!key)
trace_cachefiles_mkdir(object, next, ret);
if (ret < 0)
goto create_error;
start = jiffies;
- ret = vfs_create(d_inode(dir), next, S_IFREG, true);
+ ret = vfs_create(&init_user_ns, d_inode(dir), next,
+ S_IFREG, true);
cachefiles_hist(cachefiles_create_histogram, start);
trace_cachefiles_create(object, next, ret);
if (ret < 0)
ret = security_path_mkdir(&path, subdir, 0700);
if (ret < 0)
goto mkdir_error;
- ret = vfs_mkdir(d_inode(dir), subdir, 0700);
+ ret = vfs_mkdir(&init_user_ns, d_inode(dir), subdir, 0700);
if (ret < 0)
goto mkdir_error;
_enter("%p{%s}", object, type);
/* attempt to install a type label directly */
- ret = vfs_setxattr(dentry, cachefiles_xattr_cache, type, 2,
- XATTR_CREATE);
+ ret = vfs_setxattr(&init_user_ns, dentry, cachefiles_xattr_cache, type,
+ 2, XATTR_CREATE);
if (ret == 0) {
_debug("SET"); /* we succeeded */
goto error;
}
/* read the current type label */
- ret = vfs_getxattr(dentry, cachefiles_xattr_cache, xtype, 3);
+ ret = vfs_getxattr(&init_user_ns, dentry, cachefiles_xattr_cache, xtype,
+ 3);
if (ret < 0) {
if (ret == -ERANGE)
goto bad_type_length;
_debug("SET #%u", auxdata->len);
clear_bit(FSCACHE_COOKIE_AUX_UPDATED, &object->fscache.cookie->flags);
- ret = vfs_setxattr(dentry, cachefiles_xattr_cache,
- &auxdata->type, auxdata->len,
- XATTR_CREATE);
+ ret = vfs_setxattr(&init_user_ns, dentry, cachefiles_xattr_cache,
+ &auxdata->type, auxdata->len, XATTR_CREATE);
if (ret < 0 && ret != -ENOMEM)
cachefiles_io_error_obj(
object,
_debug("SET #%u", auxdata->len);
clear_bit(FSCACHE_COOKIE_AUX_UPDATED, &object->fscache.cookie->flags);
- ret = vfs_setxattr(dentry, cachefiles_xattr_cache,
- &auxdata->type, auxdata->len,
- XATTR_REPLACE);
+ ret = vfs_setxattr(&init_user_ns, dentry, cachefiles_xattr_cache,
+ &auxdata->type, auxdata->len, XATTR_REPLACE);
if (ret < 0 && ret != -ENOMEM)
cachefiles_io_error_obj(
object,
if (!auxbuf)
return -ENOMEM;
- xlen = vfs_getxattr(dentry, cachefiles_xattr_cache,
+ xlen = vfs_getxattr(&init_user_ns, dentry, cachefiles_xattr_cache,
&auxbuf->type, 512 + 1);
ret = -ESTALE;
if (xlen < 1 ||
}
/* read the current type label */
- ret = vfs_getxattr(dentry, cachefiles_xattr_cache,
+ ret = vfs_getxattr(&init_user_ns, dentry, cachefiles_xattr_cache,
&auxbuf->type, 512 + 1);
if (ret < 0) {
if (ret == -ENODATA)
}
/* update the current label */
- ret = vfs_setxattr(dentry, cachefiles_xattr_cache,
- &auxdata->type, auxdata->len,
- XATTR_REPLACE);
+ ret = vfs_setxattr(&init_user_ns, dentry,
+ cachefiles_xattr_cache, &auxdata->type,
+ auxdata->len, XATTR_REPLACE);
if (ret < 0) {
cachefiles_io_error_obj(object,
"Can't update xattr on %lu"
{
int ret;
- ret = vfs_removexattr(dentry, cachefiles_xattr_cache);
+ ret = vfs_removexattr(&init_user_ns, dentry, cachefiles_xattr_cache);
if (ret < 0) {
if (ret == -ENOENT || ret == -ENODATA)
ret = 0;
return acl;
}
-int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+int ceph_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
+ struct posix_acl *acl, int type)
{
int ret = 0, size = 0;
const char *name = NULL;
case ACL_TYPE_ACCESS:
name = XATTR_NAME_POSIX_ACL_ACCESS;
if (acl) {
- ret = posix_acl_update_mode(inode, &new_mode, &acl);
+ ret = posix_acl_update_mode(&init_user_ns, inode,
+ &new_mode, &acl);
if (ret)
goto out;
}
return PTR_ERR(result);
}
-static int ceph_mknod(struct inode *dir, struct dentry *dentry,
- umode_t mode, dev_t rdev)
+static int ceph_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, dev_t rdev)
{
struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb);
struct ceph_mds_request *req;
return err;
}
-static int ceph_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- bool excl)
+static int ceph_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool excl)
{
- return ceph_mknod(dir, dentry, mode, 0);
+ return ceph_mknod(mnt_userns, dir, dentry, mode, 0);
}
-static int ceph_symlink(struct inode *dir, struct dentry *dentry,
- const char *dest)
+static int ceph_symlink(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, const char *dest)
{
struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb);
struct ceph_mds_request *req;
return err;
}
-static int ceph_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int ceph_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb);
struct ceph_mds_request *req;
return err;
}
-static int ceph_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry,
- unsigned int flags)
+static int ceph_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
+ struct dentry *old_dentry, struct inode *new_dir,
+ struct dentry *new_dentry, unsigned int flags)
{
struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(old_dir->i_sb);
struct ceph_mds_request *req;
/*
* setattr
*/
-int ceph_setattr(struct dentry *dentry, struct iattr *attr)
+int ceph_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
if (ceph_snap(inode) != CEPH_NOSNAP)
return -EROFS;
- err = setattr_prepare(dentry, attr);
+ err = setattr_prepare(&init_user_ns, dentry, attr);
if (err != 0)
return err;
err = __ceph_setattr(inode, attr);
if (err >= 0 && (attr->ia_valid & ATTR_MODE))
- err = posix_acl_chmod(inode, attr->ia_mode);
+ err = posix_acl_chmod(&init_user_ns, inode, attr->ia_mode);
return err;
}
* Check inode permissions. We verify we have a valid value for
* the AUTH cap, then call the generic handler.
*/
-int ceph_permission(struct inode *inode, int mask)
+int ceph_permission(struct user_namespace *mnt_userns, struct inode *inode,
+ int mask)
{
int err;
err = ceph_do_getattr(inode, CEPH_CAP_AUTH_SHARED, false);
if (!err)
- err = generic_permission(inode, mask);
+ err = generic_permission(&init_user_ns, inode, mask);
return err;
}
* Get all the attributes. If we have sufficient caps for the requested attrs,
* then we can avoid talking to the MDS at all.
*/
-int ceph_getattr(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int flags)
+int ceph_getattr(struct user_namespace *mnt_userns, const struct path *path,
+ struct kstat *stat, u32 request_mask, unsigned int flags)
{
struct inode *inode = d_inode(path->dentry);
struct ceph_inode_info *ci = ceph_inode(inode);
return err;
}
- generic_fillattr(inode, stat);
+ generic_fillattr(&init_user_ns, inode, stat);
stat->ino = ceph_present_inode(inode);
/*
{
return __ceph_do_getattr(inode, NULL, mask, force);
}
-extern int ceph_permission(struct inode *inode, int mask);
+extern int ceph_permission(struct user_namespace *mnt_userns,
+ struct inode *inode, int mask);
extern int __ceph_setattr(struct inode *inode, struct iattr *attr);
-extern int ceph_setattr(struct dentry *dentry, struct iattr *attr);
-extern int ceph_getattr(const struct path *path, struct kstat *stat,
+extern int ceph_setattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct iattr *attr);
+extern int ceph_getattr(struct user_namespace *mnt_userns,
+ const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int flags);
/* xattr.c */
#ifdef CONFIG_CEPH_FS_POSIX_ACL
struct posix_acl *ceph_get_acl(struct inode *, int);
-int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type);
+int ceph_set_acl(struct user_namespace *mnt_userns,
+ struct inode *inode, struct posix_acl *acl, int type);
int ceph_pre_init_acls(struct inode *dir, umode_t *mode,
struct ceph_acl_sec_ctx *as_ctx);
void ceph_init_inode_acls(struct inode *inode,
}
static int ceph_set_xattr_handler(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
return -EOPNOTSUPP;
}
-static int cifs_permission(struct inode *inode, int mask)
+static int cifs_permission(struct user_namespace *mnt_userns,
+ struct inode *inode, int mask)
{
struct cifs_sb_info *cifs_sb;
on the client (above and beyond ACL on servers) for
servers which do not support setting and viewing mode bits,
so allowing client to check permissions is useful */
- return generic_permission(inode, mask);
+ return generic_permission(&init_user_ns, inode, mask);
}
static struct kmem_cache *cifs_inode_cachep;
/* Functions related to inodes */
extern const struct inode_operations cifs_dir_inode_ops;
extern struct inode *cifs_root_iget(struct super_block *);
-extern int cifs_create(struct inode *, struct dentry *, umode_t,
- bool excl);
+extern int cifs_create(struct user_namespace *, struct inode *,
+ struct dentry *, umode_t, bool excl);
extern int cifs_atomic_open(struct inode *, struct dentry *,
struct file *, unsigned, umode_t);
extern struct dentry *cifs_lookup(struct inode *, struct dentry *,
unsigned int);
extern int cifs_unlink(struct inode *dir, struct dentry *dentry);
extern int cifs_hardlink(struct dentry *, struct inode *, struct dentry *);
-extern int cifs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
-extern int cifs_mkdir(struct inode *, struct dentry *, umode_t);
+extern int cifs_mknod(struct user_namespace *, struct inode *, struct dentry *,
+ umode_t, dev_t);
+extern int cifs_mkdir(struct user_namespace *, struct inode *, struct dentry *,
+ umode_t);
extern int cifs_rmdir(struct inode *, struct dentry *);
-extern int cifs_rename2(struct inode *, struct dentry *, struct inode *,
- struct dentry *, unsigned int);
+extern int cifs_rename2(struct user_namespace *, struct inode *,
+ struct dentry *, struct inode *, struct dentry *,
+ unsigned int);
extern int cifs_revalidate_file_attr(struct file *filp);
extern int cifs_revalidate_dentry_attr(struct dentry *);
extern int cifs_revalidate_file(struct file *filp);
extern int cifs_invalidate_mapping(struct inode *inode);
extern int cifs_revalidate_mapping(struct inode *inode);
extern int cifs_zap_mapping(struct inode *inode);
-extern int cifs_getattr(const struct path *, struct kstat *, u32, unsigned int);
-extern int cifs_setattr(struct dentry *, struct iattr *);
+extern int cifs_getattr(struct user_namespace *, const struct path *,
+ struct kstat *, u32, unsigned int);
+extern int cifs_setattr(struct user_namespace *, struct dentry *,
+ struct iattr *);
extern int cifs_fiemap(struct inode *, struct fiemap_extent_info *, u64 start,
u64 len);
/* Functions related to symlinks */
extern const char *cifs_get_link(struct dentry *, struct inode *,
struct delayed_call *);
-extern int cifs_symlink(struct inode *inode, struct dentry *direntry,
- const char *symname);
+extern int cifs_symlink(struct user_namespace *mnt_userns, struct inode *inode,
+ struct dentry *direntry, const char *symname);
#ifdef CONFIG_CIFS_XATTR
extern const struct xattr_handler *cifs_xattr_handlers[];
return rc;
}
-int cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode,
- bool excl)
+int cifs_create(struct user_namespace *mnt_userns, struct inode *inode,
+ struct dentry *direntry, umode_t mode, bool excl)
{
int rc;
unsigned int xid = get_xid();
return rc;
}
-int cifs_mknod(struct inode *inode, struct dentry *direntry, umode_t mode,
- dev_t device_number)
+int cifs_mknod(struct user_namespace *mnt_userns, struct inode *inode,
+ struct dentry *direntry, umode_t mode, dev_t device_number)
{
int rc = -EPERM;
unsigned int xid;
goto posix_mkdir_out;
}
-int cifs_mkdir(struct inode *inode, struct dentry *direntry, umode_t mode)
+int cifs_mkdir(struct user_namespace *mnt_userns, struct inode *inode,
+ struct dentry *direntry, umode_t mode)
{
int rc = 0;
unsigned int xid;
}
int
-cifs_rename2(struct inode *source_dir, struct dentry *source_dentry,
- struct inode *target_dir, struct dentry *target_dentry,
- unsigned int flags)
+cifs_rename2(struct user_namespace *mnt_userns, struct inode *source_dir,
+ struct dentry *source_dentry, struct inode *target_dir,
+ struct dentry *target_dentry, unsigned int flags)
{
char *from_name = NULL;
char *to_name = NULL;
return cifs_revalidate_mapping(inode);
}
-int cifs_getattr(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int flags)
+int cifs_getattr(struct user_namespace *mnt_userns, const struct path *path,
+ struct kstat *stat, u32 request_mask, unsigned int flags)
{
struct dentry *dentry = path->dentry;
struct cifs_sb_info *cifs_sb = CIFS_SB(dentry->d_sb);
return rc;
}
- generic_fillattr(inode, stat);
+ generic_fillattr(&init_user_ns, inode, stat);
stat->blksize = cifs_sb->ctx->bsize;
stat->ino = CIFS_I(inode)->uniqueid;
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM)
attrs->ia_valid |= ATTR_FORCE;
- rc = setattr_prepare(direntry, attrs);
+ rc = setattr_prepare(&init_user_ns, direntry, attrs);
if (rc < 0)
goto out;
attrs->ia_size != i_size_read(inode))
truncate_setsize(inode, attrs->ia_size);
- setattr_copy(inode, attrs);
+ setattr_copy(&init_user_ns, inode, attrs);
mark_inode_dirty(inode);
/* force revalidate when any of these times are set since some
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM)
attrs->ia_valid |= ATTR_FORCE;
- rc = setattr_prepare(direntry, attrs);
+ rc = setattr_prepare(&init_user_ns, direntry, attrs);
if (rc < 0) {
free_xid(xid);
return rc;
attrs->ia_size != i_size_read(inode))
truncate_setsize(inode, attrs->ia_size);
- setattr_copy(inode, attrs);
+ setattr_copy(&init_user_ns, inode, attrs);
mark_inode_dirty(inode);
cifs_setattr_exit:
}
int
-cifs_setattr(struct dentry *direntry, struct iattr *attrs)
+cifs_setattr(struct user_namespace *mnt_userns, struct dentry *direntry,
+ struct iattr *attrs)
{
struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb);
struct cifs_tcon *pTcon = cifs_sb_master_tcon(cifs_sb);
}
int
-cifs_symlink(struct inode *inode, struct dentry *direntry, const char *symname)
+cifs_symlink(struct user_namespace *mnt_userns, struct inode *inode,
+ struct dentry *direntry, const char *symname)
{
int rc = -EOPNOTSUPP;
unsigned int xid;
}
static int cifs_xattr_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *dentry, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
/* operations shared over more than one file */
int coda_open(struct inode *i, struct file *f);
int coda_release(struct inode *i, struct file *f);
-int coda_permission(struct inode *inode, int mask);
+int coda_permission(struct user_namespace *mnt_userns, struct inode *inode,
+ int mask);
int coda_revalidate_inode(struct inode *);
-int coda_getattr(const struct path *, struct kstat *, u32, unsigned int);
-int coda_setattr(struct dentry *, struct iattr *);
+int coda_getattr(struct user_namespace *, const struct path *, struct kstat *,
+ u32, unsigned int);
+int coda_setattr(struct user_namespace *, struct dentry *, struct iattr *);
/* this file: heloers */
char *coda_f2s(struct CodaFid *f);
}
-int coda_permission(struct inode *inode, int mask)
+int coda_permission(struct user_namespace *mnt_userns, struct inode *inode,
+ int mask)
{
int error;
}
/* creation routines: create, mknod, mkdir, link, symlink */
-static int coda_create(struct inode *dir, struct dentry *de, umode_t mode, bool excl)
+static int coda_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *de, umode_t mode, bool excl)
{
int error;
const char *name=de->d_name.name;
return error;
}
-static int coda_mkdir(struct inode *dir, struct dentry *de, umode_t mode)
+static int coda_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *de, umode_t mode)
{
struct inode *inode;
struct coda_vattr attrs;
}
-static int coda_symlink(struct inode *dir_inode, struct dentry *de,
+static int coda_symlink(struct user_namespace *mnt_userns,
+ struct inode *dir_inode, struct dentry *de,
const char *symname)
{
const char *name = de->d_name.name;
}
/* rename */
-static int coda_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry,
- unsigned int flags)
+static int coda_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
+ struct dentry *old_dentry, struct inode *new_dir,
+ struct dentry *new_dentry, unsigned int flags)
{
const char *old_name = old_dentry->d_name.name;
const char *new_name = new_dentry->d_name.name;
coda_cache_clear_inode(inode);
}
-int coda_getattr(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int flags)
+int coda_getattr(struct user_namespace *mnt_userns, const struct path *path,
+ struct kstat *stat, u32 request_mask, unsigned int flags)
{
int err = coda_revalidate_inode(d_inode(path->dentry));
if (!err)
- generic_fillattr(d_inode(path->dentry), stat);
+ generic_fillattr(&init_user_ns, d_inode(path->dentry), stat);
return err;
}
-int coda_setattr(struct dentry *de, struct iattr *iattr)
+int coda_setattr(struct user_namespace *mnt_userns, struct dentry *de,
+ struct iattr *iattr)
{
struct inode *inode = d_inode(de);
struct coda_vattr vattr;
#include "coda_linux.h"
/* pioctl ops */
-static int coda_ioctl_permission(struct inode *inode, int mask);
+static int coda_ioctl_permission(struct user_namespace *mnt_userns,
+ struct inode *inode, int mask);
static long coda_pioctl(struct file *filp, unsigned int cmd,
unsigned long user_data);
};
/* the coda pioctl inode ops */
-static int coda_ioctl_permission(struct inode *inode, int mask)
+static int coda_ioctl_permission(struct user_namespace *mnt_userns,
+ struct inode *inode, int mask)
{
return (mask & MAY_EXEC) ? -EACCES : 0;
}
extern const unsigned char * configfs_get_name(struct configfs_dirent *sd);
extern void configfs_drop_dentry(struct configfs_dirent *sd, struct dentry *parent);
-extern int configfs_setattr(struct dentry *dentry, struct iattr *iattr);
+extern int configfs_setattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct iattr *iattr);
extern struct dentry *configfs_pin_fs(void);
extern void configfs_release_fs(void);
extern const struct inode_operations configfs_symlink_inode_operations;
extern const struct dentry_operations configfs_dentry_ops;
-extern int configfs_symlink(struct inode *dir, struct dentry *dentry,
+extern int configfs_symlink(struct user_namespace *mnt_userns,
+ struct inode *dir, struct dentry *dentry,
const char *symname);
extern int configfs_unlink(struct inode *dir, struct dentry *dentry);
}
EXPORT_SYMBOL(configfs_depend_item_unlocked);
-static int configfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int configfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
int ret = 0;
int module_got = 0;
.setattr = configfs_setattr,
};
-int configfs_setattr(struct dentry * dentry, struct iattr * iattr)
+int configfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *iattr)
{
struct inode * inode = d_inode(dentry);
struct configfs_dirent * sd = dentry->d_fsdata;
}
/* attributes were changed atleast once in past */
- error = simple_setattr(dentry, iattr);
+ error = simple_setattr(mnt_userns, dentry, iattr);
if (error)
return error;
}
-int configfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
+int configfs_symlink(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, const char *symname)
{
int ret;
struct path path;
if (dentry->d_inode || d_unhashed(dentry))
ret = -EEXIST;
else
- ret = inode_permission(dir, MAY_WRITE | MAY_EXEC);
+ ret = inode_permission(&init_user_ns, dir,
+ MAY_WRITE | MAY_EXEC);
if (!ret)
ret = type->ct_item_ops->allow_link(parent_item, target_item);
if (!ret) {
goto close_fail;
}
} else {
+ struct user_namespace *mnt_userns;
struct inode *inode;
int open_flags = O_CREAT | O_RDWR | O_NOFOLLOW |
O_LARGEFILE | O_EXCL;
* a process dumps core while its cwd is e.g. on a vfat
* filesystem.
*/
- if (!uid_eq(inode->i_uid, current_fsuid()))
+ mnt_userns = file_mnt_user_ns(cprm.file);
+ if (!uid_eq(i_uid_into_mnt(mnt_userns, inode), current_fsuid()))
goto close_fail;
if ((inode->i_mode & 0677) != 0600)
goto close_fail;
if (!(cprm.file->f_mode & FMODE_CAN_WRITE))
goto close_fail;
- if (do_truncate(cprm.file->f_path.dentry, 0, 0, cprm.file))
+ if (do_truncate(mnt_userns, cprm.file->f_path.dentry,
+ 0, 0, cprm.file))
goto close_fail;
}
if (file->f_op->llseek && file->f_op->llseek != no_llseek) {
offset = file->f_op->llseek(file, 0, SEEK_CUR);
if (i_size_read(file->f_mapping->host) < offset)
- do_truncate(file->f_path.dentry, offset, 0, file);
+ do_truncate(file_mnt_user_ns(file), file->f_path.dentry,
+ offset, 0, file);
}
}
EXPORT_SYMBOL(dump_truncate);
return -EFAULT;
policy.version = version;
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(&init_user_ns, inode))
return -EACCES;
ret = mnt_want_write_file(filp);
* so that we can use the file mode as part of a heuristic to determine whether
* to lock down individual files.
*/
-static int debugfs_setattr(struct dentry *dentry, struct iattr *ia)
+static int debugfs_setattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct iattr *ia)
{
int ret = security_locked_down(LOCKDOWN_DEBUGFS);
if (ret && (ia->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)))
return ret;
- return simple_setattr(dentry, ia);
+ return simple_setattr(&init_user_ns, dentry, ia);
}
static const struct inode_operations debugfs_file_inode_operations = {
take_dentry_name_snapshot(&old_name, old_dentry);
- error = simple_rename(d_inode(old_dir), old_dentry, d_inode(new_dir),
- dentry, 0);
+ error = simple_rename(&init_user_ns, d_inode(old_dir), old_dentry,
+ d_inode(new_dir), dentry, 0);
if (error) {
release_dentry_name_snapshot(&old_name);
goto exit;
}
inode_lock(lower_inode);
- rc = __vfs_setxattr(lower_dentry, lower_inode, ECRYPTFS_XATTR_NAME,
- page_virt, size, 0);
+ rc = __vfs_setxattr(&init_user_ns, lower_dentry, lower_inode,
+ ECRYPTFS_XATTR_NAME, page_virt, size, 0);
if (!rc && ecryptfs_inode)
fsstack_copy_attr_all(ecryptfs_inode, lower_inode);
inode_unlock(lower_inode);
else if (d_unhashed(lower_dentry))
rc = -EINVAL;
else
- rc = vfs_unlink(lower_dir_inode, lower_dentry, NULL);
+ rc = vfs_unlink(&init_user_ns, lower_dir_inode, lower_dentry,
+ NULL);
if (rc) {
printk(KERN_ERR "Error in vfs_unlink; rc = [%d]\n", rc);
goto out_unlock;
lower_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry);
lower_dir_dentry = lock_parent(lower_dentry);
- rc = vfs_create(d_inode(lower_dir_dentry), lower_dentry, mode, true);
+ rc = vfs_create(&init_user_ns, d_inode(lower_dir_dentry), lower_dentry,
+ mode, true);
if (rc) {
printk(KERN_ERR "%s: Failure to create dentry in lower fs; "
"rc = [%d]\n", __func__, rc);
inode = __ecryptfs_get_inode(d_inode(lower_dentry),
directory_inode->i_sb);
if (IS_ERR(inode)) {
- vfs_unlink(d_inode(lower_dir_dentry), lower_dentry, NULL);
+ vfs_unlink(&init_user_ns, d_inode(lower_dir_dentry),
+ lower_dentry, NULL);
goto out_lock;
}
fsstack_copy_attr_times(directory_inode, d_inode(lower_dir_dentry));
* Returns zero on success; non-zero on error condition
*/
static int
-ecryptfs_create(struct inode *directory_inode, struct dentry *ecryptfs_dentry,
+ecryptfs_create(struct user_namespace *mnt_userns,
+ struct inode *directory_inode, struct dentry *ecryptfs_dentry,
umode_t mode, bool excl)
{
struct inode *ecryptfs_inode;
dget(lower_old_dentry);
dget(lower_new_dentry);
lower_dir_dentry = lock_parent(lower_new_dentry);
- rc = vfs_link(lower_old_dentry, d_inode(lower_dir_dentry),
- lower_new_dentry, NULL);
+ rc = vfs_link(lower_old_dentry, &init_user_ns,
+ d_inode(lower_dir_dentry), lower_new_dentry, NULL);
if (rc || d_really_is_negative(lower_new_dentry))
goto out_lock;
rc = ecryptfs_interpose(lower_new_dentry, new_dentry, dir->i_sb);
return ecryptfs_do_unlink(dir, dentry, d_inode(dentry));
}
-static int ecryptfs_symlink(struct inode *dir, struct dentry *dentry,
+static int ecryptfs_symlink(struct user_namespace *mnt_userns,
+ struct inode *dir, struct dentry *dentry,
const char *symname)
{
int rc;
strlen(symname));
if (rc)
goto out_lock;
- rc = vfs_symlink(d_inode(lower_dir_dentry), lower_dentry,
+ rc = vfs_symlink(&init_user_ns, d_inode(lower_dir_dentry), lower_dentry,
encoded_symname);
kfree(encoded_symname);
if (rc || d_really_is_negative(lower_dentry))
return rc;
}
-static int ecryptfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int ecryptfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
int rc;
struct dentry *lower_dentry;
lower_dentry = ecryptfs_dentry_to_lower(dentry);
lower_dir_dentry = lock_parent(lower_dentry);
- rc = vfs_mkdir(d_inode(lower_dir_dentry), lower_dentry, mode);
+ rc = vfs_mkdir(&init_user_ns, d_inode(lower_dir_dentry), lower_dentry,
+ mode);
if (rc || d_really_is_negative(lower_dentry))
goto out;
rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb);
else if (d_unhashed(lower_dentry))
rc = -EINVAL;
else
- rc = vfs_rmdir(lower_dir_inode, lower_dentry);
+ rc = vfs_rmdir(&init_user_ns, lower_dir_inode, lower_dentry);
if (!rc) {
clear_nlink(d_inode(dentry));
fsstack_copy_attr_times(dir, lower_dir_inode);
}
static int
-ecryptfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev)
+ecryptfs_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, dev_t dev)
{
int rc;
struct dentry *lower_dentry;
lower_dentry = ecryptfs_dentry_to_lower(dentry);
lower_dir_dentry = lock_parent(lower_dentry);
- rc = vfs_mknod(d_inode(lower_dir_dentry), lower_dentry, mode, dev);
+ rc = vfs_mknod(&init_user_ns, d_inode(lower_dir_dentry), lower_dentry,
+ mode, dev);
if (rc || d_really_is_negative(lower_dentry))
goto out;
rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb);
}
static int
-ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry,
- unsigned int flags)
+ecryptfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
+ struct dentry *old_dentry, struct inode *new_dir,
+ struct dentry *new_dentry, unsigned int flags)
{
int rc;
struct dentry *lower_old_dentry;
struct dentry *lower_new_dir_dentry;
struct dentry *trap;
struct inode *target_inode;
+ struct renamedata rd = {};
if (flags)
return -EINVAL;
rc = -ENOTEMPTY;
goto out_lock;
}
- rc = vfs_rename(d_inode(lower_old_dir_dentry), lower_old_dentry,
- d_inode(lower_new_dir_dentry), lower_new_dentry,
- NULL, 0);
+
+ rd.old_mnt_userns = &init_user_ns;
+ rd.old_dir = d_inode(lower_old_dir_dentry);
+ rd.old_dentry = lower_old_dentry;
+ rd.new_mnt_userns = &init_user_ns;
+ rd.new_dir = d_inode(lower_new_dir_dentry);
+ rd.new_dentry = lower_new_dentry;
+ rc = vfs_rename(&rd);
if (rc)
goto out_lock;
if (target_inode)
struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry);
inode_lock(d_inode(lower_dentry));
- rc = notify_change(lower_dentry, &lower_ia, NULL);
+ rc = notify_change(&init_user_ns, lower_dentry,
+ &lower_ia, NULL);
inode_unlock(d_inode(lower_dentry));
}
return rc;
}
static int
-ecryptfs_permission(struct inode *inode, int mask)
+ecryptfs_permission(struct user_namespace *mnt_userns, struct inode *inode,
+ int mask)
{
- return inode_permission(ecryptfs_inode_to_lower(inode), mask);
+ return inode_permission(&init_user_ns,
+ ecryptfs_inode_to_lower(inode), mask);
}
/**
* All other metadata changes will be passed right to the lower filesystem,
* and we will just update our inode to look like the lower.
*/
-static int ecryptfs_setattr(struct dentry *dentry, struct iattr *ia)
+static int ecryptfs_setattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct iattr *ia)
{
int rc = 0;
struct dentry *lower_dentry;
}
mutex_unlock(&crypt_stat->cs_mutex);
- rc = setattr_prepare(dentry, ia);
+ rc = setattr_prepare(&init_user_ns, dentry, ia);
if (rc)
goto out;
if (ia->ia_valid & ATTR_SIZE) {
lower_ia.ia_valid &= ~ATTR_MODE;
inode_lock(d_inode(lower_dentry));
- rc = notify_change(lower_dentry, &lower_ia, NULL);
+ rc = notify_change(&init_user_ns, lower_dentry, &lower_ia, NULL);
inode_unlock(d_inode(lower_dentry));
out:
fsstack_copy_attr_all(inode, lower_inode);
return rc;
}
-static int ecryptfs_getattr_link(const struct path *path, struct kstat *stat,
+static int ecryptfs_getattr_link(struct user_namespace *mnt_userns,
+ const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int flags)
{
struct dentry *dentry = path->dentry;
mount_crypt_stat = &ecryptfs_superblock_to_private(
dentry->d_sb)->mount_crypt_stat;
- generic_fillattr(d_inode(dentry), stat);
+ generic_fillattr(&init_user_ns, d_inode(dentry), stat);
if (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES) {
char *target;
size_t targetsiz;
return rc;
}
-static int ecryptfs_getattr(const struct path *path, struct kstat *stat,
+static int ecryptfs_getattr(struct user_namespace *mnt_userns,
+ const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int flags)
{
struct dentry *dentry = path->dentry;
if (!rc) {
fsstack_copy_attr_all(d_inode(dentry),
ecryptfs_inode_to_lower(d_inode(dentry)));
- generic_fillattr(d_inode(dentry), stat);
+ generic_fillattr(&init_user_ns, d_inode(dentry), stat);
stat->blocks = lower_stat.blocks;
}
return rc;
goto out;
}
inode_lock(lower_inode);
- rc = __vfs_setxattr_locked(lower_dentry, name, value, size, flags, NULL);
+ rc = __vfs_setxattr_locked(&init_user_ns, lower_dentry, name, value, size, flags, NULL);
inode_unlock(lower_inode);
if (!rc && inode)
fsstack_copy_attr_all(inode, lower_inode);
goto out;
}
inode_lock(lower_inode);
- rc = __vfs_removexattr(lower_dentry, name);
+ rc = __vfs_removexattr(&init_user_ns, lower_dentry, name);
inode_unlock(lower_inode);
out:
return rc;
}
static int ecryptfs_xattr_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *dentry, struct inode *inode,
const char *name, const void *value, size_t size,
int flags)
goto out_free;
}
+ if (mnt_user_ns(path.mnt) != &init_user_ns) {
+ rc = -EINVAL;
+ printk(KERN_ERR "Mounting on idmapped mounts currently disallowed\n");
+ goto out_free;
+ }
+
if (check_ruid && !uid_eq(d_inode(path.dentry)->i_uid, current_uid())) {
rc = -EPERM;
printk(KERN_ERR "Mount of device (uid: %d) not owned by "
if (size < 0)
size = 8;
put_unaligned_be64(i_size_read(ecryptfs_inode), xattr_virt);
- rc = __vfs_setxattr(lower_dentry, lower_inode, ECRYPTFS_XATTR_NAME,
- xattr_virt, size, 0);
+ rc = __vfs_setxattr(&init_user_ns, lower_dentry, lower_inode,
+ ECRYPTFS_XATTR_NAME, xattr_virt, size, 0);
inode_unlock(lower_inode);
if (rc)
printk(KERN_ERR "Error whilst attempting to write inode size "
unsigned int oldflags = efivarfs_getflags(inode);
int error;
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(&init_user_ns, inode))
return -EACCES;
if (copy_from_user(&flags, arg, sizeof(flags)))
return uuid_is_valid(s);
}
-static int efivarfs_create(struct inode *dir, struct dentry *dentry,
- umode_t mode, bool excl)
+static int efivarfs_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool excl)
{
struct inode *inode = NULL;
struct efivar_entry *var;
return inode;
}
-int erofs_getattr(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int query_flags)
+int erofs_getattr(struct user_namespace *mnt_userns, const struct path *path,
+ struct kstat *stat, u32 request_mask,
+ unsigned int query_flags)
{
struct inode *const inode = d_inode(path->dentry);
stat->attributes_mask |= (STATX_ATTR_COMPRESSED |
STATX_ATTR_IMMUTABLE);
- generic_fillattr(inode, stat);
+ generic_fillattr(&init_user_ns, inode, stat);
return 0;
}
extern const struct inode_operations erofs_fast_symlink_iops;
struct inode *erofs_iget(struct super_block *sb, erofs_nid_t nid, bool dir);
-int erofs_getattr(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int query_flags);
+int erofs_getattr(struct user_namespace *mnt_userns, const struct path *path,
+ struct kstat *stat, u32 request_mask,
+ unsigned int query_flags);
/* namei.c */
extern const struct inode_operations erofs_dir_iops;
void would_dump(struct linux_binprm *bprm, struct file *file)
{
struct inode *inode = file_inode(file);
- if (inode_permission(inode, MAY_READ) < 0) {
+ struct user_namespace *mnt_userns = file_mnt_user_ns(file);
+ if (inode_permission(mnt_userns, inode, MAY_READ) < 0) {
struct user_namespace *old, *user_ns;
bprm->interp_flags |= BINPRM_FLAGS_ENFORCE_NONDUMP;
/* Ensure mm->user_ns contains the executable */
user_ns = old = bprm->mm->user_ns;
while ((user_ns != &init_user_ns) &&
- !privileged_wrt_inode_uidgid(user_ns, inode))
+ !privileged_wrt_inode_uidgid(user_ns, mnt_userns, inode))
user_ns = user_ns->parent;
if (old != user_ns) {
static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file)
{
/* Handle suid and sgid on files */
+ struct user_namespace *mnt_userns;
struct inode *inode;
unsigned int mode;
kuid_t uid;
if (!(mode & (S_ISUID|S_ISGID)))
return;
+ mnt_userns = file_mnt_user_ns(file);
+
/* Be careful if suid/sgid is set */
inode_lock(inode);
/* reload atomically mode/uid/gid now that lock held */
mode = inode->i_mode;
- uid = inode->i_uid;
- gid = inode->i_gid;
+ uid = i_uid_into_mnt(mnt_userns, inode);
+ gid = i_gid_into_mnt(mnt_userns, inode);
inode_unlock(inode);
/* We ignore suid/sgid if there are no mappings for them in the ns */
extern const struct file_operations exfat_file_operations;
int __exfat_truncate(struct inode *inode, loff_t new_size);
void exfat_truncate(struct inode *inode, loff_t size);
-int exfat_setattr(struct dentry *dentry, struct iattr *attr);
-int exfat_getattr(const struct path *path, struct kstat *stat,
- unsigned int request_mask, unsigned int query_flags);
+int exfat_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr);
+int exfat_getattr(struct user_namespace *mnt_userns, const struct path *path,
+ struct kstat *stat, unsigned int request_mask,
+ unsigned int query_flags);
int exfat_file_fsync(struct file *file, loff_t start, loff_t end, int datasync);
/* namei.c */
mutex_unlock(&sbi->s_lock);
}
-int exfat_getattr(const struct path *path, struct kstat *stat,
- unsigned int request_mask, unsigned int query_flags)
+int exfat_getattr(struct user_namespace *mnt_uerns, const struct path *path,
+ struct kstat *stat, unsigned int request_mask,
+ unsigned int query_flags)
{
struct inode *inode = d_backing_inode(path->dentry);
struct exfat_inode_info *ei = EXFAT_I(inode);
- generic_fillattr(inode, stat);
+ generic_fillattr(&init_user_ns, inode, stat);
exfat_truncate_atime(&stat->atime);
stat->result_mask |= STATX_BTIME;
stat->btime.tv_sec = ei->i_crtime.tv_sec;
return 0;
}
-int exfat_setattr(struct dentry *dentry, struct iattr *attr)
+int exfat_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr)
{
struct exfat_sb_info *sbi = EXFAT_SB(dentry->d_sb);
struct inode *inode = dentry->d_inode;
ATTR_TIMES_SET);
}
- error = setattr_prepare(dentry, attr);
+ error = setattr_prepare(&init_user_ns, dentry, attr);
attr->ia_valid = ia_valid;
if (error)
goto out;
up_write(&EXFAT_I(inode)->truncate_lock);
}
- setattr_copy(inode, attr);
+ setattr_copy(&init_user_ns, inode, attr);
exfat_truncate_atime(&inode->i_atime);
mark_inode_dirty(inode);
return ret;
}
-static int exfat_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- bool excl)
+static int exfat_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool excl)
{
struct super_block *sb = dir->i_sb;
struct inode *inode;
return err;
}
-static int exfat_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int exfat_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
struct super_block *sb = dir->i_sb;
struct inode *inode;
return ret;
}
-static int exfat_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry,
- unsigned int flags)
+static int exfat_rename(struct user_namespace *mnt_userns,
+ struct inode *old_dir, struct dentry *old_dentry,
+ struct inode *new_dir, struct dentry *new_dentry,
+ unsigned int flags)
{
struct inode *old_inode, *new_inode;
struct super_block *sb = old_dir->i_sb;
* inode->i_mutex: down
*/
int
-ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+ext2_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
+ struct posix_acl *acl, int type)
{
int error;
int update_mode = 0;
umode_t mode = inode->i_mode;
if (type == ACL_TYPE_ACCESS && acl) {
- error = posix_acl_update_mode(inode, &mode, &acl);
+ error = posix_acl_update_mode(&init_user_ns, inode, &mode,
+ &acl);
if (error)
return error;
update_mode = 1;
/* acl.c */
extern struct posix_acl *ext2_get_acl(struct inode *inode, int type);
-extern int ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type);
+extern int ext2_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
+ struct posix_acl *acl, int type);
extern int ext2_init_acl (struct inode *, struct inode *);
#else
extern int ext2_write_inode (struct inode *, struct writeback_control *);
extern void ext2_evict_inode(struct inode *);
extern int ext2_get_block(struct inode *, sector_t, struct buffer_head *, int);
-extern int ext2_setattr (struct dentry *, struct iattr *);
-extern int ext2_getattr (const struct path *, struct kstat *, u32, unsigned int);
+extern int ext2_setattr (struct user_namespace *, struct dentry *, struct iattr *);
+extern int ext2_getattr (struct user_namespace *, const struct path *,
+ struct kstat *, u32, unsigned int);
extern void ext2_set_inode_flags(struct inode *inode);
extern int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 len);
inode->i_uid = current_fsuid();
inode->i_gid = dir->i_gid;
} else
- inode_init_owner(inode, dir, mode);
+ inode_init_owner(&init_user_ns, inode, dir, mode);
inode->i_ino = ino;
inode->i_blocks = 0;
return __ext2_write_inode(inode, wbc->sync_mode == WB_SYNC_ALL);
}
-int ext2_getattr(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int query_flags)
+int ext2_getattr(struct user_namespace *mnt_userns, const struct path *path,
+ struct kstat *stat, u32 request_mask, unsigned int query_flags)
{
struct inode *inode = d_inode(path->dentry);
struct ext2_inode_info *ei = EXT2_I(inode);
STATX_ATTR_IMMUTABLE |
STATX_ATTR_NODUMP);
- generic_fillattr(inode, stat);
+ generic_fillattr(&init_user_ns, inode, stat);
return 0;
}
-int ext2_setattr(struct dentry *dentry, struct iattr *iattr)
+int ext2_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *iattr)
{
struct inode *inode = d_inode(dentry);
int error;
- error = setattr_prepare(dentry, iattr);
+ error = setattr_prepare(&init_user_ns, dentry, iattr);
if (error)
return error;
if (error)
return error;
}
- setattr_copy(inode, iattr);
+ setattr_copy(&init_user_ns, inode, iattr);
if (iattr->ia_valid & ATTR_MODE)
- error = posix_acl_chmod(inode, inode->i_mode);
+ error = posix_acl_chmod(&init_user_ns, inode, inode->i_mode);
mark_inode_dirty(inode);
return error;
if (ret)
return ret;
- if (!inode_owner_or_capable(inode)) {
+ if (!inode_owner_or_capable(&init_user_ns, inode)) {
ret = -EACCES;
goto setflags_out;
}
case EXT2_IOC_SETVERSION: {
__u32 generation;
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(&init_user_ns, inode))
return -EPERM;
ret = mnt_want_write_file(filp);
if (ret)
if (!test_opt(inode->i_sb, RESERVATION) ||!S_ISREG(inode->i_mode))
return -ENOTTY;
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(&init_user_ns, inode))
return -EACCES;
if (get_user(rsv_window_size, (int __user *)arg))
* If the create succeeds, we fill in the inode information
* with d_instantiate().
*/
-static int ext2_create (struct inode * dir, struct dentry * dentry, umode_t mode, bool excl)
+static int ext2_create (struct user_namespace * mnt_userns,
+ struct inode * dir, struct dentry * dentry,
+ umode_t mode, bool excl)
{
struct inode *inode;
int err;
return ext2_add_nondir(dentry, inode);
}
-static int ext2_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int ext2_tmpfile(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
struct inode *inode = ext2_new_inode(dir, mode, NULL);
if (IS_ERR(inode))
return 0;
}
-static int ext2_mknod (struct inode * dir, struct dentry *dentry, umode_t mode, dev_t rdev)
+static int ext2_mknod (struct user_namespace * mnt_userns, struct inode * dir,
+ struct dentry *dentry, umode_t mode, dev_t rdev)
{
struct inode * inode;
int err;
return err;
}
-static int ext2_symlink (struct inode * dir, struct dentry * dentry,
- const char * symname)
+static int ext2_symlink (struct user_namespace * mnt_userns, struct inode * dir,
+ struct dentry * dentry, const char * symname)
{
struct super_block * sb = dir->i_sb;
int err = -ENAMETOOLONG;
return err;
}
-static int ext2_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
+static int ext2_mkdir(struct user_namespace * mnt_userns,
+ struct inode * dir, struct dentry * dentry, umode_t mode)
{
struct inode * inode;
int err;
return err;
}
-static int ext2_rename (struct inode * old_dir, struct dentry * old_dentry,
- struct inode * new_dir, struct dentry * new_dentry,
+static int ext2_rename (struct user_namespace * mnt_userns,
+ struct inode * old_dir, struct dentry * old_dentry,
+ struct inode * new_dir, struct dentry * new_dentry,
unsigned int flags)
{
struct inode * old_inode = d_inode(old_dentry);
static int
ext2_xattr_security_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
static int
ext2_xattr_trusted_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
static int
ext2_xattr_user_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
}
int
-ext4_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+ext4_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
+ struct posix_acl *acl, int type)
{
handle_t *handle;
int error, credits, retries = 0;
ext4_fc_start_update(inode);
if ((type == ACL_TYPE_ACCESS) && acl) {
- error = posix_acl_update_mode(inode, &mode, &acl);
+ error = posix_acl_update_mode(mnt_userns, inode, &mode, &acl);
if (error)
goto out_stop;
if (mode != inode->i_mode)
/* acl.c */
struct posix_acl *ext4_get_acl(struct inode *inode, int type);
-int ext4_set_acl(struct inode *inode, struct posix_acl *acl, int type);
+int ext4_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
+ struct posix_acl *acl, int type);
extern int ext4_init_acl(handle_t *, struct inode *, struct inode *);
#else /* CONFIG_EXT4_FS_POSIX_ACL */
/* ialloc.c */
extern int ext4_mark_inode_used(struct super_block *sb, int ino);
-extern struct inode *__ext4_new_inode(handle_t *, struct inode *, umode_t,
+extern struct inode *__ext4_new_inode(struct user_namespace *, handle_t *,
+ struct inode *, umode_t,
const struct qstr *qstr, __u32 goal,
uid_t *owner, __u32 i_flags,
int handle_type, unsigned int line_no,
int nblocks);
-#define ext4_new_inode(handle, dir, mode, qstr, goal, owner, i_flags) \
- __ext4_new_inode((handle), (dir), (mode), (qstr), (goal), (owner), \
- i_flags, 0, 0, 0)
-#define ext4_new_inode_start_handle(dir, mode, qstr, goal, owner, \
+#define ext4_new_inode(handle, dir, mode, qstr, goal, owner, i_flags) \
+ __ext4_new_inode(&init_user_ns, (handle), (dir), (mode), (qstr), \
+ (goal), (owner), i_flags, 0, 0, 0)
+#define ext4_new_inode_start_handle(mnt_userns, dir, mode, qstr, goal, owner, \
type, nblocks) \
- __ext4_new_inode(NULL, (dir), (mode), (qstr), (goal), (owner), \
+ __ext4_new_inode((mnt_userns), NULL, (dir), (mode), (qstr), (goal), (owner), \
0, (type), __LINE__, (nblocks))
__ext4_iget((sb), (ino), (flags), __func__, __LINE__)
extern int ext4_write_inode(struct inode *, struct writeback_control *);
-extern int ext4_setattr(struct dentry *, struct iattr *);
-extern int ext4_getattr(const struct path *, struct kstat *, u32, unsigned int);
+extern int ext4_setattr(struct user_namespace *, struct dentry *,
+ struct iattr *);
+extern int ext4_getattr(struct user_namespace *, const struct path *,
+ struct kstat *, u32, unsigned int);
extern void ext4_evict_inode(struct inode *);
extern void ext4_clear_inode(struct inode *);
-extern int ext4_file_getattr(const struct path *, struct kstat *, u32, unsigned int);
+extern int ext4_file_getattr(struct user_namespace *, const struct path *,
+ struct kstat *, u32, unsigned int);
extern int ext4_sync_inode(handle_t *, struct inode *);
extern void ext4_dirty_inode(struct inode *, int);
extern int ext4_change_inode_journal_flag(struct inode *, int);
* For other inodes, search forward from the parent directory's block
* group to find a free inode.
*/
-struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
+struct inode *__ext4_new_inode(struct user_namespace *mnt_userns,
+ handle_t *handle, struct inode *dir,
umode_t mode, const struct qstr *qstr,
__u32 goal, uid_t *owner, __u32 i_flags,
int handle_type, unsigned int line_no,
i_gid_write(inode, owner[1]);
} else if (test_opt(sb, GRPID)) {
inode->i_mode = mode;
- inode->i_uid = current_fsuid();
+ inode->i_uid = fsuid_into_mnt(mnt_userns);
inode->i_gid = dir->i_gid;
} else
- inode_init_owner(inode, dir, mode);
+ inode_init_owner(mnt_userns, inode, dir, mode);
if (ext4_has_feature_project(sb) &&
ext4_test_inode_flag(dir, EXT4_INODE_PROJINHERIT))
*/
#include <linux/fs.h>
+#include <linux/mount.h>
#include <linux/time.h>
#include <linux/highuid.h>
#include <linux/pagemap.h>
*
* Called with inode->i_mutex down.
*/
-int ext4_setattr(struct dentry *dentry, struct iattr *attr)
+int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
int error, rc = 0;
ATTR_GID | ATTR_TIMES_SET))))
return -EPERM;
- error = setattr_prepare(dentry, attr);
+ error = setattr_prepare(mnt_userns, dentry, attr);
if (error)
return error;
}
if (!error) {
- setattr_copy(inode, attr);
+ setattr_copy(mnt_userns, inode, attr);
mark_inode_dirty(inode);
}
ext4_orphan_del(NULL, inode);
if (!error && (ia_valid & ATTR_MODE))
- rc = posix_acl_chmod(inode, inode->i_mode);
+ rc = posix_acl_chmod(mnt_userns, inode, inode->i_mode);
err_out:
if (error)
return error;
}
-int ext4_getattr(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int query_flags)
+int ext4_getattr(struct user_namespace *mnt_userns, const struct path *path,
+ struct kstat *stat, u32 request_mask, unsigned int query_flags)
{
struct inode *inode = d_inode(path->dentry);
struct ext4_inode *raw_inode;
STATX_ATTR_NODUMP |
STATX_ATTR_VERITY);
- generic_fillattr(inode, stat);
+ generic_fillattr(mnt_userns, inode, stat);
return 0;
}
-int ext4_file_getattr(const struct path *path, struct kstat *stat,
+int ext4_file_getattr(struct user_namespace *mnt_userns,
+ const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int query_flags)
{
struct inode *inode = d_inode(path->dentry);
u64 delalloc_blocks;
- ext4_getattr(path, stat, request_mask, query_flags);
+ ext4_getattr(mnt_userns, path, stat, request_mask, query_flags);
/*
* If there is inline data in the inode, the inode will normally not
* important fields of the inodes.
*
* @sb: the super block of the filesystem
+ * @mnt_userns: user namespace of the mount the inode was found from
* @inode: the inode to swap with EXT4_BOOT_LOADER_INO
*
*/
static long swap_inode_boot_loader(struct super_block *sb,
+ struct user_namespace *mnt_userns,
struct inode *inode)
{
handle_t *handle;
}
if (IS_RDONLY(inode) || IS_APPEND(inode) || IS_IMMUTABLE(inode) ||
- !inode_owner_or_capable(inode) || !capable(CAP_SYS_ADMIN)) {
+ !inode_owner_or_capable(mnt_userns, inode) ||
+ !capable(CAP_SYS_ADMIN)) {
err = -EPERM;
goto journal_err_out;
}
struct inode *inode = file_inode(filp);
struct super_block *sb = inode->i_sb;
struct ext4_inode_info *ei = EXT4_I(inode);
+ struct user_namespace *mnt_userns = file_mnt_user_ns(filp);
unsigned int flags;
ext4_debug("cmd = %u, arg = %lu\n", cmd, arg);
case FS_IOC_SETFLAGS: {
int err;
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(mnt_userns, inode))
return -EACCES;
if (get_user(flags, (int __user *) arg))
__u32 generation;
int err;
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(mnt_userns, inode))
return -EPERM;
if (ext4_has_metadata_csum(inode->i_sb)) {
case EXT4_IOC_MIGRATE:
{
int err;
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(mnt_userns, inode))
return -EACCES;
err = mnt_want_write_file(filp);
case EXT4_IOC_ALLOC_DA_BLKS:
{
int err;
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(mnt_userns, inode))
return -EACCES;
err = mnt_want_write_file(filp);
err = mnt_want_write_file(filp);
if (err)
return err;
- err = swap_inode_boot_loader(sb, inode);
+ err = swap_inode_boot_loader(sb, mnt_userns, inode);
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_CLEAR_ES_CACHE:
{
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(mnt_userns, inode))
return -EACCES;
ext4_clear_inode_es(inode);
return 0;
return -EFAULT;
/* Make sure caller has proper permission */
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(mnt_userns, inode))
return -EACCES;
if (fa.fsx_xflags & ~EXT4_SUPPORTED_FS_XFLAGS)
* If the create succeeds, we fill in the inode information
* with d_instantiate().
*/
-static int ext4_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- bool excl)
+static int ext4_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool excl)
{
handle_t *handle;
struct inode *inode;
credits = (EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3);
retry:
- inode = ext4_new_inode_start_handle(dir, mode, &dentry->d_name, 0,
- NULL, EXT4_HT_DIR, credits);
+ inode = ext4_new_inode_start_handle(mnt_userns, dir, mode, &dentry->d_name,
+ 0, NULL, EXT4_HT_DIR, credits);
handle = ext4_journal_current_handle();
err = PTR_ERR(inode);
if (!IS_ERR(inode)) {
return err;
}
-static int ext4_mknod(struct inode *dir, struct dentry *dentry,
- umode_t mode, dev_t rdev)
+static int ext4_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, dev_t rdev)
{
handle_t *handle;
struct inode *inode;
credits = (EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3);
retry:
- inode = ext4_new_inode_start_handle(dir, mode, &dentry->d_name, 0,
- NULL, EXT4_HT_DIR, credits);
+ inode = ext4_new_inode_start_handle(mnt_userns, dir, mode, &dentry->d_name,
+ 0, NULL, EXT4_HT_DIR, credits);
handle = ext4_journal_current_handle();
err = PTR_ERR(inode);
if (!IS_ERR(inode)) {
return err;
}
-static int ext4_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int ext4_tmpfile(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
handle_t *handle;
struct inode *inode;
return err;
retry:
- inode = ext4_new_inode_start_handle(dir, mode,
+ inode = ext4_new_inode_start_handle(mnt_userns, dir, mode,
NULL, 0, NULL,
EXT4_HT_DIR,
EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb) +
return err;
}
-static int ext4_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int ext4_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
handle_t *handle;
struct inode *inode;
credits = (EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3);
retry:
- inode = ext4_new_inode_start_handle(dir, S_IFDIR | mode,
+ inode = ext4_new_inode_start_handle(mnt_userns, dir, S_IFDIR | mode,
&dentry->d_name,
0, NULL, EXT4_HT_DIR, credits);
handle = ext4_journal_current_handle();
return retval;
}
-static int ext4_symlink(struct inode *dir,
+static int ext4_symlink(struct user_namespace *mnt_userns, struct inode *dir,
struct dentry *dentry, const char *symname)
{
handle_t *handle;
EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3;
}
- inode = ext4_new_inode_start_handle(dir, S_IFLNK|S_IRWXUGO,
+ inode = ext4_new_inode_start_handle(mnt_userns, dir, S_IFLNK|S_IRWXUGO,
&dentry->d_name, 0, NULL,
EXT4_HT_DIR, credits);
handle = ext4_journal_current_handle();
}
}
-static struct inode *ext4_whiteout_for_rename(struct ext4_renament *ent,
+static struct inode *ext4_whiteout_for_rename(struct user_namespace *mnt_userns,
+ struct ext4_renament *ent,
int credits, handle_t **h)
{
struct inode *wh;
credits += (EXT4_MAXQUOTAS_TRANS_BLOCKS(ent->dir->i_sb) +
EXT4_XATTR_TRANS_BLOCKS + 4);
retry:
- wh = ext4_new_inode_start_handle(ent->dir, S_IFCHR | WHITEOUT_MODE,
+ wh = ext4_new_inode_start_handle(mnt_userns, ent->dir,
+ S_IFCHR | WHITEOUT_MODE,
&ent->dentry->d_name, 0, NULL,
EXT4_HT_DIR, credits);
* while new_{dentry,inode) refers to the destination dentry/inode
* This comes from rename(const char *oldpath, const char *newpath)
*/
-static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry,
- unsigned int flags)
+static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
+ struct dentry *old_dentry, struct inode *new_dir,
+ struct dentry *new_dentry, unsigned int flags)
{
handle_t *handle = NULL;
struct ext4_renament old = {
goto end_rename;
}
} else {
- whiteout = ext4_whiteout_for_rename(&old, credits, &handle);
+ whiteout = ext4_whiteout_for_rename(mnt_userns, &old, credits, &handle);
if (IS_ERR(whiteout)) {
retval = PTR_ERR(whiteout);
whiteout = NULL;
return retval;
}
-static int ext4_rename2(struct inode *old_dir, struct dentry *old_dentry,
+static int ext4_rename2(struct user_namespace *mnt_userns,
+ struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
new_dir, new_dentry);
}
- return ext4_rename(old_dir, old_dentry, new_dir, new_dentry, flags);
+ return ext4_rename(mnt_userns, old_dir, old_dentry, new_dir, new_dentry, flags);
}
/*
.name = "ext4",
.mount = ext4_mount,
.kill_sb = kill_block_super,
- .fs_flags = FS_REQUIRES_DEV,
+ .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP,
};
MODULE_ALIAS_FS("ext4");
static int
ext4_xattr_hurd_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
static int
ext4_xattr_security_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
static int
ext4_xattr_trusted_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
static int
ext4_xattr_user_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
return error;
if (error == 0)
*acl = NULL;
- if (!in_group_p(inode->i_gid) &&
- !capable_wrt_inode_uidgid(inode, CAP_FSETID))
+ if (!in_group_p(i_gid_into_mnt(&init_user_ns, inode)) &&
+ !capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_FSETID))
mode &= ~S_ISGID;
*mode_p = mode;
return 0;
return error;
}
-int f2fs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+int f2fs_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
+ struct posix_acl *acl, int type)
{
if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
return -EIO;
#ifdef CONFIG_F2FS_FS_POSIX_ACL
extern struct posix_acl *f2fs_get_acl(struct inode *, int);
-extern int f2fs_set_acl(struct inode *, struct posix_acl *, int);
+extern int f2fs_set_acl(struct user_namespace *, struct inode *,
+ struct posix_acl *, int);
extern int f2fs_init_acl(struct inode *, struct inode *, struct page *,
struct page *);
#else
int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock);
int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock);
int f2fs_truncate(struct inode *inode);
-int f2fs_getattr(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int flags);
-int f2fs_setattr(struct dentry *dentry, struct iattr *attr);
+int f2fs_getattr(struct user_namespace *mnt_userns, const struct path *path,
+ struct kstat *stat, u32 request_mask, unsigned int flags);
+int f2fs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr);
int f2fs_truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end);
void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count);
int f2fs_precache_extents(struct inode *inode);
return 0;
}
-int f2fs_getattr(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int query_flags)
+int f2fs_getattr(struct user_namespace *mnt_userns, const struct path *path,
+ struct kstat *stat, u32 request_mask, unsigned int query_flags)
{
struct inode *inode = d_inode(path->dentry);
struct f2fs_inode_info *fi = F2FS_I(inode);
STATX_ATTR_NODUMP |
STATX_ATTR_VERITY);
- generic_fillattr(inode, stat);
+ generic_fillattr(&init_user_ns, inode, stat);
/* we need to show initial sectors used for inline_data/dentries */
if ((S_ISREG(inode->i_mode) && f2fs_has_inline_data(inode)) ||
}
#ifdef CONFIG_F2FS_FS_POSIX_ACL
-static void __setattr_copy(struct inode *inode, const struct iattr *attr)
+static void __setattr_copy(struct user_namespace *mnt_userns,
+ struct inode *inode, const struct iattr *attr)
{
unsigned int ia_valid = attr->ia_valid;
inode->i_ctime = attr->ia_ctime;
if (ia_valid & ATTR_MODE) {
umode_t mode = attr->ia_mode;
+ kgid_t kgid = i_gid_into_mnt(mnt_userns, inode);
- if (!in_group_p(inode->i_gid) &&
- !capable_wrt_inode_uidgid(inode, CAP_FSETID))
+ if (!in_group_p(kgid) && !capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FSETID))
mode &= ~S_ISGID;
set_acl_inode(inode, mode);
}
#define __setattr_copy setattr_copy
#endif
-int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
+int f2fs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
int err;
!f2fs_is_compress_backend_ready(inode))
return -EOPNOTSUPP;
- err = setattr_prepare(dentry, attr);
+ err = setattr_prepare(&init_user_ns, dentry, attr);
if (err)
return err;
spin_unlock(&F2FS_I(inode)->i_size_lock);
}
- __setattr_copy(inode, attr);
+ __setattr_copy(&init_user_ns, inode, attr);
if (attr->ia_valid & ATTR_MODE) {
- err = posix_acl_chmod(inode, f2fs_get_inode_mode(inode));
+ err = posix_acl_chmod(&init_user_ns, inode, f2fs_get_inode_mode(inode));
if (is_inode_flag_set(inode, FI_ACL_MODE)) {
if (!err)
u32 iflags;
int ret;
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(&init_user_ns, inode))
return -EACCES;
if (get_user(fsflags, (int __user *)arg))
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
int ret;
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(&init_user_ns, inode))
return -EACCES;
if (!S_ISREG(inode->i_mode))
struct inode *inode = file_inode(filp);
int ret;
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(&init_user_ns, inode))
return -EACCES;
ret = mnt_want_write_file(filp);
struct inode *inode = file_inode(filp);
int ret;
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(&init_user_ns, inode))
return -EACCES;
if (!S_ISREG(inode->i_mode))
struct inode *inode = file_inode(filp);
int ret;
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(&init_user_ns, inode))
return -EACCES;
ret = mnt_want_write_file(filp);
struct inode *inode = file_inode(filp);
int ret;
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(&init_user_ns, inode))
return -EACCES;
ret = mnt_want_write_file(filp);
return -EFAULT;
/* Make sure caller has proper permission */
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(&init_user_ns, inode))
return -EACCES;
if (fa.fsx_xflags & ~F2FS_SUPPORTED_XFLAGS)
nid_free = true;
- inode_init_owner(inode, dir, mode);
+ inode_init_owner(&init_user_ns, inode, dir, mode);
inode->i_ino = ino;
inode->i_blocks = 0;
}
}
-static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- bool excl)
+static int f2fs_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool excl)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct inode *inode;
return link;
}
-static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
- const char *symname)
+static int f2fs_symlink(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, const char *symname)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct inode *inode;
return err;
}
-static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int f2fs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct inode *inode;
return -ENOTEMPTY;
}
-static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
- umode_t mode, dev_t rdev)
+static int f2fs_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, dev_t rdev)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct inode *inode;
return err;
}
-static int f2fs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int f2fs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
return err;
}
-static int f2fs_rename2(struct inode *old_dir, struct dentry *old_dentry,
+static int f2fs_rename2(struct user_namespace *mnt_userns,
+ struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
}
static int f2fs_xattr_generic_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
}
static int f2fs_xattr_advise_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
unsigned char old_advise = F2FS_I(inode)->i_advise;
unsigned char new_advise;
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(&init_user_ns, inode))
return -EPERM;
if (value == NULL)
return -EINVAL;
unsigned long arg);
extern const struct file_operations fat_file_operations;
extern const struct inode_operations fat_file_inode_operations;
-extern int fat_setattr(struct dentry *dentry, struct iattr *attr);
+extern int fat_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr);
extern void fat_truncate_blocks(struct inode *inode, loff_t offset);
-extern int fat_getattr(const struct path *path, struct kstat *stat,
+extern int fat_getattr(struct user_namespace *mnt_userns,
+ const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int flags);
extern int fat_file_fsync(struct file *file, loff_t start, loff_t end,
int datasync);
goto out_unlock_inode;
/* This MUST be done before doing anything irreversible... */
- err = fat_setattr(file->f_path.dentry, &ia);
+ err = fat_setattr(file_mnt_user_ns(file), file->f_path.dentry, &ia);
if (err)
goto out_unlock_inode;
fat_flush_inodes(inode->i_sb, inode, NULL);
}
-int fat_getattr(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int flags)
+int fat_getattr(struct user_namespace *mnt_userns, const struct path *path,
+ struct kstat *stat, u32 request_mask, unsigned int flags)
{
struct inode *inode = d_inode(path->dentry);
- generic_fillattr(inode, stat);
+ generic_fillattr(mnt_userns, inode, stat);
stat->blksize = MSDOS_SB(inode->i_sb)->cluster_size;
if (MSDOS_SB(inode->i_sb)->options.nfs == FAT_NFS_NOSTALE_RO) {
return 0;
}
-static int fat_allow_set_time(struct msdos_sb_info *sbi, struct inode *inode)
+static int fat_allow_set_time(struct user_namespace *mnt_userns,
+ struct msdos_sb_info *sbi, struct inode *inode)
{
umode_t allow_utime = sbi->options.allow_utime;
- if (!uid_eq(current_fsuid(), inode->i_uid)) {
- if (in_group_p(inode->i_gid))
+ if (!uid_eq(current_fsuid(), i_uid_into_mnt(mnt_userns, inode))) {
+ if (in_group_p(i_gid_into_mnt(mnt_userns, inode)))
allow_utime >>= 3;
if (allow_utime & MAY_WRITE)
return 1;
/* valid file mode bits */
#define FAT_VALID_MODE (S_IFREG | S_IFDIR | S_IRWXUGO)
-int fat_setattr(struct dentry *dentry, struct iattr *attr)
+int fat_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr)
{
struct msdos_sb_info *sbi = MSDOS_SB(dentry->d_sb);
struct inode *inode = d_inode(dentry);
/* Check for setting the inode time. */
ia_valid = attr->ia_valid;
if (ia_valid & TIMES_SET_FLAGS) {
- if (fat_allow_set_time(sbi, inode))
+ if (fat_allow_set_time(mnt_userns, sbi, inode))
attr->ia_valid &= ~TIMES_SET_FLAGS;
}
- error = setattr_prepare(dentry, attr);
+ error = setattr_prepare(mnt_userns, dentry, attr);
attr->ia_valid = ia_valid;
if (error) {
if (sbi->options.quiet)
fat_truncate_time(inode, &attr->ia_mtime, S_MTIME);
attr->ia_valid &= ~(ATTR_ATIME|ATTR_CTIME|ATTR_MTIME);
- setattr_copy(inode, attr);
+ setattr_copy(mnt_userns, inode, attr);
mark_inode_dirty(inode);
out:
return error;
}
/***** Create a file */
-static int msdos_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- bool excl)
+static int msdos_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool excl)
{
struct super_block *sb = dir->i_sb;
struct inode *inode = NULL;
}
/***** Make a directory */
-static int msdos_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int msdos_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
struct super_block *sb = dir->i_sb;
struct fat_slot_info sinfo;
}
/***** Rename, a wrapper for rename_same_dir & rename_diff_dir */
-static int msdos_rename(struct inode *old_dir, struct dentry *old_dentry,
+static int msdos_rename(struct user_namespace *mnt_userns,
+ struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
.name = "msdos",
.mount = msdos_mount,
.kill_sb = kill_block_super,
- .fs_flags = FS_REQUIRES_DEV,
+ .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP,
};
MODULE_ALIAS_FS("msdos");
return ERR_PTR(err);
}
-static int vfat_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- bool excl)
+static int vfat_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool excl)
{
struct super_block *sb = dir->i_sb;
struct inode *inode;
return err;
}
-static int vfat_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int vfat_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
struct super_block *sb = dir->i_sb;
struct inode *inode;
return err;
}
-static int vfat_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry,
- unsigned int flags)
+static int vfat_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
+ struct dentry *old_dentry, struct inode *new_dir,
+ struct dentry *new_dentry, unsigned int flags)
{
struct buffer_head *dotdot_bh;
struct msdos_dir_entry *dotdot_de;
.name = "vfat",
.mount = vfat_mount,
.kill_sb = kill_block_super,
- .fs_flags = FS_REQUIRES_DEV,
+ .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP,
};
MODULE_ALIAS_FS("vfat");
#include <linux/user_namespace.h>
#include <linux/memfd.h>
#include <linux/compat.h>
+#include <linux/mount.h>
#include <linux/poll.h>
#include <asm/siginfo.h>
/* O_NOATIME can only be set by the owner or superuser */
if ((arg & O_NOATIME) && !(filp->f_flags & O_NOATIME))
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(file_mnt_user_ns(filp), inode))
return -EPERM;
/* required for strict SunOS emulation */
return acl;
}
-int fuse_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+int fuse_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
+ struct posix_acl *acl, int type)
{
struct fuse_conn *fc = get_fuse_conn(inode);
const char *name;
return err;
}
-static int fuse_mknod(struct inode *, struct dentry *, umode_t, dev_t);
+static int fuse_mknod(struct user_namespace *, struct inode *, struct dentry *,
+ umode_t, dev_t);
static int fuse_atomic_open(struct inode *dir, struct dentry *entry,
struct file *file, unsigned flags,
umode_t mode)
return err;
mknod:
- err = fuse_mknod(dir, entry, mode, 0);
+ err = fuse_mknod(&init_user_ns, dir, entry, mode, 0);
if (err)
goto out_dput;
no_open:
return err;
}
-static int fuse_mknod(struct inode *dir, struct dentry *entry, umode_t mode,
- dev_t rdev)
+static int fuse_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *entry, umode_t mode, dev_t rdev)
{
struct fuse_mknod_in inarg;
struct fuse_mount *fm = get_fuse_mount(dir);
return create_new_entry(fm, &args, dir, entry, mode);
}
-static int fuse_create(struct inode *dir, struct dentry *entry, umode_t mode,
- bool excl)
+static int fuse_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *entry, umode_t mode, bool excl)
{
- return fuse_mknod(dir, entry, mode, 0);
+ return fuse_mknod(&init_user_ns, dir, entry, mode, 0);
}
-static int fuse_mkdir(struct inode *dir, struct dentry *entry, umode_t mode)
+static int fuse_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *entry, umode_t mode)
{
struct fuse_mkdir_in inarg;
struct fuse_mount *fm = get_fuse_mount(dir);
return create_new_entry(fm, &args, dir, entry, S_IFDIR);
}
-static int fuse_symlink(struct inode *dir, struct dentry *entry,
- const char *link)
+static int fuse_symlink(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *entry, const char *link)
{
struct fuse_mount *fm = get_fuse_mount(dir);
unsigned len = strlen(link) + 1;
return err;
}
-static int fuse_rename2(struct inode *olddir, struct dentry *oldent,
- struct inode *newdir, struct dentry *newent,
- unsigned int flags)
+static int fuse_rename2(struct user_namespace *mnt_userns, struct inode *olddir,
+ struct dentry *oldent, struct inode *newdir,
+ struct dentry *newent, unsigned int flags)
{
struct fuse_conn *fc = get_fuse_conn(olddir);
int err;
forget_all_cached_acls(inode);
err = fuse_do_getattr(inode, stat, file);
} else if (stat) {
- generic_fillattr(inode, stat);
+ generic_fillattr(&init_user_ns, inode, stat);
stat->mode = fi->orig_i_mode;
stat->ino = fi->orig_ino;
}
* access request is sent. Execute permission is still checked
* locally based on file mode.
*/
-static int fuse_permission(struct inode *inode, int mask)
+static int fuse_permission(struct user_namespace *mnt_userns,
+ struct inode *inode, int mask)
{
struct fuse_conn *fc = get_fuse_conn(inode);
bool refreshed = false;
}
if (fc->default_permissions) {
- err = generic_permission(inode, mask);
+ err = generic_permission(&init_user_ns, inode, mask);
/* If permission is denied, try to refresh file
attributes. This is also needed, because the root
if (err == -EACCES && !refreshed) {
err = fuse_perm_getattr(inode, mask);
if (!err)
- err = generic_permission(inode, mask);
+ err = generic_permission(&init_user_ns,
+ inode, mask);
}
/* Note: the opposite of the above test does not
if (!fc->default_permissions)
attr->ia_valid |= ATTR_FORCE;
- err = setattr_prepare(dentry, attr);
+ err = setattr_prepare(&init_user_ns, dentry, attr);
if (err)
return err;
return err;
}
-static int fuse_setattr(struct dentry *entry, struct iattr *attr)
+static int fuse_setattr(struct user_namespace *mnt_userns, struct dentry *entry,
+ struct iattr *attr)
{
struct inode *inode = d_inode(entry);
struct fuse_conn *fc = get_fuse_conn(inode);
return ret;
}
-static int fuse_getattr(const struct path *path, struct kstat *stat,
+static int fuse_getattr(struct user_namespace *mnt_userns,
+ const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int flags)
{
struct inode *inode = d_inode(path->dentry);
struct posix_acl;
struct posix_acl *fuse_get_acl(struct inode *inode, int type);
-int fuse_set_acl(struct inode *inode, struct posix_acl *acl, int type);
-
+int fuse_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
+ struct posix_acl *acl, int type);
/* readdir.c */
int fuse_readdir(struct file *file, struct dir_context *ctx);
}
static int fuse_xattr_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *dentry, struct inode *inode,
const char *name, const void *value, size_t size,
int flags)
}
static int no_xattr_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *dentry, struct inode *nodee,
const char *name, const void *value,
size_t size, int flags)
return error;
}
-int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+int gfs2_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
+ struct posix_acl *acl, int type)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder gh;
mode = inode->i_mode;
if (type == ACL_TYPE_ACCESS && acl) {
- ret = posix_acl_update_mode(inode, &mode, &acl);
+ ret = posix_acl_update_mode(&init_user_ns, inode, &mode, &acl);
if (ret)
goto unlock;
}
extern struct posix_acl *gfs2_get_acl(struct inode *inode, int type);
extern int __gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type);
-extern int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type);
+extern int gfs2_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
+ struct posix_acl *acl, int type);
#endif /* __ACL_DOT_H__ */
goto out;
error = -EACCES;
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(&init_user_ns, inode))
goto out;
error = 0;
!capable(CAP_LINUX_IMMUTABLE))
goto out;
if (!IS_IMMUTABLE(inode)) {
- error = gfs2_permission(inode, MAY_WRITE);
+ error = gfs2_permission(&init_user_ns, inode, MAY_WRITE);
if (error)
goto out;
}
}
if (!is_root) {
- error = gfs2_permission(dir, MAY_EXEC);
+ error = gfs2_permission(&init_user_ns, dir, MAY_EXEC);
if (error)
goto out;
}
{
int error;
- error = gfs2_permission(&dip->i_inode, MAY_WRITE | MAY_EXEC);
+ error = gfs2_permission(&init_user_ns, &dip->i_inode,
+ MAY_WRITE | MAY_EXEC);
if (error)
return error;
* Returns: errno
*/
-static int gfs2_create(struct inode *dir, struct dentry *dentry,
- umode_t mode, bool excl)
+static int gfs2_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool excl)
{
return gfs2_create_inode(dir, dentry, NULL, S_IFREG | mode, 0, NULL, 0, excl);
}
if (inode->i_nlink == 0)
goto out_gunlock;
- error = gfs2_permission(dir, MAY_WRITE | MAY_EXEC);
+ error = gfs2_permission(&init_user_ns, dir, MAY_WRITE | MAY_EXEC);
if (error)
goto out_gunlock;
if (IS_APPEND(&dip->i_inode))
return -EPERM;
- error = gfs2_permission(&dip->i_inode, MAY_WRITE | MAY_EXEC);
+ error = gfs2_permission(&init_user_ns, &dip->i_inode,
+ MAY_WRITE | MAY_EXEC);
if (error)
return error;
* Returns: errno
*/
-static int gfs2_symlink(struct inode *dir, struct dentry *dentry,
- const char *symname)
+static int gfs2_symlink(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, const char *symname)
{
unsigned int size;
* Returns: errno
*/
-static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int gfs2_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
unsigned dsize = gfs2_max_stuffed_size(GFS2_I(dir));
return gfs2_create_inode(dir, dentry, NULL, S_IFDIR | mode, 0, NULL, dsize, 0);
*
*/
-static int gfs2_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
- dev_t dev)
+static int gfs2_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, dev_t dev)
{
return gfs2_create_inode(dir, dentry, NULL, mode, dev, NULL, 0, 0);
}
}
}
} else {
- error = gfs2_permission(ndir, MAY_WRITE | MAY_EXEC);
+ error = gfs2_permission(&init_user_ns, ndir,
+ MAY_WRITE | MAY_EXEC);
if (error)
goto out_gunlock;
/* Check out the dir to be renamed */
if (dir_rename) {
- error = gfs2_permission(d_inode(odentry), MAY_WRITE);
+ error = gfs2_permission(&init_user_ns, d_inode(odentry),
+ MAY_WRITE);
if (error)
goto out_gunlock;
}
goto out_gunlock;
if (S_ISDIR(old_mode)) {
- error = gfs2_permission(odentry->d_inode, MAY_WRITE);
+ error = gfs2_permission(&init_user_ns, odentry->d_inode,
+ MAY_WRITE);
if (error)
goto out_gunlock;
}
if (S_ISDIR(new_mode)) {
- error = gfs2_permission(ndentry->d_inode, MAY_WRITE);
+ error = gfs2_permission(&init_user_ns, ndentry->d_inode,
+ MAY_WRITE);
if (error)
goto out_gunlock;
}
return error;
}
-static int gfs2_rename2(struct inode *odir, struct dentry *odentry,
- struct inode *ndir, struct dentry *ndentry,
- unsigned int flags)
+static int gfs2_rename2(struct user_namespace *mnt_userns, struct inode *odir,
+ struct dentry *odentry, struct inode *ndir,
+ struct dentry *ndentry, unsigned int flags)
{
flags &= ~RENAME_NOREPLACE;
* Returns: errno
*/
-int gfs2_permission(struct inode *inode, int mask)
+int gfs2_permission(struct user_namespace *mnt_userns, struct inode *inode,
+ int mask)
{
struct gfs2_inode *ip;
struct gfs2_holder i_gh;
if ((mask & MAY_WRITE) && IS_IMMUTABLE(inode))
error = -EPERM;
else
- error = generic_permission(inode, mask);
+ error = generic_permission(&init_user_ns, inode, mask);
if (gfs2_holder_initialized(&i_gh))
gfs2_glock_dq_uninit(&i_gh);
static int __gfs2_setattr_simple(struct inode *inode, struct iattr *attr)
{
- setattr_copy(inode, attr);
+ setattr_copy(&init_user_ns, inode, attr);
mark_inode_dirty(inode);
return 0;
}
* Returns: errno
*/
-static int gfs2_setattr(struct dentry *dentry, struct iattr *attr)
+static int gfs2_setattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
struct gfs2_inode *ip = GFS2_I(inode);
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
goto error;
- error = setattr_prepare(dentry, attr);
+ error = setattr_prepare(&init_user_ns, dentry, attr);
if (error)
goto error;
else {
error = gfs2_setattr_simple(inode, attr);
if (!error && attr->ia_valid & ATTR_MODE)
- error = posix_acl_chmod(inode, inode->i_mode);
+ error = posix_acl_chmod(&init_user_ns, inode,
+ inode->i_mode);
}
error:
/**
* gfs2_getattr - Read out an inode's attributes
+ * @mnt_userns: user namespace of the mount the inode was found from
* @path: Object to query
* @stat: The inode's stats
* @request_mask: Mask of STATX_xxx flags indicating the caller's interests
* Returns: errno
*/
-static int gfs2_getattr(const struct path *path, struct kstat *stat,
+static int gfs2_getattr(struct user_namespace *mnt_userns,
+ const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int flags)
{
struct inode *inode = d_inode(path->dentry);
STATX_ATTR_IMMUTABLE |
STATX_ATTR_NODUMP);
- generic_fillattr(inode, stat);
+ generic_fillattr(&init_user_ns, inode, stat);
if (gfs2_holder_initialized(&gh))
gfs2_glock_dq_uninit(&gh);
extern struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name,
int is_root);
-extern int gfs2_permission(struct inode *inode, int mask);
+extern int gfs2_permission(struct user_namespace *mnt_userns,
+ struct inode *inode, int mask);
extern int gfs2_setattr_simple(struct inode *inode, struct iattr *attr);
extern struct inode *gfs2_lookup_simple(struct inode *dip, const char *name);
extern void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf);
}
static int gfs2_xattr_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
}
static int hfs_xattr_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *name, const void *value, size_t size,
int flags)
* a directory and return a corresponding inode, given the inode for
* the directory and the name (and its length) of the new file.
*/
-static int hfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- bool excl)
+static int hfs_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool excl)
{
struct inode *inode;
int res;
* in a directory, given the inode for the parent directory and the
* name (and its length) of the new directory.
*/
-static int hfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int hfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
struct inode *inode;
int res;
* new file/directory.
* XXX: how do you handle must_be dir?
*/
-static int hfs_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry,
- unsigned int flags)
+static int hfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
+ struct dentry *old_dentry, struct inode *new_dir,
+ struct dentry *new_dentry, unsigned int flags)
{
int res;
extern struct inode *hfs_new_inode(struct inode *, const struct qstr *, umode_t);
extern void hfs_inode_write_fork(struct inode *, struct hfs_extent *, __be32 *, __be32 *);
extern int hfs_write_inode(struct inode *, struct writeback_control *);
-extern int hfs_inode_setattr(struct dentry *, struct iattr *);
+extern int hfs_inode_setattr(struct user_namespace *, struct dentry *,
+ struct iattr *);
extern void hfs_inode_read_fork(struct inode *inode, struct hfs_extent *ext,
__be32 log_size, __be32 phys_size, u32 clump_size);
extern struct inode *hfs_iget(struct super_block *, struct hfs_cat_key *, hfs_cat_rec *);
* correspond to the same HFS file.
*/
-int hfs_inode_setattr(struct dentry *dentry, struct iattr * attr)
+int hfs_inode_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
struct hfs_sb_info *hsb = HFS_SB(inode->i_sb);
int error;
- error = setattr_prepare(dentry, attr); /* basic permission checks */
+ error = setattr_prepare(&init_user_ns, dentry,
+ attr); /* basic permission checks */
if (error)
return error;
current_time(inode);
}
- setattr_copy(inode, attr);
+ setattr_copy(&init_user_ns, inode, attr);
mark_inode_dirty(inode);
return 0;
}
return res;
}
-static int hfsplus_symlink(struct inode *dir, struct dentry *dentry,
- const char *symname)
+static int hfsplus_symlink(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, const char *symname)
{
struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb);
struct inode *inode;
return res;
}
-static int hfsplus_mknod(struct inode *dir, struct dentry *dentry,
- umode_t mode, dev_t rdev)
+static int hfsplus_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, dev_t rdev)
{
struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb);
struct inode *inode;
return res;
}
-static int hfsplus_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- bool excl)
+static int hfsplus_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool excl)
{
- return hfsplus_mknod(dir, dentry, mode, 0);
+ return hfsplus_mknod(&init_user_ns, dir, dentry, mode, 0);
}
-static int hfsplus_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int hfsplus_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
- return hfsplus_mknod(dir, dentry, mode | S_IFDIR, 0);
+ return hfsplus_mknod(&init_user_ns, dir, dentry, mode | S_IFDIR, 0);
}
-static int hfsplus_rename(struct inode *old_dir, struct dentry *old_dentry,
+static int hfsplus_rename(struct user_namespace *mnt_userns,
+ struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
struct hfsplus_fork_raw *fork);
int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd);
int hfsplus_cat_write_inode(struct inode *inode);
-int hfsplus_getattr(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int query_flags);
+int hfsplus_getattr(struct user_namespace *mnt_userns, const struct path *path,
+ struct kstat *stat, u32 request_mask,
+ unsigned int query_flags);
int hfsplus_file_fsync(struct file *file, loff_t start, loff_t end,
int datasync);
return 0;
}
-static int hfsplus_setattr(struct dentry *dentry, struct iattr *attr)
+static int hfsplus_setattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
int error;
- error = setattr_prepare(dentry, attr);
+ error = setattr_prepare(&init_user_ns, dentry, attr);
if (error)
return error;
inode->i_mtime = inode->i_ctime = current_time(inode);
}
- setattr_copy(inode, attr);
+ setattr_copy(&init_user_ns, inode, attr);
mark_inode_dirty(inode);
return 0;
}
-int hfsplus_getattr(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int query_flags)
+int hfsplus_getattr(struct user_namespace *mnt_userns, const struct path *path,
+ struct kstat *stat, u32 request_mask,
+ unsigned int query_flags)
{
struct inode *inode = d_inode(path->dentry);
struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
stat->attributes_mask |= STATX_ATTR_APPEND | STATX_ATTR_IMMUTABLE |
STATX_ATTR_NODUMP;
- generic_fillattr(inode, stat);
+ generic_fillattr(&init_user_ns, inode, stat);
return 0;
}
return NULL;
inode->i_ino = sbi->next_cnid++;
- inode_init_owner(inode, dir, mode);
+ inode_init_owner(&init_user_ns, inode, dir, mode);
set_nlink(inode, 1);
inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
if (err)
goto out;
- if (!inode_owner_or_capable(inode)) {
+ if (!inode_owner_or_capable(&init_user_ns, inode)) {
err = -EACCES;
goto out_drop_write;
}
}
static int hfsplus_osx_setxattr(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *name, const void *buffer,
size_t size, int flags)
}
static int hfsplus_security_setxattr(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *name, const void *buffer,
size_t size, int flags)
}
static int hfsplus_trusted_setxattr(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *name, const void *buffer,
size_t size, int flags)
}
static int hfsplus_user_setxattr(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *name, const void *buffer,
size_t size, int flags)
return 0;
}
-static int hostfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- bool excl)
+static int hostfs_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool excl)
{
struct inode *inode;
char *name;
return err;
}
-static int hostfs_symlink(struct inode *ino, struct dentry *dentry,
- const char *to)
+static int hostfs_symlink(struct user_namespace *mnt_userns, struct inode *ino,
+ struct dentry *dentry, const char *to)
{
char *file;
int err;
return err;
}
-static int hostfs_mkdir(struct inode *ino, struct dentry *dentry, umode_t mode)
+static int hostfs_mkdir(struct user_namespace *mnt_userns, struct inode *ino,
+ struct dentry *dentry, umode_t mode)
{
char *file;
int err;
return err;
}
-static int hostfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev)
+static int hostfs_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, dev_t dev)
{
struct inode *inode;
char *name;
return err;
}
-static int hostfs_rename2(struct inode *old_dir, struct dentry *old_dentry,
+static int hostfs_rename2(struct user_namespace *mnt_userns,
+ struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
return err;
}
-static int hostfs_permission(struct inode *ino, int desired)
+static int hostfs_permission(struct user_namespace *mnt_userns,
+ struct inode *ino, int desired)
{
char *name;
int r = 0, w = 0, x = 0, err;
err = access_file(name, r, w, x);
__putname(name);
if (!err)
- err = generic_permission(ino, desired);
+ err = generic_permission(&init_user_ns, ino, desired);
return err;
}
-static int hostfs_setattr(struct dentry *dentry, struct iattr *attr)
+static int hostfs_setattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
struct hostfs_iattr attrs;
int fd = HOSTFS_I(inode)->fd;
- err = setattr_prepare(dentry, attr);
+ err = setattr_prepare(&init_user_ns, dentry, attr);
if (err)
return err;
attr->ia_size != i_size_read(inode))
truncate_setsize(inode, attr->ia_size);
- setattr_copy(inode, attr);
+ setattr_copy(&init_user_ns, inode, attr);
mark_inode_dirty(inode);
return 0;
}
void hpfs_read_inode(struct inode *);
void hpfs_write_inode(struct inode *);
void hpfs_write_inode_nolock(struct inode *);
-int hpfs_setattr(struct dentry *, struct iattr *);
+int hpfs_setattr(struct user_namespace *, struct dentry *, struct iattr *);
void hpfs_write_if_changed(struct inode *);
void hpfs_evict_inode(struct inode *);
brelse(bh);
}
-int hpfs_setattr(struct dentry *dentry, struct iattr *attr)
+int hpfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
int error = -EINVAL;
if ((attr->ia_valid & ATTR_SIZE) && attr->ia_size > inode->i_size)
goto out_unlock;
- error = setattr_prepare(dentry, attr);
+ error = setattr_prepare(&init_user_ns, dentry, attr);
if (error)
goto out_unlock;
hpfs_truncate(inode);
}
- setattr_copy(inode, attr);
+ setattr_copy(&init_user_ns, inode, attr);
hpfs_write_inode(inode);
hpfs_write_inode_nolock(dir);
}
-static int hpfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int hpfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
const unsigned char *name = dentry->d_name.name;
unsigned len = dentry->d_name.len;
return err;
}
-static int hpfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl)
+static int hpfs_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool excl)
{
const unsigned char *name = dentry->d_name.name;
unsigned len = dentry->d_name.len;
return err;
}
-static int hpfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev)
+static int hpfs_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, dev_t rdev)
{
const unsigned char *name = dentry->d_name.name;
unsigned len = dentry->d_name.len;
return err;
}
-static int hpfs_symlink(struct inode *dir, struct dentry *dentry, const char *symlink)
+static int hpfs_symlink(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, const char *symlink)
{
const unsigned char *name = dentry->d_name.name;
unsigned len = dentry->d_name.len;
const struct address_space_operations hpfs_symlink_aops = {
.readpage = hpfs_symlink_readpage
};
-
-static int hpfs_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry,
- unsigned int flags)
+
+static int hpfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
+ struct dentry *old_dentry, struct inode *new_dir,
+ struct dentry *new_dentry, unsigned int flags)
{
const unsigned char *old_name = old_dentry->d_name.name;
unsigned old_len = old_dentry->d_name.len;
return error;
}
-static int hugetlbfs_setattr(struct dentry *dentry, struct iattr *attr)
+static int hugetlbfs_setattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
struct hstate *h = hstate_inode(inode);
BUG_ON(!inode);
- error = setattr_prepare(dentry, attr);
+ error = setattr_prepare(&init_user_ns, dentry, attr);
if (error)
return error;
return error;
}
- setattr_copy(inode, attr);
+ setattr_copy(&init_user_ns, inode, attr);
mark_inode_dirty(inode);
return 0;
}
struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode);
inode->i_ino = get_next_ino();
- inode_init_owner(inode, dir, mode);
+ inode_init_owner(&init_user_ns, inode, dir, mode);
lockdep_set_class(&inode->i_mapping->i_mmap_rwsem,
&hugetlbfs_i_mmap_rwsem_key);
inode->i_mapping->a_ops = &hugetlbfs_aops;
return error;
}
-static int hugetlbfs_mknod(struct inode *dir,
- struct dentry *dentry, umode_t mode, dev_t dev)
+static int hugetlbfs_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, dev_t dev)
{
return do_hugetlbfs_mknod(dir, dentry, mode, dev, false);
}
-static int hugetlbfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int hugetlbfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
- int retval = hugetlbfs_mknod(dir, dentry, mode | S_IFDIR, 0);
+ int retval = hugetlbfs_mknod(&init_user_ns, dir, dentry,
+ mode | S_IFDIR, 0);
if (!retval)
inc_nlink(dir);
return retval;
}
-static int hugetlbfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl)
+static int hugetlbfs_create(struct user_namespace *mnt_userns,
+ struct inode *dir, struct dentry *dentry,
+ umode_t mode, bool excl)
{
- return hugetlbfs_mknod(dir, dentry, mode | S_IFREG, 0);
+ return hugetlbfs_mknod(&init_user_ns, dir, dentry, mode | S_IFREG, 0);
}
-static int hugetlbfs_tmpfile(struct inode *dir,
- struct dentry *dentry, umode_t mode)
+static int hugetlbfs_tmpfile(struct user_namespace *mnt_userns,
+ struct inode *dir, struct dentry *dentry,
+ umode_t mode)
{
return do_hugetlbfs_mknod(dir, dentry, mode | S_IFREG, 0, true);
}
-static int hugetlbfs_symlink(struct inode *dir,
- struct dentry *dentry, const char *symname)
+static int hugetlbfs_symlink(struct user_namespace *mnt_userns,
+ struct inode *dir, struct dentry *dentry,
+ const char *symname)
{
struct inode *inode;
int error = -ENOSPC;
error = kern_path(filename, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &path);
if (error)
return error;
- error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_CHDIR);
+ error = path_permission(&path, MAY_EXEC | MAY_CHDIR);
if (!error)
set_fs_pwd(current->fs, &path);
path_put(&path);
error = kern_path(filename, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &path);
if (error)
return error;
- error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_CHDIR);
+ error = path_permission(&path, MAY_EXEC | MAY_CHDIR);
if (error)
goto dput_and_out;
error = -EPERM;
error = kern_path(filename, LOOKUP_FOLLOW, &path);
if (error)
return error;
- error = inode_permission(d_inode(path.dentry), MAY_ACCESS);
+ error = path_permission(&path, MAY_ACCESS);
path_put(&path);
return error;
}
mode &= ~current_umask();
error = security_path_mknod(&path, dentry, mode, dev);
if (!error)
- error = vfs_mknod(path.dentry->d_inode, dentry, mode,
- new_decode_dev(dev));
+ error = vfs_mknod(mnt_user_ns(path.mnt), path.dentry->d_inode,
+ dentry, mode, new_decode_dev(dev));
done_path_create(&path, dentry);
return error;
}
{
struct dentry *new_dentry;
struct path old_path, new_path;
+ struct user_namespace *mnt_userns;
int error;
error = kern_path(oldname, 0, &old_path);
error = -EXDEV;
if (old_path.mnt != new_path.mnt)
goto out_dput;
- error = may_linkat(&old_path);
+ mnt_userns = mnt_user_ns(new_path.mnt);
+ error = may_linkat(mnt_userns, &old_path);
if (unlikely(error))
goto out_dput;
error = security_path_link(old_path.dentry, &new_path, new_dentry);
if (error)
goto out_dput;
- error = vfs_link(old_path.dentry, new_path.dentry->d_inode, new_dentry,
- NULL);
+ error = vfs_link(old_path.dentry, mnt_userns, new_path.dentry->d_inode,
+ new_dentry, NULL);
out_dput:
done_path_create(&new_path, new_dentry);
out:
return PTR_ERR(dentry);
error = security_path_symlink(&path, dentry, oldname);
if (!error)
- error = vfs_symlink(path.dentry->d_inode, dentry, oldname);
+ error = vfs_symlink(mnt_user_ns(path.mnt), path.dentry->d_inode,
+ dentry, oldname);
done_path_create(&path, dentry);
return error;
}
mode &= ~current_umask();
error = security_path_mkdir(&path, dentry, mode);
if (!error)
- error = vfs_mkdir(path.dentry->d_inode, dentry, mode);
+ error = vfs_mkdir(mnt_user_ns(path.mnt), path.dentry->d_inode,
+ dentry, mode);
done_path_create(&path, dentry);
return error;
}
/* Atime updates will likely cause i_uid and i_gid to be written
* back improprely if their true value is unknown to the vfs.
*/
- if (HAS_UNMAPPED_ID(inode))
+ if (HAS_UNMAPPED_ID(mnt_user_ns(mnt), inode))
return false;
if (IS_NOATIME(inode))
return mask;
}
-static int __remove_privs(struct dentry *dentry, int kill)
+static int __remove_privs(struct user_namespace *mnt_userns,
+ struct dentry *dentry, int kill)
{
struct iattr newattrs;
* Note we call this on write, so notify_change will not
* encounter any conflicting delegations:
*/
- return notify_change(dentry, &newattrs, NULL);
+ return notify_change(mnt_userns, dentry, &newattrs, NULL);
}
/*
if (kill < 0)
return kill;
if (kill)
- error = __remove_privs(dentry, kill);
+ error = __remove_privs(file_mnt_user_ns(file), dentry, kill);
if (!error)
inode_has_no_xattr(inode);
/**
* inode_init_owner - Init uid,gid,mode for new inode according to posix standards
+ * @mnt_userns: User namespace of the mount the inode was created from
* @inode: New inode
* @dir: Directory inode
* @mode: mode of the new inode
+ *
+ * If the inode has been created through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then take
+ * care to map the inode according to @mnt_userns before checking permissions
+ * and initializing i_uid and i_gid. On non-idmapped mounts or if permission
+ * checking is to be performed on the raw inode simply passs init_user_ns.
*/
-void inode_init_owner(struct inode *inode, const struct inode *dir,
- umode_t mode)
+void inode_init_owner(struct user_namespace *mnt_userns, struct inode *inode,
+ const struct inode *dir, umode_t mode)
{
- inode->i_uid = current_fsuid();
+ inode->i_uid = fsuid_into_mnt(mnt_userns);
if (dir && dir->i_mode & S_ISGID) {
inode->i_gid = dir->i_gid;
if (S_ISDIR(mode))
mode |= S_ISGID;
else if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP) &&
- !in_group_p(inode->i_gid) &&
- !capable_wrt_inode_uidgid(dir, CAP_FSETID))
+ !in_group_p(i_gid_into_mnt(mnt_userns, dir)) &&
+ !capable_wrt_inode_uidgid(mnt_userns, dir, CAP_FSETID))
mode &= ~S_ISGID;
} else
- inode->i_gid = current_fsgid();
+ inode->i_gid = fsgid_into_mnt(mnt_userns);
inode->i_mode = mode;
}
EXPORT_SYMBOL(inode_init_owner);
/**
* inode_owner_or_capable - check current task permissions to inode
+ * @mnt_userns: user namespace of the mount the inode was found from
* @inode: inode being checked
*
* Return true if current either has CAP_FOWNER in a namespace with the
* inode owner uid mapped, or owns the file.
+ *
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then take
+ * care to map the inode according to @mnt_userns before checking permissions.
+ * On non-idmapped mounts or if permission checking is to be performed on the
+ * raw inode simply passs init_user_ns.
*/
-bool inode_owner_or_capable(const struct inode *inode)
+bool inode_owner_or_capable(struct user_namespace *mnt_userns,
+ const struct inode *inode)
{
+ kuid_t i_uid;
struct user_namespace *ns;
- if (uid_eq(current_fsuid(), inode->i_uid))
+ i_uid = i_uid_into_mnt(mnt_userns, inode);
+ if (uid_eq(current_fsuid(), i_uid))
return true;
ns = current_user_ns();
- if (kuid_has_mapping(ns, inode->i_uid) && ns_capable(ns, CAP_FOWNER))
+ if (kuid_has_mapping(ns, i_uid) && ns_capable(ns, CAP_FOWNER))
return true;
return false;
}
const char *, unsigned int, struct path *);
long do_rmdir(int dfd, struct filename *name);
long do_unlinkat(int dfd, struct filename *name);
-int may_linkat(struct path *link);
+int may_linkat(struct user_namespace *mnt_userns, struct path *link);
int do_renameat2(int olddfd, struct filename *oldname, int newdfd,
struct filename *newname, unsigned int flags);
return rc;
}
-int jffs2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+int jffs2_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
+ struct posix_acl *acl, int type)
{
int rc, xprefix;
if (acl) {
umode_t mode;
- rc = posix_acl_update_mode(inode, &mode, &acl);
+ rc = posix_acl_update_mode(&init_user_ns, inode, &mode,
+ &acl);
if (rc)
return rc;
if (inode->i_mode != mode) {
#ifdef CONFIG_JFFS2_FS_POSIX_ACL
struct posix_acl *jffs2_get_acl(struct inode *inode, int type);
-int jffs2_set_acl(struct inode *inode, struct posix_acl *acl, int type);
+int jffs2_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
+ struct posix_acl *acl, int type);
extern int jffs2_init_acl_pre(struct inode *, struct inode *, umode_t *);
extern int jffs2_init_acl_post(struct inode *);
static int jffs2_readdir (struct file *, struct dir_context *);
-static int jffs2_create (struct inode *,struct dentry *,umode_t,
- bool);
+static int jffs2_create (struct user_namespace *, struct inode *,
+ struct dentry *, umode_t, bool);
static struct dentry *jffs2_lookup (struct inode *,struct dentry *,
unsigned int);
static int jffs2_link (struct dentry *,struct inode *,struct dentry *);
static int jffs2_unlink (struct inode *,struct dentry *);
-static int jffs2_symlink (struct inode *,struct dentry *,const char *);
-static int jffs2_mkdir (struct inode *,struct dentry *,umode_t);
+static int jffs2_symlink (struct user_namespace *, struct inode *,
+ struct dentry *, const char *);
+static int jffs2_mkdir (struct user_namespace *, struct inode *,struct dentry *,
+ umode_t);
static int jffs2_rmdir (struct inode *,struct dentry *);
-static int jffs2_mknod (struct inode *,struct dentry *,umode_t,dev_t);
-static int jffs2_rename (struct inode *, struct dentry *,
- struct inode *, struct dentry *,
+static int jffs2_mknod (struct user_namespace *, struct inode *,struct dentry *,
+ umode_t,dev_t);
+static int jffs2_rename (struct user_namespace *, struct inode *,
+ struct dentry *, struct inode *, struct dentry *,
unsigned int);
const struct file_operations jffs2_dir_operations =
/***********************************************************************/
-static int jffs2_create(struct inode *dir_i, struct dentry *dentry,
- umode_t mode, bool excl)
+static int jffs2_create(struct user_namespace *mnt_userns, struct inode *dir_i,
+ struct dentry *dentry, umode_t mode, bool excl)
{
struct jffs2_raw_inode *ri;
struct jffs2_inode_info *f, *dir_f;
/***********************************************************************/
-static int jffs2_symlink (struct inode *dir_i, struct dentry *dentry, const char *target)
+static int jffs2_symlink (struct user_namespace *mnt_userns, struct inode *dir_i,
+ struct dentry *dentry, const char *target)
{
struct jffs2_inode_info *f, *dir_f;
struct jffs2_sb_info *c;
}
-static int jffs2_mkdir (struct inode *dir_i, struct dentry *dentry, umode_t mode)
+static int jffs2_mkdir (struct user_namespace *mnt_userns, struct inode *dir_i,
+ struct dentry *dentry, umode_t mode)
{
struct jffs2_inode_info *f, *dir_f;
struct jffs2_sb_info *c;
return ret;
}
-static int jffs2_mknod (struct inode *dir_i, struct dentry *dentry, umode_t mode, dev_t rdev)
+static int jffs2_mknod (struct user_namespace *mnt_userns, struct inode *dir_i,
+ struct dentry *dentry, umode_t mode, dev_t rdev)
{
struct jffs2_inode_info *f, *dir_f;
struct jffs2_sb_info *c;
return ret;
}
-static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry,
+static int jffs2_rename (struct user_namespace *mnt_userns,
+ struct inode *old_dir_i, struct dentry *old_dentry,
struct inode *new_dir_i, struct dentry *new_dentry,
unsigned int flags)
{
return 0;
}
-int jffs2_setattr(struct dentry *dentry, struct iattr *iattr)
+int jffs2_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *iattr)
{
struct inode *inode = d_inode(dentry);
int rc;
- rc = setattr_prepare(dentry, iattr);
+ rc = setattr_prepare(&init_user_ns, dentry, iattr);
if (rc)
return rc;
rc = jffs2_do_setattr(inode, iattr);
if (!rc && (iattr->ia_valid & ATTR_MODE))
- rc = posix_acl_chmod(inode, inode->i_mode);
+ rc = posix_acl_chmod(&init_user_ns, inode, inode->i_mode);
return rc;
}
extern const struct inode_operations jffs2_symlink_inode_operations;
/* fs.c */
-int jffs2_setattr (struct dentry *, struct iattr *);
+int jffs2_setattr (struct user_namespace *, struct dentry *, struct iattr *);
int jffs2_do_setattr (struct inode *, struct iattr *);
struct inode *jffs2_iget(struct super_block *, unsigned long);
void jffs2_evict_inode (struct inode *);
}
static int jffs2_security_setxattr(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *name, const void *buffer,
size_t size, int flags)
}
static int jffs2_trusted_setxattr(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *name, const void *buffer,
size_t size, int flags)
}
static int jffs2_user_setxattr(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *name, const void *buffer,
size_t size, int flags)
return rc;
}
-int jfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+int jfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
+ struct posix_acl *acl, int type)
{
int rc;
tid_t tid;
tid = txBegin(inode->i_sb, 0);
mutex_lock(&JFS_IP(inode)->commit_mutex);
if (type == ACL_TYPE_ACCESS && acl) {
- rc = posix_acl_update_mode(inode, &mode, &acl);
+ rc = posix_acl_update_mode(&init_user_ns, inode, &mode, &acl);
if (rc)
goto end_tx;
if (mode != inode->i_mode)
return 0;
}
-int jfs_setattr(struct dentry *dentry, struct iattr *iattr)
+int jfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *iattr)
{
struct inode *inode = d_inode(dentry);
int rc;
- rc = setattr_prepare(dentry, iattr);
+ rc = setattr_prepare(&init_user_ns, dentry, iattr);
if (rc)
return rc;
jfs_truncate(inode);
}
- setattr_copy(inode, iattr);
+ setattr_copy(&init_user_ns, inode, iattr);
mark_inode_dirty(inode);
if (iattr->ia_valid & ATTR_MODE)
- rc = posix_acl_chmod(inode, inode->i_mode);
+ rc = posix_acl_chmod(&init_user_ns, inode, inode->i_mode);
return rc;
}
if (err)
return err;
- if (!inode_owner_or_capable(inode)) {
+ if (!inode_owner_or_capable(&init_user_ns, inode)) {
err = -EACCES;
goto setflags_out;
}
#ifdef CONFIG_JFS_POSIX_ACL
struct posix_acl *jfs_get_acl(struct inode *inode, int type);
-int jfs_set_acl(struct inode *inode, struct posix_acl *acl, int type);
+int jfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
+ struct posix_acl *acl, int type);
int jfs_init_acl(tid_t, struct inode *, struct inode *);
#else
goto fail_put;
}
- inode_init_owner(inode, parent, mode);
+ inode_init_owner(&init_user_ns, inode, parent, mode);
/*
* New inodes need to save sane values on disk when
* uid & gid mount options are used
int fh_len, int fh_type);
extern void jfs_set_inode_flags(struct inode *);
extern int jfs_get_block(struct inode *, sector_t, struct buffer_head *, int);
-extern int jfs_setattr(struct dentry *, struct iattr *);
+extern int jfs_setattr(struct user_namespace *, struct dentry *, struct iattr *);
extern const struct address_space_operations jfs_aops;
extern const struct inode_operations jfs_dir_inode_operations;
* RETURN: Errors from subroutines
*
*/
-static int jfs_create(struct inode *dip, struct dentry *dentry, umode_t mode,
- bool excl)
+static int jfs_create(struct user_namespace *mnt_userns, struct inode *dip,
+ struct dentry *dentry, umode_t mode, bool excl)
{
int rc = 0;
tid_t tid; /* transaction id */
* note:
* EACCES: user needs search+write permission on the parent directory
*/
-static int jfs_mkdir(struct inode *dip, struct dentry *dentry, umode_t mode)
+static int jfs_mkdir(struct user_namespace *mnt_userns, struct inode *dip,
+ struct dentry *dentry, umode_t mode)
{
int rc = 0;
tid_t tid; /* transaction id */
* an intermediate result whose length exceeds PATH_MAX [XPG4.2]
*/
-static int jfs_symlink(struct inode *dip, struct dentry *dentry,
- const char *name)
+static int jfs_symlink(struct user_namespace *mnt_userns, struct inode *dip,
+ struct dentry *dentry, const char *name)
{
int rc;
tid_t tid;
*
* FUNCTION: rename a file or directory
*/
-static int jfs_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry,
- unsigned int flags)
+static int jfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
+ struct dentry *old_dentry, struct inode *new_dir,
+ struct dentry *new_dentry, unsigned int flags)
{
struct btstack btstack;
ino_t ino;
*
* FUNCTION: Create a special file (device)
*/
-static int jfs_mknod(struct inode *dir, struct dentry *dentry,
- umode_t mode, dev_t rdev)
+static int jfs_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, dev_t rdev)
{
struct jfs_inode_info *jfs_ip;
struct btstack btstack;
}
static int jfs_xattr_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
}
static int jfs_xattr_set_os2(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
return ret;
}
-static int kernfs_iop_mkdir(struct inode *dir, struct dentry *dentry,
+static int kernfs_iop_mkdir(struct user_namespace *mnt_userns,
+ struct inode *dir, struct dentry *dentry,
umode_t mode)
{
struct kernfs_node *parent = dir->i_private;
return ret;
}
-static int kernfs_iop_rename(struct inode *old_dir, struct dentry *old_dentry,
+static int kernfs_iop_rename(struct user_namespace *mnt_userns,
+ struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
return ret;
}
-int kernfs_iop_setattr(struct dentry *dentry, struct iattr *iattr)
+int kernfs_iop_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *iattr)
{
struct inode *inode = d_inode(dentry);
struct kernfs_node *kn = inode->i_private;
return -EINVAL;
mutex_lock(&kernfs_mutex);
- error = setattr_prepare(dentry, iattr);
+ error = setattr_prepare(&init_user_ns, dentry, iattr);
if (error)
goto out;
goto out;
/* this ignores size changes */
- setattr_copy(inode, iattr);
+ setattr_copy(&init_user_ns, inode, iattr);
out:
mutex_unlock(&kernfs_mutex);
set_nlink(inode, kn->dir.subdirs + 2);
}
-int kernfs_iop_getattr(const struct path *path, struct kstat *stat,
+int kernfs_iop_getattr(struct user_namespace *mnt_userns,
+ const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int query_flags)
{
struct inode *inode = d_inode(path->dentry);
kernfs_refresh_inode(kn, inode);
mutex_unlock(&kernfs_mutex);
- generic_fillattr(inode, stat);
+ generic_fillattr(&init_user_ns, inode, stat);
return 0;
}
kernfs_put(kn);
}
-int kernfs_iop_permission(struct inode *inode, int mask)
+int kernfs_iop_permission(struct user_namespace *mnt_userns,
+ struct inode *inode, int mask)
{
struct kernfs_node *kn;
kernfs_refresh_inode(kn, inode);
mutex_unlock(&kernfs_mutex);
- return generic_permission(inode, mask);
+ return generic_permission(&init_user_ns, inode, mask);
}
int kernfs_xattr_get(struct kernfs_node *kn, const char *name,
}
static int kernfs_vfs_xattr_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *suffix, const void *value,
size_t size, int flags)
}
static int kernfs_vfs_user_xattr_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *suffix, const void *value,
size_t size, int flags)
*/
extern const struct xattr_handler *kernfs_xattr_handlers[];
void kernfs_evict_inode(struct inode *inode);
-int kernfs_iop_permission(struct inode *inode, int mask);
-int kernfs_iop_setattr(struct dentry *dentry, struct iattr *iattr);
-int kernfs_iop_getattr(const struct path *path, struct kstat *stat,
+int kernfs_iop_permission(struct user_namespace *mnt_userns,
+ struct inode *inode, int mask);
+int kernfs_iop_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *iattr);
+int kernfs_iop_getattr(struct user_namespace *mnt_userns,
+ const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int query_flags);
ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size);
int __kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr);
#include "internal.h"
-int simple_getattr(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int query_flags)
+int simple_getattr(struct user_namespace *mnt_userns, const struct path *path,
+ struct kstat *stat, u32 request_mask,
+ unsigned int query_flags)
{
struct inode *inode = d_inode(path->dentry);
- generic_fillattr(inode, stat);
+ generic_fillattr(&init_user_ns, inode, stat);
stat->blocks = inode->i_mapping->nrpages << (PAGE_SHIFT - 9);
return 0;
}
}
EXPORT_SYMBOL(simple_rmdir);
-int simple_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry,
- unsigned int flags)
+int simple_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
+ struct dentry *old_dentry, struct inode *new_dir,
+ struct dentry *new_dentry, unsigned int flags)
{
struct inode *inode = d_inode(old_dentry);
int they_are_dirs = d_is_dir(old_dentry);
* on simple regular filesystems. Anything that needs to change on-disk
* or wire state on size changes needs its own setattr method.
*/
-int simple_setattr(struct dentry *dentry, struct iattr *iattr)
+int simple_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *iattr)
{
struct inode *inode = d_inode(dentry);
int error;
- error = setattr_prepare(dentry, iattr);
+ error = setattr_prepare(mnt_userns, dentry, iattr);
if (error)
return error;
if (iattr->ia_valid & ATTR_SIZE)
truncate_setsize(inode, iattr->ia_size);
- setattr_copy(inode, iattr);
+ setattr_copy(mnt_userns, inode, iattr);
mark_inode_dirty(inode);
return 0;
}
return ERR_PTR(-ENOENT);
}
-static int empty_dir_getattr(const struct path *path, struct kstat *stat,
+static int empty_dir_getattr(struct user_namespace *mnt_userns,
+ const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int query_flags)
{
struct inode *inode = d_inode(path->dentry);
- generic_fillattr(inode, stat);
+ generic_fillattr(&init_user_ns, inode, stat);
return 0;
}
-static int empty_dir_setattr(struct dentry *dentry, struct iattr *attr)
+static int empty_dir_setattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct iattr *attr)
{
return -EPERM;
}
iput(inode);
return NULL;
}
- inode_init_owner(inode, dir, mode);
+ inode_init_owner(&init_user_ns, inode, dir, mode);
inode->i_ino = j;
inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
inode->i_blocks = 0;
.splice_read = generic_file_splice_read,
};
-static int minix_setattr(struct dentry *dentry, struct iattr *attr)
+static int minix_setattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
int error;
- error = setattr_prepare(dentry, attr);
+ error = setattr_prepare(&init_user_ns, dentry, attr);
if (error)
return error;
minix_truncate(inode);
}
- setattr_copy(inode, attr);
+ setattr_copy(&init_user_ns, inode, attr);
mark_inode_dirty(inode);
return 0;
}
return err;
}
-int minix_getattr(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int flags)
+int minix_getattr(struct user_namespace *mnt_userns, const struct path *path,
+ struct kstat *stat, u32 request_mask, unsigned int flags)
{
struct super_block *sb = path->dentry->d_sb;
struct inode *inode = d_inode(path->dentry);
- generic_fillattr(inode, stat);
+ generic_fillattr(&init_user_ns, inode, stat);
if (INODE_VERSION(inode) == MINIX_V1)
stat->blocks = (BLOCK_SIZE / 512) * V1_minix_blocks(stat->size, sb);
else
extern int minix_new_block(struct inode * inode);
extern void minix_free_block(struct inode *inode, unsigned long block);
extern unsigned long minix_count_free_blocks(struct super_block *sb);
-extern int minix_getattr(const struct path *, struct kstat *, u32, unsigned int);
+extern int minix_getattr(struct user_namespace *, const struct path *,
+ struct kstat *, u32, unsigned int);
extern int minix_prepare_chunk(struct page *page, loff_t pos, unsigned len);
extern void V1_minix_truncate(struct inode *);
return d_splice_alias(inode, dentry);
}
-static int minix_mknod(struct inode * dir, struct dentry *dentry, umode_t mode, dev_t rdev)
+static int minix_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, dev_t rdev)
{
int error;
struct inode *inode;
return error;
}
-static int minix_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int minix_tmpfile(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
int error;
struct inode *inode = minix_new_inode(dir, mode, &error);
return error;
}
-static int minix_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- bool excl)
+static int minix_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool excl)
{
- return minix_mknod(dir, dentry, mode, 0);
+ return minix_mknod(mnt_userns, dir, dentry, mode, 0);
}
-static int minix_symlink(struct inode * dir, struct dentry *dentry,
- const char * symname)
+static int minix_symlink(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, const char *symname)
{
int err = -ENAMETOOLONG;
int i = strlen(symname)+1;
return add_nondir(dentry, inode);
}
-static int minix_mkdir(struct inode * dir, struct dentry *dentry, umode_t mode)
+static int minix_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
struct inode * inode;
int err;
return err;
}
-static int minix_rename(struct inode * old_dir, struct dentry *old_dentry,
- struct inode * new_dir, struct dentry *new_dentry,
+static int minix_rename(struct user_namespace *mnt_userns,
+ struct inode *old_dir, struct dentry *old_dentry,
+ struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
struct inode * old_inode = d_inode(old_dentry);
extern seqlock_t mount_lock;
-static inline void lock_mount_hash(void)
-{
- write_seqlock(&mount_lock);
-}
-
-static inline void unlock_mount_hash(void)
-{
- write_sequnlock(&mount_lock);
-}
-
struct proc_mounts {
struct mnt_namespace *ns;
struct path root;
__putname(name);
}
-static int check_acl(struct inode *inode, int mask)
+/**
+ * check_acl - perform ACL permission checking
+ * @mnt_userns: user namespace of the mount the inode was found from
+ * @inode: inode to check permissions on
+ * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...)
+ *
+ * This function performs the ACL permission checking. Since this function
+ * retrieve POSIX acls it needs to know whether it is called from a blocking or
+ * non-blocking context and thus cares about the MAY_NOT_BLOCK bit.
+ *
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then take
+ * care to map the inode according to @mnt_userns before checking permissions.
+ * On non-idmapped mounts or if permission checking is to be performed on the
+ * raw inode simply passs init_user_ns.
+ */
+static int check_acl(struct user_namespace *mnt_userns,
+ struct inode *inode, int mask)
{
#ifdef CONFIG_FS_POSIX_ACL
struct posix_acl *acl;
/* no ->get_acl() calls in RCU mode... */
if (is_uncached_acl(acl))
return -ECHILD;
- return posix_acl_permission(inode, acl, mask);
+ return posix_acl_permission(mnt_userns, inode, acl, mask);
}
acl = get_acl(inode, ACL_TYPE_ACCESS);
if (IS_ERR(acl))
return PTR_ERR(acl);
if (acl) {
- int error = posix_acl_permission(inode, acl, mask);
+ int error = posix_acl_permission(mnt_userns, inode, acl, mask);
posix_acl_release(acl);
return error;
}
return -EAGAIN;
}
-/*
- * This does the basic UNIX permission checking.
+/**
+ * acl_permission_check - perform basic UNIX permission checking
+ * @mnt_userns: user namespace of the mount the inode was found from
+ * @inode: inode to check permissions on
+ * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...)
+ *
+ * This function performs the basic UNIX permission checking. Since this
+ * function may retrieve POSIX acls it needs to know whether it is called from a
+ * blocking or non-blocking context and thus cares about the MAY_NOT_BLOCK bit.
*
- * Note that the POSIX ACL check cares about the MAY_NOT_BLOCK bit,
- * for RCU walking.
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then take
+ * care to map the inode according to @mnt_userns before checking permissions.
+ * On non-idmapped mounts or if permission checking is to be performed on the
+ * raw inode simply passs init_user_ns.
*/
-static int acl_permission_check(struct inode *inode, int mask)
+static int acl_permission_check(struct user_namespace *mnt_userns,
+ struct inode *inode, int mask)
{
unsigned int mode = inode->i_mode;
+ kuid_t i_uid;
/* Are we the owner? If so, ACL's don't matter */
- if (likely(uid_eq(current_fsuid(), inode->i_uid))) {
+ i_uid = i_uid_into_mnt(mnt_userns, inode);
+ if (likely(uid_eq(current_fsuid(), i_uid))) {
mask &= 7;
mode >>= 6;
return (mask & ~mode) ? -EACCES : 0;
/* Do we have ACL's? */
if (IS_POSIXACL(inode) && (mode & S_IRWXG)) {
- int error = check_acl(inode, mask);
+ int error = check_acl(mnt_userns, inode, mask);
if (error != -EAGAIN)
return error;
}
* about? Need to check group ownership if so.
*/
if (mask & (mode ^ (mode >> 3))) {
- if (in_group_p(inode->i_gid))
+ kgid_t kgid = i_gid_into_mnt(mnt_userns, inode);
+ if (in_group_p(kgid))
mode >>= 3;
}
/**
* generic_permission - check for access rights on a Posix-like filesystem
+ * @mnt_userns: user namespace of the mount the inode was found from
* @inode: inode to check access rights for
* @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC,
* %MAY_NOT_BLOCK ...)
* generic_permission is rcu-walk aware. It returns -ECHILD in case an rcu-walk
* request cannot be satisfied (eg. requires blocking or too much complexity).
* It would then be called again in ref-walk mode.
+ *
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then take
+ * care to map the inode according to @mnt_userns before checking permissions.
+ * On non-idmapped mounts or if permission checking is to be performed on the
+ * raw inode simply passs init_user_ns.
*/
-int generic_permission(struct inode *inode, int mask)
+int generic_permission(struct user_namespace *mnt_userns, struct inode *inode,
+ int mask)
{
int ret;
/*
* Do the basic permission checks.
*/
- ret = acl_permission_check(inode, mask);
+ ret = acl_permission_check(mnt_userns, inode, mask);
if (ret != -EACCES)
return ret;
if (S_ISDIR(inode->i_mode)) {
/* DACs are overridable for directories */
if (!(mask & MAY_WRITE))
- if (capable_wrt_inode_uidgid(inode,
+ if (capable_wrt_inode_uidgid(mnt_userns, inode,
CAP_DAC_READ_SEARCH))
return 0;
- if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE))
+ if (capable_wrt_inode_uidgid(mnt_userns, inode,
+ CAP_DAC_OVERRIDE))
return 0;
return -EACCES;
}
*/
mask &= MAY_READ | MAY_WRITE | MAY_EXEC;
if (mask == MAY_READ)
- if (capable_wrt_inode_uidgid(inode, CAP_DAC_READ_SEARCH))
+ if (capable_wrt_inode_uidgid(mnt_userns, inode,
+ CAP_DAC_READ_SEARCH))
return 0;
/*
* Read/write DACs are always overridable.
* at least one exec bit set.
*/
if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO))
- if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE))
+ if (capable_wrt_inode_uidgid(mnt_userns, inode,
+ CAP_DAC_OVERRIDE))
return 0;
return -EACCES;
}
EXPORT_SYMBOL(generic_permission);
-/*
+/**
+ * do_inode_permission - UNIX permission checking
+ * @mnt_userns: user namespace of the mount the inode was found from
+ * @inode: inode to check permissions on
+ * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...)
+ *
* We _really_ want to just do "generic_permission()" without
* even looking at the inode->i_op values. So we keep a cache
* flag in inode->i_opflags, that says "this has not special
* permission function, use the fast case".
*/
-static inline int do_inode_permission(struct inode *inode, int mask)
+static inline int do_inode_permission(struct user_namespace *mnt_userns,
+ struct inode *inode, int mask)
{
if (unlikely(!(inode->i_opflags & IOP_FASTPERM))) {
if (likely(inode->i_op->permission))
- return inode->i_op->permission(inode, mask);
+ return inode->i_op->permission(mnt_userns, inode, mask);
/* This gets set once for the inode lifetime */
spin_lock(&inode->i_lock);
inode->i_opflags |= IOP_FASTPERM;
spin_unlock(&inode->i_lock);
}
- return generic_permission(inode, mask);
+ return generic_permission(mnt_userns, inode, mask);
}
/**
/**
* inode_permission - Check for access rights to a given inode
- * @inode: Inode to check permission on
- * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
+ * @mnt_userns: User namespace of the mount the inode was found from
+ * @inode: Inode to check permission on
+ * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
*
* Check for read/write/execute permissions on an inode. We use fs[ug]id for
* this, letting us set arbitrary permissions for filesystem access without
*
* When checking for MAY_APPEND, MAY_WRITE must also be set in @mask.
*/
-int inode_permission(struct inode *inode, int mask)
+int inode_permission(struct user_namespace *mnt_userns,
+ struct inode *inode, int mask)
{
int retval;
* written back improperly if their true value is unknown
* to the vfs.
*/
- if (HAS_UNMAPPED_ID(inode))
+ if (HAS_UNMAPPED_ID(mnt_userns, inode))
return -EACCES;
}
- retval = do_inode_permission(inode, mask);
+ retval = do_inode_permission(mnt_userns, inode, mask);
if (retval)
return retval;
*/
static inline int may_follow_link(struct nameidata *nd, const struct inode *inode)
{
+ struct user_namespace *mnt_userns;
+ kuid_t i_uid;
+
if (!sysctl_protected_symlinks)
return 0;
+ mnt_userns = mnt_user_ns(nd->path.mnt);
+ i_uid = i_uid_into_mnt(mnt_userns, inode);
/* Allowed if owner and follower match. */
- if (uid_eq(current_cred()->fsuid, inode->i_uid))
+ if (uid_eq(current_cred()->fsuid, i_uid))
return 0;
/* Allowed if parent directory not sticky and world-writable. */
return 0;
/* Allowed if parent directory and link owner match. */
- if (uid_valid(nd->dir_uid) && uid_eq(nd->dir_uid, inode->i_uid))
+ if (uid_valid(nd->dir_uid) && uid_eq(nd->dir_uid, i_uid))
return 0;
if (nd->flags & LOOKUP_RCU)
/**
* safe_hardlink_source - Check for safe hardlink conditions
+ * @mnt_userns: user namespace of the mount the inode was found from
* @inode: the source inode to hardlink from
*
* Return false if at least one of the following conditions:
*
* Otherwise returns true.
*/
-static bool safe_hardlink_source(struct inode *inode)
+static bool safe_hardlink_source(struct user_namespace *mnt_userns,
+ struct inode *inode)
{
umode_t mode = inode->i_mode;
return false;
/* Hardlinking to unreadable or unwritable sources is dangerous. */
- if (inode_permission(inode, MAY_READ | MAY_WRITE))
+ if (inode_permission(mnt_userns, inode, MAY_READ | MAY_WRITE))
return false;
return true;
/**
* may_linkat - Check permissions for creating a hardlink
+ * @mnt_userns: user namespace of the mount the inode was found from
* @link: the source to hardlink from
*
* Block hardlink when all of:
* - hardlink source is unsafe (see safe_hardlink_source() above)
* - not CAP_FOWNER in a namespace with the inode owner uid mapped
*
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then take
+ * care to map the inode according to @mnt_userns before checking permissions.
+ * On non-idmapped mounts or if permission checking is to be performed on the
+ * raw inode simply passs init_user_ns.
+ *
* Returns 0 if successful, -ve on error.
*/
-int may_linkat(struct path *link)
+int may_linkat(struct user_namespace *mnt_userns, struct path *link)
{
struct inode *inode = link->dentry->d_inode;
/* Inode writeback is not safe when the uid or gid are invalid. */
- if (!uid_valid(inode->i_uid) || !gid_valid(inode->i_gid))
+ if (!uid_valid(i_uid_into_mnt(mnt_userns, inode)) ||
+ !gid_valid(i_gid_into_mnt(mnt_userns, inode)))
return -EOVERFLOW;
if (!sysctl_protected_hardlinks)
/* Source inode owner (or CAP_FOWNER) can hardlink all they like,
* otherwise, it must be a safe source.
*/
- if (safe_hardlink_source(inode) || inode_owner_or_capable(inode))
+ if (safe_hardlink_source(mnt_userns, inode) ||
+ inode_owner_or_capable(mnt_userns, inode))
return 0;
audit_log_path_denied(AUDIT_ANOM_LINK, "linkat");
* may_create_in_sticky - Check whether an O_CREAT open in a sticky directory
* should be allowed, or not, on files that already
* exist.
+ * @mnt_userns: user namespace of the mount the inode was found from
* @dir_mode: mode bits of directory
* @dir_uid: owner of directory
* @inode: the inode of the file to open
* the directory doesn't have to be world writable: being group writable will
* be enough.
*
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then take
+ * care to map the inode according to @mnt_userns before checking permissions.
+ * On non-idmapped mounts or if permission checking is to be performed on the
+ * raw inode simply passs init_user_ns.
+ *
* Returns 0 if the open is allowed, -ve on error.
*/
-static int may_create_in_sticky(umode_t dir_mode, kuid_t dir_uid,
- struct inode * const inode)
+static int may_create_in_sticky(struct user_namespace *mnt_userns,
+ struct nameidata *nd, struct inode *const inode)
{
+ umode_t dir_mode = nd->dir_mode;
+ kuid_t dir_uid = nd->dir_uid;
+
if ((!sysctl_protected_fifos && S_ISFIFO(inode->i_mode)) ||
(!sysctl_protected_regular && S_ISREG(inode->i_mode)) ||
likely(!(dir_mode & S_ISVTX)) ||
- uid_eq(inode->i_uid, dir_uid) ||
- uid_eq(current_fsuid(), inode->i_uid))
+ uid_eq(i_uid_into_mnt(mnt_userns, inode), dir_uid) ||
+ uid_eq(current_fsuid(), i_uid_into_mnt(mnt_userns, inode)))
return 0;
if (likely(dir_mode & 0002) ||
return res;
}
-static inline int may_lookup(struct nameidata *nd)
+static inline int may_lookup(struct user_namespace *mnt_userns,
+ struct nameidata *nd)
{
if (nd->flags & LOOKUP_RCU) {
- int err = inode_permission(nd->inode, MAY_EXEC|MAY_NOT_BLOCK);
+ int err = inode_permission(mnt_userns, nd->inode, MAY_EXEC|MAY_NOT_BLOCK);
if (err != -ECHILD || !try_to_unlazy(nd))
return err;
}
- return inode_permission(nd->inode, MAY_EXEC);
+ return inode_permission(mnt_userns, nd->inode, MAY_EXEC);
}
static int reserve_stack(struct nameidata *nd, struct path *link, unsigned seq)
/* At this point we know we have a real path component. */
for(;;) {
+ struct user_namespace *mnt_userns;
const char *link;
u64 hash_len;
int type;
- err = may_lookup(nd);
+ mnt_userns = mnt_user_ns(nd->path.mnt);
+ err = may_lookup(mnt_userns, nd);
if (err)
return err;
OK:
/* pathname or trailing symlink, done */
if (!depth) {
- nd->dir_uid = nd->inode->i_uid;
+ nd->dir_uid = i_uid_into_mnt(mnt_userns, nd->inode);
nd->dir_mode = nd->inode->i_mode;
nd->flags &= ~LOOKUP_PARENT;
return 0;
return err;
}
- return inode_permission(base->d_inode, MAY_EXEC);
+ return inode_permission(&init_user_ns, base->d_inode, MAY_EXEC);
}
/**
}
EXPORT_SYMBOL(user_path_at_empty);
-int __check_sticky(struct inode *dir, struct inode *inode)
+int __check_sticky(struct user_namespace *mnt_userns, struct inode *dir,
+ struct inode *inode)
{
kuid_t fsuid = current_fsuid();
- if (uid_eq(inode->i_uid, fsuid))
+ if (uid_eq(i_uid_into_mnt(mnt_userns, inode), fsuid))
return 0;
- if (uid_eq(dir->i_uid, fsuid))
+ if (uid_eq(i_uid_into_mnt(mnt_userns, dir), fsuid))
return 0;
- return !capable_wrt_inode_uidgid(inode, CAP_FOWNER);
+ return !capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FOWNER);
}
EXPORT_SYMBOL(__check_sticky);
* 11. We don't allow removal of NFS sillyrenamed files; it's handled by
* nfs_async_unlink().
*/
-static int may_delete(struct inode *dir, struct dentry *victim, bool isdir)
+static int may_delete(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *victim, bool isdir)
{
struct inode *inode = d_backing_inode(victim);
int error;
BUG_ON(victim->d_parent->d_inode != dir);
/* Inode writeback is not safe when the uid or gid are invalid. */
- if (!uid_valid(inode->i_uid) || !gid_valid(inode->i_gid))
+ if (!uid_valid(i_uid_into_mnt(mnt_userns, inode)) ||
+ !gid_valid(i_gid_into_mnt(mnt_userns, inode)))
return -EOVERFLOW;
audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE);
- error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
+ error = inode_permission(mnt_userns, dir, MAY_WRITE | MAY_EXEC);
if (error)
return error;
if (IS_APPEND(dir))
return -EPERM;
- if (check_sticky(dir, inode) || IS_APPEND(inode) ||
- IS_IMMUTABLE(inode) || IS_SWAPFILE(inode) || HAS_UNMAPPED_ID(inode))
+ if (check_sticky(mnt_userns, dir, inode) || IS_APPEND(inode) ||
+ IS_IMMUTABLE(inode) || IS_SWAPFILE(inode) ||
+ HAS_UNMAPPED_ID(mnt_userns, inode))
return -EPERM;
if (isdir) {
if (!d_is_dir(victim))
* 4. We should have write and exec permissions on dir
* 5. We can't do it if dir is immutable (done in permission())
*/
-static inline int may_create(struct inode *dir, struct dentry *child)
+static inline int may_create(struct user_namespace *mnt_userns,
+ struct inode *dir, struct dentry *child)
{
struct user_namespace *s_user_ns;
audit_inode_child(dir, child, AUDIT_TYPE_CHILD_CREATE);
if (IS_DEADDIR(dir))
return -ENOENT;
s_user_ns = dir->i_sb->s_user_ns;
- if (!kuid_has_mapping(s_user_ns, current_fsuid()) ||
- !kgid_has_mapping(s_user_ns, current_fsgid()))
+ if (!kuid_has_mapping(s_user_ns, fsuid_into_mnt(mnt_userns)) ||
+ !kgid_has_mapping(s_user_ns, fsgid_into_mnt(mnt_userns)))
return -EOVERFLOW;
- return inode_permission(dir, MAY_WRITE | MAY_EXEC);
+ return inode_permission(mnt_userns, dir, MAY_WRITE | MAY_EXEC);
}
/*
}
EXPORT_SYMBOL(unlock_rename);
-int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- bool want_excl)
+/**
+ * vfs_create - create new file
+ * @mnt_userns: user namespace of the mount the inode was found from
+ * @dir: inode of @dentry
+ * @dentry: pointer to dentry of the base directory
+ * @mode: mode of the new file
+ * @want_excl: whether the file must not yet exist
+ *
+ * Create a new file.
+ *
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then take
+ * care to map the inode according to @mnt_userns before checking permissions.
+ * On non-idmapped mounts or if permission checking is to be performed on the
+ * raw inode simply passs init_user_ns.
+ */
+int vfs_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool want_excl)
{
- int error = may_create(dir, dentry);
+ int error = may_create(mnt_userns, dir, dentry);
if (error)
return error;
error = security_inode_create(dir, dentry, mode);
if (error)
return error;
- error = dir->i_op->create(dir, dentry, mode, want_excl);
+ error = dir->i_op->create(mnt_userns, dir, dentry, mode, want_excl);
if (!error)
fsnotify_create(dir, dentry);
return error;
void *arg)
{
struct inode *dir = dentry->d_parent->d_inode;
- int error = may_create(dir, dentry);
+ int error = may_create(&init_user_ns, dir, dentry);
if (error)
return error;
!(path->mnt->mnt_sb->s_iflags & SB_I_NODEV);
}
-static int may_open(const struct path *path, int acc_mode, int flag)
+static int may_open(struct user_namespace *mnt_userns, const struct path *path,
+ int acc_mode, int flag)
{
struct dentry *dentry = path->dentry;
struct inode *inode = dentry->d_inode;
break;
}
- error = inode_permission(inode, MAY_OPEN | acc_mode);
+ error = inode_permission(mnt_userns, inode, MAY_OPEN | acc_mode);
if (error)
return error;
}
/* O_NOATIME can only be set by the owner or superuser */
- if (flag & O_NOATIME && !inode_owner_or_capable(inode))
+ if (flag & O_NOATIME && !inode_owner_or_capable(mnt_userns, inode))
return -EPERM;
return 0;
}
-static int handle_truncate(struct file *filp)
+static int handle_truncate(struct user_namespace *mnt_userns, struct file *filp)
{
const struct path *path = &filp->f_path;
struct inode *inode = path->dentry->d_inode;
if (!error)
error = security_path_truncate(path);
if (!error) {
- error = do_truncate(path->dentry, 0,
+ error = do_truncate(mnt_userns, path->dentry, 0,
ATTR_MTIME|ATTR_CTIME|ATTR_OPEN,
filp);
}
return flag;
}
-static int may_o_create(const struct path *dir, struct dentry *dentry, umode_t mode)
+static int may_o_create(struct user_namespace *mnt_userns,
+ const struct path *dir, struct dentry *dentry,
+ umode_t mode)
{
struct user_namespace *s_user_ns;
int error = security_path_mknod(dir, dentry, mode, 0);
return error;
s_user_ns = dir->dentry->d_sb->s_user_ns;
- if (!kuid_has_mapping(s_user_ns, current_fsuid()) ||
- !kgid_has_mapping(s_user_ns, current_fsgid()))
+ if (!kuid_has_mapping(s_user_ns, fsuid_into_mnt(mnt_userns)) ||
+ !kgid_has_mapping(s_user_ns, fsgid_into_mnt(mnt_userns)))
return -EOVERFLOW;
- error = inode_permission(dir->dentry->d_inode, MAY_WRITE | MAY_EXEC);
+ error = inode_permission(mnt_userns, dir->dentry->d_inode,
+ MAY_WRITE | MAY_EXEC);
if (error)
return error;
const struct open_flags *op,
bool got_write)
{
+ struct user_namespace *mnt_userns;
struct dentry *dir = nd->path.dentry;
struct inode *dir_inode = dir->d_inode;
int open_flag = op->open_flag;
*/
if (unlikely(!got_write))
open_flag &= ~O_TRUNC;
+ mnt_userns = mnt_user_ns(nd->path.mnt);
if (open_flag & O_CREAT) {
if (open_flag & O_EXCL)
open_flag &= ~O_TRUNC;
if (!IS_POSIXACL(dir->d_inode))
mode &= ~current_umask();
if (likely(got_write))
- create_error = may_o_create(&nd->path, dentry, mode);
+ create_error = may_o_create(mnt_userns, &nd->path,
+ dentry, mode);
else
create_error = -EROFS;
}
error = -EACCES;
goto out_dput;
}
- error = dir_inode->i_op->create(dir_inode, dentry, mode,
- open_flag & O_EXCL);
+
+ error = dir_inode->i_op->create(mnt_userns, dir_inode, dentry,
+ mode, open_flag & O_EXCL);
if (error)
goto out_dput;
}
static int do_open(struct nameidata *nd,
struct file *file, const struct open_flags *op)
{
+ struct user_namespace *mnt_userns;
int open_flag = op->open_flag;
bool do_truncate;
int acc_mode;
}
if (!(file->f_mode & FMODE_CREATED))
audit_inode(nd->name, nd->path.dentry, 0);
+ mnt_userns = mnt_user_ns(nd->path.mnt);
if (open_flag & O_CREAT) {
if ((open_flag & O_EXCL) && !(file->f_mode & FMODE_CREATED))
return -EEXIST;
if (d_is_dir(nd->path.dentry))
return -EISDIR;
- error = may_create_in_sticky(nd->dir_mode, nd->dir_uid,
+ error = may_create_in_sticky(mnt_userns, nd,
d_backing_inode(nd->path.dentry));
if (unlikely(error))
return error;
return error;
do_truncate = true;
}
- error = may_open(&nd->path, acc_mode, open_flag);
+ error = may_open(mnt_userns, &nd->path, acc_mode, open_flag);
if (!error && !(file->f_mode & FMODE_OPENED))
error = vfs_open(&nd->path, file);
if (!error)
error = ima_file_check(file, op->acc_mode);
if (!error && do_truncate)
- error = handle_truncate(file);
+ error = handle_truncate(mnt_userns, file);
if (unlikely(error > 0)) {
WARN_ON(1);
error = -EINVAL;
return error;
}
-struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag)
+/**
+ * vfs_tmpfile - create tmpfile
+ * @mnt_userns: user namespace of the mount the inode was found from
+ * @dentry: pointer to dentry of the base directory
+ * @mode: mode of the new tmpfile
+ * @open_flags: flags
+ *
+ * Create a temporary file.
+ *
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then take
+ * care to map the inode according to @mnt_userns before checking permissions.
+ * On non-idmapped mounts or if permission checking is to be performed on the
+ * raw inode simply passs init_user_ns.
+ */
+struct dentry *vfs_tmpfile(struct user_namespace *mnt_userns,
+ struct dentry *dentry, umode_t mode, int open_flag)
{
struct dentry *child = NULL;
struct inode *dir = dentry->d_inode;
int error;
/* we want directory to be writable */
- error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
+ error = inode_permission(mnt_userns, dir, MAY_WRITE | MAY_EXEC);
if (error)
goto out_err;
error = -EOPNOTSUPP;
child = d_alloc(dentry, &slash_name);
if (unlikely(!child))
goto out_err;
- error = dir->i_op->tmpfile(dir, child, mode);
+ error = dir->i_op->tmpfile(mnt_userns, dir, child, mode);
if (error)
goto out_err;
error = -ENOENT;
inode->i_state |= I_LINKABLE;
spin_unlock(&inode->i_lock);
}
- ima_post_create_tmpfile(inode);
+ ima_post_create_tmpfile(mnt_userns, inode);
return child;
out_err:
const struct open_flags *op,
struct file *file)
{
+ struct user_namespace *mnt_userns;
struct dentry *child;
struct path path;
int error = path_lookupat(nd, flags | LOOKUP_DIRECTORY, &path);
error = mnt_want_write(path.mnt);
if (unlikely(error))
goto out;
- child = vfs_tmpfile(path.dentry, op->mode, op->open_flag);
+ mnt_userns = mnt_user_ns(path.mnt);
+ child = vfs_tmpfile(mnt_userns, path.dentry, op->mode, op->open_flag);
error = PTR_ERR(child);
if (IS_ERR(child))
goto out2;
path.dentry = child;
audit_inode(nd->name, child, 0);
/* Don't check for other permissions, the inode was just created */
- error = may_open(&path, 0, op->open_flag);
+ error = may_open(mnt_userns, &path, 0, op->open_flag);
if (!error)
error = vfs_open(&path, file);
out2:
}
EXPORT_SYMBOL(user_path_create);
-int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev)
+/**
+ * vfs_mknod - create device node or file
+ * @mnt_userns: user namespace of the mount the inode was found from
+ * @dir: inode of @dentry
+ * @dentry: pointer to dentry of the base directory
+ * @mode: mode of the new device node or file
+ * @dev: device number of device to create
+ *
+ * Create a device node or file.
+ *
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then take
+ * care to map the inode according to @mnt_userns before checking permissions.
+ * On non-idmapped mounts or if permission checking is to be performed on the
+ * raw inode simply passs init_user_ns.
+ */
+int vfs_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, dev_t dev)
{
bool is_whiteout = S_ISCHR(mode) && dev == WHITEOUT_DEV;
- int error = may_create(dir, dentry);
+ int error = may_create(mnt_userns, dir, dentry);
if (error)
return error;
if (error)
return error;
- error = dir->i_op->mknod(dir, dentry, mode, dev);
+ error = dir->i_op->mknod(mnt_userns, dir, dentry, mode, dev);
if (!error)
fsnotify_create(dir, dentry);
return error;
static long do_mknodat(int dfd, const char __user *filename, umode_t mode,
unsigned int dev)
{
+ struct user_namespace *mnt_userns;
struct dentry *dentry;
struct path path;
int error;
error = security_path_mknod(&path, dentry, mode, dev);
if (error)
goto out;
+
+ mnt_userns = mnt_user_ns(path.mnt);
switch (mode & S_IFMT) {
case 0: case S_IFREG:
- error = vfs_create(path.dentry->d_inode,dentry,mode,true);
+ error = vfs_create(mnt_userns, path.dentry->d_inode,
+ dentry, mode, true);
if (!error)
- ima_post_path_mknod(dentry);
+ ima_post_path_mknod(mnt_userns, dentry);
break;
case S_IFCHR: case S_IFBLK:
- error = vfs_mknod(path.dentry->d_inode,dentry,mode,
- new_decode_dev(dev));
+ error = vfs_mknod(mnt_userns, path.dentry->d_inode,
+ dentry, mode, new_decode_dev(dev));
break;
case S_IFIFO: case S_IFSOCK:
- error = vfs_mknod(path.dentry->d_inode,dentry,mode,0);
+ error = vfs_mknod(mnt_userns, path.dentry->d_inode,
+ dentry, mode, 0);
break;
}
out:
return do_mknodat(AT_FDCWD, filename, mode, dev);
}
-int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+/**
+ * vfs_mkdir - create directory
+ * @mnt_userns: user namespace of the mount the inode was found from
+ * @dir: inode of @dentry
+ * @dentry: pointer to dentry of the base directory
+ * @mode: mode of the new directory
+ *
+ * Create a directory.
+ *
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then take
+ * care to map the inode according to @mnt_userns before checking permissions.
+ * On non-idmapped mounts or if permission checking is to be performed on the
+ * raw inode simply passs init_user_ns.
+ */
+int vfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
- int error = may_create(dir, dentry);
+ int error = may_create(mnt_userns, dir, dentry);
unsigned max_links = dir->i_sb->s_max_links;
if (error)
if (max_links && dir->i_nlink >= max_links)
return -EMLINK;
- error = dir->i_op->mkdir(dir, dentry, mode);
+ error = dir->i_op->mkdir(mnt_userns, dir, dentry, mode);
if (!error)
fsnotify_mkdir(dir, dentry);
return error;
if (!IS_POSIXACL(path.dentry->d_inode))
mode &= ~current_umask();
error = security_path_mkdir(&path, dentry, mode);
- if (!error)
- error = vfs_mkdir(path.dentry->d_inode, dentry, mode);
+ if (!error) {
+ struct user_namespace *mnt_userns;
+ mnt_userns = mnt_user_ns(path.mnt);
+ error = vfs_mkdir(mnt_userns, path.dentry->d_inode, dentry,
+ mode);
+ }
done_path_create(&path, dentry);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
return do_mkdirat(AT_FDCWD, pathname, mode);
}
-int vfs_rmdir(struct inode *dir, struct dentry *dentry)
+/**
+ * vfs_rmdir - remove directory
+ * @mnt_userns: user namespace of the mount the inode was found from
+ * @dir: inode of @dentry
+ * @dentry: pointer to dentry of the base directory
+ *
+ * Remove a directory.
+ *
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then take
+ * care to map the inode according to @mnt_userns before checking permissions.
+ * On non-idmapped mounts or if permission checking is to be performed on the
+ * raw inode simply passs init_user_ns.
+ */
+int vfs_rmdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry)
{
- int error = may_delete(dir, dentry, 1);
+ int error = may_delete(mnt_userns, dir, dentry, 1);
if (error)
return error;
long do_rmdir(int dfd, struct filename *name)
{
+ struct user_namespace *mnt_userns;
int error = 0;
struct dentry *dentry;
struct path path;
error = security_path_rmdir(&path, dentry);
if (error)
goto exit3;
- error = vfs_rmdir(path.dentry->d_inode, dentry);
+ mnt_userns = mnt_user_ns(path.mnt);
+ error = vfs_rmdir(mnt_userns, path.dentry->d_inode, dentry);
exit3:
dput(dentry);
exit2:
/**
* vfs_unlink - unlink a filesystem object
+ * @mnt_userns: user namespace of the mount the inode was found from
* @dir: parent directory
* @dentry: victim
* @delegated_inode: returns victim inode, if the inode is delegated.
* Alternatively, a caller may pass NULL for delegated_inode. This may
* be appropriate for callers that expect the underlying filesystem not
* to be NFS exported.
+ *
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then take
+ * care to map the inode according to @mnt_userns before checking permissions.
+ * On non-idmapped mounts or if permission checking is to be performed on the
+ * raw inode simply passs init_user_ns.
*/
-int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegated_inode)
+int vfs_unlink(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, struct inode **delegated_inode)
{
struct inode *target = dentry->d_inode;
- int error = may_delete(dir, dentry, 0);
+ int error = may_delete(mnt_userns, dir, dentry, 0);
if (error)
return error;
dentry = __lookup_hash(&last, path.dentry, lookup_flags);
error = PTR_ERR(dentry);
if (!IS_ERR(dentry)) {
+ struct user_namespace *mnt_userns;
+
/* Why not before? Because we want correct error value */
if (last.name[last.len])
goto slashes;
error = security_path_unlink(&path, dentry);
if (error)
goto exit2;
- error = vfs_unlink(path.dentry->d_inode, dentry, &delegated_inode);
+ mnt_userns = mnt_user_ns(path.mnt);
+ error = vfs_unlink(mnt_userns, path.dentry->d_inode, dentry,
+ &delegated_inode);
exit2:
dput(dentry);
}
return do_unlinkat(AT_FDCWD, getname(pathname));
}
-int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname)
+/**
+ * vfs_symlink - create symlink
+ * @mnt_userns: user namespace of the mount the inode was found from
+ * @dir: inode of @dentry
+ * @dentry: pointer to dentry of the base directory
+ * @oldname: name of the file to link to
+ *
+ * Create a symlink.
+ *
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then take
+ * care to map the inode according to @mnt_userns before checking permissions.
+ * On non-idmapped mounts or if permission checking is to be performed on the
+ * raw inode simply passs init_user_ns.
+ */
+int vfs_symlink(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, const char *oldname)
{
- int error = may_create(dir, dentry);
+ int error = may_create(mnt_userns, dir, dentry);
if (error)
return error;
if (error)
return error;
- error = dir->i_op->symlink(dir, dentry, oldname);
+ error = dir->i_op->symlink(mnt_userns, dir, dentry, oldname);
if (!error)
fsnotify_create(dir, dentry);
return error;
goto out_putname;
error = security_path_symlink(&path, dentry, from->name);
- if (!error)
- error = vfs_symlink(path.dentry->d_inode, dentry, from->name);
+ if (!error) {
+ struct user_namespace *mnt_userns;
+
+ mnt_userns = mnt_user_ns(path.mnt);
+ error = vfs_symlink(mnt_userns, path.dentry->d_inode, dentry,
+ from->name);
+ }
done_path_create(&path, dentry);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
/**
* vfs_link - create a new link
* @old_dentry: object to be linked
+ * @mnt_userns: the user namespace of the mount
* @dir: new parent
* @new_dentry: where to create the new link
* @delegated_inode: returns inode needing a delegation break
* Alternatively, a caller may pass NULL for delegated_inode. This may
* be appropriate for callers that expect the underlying filesystem not
* to be NFS exported.
+ *
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then take
+ * care to map the inode according to @mnt_userns before checking permissions.
+ * On non-idmapped mounts or if permission checking is to be performed on the
+ * raw inode simply passs init_user_ns.
*/
-int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry, struct inode **delegated_inode)
+int vfs_link(struct dentry *old_dentry, struct user_namespace *mnt_userns,
+ struct inode *dir, struct dentry *new_dentry,
+ struct inode **delegated_inode)
{
struct inode *inode = old_dentry->d_inode;
unsigned max_links = dir->i_sb->s_max_links;
if (!inode)
return -ENOENT;
- error = may_create(dir, new_dentry);
+ error = may_create(mnt_userns, dir, new_dentry);
if (error)
return error;
* be writen back improperly if their true value is unknown to
* the vfs.
*/
- if (HAS_UNMAPPED_ID(inode))
+ if (HAS_UNMAPPED_ID(mnt_userns, inode))
return -EPERM;
if (!dir->i_op->link)
return -EPERM;
static int do_linkat(int olddfd, const char __user *oldname, int newdfd,
const char __user *newname, int flags)
{
+ struct user_namespace *mnt_userns;
struct dentry *new_dentry;
struct path old_path, new_path;
struct inode *delegated_inode = NULL;
error = -EXDEV;
if (old_path.mnt != new_path.mnt)
goto out_dput;
- error = may_linkat(&old_path);
+ mnt_userns = mnt_user_ns(new_path.mnt);
+ error = may_linkat(mnt_userns, &old_path);
if (unlikely(error))
goto out_dput;
error = security_path_link(old_path.dentry, &new_path, new_dentry);
if (error)
goto out_dput;
- error = vfs_link(old_path.dentry, new_path.dentry->d_inode, new_dentry, &delegated_inode);
+ error = vfs_link(old_path.dentry, mnt_userns, new_path.dentry->d_inode,
+ new_dentry, &delegated_inode);
out_dput:
done_path_create(&new_path, new_dentry);
if (delegated_inode) {
/**
* vfs_rename - rename a filesystem object
- * @old_dir: parent of source
- * @old_dentry: source
- * @new_dir: parent of destination
- * @new_dentry: destination
- * @delegated_inode: returns an inode needing a delegation break
- * @flags: rename flags
+ * @old_mnt_userns: old user namespace of the mount the inode was found from
+ * @old_dir: parent of source
+ * @old_dentry: source
+ * @new_mnt_userns: new user namespace of the mount the inode was found from
+ * @new_dir: parent of destination
+ * @new_dentry: destination
+ * @delegated_inode: returns an inode needing a delegation break
+ * @flags: rename flags
*
* The caller must hold multiple mutexes--see lock_rename()).
*
* ->i_mutex on parents, which works but leads to some truly excessive
* locking].
*/
-int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry,
- struct inode **delegated_inode, unsigned int flags)
+int vfs_rename(struct renamedata *rd)
{
int error;
+ struct inode *old_dir = rd->old_dir, *new_dir = rd->new_dir;
+ struct dentry *old_dentry = rd->old_dentry;
+ struct dentry *new_dentry = rd->new_dentry;
+ struct inode **delegated_inode = rd->delegated_inode;
+ unsigned int flags = rd->flags;
bool is_dir = d_is_dir(old_dentry);
struct inode *source = old_dentry->d_inode;
struct inode *target = new_dentry->d_inode;
if (source == target)
return 0;
- error = may_delete(old_dir, old_dentry, is_dir);
+ error = may_delete(rd->old_mnt_userns, old_dir, old_dentry, is_dir);
if (error)
return error;
if (!target) {
- error = may_create(new_dir, new_dentry);
+ error = may_create(rd->new_mnt_userns, new_dir, new_dentry);
} else {
new_is_dir = d_is_dir(new_dentry);
if (!(flags & RENAME_EXCHANGE))
- error = may_delete(new_dir, new_dentry, is_dir);
+ error = may_delete(rd->new_mnt_userns, new_dir,
+ new_dentry, is_dir);
else
- error = may_delete(new_dir, new_dentry, new_is_dir);
+ error = may_delete(rd->new_mnt_userns, new_dir,
+ new_dentry, new_is_dir);
}
if (error)
return error;
*/
if (new_dir != old_dir) {
if (is_dir) {
- error = inode_permission(source, MAY_WRITE);
+ error = inode_permission(rd->old_mnt_userns, source,
+ MAY_WRITE);
if (error)
return error;
}
if ((flags & RENAME_EXCHANGE) && new_is_dir) {
- error = inode_permission(target, MAY_WRITE);
+ error = inode_permission(rd->new_mnt_userns, target,
+ MAY_WRITE);
if (error)
return error;
}
if (error)
goto out;
}
- error = old_dir->i_op->rename(old_dir, old_dentry,
- new_dir, new_dentry, flags);
+ error = old_dir->i_op->rename(rd->new_mnt_userns, old_dir, old_dentry,
+ new_dir, new_dentry, flags);
if (error)
goto out;
int do_renameat2(int olddfd, struct filename *from, int newdfd,
struct filename *to, unsigned int flags)
{
+ struct renamedata rd;
struct dentry *old_dentry, *new_dentry;
struct dentry *trap;
struct path old_path, new_path;
&new_path, new_dentry, flags);
if (error)
goto exit5;
- error = vfs_rename(old_path.dentry->d_inode, old_dentry,
- new_path.dentry->d_inode, new_dentry,
- &delegated_inode, flags);
+
+ rd.old_dir = old_path.dentry->d_inode;
+ rd.old_dentry = old_dentry;
+ rd.old_mnt_userns = mnt_user_ns(old_path.mnt);
+ rd.new_dir = new_path.dentry->d_inode;
+ rd.new_dentry = new_dentry;
+ rd.new_mnt_userns = mnt_user_ns(new_path.mnt);
+ rd.delegated_inode = &delegated_inode;
+ rd.flags = flags;
+ error = vfs_rename(&rd);
exit5:
dput(new_dentry);
exit4:
#include <linux/proc_ns.h>
#include <linux/magic.h>
#include <linux/memblock.h>
+#include <linux/proc_fs.h>
#include <linux/task_work.h>
#include <linux/sched/task.h>
#include <uapi/linux/mount.h>
static HLIST_HEAD(unmounted); /* protected by namespace_sem */
static LIST_HEAD(ex_mountpoints); /* protected by namespace_sem */
+struct mount_kattr {
+ unsigned int attr_set;
+ unsigned int attr_clr;
+ unsigned int propagation;
+ unsigned int lookup_flags;
+ bool recurse;
+ struct user_namespace *mnt_userns;
+};
+
/* /sys/fs */
struct kobject *fs_kobj;
EXPORT_SYMBOL_GPL(fs_kobj);
*/
__cacheline_aligned_in_smp DEFINE_SEQLOCK(mount_lock);
+static inline void lock_mount_hash(void)
+{
+ write_seqlock(&mount_lock);
+}
+
+static inline void unlock_mount_hash(void)
+{
+ write_sequnlock(&mount_lock);
+}
+
static inline struct hlist_head *m_hash(struct vfsmount *mnt, struct dentry *dentry)
{
unsigned long tmp = ((unsigned long)mnt / L1_CACHE_BYTES);
INIT_HLIST_NODE(&mnt->mnt_mp_list);
INIT_LIST_HEAD(&mnt->mnt_umounting);
INIT_HLIST_HEAD(&mnt->mnt_stuck_children);
+ mnt->mnt.mnt_userns = &init_user_ns;
}
return mnt;
}
EXPORT_SYMBOL(mnt_drop_write_file);
-static int mnt_make_readonly(struct mount *mnt)
+static inline int mnt_hold_writers(struct mount *mnt)
{
- int ret = 0;
-
- lock_mount_hash();
mnt->mnt.mnt_flags |= MNT_WRITE_HOLD;
/*
* After storing MNT_WRITE_HOLD, we'll read the counters. This store
* we're counting up here.
*/
if (mnt_get_writers(mnt) > 0)
- ret = -EBUSY;
- else
- mnt->mnt.mnt_flags |= MNT_READONLY;
+ return -EBUSY;
+
+ return 0;
+}
+
+static inline void mnt_unhold_writers(struct mount *mnt)
+{
/*
* MNT_READONLY must become visible before ~MNT_WRITE_HOLD, so writers
* that become unheld will see MNT_READONLY.
*/
smp_wmb();
mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD;
- unlock_mount_hash();
- return ret;
}
-static int __mnt_unmake_readonly(struct mount *mnt)
+static int mnt_make_readonly(struct mount *mnt)
{
- lock_mount_hash();
- mnt->mnt.mnt_flags &= ~MNT_READONLY;
- unlock_mount_hash();
- return 0;
+ int ret;
+
+ ret = mnt_hold_writers(mnt);
+ if (!ret)
+ mnt->mnt.mnt_flags |= MNT_READONLY;
+ mnt_unhold_writers(mnt);
+ return ret;
}
int sb_prepare_remount_readonly(struct super_block *sb)
static void free_vfsmnt(struct mount *mnt)
{
+ struct user_namespace *mnt_userns;
+
+ mnt_userns = mnt_user_ns(&mnt->mnt);
+ if (mnt_userns != &init_user_ns)
+ put_user_ns(mnt_userns);
kfree_const(mnt->mnt_devname);
#ifdef CONFIG_SMP
free_percpu(mnt->mnt_pcp);
mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL);
atomic_inc(&sb->s_active);
+ mnt->mnt.mnt_userns = mnt_user_ns(&old->mnt);
+ if (mnt->mnt.mnt_userns != &init_user_ns)
+ mnt->mnt.mnt_userns = get_user_ns(mnt->mnt.mnt_userns);
mnt->mnt.mnt_sb = sb;
mnt->mnt.mnt_root = dget(root);
mnt->mnt_mountpoint = mnt->mnt.mnt_root;
if (readonly_request)
return mnt_make_readonly(mnt);
- return __mnt_unmake_readonly(mnt);
+ mnt->mnt.mnt_flags &= ~MNT_READONLY;
+ return 0;
}
-/*
- * Update the user-settable attributes on a mount. The caller must hold
- * sb->s_umount for writing.
- */
static void set_mount_attributes(struct mount *mnt, unsigned int mnt_flags)
{
- lock_mount_hash();
mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK;
mnt->mnt.mnt_flags = mnt_flags;
touch_mnt_namespace(mnt->mnt_ns);
- unlock_mount_hash();
}
static void mnt_warn_timestamp_expiry(struct path *mountpoint, struct vfsmount *mnt)
if (!can_change_locked_flags(mnt, mnt_flags))
return -EPERM;
- down_write(&sb->s_umount);
+ /*
+ * We're only checking whether the superblock is read-only not
+ * changing it, so only take down_read(&sb->s_umount).
+ */
+ down_read(&sb->s_umount);
+ lock_mount_hash();
ret = change_mount_ro_state(mnt, mnt_flags);
if (ret == 0)
set_mount_attributes(mnt, mnt_flags);
- up_write(&sb->s_umount);
+ unlock_mount_hash();
+ up_read(&sb->s_umount);
mnt_warn_timestamp_expiry(path, &mnt->mnt);
err = -EPERM;
if (ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) {
err = reconfigure_super(fc);
- if (!err)
+ if (!err) {
+ lock_mount_hash();
set_mount_attributes(mnt, mnt_flags);
+ unlock_mount_hash();
+ }
}
up_write(&sb->s_umount);
}
return ret;
}
+#define FSMOUNT_VALID_FLAGS \
+ (MOUNT_ATTR_RDONLY | MOUNT_ATTR_NOSUID | MOUNT_ATTR_NODEV | \
+ MOUNT_ATTR_NOEXEC | MOUNT_ATTR__ATIME | MOUNT_ATTR_NODIRATIME)
+
+#define MOUNT_SETATTR_VALID_FLAGS (FSMOUNT_VALID_FLAGS | MOUNT_ATTR_IDMAP)
+
+#define MOUNT_SETATTR_PROPAGATION_FLAGS \
+ (MS_UNBINDABLE | MS_PRIVATE | MS_SLAVE | MS_SHARED)
+
+static unsigned int attr_flags_to_mnt_flags(u64 attr_flags)
+{
+ unsigned int mnt_flags = 0;
+
+ if (attr_flags & MOUNT_ATTR_RDONLY)
+ mnt_flags |= MNT_READONLY;
+ if (attr_flags & MOUNT_ATTR_NOSUID)
+ mnt_flags |= MNT_NOSUID;
+ if (attr_flags & MOUNT_ATTR_NODEV)
+ mnt_flags |= MNT_NODEV;
+ if (attr_flags & MOUNT_ATTR_NOEXEC)
+ mnt_flags |= MNT_NOEXEC;
+ if (attr_flags & MOUNT_ATTR_NODIRATIME)
+ mnt_flags |= MNT_NODIRATIME;
+
+ return mnt_flags;
+}
+
/*
* Create a kernel mount representation for a new, prepared superblock
* (specified by fs_fd) and attach to an open_tree-like file descriptor.
if ((flags & ~(FSMOUNT_CLOEXEC)) != 0)
return -EINVAL;
- if (attr_flags & ~(MOUNT_ATTR_RDONLY |
- MOUNT_ATTR_NOSUID |
- MOUNT_ATTR_NODEV |
- MOUNT_ATTR_NOEXEC |
- MOUNT_ATTR__ATIME |
- MOUNT_ATTR_NODIRATIME))
+ if (attr_flags & ~FSMOUNT_VALID_FLAGS)
return -EINVAL;
- if (attr_flags & MOUNT_ATTR_RDONLY)
- mnt_flags |= MNT_READONLY;
- if (attr_flags & MOUNT_ATTR_NOSUID)
- mnt_flags |= MNT_NOSUID;
- if (attr_flags & MOUNT_ATTR_NODEV)
- mnt_flags |= MNT_NODEV;
- if (attr_flags & MOUNT_ATTR_NOEXEC)
- mnt_flags |= MNT_NOEXEC;
- if (attr_flags & MOUNT_ATTR_NODIRATIME)
- mnt_flags |= MNT_NODIRATIME;
+ mnt_flags = attr_flags_to_mnt_flags(attr_flags);
switch (attr_flags & MOUNT_ATTR__ATIME) {
case MOUNT_ATTR_STRICTATIME:
return error;
}
+static unsigned int recalc_flags(struct mount_kattr *kattr, struct mount *mnt)
+{
+ unsigned int flags = mnt->mnt.mnt_flags;
+
+ /* flags to clear */
+ flags &= ~kattr->attr_clr;
+ /* flags to raise */
+ flags |= kattr->attr_set;
+
+ return flags;
+}
+
+static int can_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt)
+{
+ struct vfsmount *m = &mnt->mnt;
+
+ if (!kattr->mnt_userns)
+ return 0;
+
+ /*
+ * Once a mount has been idmapped we don't allow it to change its
+ * mapping. It makes things simpler and callers can just create
+ * another bind-mount they can idmap if they want to.
+ */
+ if (mnt_user_ns(m) != &init_user_ns)
+ return -EPERM;
+
+ /* The underlying filesystem doesn't support idmapped mounts yet. */
+ if (!(m->mnt_sb->s_type->fs_flags & FS_ALLOW_IDMAP))
+ return -EINVAL;
+
+ /* We're not controlling the superblock. */
+ if (!ns_capable(m->mnt_sb->s_user_ns, CAP_SYS_ADMIN))
+ return -EPERM;
+
+ /* Mount has already been visible in the filesystem hierarchy. */
+ if (!is_anon_ns(mnt->mnt_ns))
+ return -EINVAL;
+
+ return 0;
+}
+
+static struct mount *mount_setattr_prepare(struct mount_kattr *kattr,
+ struct mount *mnt, int *err)
+{
+ struct mount *m = mnt, *last = NULL;
+
+ if (!is_mounted(&m->mnt)) {
+ *err = -EINVAL;
+ goto out;
+ }
+
+ if (!(mnt_has_parent(m) ? check_mnt(m) : is_anon_ns(m->mnt_ns))) {
+ *err = -EINVAL;
+ goto out;
+ }
+
+ do {
+ unsigned int flags;
+
+ flags = recalc_flags(kattr, m);
+ if (!can_change_locked_flags(m, flags)) {
+ *err = -EPERM;
+ goto out;
+ }
+
+ *err = can_idmap_mount(kattr, m);
+ if (*err)
+ goto out;
+
+ last = m;
+
+ if ((kattr->attr_set & MNT_READONLY) &&
+ !(m->mnt.mnt_flags & MNT_READONLY)) {
+ *err = mnt_hold_writers(m);
+ if (*err)
+ goto out;
+ }
+ } while (kattr->recurse && (m = next_mnt(m, mnt)));
+
+out:
+ return last;
+}
+
+static void do_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt)
+{
+ struct user_namespace *mnt_userns;
+
+ if (!kattr->mnt_userns)
+ return;
+
+ mnt_userns = get_user_ns(kattr->mnt_userns);
+ /* Pairs with smp_load_acquire() in mnt_user_ns(). */
+ smp_store_release(&mnt->mnt.mnt_userns, mnt_userns);
+}
+
+static void mount_setattr_commit(struct mount_kattr *kattr,
+ struct mount *mnt, struct mount *last,
+ int err)
+{
+ struct mount *m = mnt;
+
+ do {
+ if (!err) {
+ unsigned int flags;
+
+ do_idmap_mount(kattr, m);
+ flags = recalc_flags(kattr, m);
+ WRITE_ONCE(m->mnt.mnt_flags, flags);
+ }
+
+ /*
+ * We either set MNT_READONLY above so make it visible
+ * before ~MNT_WRITE_HOLD or we failed to recursively
+ * apply mount options.
+ */
+ if ((kattr->attr_set & MNT_READONLY) &&
+ (m->mnt.mnt_flags & MNT_WRITE_HOLD))
+ mnt_unhold_writers(m);
+
+ if (!err && kattr->propagation)
+ change_mnt_propagation(m, kattr->propagation);
+
+ /*
+ * On failure, only cleanup until we found the first mount
+ * we failed to handle.
+ */
+ if (err && m == last)
+ break;
+ } while (kattr->recurse && (m = next_mnt(m, mnt)));
+
+ if (!err)
+ touch_mnt_namespace(mnt->mnt_ns);
+}
+
+static int do_mount_setattr(struct path *path, struct mount_kattr *kattr)
+{
+ struct mount *mnt = real_mount(path->mnt), *last = NULL;
+ int err = 0;
+
+ if (path->dentry != mnt->mnt.mnt_root)
+ return -EINVAL;
+
+ if (kattr->propagation) {
+ /*
+ * Only take namespace_lock() if we're actually changing
+ * propagation.
+ */
+ namespace_lock();
+ if (kattr->propagation == MS_SHARED) {
+ err = invent_group_ids(mnt, kattr->recurse);
+ if (err) {
+ namespace_unlock();
+ return err;
+ }
+ }
+ }
+
+ lock_mount_hash();
+
+ /*
+ * Get the mount tree in a shape where we can change mount
+ * properties without failure.
+ */
+ last = mount_setattr_prepare(kattr, mnt, &err);
+ if (last) /* Commit all changes or revert to the old state. */
+ mount_setattr_commit(kattr, mnt, last, err);
+
+ unlock_mount_hash();
+
+ if (kattr->propagation) {
+ namespace_unlock();
+ if (err)
+ cleanup_group_ids(mnt, NULL);
+ }
+
+ return err;
+}
+
+static int build_mount_idmapped(const struct mount_attr *attr, size_t usize,
+ struct mount_kattr *kattr, unsigned int flags)
+{
+ int err = 0;
+ struct ns_common *ns;
+ struct user_namespace *mnt_userns;
+ struct file *file;
+
+ if (!((attr->attr_set | attr->attr_clr) & MOUNT_ATTR_IDMAP))
+ return 0;
+
+ /*
+ * We currently do not support clearing an idmapped mount. If this ever
+ * is a use-case we can revisit this but for now let's keep it simple
+ * and not allow it.
+ */
+ if (attr->attr_clr & MOUNT_ATTR_IDMAP)
+ return -EINVAL;
+
+ if (attr->userns_fd > INT_MAX)
+ return -EINVAL;
+
+ file = fget(attr->userns_fd);
+ if (!file)
+ return -EBADF;
+
+ if (!proc_ns_file(file)) {
+ err = -EINVAL;
+ goto out_fput;
+ }
+
+ ns = get_proc_ns(file_inode(file));
+ if (ns->ops->type != CLONE_NEWUSER) {
+ err = -EINVAL;
+ goto out_fput;
+ }
+
+ /*
+ * The init_user_ns is used to indicate that a vfsmount is not idmapped.
+ * This is simpler than just having to treat NULL as unmapped. Users
+ * wanting to idmap a mount to init_user_ns can just use a namespace
+ * with an identity mapping.
+ */
+ mnt_userns = container_of(ns, struct user_namespace, ns);
+ if (mnt_userns == &init_user_ns) {
+ err = -EPERM;
+ goto out_fput;
+ }
+ kattr->mnt_userns = get_user_ns(mnt_userns);
+
+out_fput:
+ fput(file);
+ return err;
+}
+
+static int build_mount_kattr(const struct mount_attr *attr, size_t usize,
+ struct mount_kattr *kattr, unsigned int flags)
+{
+ unsigned int lookup_flags = LOOKUP_AUTOMOUNT | LOOKUP_FOLLOW;
+
+ if (flags & AT_NO_AUTOMOUNT)
+ lookup_flags &= ~LOOKUP_AUTOMOUNT;
+ if (flags & AT_SYMLINK_NOFOLLOW)
+ lookup_flags &= ~LOOKUP_FOLLOW;
+ if (flags & AT_EMPTY_PATH)
+ lookup_flags |= LOOKUP_EMPTY;
+
+ *kattr = (struct mount_kattr) {
+ .lookup_flags = lookup_flags,
+ .recurse = !!(flags & AT_RECURSIVE),
+ };
+
+ if (attr->propagation & ~MOUNT_SETATTR_PROPAGATION_FLAGS)
+ return -EINVAL;
+ if (hweight32(attr->propagation & MOUNT_SETATTR_PROPAGATION_FLAGS) > 1)
+ return -EINVAL;
+ kattr->propagation = attr->propagation;
+
+ if ((attr->attr_set | attr->attr_clr) & ~MOUNT_SETATTR_VALID_FLAGS)
+ return -EINVAL;
+
+ kattr->attr_set = attr_flags_to_mnt_flags(attr->attr_set);
+ kattr->attr_clr = attr_flags_to_mnt_flags(attr->attr_clr);
+
+ /*
+ * Since the MOUNT_ATTR_<atime> values are an enum, not a bitmap,
+ * users wanting to transition to a different atime setting cannot
+ * simply specify the atime setting in @attr_set, but must also
+ * specify MOUNT_ATTR__ATIME in the @attr_clr field.
+ * So ensure that MOUNT_ATTR__ATIME can't be partially set in
+ * @attr_clr and that @attr_set can't have any atime bits set if
+ * MOUNT_ATTR__ATIME isn't set in @attr_clr.
+ */
+ if (attr->attr_clr & MOUNT_ATTR__ATIME) {
+ if ((attr->attr_clr & MOUNT_ATTR__ATIME) != MOUNT_ATTR__ATIME)
+ return -EINVAL;
+
+ /*
+ * Clear all previous time settings as they are mutually
+ * exclusive.
+ */
+ kattr->attr_clr |= MNT_RELATIME | MNT_NOATIME;
+ switch (attr->attr_set & MOUNT_ATTR__ATIME) {
+ case MOUNT_ATTR_RELATIME:
+ kattr->attr_set |= MNT_RELATIME;
+ break;
+ case MOUNT_ATTR_NOATIME:
+ kattr->attr_set |= MNT_NOATIME;
+ break;
+ case MOUNT_ATTR_STRICTATIME:
+ break;
+ default:
+ return -EINVAL;
+ }
+ } else {
+ if (attr->attr_set & MOUNT_ATTR__ATIME)
+ return -EINVAL;
+ }
+
+ return build_mount_idmapped(attr, usize, kattr, flags);
+}
+
+static void finish_mount_kattr(struct mount_kattr *kattr)
+{
+ put_user_ns(kattr->mnt_userns);
+ kattr->mnt_userns = NULL;
+}
+
+SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path,
+ unsigned int, flags, struct mount_attr __user *, uattr,
+ size_t, usize)
+{
+ int err;
+ struct path target;
+ struct mount_attr attr;
+ struct mount_kattr kattr;
+
+ BUILD_BUG_ON(sizeof(struct mount_attr) != MOUNT_ATTR_SIZE_VER0);
+
+ if (flags & ~(AT_EMPTY_PATH |
+ AT_RECURSIVE |
+ AT_SYMLINK_NOFOLLOW |
+ AT_NO_AUTOMOUNT))
+ return -EINVAL;
+
+ if (unlikely(usize > PAGE_SIZE))
+ return -E2BIG;
+ if (unlikely(usize < MOUNT_ATTR_SIZE_VER0))
+ return -EINVAL;
+
+ if (!may_mount())
+ return -EPERM;
+
+ err = copy_struct_from_user(&attr, sizeof(attr), uattr, usize);
+ if (err)
+ return err;
+
+ /* Don't bother walking through the mounts if this is a nop. */
+ if (attr.attr_set == 0 &&
+ attr.attr_clr == 0 &&
+ attr.propagation == 0)
+ return 0;
+
+ err = build_mount_kattr(&attr, usize, &kattr, flags);
+ if (err)
+ return err;
+
+ err = user_path_at(dfd, path, kattr.lookup_flags, &target);
+ if (err)
+ return err;
+
+ err = do_mount_setattr(&target, &kattr);
+ finish_mount_kattr(&kattr);
+ path_put(&target);
+ return err;
+}
+
static void __init init_mount_tree(void)
{
struct vfsmount *mnt;
* that the operation succeeded on the server, but an error in the
* reply path made it appear to have failed.
*/
-int nfs_create(struct inode *dir, struct dentry *dentry,
- umode_t mode, bool excl)
+int nfs_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool excl)
{
struct iattr attr;
int open_flags = excl ? O_CREAT | O_EXCL : O_CREAT;
* See comments for nfs_proc_create regarding failed operations.
*/
int
-nfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev)
+nfs_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, dev_t rdev)
{
struct iattr attr;
int status;
/*
* See comments for nfs_proc_create regarding failed operations.
*/
-int nfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+int nfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
struct iattr attr;
int error;
* now have a new file handle and can instantiate an in-core NFS inode
* and move the raw page into its mapping.
*/
-int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
+int nfs_symlink(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, const char *symname)
{
struct page *page;
char *kaddr;
* If these conditions are met, we can drop the dentries before doing
* the rename.
*/
-int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry,
- unsigned int flags)
+int nfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
+ struct dentry *old_dentry, struct inode *new_dir,
+ struct dentry *new_dentry, unsigned int flags)
{
struct inode *old_inode = d_inode(old_dentry);
struct inode *new_inode = d_inode(new_dentry);
return ret;
}
-int nfs_permission(struct inode *inode, int mask)
+int nfs_permission(struct user_namespace *mnt_userns,
+ struct inode *inode,
+ int mask)
{
const struct cred *cred = current_cred();
int res = 0;
res = nfs_revalidate_inode(NFS_SERVER(inode), inode);
if (res == 0)
- res = generic_permission(inode, mask);
+ res = generic_permission(&init_user_ns, inode, mask);
goto out;
}
EXPORT_SYMBOL_GPL(nfs_permission);
#define NFS_VALID_ATTRS (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_SIZE|ATTR_ATIME|ATTR_ATIME_SET|ATTR_MTIME|ATTR_MTIME_SET|ATTR_FILE|ATTR_OPEN)
int
-nfs_setattr(struct dentry *dentry, struct iattr *attr)
+nfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
struct nfs_fattr *fattr;
return false;
}
-int nfs_getattr(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int query_flags)
+int nfs_getattr(struct user_namespace *mnt_userns, const struct path *path,
+ struct kstat *stat, u32 request_mask, unsigned int query_flags)
{
struct inode *inode = d_inode(path->dentry);
struct nfs_server *server = NFS_SERVER(inode);
/* Only return attributes that were revalidated. */
stat->result_mask &= request_mask;
out_no_update:
- generic_fillattr(inode, stat);
+ generic_fillattr(&init_user_ns, inode, stat);
stat->ino = nfs_compat_user_ino64(NFS_FILEID(inode));
if (S_ISDIR(inode->i_mode))
stat->blksize = NFS_SERVER(inode)->dtsize;
extern unsigned long nfs_access_cache_scan(struct shrinker *shrink,
struct shrink_control *sc);
struct dentry *nfs_lookup(struct inode *, struct dentry *, unsigned int);
-int nfs_create(struct inode *, struct dentry *, umode_t, bool);
-int nfs_mkdir(struct inode *, struct dentry *, umode_t);
+int nfs_create(struct user_namespace *, struct inode *, struct dentry *,
+ umode_t, bool);
+int nfs_mkdir(struct user_namespace *, struct inode *, struct dentry *,
+ umode_t);
int nfs_rmdir(struct inode *, struct dentry *);
int nfs_unlink(struct inode *, struct dentry *);
-int nfs_symlink(struct inode *, struct dentry *, const char *);
+int nfs_symlink(struct user_namespace *, struct inode *, struct dentry *,
+ const char *);
int nfs_link(struct dentry *, struct inode *, struct dentry *);
-int nfs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
-int nfs_rename(struct inode *, struct dentry *,
+int nfs_mknod(struct user_namespace *, struct inode *, struct dentry *, umode_t,
+ dev_t);
+int nfs_rename(struct user_namespace *, struct inode *, struct dentry *,
struct inode *, struct dentry *, unsigned int);
/* file.c */
}
static int
-nfs_namespace_getattr(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int query_flags)
+nfs_namespace_getattr(struct user_namespace *mnt_userns,
+ const struct path *path, struct kstat *stat,
+ u32 request_mask, unsigned int query_flags)
{
if (NFS_FH(d_inode(path->dentry))->size != 0)
- return nfs_getattr(path, stat, request_mask, query_flags);
- generic_fillattr(d_inode(path->dentry), stat);
+ return nfs_getattr(mnt_userns, path, stat, request_mask,
+ query_flags);
+ generic_fillattr(&init_user_ns, d_inode(path->dentry), stat);
return 0;
}
static int
-nfs_namespace_setattr(struct dentry *dentry, struct iattr *attr)
+nfs_namespace_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr)
{
if (NFS_FH(d_inode(dentry))->size != 0)
- return nfs_setattr(dentry, attr);
+ return nfs_setattr(mnt_userns, dentry, attr);
return -EACCES;
}
*/
#ifdef CONFIG_NFS_V3_ACL
extern struct posix_acl *nfs3_get_acl(struct inode *inode, int type);
-extern int nfs3_set_acl(struct inode *inode, struct posix_acl *acl, int type);
+extern int nfs3_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
+ struct posix_acl *acl, int type);
extern int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
struct posix_acl *dfacl);
extern ssize_t nfs3_listxattr(struct dentry *, char *, size_t);
}
-int nfs3_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+int nfs3_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
+ struct posix_acl *acl, int type)
{
struct posix_acl *orig = acl, *dfacl = NULL, *alloc;
int status;
#define XATTR_NAME_NFSV4_ACL "system.nfs4_acl"
static int nfs4_xattr_set_nfs4_acl(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *key, const void *buf,
size_t buflen, int flags)
#ifdef CONFIG_NFS_V4_SECURITY_LABEL
static int nfs4_xattr_set_nfs4_label(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *key, const void *buf,
size_t buflen, int flags)
#ifdef CONFIG_NFS_V4_2
static int nfs4_xattr_set_nfs4_user(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *key, const void *buf,
size_t buflen, int flags)
struct svc_export *old);
static struct svc_export *svc_export_lookup(struct svc_export *);
-static int check_export(struct inode *inode, int *flags, unsigned char *uuid)
+static int check_export(struct path *path, int *flags, unsigned char *uuid)
{
+ struct inode *inode = d_inode(path->dentry);
/*
* We currently export only dirs, regular files, and (for v4
* or an FSID number (so NFSEXP_FSID or ->uuid is needed).
* 2: We must be able to find an inode from a filehandle.
* This means that s_export_op must be set.
+ * 3: We must not currently be on an idmapped mount.
*/
if (!(inode->i_sb->s_type->fs_flags & FS_REQUIRES_DEV) &&
!(*flags & NFSEXP_FSID) &&
return -EINVAL;
}
+ if (mnt_user_ns(path->mnt) != &init_user_ns) {
+ dprintk("exp_export: export of idmapped mounts not yet supported.\n");
+ return -EINVAL;
+ }
+
if (inode->i_sb->s_export_op->flags & EXPORT_OP_NOSUBTREECHK &&
!(*flags & NFSEXP_NOSUBTREECHECK)) {
dprintk("%s: %s does not support subtree checking!\n",
goto out4;
}
- err = check_export(d_inode(exp.ex_path.dentry), &exp.ex_flags,
- exp.ex_uuid);
+ err = check_export(&exp.ex_path, &exp.ex_flags, exp.ex_uuid);
if (err)
goto out4;
/*
fh_lock(fh);
- error = set_posix_acl(inode, ACL_TYPE_ACCESS, argp->acl_access);
+ error = set_posix_acl(&init_user_ns, inode, ACL_TYPE_ACCESS,
+ argp->acl_access);
if (error)
goto out_drop_lock;
- error = set_posix_acl(inode, ACL_TYPE_DEFAULT, argp->acl_default);
+ error = set_posix_acl(&init_user_ns, inode, ACL_TYPE_DEFAULT,
+ argp->acl_default);
if (error)
goto out_drop_lock;
fh_lock(fh);
- error = set_posix_acl(inode, ACL_TYPE_ACCESS, argp->acl_access);
+ error = set_posix_acl(&init_user_ns, inode, ACL_TYPE_ACCESS,
+ argp->acl_access);
if (error)
goto out_drop_lock;
- error = set_posix_acl(inode, ACL_TYPE_DEFAULT, argp->acl_default);
+ error = set_posix_acl(&init_user_ns, inode, ACL_TYPE_DEFAULT,
+ argp->acl_default);
out_drop_lock:
fh_unlock(fh);
fh_lock(fhp);
- host_error = set_posix_acl(inode, ACL_TYPE_ACCESS, pacl);
+ host_error = set_posix_acl(&init_user_ns, inode, ACL_TYPE_ACCESS, pacl);
if (host_error < 0)
goto out_drop_lock;
if (S_ISDIR(inode->i_mode)) {
- host_error = set_posix_acl(inode, ACL_TYPE_DEFAULT, dpacl);
+ host_error = set_posix_acl(&init_user_ns, inode,
+ ACL_TYPE_DEFAULT, dpacl);
}
out_drop_lock:
* as well be forgiving and just succeed silently.
*/
goto out_put;
- status = vfs_mkdir(d_inode(dir), dentry, S_IRWXU);
+ status = vfs_mkdir(&init_user_ns, d_inode(dir), dentry, S_IRWXU);
out_put:
dput(dentry);
out_unlock:
status = -ENOENT;
if (d_really_is_negative(dentry))
goto out;
- status = vfs_rmdir(d_inode(dir), dentry);
+ status = vfs_rmdir(&init_user_ns, d_inode(dir), dentry);
out:
dput(dentry);
out_unlock:
if (nfs4_has_reclaimed_state(name, nn))
goto out_free;
- status = vfs_rmdir(d_inode(parent), child);
+ status = vfs_rmdir(&init_user_ns, d_inode(parent), child);
if (status)
printk("failed to remove client recovery directory %pd\n",
child);
/* make sure parents give x permission to user */
int err;
parent = dget_parent(tdentry);
- err = inode_permission(d_inode(parent), MAY_EXEC);
+ err = inode_permission(&init_user_ns,
+ d_inode(parent), MAY_EXEC);
if (err < 0) {
dput(parent);
break;
if (delta < 0)
delta = -delta;
if (delta < MAX_TOUCH_TIME_ERROR &&
- setattr_prepare(fhp->fh_dentry, iap) != 0) {
+ setattr_prepare(&init_user_ns, fhp->fh_dentry, iap) != 0) {
/*
* Turn off ATTR_[AM]TIME_SET but leave ATTR_[AM]TIME.
* This will cause notify_change to set these times
.ia_size = iap->ia_size,
};
- host_err = notify_change(dentry, &size_attr, NULL);
+ host_err = notify_change(&init_user_ns, dentry, &size_attr, NULL);
if (host_err)
goto out_unlock;
iap->ia_valid &= ~ATTR_SIZE;
}
iap->ia_valid |= ATTR_CTIME;
- host_err = notify_change(dentry, iap, NULL);
+ host_err = notify_change(&init_user_ns, dentry, iap, NULL);
out_unlock:
fh_unlock(fhp);
return 0;
if (!(inode->i_mode & S_ISVTX))
return 0;
- if (vfs_getxattr(dentry, NFSD_JUNCTION_XATTR_NAME, NULL, 0) <= 0)
+ if (vfs_getxattr(&init_user_ns, dentry, NFSD_JUNCTION_XATTR_NAME,
+ NULL, 0) <= 0)
return 0;
return 1;
}
host_err = 0;
switch (type) {
case S_IFREG:
- host_err = vfs_create(dirp, dchild, iap->ia_mode, true);
+ host_err = vfs_create(&init_user_ns, dirp, dchild, iap->ia_mode, true);
if (!host_err)
nfsd_check_ignore_resizing(iap);
break;
case S_IFDIR:
- host_err = vfs_mkdir(dirp, dchild, iap->ia_mode);
+ host_err = vfs_mkdir(&init_user_ns, dirp, dchild, iap->ia_mode);
if (!host_err && unlikely(d_unhashed(dchild))) {
struct dentry *d;
d = lookup_one_len(dchild->d_name.name,
case S_IFBLK:
case S_IFIFO:
case S_IFSOCK:
- host_err = vfs_mknod(dirp, dchild, iap->ia_mode, rdev);
+ host_err = vfs_mknod(&init_user_ns, dirp, dchild,
+ iap->ia_mode, rdev);
break;
default:
printk(KERN_WARNING "nfsd: bad file type %o in nfsd_create\n",
if (!IS_POSIXACL(dirp))
iap->ia_mode &= ~current_umask();
- host_err = vfs_create(dirp, dchild, iap->ia_mode, true);
+ host_err = vfs_create(&init_user_ns, dirp, dchild, iap->ia_mode, true);
if (host_err < 0) {
fh_drop_write(fhp);
goto out_nfserr;
if (IS_ERR(dnew))
goto out_nfserr;
- host_err = vfs_symlink(d_inode(dentry), dnew, path);
+ host_err = vfs_symlink(&init_user_ns, d_inode(dentry), dnew, path);
err = nfserrno(host_err);
if (!err)
err = nfserrno(commit_metadata(fhp));
err = nfserr_noent;
if (d_really_is_negative(dold))
goto out_dput;
- host_err = vfs_link(dold, dirp, dnew, NULL);
+ host_err = vfs_link(dold, &init_user_ns, dirp, dnew, NULL);
if (!host_err) {
err = nfserrno(commit_metadata(ffhp));
if (!err)
close_cached = true;
goto out_dput_old;
} else {
- host_err = vfs_rename(fdir, odentry, tdir, ndentry, NULL, 0);
+ struct renamedata rd = {
+ .old_mnt_userns = &init_user_ns,
+ .old_dir = fdir,
+ .old_dentry = odentry,
+ .new_mnt_userns = &init_user_ns,
+ .new_dir = tdir,
+ .new_dentry = ndentry,
+ };
+ host_err = vfs_rename(&rd);
if (!host_err) {
host_err = commit_metadata(tfhp);
if (!host_err)
if (type != S_IFDIR) {
if (rdentry->d_sb->s_export_op->flags & EXPORT_OP_CLOSE_BEFORE_UNLINK)
nfsd_close_cached_files(rdentry);
- host_err = vfs_unlink(dirp, rdentry, NULL);
+ host_err = vfs_unlink(&init_user_ns, dirp, rdentry, NULL);
} else {
- host_err = vfs_rmdir(dirp, rdentry);
+ host_err = vfs_rmdir(&init_user_ns, dirp, rdentry);
}
if (!host_err)
inode_lock_shared(inode);
- len = vfs_getxattr(dentry, name, NULL, 0);
+ len = vfs_getxattr(&init_user_ns, dentry, name, NULL, 0);
/*
* Zero-length attribute, just return.
goto out;
}
- len = vfs_getxattr(dentry, name, buf, len);
+ len = vfs_getxattr(&init_user_ns, dentry, name, buf, len);
if (len <= 0) {
kvfree(buf);
buf = NULL;
fh_lock(fhp);
- ret = __vfs_removexattr_locked(fhp->fh_dentry, name, NULL);
+ ret = __vfs_removexattr_locked(&init_user_ns, fhp->fh_dentry,
+ name, NULL);
fh_unlock(fhp);
fh_drop_write(fhp);
return nfserrno(ret);
fh_lock(fhp);
- ret = __vfs_setxattr_locked(fhp->fh_dentry, name, buf, len, flags,
- NULL);
+ ret = __vfs_setxattr_locked(&init_user_ns, fhp->fh_dentry, name, buf,
+ len, flags, NULL);
fh_unlock(fhp);
fh_drop_write(fhp);
return 0;
/* This assumes NFSD_MAY_{READ,WRITE,EXEC} == MAY_{READ,WRITE,EXEC} */
- err = inode_permission(inode, acc & (MAY_READ|MAY_WRITE|MAY_EXEC));
+ err = inode_permission(&init_user_ns, inode,
+ acc & (MAY_READ | MAY_WRITE | MAY_EXEC));
/* Allow read access to binaries even when mode 111 */
if (err == -EACCES && S_ISREG(inode->i_mode) &&
(acc == (NFSD_MAY_READ | NFSD_MAY_OWNER_OVERRIDE) ||
acc == (NFSD_MAY_READ | NFSD_MAY_READ_IF_EXEC)))
- err = inode_permission(inode, MAY_EXEC);
+ err = inode_permission(&init_user_ns, inode, MAY_EXEC);
return err? nfserrno(err) : 0;
}
/* reference count of i_bh inherits from nilfs_mdt_read_block() */
atomic64_inc(&root->inodes_count);
- inode_init_owner(inode, dir, mode);
+ inode_init_owner(&init_user_ns, inode, dir, mode);
inode->i_ino = ino;
inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
*/
}
-int nilfs_setattr(struct dentry *dentry, struct iattr *iattr)
+int nilfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *iattr)
{
struct nilfs_transaction_info ti;
struct inode *inode = d_inode(dentry);
struct super_block *sb = inode->i_sb;
int err;
- err = setattr_prepare(dentry, iattr);
+ err = setattr_prepare(&init_user_ns, dentry, iattr);
if (err)
return err;
nilfs_truncate(inode);
}
- setattr_copy(inode, iattr);
+ setattr_copy(&init_user_ns, inode, iattr);
mark_inode_dirty(inode);
if (iattr->ia_valid & ATTR_MODE) {
return err;
}
-int nilfs_permission(struct inode *inode, int mask)
+int nilfs_permission(struct user_namespace *mnt_userns, struct inode *inode,
+ int mask)
{
struct nilfs_root *root = NILFS_I(inode)->i_root;
root->cno != NILFS_CPTREE_CURRENT_CNO)
return -EROFS; /* snapshot is not writable */
- return generic_permission(inode, mask);
+ return generic_permission(&init_user_ns, inode, mask);
}
int nilfs_load_inode_block(struct inode *inode, struct buffer_head **pbh)
unsigned int flags, oldflags;
int ret;
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(&init_user_ns, inode))
return -EACCES;
if (get_user(flags, (int __user *)argp))
* If the create succeeds, we fill in the inode information
* with d_instantiate().
*/
-static int nilfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- bool excl)
+static int nilfs_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool excl)
{
struct inode *inode;
struct nilfs_transaction_info ti;
}
static int
-nilfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev)
+nilfs_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, dev_t rdev)
{
struct inode *inode;
struct nilfs_transaction_info ti;
return err;
}
-static int nilfs_symlink(struct inode *dir, struct dentry *dentry,
- const char *symname)
+static int nilfs_symlink(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, const char *symname)
{
struct nilfs_transaction_info ti;
struct super_block *sb = dir->i_sb;
return err;
}
-static int nilfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int nilfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
struct inode *inode;
struct nilfs_transaction_info ti;
return err;
}
-static int nilfs_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry,
+static int nilfs_rename(struct user_namespace *mnt_userns,
+ struct inode *old_dir, struct dentry *old_dentry,
+ struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
struct inode *old_inode = d_inode(old_dentry);
extern void nilfs_update_inode(struct inode *, struct buffer_head *, int);
extern void nilfs_truncate(struct inode *);
extern void nilfs_evict_inode(struct inode *);
-extern int nilfs_setattr(struct dentry *, struct iattr *);
+extern int nilfs_setattr(struct user_namespace *, struct dentry *,
+ struct iattr *);
extern void nilfs_write_failed(struct address_space *mapping, loff_t to);
-int nilfs_permission(struct inode *inode, int mask);
+int nilfs_permission(struct user_namespace *mnt_userns, struct inode *inode,
+ int mask);
int nilfs_load_inode_block(struct inode *inode, struct buffer_head **pbh);
extern int nilfs_inode_dirty(struct inode *);
int nilfs_set_file_dirty(struct inode *inode, unsigned int nr_dirty);
}
/* you can only watch an inode if you have read permissions on it */
- ret = inode_permission(path->dentry->d_inode, MAY_READ);
+ ret = path_permission(path, MAY_READ);
if (ret) {
path_put(path);
goto out;
if (error)
return error;
/* you can only watch an inode if you have read permissions on it */
- error = inode_permission(path->dentry->d_inode, MAY_READ);
+ error = path_permission(path, MAY_READ);
if (error) {
path_put(path);
return error;
/**
* ntfs_setattr - called from notify_change() when an attribute is being changed
+ * @mnt_userns: user namespace of the mount the inode was found from
* @dentry: dentry whose attributes to change
* @attr: structure describing the attributes and the changes
*
*
* Called with ->i_mutex held.
*/
-int ntfs_setattr(struct dentry *dentry, struct iattr *attr)
+int ntfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr)
{
struct inode *vi = d_inode(dentry);
int err;
unsigned int ia_valid = attr->ia_valid;
- err = setattr_prepare(dentry, attr);
+ err = setattr_prepare(&init_user_ns, dentry, attr);
if (err)
goto out;
/* We do not support NTFS ACLs yet. */
extern int ntfs_truncate(struct inode *vi);
extern void ntfs_truncate_vfs(struct inode *vi);
-extern int ntfs_setattr(struct dentry *dentry, struct iattr *attr);
+extern int ntfs_setattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct iattr *attr);
extern int __ntfs_write_inode(struct inode *vi, int sync);
return ret;
}
-int ocfs2_iop_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+int ocfs2_iop_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
+ struct posix_acl *acl, int type)
{
struct buffer_head *bh = NULL;
int status, had_lock;
if (type == ACL_TYPE_ACCESS && acl) {
umode_t mode;
- status = posix_acl_update_mode(inode, &mode, &acl);
+ status = posix_acl_update_mode(&init_user_ns, inode, &mode,
+ &acl);
if (status)
goto unlock;
};
struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type);
-int ocfs2_iop_set_acl(struct inode *inode, struct posix_acl *acl, int type);
+int ocfs2_iop_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
+ struct posix_acl *acl, int type);
extern int ocfs2_acl_chmod(struct inode *, struct buffer_head *);
extern int ocfs2_init_acl(handle_t *, struct inode *, struct inode *,
struct buffer_head *, struct buffer_head *,
* We do ->setattr() just to override size changes. Our size is the size
* of the LVB and nothing else.
*/
-static int dlmfs_file_setattr(struct dentry *dentry, struct iattr *attr)
+static int dlmfs_file_setattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct iattr *attr)
{
int error;
struct inode *inode = d_inode(dentry);
attr->ia_valid &= ~ATTR_SIZE;
- error = setattr_prepare(dentry, attr);
+ error = setattr_prepare(&init_user_ns, dentry, attr);
if (error)
return error;
- setattr_copy(inode, attr);
+ setattr_copy(&init_user_ns, inode, attr);
mark_inode_dirty(inode);
return 0;
}
if (inode) {
inode->i_ino = get_next_ino();
- inode_init_owner(inode, NULL, mode);
+ inode_init_owner(&init_user_ns, inode, NULL, mode);
inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
inc_nlink(inode);
return NULL;
inode->i_ino = get_next_ino();
- inode_init_owner(inode, parent, mode);
+ inode_init_owner(&init_user_ns, inode, parent, mode);
inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
ip = DLMFS_I(inode);
* File creation. Allocate an inode, and we're done..
*/
/* SMP-safe */
-static int dlmfs_mkdir(struct inode * dir,
+static int dlmfs_mkdir(struct user_namespace * mnt_userns,
+ struct inode * dir,
struct dentry * dentry,
umode_t mode)
{
return status;
}
-static int dlmfs_create(struct inode *dir,
+static int dlmfs_create(struct user_namespace *mnt_userns,
+ struct inode *dir,
struct dentry *dentry,
umode_t mode,
bool excl)
return ret;
}
-int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
+int ocfs2_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr)
{
int status = 0, size_change;
int inode_locked = 0;
if (!(attr->ia_valid & OCFS2_VALID_ATTRS))
return 0;
- status = setattr_prepare(dentry, attr);
+ status = setattr_prepare(&init_user_ns, dentry, attr);
if (status)
return status;
}
}
- setattr_copy(inode, attr);
+ setattr_copy(&init_user_ns, inode, attr);
mark_inode_dirty(inode);
status = ocfs2_mark_inode_dirty(handle, inode, bh);
return status;
}
-int ocfs2_getattr(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int flags)
+int ocfs2_getattr(struct user_namespace *mnt_userns, const struct path *path,
+ struct kstat *stat, u32 request_mask, unsigned int flags)
{
struct inode *inode = d_inode(path->dentry);
struct super_block *sb = path->dentry->d_sb;
goto bail;
}
- generic_fillattr(inode, stat);
+ generic_fillattr(&init_user_ns, inode, stat);
/*
* If there is inline data in the inode, the inode will normally not
* have data blocks allocated (it may have an external xattr block).
return err;
}
-int ocfs2_permission(struct inode *inode, int mask)
+int ocfs2_permission(struct user_namespace *mnt_userns, struct inode *inode,
+ int mask)
{
int ret, had_lock;
struct ocfs2_lock_holder oh;
dump_stack();
}
- ret = generic_permission(inode, mask);
+ ret = generic_permission(&init_user_ns, inode, mask);
ocfs2_inode_unlock_tracker(inode, 0, &oh, had_lock);
out:
u64 new_i_size, u64 zero_to);
int ocfs2_zero_extend(struct inode *inode, struct buffer_head *di_bh,
loff_t zero_to);
-int ocfs2_setattr(struct dentry *dentry, struct iattr *attr);
-int ocfs2_getattr(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int flags);
-int ocfs2_permission(struct inode *inode, int mask);
+int ocfs2_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr);
+int ocfs2_getattr(struct user_namespace *mnt_userns, const struct path *path,
+ struct kstat *stat, u32 request_mask, unsigned int flags);
+int ocfs2_permission(struct user_namespace *mnt_userns,
+ struct inode *inode,
+ int mask);
int ocfs2_should_update_atime(struct inode *inode,
struct vfsmount *vfsmnt);
}
status = -EACCES;
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(&init_user_ns, inode))
goto bail_unlock;
if (!S_ISDIR(inode->i_mode))
* callers. */
if (S_ISDIR(mode))
set_nlink(inode, 2);
- inode_init_owner(inode, dir, mode);
+ inode_init_owner(&init_user_ns, inode, dir, mode);
status = dquot_initialize(inode);
if (status)
return ERR_PTR(status);
iput(inode);
}
-static int ocfs2_mknod(struct inode *dir,
+static int ocfs2_mknod(struct user_namespace *mnt_userns,
+ struct inode *dir,
struct dentry *dentry,
umode_t mode,
dev_t dev)
return status;
}
-static int ocfs2_mkdir(struct inode *dir,
+static int ocfs2_mkdir(struct user_namespace *mnt_userns,
+ struct inode *dir,
struct dentry *dentry,
umode_t mode)
{
trace_ocfs2_mkdir(dir, dentry, dentry->d_name.len, dentry->d_name.name,
OCFS2_I(dir)->ip_blkno, mode);
- ret = ocfs2_mknod(dir, dentry, mode | S_IFDIR, 0);
+ ret = ocfs2_mknod(&init_user_ns, dir, dentry, mode | S_IFDIR, 0);
if (ret)
mlog_errno(ret);
return ret;
}
-static int ocfs2_create(struct inode *dir,
+static int ocfs2_create(struct user_namespace *mnt_userns,
+ struct inode *dir,
struct dentry *dentry,
umode_t mode,
bool excl)
trace_ocfs2_create(dir, dentry, dentry->d_name.len, dentry->d_name.name,
(unsigned long long)OCFS2_I(dir)->ip_blkno, mode);
- ret = ocfs2_mknod(dir, dentry, mode | S_IFREG, 0);
+ ret = ocfs2_mknod(&init_user_ns, dir, dentry, mode | S_IFREG, 0);
if (ret)
mlog_errno(ret);
ocfs2_inode_unlock(inode2, 1);
}
-static int ocfs2_rename(struct inode *old_dir,
+static int ocfs2_rename(struct user_namespace *mnt_userns,
+ struct inode *old_dir,
struct dentry *old_dentry,
struct inode *new_dir,
struct dentry *new_dentry,
return status;
}
-static int ocfs2_symlink(struct inode *dir,
+static int ocfs2_symlink(struct user_namespace *mnt_userns,
+ struct inode *dir,
struct dentry *dentry,
const char *symname)
{
return -EEXIST;
if (IS_DEADDIR(dir))
return -ENOENT;
- return inode_permission(dir, MAY_WRITE | MAY_EXEC);
+ return inode_permission(&init_user_ns, dir, MAY_WRITE | MAY_EXEC);
}
/**
* file.
*/
if (!preserve) {
- error = inode_permission(inode, MAY_READ);
+ error = inode_permission(&init_user_ns, inode, MAY_READ);
if (error)
return error;
}
}
static int ocfs2_xattr_security_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
}
static int ocfs2_xattr_trusted_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
}
static int ocfs2_xattr_user_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
return err;
}
-static int omfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int omfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
return omfs_add_node(dir, dentry, mode | S_IFDIR);
}
-static int omfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- bool excl)
+static int omfs_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool excl)
{
return omfs_add_node(dir, dentry, mode | S_IFREG);
}
return true;
}
-static int omfs_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry,
- unsigned int flags)
+static int omfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
+ struct dentry *old_dentry, struct inode *new_dir,
+ struct dentry *new_dentry, unsigned int flags)
{
struct inode *new_inode = d_inode(new_dentry);
struct inode *old_inode = d_inode(old_dentry);
.splice_read = generic_file_splice_read,
};
-static int omfs_setattr(struct dentry *dentry, struct iattr *attr)
+static int omfs_setattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
int error;
- error = setattr_prepare(dentry, attr);
+ error = setattr_prepare(&init_user_ns, dentry, attr);
if (error)
return error;
omfs_truncate(inode);
}
- setattr_copy(inode, attr);
+ setattr_copy(&init_user_ns, inode, attr);
mark_inode_dirty(inode);
return 0;
}
goto fail;
inode->i_ino = new_block;
- inode_init_owner(inode, NULL, mode);
+ inode_init_owner(&init_user_ns, inode, NULL, mode);
inode->i_mapping->a_ops = &omfs_aops;
inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
#include "internal.h"
-int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs,
- struct file *filp)
+int do_truncate(struct user_namespace *mnt_userns, struct dentry *dentry,
+ loff_t length, unsigned int time_attrs, struct file *filp)
{
int ret;
struct iattr newattrs;
inode_lock(dentry->d_inode);
/* Note any delegations or leases have already been broken: */
- ret = notify_change(dentry, &newattrs, NULL);
+ ret = notify_change(mnt_userns, dentry, &newattrs, NULL);
inode_unlock(dentry->d_inode);
return ret;
}
long vfs_truncate(const struct path *path, loff_t length)
{
+ struct user_namespace *mnt_userns;
struct inode *inode;
long error;
if (error)
goto out;
- error = inode_permission(inode, MAY_WRITE);
+ mnt_userns = mnt_user_ns(path->mnt);
+ error = inode_permission(mnt_userns, inode, MAY_WRITE);
if (error)
goto mnt_drop_write_and_out;
if (!error)
error = security_path_truncate(path);
if (!error)
- error = do_truncate(path->dentry, length, 0, NULL);
+ error = do_truncate(mnt_userns, path->dentry, length, 0, NULL);
put_write_and_out:
put_write_access(inode);
/* Check IS_APPEND on real upper inode */
if (IS_APPEND(file_inode(f.file)))
goto out_putf;
-
sb_start_write(inode->i_sb);
error = locks_verify_truncate(inode, f.file, length);
if (!error)
error = security_path_truncate(&f.file->f_path);
if (!error)
- error = do_truncate(dentry, length, ATTR_MTIME|ATTR_CTIME, f.file);
+ error = do_truncate(file_mnt_user_ns(f.file), dentry, length,
+ ATTR_MTIME | ATTR_CTIME, f.file);
sb_end_write(inode->i_sb);
out_putf:
fdput(f);
goto out_path_release;
}
- res = inode_permission(inode, mode | MAY_ACCESS);
+ res = inode_permission(mnt_user_ns(path.mnt), inode, mode | MAY_ACCESS);
/* SuS v2 requires we report a read only fs too */
if (res || !(mode & S_IWOTH) || special_file(inode->i_mode))
goto out_path_release;
if (error)
goto out;
- error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_CHDIR);
+ error = path_permission(&path, MAY_EXEC | MAY_CHDIR);
if (error)
goto dput_and_out;
if (!d_can_lookup(f.file->f_path.dentry))
goto out_putf;
- error = inode_permission(file_inode(f.file), MAY_EXEC | MAY_CHDIR);
+ error = file_permission(f.file, MAY_EXEC | MAY_CHDIR);
if (!error)
set_fs_pwd(current->fs, &f.file->f_path);
out_putf:
if (error)
goto out;
- error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_CHDIR);
+ error = path_permission(&path, MAY_EXEC | MAY_CHDIR);
if (error)
goto dput_and_out;
goto out_unlock;
newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO);
newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
- error = notify_change(path->dentry, &newattrs, &delegated_inode);
+ error = notify_change(mnt_user_ns(path->mnt), path->dentry,
+ &newattrs, &delegated_inode);
out_unlock:
inode_unlock(inode);
if (delegated_inode) {
int chown_common(const struct path *path, uid_t user, gid_t group)
{
+ struct user_namespace *mnt_userns;
struct inode *inode = path->dentry->d_inode;
struct inode *delegated_inode = NULL;
int error;
uid = make_kuid(current_user_ns(), user);
gid = make_kgid(current_user_ns(), group);
+ mnt_userns = mnt_user_ns(path->mnt);
+ uid = kuid_from_mnt(mnt_userns, uid);
+ gid = kgid_from_mnt(mnt_userns, gid);
+
retry_deleg:
newattrs.ia_valid = ATTR_CTIME;
if (user != (uid_t) -1) {
inode_lock(inode);
error = security_path_chown(path, uid, gid);
if (!error)
- error = notify_change(path->dentry, &newattrs, &delegated_inode);
+ error = notify_change(mnt_userns, path->dentry, &newattrs,
+ &delegated_inode);
inode_unlock(inode);
if (delegated_inode) {
error = break_deleg_wait(&delegated_inode);
return error;
}
-int orangefs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+int orangefs_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
+ struct posix_acl *acl, int type)
{
int error;
struct iattr iattr;
* and "mode" to the new desired value. It is up to
* us to propagate the new mode back to the server...
*/
- error = posix_acl_update_mode(inode, &iattr.ia_mode, &acl);
+ error = posix_acl_update_mode(&init_user_ns, inode,
+ &iattr.ia_mode, &acl);
if (error) {
gossip_err("%s: posix_acl_update_mode err: %d\n",
__func__,
ORANGEFS_I(inode)->attr_uid = current_fsuid();
ORANGEFS_I(inode)->attr_gid = current_fsgid();
}
- setattr_copy(inode, iattr);
+ setattr_copy(&init_user_ns, inode, iattr);
spin_unlock(&inode->i_lock);
mark_inode_dirty(inode);
if (iattr->ia_valid & ATTR_MODE)
/* change mod on a file that has ACLs */
- ret = posix_acl_chmod(inode, inode->i_mode);
+ ret = posix_acl_chmod(&init_user_ns, inode, inode->i_mode);
ret = 0;
out:
/*
* Change attributes of an object referenced by dentry.
*/
-int orangefs_setattr(struct dentry *dentry, struct iattr *iattr)
+int orangefs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *iattr)
{
int ret;
gossip_debug(GOSSIP_INODE_DEBUG, "__orangefs_setattr: called on %pd\n",
dentry);
- ret = setattr_prepare(dentry, iattr);
+ ret = setattr_prepare(&init_user_ns, dentry, iattr);
if (ret)
goto out;
ret = __orangefs_setattr(d_inode(dentry), iattr);
/*
* Obtain attributes of an object given a dentry
*/
-int orangefs_getattr(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int flags)
+int orangefs_getattr(struct user_namespace *mnt_userns, const struct path *path,
+ struct kstat *stat, u32 request_mask, unsigned int flags)
{
int ret;
struct inode *inode = path->dentry->d_inode;
ret = orangefs_inode_getattr(inode,
request_mask & STATX_SIZE ? ORANGEFS_GETATTR_SIZE : 0);
if (ret == 0) {
- generic_fillattr(inode, stat);
+ generic_fillattr(&init_user_ns, inode, stat);
/* override block size reported to stat */
if (!(request_mask & STATX_SIZE))
return ret;
}
-int orangefs_permission(struct inode *inode, int mask)
+int orangefs_permission(struct user_namespace *mnt_userns,
+ struct inode *inode, int mask)
{
int ret;
if (ret < 0)
return ret;
- return generic_permission(inode, mask);
+ return generic_permission(&init_user_ns, inode, mask);
}
int orangefs_update_time(struct inode *inode, struct timespec64 *time, int flags)
/*
* Get a newly allocated inode to go with a negative dentry.
*/
-static int orangefs_create(struct inode *dir,
+static int orangefs_create(struct user_namespace *mnt_userns,
+ struct inode *dir,
struct dentry *dentry,
umode_t mode,
bool exclusive)
return ret;
}
-static int orangefs_symlink(struct inode *dir,
+static int orangefs_symlink(struct user_namespace *mnt_userns,
+ struct inode *dir,
struct dentry *dentry,
const char *symname)
{
return ret;
}
-static int orangefs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int orangefs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
struct orangefs_inode_s *parent = ORANGEFS_I(dir);
struct orangefs_kernel_op_s *new_op;
return ret;
}
-static int orangefs_rename(struct inode *old_dir,
+static int orangefs_rename(struct user_namespace *mnt_userns,
+ struct inode *old_dir,
struct dentry *old_dentry,
struct inode *new_dir,
struct dentry *new_dentry,
extern const struct xattr_handler *orangefs_xattr_handlers[];
extern struct posix_acl *orangefs_get_acl(struct inode *inode, int type);
-extern int orangefs_set_acl(struct inode *inode, struct posix_acl *acl, int type);
+extern int orangefs_set_acl(struct user_namespace *mnt_userns,
+ struct inode *inode, struct posix_acl *acl,
+ int type);
/*
* orangefs data structures
struct orangefs_object_kref *ref);
int __orangefs_setattr(struct inode *, struct iattr *);
-int orangefs_setattr(struct dentry *, struct iattr *);
+int orangefs_setattr(struct user_namespace *, struct dentry *, struct iattr *);
-int orangefs_getattr(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int flags);
+int orangefs_getattr(struct user_namespace *mnt_userns, const struct path *path,
+ struct kstat *stat, u32 request_mask, unsigned int flags);
-int orangefs_permission(struct inode *inode, int mask);
+int orangefs_permission(struct user_namespace *mnt_userns,
+ struct inode *inode, int mask);
int orangefs_update_time(struct inode *, struct timespec64 *, int);
}
static int orangefs_xattr_set_default(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused,
struct inode *inode,
const char *name,
continue; /* Discard */
}
retry:
- size = vfs_getxattr(old, name, value, value_size);
+ size = vfs_getxattr(&init_user_ns, old, name, value, value_size);
if (size == -ERANGE)
- size = vfs_getxattr(old, name, NULL, 0);
+ size = vfs_getxattr(&init_user_ns, old, name, NULL, 0);
if (size < 0) {
error = size;
goto retry;
}
- error = vfs_setxattr(new, name, value, size, 0);
+ error = vfs_setxattr(&init_user_ns, new, name, value, size, 0);
if (error) {
if (error != -EOPNOTSUPP || ovl_must_copy_xattr(name))
break;
.ia_size = stat->size,
};
- return notify_change(upperdentry, &attr, NULL);
+ return notify_change(&init_user_ns, upperdentry, &attr, NULL);
}
static int ovl_set_timestamps(struct dentry *upperdentry, struct kstat *stat)
.ia_mtime = stat->mtime,
};
- return notify_change(upperdentry, &attr, NULL);
+ return notify_change(&init_user_ns, upperdentry, &attr, NULL);
}
int ovl_set_attr(struct dentry *upperdentry, struct kstat *stat)
.ia_valid = ATTR_MODE,
.ia_mode = stat->mode,
};
- err = notify_change(upperdentry, &attr, NULL);
+ err = notify_change(&init_user_ns, upperdentry, &attr, NULL);
}
if (!err) {
struct iattr attr = {
.ia_uid = stat->uid,
.ia_gid = stat->gid,
};
- err = notify_change(upperdentry, &attr, NULL);
+ err = notify_change(&init_user_ns, upperdentry, &attr, NULL);
}
if (!err)
ovl_set_timestamps(upperdentry, stat);
ssize_t res;
char *buf;
- res = vfs_getxattr(dentry, name, NULL, 0);
+ res = vfs_getxattr(&init_user_ns, dentry, name, NULL, 0);
if (res == -ENODATA || res == -EOPNOTSUPP)
res = 0;
if (!buf)
return -ENOMEM;
- res = vfs_getxattr(dentry, name, buf, res);
+ res = vfs_getxattr(&init_user_ns, dentry, name, buf, res);
if (res < 0)
kfree(buf);
else
* don't want that to happen for normal copy-up operation.
*/
if (capability) {
- err = vfs_setxattr(upperpath.dentry, XATTR_NAME_CAPS,
- capability, cap_size, 0);
+ err = vfs_setxattr(&init_user_ns, upperpath.dentry,
+ XATTR_NAME_CAPS, capability, cap_size, 0);
if (err)
goto out_free;
}
if (err < 0)
goto out_free;
- err = vfs_setxattr(upperdentry, name, buffer, size, XATTR_CREATE);
+ err = vfs_setxattr(&init_user_ns, upperdentry, name, buffer, size, XATTR_CREATE);
out_free:
kfree(buffer);
return err;
.ia_mode = cattr->mode,
};
inode_lock(newdentry->d_inode);
- err = notify_change(newdentry, &attr, NULL);
+ err = notify_change(&init_user_ns, newdentry, &attr, NULL);
inode_unlock(newdentry->d_inode);
if (err)
goto out_cleanup;
inode->i_state |= I_CREATING;
spin_unlock(&inode->i_lock);
- inode_init_owner(inode, dentry->d_parent->d_inode, mode);
+ inode_init_owner(&init_user_ns, inode, dentry->d_parent->d_inode, mode);
attr.mode = inode->i_mode;
err = ovl_create_or_link(dentry, inode, &attr, false);
return err;
}
-static int ovl_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- bool excl)
+static int ovl_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool excl)
{
return ovl_create_object(dentry, (mode & 07777) | S_IFREG, 0, NULL);
}
-static int ovl_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int ovl_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
return ovl_create_object(dentry, (mode & 07777) | S_IFDIR, 0, NULL);
}
-static int ovl_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
- dev_t rdev)
+static int ovl_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, dev_t rdev)
{
/* Don't allow creation of "whiteout" on overlay */
if (S_ISCHR(mode) && rdev == WHITEOUT_DEV)
return ovl_create_object(dentry, mode, rdev, NULL);
}
-static int ovl_symlink(struct inode *dir, struct dentry *dentry,
- const char *link)
+static int ovl_symlink(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, const char *link)
{
return ovl_create_object(dentry, S_IFLNK, 0, link);
}
goto out_dput_upper;
if (is_dir)
- err = vfs_rmdir(dir, upper);
+ err = vfs_rmdir(&init_user_ns, dir, upper);
else
- err = vfs_unlink(dir, upper, NULL);
+ err = vfs_unlink(&init_user_ns, dir, upper, NULL);
ovl_dir_modified(dentry->d_parent, ovl_type_origin(dentry));
/*
return err;
}
-static int ovl_rename(struct inode *olddir, struct dentry *old,
- struct inode *newdir, struct dentry *new,
- unsigned int flags)
+static int ovl_rename(struct user_namespace *mnt_userns, struct inode *olddir,
+ struct dentry *old, struct inode *newdir,
+ struct dentry *new, unsigned int flags)
{
int err;
struct dentry *old_upperdir;
acc_mode |= MAY_APPEND;
old_cred = ovl_override_creds(inode->i_sb);
- err = inode_permission(realinode, MAY_OPEN | acc_mode);
+ err = inode_permission(&init_user_ns, realinode, MAY_OPEN | acc_mode);
if (err) {
realfile = ERR_PTR(err);
} else {
- if (!inode_owner_or_capable(realinode))
+ if (!inode_owner_or_capable(&init_user_ns, realinode))
flags &= ~O_NOATIME;
realfile = open_with_fake_path(&file->f_path, flags, realinode,
long ret;
struct inode *inode = file_inode(file);
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(&init_user_ns, inode))
return -EACCES;
ret = mnt_want_write_file(file);
#include "overlayfs.h"
-int ovl_setattr(struct dentry *dentry, struct iattr *attr)
+int ovl_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr)
{
int err;
bool full_copy_up = false;
struct dentry *upperdentry;
const struct cred *old_cred;
- err = setattr_prepare(dentry, attr);
+ err = setattr_prepare(&init_user_ns, dentry, attr);
if (err)
return err;
inode_lock(upperdentry->d_inode);
old_cred = ovl_override_creds(dentry->d_sb);
- err = notify_change(upperdentry, attr, NULL);
+ err = notify_change(&init_user_ns, upperdentry, attr, NULL);
revert_creds(old_cred);
if (!err)
ovl_copyattr(upperdentry->d_inode, dentry->d_inode);
return 0;
}
-int ovl_getattr(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int flags)
+int ovl_getattr(struct user_namespace *mnt_userns, const struct path *path,
+ struct kstat *stat, u32 request_mask, unsigned int flags)
{
struct dentry *dentry = path->dentry;
enum ovl_path_type type;
return err;
}
-int ovl_permission(struct inode *inode, int mask)
+int ovl_permission(struct user_namespace *mnt_userns,
+ struct inode *inode, int mask)
{
struct inode *upperinode = ovl_inode_upper(inode);
struct inode *realinode = upperinode ?: ovl_inode_lower(inode);
* Check overlay inode with the creds of task and underlying inode
* with creds of mounter
*/
- err = generic_permission(inode, mask);
+ err = generic_permission(&init_user_ns, inode, mask);
if (err)
return err;
/* Make sure mounter can read file for copy up later */
mask |= MAY_READ;
}
- err = inode_permission(realinode, mask);
+ err = inode_permission(&init_user_ns, realinode, mask);
revert_creds(old_cred);
return err;
if (!value && !upperdentry) {
old_cred = ovl_override_creds(dentry->d_sb);
- err = vfs_getxattr(realdentry, name, NULL, 0);
+ err = vfs_getxattr(&init_user_ns, realdentry, name, NULL, 0);
revert_creds(old_cred);
if (err < 0)
goto out_drop_write;
old_cred = ovl_override_creds(dentry->d_sb);
if (value)
- err = vfs_setxattr(realdentry, name, value, size, flags);
+ err = vfs_setxattr(&init_user_ns, realdentry, name, value, size,
+ flags);
else {
WARN_ON(flags != XATTR_REPLACE);
- err = vfs_removexattr(realdentry, name);
+ err = vfs_removexattr(&init_user_ns, realdentry, name);
}
revert_creds(old_cred);
ovl_i_dentry_upper(inode) ?: ovl_dentry_lower(dentry);
old_cred = ovl_override_creds(dentry->d_sb);
- res = vfs_getxattr(realdentry, name, value, size);
+ res = vfs_getxattr(&init_user_ns, realdentry, name, value, size);
revert_creds(old_cred);
return res;
}
static inline int ovl_do_rmdir(struct inode *dir, struct dentry *dentry)
{
- int err = vfs_rmdir(dir, dentry);
+ int err = vfs_rmdir(&init_user_ns, dir, dentry);
pr_debug("rmdir(%pd2) = %i\n", dentry, err);
return err;
static inline int ovl_do_unlink(struct inode *dir, struct dentry *dentry)
{
- int err = vfs_unlink(dir, dentry, NULL);
+ int err = vfs_unlink(&init_user_ns, dir, dentry, NULL);
pr_debug("unlink(%pd2) = %i\n", dentry, err);
return err;
static inline int ovl_do_link(struct dentry *old_dentry, struct inode *dir,
struct dentry *new_dentry)
{
- int err = vfs_link(old_dentry, dir, new_dentry, NULL);
+ int err = vfs_link(old_dentry, &init_user_ns, dir, new_dentry, NULL);
pr_debug("link(%pd2, %pd2) = %i\n", old_dentry, new_dentry, err);
return err;
static inline int ovl_do_create(struct inode *dir, struct dentry *dentry,
umode_t mode)
{
- int err = vfs_create(dir, dentry, mode, true);
+ int err = vfs_create(&init_user_ns, dir, dentry, mode, true);
pr_debug("create(%pd2, 0%o) = %i\n", dentry, mode, err);
return err;
static inline int ovl_do_mkdir(struct inode *dir, struct dentry *dentry,
umode_t mode)
{
- int err = vfs_mkdir(dir, dentry, mode);
+ int err = vfs_mkdir(&init_user_ns, dir, dentry, mode);
pr_debug("mkdir(%pd2, 0%o) = %i\n", dentry, mode, err);
return err;
}
static inline int ovl_do_mknod(struct inode *dir, struct dentry *dentry,
umode_t mode, dev_t dev)
{
- int err = vfs_mknod(dir, dentry, mode, dev);
+ int err = vfs_mknod(&init_user_ns, dir, dentry, mode, dev);
pr_debug("mknod(%pd2, 0%o, 0%o) = %i\n", dentry, mode, dev, err);
return err;
static inline int ovl_do_symlink(struct inode *dir, struct dentry *dentry,
const char *oldname)
{
- int err = vfs_symlink(dir, dentry, oldname);
+ int err = vfs_symlink(&init_user_ns, dir, dentry, oldname);
pr_debug("symlink(\"%s\", %pd2) = %i\n", oldname, dentry, err);
return err;
size_t size)
{
const char *name = ovl_xattr(ofs, ox);
- return vfs_getxattr(dentry, name, value, size);
+ return vfs_getxattr(&init_user_ns, dentry, name, value, size);
}
static inline int ovl_do_setxattr(struct ovl_fs *ofs, struct dentry *dentry,
size_t size)
{
const char *name = ovl_xattr(ofs, ox);
- int err = vfs_setxattr(dentry, name, value, size, 0);
+ int err = vfs_setxattr(&init_user_ns, dentry, name, value, size, 0);
pr_debug("setxattr(%pd2, \"%s\", \"%*pE\", %zu, 0) = %i\n",
dentry, name, min((int)size, 48), value, size, err);
return err;
enum ovl_xattr ox)
{
const char *name = ovl_xattr(ofs, ox);
- int err = vfs_removexattr(dentry, name);
+ int err = vfs_removexattr(&init_user_ns, dentry, name);
pr_debug("removexattr(%pd2, \"%s\") = %i\n", dentry, name, err);
return err;
}
unsigned int flags)
{
int err;
+ struct renamedata rd = {
+ .old_mnt_userns = &init_user_ns,
+ .old_dir = olddir,
+ .old_dentry = olddentry,
+ .new_mnt_userns = &init_user_ns,
+ .new_dir = newdir,
+ .new_dentry = newdentry,
+ .flags = flags,
+ };
pr_debug("rename(%pd2, %pd2, 0x%x)\n", olddentry, newdentry, flags);
- err = vfs_rename(olddir, olddentry, newdir, newdentry, NULL, flags);
+ err = vfs_rename(&rd);
if (err) {
pr_debug("...rename(%pd2, %pd2, ...) = %i\n",
olddentry, newdentry, err);
static inline int ovl_do_whiteout(struct inode *dir, struct dentry *dentry)
{
- int err = vfs_whiteout(dir, dentry);
+ int err = vfs_whiteout(&init_user_ns, dir, dentry);
pr_debug("whiteout(%pd2) = %i\n", dentry, err);
return err;
}
static inline struct dentry *ovl_do_tmpfile(struct dentry *dentry, umode_t mode)
{
- struct dentry *ret = vfs_tmpfile(dentry, mode, 0);
+ struct dentry *ret = vfs_tmpfile(&init_user_ns, dentry, mode, 0);
int err = PTR_ERR_OR_ZERO(ret);
pr_debug("tmpfile(%pd2, 0%o) = %i\n", dentry, mode, err);
unsigned int ovl_get_nlink(struct ovl_fs *ofs, struct dentry *lowerdentry,
struct dentry *upperdentry,
unsigned int fallback);
-int ovl_setattr(struct dentry *dentry, struct iattr *attr);
-int ovl_getattr(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int flags);
-int ovl_permission(struct inode *inode, int mask);
+int ovl_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr);
+int ovl_getattr(struct user_namespace *mnt_userns, const struct path *path,
+ struct kstat *stat, u32 request_mask, unsigned int flags);
+int ovl_permission(struct user_namespace *mnt_userns, struct inode *inode,
+ int mask);
int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name,
const void *value, size_t size, int flags);
int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name,
* allowed as upper are limited to "normal" ones, where checking
* for the above two errors is sufficient.
*/
- err = vfs_removexattr(work, XATTR_NAME_POSIX_ACL_DEFAULT);
+ err = vfs_removexattr(&init_user_ns, work,
+ XATTR_NAME_POSIX_ACL_DEFAULT);
if (err && err != -ENODATA && err != -EOPNOTSUPP)
goto out_dput;
- err = vfs_removexattr(work, XATTR_NAME_POSIX_ACL_ACCESS);
+ err = vfs_removexattr(&init_user_ns, work,
+ XATTR_NAME_POSIX_ACL_ACCESS);
if (err && err != -ENODATA && err != -EOPNOTSUPP)
goto out_dput;
/* Clear any inherited mode bits */
inode_lock(work->d_inode);
- err = notify_change(work, &attr, NULL);
+ err = notify_change(&init_user_ns, work, &attr, NULL);
inode_unlock(work->d_inode);
if (err)
goto out_dput;
pr_err("filesystem on '%s' not supported\n", name);
goto out_put;
}
+ if (mnt_user_ns(path->mnt) != &init_user_ns) {
+ pr_err("idmapped layers are currently not supported\n");
+ goto out_put;
+ }
if (!d_is_dir(path->dentry)) {
pr_err("'%s' not a directory\n", name);
goto out_put;
static int __maybe_unused
ovl_posix_acl_xattr_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *dentry, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
goto out_acl_release;
}
err = -EPERM;
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(&init_user_ns, inode))
goto out_acl_release;
posix_acl_release(acl);
if (unlikely(inode->i_mode & S_ISGID) &&
handler->flags == ACL_TYPE_ACCESS &&
!in_group_p(inode->i_gid) &&
- !capable_wrt_inode_uidgid(inode, CAP_FSETID)) {
+ !capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_FSETID)) {
struct iattr iattr = { .ia_valid = ATTR_KILL_SGID };
- err = ovl_setattr(dentry, &iattr);
+ err = ovl_setattr(&init_user_ns, dentry, &iattr);
if (err)
return err;
}
}
static int ovl_own_xattr_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *dentry, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
}
static int ovl_other_xattr_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *dentry, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
BUG();
}
- err = inode_permission(inode, acc_mode | MAY_OPEN);
+ err = inode_permission(&init_user_ns, inode, acc_mode | MAY_OPEN);
if (err)
return ERR_PTR(err);
/* O_NOATIME is an optimization, don't fail if not permitted */
- if (inode_owner_or_capable(inode))
+ if (inode_owner_or_capable(&init_user_ns, inode))
flags |= O_NOATIME;
return dentry_open(path, flags, current_cred());
* by the acl. Returns -E... otherwise.
*/
int
-posix_acl_permission(struct inode *inode, const struct posix_acl *acl, int want)
+posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode,
+ const struct posix_acl *acl, int want)
{
const struct posix_acl_entry *pa, *pe, *mask_obj;
int found = 0;
+ kuid_t uid;
+ kgid_t gid;
want &= MAY_READ | MAY_WRITE | MAY_EXEC;
switch(pa->e_tag) {
case ACL_USER_OBJ:
/* (May have been checked already) */
- if (uid_eq(inode->i_uid, current_fsuid()))
+ uid = i_uid_into_mnt(mnt_userns, inode);
+ if (uid_eq(uid, current_fsuid()))
goto check_perm;
break;
case ACL_USER:
- if (uid_eq(pa->e_uid, current_fsuid()))
+ uid = kuid_into_mnt(mnt_userns, pa->e_uid);
+ if (uid_eq(uid, current_fsuid()))
goto mask;
break;
case ACL_GROUP_OBJ:
- if (in_group_p(inode->i_gid)) {
+ gid = i_gid_into_mnt(mnt_userns, inode);
+ if (in_group_p(gid)) {
found = 1;
if ((pa->e_perm & want) == want)
goto mask;
}
break;
case ACL_GROUP:
- if (in_group_p(pa->e_gid)) {
+ gid = kgid_into_mnt(mnt_userns, pa->e_gid);
+ if (in_group_p(gid)) {
found = 1;
if ((pa->e_perm & want) == want)
goto mask;
}
EXPORT_SYMBOL(__posix_acl_chmod);
+/**
+ * posix_acl_chmod - chmod a posix acl
+ *
+ * @mnt_userns: user namespace of the mount @inode was found from
+ * @inode: inode to check permissions on
+ * @mode: the new mode of @inode
+ *
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then
+ * take care to map the inode according to @mnt_userns before checking
+ * permissions. On non-idmapped mounts or if permission checking is to be
+ * performed on the raw inode simply passs init_user_ns.
+ */
int
-posix_acl_chmod(struct inode *inode, umode_t mode)
+ posix_acl_chmod(struct user_namespace *mnt_userns, struct inode *inode,
+ umode_t mode)
{
struct posix_acl *acl;
int ret = 0;
ret = __posix_acl_chmod(&acl, GFP_KERNEL, mode);
if (ret)
return ret;
- ret = inode->i_op->set_acl(inode, acl, ACL_TYPE_ACCESS);
+ ret = inode->i_op->set_acl(mnt_userns, inode, acl, ACL_TYPE_ACCESS);
posix_acl_release(acl);
return ret;
}
/**
* posix_acl_update_mode - update mode in set_acl
- * @inode: target inode
- * @mode_p: mode (pointer) for update
- * @acl: acl pointer
+ * @mnt_userns: user namespace of the mount @inode was found from
+ * @inode: target inode
+ * @mode_p: mode (pointer) for update
+ * @acl: acl pointer
*
* Update the file mode when setting an ACL: compute the new file permission
* bits based on the ACL. In addition, if the ACL is equivalent to the new
* As with chmod, clear the setgid bit if the caller is not in the owning group
* or capable of CAP_FSETID (see inode_change_ok).
*
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then
+ * take care to map the inode according to @mnt_userns before checking
+ * permissions. On non-idmapped mounts or if permission checking is to be
+ * performed on the raw inode simply passs init_user_ns.
+ *
* Called from set_acl inode operations.
*/
-int posix_acl_update_mode(struct inode *inode, umode_t *mode_p,
+int posix_acl_update_mode(struct user_namespace *mnt_userns,
+ struct inode *inode, umode_t *mode_p,
struct posix_acl **acl)
{
umode_t mode = inode->i_mode;
return error;
if (error == 0)
*acl = NULL;
- if (!in_group_p(inode->i_gid) &&
- !capable_wrt_inode_uidgid(inode, CAP_FSETID))
+ if (!in_group_p(i_gid_into_mnt(mnt_userns, inode)) &&
+ !capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FSETID))
mode &= ~S_ISGID;
*mode_p = mode;
return 0;
*/
static void posix_acl_fix_xattr_userns(
struct user_namespace *to, struct user_namespace *from,
- void *value, size_t size)
+ struct user_namespace *mnt_userns,
+ void *value, size_t size, bool from_user)
{
struct posix_acl_xattr_header *header = value;
struct posix_acl_xattr_entry *entry = (void *)(header + 1), *end;
switch(le16_to_cpu(entry->e_tag)) {
case ACL_USER:
uid = make_kuid(from, le32_to_cpu(entry->e_id));
+ if (from_user)
+ uid = kuid_from_mnt(mnt_userns, uid);
+ else
+ uid = kuid_into_mnt(mnt_userns, uid);
entry->e_id = cpu_to_le32(from_kuid(to, uid));
break;
case ACL_GROUP:
gid = make_kgid(from, le32_to_cpu(entry->e_id));
+ if (from_user)
+ gid = kgid_from_mnt(mnt_userns, gid);
+ else
+ gid = kgid_into_mnt(mnt_userns, gid);
entry->e_id = cpu_to_le32(from_kgid(to, gid));
break;
default:
}
}
-void posix_acl_fix_xattr_from_user(void *value, size_t size)
+void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns,
+ void *value, size_t size)
{
struct user_namespace *user_ns = current_user_ns();
- if (user_ns == &init_user_ns)
+ if ((user_ns == &init_user_ns) && (mnt_userns == &init_user_ns))
return;
- posix_acl_fix_xattr_userns(&init_user_ns, user_ns, value, size);
+ posix_acl_fix_xattr_userns(&init_user_ns, user_ns, mnt_userns, value,
+ size, true);
}
-void posix_acl_fix_xattr_to_user(void *value, size_t size)
+void posix_acl_fix_xattr_to_user(struct user_namespace *mnt_userns,
+ void *value, size_t size)
{
struct user_namespace *user_ns = current_user_ns();
- if (user_ns == &init_user_ns)
+ if ((user_ns == &init_user_ns) && (mnt_userns == &init_user_ns))
return;
- posix_acl_fix_xattr_userns(user_ns, &init_user_ns, value, size);
+ posix_acl_fix_xattr_userns(user_ns, &init_user_ns, mnt_userns, value,
+ size, false);
}
/*
}
int
-set_posix_acl(struct inode *inode, int type, struct posix_acl *acl)
+set_posix_acl(struct user_namespace *mnt_userns, struct inode *inode,
+ int type, struct posix_acl *acl)
{
if (!IS_POSIXACL(inode))
return -EOPNOTSUPP;
if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode))
return acl ? -EACCES : 0;
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(mnt_userns, inode))
return -EPERM;
if (acl) {
if (ret)
return ret;
}
- return inode->i_op->set_acl(inode, acl, type);
+ return inode->i_op->set_acl(mnt_userns, inode, acl, type);
}
EXPORT_SYMBOL(set_posix_acl);
static int
posix_acl_xattr_set(const struct xattr_handler *handler,
- struct dentry *unused, struct inode *inode,
- const char *name, const void *value,
- size_t size, int flags)
+ struct user_namespace *mnt_userns,
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *value, size_t size,
+ int flags)
{
struct posix_acl *acl = NULL;
int ret;
if (IS_ERR(acl))
return PTR_ERR(acl);
}
- ret = set_posix_acl(inode, handler->flags, acl);
+ ret = set_posix_acl(mnt_userns, inode, handler->flags, acl);
posix_acl_release(acl);
return ret;
}
};
EXPORT_SYMBOL_GPL(posix_acl_default_xattr_handler);
-int simple_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+int simple_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
+ struct posix_acl *acl, int type)
{
int error;
if (type == ACL_TYPE_ACCESS) {
- error = posix_acl_update_mode(inode,
+ error = posix_acl_update_mode(mnt_userns, inode,
&inode->i_mode, &acl);
if (error)
return error;
return allowed;
}
-int proc_setattr(struct dentry *dentry, struct iattr *attr)
+int proc_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr)
{
int error;
struct inode *inode = d_inode(dentry);
if (attr->ia_valid & ATTR_MODE)
return -EPERM;
- error = setattr_prepare(dentry, attr);
+ error = setattr_prepare(&init_user_ns, dentry, attr);
if (error)
return error;
- setattr_copy(inode, attr);
+ setattr_copy(&init_user_ns, inode, attr);
mark_inode_dirty(inode);
return 0;
}
}
-static int proc_pid_permission(struct inode *inode, int mask)
+static int proc_pid_permission(struct user_namespace *mnt_userns,
+ struct inode *inode, int mask)
{
struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb);
struct task_struct *task;
return -EPERM;
}
- return generic_permission(inode, mask);
+ return generic_permission(&init_user_ns, inode, mask);
}
return NULL;
}
-int pid_getattr(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int query_flags)
+int pid_getattr(struct user_namespace *mnt_userns, const struct path *path,
+ struct kstat *stat, u32 request_mask, unsigned int query_flags)
{
struct inode *inode = d_inode(path->dentry);
struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb);
struct task_struct *task;
- generic_fillattr(inode, stat);
+ generic_fillattr(&init_user_ns, inode, stat);
stat->uid = GLOBAL_ROOT_UID;
stat->gid = GLOBAL_ROOT_GID;
* This function makes sure that the node is always accessible for members of
* same thread group.
*/
-static int proc_tid_comm_permission(struct inode *inode, int mask)
+static int proc_tid_comm_permission(struct user_namespace *mnt_userns,
+ struct inode *inode, int mask)
{
bool is_same_tgroup;
struct task_struct *task;
return 0;
}
- return generic_permission(inode, mask);
+ return generic_permission(&init_user_ns, inode, mask);
}
static const struct inode_operations proc_tid_comm_inode_operations = {
return 0;
}
-static int proc_task_getattr(const struct path *path, struct kstat *stat,
+static int proc_task_getattr(struct user_namespace *mnt_userns,
+ const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int query_flags)
{
struct inode *inode = d_inode(path->dentry);
struct task_struct *p = get_proc_task(inode);
- generic_fillattr(inode, stat);
+ generic_fillattr(&init_user_ns, inode, stat);
if (p) {
stat->nlink += get_nr_threads(p);
* /proc/pid/fd needs a special permission handler so that a process can still
* access /proc/self/fd after it has executed a setuid().
*/
-int proc_fd_permission(struct inode *inode, int mask)
+int proc_fd_permission(struct user_namespace *mnt_userns,
+ struct inode *inode, int mask)
{
struct task_struct *p;
int rv;
- rv = generic_permission(inode, mask);
+ rv = generic_permission(&init_user_ns, inode, mask);
if (rv == 0)
return rv;
extern const struct file_operations proc_fdinfo_operations;
extern const struct inode_operations proc_fdinfo_inode_operations;
-extern int proc_fd_permission(struct inode *inode, int mask);
+extern int proc_fd_permission(struct user_namespace *mnt_userns,
+ struct inode *inode, int mask);
static inline unsigned int proc_fd(struct inode *inode)
{
return true;
}
-static int proc_notify_change(struct dentry *dentry, struct iattr *iattr)
+static int proc_notify_change(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct iattr *iattr)
{
struct inode *inode = d_inode(dentry);
struct proc_dir_entry *de = PDE(inode);
int error;
- error = setattr_prepare(dentry, iattr);
+ error = setattr_prepare(&init_user_ns, dentry, iattr);
if (error)
return error;
- setattr_copy(inode, iattr);
+ setattr_copy(&init_user_ns, inode, iattr);
mark_inode_dirty(inode);
proc_set_user(de, inode->i_uid, inode->i_gid);
return 0;
}
-static int proc_getattr(const struct path *path, struct kstat *stat,
+static int proc_getattr(struct user_namespace *mnt_userns,
+ const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int query_flags)
{
struct inode *inode = d_inode(path->dentry);
}
}
- generic_fillattr(inode, stat);
+ generic_fillattr(&init_user_ns, inode, stat);
return 0;
}
* base.c
*/
extern const struct dentry_operations pid_dentry_operations;
-extern int pid_getattr(const struct path *, struct kstat *, u32, unsigned int);
-extern int proc_setattr(struct dentry *, struct iattr *);
+extern int pid_getattr(struct user_namespace *, const struct path *,
+ struct kstat *, u32, unsigned int);
+extern int proc_setattr(struct user_namespace *, struct dentry *,
+ struct iattr *);
extern void proc_pid_evict_inode(struct proc_inode *);
extern struct inode *proc_pid_make_inode(struct super_block *, struct task_struct *, umode_t);
extern void pid_update_inode(struct task_struct *, struct inode *);
return de;
}
-static int proc_tgid_net_getattr(const struct path *path, struct kstat *stat,
+static int proc_tgid_net_getattr(struct user_namespace *mnt_userns,
+ const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int query_flags)
{
struct inode *inode = d_inode(path->dentry);
net = get_proc_task_net(inode);
- generic_fillattr(inode, stat);
+ generic_fillattr(&init_user_ns, inode, stat);
if (net != NULL) {
stat->nlink = net->proc_net->nlink;
return 0;
}
-static int proc_sys_permission(struct inode *inode, int mask)
+static int proc_sys_permission(struct user_namespace *mnt_userns,
+ struct inode *inode, int mask)
{
/*
* sysctl entries that are not writeable,
return error;
}
-static int proc_sys_setattr(struct dentry *dentry, struct iattr *attr)
+static int proc_sys_setattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
int error;
if (attr->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID))
return -EPERM;
- error = setattr_prepare(dentry, attr);
+ error = setattr_prepare(&init_user_ns, dentry, attr);
if (error)
return error;
- setattr_copy(inode, attr);
+ setattr_copy(&init_user_ns, inode, attr);
mark_inode_dirty(inode);
return 0;
}
-static int proc_sys_getattr(const struct path *path, struct kstat *stat,
+static int proc_sys_getattr(struct user_namespace *mnt_userns,
+ const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int query_flags)
{
struct inode *inode = d_inode(path->dentry);
if (IS_ERR(head))
return PTR_ERR(head);
- generic_fillattr(inode, stat);
+ generic_fillattr(&init_user_ns, inode, stat);
if (table)
stat->mode = (stat->mode & S_IFMT) | table->mode;
register_filesystem(&proc_fs_type);
}
-static int proc_root_getattr(const struct path *path, struct kstat *stat,
+static int proc_root_getattr(struct user_namespace *mnt_userns,
+ const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int query_flags)
{
- generic_fillattr(d_inode(path->dentry), stat);
+ generic_fillattr(&init_user_ns, d_inode(path->dentry), stat);
stat->nlink = proc_root.nlink + nr_processes();
return 0;
}
if (mnt->mnt_flags & fs_infop->flag)
seq_puts(m, fs_infop->str);
}
+
+ if (mnt_user_ns(mnt) != &init_user_ns)
+ seq_puts(m, ",idmapped");
}
static inline void mangle(struct seq_file *m, const char *s)
#include <linux/uaccess.h>
#include "internal.h"
-static int ramfs_nommu_setattr(struct dentry *, struct iattr *);
+static int ramfs_nommu_setattr(struct user_namespace *, struct dentry *, struct iattr *);
static unsigned long ramfs_nommu_get_unmapped_area(struct file *file,
unsigned long addr,
unsigned long len,
* handle a change of attributes
* - we're specifically interested in a change of size
*/
-static int ramfs_nommu_setattr(struct dentry *dentry, struct iattr *ia)
+static int ramfs_nommu_setattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct iattr *ia)
{
struct inode *inode = d_inode(dentry);
unsigned int old_ia_valid = ia->ia_valid;
int ret = 0;
/* POSIX UID/GID verification for setting inode attributes */
- ret = setattr_prepare(dentry, ia);
+ ret = setattr_prepare(&init_user_ns, dentry, ia);
if (ret)
return ret;
}
}
- setattr_copy(inode, ia);
+ setattr_copy(&init_user_ns, inode, ia);
out:
ia->ia_valid = old_ia_valid;
return ret;
if (inode) {
inode->i_ino = get_next_ino();
- inode_init_owner(inode, dir, mode);
+ inode_init_owner(&init_user_ns, inode, dir, mode);
inode->i_mapping->a_ops = &ramfs_aops;
mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
mapping_set_unevictable(inode->i_mapping);
*/
/* SMP-safe */
static int
-ramfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev)
+ramfs_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, dev_t dev)
{
struct inode * inode = ramfs_get_inode(dir->i_sb, dir, mode, dev);
int error = -ENOSPC;
return error;
}
-static int ramfs_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
+static int ramfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
- int retval = ramfs_mknod(dir, dentry, mode | S_IFDIR, 0);
+ int retval = ramfs_mknod(&init_user_ns, dir, dentry, mode | S_IFDIR, 0);
if (!retval)
inc_nlink(dir);
return retval;
}
-static int ramfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl)
+static int ramfs_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool excl)
{
- return ramfs_mknod(dir, dentry, mode | S_IFREG, 0);
+ return ramfs_mknod(&init_user_ns, dir, dentry, mode | S_IFREG, 0);
}
-static int ramfs_symlink(struct inode * dir, struct dentry *dentry, const char * symname)
+static int ramfs_symlink(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, const char *symname)
{
struct inode *inode;
int error = -ENOSPC;
#ifdef CONFIG_REISERFS_FS_POSIX_ACL
struct posix_acl *reiserfs_get_acl(struct inode *inode, int type);
-int reiserfs_set_acl(struct inode *inode, struct posix_acl *acl, int type);
+int reiserfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
+ struct posix_acl *acl, int type);
int reiserfs_acl_chmod(struct inode *inode);
int reiserfs_inherit_default_acl(struct reiserfs_transaction_handle *th,
struct inode *dir, struct dentry *dentry,
return ret;
}
-int reiserfs_setattr(struct dentry *dentry, struct iattr *attr)
+int reiserfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
unsigned int ia_valid;
int error;
- error = setattr_prepare(dentry, attr);
+ error = setattr_prepare(&init_user_ns, dentry, attr);
if (error)
return error;
}
if (!error) {
- setattr_copy(inode, attr);
+ setattr_copy(&init_user_ns, inode, attr);
mark_inode_dirty(inode);
}
if (err)
break;
- if (!inode_owner_or_capable(inode)) {
+ if (!inode_owner_or_capable(&init_user_ns, inode)) {
err = -EPERM;
goto setflags_out;
}
err = put_user(inode->i_generation, (int __user *)arg);
break;
case REISERFS_IOC_SETVERSION:
- if (!inode_owner_or_capable(inode)) {
+ if (!inode_owner_or_capable(&init_user_ns, inode)) {
err = -EPERM;
break;
}
* the quota init calls have to know who to charge the quota to, so
* we have to set uid and gid here
*/
- inode_init_owner(inode, dir, mode);
+ inode_init_owner(&init_user_ns, inode, dir, mode);
return dquot_initialize(inode);
}
-static int reiserfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- bool excl)
+static int reiserfs_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool excl)
{
int retval;
struct inode *inode;
return retval;
}
-static int reiserfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
- dev_t rdev)
+static int reiserfs_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, dev_t rdev)
{
int retval;
struct inode *inode;
return retval;
}
-static int reiserfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int reiserfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
int retval;
struct inode *inode;
return retval;
}
-static int reiserfs_symlink(struct inode *parent_dir,
- struct dentry *dentry, const char *symname)
+static int reiserfs_symlink(struct user_namespace *mnt_userns,
+ struct inode *parent_dir, struct dentry *dentry,
+ const char *symname)
{
int retval;
struct inode *inode;
* one path. If it holds 2 or more, it can get into endless waiting in
* get_empty_nodes or its clones
*/
-static int reiserfs_rename(struct inode *old_dir, struct dentry *old_dentry,
+static int reiserfs_rename(struct user_namespace *mnt_userns,
+ struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
}
void sd_attrs_to_i_attrs(__u16 sd_attrs, struct inode *inode);
-int reiserfs_setattr(struct dentry *dentry, struct iattr *attr);
+int reiserfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr);
int __reiserfs_write_begin(struct page *page, unsigned from, unsigned len);
static int xattr_create(struct inode *dir, struct dentry *dentry, int mode)
{
BUG_ON(!inode_is_locked(dir));
- return dir->i_op->create(dir, dentry, mode, true);
+ return dir->i_op->create(&init_user_ns, dir, dentry, mode, true);
}
#endif
static int xattr_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
BUG_ON(!inode_is_locked(dir));
- return dir->i_op->mkdir(dir, dentry, mode);
+ return dir->i_op->mkdir(&init_user_ns, dir, dentry, mode);
}
/*
* ATTR_MODE is set.
*/
attrs->ia_valid &= (ATTR_UID|ATTR_GID);
- err = reiserfs_setattr(dentry, attrs);
+ err = reiserfs_setattr(&init_user_ns, dentry, attrs);
attrs->ia_valid = ia_valid;
return err;
inode_lock_nested(d_inode(dentry), I_MUTEX_XATTR);
inode_dio_wait(d_inode(dentry));
- err = reiserfs_setattr(dentry, &newattrs);
+ err = reiserfs_setattr(&init_user_ns, dentry, &newattrs);
inode_unlock(d_inode(dentry));
} else
update_ctime(inode);
return 0;
}
-int reiserfs_permission(struct inode *inode, int mask)
+int reiserfs_permission(struct user_namespace *mnt_userns, struct inode *inode,
+ int mask)
{
/*
* We don't do permission checks on the internal objects.
if (IS_PRIVATE(inode))
return 0;
- return generic_permission(inode, mask);
+ return generic_permission(&init_user_ns, inode, mask);
}
static int xattr_hide_revalidate(struct dentry *dentry, unsigned int flags)
int reiserfs_lookup_privroot(struct super_block *sb);
int reiserfs_delete_xattrs(struct inode *inode);
int reiserfs_chown_xattrs(struct inode *inode, struct iattr *attrs);
-int reiserfs_permission(struct inode *inode, int mask);
+int reiserfs_permission(struct user_namespace *mnt_userns,
+ struct inode *inode, int mask);
#ifdef CONFIG_REISERFS_FS_XATTR
#define has_xattr_dir(inode) (REISERFS_I(inode)->i_flags & i_has_xattr_dir)
int
-reiserfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+reiserfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
+ struct posix_acl *acl, int type)
{
int error, error2;
struct reiserfs_transaction_handle th;
reiserfs_write_unlock(inode->i_sb);
if (error == 0) {
if (type == ACL_TYPE_ACCESS && acl) {
- error = posix_acl_update_mode(inode, &mode, &acl);
+ error = posix_acl_update_mode(&init_user_ns, inode,
+ &mode, &acl);
if (error)
goto unlock;
update_mode = 1;
!reiserfs_posixacl(inode->i_sb))
return 0;
- return posix_acl_chmod(inode, inode->i_mode);
+ return posix_acl_chmod(&init_user_ns, inode, inode->i_mode);
}
}
static int
-security_set(const struct xattr_handler *handler, struct dentry *unused,
+security_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns, struct dentry *unused,
struct inode *inode, const char *name, const void *buffer,
size_t size, int flags)
{
}
static int
-trusted_set(const struct xattr_handler *handler, struct dentry *unused,
+trusted_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns, struct dentry *unused,
struct inode *inode, const char *name, const void *buffer,
size_t size, int flags)
{
}
static int
-user_set(const struct xattr_handler *handler, struct dentry *unused,
+user_set(const struct xattr_handler *handler, struct user_namespace *mnt_userns,
+ struct dentry *unused,
struct inode *inode, const char *name, const void *buffer,
size_t size, int flags)
{
/* Check whether we are allowed to dedupe the destination file */
static bool allow_file_dedupe(struct file *file)
{
+ struct user_namespace *mnt_userns = file_mnt_user_ns(file);
+ struct inode *inode = file_inode(file);
+
if (capable(CAP_SYS_ADMIN))
return true;
if (file->f_mode & FMODE_WRITE)
return true;
- if (uid_eq(current_fsuid(), file_inode(file)->i_uid))
+ if (uid_eq(current_fsuid(), i_uid_into_mnt(mnt_userns, inode)))
return true;
- if (!inode_permission(file_inode(file), MAY_WRITE))
+ if (!inode_permission(mnt_userns, inode, MAY_WRITE))
return true;
return false;
}
/**
* generic_fillattr - Fill in the basic attributes from the inode struct
- * @inode: Inode to use as the source
- * @stat: Where to fill in the attributes
+ * @mnt_userns: user namespace of the mount the inode was found from
+ * @inode: Inode to use as the source
+ * @stat: Where to fill in the attributes
*
* Fill in the basic attributes in the kstat structure from data that's to be
* found on the VFS inode structure. This is the default if no getattr inode
* operation is supplied.
+ *
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then
+ * take care to map the inode according to @mnt_userns before filling in the
+ * uid and gid filds. On non-idmapped mounts or if permission checking is to be
+ * performed on the raw inode simply passs init_user_ns.
*/
-void generic_fillattr(struct inode *inode, struct kstat *stat)
+void generic_fillattr(struct user_namespace *mnt_userns, struct inode *inode,
+ struct kstat *stat)
{
stat->dev = inode->i_sb->s_dev;
stat->ino = inode->i_ino;
stat->mode = inode->i_mode;
stat->nlink = inode->i_nlink;
- stat->uid = inode->i_uid;
- stat->gid = inode->i_gid;
+ stat->uid = i_uid_into_mnt(mnt_userns, inode);
+ stat->gid = i_gid_into_mnt(mnt_userns, inode);
stat->rdev = inode->i_rdev;
stat->size = i_size_read(inode);
stat->atime = inode->i_atime;
int vfs_getattr_nosec(const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int query_flags)
{
+ struct user_namespace *mnt_userns;
struct inode *inode = d_backing_inode(path->dentry);
memset(stat, 0, sizeof(*stat));
if (IS_DAX(inode))
stat->attributes |= STATX_ATTR_DAX;
+ mnt_userns = mnt_user_ns(path->mnt);
if (inode->i_op->getattr)
- return inode->i_op->getattr(path, stat, request_mask,
- query_flags);
+ return inode->i_op->getattr(mnt_userns, path, stat,
+ request_mask, query_flags);
- generic_fillattr(inode, stat);
+ generic_fillattr(mnt_userns, inode, stat);
return 0;
}
EXPORT_SYMBOL(vfs_getattr_nosec);
.splice_read = generic_file_splice_read,
};
-static int sysv_setattr(struct dentry *dentry, struct iattr *attr)
+static int sysv_setattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
int error;
- error = setattr_prepare(dentry, attr);
+ error = setattr_prepare(&init_user_ns, dentry, attr);
if (error)
return error;
sysv_truncate(inode);
}
- setattr_copy(inode, attr);
+ setattr_copy(&init_user_ns, inode, attr);
mark_inode_dirty(inode);
return 0;
}
*sbi->s_sb_fic_count = cpu_to_fs16(sbi, count);
fs16_add(sbi, sbi->s_sb_total_free_inodes, -1);
dirty_sb(sb);
- inode_init_owner(inode, dir, mode);
+ inode_init_owner(&init_user_ns, inode, dir, mode);
inode->i_ino = fs16_to_cpu(sbi, ino);
inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
inode->i_blocks = 0;
return blocks;
}
-int sysv_getattr(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int flags)
+int sysv_getattr(struct user_namespace *mnt_userns, const struct path *path,
+ struct kstat *stat, u32 request_mask, unsigned int flags)
{
struct super_block *s = path->dentry->d_sb;
- generic_fillattr(d_inode(path->dentry), stat);
+ generic_fillattr(&init_user_ns, d_inode(path->dentry), stat);
stat->blocks = (s->s_blocksize / 512) * sysv_nblocks(s, stat->size);
stat->blksize = s->s_blocksize;
return 0;
return d_splice_alias(inode, dentry);
}
-static int sysv_mknod(struct inode * dir, struct dentry * dentry, umode_t mode, dev_t rdev)
+static int sysv_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, dev_t rdev)
{
struct inode * inode;
int err;
return err;
}
-static int sysv_create(struct inode * dir, struct dentry * dentry, umode_t mode, bool excl)
+static int sysv_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool excl)
{
- return sysv_mknod(dir, dentry, mode, 0);
+ return sysv_mknod(&init_user_ns, dir, dentry, mode, 0);
}
-static int sysv_symlink(struct inode * dir, struct dentry * dentry,
- const char * symname)
+static int sysv_symlink(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, const char *symname)
{
int err = -ENAMETOOLONG;
int l = strlen(symname)+1;
return add_nondir(dentry, inode);
}
-static int sysv_mkdir(struct inode * dir, struct dentry *dentry, umode_t mode)
+static int sysv_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
struct inode * inode;
int err;
* Anybody can rename anything with this: the permission checks are left to the
* higher-level routines.
*/
-static int sysv_rename(struct inode * old_dir, struct dentry * old_dentry,
- struct inode * new_dir, struct dentry * new_dentry,
- unsigned int flags)
+static int sysv_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
+ struct dentry *old_dentry, struct inode *new_dir,
+ struct dentry *new_dentry, unsigned int flags)
{
struct inode * old_inode = d_inode(old_dentry);
struct inode * new_inode = d_inode(new_dentry);
extern int sysv_write_inode(struct inode *, struct writeback_control *wbc);
extern int sysv_sync_inode(struct inode *);
extern void sysv_set_inode(struct inode *, dev_t);
-extern int sysv_getattr(const struct path *, struct kstat *, u32, unsigned int);
+extern int sysv_getattr(struct user_namespace *, const struct path *,
+ struct kstat *, u32, unsigned int);
extern int sysv_init_icache(void);
extern void sysv_destroy_icache(void);
return name;
}
-static int tracefs_syscall_mkdir(struct inode *inode, struct dentry *dentry, umode_t mode)
+static int tracefs_syscall_mkdir(struct user_namespace *mnt_userns,
+ struct inode *inode, struct dentry *dentry,
+ umode_t mode)
{
char *name;
int ret;
*/
inode->i_flags |= S_NOCMTIME;
- inode_init_owner(inode, dir, mode);
+ inode_init_owner(&init_user_ns, inode, dir, mode);
inode->i_mtime = inode->i_atime = inode->i_ctime =
current_time(inode);
inode->i_mapping->nrpages = 0;
return fscrypt_setup_filename(dir, &dentry->d_name, 0, nm);
}
-static int ubifs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- bool excl)
+static int ubifs_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool excl)
{
struct inode *inode;
struct ubifs_info *c = dir->i_sb->s_fs_info;
return err;
}
-static int ubifs_tmpfile(struct inode *dir, struct dentry *dentry,
- umode_t mode)
+static int ubifs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
return do_tmpfile(dir, dentry, mode, NULL);
}
return err;
}
-static int ubifs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int ubifs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
struct inode *inode;
struct ubifs_inode *dir_ui = ubifs_inode(dir);
return err;
}
-static int ubifs_mknod(struct inode *dir, struct dentry *dentry,
- umode_t mode, dev_t rdev)
+static int ubifs_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, dev_t rdev)
{
struct inode *inode;
struct ubifs_inode *ui;
return err;
}
-static int ubifs_symlink(struct inode *dir, struct dentry *dentry,
- const char *symname)
+static int ubifs_symlink(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, const char *symname)
{
struct inode *inode;
struct ubifs_inode *ui;
return err;
}
-static int ubifs_rename(struct inode *old_dir, struct dentry *old_dentry,
+static int ubifs_rename(struct user_namespace *mnt_userns,
+ struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
return do_rename(old_dir, old_dentry, new_dir, new_dentry, flags);
}
-int ubifs_getattr(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int flags)
+int ubifs_getattr(struct user_namespace *mnt_userns, const struct path *path,
+ struct kstat *stat, u32 request_mask, unsigned int flags)
{
loff_t size;
struct inode *inode = d_inode(path->dentry);
STATX_ATTR_ENCRYPTED |
STATX_ATTR_IMMUTABLE);
- generic_fillattr(inode, stat);
+ generic_fillattr(&init_user_ns, inode, stat);
stat->blksize = UBIFS_BLOCK_SIZE;
stat->size = ui->ui_size;
return err;
}
-int ubifs_setattr(struct dentry *dentry, struct iattr *attr)
+int ubifs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr)
{
int err;
struct inode *inode = d_inode(dentry);
dbg_gen("ino %lu, mode %#x, ia_valid %#x",
inode->i_ino, inode->i_mode, attr->ia_valid);
- err = setattr_prepare(dentry, attr);
+ err = setattr_prepare(&init_user_ns, dentry, attr);
if (err)
return err;
if (IS_RDONLY(inode))
return -EROFS;
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(&init_user_ns, inode))
return -EACCES;
if (get_user(flags, (int __user *) arg))
/* file.c */
int ubifs_fsync(struct file *file, loff_t start, loff_t end, int datasync);
-int ubifs_setattr(struct dentry *dentry, struct iattr *attr);
+int ubifs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr);
int ubifs_update_time(struct inode *inode, struct timespec64 *time, int flags);
/* dir.c */
struct inode *ubifs_new_inode(struct ubifs_info *c, struct inode *dir,
umode_t mode);
-int ubifs_getattr(const struct path *path, struct kstat *stat,
+int ubifs_getattr(struct user_namespace *mnt_userns, const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int flags);
int ubifs_check_dir_empty(struct inode *dir);
}
static int xattr_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *dentry, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
long old_block, new_block;
int result;
- if (inode_permission(inode, MAY_READ) != 0) {
+ if (file_permission(filp, MAY_READ) != 0) {
udf_debug("no permission to access inode %lu\n", inode->i_ino);
return -EPERM;
}
.llseek = generic_file_llseek,
};
-static int udf_setattr(struct dentry *dentry, struct iattr *attr)
+static int udf_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
struct super_block *sb = inode->i_sb;
int error;
- error = setattr_prepare(dentry, attr);
+ error = setattr_prepare(&init_user_ns, dentry, attr);
if (error)
return error;
if (attr->ia_valid & ATTR_MODE)
udf_update_extra_perms(inode, attr->ia_mode);
- setattr_copy(inode, attr);
+ setattr_copy(&init_user_ns, inode, attr);
mark_inode_dirty(inode);
return 0;
}
mutex_unlock(&sbi->s_alloc_mutex);
}
- inode_init_owner(inode, dir, mode);
+ inode_init_owner(&init_user_ns, inode, dir, mode);
if (UDF_QUERY_FLAG(sb, UDF_FLAG_UID_SET))
inode->i_uid = sbi->s_uid;
if (UDF_QUERY_FLAG(sb, UDF_FLAG_GID_SET))
return 0;
}
-static int udf_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- bool excl)
+static int udf_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool excl)
{
struct inode *inode = udf_new_inode(dir, mode);
return udf_add_nondir(dentry, inode);
}
-static int udf_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int udf_tmpfile(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
struct inode *inode = udf_new_inode(dir, mode);
return 0;
}
-static int udf_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
- dev_t rdev)
+static int udf_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, dev_t rdev)
{
struct inode *inode;
return udf_add_nondir(dentry, inode);
}
-static int udf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int udf_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
struct inode *inode;
struct udf_fileident_bh fibh;
return retval;
}
-static int udf_symlink(struct inode *dir, struct dentry *dentry,
- const char *symname)
+static int udf_symlink(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, const char *symname)
{
struct inode *inode = udf_new_inode(dir, S_IFLNK | 0777);
struct pathComponent *pc;
/* Anybody can rename anything with this: the permission checks are left to the
* higher-level routines.
*/
-static int udf_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry,
- unsigned int flags)
+static int udf_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
+ struct dentry *old_dentry, struct inode *new_dir,
+ struct dentry *new_dentry, unsigned int flags)
{
struct inode *old_inode = d_inode(old_dentry);
struct inode *new_inode = d_inode(new_dentry);
return err;
}
-static int udf_symlink_getattr(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int flags)
+static int udf_symlink_getattr(struct user_namespace *mnt_userns,
+ const struct path *path, struct kstat *stat,
+ u32 request_mask, unsigned int flags)
{
struct dentry *dentry = path->dentry;
struct inode *inode = d_backing_inode(dentry);
struct page *page;
- generic_fillattr(inode, stat);
+ generic_fillattr(&init_user_ns, inode, stat);
page = read_mapping_page(inode->i_mapping, 0, NULL);
if (IS_ERR(page))
return PTR_ERR(page);
ufs_mark_sb_dirty(sb);
inode->i_ino = cg * uspi->s_ipg + bit;
- inode_init_owner(inode, dir, mode);
+ inode_init_owner(&init_user_ns, inode, dir, mode);
inode->i_blocks = 0;
inode->i_generation = 0;
inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
return err;
}
-int ufs_setattr(struct dentry *dentry, struct iattr *attr)
+int ufs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
unsigned int ia_valid = attr->ia_valid;
int error;
- error = setattr_prepare(dentry, attr);
+ error = setattr_prepare(&init_user_ns, dentry, attr);
if (error)
return error;
return error;
}
- setattr_copy(inode, attr);
+ setattr_copy(&init_user_ns, inode, attr);
mark_inode_dirty(inode);
return 0;
}
* If the create succeeds, we fill in the inode information
* with d_instantiate().
*/
-static int ufs_create (struct inode * dir, struct dentry * dentry, umode_t mode,
+static int ufs_create (struct user_namespace * mnt_userns,
+ struct inode * dir, struct dentry * dentry, umode_t mode,
bool excl)
{
struct inode *inode;
return ufs_add_nondir(dentry, inode);
}
-static int ufs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev)
+static int ufs_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, dev_t rdev)
{
struct inode *inode;
int err;
return err;
}
-static int ufs_symlink (struct inode * dir, struct dentry * dentry,
- const char * symname)
+static int ufs_symlink (struct user_namespace * mnt_userns, struct inode * dir,
+ struct dentry * dentry, const char * symname)
{
struct super_block * sb = dir->i_sb;
int err;
return error;
}
-static int ufs_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
+static int ufs_mkdir(struct user_namespace * mnt_userns, struct inode * dir,
+ struct dentry * dentry, umode_t mode)
{
struct inode * inode;
int err;
return err;
}
-static int ufs_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry,
- unsigned int flags)
+static int ufs_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
+ struct dentry *old_dentry, struct inode *new_dir,
+ struct dentry *new_dentry, unsigned int flags)
{
struct inode *old_inode = d_inode(old_dentry);
struct inode *new_inode = d_inode(new_dentry);
extern int ufs_write_inode (struct inode *, struct writeback_control *);
extern int ufs_sync_inode (struct inode *);
extern void ufs_evict_inode (struct inode *);
-extern int ufs_setattr(struct dentry *dentry, struct iattr *attr);
+extern int ufs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *attr);
/* namei.c */
extern const struct file_operations ufs_dir_operations;
}
retry_deleg:
inode_lock(inode);
- error = notify_change(path->dentry, &newattrs, &delegated_inode);
+ error = notify_change(mnt_user_ns(path->mnt), path->dentry, &newattrs,
+ &delegated_inode);
inode_unlock(inode);
if (delegated_inode) {
error = break_deleg_wait(&delegated_inode);
return 0;
}
-static int vboxsf_dir_mkfile(struct inode *parent, struct dentry *dentry,
+static int vboxsf_dir_mkfile(struct user_namespace *mnt_userns,
+ struct inode *parent, struct dentry *dentry,
umode_t mode, bool excl)
{
return vboxsf_dir_create(parent, dentry, mode, 0);
}
-static int vboxsf_dir_mkdir(struct inode *parent, struct dentry *dentry,
+static int vboxsf_dir_mkdir(struct user_namespace *mnt_userns,
+ struct inode *parent, struct dentry *dentry,
umode_t mode)
{
return vboxsf_dir_create(parent, dentry, mode, 1);
return 0;
}
-static int vboxsf_dir_rename(struct inode *old_parent,
+static int vboxsf_dir_rename(struct user_namespace *mnt_userns,
+ struct inode *old_parent,
struct dentry *old_dentry,
struct inode *new_parent,
struct dentry *new_dentry,
return err;
}
-static int vboxsf_dir_symlink(struct inode *parent, struct dentry *dentry,
+static int vboxsf_dir_symlink(struct user_namespace *mnt_userns,
+ struct inode *parent, struct dentry *dentry,
const char *symname)
{
struct vboxsf_inode *sf_parent_i = VBOXSF_I(parent);
return 0;
}
-int vboxsf_getattr(const struct path *path, struct kstat *kstat,
- u32 request_mask, unsigned int flags)
+int vboxsf_getattr(struct user_namespace *mnt_userns, const struct path *path,
+ struct kstat *kstat, u32 request_mask, unsigned int flags)
{
int err;
struct dentry *dentry = path->dentry;
if (err)
return err;
- generic_fillattr(d_inode(dentry), kstat);
+ generic_fillattr(&init_user_ns, d_inode(dentry), kstat);
return 0;
}
-int vboxsf_setattr(struct dentry *dentry, struct iattr *iattr)
+int vboxsf_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *iattr)
{
struct vboxsf_inode *sf_i = VBOXSF_I(d_inode(dentry));
struct vboxsf_sbi *sbi = VBOXSF_SBI(dentry->d_sb);
struct shfl_fsobjinfo *info);
int vboxsf_stat_dentry(struct dentry *dentry, struct shfl_fsobjinfo *info);
int vboxsf_inode_revalidate(struct dentry *dentry);
-int vboxsf_getattr(const struct path *path, struct kstat *kstat,
- u32 request_mask, unsigned int query_flags);
-int vboxsf_setattr(struct dentry *dentry, struct iattr *iattr);
+int vboxsf_getattr(struct user_namespace *mnt_userns, const struct path *path,
+ struct kstat *kstat, u32 request_mask,
+ unsigned int query_flags);
+int vboxsf_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct iattr *iattr);
struct shfl_string *vboxsf_path_from_dentry(struct vboxsf_sbi *sbi,
struct dentry *dentry);
int vboxsf_nlscpy(struct vboxsf_sbi *sbi, char *name, size_t name_bound_len,
* has verity enabled, and to stabilize the data being hashed.
*/
- err = inode_permission(inode, MAY_WRITE);
+ err = file_permission(filp, MAY_WRITE);
if (err)
return err;
* because different namespaces have very different rules.
*/
static int
-xattr_permission(struct inode *inode, const char *name, int mask)
+xattr_permission(struct user_namespace *mnt_userns, struct inode *inode,
+ const char *name, int mask)
{
/*
* We can never set or remove an extended attribute on a read-only
* to be writen back improperly if their true value is
* unknown to the vfs.
*/
- if (HAS_UNMAPPED_ID(inode))
+ if (HAS_UNMAPPED_ID(mnt_userns, inode))
return -EPERM;
}
if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode))
return (mask & MAY_WRITE) ? -EPERM : -ENODATA;
if (S_ISDIR(inode->i_mode) && (inode->i_mode & S_ISVTX) &&
- (mask & MAY_WRITE) && !inode_owner_or_capable(inode))
+ (mask & MAY_WRITE) &&
+ !inode_owner_or_capable(mnt_userns, inode))
return -EPERM;
}
- return inode_permission(inode, mask);
+ return inode_permission(mnt_userns, inode, mask);
}
/*
EXPORT_SYMBOL(xattr_supported_namespace);
int
-__vfs_setxattr(struct dentry *dentry, struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
+__vfs_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct inode *inode, const char *name, const void *value,
+ size_t size, int flags)
{
const struct xattr_handler *handler;
return -EOPNOTSUPP;
if (size == 0)
value = ""; /* empty EA, do not remove */
- return handler->set(handler, dentry, inode, name, value, size, flags);
+ return handler->set(handler, mnt_userns, dentry, inode, name, value,
+ size, flags);
}
EXPORT_SYMBOL(__vfs_setxattr);
* __vfs_setxattr_noperm - perform setxattr operation without performing
* permission checks.
*
+ * @mnt_userns - user namespace of the mount the inode was found from
* @dentry - object to perform setxattr on
* @name - xattr name to set
* @value - value to set @name to
* is executed. It also assumes that the caller will make the appropriate
* permission checks.
*/
-int __vfs_setxattr_noperm(struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags)
+int __vfs_setxattr_noperm(struct user_namespace *mnt_userns,
+ struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags)
{
struct inode *inode = dentry->d_inode;
int error = -EAGAIN;
if (issec)
inode->i_flags &= ~S_NOSEC;
if (inode->i_opflags & IOP_XATTR) {
- error = __vfs_setxattr(dentry, inode, name, value, size, flags);
+ error = __vfs_setxattr(mnt_userns, dentry, inode, name, value,
+ size, flags);
if (!error) {
fsnotify_xattr(dentry);
security_inode_post_setxattr(dentry, name, value,
* a delegation was broken on, NULL if none.
*/
int
-__vfs_setxattr_locked(struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags,
- struct inode **delegated_inode)
+__vfs_setxattr_locked(struct user_namespace *mnt_userns, struct dentry *dentry,
+ const char *name, const void *value, size_t size,
+ int flags, struct inode **delegated_inode)
{
struct inode *inode = dentry->d_inode;
int error;
- error = xattr_permission(inode, name, MAY_WRITE);
+ error = xattr_permission(mnt_userns, inode, name, MAY_WRITE);
if (error)
return error;
- error = security_inode_setxattr(dentry, name, value, size, flags);
+ error = security_inode_setxattr(mnt_userns, dentry, name, value, size,
+ flags);
if (error)
goto out;
if (error)
goto out;
- error = __vfs_setxattr_noperm(dentry, name, value, size, flags);
+ error = __vfs_setxattr_noperm(mnt_userns, dentry, name, value,
+ size, flags);
out:
return error;
EXPORT_SYMBOL_GPL(__vfs_setxattr_locked);
int
-vfs_setxattr(struct dentry *dentry, const char *name, const void *value,
- size_t size, int flags)
+vfs_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ const char *name, const void *value, size_t size, int flags)
{
struct inode *inode = dentry->d_inode;
struct inode *delegated_inode = NULL;
int error;
if (size && strcmp(name, XATTR_NAME_CAPS) == 0) {
- error = cap_convert_nscap(dentry, &value, size);
+ error = cap_convert_nscap(mnt_userns, dentry, &value, size);
if (error < 0)
return error;
size = error;
retry_deleg:
inode_lock(inode);
- error = __vfs_setxattr_locked(dentry, name, value, size, flags,
- &delegated_inode);
+ error = __vfs_setxattr_locked(mnt_userns, dentry, name, value, size,
+ flags, &delegated_inode);
inode_unlock(inode);
if (delegated_inode) {
EXPORT_SYMBOL_GPL(vfs_setxattr);
static ssize_t
-xattr_getsecurity(struct inode *inode, const char *name, void *value,
- size_t size)
+xattr_getsecurity(struct user_namespace *mnt_userns, struct inode *inode,
+ const char *name, void *value, size_t size)
{
void *buffer = NULL;
ssize_t len;
if (!value || !size) {
- len = security_inode_getsecurity(inode, name, &buffer, false);
+ len = security_inode_getsecurity(mnt_userns, inode, name,
+ &buffer, false);
goto out_noalloc;
}
- len = security_inode_getsecurity(inode, name, &buffer, true);
+ len = security_inode_getsecurity(mnt_userns, inode, name, &buffer,
+ true);
if (len < 0)
return len;
if (size < len) {
* Returns the result of alloc, if failed, or the getxattr operation.
*/
ssize_t
-vfs_getxattr_alloc(struct dentry *dentry, const char *name, char **xattr_value,
- size_t xattr_size, gfp_t flags)
+vfs_getxattr_alloc(struct user_namespace *mnt_userns, struct dentry *dentry,
+ const char *name, char **xattr_value, size_t xattr_size,
+ gfp_t flags)
{
const struct xattr_handler *handler;
struct inode *inode = dentry->d_inode;
char *value = *xattr_value;
int error;
- error = xattr_permission(inode, name, MAY_READ);
+ error = xattr_permission(mnt_userns, inode, name, MAY_READ);
if (error)
return error;
EXPORT_SYMBOL(__vfs_getxattr);
ssize_t
-vfs_getxattr(struct dentry *dentry, const char *name, void *value, size_t size)
+vfs_getxattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ const char *name, void *value, size_t size)
{
struct inode *inode = dentry->d_inode;
int error;
- error = xattr_permission(inode, name, MAY_READ);
+ error = xattr_permission(mnt_userns, inode, name, MAY_READ);
if (error)
return error;
if (!strncmp(name, XATTR_SECURITY_PREFIX,
XATTR_SECURITY_PREFIX_LEN)) {
const char *suffix = name + XATTR_SECURITY_PREFIX_LEN;
- int ret = xattr_getsecurity(inode, suffix, value, size);
+ int ret = xattr_getsecurity(mnt_userns, inode, suffix, value,
+ size);
/*
* Only overwrite the return value if a security module
* is actually active.
EXPORT_SYMBOL_GPL(vfs_listxattr);
int
-__vfs_removexattr(struct dentry *dentry, const char *name)
+__vfs_removexattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ const char *name)
{
struct inode *inode = d_inode(dentry);
const struct xattr_handler *handler;
return PTR_ERR(handler);
if (!handler->set)
return -EOPNOTSUPP;
- return handler->set(handler, dentry, inode, name, NULL, 0, XATTR_REPLACE);
+ return handler->set(handler, mnt_userns, dentry, inode, name, NULL, 0,
+ XATTR_REPLACE);
}
EXPORT_SYMBOL(__vfs_removexattr);
* a delegation was broken on, NULL if none.
*/
int
-__vfs_removexattr_locked(struct dentry *dentry, const char *name,
- struct inode **delegated_inode)
+__vfs_removexattr_locked(struct user_namespace *mnt_userns,
+ struct dentry *dentry, const char *name,
+ struct inode **delegated_inode)
{
struct inode *inode = dentry->d_inode;
int error;
- error = xattr_permission(inode, name, MAY_WRITE);
+ error = xattr_permission(mnt_userns, inode, name, MAY_WRITE);
if (error)
return error;
- error = security_inode_removexattr(dentry, name);
+ error = security_inode_removexattr(mnt_userns, dentry, name);
if (error)
goto out;
if (error)
goto out;
- error = __vfs_removexattr(dentry, name);
+ error = __vfs_removexattr(mnt_userns, dentry, name);
if (!error) {
fsnotify_xattr(dentry);
EXPORT_SYMBOL_GPL(__vfs_removexattr_locked);
int
-vfs_removexattr(struct dentry *dentry, const char *name)
+vfs_removexattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+ const char *name)
{
struct inode *inode = dentry->d_inode;
struct inode *delegated_inode = NULL;
retry_deleg:
inode_lock(inode);
- error = __vfs_removexattr_locked(dentry, name, &delegated_inode);
+ error = __vfs_removexattr_locked(mnt_userns, dentry,
+ name, &delegated_inode);
inode_unlock(inode);
if (delegated_inode) {
* Extended attribute SET operations
*/
static long
-setxattr(struct dentry *d, const char __user *name, const void __user *value,
- size_t size, int flags)
+setxattr(struct user_namespace *mnt_userns, struct dentry *d,
+ const char __user *name, const void __user *value, size_t size,
+ int flags)
{
int error;
void *kvalue = NULL;
}
if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) ||
(strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0))
- posix_acl_fix_xattr_from_user(kvalue, size);
+ posix_acl_fix_xattr_from_user(mnt_userns, kvalue, size);
}
- error = vfs_setxattr(d, kname, kvalue, size, flags);
+ error = vfs_setxattr(mnt_userns, d, kname, kvalue, size, flags);
out:
kvfree(kvalue);
{
struct path path;
int error;
+
retry:
error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
if (error)
return error;
error = mnt_want_write(path.mnt);
if (!error) {
- error = setxattr(path.dentry, name, value, size, flags);
+ error = setxattr(mnt_user_ns(path.mnt), path.dentry, name,
+ value, size, flags);
mnt_drop_write(path.mnt);
}
path_put(&path);
audit_file(f.file);
error = mnt_want_write_file(f.file);
if (!error) {
- error = setxattr(f.file->f_path.dentry, name, value, size, flags);
+ error = setxattr(file_mnt_user_ns(f.file),
+ f.file->f_path.dentry, name,
+ value, size, flags);
mnt_drop_write_file(f.file);
}
fdput(f);
* Extended attribute GET operations
*/
static ssize_t
-getxattr(struct dentry *d, const char __user *name, void __user *value,
- size_t size)
+getxattr(struct user_namespace *mnt_userns, struct dentry *d,
+ const char __user *name, void __user *value, size_t size)
{
ssize_t error;
void *kvalue = NULL;
return -ENOMEM;
}
- error = vfs_getxattr(d, kname, kvalue, size);
+ error = vfs_getxattr(mnt_userns, d, kname, kvalue, size);
if (error > 0) {
if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) ||
(strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0))
- posix_acl_fix_xattr_to_user(kvalue, error);
+ posix_acl_fix_xattr_to_user(mnt_userns, kvalue, error);
if (size && copy_to_user(value, kvalue, error))
error = -EFAULT;
} else if (error == -ERANGE && size >= XATTR_SIZE_MAX) {
error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
if (error)
return error;
- error = getxattr(path.dentry, name, value, size);
+ error = getxattr(mnt_user_ns(path.mnt), path.dentry, name, value, size);
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
if (!f.file)
return error;
audit_file(f.file);
- error = getxattr(f.file->f_path.dentry, name, value, size);
+ error = getxattr(file_mnt_user_ns(f.file), f.file->f_path.dentry,
+ name, value, size);
fdput(f);
return error;
}
* Extended attribute REMOVE operations
*/
static long
-removexattr(struct dentry *d, const char __user *name)
+removexattr(struct user_namespace *mnt_userns, struct dentry *d,
+ const char __user *name)
{
int error;
char kname[XATTR_NAME_MAX + 1];
if (error < 0)
return error;
- return vfs_removexattr(d, kname);
+ return vfs_removexattr(mnt_userns, d, kname);
}
static int path_removexattr(const char __user *pathname,
return error;
error = mnt_want_write(path.mnt);
if (!error) {
- error = removexattr(path.dentry, name);
+ error = removexattr(mnt_user_ns(path.mnt), path.dentry, name);
mnt_drop_write(path.mnt);
}
path_put(&path);
audit_file(f.file);
error = mnt_want_write_file(f.file);
if (!error) {
- error = removexattr(f.file->f_path.dentry, name);
+ error = removexattr(file_mnt_user_ns(f.file),
+ f.file->f_path.dentry, name);
mnt_drop_write_file(f.file);
}
fdput(f);
}
int
-xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+xfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
+ struct posix_acl *acl, int type)
{
umode_t mode;
bool set_mode = false;
return error;
if (type == ACL_TYPE_ACCESS) {
- error = posix_acl_update_mode(inode, &mode, &acl);
+ error = posix_acl_update_mode(mnt_userns, inode, &mode, &acl);
if (error)
return error;
set_mode = true;
#ifdef CONFIG_XFS_POSIX_ACL
extern struct posix_acl *xfs_get_acl(struct inode *inode, int type);
-extern int xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type);
+extern int xfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
+ struct posix_acl *acl, int type);
extern int __xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type);
void xfs_forget_acl(struct inode *inode, const char *name);
#else
#include <linux/backing-dev.h>
#include <linux/mman.h>
#include <linux/fadvise.h>
+#include <linux/mount.h>
static const struct vm_operations_struct xfs_file_vm_ops;
iattr.ia_valid = ATTR_SIZE;
iattr.ia_size = new_size;
- error = xfs_vn_setattr_size(file_dentry(file), &iattr);
+ error = xfs_vn_setattr_size(file_mnt_user_ns(file),
+ file_dentry(file), &iattr);
if (error)
goto out_unlock;
}
*/
static int
xfs_init_new_inode(
+ struct user_namespace *mnt_userns,
struct xfs_trans *tp,
struct xfs_inode *pip,
xfs_ino_t ino,
if (dir && !(dir->i_mode & S_ISGID) &&
(mp->m_flags & XFS_MOUNT_GRPID)) {
- inode->i_uid = current_fsuid();
+ inode->i_uid = fsuid_into_mnt(mnt_userns);
inode->i_gid = dir->i_gid;
inode->i_mode = mode;
} else {
- inode_init_owner(inode, dir, mode);
+ inode_init_owner(mnt_userns, inode, dir, mode);
}
/*
* (and only if the irix_sgid_inherit compatibility variable is set).
*/
if (irix_sgid_inherit &&
- (inode->i_mode & S_ISGID) && !in_group_p(inode->i_gid))
+ (inode->i_mode & S_ISGID) &&
+ !in_group_p(i_gid_into_mnt(mnt_userns, inode)))
inode->i_mode &= ~S_ISGID;
ip->i_d.di_size = 0;
*/
int
xfs_dir_ialloc(
+ struct user_namespace *mnt_userns,
struct xfs_trans **tpp,
struct xfs_inode *dp,
umode_t mode,
return error;
ASSERT(ino != NULLFSINO);
- return xfs_init_new_inode(*tpp, dp, ino, mode, nlink, rdev, prid, ipp);
+ return xfs_init_new_inode(mnt_userns, *tpp, dp, ino, mode, nlink, rdev,
+ prid, ipp);
}
/*
int
xfs_create(
+ struct user_namespace *mnt_userns,
xfs_inode_t *dp,
struct xfs_name *name,
umode_t mode,
* entry pointing to them, but a directory also the "." entry
* pointing to itself.
*/
- error = xfs_dir_ialloc(&tp, dp, mode, is_dir ? 2 : 1, rdev, prid, &ip);
+ error = xfs_dir_ialloc(mnt_userns, &tp, dp, mode, is_dir ? 2 : 1, rdev,
+ prid, &ip);
if (error)
goto out_trans_cancel;
int
xfs_create_tmpfile(
+ struct user_namespace *mnt_userns,
struct xfs_inode *dp,
umode_t mode,
struct xfs_inode **ipp)
if (error)
goto out_release_dquots;
- error = xfs_dir_ialloc(&tp, dp, mode, 0, 0, prid, &ip);
+ error = xfs_dir_ialloc(mnt_userns, &tp, dp, mode, 0, 0, prid, &ip);
if (error)
goto out_trans_cancel;
*/
static int
xfs_rename_alloc_whiteout(
+ struct user_namespace *mnt_userns,
struct xfs_inode *dp,
struct xfs_inode **wip)
{
struct xfs_inode *tmpfile;
int error;
- error = xfs_create_tmpfile(dp, S_IFCHR | WHITEOUT_MODE, &tmpfile);
+ error = xfs_create_tmpfile(mnt_userns, dp, S_IFCHR | WHITEOUT_MODE,
+ &tmpfile);
if (error)
return error;
*/
int
xfs_rename(
+ struct user_namespace *mnt_userns,
struct xfs_inode *src_dp,
struct xfs_name *src_name,
struct xfs_inode *src_ip,
*/
if (flags & RENAME_WHITEOUT) {
ASSERT(!(flags & (RENAME_NOREPLACE | RENAME_EXCHANGE)));
- error = xfs_rename_alloc_whiteout(target_dp, &wip);
+ error = xfs_rename_alloc_whiteout(mnt_userns, target_dp, &wip);
if (error)
return error;
void xfs_inactive(struct xfs_inode *ip);
int xfs_lookup(struct xfs_inode *dp, struct xfs_name *name,
struct xfs_inode **ipp, struct xfs_name *ci_name);
-int xfs_create(struct xfs_inode *dp, struct xfs_name *name,
+int xfs_create(struct user_namespace *mnt_userns,
+ struct xfs_inode *dp, struct xfs_name *name,
umode_t mode, dev_t rdev, struct xfs_inode **ipp);
-int xfs_create_tmpfile(struct xfs_inode *dp, umode_t mode,
+int xfs_create_tmpfile(struct user_namespace *mnt_userns,
+ struct xfs_inode *dp, umode_t mode,
struct xfs_inode **ipp);
int xfs_remove(struct xfs_inode *dp, struct xfs_name *name,
struct xfs_inode *ip);
int xfs_link(struct xfs_inode *tdp, struct xfs_inode *sip,
struct xfs_name *target_name);
-int xfs_rename(struct xfs_inode *src_dp, struct xfs_name *src_name,
+int xfs_rename(struct user_namespace *mnt_userns,
+ struct xfs_inode *src_dp, struct xfs_name *src_name,
struct xfs_inode *src_ip, struct xfs_inode *target_dp,
struct xfs_name *target_name,
struct xfs_inode *target_ip, unsigned int flags);
xfs_extlen_t xfs_get_extsz_hint(struct xfs_inode *ip);
xfs_extlen_t xfs_get_cowextsz_hint(struct xfs_inode *ip);
-int xfs_dir_ialloc(struct xfs_trans **tpp, struct xfs_inode *dp, umode_t mode,
- xfs_nlink_t nlink, dev_t dev, prid_t prid,
- struct xfs_inode **ipp);
+int xfs_dir_ialloc(struct user_namespace *mnt_userns,
+ struct xfs_trans **tpp, struct xfs_inode *dp,
+ umode_t mode, xfs_nlink_t nlink, dev_t dev,
+ prid_t prid, struct xfs_inode **ipp);
static inline int
xfs_itruncate_extents(
iattr.ia_valid = ATTR_SIZE;
iattr.ia_size = bf->l_start;
- error = xfs_vn_setattr_size(file_dentry(filp), &iattr);
+ error = xfs_vn_setattr_size(file_mnt_user_ns(filp), file_dentry(filp),
+ &iattr);
if (error)
goto out_unlock;
STATIC int
xfs_ioc_fsbulkstat(
- xfs_mount_t *mp,
+ struct file *file,
unsigned int cmd,
void __user *arg)
{
+ struct xfs_mount *mp = XFS_I(file_inode(file))->i_mount;
struct xfs_fsop_bulkreq bulkreq;
struct xfs_ibulk breq = {
.mp = mp,
+ .mnt_userns = file_mnt_user_ns(file),
.ocount = 0,
};
xfs_ino_t lastino;
/* Handle the v5 bulkstat ioctl. */
STATIC int
xfs_ioc_bulkstat(
- struct xfs_mount *mp,
+ struct file *file,
unsigned int cmd,
struct xfs_bulkstat_req __user *arg)
{
+ struct xfs_mount *mp = XFS_I(file_inode(file))->i_mount;
struct xfs_bulk_ireq hdr;
struct xfs_ibulk breq = {
.mp = mp,
+ .mnt_userns = file_mnt_user_ns(file),
};
int error;
*/
static struct xfs_trans *
xfs_ioctl_setattr_get_trans(
- struct xfs_inode *ip,
+ struct file *file,
struct xfs_dquot *pdqp)
{
+ struct xfs_inode *ip = XFS_I(file_inode(file));
struct xfs_mount *mp = ip->i_mount;
struct xfs_trans *tp;
int error = -EROFS;
* The user ID of the calling process must be equal to the file owner
* ID, except in cases where the CAP_FSETID capability is applicable.
*/
- if (!inode_owner_or_capable(VFS_I(ip))) {
+ if (!inode_owner_or_capable(file_mnt_user_ns(file), VFS_I(ip))) {
error = -EPERM;
goto out_cancel;
}
STATIC int
xfs_ioctl_setattr(
- xfs_inode_t *ip,
+ struct file *file,
struct fsxattr *fa)
{
+ struct user_namespace *mnt_userns = file_mnt_user_ns(file);
+ struct xfs_inode *ip = XFS_I(file_inode(file));
struct fsxattr old_fa;
struct xfs_mount *mp = ip->i_mount;
struct xfs_trans *tp;
xfs_ioctl_setattr_prepare_dax(ip, fa);
- tp = xfs_ioctl_setattr_get_trans(ip, pdqp);
+ tp = xfs_ioctl_setattr_get_trans(file, pdqp);
if (IS_ERR(tp)) {
error = PTR_ERR(tp);
goto error_free_dquots;
*/
if ((VFS_I(ip)->i_mode & (S_ISUID|S_ISGID)) &&
- !capable_wrt_inode_uidgid(VFS_I(ip), CAP_FSETID))
+ !capable_wrt_inode_uidgid(mnt_userns, VFS_I(ip), CAP_FSETID))
VFS_I(ip)->i_mode &= ~(S_ISUID|S_ISGID);
/* Change the ownerships and register project quota modifications */
STATIC int
xfs_ioc_fssetxattr(
- xfs_inode_t *ip,
struct file *filp,
void __user *arg)
{
error = mnt_want_write_file(filp);
if (error)
return error;
- error = xfs_ioctl_setattr(ip, &fa);
+ error = xfs_ioctl_setattr(filp, &fa);
mnt_drop_write_file(filp);
return error;
}
xfs_ioctl_setattr_prepare_dax(ip, &fa);
- tp = xfs_ioctl_setattr_get_trans(ip, NULL);
+ tp = xfs_ioctl_setattr_get_trans(filp, NULL);
if (IS_ERR(tp)) {
error = PTR_ERR(tp);
goto out_drop_write;
case XFS_IOC_FSBULKSTAT_SINGLE:
case XFS_IOC_FSBULKSTAT:
case XFS_IOC_FSINUMBERS:
- return xfs_ioc_fsbulkstat(mp, cmd, arg);
+ return xfs_ioc_fsbulkstat(filp, cmd, arg);
case XFS_IOC_BULKSTAT:
- return xfs_ioc_bulkstat(mp, cmd, arg);
+ return xfs_ioc_bulkstat(filp, cmd, arg);
case XFS_IOC_INUMBERS:
return xfs_ioc_inumbers(mp, cmd, arg);
case XFS_IOC_FSGETXATTRA:
return xfs_ioc_fsgetxattr(ip, 1, arg);
case XFS_IOC_FSSETXATTR:
- return xfs_ioc_fssetxattr(ip, filp, arg);
+ return xfs_ioc_fssetxattr(filp, arg);
case XFS_IOC_GETXFLAGS:
return xfs_ioc_getxflags(ip, arg);
case XFS_IOC_SETXFLAGS:
/* copied from xfs_ioctl.c */
STATIC int
xfs_compat_ioc_fsbulkstat(
- xfs_mount_t *mp,
+ struct file *file,
unsigned int cmd,
struct compat_xfs_fsop_bulkreq __user *p32)
{
+ struct xfs_mount *mp = XFS_I(file_inode(file))->i_mount;
u32 addr;
struct xfs_fsop_bulkreq bulkreq;
struct xfs_ibulk breq = {
.mp = mp,
+ .mnt_userns = file_mnt_user_ns(file),
.ocount = 0,
};
xfs_ino_t lastino;
{
struct inode *inode = file_inode(filp);
struct xfs_inode *ip = XFS_I(inode);
- struct xfs_mount *mp = ip->i_mount;
void __user *arg = compat_ptr(p);
int error;
return xfs_ioc_space(filp, &bf);
}
case XFS_IOC_FSGEOMETRY_V1_32:
- return xfs_compat_ioc_fsgeometry_v1(mp, arg);
+ return xfs_compat_ioc_fsgeometry_v1(ip->i_mount, arg);
case XFS_IOC_FSGROWFSDATA_32: {
struct xfs_growfs_data in;
error = mnt_want_write_file(filp);
if (error)
return error;
- error = xfs_growfs_data(mp, &in);
+ error = xfs_growfs_data(ip->i_mount, &in);
mnt_drop_write_file(filp);
return error;
}
error = mnt_want_write_file(filp);
if (error)
return error;
- error = xfs_growfs_rt(mp, &in);
+ error = xfs_growfs_rt(ip->i_mount, &in);
mnt_drop_write_file(filp);
return error;
}
case XFS_IOC_FSBULKSTAT_32:
case XFS_IOC_FSBULKSTAT_SINGLE_32:
case XFS_IOC_FSINUMBERS_32:
- return xfs_compat_ioc_fsbulkstat(mp, cmd, arg);
+ return xfs_compat_ioc_fsbulkstat(filp, cmd, arg);
case XFS_IOC_FD_TO_HANDLE_32:
case XFS_IOC_PATH_TO_HANDLE_32:
case XFS_IOC_PATH_TO_FSHANDLE_32: {
STATIC int
xfs_generic_create(
+ struct user_namespace *mnt_userns,
struct inode *dir,
struct dentry *dentry,
umode_t mode,
goto out_free_acl;
if (!tmpfile) {
- error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip);
+ error = xfs_create(mnt_userns, XFS_I(dir), &name, mode, rdev,
+ &ip);
} else {
- error = xfs_create_tmpfile(XFS_I(dir), mode, &ip);
+ error = xfs_create_tmpfile(mnt_userns, XFS_I(dir), mode, &ip);
}
if (unlikely(error))
goto out_free_acl;
STATIC int
xfs_vn_mknod(
- struct inode *dir,
- struct dentry *dentry,
- umode_t mode,
- dev_t rdev)
+ struct user_namespace *mnt_userns,
+ struct inode *dir,
+ struct dentry *dentry,
+ umode_t mode,
+ dev_t rdev)
{
- return xfs_generic_create(dir, dentry, mode, rdev, false);
+ return xfs_generic_create(mnt_userns, dir, dentry, mode, rdev, false);
}
STATIC int
xfs_vn_create(
- struct inode *dir,
- struct dentry *dentry,
- umode_t mode,
- bool flags)
+ struct user_namespace *mnt_userns,
+ struct inode *dir,
+ struct dentry *dentry,
+ umode_t mode,
+ bool flags)
{
- return xfs_generic_create(dir, dentry, mode, 0, false);
+ return xfs_generic_create(mnt_userns, dir, dentry, mode, 0, false);
}
STATIC int
xfs_vn_mkdir(
- struct inode *dir,
- struct dentry *dentry,
- umode_t mode)
+ struct user_namespace *mnt_userns,
+ struct inode *dir,
+ struct dentry *dentry,
+ umode_t mode)
{
- return xfs_generic_create(dir, dentry, mode | S_IFDIR, 0, false);
+ return xfs_generic_create(mnt_userns, dir, dentry, mode | S_IFDIR, 0,
+ false);
}
STATIC struct dentry *
STATIC int
xfs_vn_symlink(
- struct inode *dir,
- struct dentry *dentry,
- const char *symname)
+ struct user_namespace *mnt_userns,
+ struct inode *dir,
+ struct dentry *dentry,
+ const char *symname)
{
struct inode *inode;
struct xfs_inode *cip = NULL;
if (unlikely(error))
goto out;
- error = xfs_symlink(XFS_I(dir), &name, symname, mode, &cip);
+ error = xfs_symlink(mnt_userns, XFS_I(dir), &name, symname, mode, &cip);
if (unlikely(error))
goto out;
STATIC int
xfs_vn_rename(
- struct inode *odir,
- struct dentry *odentry,
- struct inode *ndir,
- struct dentry *ndentry,
- unsigned int flags)
+ struct user_namespace *mnt_userns,
+ struct inode *odir,
+ struct dentry *odentry,
+ struct inode *ndir,
+ struct dentry *ndentry,
+ unsigned int flags)
{
struct inode *new_inode = d_inode(ndentry);
int omode = 0;
if (unlikely(error))
return error;
- return xfs_rename(XFS_I(odir), &oname, XFS_I(d_inode(odentry)),
- XFS_I(ndir), &nname,
+ return xfs_rename(mnt_userns, XFS_I(odir), &oname,
+ XFS_I(d_inode(odentry)), XFS_I(ndir), &nname,
new_inode ? XFS_I(new_inode) : NULL, flags);
}
STATIC int
xfs_vn_getattr(
+ struct user_namespace *mnt_userns,
const struct path *path,
struct kstat *stat,
u32 request_mask,
stat->dev = inode->i_sb->s_dev;
stat->mode = inode->i_mode;
stat->nlink = inode->i_nlink;
- stat->uid = inode->i_uid;
- stat->gid = inode->i_gid;
+ stat->uid = i_uid_into_mnt(mnt_userns, inode);
+ stat->gid = i_gid_into_mnt(mnt_userns, inode);
stat->ino = ip->i_ino;
stat->atime = inode->i_atime;
stat->mtime = inode->i_mtime;
static int
xfs_vn_change_ok(
- struct dentry *dentry,
- struct iattr *iattr)
+ struct user_namespace *mnt_userns,
+ struct dentry *dentry,
+ struct iattr *iattr)
{
struct xfs_mount *mp = XFS_I(d_inode(dentry))->i_mount;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
- return setattr_prepare(dentry, iattr);
+ return setattr_prepare(mnt_userns, dentry, iattr);
}
/*
*/
static int
xfs_setattr_nonsize(
+ struct user_namespace *mnt_userns,
struct xfs_inode *ip,
struct iattr *iattr)
{
* Posix ACL code seems to care about this issue either.
*/
if (mask & ATTR_MODE) {
- error = posix_acl_chmod(inode, inode->i_mode);
+ error = posix_acl_chmod(mnt_userns, inode, inode->i_mode);
if (error)
return error;
}
*/
STATIC int
xfs_setattr_size(
+ struct user_namespace *mnt_userns,
struct xfs_inode *ip,
struct iattr *iattr)
{
* Use the regular setattr path to update the timestamps.
*/
iattr->ia_valid &= ~ATTR_SIZE;
- return xfs_setattr_nonsize(ip, iattr);
+ return xfs_setattr_nonsize(mnt_userns, ip, iattr);
}
/*
int
xfs_vn_setattr_size(
+ struct user_namespace *mnt_userns,
struct dentry *dentry,
struct iattr *iattr)
{
trace_xfs_setattr(ip);
- error = xfs_vn_change_ok(dentry, iattr);
+ error = xfs_vn_change_ok(mnt_userns, dentry, iattr);
if (error)
return error;
- return xfs_setattr_size(ip, iattr);
+ return xfs_setattr_size(mnt_userns, ip, iattr);
}
STATIC int
xfs_vn_setattr(
+ struct user_namespace *mnt_userns,
struct dentry *dentry,
struct iattr *iattr)
{
return error;
}
- error = xfs_vn_setattr_size(dentry, iattr);
+ error = xfs_vn_setattr_size(mnt_userns, dentry, iattr);
xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
} else {
trace_xfs_setattr(ip);
- error = xfs_vn_change_ok(dentry, iattr);
+ error = xfs_vn_change_ok(mnt_userns, dentry, iattr);
if (!error)
- error = xfs_setattr_nonsize(ip, iattr);
+ error = xfs_setattr_nonsize(mnt_userns, ip, iattr);
}
return error;
STATIC int
xfs_vn_tmpfile(
- struct inode *dir,
- struct dentry *dentry,
- umode_t mode)
+ struct user_namespace *mnt_userns,
+ struct inode *dir,
+ struct dentry *dentry,
+ umode_t mode)
{
- return xfs_generic_create(dir, dentry, mode, 0, true);
+ return xfs_generic_create(mnt_userns, dir, dentry, mode, 0, true);
}
static const struct inode_operations xfs_inode_operations = {
extern ssize_t xfs_vn_listxattr(struct dentry *, char *data, size_t size);
extern void xfs_setattr_time(struct xfs_inode *ip, struct iattr *iattr);
-extern int xfs_vn_setattr_size(struct dentry *dentry, struct iattr *vap);
+int xfs_vn_setattr_size(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct iattr *vap);
#endif /* __XFS_IOPS_H__ */
STATIC int
xfs_bulkstat_one_int(
struct xfs_mount *mp,
+ struct user_namespace *mnt_userns,
struct xfs_trans *tp,
xfs_ino_t ino,
struct xfs_bstat_chunk *bc)
{
+ struct user_namespace *sb_userns = mp->m_super->s_user_ns;
struct xfs_icdinode *dic; /* dinode core info pointer */
struct xfs_inode *ip; /* incore inode pointer */
struct inode *inode;
*/
buf->bs_projectid = ip->i_d.di_projid;
buf->bs_ino = ino;
- buf->bs_uid = i_uid_read(inode);
- buf->bs_gid = i_gid_read(inode);
+ buf->bs_uid = from_kuid(sb_userns, i_uid_into_mnt(mnt_userns, inode));
+ buf->bs_gid = from_kgid(sb_userns, i_gid_into_mnt(mnt_userns, inode));
buf->bs_size = dic->di_size;
buf->bs_nlink = inode->i_nlink;
if (!bc.buf)
return -ENOMEM;
- error = xfs_bulkstat_one_int(breq->mp, NULL, breq->startino, &bc);
+ error = xfs_bulkstat_one_int(breq->mp, breq->mnt_userns, NULL,
+ breq->startino, &bc);
kmem_free(bc.buf);
xfs_ino_t ino,
void *data)
{
+ struct xfs_bstat_chunk *bc = data;
int error;
- error = xfs_bulkstat_one_int(mp, tp, ino, data);
+ error = xfs_bulkstat_one_int(mp, bc->breq->mnt_userns, tp, ino, data);
/* bulkstat just skips over missing inodes */
if (error == -ENOENT || error == -EINVAL)
return 0;
};
int error;
+ if (breq->mnt_userns != &init_user_ns) {
+ xfs_warn_ratelimited(breq->mp,
+ "bulkstat not supported inside of idmapped mounts.");
+ return -EINVAL;
+ }
if (xfs_bulkstat_already_done(breq->mp, breq->startino))
return 0;
/* In-memory representation of a userspace request for batch inode data. */
struct xfs_ibulk {
struct xfs_mount *mp;
+ struct user_namespace *mnt_userns;
void __user *ubuffer; /* user output buffer */
xfs_ino_t startino; /* start with this inode */
unsigned int icount; /* number of elements in ubuffer */
return error;
if (need_alloc) {
- error = xfs_dir_ialloc(&tp, NULL, S_IFREG, 1, 0, 0, ipp);
+ error = xfs_dir_ialloc(&init_user_ns, &tp, NULL, S_IFREG, 1, 0,
+ 0, ipp);
if (error) {
xfs_trans_cancel(tp);
return error;
.init_fs_context = xfs_init_fs_context,
.parameters = xfs_fs_parameters,
.kill_sb = kill_block_super,
- .fs_flags = FS_REQUIRES_DEV,
+ .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP,
};
MODULE_ALIAS_FS("xfs");
int
xfs_symlink(
+ struct user_namespace *mnt_userns,
struct xfs_inode *dp,
struct xfs_name *link_name,
const char *target_path,
/*
* Allocate an inode for the symlink.
*/
- error = xfs_dir_ialloc(&tp, dp, S_IFLNK | (mode & ~S_IFMT), 1, 0,
- prid, &ip);
+ error = xfs_dir_ialloc(mnt_userns, &tp, dp, S_IFLNK | (mode & ~S_IFMT),
+ 1, 0, prid, &ip);
if (error)
goto out_trans_cancel;
/* Kernel only symlink definitions */
-int xfs_symlink(struct xfs_inode *dp, struct xfs_name *link_name,
- const char *target_path, umode_t mode, struct xfs_inode **ipp);
+int xfs_symlink(struct user_namespace *mnt_userns, struct xfs_inode *dp,
+ struct xfs_name *link_name, const char *target_path,
+ umode_t mode, struct xfs_inode **ipp);
int xfs_readlink_bmap_ilocked(struct xfs_inode *ip, char *link);
int xfs_readlink(struct xfs_inode *ip, char *link);
int xfs_inactive_symlink(struct xfs_inode *ip);
}
static int
-xfs_xattr_set(const struct xattr_handler *handler, struct dentry *unused,
- struct inode *inode, const char *name, const void *value,
- size_t size, int flags)
+xfs_xattr_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns, struct dentry *unused,
+ struct inode *inode, const char *name, const void *value,
+ size_t size, int flags)
{
struct xfs_da_args args = {
.dp = XFS_I(inode),
return ret;
}
-static int zonefs_inode_setattr(struct dentry *dentry, struct iattr *iattr)
+static int zonefs_inode_setattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct iattr *iattr)
{
struct inode *inode = d_inode(dentry);
int ret;
if (unlikely(IS_IMMUTABLE(inode)))
return -EPERM;
- ret = setattr_prepare(dentry, iattr);
+ ret = setattr_prepare(&init_user_ns, dentry, iattr);
if (ret)
return ret;
return ret;
}
- setattr_copy(inode, iattr);
+ setattr_copy(&init_user_ns, inode, iattr);
return 0;
}
struct super_block *sb = parent->i_sb;
inode->i_ino = blkdev_nr_zones(sb->s_bdev->bd_disk) + type + 1;
- inode_init_owner(inode, parent, S_IFDIR | 0555);
+ inode_init_owner(&init_user_ns, inode, parent, S_IFDIR | 0555);
inode->i_op = &zonefs_dir_inode_operations;
inode->i_fop = &simple_dir_operations;
set_nlink(inode, 2);
return true;
}
#endif /* CONFIG_MULTIUSER */
-extern bool privileged_wrt_inode_uidgid(struct user_namespace *ns, const struct inode *inode);
-extern bool capable_wrt_inode_uidgid(const struct inode *inode, int cap);
+bool privileged_wrt_inode_uidgid(struct user_namespace *ns,
+ struct user_namespace *mnt_userns,
+ const struct inode *inode);
+bool capable_wrt_inode_uidgid(struct user_namespace *mnt_userns,
+ const struct inode *inode, int cap);
extern bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap);
extern bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns);
static inline bool perfmon_capable(void)
}
/* audit system wants to get cap info from files as well */
-extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps);
+int get_vfs_caps_from_disk(struct user_namespace *mnt_userns,
+ const struct dentry *dentry,
+ struct cpu_vfs_cap_data *cpu_caps);
-extern int cap_convert_nscap(struct dentry *dentry, const void **ivalue, size_t size);
+int cap_convert_nscap(struct user_namespace *mnt_userns, struct dentry *dentry,
+ const void **ivalue, size_t size);
#endif /* !_LINUX_CAPABILITY_H */
#include <linux/fs_types.h>
#include <linux/build_bug.h>
#include <linux/stddef.h>
+#include <linux/mount.h>
+#include <linux/cred.h>
#include <asm/byteorder.h>
#include <uapi/linux/fs.h>
inode->i_gid = make_kgid(inode->i_sb->s_user_ns, gid);
}
+static inline kuid_t kuid_into_mnt(struct user_namespace *mnt_userns,
+ kuid_t kuid)
+{
+ return make_kuid(mnt_userns, __kuid_val(kuid));
+}
+
+static inline kgid_t kgid_into_mnt(struct user_namespace *mnt_userns,
+ kgid_t kgid)
+{
+ return make_kgid(mnt_userns, __kgid_val(kgid));
+}
+
+static inline kuid_t i_uid_into_mnt(struct user_namespace *mnt_userns,
+ const struct inode *inode)
+{
+ return kuid_into_mnt(mnt_userns, inode->i_uid);
+}
+
+static inline kgid_t i_gid_into_mnt(struct user_namespace *mnt_userns,
+ const struct inode *inode)
+{
+ return kgid_into_mnt(mnt_userns, inode->i_gid);
+}
+
+static inline kuid_t kuid_from_mnt(struct user_namespace *mnt_userns,
+ kuid_t kuid)
+{
+ return KUIDT_INIT(from_kuid(mnt_userns, kuid));
+}
+
+static inline kgid_t kgid_from_mnt(struct user_namespace *mnt_userns,
+ kgid_t kgid)
+{
+ return KGIDT_INIT(from_kgid(mnt_userns, kgid));
+}
+
+static inline kuid_t fsuid_into_mnt(struct user_namespace *mnt_userns)
+{
+ return kuid_from_mnt(mnt_userns, current_fsuid());
+}
+
+static inline kgid_t fsgid_into_mnt(struct user_namespace *mnt_userns)
+{
+ return kgid_from_mnt(mnt_userns, current_fsgid());
+}
+
extern struct timespec64 current_time(struct inode *inode);
/*
return __sb_start_write_trylock(sb, SB_FREEZE_FS);
}
-
-extern bool inode_owner_or_capable(const struct inode *inode);
+bool inode_owner_or_capable(struct user_namespace *mnt_userns,
+ const struct inode *inode);
/*
* VFS helper functions..
*/
-extern int vfs_create(struct inode *, struct dentry *, umode_t, bool);
-extern int vfs_mkdir(struct inode *, struct dentry *, umode_t);
-extern int vfs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
-extern int vfs_symlink(struct inode *, struct dentry *, const char *);
-extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct inode **);
-extern int vfs_rmdir(struct inode *, struct dentry *);
-extern int vfs_unlink(struct inode *, struct dentry *, struct inode **);
-extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int);
+int vfs_create(struct user_namespace *, struct inode *,
+ struct dentry *, umode_t, bool);
+int vfs_mkdir(struct user_namespace *, struct inode *,
+ struct dentry *, umode_t);
+int vfs_mknod(struct user_namespace *, struct inode *, struct dentry *,
+ umode_t, dev_t);
+int vfs_symlink(struct user_namespace *, struct inode *,
+ struct dentry *, const char *);
+int vfs_link(struct dentry *, struct user_namespace *, struct inode *,
+ struct dentry *, struct inode **);
+int vfs_rmdir(struct user_namespace *, struct inode *, struct dentry *);
+int vfs_unlink(struct user_namespace *, struct inode *, struct dentry *,
+ struct inode **);
+
+struct renamedata {
+ struct user_namespace *old_mnt_userns;
+ struct inode *old_dir;
+ struct dentry *old_dentry;
+ struct user_namespace *new_mnt_userns;
+ struct inode *new_dir;
+ struct dentry *new_dentry;
+ struct inode **delegated_inode;
+ unsigned int flags;
+} __randomize_layout;
-static inline int vfs_whiteout(struct inode *dir, struct dentry *dentry)
+int vfs_rename(struct renamedata *);
+
+static inline int vfs_whiteout(struct user_namespace *mnt_userns,
+ struct inode *dir, struct dentry *dentry)
{
- return vfs_mknod(dir, dentry, S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV);
+ return vfs_mknod(mnt_userns, dir, dentry, S_IFCHR | WHITEOUT_MODE,
+ WHITEOUT_DEV);
}
-extern struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode,
- int open_flag);
+struct dentry *vfs_tmpfile(struct user_namespace *mnt_userns,
+ struct dentry *dentry, umode_t mode, int open_flag);
int vfs_mkobj(struct dentry *, umode_t,
int (*f)(struct dentry *, umode_t, void *),
/*
* VFS file helper functions.
*/
-extern void inode_init_owner(struct inode *inode, const struct inode *dir,
- umode_t mode);
+void inode_init_owner(struct user_namespace *mnt_userns, struct inode *inode,
+ const struct inode *dir, umode_t mode);
extern bool may_open_dev(const struct path *path);
/*
struct inode_operations {
struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *);
- int (*permission) (struct inode *, int);
+ int (*permission) (struct user_namespace *, struct inode *, int);
struct posix_acl * (*get_acl)(struct inode *, int);
int (*readlink) (struct dentry *, char __user *,int);
- int (*create) (struct inode *,struct dentry *, umode_t, bool);
+ int (*create) (struct user_namespace *, struct inode *,struct dentry *,
+ umode_t, bool);
int (*link) (struct dentry *,struct inode *,struct dentry *);
int (*unlink) (struct inode *,struct dentry *);
- int (*symlink) (struct inode *,struct dentry *,const char *);
- int (*mkdir) (struct inode *,struct dentry *,umode_t);
+ int (*symlink) (struct user_namespace *, struct inode *,struct dentry *,
+ const char *);
+ int (*mkdir) (struct user_namespace *, struct inode *,struct dentry *,
+ umode_t);
int (*rmdir) (struct inode *,struct dentry *);
- int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t);
- int (*rename) (struct inode *, struct dentry *,
+ int (*mknod) (struct user_namespace *, struct inode *,struct dentry *,
+ umode_t,dev_t);
+ int (*rename) (struct user_namespace *, struct inode *, struct dentry *,
struct inode *, struct dentry *, unsigned int);
- int (*setattr) (struct dentry *, struct iattr *);
- int (*getattr) (const struct path *, struct kstat *, u32, unsigned int);
+ int (*setattr) (struct user_namespace *, struct dentry *,
+ struct iattr *);
+ int (*getattr) (struct user_namespace *, const struct path *,
+ struct kstat *, u32, unsigned int);
ssize_t (*listxattr) (struct dentry *, char *, size_t);
int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
u64 len);
int (*atomic_open)(struct inode *, struct dentry *,
struct file *, unsigned open_flag,
umode_t create_mode);
- int (*tmpfile) (struct inode *, struct dentry *, umode_t);
- int (*set_acl)(struct inode *, struct posix_acl *, int);
+ int (*tmpfile) (struct user_namespace *, struct inode *,
+ struct dentry *, umode_t);
+ int (*set_acl)(struct user_namespace *, struct inode *,
+ struct posix_acl *, int);
} ____cacheline_aligned;
static inline ssize_t call_read_iter(struct file *file, struct kiocb *kio,
#define IS_WHITEOUT(inode) (S_ISCHR(inode->i_mode) && \
(inode)->i_rdev == WHITEOUT_DEV)
-static inline bool HAS_UNMAPPED_ID(struct inode *inode)
+static inline bool HAS_UNMAPPED_ID(struct user_namespace *mnt_userns,
+ struct inode *inode)
{
- return !uid_valid(inode->i_uid) || !gid_valid(inode->i_gid);
+ return !uid_valid(i_uid_into_mnt(mnt_userns, inode)) ||
+ !gid_valid(i_gid_into_mnt(mnt_userns, inode));
}
static inline enum rw_hint file_write_hint(struct file *file)
#define FS_HAS_SUBTYPE 4
#define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */
#define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */
+#define FS_ALLOW_IDMAP 32 /* FS has been updated to handle vfs idmappings. */
#define FS_THP_SUPPORT 8192 /* Remove once all fs converted */
#define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */
int (*init_fs_context)(struct fs_context *);
};
static_assert(offsetof(struct filename, iname) % sizeof(long) == 0);
+static inline struct user_namespace *file_mnt_user_ns(struct file *file)
+{
+ return mnt_user_ns(file->f_path.mnt);
+}
extern long vfs_truncate(const struct path *, loff_t);
-extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs,
- struct file *filp);
+int do_truncate(struct user_namespace *, struct dentry *, loff_t start,
+ unsigned int time_attrs, struct file *filp);
extern int vfs_fallocate(struct file *file, int mode, loff_t offset,
loff_t len);
extern long do_sys_open(int dfd, const char __user *filename, int flags,
}
#endif
-extern int notify_change(struct dentry *, struct iattr *, struct inode **);
-extern int inode_permission(struct inode *, int);
-extern int generic_permission(struct inode *, int);
-extern int __check_sticky(struct inode *dir, struct inode *inode);
+int notify_change(struct user_namespace *, struct dentry *,
+ struct iattr *, struct inode **);
+int inode_permission(struct user_namespace *, struct inode *, int);
+int generic_permission(struct user_namespace *, struct inode *, int);
+static inline int file_permission(struct file *file, int mask)
+{
+ return inode_permission(file_mnt_user_ns(file),
+ file_inode(file), mask);
+}
+static inline int path_permission(const struct path *path, int mask)
+{
+ return inode_permission(mnt_user_ns(path->mnt),
+ d_inode(path->dentry), mask);
+}
+int __check_sticky(struct user_namespace *mnt_userns, struct inode *dir,
+ struct inode *inode);
static inline bool execute_ok(struct inode *inode)
{
extern int page_symlink(struct inode *inode, const char *symname, int len);
extern const struct inode_operations page_symlink_inode_operations;
extern void kfree_link(void *);
-extern void generic_fillattr(struct inode *, struct kstat *);
+void generic_fillattr(struct user_namespace *, struct inode *, struct kstat *);
extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int);
extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int);
void __inode_add_bytes(struct inode *inode, loff_t bytes);
extern int dcache_dir_close(struct inode *, struct file *);
extern loff_t dcache_dir_lseek(struct file *, loff_t, int);
extern int dcache_readdir(struct file *, struct dir_context *);
-extern int simple_setattr(struct dentry *, struct iattr *);
-extern int simple_getattr(const struct path *, struct kstat *, u32, unsigned int);
+extern int simple_setattr(struct user_namespace *, struct dentry *,
+ struct iattr *);
+extern int simple_getattr(struct user_namespace *, const struct path *,
+ struct kstat *, u32, unsigned int);
extern int simple_statfs(struct dentry *, struct kstatfs *);
extern int simple_open(struct inode *inode, struct file *file);
extern int simple_link(struct dentry *, struct inode *, struct dentry *);
extern int simple_unlink(struct inode *, struct dentry *);
extern int simple_rmdir(struct inode *, struct dentry *);
-extern int simple_rename(struct inode *, struct dentry *,
- struct inode *, struct dentry *, unsigned int);
+extern int simple_rename(struct user_namespace *, struct inode *,
+ struct dentry *, struct inode *, struct dentry *,
+ unsigned int);
extern void simple_recursive_removal(struct dentry *,
void (*callback)(struct dentry *));
extern int noop_fsync(struct file *, loff_t, loff_t, int);
#define buffer_migrate_page_norefs NULL
#endif
-extern int setattr_prepare(struct dentry *, struct iattr *);
+int setattr_prepare(struct user_namespace *, struct dentry *, struct iattr *);
extern int inode_newsize_ok(const struct inode *, loff_t offset);
-extern void setattr_copy(struct inode *inode, const struct iattr *attr);
+void setattr_copy(struct user_namespace *, struct inode *inode,
+ const struct iattr *attr);
extern int file_update_time(struct file *file);
return (mode & S_ISUID) || ((mode & S_ISGID) && (mode & S_IXGRP));
}
-static inline int check_sticky(struct inode *dir, struct inode *inode)
+static inline int check_sticky(struct user_namespace *mnt_userns,
+ struct inode *dir, struct inode *inode)
{
if (!(dir->i_mode & S_ISVTX))
return 0;
- return __check_sticky(dir, inode);
+ return __check_sticky(mnt_userns, dir, inode);
}
static inline void inode_has_no_xattr(struct inode *inode)
#ifdef CONFIG_IMA
extern int ima_bprm_check(struct linux_binprm *bprm);
extern int ima_file_check(struct file *file, int mask);
-extern void ima_post_create_tmpfile(struct inode *inode);
+extern void ima_post_create_tmpfile(struct user_namespace *mnt_userns,
+ struct inode *inode);
extern void ima_file_free(struct file *file);
extern int ima_file_mmap(struct file *file, unsigned long prot);
extern int ima_file_mprotect(struct vm_area_struct *vma, unsigned long prot);
bool contents);
extern int ima_post_read_file(struct file *file, void *buf, loff_t size,
enum kernel_read_file_id id);
-extern void ima_post_path_mknod(struct dentry *dentry);
+extern void ima_post_path_mknod(struct user_namespace *mnt_userns,
+ struct dentry *dentry);
extern int ima_file_hash(struct file *file, char *buf, size_t buf_size);
extern int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size);
extern void ima_kexec_cmdline(int kernel_fd, const void *buf, int size);
return 0;
}
-static inline void ima_post_create_tmpfile(struct inode *inode)
+static inline void ima_post_create_tmpfile(struct user_namespace *mnt_userns,
+ struct inode *inode)
{
}
return 0;
}
-static inline void ima_post_path_mknod(struct dentry *dentry)
+static inline void ima_post_path_mknod(struct user_namespace *mnt_userns,
+ struct dentry *dentry)
{
return;
}
#ifdef CONFIG_IMA_APPRAISE
extern bool is_ima_appraise_enabled(void);
-extern void ima_inode_post_setattr(struct dentry *dentry);
+extern void ima_inode_post_setattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry);
extern int ima_inode_setxattr(struct dentry *dentry, const char *xattr_name,
const void *xattr_value, size_t xattr_value_len);
extern int ima_inode_removexattr(struct dentry *dentry, const char *xattr_name);
return 0;
}
-static inline void ima_inode_post_setattr(struct dentry *dentry)
+static inline void ima_inode_post_setattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry)
{
return;
}
LSM_HOOK(int, 0, inode_permission, struct inode *inode, int mask)
LSM_HOOK(int, 0, inode_setattr, struct dentry *dentry, struct iattr *attr)
LSM_HOOK(int, 0, inode_getattr, const struct path *path)
-LSM_HOOK(int, 0, inode_setxattr, struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags)
+LSM_HOOK(int, 0, inode_setxattr, struct user_namespace *mnt_userns,
+ struct dentry *dentry, const char *name, const void *value,
+ size_t size, int flags)
LSM_HOOK(void, LSM_RET_VOID, inode_post_setxattr, struct dentry *dentry,
const char *name, const void *value, size_t size, int flags)
LSM_HOOK(int, 0, inode_getxattr, struct dentry *dentry, const char *name)
LSM_HOOK(int, 0, inode_listxattr, struct dentry *dentry)
-LSM_HOOK(int, 0, inode_removexattr, struct dentry *dentry, const char *name)
+LSM_HOOK(int, 0, inode_removexattr, struct user_namespace *mnt_userns,
+ struct dentry *dentry, const char *name)
LSM_HOOK(int, 0, inode_need_killpriv, struct dentry *dentry)
-LSM_HOOK(int, 0, inode_killpriv, struct dentry *dentry)
-LSM_HOOK(int, -EOPNOTSUPP, inode_getsecurity, struct inode *inode,
- const char *name, void **buffer, bool alloc)
+LSM_HOOK(int, 0, inode_killpriv, struct user_namespace *mnt_userns,
+ struct dentry *dentry)
+LSM_HOOK(int, -EOPNOTSUPP, inode_getsecurity, struct user_namespace *mnt_userns,
+ struct inode *inode, const char *name, void **buffer, bool alloc)
LSM_HOOK(int, -EOPNOTSUPP, inode_setsecurity, struct inode *inode,
const char *name, const void *value, size_t size, int flags)
LSM_HOOK(int, 0, inode_listsecurity, struct inode *inode, char *buffer,
* @inode_killpriv:
* The setuid bit is being removed. Remove similar security labels.
* Called with the dentry->d_inode->i_mutex held.
+ * @mnt_userns: user namespace of the mount
* @dentry is the dentry being changed.
* Return 0 on success. If error is returned, then the operation
* causing setuid bit removal is failed.
struct dentry *mnt_root; /* root of the mounted tree */
struct super_block *mnt_sb; /* pointer to superblock */
int mnt_flags;
+ struct user_namespace *mnt_userns;
} __randomize_layout;
+static inline struct user_namespace *mnt_user_ns(const struct vfsmount *mnt)
+{
+ /* Pairs with smp_store_release() in do_idmap_mount(). */
+ return smp_load_acquire(&mnt->mnt_userns);
+}
+
struct file; /* forward dec */
struct path;
extern int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr);
extern int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr);
extern int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr);
-extern int nfs_getattr(const struct path *, struct kstat *, u32, unsigned int);
+extern int nfs_getattr(struct user_namespace *, const struct path *,
+ struct kstat *, u32, unsigned int);
extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *);
extern void nfs_access_set_mask(struct nfs_access_entry *, u32);
-extern int nfs_permission(struct inode *, int);
+extern int nfs_permission(struct user_namespace *, struct inode *, int);
extern int nfs_open(struct inode *, struct file *);
extern int nfs_attribute_cache_expired(struct inode *inode);
extern int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode);
extern bool nfs_mapping_need_revalidate_inode(struct inode *inode);
extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping);
extern int nfs_revalidate_mapping_rcu(struct inode *inode);
-extern int nfs_setattr(struct dentry *, struct iattr *);
+extern int nfs_setattr(struct user_namespace *, struct dentry *, struct iattr *);
extern void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, struct nfs_fattr *);
extern void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr,
struct nfs4_label *label);
#include <linux/refcount.h>
#include <uapi/linux/posix_acl.h>
+struct user_namespace;
+
struct posix_acl_entry {
short e_tag;
unsigned short e_perm;
extern void posix_acl_init(struct posix_acl *, int);
extern struct posix_acl *posix_acl_alloc(int, gfp_t);
-extern int posix_acl_valid(struct user_namespace *, const struct posix_acl *);
-extern int posix_acl_permission(struct inode *, const struct posix_acl *, int);
extern struct posix_acl *posix_acl_from_mode(umode_t, gfp_t);
extern int posix_acl_equiv_mode(const struct posix_acl *, umode_t *);
extern int __posix_acl_create(struct posix_acl **, gfp_t, umode_t *);
extern int __posix_acl_chmod(struct posix_acl **, gfp_t, umode_t);
extern struct posix_acl *get_posix_acl(struct inode *, int);
-extern int set_posix_acl(struct inode *, int, struct posix_acl *);
+extern int set_posix_acl(struct user_namespace *, struct inode *, int,
+ struct posix_acl *);
#ifdef CONFIG_FS_POSIX_ACL
-extern int posix_acl_chmod(struct inode *, umode_t);
+int posix_acl_chmod(struct user_namespace *, struct inode *, umode_t);
extern int posix_acl_create(struct inode *, umode_t *, struct posix_acl **,
struct posix_acl **);
-extern int posix_acl_update_mode(struct inode *, umode_t *, struct posix_acl **);
+int posix_acl_update_mode(struct user_namespace *, struct inode *, umode_t *,
+ struct posix_acl **);
-extern int simple_set_acl(struct inode *, struct posix_acl *, int);
+extern int simple_set_acl(struct user_namespace *, struct inode *,
+ struct posix_acl *, int);
extern int simple_acl_create(struct inode *, struct inode *);
struct posix_acl *get_cached_acl(struct inode *inode, int type);
void set_cached_acl(struct inode *inode, int type, struct posix_acl *acl);
void forget_cached_acl(struct inode *inode, int type);
void forget_all_cached_acls(struct inode *inode);
+int posix_acl_valid(struct user_namespace *, const struct posix_acl *);
+int posix_acl_permission(struct user_namespace *, struct inode *,
+ const struct posix_acl *, int);
static inline void cache_no_acl(struct inode *inode)
{
inode->i_default_acl = NULL;
}
#else
-static inline int posix_acl_chmod(struct inode *inode, umode_t mode)
+static inline int posix_acl_chmod(struct user_namespace *mnt_userns,
+ struct inode *inode, umode_t mode)
{
return 0;
}
}
#ifdef CONFIG_FS_POSIX_ACL
-void posix_acl_fix_xattr_from_user(void *value, size_t size);
-void posix_acl_fix_xattr_to_user(void *value, size_t size);
+void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns,
+ void *value, size_t size);
+void posix_acl_fix_xattr_to_user(struct user_namespace *mnt_userns,
+ void *value, size_t size);
#else
-static inline void posix_acl_fix_xattr_from_user(void *value, size_t size)
+static inline void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns,
+ void *value, size_t size)
{
}
-static inline void posix_acl_fix_xattr_to_user(void *value, size_t size)
+static inline void posix_acl_fix_xattr_to_user(struct user_namespace *mnt_userns,
+ void *value, size_t size)
{
}
#endif
const kernel_cap_t *inheritable,
const kernel_cap_t *permitted);
extern int cap_bprm_creds_from_file(struct linux_binprm *bprm, struct file *file);
-extern int cap_inode_setxattr(struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags);
-extern int cap_inode_removexattr(struct dentry *dentry, const char *name);
-extern int cap_inode_need_killpriv(struct dentry *dentry);
-extern int cap_inode_killpriv(struct dentry *dentry);
-extern int cap_inode_getsecurity(struct inode *inode, const char *name,
- void **buffer, bool alloc);
+int cap_inode_setxattr(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags);
+int cap_inode_removexattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, const char *name);
+int cap_inode_need_killpriv(struct dentry *dentry);
+int cap_inode_killpriv(struct user_namespace *mnt_userns,
+ struct dentry *dentry);
+int cap_inode_getsecurity(struct user_namespace *mnt_userns,
+ struct inode *inode, const char *name, void **buffer,
+ bool alloc);
extern int cap_mmap_addr(unsigned long addr);
extern int cap_mmap_file(struct file *file, unsigned long reqprot,
unsigned long prot, unsigned long flags);
int security_inode_permission(struct inode *inode, int mask);
int security_inode_setattr(struct dentry *dentry, struct iattr *attr);
int security_inode_getattr(const struct path *path);
-int security_inode_setxattr(struct dentry *dentry, const char *name,
+int security_inode_setxattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, const char *name,
const void *value, size_t size, int flags);
void security_inode_post_setxattr(struct dentry *dentry, const char *name,
const void *value, size_t size, int flags);
int security_inode_getxattr(struct dentry *dentry, const char *name);
int security_inode_listxattr(struct dentry *dentry);
-int security_inode_removexattr(struct dentry *dentry, const char *name);
+int security_inode_removexattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, const char *name);
int security_inode_need_killpriv(struct dentry *dentry);
-int security_inode_killpriv(struct dentry *dentry);
-int security_inode_getsecurity(struct inode *inode, const char *name, void **buffer, bool alloc);
+int security_inode_killpriv(struct user_namespace *mnt_userns,
+ struct dentry *dentry);
+int security_inode_getsecurity(struct user_namespace *mnt_userns,
+ struct inode *inode, const char *name,
+ void **buffer, bool alloc);
int security_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags);
int security_inode_listsecurity(struct inode *inode, char *buffer, size_t buffer_size);
void security_inode_getsecid(struct inode *inode, u32 *secid);
return 0;
}
-static inline int security_inode_setxattr(struct dentry *dentry,
- const char *name, const void *value, size_t size, int flags)
+static inline int security_inode_setxattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, const char *name, const void *value,
+ size_t size, int flags)
{
return cap_inode_setxattr(dentry, name, value, size, flags);
}
return 0;
}
-static inline int security_inode_removexattr(struct dentry *dentry,
- const char *name)
+static inline int security_inode_removexattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry,
+ const char *name)
{
- return cap_inode_removexattr(dentry, name);
+ return cap_inode_removexattr(mnt_userns, dentry, name);
}
static inline int security_inode_need_killpriv(struct dentry *dentry)
return cap_inode_need_killpriv(dentry);
}
-static inline int security_inode_killpriv(struct dentry *dentry)
+static inline int security_inode_killpriv(struct user_namespace *mnt_userns,
+ struct dentry *dentry)
{
- return cap_inode_killpriv(dentry);
+ return cap_inode_killpriv(mnt_userns, dentry);
}
-static inline int security_inode_getsecurity(struct inode *inode, const char *name, void **buffer, bool alloc)
+static inline int security_inode_getsecurity(struct user_namespace *mnt_userns,
+ struct inode *inode,
+ const char *name, void **buffer,
+ bool alloc)
{
- return cap_inode_getsecurity(inode, name, buffer, alloc);
+ return cap_inode_getsecurity(mnt_userns, inode, name, buffer, alloc);
}
static inline int security_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags)
struct io_uring_params;
struct clone_args;
struct open_how;
+struct mount_attr;
#include <linux/types.h>
#include <linux/aio_abi.h>
asmlinkage long sys_move_mount(int from_dfd, const char __user *from_path,
int to_dfd, const char __user *to_path,
unsigned int ms_flags);
+asmlinkage long sys_mount_setattr(int dfd, const char __user *path,
+ unsigned int flags,
+ struct mount_attr __user *uattr, size_t usize);
asmlinkage long sys_fsopen(const char __user *fs_name, unsigned int flags);
asmlinkage long sys_fsconfig(int fs_fd, unsigned int cmd, const char __user *key,
const void __user *value, int aux);
#include <linux/types.h>
#include <linux/spinlock.h>
#include <linux/mm.h>
+#include <linux/user_namespace.h>
#include <uapi/linux/xattr.h>
struct inode;
int (*get)(const struct xattr_handler *, struct dentry *dentry,
struct inode *inode, const char *name, void *buffer,
size_t size);
- int (*set)(const struct xattr_handler *, struct dentry *dentry,
+ int (*set)(const struct xattr_handler *,
+ struct user_namespace *mnt_userns, struct dentry *dentry,
struct inode *inode, const char *name, const void *buffer,
size_t size, int flags);
};
};
ssize_t __vfs_getxattr(struct dentry *, struct inode *, const char *, void *, size_t);
-ssize_t vfs_getxattr(struct dentry *, const char *, void *, size_t);
+ssize_t vfs_getxattr(struct user_namespace *, struct dentry *, const char *,
+ void *, size_t);
ssize_t vfs_listxattr(struct dentry *d, char *list, size_t size);
-int __vfs_setxattr(struct dentry *, struct inode *, const char *, const void *, size_t, int);
-int __vfs_setxattr_noperm(struct dentry *, const char *, const void *, size_t, int);
-int __vfs_setxattr_locked(struct dentry *, const char *, const void *, size_t, int, struct inode **);
-int vfs_setxattr(struct dentry *, const char *, const void *, size_t, int);
-int __vfs_removexattr(struct dentry *, const char *);
-int __vfs_removexattr_locked(struct dentry *, const char *, struct inode **);
-int vfs_removexattr(struct dentry *, const char *);
+int __vfs_setxattr(struct user_namespace *, struct dentry *, struct inode *,
+ const char *, const void *, size_t, int);
+int __vfs_setxattr_noperm(struct user_namespace *, struct dentry *,
+ const char *, const void *, size_t, int);
+int __vfs_setxattr_locked(struct user_namespace *, struct dentry *,
+ const char *, const void *, size_t, int,
+ struct inode **);
+int vfs_setxattr(struct user_namespace *, struct dentry *, const char *,
+ const void *, size_t, int);
+int __vfs_removexattr(struct user_namespace *, struct dentry *, const char *);
+int __vfs_removexattr_locked(struct user_namespace *, struct dentry *,
+ const char *, struct inode **);
+int vfs_removexattr(struct user_namespace *, struct dentry *, const char *);
ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size);
-ssize_t vfs_getxattr_alloc(struct dentry *dentry, const char *name,
+ssize_t vfs_getxattr_alloc(struct user_namespace *mnt_userns,
+ struct dentry *dentry, const char *name,
char **xattr_value, size_t size, gfp_t flags);
int xattr_supported_namespace(struct inode *inode, const char *prefix);
__SYSCALL(__NR_process_madvise, sys_process_madvise)
#define __NR_epoll_pwait2 441
__SC_COMP(__NR_epoll_pwait2, sys_epoll_pwait2, compat_sys_epoll_pwait2)
+#define __NR_mount_setattr 442
+__SYSCALL(__NR_mount_setattr, sys_mount_setattr)
#undef __NR_syscalls
-#define __NR_syscalls 442
+#define __NR_syscalls 443
/*
* 32 bit systems traditionally used different
#ifndef _UAPI_LINUX_MOUNT_H
#define _UAPI_LINUX_MOUNT_H
+#include <linux/types.h>
+
/*
* These are the fs-independent mount-flags: up to 32 flags are supported
*
#define MOUNT_ATTR_NOATIME 0x00000010 /* - Do not update access times. */
#define MOUNT_ATTR_STRICTATIME 0x00000020 /* - Always perform atime updates */
#define MOUNT_ATTR_NODIRATIME 0x00000080 /* Do not update directory access times */
+#define MOUNT_ATTR_IDMAP 0x00100000 /* Idmap mount to @userns_fd in struct mount_attr. */
+
+/*
+ * mount_setattr()
+ */
+struct mount_attr {
+ __u64 attr_set;
+ __u64 attr_clr;
+ __u64 propagation;
+ __u64 userns_fd;
+};
+
+/* List of all mount_attr versions. */
+#define MOUNT_ATTR_SIZE_VER0 32 /* sizeof first published struct */
#endif /* _UAPI_LINUX_MOUNT_H */
return error;
}
-static int mqueue_create(struct inode *dir, struct dentry *dentry,
- umode_t mode, bool excl)
+static int mqueue_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool excl)
{
return mqueue_create_attr(dentry, mode, NULL);
}
if ((oflag & O_ACCMODE) == (O_RDWR | O_WRONLY))
return -EINVAL;
acc = oflag2acc[oflag & O_ACCMODE];
- return inode_permission(d_inode(dentry), acc);
+ return inode_permission(&init_user_ns, d_inode(dentry), acc);
}
static int do_mq_open(const char __user *u_name, int oflag, umode_t mode,
err = -ENOENT;
} else {
ihold(inode);
- err = vfs_unlink(d_inode(dentry->d_parent), dentry, NULL);
+ err = vfs_unlink(&init_user_ns, d_inode(dentry->d_parent),
+ dentry, NULL);
}
dput(dentry);
if (!dentry)
return 0;
- rc = get_vfs_caps_from_disk(dentry, &caps);
+ rc = get_vfs_caps_from_disk(&init_user_ns, dentry, &caps);
if (rc)
return rc;
ax->d.next = context->aux;
context->aux = (void *)ax;
- get_vfs_caps_from_disk(bprm->file->f_path.dentry, &vcaps);
+ get_vfs_caps_from_disk(&init_user_ns,
+ bprm->file->f_path.dentry, &vcaps);
ax->fcap.permitted = vcaps.permitted;
ax->fcap.inheritable = vcaps.inheritable;
inode->i_mtime = inode->i_atime;
inode->i_ctime = inode->i_atime;
- inode_init_owner(inode, dir, mode);
+ inode_init_owner(&init_user_ns, inode, dir, mode);
return inode;
}
dir->i_ctime = dir->i_mtime;
}
-static int bpf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int bpf_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
struct inode *inode;
return simple_lookup(dir, dentry, flags);
}
-static int bpf_symlink(struct inode *dir, struct dentry *dentry,
- const char *target)
+static int bpf_symlink(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, const char *target)
{
char *link = kstrdup(target, GFP_USER | __GFP_NOWARN);
struct inode *inode;
return ERR_PTR(ret);
inode = d_backing_inode(path.dentry);
- ret = inode_permission(inode, ACC_MODE(flags));
+ ret = path_permission(&path, ACC_MODE(flags));
if (ret)
goto out;
static struct bpf_prog *__get_prog_inode(struct inode *inode, enum bpf_prog_type type)
{
struct bpf_prog *prog;
- int ret = inode_permission(inode, MAY_READ);
+ int ret = inode_permission(&init_user_ns, inode, MAY_READ);
if (ret)
return ERR_PTR(ret);
*
* Return true if the inode uid and gid are within the namespace.
*/
-bool privileged_wrt_inode_uidgid(struct user_namespace *ns, const struct inode *inode)
+bool privileged_wrt_inode_uidgid(struct user_namespace *ns,
+ struct user_namespace *mnt_userns,
+ const struct inode *inode)
{
- return kuid_has_mapping(ns, inode->i_uid) &&
- kgid_has_mapping(ns, inode->i_gid);
+ return kuid_has_mapping(ns, i_uid_into_mnt(mnt_userns, inode)) &&
+ kgid_has_mapping(ns, i_gid_into_mnt(mnt_userns, inode));
}
/**
* its own user namespace and that the given inode's uid and gid are
* mapped into the current user namespace.
*/
-bool capable_wrt_inode_uidgid(const struct inode *inode, int cap)
+bool capable_wrt_inode_uidgid(struct user_namespace *mnt_userns,
+ const struct inode *inode, int cap)
{
struct user_namespace *ns = current_user_ns();
- return ns_capable(ns, cap) && privileged_wrt_inode_uidgid(ns, inode);
+ return ns_capable(ns, cap) &&
+ privileged_wrt_inode_uidgid(ns, mnt_userns, inode);
}
EXPORT_SYMBOL(capable_wrt_inode_uidgid);
if (!inode)
return -ENOMEM;
- ret = inode_permission(inode, MAY_WRITE);
+ ret = inode_permission(&init_user_ns, inode, MAY_WRITE);
iput(inode);
return ret;
}
if (!S_ISREG(inode->i_mode) || path_noexec(&exe.file->f_path))
goto exit;
- err = inode_permission(inode, MAY_EXEC);
+ err = file_permission(exe.file, MAY_EXEC);
if (err)
goto exit;
* otherwise we'd be including shared non-exclusive mappings, which
* opens a side channel.
*/
- return inode_owner_or_capable(file_inode(vma->vm_file)) ||
- inode_permission(file_inode(vma->vm_file), MAY_WRITE) == 0;
+ return inode_owner_or_capable(&init_user_ns,
+ file_inode(vma->vm_file)) ||
+ file_permission(vma->vm_file, MAY_WRITE) == 0;
}
static long madvise_pageout(struct vm_area_struct *vma,
/* the process need read permission on control file */
/* AV: shouldn't we check that it's been opened for read instead? */
- ret = inode_permission(file_inode(cfile.file), MAY_READ);
+ ret = file_permission(cfile.file, MAY_READ);
if (ret < 0)
goto out_put_cfile;
* for writing; otherwise we'd be including shared non-exclusive
* mappings, which opens a side channel.
*/
- return inode_owner_or_capable(file_inode(vma->vm_file)) ||
- inode_permission(file_inode(vma->vm_file), MAY_WRITE) == 0;
+ return inode_owner_or_capable(&init_user_ns,
+ file_inode(vma->vm_file)) ||
+ file_permission(vma->vm_file, MAY_WRITE) == 0;
}
static const struct mm_walk_ops mincore_walk_ops = {
}
EXPORT_SYMBOL_GPL(shmem_truncate_range);
-static int shmem_getattr(const struct path *path, struct kstat *stat,
+static int shmem_getattr(struct user_namespace *mnt_userns,
+ const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int query_flags)
{
struct inode *inode = path->dentry->d_inode;
shmem_recalc_inode(inode);
spin_unlock_irq(&info->lock);
}
- generic_fillattr(inode, stat);
+ generic_fillattr(&init_user_ns, inode, stat);
if (is_huge_enabled(sb_info))
stat->blksize = HPAGE_PMD_SIZE;
return 0;
}
-static int shmem_setattr(struct dentry *dentry, struct iattr *attr)
+static int shmem_setattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
struct shmem_inode_info *info = SHMEM_I(inode);
struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
int error;
- error = setattr_prepare(dentry, attr);
+ error = setattr_prepare(&init_user_ns, dentry, attr);
if (error)
return error;
}
}
- setattr_copy(inode, attr);
+ setattr_copy(&init_user_ns, inode, attr);
if (attr->ia_valid & ATTR_MODE)
- error = posix_acl_chmod(inode, inode->i_mode);
+ error = posix_acl_chmod(&init_user_ns, inode, inode->i_mode);
return error;
}
inode = new_inode(sb);
if (inode) {
inode->i_ino = ino;
- inode_init_owner(inode, dir, mode);
+ inode_init_owner(&init_user_ns, inode, dir, mode);
inode->i_blocks = 0;
inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
inode->i_generation = prandom_u32();
* File creation. Allocate an inode, and we're done..
*/
static int
-shmem_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev)
+shmem_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, dev_t dev)
{
struct inode *inode;
int error = -ENOSPC;
}
static int
-shmem_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
+shmem_tmpfile(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
struct inode *inode;
int error = -ENOSPC;
return error;
}
-static int shmem_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int shmem_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
int error;
- if ((error = shmem_mknod(dir, dentry, mode | S_IFDIR, 0)))
+ if ((error = shmem_mknod(&init_user_ns, dir, dentry,
+ mode | S_IFDIR, 0)))
return error;
inc_nlink(dir);
return 0;
}
-static int shmem_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- bool excl)
+static int shmem_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool excl)
{
- return shmem_mknod(dir, dentry, mode | S_IFREG, 0);
+ return shmem_mknod(&init_user_ns, dir, dentry, mode | S_IFREG, 0);
}
/*
return 0;
}
-static int shmem_whiteout(struct inode *old_dir, struct dentry *old_dentry)
+static int shmem_whiteout(struct user_namespace *mnt_userns,
+ struct inode *old_dir, struct dentry *old_dentry)
{
struct dentry *whiteout;
int error;
if (!whiteout)
return -ENOMEM;
- error = shmem_mknod(old_dir, whiteout,
+ error = shmem_mknod(&init_user_ns, old_dir, whiteout,
S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV);
dput(whiteout);
if (error)
* it exists so that the VFS layer correctly free's it when it
* gets overwritten.
*/
-static int shmem_rename2(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags)
+static int shmem_rename2(struct user_namespace *mnt_userns,
+ struct inode *old_dir, struct dentry *old_dentry,
+ struct inode *new_dir, struct dentry *new_dentry,
+ unsigned int flags)
{
struct inode *inode = d_inode(old_dentry);
int they_are_dirs = S_ISDIR(inode->i_mode);
if (flags & RENAME_WHITEOUT) {
int error;
- error = shmem_whiteout(old_dir, old_dentry);
+ error = shmem_whiteout(&init_user_ns, old_dir, old_dentry);
if (error)
return error;
}
return 0;
}
-static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
+static int shmem_symlink(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, const char *symname)
{
int error;
int len;
}
static int shmem_xattr_handler_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
};
static int sockfs_security_xattr_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *dentry, struct inode *inode,
const char *suffix, const void *value,
size_t size, int flags)
return used;
}
-static int sockfs_setattr(struct dentry *dentry, struct iattr *iattr)
+static int sockfs_setattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct iattr *iattr)
{
- int err = simple_setattr(dentry, iattr);
+ int err = simple_setattr(&init_user_ns, dentry, iattr);
if (!err && (iattr->ia_valid & ATTR_UID)) {
struct socket *sock = SOCKET_I(d_inode(dentry));
if (err)
goto fail;
inode = d_backing_inode(path.dentry);
- err = inode_permission(inode, MAY_WRITE);
+ err = path_permission(&path, MAY_WRITE);
if (err)
goto put_fail;
*/
err = security_path_mknod(&path, dentry, mode, 0);
if (!err) {
- err = vfs_mknod(d_inode(path.dentry), dentry, mode, 0);
+ err = vfs_mknod(mnt_user_ns(path.mnt), d_inode(path.dentry),
+ dentry, mode, 0);
if (!err) {
res->mnt = mntget(path.mnt);
res->dentry = dget(dentry);
return error;
}
-static int ns_mkdir_op(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int ns_mkdir_op(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
struct aa_ns *ns, *parent;
/* TODO: improve permission check */
#include <linux/errno.h>
#include <linux/fdtable.h>
+#include <linux/fs.h>
#include <linux/file.h>
#include <linux/mount.h>
#include <linux/syscalls.h>
#include <linux/tracehook.h>
#include <linux/personality.h>
#include <linux/xattr.h>
+#include <linux/user_namespace.h>
#include "include/audit.h"
#include "include/apparmorfs.h"
d = bprm->file->f_path.dentry;
for (i = 0; i < profile->xattr_count; i++) {
- size = vfs_getxattr_alloc(d, profile->xattrs[i], &value,
- value_size, GFP_KERNEL);
+ size = vfs_getxattr_alloc(&init_user_ns, d, profile->xattrs[i],
+ &value, value_size, GFP_KERNEL);
if (size >= 0) {
u32 perm;
const char *info = NULL;
int error = 0;
bool unsafe = false;
+ kuid_t i_uid = i_uid_into_mnt(file_mnt_user_ns(bprm->file),
+ file_inode(bprm->file));
struct path_cond cond = {
- file_inode(bprm->file)->i_uid,
+ i_uid,
file_inode(bprm->file)->i_mode
};
error = fn_for_each(label, profile,
aa_audit_file(profile, &nullperms, OP_EXEC, MAY_EXEC,
bprm->filename, NULL, new,
- file_inode(bprm->file)->i_uid, info,
- error));
+ i_uid, info, error));
aa_put_label(new);
goto done;
}
#include <linux/tty.h>
#include <linux/fdtable.h>
#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/mount.h>
#include "include/apparmor.h"
#include "include/audit.h"
struct aa_profile *profile;
struct aa_perms perms = {};
struct path_cond cond = {
- .uid = file_inode(file)->i_uid,
+ .uid = i_uid_into_mnt(file_mnt_user_ns(file), file_inode(file)),
.mode = file_inode(file)->i_mode
};
char *buffer;
*/
static int common_perm_cond(const char *op, const struct path *path, u32 mask)
{
- struct path_cond cond = { d_backing_inode(path->dentry)->i_uid,
- d_backing_inode(path->dentry)->i_mode
+ struct user_namespace *mnt_userns = mnt_user_ns(path->mnt);
+ struct path_cond cond = {
+ i_uid_into_mnt(mnt_userns, d_backing_inode(path->dentry)),
+ d_backing_inode(path->dentry)->i_mode
};
if (!path_mediated_fs(path->dentry))
struct dentry *dentry, u32 mask)
{
struct inode *inode = d_backing_inode(dentry);
+ struct user_namespace *mnt_userns = mnt_user_ns(dir->mnt);
struct path_cond cond = { };
if (!inode || !path_mediated_fs(dentry))
return 0;
- cond.uid = inode->i_uid;
+ cond.uid = i_uid_into_mnt(mnt_userns, inode);
cond.mode = inode->i_mode;
return common_perm_dir_dentry(op, dir, dentry, mask, &cond);
label = begin_current_label_crit_section();
if (!unconfined(label)) {
+ struct user_namespace *mnt_userns = mnt_user_ns(old_dir->mnt);
struct path old_path = { .mnt = old_dir->mnt,
.dentry = old_dentry };
struct path new_path = { .mnt = new_dir->mnt,
.dentry = new_dentry };
- struct path_cond cond = { d_backing_inode(old_dentry)->i_uid,
- d_backing_inode(old_dentry)->i_mode
+ struct path_cond cond = {
+ i_uid_into_mnt(mnt_userns, d_backing_inode(old_dentry)),
+ d_backing_inode(old_dentry)->i_mode
};
error = aa_path_perm(OP_RENAME_SRC, label, &old_path, 0,
label = aa_get_newest_cred_label(file->f_cred);
if (!unconfined(label)) {
+ struct user_namespace *mnt_userns = file_mnt_user_ns(file);
struct inode *inode = file_inode(file);
- struct path_cond cond = { inode->i_uid, inode->i_mode };
+ struct path_cond cond = {
+ i_uid_into_mnt(mnt_userns, inode),
+ inode->i_mode
+ };
error = aa_path_perm(OP_OPEN, label, &file->f_path, 0,
aa_map_file_to_perms(file), &cond);
/**
* cap_inode_killpriv - Erase the security markings on an inode
- * @dentry: The inode/dentry to alter
+ *
+ * @mnt_userns: user namespace of the mount the inode was found from
+ * @dentry: The inode/dentry to alter
*
* Erase the privilege-enhancing security markings on an inode.
*
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then
+ * take care to map the inode according to @mnt_userns before checking
+ * permissions. On non-idmapped mounts or if permission checking is to be
+ * performed on the raw inode simply passs init_user_ns.
+ *
* Returns 0 if successful, -ve on error.
*/
-int cap_inode_killpriv(struct dentry *dentry)
+int cap_inode_killpriv(struct user_namespace *mnt_userns, struct dentry *dentry)
{
int error;
- error = __vfs_removexattr(dentry, XATTR_NAME_CAPS);
+ error = __vfs_removexattr(mnt_userns, dentry, XATTR_NAME_CAPS);
if (error == -EOPNOTSUPP)
error = 0;
return error;
* by the integrity subsystem, which really wants the unconverted values -
* so that's good.
*/
-int cap_inode_getsecurity(struct inode *inode, const char *name, void **buffer,
+int cap_inode_getsecurity(struct user_namespace *mnt_userns,
+ struct inode *inode, const char *name, void **buffer,
bool alloc)
{
int size, ret;
return -EINVAL;
size = sizeof(struct vfs_ns_cap_data);
- ret = (int) vfs_getxattr_alloc(dentry, XATTR_NAME_CAPS,
- &tmpbuf, size, GFP_NOFS);
+ ret = (int)vfs_getxattr_alloc(mnt_userns, dentry, XATTR_NAME_CAPS,
+ &tmpbuf, size, GFP_NOFS);
dput(dentry);
if (ret < 0)
kroot = make_kuid(fs_ns, root);
+ /* If this is an idmapped mount shift the kuid. */
+ kroot = kuid_into_mnt(mnt_userns, kroot);
+
/* If the root kuid maps to a valid uid in current ns, then return
* this as a nscap. */
mappedroot = from_kuid(current_user_ns(), kroot);
return size;
}
+/**
+ * rootid_from_xattr - translate root uid of vfs caps
+ *
+ * @value: vfs caps value which may be modified by this function
+ * @size: size of @ivalue
+ * @task_ns: user namespace of the caller
+ * @mnt_userns: user namespace of the mount the inode was found from
+ *
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then
+ * take care to map the inode according to @mnt_userns before checking
+ * permissions. On non-idmapped mounts or if permission checking is to be
+ * performed on the raw inode simply passs init_user_ns.
+ */
static kuid_t rootid_from_xattr(const void *value, size_t size,
- struct user_namespace *task_ns)
+ struct user_namespace *task_ns,
+ struct user_namespace *mnt_userns)
{
const struct vfs_ns_cap_data *nscap = value;
+ kuid_t rootkid;
uid_t rootid = 0;
if (size == XATTR_CAPS_SZ_3)
rootid = le32_to_cpu(nscap->rootid);
- return make_kuid(task_ns, rootid);
+ rootkid = make_kuid(task_ns, rootid);
+ return kuid_from_mnt(mnt_userns, rootkid);
}
static bool validheader(size_t size, const struct vfs_cap_data *cap)
return is_v2header(size, cap) || is_v3header(size, cap);
}
-/*
+/**
+ * cap_convert_nscap - check vfs caps
+ *
+ * @mnt_userns: user namespace of the mount the inode was found from
+ * @dentry: used to retrieve inode to check permissions on
+ * @ivalue: vfs caps value which may be modified by this function
+ * @size: size of @ivalue
+ *
* User requested a write of security.capability. If needed, update the
* xattr to change from v2 to v3, or to fixup the v3 rootid.
*
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then
+ * take care to map the inode according to @mnt_userns before checking
+ * permissions. On non-idmapped mounts or if permission checking is to be
+ * performed on the raw inode simply passs init_user_ns.
+ *
* If all is ok, we return the new size, on error return < 0.
*/
-int cap_convert_nscap(struct dentry *dentry, const void **ivalue, size_t size)
+int cap_convert_nscap(struct user_namespace *mnt_userns, struct dentry *dentry,
+ const void **ivalue, size_t size)
{
struct vfs_ns_cap_data *nscap;
uid_t nsrootid;
return -EINVAL;
if (!validheader(size, cap))
return -EINVAL;
- if (!capable_wrt_inode_uidgid(inode, CAP_SETFCAP))
+ if (!capable_wrt_inode_uidgid(mnt_userns, inode, CAP_SETFCAP))
return -EPERM;
- if (size == XATTR_CAPS_SZ_2)
+ if (size == XATTR_CAPS_SZ_2 && (mnt_userns == &init_user_ns))
if (ns_capable(inode->i_sb->s_user_ns, CAP_SETFCAP))
/* user is privileged, just write the v2 */
return size;
- rootid = rootid_from_xattr(*ivalue, size, task_ns);
+ rootid = rootid_from_xattr(*ivalue, size, task_ns, mnt_userns);
if (!uid_valid(rootid))
return -EINVAL;
return *effective ? ret : 0;
}
-/*
+/**
+ * get_vfs_caps_from_disk - retrieve vfs caps from disk
+ *
+ * @mnt_userns: user namespace of the mount the inode was found from
+ * @dentry: dentry from which @inode is retrieved
+ * @cpu_caps: vfs capabilities
+ *
* Extract the on-exec-apply capability sets for an executable file.
+ *
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then
+ * take care to map the inode according to @mnt_userns before checking
+ * permissions. On non-idmapped mounts or if permission checking is to be
+ * performed on the raw inode simply passs init_user_ns.
*/
-int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps)
+int get_vfs_caps_from_disk(struct user_namespace *mnt_userns,
+ const struct dentry *dentry,
+ struct cpu_vfs_cap_data *cpu_caps)
{
struct inode *inode = d_backing_inode(dentry);
__u32 magic_etc;
/* Limit the caps to the mounter of the filesystem
* or the more limited uid specified in the xattr.
*/
+ rootkuid = kuid_into_mnt(mnt_userns, rootkuid);
if (!rootid_owns_currentns(rootkuid))
return -ENODATA;
if (!current_in_userns(file->f_path.mnt->mnt_sb->s_user_ns))
return 0;
- rc = get_vfs_caps_from_disk(file->f_path.dentry, &vcaps);
+ rc = get_vfs_caps_from_disk(file_mnt_user_ns(file),
+ file->f_path.dentry, &vcaps);
if (rc < 0) {
if (rc == -EINVAL)
printk(KERN_NOTICE "Invalid argument reading file caps for %s\n",
/**
* cap_inode_removexattr - Determine whether an xattr may be removed
- * @dentry: The inode/dentry being altered
- * @name: The name of the xattr to be changed
+ *
+ * @mnt_userns: User namespace of the mount the inode was found from
+ * @dentry: The inode/dentry being altered
+ * @name: The name of the xattr to be changed
*
* Determine whether an xattr may be removed from an inode, returning 0 if
* permission is granted, -ve if denied.
*
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then
+ * take care to map the inode according to @mnt_userns before checking
+ * permissions. On non-idmapped mounts or if permission checking is to be
+ * performed on the raw inode simply passs init_user_ns.
+ *
* This is used to make sure security xattrs don't get removed by those who
* aren't privileged to remove them.
*/
-int cap_inode_removexattr(struct dentry *dentry, const char *name)
+int cap_inode_removexattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, const char *name)
{
struct user_namespace *user_ns = dentry->d_sb->s_user_ns;
struct inode *inode = d_backing_inode(dentry);
if (!inode)
return -EINVAL;
- if (!capable_wrt_inode_uidgid(inode, CAP_SETFCAP))
+ if (!capable_wrt_inode_uidgid(mnt_userns, inode, CAP_SETFCAP))
return -EPERM;
return 0;
}
ima_present = true;
continue;
}
- size = vfs_getxattr_alloc(dentry, xattr->name,
+ size = vfs_getxattr_alloc(&init_user_ns, dentry, xattr->name,
&xattr_value, xattr_size, GFP_NOFS);
if (size == -ENOMEM) {
error = -ENOMEM;
return 1;
/* Do this the hard way */
- rc = vfs_getxattr_alloc(dentry, XATTR_NAME_EVM, (char **)&xattr_data, 0,
- GFP_NOFS);
+ rc = vfs_getxattr_alloc(&init_user_ns, dentry, XATTR_NAME_EVM,
+ (char **)&xattr_data, 0, GFP_NOFS);
if (rc <= 0) {
if (rc == -ENODATA)
return 0;
xattr_value_len, &data);
if (rc == 0) {
data.hdr.xattr.sha1.type = EVM_XATTR_HMAC;
- rc = __vfs_setxattr_noperm(dentry, XATTR_NAME_EVM,
+ rc = __vfs_setxattr_noperm(&init_user_ns, dentry,
+ XATTR_NAME_EVM,
&data.hdr.xattr.data[1],
SHA1_DIGEST_SIZE + 1, 0);
} else if (rc == -ENODATA && (inode->i_opflags & IOP_XATTR)) {
- rc = __vfs_removexattr(dentry, XATTR_NAME_EVM);
+ rc = __vfs_removexattr(&init_user_ns, dentry, XATTR_NAME_EVM);
}
return rc;
}
/* if status is not PASS, try to check again - against -ENOMEM */
/* first need to know the sig type */
- rc = vfs_getxattr_alloc(dentry, XATTR_NAME_EVM, (char **)&xattr_data, 0,
- GFP_NOFS);
+ rc = vfs_getxattr_alloc(&init_user_ns, dentry, XATTR_NAME_EVM,
+ (char **)&xattr_data, 0, GFP_NOFS);
if (rc <= 0) {
evm_status = INTEGRITY_FAIL;
if (rc == -ENODATA) {
newattrs.ia_valid = ATTR_MODE;
inode = evm_xattrs->d_inode;
inode_lock(inode);
- err = simple_setattr(evm_xattrs, &newattrs);
+ err = simple_setattr(&init_user_ns, evm_xattrs, &newattrs);
inode_unlock(inode);
if (!err)
err = count;
#endif /* CONFIG_IMA_QUEUE_EARLY_BOOT_KEYS */
/* LIM API function definitions */
-int ima_get_action(struct inode *inode, const struct cred *cred, u32 secid,
- int mask, enum ima_hooks func, int *pcr,
+int ima_get_action(struct user_namespace *mnt_userns, struct inode *inode,
+ const struct cred *cred, u32 secid, int mask,
+ enum ima_hooks func, int *pcr,
struct ima_template_desc **template_desc,
const char *func_data);
int ima_must_measure(struct inode *inode, int mask, enum ima_hooks func);
struct evm_ima_xattr_data *xattr_value,
int xattr_len, const struct modsig *modsig, int pcr,
struct ima_template_desc *template_desc);
-void process_buffer_measurement(struct inode *inode, const void *buf, int size,
+void process_buffer_measurement(struct user_namespace *mnt_userns,
+ struct inode *inode, const void *buf, int size,
const char *eventname, enum ima_hooks func,
int pcr, const char *func_data,
bool buf_hash);
const char *ima_d_path(const struct path *path, char **pathbuf, char *filename);
/* IMA policy related functions */
-int ima_match_policy(struct inode *inode, const struct cred *cred, u32 secid,
- enum ima_hooks func, int mask, int flags, int *pcr,
+int ima_match_policy(struct user_namespace *mnt_userns, struct inode *inode,
+ const struct cred *cred, u32 secid, enum ima_hooks func,
+ int mask, int flags, int *pcr,
struct ima_template_desc **template_desc,
const char *func_data);
void ima_init_policy(void);
struct file *file, const unsigned char *filename,
struct evm_ima_xattr_data *xattr_value,
int xattr_len, const struct modsig *modsig);
-int ima_must_appraise(struct inode *inode, int mask, enum ima_hooks func);
+int ima_must_appraise(struct user_namespace *mnt_userns, struct inode *inode,
+ int mask, enum ima_hooks func);
void ima_update_xattr(struct integrity_iint_cache *iint, struct file *file);
enum integrity_status ima_get_cache_status(struct integrity_iint_cache *iint,
enum ima_hooks func);
return INTEGRITY_UNKNOWN;
}
-static inline int ima_must_appraise(struct inode *inode, int mask,
+static inline int ima_must_appraise(struct user_namespace *mnt_userns,
+ struct inode *inode, int mask,
enum ima_hooks func)
{
return 0;
/**
* ima_get_action - appraise & measure decision based on policy.
+ * @mnt_userns: user namespace of the mount the inode was found from
* @inode: pointer to the inode associated with the object being validated
* @cred: pointer to credentials structure to validate
* @secid: secid of the task being validated
* Returns IMA_MEASURE, IMA_APPRAISE mask.
*
*/
-int ima_get_action(struct inode *inode, const struct cred *cred, u32 secid,
- int mask, enum ima_hooks func, int *pcr,
+int ima_get_action(struct user_namespace *mnt_userns, struct inode *inode,
+ const struct cred *cred, u32 secid, int mask,
+ enum ima_hooks func, int *pcr,
struct ima_template_desc **template_desc,
const char *func_data)
{
flags &= ima_policy_flag;
- return ima_match_policy(inode, cred, secid, func, mask, flags, pcr,
- template_desc, func_data);
+ return ima_match_policy(mnt_userns, inode, cred, secid, func, mask,
+ flags, pcr, template_desc, func_data);
}
/*
*
* Return 1 to appraise or hash
*/
-int ima_must_appraise(struct inode *inode, int mask, enum ima_hooks func)
+int ima_must_appraise(struct user_namespace *mnt_userns, struct inode *inode,
+ int mask, enum ima_hooks func)
{
u32 secid;
return 0;
security_task_getsecid(current, &secid);
- return ima_match_policy(inode, current_cred(), secid, func, mask,
- IMA_APPRAISE | IMA_HASH, NULL, NULL, NULL);
+ return ima_match_policy(mnt_userns, inode, current_cred(), secid, func,
+ mask, IMA_APPRAISE | IMA_HASH, NULL, NULL, NULL);
}
static int ima_fix_xattr(struct dentry *dentry,
iint->ima_hash->xattr.ng.type = IMA_XATTR_DIGEST_NG;
iint->ima_hash->xattr.ng.algo = algo;
}
- rc = __vfs_setxattr_noperm(dentry, XATTR_NAME_IMA,
+ rc = __vfs_setxattr_noperm(&init_user_ns, dentry, XATTR_NAME_IMA,
&iint->ima_hash->xattr.data[offset],
(sizeof(iint->ima_hash->xattr) - offset) +
iint->ima_hash->length, 0);
{
ssize_t ret;
- ret = vfs_getxattr_alloc(dentry, XATTR_NAME_IMA, (char **)xattr_value,
- 0, GFP_NOFS);
+ ret = vfs_getxattr_alloc(&init_user_ns, dentry, XATTR_NAME_IMA,
+ (char **)xattr_value, 0, GFP_NOFS);
if (ret == -EOPNOTSUPP)
ret = 0;
return ret;
rc = is_binary_blacklisted(digest, digestsize);
if ((rc == -EPERM) && (iint->flags & IMA_MEASURE))
- process_buffer_measurement(NULL, digest, digestsize,
+ process_buffer_measurement(&init_user_ns, NULL, digest, digestsize,
"blacklisted-hash", NONE,
pcr, NULL, false);
}
/**
* ima_inode_post_setattr - reflect file metadata changes
+ * @mnt_userns: user namespace of the mount the inode was found from
* @dentry: pointer to the affected dentry
*
* Changes to a dentry's metadata might result in needing to appraise.
* This function is called from notify_change(), which expects the caller
* to lock the inode's i_mutex.
*/
-void ima_inode_post_setattr(struct dentry *dentry)
+void ima_inode_post_setattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry)
{
struct inode *inode = d_backing_inode(dentry);
struct integrity_iint_cache *iint;
|| !(inode->i_opflags & IOP_XATTR))
return;
- action = ima_must_appraise(inode, MAY_ACCESS, POST_SETATTR);
+ action = ima_must_appraise(mnt_userns, inode, MAY_ACCESS, POST_SETATTR);
if (!action)
- __vfs_removexattr(dentry, XATTR_NAME_IMA);
+ __vfs_removexattr(&init_user_ns, dentry, XATTR_NAME_IMA);
iint = integrity_iint_find(inode);
if (iint) {
set_bit(IMA_CHANGE_ATTR, &iint->atomic_flags);
*/
#include <keys/asymmetric-type.h>
+#include <linux/user_namespace.h>
#include "ima.h"
/**
* if the IMA policy is configured to measure a key linked
* to the given keyring.
*/
- process_buffer_measurement(NULL, payload, payload_len,
+ process_buffer_measurement(&init_user_ns, NULL, payload, payload_len,
keyring->description, KEY_CHECK, 0,
keyring->description, false);
}
* bitmask based on the appraise/audit/measurement policy.
* Included is the appraise submask.
*/
- action = ima_get_action(inode, cred, secid, mask, func, &pcr,
- &template_desc, NULL);
+ action = ima_get_action(file_mnt_user_ns(file), inode, cred, secid,
+ mask, func, &pcr, &template_desc, NULL);
violation_check = ((func == FILE_CHECK || func == MMAP_CHECK) &&
(ima_policy_flag & IMA_MEASURE));
if (!action && !violation_check)
security_task_getsecid(current, &secid);
inode = file_inode(vma->vm_file);
- action = ima_get_action(inode, current_cred(), secid, MAY_EXEC,
- MMAP_CHECK, &pcr, &template, 0);
+ action = ima_get_action(file_mnt_user_ns(vma->vm_file), inode,
+ current_cred(), secid, MAY_EXEC, MMAP_CHECK,
+ &pcr, &template, 0);
/* Is the mmap'ed file in policy? */
if (!(action & (IMA_MEASURE | IMA_APPRAISE_SUBMASK)))
/**
* ima_post_create_tmpfile - mark newly created tmpfile as new
+ * @mnt_userns: user namespace of the mount the inode was found from
* @file : newly created tmpfile
*
* No measuring, appraising or auditing of newly created tmpfiles is needed.
* Skip calling process_measurement(), but indicate which newly, created
* tmpfiles are in policy.
*/
-void ima_post_create_tmpfile(struct inode *inode)
+void ima_post_create_tmpfile(struct user_namespace *mnt_userns,
+ struct inode *inode)
{
struct integrity_iint_cache *iint;
int must_appraise;
- must_appraise = ima_must_appraise(inode, MAY_ACCESS, FILE_CHECK);
+ must_appraise = ima_must_appraise(mnt_userns, inode, MAY_ACCESS,
+ FILE_CHECK);
if (!must_appraise)
return;
/**
* ima_post_path_mknod - mark as a new inode
+ * @mnt_userns: user namespace of the mount the inode was found from
* @dentry: newly created dentry
*
* Mark files created via the mknodat syscall as new, so that the
* file data can be written later.
*/
-void ima_post_path_mknod(struct dentry *dentry)
+void ima_post_path_mknod(struct user_namespace *mnt_userns,
+ struct dentry *dentry)
{
struct integrity_iint_cache *iint;
struct inode *inode = dentry->d_inode;
int must_appraise;
- must_appraise = ima_must_appraise(inode, MAY_ACCESS, FILE_CHECK);
+ must_appraise = ima_must_appraise(mnt_userns, inode, MAY_ACCESS,
+ FILE_CHECK);
if (!must_appraise)
return;
/*
* process_buffer_measurement - Measure the buffer or the buffer data hash
+ * @mnt_userns: user namespace of the mount the inode was found from
* @inode: inode associated with the object being measured (NULL for KEY_CHECK)
* @buf: pointer to the buffer that needs to be added to the log.
* @size: size of buffer(in bytes).
*
* Based on policy, either the buffer data or buffer data hash is measured
*/
-void process_buffer_measurement(struct inode *inode, const void *buf, int size,
+void process_buffer_measurement(struct user_namespace *mnt_userns,
+ struct inode *inode, const void *buf, int size,
const char *eventname, enum ima_hooks func,
int pcr, const char *func_data,
bool buf_hash)
*/
if (func) {
security_task_getsecid(current, &secid);
- action = ima_get_action(inode, current_cred(), secid, 0, func,
- &pcr, &template, func_data);
+ action = ima_get_action(mnt_userns, inode, current_cred(),
+ secid, 0, func, &pcr, &template,
+ func_data);
if (!(action & IMA_MEASURE))
return;
}
if (!f.file)
return;
- process_buffer_measurement(file_inode(f.file), buf, size,
- "kexec-cmdline", KEXEC_CMDLINE, 0, NULL,
- false);
+ process_buffer_measurement(file_mnt_user_ns(f.file), file_inode(f.file),
+ buf, size, "kexec-cmdline", KEXEC_CMDLINE, 0,
+ NULL, false);
fdput(f);
}
if (!event_name || !event_label || !buf || !buf_len)
return;
- process_buffer_measurement(NULL, buf, buf_len, event_name,
+ process_buffer_measurement(&init_user_ns, NULL, buf, buf_len, event_name,
CRITICAL_DATA, 0, event_label,
hash);
}
/**
* ima_match_rules - determine whether an inode matches the policy rule.
* @rule: a pointer to a rule
+ * @mnt_userns: user namespace of the mount the inode was found from
* @inode: a pointer to an inode
* @cred: a pointer to a credentials structure for user validation
* @secid: the secid of the task to be validated
*
* Returns true on rule match, false on failure.
*/
-static bool ima_match_rules(struct ima_rule_entry *rule, struct inode *inode,
- const struct cred *cred, u32 secid,
- enum ima_hooks func, int mask,
+static bool ima_match_rules(struct ima_rule_entry *rule,
+ struct user_namespace *mnt_userns,
+ struct inode *inode, const struct cred *cred,
+ u32 secid, enum ima_hooks func, int mask,
const char *func_data)
{
int i;
}
if ((rule->flags & IMA_FOWNER) &&
- !rule->fowner_op(inode->i_uid, rule->fowner))
+ !rule->fowner_op(i_uid_into_mnt(mnt_userns, inode), rule->fowner))
return false;
for (i = 0; i < MAX_LSM_RULES; i++) {
int rc = 0;
/**
* ima_match_policy - decision based on LSM and other conditions
+ * @mnt_userns: user namespace of the mount the inode was found from
* @inode: pointer to an inode for which the policy decision is being made
* @cred: pointer to a credentials structure for which the policy decision is
* being made
* list when walking it. Reads are many orders of magnitude more numerous
* than writes so ima_match_policy() is classical RCU candidate.
*/
-int ima_match_policy(struct inode *inode, const struct cred *cred, u32 secid,
- enum ima_hooks func, int mask, int flags, int *pcr,
+int ima_match_policy(struct user_namespace *mnt_userns, struct inode *inode,
+ const struct cred *cred, u32 secid, enum ima_hooks func,
+ int mask, int flags, int *pcr,
struct ima_template_desc **template_desc,
const char *func_data)
{
if (!(entry->action & actmask))
continue;
- if (!ima_match_rules(entry, inode, cred, secid, func, mask,
- func_data))
+ if (!ima_match_rules(entry, mnt_userns, inode, cred, secid,
+ func, mask, func_data))
continue;
action |= entry->flags & IMA_ACTION_FLAGS;
* Enables deferred processing of keys
*/
+#include <linux/user_namespace.h>
#include <linux/workqueue.h>
#include <keys/asymmetric-type.h>
#include "ima.h"
list_for_each_entry_safe(entry, tmp, &ima_keys, list) {
if (!timer_expired)
- process_buffer_measurement(NULL, entry->payload,
+ process_buffer_measurement(&init_user_ns, NULL,
+ entry->payload,
entry->payload_len,
entry->keyring_name,
KEY_CHECK, 0,
return call_int_hook(inode_getattr, 0, path);
}
-int security_inode_setxattr(struct dentry *dentry, const char *name,
+int security_inode_setxattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, const char *name,
const void *value, size_t size, int flags)
{
int ret;
* SELinux and Smack integrate the cap call,
* so assume that all LSMs supplying this call do so.
*/
- ret = call_int_hook(inode_setxattr, 1, dentry, name, value, size,
- flags);
+ ret = call_int_hook(inode_setxattr, 1, mnt_userns, dentry, name, value,
+ size, flags);
if (ret == 1)
ret = cap_inode_setxattr(dentry, name, value, size, flags);
return call_int_hook(inode_listxattr, 0, dentry);
}
-int security_inode_removexattr(struct dentry *dentry, const char *name)
+int security_inode_removexattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, const char *name)
{
int ret;
* SELinux and Smack integrate the cap call,
* so assume that all LSMs supplying this call do so.
*/
- ret = call_int_hook(inode_removexattr, 1, dentry, name);
+ ret = call_int_hook(inode_removexattr, 1, mnt_userns, dentry, name);
if (ret == 1)
- ret = cap_inode_removexattr(dentry, name);
+ ret = cap_inode_removexattr(mnt_userns, dentry, name);
if (ret)
return ret;
ret = ima_inode_removexattr(dentry, name);
return call_int_hook(inode_need_killpriv, 0, dentry);
}
-int security_inode_killpriv(struct dentry *dentry)
+int security_inode_killpriv(struct user_namespace *mnt_userns,
+ struct dentry *dentry)
{
- return call_int_hook(inode_killpriv, 0, dentry);
+ return call_int_hook(inode_killpriv, 0, mnt_userns, dentry);
}
-int security_inode_getsecurity(struct inode *inode, const char *name, void **buffer, bool alloc)
+int security_inode_getsecurity(struct user_namespace *mnt_userns,
+ struct inode *inode, const char *name,
+ void **buffer, bool alloc)
{
struct security_hook_list *hp;
int rc;
* Only one module will provide an attribute with a given name.
*/
hlist_for_each_entry(hp, &security_hook_heads.inode_getsecurity, list) {
- rc = hp->hook.inode_getsecurity(inode, name, buffer, alloc);
+ rc = hp->hook.inode_getsecurity(mnt_userns, inode, name, buffer, alloc);
if (rc != LSM_RET_DEFAULT(inode_getsecurity))
return rc;
}
return true;
}
-static int selinux_inode_setxattr(struct dentry *dentry, const char *name,
+static int selinux_inode_setxattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, const char *name,
const void *value, size_t size, int flags)
{
struct inode *inode = d_backing_inode(dentry);
}
if (!selinux_initialized(&selinux_state))
- return (inode_owner_or_capable(inode) ? 0 : -EPERM);
+ return (inode_owner_or_capable(mnt_userns, inode) ? 0 : -EPERM);
sbsec = inode->i_sb->s_security;
if (!(sbsec->flags & SBLABEL_MNT))
return -EOPNOTSUPP;
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(mnt_userns, inode))
return -EPERM;
ad.type = LSM_AUDIT_DATA_DENTRY;
return dentry_has_perm(cred, dentry, FILE__GETATTR);
}
-static int selinux_inode_removexattr(struct dentry *dentry, const char *name)
+static int selinux_inode_removexattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, const char *name)
{
if (strcmp(name, XATTR_NAME_SELINUX)) {
- int rc = cap_inode_removexattr(dentry, name);
+ int rc = cap_inode_removexattr(mnt_userns, dentry, name);
if (rc)
return rc;
*
* Permission check is handled by selinux_inode_getxattr hook.
*/
-static int selinux_inode_getsecurity(struct inode *inode, const char *name, void **buffer, bool alloc)
+static int selinux_inode_getsecurity(struct user_namespace *mnt_userns,
+ struct inode *inode, const char *name,
+ void **buffer, bool alloc)
{
u32 size;
int error;
*/
static int selinux_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen)
{
- return __vfs_setxattr_noperm(dentry, XATTR_NAME_SELINUX, ctx, ctxlen, 0);
+ return __vfs_setxattr_noperm(&init_user_ns, dentry, XATTR_NAME_SELINUX,
+ ctx, ctxlen, 0);
}
static int selinux_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen)
{
int len = 0;
- len = selinux_inode_getsecurity(inode, XATTR_SELINUX_SUFFIX,
- ctx, true);
+ len = selinux_inode_getsecurity(&init_user_ns, inode,
+ XATTR_SELINUX_SUFFIX, ctx, true);
if (len < 0)
return len;
*ctxlen = len;
*
* Returns 0 if access is permitted, an error code otherwise
*/
-static int smack_inode_setxattr(struct dentry *dentry, const char *name,
+static int smack_inode_setxattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, const char *name,
const void *value, size_t size, int flags)
{
struct smk_audit_info ad;
*
* Returns 0 if access is permitted, an error code otherwise
*/
-static int smack_inode_removexattr(struct dentry *dentry, const char *name)
+static int smack_inode_removexattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, const char *name)
{
struct inode_smack *isp;
struct smk_audit_info ad;
if (!smack_privileged(CAP_MAC_ADMIN))
rc = -EPERM;
} else
- rc = cap_inode_removexattr(dentry, name);
+ rc = cap_inode_removexattr(mnt_userns, dentry, name);
if (rc != 0)
return rc;
*
* Returns the size of the attribute or an error code
*/
-static int smack_inode_getsecurity(struct inode *inode,
- const char *name, void **buffer,
- bool alloc)
+static int smack_inode_getsecurity(struct user_namespace *mnt_userns,
+ struct inode *inode, const char *name,
+ void **buffer, bool alloc)
{
struct socket_smack *ssp;
struct socket *sock;
*/
if (isp->smk_flags & SMK_INODE_CHANGED) {
isp->smk_flags &= ~SMK_INODE_CHANGED;
- rc = __vfs_setxattr(dp, inode,
+ rc = __vfs_setxattr(&init_user_ns, dp, inode,
XATTR_NAME_SMACKTRANSMUTE,
TRANS_TRUE, TRANS_TRUE_SIZE,
0);
static int smack_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen)
{
- return smack_inode_setsecurity(inode, XATTR_SMACK_SUFFIX, ctx, ctxlen, 0);
+ return smack_inode_setsecurity(inode, XATTR_SMACK_SUFFIX, ctx,
+ ctxlen, 0);
}
static int smack_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen)
{
- return __vfs_setxattr_noperm(dentry, XATTR_NAME_SMACK, ctx, ctxlen, 0);
+ return __vfs_setxattr_noperm(&init_user_ns, dentry, XATTR_NAME_SMACK,
+ ctx, ctxlen, 0);
}
static int smack_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen)
__SYSCALL(__NR_process_madvise, sys_process_madvise)
#define __NR_epoll_pwait2 441
__SC_COMP(__NR_epoll_pwait2, sys_epoll_pwait2, compat_sys_epoll_pwait2)
+#define __NR_mount_setattr 442
+__SYSCALL(__NR_mount_setattr, sys_mount_setattr)
#undef __NR_syscalls
-#define __NR_syscalls 442
+#define __NR_syscalls 443
/*
* 32 bit systems traditionally used different
TARGETS += memory-hotplug
TARGETS += mincore
TARGETS += mount
+TARGETS += mount_setattr
TARGETS += mqueue
TARGETS += nci
TARGETS += net
--- /dev/null
+mount_setattr_test
--- /dev/null
+# SPDX-License-Identifier: GPL-2.0
+# Makefile for mount selftests.
+CFLAGS = -g -I../../../../usr/include/ -Wall -O2 -pthread
+
+TEST_GEN_FILES += mount_setattr_test
+
+include ../lib.mk
--- /dev/null
+CONFIG_USER_NS=y
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <sched.h>
+#include <stdio.h>
+#include <errno.h>
+#include <pthread.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <sys/mount.h>
+#include <sys/wait.h>
+#include <sys/vfs.h>
+#include <sys/statvfs.h>
+#include <sys/sysinfo.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <grp.h>
+#include <stdbool.h>
+#include <stdarg.h>
+
+#include "../kselftest_harness.h"
+
+#ifndef CLONE_NEWNS
+#define CLONE_NEWNS 0x00020000
+#endif
+
+#ifndef CLONE_NEWUSER
+#define CLONE_NEWUSER 0x10000000
+#endif
+
+#ifndef MS_REC
+#define MS_REC 16384
+#endif
+
+#ifndef MS_RELATIME
+#define MS_RELATIME (1 << 21)
+#endif
+
+#ifndef MS_STRICTATIME
+#define MS_STRICTATIME (1 << 24)
+#endif
+
+#ifndef MOUNT_ATTR_RDONLY
+#define MOUNT_ATTR_RDONLY 0x00000001
+#endif
+
+#ifndef MOUNT_ATTR_NOSUID
+#define MOUNT_ATTR_NOSUID 0x00000002
+#endif
+
+#ifndef MOUNT_ATTR_NOEXEC
+#define MOUNT_ATTR_NOEXEC 0x00000008
+#endif
+
+#ifndef MOUNT_ATTR_NODIRATIME
+#define MOUNT_ATTR_NODIRATIME 0x00000080
+#endif
+
+#ifndef MOUNT_ATTR__ATIME
+#define MOUNT_ATTR__ATIME 0x00000070
+#endif
+
+#ifndef MOUNT_ATTR_RELATIME
+#define MOUNT_ATTR_RELATIME 0x00000000
+#endif
+
+#ifndef MOUNT_ATTR_NOATIME
+#define MOUNT_ATTR_NOATIME 0x00000010
+#endif
+
+#ifndef MOUNT_ATTR_STRICTATIME
+#define MOUNT_ATTR_STRICTATIME 0x00000020
+#endif
+
+#ifndef AT_RECURSIVE
+#define AT_RECURSIVE 0x8000
+#endif
+
+#ifndef MS_SHARED
+#define MS_SHARED (1 << 20)
+#endif
+
+#define DEFAULT_THREADS 4
+#define ptr_to_int(p) ((int)((intptr_t)(p)))
+#define int_to_ptr(u) ((void *)((intptr_t)(u)))
+
+#ifndef __NR_mount_setattr
+ #if defined __alpha__
+ #define __NR_mount_setattr 552
+ #elif defined _MIPS_SIM
+ #if _MIPS_SIM == _MIPS_SIM_ABI32 /* o32 */
+ #define __NR_mount_setattr (442 + 4000)
+ #endif
+ #if _MIPS_SIM == _MIPS_SIM_NABI32 /* n32 */
+ #define __NR_mount_setattr (442 + 6000)
+ #endif
+ #if _MIPS_SIM == _MIPS_SIM_ABI64 /* n64 */
+ #define __NR_mount_setattr (442 + 5000)
+ #endif
+ #elif defined __ia64__
+ #define __NR_mount_setattr (442 + 1024)
+ #else
+ #define __NR_mount_setattr 442
+ #endif
+
+struct mount_attr {
+ __u64 attr_set;
+ __u64 attr_clr;
+ __u64 propagation;
+ __u64 userns_fd;
+};
+#endif
+
+#ifndef __NR_open_tree
+ #if defined __alpha__
+ #define __NR_open_tree 538
+ #elif defined _MIPS_SIM
+ #if _MIPS_SIM == _MIPS_SIM_ABI32 /* o32 */
+ #define __NR_open_tree 4428
+ #endif
+ #if _MIPS_SIM == _MIPS_SIM_NABI32 /* n32 */
+ #define __NR_open_tree 6428
+ #endif
+ #if _MIPS_SIM == _MIPS_SIM_ABI64 /* n64 */
+ #define __NR_open_tree 5428
+ #endif
+ #elif defined __ia64__
+ #define __NR_open_tree (428 + 1024)
+ #else
+ #define __NR_open_tree 428
+ #endif
+#endif
+
+#ifndef MOUNT_ATTR_IDMAP
+#define MOUNT_ATTR_IDMAP 0x00100000
+#endif
+
+static inline int sys_mount_setattr(int dfd, const char *path, unsigned int flags,
+ struct mount_attr *attr, size_t size)
+{
+ return syscall(__NR_mount_setattr, dfd, path, flags, attr, size);
+}
+
+#ifndef OPEN_TREE_CLONE
+#define OPEN_TREE_CLONE 1
+#endif
+
+#ifndef OPEN_TREE_CLOEXEC
+#define OPEN_TREE_CLOEXEC O_CLOEXEC
+#endif
+
+#ifndef AT_RECURSIVE
+#define AT_RECURSIVE 0x8000 /* Apply to the entire subtree */
+#endif
+
+static inline int sys_open_tree(int dfd, const char *filename, unsigned int flags)
+{
+ return syscall(__NR_open_tree, dfd, filename, flags);
+}
+
+static ssize_t write_nointr(int fd, const void *buf, size_t count)
+{
+ ssize_t ret;
+
+ do {
+ ret = write(fd, buf, count);
+ } while (ret < 0 && errno == EINTR);
+
+ return ret;
+}
+
+static int write_file(const char *path, const void *buf, size_t count)
+{
+ int fd;
+ ssize_t ret;
+
+ fd = open(path, O_WRONLY | O_CLOEXEC | O_NOCTTY | O_NOFOLLOW);
+ if (fd < 0)
+ return -1;
+
+ ret = write_nointr(fd, buf, count);
+ close(fd);
+ if (ret < 0 || (size_t)ret != count)
+ return -1;
+
+ return 0;
+}
+
+static int create_and_enter_userns(void)
+{
+ uid_t uid;
+ gid_t gid;
+ char map[100];
+
+ uid = getuid();
+ gid = getgid();
+
+ if (unshare(CLONE_NEWUSER))
+ return -1;
+
+ if (write_file("/proc/self/setgroups", "deny", sizeof("deny") - 1) &&
+ errno != ENOENT)
+ return -1;
+
+ snprintf(map, sizeof(map), "0 %d 1", uid);
+ if (write_file("/proc/self/uid_map", map, strlen(map)))
+ return -1;
+
+
+ snprintf(map, sizeof(map), "0 %d 1", gid);
+ if (write_file("/proc/self/gid_map", map, strlen(map)))
+ return -1;
+
+ if (setgid(0))
+ return -1;
+
+ if (setuid(0))
+ return -1;
+
+ return 0;
+}
+
+static int prepare_unpriv_mountns(void)
+{
+ if (create_and_enter_userns())
+ return -1;
+
+ if (unshare(CLONE_NEWNS))
+ return -1;
+
+ if (mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0))
+ return -1;
+
+ return 0;
+}
+
+static int read_mnt_flags(const char *path)
+{
+ int ret;
+ struct statvfs stat;
+ unsigned int mnt_flags;
+
+ ret = statvfs(path, &stat);
+ if (ret != 0)
+ return -EINVAL;
+
+ if (stat.f_flag &
+ ~(ST_RDONLY | ST_NOSUID | ST_NODEV | ST_NOEXEC | ST_NOATIME |
+ ST_NODIRATIME | ST_RELATIME | ST_SYNCHRONOUS | ST_MANDLOCK))
+ return -EINVAL;
+
+ mnt_flags = 0;
+ if (stat.f_flag & ST_RDONLY)
+ mnt_flags |= MS_RDONLY;
+ if (stat.f_flag & ST_NOSUID)
+ mnt_flags |= MS_NOSUID;
+ if (stat.f_flag & ST_NODEV)
+ mnt_flags |= MS_NODEV;
+ if (stat.f_flag & ST_NOEXEC)
+ mnt_flags |= MS_NOEXEC;
+ if (stat.f_flag & ST_NOATIME)
+ mnt_flags |= MS_NOATIME;
+ if (stat.f_flag & ST_NODIRATIME)
+ mnt_flags |= MS_NODIRATIME;
+ if (stat.f_flag & ST_RELATIME)
+ mnt_flags |= MS_RELATIME;
+ if (stat.f_flag & ST_SYNCHRONOUS)
+ mnt_flags |= MS_SYNCHRONOUS;
+ if (stat.f_flag & ST_MANDLOCK)
+ mnt_flags |= ST_MANDLOCK;
+
+ return mnt_flags;
+}
+
+static char *get_field(char *src, int nfields)
+{
+ int i;
+ char *p = src;
+
+ for (i = 0; i < nfields; i++) {
+ while (*p && *p != ' ' && *p != '\t')
+ p++;
+
+ if (!*p)
+ break;
+
+ p++;
+ }
+
+ return p;
+}
+
+static void null_endofword(char *word)
+{
+ while (*word && *word != ' ' && *word != '\t')
+ word++;
+ *word = '\0';
+}
+
+static bool is_shared_mount(const char *path)
+{
+ size_t len = 0;
+ char *line = NULL;
+ FILE *f = NULL;
+
+ f = fopen("/proc/self/mountinfo", "re");
+ if (!f)
+ return false;
+
+ while (getline(&line, &len, f) != -1) {
+ char *opts, *target;
+
+ target = get_field(line, 4);
+ if (!target)
+ continue;
+
+ opts = get_field(target, 2);
+ if (!opts)
+ continue;
+
+ null_endofword(target);
+
+ if (strcmp(target, path) != 0)
+ continue;
+
+ null_endofword(opts);
+ if (strstr(opts, "shared:"))
+ return true;
+ }
+
+ free(line);
+ fclose(f);
+
+ return false;
+}
+
+static void *mount_setattr_thread(void *data)
+{
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_RDONLY | MOUNT_ATTR_NOSUID,
+ .attr_clr = 0,
+ .propagation = MS_SHARED,
+ };
+
+ if (sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)))
+ pthread_exit(int_to_ptr(-1));
+
+ pthread_exit(int_to_ptr(0));
+}
+
+/* Attempt to de-conflict with the selftests tree. */
+#ifndef SKIP
+#define SKIP(s, ...) XFAIL(s, ##__VA_ARGS__)
+#endif
+
+static bool mount_setattr_supported(void)
+{
+ int ret;
+
+ ret = sys_mount_setattr(-EBADF, "", AT_EMPTY_PATH, NULL, 0);
+ if (ret < 0 && errno == ENOSYS)
+ return false;
+
+ return true;
+}
+
+FIXTURE(mount_setattr) {
+};
+
+FIXTURE_SETUP(mount_setattr)
+{
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ ASSERT_EQ(prepare_unpriv_mountns(), 0);
+
+ (void)umount2("/mnt", MNT_DETACH);
+ (void)umount2("/tmp", MNT_DETACH);
+
+ ASSERT_EQ(mount("testing", "/tmp", "tmpfs", MS_NOATIME | MS_NODEV,
+ "size=100000,mode=700"), 0);
+
+ ASSERT_EQ(mkdir("/tmp/B", 0777), 0);
+
+ ASSERT_EQ(mount("testing", "/tmp/B", "tmpfs", MS_NOATIME | MS_NODEV,
+ "size=100000,mode=700"), 0);
+
+ ASSERT_EQ(mkdir("/tmp/B/BB", 0777), 0);
+
+ ASSERT_EQ(mount("testing", "/tmp/B/BB", "tmpfs", MS_NOATIME | MS_NODEV,
+ "size=100000,mode=700"), 0);
+
+ ASSERT_EQ(mount("testing", "/mnt", "tmpfs", MS_NOATIME | MS_NODEV,
+ "size=100000,mode=700"), 0);
+
+ ASSERT_EQ(mkdir("/mnt/A", 0777), 0);
+
+ ASSERT_EQ(mount("testing", "/mnt/A", "tmpfs", MS_NOATIME | MS_NODEV,
+ "size=100000,mode=700"), 0);
+
+ ASSERT_EQ(mkdir("/mnt/A/AA", 0777), 0);
+
+ ASSERT_EQ(mount("/tmp", "/mnt/A/AA", NULL, MS_BIND | MS_REC, NULL), 0);
+
+ ASSERT_EQ(mkdir("/mnt/B", 0777), 0);
+
+ ASSERT_EQ(mount("testing", "/mnt/B", "ramfs",
+ MS_NOATIME | MS_NODEV | MS_NOSUID, 0), 0);
+
+ ASSERT_EQ(mkdir("/mnt/B/BB", 0777), 0);
+
+ ASSERT_EQ(mount("testing", "/tmp/B/BB", "devpts",
+ MS_RELATIME | MS_NOEXEC | MS_RDONLY, 0), 0);
+}
+
+FIXTURE_TEARDOWN(mount_setattr)
+{
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ (void)umount2("/mnt/A", MNT_DETACH);
+ (void)umount2("/tmp", MNT_DETACH);
+}
+
+TEST_F(mount_setattr, invalid_attributes)
+{
+ struct mount_attr invalid_attr = {
+ .attr_set = (1U << 31),
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ ASSERT_NE(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &invalid_attr,
+ sizeof(invalid_attr)), 0);
+
+ invalid_attr.attr_set = 0;
+ invalid_attr.attr_clr = (1U << 31);
+ ASSERT_NE(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &invalid_attr,
+ sizeof(invalid_attr)), 0);
+
+ invalid_attr.attr_clr = 0;
+ invalid_attr.propagation = (1U << 31);
+ ASSERT_NE(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &invalid_attr,
+ sizeof(invalid_attr)), 0);
+
+ invalid_attr.attr_set = (1U << 31);
+ invalid_attr.attr_clr = (1U << 31);
+ invalid_attr.propagation = (1U << 31);
+ ASSERT_NE(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &invalid_attr,
+ sizeof(invalid_attr)), 0);
+
+ ASSERT_NE(sys_mount_setattr(-1, "mnt/A", AT_RECURSIVE, &invalid_attr,
+ sizeof(invalid_attr)), 0);
+}
+
+TEST_F(mount_setattr, extensibility)
+{
+ unsigned int old_flags = 0, new_flags = 0, expected_flags = 0;
+ char *s = "dummy";
+ struct mount_attr invalid_attr = {};
+ struct mount_attr_large {
+ struct mount_attr attr1;
+ struct mount_attr attr2;
+ struct mount_attr attr3;
+ } large_attr = {};
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ old_flags = read_mnt_flags("/mnt/A");
+ ASSERT_GT(old_flags, 0);
+
+ ASSERT_NE(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, NULL,
+ sizeof(invalid_attr)), 0);
+ ASSERT_EQ(errno, EFAULT);
+
+ ASSERT_NE(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, (void *)s,
+ sizeof(invalid_attr)), 0);
+ ASSERT_EQ(errno, EINVAL);
+
+ ASSERT_NE(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &invalid_attr, 0), 0);
+ ASSERT_EQ(errno, EINVAL);
+
+ ASSERT_NE(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &invalid_attr,
+ sizeof(invalid_attr) / 2), 0);
+ ASSERT_EQ(errno, EINVAL);
+
+ ASSERT_NE(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &invalid_attr,
+ sizeof(invalid_attr) / 2), 0);
+ ASSERT_EQ(errno, EINVAL);
+
+ ASSERT_EQ(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE,
+ (void *)&large_attr, sizeof(large_attr)), 0);
+
+ large_attr.attr3.attr_set = MOUNT_ATTR_RDONLY;
+ ASSERT_NE(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE,
+ (void *)&large_attr, sizeof(large_attr)), 0);
+
+ large_attr.attr3.attr_set = 0;
+ large_attr.attr1.attr_set = MOUNT_ATTR_RDONLY;
+ ASSERT_EQ(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE,
+ (void *)&large_attr, sizeof(large_attr)), 0);
+
+ expected_flags = old_flags;
+ expected_flags |= MS_RDONLY;
+
+ new_flags = read_mnt_flags("/mnt/A");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B/BB");
+ ASSERT_EQ(new_flags, expected_flags);
+}
+
+TEST_F(mount_setattr, basic)
+{
+ unsigned int old_flags = 0, new_flags = 0, expected_flags = 0;
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_RDONLY | MOUNT_ATTR_NOEXEC | MOUNT_ATTR_RELATIME,
+ .attr_clr = MOUNT_ATTR__ATIME,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ old_flags = read_mnt_flags("/mnt/A");
+ ASSERT_GT(old_flags, 0);
+
+ ASSERT_EQ(sys_mount_setattr(-1, "/mnt/A", 0, &attr, sizeof(attr)), 0);
+
+ expected_flags = old_flags;
+ expected_flags |= MS_RDONLY;
+ expected_flags |= MS_NOEXEC;
+ expected_flags &= ~MS_NOATIME;
+ expected_flags |= MS_RELATIME;
+
+ new_flags = read_mnt_flags("/mnt/A");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA");
+ ASSERT_EQ(new_flags, old_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B");
+ ASSERT_EQ(new_flags, old_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B/BB");
+ ASSERT_EQ(new_flags, old_flags);
+}
+
+TEST_F(mount_setattr, basic_recursive)
+{
+ int fd;
+ unsigned int old_flags = 0, new_flags = 0, expected_flags = 0;
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_RDONLY | MOUNT_ATTR_NOEXEC | MOUNT_ATTR_RELATIME,
+ .attr_clr = MOUNT_ATTR__ATIME,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ old_flags = read_mnt_flags("/mnt/A");
+ ASSERT_GT(old_flags, 0);
+
+ ASSERT_EQ(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ expected_flags = old_flags;
+ expected_flags |= MS_RDONLY;
+ expected_flags |= MS_NOEXEC;
+ expected_flags &= ~MS_NOATIME;
+ expected_flags |= MS_RELATIME;
+
+ new_flags = read_mnt_flags("/mnt/A");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B/BB");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ memset(&attr, 0, sizeof(attr));
+ attr.attr_clr = MOUNT_ATTR_RDONLY;
+ attr.propagation = MS_SHARED;
+ ASSERT_EQ(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ expected_flags &= ~MS_RDONLY;
+ new_flags = read_mnt_flags("/mnt/A");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ ASSERT_EQ(is_shared_mount("/mnt/A"), true);
+
+ new_flags = read_mnt_flags("/mnt/A/AA");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ ASSERT_EQ(is_shared_mount("/mnt/A/AA"), true);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ ASSERT_EQ(is_shared_mount("/mnt/A/AA/B"), true);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B/BB");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ ASSERT_EQ(is_shared_mount("/mnt/A/AA/B/BB"), true);
+
+ fd = open("/mnt/A/AA/B/b", O_RDWR | O_CLOEXEC | O_CREAT | O_EXCL, 0777);
+ ASSERT_GE(fd, 0);
+
+ /*
+ * We're holding a fd open for writing so this needs to fail somewhere
+ * in the middle and the mount options need to be unchanged.
+ */
+ attr.attr_set = MOUNT_ATTR_RDONLY;
+ ASSERT_LT(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ new_flags = read_mnt_flags("/mnt/A");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ ASSERT_EQ(is_shared_mount("/mnt/A"), true);
+
+ new_flags = read_mnt_flags("/mnt/A/AA");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ ASSERT_EQ(is_shared_mount("/mnt/A/AA"), true);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ ASSERT_EQ(is_shared_mount("/mnt/A/AA/B"), true);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B/BB");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ ASSERT_EQ(is_shared_mount("/mnt/A/AA/B/BB"), true);
+
+ EXPECT_EQ(close(fd), 0);
+}
+
+TEST_F(mount_setattr, mount_has_writers)
+{
+ int fd, dfd;
+ unsigned int old_flags = 0, new_flags = 0;
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_RDONLY | MOUNT_ATTR_NOEXEC | MOUNT_ATTR_RELATIME,
+ .attr_clr = MOUNT_ATTR__ATIME,
+ .propagation = MS_SHARED,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ old_flags = read_mnt_flags("/mnt/A");
+ ASSERT_GT(old_flags, 0);
+
+ fd = open("/mnt/A/AA/B/b", O_RDWR | O_CLOEXEC | O_CREAT | O_EXCL, 0777);
+ ASSERT_GE(fd, 0);
+
+ /*
+ * We're holding a fd open to a mount somwhere in the middle so this
+ * needs to fail somewhere in the middle. After this the mount options
+ * need to be unchanged.
+ */
+ ASSERT_LT(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ new_flags = read_mnt_flags("/mnt/A");
+ ASSERT_EQ(new_flags, old_flags);
+
+ ASSERT_EQ(is_shared_mount("/mnt/A"), false);
+
+ new_flags = read_mnt_flags("/mnt/A/AA");
+ ASSERT_EQ(new_flags, old_flags);
+
+ ASSERT_EQ(is_shared_mount("/mnt/A/AA"), false);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B");
+ ASSERT_EQ(new_flags, old_flags);
+
+ ASSERT_EQ(is_shared_mount("/mnt/A/AA/B"), false);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B/BB");
+ ASSERT_EQ(new_flags, old_flags);
+
+ ASSERT_EQ(is_shared_mount("/mnt/A/AA/B/BB"), false);
+
+ dfd = open("/mnt/A/AA/B", O_DIRECTORY | O_CLOEXEC);
+ ASSERT_GE(dfd, 0);
+ EXPECT_EQ(fsync(dfd), 0);
+ EXPECT_EQ(close(dfd), 0);
+
+ EXPECT_EQ(fsync(fd), 0);
+ EXPECT_EQ(close(fd), 0);
+
+ /* All writers are gone so this should succeed. */
+ ASSERT_EQ(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+}
+
+TEST_F(mount_setattr, mixed_mount_options)
+{
+ unsigned int old_flags1 = 0, old_flags2 = 0, new_flags = 0, expected_flags = 0;
+ struct mount_attr attr = {
+ .attr_clr = MOUNT_ATTR_RDONLY | MOUNT_ATTR_NOSUID | MOUNT_ATTR_NOEXEC | MOUNT_ATTR__ATIME,
+ .attr_set = MOUNT_ATTR_RELATIME,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ old_flags1 = read_mnt_flags("/mnt/B");
+ ASSERT_GT(old_flags1, 0);
+
+ old_flags2 = read_mnt_flags("/mnt/B/BB");
+ ASSERT_GT(old_flags2, 0);
+
+ ASSERT_EQ(sys_mount_setattr(-1, "/mnt/B", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ expected_flags = old_flags2;
+ expected_flags &= ~(MS_RDONLY | MS_NOEXEC | MS_NOATIME | MS_NOSUID);
+ expected_flags |= MS_RELATIME;
+
+ new_flags = read_mnt_flags("/mnt/B");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ expected_flags = old_flags2;
+ expected_flags &= ~(MS_RDONLY | MS_NOEXEC | MS_NOATIME | MS_NOSUID);
+ expected_flags |= MS_RELATIME;
+
+ new_flags = read_mnt_flags("/mnt/B/BB");
+ ASSERT_EQ(new_flags, expected_flags);
+}
+
+TEST_F(mount_setattr, time_changes)
+{
+ unsigned int old_flags = 0, new_flags = 0, expected_flags = 0;
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_NODIRATIME | MOUNT_ATTR_NOATIME,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ ASSERT_NE(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ attr.attr_set = MOUNT_ATTR_STRICTATIME;
+ ASSERT_NE(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ attr.attr_set = MOUNT_ATTR_STRICTATIME | MOUNT_ATTR_NOATIME;
+ ASSERT_NE(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ attr.attr_set = MOUNT_ATTR_STRICTATIME | MOUNT_ATTR_NOATIME;
+ attr.attr_clr = MOUNT_ATTR__ATIME;
+ ASSERT_NE(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ attr.attr_set = 0;
+ attr.attr_clr = MOUNT_ATTR_STRICTATIME;
+ ASSERT_NE(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ attr.attr_clr = MOUNT_ATTR_NOATIME;
+ ASSERT_NE(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ old_flags = read_mnt_flags("/mnt/A");
+ ASSERT_GT(old_flags, 0);
+
+ attr.attr_set = MOUNT_ATTR_NODIRATIME | MOUNT_ATTR_NOATIME;
+ attr.attr_clr = MOUNT_ATTR__ATIME;
+ ASSERT_EQ(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ expected_flags = old_flags;
+ expected_flags |= MS_NOATIME;
+ expected_flags |= MS_NODIRATIME;
+
+ new_flags = read_mnt_flags("/mnt/A");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B/BB");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ memset(&attr, 0, sizeof(attr));
+ attr.attr_set &= ~MOUNT_ATTR_NOATIME;
+ attr.attr_set |= MOUNT_ATTR_RELATIME;
+ attr.attr_clr |= MOUNT_ATTR__ATIME;
+ ASSERT_EQ(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ expected_flags &= ~MS_NOATIME;
+ expected_flags |= MS_RELATIME;
+
+ new_flags = read_mnt_flags("/mnt/A");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B/BB");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ memset(&attr, 0, sizeof(attr));
+ attr.attr_set &= ~MOUNT_ATTR_RELATIME;
+ attr.attr_set |= MOUNT_ATTR_STRICTATIME;
+ attr.attr_clr |= MOUNT_ATTR__ATIME;
+ ASSERT_EQ(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ expected_flags &= ~MS_RELATIME;
+
+ new_flags = read_mnt_flags("/mnt/A");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B/BB");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ memset(&attr, 0, sizeof(attr));
+ attr.attr_set &= ~MOUNT_ATTR_STRICTATIME;
+ attr.attr_set |= MOUNT_ATTR_NOATIME;
+ attr.attr_clr |= MOUNT_ATTR__ATIME;
+ ASSERT_EQ(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ expected_flags |= MS_NOATIME;
+ new_flags = read_mnt_flags("/mnt/A");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B/BB");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ memset(&attr, 0, sizeof(attr));
+ ASSERT_EQ(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ new_flags = read_mnt_flags("/mnt/A");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B/BB");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ memset(&attr, 0, sizeof(attr));
+ attr.attr_clr = MOUNT_ATTR_NODIRATIME;
+ ASSERT_EQ(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ expected_flags &= ~MS_NODIRATIME;
+
+ new_flags = read_mnt_flags("/mnt/A");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B/BB");
+ ASSERT_EQ(new_flags, expected_flags);
+}
+
+TEST_F(mount_setattr, multi_threaded)
+{
+ int i, j, nthreads, ret = 0;
+ unsigned int old_flags = 0, new_flags = 0, expected_flags = 0;
+ pthread_attr_t pattr;
+ pthread_t threads[DEFAULT_THREADS];
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ old_flags = read_mnt_flags("/mnt/A");
+ ASSERT_GT(old_flags, 0);
+
+ /* Try to change mount options from multiple threads. */
+ nthreads = get_nprocs_conf();
+ if (nthreads > DEFAULT_THREADS)
+ nthreads = DEFAULT_THREADS;
+
+ pthread_attr_init(&pattr);
+ for (i = 0; i < nthreads; i++)
+ ASSERT_EQ(pthread_create(&threads[i], &pattr, mount_setattr_thread, NULL), 0);
+
+ for (j = 0; j < i; j++) {
+ void *retptr = NULL;
+
+ EXPECT_EQ(pthread_join(threads[j], &retptr), 0);
+
+ ret += ptr_to_int(retptr);
+ EXPECT_EQ(ret, 0);
+ }
+ pthread_attr_destroy(&pattr);
+
+ ASSERT_EQ(ret, 0);
+
+ expected_flags = old_flags;
+ expected_flags |= MS_RDONLY;
+ expected_flags |= MS_NOSUID;
+ new_flags = read_mnt_flags("/mnt/A");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ ASSERT_EQ(is_shared_mount("/mnt/A"), true);
+
+ new_flags = read_mnt_flags("/mnt/A/AA");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ ASSERT_EQ(is_shared_mount("/mnt/A/AA"), true);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ ASSERT_EQ(is_shared_mount("/mnt/A/AA/B"), true);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B/BB");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ ASSERT_EQ(is_shared_mount("/mnt/A/AA/B/BB"), true);
+}
+
+TEST_F(mount_setattr, wrong_user_namespace)
+{
+ int ret;
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_RDONLY,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ EXPECT_EQ(create_and_enter_userns(), 0);
+ ret = sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr));
+ ASSERT_LT(ret, 0);
+ ASSERT_EQ(errno, EPERM);
+}
+
+TEST_F(mount_setattr, wrong_mount_namespace)
+{
+ int fd, ret;
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_RDONLY,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ fd = open("/mnt/A", O_DIRECTORY | O_CLOEXEC);
+ ASSERT_GE(fd, 0);
+
+ ASSERT_EQ(unshare(CLONE_NEWNS), 0);
+
+ ret = sys_mount_setattr(fd, "", AT_EMPTY_PATH | AT_RECURSIVE, &attr, sizeof(attr));
+ ASSERT_LT(ret, 0);
+ ASSERT_EQ(errno, EINVAL);
+}
+
+FIXTURE(mount_setattr_idmapped) {
+};
+
+FIXTURE_SETUP(mount_setattr_idmapped)
+{
+ int img_fd = -EBADF;
+
+ ASSERT_EQ(unshare(CLONE_NEWNS), 0);
+
+ ASSERT_EQ(mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0), 0);
+
+ (void)umount2("/mnt", MNT_DETACH);
+ (void)umount2("/tmp", MNT_DETACH);
+
+ ASSERT_EQ(mount("testing", "/tmp", "tmpfs", MS_NOATIME | MS_NODEV,
+ "size=100000,mode=700"), 0);
+
+ ASSERT_EQ(mkdir("/tmp/B", 0777), 0);
+ ASSERT_EQ(mknodat(-EBADF, "/tmp/B/b", S_IFREG | 0644, 0), 0);
+ ASSERT_EQ(chown("/tmp/B/b", 0, 0), 0);
+
+ ASSERT_EQ(mount("testing", "/tmp/B", "tmpfs", MS_NOATIME | MS_NODEV,
+ "size=100000,mode=700"), 0);
+
+ ASSERT_EQ(mkdir("/tmp/B/BB", 0777), 0);
+ ASSERT_EQ(mknodat(-EBADF, "/tmp/B/BB/b", S_IFREG | 0644, 0), 0);
+ ASSERT_EQ(chown("/tmp/B/BB/b", 0, 0), 0);
+
+ ASSERT_EQ(mount("testing", "/tmp/B/BB", "tmpfs", MS_NOATIME | MS_NODEV,
+ "size=100000,mode=700"), 0);
+
+ ASSERT_EQ(mount("testing", "/mnt", "tmpfs", MS_NOATIME | MS_NODEV,
+ "size=100000,mode=700"), 0);
+
+ ASSERT_EQ(mkdir("/mnt/A", 0777), 0);
+
+ ASSERT_EQ(mount("testing", "/mnt/A", "tmpfs", MS_NOATIME | MS_NODEV,
+ "size=100000,mode=700"), 0);
+
+ ASSERT_EQ(mkdir("/mnt/A/AA", 0777), 0);
+
+ ASSERT_EQ(mount("/tmp", "/mnt/A/AA", NULL, MS_BIND | MS_REC, NULL), 0);
+
+ ASSERT_EQ(mkdir("/mnt/B", 0777), 0);
+
+ ASSERT_EQ(mount("testing", "/mnt/B", "ramfs",
+ MS_NOATIME | MS_NODEV | MS_NOSUID, 0), 0);
+
+ ASSERT_EQ(mkdir("/mnt/B/BB", 0777), 0);
+
+ ASSERT_EQ(mount("testing", "/tmp/B/BB", "devpts",
+ MS_RELATIME | MS_NOEXEC | MS_RDONLY, 0), 0);
+
+ ASSERT_EQ(mkdir("/mnt/C", 0777), 0);
+ ASSERT_EQ(mkdir("/mnt/D", 0777), 0);
+ img_fd = openat(-EBADF, "/mnt/C/ext4.img", O_CREAT | O_WRONLY, 0600);
+ ASSERT_GE(img_fd, 0);
+ ASSERT_EQ(ftruncate(img_fd, 1024 * 2048), 0);
+ ASSERT_EQ(system("mkfs.ext4 -q /mnt/C/ext4.img"), 0);
+ ASSERT_EQ(system("mount -o loop -t ext4 /mnt/C/ext4.img /mnt/D/"), 0);
+ ASSERT_EQ(close(img_fd), 0);
+}
+
+FIXTURE_TEARDOWN(mount_setattr_idmapped)
+{
+ (void)umount2("/mnt/A", MNT_DETACH);
+ (void)umount2("/tmp", MNT_DETACH);
+}
+
+/**
+ * Validate that negative fd values are rejected.
+ */
+TEST_F(mount_setattr_idmapped, invalid_fd_negative)
+{
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_IDMAP,
+ .userns_fd = -EBADF,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ ASSERT_NE(sys_mount_setattr(-1, "/", 0, &attr, sizeof(attr)), 0) {
+ TH_LOG("failure: created idmapped mount with negative fd");
+ }
+}
+
+/**
+ * Validate that excessively large fd values are rejected.
+ */
+TEST_F(mount_setattr_idmapped, invalid_fd_large)
+{
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_IDMAP,
+ .userns_fd = INT64_MAX,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ ASSERT_NE(sys_mount_setattr(-1, "/", 0, &attr, sizeof(attr)), 0) {
+ TH_LOG("failure: created idmapped mount with too large fd value");
+ }
+}
+
+/**
+ * Validate that closed fd values are rejected.
+ */
+TEST_F(mount_setattr_idmapped, invalid_fd_closed)
+{
+ int fd;
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_IDMAP,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ fd = open("/dev/null", O_RDONLY | O_CLOEXEC);
+ ASSERT_GE(fd, 0);
+ ASSERT_GE(close(fd), 0);
+
+ attr.userns_fd = fd;
+ ASSERT_NE(sys_mount_setattr(-1, "/", 0, &attr, sizeof(attr)), 0) {
+ TH_LOG("failure: created idmapped mount with closed fd");
+ }
+}
+
+/**
+ * Validate that the initial user namespace is rejected.
+ */
+TEST_F(mount_setattr_idmapped, invalid_fd_initial_userns)
+{
+ int open_tree_fd = -EBADF;
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_IDMAP,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ open_tree_fd = sys_open_tree(-EBADF, "/mnt/D",
+ AT_NO_AUTOMOUNT |
+ AT_SYMLINK_NOFOLLOW |
+ OPEN_TREE_CLOEXEC | OPEN_TREE_CLONE);
+ ASSERT_GE(open_tree_fd, 0);
+
+ attr.userns_fd = open("/proc/1/ns/user", O_RDONLY | O_CLOEXEC);
+ ASSERT_GE(attr.userns_fd, 0);
+ ASSERT_NE(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0);
+ ASSERT_EQ(errno, EPERM);
+ ASSERT_EQ(close(attr.userns_fd), 0);
+ ASSERT_EQ(close(open_tree_fd), 0);
+}
+
+static int map_ids(pid_t pid, unsigned long nsid, unsigned long hostid,
+ unsigned long range)
+{
+ char map[100], procfile[256];
+
+ snprintf(procfile, sizeof(procfile), "/proc/%d/uid_map", pid);
+ snprintf(map, sizeof(map), "%lu %lu %lu", nsid, hostid, range);
+ if (write_file(procfile, map, strlen(map)))
+ return -1;
+
+
+ snprintf(procfile, sizeof(procfile), "/proc/%d/gid_map", pid);
+ snprintf(map, sizeof(map), "%lu %lu %lu", nsid, hostid, range);
+ if (write_file(procfile, map, strlen(map)))
+ return -1;
+
+ return 0;
+}
+
+#define __STACK_SIZE (8 * 1024 * 1024)
+static pid_t do_clone(int (*fn)(void *), void *arg, int flags)
+{
+ void *stack;
+
+ stack = malloc(__STACK_SIZE);
+ if (!stack)
+ return -ENOMEM;
+
+#ifdef __ia64__
+ return __clone2(fn, stack, __STACK_SIZE, flags | SIGCHLD, arg, NULL);
+#else
+ return clone(fn, stack + __STACK_SIZE, flags | SIGCHLD, arg, NULL);
+#endif
+}
+
+static int get_userns_fd_cb(void *data)
+{
+ return kill(getpid(), SIGSTOP);
+}
+
+static int wait_for_pid(pid_t pid)
+{
+ int status, ret;
+
+again:
+ ret = waitpid(pid, &status, 0);
+ if (ret == -1) {
+ if (errno == EINTR)
+ goto again;
+
+ return -1;
+ }
+
+ if (!WIFEXITED(status))
+ return -1;
+
+ return WEXITSTATUS(status);
+}
+
+static int get_userns_fd(unsigned long nsid, unsigned long hostid, unsigned long range)
+{
+ int ret;
+ pid_t pid;
+ char path[256];
+
+ pid = do_clone(get_userns_fd_cb, NULL, CLONE_NEWUSER);
+ if (pid < 0)
+ return -errno;
+
+ ret = map_ids(pid, nsid, hostid, range);
+ if (ret < 0)
+ return ret;
+
+ snprintf(path, sizeof(path), "/proc/%d/ns/user", pid);
+ ret = open(path, O_RDONLY | O_CLOEXEC);
+ kill(pid, SIGKILL);
+ wait_for_pid(pid);
+ return ret;
+}
+
+/**
+ * Validate that an attached mount in our mount namespace can be idmapped.
+ * (The kernel enforces that the mount's mount namespace and the caller's mount
+ * namespace match.)
+ */
+TEST_F(mount_setattr_idmapped, attached_mount_inside_current_mount_namespace)
+{
+ int open_tree_fd = -EBADF;
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_IDMAP,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ open_tree_fd = sys_open_tree(-EBADF, "/mnt/D",
+ AT_EMPTY_PATH |
+ AT_NO_AUTOMOUNT |
+ AT_SYMLINK_NOFOLLOW |
+ OPEN_TREE_CLOEXEC);
+ ASSERT_GE(open_tree_fd, 0);
+
+ attr.userns_fd = get_userns_fd(0, 10000, 10000);
+ ASSERT_GE(attr.userns_fd, 0);
+ ASSERT_EQ(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0);
+ ASSERT_EQ(close(attr.userns_fd), 0);
+ ASSERT_EQ(close(open_tree_fd), 0);
+}
+
+/**
+ * Validate that idmapping a mount is rejected if the mount's mount namespace
+ * and our mount namespace don't match.
+ * (The kernel enforces that the mount's mount namespace and the caller's mount
+ * namespace match.)
+ */
+TEST_F(mount_setattr_idmapped, attached_mount_outside_current_mount_namespace)
+{
+ int open_tree_fd = -EBADF;
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_IDMAP,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ open_tree_fd = sys_open_tree(-EBADF, "/mnt/D",
+ AT_EMPTY_PATH |
+ AT_NO_AUTOMOUNT |
+ AT_SYMLINK_NOFOLLOW |
+ OPEN_TREE_CLOEXEC);
+ ASSERT_GE(open_tree_fd, 0);
+
+ ASSERT_EQ(unshare(CLONE_NEWNS), 0);
+
+ attr.userns_fd = get_userns_fd(0, 10000, 10000);
+ ASSERT_GE(attr.userns_fd, 0);
+ ASSERT_NE(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr,
+ sizeof(attr)), 0);
+ ASSERT_EQ(close(attr.userns_fd), 0);
+ ASSERT_EQ(close(open_tree_fd), 0);
+}
+
+/**
+ * Validate that an attached mount in our mount namespace can be idmapped.
+ */
+TEST_F(mount_setattr_idmapped, detached_mount_inside_current_mount_namespace)
+{
+ int open_tree_fd = -EBADF;
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_IDMAP,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ open_tree_fd = sys_open_tree(-EBADF, "/mnt/D",
+ AT_EMPTY_PATH |
+ AT_NO_AUTOMOUNT |
+ AT_SYMLINK_NOFOLLOW |
+ OPEN_TREE_CLOEXEC |
+ OPEN_TREE_CLONE);
+ ASSERT_GE(open_tree_fd, 0);
+
+ /* Changing mount properties on a detached mount. */
+ attr.userns_fd = get_userns_fd(0, 10000, 10000);
+ ASSERT_GE(attr.userns_fd, 0);
+ ASSERT_EQ(sys_mount_setattr(open_tree_fd, "",
+ AT_EMPTY_PATH, &attr, sizeof(attr)), 0);
+ ASSERT_EQ(close(attr.userns_fd), 0);
+ ASSERT_EQ(close(open_tree_fd), 0);
+}
+
+/**
+ * Validate that a detached mount not in our mount namespace can be idmapped.
+ */
+TEST_F(mount_setattr_idmapped, detached_mount_outside_current_mount_namespace)
+{
+ int open_tree_fd = -EBADF;
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_IDMAP,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ open_tree_fd = sys_open_tree(-EBADF, "/mnt/D",
+ AT_EMPTY_PATH |
+ AT_NO_AUTOMOUNT |
+ AT_SYMLINK_NOFOLLOW |
+ OPEN_TREE_CLOEXEC |
+ OPEN_TREE_CLONE);
+ ASSERT_GE(open_tree_fd, 0);
+
+ ASSERT_EQ(unshare(CLONE_NEWNS), 0);
+
+ /* Changing mount properties on a detached mount. */
+ attr.userns_fd = get_userns_fd(0, 10000, 10000);
+ ASSERT_GE(attr.userns_fd, 0);
+ ASSERT_EQ(sys_mount_setattr(open_tree_fd, "",
+ AT_EMPTY_PATH, &attr, sizeof(attr)), 0);
+ ASSERT_EQ(close(attr.userns_fd), 0);
+ ASSERT_EQ(close(open_tree_fd), 0);
+}
+
+/**
+ * Validate that currently changing the idmapping of an idmapped mount fails.
+ */
+TEST_F(mount_setattr_idmapped, change_idmapping)
+{
+ int open_tree_fd = -EBADF;
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_IDMAP,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ open_tree_fd = sys_open_tree(-EBADF, "/mnt/D",
+ AT_EMPTY_PATH |
+ AT_NO_AUTOMOUNT |
+ AT_SYMLINK_NOFOLLOW |
+ OPEN_TREE_CLOEXEC |
+ OPEN_TREE_CLONE);
+ ASSERT_GE(open_tree_fd, 0);
+
+ attr.userns_fd = get_userns_fd(0, 10000, 10000);
+ ASSERT_GE(attr.userns_fd, 0);
+ ASSERT_EQ(sys_mount_setattr(open_tree_fd, "",
+ AT_EMPTY_PATH, &attr, sizeof(attr)), 0);
+ ASSERT_EQ(close(attr.userns_fd), 0);
+
+ /* Change idmapping on a detached mount that is already idmapped. */
+ attr.userns_fd = get_userns_fd(0, 20000, 10000);
+ ASSERT_GE(attr.userns_fd, 0);
+ ASSERT_NE(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0);
+ ASSERT_EQ(close(attr.userns_fd), 0);
+ ASSERT_EQ(close(open_tree_fd), 0);
+}
+
+static bool expected_uid_gid(int dfd, const char *path, int flags,
+ uid_t expected_uid, gid_t expected_gid)
+{
+ int ret;
+ struct stat st;
+
+ ret = fstatat(dfd, path, &st, flags);
+ if (ret < 0)
+ return false;
+
+ return st.st_uid == expected_uid && st.st_gid == expected_gid;
+}
+
+TEST_F(mount_setattr_idmapped, idmap_mount_tree_invalid)
+{
+ int open_tree_fd = -EBADF;
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_IDMAP,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ ASSERT_EQ(expected_uid_gid(-EBADF, "/tmp/B/b", 0, 0, 0), 0);
+ ASSERT_EQ(expected_uid_gid(-EBADF, "/tmp/B/BB/b", 0, 0, 0), 0);
+
+ open_tree_fd = sys_open_tree(-EBADF, "/mnt/A",
+ AT_RECURSIVE |
+ AT_EMPTY_PATH |
+ AT_NO_AUTOMOUNT |
+ AT_SYMLINK_NOFOLLOW |
+ OPEN_TREE_CLOEXEC |
+ OPEN_TREE_CLONE);
+ ASSERT_GE(open_tree_fd, 0);
+
+ attr.userns_fd = get_userns_fd(0, 10000, 10000);
+ ASSERT_GE(attr.userns_fd, 0);
+ ASSERT_NE(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0);
+ ASSERT_EQ(close(attr.userns_fd), 0);
+ ASSERT_EQ(close(open_tree_fd), 0);
+
+ ASSERT_EQ(expected_uid_gid(-EBADF, "/tmp/B/b", 0, 0, 0), 0);
+ ASSERT_EQ(expected_uid_gid(-EBADF, "/tmp/B/BB/b", 0, 0, 0), 0);
+ ASSERT_EQ(expected_uid_gid(open_tree_fd, "B/b", 0, 0, 0), 0);
+ ASSERT_EQ(expected_uid_gid(open_tree_fd, "B/BB/b", 0, 0, 0), 0);
+}
+
+TEST_HARNESS_MAIN