SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode)
{
const struct cred *old_cred;
struct cred *override_cred;
struct path path;
struct inode *inode;
int res;
if (mode & ~S_IRWXO)
return -EINVAL;
override_cred = prepare_creds();
if (!override_cred)
return -ENOMEM;
override_cred->fsuid = override_cred->uid;
override_cred->fsgid = override_cred->gid;
if (!issecure(SECURE_NO_SETUID_FIXUP)) {
if (override_cred->uid)
cap_clear(override_cred->cap_effective);
else
override_cred->cap_effective =
override_cred->cap_permitted;
}
old_cred = override_creds(override_cred);
res = user_path_at(dfd, filename, LOOKUP_FOLLOW, &path);
if (res)
goto out;
inode = path.dentry->d_inode;
if ((mode & MAY_EXEC) && S_ISREG(inode->i_mode)) {
res = -EACCES;
if (path.mnt->mnt_flags & MNT_NOEXEC)
goto out_path_release;
}
res = inode_permission(inode, mode | MAY_ACCESS);
if (res || !(mode & S_IWOTH) || special_file(inode->i_mode))
goto out_path_release;
if (__mnt_is_readonly(path.mnt))
res = -EROFS;
out_path_release:
path_put(&path);
out:
revert_creds(old_cred);
put_cred(override_cred);
return res;
}
/*
* access() needs to use the real uid/gid, not the effective uid/gid.
* We do this by temporarily clearing all FS-related capabilities and
* switching the fsuid/fsgid around to the real ones.
*/
SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode)
{
const struct cred *old_cred;
struct cred *override_cred;
struct path path;
struct inode *inode;
int res;
if (mode & ~S_IRWXO) /* where's F_OK, X_OK, W_OK, R_OK? */
return -EINVAL;
override_cred = prepare_creds();
if (!override_cred)
return -ENOMEM;
override_cred->fsuid = override_cred->uid;
override_cred->fsgid = override_cred->gid;
if (!issecure(SECURE_NO_SETUID_FIXUP)) {
/* Clear the capabilities if we switch to a non-root user */
if (override_cred->uid)
cap_clear(override_cred->cap_effective);
else
override_cred->cap_effective =
override_cred->cap_permitted;
}
old_cred = override_creds(override_cred);
res = user_path_at(dfd, filename, LOOKUP_FOLLOW, &path);
if (res)
goto out;
inode = path.dentry->d_inode;
if ((mode & MAY_EXEC) && S_ISREG(inode->i_mode)) {
/*
* MAY_EXEC on regular files is denied if the fs is mounted
* with the "noexec" flag.
*/
res = -EACCES;
if (path.mnt->mnt_flags & MNT_NOEXEC)
goto out_path_release;
}
res = inode_permission(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;
/*
* This is a rare case where using __mnt_is_readonly()
* is OK without a mnt_want/drop_write() pair. Since
* no actual write to the fs is performed here, we do
* not need to telegraph to that to anyone.
*
* By doing this, we accept that this access is
* inherently racy and know that the fs may change
* state before we even see this result.
*/
if (__mnt_is_readonly(path.mnt))
res = -EROFS;
out_path_release:
path_put(&path);
out:
revert_creds(old_cred);
put_cred(override_cred);
return res;
}
static int show_vfsmnt(struct seq_file *m, struct vfsmount *mnt)
{
struct mount *r = real_mount(mnt);
int err = 0;
struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
struct super_block *sb = mnt_path.dentry->d_sb;
if (sb->s_op->show_devname) {
err = sb->s_op->show_devname(m, mnt_path.dentry);
if (err)
goto out;
} else {
mangle(m, r->mnt_devname ? r->mnt_devname : "none");
}
seq_putc(m, ' ');
seq_path(m, &mnt_path, " \t\n\\");
seq_putc(m, ' ');
show_type(m, sb);
seq_puts(m, __mnt_is_readonly(mnt) ? " ro" : " rw");
err = show_sb_opts(m, sb);
if (err)
goto out;
show_mnt_opts(m, mnt);
if (sb->s_op->show_options)
err = sb->s_op->show_options(m, mnt_path.dentry);
seq_puts(m, " 0 0\n");
out:
return err;
}
static int show_mountinfo(struct seq_file *m, struct vfsmount *mnt)
{
struct proc_mounts *p = proc_mounts(m);
struct mount *r = real_mount(mnt);
struct super_block *sb = mnt->mnt_sb;
struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
struct path root = p->root;
int err = 0;
seq_printf(m, "%i %i %u:%u ", r->mnt_id, r->mnt_parent->mnt_id,
MAJOR(sb->s_dev), MINOR(sb->s_dev));
if (sb->s_op->show_path)
err = sb->s_op->show_path(m, mnt->mnt_root);
else
seq_dentry(m, mnt->mnt_root, " \t\n\\");
if (err)
goto out;
seq_putc(m, ' ');
/* mountpoints outside of chroot jail will give SEQ_SKIP on this */
err = seq_path_root(m, &mnt_path, &root, " \t\n\\");
if (err)
goto out;
seq_puts(m, mnt->mnt_flags & MNT_READONLY ? " ro" : " rw");
show_mnt_opts(m, mnt);
/* Tagged fields ("foo:X" or "bar") */
if (IS_MNT_SHARED(r))
seq_printf(m, " shared:%i", r->mnt_group_id);
if (IS_MNT_SLAVE(r)) {
int master = r->mnt_master->mnt_group_id;
int dom = get_dominating_id(r, &p->root);
seq_printf(m, " master:%i", master);
if (dom && dom != master)
seq_printf(m, " propagate_from:%i", dom);
}
if (IS_MNT_UNBINDABLE(r))
seq_puts(m, " unbindable");
/* Filesystem specific data */
seq_puts(m, " - ");
show_type(m, sb);
seq_putc(m, ' ');
if (sb->s_op->show_devname)
err = sb->s_op->show_devname(m, mnt->mnt_root);
else
mangle(m, r->mnt_devname ? r->mnt_devname : "none");
if (err)
goto out;
seq_puts(m, sb->s_flags & MS_RDONLY ? " ro" : " rw");
err = show_sb_opts(m, sb);
if (err)
goto out;
if (sb->s_op->show_options)
err = sb->s_op->show_options(m, mnt->mnt_root);
seq_putc(m, '\n');
out:
return err;
}
static int show_vfsstat(struct seq_file *m, struct vfsmount *mnt)
{
struct mount *r = real_mount(mnt);
struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
struct super_block *sb = mnt_path.dentry->d_sb;
int err = 0;
/* device */
if (sb->s_op->show_devname) {
seq_puts(m, "device ");
err = sb->s_op->show_devname(m, mnt_path.dentry);
} else {
if (r->mnt_devname) {
seq_puts(m, "device ");
mangle(m, r->mnt_devname);
} else
seq_puts(m, "no device");
}
/* mount point */
seq_puts(m, " mounted on ");
seq_path(m, &mnt_path, " \t\n\\");
seq_putc(m, ' ');
/* file system type */
seq_puts(m, "with fstype ");
show_type(m, sb);
/* optional statistics */
if (sb->s_op->show_stats) {
seq_putc(m, ' ');
if (!err)
err = sb->s_op->show_stats(m, mnt_path.dentry);
}
seq_putc(m, '\n');
return err;
}
static int mounts_open_common(struct inode *inode, struct file *file,
int (*show)(struct seq_file *, struct vfsmount *))
{
struct task_struct *task = get_proc_task(inode);
struct nsproxy *nsp;
struct mnt_namespace *ns = NULL;
struct path root;
struct proc_mounts *p;
int ret = -EINVAL;
if (!task)
goto err;
task_lock(task);
nsp = task->nsproxy;
if (!nsp || !nsp->mnt_ns) {
task_unlock(task);
put_task_struct(task);
goto err;
}
ns = nsp->mnt_ns;
get_mnt_ns(ns);
if (!task->fs) {
task_unlock(task);
put_task_struct(task);
ret = -ENOENT;
goto err_put_ns;
}
get_fs_root(task->fs, &root);
task_unlock(task);
put_task_struct(task);
ret = -ENOMEM;
p = kmalloc(sizeof(struct proc_mounts), GFP_KERNEL);
if (!p)
goto err_put_path;
file->private_data = &p->m;
ret = seq_open(file, &mounts_op);
if (ret)
goto err_free;
p->ns = ns;
p->root = root;
p->m.poll_event = ns->event;
p->show = show;
return 0;
err_free:
kfree(p);
err_put_path:
path_put(&root);
err_put_ns:
put_mnt_ns(ns);
err:
return ret;
}
static int mounts_release(struct inode *inode, struct file *file)
{
struct proc_mounts *p = proc_mounts(file->private_data);
path_put(&p->root);
put_mnt_ns(p->ns);
return seq_release(inode, file);
}
static int mounts_open(struct inode *inode, struct file *file)
{
return mounts_open_common(inode, file, show_vfsmnt);
}
static int mountinfo_open(struct inode *inode, struct file *file)
{
return mounts_open_common(inode, file, show_mountinfo);
}
static int mountstats_open(struct inode *inode, struct file *file)
{
return mounts_open_common(inode, file, show_vfsstat);
}
const struct file_operations proc_mounts_operations = {
.open = mounts_open,
.read = seq_read,
.llseek = seq_lseek,
.release = mounts_release,
.poll = mounts_poll,
};
const struct file_operations proc_mountinfo_operations = {
.open = mountinfo_open,
.read = seq_read,
.llseek = seq_lseek,
.release = mounts_release,
.poll = mounts_poll,
};
const struct file_operations proc_mountstats_operations = {
.open = mountstats_open,
.read = seq_read,
.llseek = seq_lseek,
.release = mounts_release,
};
/*
* access() needs to use the real uid/gid, not the effective uid/gid.
* We do this by temporarily clearing all FS-related capabilities and
* switching the fsuid/fsgid around to the real ones.
*/
asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode)
{
struct path path;
struct inode *inode;
int old_fsuid, old_fsgid;
kernel_cap_t uninitialized_var(old_cap); /* !SECURE_NO_SETUID_FIXUP */
int res;
if (mode & ~S_IRWXO) /* where's F_OK, X_OK, W_OK, R_OK? */
return -EINVAL;
old_fsuid = current->fsuid;
old_fsgid = current->fsgid;
current->fsuid = current->uid;
current->fsgid = current->gid;
if (!issecure(SECURE_NO_SETUID_FIXUP)) {
/*
* Clear the capabilities if we switch to a non-root user
*/
#ifndef CONFIG_SECURITY_FILE_CAPABILITIES
/*
* FIXME: There is a race here against sys_capset. The
* capabilities can change yet we will restore the old
* value below. We should hold task_capabilities_lock,
* but we cannot because user_path_at can sleep.
*/
#endif /* ndef CONFIG_SECURITY_FILE_CAPABILITIES */
if (current->uid)
old_cap = cap_set_effective(__cap_empty_set);
else
old_cap = cap_set_effective(current->cap_permitted);
}
res = user_path_at(dfd, filename, LOOKUP_FOLLOW, &path);
if (res)
goto out;
inode = path.dentry->d_inode;
if ((mode & MAY_EXEC) && S_ISREG(inode->i_mode)) {
/*
* MAY_EXEC on regular files is denied if the fs is mounted
* with the "noexec" flag.
*/
res = -EACCES;
if (path.mnt->mnt_flags & MNT_NOEXEC)
goto out_path_release;
}
res = inode_permission(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;
/*
* This is a rare case where using __mnt_is_readonly()
* is OK without a mnt_want/drop_write() pair. Since
* no actual write to the fs is performed here, we do
* not need to telegraph to that to anyone.
*
* By doing this, we accept that this access is
* inherently racy and know that the fs may change
* state before we even see this result.
*/
if (__mnt_is_readonly(path.mnt))
res = -EROFS;
out_path_release:
path_put(&path);
out:
current->fsuid = old_fsuid;
current->fsgid = old_fsgid;
if (!issecure(SECURE_NO_SETUID_FIXUP))
cap_set_effective(old_cap);
return res;
}