Re: [RFC PATCH 3/8] kmod - teach call_usermodehelper() to use a namespace

[Jeff Layton <jeff.layton@primarydata.com>]

On Thu, 05 Feb 2015 10:34:11 +0800
Ian Kent <ikent@redhat.com> wrote:

> The call_usermodehelper() function executes all binaries in the
> global "init" root context. This doesn't allow a binary to be run
> within a namespace (eg. the namespace of a container).
> 
> Both containerized NFS client and NFS server need the ability to
> execute a binary in a container's context. To do this use the init
> process of the callers environment is used to setup the namespaces
> in the same way the root init process is used otherwise.
> 
> Signed-off-by: Ian Kent <ikent@redhat.com>
> Cc: Benjamin Coddington <bcodding@redhat.com>
> Cc: Al Viro <viro@ZenIV.linux.org.uk>
> Cc: J. Bruce Fields <bfields@fieldses.org>
> Cc: David Howells <dhowells@redhat.com>
> Cc: Trond Myklebust <trond.myklebust@primarydata.com>
> Cc: Oleg Nesterov <onestero@redhat.com>
> Cc: Eric W. Biederman <ebiederm@xmission.com>
> Cc: Jeff Layton <jeff.layton@primarydata.com>
> ---
>  include/linux/kmod.h |   16 +++++++
>  kernel/kmod.c        |  115 +++++++++++++++++++++++++++++++++++++++++++++++++-
>  2 files changed, 128 insertions(+), 3 deletions(-)
> 
> diff --git a/include/linux/kmod.h b/include/linux/kmod.h
> index 15bdeed..b0f1b3c 100644
> --- a/include/linux/kmod.h
> +++ b/include/linux/kmod.h
> @@ -52,6 +52,7 @@ struct file;
>  #define UMH_WAIT_EXEC	1	/* wait for the exec, but not the process */
>  #define UMH_WAIT_PROC	2	/* wait for the process to complete */
>  #define UMH_KILLABLE	4	/* wait for EXEC/PROC killable */
> +#define UMH_USE_NS	8	/* exec using caller's init namespace */
>  
>  struct subprocess_info {
>  	struct work_struct work;
> @@ -69,6 +70,21 @@ struct subprocess_info {
>  extern int
>  call_usermodehelper(char *path, char **argv, char **envp, int flags);
>  
> +#if !defined(CONFIG_PROC_FS) || !defined(CONFIG_NAMESPACES)
> +inline struct task_struct *umh_get_init_task(void)
> +{
> +	return ERR_PTR(-ENOTSUP);
> +}
> +
> +inline int umh_enter_ns(struct task_struct *tsk, struct cred *new)
> +{
> +	return -ENOTSUP;
> +}
> +#else
> +struct task_struct *umh_get_init_pid(void);
> +int umh_enter_ns(struct task_struct *tsk, struct cred *new);
> +#endif
> +
>  extern struct subprocess_info *
>  call_usermodehelper_setup(char *path, char **argv, char **envp, gfp_t gfp_mask,
>  			  int (*init)(struct subprocess_info *info, struct cred *new),
> diff --git a/kernel/kmod.c b/kernel/kmod.c
> index 14c0188..4c649d6 100644
> --- a/kernel/kmod.c
> +++ b/kernel/kmod.c
> @@ -582,6 +582,98 @@ unlock:
>  }
>  EXPORT_SYMBOL(call_usermodehelper_exec);
>  
> +#if defined(CONFIG_PROC_FS) && defined(CONFIG_NAMESPACES)
> +#define NS_PATH_MAX	35
> +#define NS_PATH_FMT	"%lu/ns/%s"
> +
> +/* Note namespace name order is significant */
> +static const char *ns_names[] = { "user", "ipc", "uts", "net", "pid", "mnt", NULL };
> +
> +struct task_struct *umh_get_init_pid(void)

nit: we're not getting a pid here but a task_struct pointer. Maybe this
should be called umh_get_init_task?

> +{
> +	struct task_struct *tsk;
> +
> +	rcu_read_lock();
> +	tsk = find_task_by_vpid(1);
> +	if (tsk)
> +		get_task_struct(tsk);
> +	rcu_read_unlock();

I'm not terribly familiar with the task_struct lifetime rules...

I assume that you can be assured that tsk won't go away while you hold
the rcu_read_lock, but is doing a get_task_struct while holding it
sufficient to pin it after you drop the lock?

IOW, could the refcount on the task_struct do a 0->1 transition here and
end up being freed anyway after you've grabbed a reference?

> +	if (!tsk)
> +		return ERR_PTR(-ESRCH);
> +
> +	return tsk;
> +}
> +EXPORT_SYMBOL(umh_get_init_pid);
> +
> +int umh_enter_ns(struct task_struct *tsk, struct cred *new)
> +{
> +	char path[NS_PATH_MAX];
> +	struct vfsmount *mnt;
> +	const char *name;
> +	pid_t pid;
> +	int err = 0;
> +
> +	pid = task_pid_nr(tsk);
> +
> +	/*
> +	 * The user mode thread runner runs in the root init namespace
> +	 * so it will see all system pids.
> +	 */
> +	mnt = task_active_pid_ns(current)->proc_mnt;
> +
> +	for (name = ns_names[0]; *name; name++) {
> +		struct file *this;
> +		int len;
> +
> +		len = snprintf(path,
> +			       NS_PATH_MAX, NS_PATH_FMT,
> +			       (unsigned long) pid, name);
> +		if (len >= NS_PATH_MAX) {
> +			err = -ENAMETOOLONG;
> +			break;
> +		}
> +
> +		this = file_open_root(mnt->mnt_root, mnt, path, O_RDONLY);
> +		if (unlikely(IS_ERR(this))) {
> +			err = PTR_ERR(this);
> +			break;
> +		}
> +
> +		err = setns_inode(file_inode(this), 0);
> +		fput(this);
> +		if (err)
> +			break;
> +	}
> +
> +	return err;
> +}
> +EXPORT_SYMBOL(umh_enter_ns);
> +
> +static int umh_set_ns(struct subprocess_info *info, struct cred *new)
> +{
> +	struct task_struct *tsk = info->data;
> +
> +	return umh_enter_ns(tsk, new);
> +}
> +
> +static void umh_free_ns(struct subprocess_info *info)
> +{
> +	struct task_struct *tsk = info->data;
> +
> +	if (tsk)
> +		put_task_struct(tsk);
> +}
> +#else
> +static int umh_set_ns(struct subprocess_info *info, struct cred *new)
> +{
> +	return 0;
> +}
> +
> +static void umh_free_ns(struct subprocess_info *info)
> +{
> +}
> +#endif
> +
>  /**
>   * call_usermodehelper() - prepare and start a usermode application
>   * @path: path to usermode executable
> @@ -599,11 +691,28 @@ int call_usermodehelper(char *path, char **argv, char **envp, int flags)
>  {
>  	struct subprocess_info *info;
>  	gfp_t gfp_mask = (flags == UMH_NO_WAIT) ? GFP_ATOMIC : GFP_KERNEL;
> +	unsigned int use_ns = flags & UMH_USE_NS;
> +	struct task_struct *tsk = NULL;
> +
> +	if (use_ns) {
> +		tsk = umh_get_init_pid();
> +		if (IS_ERR(tsk))
> +			return PTR_ERR(tsk);
> +	}
>  
> -	info = call_usermodehelper_setup(path, argv, envp, gfp_mask,
> -					 NULL, NULL, NULL);
> -	if (info == NULL)
> +	if (!tsk)
> +		info = call_usermodehelper_setup(path, argv, envp,
> +						 gfp_mask, NULL, NULL, NULL);
> +	else {
> +		info = call_usermodehelper_setup(path, argv, envp, gfp_mask,
> +						 umh_set_ns, umh_free_ns,
> +						 tsk);
> +	}
> +	if (info == NULL) {
> +		if (tsk)
> +			put_task_struct(tsk);
>  		return -ENOMEM;
> +	}
>  
>  	return call_usermodehelper_exec(info, flags);
>  }
> 


-- 
Jeff Layton <jeff.layton@primarydata.com>