[PATCH 3/5] um: Do a double clone to disable rseq

[Tiwei Bie]

On 5/28/24 4:54 PM, benjamin at sipsolutions.net wrote:
> From: Benjamin Berg <benjamin.berg at intel.com>
> 
> Newer glibc versions are enabling rseq support by default. This remains
> enabled in the cloned child process, potentially causing the host kernel
> to write/read memory in the child.
> 
> It appears that this was purely not an issue because the used memory
> area happened to be above TASK_SIZE and remains mapped.

I also encountered this issue. In my case, with "Force a static link"
(CONFIG_STATIC_LINK) enabled, UML will crash immediately every time
it starts up. I worked around this by setting the glibc.pthread.rseq
tunable via GLIBC_TUNABLES [1] before launching UML.

So another easy way to work around this issue without introducing runtime
overhead might be to add the GLIBC_TUNABLES=glibc.pthread.rseq=0 environment
variable and exec /proc/self/exe in UML on startup.

[1] https://www.gnu.org/software/libc/manual/html_node/Tunables.html

Regards,
Tiwei

> 
> Note that a better approach would be to exec a small static binary that
> does not link with other libraries. Using a memfd and execveat the
> binary could be embedded into UML itself and it would result in an
> entirely clean execution environment for userspace.
> 
> Signed-off-by: Benjamin Berg <benjamin.berg at intel.com>
> ---
>  arch/um/os-Linux/skas/process.c | 54 ++++++++++++++++++++++++++++++---
>  1 file changed, 50 insertions(+), 4 deletions(-)
> 
> diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c
> index 41a288dcfc34..ee332a2aeea6 100644
> --- a/arch/um/os-Linux/skas/process.c
> +++ b/arch/um/os-Linux/skas/process.c
> @@ -255,6 +255,31 @@ static int userspace_tramp(void *stack)
>  int userspace_pid[NR_CPUS];
>  int kill_userspace_mm[NR_CPUS];
>  
> +struct tramp_data {
> +	int pid;
> +	void *clone_sp;
> +	void *stack;
> +};
> +
> +static int userspace_tramp_clone_vm(void *data)
> +{
> +	struct tramp_data *tramp_data = data;
> +
> +	/*
> +	 * This helper exist to do a double-clone. First with CLONE_VM which
> +	 * effectively disables things like rseq, and then the second one to
> +	 * get a new memory space.
> +	 */
> +
> +	tramp_data->pid = clone(userspace_tramp, tramp_data->clone_sp,
> +				CLONE_PARENT | CLONE_FILES | SIGCHLD,
> +				tramp_data->stack);
> +	if (tramp_data->pid < 0)
> +		tramp_data->pid = -errno;
> +
> +	exit(0);
> +}
> +
>  /**
>   * start_userspace() - prepare a new userspace process
>   * @stub_stack:	pointer to the stub stack.
> @@ -268,9 +293,10 @@ int kill_userspace_mm[NR_CPUS];
>   */
>  int start_userspace(unsigned long stub_stack)
>  {
> +	struct tramp_data tramp_data;
>  	void *stack;
>  	unsigned long sp;
> -	int pid, status, n, flags, err;
> +	int pid, status, n, err;
>  
>  	/* setup a temporary stack page */
>  	stack = mmap(NULL, UM_KERN_PAGE_SIZE,
> @@ -286,10 +312,13 @@ int start_userspace(unsigned long stub_stack)
>  	/* set stack pointer to the end of the stack page, so it can grow downwards */
>  	sp = (unsigned long)stack + UM_KERN_PAGE_SIZE;
>  
> -	flags = CLONE_FILES | SIGCHLD;
> +	tramp_data.stack = (void *) stub_stack;
> +	tramp_data.clone_sp = (void *) sp;
> +	tramp_data.pid = -EINVAL;
>  
>  	/* clone into new userspace process */
> -	pid = clone(userspace_tramp, (void *) sp, flags, (void *) stub_stack);
> +	pid = clone(userspace_tramp_clone_vm, (void *) sp,
> +		    CLONE_VM | CLONE_FILES | SIGCHLD, &tramp_data);
>  	if (pid < 0) {
>  		err = -errno;
>  		printk(UM_KERN_ERR "%s : clone failed, errno = %d\n",
> @@ -305,7 +334,24 @@ int start_userspace(unsigned long stub_stack)
>  			       __func__, errno);
>  			goto out_kill;
>  		}
> -	} while (WIFSTOPPED(status) && (WSTOPSIG(status) == SIGALRM));
> +	} while (!WIFEXITED(status));
> +
> +	pid = tramp_data.pid;
> +	if (pid < 0) {
> +		printk(UM_KERN_ERR "%s : second clone failed, errno = %d\n",
> +		       __func__, -pid);
> +		return pid;
> +	}
> +
> +	do {
> +		CATCH_EINTR(n = waitpid(pid, &status, WUNTRACED | __WALL));
> +		if (n < 0) {
> +			err = -errno;
> +			printk(UM_KERN_ERR "%s : wait failed, errno = %d\n",
> +			       __func__, errno);
> +			goto out_kill;
> +		}
> +	} while (WIFEXITED(status) && (WSTOPSIG(status) == SIGALRM));
>  
>  	if (!WIFSTOPPED(status) || (WSTOPSIG(status) != SIGSTOP)) {
>  		err = -EINVAL;