Re: [PATCH v4 30/39] unwind_user/deferred: Make unwind deferral requests NMI-safe

[Peter Zijlstra]

On Tue, Jan 21, 2025 at 06:31:22PM -0800, Josh Poimboeuf wrote:

> diff --git a/kernel/unwind/deferred.c b/kernel/unwind/deferred.c
> index 2f38055cce48..939c94abaa50 100644
> --- a/kernel/unwind/deferred.c
> +++ b/kernel/unwind/deferred.c
> @@ -29,27 +29,49 @@ static u64 ctx_to_cookie(u64 cpu, u64 ctx)
>  
>  /*
>   * Read the task context cookie, first initializing it if this is the first
> - * call to get_cookie() since the most recent entry from user.
> + * call to get_cookie() since the most recent entry from user.  This has to be
> + * done carefully to coordinate with unwind_deferred_request_nmi().
>   */
>  static u64 get_cookie(struct unwind_task_info *info)
>  {
>  	u64 ctx_ctr;
>  	u64 cookie;
> -	u64 cpu;
>  
>  	guard(irqsave)();
>  
> -	cookie = info->cookie;
> +	cookie = READ_ONCE(info->cookie);
>  	if (cookie)
>  		return cookie;
>  
> +	ctx_ctr = __this_cpu_read(unwind_ctx_ctr);
>  
> -	cpu = raw_smp_processor_id();
> -	ctx_ctr = __this_cpu_inc_return(unwind_ctx_ctr);
> -	info->cookie = ctx_to_cookie(cpu, ctx_ctr);
> +	/* Read ctx_ctr before info->nmi_cookie */
> +	barrier();
> +
> +	cookie = READ_ONCE(info->nmi_cookie);
> +	if (cookie) {
> +		/*
> +		 * This is the first call to get_cookie() since an NMI handler
> +		 * first wrote it to info->nmi_cookie.  Sync it.
> +		 */
> +		WRITE_ONCE(info->cookie, cookie);
> +		WRITE_ONCE(info->nmi_cookie, 0);
> +		return cookie;
> +	}
> +
> +	/*
> +	 * Write info->cookie.  It's ok to race with an NMI here.  The value of
> +	 * the cookie is based on ctx_ctr from before the NMI could have
> +	 * incremented it.  The result will be the same even if cookie or
> +	 * ctx_ctr end up getting written twice.
> +	 */
> +	cookie = ctx_to_cookie(raw_smp_processor_id(), ctx_ctr + 1);
> +	WRITE_ONCE(info->cookie, cookie);
> +	WRITE_ONCE(info->nmi_cookie, 0);
> +	barrier();
> +	__this_cpu_write(unwind_ctx_ctr, ctx_ctr + 1);
>  
>  	return cookie;
> -
>  }

Oh gawd. Can we please do something simple like:

	guard(irqsave)();
	cpu = raw_smp_processor_id();
	ctr = __this_cpu_read(unwind_ctx_cnt);
	cookie = READ_ONCE(current->unwind_info.cookie);
	do {
		if (cookie)
			return cookie;
		cookie = ctx_to_cookie(cpu, ctr+1);
	} while (!try_cmpxchg64(&current->unwind_info.cookie, &cookie, cookie));
	__this_cpu_write(unwind_ctx_ctr, ctr+1);
	return cookie;