Re: [PATCH -tip 23/32] sched: Add a per-thread core scheduling interface

[Joel Fernandes]

On Wed, Dec 02, 2020 at 04:47:17PM -0500, Chris Hyser wrote:
> On Tue, Nov 17, 2020 at 06:19:53PM -0500, Joel Fernandes (Google) wrote:
> > Add a per-thread core scheduling interface which allows a thread to share a
> > core with another thread, or have a core exclusively for itself.
> > 
> > ChromeOS uses core-scheduling to securely enable hyperthreading.  This cuts
> > down the keypress latency in Google docs from 150ms to 50ms while improving
> > the camera streaming frame rate by ~3%.
> > 
> 
> Inline is a patch for comment to extend this interface to make it more useful.
> This patch would still need to provide doc and selftests updates as well.
> 
> -chrish
> 
> ---8<-----------------------
[..]  
> diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
> index 217b048..f8e4e96 100644
> --- a/include/uapi/linux/prctl.h
> +++ b/include/uapi/linux/prctl.h
> @@ -250,5 +250,8 @@ struct prctl_mm_map {
>  
>  /* Request the scheduler to share a core */
>  #define PR_SCHED_CORE_SHARE		59
> +# define PR_SCHED_CORE_CLEAR		0  /* clear core_sched cookie of pid */
> +# define PR_SCHED_CORE_SHARE_FROM	1  /* get core_sched cookie from pid */
> +# define PR_SCHED_CORE_SHARE_TO		2  /* push core_sched cookie to pid */
>  
>  #endif /* _LINUX_PRCTL_H */
> diff --git a/kernel/sched/coretag.c b/kernel/sched/coretag.c
> index 800c0f8..14feac1 100644
> --- a/kernel/sched/coretag.c
> +++ b/kernel/sched/coretag.c
> @@ -9,6 +9,7 @@
>   */
>  
>  #include "sched.h"
> +#include "linux/prctl.h"
>  
>  /*
>   * Wrapper representing a complete cookie. The address of the cookie is used as
> @@ -456,40 +457,45 @@ int sched_core_share_tasks(struct task_struct *t1, struct task_struct *t2)
>  }
>  
>  /* Called from prctl interface: PR_SCHED_CORE_SHARE */
> -int sched_core_share_pid(pid_t pid)
> +int sched_core_share_pid(unsigned long flags, pid_t pid)
>  {
> +	struct task_struct *dest;
> +	struct task_struct *src;
>  	struct task_struct *task;
>  	int err;
>  
> -	if (pid == 0) { /* Recent current task's cookie. */
> -		/* Resetting a cookie requires privileges. */
> -		if (current->core_task_cookie)
> -			if (!capable(CAP_SYS_ADMIN))
> -				return -EPERM;
> -		task = NULL;
> -	} else {
> -		rcu_read_lock();
> -		task = pid ? find_task_by_vpid(pid) : current;
> -		if (!task) {
> -			rcu_read_unlock();
> -			return -ESRCH;
> -		}
> -
> -		get_task_struct(task);
> -
> -		/*
> -		 * Check if this process has the right to modify the specified
> -		 * process. Use the regular "ptrace_may_access()" checks.
> -		 */
> -		if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) {
> -			rcu_read_unlock();
> -			err = -EPERM;
> -			goto out;
> -		}
> +	rcu_read_lock();
> +	task = find_task_by_vpid(pid);
> +	if (!task) {
>  		rcu_read_unlock();
> +		return -ESRCH;
>  	}
>  
> -	err = sched_core_share_tasks(current, task);
> +	get_task_struct(task);
> +
> +	/*
> +	 * Check if this process has the right to modify the specified
> +	 * process. Use the regular "ptrace_may_access()" checks.
> +	 */
> +	if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) {
> +		rcu_read_unlock();
> +		err = -EPERM;
> +		goto out;
> +	}
> +	rcu_read_unlock();
> +
> +	if (flags == PR_SCHED_CORE_CLEAR) {
> +		dest = task;
> +		src = NULL;
> +	} else if (flags == PR_SCHED_CORE_SHARE_TO) {
> +		dest = task;
> +		src = current;
> +	} else if (flags == PR_SCHED_CORE_SHARE_FROM) {
> +		dest = current;
> +		src = task;
> +	}

Looks ok to me except the missing else { } clause you found. Also, maybe
dest/src can be renamed to from/to to make meaning of variables more clear?

Also looking forward to the docs/test updates.

thanks!

 - Joel


> +
> +	err = sched_core_share_tasks(dest, src);
>  out:
>  	if (task)
>  		put_task_struct(task);
> diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
> index cffdfab..50c31f3 100644
> --- a/kernel/sched/debug.c
> +++ b/kernel/sched/debug.c
> @@ -1030,6 +1030,7 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
>  
>  #ifdef CONFIG_SCHED_CORE
>  	__PS("core_cookie", p->core_cookie);
> +	__PS("core_task_cookie", p->core_task_cookie);
>  #endif
>  
>  	sched_show_numa(p, m);
> diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
> index b3b89bd..eafb399 100644
> --- a/kernel/sched/sched.h
> +++ b/kernel/sched/sched.h
> @@ -1202,7 +1202,7 @@ void sched_core_dequeue(struct rq *rq, struct task_struct *p);
>  void sched_core_get(void);
>  void sched_core_put(void);
>  
> -int sched_core_share_pid(pid_t pid);
> +int sched_core_share_pid(unsigned long flags, pid_t pid);
>  int sched_core_share_tasks(struct task_struct *t1, struct task_struct *t2);
>  
>  #ifdef CONFIG_CGROUP_SCHED
> diff --git a/kernel/sys.c b/kernel/sys.c
> index 61a3c98..da52a0d 100644
> --- a/kernel/sys.c
> +++ b/kernel/sys.c
> @@ -2530,9 +2530,13 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
>  
>  		error = (current->flags & PR_IO_FLUSHER) == PR_IO_FLUSHER;
>  		break;
> +#ifdef CONFIG_SCHED_CORE
>  	case PR_SCHED_CORE_SHARE:
> -		error = sched_core_share_pid(arg2);
> +		if (arg4 || arg5)
> +			return -EINVAL;
> +		error = sched_core_share_pid(arg2, arg3);
>  		break;
> +#endif
>  	default:
>  		error = -EINVAL;
>  		break;