Re: [for-next][PATCH 4/5] tracing: Check all tasks on each CPU when filtering pids

[Jiaxing Wang <hello.wjx@gmail.com>]

On Thu, Oct 29, 2015 at 03:07:58AM -0400, Steven Rostedt wrote:
>  static ssize_t
>  ftrace_event_pid_write(struct file *filp, const char __user *ubuf,
>  		       size_t cnt, loff_t *ppos)
> @@ -1711,6 +1727,12 @@ ftrace_event_pid_write(struct file *filp, const char __user *ubuf,
>  						 tr, INT_MAX);
>  		register_trace_prio_sched_wakeup(event_filter_pid_sched_wakeup_probe_post,
>  						 tr, 0);
> +
> +		/*
> +		 * Ignoring of pids is done at task switch. But we have to
> +		 * check for those tasks that are currently running.
> +		 */
> +		on_each_cpu(ignore_task_cpu, tr, 1);
>  	}
on_each_cpu(ignore_task_cpu, tr, 1); can be put outside of the else
block, then ignore_pid can be updated when appending pid, 
eg. echo 'xxx' >> set_event_pid, in case xxx is running on some cpu.
>  
>  	mutex_unlock(&event_mutex);