Re: [PATCH 2/5 v2] tracing: Replace the per_cpu() with this_cpu() in trace_stack.c

[Paul E. McKenney]

On Fri, Apr 07, 2017 at 10:01:08AM -0400, Steven Rostedt wrote:
> From: "Steven Rostedt (VMware)" <rostedt@xxxxxxxxxxx>
> 
> The updates to the trace_active per cpu variable can be updated with the
> this_cpu_*() functions as it only gets updated on the CPU that the variable
> is on.
> 
> Signed-off-by: Steven Rostedt (VMware) <rostedt@xxxxxxxxxxx>
> ---
>  kernel/trace/trace_stack.c | 23 +++++++----------------
>  1 file changed, 7 insertions(+), 16 deletions(-)
> 
> diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
> index 5fb1f2c87e6b..05ad2b86461e 100644
> --- a/kernel/trace/trace_stack.c
> +++ b/kernel/trace/trace_stack.c
> @@ -207,13 +207,12 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip,
>  		 struct ftrace_ops *op, struct pt_regs *pt_regs)
>  {
>  	unsigned long stack;
> -	int cpu;
> 
>  	preempt_disable_notrace();
> 
> -	cpu = raw_smp_processor_id();
>  	/* no atomic needed, we only modify this variable by this cpu */
> -	if (per_cpu(trace_active, cpu)++ != 0)
> +	this_cpu_inc(trace_active);

For whatever it is worth...

I was about to complain that this_cpu_inc() only disables preemption,
not interrupts, but then I realized that any correct interrupt handler
would have to restore the per-CPU variable to its original value.

Presumably you have to sum up all the per-CPU trace_active counts,
given that there is no guarantee that a process-level dec will happen
on the same CPU that did the inc.

							Thanx, Paul

> +	if (this_cpu_read(trace_active) != 1)
>  		goto out;
> 
>  	ip += MCOUNT_INSN_SIZE;
> @@ -221,7 +220,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip,
>  	check_stack(ip, &stack);
> 
>   out:
> -	per_cpu(trace_active, cpu)--;
> +	this_cpu_dec(trace_active);
>  	/* prevent recursion in schedule */
>  	preempt_enable_notrace();
>  }
> @@ -253,7 +252,6 @@ stack_max_size_write(struct file *filp, const char __user *ubuf,
>  	long *ptr = filp->private_data;
>  	unsigned long val, flags;
>  	int ret;
> -	int cpu;
> 
>  	ret = kstrtoul_from_user(ubuf, count, 10, &val);
>  	if (ret)
> @@ -266,14 +264,13 @@ stack_max_size_write(struct file *filp, const char __user *ubuf,
>  	 * we will cause circular lock, so we also need to increase
>  	 * the percpu trace_active here.
>  	 */
> -	cpu = smp_processor_id();
> -	per_cpu(trace_active, cpu)++;
> +	this_cpu_inc(trace_active);
> 
>  	arch_spin_lock(&stack_trace_max_lock);
>  	*ptr = val;
>  	arch_spin_unlock(&stack_trace_max_lock);
> 
> -	per_cpu(trace_active, cpu)--;
> +	this_cpu_dec(trace_active);
>  	local_irq_restore(flags);
> 
>  	return count;
> @@ -307,12 +304,9 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
> 
>  static void *t_start(struct seq_file *m, loff_t *pos)
>  {
> -	int cpu;
> -
>  	local_irq_disable();
> 
> -	cpu = smp_processor_id();
> -	per_cpu(trace_active, cpu)++;
> +	this_cpu_inc(trace_active);
> 
>  	arch_spin_lock(&stack_trace_max_lock);
> 
> @@ -324,12 +318,9 @@ static void *t_start(struct seq_file *m, loff_t *pos)
> 
>  static void t_stop(struct seq_file *m, void *p)
>  {
> -	int cpu;
> -
>  	arch_spin_unlock(&stack_trace_max_lock);
> 
> -	cpu = smp_processor_id();
> -	per_cpu(trace_active, cpu)--;
> +	this_cpu_dec(trace_active);
> 
>  	local_irq_enable();
>  }
> -- 
> 2.10.2
> 
>