Re: [PATCH V8 02/12] perf/x86/intel/pt: Add support for pause / resume

[Peter Zijlstra <peterz@infradead.org>]

On Fri, Jun 28, 2024 at 09:51:01AM +0300, Adrian Hunter wrote:

> @@ -534,7 +537,20 @@ static void pt_config(struct perf_event *event)
>  	reg |= (event->attr.config & PT_CONFIG_MASK);
>  
>  	event->hw.config = reg;
> +
> +	/*
> +	 * Allow resume before starting so as not to overwrite a value set by a
> +	 * PMI.
> +	 */
> +	WRITE_ONCE(pt->resume_allowed, 1);
	barrier();
>  	pt_config_start(event);
	barrier();
> +	/*
> +	 * Allow pause after starting so its pt_config_stop() doesn't race with
> +	 * pt_config_start().
> +	 */
> +	WRITE_ONCE(pt->pause_allowed, 1);

IIRC you need those barrier()s, because if the compiler 'helpfully'
inlines the static pt_config_start(), you loose your sequence point and
things can get re-ordered. WRITE_ONCE() only ensures the store is whole
and ordered against other volatile ops, but not against much else.

>  }
>  
>  static void pt_config_stop(struct perf_event *event)
> @@ -1511,6 +1527,7 @@ void intel_pt_interrupt(void)
>  		buf = perf_aux_output_begin(&pt->handle, event);
>  		if (!buf) {
>  			event->hw.state = PERF_HES_STOPPED;
> +			pt->resume_allowed = 0;
>  			return;
>  		}
>  
> @@ -1519,6 +1536,7 @@ void intel_pt_interrupt(void)
>  		ret = pt_buffer_reset_markers(buf, &pt->handle);
>  		if (ret) {
>  			perf_aux_output_end(&pt->handle, 0);
> +			pt->resume_allowed = 0;
>  			return;
>  		}
>  

Above you WRITE_ONCE() on ->resume_allowed, here you do not. Some *SAN
thing or other is bound to get upset about things like that.

> @@ -1573,6 +1591,26 @@ static void pt_event_start(struct perf_event *event, int mode)
>  	struct pt *pt = this_cpu_ptr(&pt_ctx);
>  	struct pt_buffer *buf;
>  
> +	if (mode & PERF_EF_RESUME) {
> +		if (READ_ONCE(pt->resume_allowed)) {

At this point I seem to have lost the plot, how do ->resume_allowed and
->aux_paused interact?

> +			u64 status;
> +
> +			/*
> +			 * Only if the trace is not active and the error and
> +			 * stopped bits are clear, is it safe to start, but a
> +			 * PMI might have just cleared these, so resume_allowed
> +			 * must be checked again also.
> +			 */
> +			rdmsrl(MSR_IA32_RTIT_STATUS, status);
> +			if (!(status & (RTIT_STATUS_TRIGGEREN |
> +					RTIT_STATUS_ERROR |
> +					RTIT_STATUS_STOPPED)) &&
> +			   READ_ONCE(pt->resume_allowed))
> +				pt_config_start(event);
> +		}
> +		return;
> +	}
> +
>  	buf = perf_aux_output_begin(&pt->handle, event);
>  	if (!buf)
>  		goto fail_stop;
> @@ -1601,6 +1639,16 @@ static void pt_event_stop(struct perf_event *event, int mode)
>  {
>  	struct pt *pt = this_cpu_ptr(&pt_ctx);
>  
> +	if (mode & PERF_EF_PAUSE) {
> +		if (READ_ONCE(pt->pause_allowed))
> +			pt_config_stop(event);
> +		return;
> +	}
> +
> +	/* Protect against racing */

No F1 cars allowed? Sure the comment can elucidate the reader as to what
actual race one is concerned about, no?

> +	WRITE_ONCE(pt->pause_allowed, 0);
> +	WRITE_ONCE(pt->resume_allowed, 0);
> +
>  	/*
>  	 * Protect against the PMI racing with disabling wrmsr,
>  	 * see comment in intel_pt_interrupt().
> @@ -1659,8 +1707,12 @@ static long pt_event_snapshot_aux(struct perf_event *event,
>  	/*
>  	 * Here, handle_nmi tells us if the tracing is on
>  	 */
> -	if (READ_ONCE(pt->handle_nmi))
> +	if (READ_ONCE(pt->handle_nmi)) {
> +		/* Protect against racing */
> +		WRITE_ONCE(pt->pause_allowed, 0);
> +		WRITE_ONCE(pt->resume_allowed, 0);

barrier()?

>  		pt_config_stop(event);
> +	}
>  
>  	pt_read_offset(buf);
>  	pt_update_head(pt);
> @@ -1677,8 +1729,11 @@ static long pt_event_snapshot_aux(struct perf_event *event,
>  	 * Compiler barrier not needed as we couldn't have been
>  	 * preempted by anything that touches pt->handle_nmi.
>  	 */
> -	if (pt->handle_nmi)
> +	if (pt->handle_nmi) {
> +		WRITE_ONCE(pt->resume_allowed, 1);
>  		pt_config_start(event);
> +		WRITE_ONCE(pt->pause_allowed, 1);

barrier() went missing again?

> +	}
>  
>  	return ret;
>  }