Re: [RESEND PATCH 09/12] perf: Extend perf_output_read

[Peter Zijlstra]

On Tue, Jun 18, 2024 at 08:10:41AM -0700, kan.liang@xxxxxxxxxxxxxxx wrote:
> From: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>
> 
> The event may have been updated in the PMU-specific implementation,
> e.g., Intel PEBS counters snapshotting. The common code should not
> read and overwrite the value.
> 
> The PERF_SAMPLE_READ in the data->sample_type can be used to detect
> whether the PMU-specific value is available. If yes, avoid the
> pmu->read() in the common code.
> 
> Reviewed-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
> Signed-off-by: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>
> ---
>  kernel/events/core.c | 15 ++++++++-------
>  1 file changed, 8 insertions(+), 7 deletions(-)
> 
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index 8f908f077935..733e507948e6 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -7243,7 +7243,7 @@ static void perf_output_read_one(struct perf_output_handle *handle,
>  
>  static void perf_output_read_group(struct perf_output_handle *handle,
>  			    struct perf_event *event,
> -			    u64 enabled, u64 running)
> +			    u64 enabled, u64 running, bool read)
>  {
>  	struct perf_event *leader = event->group_leader, *sub;
>  	u64 read_format = event->attr.read_format;
> @@ -7265,7 +7265,7 @@ static void perf_output_read_group(struct perf_output_handle *handle,
>  	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
>  		values[n++] = running;
>  
> -	if ((leader != event) &&
> +	if ((leader != event) && read &&
>  	    (leader->state == PERF_EVENT_STATE_ACTIVE))
>  		leader->pmu->read(leader);
>  
> @@ -7280,7 +7280,7 @@ static void perf_output_read_group(struct perf_output_handle *handle,
>  	for_each_sibling_event(sub, leader) {
>  		n = 0;
>  
> -		if ((sub != event) &&
> +		if ((sub != event) && read &&
>  		    (sub->state == PERF_EVENT_STATE_ACTIVE))
>  			sub->pmu->read(sub);
>  
> @@ -7307,7 +7307,8 @@ static void perf_output_read_group(struct perf_output_handle *handle,
>   * on another CPU, from interrupt/NMI context.
>   */
>  static void perf_output_read(struct perf_output_handle *handle,
> -			     struct perf_event *event)
> +			     struct perf_event *event,
> +			     bool read)
>  {
>  	u64 enabled = 0, running = 0, now;
>  	u64 read_format = event->attr.read_format;
> @@ -7325,7 +7326,7 @@ static void perf_output_read(struct perf_output_handle *handle,
>  		calc_timer_values(event, &now, &enabled, &running);
>  
>  	if (event->attr.read_format & PERF_FORMAT_GROUP)
> -		perf_output_read_group(handle, event, enabled, running);
> +		perf_output_read_group(handle, event, enabled, running, read);
>  	else
>  		perf_output_read_one(handle, event, enabled, running);
>  }
> @@ -7367,7 +7368,7 @@ void perf_output_sample(struct perf_output_handle *handle,
>  		perf_output_put(handle, data->period);
>  
>  	if (sample_type & PERF_SAMPLE_READ)
> -		perf_output_read(handle, event);
> +		perf_output_read(handle, event, !(data->sample_flags & PERF_SAMPLE_READ));
>  
>  	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
>  		int size = 1;

this can't be right. The output is order sensitive. If a
PERF_SAMPLE_READ is part of the PERF_RECORD_SAMPLE, it must be in this
location.