Re: [PATCH RFC 04/10] perf: Introduce deferred user callchains

[Peter Zijlstra]

On Wed, Nov 15, 2023 at 08:13:31AM -0800, Namhyung Kim wrote:

> ---8<---
> diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
> index 39c6a250dd1b..a3765ff59798 100644
> --- a/include/uapi/linux/perf_event.h
> +++ b/include/uapi/linux/perf_event.h
> @@ -456,7 +456,8 @@ struct perf_event_attr {
>  				inherit_thread :  1, /* children only inherit if cloned with CLONE_THREAD */
>  				remove_on_exec :  1, /* event is removed from task on exec */
>  				sigtrap        :  1, /* send synchronous SIGTRAP on event */
> -				__reserved_1   : 26;
> +				defer_callchain:  1, /* generate DEFERRED_CALLCHAINS records for userspace */
> +				__reserved_1   : 25;
>  
>  	union {
>  		__u32		wakeup_events;	  /* wakeup every n events */
> @@ -1207,6 +1208,20 @@ enum perf_event_type {
>  	 */
>  	PERF_RECORD_AUX_OUTPUT_HW_ID		= 21,
>  
> +	/*
> +	 * Deferred user stack callchains (for SFrame).  Previous samples would

Possibly also useful for ShadowStack based unwinders. And by virtue of
it possibly saving work when multiple consecutive samples hit
the same kernel section, for everything.

> +	 * have kernel callchains only and they need to be stitched with this
> +	 * to make full callchains.
> +	 *
> +	 * struct {
> +	 *	struct perf_event_header	header;
> +	 *	u64				nr;
> +	 *	u64				ips[nr];
> +	 *	struct sample_id		sample_id;
> +	 * };
> +	 */
> +	PERF_RECORD_DEFERRED_CALLCHAINS		= 22,
> +
>  	PERF_RECORD_MAX,			/* non-ABI */
>  };
>  

Anyway, yeah, that should do I suppose.