Re: [PATCH 4/9] perf/x86: special case per-cpu core misc PMU events

[Mark Rutland <mark.rutland@arm.com>]

On Thu, Jul 16, 2015 at 09:33:46PM +0100, kan.liang@intel.com wrote:
> From: Kan Liang <kan.liang@intel.com>
> 
> This patch special case per-cpu core_misc PMU events and allow them to
> be part of any hardware/software group for system-wide monitoring.
> An useful example would be to include the ASTATE/MSTATE event in a
> sampling group. This can be used to calculate the frequency during each
> sampling period, and track it over time.
> 
> A new context type (perf_free_context) is introduced to indicate these
> per-cpu core misc PMU events. They are
>  - Free running counter
>  - Don't have any state to switch on context switch and never fails
>    to schedule
>  - No sampling support
>  - Only support system-wide monitoring
>  - per-cpu
> We also defined a new PERF event type PERF_TYPE_CORE_MISC_FREE for them.
> 
> It's safe to mix cpu PMU events and CORE_MISC_FREE events in a group.
> Because when cpu PMU events disable/enable, we can disable/enable
> them at the same time without failure.

Which effectively means you're context-switching their state (given what
your enable/disable code does).

As with my earlier comments, I don't think these can be grouped with
events (not even from the same PMU given their free-running nature).

They're CPU-affine, so you can associate them with work done on that
CPU.

So as far as I can see, you should be able to handle the per-cpu misc
events in the perf_hardware_context, providing you reject grouping in
your event_init functions.

What does this extra context give you?

Mark.

> Since there is no sampling support for these events. They are only
> available for group reading and system-wide monitoring.
> 
> Signed-off-by: Kan Liang <kan.liang@intel.com>
> ---
>  arch/x86/kernel/cpu/perf_event_intel_core_misc.c |  8 +++++---
>  include/linux/perf_event.h                       | 10 ++++++++++
>  include/linux/sched.h                            |  1 +
>  include/uapi/linux/perf_event.h                  |  1 +
>  kernel/events/core.c                             |  9 +++++++++
>  5 files changed, 26 insertions(+), 3 deletions(-)
> 
> diff --git a/arch/x86/kernel/cpu/perf_event_intel_core_misc.c b/arch/x86/kernel/cpu/perf_event_intel_core_misc.c
> index 4efe842..dad4495 100644
> --- a/arch/x86/kernel/cpu/perf_event_intel_core_misc.c
> +++ b/arch/x86/kernel/cpu/perf_event_intel_core_misc.c
> @@ -889,7 +889,6 @@ static void __init core_misc_pmus_register(void)
>  
>  		type->pmu = (struct pmu) {
>  			.attr_groups	= type->pmu_group,
> -			.task_ctx_nr	= perf_invalid_context,
>  			.event_init	= core_misc_pmu_event_init,
>  			.add		= core_misc_pmu_event_add, /* must have */
>  			.del		= core_misc_pmu_event_del, /* must have */
> @@ -902,9 +901,12 @@ static void __init core_misc_pmus_register(void)
>  		if (type->type == perf_intel_core_misc_thread) {
>  			type->pmu.pmu_disable = (void *) intel_core_misc_pmu_disable;
>  			type->pmu.pmu_enable = (void *) intel_core_misc_pmu_enable;
> +			type->pmu.task_ctx_nr = perf_free_context;
> +			err = perf_pmu_register(&type->pmu, type->name, PERF_TYPE_CORE_MISC_FREE);
> +		} else {
> +			type->pmu.task_ctx_nr = perf_invalid_context;
> +			err = perf_pmu_register(&type->pmu, type->name, -1);
>  		}
> -
> -		err = perf_pmu_register(&type->pmu, type->name, -1);
>  		if (WARN_ON(err))
>  			pr_info("Failed to register PMU %s error %d\n",
>  				type->pmu.name, err);
> diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
> index fea0ddf..3538f1c 100644
> --- a/include/linux/perf_event.h
> +++ b/include/linux/perf_event.h
> @@ -773,6 +773,16 @@ static inline int is_hardware_event(struct perf_event *event)
>  	return event->pmu->task_ctx_nr == perf_hw_context;
>  }
>  
> +static inline int is_free_event(struct perf_event *event)
> +{
> +	return event->pmu->task_ctx_nr == perf_free_context;
> +}
> +
> +static inline int has_context_event(struct perf_event *event)
> +{
> +	return event->pmu->task_ctx_nr > perf_invalid_context;
> +}
> +
>  extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX];
>  
>  extern void ___perf_sw_event(u32, u64, struct pt_regs *, u64);
> diff --git a/include/linux/sched.h b/include/linux/sched.h
> index ae21f15..717f492 100644
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -1335,6 +1335,7 @@ union rcu_special {
>  struct rcu_node;
>  
>  enum perf_event_task_context {
> +	perf_free_context = -2,
>  	perf_invalid_context = -1,
>  	perf_hw_context = 0,
>  	perf_sw_context,
> diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
> index d97f84c..232b674 100644
> --- a/include/uapi/linux/perf_event.h
> +++ b/include/uapi/linux/perf_event.h
> @@ -32,6 +32,7 @@ enum perf_type_id {
>  	PERF_TYPE_HW_CACHE			= 3,
>  	PERF_TYPE_RAW				= 4,
>  	PERF_TYPE_BREAKPOINT			= 5,
> +	PERF_TYPE_CORE_MISC_FREE		= 6,
>  
>  	PERF_TYPE_MAX,				/* non-ABI */
>  };
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index 9077867..995b436 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -8019,6 +8019,15 @@ SYSCALL_DEFINE5(perf_event_open,
>  	}
>  
>  	/*
> +	 * Special case per-cpu free counter events and allow them to be part of
> +	 * any hardware/software group for system-wide monitoring.
> +	 */
> +	if (group_leader && !task &&
> +	    is_free_event(event) &&
> +	    has_context_event(group_leader))
> +		pmu = group_leader->pmu;
> +
> +	/*
>  	 * Get the target context (task or percpu):
>  	 */
>  	ctx = find_get_context(pmu, task, event);
> -- 
> 1.8.3.1
>