Re: [PATCH v7 07/12] perf/x86: no counter allocation support

[Peter Zijlstra]

On Mon, Jul 08, 2019 at 09:23:14AM +0800, Wei Wang wrote:
> In some cases, an event may be created without needing a counter
> allocation. For example, an lbr event may be created by the host
> only to help save/restore the lbr stack on the vCPU context switching.
> 
> This patch adds a new interface to allow users to create a perf event
> without the need of counter assignment.
> 
> Signed-off-by: Wei Wang <wei.w.wang@xxxxxxxxx>
> Cc: Andi Kleen <ak@xxxxxxxxxxxxxxx>
> Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
> ---

I _really_ hate this one.

>  arch/x86/events/core.c     | 12 ++++++++++++
>  include/linux/perf_event.h | 13 +++++++++++++
>  kernel/events/core.c       | 37 +++++++++++++++++++++++++------------
>  3 files changed, 50 insertions(+), 12 deletions(-)
> 
> diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
> index f315425..eebbd65 100644
> --- a/arch/x86/events/core.c
> +++ b/arch/x86/events/core.c
> @@ -410,6 +410,9 @@ int x86_setup_perfctr(struct perf_event *event)
>  	struct hw_perf_event *hwc = &event->hw;
>  	u64 config;
>  
> +	if (is_no_counter_event(event))
> +		return 0;
> +
>  	if (!is_sampling_event(event)) {
>  		hwc->sample_period = x86_pmu.max_period;
>  		hwc->last_period = hwc->sample_period;
> @@ -1248,6 +1251,12 @@ static int x86_pmu_add(struct perf_event *event, int flags)
>  	hwc = &event->hw;
>  
>  	n0 = cpuc->n_events;
> +
> +	if (is_no_counter_event(event)) {
> +		n = n0;
> +		goto done_collect;
> +	}
> +
>  	ret = n = collect_events(cpuc, event, false);
>  	if (ret < 0)
>  		goto out;
> @@ -1422,6 +1431,9 @@ static void x86_pmu_del(struct perf_event *event, int flags)
>  	if (cpuc->txn_flags & PERF_PMU_TXN_ADD)
>  		goto do_del;
>  
> +	if (is_no_counter_event(event))
> +		goto do_del;
> +
>  	/*
>  	 * Not a TXN, therefore cleanup properly.
>  	 */

That's truely an abomination.

> diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
> index 0ab99c7..19e6593 100644
> --- a/include/linux/perf_event.h
> +++ b/include/linux/perf_event.h
> @@ -528,6 +528,7 @@ typedef void (*perf_overflow_handler_t)(struct perf_event *,
>   */
>  #define PERF_EV_CAP_SOFTWARE		BIT(0)
>  #define PERF_EV_CAP_READ_ACTIVE_PKG	BIT(1)
> +#define PERF_EV_CAP_NO_COUNTER		BIT(2)
>  
>  #define SWEVENT_HLIST_BITS		8
>  #define SWEVENT_HLIST_SIZE		(1 << SWEVENT_HLIST_BITS)
> @@ -895,6 +896,13 @@ extern int perf_event_refresh(struct perf_event *event, int refresh);
>  extern void perf_event_update_userpage(struct perf_event *event);
>  extern int perf_event_release_kernel(struct perf_event *event);
>  extern struct perf_event *
> +perf_event_create(struct perf_event_attr *attr,
> +		  int cpu,
> +		  struct task_struct *task,
> +		  perf_overflow_handler_t overflow_handler,
> +		  void *context,
> +		  bool counter_assignment);
> +extern struct perf_event *
>  perf_event_create_kernel_counter(struct perf_event_attr *attr,
>  				int cpu,
>  				struct task_struct *task,

Why the heck are you creating this wrapper nonsense?