Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Fri, 24 Jul 2020 12:55:43 +0200
From:   peterz@infradead.org
To:     kan.liang@linux.intel.com
Cc:     acme@redhat.com, mingo@kernel.org, linux-kernel@vger.kernel.org,
        jolsa@kernel.org, eranian@google.com,
        alexander.shishkin@linux.intel.com, ak@linux.intel.com,
        like.xu@linux.intel.com
Subject: Re: [PATCH V7 07/14] perf/core: Add a new PERF_EV_CAP_COEXIST event
 capability
Message-ID: <20200724105543.GV119549@hirez.programming.kicks-ass.net>
References: <20200723171117.9918-1-kan.liang@linux.intel.com>
 <20200723171117.9918-8-kan.liang@linux.intel.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20200723171117.9918-8-kan.liang@linux.intel.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Thu, Jul 23, 2020 at 10:11:10AM -0700, kan.liang@linux.intel.com wrote:

> diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
> index 3b22db08b6fb..93631e5389bf 100644
> --- a/include/linux/perf_event.h
> +++ b/include/linux/perf_event.h
> @@ -576,9 +576,14 @@ typedef void (*perf_overflow_handler_t)(struct perf_event *,
>   * PERF_EV_CAP_SOFTWARE: Is a software event.
>   * PERF_EV_CAP_READ_ACTIVE_PKG: A CPU event (or cgroup event) that can be read
>   * from any CPU in the package where it is active.
> + * PERF_EV_CAP_COEXIST: An event with this flag must coexist with other sibling
> + * events, which have the same flag. If any event with the flag is detached
> + * from the group, split the group into singleton events, and move the events
> + * with the flag to the unrecoverable ERROR state.
>   */
>  #define PERF_EV_CAP_SOFTWARE		BIT(0)
>  #define PERF_EV_CAP_READ_ACTIVE_PKG	BIT(1)
> +#define PERF_EV_CAP_COEXIST		BIT(2)
>  
>  #define SWEVENT_HLIST_BITS		8
>  #define SWEVENT_HLIST_SIZE		(1 << SWEVENT_HLIST_BITS)
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index 7c436d705fbd..e35d549a356d 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -2133,10 +2133,28 @@ static inline struct list_head *get_event_list(struct perf_event *event)
>  	return event->attr.pinned ? &ctx->pinned_active : &ctx->flexible_active;
>  }
>  
> +/*
> + * If the event has PERF_EV_CAP_COEXIST capability,
> + * schedule it out and move it into the ERROR state.
> + */
> +static inline void perf_remove_coexist_events(struct perf_event *event)
> +{
> +	struct perf_event_context *ctx = event->ctx;
> +	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
> +
> +	if (!(event->event_caps & PERF_EV_CAP_COEXIST))
> +		return;
> +
> +	event_sched_out(event, cpuctx, ctx);
> +	perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
> +}

Ah, so the problem here is that ERROR is actually recoverable using
IOC_ENABLE. We don't want that either. Let me try and figure out of EXIT
would work.