Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.32 as permitted sender) client-ip=23.128.96.32;
From:   Dapeng Mi <dapeng1.mi@linux.intel.com>
To:     Sean Christopherson <seanjc@google.com>,
        Paolo Bonzini <pbonzini@redhat.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Arnaldo Carvalho de Melo <acme@kernel.org>,
        Kan Liang <kan.liang@linux.intel.com>,
        Like Xu <likexu@tencent.com>,
        Mark Rutland <mark.rutland@arm.com>,
        Alexander Shishkin <alexander.shishkin@linux.intel.com>,
        Jiri Olsa <jolsa@kernel.org>,
        Namhyung Kim <namhyung@kernel.org>,
        Ian Rogers <irogers@google.com>,
        Adrian Hunter <adrian.hunter@intel.com>
Cc:     kvm@vger.kernel.org, linux-perf-users@vger.kernel.org,
        linux-kernel@vger.kernel.org,
        Zhenyu Wang <zhenyuw@linux.intel.com>,
        Zhang Xiong <xiong.y.zhang@intel.com>,
        Lv Zhiyuan <zhiyuan.lv@intel.com>,
        Yang Weijiang <weijiang.yang@intel.com>,
        Dapeng Mi <dapeng1.mi@intel.com>,
        Dapeng Mi <dapeng1.mi@linux.intel.com>
Subject: [Patch v4 08/13] perf/core: Add new function perf_event_topdown_metrics()
Date:   Wed, 27 Sep 2023 11:31:19 +0800
Message-Id: <20230927033124.1226509-9-dapeng1.mi@linux.intel.com>
In-Reply-To: <20230927033124.1226509-1-dapeng1.mi@linux.intel.com>
References: <20230927033124.1226509-1-dapeng1.mi@linux.intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Add a new function perf_event_topdown_metrics(). This new function is
quite familiar with function perf_event_period(), but it updates slots
count and metrics raw data instead of sample period into perf system.

When guest restores FIXED_CTR3 and PERF_METRICS MSRs in sched-in process,
KVM needs to capture the MSR writing trap and set the MSR values of guest
into corresponding perf events just like function perf_event_period()
does.

Initially we tried to reuse the function perf_event_period() to set the
slots/metrics value, but we found it was quite hard. The function
perf_event_period() only works on sampling events but unfortunately
slots event and metric events in topdown mode are all non-sampling
events. There are sampling event check and lots of sampling period
related check and setting in the function perf_event_period()
call-chain. If we want to reuse the function perf_event_period(), we
have to add lots of if-else changes on the entire function-chain and
even modify the function name. This would totally mess up the function
perf_event_period().

Thus, we select to create a new function perf_event_topdown_metrics() to
set the slots/metrics values. This makes logic and code both be clearer.

Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
---
 include/linux/perf_event.h | 13 ++++++++
 kernel/events/core.c       | 62 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 75 insertions(+)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 04e12a8e6584..10d737aab7fa 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1057,6 +1057,11 @@ perf_cgroup_from_task(struct task_struct *task, struct perf_event_context *ctx)
 }
 #endif /* CONFIG_CGROUP_PERF */
 
+struct td_metrics {
+	u64	slots;
+	u64	metric;
+};
+
 #ifdef CONFIG_PERF_EVENTS
 
 extern struct perf_event_context *perf_cpu_task_ctx(void);
@@ -1707,6 +1712,8 @@ extern void perf_event_task_tick(void);
 extern int perf_event_account_interrupt(struct perf_event *event);
 extern int perf_event_period(struct perf_event *event, u64 value);
 extern u64 perf_event_pause(struct perf_event *event, bool reset);
+extern int perf_event_topdown_metrics(struct perf_event *event,
+				      struct td_metrics *value);
 #else /* !CONFIG_PERF_EVENTS: */
 static inline void *
 perf_aux_output_begin(struct perf_output_handle *handle,
@@ -1793,6 +1800,12 @@ static inline u64 perf_event_pause(struct perf_event *event, bool reset)
 {
 	return 0;
 }
+
+static inline int perf_event_topdown_metrics(struct perf_event *event,
+					     struct td_metrics *value)
+{
+	return 0;
+}
 #endif
 
 #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 3cc870d450c5..500ffcd2c621 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5776,6 +5776,68 @@ int perf_event_period(struct perf_event *event, u64 value)
 }
 EXPORT_SYMBOL_GPL(perf_event_period);
 
+static void __perf_event_topdown_metrics(struct perf_event *event,
+					 struct perf_cpu_context *cpuctx,
+					 struct perf_event_context *ctx,
+					 void *info)
+{
+	struct td_metrics *td_metrics = (struct td_metrics *)info;
+	bool active;
+
+	active = (event->state == PERF_EVENT_STATE_ACTIVE);
+	if (active) {
+		perf_pmu_disable(event->pmu);
+		/*
+		 * We could be throttled; unthrottle now to avoid the tick
+		 * trying to unthrottle while we already re-started the event.
+		 */
+		if (event->hw.interrupts == MAX_INTERRUPTS) {
+			event->hw.interrupts = 0;
+			perf_log_throttle(event, 1);
+		}
+		event->pmu->stop(event, PERF_EF_UPDATE);
+	}
+
+	event->hw.saved_slots = td_metrics->slots;
+	event->hw.saved_metric = td_metrics->metric;
+
+	if (active) {
+		event->pmu->start(event, PERF_EF_RELOAD);
+		perf_pmu_enable(event->pmu);
+	}
+}
+
+static int _perf_event_topdown_metrics(struct perf_event *event,
+				       struct td_metrics *value)
+{
+	/*
+	 * Slots event in topdown metrics scenario
+	 * must be non-sampling event.
+	 */
+	if (is_sampling_event(event))
+		return -EINVAL;
+
+	if (!value)
+		return -EINVAL;
+
+	event_function_call(event, __perf_event_topdown_metrics, value);
+
+	return 0;
+}
+
+int perf_event_topdown_metrics(struct perf_event *event, struct td_metrics *value)
+{
+	struct perf_event_context *ctx;
+	int ret;
+
+	ctx = perf_event_ctx_lock(event);
+	ret = _perf_event_topdown_metrics(event, value);
+	perf_event_ctx_unlock(event, ctx);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(perf_event_topdown_metrics);
+
 static const struct file_operations perf_fops;
 
 static inline int perf_fget_light(int fd, struct fd *p)
-- 
2.34.1