On 6/14/24 20:31, Mark Rutland wrote:

On Thu, Jun 13, 2024 at 11:47:25AM +0530, Anshuman Khandual wrote:

quoted

@@ -289,6 +289,23 @@ static void armpmu_start(struct perf_event *event, int flags)
 {
 	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
+	struct pmu_hw_events *cpuc = this_cpu_ptr(armpmu->hw_events);
+	int idx;
+
+	/*
+	 * Merge all branch filter requests from different perf
+	 * events being added into this PMU. This includes both
+	 * privilege and branch type filters.
+	 */
+	if (armpmu->has_branch_stack) {
+		cpuc->branch_sample_type = 0;
+		for (idx = 0; idx < ARMPMU_MAX_HWEVENTS; idx++) {
+			struct perf_event *event_idx = cpuc->events[idx];
+
+			if (event_idx && has_branch_stack(event_idx))
+				cpuc->branch_sample_type |= event_idx->attr.branch_sample_type;
+		}
+	}

When we spoke about this, I meant that we should do this under armpmu::start(),
or a callee or caller thereof once we know all the events are configured, just
before we actually enable the PMU.

For example, this could live in armv8pmu_branch_enable(), which'd allow
all the actual logic to be added in the BRBE enablement patch.

Doing this in armpmu_start() doesn't work as well because it won't handle
events being removed.

Sure, will move this filter aggregation inside armv8pmu_branch_enable() instead
which is being added via the BRBE driver.

diff --git a/drivers/perf/arm_brbe.c b/drivers/perf/arm_brbe.c
index d795e8fd646f..9cf824bdc8b7 100644
--- a/drivers/perf/arm_brbe.c
+++ b/drivers/perf/arm_brbe.c

@@ -856,6 +856,22 @@ void armv8pmu_branch_enable(struct arm_pmu *arm_pmu)
 {
        struct pmu_hw_events *cpuc = this_cpu_ptr(arm_pmu->hw_events);
        u64 brbfcr, brbcr;
+       int idx;
+
+       /*
+        * Merge all branch filter requests from different perf
+        * events being added into this PMU. This includes both
+        * privilege and branch type filters.
+        */
+       if (arm_pmu->has_branch_stack) {
+               cpuc->branch_sample_type = 0;
+               for (idx = 0; idx < ARMPMU_MAX_HWEVENTS; idx++) {
+                       struct perf_event *event_idx = cpuc->events[idx];
+
+                       if (event_idx && has_branch_stack(event_idx))
+                               cpuc->branch_sample_type |= event_idx->attr.branch_sample_type;
+               }
+       }
 
        if (!(cpuc->branch_sample_type && cpuc->branch_users))
                return;

[...]

quoted

diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index b3b34f6670cf..9eda16dd684e 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h

@@ -46,6 +46,18 @@ static_assert((PERF_EVENT_FLAG_ARCH & ARMPMU_EVT_63BIT) == ARMPMU_EVT_63BIT);
 	},								\
 }
 
+/*
+ * Maximum branch record entries which could be processed
+ * for core perf branch stack sampling support, regardless
+ * of the hardware support available on a given ARM PMU.
+ */
+#define MAX_BRANCH_RECORDS 64
+
+struct branch_records {
+	struct perf_branch_stack	branch_stack;
+	struct perf_branch_entry	branch_entries[MAX_BRANCH_RECORDS];
+};
+
 /* The events for a given PMU register set. */
 struct pmu_hw_events {
 	/*

@@ -66,6 +78,17 @@ struct pmu_hw_events {
 	struct arm_pmu		*percpu_pmu;
 
 	int irq;
+
+	struct branch_records	*branches;
+
+	/* Active context for task events */
+	void			*branch_context;

Using 'void *' here makes this harder to reason about and hides type
safety issues.

Give this a real type. IIUC it should be 'perf_event_context *'.

Sure, will change the type.

quoted

+
+	/* Active events requesting branch records */
+	unsigned int		branch_users;
+
+	/* Active branch sample type filters */
+	unsigned long		branch_sample_type;
 };
 
 enum armpmu_attr_groups {

@@ -96,8 +119,15 @@ struct arm_pmu {
 	void		(*stop)(struct arm_pmu *);
 	void		(*reset)(void *);
 	int		(*map_event)(struct perf_event *event);
+	void		(*sched_task)(struct perf_event_pmu_context *pmu_ctx, bool sched_in);
+	bool		(*branch_stack_init)(struct perf_event *event);
+	void		(*branch_stack_add)(struct perf_event *event, struct pmu_hw_events *cpuc);
+	void		(*branch_stack_del)(struct perf_event *event, struct pmu_hw_events *cpuc);
+	void		(*branch_stack_reset)(void);

The reset callback isn't used in this series; s

Subsequent patches call armv8pmu_branch_stack_reset() directly from
PMUv3 and the BRBE driver, and arm_pmu::branch_stack_reset() is never
used, so we can delete it.

Sure, will drop branch_stack_reset() callback.