1 files changed, 116 insertions, 24 deletions

diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c
index c0c60e6a1703..f1551c08ecb2 100644
--- a/drivers/hwtracing/coresight/coresight-etm-perf.c
+++ b/drivers/hwtracing/coresight/coresight-etm-perf.c
@@ -136,13 +136,13 @@ static const struct attribute_group *etm_pmu_attr_groups[] = {
 	NULL,
 };
 
-static inline struct list_head **
+static inline struct coresight_path **
 etm_event_cpu_path_ptr(struct etm_event_data *data, int cpu)
 {
 	return per_cpu_ptr(data->path, cpu);
 }
 
-static inline struct list_head *
+static inline struct coresight_path *
 etm_event_cpu_path(struct etm_event_data *data, int cpu)
 {
 	return *etm_event_cpu_path_ptr(data, cpu);
@@ -226,18 +226,27 @@ static void free_event_data(struct work_struct *work)
 		cscfg_deactivate_config(event_data->cfg_hash);
 
 	for_each_cpu(cpu, mask) {
-		struct list_head **ppath;
+		struct coresight_path **ppath;
 
 		ppath = etm_event_cpu_path_ptr(event_data, cpu);
-		if (!(IS_ERR_OR_NULL(*ppath)))
+		if (!(IS_ERR_OR_NULL(*ppath))) {
+			struct coresight_device *sink = coresight_get_sink(*ppath);
+
+			/*
+			 * Mark perf event as done for trace id allocator, but don't call
+			 * coresight_trace_id_put_cpu_id_map() on individual IDs. Perf sessions
+			 * never free trace IDs to ensure that the ID associated with a CPU
+			 * cannot change during their and other's concurrent sessions. Instead,
+			 * a refcount is used so that the last event to call
+			 * coresight_trace_id_perf_stop() frees all IDs.
+			 */
+			coresight_trace_id_perf_stop(&sink->perf_sink_id_map);
+
 			coresight_release_path(*ppath);
+		}
 		*ppath = NULL;
-		coresight_trace_id_put_cpu_id(cpu);
 	}
 
-	/* mark perf event as done for trace id allocator */
-	coresight_trace_id_perf_stop();
-
 	free_percpu(event_data->path);
 	kfree(event_data);
 }
@@ -267,7 +276,7 @@ static void *alloc_event_data(int cpu)
 	 * unused memory when dealing with single CPU trace scenarios is small
 	 * compared to the cost of searching through an optimized array.
 	 */
-	event_data->path = alloc_percpu(struct list_head *);
+	event_data->path = alloc_percpu(struct coresight_path *);
 
 	if (!event_data->path) {
 		kfree(event_data);
@@ -308,7 +317,6 @@ static void *etm_setup_aux(struct perf_event *event, void **pages,
 {
 	u32 id, cfg_hash;
 	int cpu = event->cpu;
-	int trace_id;
 	cpumask_t *mask;
 	struct coresight_device *sink = NULL;
 	struct coresight_device *user_sink = NULL, *last_sink = NULL;
@@ -325,9 +333,6 @@ static void *etm_setup_aux(struct perf_event *event, void **pages,
 		sink = user_sink = coresight_get_sink_by_id(id);
 	}
 
-	/* tell the trace ID allocator that a perf event is starting up */
-	coresight_trace_id_perf_start();
-
 	/* check if user wants a coresight configuration selected */
 	cfg_hash = (u32)((event->attr.config2 & GENMASK_ULL(63, 32)) >> 32);
 	if (cfg_hash) {
@@ -346,7 +351,7 @@ static void *etm_setup_aux(struct perf_event *event, void **pages,
 	 * CPUs, we can handle it and fail the session.
 	 */
 	for_each_cpu(cpu, mask) {
-		struct list_head *path;
+		struct coresight_path *path;
 		struct coresight_device *csdev;
 
 		csdev = per_cpu(csdev_src, cpu);
@@ -361,6 +366,18 @@ static void *etm_setup_aux(struct perf_event *event, void **pages,
 		}
 
 		/*
+		 * If AUX pause feature is enabled but the ETM driver does not
+		 * support the operations, clear this CPU from the mask and
+		 * continue to next one.
+		 */
+		if (event->attr.aux_start_paused &&
+		    (!source_ops(csdev)->pause_perf || !source_ops(csdev)->resume_perf)) {
+			dev_err_once(&csdev->dev, "AUX pause is not supported.\n");
+			cpumask_clear_cpu(cpu, mask);
+			continue;
+		}
+
+		/*
 		 * No sink provided - look for a default sink for all the ETMs,
 		 * where this event can be scheduled.
 		 * We allocate the sink specific buffers only once for this
@@ -401,13 +418,14 @@ static void *etm_setup_aux(struct perf_event *event, void **pages,
 		}
 
 		/* ensure we can allocate a trace ID for this CPU */
-		trace_id = coresight_trace_id_get_cpu_id(cpu);
-		if (!IS_VALID_CS_TRACE_ID(trace_id)) {
+		coresight_path_assign_trace_id(path, CS_MODE_PERF);
+		if (!IS_VALID_CS_TRACE_ID(path->trace_id)) {
 			cpumask_clear_cpu(cpu, mask);
 			coresight_release_path(path);
 			continue;
 		}
 
+		coresight_trace_id_perf_start(&sink->perf_sink_id_map);
 		*etm_event_cpu_path_ptr(event_data, cpu) = path;
 	}
 
@@ -444,6 +462,15 @@ err:
 	goto out;
 }
 
+static int etm_event_resume(struct coresight_device *csdev,
+			     struct etm_ctxt *ctxt)
+{
+	if (!ctxt->event_data)
+		return 0;
+
+	return coresight_resume_source(csdev);
+}
+
 static void etm_event_start(struct perf_event *event, int flags)
 {
 	int cpu = smp_processor_id();
@@ -451,12 +478,20 @@ static void etm_event_start(struct perf_event *event, int flags)
 	struct etm_ctxt *ctxt = this_cpu_ptr(&etm_ctxt);
 	struct perf_output_handle *handle = &ctxt->handle;
 	struct coresight_device *sink, *csdev = per_cpu(csdev_src, cpu);
-	struct list_head *path;
+	struct coresight_path *path;
 	u64 hw_id;
 
 	if (!csdev)
 		goto fail;
 
+	if (flags & PERF_EF_RESUME) {
+		if (etm_event_resume(csdev, ctxt) < 0) {
+			dev_err(&csdev->dev, "Failed to resume ETM event.\n");
+			goto fail;
+		}
+		return;
+	}
+
 	/* Have we messed up our tracking ? */
 	if (WARN_ON(ctxt->event_data))
 		goto fail;
@@ -495,7 +530,7 @@ static void etm_event_start(struct perf_event *event, int flags)
 		goto fail_end_stop;
 
 	/* Finally enable the tracer */
-	if (source_ops(csdev)->enable(csdev, event, CS_MODE_PERF))
+	if (source_ops(csdev)->enable(csdev, event, CS_MODE_PERF, path))
 		goto fail_disable_path;
 
 	/*
@@ -504,10 +539,14 @@ static void etm_event_start(struct perf_event *event, int flags)
 	 */
 	if (!cpumask_test_cpu(cpu, &event_data->aux_hwid_done)) {
 		cpumask_set_cpu(cpu, &event_data->aux_hwid_done);
-		hw_id = FIELD_PREP(CS_AUX_HW_ID_VERSION_MASK,
-				   CS_AUX_HW_ID_CURR_VERSION);
-		hw_id |= FIELD_PREP(CS_AUX_HW_ID_TRACE_ID_MASK,
-				    coresight_trace_id_read_cpu_id(cpu));
+
+		hw_id = FIELD_PREP(CS_AUX_HW_ID_MAJOR_VERSION_MASK,
+				CS_AUX_HW_ID_MAJOR_VERSION);
+		hw_id |= FIELD_PREP(CS_AUX_HW_ID_MINOR_VERSION_MASK,
+				CS_AUX_HW_ID_MINOR_VERSION);
+		hw_id |= FIELD_PREP(CS_AUX_HW_ID_TRACE_ID_MASK, path->trace_id);
+		hw_id |= FIELD_PREP(CS_AUX_HW_ID_SINK_ID_MASK, coresight_get_sink_id(sink));
+
 		perf_report_aux_output_id(event, hw_id);
 	}
 
@@ -535,6 +574,55 @@ fail:
 	return;
 }
 
+static void etm_event_pause(struct perf_event *event,
+			    struct coresight_device *csdev,
+			    struct etm_ctxt *ctxt)
+{
+	int cpu = smp_processor_id();
+	struct coresight_device *sink;
+	struct perf_output_handle *handle = &ctxt->handle;
+	struct coresight_path *path;
+	unsigned long size;
+
+	if (!ctxt->event_data)
+		return;
+
+	/* Stop tracer */
+	coresight_pause_source(csdev);
+
+	path = etm_event_cpu_path(ctxt->event_data, cpu);
+	sink = coresight_get_sink(path);
+	if (WARN_ON_ONCE(!sink))
+		return;
+
+	/*
+	 * The per CPU sink has own interrupt handling, it might have
+	 * race condition with updating buffer on AUX trace pause if
+	 * it is invoked from NMI.  To avoid the race condition,
+	 * disallows updating buffer for the per CPU sink case.
+	 */
+	if (coresight_is_percpu_sink(sink))
+		return;
+
+	if (WARN_ON_ONCE(handle->event != event))
+		return;
+
+	if (!sink_ops(sink)->update_buffer)
+		return;
+
+	size = sink_ops(sink)->update_buffer(sink, handle,
+					     ctxt->event_data->snk_config);
+	if (READ_ONCE(handle->event)) {
+		if (!size)
+			return;
+
+		perf_aux_output_end(handle, size);
+		perf_aux_output_begin(handle, event);
+	} else {
+		WARN_ON_ONCE(size);
+	}
+}
+
 static void etm_event_stop(struct perf_event *event, int mode)
 {
 	int cpu = smp_processor_id();
@@ -543,7 +631,10 @@ static void etm_event_stop(struct perf_event *event, int mode)
 	struct etm_ctxt *ctxt = this_cpu_ptr(&etm_ctxt);
 	struct perf_output_handle *handle = &ctxt->handle;
 	struct etm_event_data *event_data;
-	struct list_head *path;
+	struct coresight_path *path;
+
+	if (mode & PERF_EF_PAUSE)
+		return etm_event_pause(event, csdev, ctxt);
 
 	/*
 	 * If we still have access to the event_data via handle,
@@ -889,7 +980,8 @@ int __init etm_perf_init(void)
 	int ret;
 
 	etm_pmu.capabilities		= (PERF_PMU_CAP_EXCLUSIVE |
-					   PERF_PMU_CAP_ITRACE);
+					   PERF_PMU_CAP_ITRACE |
+					   PERF_PMU_CAP_AUX_PAUSE);
 
 	etm_pmu.attr_groups		= etm_pmu_attr_groups;
 	etm_pmu.task_ctx_nr		= perf_sw_context;