profiling task: modify task profiling with performance counter macro

This patch is used to make sure profiling code only can be run
with performance profiling build, and unify all performance profiling
with same format and usage.

Signed-off-by: Baofeng Tian <baofeng.tian@intel.com>

Author: btian1

src/include/sof/schedule/task.h

@@ -14,6 +14,8 @@
 #include <stdbool.h>
 #include <stdint.h>
 #include <rtos/kernel.h>
+#include <sof/lib/perf_cnt.h>
+
 
 struct comp_dev;
 struct sof;
@@ -72,6 +74,9 @@ struct task {
 	uint32_t cycles_max;
 	uint32_t cycles_cnt;
 #endif
+#if CONFIG_PERFORMANCE_COUNTERS
+	struct perf_cnt_data pcd;
+#endif
 };
 
 static inline bool task_is_active(struct task *task)

src/schedule/zephyr_ll.c

@@ -12,7 +12,7 @@
 #include <sof/schedule/ll_schedule_domain.h>
 #include <sof/schedule/schedule.h>
 #include <sof/schedule/task.h>
-
+#include <sof/lib/perf_cnt.h>
 #include <zephyr/kernel.h>
 
 LOG_MODULE_REGISTER(ll_schedule, CONFIG_SOF_LOG_LEVEL);
@@ -122,30 +122,18 @@ static void zephyr_ll_task_insert_after_unlocked(struct task *task, struct task
 
 static inline enum task_state do_task_run(struct task *task)
 {
-	uint32_t cycles0, cycles1, diff;
 	enum task_state state;
 
-	cycles0 = k_cycle_get_32();
+#if CONFIG_PERFORMANCE_COUNTERS
+	perf_cnt_init(&task->pcd);
+#endif
 
 	state = task_run(task);
 
-	cycles1 = k_cycle_get_32();
-	if (cycles1 > cycles0)
-		diff = cycles1 - cycles0;
-	else
-		diff = UINT32_MAX - cycles0 + cycles1;
-
-	task->cycles_sum += diff;
-	task->cycles_max = diff > task->cycles_max ? diff : task->cycles_max;
-
-	if (++task->cycles_cnt == 1 << CYCLES_WINDOW_SIZE) {
-		task->cycles_sum >>= CYCLES_WINDOW_SIZE;
-		tr_info(&ll_tr, "ll task %p %pU avg %u, max %u",
-			task, task->uid, task->cycles_sum, task->cycles_max);
-		task->cycles_sum = 0;
-		task->cycles_cnt = 0;
-		task->cycles_max = 0;
-	}
+#if CONFIG_PERFORMANCE_COUNTERS
+	perf_cnt_stamp(&task->pcd, perf_trace_null, NULL);
+	task_perf_cnt_avg(&task->pcd, task_perf_avg_info, &ll_tr, task);
+#endif
 
 	return state;
 }

xtos/include/sof/lib/perf_cnt.h

@@ -79,6 +79,22 @@ struct perf_cnt_data {
 
 /* perf measurement windows size 2^x */
 #define PERF_CNT_CHECK_WINDOW_SIZE 10
+#define task_perf_avg_info(pcd, task_p, class)					\
+	tr_info(task_p, "perf_cycle task %p, %pU cpu avg %u peak %u",\
+		  class, (class)->uid, \
+		  (uint32_t)((pcd)->cpu_delta_sum),			\
+		  (uint32_t)((pcd)->cpu_delta_peak))
+#define task_perf_cnt_avg(pcd, trace_m, arg, class) do {                             \
+		(pcd)->cpu_delta_sum += (pcd)->cpu_delta_last;          \
+		if (++(pcd)->sample_cnt == 1 << PERF_CNT_CHECK_WINDOW_SIZE) { \
+			(pcd)->cpu_delta_sum >>= PERF_CNT_CHECK_WINDOW_SIZE;      \
+			trace_m(pcd, arg, class);                                 \
+			(pcd)->cpu_delta_sum = 0;                                 \
+			(pcd)->sample_cnt = 0;                                    \
+			(pcd)->plat_delta_peak = 0;                               \
+			(pcd)->cpu_delta_peak = 0;                                \
+		}                                                             \
+		} while (0)
 
 /** \brief Accumulates cpu timer delta samples calculated by perf_cnt_stamp().
  *
@@ -100,6 +116,8 @@ struct perf_cnt_data {
 
 #else
 #define perf_cnt_average(pcd, trace_m, arg)
+#define task_perf_cnt_avg(pcd, trace_m, arg, class)
+#define task_perf_avg_info(pcd, task_p, class)
 #endif /* CONFIG_PERFORMANCE_COUNTERS_RUN_AVERAGE */
 
 /** \brief Reads the timers and computes delta to the previous readings.