cpuidle: teo: Simplify counting events used for tick management

Replace the tick_hits metric with a new tick_intercepts one that can be
used directly when deciding whether or not to stop the scheduler tick
and update the governor functional description accordingly.

No intentional functional impact.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Christian Loehle <christian.loehle@arm.com>
Tested-by: Aboorva Devarajan <aboorvad@linux.ibm.com>
Tested-by: Christian Loehle <christian.loehle@arm.com>
Link: https://patch.msgid.link/1987985.PYKUYFuaPT@rjwysocki.net

diff --git a/drivers/cpuidle/governors/teo.c b/drivers/cpuidle/governors/teo.c
index 411b315081f8bc3d9cc32b2188caa0a7346e0297..62f323f2e245cae011ccd1c6f1949f02faa249cf 100644 (file)
--- a/drivers/cpuidle/governors/teo.c
+++ b/drivers/cpuidle/governors/teo.c
@@ -41,11 +41,7 @@
  * idle state 2, the third bin spans from the target residency of idle state 2
  * up to, but not including, the target residency of idle state 3 and so on.
  * The last bin spans from the target residency of the deepest idle state
- * supplied by the driver to the scheduler tick period length or to infinity if
- * the tick period length is less than the target residency of that state.  In
- * the latter case, the governor also counts events with the measured idle
- * duration between the tick period length and the target residency of the
- * deepest idle state.
+ * supplied by the driver to infinity.
  *
  * Two metrics called "hits" and "intercepts" are associated with each bin.
  * They are updated every time before selecting an idle state for the given CPU
@@ -60,6 +56,10 @@
  * into by the sleep length (these events are also referred to as "intercepts"
  * below).
  *
+ * The governor also counts "intercepts" with the measured idle duration below
+ * the tick period length and uses this information when deciding whether or not
+ * to stop the scheduler tick.
+ *
  * In order to select an idle state for a CPU, the governor takes the following
  * steps (modulo the possible latency constraint that must be taken into account
  * too):
@@ -128,14 +128,14 @@ struct teo_bin {
  * @sleep_length_ns: Time till the closest timer event (at the selection time).
  * @state_bins: Idle state data bins for this CPU.
  * @total: Grand total of the "intercepts" and "hits" metrics for all bins.
- * @tick_hits: Number of "hits" after TICK_NSEC.
+ * @tick_intercepts: "Intercepts" before TICK_NSEC.
  */
 struct teo_cpu {
        s64 time_span_ns;
        s64 sleep_length_ns;
        struct teo_bin state_bins[CPUIDLE_STATE_MAX];
        unsigned int total;
-       unsigned int tick_hits;
+       unsigned int tick_intercepts;
 };
 
 static DEFINE_PER_CPU(struct teo_cpu, teo_cpus);
@@ -207,38 +207,21 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
                }
        }
 
-       /*
-        * If the deepest state's target residency is below the tick length,
-        * make a record of it to help teo_select() decide whether or not
-        * to stop the tick.  This effectively adds an extra hits-only bin
-        * beyond the last state-related one.
-        */
-       if (target_residency_ns < TICK_NSEC) {
-               cpu_data->tick_hits -= cpu_data->tick_hits >> DECAY_SHIFT;
-
-               cpu_data->total += cpu_data->tick_hits;
-
-               if (TICK_NSEC <= cpu_data->sleep_length_ns) {
-                       idx_timer = drv->state_count;
-                       if (TICK_NSEC <= measured_ns) {
-                               cpu_data->tick_hits += PULSE;
-                               goto end;
-                       }
-               }
-       }
-
+       cpu_data->tick_intercepts -= cpu_data->tick_intercepts >> DECAY_SHIFT;
        /*
         * If the measured idle duration falls into the same bin as the sleep
         * length, this is a "hit", so update the "hits" metric for that bin.
         * Otherwise, update the "intercepts" metric for the bin fallen into by
         * the measured idle duration.
         */
-       if (idx_timer == idx_duration)
+       if (idx_timer == idx_duration) {
                cpu_data->state_bins[idx_timer].hits += PULSE;
-       else
+       } else {
                cpu_data->state_bins[idx_duration].intercepts += PULSE;
+               if (TICK_NSEC <= measured_ns)
+                       cpu_data->tick_intercepts += PULSE;
+       }
 
-end:
        cpu_data->total += PULSE;
 }
 
@@ -286,7 +269,6 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
        struct teo_cpu *cpu_data = per_cpu_ptr(&teo_cpus, dev->cpu);
        s64 latency_req = cpuidle_governor_latency_req(dev->cpu);
        ktime_t delta_tick = TICK_NSEC / 2;
-       unsigned int tick_intercept_sum = 0;
        unsigned int idx_intercept_sum = 0;
        unsigned int intercept_sum = 0;
        unsigned int idx_hit_sum = 0;
@@ -365,9 +347,6 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
                goto end;
        }
 
-       tick_intercept_sum = intercept_sum +
-                       cpu_data->state_bins[drv->state_count-1].intercepts;
-
        /*
         * If the sum of the intercepts metric for all of the idle states
         * shallower than the current candidate one (idx) is greater than the
@@ -477,7 +456,7 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
         * total wakeup events, do not stop the tick.
         */
        if (drv->states[idx].target_residency_ns < TICK_NSEC &&
-           tick_intercept_sum > cpu_data->total / 2 + cpu_data->total / 8)
+           cpu_data->tick_intercepts > cpu_data->total / 2 + cpu_data->total / 8)
                duration_ns = TICK_NSEC / 2;
 
 end: