sched: eliminate sched_account_wait_time knob

Kill unused scheduler knob sched_account_wait_time.  With this change
scheduler always accounts task's wait time into demand.

Change-Id: Ifa4bcb5685798f48fd020f3d0c9853220b3f5fdc
Signed-off-by: Joonwoo Park <joonwoop@codeaurora.org>

Documentation/scheduler/sched-zone.txt

@@ -1113,16 +1113,7 @@ tracking mechanism maintains per task. If default values are used for
 both this and sched_ravg_window then a total of 50ms of task history
 would be maintained in 5 10ms windows.
 
-*** 7.11 sched_account_wait_time
+*** 7.11 sched_freq_account_wait_time
-
-Appears at: /proc/sys/kernel/sched_account_wait_time
-
-Default value: 1
-
-This controls whether a task's wait time is accounted as its demand for cpu
-and thus the values found in its sum, sum_history[] and demand attributes.
-
-*** 7.12 sched_freq_account_wait_time
 
 Appears at: /proc/sys/kernel/sched_freq_account_wait_time
 
@@ -1132,7 +1123,7 @@ This controls whether a task's wait time is accounted in its curr_window and
 prev_window attributes and thus in a cpu's curr_runnable_sum and
 prev_runnable_sum counters.
 
-*** 7.13 sched_migration_fixup
+*** 7.12 sched_migration_fixup
 
 Appears at: /proc/sys/kernel/sched_migration_fixup
 
@@ -1141,7 +1132,7 @@ Default value: 1
 This controls whether a cpu's busy time counters are adjusted during task
 migration.
 
-*** 7.14 sched_freq_inc_notify
+*** 7.13 sched_freq_inc_notify
 
 Appears at: /proc/sys/kernel/sched_freq_inc_notify
 
@@ -1153,7 +1144,7 @@ exceeds sched_freq_inc_notify, where freq_required is the frequency calculated
 by scheduler to meet current task demand. Note that sched_freq_inc_notify is
 specified in kHz units.
 
-*** 7.15 sched_freq_dec_notify
+*** 7.14 sched_freq_dec_notify
 
 Appears at: /proc/sys/kernel/sched_freq_dec_notify
 
@@ -1166,7 +1157,7 @@ exceeds sched_freq_dec_notify, where freq_required is the frequency calculated
 by scheduler to meet current task demand. Note that sched_freq_dec_notify is
 specified in kHz units.
 
-** 7.16 sched_heavy_task
+** 7.15 sched_heavy_task
 
 Appears at: /proc/sys/kernel/sched_heavy_task
 
@@ -1178,7 +1169,7 @@ comparison. Scheduler will request a raise in cpu frequency when heavy tasks
 wakeup after at least one window of sleep, where window size is defined by
 sched_ravg_window. Value 0 will disable this feature.
 
-*** 7.17 sched_cpu_high_irqload
+*** 7.16 sched_cpu_high_irqload
 
 Appears at: /proc/sys/kernel/sched_cpu_high_irqload
 
@@ -1196,7 +1187,7 @@ longer eligible for placement. This will affect the task placement logic
 described above, causing the scheduler to try and steer tasks away from
 the CPU.
 
-** 7.18 cpu.upmigrate_discourage
+** 7.17 cpu.upmigrate_discourage
 
 Default value : 0
 
@@ -1212,7 +1203,7 @@ overcommitted scenario. See notes on sched_spill_nr_run and sched_spill_load for
 how overcommitment threshold is defined and also notes on
 'sched_upmigrate_min_nice' tunable.
 
-*** 7.19 sched_static_cpu_pwr_cost
+*** 7.18 sched_static_cpu_pwr_cost
 
 Default value: 0
 
@@ -1227,7 +1218,7 @@ within a cluster and possibly have differing value between clusters as
 needed.
 
 
-*** 7.20 sched_static_cluster_pwr_cost
+*** 7.19 sched_static_cluster_pwr_cost
 
 Default value: 0
 
@@ -1238,7 +1229,7 @@ power mode. It ignores the actual D-state that a cluster may be in and assumes
 the worst case power cost of the highest D-state. It is means of biasing task
 placement away from idle clusters when necessary.
 
-***7.23 sched_early_detection_duration
+*** 7.20 sched_early_detection_duration
 
 Default value: 9500000
 
@@ -1249,7 +1240,7 @@ tick for it to be eligible for the scheduler's early detection feature
 under scheduler boost. For more information on the feature itself please
 refer to section 5.2.1.
 
-*** 7.24 sched_restrict_cluster_spill
+*** 7.21 sched_restrict_cluster_spill
 
 Default value: 0
 
@@ -1268,7 +1259,7 @@ CPU across all clusters. When this tunable is enabled, the RT tasks are
 restricted to the lowest possible power cluster.
 
 
-*** 7.25 sched_downmigrate
+*** 7.22 sched_downmigrate
 
 Appears at: /proc/sys/kernel/sched_downmigrate
 
@@ -1281,7 +1272,7 @@ its demand *in reference to the power-efficient cpu* drops less than 60%
 (sched_downmigrate).
 
 
-*** 7.26 sched_small_wakee_task_load
+*** 7.23 sched_small_wakee_task_load
 
 Appears at: /proc/sys/kernel/sched_small_wakee_task_load
 
@@ -1293,7 +1284,7 @@ categorized as small wakee tasks.  Scheduler places small wakee tasks on the
 waker's cluster.
 
 
-*** 7.26 sched_big_waker_task_load
+*** 7.24 sched_big_waker_task_load
 
 Appears at: /proc/sys/kernel/sched_big_waker_task_load
 
@@ -1450,10 +1441,9 @@ cpus are being reset. Changes to below attributes result in such a reset:
 
 * sched_ravg_window (See Sec 2)
 * sched_window_stats_policy (See Sec 2.4)
-* sched_account_wait_time (See Sec 7.15)
 * sched_ravg_hist_size (See Sec 7.11)
-* sched_migration_fixup (See Sec 7.17)
+* sched_migration_fixup (See Sec 7.12)
-* sched_freq_account_wait_time (See Sec 7.16)
+* sched_freq_account_wait_time (See Sec 7.11)
 
 <task>-0     [004] d.h4 12700.711489: sched_reset_all_windows_stats: time_taken 1123 window_start 0 window_size 0 reason POLICY_CHANGE old_val 0 new_val 1
 

include/linux/sched/sysctl.h

@@ -42,7 +42,6 @@ extern unsigned int sysctl_sched_child_runs_first;
 extern unsigned int sysctl_sched_wake_to_idle;
 extern unsigned int sysctl_sched_wakeup_load_threshold;
 extern unsigned int sysctl_sched_window_stats_policy;
-extern unsigned int sysctl_sched_account_wait_time;
 extern unsigned int sysctl_sched_ravg_hist_size;
 extern unsigned int sysctl_sched_cpu_high_irqload;
 extern unsigned int sysctl_sched_freq_account_wait_time;

kernel/sched/core.c

@@ -1763,7 +1763,7 @@ struct cpu_cycle {
 #if defined(CONFIG_SCHED_HMP)
 
 /*
- * sched_window_stats_policy, sched_account_wait_time, sched_ravg_hist_size,
+ * sched_window_stats_policy, sched_ravg_hist_size,
  * sched_migration_fixup, sched_freq_account_wait_time have a 'sysctl' copy
  * associated with them. This is required for atomic update of those variables
  * when being modifed via sysctl interface.
@@ -1786,8 +1786,7 @@ static __read_mostly unsigned int sched_window_stats_policy =
 __read_mostly unsigned int sysctl_sched_window_stats_policy =
 	WINDOW_STATS_MAX_RECENT_AVG;
 
-static __read_mostly unsigned int sched_account_wait_time = 1;
+#define SCHED_ACCOUNT_WAIT_TIME 1
-__read_mostly unsigned int sysctl_sched_account_wait_time = 1;
 
 __read_mostly unsigned int sysctl_sched_cpu_high_irqload = (10 * NSEC_PER_MSEC);
 
@@ -2794,7 +2793,7 @@ static int account_busy_for_task_demand(struct task_struct *p, int event)
 	 * time. Likewise, if wait time is not treated as busy time, then
 	 * when a task begins to run or is migrated, it is not running and
 	 * is completing a segment of non-busy time. */
-	if (event == TASK_WAKE || (!sched_account_wait_time &&
+	if (event == TASK_WAKE || (!SCHED_ACCOUNT_WAIT_TIME &&
 			 (event == PICK_NEXT_TASK || event == TASK_MIGRATE)))
 		return 0;
 
@@ -3185,7 +3184,6 @@ static void enable_window_stats(void)
 enum reset_reason_code {
 	WINDOW_CHANGE,
 	POLICY_CHANGE,
-	ACCOUNT_WAIT_TIME_CHANGE,
 	HIST_SIZE_CHANGE,
 	MIGRATION_FIXUP_CHANGE,
 	FREQ_ACCOUNT_WAIT_TIME_CHANGE,
@@ -3195,7 +3193,6 @@ enum reset_reason_code {
 const char *sched_window_reset_reasons[] = {
 	"WINDOW_CHANGE",
 	"POLICY_CHANGE",
-	"ACCOUNT_WAIT_TIME_CHANGE",
 	"HIST_SIZE_CHANGE",
 	"MIGRATION_FIXUP_CHANGE",
 	"FREQ_ACCOUNT_WAIT_TIME_CHANGE"};
@@ -3260,11 +3257,6 @@ void reset_all_window_stats(u64 window_start, unsigned int window_size)
 		old = sched_window_stats_policy;
 		new = sysctl_sched_window_stats_policy;
 		sched_window_stats_policy = sysctl_sched_window_stats_policy;
-	} else if (sched_account_wait_time != sysctl_sched_account_wait_time) {
-		reason = ACCOUNT_WAIT_TIME_CHANGE;
-		old = sched_account_wait_time;
-		new = sysctl_sched_account_wait_time;
-		sched_account_wait_time = sysctl_sched_account_wait_time;
 	} else if (sched_ravg_hist_size != sysctl_sched_ravg_hist_size) {
 		reason = HIST_SIZE_CHANGE;
 		old = sched_ravg_hist_size;

kernel/sched/fair.c

@@ -4080,16 +4080,12 @@ static inline int invalid_value(unsigned int *data)
 	if (data == &sysctl_sched_window_stats_policy)
 		return val >= WINDOW_STATS_INVALID_POLICY;
 
-	if (data == &sysctl_sched_account_wait_time)
-		return !(val == 0 || val == 1);
-
 	return invalid_value_freq_input(data);
 }
 
 /*
  * Handle "atomic" update of sysctl_sched_window_stats_policy,
- * sysctl_sched_ravg_hist_size, sysctl_sched_account_wait_time and
+ * sysctl_sched_ravg_hist_size and sched_freq_legacy_mode variables.
- * sched_freq_legacy_mode variables.
  */
 int sched_window_update_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *lenp,

kernel/sysctl.c

@@ -339,13 +339,6 @@ static struct ctl_table kern_table[] = {
 	},
 #endif
 #ifdef CONFIG_SCHED_HMP
-	{
-		.procname       = "sched_account_wait_time",
-		.data           = &sysctl_sched_account_wait_time,
-		.maxlen         = sizeof(unsigned int),
-		.mode           = 0644,
-		.proc_handler   = sched_window_update_handler,
-	},
 	{
 		.procname       = "sched_cpu_high_irqload",
 		.data           = &sysctl_sched_cpu_high_irqload,