[PATCH] sched: reduce debug code

move the rest of the debugging/instrumentation code to under
CONFIG_SCHEDSTATS too. This reduces code size and speeds code up:

    text    data     bss     dec     hex filename
   33044    4122      28   37194    914a sched.o.before
   32708    4122      28   36858    8ffa sched.o.after

Signed-off-by: Ingo Molnar <mingo@elte.hu>

kernel/sched.c

@@ -983,18 +983,21 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	u64 clock_offset, fair_clock_offset;
 
 	clock_offset = old_rq->clock - new_rq->clock;
-	fair_clock_offset = old_rq->cfs.fair_clock -
-						 new_rq->cfs.fair_clock;
-	if (p->se.wait_start)
-		p->se.wait_start -= clock_offset;
+	fair_clock_offset = old_rq->cfs.fair_clock - new_rq->cfs.fair_clock;
+
 	if (p->se.wait_start_fair)
 		p->se.wait_start_fair -= fair_clock_offset;
+	if (p->se.sleep_start_fair)
+		p->se.sleep_start_fair -= fair_clock_offset;
+
+#ifdef CONFIG_SCHEDSTATS
+	if (p->se.wait_start)
+		p->se.wait_start -= clock_offset;
 	if (p->se.sleep_start)
 		p->se.sleep_start -= clock_offset;
 	if (p->se.block_start)
 		p->se.block_start -= clock_offset;
-	if (p->se.sleep_start_fair)
-		p->se.sleep_start_fair -= fair_clock_offset;
+#endif
 
 	__set_task_cpu(p, new_cpu);
 }
@@ -1555,24 +1558,27 @@ int fastcall wake_up_state(struct task_struct *p, unsigned int state)
 static void __sched_fork(struct task_struct *p)
 {
 	p->se.wait_start_fair		= 0;
-	p->se.wait_start		= 0;
 	p->se.exec_start		= 0;
 	p->se.sum_exec_runtime		= 0;
 	p->se.delta_exec		= 0;
 	p->se.delta_fair_run		= 0;
 	p->se.delta_fair_sleep		= 0;
 	p->se.wait_runtime		= 0;
+	p->se.sleep_start_fair		= 0;
+
+#ifdef CONFIG_SCHEDSTATS
+	p->se.wait_start		= 0;
 	p->se.sum_wait_runtime		= 0;
 	p->se.sum_sleep_runtime		= 0;
 	p->se.sleep_start		= 0;
-	p->se.sleep_start_fair		= 0;
 	p->se.block_start		= 0;
 	p->se.sleep_max			= 0;
 	p->se.block_max			= 0;
 	p->se.exec_max			= 0;
 	p->se.wait_max			= 0;
 	p->se.wait_runtime_overruns	= 0;
 	p->se.wait_runtime_underruns	= 0;
+#endif
 
 	INIT_LIST_HEAD(&p->run_list);
 	p->se.on_rq = 0;
@@ -6579,12 +6585,14 @@ void normalize_rt_tasks(void)
 	do_each_thread(g, p) {
 		p->se.fair_key			= 0;
 		p->se.wait_runtime		= 0;
+		p->se.exec_start		= 0;
 		p->se.wait_start_fair		= 0;
+		p->se.sleep_start_fair		= 0;
+#ifdef CONFIG_SCHEDSTATS
 		p->se.wait_start		= 0;
-		p->se.exec_start		= 0;
 		p->se.sleep_start		= 0;
-		p->se.sleep_start_fair		= 0;
 		p->se.block_start		= 0;
+#endif
 		task_rq(p)->cfs.fair_clock	= 0;
 		task_rq(p)->clock		= 0;
 

kernel/sched_debug.c

@@ -44,11 +44,16 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p, u64 now)
 		(long long)p->se.wait_runtime,
 		(long long)(p->nvcsw + p->nivcsw),
 		p->prio,
+#ifdef CONFIG_SCHEDSTATS
 		(long long)p->se.sum_exec_runtime,
 		(long long)p->se.sum_wait_runtime,
 		(long long)p->se.sum_sleep_runtime,
 		(long long)p->se.wait_runtime_overruns,
-		(long long)p->se.wait_runtime_underruns);
+		(long long)p->se.wait_runtime_underruns
+#else
+		0LL, 0LL, 0LL, 0LL, 0LL
+#endif
+	);
 }
 
 static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu, u64 now)
@@ -171,7 +176,7 @@ static int sched_debug_show(struct seq_file *m, void *v)
 	u64 now = ktime_to_ns(ktime_get());
 	int cpu;
 
-	SEQ_printf(m, "Sched Debug Version: v0.05, %s %.*s\n",
+	SEQ_printf(m, "Sched Debug Version: v0.05-v20, %s %.*s\n",
 		init_utsname()->release,
 		(int)strcspn(init_utsname()->version, " "),
 		init_utsname()->version);
@@ -235,21 +240,24 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 #define P(F) \
 	SEQ_printf(m, "%-25s:%20Ld\n", #F, (long long)p->F)
 
-	P(se.wait_start);
+	P(se.wait_runtime);
 	P(se.wait_start_fair);
 	P(se.exec_start);
-	P(se.sleep_start);
 	P(se.sleep_start_fair);
+	P(se.sum_exec_runtime);
+
+#ifdef CONFIG_SCHEDSTATS
+	P(se.wait_start);
+	P(se.sleep_start);
 	P(se.block_start);
 	P(se.sleep_max);
 	P(se.block_max);
 	P(se.exec_max);
 	P(se.wait_max);
-	P(se.wait_runtime);
 	P(se.wait_runtime_overruns);
 	P(se.wait_runtime_underruns);
 	P(se.sum_wait_runtime);
-	P(se.sum_exec_runtime);
+#endif
 	SEQ_printf(m, "%-25s:%20Ld\n",
 		   "nr_switches", (long long)(p->nvcsw + p->nivcsw));
 	P(se.load.weight);
@@ -269,7 +277,9 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 
 void proc_sched_set_task(struct task_struct *p)
 {
+#ifdef CONFIG_SCHEDSTATS
 	p->se.sleep_max = p->se.block_max = p->se.exec_max = p->se.wait_max = 0;
 	p->se.wait_runtime_overruns = p->se.wait_runtime_underruns = 0;
+#endif
 	p->se.sum_exec_runtime = 0;
 }

kernel/sched_fair.c

@@ -349,7 +349,7 @@ static inline void
 update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se, u64 now)
 {
 	se->wait_start_fair = cfs_rq->fair_clock;
-	se->wait_start = now;
+	schedstat_set(se->wait_start, now);
 }
 
 /*
@@ -447,7 +447,7 @@ update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se, u64 now)
 	}
 
 	se->wait_start_fair = 0;
-	se->wait_start = 0;
+	schedstat_set(se->wait_start, 0);
 }
 
 static inline void

kernel/sched_rt.c

@@ -18,8 +18,8 @@ static inline void update_curr_rt(struct rq *rq, u64 now)
 	delta_exec = now - curr->se.exec_start;
 	if (unlikely((s64)delta_exec < 0))
 		delta_exec = 0;
-	if (unlikely(delta_exec > curr->se.exec_max))
-		curr->se.exec_max = delta_exec;
+
+	schedstat_set(curr->se.exec_max, max(curr->se.exec_max, delta_exec));
 
 	curr->se.sum_exec_runtime += delta_exec;
 	curr->se.exec_start = now;