scheduler: cpuacct: Enable platform hooks to track cpuusage for CPU frequencies

Introduce new platform callback hooks for cpuacct for tracking CPU frequencies

Not all platforms / architectures have a set CPU_FREQ_TABLE defined
for CPU transition speeds. In order to track time spent in at various
CPU frequencies, we enable platform callbacks from cpuacct for this accounting.

Architectures that support overclock boosting, or don't have pre-defined
frequency tables can implement their own bucketing system that makes sense
given their cpufreq scaling abilities.

New file:
cpuacct.cpufreq reports the CPU time (in nanoseconds) spent at each CPU
frequency.

Change-Id: I10a80b3162e6fff3a8a2f74dd6bb37e88b12ba96
Signed-off-by: Mike Chan <mike@android.com>

1 files changed, 49 insertions, 0 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index 279d2552dae7..a01185969457 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -71,6 +71,7 @@
 #include <linux/ctype.h>
 #include <linux/ftrace.h>
 #include <linux/slab.h>
+#include <linux/cpuacct.h>
 
 #include <asm/tlb.h>
 #include <asm/irq_regs.h>
@@ -9104,8 +9105,30 @@ struct cpuacct {
 	u64 __percpu *cpuusage;
 	struct percpu_counter cpustat[CPUACCT_STAT_NSTATS];
 	struct cpuacct *parent;
+	struct cpuacct_charge_calls *cpufreq_fn;
+	void *cpuacct_data;
 };
 
+static struct cpuacct *cpuacct_root;
+
+/* Default calls for cpufreq accounting */
+static struct cpuacct_charge_calls *cpuacct_cpufreq;
+int cpuacct_register_cpufreq(struct cpuacct_charge_calls *fn)
+{
+	cpuacct_cpufreq = fn;
+
+	/*
+	 * Root node is created before platform can register callbacks,
+	 * initalize here.
+	 */
+	if (cpuacct_root && fn) {
+		cpuacct_root->cpufreq_fn = fn;
+		if (fn->init)
+			fn->init(&cpuacct_root->cpuacct_data);
+	}
+	return 0;
+}
+
 struct cgroup_subsys cpuacct_subsys;
 
 /* return cpu accounting group corresponding to this container */
@@ -9140,8 +9163,16 @@ static struct cgroup_subsys_state *cpuacct_create(
 		if (percpu_counter_init(&ca->cpustat[i], 0))
 			goto out_free_counters;
 
+	ca->cpufreq_fn = cpuacct_cpufreq;
+
+	/* If available, have platform code initalize cpu frequency table */
+	if (ca->cpufreq_fn && ca->cpufreq_fn->init)
+		ca->cpufreq_fn->init(&ca->cpuacct_data);
+
 	if (cgrp->parent)
 		ca->parent = cgroup_ca(cgrp->parent);
+	else
+		cpuacct_root = ca;
 
 	return &ca->css;
 
@@ -9269,6 +9300,16 @@ static int cpuacct_stats_show(struct cgroup *cgrp, struct cftype *cft,
 	return 0;
 }
 
+static int cpuacct_cpufreq_show(struct cgroup *cgrp, struct cftype *cft,
+		struct cgroup_map_cb *cb)
+{
+	struct cpuacct *ca = cgroup_ca(cgrp);
+	if (ca->cpufreq_fn && ca->cpufreq_fn->show)
+		ca->cpufreq_fn->show(ca->cpuacct_data, cb);
+
+	return 0;
+}
+
 static struct cftype files[] = {
 	{
 		.name = "usage",
@@ -9283,6 +9324,10 @@ static struct cftype files[] = {
 		.name = "stat",
 		.read_map = cpuacct_stats_show,
 	},
+	{
+		.name =  "cpufreq",
+		.read_map = cpuacct_cpufreq_show,
+	},
 };
 
 static int cpuacct_populate(struct cgroup_subsys *ss, struct cgroup *cgrp)
@@ -9312,6 +9357,10 @@ static void cpuacct_charge(struct task_struct *tsk, u64 cputime)
 	for (; ca; ca = ca->parent) {
 		u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
 		*cpuusage += cputime;
+
+		/* Call back into platform code to account for CPU speeds */
+		if (ca->cpufreq_fn && ca->cpufreq_fn->charge)
+			ca->cpufreq_fn->charge(ca->cpuacct_data, cputime, cpu);
 	}
 
 	rcu_read_unlock();