[PATCH v2 2/3] scheduler: cpuacct: Enable platform callbacks for cpuacct power tracking

[Mike Chan <mike@android.com>]

V2:
- Rebased off Thomass Renninger's cgroup_cpuacct refactoring

Platform must register cpu power function that return power in
milliWatt seconds.

New file:
cpuacct.power reports the power consumed in milliWatt seconds

Signed-off-by: Mike Chan <mike@android.com>
---
 Documentation/cgroups/cpuacct.txt |    3 +++
 include/linux/cpuacct.h           |    4 +++-
 kernel/cgroup_cpuaccount.c        |   24 ++++++++++++++++++++++--
 3 files changed, 28 insertions(+), 3 deletions(-)

diff --git a/Documentation/cgroups/cpuacct.txt b/Documentation/cgroups/cpuacct.txt
index 600d2d0..84e471b 100644
--- a/Documentation/cgroups/cpuacct.txt
+++ b/Documentation/cgroups/cpuacct.txt
@@ -44,6 +44,9 @@ cpuacct.cpufreq file gives CPU time (in nanoseconds) spent at each CPU
 frequency. Platform hooks must be implemented inorder to properly track
 time at each CPU frequency.
 
+cpuacct.power file gives CPU power consumed (in milliWatt seconds). Platform
+must provide and implement power callback functions.
+
 cpuacct controller uses percpu_counter interface to collect user and
 system times. This has two side effects:
 
diff --git a/include/linux/cpuacct.h b/include/linux/cpuacct.h
index 6205d29..c17a634 100644
--- a/include/linux/cpuacct.h
+++ b/include/linux/cpuacct.h
@@ -31,7 +31,9 @@ struct cpuacct_charge_calls {
 	 */
 	void (*init) (void **cpuacct_data);
 	void (*charge) (void *cpuacct_data,  u64 cputime, unsigned int cpu);
-	void (*show) (void *cpuacct_data, struct cgroup_map_cb *cb);
+	void (*cpufreq_show) (void *cpuacct_data, struct cgroup_map_cb *cb);
+	/* Returns power consumed in milliWatt seconds */
+	u64 (*power_usage) (void *cpuacct_data);
 };
 
 int cpuacct_charge_register(struct cpuacct_charge_calls *fn);
diff --git a/kernel/cgroup_cpuaccount.c b/kernel/cgroup_cpuaccount.c
index 11799a7..d9bf889 100644
--- a/kernel/cgroup_cpuaccount.c
+++ b/kernel/cgroup_cpuaccount.c
@@ -226,12 +226,28 @@ 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);
+	if (ca->cpufreq_fn && ca->cpufreq_fn->cpufreq_show)
+		ca->cpufreq_fn->cpufreq_show(ca->cpuacct_data, cb);
 
 	return 0;
 }
 
+/* return total cpu power usage (milliWatt second) of a group */
+static u64 cpuacct_powerusage_read(struct cgroup *cgrp, struct cftype *cft)
+{
+	int i;
+	struct cpuacct *ca = cgroup_ca(cgrp);
+	u64 totalpower = 0;
+
+	if (ca->cpufreq_fn && ca->cpufreq_fn->power_usage)
+		for_each_present_cpu(i) {
+			totalpower += ca->cpufreq_fn->power_usage(
+					ca->cpuacct_data);
+		}
+
+	return totalpower;
+}
+
 static struct cftype files[] = {
 	{
 		.name = "usage",
@@ -250,6 +266,10 @@ static struct cftype files[] = {
 		.name =  "cpufreq",
 		.read_map = cpuacct_cpufreq_show,
 	},
+	{
+		.name = "power",
+		.read_u64 = cpuacct_powerusage_read
+	},
 };
 
 static int cpuacct_populate(struct cgroup_subsys *ss, struct cgroup *cgrp)
-- 
1.7.0.1