The MSR_PKG_POWER_INFO register (Intel ASDM, section 14.9.3
"Package RAPL Domain") provides a maximum time window which the
system can support. This window is read-only and is currently
not examined when setting the time windows for the package.
This patch implements get_max_time_window_us() and checks the window when
a user attempts to set power capping for the package.
Before the patch it was possible to set the window to, for example, 10000
micro seconds:
[root@intel-chiefriver-03 rhel7]# echo 10000 >
/sys/devices/virtual/powercap/intel-rapl/intel-rapl\:0/constraint_0_time_window_us;
egrep ^
/sys/devices/virtual/powercap/intel-rapl/intel-rapl\:0/constraint_0_time_window_us
/sys/devices/virtual/powercap/intel-rapl/intel-rapl:0/constraint_0_time_window_us:1:9765
but from 'turbostat -d', the package is limited to 976us:
cpu0: MSR_PKG_POWER_INFO: 0x01200168 (45 W TDP, RAPL 36 - 0 W, 0.000977 sec.)
(Note, there appears to be a rounding issue in turbostat which needs to
also be fixed. Looking at the values in the register it is clear the
value is 1/1024 = 976us.)
After the patch we are limited by the maximum time window:
[root@intel-chiefriver-03 rhel7]# echo 10000 >
/sys/devices/virtual/powercap/intel-rapl/intel-rapl\:0/constraint_0_time_window_us;
egrep ^
/sys/devices/virtual/powercap/intel-rapl/intel-rapl\:0/constraint_0_time_window_us
-bash: echo: write error: Invalid argument
/sys/devices/virtual/powercap/intel-rapl/intel-rapl:0/constraint_0_time_window_us:1:976
Cc: "Rafael J. Wysocki" <rafael.j.wyso...@intel.com>
Cc: Prarit Bhargava <pra...@redhat.com>
Cc: Radivoje Jovanovic <radivoje.jovano...@intel.com>
Cc: Seiichi Ikarashi <s.ikara...@jp.fujitsu.com>
Cc: Mathias Krause <mini...@googlemail.com>
Cc: Ajay Thomas <ajay.thomas.david.rajamanic...@intel.com>
Signed-off-by: Prarit Bhargava <pra...@redhat.com>
---
drivers/powercap/intel_rapl.c | 31 +++++++++++++++++++++++++++++++
drivers/powercap/powercap_sys.c | 6 ++++--
2 files changed, 35 insertions(+), 2 deletions(-)
diff --git a/drivers/powercap/intel_rapl.c b/drivers/powercap/intel_rapl.c
index 6c592dc..feb063d 100644
--- a/drivers/powercap/intel_rapl.c
+++ b/drivers/powercap/intel_rapl.c
@@ -493,13 +493,42 @@ static int get_current_power_limit(struct powercap_zone
*power_zone, int id,
return ret;
}
+static int get_max_time_window(struct powercap_zone *power_zone, int id,
+ u64 *data)
+{
+ struct rapl_domain *rd;
+ int ret = 0;
+ u64 val;
+
+ get_online_cpus();
+ rd = power_zone_to_rapl_domain(power_zone);
+
+ if (rapl_read_data_raw(rd, MAX_TIME_WINDOW, true, &val))
+ ret = -EIO;
+ else
+ *data = val;
+
+ put_online_cpus();
+ return ret;
+}
+
static int set_time_window(struct powercap_zone *power_zone, int id,
u64 window)
{
struct rapl_domain *rd;
int ret = 0;
+ u64 max_window;
get_online_cpus();
+ ret = get_max_time_window(power_zone, id, &max_window);
+ if (ret < 0)
+ goto out;
+
+ if (window > max_window) {
+ ret = -EINVAL;
+ goto out;
+ }
+
rd = power_zone_to_rapl_domain(power_zone);
switch (rd->rpl[id].prim_id) {
case PL1_ENABLE:
@@ -511,6 +540,7 @@ static int set_time_window(struct powercap_zone
*power_zone, int id,
default:
ret = -EINVAL;
}
+out:
put_online_cpus();
return ret;
}
@@ -590,6 +620,7 @@ static const struct powercap_zone_constraint_ops
constraint_ops = {
.set_time_window_us = set_time_window,
.get_time_window_us = get_time_window,
.get_max_power_uw = get_max_power,
+ .get_max_time_window_us = get_max_time_window,
.get_name = get_constraint_name,
};
diff --git a/drivers/powercap/powercap_sys.c b/drivers/powercap/powercap_sys.c
index 14bde0d..53fad0f 100644
--- a/drivers/powercap/powercap_sys.c
+++ b/drivers/powercap/powercap_sys.c
@@ -101,7 +101,7 @@ static ssize_t store_constraint_##_attr(struct device *dev,\
int err; \
u64 value; \
struct powercap_zone *power_zone = to_powercap_zone(dev); \
- int id; \
+ int id, ret; \
struct powercap_zone_constraint *pconst;\
\
if (!sscanf(dev_attr->attr.name, "constraint_%d_", &id)) \
@@ -113,8 +113,10 @@ static ssize_t store_constraint_##_attr(struct device
*dev,\
if (err) \
return -EINVAL; \
if (pconst && pconst->ops && pconst->ops->set_##_attr) { \
- if (!pconst->ops->set_##_attr(power_zone, id, value)) \
+ ret = pconst->ops->set_##_attr(power_zone, id, value); \
+ if (!ret) \
return count; \
+ return ret; \
} \
\
return -ENODATA; \
--
1.7.9.3
