From: "David E. Box" <david.e.box@linux.intel.com>
To: david.e.box@linux.intel.com, jacob.jun.pan@linux.intel.com,
linux-pm@vger.kernel.org, rafael.j.wysocki@intel.com,
linux-kernel@vger.kernel.org, hpa@linux.intel.com
Cc: alan@linux.intel.com, durgadoss.r@intel.com, kristen.c.accardi@intel.com
Subject: [PATCH v2 4/4] powercap/rapl: change floor frequency for vallewview
Date: Tue, 29 Apr 2014 15:33:09 -0700 [thread overview]
Message-ID: <1398810789-2301-5-git-send-email-david.e.box@linux.intel.com> (raw)
In-Reply-To: <1398810789-2301-1-git-send-email-david.e.box@linux.intel.com>
From: Jacob Pan <jacob.jun.pan@linux.intel.com>
RAPL power limit reduce power by limiting CPU P-state and
other techniques. On Valleyview, RAPL power limit cannot
go to LFM (low frequency mode) if we don't set the floor
frequency via IOSF mailbox.
This patch enables setting of floor frquency such that
RAPL power limit is more effective.
Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
---
drivers/powercap/intel_rapl.c | 27 +++++++++++++++++++--------
1 file changed, 19 insertions(+), 8 deletions(-)
diff --git a/drivers/powercap/intel_rapl.c b/drivers/powercap/intel_rapl.c
index b1cda6f..13e4776 100644
--- a/drivers/powercap/intel_rapl.c
+++ b/drivers/powercap/intel_rapl.c
@@ -32,6 +32,7 @@
#include <asm/processor.h>
#include <asm/cpu_device_id.h>
+#include <asm/iosf_mbi.h>
/* bitmasks for RAPL MSRs, used by primitive access functions */
#define ENERGY_STATUS_MASK 0xffffffff
@@ -336,11 +337,17 @@ static int find_nr_power_limit(struct rapl_domain *rd)
return i;
}
+#define VLV_CPU_POWER_BUDGET_CTL (0x2)
+static const struct x86_cpu_id valleyview_id[] = {
+ { X86_VENDOR_INTEL, 6, 0x37},
+ {}
+};
+
static int set_domain_enable(struct powercap_zone *power_zone, bool mode)
{
struct rapl_domain *rd = power_zone_to_rapl_domain(power_zone);
int nr_powerlimit;
-
+ u32 mdata = 0;
if (rd->state & DOMAIN_STATE_BIOS_LOCKED)
return -EACCES;
get_online_cpus();
@@ -350,7 +357,16 @@ static int set_domain_enable(struct powercap_zone *power_zone, bool mode)
/* always enable clamp such that p-state can go below OS requested
* range. power capping priority over guranteed frequency.
*/
- rapl_write_data_raw(rd, PL1_CLAMP, mode);
+ if (x86_match_cpu(valleyview_id)) {
+ iosf_mbi_read(BT_MBI_UNIT_PMC, BT_MBI_PMC_READ,
+ VLV_CPU_POWER_BUDGET_CTL, &mdata);
+ mdata &= ~(0x7f << 8);
+ mdata |= 1 << 8;
+ iosf_mbi_write(BT_MBI_UNIT_PMC, BT_MBI_PMC_WRITE,
+ VLV_CPU_POWER_BUDGET_CTL, mdata);
+ } else
+ rapl_write_data_raw(rd, PL1_CLAMP, mode);
+
/* some domains have pl2 */
if (nr_powerlimit > 1) {
rapl_write_data_raw(rd, PL2_ENABLE, mode);
@@ -833,11 +849,6 @@ static int rapl_write_data_raw(struct rapl_domain *rd,
return 0;
}
-static const struct x86_cpu_id energy_unit_quirk_ids[] = {
- { X86_VENDOR_INTEL, 6, 0x37},/* Valleyview */
- {}
-};
-
static int rapl_check_unit(struct rapl_package *rp, int cpu)
{
u64 msr_val;
@@ -859,7 +870,7 @@ static int rapl_check_unit(struct rapl_package *rp, int cpu)
*/
value = (msr_val & ENERGY_UNIT_MASK) >> ENERGY_UNIT_OFFSET;
/* some CPUs have different way to calculate energy unit */
- if (x86_match_cpu(energy_unit_quirk_ids))
+ if (x86_match_cpu(valleyview_id))
rp->energy_unit_divisor = 1000000 / (1 << value);
else
rp->energy_unit_divisor = 1 << value;
--
1.7.10.4
next prev parent reply other threads:[~2014-04-29 22:33 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-04-28 14:04 [PATCH 0/5] RAPL driver updates Jacob Pan
2014-04-28 14:04 ` [PATCH 1/5] powercap/rapl: further relax energy counter checks Jacob Pan
2014-04-28 14:04 ` [PATCH 2/5] powercap/rapl: add new cpu ids Jacob Pan
2014-04-28 14:04 ` [PATCH 3/5] x86, iosf: Add dummy functions for loadable modules Jacob Pan
2014-04-28 14:04 ` [PATCH 4/5] x86/iosf: kconfig and used by other drivers Jacob Pan
2014-04-28 14:04 ` [PATCH 5/5] powercap/rapl: change floor frequency for vallewview Jacob Pan
2014-04-29 2:45 ` R, Durgadoss
2014-04-29 13:02 ` Jacob Pan
2014-04-29 14:40 ` R, Durgadoss
2014-04-29 8:23 ` Jacob Pan
2014-04-29 22:33 ` [PATCH v2 0/4] RAPL driver updates David E. Box
2014-04-29 22:33 ` [PATCH v2 1/4] powercap/rapl: further relax energy counter checks David E. Box
2014-04-30 5:29 ` R, Durgadoss
2014-04-29 22:33 ` [PATCH v2 2/4] powercap/rapl: add new cpu ids David E. Box
2014-04-29 22:33 ` [PATCH v2 3/4] x86/iosf: Make IOSF driver modular and usable by more drivers David E. Box
2014-04-29 22:33 ` David E. Box [this message]
2014-04-29 23:02 ` [PATCH v2 0/4] RAPL driver updates Rafael J. Wysocki
2014-04-29 23:38 ` Jacob Pan
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1398810789-2301-5-git-send-email-david.e.box@linux.intel.com \
--to=david.e.box@linux.intel.com \
--cc=alan@linux.intel.com \
--cc=durgadoss.r@intel.com \
--cc=hpa@linux.intel.com \
--cc=jacob.jun.pan@linux.intel.com \
--cc=kristen.c.accardi@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=rafael.j.wysocki@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).