* [PATCH 0/3] powernow-k8: Misc fixes
@ 2012-01-06 14:55 ` Andreas Herrmann
0 siblings, 0 replies; 9+ messages in thread
From: Andreas Herrmann @ 2012-01-06 14:55 UTC (permalink / raw)
To: Dave Jones; +Cc: cpufreq, linux-kernel
Hi Dave,
Following two fixes are required on systems where intermediate Pstates
are disabled.
Please apply.
Thanks,
Andreas
^ permalink raw reply [flat|nested] 9+ messages in thread
* [PATCH 1/3] powernow-k8: Avoid Pstate MSR accesses on systems supporting CPB
2012-01-06 14:55 ` Andreas Herrmann
@ 2012-01-06 14:56 ` Andreas Herrmann
-1 siblings, 0 replies; 9+ messages in thread
From: Andreas Herrmann @ 2012-01-06 14:56 UTC (permalink / raw)
To: Dave Jones; +Cc: cpufreq, linux-kernel
Due to CPB we can't directly map SW Pstates to Pstate MSRs. Get rid of
the paranoia check. (assuming that the ACPI Pstate information is
correct.)
Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com>
---
drivers/cpufreq/powernow-k8.c | 19 ++++++++++---------
1 files changed, 10 insertions(+), 9 deletions(-)
diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c
index bce576d..e0329f9 100644
--- a/drivers/cpufreq/powernow-k8.c
+++ b/drivers/cpufreq/powernow-k8.c
@@ -926,23 +926,24 @@ static int fill_powernow_table_pstate(struct powernow_k8_data *data,
invalidate_entry(powernow_table, i);
continue;
}
- rdmsr(MSR_PSTATE_DEF_BASE + index, lo, hi);
- if (!(hi & HW_PSTATE_VALID_MASK)) {
- pr_debug("invalid pstate %d, ignoring\n", index);
- invalidate_entry(powernow_table, i);
- continue;
- }
-
- powernow_table[i].index = index;
-
/* Frequency may be rounded for these */
if ((boot_cpu_data.x86 == 0x10 && boot_cpu_data.x86_model < 10)
|| boot_cpu_data.x86 == 0x11) {
+
+ rdmsr(MSR_PSTATE_DEF_BASE + index, lo, hi);
+ if (!(hi & HW_PSTATE_VALID_MASK)) {
+ pr_debug("invalid pstate %d, ignoring\n", index);
+ invalidate_entry(powernow_table, i);
+ continue;
+ }
+
powernow_table[i].frequency =
freq_from_fid_did(lo & 0x3f, (lo >> 6) & 7);
} else
powernow_table[i].frequency =
data->acpi_data.states[i].core_frequency * 1000;
+
+ powernow_table[i].index = index;
}
return 0;
}
--
1.7.8.1
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH 1/3] powernow-k8: Avoid Pstate MSR accesses on systems supporting CPB
@ 2012-01-06 14:56 ` Andreas Herrmann
0 siblings, 0 replies; 9+ messages in thread
From: Andreas Herrmann @ 2012-01-06 14:56 UTC (permalink / raw)
To: Dave Jones; +Cc: cpufreq, linux-kernel
Due to CPB we can't directly map SW Pstates to Pstate MSRs. Get rid of
the paranoia check. (assuming that the ACPI Pstate information is
correct.)
Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com>
---
drivers/cpufreq/powernow-k8.c | 19 ++++++++++---------
1 files changed, 10 insertions(+), 9 deletions(-)
diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c
index bce576d..e0329f9 100644
--- a/drivers/cpufreq/powernow-k8.c
+++ b/drivers/cpufreq/powernow-k8.c
@@ -926,23 +926,24 @@ static int fill_powernow_table_pstate(struct powernow_k8_data *data,
invalidate_entry(powernow_table, i);
continue;
}
- rdmsr(MSR_PSTATE_DEF_BASE + index, lo, hi);
- if (!(hi & HW_PSTATE_VALID_MASK)) {
- pr_debug("invalid pstate %d, ignoring\n", index);
- invalidate_entry(powernow_table, i);
- continue;
- }
-
- powernow_table[i].index = index;
-
/* Frequency may be rounded for these */
if ((boot_cpu_data.x86 == 0x10 && boot_cpu_data.x86_model < 10)
|| boot_cpu_data.x86 == 0x11) {
+
+ rdmsr(MSR_PSTATE_DEF_BASE + index, lo, hi);
+ if (!(hi & HW_PSTATE_VALID_MASK)) {
+ pr_debug("invalid pstate %d, ignoring\n", index);
+ invalidate_entry(powernow_table, i);
+ continue;
+ }
+
powernow_table[i].frequency =
freq_from_fid_did(lo & 0x3f, (lo >> 6) & 7);
} else
powernow_table[i].frequency =
data->acpi_data.states[i].core_frequency * 1000;
+
+ powernow_table[i].index = index;
}
return 0;
}
--
1.7.8.1
^ permalink raw reply related [flat|nested] 9+ messages in thread
* [PATCH 2/3] powernow-k8: Fix indexing issue
2012-01-06 14:55 ` Andreas Herrmann
@ 2012-01-06 14:57 ` Andreas Herrmann
-1 siblings, 0 replies; 9+ messages in thread
From: Andreas Herrmann @ 2012-01-06 14:57 UTC (permalink / raw)
To: Dave Jones; +Cc: cpufreq, linux-kernel
The driver uses the pstate number from the status register as index in
its table of ACPI pstates (powernow_table). This is wrong as this is
not a 1-to-1 mapping.
For example we can have _PSS information to just utilize Pstate 0 and
Pstate 4, ie.
powernow-k8: Core Performance Boosting: on.
powernow-k8: 0 : pstate 0 (2200 MHz)
powernow-k8: 1 : pstate 4 (1400 MHz)
In this example the driver's powernow_table has just 2 entries. Using
the pstate number (4) as index into this table is just plain wrong.
Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com>
---
drivers/cpufreq/powernow-k8.c | 15 +++++++++++----
1 files changed, 11 insertions(+), 4 deletions(-)
diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c
index e0329f9..ad683ec 100644
--- a/drivers/cpufreq/powernow-k8.c
+++ b/drivers/cpufreq/powernow-k8.c
@@ -54,6 +54,9 @@ static DEFINE_PER_CPU(struct powernow_k8_data *, powernow_data);
static int cpu_family = CPU_OPTERON;
+/* array to map SW pstate number to acpi state */
+static u32 ps_to_as[8];
+
/* core performance boost */
static bool cpb_capable, cpb_enabled;
static struct msr __percpu *msrs;
@@ -80,9 +83,9 @@ static u32 find_khz_freq_from_fid(u32 fid)
}
static u32 find_khz_freq_from_pstate(struct cpufreq_frequency_table *data,
- u32 pstate)
+ u32 pstate)
{
- return data[pstate].frequency;
+ return data[ps_to_as[pstate]].frequency;
}
/* Return the vco fid for an input fid
@@ -926,6 +929,9 @@ static int fill_powernow_table_pstate(struct powernow_k8_data *data,
invalidate_entry(powernow_table, i);
continue;
}
+
+ ps_to_as[index] = i;
+
/* Frequency may be rounded for these */
if ((boot_cpu_data.x86 == 0x10 && boot_cpu_data.x86_model < 10)
|| boot_cpu_data.x86 == 0x11) {
@@ -1190,7 +1196,8 @@ static int powernowk8_target(struct cpufreq_policy *pol,
powernow_k8_acpi_pst_values(data, newstate);
if (cpu_family == CPU_HW_PSTATE)
- ret = transition_frequency_pstate(data, newstate);
+ ret = transition_frequency_pstate(data,
+ data->powernow_table[newstate].index);
else
ret = transition_frequency_fidvid(data, newstate);
if (ret) {
@@ -1203,7 +1210,7 @@ static int powernowk8_target(struct cpufreq_policy *pol,
if (cpu_family == CPU_HW_PSTATE)
pol->cur = find_khz_freq_from_pstate(data->powernow_table,
- newstate);
+ data->powernow_table[newstate].index);
else
pol->cur = find_khz_freq_from_fid(data->currfid);
ret = 0;
--
1.7.8.1
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH 2/3] powernow-k8: Fix indexing issue
@ 2012-01-06 14:57 ` Andreas Herrmann
0 siblings, 0 replies; 9+ messages in thread
From: Andreas Herrmann @ 2012-01-06 14:57 UTC (permalink / raw)
To: Dave Jones; +Cc: cpufreq, linux-kernel
The driver uses the pstate number from the status register as index in
its table of ACPI pstates (powernow_table). This is wrong as this is
not a 1-to-1 mapping.
For example we can have _PSS information to just utilize Pstate 0 and
Pstate 4, ie.
powernow-k8: Core Performance Boosting: on.
powernow-k8: 0 : pstate 0 (2200 MHz)
powernow-k8: 1 : pstate 4 (1400 MHz)
In this example the driver's powernow_table has just 2 entries. Using
the pstate number (4) as index into this table is just plain wrong.
Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com>
---
drivers/cpufreq/powernow-k8.c | 15 +++++++++++----
1 files changed, 11 insertions(+), 4 deletions(-)
diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c
index e0329f9..ad683ec 100644
--- a/drivers/cpufreq/powernow-k8.c
+++ b/drivers/cpufreq/powernow-k8.c
@@ -54,6 +54,9 @@ static DEFINE_PER_CPU(struct powernow_k8_data *, powernow_data);
static int cpu_family = CPU_OPTERON;
+/* array to map SW pstate number to acpi state */
+static u32 ps_to_as[8];
+
/* core performance boost */
static bool cpb_capable, cpb_enabled;
static struct msr __percpu *msrs;
@@ -80,9 +83,9 @@ static u32 find_khz_freq_from_fid(u32 fid)
}
static u32 find_khz_freq_from_pstate(struct cpufreq_frequency_table *data,
- u32 pstate)
+ u32 pstate)
{
- return data[pstate].frequency;
+ return data[ps_to_as[pstate]].frequency;
}
/* Return the vco fid for an input fid
@@ -926,6 +929,9 @@ static int fill_powernow_table_pstate(struct powernow_k8_data *data,
invalidate_entry(powernow_table, i);
continue;
}
+
+ ps_to_as[index] = i;
+
/* Frequency may be rounded for these */
if ((boot_cpu_data.x86 == 0x10 && boot_cpu_data.x86_model < 10)
|| boot_cpu_data.x86 == 0x11) {
@@ -1190,7 +1196,8 @@ static int powernowk8_target(struct cpufreq_policy *pol,
powernow_k8_acpi_pst_values(data, newstate);
if (cpu_family == CPU_HW_PSTATE)
- ret = transition_frequency_pstate(data, newstate);
+ ret = transition_frequency_pstate(data,
+ data->powernow_table[newstate].index);
else
ret = transition_frequency_fidvid(data, newstate);
if (ret) {
@@ -1203,7 +1210,7 @@ static int powernowk8_target(struct cpufreq_policy *pol,
if (cpu_family == CPU_HW_PSTATE)
pol->cur = find_khz_freq_from_pstate(data->powernow_table,
- newstate);
+ data->powernow_table[newstate].index);
else
pol->cur = find_khz_freq_from_fid(data->currfid);
ret = 0;
--
1.7.8.1
^ permalink raw reply related [flat|nested] 9+ messages in thread
* [PATCH 3/3] powernow-k8: Update copyright, maintainer and documentation information
2012-01-06 14:55 ` Andreas Herrmann
@ 2012-01-06 14:59 ` Andreas Herrmann
-1 siblings, 0 replies; 9+ messages in thread
From: Andreas Herrmann @ 2012-01-06 14:59 UTC (permalink / raw)
To: Dave Jones; +Cc: cpufreq, linux-kernel
Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com>
---
drivers/cpufreq/powernow-k8.c | 17 ++++++++++-------
1 files changed, 10 insertions(+), 7 deletions(-)
diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c
index ad683ec..8f9b2ce 100644
--- a/drivers/cpufreq/powernow-k8.c
+++ b/drivers/cpufreq/powernow-k8.c
@@ -1,10 +1,11 @@
/*
- * (c) 2003-2010 Advanced Micro Devices, Inc.
+ * (c) 2003-2012 Advanced Micro Devices, Inc.
* Your use of this code is subject to the terms and conditions of the
* GNU general public license version 2. See "COPYING" or
* http://www.gnu.org/licenses/gpl.html
*
- * Support : mark.langsdorf@amd.com
+ * Maintainer:
+ * Andreas Herrmann <andreas.herrmann3@amd.com>
*
* Based on the powernow-k7.c module written by Dave Jones.
* (C) 2003 Dave Jones on behalf of SuSE Labs
@@ -16,12 +17,14 @@
* Valuable input gratefully received from Dave Jones, Pavel Machek,
* Dominik Brodowski, Jacob Shin, and others.
* Originally developed by Paul Devriendt.
- * Processor information obtained from Chapter 9 (Power and Thermal Management)
- * of the "BIOS and Kernel Developer's Guide for the AMD Athlon 64 and AMD
- * Opteron Processors" available for download from www.amd.com
*
- * Tables for specific CPUs can be inferred from
- * http://www.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/30430.pdf
+ * Processor information obtained from Chapter 9 (Power and Thermal
+ * Management) of the "BIOS and Kernel Developer's Guide (BKDG) for
+ * the AMD Athlon 64 and AMD Opteron Processors" and section "2.x
+ * Power Management" in BKDGs for newer AMD CPU families.
+ *
+ * Tables for specific CPUs can be inferred from AMD's processor
+ * power and thermal data sheets, (e.g. 30417.pdf, 30430.pdf, 43375.pdf)
*/
#include <linux/kernel.h>
--
1.7.8.1
^ permalink raw reply related [flat|nested] 9+ messages in thread
* [PATCH 3/3] powernow-k8: Update copyright, maintainer and documentation information
@ 2012-01-06 14:59 ` Andreas Herrmann
0 siblings, 0 replies; 9+ messages in thread
From: Andreas Herrmann @ 2012-01-06 14:59 UTC (permalink / raw)
To: Dave Jones; +Cc: cpufreq, linux-kernel
Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com>
---
drivers/cpufreq/powernow-k8.c | 17 ++++++++++-------
1 files changed, 10 insertions(+), 7 deletions(-)
diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c
index ad683ec..8f9b2ce 100644
--- a/drivers/cpufreq/powernow-k8.c
+++ b/drivers/cpufreq/powernow-k8.c
@@ -1,10 +1,11 @@
/*
- * (c) 2003-2010 Advanced Micro Devices, Inc.
+ * (c) 2003-2012 Advanced Micro Devices, Inc.
* Your use of this code is subject to the terms and conditions of the
* GNU general public license version 2. See "COPYING" or
* http://www.gnu.org/licenses/gpl.html
*
- * Support : mark.langsdorf@amd.com
+ * Maintainer:
+ * Andreas Herrmann <andreas.herrmann3@amd.com>
*
* Based on the powernow-k7.c module written by Dave Jones.
* (C) 2003 Dave Jones on behalf of SuSE Labs
@@ -16,12 +17,14 @@
* Valuable input gratefully received from Dave Jones, Pavel Machek,
* Dominik Brodowski, Jacob Shin, and others.
* Originally developed by Paul Devriendt.
- * Processor information obtained from Chapter 9 (Power and Thermal Management)
- * of the "BIOS and Kernel Developer's Guide for the AMD Athlon 64 and AMD
- * Opteron Processors" available for download from www.amd.com
*
- * Tables for specific CPUs can be inferred from
- * http://www.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/30430.pdf
+ * Processor information obtained from Chapter 9 (Power and Thermal
+ * Management) of the "BIOS and Kernel Developer's Guide (BKDG) for
+ * the AMD Athlon 64 and AMD Opteron Processors" and section "2.x
+ * Power Management" in BKDGs for newer AMD CPU families.
+ *
+ * Tables for specific CPUs can be inferred from AMD's processor
+ * power and thermal data sheets, (e.g. 30417.pdf, 30430.pdf, 43375.pdf)
*/
#include <linux/kernel.h>
--
1.7.8.1
^ permalink raw reply related [flat|nested] 9+ messages in thread
* Re: [PATCH 3/3] powernow-k8: Update copyright, maintainer and documentation information
2012-01-06 14:59 ` Andreas Herrmann
(?)
@ 2012-01-06 16:15 ` Mark Langsdorf
-1 siblings, 0 replies; 9+ messages in thread
From: Mark Langsdorf @ 2012-01-06 16:15 UTC (permalink / raw)
To: Andreas Herrmann
Cc: Dave Jones, cpufreq@vger.kernel.org, linux-kernel@vger.kernel.org
On 01/06/2012 08:59 AM, Andreas Herrmann wrote:
>
> Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com>
> ---
> drivers/cpufreq/powernow-k8.c | 17 ++++++++++-------
> 1 files changed, 10 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c
> index ad683ec..8f9b2ce 100644
> --- a/drivers/cpufreq/powernow-k8.c
> +++ b/drivers/cpufreq/powernow-k8.c
> @@ -1,10 +1,11 @@
> /*
> - * (c) 2003-2010 Advanced Micro Devices, Inc.
> + * (c) 2003-2012 Advanced Micro Devices, Inc.
> * Your use of this code is subject to the terms and conditions of the
> * GNU general public license version 2. See "COPYING" or
> * http://www.gnu.org/licenses/gpl.html
> *
> - * Support : mark.langsdorf@amd.com
> + * Maintainer:
> + * Andreas Herrmann <andreas.herrmann3@amd.com>
> *
> * Based on the powernow-k7.c module written by Dave Jones.
> * (C) 2003 Dave Jones on behalf of SuSE Labs
> @@ -16,12 +17,14 @@
> * Valuable input gratefully received from Dave Jones, Pavel Machek,
> * Dominik Brodowski, Jacob Shin, and others.
> * Originally developed by Paul Devriendt.
> - * Processor information obtained from Chapter 9 (Power and Thermal Management)
> - * of the "BIOS and Kernel Developer's Guide for the AMD Athlon 64 and AMD
> - * Opteron Processors" available for download from www.amd.com
> *
> - * Tables for specific CPUs can be inferred from
> - * http://www.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/30430.pdf
> + * Processor information obtained from Chapter 9 (Power and Thermal
> + * Management) of the "BIOS and Kernel Developer's Guide (BKDG) for
> + * the AMD Athlon 64 and AMD Opteron Processors" and section "2.x
> + * Power Management" in BKDGs for newer AMD CPU families.
> + *
> + * Tables for specific CPUs can be inferred from AMD's processor
> + * power and thermal data sheets, (e.g. 30417.pdf, 30430.pdf, 43375.pdf)
> */
>
> #include <linux/kernel.h>
Acked-by: Mark Langsdorf <mark.langsdorf@calxeda.com>
formerly mark.langsdorf@amd.com
^ permalink raw reply [flat|nested] 9+ messages in thread