diff mbox

[v3] cpufreq: Add sfi based cpufreq driver support

Message ID 20141017054353.GA515@intel-desktop (mailing list archive)
State Not Applicable, archived
Headers show

Commit Message

Kasagar, Srinidhi Oct. 17, 2014, 5:44 a.m. UTC
This adds the sfi based cpu freq driver for some of the
Intel's Silver Mont based atom architectures like
Merrifield and Moorfield (intel-mid)

Signed-off-by: Rudramuni, Vishwesh M <vishwesh.m.rudramuni@intel.com>
Signed-off-by: Srinidhi Kasagar <srinidhi.kasagar@intel.com>
---
v2:
* rephrase the Kconfig text
* merge the header file as its not being shared with anyone
* remove the unnecessary checks in sfi_cpufreq_target
* style changes in kzalloc
* fix the potential memory leak sfi_cpufreq_cpu_init
* move the cpufreq driver flag to the structure definition
* remove the redundant init of policy->cpu and policy->cur
* remove the unnecessary check while init the freq table
* merge the for loops in cpu_init
* use cpufreq_generic_attr rather than the custom one

v3:
* Add this change log
* remove the left over not used cached_freq var
* merge yet another for loop in cpu_init

 drivers/cpufreq/Kconfig.x86   |   10 ++
 drivers/cpufreq/Makefile      |    1 +
 drivers/cpufreq/sfi-cpufreq.c |  326 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 337 insertions(+)
 create mode 100644 drivers/cpufreq/sfi-cpufreq.c

Comments

Viresh Kumar Oct. 17, 2014, 6:13 a.m. UTC | #1
On 17 October 2014 11:14, Srinidhi Kasagar <srinidhi.kasagar@intel.com> wrote:
> This adds the sfi based cpu freq driver for some of the
> Intel's Silver Mont based atom architectures like
> Merrifield and Moorfield (intel-mid)
>
> Signed-off-by: Rudramuni, Vishwesh M <vishwesh.m.rudramuni@intel.com>
> Signed-off-by: Srinidhi Kasagar <srinidhi.kasagar@intel.com>
> ---
> v2:
> * rephrase the Kconfig text
> * merge the header file as its not being shared with anyone
> * remove the unnecessary checks in sfi_cpufreq_target
> * style changes in kzalloc
> * fix the potential memory leak sfi_cpufreq_cpu_init
> * move the cpufreq driver flag to the structure definition
> * remove the redundant init of policy->cpu and policy->cur
> * remove the unnecessary check while init the freq table
> * merge the for loops in cpu_init
> * use cpufreq_generic_attr rather than the custom one
>
> v3:
> * Add this change log
> * remove the left over not used cached_freq var
> * merge yet another for loop in cpu_init
>
>  drivers/cpufreq/Kconfig.x86   |   10 ++
>  drivers/cpufreq/Makefile      |    1 +
>  drivers/cpufreq/sfi-cpufreq.c |  326 +++++++++++++++++++++++++++++++++++++++++
>  3 files changed, 337 insertions(+)
>  create mode 100644 drivers/cpufreq/sfi-cpufreq.c

From coding perspective:

Acked-by: Viresh Kumar <viresh.kumar@linaro.org>

From X86 working aspect would be good if Rafael or Dirk also
review it :)
--
To unsubscribe from this list: send the line "unsubscribe linux-pm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox

Patch

diff --git a/drivers/cpufreq/Kconfig.x86 b/drivers/cpufreq/Kconfig.x86
index 89ae88f91895..2bca6a5dcffd 100644
--- a/drivers/cpufreq/Kconfig.x86
+++ b/drivers/cpufreq/Kconfig.x86
@@ -57,6 +57,16 @@  config X86_ACPI_CPUFREQ_CPB
 	  By enabling this option the acpi_cpufreq driver provides the old
 	  entry in addition to the new boost ones, for compatibility reasons.
 
+config X86_SFI_CPUFREQ
+	tristate "SFI Processor P-States driver"
+	depends on X86_INTEL_MID && SFI
+	help
+	  This adds a CPUFreq driver for some Silver Mont based Intel
+	  Atom platforms (like INTEL_MID) which utilizes the SFI based
+	  processor performance states.
+
+	  If in doubt, say N.
+
 config ELAN_CPUFREQ
 	tristate "AMD Elan SC400 and SC410"
 	depends on MELAN
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index db6d9a2fea4d..c3b51efd4a85 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -41,6 +41,7 @@  obj-$(CONFIG_X86_P4_CLOCKMOD)		+= p4-clockmod.o
 obj-$(CONFIG_X86_CPUFREQ_NFORCE2)	+= cpufreq-nforce2.o
 obj-$(CONFIG_X86_INTEL_PSTATE)		+= intel_pstate.o
 obj-$(CONFIG_X86_AMD_FREQ_SENSITIVITY)	+= amd_freq_sensitivity.o
+obj-$(CONFIG_X86_SFI_CPUFREQ)		+= sfi-cpufreq.o
 
 ##################################################################################
 # ARM SoC drivers
diff --git a/drivers/cpufreq/sfi-cpufreq.c b/drivers/cpufreq/sfi-cpufreq.c
new file mode 100644
index 000000000000..a4e4ee1de114
--- /dev/null
+++ b/drivers/cpufreq/sfi-cpufreq.c
@@ -0,0 +1,326 @@ 
+/*
+ *  SFI Processor P-States Driver
+ *  Based on ACPI Processor P-States Driver
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ *  Author: Vishwesh M Rudramuni <vishwesh.m.rudramuni@intel.com>
+ *  Author: Srinidhi Kasagar <srinidhi.kasagar@intel.com>
+ */
+
+#include <linux/cpufreq.h>
+#include <linux/cpuidle.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sfi.h>
+#include <linux/slab.h>
+#include <linux/smp.h>
+
+#include <asm/msr.h>
+#include <asm/processor.h>
+
+#define SFI_FREQ_MAX		32
+#define INTEL_MSR_RANGE		0xffff
+#define INTEL_MSR_BUSRATIO_MASK	0xff00
+#define SFI_CPU_MAX		8
+
+static DEFINE_PER_CPU(struct sfi_cpufreq_data *, drv_data);
+static DEFINE_MUTEX(performance_mutex);
+static struct sfi_freq_table_entry sfi_cpufreq_array[SFI_FREQ_MAX];
+
+/* sfi_perf_data is a pointer to percpu data. */
+static struct sfi_processor_performance *sfi_perf_data;
+static struct cpufreq_driver sfi_cpufreq_driver;
+static int sfi_cpufreq_num;
+
+/* Performance management */
+struct sfi_processor_px {
+	u32 core_frequency;	/* megahertz */
+	u32 transition_latency;	/* microseconds */
+	u32 control;	/* control value */
+};
+
+struct sfi_processor_performance {
+	unsigned int state;
+	unsigned int state_count;
+	struct sfi_processor_px *states;
+};
+
+struct sfi_cpufreq_data {
+	struct sfi_processor_performance *sfi_data;
+	struct cpufreq_frequency_table *freq_table;
+};
+
+static int parse_freq(struct sfi_table_header *table)
+{
+	struct sfi_table_simple *sb;
+	struct sfi_freq_table_entry *pentry;
+	int total_len;
+
+	sb = (struct sfi_table_simple *)table;
+	if (!sb) {
+		pr_warn("SFI: Unable to map frequency table\n");
+		return -ENODEV;
+	}
+
+	if (!sfi_cpufreq_num) {
+		sfi_cpufreq_num = SFI_GET_NUM_ENTRIES(sb,
+			 struct sfi_freq_table_entry);
+		pentry = (struct sfi_freq_table_entry *)sb->pentry;
+		total_len = sfi_cpufreq_num * sizeof(*pentry);
+		memcpy(sfi_cpufreq_array, pentry, total_len);
+	}
+
+	return 0;
+}
+
+static int sfi_processor_get_performance_states(
+			struct sfi_processor_performance *performance)
+{
+	int result = 0;
+	int i;
+
+	performance->state_count = sfi_cpufreq_num;
+	performance->states =
+	    kmalloc(sizeof(struct sfi_processor_px) * sfi_cpufreq_num,
+		    GFP_KERNEL);
+	if (!performance->states)
+		result = -ENOMEM;
+
+	pr_info("Num p-states %d\n", sfi_cpufreq_num);
+
+	/* Populate the P-states info from the SFI table */
+	for (i = 0; i < sfi_cpufreq_num; i++) {
+		performance->states[i].core_frequency =
+			sfi_cpufreq_array[i].freq_mhz;
+		performance->states[i].transition_latency =
+			sfi_cpufreq_array[i].latency;
+		performance->states[i].control =
+			sfi_cpufreq_array[i].ctrl_val;
+		pr_info("State [%d]: core_frequency[%d] transition_latency[%d] control[0x%x]\n",
+			i,
+			(u32) performance->states[i].core_frequency,
+			(u32) performance->states[i].transition_latency,
+			(u32) performance->states[i].control);
+	}
+
+	return result;
+}
+
+static int sfi_processor_register_performance(
+			struct sfi_processor_performance *performance)
+{
+	mutex_lock(&performance_mutex);
+
+	/* parse the freq table from sfi */
+	sfi_cpufreq_num = 0;
+	sfi_table_parse(SFI_SIG_FREQ, NULL, NULL, parse_freq);
+
+	sfi_processor_get_performance_states(performance);
+
+	mutex_unlock(&performance_mutex);
+
+	return 0;
+}
+
+void sfi_processor_unregister_performance(
+			struct sfi_processor_performance *performance)
+{
+	mutex_lock(&performance_mutex);
+	kfree(performance->states);
+	mutex_unlock(&performance_mutex);
+}
+
+static unsigned extract_freq(u32 msr, unsigned int cpu)
+{
+	struct cpufreq_frequency_table *pos;
+	struct sfi_processor_performance *perf;
+	struct sfi_cpufreq_data *data = per_cpu(drv_data, cpu);
+	u32 sfi_ctrl;
+
+	msr &= INTEL_MSR_BUSRATIO_MASK;
+	perf = data->sfi_data;
+
+	cpufreq_for_each_entry(pos, data->freq_table) {
+		sfi_ctrl = perf->states[pos->driver_data].control
+			& INTEL_MSR_BUSRATIO_MASK;
+		if (sfi_ctrl == msr)
+			return pos->frequency;
+	}
+	return data->freq_table[0].frequency;
+}
+
+static u32 get_cur_val(const struct cpumask *mask)
+{
+	u32 val, dummy;
+
+	if (unlikely(cpumask_empty(mask)))
+		return 0;
+
+	rdmsr_on_cpu(cpumask_any(mask), MSR_IA32_PERF_STATUS, &val, &dummy);
+
+	return val;
+}
+
+static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
+{
+	pr_debug("get_cur_freq_on_cpu (%d)\n", cpu);
+
+	return extract_freq(get_cur_val(cpumask_of(cpu)), cpu);
+}
+
+static int sfi_cpufreq_target(struct cpufreq_policy *policy,
+				unsigned int index)
+{
+	struct sfi_cpufreq_data *data = per_cpu(drv_data, policy->cpu);
+	struct sfi_processor_performance *perf;
+	unsigned int next_perf_state = 0; /* Index into perf table */
+	u32 lo, hi;
+
+	perf = data->sfi_data;
+	next_perf_state = data->freq_table[index].driver_data;
+
+	rdmsr_on_cpu(policy->cpu, MSR_IA32_PERF_CTL, &lo, &hi);
+	lo = (lo & ~INTEL_MSR_RANGE) |
+		((u32) perf->states[next_perf_state].control & INTEL_MSR_RANGE);
+	wrmsr_on_cpu(policy->cpu, MSR_IA32_PERF_CTL, lo, hi);
+
+	perf->state = next_perf_state;
+
+	return 0;
+}
+
+static int sfi_cpufreq_cpu_init(struct cpufreq_policy *policy)
+{
+	unsigned int i, result = 0, valid_states = 0;
+	unsigned int cpu = policy->cpu;
+	struct sfi_cpufreq_data *data;
+	struct sfi_processor_performance *perf;
+
+	pr_debug("%s: CPU:%d\n", __func__, cpu);
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->sfi_data = per_cpu_ptr(sfi_perf_data, cpu);
+	per_cpu(drv_data, cpu) = data;
+
+	result = sfi_processor_register_performance(data->sfi_data);
+	if (result)
+		goto err_free;
+
+	perf = data->sfi_data;
+	policy->shared_type = CPUFREQ_SHARED_TYPE_HW;
+
+	/* capability check */
+	if (perf->state_count <= 1) {
+		pr_debug("No P-States\n");
+		result = -ENODEV;
+		goto err_unreg;
+	}
+
+	data->freq_table = kzalloc(sizeof(*data->freq_table) *
+				(perf->state_count+1), GFP_KERNEL);
+	if (!data->freq_table) {
+		result = -ENOMEM;
+		goto err_unreg;
+	}
+
+	policy->cpuinfo.transition_latency = 0;
+	for (i = 0; i < perf->state_count; i++) {
+		/* detect transition latency */
+		if ((perf->states[i].transition_latency * 1000) >
+		    policy->cpuinfo.transition_latency)
+			policy->cpuinfo.transition_latency =
+				perf->states[i].transition_latency * 1000;
+
+		/* initialize the freq table */
+		data->freq_table[valid_states].driver_data = i;
+		data->freq_table[valid_states].frequency =
+				perf->states[i].core_frequency * 1000;
+		valid_states++;
+
+		pr_debug("     %cP%d: %d MHz, %d uS\n",
+			(i == perf->state ? '*' : ' '), i,
+			(u32) perf->states[i].core_frequency,
+			(u32) perf->states[i].transition_latency);
+	}
+
+	data->freq_table[valid_states].frequency = CPUFREQ_TABLE_END;
+	perf->state = 0;
+
+	result = cpufreq_table_validate_and_show(policy, data->freq_table);
+	if (result)
+		goto err_freqfree;
+
+	pr_debug("CPU%u - SFI performance management activated.\n", cpu);
+
+	return result;
+
+err_freqfree:
+	kfree(data->freq_table);
+err_unreg:
+	sfi_processor_unregister_performance(perf);
+err_free:
+	kfree(data);
+	per_cpu(drv_data, cpu) = NULL;
+
+	return result;
+}
+
+static int sfi_cpufreq_cpu_exit(struct cpufreq_policy *policy)
+{
+	struct sfi_cpufreq_data *data = per_cpu(drv_data, policy->cpu);
+
+	pr_debug("sfi_cpufreq_cpu_exit\n");
+
+	per_cpu(drv_data, policy->cpu) = NULL;
+	sfi_processor_unregister_performance(data->sfi_data);
+	kfree(data->freq_table);
+	kfree(data);
+
+	return 0;
+}
+
+static struct cpufreq_driver sfi_cpufreq_driver = {
+	.flags		= CPUFREQ_CONST_LOOPS,
+	.get		= get_cur_freq_on_cpu,
+	.verify		= cpufreq_generic_frequency_table_verify,
+	.target_index	= sfi_cpufreq_target,
+	.init		= sfi_cpufreq_cpu_init,
+	.exit		= sfi_cpufreq_cpu_exit,
+	.name		= "sfi-cpufreq",
+	.attr		= cpufreq_generic_attr,
+};
+
+static int __init sfi_cpufreq_init(void)
+{
+	sfi_perf_data = alloc_percpu(struct sfi_processor_performance);
+	if (!sfi_perf_data) {
+		pr_err("Memory allocation error for sfi_perf_data.\n");
+		return -ENOMEM;
+	}
+
+	return cpufreq_register_driver(&sfi_cpufreq_driver);
+}
+late_initcall(sfi_cpufreq_init);
+
+static void __exit sfi_cpufreq_exit(void)
+{
+	cpufreq_unregister_driver(&sfi_cpufreq_driver);
+	free_percpu(sfi_perf_data);
+}
+module_exit(sfi_cpufreq_exit);
+
+MODULE_AUTHOR("Vishwesh M Rudramuni <vishwesh.m.rudramuni@intel.com>");
+MODULE_DESCRIPTION("SFI P-States Driver");
+MODULE_LICENSE("GPL");