cpufreq: powernv: cpufreq driver for powernv platform

Backend driver to dynamically set voltage and frequency on
IBM POWER non-virtualized platforms.  Power management SPRs
are used to set the required PState.

This driver works in conjunction with cpufreq governors
like 'ondemand' to provide a demand based frequency and
voltage setting on IBM POWER non-virtualized platforms.

PState table is obtained from OPAL v3 firmware through device
tree.

powernv_cpufreq back-end driver would parse the relevant device-tree
nodes and initialise the cpufreq subsystem on powernv platform.

The code was originally written by svaidy@linux.vnet.ibm.com. Over
time it was modified to accomodate bug-fixes as well as updates to the
the cpu-freq core. Relevant portions of the change logs corresponding
to those modifications are noted below:

 * The policy->cpus needs to be populated in a hotplug-invariant
   manner instead of using cpu_sibling_mask() which varies with
   cpu-hotplug. This is because the cpufreq core code copies this
   content into policy->related_cpus mask which should not vary on
   cpu-hotplug. [Authored by srivatsa.bhat@linux.vnet.ibm.com]

 * Create a helper routine that can return the cpu-frequency for the
   corresponding pstate_id. Also, cache the values of the pstate_max,
   pstate_min and pstate_nominal and nr_pstates in a static structure
   so that they can be reused in the future to perform any
   validations. [Authored by ego@linux.vnet.ibm.com]

 * Create a driver attribute named cpuinfo_nominal_freq which creates
   a sysfs read-only file named cpuinfo_nominal_freq. Export the
   frequency corresponding to the nominal_pstate through this
   interface.

     Nominal frequency is the highest non-turbo frequency for the
   platform.  This is generally used for setting governor policies
   from user space for optimal energy efficiency. [Authored by
   ego@linux.vnet.ibm.com]

 * Implement a powernv_cpufreq_get(unsigned int cpu) method which will
   return the current operating frequency. Export this via the sysfs
   interface cpuinfo_cur_freq by setting powernv_cpufreq_driver.get to
   powernv_cpufreq_get(). [Authored by ego@linux.vnet.ibm.com]

[Change log updated by ego@linux.vnet.ibm.com]

Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

3 files changed, 351 insertions, 0 deletions

diff --git a/drivers/cpufreq/Kconfig.powerpc b/drivers/cpufreq/Kconfig.powerpc
index ca0021a96e19..72564b701b4a 100644
--- a/drivers/cpufreq/Kconfig.powerpc
+++ b/drivers/cpufreq/Kconfig.powerpc
@@ -54,3 +54,11 @@ config PPC_PASEMI_CPUFREQ
 	help
 	  This adds the support for frequency switching on PA Semi
 	  PWRficient processors.
+
+config POWERNV_CPUFREQ
+       tristate "CPU frequency scaling for IBM POWERNV platform"
+       depends on PPC_POWERNV
+       default y
+       help
+	 This adds support for CPU frequency switching on IBM POWERNV
+	 platform
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index 74945652dd7a..0dbb963c1aef 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -86,6 +86,7 @@ obj-$(CONFIG_PPC_CORENET_CPUFREQ)   += ppc-corenet-cpufreq.o
 obj-$(CONFIG_CPU_FREQ_PMAC)		+= pmac32-cpufreq.o
 obj-$(CONFIG_CPU_FREQ_PMAC64)		+= pmac64-cpufreq.o
 obj-$(CONFIG_PPC_PASEMI_CPUFREQ)	+= pasemi-cpufreq.o
+obj-$(CONFIG_POWERNV_CPUFREQ)		+= powernv-cpufreq.o
 
 ##################################################################################
 # Other platform drivers
diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c
new file mode 100644
index 000000000000..e1e519703dfe
--- /dev/null
+++ b/drivers/cpufreq/powernv-cpufreq.c
@@ -0,0 +1,342 @@
+/*
+ * POWERNV cpufreq driver for the IBM POWER processors
+ *
+ * (C) Copyright IBM 2014
+ *
+ * Author: Vaidyanathan Srinivasan <svaidy at linux.vnet.ibm.com>
+ *
+ * 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, or (at your option)
+ * any later version.
+ *
+ * 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.
+ *
+ */
+
+#define pr_fmt(fmt)	"powernv-cpufreq: " fmt
+
+#include <linux/kernel.h>
+#include <linux/sysfs.h>
+#include <linux/cpumask.h>
+#include <linux/module.h>
+#include <linux/cpufreq.h>
+#include <linux/smp.h>
+#include <linux/of.h>
+
+#include <asm/cputhreads.h>
+#include <asm/reg.h>
+
+#define POWERNV_MAX_PSTATES	256
+
+static struct cpufreq_frequency_table powernv_freqs[POWERNV_MAX_PSTATES+1];
+static int powernv_pstate_ids[POWERNV_MAX_PSTATES+1];
+
+/*
+ * Note: The set of pstates consists of contiguous integers, the
+ * smallest of which is indicated by powernv_pstate_info.min, the
+ * largest of which is indicated by powernv_pstate_info.max.
+ *
+ * The nominal pstate is the highest non-turbo pstate in this
+ * platform. This is indicated by powernv_pstate_info.nominal.
+ */
+static struct powernv_pstate_info {
+	int min;
+	int max;
+	int nominal;
+	int nr_pstates;
+} powernv_pstate_info;
+
+/*
+ * Initialize the freq table based on data obtained
+ * from the firmware passed via device-tree
+ */
+static int init_powernv_pstates(void)
+{
+	struct device_node *power_mgt;
+	int i, pstate_min, pstate_max, pstate_nominal, nr_pstates = 0;
+	const __be32 *pstate_ids, *pstate_freqs;
+	u32 len_ids, len_freqs;
+
+	power_mgt = of_find_node_by_path("/ibm,opal/power-mgt");
+	if (!power_mgt) {
+		pr_warn("power-mgt node not found\n");
+		return -ENODEV;
+	}
+
+	if (of_property_read_u32(power_mgt, "ibm,pstate-min", &pstate_min)) {
+		pr_warn("ibm,pstate-min node not found\n");
+		return -ENODEV;
+	}
+
+	if (of_property_read_u32(power_mgt, "ibm,pstate-max", &pstate_max)) {
+		pr_warn("ibm,pstate-max node not found\n");
+		return -ENODEV;
+	}
+
+	if (of_property_read_u32(power_mgt, "ibm,pstate-nominal",
+				 &pstate_nominal)) {
+		pr_warn("ibm,pstate-nominal not found\n");
+		return -ENODEV;
+	}
+	pr_info("cpufreq pstate min %d nominal %d max %d\n", pstate_min,
+		pstate_nominal, pstate_max);
+
+	pstate_ids = of_get_property(power_mgt, "ibm,pstate-ids", &len_ids);
+	if (!pstate_ids) {
+		pr_warn("ibm,pstate-ids not found\n");
+		return -ENODEV;
+	}
+
+	pstate_freqs = of_get_property(power_mgt, "ibm,pstate-frequencies-mhz",
+				      &len_freqs);
+	if (!pstate_freqs) {
+		pr_warn("ibm,pstate-frequencies-mhz not found\n");
+		return -ENODEV;
+	}
+
+	WARN_ON(len_ids != len_freqs);
+	nr_pstates = min(len_ids, len_freqs) / sizeof(u32);
+	if (!nr_pstates) {
+		pr_warn("No PStates found\n");
+		return -ENODEV;
+	}
+
+	pr_debug("NR PStates %d\n", nr_pstates);
+	for (i = 0; i < nr_pstates; i++) {
+		u32 id = be32_to_cpu(pstate_ids[i]);
+		u32 freq = be32_to_cpu(pstate_freqs[i]);
+
+		pr_debug("PState id %d freq %d MHz\n", id, freq);
+		powernv_freqs[i].frequency = freq * 1000; /* kHz */
+		powernv_pstate_ids[i] = id;
+	}
+	/* End of list marker entry */
+	powernv_freqs[i].frequency = CPUFREQ_TABLE_END;
+
+	powernv_pstate_info.min = pstate_min;
+	powernv_pstate_info.max = pstate_max;
+	powernv_pstate_info.nominal = pstate_nominal;
+	powernv_pstate_info.nr_pstates = nr_pstates;
+
+	return 0;
+}
+
+/* Returns the CPU frequency corresponding to the pstate_id. */
+static unsigned int pstate_id_to_freq(int pstate_id)
+{
+	int i;
+
+	i = powernv_pstate_info.max - pstate_id;
+	BUG_ON(i >= powernv_pstate_info.nr_pstates || i < 0);
+
+	return powernv_freqs[i].frequency;
+}
+
+/*
+ * cpuinfo_nominal_freq_show - Show the nominal CPU frequency as indicated by
+ * the firmware
+ */
+static ssize_t cpuinfo_nominal_freq_show(struct cpufreq_policy *policy,
+					char *buf)
+{
+	return sprintf(buf, "%u\n",
+		pstate_id_to_freq(powernv_pstate_info.nominal));
+}
+
+struct freq_attr cpufreq_freq_attr_cpuinfo_nominal_freq =
+	__ATTR_RO(cpuinfo_nominal_freq);
+
+static struct freq_attr *powernv_cpu_freq_attr[] = {
+	&cpufreq_freq_attr_scaling_available_freqs,
+	&cpufreq_freq_attr_cpuinfo_nominal_freq,
+	NULL,
+};
+
+/* Helper routines */
+
+/* Access helpers to power mgt SPR */
+
+static inline unsigned long get_pmspr(unsigned long sprn)
+{
+	switch (sprn) {
+	case SPRN_PMCR:
+		return mfspr(SPRN_PMCR);
+
+	case SPRN_PMICR:
+		return mfspr(SPRN_PMICR);
+
+	case SPRN_PMSR:
+		return mfspr(SPRN_PMSR);
+	}
+	BUG();
+}
+
+static inline void set_pmspr(unsigned long sprn, unsigned long val)
+{
+	switch (sprn) {
+	case SPRN_PMCR:
+		mtspr(SPRN_PMCR, val);
+		return;
+
+	case SPRN_PMICR:
+		mtspr(SPRN_PMICR, val);
+		return;
+	}
+	BUG();
+}
+
+/*
+ * Use objects of this type to query/update
+ * pstates on a remote CPU via smp_call_function.
+ */
+struct powernv_smp_call_data {
+	unsigned int freq;
+	int pstate_id;
+};
+
+/*
+ * powernv_read_cpu_freq: Reads the current frequency on this CPU.
+ *
+ * Called via smp_call_function.
+ *
+ * Note: The caller of the smp_call_function should pass an argument of
+ * the type 'struct powernv_smp_call_data *' along with this function.
+ *
+ * The current frequency on this CPU will be returned via
+ * ((struct powernv_smp_call_data *)arg)->freq;
+ */
+static void powernv_read_cpu_freq(void *arg)
+{
+	unsigned long pmspr_val;
+	s8 local_pstate_id;
+	struct powernv_smp_call_data *freq_data = arg;
+
+	pmspr_val = get_pmspr(SPRN_PMSR);
+
+	/*
+	 * The local pstate id corresponds bits 48..55 in the PMSR.
+	 * Note: Watch out for the sign!
+	 */
+	local_pstate_id = (pmspr_val >> 48) & 0xFF;
+	freq_data->pstate_id = local_pstate_id;
+	freq_data->freq = pstate_id_to_freq(freq_data->pstate_id);
+
+	pr_debug("cpu %d pmsr %016lX pstate_id %d frequency %d kHz\n",
+		raw_smp_processor_id(), pmspr_val, freq_data->pstate_id,
+		freq_data->freq);
+}
+
+/*
+ * powernv_cpufreq_get: Returns the CPU frequency as reported by the
+ * firmware for CPU 'cpu'. This value is reported through the sysfs
+ * file cpuinfo_cur_freq.
+ */
+unsigned int powernv_cpufreq_get(unsigned int cpu)
+{
+	struct powernv_smp_call_data freq_data;
+
+	smp_call_function_any(cpu_sibling_mask(cpu), powernv_read_cpu_freq,
+			&freq_data, 1);
+
+	return freq_data.freq;
+}
+
+/*
+ * set_pstate: Sets the pstate on this CPU.
+ *
+ * This is called via an smp_call_function.
+ *
+ * The caller must ensure that freq_data is of the type
+ * (struct powernv_smp_call_data *) and the pstate_id which needs to be set
+ * on this CPU should be present in freq_data->pstate_id.
+ */
+static void set_pstate(void *freq_data)
+{
+	unsigned long val;
+	unsigned long pstate_ul =
+		((struct powernv_smp_call_data *) freq_data)->pstate_id;
+
+	val = get_pmspr(SPRN_PMCR);
+	val = val & 0x0000FFFFFFFFFFFFULL;
+
+	pstate_ul = pstate_ul & 0xFF;
+
+	/* Set both global(bits 56..63) and local(bits 48..55) PStates */
+	val = val | (pstate_ul << 56) | (pstate_ul << 48);
+
+	pr_debug("Setting cpu %d pmcr to %016lX\n",
+			raw_smp_processor_id(), val);
+	set_pmspr(SPRN_PMCR, val);
+}
+
+/*
+ * powernv_cpufreq_target_index: Sets the frequency corresponding to
+ * the cpufreq table entry indexed by new_index on the cpus in the
+ * mask policy->cpus
+ */
+static int powernv_cpufreq_target_index(struct cpufreq_policy *policy,
+					unsigned int new_index)
+{
+	struct powernv_smp_call_data freq_data;
+
+	freq_data.pstate_id = powernv_pstate_ids[new_index];
+
+	/*
+	 * Use smp_call_function to send IPI and execute the
+	 * mtspr on target CPU.  We could do that without IPI
+	 * if current CPU is within policy->cpus (core)
+	 */
+	smp_call_function_any(policy->cpus, set_pstate, &freq_data, 1);
+
+	return 0;
+}
+
+static int powernv_cpufreq_cpu_init(struct cpufreq_policy *policy)
+{
+	int base, i;
+
+	base = cpu_first_thread_sibling(policy->cpu);
+
+	for (i = 0; i < threads_per_core; i++)
+		cpumask_set_cpu(base + i, policy->cpus);
+
+	return cpufreq_table_validate_and_show(policy, powernv_freqs);
+}
+
+static struct cpufreq_driver powernv_cpufreq_driver = {
+	.name		= "powernv-cpufreq",
+	.flags		= CPUFREQ_CONST_LOOPS,
+	.init		= powernv_cpufreq_cpu_init,
+	.verify		= cpufreq_generic_frequency_table_verify,
+	.target_index	= powernv_cpufreq_target_index,
+	.get		= powernv_cpufreq_get,
+	.attr		= powernv_cpu_freq_attr,
+};
+
+static int __init powernv_cpufreq_init(void)
+{
+	int rc = 0;
+
+	/* Discover pstates from device tree and init */
+	rc = init_powernv_pstates();
+	if (rc) {
+		pr_info("powernv-cpufreq disabled. System does not support PState control\n");
+		return rc;
+	}
+
+	return cpufreq_register_driver(&powernv_cpufreq_driver);
+}
+module_init(powernv_cpufreq_init);
+
+static void __exit powernv_cpufreq_exit(void)
+{
+	cpufreq_unregister_driver(&powernv_cpufreq_driver);
+}
+module_exit(powernv_cpufreq_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Vaidyanathan Srinivasan <svaidy at linux.vnet.ibm.com>");