cpufreq: powernv: Set the cpus to nominal frequency during reboot/kexec

This patch ensures the cpus to kexec/reboot at nominal frequency.
Nominal frequency is the highest cpu frequency on PowerPC at
which the cores can run without getting throttled.

If the host kernel had set the cpus to a low pstate and then it
kexecs/reboots to a cpufreq disabled kernel it would cause the target
kernel to perform poorly. It will also increase the boot up time of
the target kernel. So set the cpus to high pstate, in this case to
nominal frequency before rebooting to avoid such scenarios.

The reboot notifier will set the cpus to nominal frequncy.

Signed-off-by: Shilpasri G Bhat <shilpa.bhat@linux.vnet.ibm.com>
Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

1 files changed, 35 insertions, 0 deletions

diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c
index 5a628f1e2cdf..2dfd4fdb5a52 100644
--- a/drivers/cpufreq/powernv-cpufreq.c
+++ b/drivers/cpufreq/powernv-cpufreq.c
@@ -26,6 +26,7 @@
 #include <linux/cpufreq.h>
 #include <linux/smp.h>
 #include <linux/of.h>
+#include <linux/reboot.h>
 
 #include <asm/cputhreads.h>
 #include <asm/firmware.h>
@@ -35,6 +36,7 @@
 #define POWERNV_MAX_PSTATES	256
 
 static struct cpufreq_frequency_table powernv_freqs[POWERNV_MAX_PSTATES+1];
+static bool rebooting;
 
 /*
  * Note: The set of pstates consists of contiguous integers, the
@@ -284,6 +286,15 @@ static void set_pstate(void *freq_data)
 }
 
 /*
+ * get_nominal_index: Returns the index corresponding to the nominal
+ * pstate in the cpufreq table
+ */
+static inline unsigned int get_nominal_index(void)
+{
+	return powernv_pstate_info.max - powernv_pstate_info.nominal;
+}
+
+/*
  * 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
@@ -293,6 +304,9 @@ static int powernv_cpufreq_target_index(struct cpufreq_policy *policy,
 {
 	struct powernv_smp_call_data freq_data;
 
+	if (unlikely(rebooting) && new_index != get_nominal_index())
+		return 0;
+
 	freq_data.pstate_id = powernv_freqs[new_index].driver_data;
 
 	/*
@@ -317,6 +331,25 @@ static int powernv_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	return cpufreq_table_validate_and_show(policy, powernv_freqs);
 }
 
+static int powernv_cpufreq_reboot_notifier(struct notifier_block *nb,
+				unsigned long action, void *unused)
+{
+	int cpu;
+	struct cpufreq_policy cpu_policy;
+
+	rebooting = true;
+	for_each_online_cpu(cpu) {
+		cpufreq_get_policy(&cpu_policy, cpu);
+		powernv_cpufreq_target_index(&cpu_policy, get_nominal_index());
+	}
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block powernv_cpufreq_reboot_nb = {
+	.notifier_call = powernv_cpufreq_reboot_notifier,
+};
+
 static void powernv_cpufreq_stop_cpu(struct cpufreq_policy *policy)
 {
 	struct powernv_smp_call_data freq_data;
@@ -351,12 +384,14 @@ static int __init powernv_cpufreq_init(void)
 		return rc;
 	}
 
+	register_reboot_notifier(&powernv_cpufreq_reboot_nb);
 	return cpufreq_register_driver(&powernv_cpufreq_driver);
 }
 module_init(powernv_cpufreq_init);
 
 static void __exit powernv_cpufreq_exit(void)
 {
+	unregister_reboot_notifier(&powernv_cpufreq_reboot_nb);
 	cpufreq_unregister_driver(&powernv_cpufreq_driver);
 }
 module_exit(powernv_cpufreq_exit);