3 files changed, 56 insertions, 12 deletions

diff --git a/kernel/drivers/cpufreq/cpufreq_userspace.c b/kernel/drivers/cpufreq/cpufreq_userspace.c
index 4dbf1db16..9cc8abd3d 100644
--- a/kernel/drivers/cpufreq/cpufreq_userspace.c
+++ b/kernel/drivers/cpufreq/cpufreq_userspace.c
@@ -17,6 +17,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/slab.h>
 
 static DEFINE_PER_CPU(unsigned int, cpu_is_managed);
 static DEFINE_MUTEX(userspace_mutex);
@@ -31,6 +32,7 @@ static DEFINE_MUTEX(userspace_mutex);
 static int cpufreq_set(struct cpufreq_policy *policy, unsigned int freq)
 {
 	int ret = -EINVAL;
+	unsigned int *setspeed = policy->governor_data;
 
 	pr_debug("cpufreq_set for cpu %u, freq %u kHz\n", policy->cpu, freq);
 
@@ -38,6 +40,8 @@ static int cpufreq_set(struct cpufreq_policy *policy, unsigned int freq)
 	if (!per_cpu(cpu_is_managed, policy->cpu))
 		goto err;
 
+	*setspeed = freq;
+
 	ret = __cpufreq_driver_target(policy, freq, CPUFREQ_RELATION_L);
  err:
 	mutex_unlock(&userspace_mutex);
@@ -49,19 +53,45 @@ static ssize_t show_speed(struct cpufreq_policy *policy, char *buf)
 	return sprintf(buf, "%u\n", policy->cur);
 }
 
+static int cpufreq_userspace_policy_init(struct cpufreq_policy *policy)
+{
+	unsigned int *setspeed;
+
+	setspeed = kzalloc(sizeof(*setspeed), GFP_KERNEL);
+	if (!setspeed)
+		return -ENOMEM;
+
+	policy->governor_data = setspeed;
+	return 0;
+}
+
 static int cpufreq_governor_userspace(struct cpufreq_policy *policy,
 				   unsigned int event)
 {
+	unsigned int *setspeed = policy->governor_data;
 	unsigned int cpu = policy->cpu;
 	int rc = 0;
 
+	if (event == CPUFREQ_GOV_POLICY_INIT)
+		return cpufreq_userspace_policy_init(policy);
+
+	if (!setspeed)
+		return -EINVAL;
+
 	switch (event) {
+	case CPUFREQ_GOV_POLICY_EXIT:
+		mutex_lock(&userspace_mutex);
+		policy->governor_data = NULL;
+		kfree(setspeed);
+		mutex_unlock(&userspace_mutex);
+		break;
 	case CPUFREQ_GOV_START:
 		BUG_ON(!policy->cur);
 		pr_debug("started managing cpu %u\n", cpu);
 
 		mutex_lock(&userspace_mutex);
 		per_cpu(cpu_is_managed, cpu) = 1;
+		*setspeed = policy->cur;
 		mutex_unlock(&userspace_mutex);
 		break;
 	case CPUFREQ_GOV_STOP:
@@ -69,20 +99,23 @@ static int cpufreq_governor_userspace(struct cpufreq_policy *policy,
 
 		mutex_lock(&userspace_mutex);
 		per_cpu(cpu_is_managed, cpu) = 0;
+		*setspeed = 0;
 		mutex_unlock(&userspace_mutex);
 		break;
 	case CPUFREQ_GOV_LIMITS:
 		mutex_lock(&userspace_mutex);
-		pr_debug("limit event for cpu %u: %u - %u kHz, currently %u kHz\n",
-			cpu, policy->min, policy->max,
-			policy->cur);
+		pr_debug("limit event for cpu %u: %u - %u kHz, currently %u kHz, last set to %u kHz\n",
+			cpu, policy->min, policy->max, policy->cur, *setspeed);
 
-		if (policy->max < policy->cur)
+		if (policy->max < *setspeed)
 			__cpufreq_driver_target(policy, policy->max,
 						CPUFREQ_RELATION_H);
-		else if (policy->min > policy->cur)
+		else if (policy->min > *setspeed)
 			__cpufreq_driver_target(policy, policy->min,
 						CPUFREQ_RELATION_L);
+		else
+			__cpufreq_driver_target(policy, *setspeed,
+						CPUFREQ_RELATION_L);
 		mutex_unlock(&userspace_mutex);
 		break;
 	}
diff --git a/kernel/drivers/cpufreq/intel_pstate.c b/kernel/drivers/cpufreq/intel_pstate.c
index 98fb88213..7ff8b15a3 100644
--- a/kernel/drivers/cpufreq/intel_pstate.c
+++ b/kernel/drivers/cpufreq/intel_pstate.c
@@ -285,14 +285,14 @@ static void intel_pstate_hwp_set(void)
 	int min, hw_min, max, hw_max, cpu, range, adj_range;
 	u64 value, cap;
 
-	rdmsrl(MSR_HWP_CAPABILITIES, cap);
-	hw_min = HWP_LOWEST_PERF(cap);
-	hw_max = HWP_HIGHEST_PERF(cap);
-	range = hw_max - hw_min;
-
 	get_online_cpus();
 
 	for_each_online_cpu(cpu) {
+		rdmsrl_on_cpu(cpu, MSR_HWP_CAPABILITIES, &cap);
+		hw_min = HWP_LOWEST_PERF(cap);
+		hw_max = HWP_HIGHEST_PERF(cap);
+		range = hw_max - hw_min;
+
 		rdmsrl_on_cpu(cpu, MSR_HWP_REQUEST, &value);
 		adj_range = limits->min_perf_pct * range / 100;
 		min = hw_min + adj_range;
@@ -662,11 +662,16 @@ static int core_get_max_pstate(void)
 			if (err)
 				goto skip_tar;
 
-			tdp_msr = MSR_CONFIG_TDP_NOMINAL + tdp_ctrl;
+			tdp_msr = MSR_CONFIG_TDP_NOMINAL + (tdp_ctrl & 0x3);
 			err = rdmsrl_safe(tdp_msr, &tdp_ratio);
 			if (err)
 				goto skip_tar;
 
+			/* For level 1 and 2, bits[23:16] contain the ratio */
+			if (tdp_ctrl)
+				tdp_ratio >>= 16;
+
+			tdp_ratio &= 0xff; /* ratios are only 8 bits long */
 			if (tdp_ratio - 1 == tar) {
 				max_pstate = tar;
 				pr_debug("max_pstate=TAC %x\n", max_pstate);
diff --git a/kernel/drivers/cpufreq/powernv-cpufreq.c b/kernel/drivers/cpufreq/powernv-cpufreq.c
index cb501386e..c4b0ef659 100644
--- a/kernel/drivers/cpufreq/powernv-cpufreq.c
+++ b/kernel/drivers/cpufreq/powernv-cpufreq.c
@@ -373,8 +373,14 @@ static int powernv_cpufreq_target_index(struct cpufreq_policy *policy,
 	if (unlikely(rebooting) && new_index != get_nominal_index())
 		return 0;
 
-	if (!throttled)
+	if (!throttled) {
+		/* we don't want to be preempted while
+		 * checking if the CPU frequency has been throttled
+		 */
+		preempt_disable();
 		powernv_cpufreq_throttle_check(NULL);
+		preempt_enable();
+	}
 
 	freq_data.pstate_id = powernv_freqs[new_index].driver_data;