3 files changed, 74 insertions, 55 deletions

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 08ca8c9f41cd..199b52b7c3e1 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1109,12 +1109,27 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif,
                 goto err_set_policy_cpu;
         }
 
+        /* related cpus should atleast have policy->cpus */
+        cpumask_or(policy->related_cpus, policy->related_cpus, policy->cpus);
+
+        /*
+         * affected cpus must always be the one, which are online. We aren't
+         * managing offline cpus here.
+         */
+        cpumask_and(policy->cpus, policy->cpus, cpu_online_mask);
+
+        if (!frozen) {
+                policy->user_policy.min = policy->min;
+                policy->user_policy.max = policy->max;
+        }
+
+        down_write(&policy->rwsem);
         write_lock_irqsave(&cpufreq_driver_lock, flags);
         for_each_cpu(j, policy->cpus)
                 per_cpu(cpufreq_cpu_data, j) = policy;
         write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-        if (cpufreq_driver->get) {
+        if (cpufreq_driver->get && !cpufreq_driver->setpolicy) {
                 policy->cur = cpufreq_driver->get(policy->cpu);
                 if (!policy->cur) {
                         pr_err("%s: ->get() failed\n", __func__);
@@ -1162,20 +1177,6 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif,
                 }
         }
 
-        /* related cpus should atleast have policy->cpus */
-        cpumask_or(policy->related_cpus, policy->related_cpus, policy->cpus);
-
-        /*
-         * affected cpus must always be the one, which are online. We aren't
-         * managing offline cpus here.
-         */
-        cpumask_and(policy->cpus, policy->cpus, cpu_online_mask);
-
-        if (!frozen) {
-                policy->user_policy.min = policy->min;
-                policy->user_policy.max = policy->max;
-        }
-
         blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
                                      CPUFREQ_START, policy);
 
@@ -1206,6 +1207,7 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif,
                 policy->user_policy.policy = policy->policy;
                 policy->user_policy.governor = policy->governor;
         }
+        up_write(&policy->rwsem);
 
         kobject_uevent(&policy->kobj, KOBJ_ADD);
         up_read(&cpufreq_rwsem);
@@ -1323,8 +1325,7 @@ static int __cpufreq_remove_dev_prepare(struct device *dev,
         up_read(&policy->rwsem);
 
         if (cpu != policy->cpu) {
-                if (!frozen)
-                        sysfs_remove_link(&dev->kobj, "cpufreq");
+                sysfs_remove_link(&dev->kobj, "cpufreq");
         } else if (cpus > 1) {
                 new_cpu = cpufreq_nominate_new_policy_cpu(policy, cpu);
                 if (new_cpu >= 0) {
@@ -1547,23 +1548,16 @@ static unsigned int __cpufreq_get(unsigned int cpu)
  */
 unsigned int cpufreq_get(unsigned int cpu)
 {
-        struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
+        struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
         unsigned int ret_freq = 0;
 
-        if (cpufreq_disabled() || !cpufreq_driver)
-                return -ENOENT;
-
-        BUG_ON(!policy);
-
-        if (!down_read_trylock(&cpufreq_rwsem))
-                return 0;
-
-        down_read(&policy->rwsem);
-
-        ret_freq = __cpufreq_get(cpu);
+        if (policy) {
+                down_read(&policy->rwsem);
+                ret_freq = __cpufreq_get(cpu);
+                up_read(&policy->rwsem);
 
-        up_read(&policy->rwsem);
-        up_read(&cpufreq_rwsem);
+                cpufreq_cpu_put(policy);
+        }
 
         return ret_freq;
 }
@@ -2149,7 +2143,7 @@ int cpufreq_update_policy(unsigned int cpu)
          * BIOS might change freq behind our back
          * -> ask driver for current freq and notify governors about a change
          */
-        if (cpufreq_driver->get) {
+        if (cpufreq_driver->get && !cpufreq_driver->setpolicy) {
                 new_policy.cur = cpufreq_driver->get(cpu);
                 if (!policy->cur) {
                         pr_debug("Driver did not initialize current freq");
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 7e257b233602..2cd36b9297f3 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -34,12 +34,15 @@
 
 #define SAMPLE_COUNT            3
 
-#define BYT_RATIOS      0x66a
-#define BYT_VIDS        0x66b
+#define BYT_RATIOS              0x66a
+#define BYT_VIDS                0x66b
+#define BYT_TURBO_RATIOS        0x66c
 
-#define FRAC_BITS 8
+
+#define FRAC_BITS 6
 #define int_tofp(X) ((int64_t)(X) << FRAC_BITS)
 #define fp_toint(X) ((X) >> FRAC_BITS)
+#define FP_ROUNDUP(X) ((X) += 1 << FRAC_BITS)
 
 static inline int32_t mul_fp(int32_t x, int32_t y)
 {
@@ -51,12 +54,11 @@ static inline int32_t div_fp(int32_t x, int32_t y)
         return div_s64((int64_t)x << FRAC_BITS, (int64_t)y);
 }
 
-static u64 energy_divisor;
-
 struct sample {
         int32_t core_pct_busy;
         u64 aperf;
         u64 mperf;
+        unsigned long long tsc;
         int freq;
 };
 
@@ -96,6 +98,7 @@ struct cpudata {
 
         u64     prev_aperf;
         u64     prev_mperf;
+        unsigned long long prev_tsc;
         int     sample_ptr;
         struct sample samples[SAMPLE_COUNT];
 };
@@ -357,7 +360,7 @@ static int byt_get_min_pstate(void)
 {
         u64 value;
         rdmsrl(BYT_RATIOS, value);
-        return value & 0xFF;
+        return (value >> 8) & 0xFF;
 }
 
 static int byt_get_max_pstate(void)
@@ -367,6 +370,13 @@ static int byt_get_max_pstate(void)
         return (value >> 16) & 0xFF;
 }
 
+static int byt_get_turbo_pstate(void)
+{
+        u64 value;
+        rdmsrl(BYT_TURBO_RATIOS, value);
+        return value & 0x3F;
+}
+
 static void byt_set_pstate(struct cpudata *cpudata, int pstate)
 {
         u64 val;
@@ -469,7 +479,7 @@ static struct cpu_defaults byt_params = {
         .funcs = {
                 .get_max = byt_get_max_pstate,
                 .get_min = byt_get_min_pstate,
-                .get_turbo = byt_get_max_pstate,
+                .get_turbo = byt_get_turbo_pstate,
                 .set = byt_set_pstate,
                 .get_vid = byt_get_vid,
         },
@@ -547,31 +557,48 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
 static inline void intel_pstate_calc_busy(struct cpudata *cpu,
                                         struct sample *sample)
 {
-        u64 core_pct;
-        core_pct = div64_u64(int_tofp(sample->aperf * 100),
-                             sample->mperf);
-        sample->freq = fp_toint(cpu->pstate.max_pstate * core_pct * 1000);
+        int32_t core_pct;
+        int32_t c0_pct;
+
+        core_pct = div_fp(int_tofp((sample->aperf)),
+                        int_tofp((sample->mperf)));
+        core_pct = mul_fp(core_pct, int_tofp(100));
+        FP_ROUNDUP(core_pct);
+
+        c0_pct = div_fp(int_tofp(sample->mperf), int_tofp(sample->tsc));
 
-        sample->core_pct_busy = core_pct;
+        sample->freq = fp_toint(
+                mul_fp(int_tofp(cpu->pstate.max_pstate * 1000), core_pct));
+
+        sample->core_pct_busy = mul_fp(core_pct, c0_pct);
 }
 
 static inline void intel_pstate_sample(struct cpudata *cpu)
 {
         u64 aperf, mperf;
+        unsigned long long tsc;
 
         rdmsrl(MSR_IA32_APERF, aperf);
         rdmsrl(MSR_IA32_MPERF, mperf);
+        tsc = native_read_tsc();
+
+        aperf = aperf >> FRAC_BITS;
+        mperf = mperf >> FRAC_BITS;
+        tsc = tsc >> FRAC_BITS;
 
         cpu->sample_ptr = (cpu->sample_ptr + 1) % SAMPLE_COUNT;
         cpu->samples[cpu->sample_ptr].aperf = aperf;
         cpu->samples[cpu->sample_ptr].mperf = mperf;
+        cpu->samples[cpu->sample_ptr].tsc = tsc;
         cpu->samples[cpu->sample_ptr].aperf -= cpu->prev_aperf;
         cpu->samples[cpu->sample_ptr].mperf -= cpu->prev_mperf;
+        cpu->samples[cpu->sample_ptr].tsc -= cpu->prev_tsc;
 
         intel_pstate_calc_busy(cpu, &cpu->samples[cpu->sample_ptr]);
 
         cpu->prev_aperf = aperf;
         cpu->prev_mperf = mperf;
+        cpu->prev_tsc = tsc;
 }
 
 static inline void intel_pstate_set_sample_time(struct cpudata *cpu)
@@ -590,7 +617,8 @@ static inline int32_t intel_pstate_get_scaled_busy(struct cpudata *cpu)
         core_busy = cpu->samples[cpu->sample_ptr].core_pct_busy;
         max_pstate = int_tofp(cpu->pstate.max_pstate);
         current_pstate = int_tofp(cpu->pstate.current_pstate);
-        return mul_fp(core_busy, div_fp(max_pstate, current_pstate));
+        core_busy = mul_fp(core_busy, div_fp(max_pstate, current_pstate));
+        return FP_ROUNDUP(core_busy);
 }
 
 static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
@@ -617,12 +645,10 @@ static void intel_pstate_timer_func(unsigned long __data)
 {
         struct cpudata *cpu = (struct cpudata *) __data;
         struct sample *sample;
-        u64 energy;
 
         intel_pstate_sample(cpu);
 
         sample = &cpu->samples[cpu->sample_ptr];
-        rdmsrl(MSR_PKG_ENERGY_STATUS, energy);
 
         intel_pstate_adjust_busy_pstate(cpu);
 
@@ -631,7 +657,6 @@ static void intel_pstate_timer_func(unsigned long __data)
                         cpu->pstate.current_pstate,
                         sample->mperf,
                         sample->aperf,
-                        div64_u64(energy, energy_divisor),
                         sample->freq);
 
         intel_pstate_set_sample_time(cpu);
@@ -913,7 +938,6 @@ static int __init intel_pstate_init(void)
         int cpu, rc = 0;
         const struct x86_cpu_id *id;
         struct cpu_defaults *cpu_info;
-        u64 units;
 
         if (no_load)
                 return -ENODEV;
@@ -947,9 +971,6 @@ static int __init intel_pstate_init(void)
         if (rc)
                 goto out;
 
-        rdmsrl(MSR_RAPL_POWER_UNIT, units);
-        energy_divisor = 1 << ((units >> 8) & 0x1f); /* bits{12:8} */
-
         intel_pstate_debug_expose_params();
         intel_pstate_sysfs_expose_params();
 
diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c
index e10b646634d7..6684e0342792 100644
--- a/drivers/cpufreq/powernow-k8.c
+++ b/drivers/cpufreq/powernow-k8.c
@@ -1076,7 +1076,7 @@ static int powernowk8_cpu_init(struct cpufreq_policy *pol)
 {
         struct powernow_k8_data *data;
         struct init_on_cpu init_on_cpu;
-        int rc;
+        int rc, cpu;
 
         smp_call_function_single(pol->cpu, check_supported_cpu, &rc, 1);
         if (rc)
@@ -1140,7 +1140,9 @@ static int powernowk8_cpu_init(struct cpufreq_policy *pol)
         pr_debug("cpu_init done, current fid 0x%x, vid 0x%x\n",
                  data->currfid, data->currvid);
 
-        per_cpu(powernow_data, pol->cpu) = data;
+        /* Point all the CPUs in this policy to the same data */
+        for_each_cpu(cpu, pol->cpus)
+                per_cpu(powernow_data, cpu) = data;
 
         return 0;
 
@@ -1155,6 +1157,7 @@ err_out:
 static int powernowk8_cpu_exit(struct cpufreq_policy *pol)
 {
         struct powernow_k8_data *data = per_cpu(powernow_data, pol->cpu);
+        int cpu;
 
         if (!data)
                 return -EINVAL;
@@ -1165,7 +1168,8 @@ static int powernowk8_cpu_exit(struct cpufreq_policy *pol)
 
         kfree(data->powernow_table);
         kfree(data);
-        per_cpu(powernow_data, pol->cpu) = NULL;
+        for_each_cpu(cpu, pol->cpus)
+                per_cpu(powernow_data, cpu) = NULL;
 
         return 0;
 }