Merge tag 'pm-4.9-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management fixes from Rafael Wysocki:
 "These fix two intel_pstate issues related to the way it works when the
  scaling_governor sysfs attribute is set to "performance" and fix up
  messages in the system suspend core code.

  Specifics:

   - Fix a missing KERN_CONT in a system suspend message by converting
     the affected code to using pr_info() and pr_cont() instead of the
     "raw" printk() (Jon Hunter).

   - Make intel_pstate set the CPU P-state from its .set_policy()
     callback when the scaling_governor sysfs attribute is set to
     "performance" so that it interacts with NOHZ_FULL more predictably
     which was the case before 4.7 (Rafael Wysocki).

   - Make intel_pstate always request the maximum allowed P-state when
     the scaling_governor sysfs attribute is set to "performance" to
     prevent it from effectively ingoring that setting is some
     situations (Rafael Wysocki)"

* tag 'pm-4.9-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  cpufreq: intel_pstate: Always set max P-state in performance mode
  PM / suspend: Fix missing KERN_CONT for suspend message
  cpufreq: intel_pstate: Set P-state upfront in performance mode

2 files changed, 34 insertions, 8 deletions

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index f535f8123258..4737520ec823 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -179,6 +179,7 @@ struct _pid {
 /**
  * struct cpudata -     Per CPU instance data storage
  * @cpu:                CPU number for this instance data
+ * @policy:             CPUFreq policy value
  * @update_util:        CPUFreq utility callback information
  * @update_util_set:    CPUFreq utility callback is set
  * @iowait_boost:       iowait-related boost fraction
@@ -201,6 +202,7 @@ struct _pid {
 struct cpudata {
         int cpu;
 
+        unsigned int policy;
         struct update_util_data update_util;
         bool   update_util_set;
 
@@ -1142,10 +1144,8 @@ static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max)
         *min = clamp_t(int, min_perf, cpu->pstate.min_pstate, max_perf);
 }
 
-static void intel_pstate_set_min_pstate(struct cpudata *cpu)
+static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
 {
-        int pstate = cpu->pstate.min_pstate;
-
         trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
         cpu->pstate.current_pstate = pstate;
         /*
@@ -1157,6 +1157,20 @@ static void intel_pstate_set_min_pstate(struct cpudata *cpu)
                       pstate_funcs.get_val(cpu, pstate));
 }
 
+static void intel_pstate_set_min_pstate(struct cpudata *cpu)
+{
+        intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate);
+}
+
+static void intel_pstate_max_within_limits(struct cpudata *cpu)
+{
+        int min_pstate, max_pstate;
+
+        update_turbo_state();
+        intel_pstate_get_min_max(cpu, &min_pstate, &max_pstate);
+        intel_pstate_set_pstate(cpu, max_pstate);
+}
+
 static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
 {
         cpu->pstate.min_pstate = pstate_funcs.get_min();
@@ -1325,7 +1339,8 @@ static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
 
         from = cpu->pstate.current_pstate;
 
-        target_pstate = pstate_funcs.get_target_pstate(cpu);
+        target_pstate = cpu->policy == CPUFREQ_POLICY_PERFORMANCE ?
+                cpu->pstate.turbo_pstate : pstate_funcs.get_target_pstate(cpu);
 
         intel_pstate_update_pstate(cpu, target_pstate);
 
@@ -1491,7 +1506,9 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
         pr_debug("set_policy cpuinfo.max %u policy->max %u\n",
                  policy->cpuinfo.max_freq, policy->max);
 
-        cpu = all_cpu_data[0];
+        cpu = all_cpu_data[policy->cpu];
+        cpu->policy = policy->policy;
+
         if (cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate &&
             policy->max < policy->cpuinfo.max_freq &&
             policy->max > cpu->pstate.max_pstate * cpu->pstate.scaling) {
@@ -1499,7 +1516,7 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
                 policy->max = policy->cpuinfo.max_freq;
         }
 
-        if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) {
+        if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE) {
                 limits = &performance_limits;
                 if (policy->max >= policy->cpuinfo.max_freq) {
                         pr_debug("set performance\n");
@@ -1535,6 +1552,15 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
         limits->max_perf = round_up(limits->max_perf, FRAC_BITS);
 
  out:
+        if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE) {
+                /*
+                 * NOHZ_FULL CPUs need this as the governor callback may not
+                 * be invoked on them.
+                 */
+                intel_pstate_clear_update_util_hook(policy->cpu);
+                intel_pstate_max_within_limits(cpu);
+        }
+
         intel_pstate_set_update_util_hook(policy->cpu);
 
         intel_pstate_hwp_set_policy(policy);
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 1e7f5da648d9..6ccb08f57fcb 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -498,9 +498,9 @@ static int enter_state(suspend_state_t state)
 
 #ifndef CONFIG_SUSPEND_SKIP_SYNC
         trace_suspend_resume(TPS("sync_filesystems"), 0, true);
-        printk(KERN_INFO "PM: Syncing filesystems ... ");
+        pr_info("PM: Syncing filesystems ... ");
         sys_sync();
-        printk("done.\n");
+        pr_cont("done.\n");
         trace_suspend_resume(TPS("sync_filesystems"), 0, false);
 #endif