Power management fixes for v4.7-rc4

- Fix a recent regression in the intel_pstate driver that may
    lead to degraded performance on some systems due to missing
    turbo state entry in the table returned by the ACPI _PSS
    object (Srinivas Pandruvada).
 
  - Fix a recent regression in the OPP (operating performance points)
    framework that may lead to degraded performance on some systems
    where the OPP table is created too early (Viresh Kumar).
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.22 (GNU/Linux)
 
 iQIcBAABCAAGBQJXZJSaAAoJEILEb/54YlRxsSIP/3La4sQznXd2U5S4E/kjy7eh
 7bidzRH1R0RlkCnE6WmRMSVwAG5dF3n3vQMYFIQxT1Mq1Fbbfmb+fPgWVJ+2xbjJ
 +2yobuq385bwE4Y1RJViLcYsEEA1t/92r6gE3eI6x2jYg0FUJ4YHYAg22aYUGyDE
 p5PmazJX1v4wuEarwe1qKloNLRW++mqyERdobH21JLTaRECuwC669ydZt6OMDNk6
 lx0thNyOtNumr6w4Z3RSgIo3+pHjSYLIjL9yxRTWgQAmAFr7WdWyfP/nh48p8fEj
 sP8yuaRcIBOzxC8IXP2jlLENmkLZI+dttFz7CQ8xEwdhzMSZ1Z9dJb82dSO5gTc8
 F8xY48xk+W5jH+qLc4ZayS4sCxWgAphFTpAq6o9N16zbRo5BPOmyYujOIlMl6lvz
 4n95r+1OkvX0k4b07rkBJcrKb8mDKhmnv2K0UDyNElz6Ihx2YgMlv2YGWOYhT88K
 8X49o2HaftRJDK2rtOhvCivQUU/cj3ldTu7Ys0hTBe+OxIeGA2+OJz1gr60gYMcz
 jN75c2llTQfJeMa4X2ysFEHUma5QNv8IqV2IsqsmGtcmZx3ARkKfH1yfqWQlzLU0
 HY1cht5S1vc1e4AsezwfejwFaNdo02U/yXa2SHYYlw0tL+0J039XGTKQswh3RRT2
 y3lQnQOl2ogeKHsTxELr
 =BG8V
 -----END PGP SIGNATURE-----

Merge tag 'pm-4.7-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management fixes from Rafael Wysocki:
 "Fixes for two recent regressions that may lead to degraded performance
  (operating performance points framework, intel_pstate).

  Specifics:

   - Fix a recent regression in the intel_pstate driver that may lead to
     degraded performance on some systems due to missing turbo state
     entry in the table returned by the ACPI _PSS object (Srinivas
     Pandruvada).

   - Fix a recent regression in the OPP (operating performance points)
     framework that may lead to degraded performance on some systems
     where the OPP table is created too early (Viresh Kumar)"

* tag 'pm-4.7-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  PM / OPP: Add 'UNKNOWN' status for shared_opp in struct opp_table
  cpufreq: intel_pstate: Adjust _PSS[0] freqeuency if needed

drivers/base/power/opp/cpu.c

@@ -211,7 +211,7 @@ int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev,
 		}
 
 		/* Mark opp-table as multiple CPUs are sharing it now */
-		opp_table->shared_opp = true;
+		opp_table->shared_opp = OPP_TABLE_ACCESS_SHARED;
 	}
 unlock:
 	mutex_unlock(&opp_table_lock);
@@ -227,7 +227,8 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_set_sharing_cpus);
  *
  * This updates the @cpumask with CPUs that are sharing OPPs with @cpu_dev.
  *
- * Returns -ENODEV if OPP table isn't already present.
+ * Returns -ENODEV if OPP table isn't already present and -EINVAL if the OPP
+ * table's status is access-unknown.
  *
  * Locking: The internal opp_table and opp structures are RCU protected.
  * Hence this function internally uses RCU updater strategy with mutex locks
@@ -249,9 +250,14 @@ int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask)
 		goto unlock;
 	}
 
+	if (opp_table->shared_opp == OPP_TABLE_ACCESS_UNKNOWN) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
 	cpumask_clear(cpumask);
 
-	if (opp_table->shared_opp) {
+	if (opp_table->shared_opp == OPP_TABLE_ACCESS_SHARED) {
 		list_for_each_entry(opp_dev, &opp_table->dev_list, node)
 			cpumask_set_cpu(opp_dev->dev->id, cpumask);
 	} else {

drivers/base/power/opp/of.c

@@ -34,7 +34,10 @@ static struct opp_table *_managed_opp(const struct device_node *np)
 			 * But the OPPs will be considered as shared only if the
 			 * OPP table contains a "opp-shared" property.
 			 */
-			return opp_table->shared_opp ? opp_table : NULL;
+			if (opp_table->shared_opp == OPP_TABLE_ACCESS_SHARED)
+				return opp_table;
+
+			return NULL;
 		}
 	}
 
@@ -353,7 +356,10 @@ static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np)
 	}
 
 	opp_table->np = opp_np;
-	opp_table->shared_opp = of_property_read_bool(opp_np, "opp-shared");
+	if (of_property_read_bool(opp_np, "opp-shared"))
+		opp_table->shared_opp = OPP_TABLE_ACCESS_SHARED;
+	else
+		opp_table->shared_opp = OPP_TABLE_ACCESS_EXCLUSIVE;
 
 	mutex_unlock(&opp_table_lock);
 

drivers/base/power/opp/opp.h

@@ -119,6 +119,12 @@ struct opp_device {
 #endif
 };
 
+enum opp_table_access {
+	OPP_TABLE_ACCESS_UNKNOWN = 0,
+	OPP_TABLE_ACCESS_EXCLUSIVE = 1,
+	OPP_TABLE_ACCESS_SHARED = 2,
+};
+
 /**
  * struct opp_table - Device opp structure
  * @node:	table node - contains the devices with OPPs that
@@ -166,7 +172,7 @@ struct opp_table {
 	/* For backward compatibility with v1 bindings */
 	unsigned int voltage_tolerance_v1;
 
-	bool shared_opp;
+	enum opp_table_access shared_opp;
 	struct dev_pm_opp *suspend_opp;
 
 	unsigned int *supported_hw;

drivers/cpufreq/intel_pstate.c

@@ -372,26 +372,9 @@ static bool intel_pstate_get_ppc_enable_status(void)
 	return acpi_ppc;
 }
 
-/*
- * The max target pstate ratio is a 8 bit value in both PLATFORM_INFO MSR and
- * in TURBO_RATIO_LIMIT MSR, which pstate driver stores in max_pstate and
- * max_turbo_pstate fields. The PERF_CTL MSR contains 16 bit value for P state
- * ratio, out of it only high 8 bits are used. For example 0x1700 is setting
- * target ratio 0x17. The _PSS control value stores in a format which can be
- * directly written to PERF_CTL MSR. But in intel_pstate driver this shift
- * occurs during write to PERF_CTL (E.g. for cores core_set_pstate()).
- * This function converts the _PSS control value to intel pstate driver format
- * for comparison and assignment.
- */
-static int convert_to_native_pstate_format(struct cpudata *cpu, int index)
-{
-	return cpu->acpi_perf_data.states[index].control >> 8;
-}
-
 static void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy)
 {
 	struct cpudata *cpu;
-	int turbo_pss_ctl;
 	int ret;
 	int i;
 
@@ -441,11 +424,10 @@ static void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy)
 	 * max frequency, which will cause a reduced performance as
 	 * this driver uses real max turbo frequency as the max
 	 * frequency. So correct this frequency in _PSS table to
-	 * correct max turbo frequency based on the turbo ratio.
+	 * correct max turbo frequency based on the turbo state.
 	 * Also need to convert to MHz as _PSS freq is in MHz.
 	 */
-	turbo_pss_ctl = convert_to_native_pstate_format(cpu, 0);
+	if (!limits->turbo_disabled)
-	if (turbo_pss_ctl > cpu->pstate.max_pstate)
 		cpu->acpi_perf_data.states[0].core_frequency =
 					policy->cpuinfo.max_freq / 1000;
 	cpu->valid_pss_table = true;