Power management fixes for 5.10-rc2

- Modify Kconfig to prevent configuring either the "conservative"
    or the "ondemand" governor as the default cpufreq governor if
    intel_pstate is selected, in which case "schedutil" is the
    default choice for the default governor setting (Rafael Wysocki).
 
  - Modify the cpufreq core, intel_pstate and the schedutil governor
    to avoid missing updates of the HWP max limit when intel_pstate
    operates in the passive mode with HWP enabled (Rafael Wysocki).
 
  - Fix max_cstate module parameter handling in intel_idle for
    processor models with C-state tables coming from ACPI (Chen Yu).
 
  - Clean up assorted pieces of power management code (Jackie Zamow,
    Tom Rix, Zhang Qilong).
 -----BEGIN PGP SIGNATURE-----
 
 iQJGBAABCAAwFiEE4fcc61cGeeHD/fCwgsRv/nhiVHEFAl+cOyISHHJqd0Byand5
 c29ja2kubmV0AAoJEILEb/54YlRxxj0P/1qmvZeLR5ODvSKLURSlzQYPiF4Ud0uo
 7huByO3K63hJ9qpEQZVVzNl0Yuu5vCa7cliebnIRNDHMy4AVOVw5Qf9Uhz/tFlmZ
 ZBvSX1LGWdvMzUnx00AASdHbNOrFy+YyooQ5RfA8sFmtvAhRhPNRW9VCzc9Midoh
 cICSQ6fQDn+0wb+hv89HQlIRvbakM6a8QDL4xI6Y8aS/a5OwOHGJQnC7ZLPIoQLi
 BxD/IEDdNvDiLFPx8OpxJ93NtLaz1tyvWFJHvqSnOREDYB22YkG8WLZftY7h8pz6
 MMbXrZN11/Tex1H0KXDI4YscCBnwxNnFuBo1ur/FX6GvDm2Sm9ybpVHCXxYKux46
 ZFc8K2auqApt98xTlrqKru/rfCB2/fubypUustqpYeCjowBENPFbjyag8bRaKLh3
 awiDwwz1wZDd2mZfEl4iaxJI4gjUwRmPDC1UiT1dlc7nozaDzPxrGGiQghAshOnW
 JVQAiw+evERIFuH5YvJ+/si1sJYhreMjoQ7mICNMmpgJ2ElVvNufpW9aVRQiycp1
 9a0u1ZgGs9DI1580+YTl1nGvsRefdgvMDpozcESwxY8dmMm+027+lyLhwlrUTPfy
 gmakUcb4jbvIicG53huxus7teqBLwrX36HOHBb1l3tSJfOkcQieddGUZxuT8Q9xp
 rAY2mRMRr7SI
 =w+LI
 -----END PGP SIGNATURE-----

Merge tag 'pm-5.10-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management fixes from Rafael Wysocki:
 "These fix a few issues related to running intel_pstate in the passive
  mode with HWP enabled, correct the handling of the max_cstate module
  parameter in intel_idle and make a few janitorial changes.

  Specifics:

   - Modify Kconfig to prevent configuring either the "conservative" or
     the "ondemand" governor as the default cpufreq governor if
     intel_pstate is selected, in which case "schedutil" is the default
     choice for the default governor setting (Rafael Wysocki).

   - Modify the cpufreq core, intel_pstate and the schedutil governor to
     avoid missing updates of the HWP max limit when intel_pstate
     operates in the passive mode with HWP enabled (Rafael Wysocki).

   - Fix max_cstate module parameter handling in intel_idle for
     processor models with C-state tables coming from ACPI (Chen Yu).

   - Clean up assorted pieces of power management code (Jackie Zamow,
     Tom Rix, Zhang Qilong)"

* tag 'pm-5.10-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  cpufreq: schedutil: Always call driver if CPUFREQ_NEED_UPDATE_LIMITS is set
  cpufreq: Introduce cpufreq_driver_test_flags()
  cpufreq: speedstep: remove unneeded semicolon
  PM: sleep: fix typo in kernel/power/process.c
  intel_idle: Fix max_cstate for processor models without C-state tables
  cpufreq: intel_pstate: Avoid missing HWP max updates in passive mode
  cpufreq: Introduce CPUFREQ_NEED_UPDATE_LIMITS driver flag
  cpufreq: Avoid configuring old governors as default with intel_pstate
  cpufreq: e_powersaver: remove unreachable break

drivers/cpufreq/Kconfig

@@ -71,6 +71,7 @@ config CPU_FREQ_DEFAULT_GOV_USERSPACE
 
 config CPU_FREQ_DEFAULT_GOV_ONDEMAND
 	bool "ondemand"
+	depends on !(X86_INTEL_PSTATE && SMP)
 	select CPU_FREQ_GOV_ONDEMAND
 	select CPU_FREQ_GOV_PERFORMANCE
 	help
@@ -83,6 +84,7 @@ config CPU_FREQ_DEFAULT_GOV_ONDEMAND
 
 config CPU_FREQ_DEFAULT_GOV_CONSERVATIVE
 	bool "conservative"
+	depends on !(X86_INTEL_PSTATE && SMP)
 	select CPU_FREQ_GOV_CONSERVATIVE
 	select CPU_FREQ_GOV_PERFORMANCE
 	help

drivers/cpufreq/cpufreq.c

@@ -1907,6 +1907,18 @@ void cpufreq_resume(void)
 	}
 }
 
+/**
+ * cpufreq_driver_test_flags - Test cpufreq driver's flags against given ones.
+ * @flags: Flags to test against the current cpufreq driver's flags.
+ *
+ * Assumes that the driver is there, so callers must ensure that this is the
+ * case.
+ */
+bool cpufreq_driver_test_flags(u16 flags)
+{
+	return !!(cpufreq_driver->flags & flags);
+}
+
 /**
  *	cpufreq_get_current_driver - return current driver's name
  *
@@ -2187,7 +2199,8 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy,
 	 * exactly same freq is called again and so we can save on few function
 	 * calls.
 	 */
-	if (target_freq == policy->cur)
+	if (target_freq == policy->cur &&
+	    !(cpufreq_driver->flags & CPUFREQ_NEED_UPDATE_LIMITS))
 		return 0;
 
 	/* Save last value to restore later on errors */

drivers/cpufreq/e_powersaver.c

@@ -223,7 +223,6 @@ static int eps_cpu_init(struct cpufreq_policy *policy)
 	case EPS_BRAND_C3:
 		pr_cont("C3\n");
 		return -ENODEV;
-		break;
 	}
 	/* Enable Enhanced PowerSaver */
 	rdmsrl(MSR_IA32_MISC_ENABLE, val);

drivers/cpufreq/intel_pstate.c

@@ -2568,14 +2568,12 @@ static int intel_cpufreq_update_pstate(struct cpudata *cpu, int target_pstate,
 	int old_pstate = cpu->pstate.current_pstate;
 
 	target_pstate = intel_pstate_prepare_request(cpu, target_pstate);
-	if (target_pstate != old_pstate) {
+	if (hwp_active) {
+		intel_cpufreq_adjust_hwp(cpu, target_pstate, fast_switch);
+		cpu->pstate.current_pstate = target_pstate;
+	} else if (target_pstate != old_pstate) {
+		intel_cpufreq_adjust_perf_ctl(cpu, target_pstate, fast_switch);
 		cpu->pstate.current_pstate = target_pstate;
-		if (hwp_active)
-			intel_cpufreq_adjust_hwp(cpu, target_pstate,
-						 fast_switch);
-		else
-			intel_cpufreq_adjust_perf_ctl(cpu, target_pstate,
-						      fast_switch);
 	}
 
 	intel_cpufreq_trace(cpu, fast_switch ? INTEL_PSTATE_TRACE_FAST_SWITCH :
@@ -3032,6 +3030,7 @@ static int __init intel_pstate_init(void)
 			hwp_mode_bdw = id->driver_data;
 			intel_pstate.attr = hwp_cpufreq_attrs;
 			intel_cpufreq.attr = hwp_cpufreq_attrs;
+			intel_cpufreq.flags |= CPUFREQ_NEED_UPDATE_LIMITS;
 			if (!default_driver)
 				default_driver = &intel_pstate;
 

drivers/cpufreq/longhaul.c

@@ -593,7 +593,6 @@ static void longhaul_setup_voltagescaling(void)
 		break;
 	default:
 		return;
-		break;
 	}
 	if (min_vid_speed >= highest_speed)
 		return;

drivers/cpufreq/speedstep-lib.c

@@ -240,7 +240,7 @@ unsigned int speedstep_get_frequency(enum speedstep_processor processor)
 		return pentium3_get_frequency(processor);
 	default:
 		return 0;
-	};
+	}
 	return 0;
 }
 EXPORT_SYMBOL_GPL(speedstep_get_frequency);

drivers/idle/intel_idle.c

@@ -1239,7 +1239,7 @@ static void __init intel_idle_init_cstates_acpi(struct cpuidle_driver *drv)
 		struct acpi_processor_cx *cx;
 		struct cpuidle_state *state;
 
-		if (intel_idle_max_cstate_reached(cstate))
+		if (intel_idle_max_cstate_reached(cstate - 1))
 			break;
 
 		cx = &acpi_state_table.states[cstate];

include/linux/cpufreq.h

@@ -298,7 +298,7 @@ __ATTR(_name, 0644, show_##_name, store_##_name)
 
 struct cpufreq_driver {
 	char		name[CPUFREQ_NAME_LEN];
-	u8		flags;
+	u16		flags;
 	void		*driver_data;
 
 	/* needed by all drivers */
@@ -422,9 +422,18 @@ struct cpufreq_driver {
  */
 #define CPUFREQ_IS_COOLING_DEV			BIT(7)
 
+/*
+ * Set by drivers that need to update internale upper and lower boundaries along
+ * with the target frequency and so the core and governors should also invoke
+ * the diver if the target frequency does not change, but the policy min or max
+ * may have changed.
+ */
+#define CPUFREQ_NEED_UPDATE_LIMITS		BIT(8)
+
 int cpufreq_register_driver(struct cpufreq_driver *driver_data);
 int cpufreq_unregister_driver(struct cpufreq_driver *driver_data);
 
+bool cpufreq_driver_test_flags(u16 flags);
 const char *cpufreq_get_current_driver(void);
 void *cpufreq_get_driver_data(void);
 

kernel/power/process.c

@@ -146,7 +146,7 @@ int freeze_processes(void)
 	BUG_ON(in_atomic());
 
 	/*
-	 * Now that the whole userspace is frozen we need to disbale
+	 * Now that the whole userspace is frozen we need to disable
 	 * the OOM killer to disallow any further interference with
 	 * killable tasks. There is no guarantee oom victims will
 	 * ever reach a point they go away we have to wait with a timeout.

kernel/sched/cpufreq_schedutil.c

@@ -102,7 +102,8 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
 static bool sugov_update_next_freq(struct sugov_policy *sg_policy, u64 time,
 				   unsigned int next_freq)
 {
-	if (sg_policy->next_freq == next_freq)
+	if (sg_policy->next_freq == next_freq &&
+	    !cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS))
 		return false;
 
 	sg_policy->next_freq = next_freq;
@@ -161,7 +162,8 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
 
 	freq = map_util_freq(util, freq, max);
 
-	if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update)
+	if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update &&
+	    !cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS))
 		return sg_policy->next_freq;
 
 	sg_policy->need_freq_update = false;