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
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index 2c7171e..85de313 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -71,6 +71,7 @@
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_CONSERVATIVE
bool "conservative"
+ depends on !(X86_INTEL_PSTATE && SMP)
select CPU_FREQ_GOV_CONSERVATIVE
select CPU_FREQ_GOV_PERFORMANCE
help
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index f4b6066..336b5e9 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1908,6 +1908,18 @@
}
/**
+ * 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
*
* Return the name string of the currently loaded cpufreq driver
@@ -2187,7 +2199,8 @@
* 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 */
diff --git a/drivers/cpufreq/e_powersaver.c b/drivers/cpufreq/e_powersaver.c
index 776a58ba..ab93bce 100644
--- a/drivers/cpufreq/e_powersaver.c
+++ b/drivers/cpufreq/e_powersaver.c
@@ -223,7 +223,6 @@
case EPS_BRAND_C3:
pr_cont("C3\n");
return -ENODEV;
- break;
}
/* Enable Enhanced PowerSaver */
rdmsrl(MSR_IA32_MISC_ENABLE, val);
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 3c14555..b7a9779 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -2568,14 +2568,12 @@
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;
- if (hwp_active)
- intel_cpufreq_adjust_hwp(cpu, target_pstate,
- fast_switch);
- else
- intel_cpufreq_adjust_perf_ctl(cpu, target_pstate,
- fast_switch);
+ } else if (target_pstate != old_pstate) {
+ intel_cpufreq_adjust_perf_ctl(cpu, target_pstate, fast_switch);
+ cpu->pstate.current_pstate = target_pstate;
}
intel_cpufreq_trace(cpu, fast_switch ? INTEL_PSTATE_TRACE_FAST_SWITCH :
@@ -3032,6 +3030,7 @@
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;
diff --git a/drivers/cpufreq/longhaul.c b/drivers/cpufreq/longhaul.c
index 123fb00..182a4dbc 100644
--- a/drivers/cpufreq/longhaul.c
+++ b/drivers/cpufreq/longhaul.c
@@ -593,7 +593,6 @@
break;
default:
return;
- break;
}
if (min_vid_speed >= highest_speed)
return;
diff --git a/drivers/cpufreq/speedstep-lib.c b/drivers/cpufreq/speedstep-lib.c
index a13a2d1..0b66df4 100644
--- a/drivers/cpufreq/speedstep-lib.c
+++ b/drivers/cpufreq/speedstep-lib.c
@@ -240,7 +240,7 @@
return pentium3_get_frequency(processor);
default:
return 0;
- };
+ }
return 0;
}
EXPORT_SYMBOL_GPL(speedstep_get_frequency);
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 56f5b80..01bace4 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -1239,7 +1239,7 @@
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];
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index fa37b1c..1eaa04f 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -298,7 +298,7 @@
struct cpufreq_driver {
char name[CPUFREQ_NAME_LEN];
- u8 flags;
+ u16 flags;
void *driver_data;
/* needed by all drivers */
@@ -422,9 +422,18 @@
*/
#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);
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 4b6a54d..45b054b 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -146,7 +146,7 @@
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.
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index e254745..c03a5775 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -102,7 +102,8 @@
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 @@
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;
