summaryrefslogtreecommitdiff
path: root/kernel/sched
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2016-07-26 17:29:07 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2016-07-26 17:29:07 -0700
commit6453dbdda30428a3c56568c96fe70ea3612f07e2 (patch)
tree9a3c6087a2832c36e8c49296fb05f95b877e0111 /kernel/sched
parent27b79027bc112a63ad4004eb83c6acacae08a0de (diff)
parentbc841e260c95608921809a2c7481cf6f03bec21a (diff)
Merge tag 'pm-4.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
Pull power management updates from Rafael Wysocki: "Again, the majority of changes go into the cpufreq subsystem, but there are no big features this time. The cpufreq changes that stand out somewhat are the governor interface rework and improvements related to the handling of frequency tables. Apart from those, there are fixes and new device/CPU IDs in drivers, cleanups and an improvement of the new schedutil governor. Next, there are some changes in the hibernation core, including a fix for a nasty problem related to the MONITOR/MWAIT usage by CPU offline during resume from hibernation, a few core improvements related to memory management during resume, a couple of additional debug features and cleanups. Finally, we have some fixes and cleanups in the devfreq subsystem, generic power domains framework improvements related to system suspend/resume, support for some new chips in intel_idle and in the power capping RAPL driver, a new version of the AnalyzeSuspend utility and some assorted fixes and cleanups. Specifics: - Rework the cpufreq governor interface to make it more straightforward and modify the conservative governor to avoid using transition notifications (Rafael Wysocki). - Rework the handling of frequency tables by the cpufreq core to make it more efficient (Viresh Kumar). - Modify the schedutil governor to reduce the number of wakeups it causes to occur in cases when the CPU frequency doesn't need to be changed (Steve Muckle, Viresh Kumar). - Fix some minor issues and clean up code in the cpufreq core and governors (Rafael Wysocki, Viresh Kumar). - Add Intel Broxton support to the intel_pstate driver (Srinivas Pandruvada). - Fix problems related to the config TDP feature and to the validity of the MSR_HWP_INTERRUPT register in intel_pstate (Jan Kiszka, Srinivas Pandruvada). - Make intel_pstate update the cpu_frequency tracepoint even if the frequency doesn't change to avoid confusing powertop (Rafael Wysocki). - Clean up the usage of __init/__initdata in intel_pstate, mark some of its internal variables as __read_mostly and drop an unused structure element from it (Jisheng Zhang, Carsten Emde). - Clean up the usage of some duplicate MSR symbols in intel_pstate and turbostat (Srinivas Pandruvada). - Update/fix the powernv, s3c24xx and mvebu cpufreq drivers (Akshay Adiga, Viresh Kumar, Ben Dooks). - Fix a regression (introduced during the 4.5 cycle) in the pcc-cpufreq driver by reverting the problematic commit (Andreas Herrmann). - Add support for Intel Denverton to intel_idle, clean up Broxton support in it and make it explicitly non-modular (Jacob Pan, Jan Beulich, Paul Gortmaker). - Add support for Denverton and Ivy Bridge server to the Intel RAPL power capping driver and make it more careful about the handing of MSRs that may not be present (Jacob Pan, Xiaolong Wang). - Fix resume from hibernation on x86-64 by making the CPU offline during resume avoid using MONITOR/MWAIT in the "play dead" loop which may lead to an inadvertent "revival" of a "dead" CPU and a page fault leading to a kernel crash from it (Rafael Wysocki). - Make memory management during resume from hibernation more straightforward (Rafael Wysocki). - Add debug features that should help to detect problems related to hibernation and resume from it (Rafael Wysocki, Chen Yu). - Clean up hibernation core somewhat (Rafael Wysocki). - Prevent KASAN from instrumenting the hibernation core which leads to large numbers of false-positives from it (James Morse). - Prevent PM (hibernate and suspend) notifiers from being called during the cleanup phase if they have not been called during the corresponding preparation phase which is possible if one of the other notifiers returns an error at that time (Lianwei Wang). - Improve suspend-related debug printout in the tasks freezer and clean up suspend-related console handling (Roger Lu, Borislav Petkov). - Update the AnalyzeSuspend script in the kernel sources to version 4.2 (Todd Brandt). - Modify the generic power domains framework to make it handle system suspend/resume better (Ulf Hansson). - Make the runtime PM framework avoid resuming devices synchronously when user space changes the runtime PM settings for them and improve its error reporting (Rafael Wysocki, Linus Walleij). - Fix error paths in devfreq drivers (exynos, exynos-ppmu, exynos-bus) and in the core, make some devfreq code explicitly non-modular and change some of it into tristate (Bartlomiej Zolnierkiewicz, Peter Chen, Paul Gortmaker). - Add DT support to the generic PM clocks management code and make it export some more symbols (Jon Hunter, Paul Gortmaker). - Make the PCI PM core code slightly more robust against possible driver errors (Andy Shevchenko). - Make it possible to change DESTDIR and PREFIX in turbostat (Andy Shevchenko)" * tag 'pm-4.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (89 commits) Revert "cpufreq: pcc-cpufreq: update default value of cpuinfo_transition_latency" PM / hibernate: Introduce test_resume mode for hibernation cpufreq: export cpufreq_driver_resolve_freq() cpufreq: Disallow ->resolve_freq() for drivers providing ->target_index() PCI / PM: check all fields in pci_set_platform_pm() cpufreq: acpi-cpufreq: use cached frequency mapping when possible cpufreq: schedutil: map raw required frequency to driver frequency cpufreq: add cpufreq_driver_resolve_freq() cpufreq: intel_pstate: Check cpuid for MSR_HWP_INTERRUPT intel_pstate: Update cpu_frequency tracepoint every time cpufreq: intel_pstate: clean remnant struct element PM / tools: scripts: AnalyzeSuspend v4.2 x86 / hibernate: Use hlt_play_dead() when resuming from hibernation cpufreq: powernv: Replacing pstate_id with frequency table index intel_pstate: Fix MSR_CONFIG_TDP_x addressing in core_get_max_pstate() PM / hibernate: Image data protection during restoration PM / hibernate: Add missing braces in __register_nosave_region() PM / hibernate: Clean up comments in snapshot.c PM / hibernate: Clean up function headers in snapshot.c PM / hibernate: Add missing braces in hibernate_setup() ...
Diffstat (limited to 'kernel/sched')
-rw-r--r--kernel/sched/cpufreq_schedutil.c74
1 files changed, 32 insertions, 42 deletions
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 14c4aa25cc45..a84641b222c1 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -47,6 +47,8 @@ struct sugov_cpu {
struct update_util_data update_util;
struct sugov_policy *sg_policy;
+ unsigned int cached_raw_freq;
+
/* The fields below are only needed when sharing a policy. */
unsigned long util;
unsigned long max;
@@ -106,7 +108,7 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time,
/**
* get_next_freq - Compute a new frequency for a given cpufreq policy.
- * @policy: cpufreq policy object to compute the new frequency for.
+ * @sg_cpu: schedutil cpu object to compute the new frequency for.
* @util: Current CPU utilization.
* @max: CPU capacity.
*
@@ -121,14 +123,25 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time,
* next_freq = C * curr_freq * util_raw / max
*
* Take C = 1.25 for the frequency tipping point at (util / max) = 0.8.
+ *
+ * The lowest driver-supported frequency which is equal or greater than the raw
+ * next_freq (as calculated above) is returned, subject to policy min/max and
+ * cpufreq driver limitations.
*/
-static unsigned int get_next_freq(struct cpufreq_policy *policy,
- unsigned long util, unsigned long max)
+static unsigned int get_next_freq(struct sugov_cpu *sg_cpu, unsigned long util,
+ unsigned long max)
{
+ struct sugov_policy *sg_policy = sg_cpu->sg_policy;
+ struct cpufreq_policy *policy = sg_policy->policy;
unsigned int freq = arch_scale_freq_invariant() ?
policy->cpuinfo.max_freq : policy->cur;
- return (freq + (freq >> 2)) * util / max;
+ freq = (freq + (freq >> 2)) * util / max;
+
+ if (freq == sg_cpu->cached_raw_freq && sg_policy->next_freq != UINT_MAX)
+ return sg_policy->next_freq;
+ sg_cpu->cached_raw_freq = freq;
+ return cpufreq_driver_resolve_freq(policy, freq);
}
static void sugov_update_single(struct update_util_data *hook, u64 time,
@@ -143,13 +156,14 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
return;
next_f = util == ULONG_MAX ? policy->cpuinfo.max_freq :
- get_next_freq(policy, util, max);
+ get_next_freq(sg_cpu, util, max);
sugov_update_commit(sg_policy, time, next_f);
}
-static unsigned int sugov_next_freq_shared(struct sugov_policy *sg_policy,
+static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu,
unsigned long util, unsigned long max)
{
+ struct sugov_policy *sg_policy = sg_cpu->sg_policy;
struct cpufreq_policy *policy = sg_policy->policy;
unsigned int max_f = policy->cpuinfo.max_freq;
u64 last_freq_update_time = sg_policy->last_freq_update_time;
@@ -189,7 +203,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_policy *sg_policy,
}
}
- return get_next_freq(policy, util, max);
+ return get_next_freq(sg_cpu, util, max);
}
static void sugov_update_shared(struct update_util_data *hook, u64 time,
@@ -206,7 +220,7 @@ static void sugov_update_shared(struct update_util_data *hook, u64 time,
sg_cpu->last_update = time;
if (sugov_should_update_freq(sg_policy, time)) {
- next_f = sugov_next_freq_shared(sg_policy, util, max);
+ next_f = sugov_next_freq_shared(sg_cpu, util, max);
sugov_update_commit(sg_policy, time, next_f);
}
@@ -394,7 +408,7 @@ static int sugov_init(struct cpufreq_policy *policy)
return ret;
}
-static int sugov_exit(struct cpufreq_policy *policy)
+static void sugov_exit(struct cpufreq_policy *policy)
{
struct sugov_policy *sg_policy = policy->governor_data;
struct sugov_tunables *tunables = sg_policy->tunables;
@@ -412,7 +426,6 @@ static int sugov_exit(struct cpufreq_policy *policy)
mutex_unlock(&global_tunables_lock);
sugov_policy_free(sg_policy);
- return 0;
}
static int sugov_start(struct cpufreq_policy *policy)
@@ -434,6 +447,7 @@ static int sugov_start(struct cpufreq_policy *policy)
sg_cpu->util = ULONG_MAX;
sg_cpu->max = 0;
sg_cpu->last_update = 0;
+ sg_cpu->cached_raw_freq = 0;
cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util,
sugov_update_shared);
} else {
@@ -444,7 +458,7 @@ static int sugov_start(struct cpufreq_policy *policy)
return 0;
}
-static int sugov_stop(struct cpufreq_policy *policy)
+static void sugov_stop(struct cpufreq_policy *policy)
{
struct sugov_policy *sg_policy = policy->governor_data;
unsigned int cpu;
@@ -456,53 +470,29 @@ static int sugov_stop(struct cpufreq_policy *policy)
irq_work_sync(&sg_policy->irq_work);
cancel_work_sync(&sg_policy->work);
- return 0;
}
-static int sugov_limits(struct cpufreq_policy *policy)
+static void sugov_limits(struct cpufreq_policy *policy)
{
struct sugov_policy *sg_policy = policy->governor_data;
if (!policy->fast_switch_enabled) {
mutex_lock(&sg_policy->work_lock);
-
- if (policy->max < policy->cur)
- __cpufreq_driver_target(policy, policy->max,
- CPUFREQ_RELATION_H);
- else if (policy->min > policy->cur)
- __cpufreq_driver_target(policy, policy->min,
- CPUFREQ_RELATION_L);
-
+ cpufreq_policy_apply_limits(policy);
mutex_unlock(&sg_policy->work_lock);
}
sg_policy->need_freq_update = true;
- return 0;
-}
-
-int sugov_governor(struct cpufreq_policy *policy, unsigned int event)
-{
- if (event == CPUFREQ_GOV_POLICY_INIT) {
- return sugov_init(policy);
- } else if (policy->governor_data) {
- switch (event) {
- case CPUFREQ_GOV_POLICY_EXIT:
- return sugov_exit(policy);
- case CPUFREQ_GOV_START:
- return sugov_start(policy);
- case CPUFREQ_GOV_STOP:
- return sugov_stop(policy);
- case CPUFREQ_GOV_LIMITS:
- return sugov_limits(policy);
- }
- }
- return -EINVAL;
}
static struct cpufreq_governor schedutil_gov = {
.name = "schedutil",
- .governor = sugov_governor,
.owner = THIS_MODULE,
+ .init = sugov_init,
+ .exit = sugov_exit,
+ .start = sugov_start,
+ .stop = sugov_stop,
+ .limits = sugov_limits,
};
static int __init sugov_module_init(void)