summaryrefslogtreecommitdiff
path: root/drivers
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2020-03-30 17:01:51 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2020-03-30 17:01:51 -0700
commit642e53ead6aea8740a219ede509a5d138fd4f780 (patch)
tree5c4680d0c07315dab24fe7333c62f56bc19ec4e4 /drivers
parent9b82f05f869a823d43ea4186f5f732f2924d3693 (diff)
parent313f16e2e35abb833eab5bdebc6ae30699adca18 (diff)
Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler updates from Ingo Molnar: "The main changes in this cycle are: - Various NUMA scheduling updates: harmonize the load-balancer and NUMA placement logic to not work against each other. The intended result is better locality, better utilization and fewer migrations. - Introduce Thermal Pressure tracking and optimizations, to improve task placement on thermally overloaded systems. - Implement frequency invariant scheduler accounting on (some) x86 CPUs. This is done by observing and sampling the 'recent' CPU frequency average at ~tick boundaries. The CPU provides this data via the APERF/MPERF MSRs. This hopefully makes our capacity estimates more precise and keeps tasks on the same CPU better even if it might seem overloaded at a lower momentary frequency. (As usual, turbo mode is a complication that we resolve by observing the maximum frequency and renormalizing to it.) - Add asymmetric CPU capacity wakeup scan to improve capacity utilization on asymmetric topologies. (big.LITTLE systems) - PSI fixes and optimizations. - RT scheduling capacity awareness fixes & improvements. - Optimize the CONFIG_RT_GROUP_SCHED constraints code. - Misc fixes, cleanups and optimizations - see the changelog for details" * 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (62 commits) threads: Update PID limit comment according to futex UAPI change sched/fair: Fix condition of avg_load calculation sched/rt: cpupri_find: Trigger a full search as fallback kthread: Do not preempt current task if it is going to call schedule() sched/fair: Improve spreading of utilization sched: Avoid scale real weight down to zero psi: Move PF_MEMSTALL out of task->flags MAINTAINERS: Add maintenance information for psi psi: Optimize switching tasks inside shared cgroups psi: Fix cpu.pressure for cpu.max and competing cgroups sched/core: Distribute tasks within affinity masks sched/fair: Fix enqueue_task_fair warning thermal/cpu-cooling, sched/core: Move the arch_set_thermal_pressure() API to generic scheduler code sched/rt: Remove unnecessary push for unfit tasks sched/rt: Allow pulling unfitting task sched/rt: Optimize cpupri_find() on non-heterogenous systems sched/rt: Re-instate old behavior in select_task_rq_rt() sched/rt: cpupri_find: Implement fallback mechanism for !fit case sched/fair: Fix reordering of enqueue/dequeue_task_fair() sched/fair: Fix runnable_avg for throttled cfs ...
Diffstat (limited to 'drivers')
-rw-r--r--drivers/cpufreq/intel_pstate.c1
-rw-r--r--drivers/thermal/cpufreq_cooling.c19
2 files changed, 18 insertions, 2 deletions
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 95abbf66e95e..4d1e25d1ced1 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -922,6 +922,7 @@ static void intel_pstate_update_limits(unsigned int cpu)
*/
if (global.turbo_disabled_mf != global.turbo_disabled) {
global.turbo_disabled_mf = global.turbo_disabled;
+ arch_set_max_freq_ratio(global.turbo_disabled);
for_each_possible_cpu(cpu)
intel_pstate_update_max_freq(cpu);
} else {
diff --git a/drivers/thermal/cpufreq_cooling.c b/drivers/thermal/cpufreq_cooling.c
index fe83d7a210d4..4ae8c856c88e 100644
--- a/drivers/thermal/cpufreq_cooling.c
+++ b/drivers/thermal/cpufreq_cooling.c
@@ -431,6 +431,10 @@ static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev,
unsigned long state)
{
struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata;
+ struct cpumask *cpus;
+ unsigned int frequency;
+ unsigned long max_capacity, capacity;
+ int ret;
/* Request state should be less than max_level */
if (WARN_ON(state > cpufreq_cdev->max_level))
@@ -442,8 +446,19 @@ static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev,
cpufreq_cdev->cpufreq_state = state;
- return freq_qos_update_request(&cpufreq_cdev->qos_req,
- get_state_freq(cpufreq_cdev, state));
+ frequency = get_state_freq(cpufreq_cdev, state);
+
+ ret = freq_qos_update_request(&cpufreq_cdev->qos_req, frequency);
+
+ if (ret > 0) {
+ cpus = cpufreq_cdev->policy->cpus;
+ max_capacity = arch_scale_cpu_capacity(cpumask_first(cpus));
+ capacity = frequency * max_capacity;
+ capacity /= cpufreq_cdev->policy->cpuinfo.max_freq;
+ arch_set_thermal_pressure(cpus, max_capacity - capacity);
+ }
+
+ return ret;
}
/* Bind cpufreq callbacks to thermal cooling device ops */