summaryrefslogtreecommitdiffstats
path: root/drivers/base/power/domain_governor.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2021-02-20 21:42:18 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2021-02-20 21:42:18 -0800
commit02f9fc286e039d0bef7284fb1200ee755b525bde (patch)
tree2ce396501ee2590ca7e37c3ea6f058d164b41474 /drivers/base/power/domain_governor.c
parent5d99aa093b566d234b51b7822c67059e2bd3ed8d (diff)
parenta9a939cb34dfffb9f43b988a681d2566ca157b74 (diff)
downloadlinux-02f9fc286e039d0bef7284fb1200ee755b525bde.tar.gz
linux-02f9fc286e039d0bef7284fb1200ee755b525bde.tar.bz2
linux-02f9fc286e039d0bef7284fb1200ee755b525bde.zip
Merge tag 'pm-5.12-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
Pull power management updates from Rafael Wysocki: "These add a new power capping facility allowing aggregate power constraints to be applied to sets of devices in a distributed manner, add a new CPU ID to the RAPL power capping driver and improve it, drop a cpufreq driver belonging to a platform that is not supported any more, drop two redundant cpufreq driver flags, update cpufreq drivers (intel_pstate, brcmstb-avs, qcom-hw), update the operating performance points (OPP) framework (code cleanups, new helpers, devfreq-related modifications), clean up devfreq, extend the PM clock layer, update the cpupower utility and make assorted janitorial changes. Specifics: - Add new power capping facility called DTPM (Dynamic Thermal Power Management), based on the existing power capping framework, to allow aggregate power constraints to be applied to sets of devices in a distributed manner, along with a CPU backend driver based on the Energy Model (Daniel Lezcano, Dan Carpenter, Colin Ian King). - Add AlderLake Mobile support to the Intel RAPL power capping driver and make it use the topology interface when laying out the system topology (Zhang Rui, Yunfeng Ye). - Drop the cpufreq tango driver belonging to a platform that is not supported any more (Arnd Bergmann). - Drop the redundant CPUFREQ_STICKY and CPUFREQ_PM_NO_WARN cpufreq driver flags (Viresh Kumar). - Update cpufreq drivers: * Fix max CPU frequency discovery in the intel_pstate driver and make janitorial changes in it (Chen Yu, Rafael Wysocki, Nigel Christian). * Fix resource leaks in the brcmstb-avs-cpufreq driver (Christophe JAILLET). * Make the tegra20 driver use the resource-managed API (Dmitry Osipenko). * Enable boost support in the qcom-hw driver (Shawn Guo). - Update the operating performance points (OPP) framework: * Clean up the OPP core (Dmitry Osipenko, Viresh Kumar). * Extend the OPP API by adding new helpers to it (Dmitry Osipenko, Viresh Kumar). * Allow required OPPs to be used for devfreq devices and update the devfreq governor code accordingly (Saravana Kannan). * Prepare the framework for introducing new dev_pm_opp_set_opp() helper (Viresh Kumar). * Drop dev_pm_opp_set_bw() and update related drivers (Viresh Kumar). * Allow lazy linking of required-OPPs (Viresh Kumar). - Simplify and clean up devfreq somewhat (Lukasz Luba, Yang Li, Pierre Kuo). - Update the generic power domains (genpd) framework: * Use device's next wakeup to determine domain idle state (Lina Iyer). * Improve initialization and debug (Dmitry Osipenko). * Simplify computations (Abaci Team). - Make janitorial changes in the core code handling system sleep and PM-runtime (Bhaskar Chowdhury, Bjorn Helgaas, Rikard Falkeborn, Zqiang). - Update the MAINTAINERS entry for the exynos cpuidle driver and drop DEBUG definition from intel_idle (Krzysztof Kozlowski, Tom Rix). - Extend the PM clock layer to cover clocks that must sleep (Nicolas Pitre). - Update the cpupower utility: * Update cpupower command, add support for AMD family 0x19 and clean up the code to remove many of the family checks to make future family updates easier (Nathan Fontenot, Robert Richter). * Add Makefile dependencies for install targets to allow building cpupower in parallel rather than serially (Ivan Babrou). - Make janitorial changes in power management Kconfig (Lukasz Luba)" * tag 'pm-5.12-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (89 commits) MAINTAINERS: cpuidle: exynos: include header in file pattern powercap: intel_rapl: Use topology interface in rapl_init_domains() powercap: intel_rapl: Use topology interface in rapl_add_package() PM: sleep: Constify static struct attribute_group PM: Kconfig: remove unneeded "default n" options PM: EM: update Kconfig description and drop "default n" option cpufreq: Remove unused flag CPUFREQ_PM_NO_WARN cpufreq: Remove CPUFREQ_STICKY flag PM / devfreq: Add required OPPs support to passive governor PM / devfreq: Cache OPP table reference in devfreq OPP: Add function to look up required OPP's for a given OPP PM / devfreq: rk3399_dmc: Remove unneeded semicolon opp: Replace ENOTSUPP with EOPNOTSUPP opp: Fix "foo * bar" should be "foo *bar" opp: Don't ignore clk_get() errors other than -ENOENT opp: Update bandwidth requirements based on scaling up/down opp: Allow lazy-linking of required-opps opp: Remove dev_pm_opp_set_bw() devfreq: tegra30: Migrate to dev_pm_opp_set_opp() drm: msm: Migrate to dev_pm_opp_set_opp() ...
Diffstat (limited to 'drivers/base/power/domain_governor.c')
-rw-r--r--drivers/base/power/domain_governor.c102
1 files changed, 93 insertions, 9 deletions
diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c
index 490ed7deb99a..c6c218758f0b 100644
--- a/drivers/base/power/domain_governor.c
+++ b/drivers/base/power/domain_governor.c
@@ -117,6 +117,55 @@ static bool default_suspend_ok(struct device *dev)
return td->cached_suspend_ok;
}
+static void update_domain_next_wakeup(struct generic_pm_domain *genpd, ktime_t now)
+{
+ ktime_t domain_wakeup = KTIME_MAX;
+ ktime_t next_wakeup;
+ struct pm_domain_data *pdd;
+ struct gpd_link *link;
+
+ if (!(genpd->flags & GENPD_FLAG_MIN_RESIDENCY))
+ return;
+
+ /*
+ * Devices that have a predictable wakeup pattern, may specify
+ * their next wakeup. Let's find the next wakeup from all the
+ * devices attached to this domain and from all the sub-domains.
+ * It is possible that component's a next wakeup may have become
+ * stale when we read that here. We will ignore to ensure the domain
+ * is able to enter its optimal idle state.
+ */
+ list_for_each_entry(pdd, &genpd->dev_list, list_node) {
+ next_wakeup = to_gpd_data(pdd)->next_wakeup;
+ if (next_wakeup != KTIME_MAX && !ktime_before(next_wakeup, now))
+ if (ktime_before(next_wakeup, domain_wakeup))
+ domain_wakeup = next_wakeup;
+ }
+
+ list_for_each_entry(link, &genpd->parent_links, parent_node) {
+ next_wakeup = link->child->next_wakeup;
+ if (next_wakeup != KTIME_MAX && !ktime_before(next_wakeup, now))
+ if (ktime_before(next_wakeup, domain_wakeup))
+ domain_wakeup = next_wakeup;
+ }
+
+ genpd->next_wakeup = domain_wakeup;
+}
+
+static bool next_wakeup_allows_state(struct generic_pm_domain *genpd,
+ unsigned int state, ktime_t now)
+{
+ ktime_t domain_wakeup = genpd->next_wakeup;
+ s64 idle_time_ns, min_sleep_ns;
+
+ min_sleep_ns = genpd->states[state].power_off_latency_ns +
+ genpd->states[state].residency_ns;
+
+ idle_time_ns = ktime_to_ns(ktime_sub(domain_wakeup, now));
+
+ return idle_time_ns >= min_sleep_ns;
+}
+
static bool __default_power_down_ok(struct dev_pm_domain *pd,
unsigned int state)
{
@@ -201,16 +250,41 @@ static bool __default_power_down_ok(struct dev_pm_domain *pd,
}
/**
- * default_power_down_ok - Default generic PM domain power off governor routine.
+ * _default_power_down_ok - Default generic PM domain power off governor routine.
* @pd: PM domain to check.
*
* This routine must be executed under the PM domain's lock.
*/
-static bool default_power_down_ok(struct dev_pm_domain *pd)
+static bool _default_power_down_ok(struct dev_pm_domain *pd, ktime_t now)
{
struct generic_pm_domain *genpd = pd_to_genpd(pd);
+ int state_idx = genpd->state_count - 1;
struct gpd_link *link;
+ /*
+ * Find the next wakeup from devices that can determine their own wakeup
+ * to find when the domain would wakeup and do it for every device down
+ * the hierarchy. It is not worth while to sleep if the state's residency
+ * cannot be met.
+ */
+ update_domain_next_wakeup(genpd, now);
+ if ((genpd->flags & GENPD_FLAG_MIN_RESIDENCY) && (genpd->next_wakeup != KTIME_MAX)) {
+ /* Let's find out the deepest domain idle state, the devices prefer */
+ while (state_idx >= 0) {
+ if (next_wakeup_allows_state(genpd, state_idx, now)) {
+ genpd->max_off_time_changed = true;
+ break;
+ }
+ state_idx--;
+ }
+
+ if (state_idx < 0) {
+ state_idx = 0;
+ genpd->cached_power_down_ok = false;
+ goto done;
+ }
+ }
+
if (!genpd->max_off_time_changed) {
genpd->state_idx = genpd->cached_power_down_state_idx;
return genpd->cached_power_down_ok;
@@ -228,21 +302,30 @@ static bool default_power_down_ok(struct dev_pm_domain *pd)
genpd->max_off_time_ns = -1;
genpd->max_off_time_changed = false;
genpd->cached_power_down_ok = true;
- genpd->state_idx = genpd->state_count - 1;
- /* Find a state to power down to, starting from the deepest. */
- while (!__default_power_down_ok(pd, genpd->state_idx)) {
- if (genpd->state_idx == 0) {
+ /*
+ * Find a state to power down to, starting from the state
+ * determined by the next wakeup.
+ */
+ while (!__default_power_down_ok(pd, state_idx)) {
+ if (state_idx == 0) {
genpd->cached_power_down_ok = false;
break;
}
- genpd->state_idx--;
+ state_idx--;
}
+done:
+ genpd->state_idx = state_idx;
genpd->cached_power_down_state_idx = genpd->state_idx;
return genpd->cached_power_down_ok;
}
+static bool default_power_down_ok(struct dev_pm_domain *pd)
+{
+ return _default_power_down_ok(pd, ktime_get());
+}
+
static bool always_on_power_down_ok(struct dev_pm_domain *domain)
{
return false;
@@ -254,11 +337,12 @@ static bool cpu_power_down_ok(struct dev_pm_domain *pd)
struct generic_pm_domain *genpd = pd_to_genpd(pd);
struct cpuidle_device *dev;
ktime_t domain_wakeup, next_hrtimer;
+ ktime_t now = ktime_get();
s64 idle_duration_ns;
int cpu, i;
/* Validate dev PM QoS constraints. */
- if (!default_power_down_ok(pd))
+ if (!_default_power_down_ok(pd, now))
return false;
if (!(genpd->flags & GENPD_FLAG_CPU_DOMAIN))
@@ -280,7 +364,7 @@ static bool cpu_power_down_ok(struct dev_pm_domain *pd)
}
/* The minimum idle duration is from now - until the next wakeup. */
- idle_duration_ns = ktime_to_ns(ktime_sub(domain_wakeup, ktime_get()));
+ idle_duration_ns = ktime_to_ns(ktime_sub(domain_wakeup, now));
if (idle_duration_ns <= 0)
return false;