This patch adds cpufreq callbacks to dpm_{suspend|resume}_noirq() for handling suspend/resume of cpufreq governors.
There are multiple problems that are fixed by this patch: - Nishanth Menon (TI) found an interesting problem on his platform, OMAP. His board wasn't working well with suspend/resume as calls for removing non-boot CPUs was turning out into a call to drivers ->target() which then tries to play with regulators. But regulators and their I2C bus were already suspended and this resulted in a failure. Many platforms have such problems, samsung, tegra, etc.. They solved it with driver specific PM notifiers where they used to disable their driver's ->target() routine. - Lan Tianyu (Intel) & Jinhyuk Choi (Broadcom) found another issue where tunables configuration for clusters/sockets with non-boot CPUs was getting lost after suspend/resume, as we were notifying governors with CPUFREQ_GOV_POLICY_EXIT on removal of the last cpu for that policy and so deallocating memory for tunables. This is also fixed with this patch as we don't allow any operation on Governors during suspend/resume now.
Reported-and-tested-by: Lan Tianyu tianyu.lan@intel.com Reported-and-tested-by: Nishanth Menon nm@ti.com Reported-by: Jinhyuk Choi jinchoi@broadcom.com Signed-off-by: Viresh Kumar viresh.kumar@linaro.org ---
This is almost same as 1/6 of V3 version of this patchset:
https://lkml.org/lkml/2013/11/25/838
This is done to get some initial fixes for 3.13. These are already tested by both the reporters of initial problems. Tegra/exynos/s5p will keep running their PM notifiers until v3.14, as they are currently able to work with them..
drivers/base/power/main.c | 3 +++ drivers/cpufreq/cpufreq.c | 50 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/cpufreq.h | 8 ++++++++ 3 files changed, 61 insertions(+)
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 1b41fca..e3219df 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -29,6 +29,7 @@ #include <linux/async.h> #include <linux/suspend.h> #include <trace/events/power.h> +#include <linux/cpufreq.h> #include <linux/cpuidle.h> #include <linux/timer.h>
@@ -540,6 +541,7 @@ static void dpm_resume_noirq(pm_message_t state) dpm_show_time(starttime, state, "noirq"); resume_device_irqs(); cpuidle_resume(); + cpufreq_resume(); }
/** @@ -955,6 +957,7 @@ static int dpm_suspend_noirq(pm_message_t state) ktime_t starttime = ktime_get(); int error = 0;
+ cpufreq_suspend(); cpuidle_pause(); suspend_device_irqs(); mutex_lock(&dpm_list_mtx); diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 02d534d..b6c7821 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -26,6 +26,7 @@ #include <linux/module.h> #include <linux/mutex.h> #include <linux/slab.h> +#include <linux/suspend.h> #include <linux/syscore_ops.h> #include <linux/tick.h> #include <trace/events/power.h> @@ -47,6 +48,9 @@ static LIST_HEAD(cpufreq_policy_list); static DEFINE_PER_CPU(char[CPUFREQ_NAME_LEN], cpufreq_cpu_governor); #endif
+/* Flag to suspend/resume CPUFreq governors */ +static bool cpufreq_suspended; + static inline bool has_target(void) { return cpufreq_driver->target_index || cpufreq_driver->target; @@ -1462,6 +1466,48 @@ static struct subsys_interface cpufreq_interface = { .remove_dev = cpufreq_remove_dev, };
+/* + * Callbacks for suspending/resuming governors as some platforms can't change + * frequency after this point in suspend cycle. Because some of the devices + * (like: i2c, regulators, etc) they use for changing frequency are suspended + * quickly after this point. + */ +void cpufreq_suspend(void) +{ + struct cpufreq_policy *policy; + + if (!has_target()) + return; + + pr_debug("%s: Suspending Governors\n", __func__); + + list_for_each_entry(policy, &cpufreq_policy_list, policy_list) + if (__cpufreq_governor(policy, CPUFREQ_GOV_STOP)) + pr_err("%s: Failed to stop governor for policy: %p\n", + __func__, policy); + + cpufreq_suspended = true; +} + +void cpufreq_resume(void) +{ + struct cpufreq_policy *policy; + + if (!has_target()) + return; + + pr_debug("%s: Resuming Governors\n", __func__); + + cpufreq_suspended = false; + + list_for_each_entry(policy, &cpufreq_policy_list, policy_list) + if (__cpufreq_governor(policy, CPUFREQ_GOV_START) || + __cpufreq_governor(policy, + CPUFREQ_GOV_LIMITS)) + pr_err("%s: Failed to start governor for policy: %p\n", + __func__, policy); +} + /** * cpufreq_bp_suspend - Prepare the boot CPU for system suspend. * @@ -1764,6 +1810,10 @@ static int __cpufreq_governor(struct cpufreq_policy *policy, struct cpufreq_governor *gov = NULL; #endif
+ /* Don't start any governor operations if we are entering suspend */ + if (cpufreq_suspended) + return 0; + if (policy->governor->max_transition_latency && policy->cpuinfo.transition_latency > policy->governor->max_transition_latency) { diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index dc196bb..ee5fe9d 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -280,6 +280,14 @@ cpufreq_verify_within_cpu_limits(struct cpufreq_policy *policy) policy->cpuinfo.max_freq); }
+#ifdef CONFIG_CPU_FREQ +void cpufreq_suspend(void); +void cpufreq_resume(void); +#else +static inline void cpufreq_suspend(void) {} +static inline void cpufreq_resume(void) {} +#endif + /********************************************************************* * CPUFREQ NOTIFIER INTERFACE * *********************************************************************/