From 4fb352df14de4b5277f38a9874f7c19cf641ae4d Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 5 Dec 2025 16:24:05 +0100 Subject: PM: sleep: Do not flag runtime PM workqueue as freezable Till now, the runtime PM workqueue has been flagged as freezable, so it does not process work items during system-wide PM transitions like system suspend and resume. The original reason to do that was to reduce the likelihood of runtime PM getting in the way of system-wide PM processing, but now it is mostly an optimization because (1) runtime suspend of devices is prevented by bumping up their runtime PM usage counters in device_prepare() and (2) device drivers are expected to disable runtime PM for the devices handled by them before they embark on system-wide PM activities that may change the state of the hardware or otherwise interfere with runtime PM. However, it prevents asynchronous runtime resume of devices from working during system-wide PM transitions, which is confusing because synchronous runtime resume is not prevented at the same time, and it also sometimes turns out to be problematic. For example, it has been reported that blk_queue_enter() may deadlock during a system suspend transition because of the pm_request_resume() usage in it [1]. It may also deadlock during a system resume transition in a similar way. That happens because the asynchronous runtime resume of the given device is not processed due to the freezing of the runtime PM workqueue. While it may be better to address this particular issue in the block layer, the very presence of it means that similar problems may be expected to occur elsewhere. For this reason, remove the WQ_FREEZABLE flag from the runtime PM workqueue and make device_suspend_late() use the generic variant of pm_runtime_disable() that will carry out runtime PM of the device synchronously if there is pending resume work for it. Also update the comment before the pm_runtime_disable() call in device_suspend_late(), to document the fact that the runtime PM should not be expected to work for the device until the end of device_resume_early(), and update the related documentation. This change may, even though it is not expected to, uncover some latent issues related to queuing up asynchronous runtime resume work items during system suspend or hibernation. However, they should be limited to the interference between runtime resume and system-wide PM callbacks in the cases when device drivers start to handle system-wide PM before disabling runtime PM as described above. Link: https://lore.kernel.org/linux-pm/20251126101636.205505-2-yang.yang@vivo.com/ Signed-off-by: Rafael J. Wysocki Reviewed-by: Ulf Hansson Link: https://patch.msgid.link/12794222.O9o76ZdvQC@rafael.j.wysocki --- kernel/power/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/power/main.c b/kernel/power/main.c index 03b2c5495c77..5f8c9e12eaec 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -1125,7 +1125,7 @@ EXPORT_SYMBOL_GPL(pm_wq); static int __init pm_start_workqueues(void) { - pm_wq = alloc_workqueue("pm", WQ_FREEZABLE | WQ_UNBOUND, 0); + pm_wq = alloc_workqueue("pm", WQ_UNBOUND, 0); if (!pm_wq) return -ENOMEM; -- cgit v1.2.3 From e9df6eba060c6db2f7f3fd8666d1af0a369d6f7b Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 8 Jan 2026 16:05:37 +0100 Subject: genirq/chip: Change irq_chip_pm_put() return type to void The irq_chip_pm_put() return value is only used in __irq_do_set_handler() to trigger a WARN_ON() if it is negative, but doing so is not useful because irq_chip_pm_put() simply passes the pm_runtime_put() return value to its callers. Returning an error code from pm_runtime_put() merely means that it has not queued up a work item to check whether or not the device can be suspended and there are many perfectly valid situations in which that can happen, like after writing "on" to the devices' runtime PM "control" attribute in sysfs for one example. For this reason, modify irq_chip_pm_put() to discard the pm_runtime_put() return value, change its return type to void, and drop the WARN_ON() around the irq_chip_pm_put() invocation from __irq_do_set_handler(). Also update the irq_chip_pm_put() kerneldoc comment to be more accurate. This will facilitate a planned change of the pm_runtime_put() return type to void in the future. Signed-off-by: Rafael J. Wysocki Reviewed-by: Thomas Gleixner Link: https://patch.msgid.link/5075294.31r3eYUQgx@rafael.j.wysocki --- kernel/irq/chip.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 678f094d261a..23f22f3d5207 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -974,7 +974,7 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle, irq_state_set_disabled(desc); if (is_chained) { desc->action = NULL; - WARN_ON(irq_chip_pm_put(irq_desc_get_irq_data(desc))); + irq_chip_pm_put(irq_desc_get_irq_data(desc)); } desc->depth = 1; } @@ -1530,20 +1530,20 @@ int irq_chip_pm_get(struct irq_data *data) } /** - * irq_chip_pm_put - Disable power for an IRQ chip + * irq_chip_pm_put - Drop a PM reference on an IRQ chip * @data: Pointer to interrupt specific data * - * Disable the power to the IRQ chip referenced by the interrupt data - * structure, belongs. Note that power will only be disabled, once this - * function has been called for all IRQs that have called irq_chip_pm_get(). + * Drop a power management reference, acquired via irq_chip_pm_get(), on the IRQ + * chip represented by the interrupt data structure. + * + * Note that this will not disable power to the IRQ chip until this function + * has been called for all IRQs that have called irq_chip_pm_get() and it may + * not disable power at all (if user space prevents that, for example). */ -int irq_chip_pm_put(struct irq_data *data) +void irq_chip_pm_put(struct irq_data *data) { struct device *dev = irq_get_pm_device(data); - int retval = 0; - - if (IS_ENABLED(CONFIG_PM) && dev) - retval = pm_runtime_put(dev); - return (retval < 0) ? retval : 0; + if (dev) + pm_runtime_put(dev); } -- cgit v1.2.3 From 1081c1649da989ef9cbc01ffa99babc190df6077 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 26 Jan 2026 21:03:57 +0100 Subject: PM: hibernate: Drop NULL pointer checks before acomp_request_free() Since acomp_request_free() checks its argument against NULL, the NULL pointer checks before calling it added by commit ("7966cf0ebe32 PM: hibernate: Fix crash when freeing invalid crypto compressor") are redundant, so drop them. No intentional functional impact. Signed-off-by: Rafael J. Wysocki Link: https://patch.msgid.link/6233709.lOV4Wx5bFT@rafael.j.wysocki --- kernel/power/swap.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 8050e5182835..7e462957c9bf 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -902,8 +902,8 @@ out_clean: for (thr = 0; thr < nr_threads; thr++) { if (data[thr].thr) kthread_stop(data[thr].thr); - if (data[thr].cr) - acomp_request_free(data[thr].cr); + + acomp_request_free(data[thr].cr); if (!IS_ERR_OR_NULL(data[thr].cc)) crypto_free_acomp(data[thr].cc); @@ -1502,8 +1502,8 @@ out_clean: for (thr = 0; thr < nr_threads; thr++) { if (data[thr].thr) kthread_stop(data[thr].thr); - if (data[thr].cr) - acomp_request_free(data[thr].cr); + + acomp_request_free(data[thr].cr); if (!IS_ERR_OR_NULL(data[thr].cc)) crypto_free_acomp(data[thr].cc); -- cgit v1.2.3 From a554a25e66efea0b78fb3d24f4f19289e037c0dc Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 28 Jan 2026 17:05:27 +0100 Subject: cpufreq: ondemand: Simplify idle cputime granularity test cpufreq calls get_cpu_idle_time_us() just to know if idle cputime accounting has a nanoseconds granularity. Use the appropriate indicator instead to make that deduction. Signed-off-by: Frederic Weisbecker Link: https://patch.msgid.link/aXozx0PXutnm8ECX@localhost.localdomain Signed-off-by: Rafael J. Wysocki --- kernel/time/hrtimer.c | 2 +- kernel/time/tick-internal.h | 2 -- kernel/time/tick-sched.c | 8 +++++++- kernel/time/timer.c | 2 +- 4 files changed, 9 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 0e4bc1ca15ff..1caf02a72ba8 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -943,7 +943,7 @@ void clock_was_set(unsigned int bases) cpumask_var_t mask; int cpu; - if (!hrtimer_hres_active(cpu_base) && !tick_nohz_active) + if (!hrtimer_hres_active(cpu_base) && !tick_nohz_is_active()) goto out_timerfd; if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) { diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 4e4f7bbe2a64..597d816d22e8 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -156,7 +156,6 @@ static inline void tick_nohz_init(void) { } #endif #ifdef CONFIG_NO_HZ_COMMON -extern unsigned long tick_nohz_active; extern void timers_update_nohz(void); extern u64 get_jiffies_update(unsigned long *basej); # ifdef CONFIG_SMP @@ -171,7 +170,6 @@ extern void timer_expire_remote(unsigned int cpu); # endif #else /* CONFIG_NO_HZ_COMMON */ static inline void timers_update_nohz(void) { } -#define tick_nohz_active (0) #endif DECLARE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases); diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 2f8a7923fa27..72e39c793117 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -693,7 +693,7 @@ void __init tick_nohz_init(void) * NO HZ enabled ? */ bool tick_nohz_enabled __read_mostly = true; -unsigned long tick_nohz_active __read_mostly; +static unsigned long tick_nohz_active __read_mostly; /* * Enable / Disable tickless mode */ @@ -704,6 +704,12 @@ static int __init setup_tick_nohz(char *str) __setup("nohz=", setup_tick_nohz); +bool tick_nohz_is_active(void) +{ + return tick_nohz_active; +} +EXPORT_SYMBOL_GPL(tick_nohz_is_active); + bool tick_nohz_tick_stopped(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 1f2364126894..7e1e3bde6b8b 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -281,7 +281,7 @@ DEFINE_STATIC_KEY_FALSE(timers_migration_enabled); static void timers_update_migration(void) { - if (sysctl_timer_migration && tick_nohz_active) + if (sysctl_timer_migration && tick_nohz_is_active()) static_branch_enable(&timers_migration_enabled); else static_branch_disable(&timers_migration_enabled); -- cgit v1.2.3