From 37b82cee81cbe6c436d967ef3d07927f56f4ed76 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sat, 25 Nov 2023 14:55:00 +0800 Subject: [PATCH 1/2] hrtimers: Push pending hrtimers away from outgoing CPU earlier mainline inclusion from mainline-v6.7-rc2 commit 5c0930ccaad5a74d74e8b18b648c5eb21ed2fe94 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8JEVI Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=5c0930ccaad5a74d74e8b18b648c5eb21ed2fe94 -------------------------------- 2b8272ff4a70 ("cpu/hotplug: Prevent self deadlock on CPU hot-unplug") solved the straight forward CPU hotplug deadlock vs. the scheduler bandwidth timer. Yu discovered a more involved variant where a task which has a bandwidth timer started on the outgoing CPU holds a lock and then gets throttled. If the lock required by one of the CPU hotplug callbacks the hotplug operation deadlocks because the unthrottling timer event is not handled on the dying CPU and can only be recovered once the control CPU reaches the hotplug state which pulls the pending hrtimers from the dead CPU. Solve this by pushing the hrtimers away from the dying CPU in the dying callbacks. Nothing can queue a hrtimer on the dying CPU at that point because all other CPUs spin in stop_machine() with interrupts disabled and once the operation is finished the CPU is marked offline. Reported-by: Yu Liao Signed-off-by: Thomas Gleixner Tested-by: Liu Tie Link: https://lore.kernel.org/r/87a5rphara.ffs@tglx Signed-off-by: Yu Liao (cherry picked from commit 1ff7bddaac372218365705ee76184901892fb366) --- include/linux/cpuhotplug.h | 1 + include/linux/hrtimer.h | 4 ++-- kernel/cpu.c | 8 +++++++- kernel/time/hrtimer.c | 33 ++++++++++++--------------------- 4 files changed, 22 insertions(+), 24 deletions(-) diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index b540e5a60ea9..b0b4efe227f8 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -154,6 +154,7 @@ enum cpuhp_state { CPUHP_AP_ARM_CORESIGHT_CTI_STARTING, CPUHP_AP_ARM64_ISNDEP_STARTING, CPUHP_AP_SMPCFD_DYING, + CPUHP_AP_HRTIMERS_DYING, CPUHP_AP_X86_TBOOT_DYING, CPUHP_AP_ARM_CACHE_B15_RAC_DYING, CPUHP_AP_ONLINE, diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index b1f2e4692e66..c1459b7974c5 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -543,9 +543,9 @@ extern void sysrq_timer_list_show(void); int hrtimers_prepare_cpu(unsigned int cpu); #ifdef CONFIG_HOTPLUG_CPU -int hrtimers_dead_cpu(unsigned int cpu); +int hrtimers_cpu_dying(unsigned int cpu); #else -#define hrtimers_dead_cpu NULL +#define hrtimers_cpu_dying NULL #endif #endif diff --git a/kernel/cpu.c b/kernel/cpu.c index c06ced18f78a..79f32a4fb7bb 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -1589,7 +1589,7 @@ static struct cpuhp_step cpuhp_hp_states[] = { [CPUHP_HRTIMERS_PREPARE] = { .name = "hrtimers:prepare", .startup.single = hrtimers_prepare_cpu, - .teardown.single = hrtimers_dead_cpu, + .teardown.single = NULL, }, [CPUHP_SMPCFD_PREPARE] = { .name = "smpcfd:prepare", @@ -1656,6 +1656,12 @@ static struct cpuhp_step cpuhp_hp_states[] = { .startup.single = NULL, .teardown.single = smpcfd_dying_cpu, }, + [CPUHP_AP_HRTIMERS_DYING] = { + .name = "hrtimers:dying", + .startup.single = NULL, + .teardown.single = hrtimers_cpu_dying, + }, + /* Entry state on starting. Interrupts enabled from here on. Transient * state for synchronsization */ [CPUHP_AP_ONLINE] = { diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 544ce87ba38a..0c44e81c4901 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -2112,29 +2112,22 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base, } } -int hrtimers_dead_cpu(unsigned int scpu) +int hrtimers_cpu_dying(unsigned int dying_cpu) { struct hrtimer_cpu_base *old_base, *new_base; - int i; + int i, ncpu = cpumask_first(cpu_active_mask); - BUG_ON(cpu_online(scpu)); - tick_cancel_sched_timer(scpu); + tick_cancel_sched_timer(dying_cpu); + + old_base = this_cpu_ptr(&hrtimer_bases); + new_base = &per_cpu(hrtimer_bases, ncpu); - /* - * this BH disable ensures that raise_softirq_irqoff() does - * not wakeup ksoftirqd (and acquire the pi-lock) while - * holding the cpu_base lock - */ - local_bh_disable(); - local_irq_disable(); - old_base = &per_cpu(hrtimer_bases, scpu); - new_base = this_cpu_ptr(&hrtimer_bases); /* * The caller is globally serialized and nobody else * takes two locks at once, deadlock is not possible. */ - raw_spin_lock(&new_base->lock); - raw_spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING); + raw_spin_lock(&old_base->lock); + raw_spin_lock_nested(&new_base->lock, SINGLE_DEPTH_NESTING); for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { migrate_hrtimer_list(&old_base->clock_base[i], @@ -2145,15 +2138,13 @@ int hrtimers_dead_cpu(unsigned int scpu) * The migration might have changed the first expiring softirq * timer on this CPU. Update it. */ - hrtimer_update_softirq_timer(new_base, false); + __hrtimer_get_next_event(new_base, HRTIMER_ACTIVE_SOFT); + /* Tell the other CPU to retrigger the next event */ + smp_call_function_single(ncpu, retrigger_next_event, NULL, 0); - raw_spin_unlock(&old_base->lock); raw_spin_unlock(&new_base->lock); + raw_spin_unlock(&old_base->lock); - /* Check, if we got expired work to do */ - __hrtimer_peek_ahead_timers(); - local_irq_enable(); - local_bh_enable(); return 0; } -- Gitee From 5d9b99af5a5e57827a5148da5418e99fd267057a Mon Sep 17 00:00:00 2001 From: Yu Liao Date: Sat, 25 Nov 2023 14:55:01 +0800 Subject: [PATCH 2/2] cpu/hotplug: fix kabi breakage in enum cpuhp_state hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8JEVI -------------------------------- Commit baecdf2dbe73 ("hrtimers: Push pending hrtimers away from outgoing CPU earlier") add a new step in enum cpuhp_state breaks kabi. In order to fix the kabi breakage, we had to move the hrtimers:dying step into smpcfd:dying and create a new function smpcfd_and_hrtimer_dying_cpu(). Signed-off-by: Yu Liao (cherry picked from commit 6fc275daa0a74e72c273411faffed333c40b355b) --- include/linux/cpuhotplug.h | 1 - include/linux/hrtimer.h | 2 +- include/linux/smp.h | 1 + kernel/cpu.c | 19 +++++++++++++------ kernel/smp.c | 8 ++++++++ 5 files changed, 23 insertions(+), 8 deletions(-) diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index b0b4efe227f8..b540e5a60ea9 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -154,7 +154,6 @@ enum cpuhp_state { CPUHP_AP_ARM_CORESIGHT_CTI_STARTING, CPUHP_AP_ARM64_ISNDEP_STARTING, CPUHP_AP_SMPCFD_DYING, - CPUHP_AP_HRTIMERS_DYING, CPUHP_AP_X86_TBOOT_DYING, CPUHP_AP_ARM_CACHE_B15_RAC_DYING, CPUHP_AP_ONLINE, diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index c1459b7974c5..cfc62d447fa0 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -545,7 +545,7 @@ int hrtimers_prepare_cpu(unsigned int cpu); #ifdef CONFIG_HOTPLUG_CPU int hrtimers_cpu_dying(unsigned int cpu); #else -#define hrtimers_cpu_dying NULL +static inline int hrtimers_cpu_dying(unsigned int cpu) { return 0; } #endif #endif diff --git a/include/linux/smp.h b/include/linux/smp.h index 84a0b4828f66..812c26f61300 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -278,5 +278,6 @@ int smp_call_on_cpu(unsigned int cpu, int (*func)(void *), void *par, int smpcfd_prepare_cpu(unsigned int cpu); int smpcfd_dead_cpu(unsigned int cpu); int smpcfd_dying_cpu(unsigned int cpu); +int smpcfd_and_hrtimer_dying_cpu(unsigned int cpu); #endif /* __LINUX_SMP_H */ diff --git a/kernel/cpu.c b/kernel/cpu.c index 79f32a4fb7bb..b7b2560d060b 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -1651,17 +1651,24 @@ static struct cpuhp_step cpuhp_hp_states[] = { .startup.single = NULL, .teardown.single = rcutree_dying_cpu, }, + /* + * In order to fix the kabi breakage, we had to move the hrtimers:dying + * step into smpcfd:dying and create a new function smpcfd_and_hrtimer_dying_cpu(). + * Please ensure that there are no other steps with teardown handler + * between smpcfd:dying and cpu:teardown. + */ [CPUHP_AP_SMPCFD_DYING] = { .name = "smpcfd:dying", .startup.single = NULL, - .teardown.single = smpcfd_dying_cpu, - }, - [CPUHP_AP_HRTIMERS_DYING] = { - .name = "hrtimers:dying", - .startup.single = NULL, - .teardown.single = hrtimers_cpu_dying, + .teardown.single = smpcfd_and_hrtimer_dying_cpu, }, + /* + * Attention: Please do not add steps between smpcfd:dying + * and ap:online. Please refer to the above for specific + * reasons. + */ + /* Entry state on starting. Interrupts enabled from here on. Transient * state for synchronsization */ [CPUHP_AP_ONLINE] = { diff --git a/kernel/smp.c b/kernel/smp.c index 114776d0d11e..863cf7e2dbdc 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -75,6 +75,14 @@ int smpcfd_dead_cpu(unsigned int cpu) return 0; } +int smpcfd_and_hrtimer_dying_cpu(unsigned int cpu) +{ + hrtimers_cpu_dying(cpu); + smpcfd_dying_cpu(cpu); + + return 0; +} + int smpcfd_dying_cpu(unsigned int cpu) { /* -- Gitee