diff --git a/arch/arm/kernel/reboot.c b/arch/arm/kernel/reboot.c index bb18ed0539f4..0ce388f15422 100644 --- a/arch/arm/kernel/reboot.c +++ b/arch/arm/kernel/reboot.c @@ -88,11 +88,11 @@ void soft_restart(unsigned long addr) * to execute e.g. a RAM-based pin loop is not sufficient. This allows the * kexec'd kernel to use any and all RAM as it sees fit, without having to * avoid any code or data used by any SW CPU pin loop. The CPU hotplug - * functionality embodied in disable_nonboot_cpus() to achieve this. + * functionality embodied in smp_shutdown_nonboot_cpus() to achieve this. */ void machine_shutdown(void) { - disable_nonboot_cpus(); + smp_shutdown_nonboot_cpus(reboot_cpu); } /* diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index 590963c9c609..5b73e92c99e3 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -166,14 +166,11 @@ int arch_hibernation_header_restore(void *addr) sleep_cpu = -EINVAL; return -EINVAL; } - if (!cpu_online(sleep_cpu)) { - pr_info("Hibernated on a CPU that is offline! Bringing CPU up.\n"); - ret = cpu_up(sleep_cpu); - if (ret) { - pr_err("Failed to bring hibernate-CPU up!\n"); - sleep_cpu = -EINVAL; - return ret; - } + + ret = bringup_hibernate_cpu(sleep_cpu); + if (ret) { + sleep_cpu = -EINVAL; + return ret; } resume_hdr = *hdr; diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 00626057a384..3e5a6ad66cbe 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -141,11 +141,11 @@ void arch_cpu_idle_dead(void) * to execute e.g. a RAM-based pin loop is not sufficient. This allows the * kexec'd kernel to use any and all RAM as it sees fit, without having to * avoid any code or data used by any SW CPU pin loop. The CPU hotplug - * functionality embodied in disable_nonboot_cpus() to achieve this. + * functionality embodied in smpt_shutdown_nonboot_cpus() to achieve this. */ void machine_shutdown(void) { - disable_nonboot_cpus(); + smp_shutdown_nonboot_cpus(reboot_cpu); } /* diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index 743aaf528327..10cb9382ab76 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -646,14 +646,8 @@ cpu_halt (void) void machine_shutdown(void) { -#ifdef CONFIG_HOTPLUG_CPU - int cpu; + smp_shutdown_nonboot_cpus(reboot_cpu); - for_each_online_cpu(cpu) { - if (cpu != smp_processor_id()) - cpu_down(cpu); - } -#endif #ifdef CONFIG_KEXEC kexec_disable_iosapic(); #endif diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index f510c00bda88..0def6242b3ea 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -696,29 +696,22 @@ EXPORT_SYMBOL(flush_tlb_one); #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST -static DEFINE_PER_CPU(atomic_t, tick_broadcast_count); static DEFINE_PER_CPU(call_single_data_t, tick_broadcast_csd); void tick_broadcast(const struct cpumask *mask) { - atomic_t *count; call_single_data_t *csd; int cpu; for_each_cpu(cpu, mask) { - count = &per_cpu(tick_broadcast_count, cpu); csd = &per_cpu(tick_broadcast_csd, cpu); - - if (atomic_inc_return(count) == 1) - smp_call_function_single_async(cpu, csd); + smp_call_function_single_async(cpu, csd); } } static void tick_broadcast_callee(void *info) { - int cpu = smp_processor_id(); tick_receive_broadcast(); - atomic_set(&per_cpu(tick_broadcast_count, cpu), 0); } static int __init tick_broadcast_init(void) diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c index 13f771f74ee3..7f2d0c0ecc80 100644 --- a/arch/parisc/kernel/processor.c +++ b/arch/parisc/kernel/processor.c @@ -212,7 +212,7 @@ static int __init processor_probe(struct parisc_device *dev) #ifdef CONFIG_SMP if (cpuid) { set_cpu_present(cpuid, true); - cpu_up(cpuid); + add_cpu(cpuid); } #endif diff --git a/arch/powerpc/kexec/core_64.c b/arch/powerpc/kexec/core_64.c index 04a7cba58eff..b4184092172a 100644 --- a/arch/powerpc/kexec/core_64.c +++ b/arch/powerpc/kexec/core_64.c @@ -212,7 +212,7 @@ static void wake_offline_cpus(void) if (!cpu_online(cpu)) { printk(KERN_INFO "kexec: Waking offline cpu %d.\n", cpu); - WARN_ON(cpu_up(cpu)); + WARN_ON(add_cpu(cpu)); } } } diff --git a/arch/sparc/kernel/ds.c b/arch/sparc/kernel/ds.c index bbf59b3b4af8..75232cbd58bf 100644 --- a/arch/sparc/kernel/ds.c +++ b/arch/sparc/kernel/ds.c @@ -555,7 +555,7 @@ static int dr_cpu_configure(struct ds_info *dp, struct ds_cap_state *cp, printk(KERN_INFO "ds-%llu: Starting cpu %d...\n", dp->id, cpu); - err = cpu_up(cpu); + err = add_cpu(cpu); if (err) { __u32 res = DR_CPU_RES_FAILURE; __u32 stat = DR_CPU_STAT_UNCONFIGURED; @@ -611,7 +611,7 @@ static int dr_cpu_unconfigure(struct ds_info *dp, printk(KERN_INFO "ds-%llu: Shutting down cpu %d...\n", dp->id, cpu); - err = cpu_down(cpu); + err = remove_cpu(cpu); if (err) dr_cpu_mark(resp, cpu, ncpus, DR_CPU_RES_FAILURE, diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c index be5bc2e47c71..b8810ebbc8ae 100644 --- a/arch/x86/kernel/topology.c +++ b/arch/x86/kernel/topology.c @@ -59,39 +59,29 @@ __setup("cpu0_hotplug", enable_cpu0_hotplug); */ int _debug_hotplug_cpu(int cpu, int action) { - struct device *dev = get_cpu_device(cpu); int ret; if (!cpu_is_hotpluggable(cpu)) return -EINVAL; - lock_device_hotplug(); - switch (action) { case 0: - ret = cpu_down(cpu); - if (!ret) { + ret = remove_cpu(cpu); + if (!ret) pr_info("DEBUG_HOTPLUG_CPU0: CPU %u is now offline\n", cpu); - dev->offline = true; - kobject_uevent(&dev->kobj, KOBJ_OFFLINE); - } else + else pr_debug("Can't offline CPU%d.\n", cpu); break; case 1: - ret = cpu_up(cpu); - if (!ret) { - dev->offline = false; - kobject_uevent(&dev->kobj, KOBJ_ONLINE); - } else { + ret = add_cpu(cpu); + if (ret) pr_debug("Can't online CPU%d.\n", cpu); - } + break; default: ret = -EINVAL; } - unlock_device_hotplug(); - return ret; } diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c index 673de6063345..109325d77b3e 100644 --- a/arch/x86/mm/mmio-mod.c +++ b/arch/x86/mm/mmio-mod.c @@ -386,7 +386,7 @@ static void enter_uniprocessor(void) put_online_cpus(); for_each_cpu(cpu, downed_cpus) { - err = cpu_down(cpu); + err = remove_cpu(cpu); if (!err) pr_info("CPU%d is down.\n", cpu); else @@ -406,7 +406,7 @@ static void leave_uniprocessor(void) return; pr_notice("Re-enabling CPUs...\n"); for_each_cpu(cpu, downed_cpus) { - err = cpu_up(cpu); + err = add_cpu(cpu); if (!err) pr_info("enabled CPU%d.\n", cpu); else diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 7a43b2ae19f1..2097fa0ebdb5 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -132,7 +132,7 @@ void __init xen_smp_cpus_done(unsigned int max_cpus) if (xen_vcpu_nr(cpu) < MAX_VIRT_CPUS) continue; - rc = cpu_down(cpu); + rc = remove_cpu(cpu); if (rc == 0) { /* diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index df19c002d747..9a1c00fbbaef 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -55,7 +55,7 @@ static int cpu_subsys_online(struct device *dev) if (from_nid == NUMA_NO_NODE) return -ENODEV; - ret = cpu_up(cpuid); + ret = cpu_device_up(dev); /* * When hot adding memory to memoryless node and enabling a cpu * on the node, node number of the cpu may internally change. @@ -69,7 +69,7 @@ static int cpu_subsys_online(struct device *dev) static int cpu_subsys_offline(struct device *dev) { - return cpu_down(dev->id); + return cpu_device_down(dev); } void unregister_cpu(struct cpu *cpu) diff --git a/drivers/firmware/psci/psci_checker.c b/drivers/firmware/psci/psci_checker.c index 6a445397771c..873841af8d57 100644 --- a/drivers/firmware/psci/psci_checker.c +++ b/drivers/firmware/psci/psci_checker.c @@ -84,7 +84,7 @@ static unsigned int down_and_up_cpus(const struct cpumask *cpus, /* Try to power down all CPUs in the mask. */ for_each_cpu(cpu, cpus) { - int ret = cpu_down(cpu); + int ret = remove_cpu(cpu); /* * cpu_down() checks the number of online CPUs before the TOS @@ -116,7 +116,7 @@ static unsigned int down_and_up_cpus(const struct cpumask *cpus, /* Try to power up all the CPUs that have been offlined. */ for_each_cpu(cpu, offlined_cpus) { - int ret = cpu_up(cpu); + int ret = add_cpu(cpu); if (ret != 0) { pr_err("Error occurred (%d) while trying " diff --git a/drivers/xen/cpu_hotplug.c b/drivers/xen/cpu_hotplug.c index f192b6f42da9..ec975decb5de 100644 --- a/drivers/xen/cpu_hotplug.c +++ b/drivers/xen/cpu_hotplug.c @@ -94,7 +94,7 @@ static int setup_cpu_watcher(struct notifier_block *notifier, for_each_possible_cpu(cpu) { if (vcpu_online(cpu) == 0) { - (void)cpu_down(cpu); + device_offline(get_cpu_device(cpu)); set_cpu_present(cpu, false); } } diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 1ca2baf817ed..beaed2dc269e 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -88,10 +88,13 @@ extern ssize_t arch_cpu_release(const char *, size_t); #ifdef CONFIG_SMP extern bool cpuhp_tasks_frozen; -int cpu_up(unsigned int cpu); +int add_cpu(unsigned int cpu); +int cpu_device_up(struct device *dev); void notify_cpu_starting(unsigned int cpu); extern void cpu_maps_update_begin(void); extern void cpu_maps_update_done(void); +int bringup_hibernate_cpu(unsigned int sleep_cpu); +void bringup_nonboot_cpus(unsigned int setup_max_cpus); #else /* CONFIG_SMP */ #define cpuhp_tasks_frozen 0 @@ -117,7 +120,9 @@ extern void lockdep_assert_cpus_held(void); extern void cpu_hotplug_disable(void); extern void cpu_hotplug_enable(void); void clear_tasks_mm_cpumask(int cpu); -int cpu_down(unsigned int cpu); +int remove_cpu(unsigned int cpu); +int cpu_device_down(struct device *dev); +extern void smp_shutdown_nonboot_cpus(unsigned int primary_cpu); #else /* CONFIG_HOTPLUG_CPU */ @@ -129,6 +134,7 @@ static inline int cpus_read_trylock(void) { return true; } static inline void lockdep_assert_cpus_held(void) { } static inline void cpu_hotplug_disable(void) { } static inline void cpu_hotplug_enable(void) { } +static inline void smp_shutdown_nonboot_cpus(unsigned int primary_cpu) { } #endif /* !CONFIG_HOTPLUG_CPU */ /* Wrappers which go away once all code is converted */ @@ -138,12 +144,18 @@ static inline void get_online_cpus(void) { cpus_read_lock(); } static inline void put_online_cpus(void) { cpus_read_unlock(); } #ifdef CONFIG_PM_SLEEP_SMP -extern int freeze_secondary_cpus(int primary); +int __freeze_secondary_cpus(int primary, bool suspend); +static inline int freeze_secondary_cpus(int primary) +{ + return __freeze_secondary_cpus(primary, true); +} + static inline int disable_nonboot_cpus(void) { - return freeze_secondary_cpus(0); + return __freeze_secondary_cpus(0, false); } -extern void enable_nonboot_cpus(void); + +void enable_nonboot_cpus(void); static inline int suspend_disable_secondary_cpus(void) { diff --git a/kernel/cpu.c b/kernel/cpu.c index 221bf6a9e98a..2371292f30b0 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -1041,7 +1041,7 @@ static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target) return _cpu_down(cpu, 0, target); } -static int do_cpu_down(unsigned int cpu, enum cpuhp_state target) +static int cpu_down(unsigned int cpu, enum cpuhp_state target) { int err; @@ -1051,11 +1051,72 @@ static int do_cpu_down(unsigned int cpu, enum cpuhp_state target) return err; } -int cpu_down(unsigned int cpu) +/** + * cpu_device_down - Bring down a cpu device + * @dev: Pointer to the cpu device to offline + * + * This function is meant to be used by device core cpu subsystem only. + * + * Other subsystems should use remove_cpu() instead. + */ +int cpu_device_down(struct device *dev) { - return do_cpu_down(cpu, CPUHP_OFFLINE); + return cpu_down(dev->id, CPUHP_OFFLINE); +} + +int remove_cpu(unsigned int cpu) +{ + int ret; + + lock_device_hotplug(); + ret = device_offline(get_cpu_device(cpu)); + unlock_device_hotplug(); + + return ret; +} +EXPORT_SYMBOL_GPL(remove_cpu); + +void smp_shutdown_nonboot_cpus(unsigned int primary_cpu) +{ + unsigned int cpu; + int error; + + cpu_maps_update_begin(); + + /* + * Make certain the cpu I'm about to reboot on is online. + * + * This is inline to what migrate_to_reboot_cpu() already do. + */ + if (!cpu_online(primary_cpu)) + primary_cpu = cpumask_first(cpu_online_mask); + + for_each_online_cpu(cpu) { + if (cpu == primary_cpu) + continue; + + error = cpu_down_maps_locked(cpu, CPUHP_OFFLINE); + if (error) { + pr_err("Failed to offline CPU%d - error=%d", + cpu, error); + break; + } + } + + /* + * Ensure all but the reboot CPU are offline. + */ + BUG_ON(num_online_cpus() > 1); + + /* + * Make sure the CPUs won't be enabled by someone else after this + * point. Kexec will reboot to a new kernel shortly resetting + * everything along the way. + */ + cpu_hotplug_disabled++; + + cpu_maps_update_done(); } -EXPORT_SYMBOL(cpu_down); #else #define takedown_cpu NULL @@ -1124,8 +1185,8 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) } /* - * The caller of do_cpu_up might have raced with another - * caller. Ignore it for now. + * The caller of cpu_up() might have raced with another + * caller. Nothing to do. */ if (st->state >= target) goto out; @@ -1169,7 +1230,7 @@ out: return ret; } -static int do_cpu_up(unsigned int cpu, enum cpuhp_state target) +static int cpu_up(unsigned int cpu, enum cpuhp_state target) { int err = 0; @@ -1203,16 +1264,70 @@ out: return err; } -int cpu_up(unsigned int cpu) +/** + * cpu_device_up - Bring up a cpu device + * @dev: Pointer to the cpu device to online + * + * This function is meant to be used by device core cpu subsystem only. + * + * Other subsystems should use add_cpu() instead. + */ +int cpu_device_up(struct device *dev) { - return do_cpu_up(cpu, CPUHP_ONLINE); + return cpu_up(dev->id, CPUHP_ONLINE); +} + +int add_cpu(unsigned int cpu) +{ + int ret; + + lock_device_hotplug(); + ret = device_online(get_cpu_device(cpu)); + unlock_device_hotplug(); + + return ret; +} +EXPORT_SYMBOL_GPL(add_cpu); + +/** + * bringup_hibernate_cpu - Bring up the CPU that we hibernated on + * @sleep_cpu: The cpu we hibernated on and should be brought up. + * + * On some architectures like arm64, we can hibernate on any CPU, but on + * wake up the CPU we hibernated on might be offline as a side effect of + * using maxcpus= for example. + */ +int bringup_hibernate_cpu(unsigned int sleep_cpu) +{ + int ret; + + if (!cpu_online(sleep_cpu)) { + pr_info("Hibernated on a CPU that is offline! Bringing CPU up.\n"); + ret = cpu_up(sleep_cpu, CPUHP_ONLINE); + if (ret) { + pr_err("Failed to bring hibernate-CPU up!\n"); + return ret; + } + } + return 0; +} + +void bringup_nonboot_cpus(unsigned int setup_max_cpus) +{ + unsigned int cpu; + + for_each_present_cpu(cpu) { + if (num_online_cpus() >= setup_max_cpus) + break; + if (!cpu_online(cpu)) + cpu_up(cpu, CPUHP_ONLINE); + } } -EXPORT_SYMBOL_GPL(cpu_up); #ifdef CONFIG_PM_SLEEP_SMP static cpumask_var_t frozen_cpus; -int freeze_secondary_cpus(int primary) +int __freeze_secondary_cpus(int primary, bool suspend) { int cpu, error = 0; @@ -1237,7 +1352,7 @@ int freeze_secondary_cpus(int primary) if (cpu == primary) continue; - if (pm_wakeup_pending()) { + if (suspend && pm_wakeup_pending()) { pr_info("Wakeup pending. Abort CPU freeze\n"); error = -EBUSY; break; @@ -2028,9 +2143,9 @@ static ssize_t write_cpuhp_target(struct device *dev, goto out; if (st->state < target) - ret = do_cpu_up(dev->id, target); + ret = cpu_up(dev->id, target); else - ret = do_cpu_down(dev->id, target); + ret = cpu_down(dev->id, target); out: unlock_device_hotplug(); return ret ? ret : count; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index c1f923d647ee..a2694ba82874 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -269,7 +269,6 @@ static void __hrtick_start(void *arg) rq_lock(rq, &rf); __hrtick_restart(rq); - rq->hrtick_csd_pending = 0; rq_unlock(rq, &rf); } @@ -293,12 +292,10 @@ void hrtick_start(struct rq *rq, u64 delay) hrtimer_set_expires(timer, time); - if (rq == this_rq()) { + if (rq == this_rq()) __hrtick_restart(rq); - } else if (!rq->hrtick_csd_pending) { + else smp_call_function_single_async(cpu_of(rq), &rq->hrtick_csd); - rq->hrtick_csd_pending = 1; - } } #else @@ -322,8 +319,6 @@ void hrtick_start(struct rq *rq, u64 delay) static void hrtick_rq_init(struct rq *rq) { #ifdef CONFIG_SMP - rq->hrtick_csd_pending = 0; - rq->hrtick_csd.flags = 0; rq->hrtick_csd.func = __hrtick_start; rq->hrtick_csd.info = rq; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 464742874be3..0f616bf7bce3 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -992,7 +992,6 @@ struct rq { #ifdef CONFIG_SCHED_HRTICK #ifdef CONFIG_SMP - int hrtick_csd_pending; call_single_data_t hrtick_csd; #endif struct hrtimer hrtick_timer; diff --git a/kernel/smp.c b/kernel/smp.c index d0ada39eb4d4..786092aabdcd 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -329,6 +329,11 @@ EXPORT_SYMBOL(smp_call_function_single); * (ie: embedded in an object) and is responsible for synchronizing it * such that the IPIs performed on the @csd are strictly serialized. * + * If the function is called with one csd which has not yet been + * processed by previous call to smp_call_function_single_async(), the + * function will return immediately with -EBUSY showing that the csd + * object is still in progress. + * * NOTE: Be careful, there is unfortunately no current debugging facility to * validate the correctness of this serialization. */ @@ -338,14 +343,17 @@ int smp_call_function_single_async(int cpu, call_single_data_t *csd) preempt_disable(); - /* We could deadlock if we have to wait here with interrupts disabled! */ - if (WARN_ON_ONCE(csd->flags & CSD_FLAG_LOCK)) - csd_lock_wait(csd); + if (csd->flags & CSD_FLAG_LOCK) { + err = -EBUSY; + goto out; + } csd->flags = CSD_FLAG_LOCK; smp_wmb(); err = generic_exec_single(cpu, csd, csd->func, csd->info); + +out: preempt_enable(); return err; @@ -589,20 +597,13 @@ void __init setup_nr_cpu_ids(void) void __init smp_init(void) { int num_nodes, num_cpus; - unsigned int cpu; idle_threads_init(); cpuhp_threads_init(); pr_info("Bringing up secondary CPUs ...\n"); - /* FIXME: This should be done in userspace --RR */ - for_each_present_cpu(cpu) { - if (num_online_cpus() >= setup_max_cpus) - break; - if (!cpu_online(cpu)) - cpu_up(cpu); - } + bringup_nonboot_cpus(setup_max_cpus); num_nodes = num_online_nodes(); num_cpus = num_online_cpus(); diff --git a/kernel/torture.c b/kernel/torture.c index 8683375dc0c7..a1a41484ff6d 100644 --- a/kernel/torture.c +++ b/kernel/torture.c @@ -101,7 +101,7 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes, torture_type, cpu); starttime = jiffies; (*n_offl_attempts)++; - ret = cpu_down(cpu); + ret = remove_cpu(cpu); if (ret) { s = ""; if (!rcu_inkernel_boot_has_ended() && ret == -EBUSY) { @@ -159,7 +159,7 @@ bool torture_online(int cpu, long *n_onl_attempts, long *n_onl_successes, torture_type, cpu); starttime = jiffies; (*n_onl_attempts)++; - ret = cpu_up(cpu); + ret = add_cpu(cpu); if (ret) { s = ""; if (!rcu_inkernel_boot_has_ended() && ret == -EBUSY) { @@ -209,17 +209,18 @@ torture_onoff(void *arg) for_each_online_cpu(cpu) maxcpu = cpu; WARN_ON(maxcpu < 0); - if (!IS_MODULE(CONFIG_TORTURE_TEST)) + if (!IS_MODULE(CONFIG_TORTURE_TEST)) { for_each_possible_cpu(cpu) { if (cpu_online(cpu)) continue; - ret = cpu_up(cpu); + ret = add_cpu(cpu); if (ret && verbose) { pr_alert("%s" TORTURE_FLAG "%s: Initial online %d: errno %d\n", __func__, torture_type, cpu, ret); } } + } if (maxcpu == 0) { VERBOSE_TOROUT_STRING("Only one CPU, so CPU-hotplug testing is disabled");