From 090e77c391dd983c8945b8e2e16d09f378d2e334 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 26 Feb 2016 18:43:23 +0000 Subject: cpu/hotplug: Restructure FROZEN state handling There are only a few callbacks which really care about FROZEN vs. !FROZEN. No need to have extra states for this. Publish the frozen state in an extra variable which is updated under the hotplug lock and let the users interested deal with it w/o imposing that extra state checks on everyone. Signed-off-by: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: Rik van Riel Cc: Rafael Wysocki Cc: "Srivatsa S. Bhat" Cc: Peter Zijlstra Cc: Arjan van de Ven Cc: Sebastian Siewior Cc: Rusty Russell Cc: Steven Rostedt Cc: Oleg Nesterov Cc: Tejun Heo Cc: Andrew Morton Cc: Paul McKenney Cc: Linus Torvalds Cc: Paul Turner Link: http://lkml.kernel.org/r/20160226182340.334912357@linutronix.de Signed-off-by: Thomas Gleixner diff --git a/include/linux/cpu.h b/include/linux/cpu.h index d2ca8c3..f2fb549 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -118,6 +118,7 @@ enum { #ifdef CONFIG_SMP +extern bool cpuhp_tasks_frozen; /* Need to know about CPUs going up/down? */ #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE) #define cpu_notifier(fn, pri) { \ @@ -177,6 +178,7 @@ extern void cpu_maps_update_done(void); #define cpu_notifier_register_done cpu_maps_update_done #else /* CONFIG_SMP */ +#define cpuhp_tasks_frozen 0 #define cpu_notifier(fn, pri) do { (void)(fn); } while (0) #define __cpu_notifier(fn, pri) do { (void)(fn); } while (0) diff --git a/kernel/cpu.c b/kernel/cpu.c index 5b9d396..41a6cb8 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -29,6 +29,8 @@ #ifdef CONFIG_SMP /* Serializes the updates to cpu_online_mask, cpu_present_mask */ static DEFINE_MUTEX(cpu_add_remove_lock); +bool cpuhp_tasks_frozen; +EXPORT_SYMBOL_GPL(cpuhp_tasks_frozen); /* * The following two APIs (cpu_maps_update_begin/done) must be used when @@ -207,27 +209,30 @@ int __register_cpu_notifier(struct notifier_block *nb) return raw_notifier_chain_register(&cpu_chain, nb); } -static int __cpu_notify(unsigned long val, void *v, int nr_to_call, +static int __cpu_notify(unsigned long val, unsigned int cpu, int nr_to_call, int *nr_calls) { + unsigned long mod = cpuhp_tasks_frozen ? CPU_TASKS_FROZEN : 0; + void *hcpu = (void *)(long)cpu; + int ret; - ret = __raw_notifier_call_chain(&cpu_chain, val, v, nr_to_call, + ret = __raw_notifier_call_chain(&cpu_chain, val | mod, hcpu, nr_to_call, nr_calls); return notifier_to_errno(ret); } -static int cpu_notify(unsigned long val, void *v) +static int cpu_notify(unsigned long val, unsigned int cpu) { - return __cpu_notify(val, v, -1, NULL); + return __cpu_notify(val, cpu, -1, NULL); } #ifdef CONFIG_HOTPLUG_CPU -static void cpu_notify_nofail(unsigned long val, void *v) +static void cpu_notify_nofail(unsigned long val, unsigned int cpu) { - BUG_ON(cpu_notify(val, v)); + BUG_ON(cpu_notify(val, cpu)); } EXPORT_SYMBOL(register_cpu_notifier); EXPORT_SYMBOL(__register_cpu_notifier); @@ -311,27 +316,21 @@ static inline void check_for_tasks(int dead_cpu) read_unlock(&tasklist_lock); } -struct take_cpu_down_param { - unsigned long mod; - void *hcpu; -}; - /* Take this CPU down. */ static int take_cpu_down(void *_param) { - struct take_cpu_down_param *param = _param; - int err; + int err, cpu = smp_processor_id(); /* Ensure this CPU doesn't handle any more interrupts. */ err = __cpu_disable(); if (err < 0) return err; - cpu_notify(CPU_DYING | param->mod, param->hcpu); + cpu_notify(CPU_DYING, cpu); /* Give up timekeeping duties */ tick_handover_do_timer(); /* Park the stopper thread */ - stop_machine_park((long)param->hcpu); + stop_machine_park(cpu); return 0; } @@ -339,12 +338,6 @@ static int take_cpu_down(void *_param) static int _cpu_down(unsigned int cpu, int tasks_frozen) { int err, nr_calls = 0; - void *hcpu = (void *)(long)cpu; - unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0; - struct take_cpu_down_param tcd_param = { - .mod = mod, - .hcpu = hcpu, - }; if (num_online_cpus() == 1) return -EBUSY; @@ -354,10 +347,12 @@ static int _cpu_down(unsigned int cpu, int tasks_frozen) cpu_hotplug_begin(); - err = __cpu_notify(CPU_DOWN_PREPARE | mod, hcpu, -1, &nr_calls); + cpuhp_tasks_frozen = tasks_frozen; + + err = __cpu_notify(CPU_DOWN_PREPARE, cpu, -1, &nr_calls); if (err) { nr_calls--; - __cpu_notify(CPU_DOWN_FAILED | mod, hcpu, nr_calls, NULL); + __cpu_notify(CPU_DOWN_FAILED, cpu, nr_calls, NULL); pr_warn("%s: attempt to take down CPU %u failed\n", __func__, cpu); goto out_release; @@ -389,10 +384,10 @@ static int _cpu_down(unsigned int cpu, int tasks_frozen) /* * So now all preempt/rcu users must observe !cpu_active(). */ - err = stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu)); + err = stop_machine(take_cpu_down, NULL, cpumask_of(cpu)); if (err) { /* CPU didn't die: tell everyone. Can't complain. */ - cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu); + cpu_notify_nofail(CPU_DOWN_FAILED, cpu); irq_unlock_sparse(); goto out_release; } @@ -419,14 +414,14 @@ static int _cpu_down(unsigned int cpu, int tasks_frozen) /* CPU is completely dead: tell everyone. Too late to complain. */ tick_cleanup_dead_cpu(cpu); - cpu_notify_nofail(CPU_DEAD | mod, hcpu); + cpu_notify_nofail(CPU_DEAD, cpu); check_for_tasks(cpu); out_release: cpu_hotplug_done(); if (!err) - cpu_notify_nofail(CPU_POST_DEAD | mod, hcpu); + cpu_notify_nofail(CPU_POST_DEAD, cpu); return err; } @@ -485,10 +480,8 @@ void smpboot_thread_init(void) /* Requires cpu_add_remove_lock to be held */ static int _cpu_up(unsigned int cpu, int tasks_frozen) { - int ret, nr_calls = 0; - void *hcpu = (void *)(long)cpu; - unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0; struct task_struct *idle; + int ret, nr_calls = 0; cpu_hotplug_begin(); @@ -507,7 +500,9 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen) if (ret) goto out; - ret = __cpu_notify(CPU_UP_PREPARE | mod, hcpu, -1, &nr_calls); + cpuhp_tasks_frozen = tasks_frozen; + + ret = __cpu_notify(CPU_UP_PREPARE, cpu, -1, &nr_calls); if (ret) { nr_calls--; pr_warn("%s: attempt to bring up CPU %u failed\n", @@ -523,11 +518,11 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen) BUG_ON(!cpu_online(cpu)); /* Now call notifier in preparation. */ - cpu_notify(CPU_ONLINE | mod, hcpu); + cpu_notify(CPU_ONLINE, cpu); out_notify: if (ret != 0) - __cpu_notify(CPU_UP_CANCELED | mod, hcpu, nr_calls, NULL); + __cpu_notify(CPU_UP_CANCELED, cpu, nr_calls, NULL); out: cpu_hotplug_done(); @@ -719,13 +714,7 @@ core_initcall(cpu_hotplug_pm_sync_init); */ void notify_cpu_starting(unsigned int cpu) { - unsigned long val = CPU_STARTING; - -#ifdef CONFIG_PM_SLEEP_SMP - if (frozen_cpus != NULL && cpumask_test_cpu(cpu, frozen_cpus)) - val = CPU_STARTING_FROZEN; -#endif /* CONFIG_PM_SLEEP_SMP */ - cpu_notify(val, (void *)(long)cpu); + cpu_notify(CPU_STARTING, cpu); } #endif /* CONFIG_SMP */ -- cgit v0.10.2 From ba997462435f48ad1501320e9da8770fd40c59b1 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 26 Feb 2016 18:43:24 +0000 Subject: cpu/hotplug: Restructure cpu_up code Split out into separate functions, so we can convert it to a state machine. Signed-off-by: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: Rik van Riel Cc: Rafael Wysocki Cc: "Srivatsa S. Bhat" Cc: Peter Zijlstra Cc: Arjan van de Ven Cc: Sebastian Siewior Cc: Rusty Russell Cc: Steven Rostedt Cc: Oleg Nesterov Cc: Tejun Heo Cc: Andrew Morton Cc: Paul McKenney Cc: Linus Torvalds Cc: Paul Turner Link: http://lkml.kernel.org/r/20160226182340.429389195@linutronix.de Signed-off-by: Thomas Gleixner diff --git a/kernel/cpu.c b/kernel/cpu.c index 41a6cb8..15a4136 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -228,6 +228,43 @@ static int cpu_notify(unsigned long val, unsigned int cpu) return __cpu_notify(val, cpu, -1, NULL); } +/* Notifier wrappers for transitioning to state machine */ +static int notify_prepare(unsigned int cpu) +{ + int nr_calls = 0; + int ret; + + ret = __cpu_notify(CPU_UP_PREPARE, cpu, -1, &nr_calls); + if (ret) { + nr_calls--; + printk(KERN_WARNING "%s: attempt to bring up CPU %u failed\n", + __func__, cpu); + __cpu_notify(CPU_UP_CANCELED, cpu, nr_calls, NULL); + } + return ret; +} + +static int notify_online(unsigned int cpu) +{ + cpu_notify(CPU_ONLINE, cpu); + return 0; +} + +static int bringup_cpu(unsigned int cpu) +{ + struct task_struct *idle = idle_thread_get(cpu); + int ret; + + /* Arch-specific enabling code. */ + ret = __cpu_up(cpu, idle); + if (ret) { + cpu_notify(CPU_UP_CANCELED, cpu); + return ret; + } + BUG_ON(!cpu_online(cpu)); + return 0; +} + #ifdef CONFIG_HOTPLUG_CPU static void cpu_notify_nofail(unsigned long val, unsigned int cpu) @@ -481,7 +518,7 @@ void smpboot_thread_init(void) static int _cpu_up(unsigned int cpu, int tasks_frozen) { struct task_struct *idle; - int ret, nr_calls = 0; + int ret; cpu_hotplug_begin(); @@ -496,33 +533,21 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen) goto out; } + cpuhp_tasks_frozen = tasks_frozen; + ret = smpboot_create_threads(cpu); if (ret) goto out; - cpuhp_tasks_frozen = tasks_frozen; - - ret = __cpu_notify(CPU_UP_PREPARE, cpu, -1, &nr_calls); - if (ret) { - nr_calls--; - pr_warn("%s: attempt to bring up CPU %u failed\n", - __func__, cpu); - goto out_notify; - } - - /* Arch-specific enabling code. */ - ret = __cpu_up(cpu, idle); - - if (ret != 0) - goto out_notify; - BUG_ON(!cpu_online(cpu)); + ret = notify_prepare(cpu); + if (ret) + goto out; - /* Now call notifier in preparation. */ - cpu_notify(CPU_ONLINE, cpu); + ret = bringup_cpu(cpu); + if (ret) + goto out; -out_notify: - if (ret != 0) - __cpu_notify(CPU_UP_CANCELED, cpu, nr_calls, NULL); + notify_online(cpu); out: cpu_hotplug_done(); -- cgit v0.10.2 From 984581728eb4b2e10baed3d606f85a119795b207 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 26 Feb 2016 18:43:25 +0000 Subject: cpu/hotplug: Split out cpu down functions Split cpu_down in separate functions in preparation for state machine conversion. Signed-off-by: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: Rik van Riel Cc: Rafael Wysocki Cc: "Srivatsa S. Bhat" Cc: Peter Zijlstra Cc: Arjan van de Ven Cc: Sebastian Siewior Cc: Rusty Russell Cc: Steven Rostedt Cc: Oleg Nesterov Cc: Tejun Heo Cc: Andrew Morton Cc: Paul McKenney Cc: Linus Torvalds Cc: Paul Turner Link: http://lkml.kernel.org/r/20160226182340.511796562@linutronix.de Signed-off-by: Thomas Gleixner diff --git a/kernel/cpu.c b/kernel/cpu.c index 15a4136..0b5d259 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -266,11 +266,6 @@ static int bringup_cpu(unsigned int cpu) } #ifdef CONFIG_HOTPLUG_CPU - -static void cpu_notify_nofail(unsigned long val, unsigned int cpu) -{ - BUG_ON(cpu_notify(val, cpu)); -} EXPORT_SYMBOL(register_cpu_notifier); EXPORT_SYMBOL(__register_cpu_notifier); @@ -353,6 +348,25 @@ static inline void check_for_tasks(int dead_cpu) read_unlock(&tasklist_lock); } +static void cpu_notify_nofail(unsigned long val, unsigned int cpu) +{ + BUG_ON(cpu_notify(val, cpu)); +} + +static int notify_down_prepare(unsigned int cpu) +{ + int err, nr_calls = 0; + + err = __cpu_notify(CPU_DOWN_PREPARE, cpu, -1, &nr_calls); + if (err) { + nr_calls--; + __cpu_notify(CPU_DOWN_FAILED, cpu, nr_calls, NULL); + pr_warn("%s: attempt to take down CPU %u failed\n", + __func__, cpu); + } + return err; +} + /* Take this CPU down. */ static int take_cpu_down(void *_param) { @@ -371,29 +385,9 @@ static int take_cpu_down(void *_param) return 0; } -/* Requires cpu_add_remove_lock to be held */ -static int _cpu_down(unsigned int cpu, int tasks_frozen) +static int takedown_cpu(unsigned int cpu) { - int err, nr_calls = 0; - - if (num_online_cpus() == 1) - return -EBUSY; - - if (!cpu_online(cpu)) - return -EINVAL; - - cpu_hotplug_begin(); - - cpuhp_tasks_frozen = tasks_frozen; - - err = __cpu_notify(CPU_DOWN_PREPARE, cpu, -1, &nr_calls); - if (err) { - nr_calls--; - __cpu_notify(CPU_DOWN_FAILED, cpu, nr_calls, NULL); - pr_warn("%s: attempt to take down CPU %u failed\n", - __func__, cpu); - goto out_release; - } + int err; /* * By now we've cleared cpu_active_mask, wait for all preempt-disabled @@ -426,7 +420,7 @@ static int _cpu_down(unsigned int cpu, int tasks_frozen) /* CPU didn't die: tell everyone. Can't complain. */ cpu_notify_nofail(CPU_DOWN_FAILED, cpu); irq_unlock_sparse(); - goto out_release; + return err; } BUG_ON(cpu_online(cpu)); @@ -449,11 +443,40 @@ static int _cpu_down(unsigned int cpu, int tasks_frozen) /* This actually kills the CPU. */ __cpu_die(cpu); - /* CPU is completely dead: tell everyone. Too late to complain. */ tick_cleanup_dead_cpu(cpu); - cpu_notify_nofail(CPU_DEAD, cpu); + return 0; +} +static int notify_dead(unsigned int cpu) +{ + cpu_notify_nofail(CPU_DEAD, cpu); check_for_tasks(cpu); + return 0; +} + +/* Requires cpu_add_remove_lock to be held */ +static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) +{ + int err; + + if (num_online_cpus() == 1) + return -EBUSY; + + if (!cpu_online(cpu)) + return -EINVAL; + + cpu_hotplug_begin(); + + cpuhp_tasks_frozen = tasks_frozen; + + err = notify_down_prepare(cpu); + if (err) + goto out_release; + err = takedown_cpu(cpu); + if (err) + goto out_release; + + notify_dead(cpu); out_release: cpu_hotplug_done(); -- cgit v0.10.2 From 5ba9ac8e2c45ab165e5b4a246f4821d319656e9d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 26 Feb 2016 18:43:27 +0000 Subject: cpu/hotplug: Add tracepoints We want to trace the hotplug machinery. Add tracepoints to track the invocation of callbacks and their result. Signed-off-by: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: Rik van Riel Cc: Rafael Wysocki Cc: "Srivatsa S. Bhat" Cc: Peter Zijlstra Cc: Arjan van de Ven Cc: Sebastian Siewior Cc: Rusty Russell Cc: Steven Rostedt Cc: Oleg Nesterov Cc: Tejun Heo Cc: Andrew Morton Cc: Paul McKenney Cc: Linus Torvalds Cc: Paul Turner Link: http://lkml.kernel.org/r/20160226182340.593563875@linutronix.de Signed-off-by: Thomas Gleixner diff --git a/include/trace/events/cpuhp.h b/include/trace/events/cpuhp.h new file mode 100644 index 0000000..a72bd93 --- /dev/null +++ b/include/trace/events/cpuhp.h @@ -0,0 +1,66 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM cpuhp + +#if !defined(_TRACE_CPUHP_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_CPUHP_H + +#include + +TRACE_EVENT(cpuhp_enter, + + TP_PROTO(unsigned int cpu, + int target, + int idx, + int (*fun)(unsigned int)), + + TP_ARGS(cpu, target, idx, fun), + + TP_STRUCT__entry( + __field( unsigned int, cpu ) + __field( int, target ) + __field( int, idx ) + __field( void *, fun ) + ), + + TP_fast_assign( + __entry->cpu = cpu; + __entry->target = target; + __entry->idx = idx; + __entry->fun = fun; + ), + + TP_printk("cpu: %04u target: %3d step: %3d (%pf)", + __entry->cpu, __entry->target, __entry->idx, __entry->fun) +); + +TRACE_EVENT(cpuhp_exit, + + TP_PROTO(unsigned int cpu, + int state, + int idx, + int ret), + + TP_ARGS(cpu, state, idx, ret), + + TP_STRUCT__entry( + __field( unsigned int, cpu ) + __field( int, state ) + __field( int, idx ) + __field( int, ret ) + ), + + TP_fast_assign( + __entry->cpu = cpu; + __entry->state = state; + __entry->idx = idx; + __entry->ret = ret; + ), + + TP_printk(" cpu: %04u state: %3d step: %3d ret: %d", + __entry->cpu, __entry->state, __entry->idx, __entry->ret) +); + +#endif + +/* This part must be outside protection */ +#include -- cgit v0.10.2 From cff7d378d3fdbb53db9b6e2578b14855f401cd41 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 26 Feb 2016 18:43:28 +0000 Subject: cpu/hotplug: Convert to a state machine for the control processor Move the split out steps into a callback array and let the cpu_up/down code iterate through the array functions. For now most of the callbacks are asymmetric to resemble the current hotplug maze. Signed-off-by: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: Rik van Riel Cc: Rafael Wysocki Cc: "Srivatsa S. Bhat" Cc: Peter Zijlstra Cc: Arjan van de Ven Cc: Sebastian Siewior Cc: Rusty Russell Cc: Steven Rostedt Cc: Oleg Nesterov Cc: Tejun Heo Cc: Andrew Morton Cc: Paul McKenney Cc: Linus Torvalds Cc: Paul Turner Link: http://lkml.kernel.org/r/20160226182340.671816690@linutronix.de Signed-off-by: Thomas Gleixner diff --git a/include/linux/cpu.h b/include/linux/cpu.h index f2fb549..78989f2 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -16,6 +16,7 @@ #include #include #include +#include struct device; struct device_node; @@ -27,6 +28,9 @@ struct cpu { struct device dev; }; +extern void boot_cpu_init(void); +extern void boot_cpu_state_init(void); + extern int register_cpu(struct cpu *cpu, int num); extern struct device *get_cpu_device(unsigned cpu); extern bool cpu_is_hotpluggable(unsigned cpu); @@ -267,11 +271,6 @@ static inline int disable_nonboot_cpus(void) { return 0; } static inline void enable_nonboot_cpus(void) {} #endif /* !CONFIG_PM_SLEEP_SMP */ -enum cpuhp_state { - CPUHP_OFFLINE, - CPUHP_ONLINE, -}; - void cpu_startup_entry(enum cpuhp_state state); void cpu_idle_poll_ctrl(bool enable); diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h new file mode 100644 index 0000000..d55c9e6 --- /dev/null +++ b/include/linux/cpuhotplug.h @@ -0,0 +1,13 @@ +#ifndef __CPUHOTPLUG_H +#define __CPUHOTPLUG_H + +enum cpuhp_state { + CPUHP_OFFLINE, + CPUHP_CREATE_THREADS, + CPUHP_NOTIFY_PREPARE, + CPUHP_BRINGUP_CPU, + CPUHP_NOTIFY_ONLINE, + CPUHP_ONLINE, +}; + +#endif diff --git a/init/main.c b/init/main.c index 58c9e37..c2ea723 100644 --- a/init/main.c +++ b/init/main.c @@ -452,20 +452,6 @@ void __init parse_early_param(void) done = 1; } -/* - * Activate the first processor. - */ - -static void __init boot_cpu_init(void) -{ - int cpu = smp_processor_id(); - /* Mark the boot cpu "present", "online" etc for SMP and UP case */ - set_cpu_online(cpu, true); - set_cpu_active(cpu, true); - set_cpu_present(cpu, true); - set_cpu_possible(cpu, true); -} - void __init __weak smp_setup_processor_id(void) { } @@ -530,6 +516,7 @@ asmlinkage __visible void __init start_kernel(void) setup_command_line(command_line); setup_nr_cpu_ids(); setup_per_cpu_areas(); + boot_cpu_state_init(); smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */ build_all_zonelists(NULL, NULL); diff --git a/kernel/cpu.c b/kernel/cpu.c index 0b5d259..3018519 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -22,10 +22,64 @@ #include #include #include + #include +#define CREATE_TRACE_POINTS +#include #include "smpboot.h" +/** + * cpuhp_cpu_state - Per cpu hotplug state storage + * @state: The current cpu state + * @target: The target state + */ +struct cpuhp_cpu_state { + enum cpuhp_state state; + enum cpuhp_state target; +}; + +static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state); + +/** + * cpuhp_step - Hotplug state machine step + * @name: Name of the step + * @startup: Startup function of the step + * @teardown: Teardown function of the step + * @skip_onerr: Do not invoke the functions on error rollback + * Will go away once the notifiers are gone + */ +struct cpuhp_step { + const char *name; + int (*startup)(unsigned int cpu); + int (*teardown)(unsigned int cpu); + bool skip_onerr; +}; + +static struct cpuhp_step cpuhp_bp_states[]; + +/** + * cpuhp_invoke_callback _ Invoke the callbacks for a given state + * @cpu: The cpu for which the callback should be invoked + * @step: The step in the state machine + * @cb: The callback function to invoke + * + * Called from cpu hotplug and from the state register machinery + */ +static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state step, + int (*cb)(unsigned int)) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + int ret = 0; + + if (cb) { + trace_cpuhp_enter(cpu, st->target, step, cb); + ret = cb(cpu); + trace_cpuhp_exit(cpu, st->state, step, ret); + } + return ret; +} + #ifdef CONFIG_SMP /* Serializes the updates to cpu_online_mask, cpu_present_mask */ static DEFINE_MUTEX(cpu_add_remove_lock); @@ -454,10 +508,29 @@ static int notify_dead(unsigned int cpu) return 0; } +#else +#define notify_down_prepare NULL +#define takedown_cpu NULL +#define notify_dead NULL +#endif + +#ifdef CONFIG_HOTPLUG_CPU +static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st) +{ + for (st->state++; st->state < st->target; st->state++) { + struct cpuhp_step *step = cpuhp_bp_states + st->state; + + if (!step->skip_onerr) + cpuhp_invoke_callback(cpu, st->state, step->startup); + } +} + /* Requires cpu_add_remove_lock to be held */ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) { - int err; + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + int prev_state, ret = 0; + bool hasdied = false; if (num_online_cpus() == 1) return -EBUSY; @@ -469,20 +542,25 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) cpuhp_tasks_frozen = tasks_frozen; - err = notify_down_prepare(cpu); - if (err) - goto out_release; - err = takedown_cpu(cpu); - if (err) - goto out_release; + prev_state = st->state; + st->target = CPUHP_OFFLINE; + for (; st->state > st->target; st->state--) { + struct cpuhp_step *step = cpuhp_bp_states + st->state; - notify_dead(cpu); + ret = cpuhp_invoke_callback(cpu, st->state, step->teardown); + if (ret) { + st->target = prev_state; + undo_cpu_down(cpu, st); + break; + } + } + hasdied = prev_state != st->state && st->state == CPUHP_OFFLINE; -out_release: cpu_hotplug_done(); - if (!err) + /* This post dead nonsense must die */ + if (!ret && hasdied) cpu_notify_nofail(CPU_POST_DEAD, cpu); - return err; + return ret; } int cpu_down(unsigned int cpu) @@ -537,11 +615,22 @@ void smpboot_thread_init(void) register_cpu_notifier(&smpboot_thread_notifier); } +static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st) +{ + for (st->state--; st->state > st->target; st->state--) { + struct cpuhp_step *step = cpuhp_bp_states + st->state; + + if (!step->skip_onerr) + cpuhp_invoke_callback(cpu, st->state, step->teardown); + } +} + /* Requires cpu_add_remove_lock to be held */ static int _cpu_up(unsigned int cpu, int tasks_frozen) { + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct task_struct *idle; - int ret; + int prev_state, ret = 0; cpu_hotplug_begin(); @@ -550,6 +639,7 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen) goto out; } + /* Let it fail before we try to bring the cpu up */ idle = idle_thread_get(cpu); if (IS_ERR(idle)) { ret = PTR_ERR(idle); @@ -558,22 +648,22 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen) cpuhp_tasks_frozen = tasks_frozen; - ret = smpboot_create_threads(cpu); - if (ret) - goto out; - - ret = notify_prepare(cpu); - if (ret) - goto out; - - ret = bringup_cpu(cpu); - if (ret) - goto out; - - notify_online(cpu); + prev_state = st->state; + st->target = CPUHP_ONLINE; + while (st->state < st->target) { + struct cpuhp_step *step; + + st->state++; + step = cpuhp_bp_states + st->state; + ret = cpuhp_invoke_callback(cpu, st->state, step->startup); + if (ret) { + st->target = prev_state; + undo_cpu_up(cpu, st); + break; + } + } out: cpu_hotplug_done(); - return ret; } @@ -767,6 +857,44 @@ void notify_cpu_starting(unsigned int cpu) #endif /* CONFIG_SMP */ +/* Boot processor state steps */ +static struct cpuhp_step cpuhp_bp_states[] = { + [CPUHP_OFFLINE] = { + .name = "offline", + .startup = NULL, + .teardown = NULL, + }, +#ifdef CONFIG_SMP + [CPUHP_CREATE_THREADS]= { + .name = "threads:create", + .startup = smpboot_create_threads, + .teardown = NULL, + }, + [CPUHP_NOTIFY_PREPARE] = { + .name = "notify:prepare", + .startup = notify_prepare, + .teardown = notify_dead, + .skip_onerr = true, + }, + [CPUHP_BRINGUP_CPU] = { + .name = "cpu:bringup", + .startup = bringup_cpu, + .teardown = takedown_cpu, + .skip_onerr = true, + }, + [CPUHP_NOTIFY_ONLINE] = { + .name = "notify:online", + .startup = notify_online, + .teardown = notify_down_prepare, + }, +#endif + [CPUHP_ONLINE] = { + .name = "online", + .startup = NULL, + .teardown = NULL, + }, +}; + /* * cpu_bit_bitmap[] is a special, "compressed" data structure that * represents all NR_CPUS bits binary values of 1<state = CPUHP_ONLINE; +} -- cgit v0.10.2 From 4baa0afc6719cbf36a1e08551484a641926b3fd1 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 26 Feb 2016 18:43:29 +0000 Subject: cpu/hotplug: Convert the hotplugged cpu work to a state machine Move the functions which need to run on the hotplugged processor into a state machine array and let the code iterate through these functions. In a later state, this will grow synchronization points between the control processor and the hotplugged processor, so we can move the various architecture implementations of the synchronizations to the core. Signed-off-by: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: Rik van Riel Cc: Rafael Wysocki Cc: "Srivatsa S. Bhat" Cc: Peter Zijlstra Cc: Arjan van de Ven Cc: Sebastian Siewior Cc: Rusty Russell Cc: Steven Rostedt Cc: Oleg Nesterov Cc: Tejun Heo Cc: Andrew Morton Cc: Paul McKenney Cc: Linus Torvalds Cc: Paul Turner Link: http://lkml.kernel.org/r/20160226182340.770651526@linutronix.de Signed-off-by: Thomas Gleixner diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index d55c9e6..d9303cc 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -6,6 +6,10 @@ enum cpuhp_state { CPUHP_CREATE_THREADS, CPUHP_NOTIFY_PREPARE, CPUHP_BRINGUP_CPU, + CPUHP_AP_OFFLINE, + CPUHP_AP_NOTIFY_STARTING, + CPUHP_AP_ONLINE, + CPUHP_TEARDOWN_CPU, CPUHP_NOTIFY_ONLINE, CPUHP_ONLINE, }; diff --git a/kernel/cpu.c b/kernel/cpu.c index 3018519..797723e 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -57,6 +57,7 @@ struct cpuhp_step { }; static struct cpuhp_step cpuhp_bp_states[]; +static struct cpuhp_step cpuhp_ap_states[]; /** * cpuhp_invoke_callback _ Invoke the callbacks for a given state @@ -304,6 +305,12 @@ static int notify_online(unsigned int cpu) return 0; } +static int notify_starting(unsigned int cpu) +{ + cpu_notify(CPU_STARTING, cpu); + return 0; +} + static int bringup_cpu(unsigned int cpu) { struct task_struct *idle = idle_thread_get(cpu); @@ -421,9 +428,17 @@ static int notify_down_prepare(unsigned int cpu) return err; } +static int notify_dying(unsigned int cpu) +{ + cpu_notify(CPU_DYING, cpu); + return 0; +} + /* Take this CPU down. */ static int take_cpu_down(void *_param) { + struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); + enum cpuhp_state target = max((int)st->target, CPUHP_AP_OFFLINE); int err, cpu = smp_processor_id(); /* Ensure this CPU doesn't handle any more interrupts. */ @@ -431,7 +446,12 @@ static int take_cpu_down(void *_param) if (err < 0) return err; - cpu_notify(CPU_DYING, cpu); + /* Invoke the former CPU_DYING callbacks */ + for (; st->state > target; st->state--) { + struct cpuhp_step *step = cpuhp_ap_states + st->state; + + cpuhp_invoke_callback(cpu, st->state, step->teardown); + } /* Give up timekeeping duties */ tick_handover_do_timer(); /* Park the stopper thread */ @@ -512,6 +532,7 @@ static int notify_dead(unsigned int cpu) #define notify_down_prepare NULL #define takedown_cpu NULL #define notify_dead NULL +#define notify_dying NULL #endif #ifdef CONFIG_HOTPLUG_CPU @@ -615,6 +636,28 @@ void smpboot_thread_init(void) register_cpu_notifier(&smpboot_thread_notifier); } +/** + * notify_cpu_starting(cpu) - call the CPU_STARTING notifiers + * @cpu: cpu that just started + * + * This function calls the cpu_chain notifiers with CPU_STARTING. + * It must be called by the arch code on the new cpu, before the new cpu + * enables interrupts and before the "boot" cpu returns from __cpu_up(). + */ +void notify_cpu_starting(unsigned int cpu) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE); + + while (st->state < target) { + struct cpuhp_step *step; + + st->state++; + step = cpuhp_ap_states + st->state; + cpuhp_invoke_callback(cpu, st->state, step->startup); + } +} + static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st) { for (st->state--; st->state > st->target; st->state--) { @@ -842,19 +885,6 @@ core_initcall(cpu_hotplug_pm_sync_init); #endif /* CONFIG_PM_SLEEP_SMP */ -/** - * notify_cpu_starting(cpu) - call the CPU_STARTING notifiers - * @cpu: cpu that just started - * - * This function calls the cpu_chain notifiers with CPU_STARTING. - * It must be called by the arch code on the new cpu, before the new cpu - * enables interrupts and before the "boot" cpu returns from __cpu_up(). - */ -void notify_cpu_starting(unsigned int cpu) -{ - cpu_notify(CPU_STARTING, cpu); -} - #endif /* CONFIG_SMP */ /* Boot processor state steps */ @@ -879,8 +909,12 @@ static struct cpuhp_step cpuhp_bp_states[] = { [CPUHP_BRINGUP_CPU] = { .name = "cpu:bringup", .startup = bringup_cpu, + .teardown = NULL, + }, + [CPUHP_TEARDOWN_CPU] = { + .name = "cpu:teardown", + .startup = NULL, .teardown = takedown_cpu, - .skip_onerr = true, }, [CPUHP_NOTIFY_ONLINE] = { .name = "notify:online", @@ -895,6 +929,23 @@ static struct cpuhp_step cpuhp_bp_states[] = { }, }; +/* Application processor state steps */ +static struct cpuhp_step cpuhp_ap_states[] = { +#ifdef CONFIG_SMP + [CPUHP_AP_NOTIFY_STARTING] = { + .name = "notify:starting", + .startup = notify_starting, + .teardown = notify_dying, + .skip_onerr = true, + }, +#endif + [CPUHP_ONLINE] = { + .name = "online", + .startup = NULL, + .teardown = NULL, + }, +}; + /* * cpu_bit_bitmap[] is a special, "compressed" data structure that * represents all NR_CPUS bits binary values of 1< Date: Fri, 26 Feb 2016 18:43:30 +0000 Subject: cpu/hotplug: Hand in target state to _cpu_up/down We want to be able to bringup/teardown the cpu to a particular state. Add a target argument to _cpu_up/down. Signed-off-by: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: Rik van Riel Cc: Rafael Wysocki Cc: "Srivatsa S. Bhat" Cc: Peter Zijlstra Cc: Arjan van de Ven Cc: Sebastian Siewior Cc: Rusty Russell Cc: Steven Rostedt Cc: Oleg Nesterov Cc: Tejun Heo Cc: Andrew Morton Cc: Paul McKenney Cc: Linus Torvalds Cc: Paul Turner Link: http://lkml.kernel.org/r/20160226182340.862113133@linutronix.de Signed-off-by: Thomas Gleixner diff --git a/kernel/cpu.c b/kernel/cpu.c index 797723e..a00f8f6 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -547,7 +547,8 @@ static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st) } /* Requires cpu_add_remove_lock to be held */ -static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) +static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, + enum cpuhp_state target) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int prev_state, ret = 0; @@ -564,7 +565,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) cpuhp_tasks_frozen = tasks_frozen; prev_state = st->state; - st->target = CPUHP_OFFLINE; + st->target = target; for (; st->state > st->target; st->state--) { struct cpuhp_step *step = cpuhp_bp_states + st->state; @@ -584,7 +585,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) return ret; } -int cpu_down(unsigned int cpu) +static int do_cpu_down(unsigned int cpu, enum cpuhp_state target) { int err; @@ -595,12 +596,16 @@ int cpu_down(unsigned int cpu) goto out; } - err = _cpu_down(cpu, 0); + err = _cpu_down(cpu, 0, target); out: cpu_maps_update_done(); return err; } +int cpu_down(unsigned int cpu) +{ + return do_cpu_down(cpu, CPUHP_OFFLINE); +} EXPORT_SYMBOL(cpu_down); #endif /*CONFIG_HOTPLUG_CPU*/ @@ -669,7 +674,7 @@ static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st) } /* Requires cpu_add_remove_lock to be held */ -static int _cpu_up(unsigned int cpu, int tasks_frozen) +static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct task_struct *idle; @@ -692,7 +697,7 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen) cpuhp_tasks_frozen = tasks_frozen; prev_state = st->state; - st->target = CPUHP_ONLINE; + st->target = target; while (st->state < st->target) { struct cpuhp_step *step; @@ -710,7 +715,7 @@ out: return ret; } -int cpu_up(unsigned int cpu) +static int do_cpu_up(unsigned int cpu, enum cpuhp_state target) { int err = 0; @@ -734,12 +739,16 @@ int cpu_up(unsigned int cpu) goto out; } - err = _cpu_up(cpu, 0); - + err = _cpu_up(cpu, 0, target); out: cpu_maps_update_done(); return err; } + +int cpu_up(unsigned int cpu) +{ + return do_cpu_up(cpu, CPUHP_ONLINE); +} EXPORT_SYMBOL_GPL(cpu_up); #ifdef CONFIG_PM_SLEEP_SMP @@ -762,7 +771,7 @@ int disable_nonboot_cpus(void) if (cpu == first_cpu) continue; trace_suspend_resume(TPS("CPU_OFF"), cpu, true); - error = _cpu_down(cpu, 1); + error = _cpu_down(cpu, 1, CPUHP_OFFLINE); trace_suspend_resume(TPS("CPU_OFF"), cpu, false); if (!error) cpumask_set_cpu(cpu, frozen_cpus); @@ -812,7 +821,7 @@ void enable_nonboot_cpus(void) for_each_cpu(cpu, frozen_cpus) { trace_suspend_resume(TPS("CPU_ON"), cpu, true); - error = _cpu_up(cpu, 1); + error = _cpu_up(cpu, 1, CPUHP_ONLINE); trace_suspend_resume(TPS("CPU_ON"), cpu, false); if (!error) { pr_info("CPU%d is up\n", cpu); -- cgit v0.10.2 From 98f8cdce1db580b99fce823a48eea2cb2bdb261e Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 26 Feb 2016 18:43:31 +0000 Subject: cpu/hotplug: Add sysfs state interface Add a sysfs interface so we can actually see in which state the cpus are in. Signed-off-by: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: Rik van Riel Cc: Rafael Wysocki Cc: "Srivatsa S. Bhat" Cc: Peter Zijlstra Cc: Arjan van de Ven Cc: Sebastian Siewior Cc: Rusty Russell Cc: Steven Rostedt Cc: Oleg Nesterov Cc: Tejun Heo Cc: Andrew Morton Cc: Paul McKenney Cc: Linus Torvalds Cc: Paul Turner Link: http://lkml.kernel.org/r/20160226182340.942257522@linutronix.de Signed-off-by: Thomas Gleixner diff --git a/kernel/cpu.c b/kernel/cpu.c index a00f8f6..1979b89 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -56,6 +56,7 @@ struct cpuhp_step { bool skip_onerr; }; +static DEFINE_MUTEX(cpuhp_state_mutex); static struct cpuhp_step cpuhp_bp_states[]; static struct cpuhp_step cpuhp_ap_states[]; @@ -955,6 +956,105 @@ static struct cpuhp_step cpuhp_ap_states[] = { }, }; +static bool cpuhp_is_ap_state(enum cpuhp_state state) +{ + return (state > CPUHP_AP_OFFLINE && state < CPUHP_AP_ONLINE); +} + +static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state) +{ + struct cpuhp_step *sp; + + sp = cpuhp_is_ap_state(state) ? cpuhp_ap_states : cpuhp_bp_states; + return sp + state; +} + +#if defined(CONFIG_SYSFS) && defined(CONFIG_HOTPLUG_CPU) +static ssize_t show_cpuhp_state(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); + + return sprintf(buf, "%d\n", st->state); +} +static DEVICE_ATTR(state, 0444, show_cpuhp_state, NULL); + +static ssize_t show_cpuhp_target(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); + + return sprintf(buf, "%d\n", st->target); +} +static DEVICE_ATTR(target, 0444, show_cpuhp_target, NULL); + +static struct attribute *cpuhp_cpu_attrs[] = { + &dev_attr_state.attr, + &dev_attr_target.attr, + NULL +}; + +static struct attribute_group cpuhp_cpu_attr_group = { + .attrs = cpuhp_cpu_attrs, + .name = "hotplug", + NULL +}; + +static ssize_t show_cpuhp_states(struct device *dev, + struct device_attribute *attr, char *buf) +{ + ssize_t cur, res = 0; + int i; + + mutex_lock(&cpuhp_state_mutex); + for (i = 0; i <= CPUHP_ONLINE; i++) { + struct cpuhp_step *sp = cpuhp_get_step(i); + + if (sp->name) { + cur = sprintf(buf, "%3d: %s\n", i, sp->name); + buf += cur; + res += cur; + } + } + mutex_unlock(&cpuhp_state_mutex); + return res; +} +static DEVICE_ATTR(states, 0444, show_cpuhp_states, NULL); + +static struct attribute *cpuhp_cpu_root_attrs[] = { + &dev_attr_states.attr, + NULL +}; + +static struct attribute_group cpuhp_cpu_root_attr_group = { + .attrs = cpuhp_cpu_root_attrs, + .name = "hotplug", + NULL +}; + +static int __init cpuhp_sysfs_init(void) +{ + int cpu, ret; + + ret = sysfs_create_group(&cpu_subsys.dev_root->kobj, + &cpuhp_cpu_root_attr_group); + if (ret) + return ret; + + for_each_possible_cpu(cpu) { + struct device *dev = get_cpu_device(cpu); + + if (!dev) + continue; + ret = sysfs_create_group(&dev->kobj, &cpuhp_cpu_attr_group); + if (ret) + return ret; + } + return 0; +} +device_initcall(cpuhp_sysfs_init); +#endif + /* * cpu_bit_bitmap[] is a special, "compressed" data structure that * represents all NR_CPUS bits binary values of 1< Date: Fri, 26 Feb 2016 18:43:32 +0000 Subject: cpu/hotplug: Make target state writeable Make it possible to write a target state to the per cpu state file, so we can switch between states. Signed-off-by: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: Rik van Riel Cc: Rafael Wysocki Cc: "Srivatsa S. Bhat" Cc: Peter Zijlstra Cc: Arjan van de Ven Cc: Sebastian Siewior Cc: Rusty Russell Cc: Steven Rostedt Cc: Oleg Nesterov Cc: Tejun Heo Cc: Andrew Morton Cc: Paul McKenney Cc: Linus Torvalds Cc: Paul Turner Link: http://lkml.kernel.org/r/20160226182341.022814799@linutronix.de Signed-off-by: Thomas Gleixner diff --git a/kernel/cpu.c b/kernel/cpu.c index 1979b89..be9335d 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -48,12 +48,14 @@ static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state); * @teardown: Teardown function of the step * @skip_onerr: Do not invoke the functions on error rollback * Will go away once the notifiers are gone + * @cant_stop: Bringup/teardown can't be stopped at this step */ struct cpuhp_step { const char *name; int (*startup)(unsigned int cpu); int (*teardown)(unsigned int cpu); bool skip_onerr; + bool cant_stop; }; static DEFINE_MUTEX(cpuhp_state_mutex); @@ -558,7 +560,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, if (num_online_cpus() == 1) return -EBUSY; - if (!cpu_online(cpu)) + if (!cpu_present(cpu)) return -EINVAL; cpu_hotplug_begin(); @@ -683,16 +685,25 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) cpu_hotplug_begin(); - if (cpu_online(cpu) || !cpu_present(cpu)) { + if (!cpu_present(cpu)) { ret = -EINVAL; goto out; } - /* Let it fail before we try to bring the cpu up */ - idle = idle_thread_get(cpu); - if (IS_ERR(idle)) { - ret = PTR_ERR(idle); + /* + * The caller of do_cpu_up might have raced with another + * caller. Ignore it for now. + */ + if (st->state >= target) goto out; + + if (st->state == CPUHP_OFFLINE) { + /* Let it fail before we try to bring the cpu up */ + idle = idle_thread_get(cpu); + if (IS_ERR(idle)) { + ret = PTR_ERR(idle); + goto out; + } } cpuhp_tasks_frozen = tasks_frozen; @@ -909,27 +920,32 @@ static struct cpuhp_step cpuhp_bp_states[] = { .name = "threads:create", .startup = smpboot_create_threads, .teardown = NULL, + .cant_stop = true, }, [CPUHP_NOTIFY_PREPARE] = { .name = "notify:prepare", .startup = notify_prepare, .teardown = notify_dead, .skip_onerr = true, + .cant_stop = true, }, [CPUHP_BRINGUP_CPU] = { .name = "cpu:bringup", .startup = bringup_cpu, .teardown = NULL, + .cant_stop = true, }, [CPUHP_TEARDOWN_CPU] = { .name = "cpu:teardown", .startup = NULL, .teardown = takedown_cpu, + .cant_stop = true, }, [CPUHP_NOTIFY_ONLINE] = { .name = "notify:online", .startup = notify_online, .teardown = notify_down_prepare, + .cant_stop = true, }, #endif [CPUHP_ONLINE] = { @@ -947,6 +963,7 @@ static struct cpuhp_step cpuhp_ap_states[] = { .startup = notify_starting, .teardown = notify_dying, .skip_onerr = true, + .cant_stop = true, }, #endif [CPUHP_ONLINE] = { @@ -979,6 +996,46 @@ static ssize_t show_cpuhp_state(struct device *dev, } static DEVICE_ATTR(state, 0444, show_cpuhp_state, NULL); +static ssize_t write_cpuhp_target(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); + struct cpuhp_step *sp; + int target, ret; + + ret = kstrtoint(buf, 10, &target); + if (ret) + return ret; + +#ifdef CONFIG_CPU_HOTPLUG_STATE_CONTROL + if (target < CPUHP_OFFLINE || target > CPUHP_ONLINE) + return -EINVAL; +#else + if (target != CPUHP_OFFLINE && target != CPUHP_ONLINE) + return -EINVAL; +#endif + + ret = lock_device_hotplug_sysfs(); + if (ret) + return ret; + + mutex_lock(&cpuhp_state_mutex); + sp = cpuhp_get_step(target); + ret = !sp->name || sp->cant_stop ? -EINVAL : 0; + mutex_unlock(&cpuhp_state_mutex); + if (ret) + return ret; + + if (st->state < target) + ret = do_cpu_up(dev->id, target); + else + ret = do_cpu_down(dev->id, target); + + unlock_device_hotplug(); + return ret ? ret : count; +} + static ssize_t show_cpuhp_target(struct device *dev, struct device_attribute *attr, char *buf) { @@ -986,7 +1043,7 @@ static ssize_t show_cpuhp_target(struct device *dev, return sprintf(buf, "%d\n", st->target); } -static DEVICE_ATTR(target, 0444, show_cpuhp_target, NULL); +static DEVICE_ATTR(target, 0644, show_cpuhp_target, write_cpuhp_target); static struct attribute *cpuhp_cpu_attrs[] = { &dev_attr_state.attr, @@ -1007,7 +1064,7 @@ static ssize_t show_cpuhp_states(struct device *dev, int i; mutex_lock(&cpuhp_state_mutex); - for (i = 0; i <= CPUHP_ONLINE; i++) { + for (i = CPUHP_OFFLINE; i <= CPUHP_ONLINE; i++) { struct cpuhp_step *sp = cpuhp_get_step(i); if (sp->name) { diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 8bfd1ac..f28f7fa 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1442,6 +1442,19 @@ config DEBUG_BLOCK_EXT_DEVT Say N if you are unsure. +config CPU_HOTPLUG_STATE_CONTROL + bool "Enable CPU hotplug state control" + depends on DEBUG_KERNEL + depends on HOTPLUG_CPU + default n + help + Allows to write steps between "offline" and "online" to the CPUs + sysfs target file so states can be stepped granular. This is a debug + option for now as the hotplug machinery cannot be stopped and + restarted at arbitrary points yet. + + Say N if your are unsure. + config NOTIFIER_ERROR_INJECTION tristate "Notifier error injection" depends on DEBUG_KERNEL -- cgit v0.10.2 From 5b7aa87e0482be768486e0c2277aa4122487eb9d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 26 Feb 2016 18:43:33 +0000 Subject: cpu/hotplug: Implement setup/removal interface Implement function which allow to setup/remove hotplug state callbacks. The default behaviour for setup is to call the startup function for this state for (or on) all cpus which have a hotplug state >= the installed state. The default behaviour for removal is to call the teardown function for this state for (or on) all cpus which have a hotplug state >= the installed state. This includes rollback to the previous state in case of failure. A special state is CPUHP_ONLINE_DYN. Its for dynamically registering a hotplug callback pair. This is for drivers which have no dependencies to avoid that we need to allocate CPUHP states for each of them For both setup and remove helper functions are provided, which prevent the core to issue the callbacks. This simplifies the conversion of existing hotplug notifiers. [ Dynamic registering implemented by Sebastian Siewior ] Signed-off-by: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: Rik van Riel Cc: Rafael Wysocki Cc: "Srivatsa S. Bhat" Cc: Peter Zijlstra Cc: Arjan van de Ven Cc: Sebastian Siewior Cc: Rusty Russell Cc: Steven Rostedt Cc: Oleg Nesterov Cc: Tejun Heo Cc: Andrew Morton Cc: Paul McKenney Cc: Linus Torvalds Cc: Paul Turner Link: http://lkml.kernel.org/r/20160226182341.103464877@linutronix.de Signed-off-by: Thomas Gleixner diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index d9303cc..2993526 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -11,7 +11,74 @@ enum cpuhp_state { CPUHP_AP_ONLINE, CPUHP_TEARDOWN_CPU, CPUHP_NOTIFY_ONLINE, + CPUHP_ONLINE_DYN, + CPUHP_ONLINE_DYN_END = CPUHP_ONLINE_DYN + 30, CPUHP_ONLINE, }; +int __cpuhp_setup_state(enum cpuhp_state state, const char *name, bool invoke, + int (*startup)(unsigned int cpu), + int (*teardown)(unsigned int cpu)); + +/** + * cpuhp_setup_state - Setup hotplug state callbacks with calling the callbacks + * @state: The state for which the calls are installed + * @name: Name of the callback (will be used in debug output) + * @startup: startup callback function + * @teardown: teardown callback function + * + * Installs the callback functions and invokes the startup callback on + * the present cpus which have already reached the @state. + */ +static inline int cpuhp_setup_state(enum cpuhp_state state, + const char *name, + int (*startup)(unsigned int cpu), + int (*teardown)(unsigned int cpu)) +{ + return __cpuhp_setup_state(state, name, true, startup, teardown); +} + +/** + * cpuhp_setup_state_nocalls - Setup hotplug state callbacks without calling the + * callbacks + * @state: The state for which the calls are installed + * @name: Name of the callback. + * @startup: startup callback function + * @teardown: teardown callback function + * + * Same as @cpuhp_setup_state except that no calls are executed are invoked + * during installation of this callback. NOP if SMP=n or HOTPLUG_CPU=n. + */ +static inline int cpuhp_setup_state_nocalls(enum cpuhp_state state, + const char *name, + int (*startup)(unsigned int cpu), + int (*teardown)(unsigned int cpu)) +{ + return __cpuhp_setup_state(state, name, false, startup, teardown); +} + +void __cpuhp_remove_state(enum cpuhp_state state, bool invoke); + +/** + * cpuhp_remove_state - Remove hotplug state callbacks and invoke the teardown + * @state: The state for which the calls are removed + * + * Removes the callback functions and invokes the teardown callback on + * the present cpus which have already reached the @state. + */ +static inline void cpuhp_remove_state(enum cpuhp_state state) +{ + __cpuhp_remove_state(state, true); +} + +/** + * cpuhp_remove_state_nocalls - Remove hotplug state callbacks without invoking + * teardown + * @state: The state for which the calls are removed + */ +static inline void cpuhp_remove_state_nocalls(enum cpuhp_state state) +{ + __cpuhp_remove_state(state, false); +} + #endif diff --git a/kernel/cpu.c b/kernel/cpu.c index be9335d..b5eacb9 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -973,6 +973,14 @@ static struct cpuhp_step cpuhp_ap_states[] = { }, }; +/* Sanity check for callbacks */ +static int cpuhp_cb_check(enum cpuhp_state state) +{ + if (state <= CPUHP_OFFLINE || state >= CPUHP_ONLINE) + return -EINVAL; + return 0; +} + static bool cpuhp_is_ap_state(enum cpuhp_state state) { return (state > CPUHP_AP_OFFLINE && state < CPUHP_AP_ONLINE); @@ -986,6 +994,222 @@ static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state) return sp + state; } +static void cpuhp_store_callbacks(enum cpuhp_state state, + const char *name, + int (*startup)(unsigned int cpu), + int (*teardown)(unsigned int cpu)) +{ + /* (Un)Install the callbacks for further cpu hotplug operations */ + struct cpuhp_step *sp; + + mutex_lock(&cpuhp_state_mutex); + sp = cpuhp_get_step(state); + sp->startup = startup; + sp->teardown = teardown; + sp->name = name; + mutex_unlock(&cpuhp_state_mutex); +} + +static void *cpuhp_get_teardown_cb(enum cpuhp_state state) +{ + return cpuhp_get_step(state)->teardown; +} + +/* Helper function to run callback on the target cpu */ +static void cpuhp_on_cpu_cb(void *__cb) +{ + int (*cb)(unsigned int cpu) = __cb; + + BUG_ON(cb(smp_processor_id())); +} + +/* + * Call the startup/teardown function for a step either on the AP or + * on the current CPU. + */ +static int cpuhp_issue_call(int cpu, enum cpuhp_state state, + int (*cb)(unsigned int), bool bringup) +{ + int ret; + + if (!cb) + return 0; + + /* + * This invokes the callback directly for now. In a later step we + * convert that to use cpuhp_invoke_callback(). + */ + if (cpuhp_is_ap_state(state)) { + /* + * Note, that a function called on the AP is not + * allowed to fail. + */ + if (cpu_online(cpu)) + smp_call_function_single(cpu, cpuhp_on_cpu_cb, cb, 1); + return 0; + } + + /* + * The non AP bound callbacks can fail on bringup. On teardown + * e.g. module removal we crash for now. + */ + ret = cb(cpu); + BUG_ON(ret && !bringup); + return ret; +} + +/* + * Called from __cpuhp_setup_state on a recoverable failure. + * + * Note: The teardown callbacks for rollback are not allowed to fail! + */ +static void cpuhp_rollback_install(int failedcpu, enum cpuhp_state state, + int (*teardown)(unsigned int cpu)) +{ + int cpu; + + if (!teardown) + return; + + /* Roll back the already executed steps on the other cpus */ + for_each_present_cpu(cpu) { + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + int cpustate = st->state; + + if (cpu >= failedcpu) + break; + + /* Did we invoke the startup call on that cpu ? */ + if (cpustate >= state) + cpuhp_issue_call(cpu, state, teardown, false); + } +} + +/* + * Returns a free for dynamic slot assignment of the Online state. The states + * are protected by the cpuhp_slot_states mutex and an empty slot is identified + * by having no name assigned. + */ +static int cpuhp_reserve_state(enum cpuhp_state state) +{ + enum cpuhp_state i; + + mutex_lock(&cpuhp_state_mutex); + for (i = CPUHP_ONLINE_DYN; i <= CPUHP_ONLINE_DYN_END; i++) { + if (cpuhp_bp_states[i].name) + continue; + + cpuhp_bp_states[i].name = "Reserved"; + mutex_unlock(&cpuhp_state_mutex); + return i; + } + mutex_unlock(&cpuhp_state_mutex); + WARN(1, "No more dynamic states available for CPU hotplug\n"); + return -ENOSPC; +} + +/** + * __cpuhp_setup_state - Setup the callbacks for an hotplug machine state + * @state: The state to setup + * @invoke: If true, the startup function is invoked for cpus where + * cpu state >= @state + * @startup: startup callback function + * @teardown: teardown callback function + * + * Returns 0 if successful, otherwise a proper error code + */ +int __cpuhp_setup_state(enum cpuhp_state state, + const char *name, bool invoke, + int (*startup)(unsigned int cpu), + int (*teardown)(unsigned int cpu)) +{ + int cpu, ret = 0; + int dyn_state = 0; + + if (cpuhp_cb_check(state) || !name) + return -EINVAL; + + get_online_cpus(); + + /* currently assignments for the ONLINE state are possible */ + if (state == CPUHP_ONLINE_DYN) { + dyn_state = 1; + ret = cpuhp_reserve_state(state); + if (ret < 0) + goto out; + state = ret; + } + + cpuhp_store_callbacks(state, name, startup, teardown); + + if (!invoke || !startup) + goto out; + + /* + * Try to call the startup callback for each present cpu + * depending on the hotplug state of the cpu. + */ + for_each_present_cpu(cpu) { + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + int cpustate = st->state; + + if (cpustate < state) + continue; + + ret = cpuhp_issue_call(cpu, state, startup, true); + if (ret) { + cpuhp_rollback_install(cpu, state, teardown); + cpuhp_store_callbacks(state, NULL, NULL, NULL); + goto out; + } + } +out: + put_online_cpus(); + if (!ret && dyn_state) + return state; + return ret; +} +EXPORT_SYMBOL(__cpuhp_setup_state); + +/** + * __cpuhp_remove_state - Remove the callbacks for an hotplug machine state + * @state: The state to remove + * @invoke: If true, the teardown function is invoked for cpus where + * cpu state >= @state + * + * The teardown callback is currently not allowed to fail. Think + * about module removal! + */ +void __cpuhp_remove_state(enum cpuhp_state state, bool invoke) +{ + int (*teardown)(unsigned int cpu) = cpuhp_get_teardown_cb(state); + int cpu; + + BUG_ON(cpuhp_cb_check(state)); + + get_online_cpus(); + + if (!invoke || !teardown) + goto remove; + + /* + * Call the teardown callback for each present cpu depending + * on the hotplug state of the cpu. This function is not + * allowed to fail currently! + */ + for_each_present_cpu(cpu) { + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + int cpustate = st->state; + + if (cpustate >= state) + cpuhp_issue_call(cpu, state, teardown, false); + } +remove: + cpuhp_store_callbacks(state, NULL, NULL, NULL); + put_online_cpus(); +} +EXPORT_SYMBOL(__cpuhp_remove_state); + #if defined(CONFIG_SYSFS) && defined(CONFIG_HOTPLUG_CPU) static ssize_t show_cpuhp_state(struct device *dev, struct device_attribute *attr, char *buf) -- cgit v0.10.2 From 949338e35131c551f7bf54f48a2e3a227af6721b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 26 Feb 2016 18:43:35 +0000 Subject: cpu/hotplug: Move scheduler cpu_online notifier to hotplug core Move the scheduler cpu online notifier part to the hotplug core. This is anyway the highest priority callback and we need that functionality right now for the next changes. Signed-off-by: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: Rik van Riel Cc: Rafael Wysocki Cc: "Srivatsa S. Bhat" Cc: Peter Zijlstra Cc: Arjan van de Ven Cc: Sebastian Siewior Cc: Rusty Russell Cc: Steven Rostedt Cc: Oleg Nesterov Cc: Tejun Heo Cc: Andrew Morton Cc: Paul McKenney Cc: Linus Torvalds Cc: Paul Turner Link: http://lkml.kernel.org/r/20160226182341.200791046@linutronix.de Signed-off-by: Thomas Gleixner diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 2993526..2f2e5d9 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -10,6 +10,7 @@ enum cpuhp_state { CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, CPUHP_TEARDOWN_CPU, + CPUHP_CPU_SET_ACTIVE, CPUHP_NOTIFY_ONLINE, CPUHP_ONLINE_DYN, CPUHP_ONLINE_DYN_END = CPUHP_ONLINE_DYN + 30, diff --git a/kernel/cpu.c b/kernel/cpu.c index b5eacb9..65e34d3 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -666,6 +666,19 @@ void notify_cpu_starting(unsigned int cpu) } } +/* + * Called from the idle task. We need to set active here, so we can kick off + * the stopper thread. + */ +static int cpuhp_set_cpu_active(unsigned int cpu) +{ + /* The cpu is marked online, set it active now */ + set_cpu_active(cpu, true); + /* Unpark the stopper thread */ + stop_machine_unpark(cpu); + return 0; +} + static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st) { for (st->state--; st->state > st->target; st->state--) { @@ -941,6 +954,11 @@ static struct cpuhp_step cpuhp_bp_states[] = { .teardown = takedown_cpu, .cant_stop = true, }, + [CPUHP_CPU_SET_ACTIVE] = { + .name = "cpu:active", + .startup = cpuhp_set_cpu_active, + .teardown = NULL, + }, [CPUHP_NOTIFY_ONLINE] = { .name = "notify:online", .startup = notify_online, diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 9503d59..6266463 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5692,16 +5692,6 @@ static int sched_cpu_active(struct notifier_block *nfb, set_cpu_rq_start_time(); return NOTIFY_OK; - case CPU_ONLINE: - /* - * At this point a starting CPU has marked itself as online via - * set_cpu_online(). But it might not yet have marked itself - * as active, which is essential from here on. - */ - set_cpu_active(cpu, true); - stop_machine_unpark(cpu); - return NOTIFY_OK; - case CPU_DOWN_FAILED: set_cpu_active(cpu, true); return NOTIFY_OK; -- cgit v0.10.2 From 931ef163309ee955611f287dc65248b39a65fc9d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 26 Feb 2016 18:43:36 +0000 Subject: cpu/hotplug: Unpark smpboot threads from the state machine Handle the smpboot threads in the state machine. Signed-off-by: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: Rik van Riel Cc: Rafael Wysocki Cc: "Srivatsa S. Bhat" Cc: Peter Zijlstra Cc: Arjan van de Ven Cc: Sebastian Siewior Cc: Rusty Russell Cc: Steven Rostedt Cc: Oleg Nesterov Cc: Tejun Heo Cc: Andrew Morton Cc: Paul McKenney Cc: Linus Torvalds Cc: Paul Turner Link: http://lkml.kernel.org/r/20160226182341.295777684@linutronix.de Signed-off-by: Thomas Gleixner diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 78989f2..83f3576 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -78,7 +78,7 @@ enum { /* migration should happen before other stuff but after perf */ CPU_PRI_PERF = 20, CPU_PRI_MIGRATION = 10, - CPU_PRI_SMPBOOT = 9, + /* bring up workqueues before normal notifiers and down after */ CPU_PRI_WORKQUEUE_UP = 5, CPU_PRI_WORKQUEUE_DOWN = -5, @@ -172,7 +172,6 @@ static inline void __unregister_cpu_notifier(struct notifier_block *nb) } #endif -void smpboot_thread_init(void); int cpu_up(unsigned int cpu); void notify_cpu_starting(unsigned int cpu); extern void cpu_maps_update_begin(void); @@ -221,10 +220,6 @@ static inline void cpu_notifier_register_done(void) { } -static inline void smpboot_thread_init(void) -{ -} - #endif /* CONFIG_SMP */ extern struct bus_type cpu_subsys; diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 2f2e5d9..3867910 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -11,6 +11,7 @@ enum cpuhp_state { CPUHP_AP_ONLINE, CPUHP_TEARDOWN_CPU, CPUHP_CPU_SET_ACTIVE, + CPUHP_SMPBOOT_THREADS, CPUHP_NOTIFY_ONLINE, CPUHP_ONLINE_DYN, CPUHP_ONLINE_DYN_END = CPUHP_ONLINE_DYN + 30, diff --git a/init/main.c b/init/main.c index c2ea723..55563fd 100644 --- a/init/main.c +++ b/init/main.c @@ -388,7 +388,6 @@ static noinline void __init_refok rest_init(void) int pid; rcu_scheduler_starting(); - smpboot_thread_init(); /* * We need to spawn init first so that it obtains pid 1, however * the init task will end up wanting to create kthreads, which, if diff --git a/kernel/cpu.c b/kernel/cpu.c index 65e34d3..3ec86bc 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -481,8 +481,6 @@ static int takedown_cpu(unsigned int cpu) else synchronize_rcu(); - smpboot_park_threads(cpu); - /* * Prevent irq alloc/free while the dying cpu reorganizes the * interrupt affinities. @@ -612,38 +610,6 @@ int cpu_down(unsigned int cpu) EXPORT_SYMBOL(cpu_down); #endif /*CONFIG_HOTPLUG_CPU*/ -/* - * Unpark per-CPU smpboot kthreads at CPU-online time. - */ -static int smpboot_thread_call(struct notifier_block *nfb, - unsigned long action, void *hcpu) -{ - int cpu = (long)hcpu; - - switch (action & ~CPU_TASKS_FROZEN) { - - case CPU_DOWN_FAILED: - case CPU_ONLINE: - smpboot_unpark_threads(cpu); - break; - - default: - break; - } - - return NOTIFY_OK; -} - -static struct notifier_block smpboot_thread_notifier = { - .notifier_call = smpboot_thread_call, - .priority = CPU_PRI_SMPBOOT, -}; - -void smpboot_thread_init(void) -{ - register_cpu_notifier(&smpboot_thread_notifier); -} - /** * notify_cpu_starting(cpu) - call the CPU_STARTING notifiers * @cpu: cpu that just started @@ -959,6 +925,11 @@ static struct cpuhp_step cpuhp_bp_states[] = { .startup = cpuhp_set_cpu_active, .teardown = NULL, }, + [CPUHP_SMPBOOT_THREADS] = { + .name = "smpboot:threads", + .startup = smpboot_unpark_threads, + .teardown = smpboot_park_threads, + }, [CPUHP_NOTIFY_ONLINE] = { .name = "notify:online", .startup = notify_online, diff --git a/kernel/smpboot.c b/kernel/smpboot.c index d264f59..13bc43d 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -226,7 +226,7 @@ static void smpboot_unpark_thread(struct smp_hotplug_thread *ht, unsigned int cp kthread_unpark(tsk); } -void smpboot_unpark_threads(unsigned int cpu) +int smpboot_unpark_threads(unsigned int cpu) { struct smp_hotplug_thread *cur; @@ -235,6 +235,7 @@ void smpboot_unpark_threads(unsigned int cpu) if (cpumask_test_cpu(cpu, cur->cpumask)) smpboot_unpark_thread(cur, cpu); mutex_unlock(&smpboot_threads_lock); + return 0; } static void smpboot_park_thread(struct smp_hotplug_thread *ht, unsigned int cpu) @@ -245,7 +246,7 @@ static void smpboot_park_thread(struct smp_hotplug_thread *ht, unsigned int cpu) kthread_park(tsk); } -void smpboot_park_threads(unsigned int cpu) +int smpboot_park_threads(unsigned int cpu) { struct smp_hotplug_thread *cur; @@ -253,6 +254,7 @@ void smpboot_park_threads(unsigned int cpu) list_for_each_entry_reverse(cur, &hotplug_threads, list) smpboot_park_thread(cur, cpu); mutex_unlock(&smpboot_threads_lock); + return 0; } static void smpboot_destroy_threads(struct smp_hotplug_thread *ht) diff --git a/kernel/smpboot.h b/kernel/smpboot.h index 72415a0..6b5f020 100644 --- a/kernel/smpboot.h +++ b/kernel/smpboot.h @@ -14,7 +14,7 @@ static inline void idle_threads_init(void) { } #endif int smpboot_create_threads(unsigned int cpu); -void smpboot_park_threads(unsigned int cpu); -void smpboot_unpark_threads(unsigned int cpu); +int smpboot_park_threads(unsigned int cpu); +int smpboot_unpark_threads(unsigned int cpu); #endif -- cgit v0.10.2 From 2e1a3483ce74d197876e58281925dd4e378a7f28 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 26 Feb 2016 18:43:37 +0000 Subject: cpu/hotplug: Split out the state walk into functions We need that for running callbacks on the AP and the BP. Signed-off-by: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: Rik van Riel Cc: Rafael Wysocki Cc: "Srivatsa S. Bhat" Cc: Peter Zijlstra Cc: Arjan van de Ven Cc: Sebastian Siewior Cc: Rusty Russell Cc: Steven Rostedt Cc: Oleg Nesterov Cc: Tejun Heo Cc: Andrew Morton Cc: Paul McKenney Cc: Linus Torvalds Cc: Paul Turner Link: http://lkml.kernel.org/r/20160226182341.374946234@linutronix.de Signed-off-by: Thomas Gleixner diff --git a/kernel/cpu.c b/kernel/cpu.c index 3ec86bc..9572ca0 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -329,10 +329,74 @@ static int bringup_cpu(unsigned int cpu) return 0; } +/* + * Hotplug state machine related functions + */ +static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st, + struct cpuhp_step *steps) +{ + for (st->state++; st->state < st->target; st->state++) { + struct cpuhp_step *step = steps + st->state; + + if (!step->skip_onerr) + cpuhp_invoke_callback(cpu, st->state, step->startup); + } +} + +static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, + struct cpuhp_step *steps, enum cpuhp_state target) +{ + enum cpuhp_state prev_state = st->state; + int ret = 0; + + for (; st->state > target; st->state--) { + struct cpuhp_step *step = steps + st->state; + + ret = cpuhp_invoke_callback(cpu, st->state, step->teardown); + if (ret) { + st->target = prev_state; + undo_cpu_down(cpu, st, steps); + break; + } + } + return ret; +} + +static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st, + struct cpuhp_step *steps) +{ + for (st->state--; st->state > st->target; st->state--) { + struct cpuhp_step *step = steps + st->state; + + if (!step->skip_onerr) + cpuhp_invoke_callback(cpu, st->state, step->teardown); + } +} + +static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, + struct cpuhp_step *steps, enum cpuhp_state target) +{ + enum cpuhp_state prev_state = st->state; + int ret = 0; + + while (st->state < target) { + struct cpuhp_step *step; + + st->state++; + step = steps + st->state; + ret = cpuhp_invoke_callback(cpu, st->state, step->startup); + if (ret) { + st->target = prev_state; + undo_cpu_up(cpu, st, steps); + break; + } + } + return ret; +} + #ifdef CONFIG_HOTPLUG_CPU EXPORT_SYMBOL(register_cpu_notifier); EXPORT_SYMBOL(__register_cpu_notifier); - void unregister_cpu_notifier(struct notifier_block *nb) { cpu_maps_update_begin(); @@ -537,15 +601,6 @@ static int notify_dead(unsigned int cpu) #endif #ifdef CONFIG_HOTPLUG_CPU -static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st) -{ - for (st->state++; st->state < st->target; st->state++) { - struct cpuhp_step *step = cpuhp_bp_states + st->state; - - if (!step->skip_onerr) - cpuhp_invoke_callback(cpu, st->state, step->startup); - } -} /* Requires cpu_add_remove_lock to be held */ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, @@ -567,16 +622,8 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, prev_state = st->state; st->target = target; - for (; st->state > st->target; st->state--) { - struct cpuhp_step *step = cpuhp_bp_states + st->state; + ret = cpuhp_down_callbacks(cpu, st, cpuhp_bp_states, target); - ret = cpuhp_invoke_callback(cpu, st->state, step->teardown); - if (ret) { - st->target = prev_state; - undo_cpu_down(cpu, st); - break; - } - } hasdied = prev_state != st->state && st->state == CPUHP_OFFLINE; cpu_hotplug_done(); @@ -645,22 +692,12 @@ static int cpuhp_set_cpu_active(unsigned int cpu) return 0; } -static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st) -{ - for (st->state--; st->state > st->target; st->state--) { - struct cpuhp_step *step = cpuhp_bp_states + st->state; - - if (!step->skip_onerr) - cpuhp_invoke_callback(cpu, st->state, step->teardown); - } -} - /* Requires cpu_add_remove_lock to be held */ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct task_struct *idle; - int prev_state, ret = 0; + int ret = 0; cpu_hotplug_begin(); @@ -687,20 +724,8 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) cpuhp_tasks_frozen = tasks_frozen; - prev_state = st->state; st->target = target; - while (st->state < st->target) { - struct cpuhp_step *step; - - st->state++; - step = cpuhp_bp_states + st->state; - ret = cpuhp_invoke_callback(cpu, st->state, step->startup); - if (ret) { - st->target = prev_state; - undo_cpu_up(cpu, st); - break; - } - } + ret = cpuhp_up_callbacks(cpu, st, cpuhp_bp_states, target); out: cpu_hotplug_done(); return ret; -- cgit v0.10.2 From 4cb28ced23c4f222ff4e3f39898017e52161a9c9 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 26 Feb 2016 18:43:38 +0000 Subject: cpu/hotplug: Create hotplug threads In order to let the hotplugged cpu take care of the setup/teardown, we need a seperate hotplug thread. Signed-off-by: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: Rik van Riel Cc: Rafael Wysocki Cc: "Srivatsa S. Bhat" Cc: Peter Zijlstra Cc: Arjan van de Ven Cc: Sebastian Siewior Cc: Rusty Russell Cc: Steven Rostedt Cc: Oleg Nesterov Cc: Tejun Heo Cc: Andrew Morton Cc: Paul McKenney Cc: Linus Torvalds Cc: Paul Turner Link: http://lkml.kernel.org/r/20160226182341.454541272@linutronix.de Signed-off-by: Thomas Gleixner diff --git a/kernel/cpu.c b/kernel/cpu.c index 9572ca0..9048c33 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #define CREATE_TRACE_POINTS @@ -33,10 +34,24 @@ * cpuhp_cpu_state - Per cpu hotplug state storage * @state: The current cpu state * @target: The target state + * @thread: Pointer to the hotplug thread + * @should_run: Thread should execute + * @cb_stat: The state for a single callback (install/uninstall) + * @cb: Single callback function (install/uninstall) + * @result: Result of the operation + * @done: Signal completion to the issuer of the task */ struct cpuhp_cpu_state { enum cpuhp_state state; enum cpuhp_state target; +#ifdef CONFIG_SMP + struct task_struct *thread; + bool should_run; + enum cpuhp_state cb_state; + int (*cb)(unsigned int cpu); + int result; + struct completion done; +#endif }; static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state); @@ -394,6 +409,134 @@ static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, return ret; } +/* + * The cpu hotplug threads manage the bringup and teardown of the cpus + */ +static void cpuhp_create(unsigned int cpu) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + + init_completion(&st->done); +} + +static int cpuhp_should_run(unsigned int cpu) +{ + struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); + + return st->should_run; +} + +/* Execute the teardown callbacks. Used to be CPU_DOWN_PREPARE */ +static int cpuhp_ap_offline(unsigned int cpu, struct cpuhp_cpu_state *st) +{ + enum cpuhp_state target = max((int)st->target, CPUHP_AP_ONLINE); + + return cpuhp_down_callbacks(cpu, st, cpuhp_ap_states, target); +} + +/* Execute the online startup callbacks. Used to be CPU_ONLINE */ +static int cpuhp_ap_online(unsigned int cpu, struct cpuhp_cpu_state *st) +{ + return cpuhp_up_callbacks(cpu, st, cpuhp_ap_states, st->target); +} + +/* + * Execute teardown/startup callbacks on the plugged cpu. Also used to invoke + * callbacks when a state gets [un]installed at runtime. + */ +static void cpuhp_thread_fun(unsigned int cpu) +{ + struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); + int ret = 0; + + /* + * Paired with the mb() in cpuhp_kick_ap_work and + * cpuhp_invoke_ap_callback, so the work set is consistent visible. + */ + smp_mb(); + if (!st->should_run) + return; + + st->should_run = false; + + /* Single callback invocation for [un]install ? */ + if (st->cb) { + if (st->cb_state < CPUHP_AP_ONLINE) { + local_irq_disable(); + ret = cpuhp_invoke_callback(cpu, st->cb_state, st->cb); + local_irq_enable(); + } else { + ret = cpuhp_invoke_callback(cpu, st->cb_state, st->cb); + } + } else { + /* Regular hotplug work */ + if (st->state < st->target) + ret = cpuhp_ap_online(cpu, st); + else if (st->state > st->target) + ret = cpuhp_ap_offline(cpu, st); + } + st->result = ret; + complete(&st->done); +} + +/* Invoke a single callback on a remote cpu */ +static int cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, + int (*cb)(unsigned int)) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + + if (!cpu_online(cpu)) + return 0; + + st->cb_state = state; + st->cb = cb; + /* + * Make sure the above stores are visible before should_run becomes + * true. Paired with the mb() above in cpuhp_thread_fun() + */ + smp_mb(); + st->should_run = true; + wake_up_process(st->thread); + wait_for_completion(&st->done); + return st->result; +} + +/* Regular hotplug invocation of the AP hotplug thread */ +static int cpuhp_kick_ap_work(unsigned int cpu) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + enum cpuhp_state state = st->state; + + trace_cpuhp_enter(cpu, st->target, state, cpuhp_kick_ap_work); + st->result = 0; + st->cb = NULL; + /* + * Make sure the above stores are visible before should_run becomes + * true. Paired with the mb() above in cpuhp_thread_fun() + */ + smp_mb(); + st->should_run = true; + wake_up_process(st->thread); + wait_for_completion(&st->done); + trace_cpuhp_exit(cpu, st->state, state, st->result); + return st->result; +} + +static struct smp_hotplug_thread cpuhp_threads = { + .store = &cpuhp_state.thread, + .create = &cpuhp_create, + .thread_should_run = cpuhp_should_run, + .thread_fn = cpuhp_thread_fun, + .thread_comm = "cpuhp/%u", + .selfparking = true, +}; + +void __init cpuhp_threads_init(void) +{ + BUG_ON(smpboot_register_percpu_thread(&cpuhp_threads)); + kthread_unpark(this_cpu_read(cpuhp_state.thread)); +} + #ifdef CONFIG_HOTPLUG_CPU EXPORT_SYMBOL(register_cpu_notifier); EXPORT_SYMBOL(__register_cpu_notifier); @@ -997,7 +1140,7 @@ static int cpuhp_cb_check(enum cpuhp_state state) static bool cpuhp_is_ap_state(enum cpuhp_state state) { - return (state > CPUHP_AP_OFFLINE && state < CPUHP_AP_ONLINE); + return (state >= CPUHP_AP_OFFLINE && state <= CPUHP_AP_ONLINE); } static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state) diff --git a/kernel/smp.c b/kernel/smp.c index d903c02..822ffb1 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -569,6 +569,7 @@ void __init smp_init(void) unsigned int cpu; idle_threads_init(); + cpuhp_threads_init(); /* FIXME: This should be done in userspace --RR */ for_each_present_cpu(cpu) { diff --git a/kernel/smpboot.h b/kernel/smpboot.h index 6b5f020..485b81c 100644 --- a/kernel/smpboot.h +++ b/kernel/smpboot.h @@ -17,4 +17,6 @@ int smpboot_create_threads(unsigned int cpu); int smpboot_park_threads(unsigned int cpu); int smpboot_unpark_threads(unsigned int cpu); +void __init cpuhp_threads_init(void); + #endif -- cgit v0.10.2 From 1cf4f629d9d246519a1e76c021806f2a51ddba4d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 26 Feb 2016 18:43:39 +0000 Subject: cpu/hotplug: Move online calls to hotplugged cpu Let the hotplugged cpu invoke the setup/teardown callbacks (CPU_ONLINE/CPU_DOWN_PREPARE) itself. Signed-off-by: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: Rik van Riel Cc: Rafael Wysocki Cc: "Srivatsa S. Bhat" Cc: Peter Zijlstra Cc: Arjan van de Ven Cc: Sebastian Siewior Cc: Rusty Russell Cc: Steven Rostedt Cc: Oleg Nesterov Cc: Tejun Heo Cc: Andrew Morton Cc: Paul McKenney Cc: Linus Torvalds Cc: Paul Turner Link: http://lkml.kernel.org/r/20160226182341.536364371@linutronix.de Signed-off-by: Thomas Gleixner diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 3867910..8a715bb 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -11,10 +11,12 @@ enum cpuhp_state { CPUHP_AP_ONLINE, CPUHP_TEARDOWN_CPU, CPUHP_CPU_SET_ACTIVE, - CPUHP_SMPBOOT_THREADS, - CPUHP_NOTIFY_ONLINE, - CPUHP_ONLINE_DYN, - CPUHP_ONLINE_DYN_END = CPUHP_ONLINE_DYN + 30, + CPUHP_KICK_AP_THREAD, + CPUHP_BP_ONLINE, + CPUHP_AP_SMPBOOT_THREADS, + CPUHP_AP_NOTIFY_ONLINE, + CPUHP_AP_ONLINE_DYN, + CPUHP_AP_ONLINE_DYN_END = CPUHP_AP_ONLINE_DYN + 30, CPUHP_ONLINE, }; diff --git a/kernel/cpu.c b/kernel/cpu.c index 9048c33..e220e56 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -429,7 +429,7 @@ static int cpuhp_should_run(unsigned int cpu) /* Execute the teardown callbacks. Used to be CPU_DOWN_PREPARE */ static int cpuhp_ap_offline(unsigned int cpu, struct cpuhp_cpu_state *st) { - enum cpuhp_state target = max((int)st->target, CPUHP_AP_ONLINE); + enum cpuhp_state target = max((int)st->target, CPUHP_TEARDOWN_CPU); return cpuhp_down_callbacks(cpu, st, cpuhp_ap_states, target); } @@ -469,6 +469,9 @@ static void cpuhp_thread_fun(unsigned int cpu) ret = cpuhp_invoke_callback(cpu, st->cb_state, st->cb); } } else { + /* Cannot happen .... */ + BUG_ON(st->state < CPUHP_KICK_AP_THREAD); + /* Regular hotplug work */ if (st->state < st->target) ret = cpuhp_ap_online(cpu, st); @@ -502,12 +505,8 @@ static int cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, } /* Regular hotplug invocation of the AP hotplug thread */ -static int cpuhp_kick_ap_work(unsigned int cpu) +static void __cpuhp_kick_ap_work(struct cpuhp_cpu_state *st) { - struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); - enum cpuhp_state state = st->state; - - trace_cpuhp_enter(cpu, st->target, state, cpuhp_kick_ap_work); st->result = 0; st->cb = NULL; /* @@ -517,6 +516,15 @@ static int cpuhp_kick_ap_work(unsigned int cpu) smp_mb(); st->should_run = true; wake_up_process(st->thread); +} + +static int cpuhp_kick_ap_work(unsigned int cpu) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + enum cpuhp_state state = st->state; + + trace_cpuhp_enter(cpu, st->target, state, cpuhp_kick_ap_work); + __cpuhp_kick_ap_work(st); wait_for_completion(&st->done); trace_cpuhp_exit(cpu, st->state, state, st->result); return st->result; @@ -688,6 +696,9 @@ static int takedown_cpu(unsigned int cpu) else synchronize_rcu(); + /* Park the hotplug thread */ + kthread_park(per_cpu_ptr(&cpuhp_state, cpu)->thread); + /* * Prevent irq alloc/free while the dying cpu reorganizes the * interrupt affinities. @@ -765,10 +776,34 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, prev_state = st->state; st->target = target; + /* + * If the current CPU state is in the range of the AP hotplug thread, + * then we need to kick the thread. + */ + if (st->state >= CPUHP_KICK_AP_THREAD) { + ret = cpuhp_kick_ap_work(cpu); + /* + * The AP side has done the error rollback already. Just + * return the error code.. + */ + if (ret) + goto out; + + /* + * We might have stopped still in the range of the AP hotplug + * thread. Nothing to do anymore. + */ + if (st->state >= CPUHP_KICK_AP_THREAD) + goto out; + } + /* + * The AP brought itself down below CPUHP_KICK_AP_THREAD. So we need + * to do the further cleanups. + */ ret = cpuhp_down_callbacks(cpu, st, cpuhp_bp_states, target); hasdied = prev_state != st->state && st->state == CPUHP_OFFLINE; - +out: cpu_hotplug_done(); /* This post dead nonsense must die */ if (!ret && hasdied) @@ -828,10 +863,13 @@ void notify_cpu_starting(unsigned int cpu) */ static int cpuhp_set_cpu_active(unsigned int cpu) { + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + /* The cpu is marked online, set it active now */ set_cpu_active(cpu, true); - /* Unpark the stopper thread */ + /* Unpark the stopper thread and the hotplug thread */ stop_machine_unpark(cpu); + kthread_unpark(st->thread); return 0; } @@ -868,6 +906,26 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) cpuhp_tasks_frozen = tasks_frozen; st->target = target; + /* + * If the current CPU state is in the range of the AP hotplug thread, + * then we need to kick the thread once more. + */ + if (st->state >= CPUHP_KICK_AP_THREAD) { + ret = cpuhp_kick_ap_work(cpu); + /* + * The AP side has done the error rollback already. Just + * return the error code.. + */ + if (ret) + goto out; + } + + /* + * Try to reach the target state. We max out on the BP at + * CPUHP_KICK_AP_THREAD. After that the AP hotplug thread is + * responsible for bringing it up to the target state. + */ + target = min((int)target, CPUHP_KICK_AP_THREAD); ret = cpuhp_up_callbacks(cpu, st, cpuhp_bp_states, target); out: cpu_hotplug_done(); @@ -1093,19 +1151,13 @@ static struct cpuhp_step cpuhp_bp_states[] = { .startup = cpuhp_set_cpu_active, .teardown = NULL, }, - [CPUHP_SMPBOOT_THREADS] = { - .name = "smpboot:threads", - .startup = smpboot_unpark_threads, - .teardown = smpboot_park_threads, - }, - [CPUHP_NOTIFY_ONLINE] = { - .name = "notify:online", - .startup = notify_online, - .teardown = notify_down_prepare, - .cant_stop = true, + [CPUHP_KICK_AP_THREAD] = { + .name = "cpuhp:kickthread", + .startup = cpuhp_kick_ap_work, + .teardown = cpuhp_kick_ap_work, }, #endif - [CPUHP_ONLINE] = { + [CPUHP_BP_ONLINE] = { .name = "online", .startup = NULL, .teardown = NULL, @@ -1122,6 +1174,16 @@ static struct cpuhp_step cpuhp_ap_states[] = { .skip_onerr = true, .cant_stop = true, }, + [CPUHP_AP_SMPBOOT_THREADS] = { + .name = "smpboot:threads", + .startup = smpboot_unpark_threads, + .teardown = smpboot_park_threads, + }, + [CPUHP_AP_NOTIFY_ONLINE] = { + .name = "notify:online", + .startup = notify_online, + .teardown = notify_down_prepare, + }, #endif [CPUHP_ONLINE] = { .name = "online", @@ -1140,7 +1202,9 @@ static int cpuhp_cb_check(enum cpuhp_state state) static bool cpuhp_is_ap_state(enum cpuhp_state state) { - return (state >= CPUHP_AP_OFFLINE && state <= CPUHP_AP_ONLINE); + if (state >= CPUHP_AP_OFFLINE && state <= CPUHP_AP_ONLINE) + return true; + return state > CPUHP_BP_ONLINE; } static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state) @@ -1172,14 +1236,6 @@ static void *cpuhp_get_teardown_cb(enum cpuhp_state state) return cpuhp_get_step(state)->teardown; } -/* Helper function to run callback on the target cpu */ -static void cpuhp_on_cpu_cb(void *__cb) -{ - int (*cb)(unsigned int cpu) = __cb; - - BUG_ON(cb(smp_processor_id())); -} - /* * Call the startup/teardown function for a step either on the AP or * on the current CPU. @@ -1191,26 +1247,18 @@ static int cpuhp_issue_call(int cpu, enum cpuhp_state state, if (!cb) return 0; - - /* - * This invokes the callback directly for now. In a later step we - * convert that to use cpuhp_invoke_callback(). - */ - if (cpuhp_is_ap_state(state)) { - /* - * Note, that a function called on the AP is not - * allowed to fail. - */ - if (cpu_online(cpu)) - smp_call_function_single(cpu, cpuhp_on_cpu_cb, cb, 1); - return 0; - } - /* * The non AP bound callbacks can fail on bringup. On teardown * e.g. module removal we crash for now. */ - ret = cb(cpu); +#ifdef CONFIG_SMP + if (cpuhp_is_ap_state(state)) + ret = cpuhp_invoke_ap_callback(cpu, state, cb); + else + ret = cpuhp_invoke_callback(cpu, state, cb); +#else + ret = cpuhp_invoke_callback(cpu, state, cb); +#endif BUG_ON(ret && !bringup); return ret; } @@ -1252,11 +1300,11 @@ static int cpuhp_reserve_state(enum cpuhp_state state) enum cpuhp_state i; mutex_lock(&cpuhp_state_mutex); - for (i = CPUHP_ONLINE_DYN; i <= CPUHP_ONLINE_DYN_END; i++) { - if (cpuhp_bp_states[i].name) + for (i = CPUHP_AP_ONLINE_DYN; i <= CPUHP_AP_ONLINE_DYN_END; i++) { + if (cpuhp_ap_states[i].name) continue; - cpuhp_bp_states[i].name = "Reserved"; + cpuhp_ap_states[i].name = "Reserved"; mutex_unlock(&cpuhp_state_mutex); return i; } @@ -1289,7 +1337,7 @@ int __cpuhp_setup_state(enum cpuhp_state state, get_online_cpus(); /* currently assignments for the ONLINE state are possible */ - if (state == CPUHP_ONLINE_DYN) { + if (state == CPUHP_AP_ONLINE_DYN) { dyn_state = 1; ret = cpuhp_reserve_state(state); if (ret < 0) -- cgit v0.10.2 From fc6d73d67436e7784758a831227bd019547a3f73 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 26 Feb 2016 18:43:40 +0000 Subject: arch/hotplug: Call into idle with a proper state Let the non boot cpus call into idle with the corresponding hotplug state, so the hotplug core can handle the further bringup. That's a first step to convert the boot side of the hotplugged cpus to do all the synchronization with the other side through the state machine. For now it'll only start the hotplug thread and kick the full bringup of the cpu. Signed-off-by: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: Rik van Riel Cc: Rafael Wysocki Cc: "Srivatsa S. Bhat" Cc: Peter Zijlstra Cc: Arjan van de Ven Cc: Sebastian Siewior Cc: Rusty Russell Cc: Steven Rostedt Cc: Oleg Nesterov Cc: Tejun Heo Cc: Andrew Morton Cc: Paul McKenney Cc: Linus Torvalds Cc: Paul Turner Link: http://lkml.kernel.org/r/20160226182341.614102639@linutronix.de Signed-off-by: Thomas Gleixner diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c index 2f24447f..46bf263 100644 --- a/arch/alpha/kernel/smp.c +++ b/arch/alpha/kernel/smp.c @@ -168,7 +168,7 @@ smp_callin(void) cpuid, current, current->active_mm)); preempt_disable(); - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } /* Wait until hwrpb->txrdy is clear for cpu. Return -1 on timeout. */ diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c index 424e937..4cb3add 100644 --- a/arch/arc/kernel/smp.c +++ b/arch/arc/kernel/smp.c @@ -142,7 +142,7 @@ void start_kernel_secondary(void) local_irq_enable(); preempt_disable(); - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } /* diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 37312f6..baee702 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -409,7 +409,7 @@ asmlinkage void secondary_start_kernel(void) /* * OK, it's off to the idle thread for us */ - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } void __init smp_cpus_done(unsigned int max_cpus) diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index b1adc51..4607657 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -195,7 +195,7 @@ asmlinkage void secondary_start_kernel(void) /* * OK, it's off to the idle thread for us */ - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } #ifdef CONFIG_HOTPLUG_CPU diff --git a/arch/blackfin/mach-common/smp.c b/arch/blackfin/mach-common/smp.c index 0030e21..23c4ef5 100644 --- a/arch/blackfin/mach-common/smp.c +++ b/arch/blackfin/mach-common/smp.c @@ -333,7 +333,7 @@ void secondary_start_kernel(void) /* We are done with local CPU inits, unblock the boot CPU. */ set_cpu_online(cpu, true); - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } void __init smp_prepare_boot_cpu(void) diff --git a/arch/hexagon/kernel/smp.c b/arch/hexagon/kernel/smp.c index ff759f2..983bae7 100644 --- a/arch/hexagon/kernel/smp.c +++ b/arch/hexagon/kernel/smp.c @@ -180,7 +180,7 @@ void start_secondary(void) local_irq_enable(); - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c index 0e76fad..74fe317 100644 --- a/arch/ia64/kernel/smpboot.c +++ b/arch/ia64/kernel/smpboot.c @@ -454,7 +454,7 @@ start_secondary (void *unused) preempt_disable(); smp_callin(); - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); return 0; } diff --git a/arch/m32r/kernel/smpboot.c b/arch/m32r/kernel/smpboot.c index a468467..f98d2f6 100644 --- a/arch/m32r/kernel/smpboot.c +++ b/arch/m32r/kernel/smpboot.c @@ -432,7 +432,7 @@ int __init start_secondary(void *unused) */ local_flush_tlb_all(); - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); return 0; } diff --git a/arch/metag/kernel/smp.c b/arch/metag/kernel/smp.c index c3c6f08..bad1323 100644 --- a/arch/metag/kernel/smp.c +++ b/arch/metag/kernel/smp.c @@ -396,7 +396,7 @@ asmlinkage void secondary_start_kernel(void) /* * OK, it's off to the idle thread for us */ - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } void __init smp_cpus_done(unsigned int max_cpus) diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index bd4385a..f2112a8 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -191,7 +191,7 @@ asmlinkage void start_secondary(void) WARN_ON_ONCE(!irqs_disabled()); mp_ops->smp_finish(); - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } static void stop_this_cpu(void *dummy) diff --git a/arch/mn10300/kernel/smp.c b/arch/mn10300/kernel/smp.c index f984193..426173c 100644 --- a/arch/mn10300/kernel/smp.c +++ b/arch/mn10300/kernel/smp.c @@ -675,7 +675,7 @@ int __init start_secondary(void *unused) #ifdef CONFIG_GENERIC_CLOCKEVENTS init_clockevents(); #endif - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); return 0; } diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c index 52e8597..c2a9cc5 100644 --- a/arch/parisc/kernel/smp.c +++ b/arch/parisc/kernel/smp.c @@ -305,7 +305,7 @@ void __init smp_callin(void) local_irq_enable(); /* Interrupts have been off until now */ - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); /* NOTREACHED */ panic("smp_callin() AAAAaaaaahhhh....\n"); diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index ec9ec20..cc13d4c 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -727,7 +727,7 @@ void start_secondary(void *unused) local_irq_enable(); - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); BUG(); } diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 3c65a8e..40a6b4f 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -798,7 +798,7 @@ static void smp_start_secondary(void *cpuvoid) set_cpu_online(smp_processor_id(), true); inc_irq_stat(CPU_RST); local_irq_enable(); - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } /* Upping and downing of CPUs */ diff --git a/arch/sh/kernel/smp.c b/arch/sh/kernel/smp.c index de6be00..13f633a 100644 --- a/arch/sh/kernel/smp.c +++ b/arch/sh/kernel/smp.c @@ -203,7 +203,7 @@ asmlinkage void start_secondary(void) set_cpu_online(cpu, true); per_cpu(cpu_state, cpu) = CPU_ONLINE; - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } extern struct { diff --git a/arch/sparc/kernel/smp_32.c b/arch/sparc/kernel/smp_32.c index b3a5d81..fb30e7c 100644 --- a/arch/sparc/kernel/smp_32.c +++ b/arch/sparc/kernel/smp_32.c @@ -364,7 +364,7 @@ static void sparc_start_secondary(void *arg) local_irq_enable(); wmb(); - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); /* We should never reach here! */ BUG(); diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 19cd08d..8a6151a 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -134,7 +134,7 @@ void smp_callin(void) local_irq_enable(); - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } void cpu_panic(void) diff --git a/arch/tile/kernel/smpboot.c b/arch/tile/kernel/smpboot.c index 20d52a9..6c0abaa 100644 --- a/arch/tile/kernel/smpboot.c +++ b/arch/tile/kernel/smpboot.c @@ -208,7 +208,7 @@ void online_secondary(void) /* Set up tile-timer clock-event device on this cpu */ setup_tile_timer(); - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } int __cpu_up(unsigned int cpu, struct task_struct *tidle) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 24d57f7..293b22a 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -248,7 +248,7 @@ static void notrace start_secondary(void *unused) x86_cpuinit.setup_percpu_clockev(); wmb(); - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } void __init smp_store_boot_cpu_info(void) diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 3f4ebf0..3c6d17f 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -112,7 +112,7 @@ asmlinkage __visible void cpu_bringup_and_idle(int cpu) xen_pvh_secondary_vcpu_init(cpu); #endif cpu_bringup(); - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } static void xen_smp_intr_free(unsigned int cpu) diff --git a/arch/xtensa/kernel/smp.c b/arch/xtensa/kernel/smp.c index 4d02e38..fc4ad21 100644 --- a/arch/xtensa/kernel/smp.c +++ b/arch/xtensa/kernel/smp.c @@ -157,7 +157,7 @@ void secondary_start_kernel(void) complete(&cpu_running); - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } static void mx_cpu_start(void *p) diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 8a715bb..4aa263a 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -13,6 +13,7 @@ enum cpuhp_state { CPUHP_CPU_SET_ACTIVE, CPUHP_KICK_AP_THREAD, CPUHP_BP_ONLINE, + CPUHP_AP_ONLINE_IDLE, CPUHP_AP_SMPBOOT_THREADS, CPUHP_AP_NOTIFY_ONLINE, CPUHP_AP_ONLINE_DYN, -- cgit v0.10.2 From 8df3e07e7f21f2ed8d001e6fabf9505946b438aa Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 26 Feb 2016 18:43:41 +0000 Subject: cpu/hotplug: Let upcoming cpu bring itself fully up Let the upcoming cpu kick the hotplug thread and let itself complete the bringup. That way the controll side can just wait for the completion or later when we made the hotplug machinery async not care at all. Signed-off-by: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: Rik van Riel Cc: Rafael Wysocki Cc: "Srivatsa S. Bhat" Cc: Peter Zijlstra Cc: Arjan van de Ven Cc: Sebastian Siewior Cc: Rusty Russell Cc: Steven Rostedt Cc: Oleg Nesterov Cc: Tejun Heo Cc: Andrew Morton Cc: Paul McKenney Cc: Linus Torvalds Cc: Paul Turner Link: http://lkml.kernel.org/r/20160226182341.697655464@linutronix.de Signed-off-by: Thomas Gleixner diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 4aa263a..ad5d7fc 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -10,9 +10,6 @@ enum cpuhp_state { CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, CPUHP_TEARDOWN_CPU, - CPUHP_CPU_SET_ACTIVE, - CPUHP_KICK_AP_THREAD, - CPUHP_BP_ONLINE, CPUHP_AP_ONLINE_IDLE, CPUHP_AP_SMPBOOT_THREADS, CPUHP_AP_NOTIFY_ONLINE, @@ -86,4 +83,10 @@ static inline void cpuhp_remove_state_nocalls(enum cpuhp_state state) __cpuhp_remove_state(state, false); } +#ifdef CONFIG_SMP +void cpuhp_online_idle(enum cpuhp_state state); +#else +static inline void cpuhp_online_idle(enum cpuhp_state state) { } +#endif + #endif diff --git a/kernel/cpu.c b/kernel/cpu.c index e220e56..f1f880f 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -329,6 +329,14 @@ static int notify_starting(unsigned int cpu) return 0; } +static int bringup_wait_for_ap(unsigned int cpu) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + + wait_for_completion(&st->done); + return st->result; +} + static int bringup_cpu(unsigned int cpu) { struct task_struct *idle = idle_thread_get(cpu); @@ -340,8 +348,9 @@ static int bringup_cpu(unsigned int cpu) cpu_notify(CPU_UP_CANCELED, cpu); return ret; } + ret = bringup_wait_for_ap(cpu); BUG_ON(!cpu_online(cpu)); - return 0; + return ret; } /* @@ -470,7 +479,7 @@ static void cpuhp_thread_fun(unsigned int cpu) } } else { /* Cannot happen .... */ - BUG_ON(st->state < CPUHP_KICK_AP_THREAD); + BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE); /* Regular hotplug work */ if (st->state < st->target) @@ -780,7 +789,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread. */ - if (st->state >= CPUHP_KICK_AP_THREAD) { + if (st->state > CPUHP_TEARDOWN_CPU) { ret = cpuhp_kick_ap_work(cpu); /* * The AP side has done the error rollback already. Just @@ -793,11 +802,11 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, * We might have stopped still in the range of the AP hotplug * thread. Nothing to do anymore. */ - if (st->state >= CPUHP_KICK_AP_THREAD) + if (st->state > CPUHP_TEARDOWN_CPU) goto out; } /* - * The AP brought itself down below CPUHP_KICK_AP_THREAD. So we need + * The AP brought itself down to CPUHP_TEARDOWN_CPU. So we need * to do the further cleanups. */ ret = cpuhp_down_callbacks(cpu, st, cpuhp_bp_states, target); @@ -859,18 +868,32 @@ void notify_cpu_starting(unsigned int cpu) /* * Called from the idle task. We need to set active here, so we can kick off - * the stopper thread. + * the stopper thread and unpark the smpboot threads. If the target state is + * beyond CPUHP_AP_ONLINE_IDLE we kick cpuhp thread and let it bring up the + * cpu further. */ -static int cpuhp_set_cpu_active(unsigned int cpu) +void cpuhp_online_idle(enum cpuhp_state state) { - struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); + unsigned int cpu = smp_processor_id(); + + /* Happens for the boot cpu */ + if (state != CPUHP_AP_ONLINE_IDLE) + return; + + st->state = CPUHP_AP_ONLINE_IDLE; /* The cpu is marked online, set it active now */ set_cpu_active(cpu, true); - /* Unpark the stopper thread and the hotplug thread */ + /* Unpark the stopper thread and the hotplug thread of this cpu */ stop_machine_unpark(cpu); kthread_unpark(st->thread); - return 0; + + /* Should we go further up ? */ + if (st->target > CPUHP_AP_ONLINE_IDLE) + __cpuhp_kick_ap_work(st); + else + complete(&st->done); } /* Requires cpu_add_remove_lock to be held */ @@ -910,7 +933,7 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread once more. */ - if (st->state >= CPUHP_KICK_AP_THREAD) { + if (st->state > CPUHP_BRINGUP_CPU) { ret = cpuhp_kick_ap_work(cpu); /* * The AP side has done the error rollback already. Just @@ -922,10 +945,10 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) /* * Try to reach the target state. We max out on the BP at - * CPUHP_KICK_AP_THREAD. After that the AP hotplug thread is + * CPUHP_BRINGUP_CPU. After that the AP hotplug thread is * responsible for bringing it up to the target state. */ - target = min((int)target, CPUHP_KICK_AP_THREAD); + target = min((int)target, CPUHP_BRINGUP_CPU); ret = cpuhp_up_callbacks(cpu, st, cpuhp_bp_states, target); out: cpu_hotplug_done(); @@ -1146,22 +1169,7 @@ static struct cpuhp_step cpuhp_bp_states[] = { .teardown = takedown_cpu, .cant_stop = true, }, - [CPUHP_CPU_SET_ACTIVE] = { - .name = "cpu:active", - .startup = cpuhp_set_cpu_active, - .teardown = NULL, - }, - [CPUHP_KICK_AP_THREAD] = { - .name = "cpuhp:kickthread", - .startup = cpuhp_kick_ap_work, - .teardown = cpuhp_kick_ap_work, - }, #endif - [CPUHP_BP_ONLINE] = { - .name = "online", - .startup = NULL, - .teardown = NULL, - }, }; /* Application processor state steps */ @@ -1204,7 +1212,7 @@ static bool cpuhp_is_ap_state(enum cpuhp_state state) { if (state >= CPUHP_AP_OFFLINE && state <= CPUHP_AP_ONLINE) return true; - return state > CPUHP_BP_ONLINE; + return state > CPUHP_BRINGUP_CPU; } static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state) diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 544a713..a4b9813 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -4,6 +4,7 @@ #include #include #include +#include #include #include #include @@ -291,5 +292,6 @@ void cpu_startup_entry(enum cpuhp_state state) boot_init_stack_canary(); #endif arch_cpu_idle_prepare(); + cpuhp_online_idle(state); cpu_idle_loop(); } -- cgit v0.10.2 From e69aab13117efc1987620090e539b4ebeb33a04c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 26 Feb 2016 18:43:43 +0000 Subject: cpu/hotplug: Make wait for dead cpu completion based Kill the busy spinning on the control side and just wait for the hotplugged cpu to tell that it reached the dead state. Signed-off-by: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: Rik van Riel Cc: Rafael Wysocki Cc: "Srivatsa S. Bhat" Cc: Peter Zijlstra Cc: Arjan van de Ven Cc: Sebastian Siewior Cc: Rusty Russell Cc: Steven Rostedt Cc: Oleg Nesterov Cc: Tejun Heo Cc: Andrew Morton Cc: Paul McKenney Cc: Linus Torvalds Cc: Paul Turner Link: http://lkml.kernel.org/r/20160226182341.776157858@linutronix.de Signed-off-by: Thomas Gleixner diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 83f3576..91a48d1 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -276,14 +276,15 @@ void arch_cpu_idle_enter(void); void arch_cpu_idle_exit(void); void arch_cpu_idle_dead(void); -DECLARE_PER_CPU(bool, cpu_dead_idle); - int cpu_report_state(int cpu); int cpu_check_up_prepare(int cpu); void cpu_set_state_online(int cpu); #ifdef CONFIG_HOTPLUG_CPU bool cpu_wait_death(unsigned int cpu, int seconds); bool cpu_report_death(void); +void cpuhp_report_idle_dead(void); +#else +static inline void cpuhp_report_idle_dead(void) { } #endif /* #ifdef CONFIG_HOTPLUG_CPU */ #endif /* _LINUX_CPU_H_ */ diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index ad5d7fc..5d68e15 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -6,6 +6,7 @@ enum cpuhp_state { CPUHP_CREATE_THREADS, CPUHP_NOTIFY_PREPARE, CPUHP_BRINGUP_CPU, + CPUHP_AP_IDLE_DEAD, CPUHP_AP_OFFLINE, CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, diff --git a/kernel/cpu.c b/kernel/cpu.c index f1f880f..0e8c07f 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -688,6 +688,7 @@ static int take_cpu_down(void *_param) static int takedown_cpu(unsigned int cpu) { + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int err; /* @@ -733,10 +734,8 @@ static int takedown_cpu(unsigned int cpu) * * Wait for the stop thread to go away. */ - while (!per_cpu(cpu_dead_idle, cpu)) - cpu_relax(); - smp_mb(); /* Read from cpu_dead_idle before __cpu_die(). */ - per_cpu(cpu_dead_idle, cpu) = false; + wait_for_completion(&st->done); + BUG_ON(st->state != CPUHP_AP_IDLE_DEAD); /* Interrupts are moved away from the dying cpu, reenable alloc/free */ irq_unlock_sparse(); @@ -756,6 +755,15 @@ static int notify_dead(unsigned int cpu) return 0; } +void cpuhp_report_idle_dead(void) +{ + struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); + + BUG_ON(st->state != CPUHP_AP_OFFLINE); + st->state = CPUHP_AP_IDLE_DEAD; + complete(&st->done); +} + #else #define notify_down_prepare NULL #define takedown_cpu NULL diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index a4b9813..8abbe89 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -194,8 +194,6 @@ exit_idle: rcu_idle_exit(); } -DEFINE_PER_CPU(bool, cpu_dead_idle); - /* * Generic idle loop implementation * @@ -224,8 +222,7 @@ static void cpu_idle_loop(void) if (cpu_is_offline(smp_processor_id())) { rcu_cpu_notify(NULL, CPU_DYING_IDLE, (void *)(long)smp_processor_id()); - smp_mb(); /* all activity before dead. */ - this_cpu_write(cpu_dead_idle, true); + cpuhp_report_idle_dead(); arch_cpu_idle_dead(); } -- cgit v0.10.2 From 27d50c7eeb0f03c3d3ca72aac4d2dd487ca1f3f0 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 26 Feb 2016 18:43:44 +0000 Subject: rcu: Make CPU_DYING_IDLE an explicit call Make the RCU CPU_DYING_IDLE callback an explicit function call, so it gets invoked at the proper place. Signed-off-by: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: Rik van Riel Cc: Rafael Wysocki Cc: "Srivatsa S. Bhat" Cc: Peter Zijlstra Cc: Arjan van de Ven Cc: Sebastian Siewior Cc: Rusty Russell Cc: Steven Rostedt Cc: Oleg Nesterov Cc: Tejun Heo Cc: Andrew Morton Cc: Paul McKenney Cc: Linus Torvalds Cc: Paul Turner Link: http://lkml.kernel.org/r/20160226182341.870167933@linutronix.de Signed-off-by: Thomas Gleixner diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 91a48d1..f9b1fab 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -101,9 +101,7 @@ enum { * Called on the new cpu, just before * enabling interrupts. Must not sleep, * must not fail */ -#define CPU_DYING_IDLE 0x000B /* CPU (unsigned)v dying, reached - * idle loop. */ -#define CPU_BROKEN 0x000C /* CPU (unsigned)v did not die properly, +#define CPU_BROKEN 0x000B /* CPU (unsigned)v did not die properly, * perhaps due to preemption. */ /* Used for CPU hotplug events occurring while tasks are frozen due to a suspend diff --git a/include/linux/notifier.h b/include/linux/notifier.h index d14a4c3..4149868 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -47,6 +47,8 @@ * runtime initialization. */ +struct notifier_block; + typedef int (*notifier_fn_t)(struct notifier_block *nb, unsigned long action, void *data); diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 14e6f47..fc46fe3 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -332,9 +332,7 @@ void rcu_init(void); void rcu_sched_qs(void); void rcu_bh_qs(void); void rcu_check_callbacks(int user); -struct notifier_block; -int rcu_cpu_notify(struct notifier_block *self, - unsigned long action, void *hcpu); +void rcu_report_dead(unsigned int cpu); #ifndef CONFIG_TINY_RCU void rcu_end_inkernel_boot(void); diff --git a/kernel/cpu.c b/kernel/cpu.c index 0e8c07f..ff8059b 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -762,6 +762,7 @@ void cpuhp_report_idle_dead(void) BUG_ON(st->state != CPUHP_AP_OFFLINE); st->state = CPUHP_AP_IDLE_DEAD; complete(&st->done); + rcu_report_dead(smp_processor_id()); } #else diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index e41dd41..85b4134 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -2607,28 +2607,6 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf) } /* - * The CPU is exiting the idle loop into the arch_cpu_idle_dead() - * function. We now remove it from the rcu_node tree's ->qsmaskinit - * bit masks. - */ -static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp) -{ - unsigned long flags; - unsigned long mask; - struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); - struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */ - - if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) - return; - - /* Remove outgoing CPU from mask in the leaf rcu_node structure. */ - mask = rdp->grpmask; - raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */ - rnp->qsmaskinitnext &= ~mask; - raw_spin_unlock_irqrestore(&rnp->lock, flags); -} - -/* * The CPU has been completely removed, and some other CPU is reporting * this fact from process context. Do the remainder of the cleanup, * including orphaning the outgoing CPU's RCU callbacks, and also @@ -4247,6 +4225,43 @@ static void rcu_prepare_cpu(int cpu) rcu_init_percpu_data(cpu, rsp); } +#ifdef CONFIG_HOTPLUG_CPU +/* + * The CPU is exiting the idle loop into the arch_cpu_idle_dead() + * function. We now remove it from the rcu_node tree's ->qsmaskinit + * bit masks. + */ +static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp) +{ + unsigned long flags; + unsigned long mask; + struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); + struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */ + + if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) + return; + + /* Remove outgoing CPU from mask in the leaf rcu_node structure. */ + mask = rdp->grpmask; + raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */ + rnp->qsmaskinitnext &= ~mask; + raw_spin_unlock_irqrestore(&rnp->lock, flags); +} + +void rcu_report_dead(unsigned int cpu) +{ + struct rcu_state *rsp; + + /* QS for any half-done expedited RCU-sched GP. */ + preempt_disable(); + rcu_report_exp_rdp(&rcu_sched_state, + this_cpu_ptr(rcu_sched_state.rda), true); + preempt_enable(); + for_each_rcu_flavor(rsp) + rcu_cleanup_dying_idle_cpu(cpu, rsp); +} +#endif + /* * Handle CPU online/offline notification events. */ @@ -4278,17 +4293,6 @@ int rcu_cpu_notify(struct notifier_block *self, for_each_rcu_flavor(rsp) rcu_cleanup_dying_cpu(rsp); break; - case CPU_DYING_IDLE: - /* QS for any half-done expedited RCU-sched GP. */ - preempt_disable(); - rcu_report_exp_rdp(&rcu_sched_state, - this_cpu_ptr(rcu_sched_state.rda), true); - preempt_enable(); - - for_each_rcu_flavor(rsp) { - rcu_cleanup_dying_idle_cpu(cpu, rsp); - } - break; case CPU_DEAD: case CPU_DEAD_FROZEN: case CPU_UP_CANCELED: diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 8abbe89..bd12c6c 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -220,8 +220,6 @@ static void cpu_idle_loop(void) rmb(); if (cpu_is_offline(smp_processor_id())) { - rcu_cpu_notify(NULL, CPU_DYING_IDLE, - (void *)(long)smp_processor_id()); cpuhp_report_idle_dead(); arch_cpu_idle_dead(); } -- cgit v0.10.2 From 71f87b2fc64c2e9b6d53cb817f28711b959d3dfe Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 3 Mar 2016 10:52:10 +0100 Subject: cpu/hotplug: Plug death reporting race Paul noticed that the conversion of the death reporting introduced a race where the outgoing cpu might be delayed after waking the controll processor, so it might not be able to call rcu_report_dead() before being physically removed, leading to RCU stalls. We cant call complete after rcu_report_dead(), so instead of going back to busy polling, simply issue a function call to do the completion. Fixes: 27d50c7eeb0f "rcu: Make CPU_DYING_IDLE an explicit call" Reported-by: Paul E. McKenney Link: http://lkml.kernel.org/r/20160302201127.GA23440@linux.vnet.ibm.com Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra diff --git a/kernel/cpu.c b/kernel/cpu.c index ff8059b..93e9d89 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -755,14 +755,26 @@ static int notify_dead(unsigned int cpu) return 0; } +static void cpuhp_complete_idle_dead(void *arg) +{ + struct cpuhp_cpu_state *st = arg; + + complete(&st->done); +} + void cpuhp_report_idle_dead(void) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); BUG_ON(st->state != CPUHP_AP_OFFLINE); - st->state = CPUHP_AP_IDLE_DEAD; - complete(&st->done); rcu_report_dead(smp_processor_id()); + st->state = CPUHP_AP_IDLE_DEAD; + /* + * We cannot call complete after rcu_report_dead() so we delegate it + * to an online cpu. + */ + smp_call_function_single(cpumask_first(cpu_online_mask), + cpuhp_complete_idle_dead, st, 0); } #else -- cgit v0.10.2 From 5d8eb84253333f8f63ec704276e3f0a8ec8f3189 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 3 Mar 2016 12:24:10 +0100 Subject: cpu/hotplug: Remove redundant state check The check for the AP range in cpuhp_is_ap_state() is redundant after commit 8df3e07e7f21 "cpu/hotplug: Let upcoming cpu bring itself fully up" because all states above CPUHP_BRINGUP_CPU are invoked on the hotplugged cpu. Remove it. Reported-by: Richard Cochran Signed-off-by: Thomas Gleixner diff --git a/kernel/cpu.c b/kernel/cpu.c index 93e9d89..373e831 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -1231,8 +1231,6 @@ static int cpuhp_cb_check(enum cpuhp_state state) static bool cpuhp_is_ap_state(enum cpuhp_state state) { - if (state >= CPUHP_AP_OFFLINE && state <= CPUHP_AP_ONLINE) - return true; return state > CPUHP_BRINGUP_CPU; } -- cgit v0.10.2 From 2a58c527bb566b7abad96289fa5b973040c33c82 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 10 Mar 2016 20:42:08 +0100 Subject: cpu/hotplug: Fix smpboot thread ordering Commit 931ef163309e moved the smpboot thread park/unpark invocation to the state machine. The move of the unpark invocation was premature as it depends on work in progress patches. As a result cpu down can fail, because rcu synchronization in takedown_cpu() eventually requires a functional softirq thread. I never encountered the problem in testing, but 0day testing managed to provide a reliable reproducer. Remove the smpboot_threads_park() call from the state machine for now and put it back into the original place after the rcu synchronization. I'm embarrassed as I knew about the dependency and still managed to get it wrong. Hotplug induced brain melt seems to be the only sensible explanation for that. Fixes: 931ef163309e "cpu/hotplug: Unpark smpboot threads from the state machine" Reported-by: Fengguang Wu Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra diff --git a/kernel/cpu.c b/kernel/cpu.c index 373e831..bcee286 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -706,8 +706,9 @@ static int takedown_cpu(unsigned int cpu) else synchronize_rcu(); - /* Park the hotplug thread */ + /* Park the smpboot threads */ kthread_park(per_cpu_ptr(&cpuhp_state, cpu)->thread); + smpboot_park_threads(cpu); /* * Prevent irq alloc/free while the dying cpu reorganizes the @@ -1206,7 +1207,7 @@ static struct cpuhp_step cpuhp_ap_states[] = { [CPUHP_AP_SMPBOOT_THREADS] = { .name = "smpboot:threads", .startup = smpboot_unpark_threads, - .teardown = smpboot_park_threads, + .teardown = NULL, }, [CPUHP_AP_NOTIFY_ONLINE] = { .name = "notify:online", -- cgit v0.10.2 From d10ef6f9380b8853c4b48eb104268fccfdc0b0c5 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 8 Mar 2016 10:36:13 +0100 Subject: cpu/hotplug: Document states better Requested-by: Peter Zijlstra Signed-off-by: Thomas Gleixner diff --git a/kernel/cpu.c b/kernel/cpu.c index bcee286..6ea42e8 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -1172,6 +1172,10 @@ static struct cpuhp_step cpuhp_bp_states[] = { .teardown = NULL, .cant_stop = true, }, + /* + * Preparatory and dead notifiers. Will be replaced once the notifiers + * are converted to states. + */ [CPUHP_NOTIFY_PREPARE] = { .name = "notify:prepare", .startup = notify_prepare, @@ -1179,12 +1183,17 @@ static struct cpuhp_step cpuhp_bp_states[] = { .skip_onerr = true, .cant_stop = true, }, + /* Kicks the plugged cpu into life */ [CPUHP_BRINGUP_CPU] = { .name = "cpu:bringup", .startup = bringup_cpu, .teardown = NULL, .cant_stop = true, }, + /* + * Handled on controll processor until the plugged processor manages + * this itself. + */ [CPUHP_TEARDOWN_CPU] = { .name = "cpu:teardown", .startup = NULL, @@ -1197,6 +1206,23 @@ static struct cpuhp_step cpuhp_bp_states[] = { /* Application processor state steps */ static struct cpuhp_step cpuhp_ap_states[] = { #ifdef CONFIG_SMP + /* Final state before CPU kills itself */ + [CPUHP_AP_IDLE_DEAD] = { + .name = "idle:dead", + }, + /* + * Last state before CPU enters the idle loop to die. Transient state + * for synchronization. + */ + [CPUHP_AP_OFFLINE] = { + .name = "ap:offline", + .cant_stop = true, + }, + /* + * Low level startup/teardown notifiers. Run with interrupts + * disabled. Will be removed once the notifiers are converted to + * states. + */ [CPUHP_AP_NOTIFY_STARTING] = { .name = "notify:starting", .startup = notify_starting, @@ -1204,17 +1230,32 @@ static struct cpuhp_step cpuhp_ap_states[] = { .skip_onerr = true, .cant_stop = true, }, + /* Entry state on starting. Interrupts enabled from here on. Transient + * state for synchronsization */ + [CPUHP_AP_ONLINE] = { + .name = "ap:online", + }, + /* Handle smpboot threads park/unpark */ [CPUHP_AP_SMPBOOT_THREADS] = { .name = "smpboot:threads", .startup = smpboot_unpark_threads, .teardown = NULL, }, + /* + * Online/down_prepare notifiers. Will be removed once the notifiers + * are converted to states. + */ [CPUHP_AP_NOTIFY_ONLINE] = { .name = "notify:online", .startup = notify_online, .teardown = notify_down_prepare, }, #endif + /* + * The dynamically registered state space is here + */ + + /* CPU is fully up and running. */ [CPUHP_ONLINE] = { .name = "online", .startup = NULL, @@ -1232,7 +1273,11 @@ static int cpuhp_cb_check(enum cpuhp_state state) static bool cpuhp_is_ap_state(enum cpuhp_state state) { - return state > CPUHP_BRINGUP_CPU; + /* + * The extra check for CPUHP_TEARDOWN_CPU is only for documentation + * purposes as that state is handled explicitely in cpu_down. + */ + return state > CPUHP_BRINGUP_CPU && state != CPUHP_TEARDOWN_CPU; } static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state) -- cgit v0.10.2