linux/kernel/cpu.c
Thomas Gleixner 38498a67aa smp: Add generic smpboot facility
Start a new file, which will hold SMP and CPU hotplug related generic
infrastructure.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Mike Frysinger <vapier@gentoo.org>
Cc: Jesper Nilsson <jesper.nilsson@axis.com>
Cc: Richard Kuo <rkuo@codeaurora.org>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Hirokazu Takata <takata@linux-m32r.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: David Howells <dhowells@redhat.com>
Cc: James E.J. Bottomley <jejb@parisc-linux.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: David S. Miller <davem@davemloft.net>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Richard Weinberger <richard@nod.at>
Cc: x86@kernel.org
Link: http://lkml.kernel.org/r/20120420124557.035417523@linutronix.de
2012-04-26 12:06:09 +02:00

679 lines
16 KiB
C

/* CPU control.
* (C) 2001, 2002, 2003, 2004 Rusty Russell
*
* This code is licenced under the GPL.
*/
#include <linux/proc_fs.h>
#include <linux/smp.h>
#include <linux/init.h>
#include <linux/notifier.h>
#include <linux/sched.h>
#include <linux/unistd.h>
#include <linux/cpu.h>
#include <linux/export.h>
#include <linux/kthread.h>
#include <linux/stop_machine.h>
#include <linux/mutex.h>
#include <linux/gfp.h>
#include <linux/suspend.h>
#include "smpboot.h"
#ifdef CONFIG_SMP
/* Serializes the updates to cpu_online_mask, cpu_present_mask */
static DEFINE_MUTEX(cpu_add_remove_lock);
/*
* The following two API's must be used when attempting
* to serialize the updates to cpu_online_mask, cpu_present_mask.
*/
void cpu_maps_update_begin(void)
{
mutex_lock(&cpu_add_remove_lock);
}
void cpu_maps_update_done(void)
{
mutex_unlock(&cpu_add_remove_lock);
}
static RAW_NOTIFIER_HEAD(cpu_chain);
/* If set, cpu_up and cpu_down will return -EBUSY and do nothing.
* Should always be manipulated under cpu_add_remove_lock
*/
static int cpu_hotplug_disabled;
#ifdef CONFIG_HOTPLUG_CPU
static struct {
struct task_struct *active_writer;
struct mutex lock; /* Synchronizes accesses to refcount, */
/*
* Also blocks the new readers during
* an ongoing cpu hotplug operation.
*/
int refcount;
} cpu_hotplug = {
.active_writer = NULL,
.lock = __MUTEX_INITIALIZER(cpu_hotplug.lock),
.refcount = 0,
};
void get_online_cpus(void)
{
might_sleep();
if (cpu_hotplug.active_writer == current)
return;
mutex_lock(&cpu_hotplug.lock);
cpu_hotplug.refcount++;
mutex_unlock(&cpu_hotplug.lock);
}
EXPORT_SYMBOL_GPL(get_online_cpus);
void put_online_cpus(void)
{
if (cpu_hotplug.active_writer == current)
return;
mutex_lock(&cpu_hotplug.lock);
if (!--cpu_hotplug.refcount && unlikely(cpu_hotplug.active_writer))
wake_up_process(cpu_hotplug.active_writer);
mutex_unlock(&cpu_hotplug.lock);
}
EXPORT_SYMBOL_GPL(put_online_cpus);
/*
* This ensures that the hotplug operation can begin only when the
* refcount goes to zero.
*
* Note that during a cpu-hotplug operation, the new readers, if any,
* will be blocked by the cpu_hotplug.lock
*
* Since cpu_hotplug_begin() is always called after invoking
* cpu_maps_update_begin(), we can be sure that only one writer is active.
*
* Note that theoretically, there is a possibility of a livelock:
* - Refcount goes to zero, last reader wakes up the sleeping
* writer.
* - Last reader unlocks the cpu_hotplug.lock.
* - A new reader arrives at this moment, bumps up the refcount.
* - The writer acquires the cpu_hotplug.lock finds the refcount
* non zero and goes to sleep again.
*
* However, this is very difficult to achieve in practice since
* get_online_cpus() not an api which is called all that often.
*
*/
static void cpu_hotplug_begin(void)
{
cpu_hotplug.active_writer = current;
for (;;) {
mutex_lock(&cpu_hotplug.lock);
if (likely(!cpu_hotplug.refcount))
break;
__set_current_state(TASK_UNINTERRUPTIBLE);
mutex_unlock(&cpu_hotplug.lock);
schedule();
}
}
static void cpu_hotplug_done(void)
{
cpu_hotplug.active_writer = NULL;
mutex_unlock(&cpu_hotplug.lock);
}
#else /* #if CONFIG_HOTPLUG_CPU */
static void cpu_hotplug_begin(void) {}
static void cpu_hotplug_done(void) {}
#endif /* #else #if CONFIG_HOTPLUG_CPU */
/* Need to know about CPUs going up/down? */
int __ref register_cpu_notifier(struct notifier_block *nb)
{
int ret;
cpu_maps_update_begin();
ret = raw_notifier_chain_register(&cpu_chain, nb);
cpu_maps_update_done();
return ret;
}
static int __cpu_notify(unsigned long val, void *v, int nr_to_call,
int *nr_calls)
{
int ret;
ret = __raw_notifier_call_chain(&cpu_chain, val, v, nr_to_call,
nr_calls);
return notifier_to_errno(ret);
}
static int cpu_notify(unsigned long val, void *v)
{
return __cpu_notify(val, v, -1, NULL);
}
#ifdef CONFIG_HOTPLUG_CPU
static void cpu_notify_nofail(unsigned long val, void *v)
{
BUG_ON(cpu_notify(val, v));
}
EXPORT_SYMBOL(register_cpu_notifier);
void __ref unregister_cpu_notifier(struct notifier_block *nb)
{
cpu_maps_update_begin();
raw_notifier_chain_unregister(&cpu_chain, nb);
cpu_maps_update_done();
}
EXPORT_SYMBOL(unregister_cpu_notifier);
static inline void check_for_tasks(int cpu)
{
struct task_struct *p;
write_lock_irq(&tasklist_lock);
for_each_process(p) {
if (task_cpu(p) == cpu && p->state == TASK_RUNNING &&
(p->utime || p->stime))
printk(KERN_WARNING "Task %s (pid = %d) is on cpu %d "
"(state = %ld, flags = %x)\n",
p->comm, task_pid_nr(p), cpu,
p->state, p->flags);
}
write_unlock_irq(&tasklist_lock);
}
struct take_cpu_down_param {
unsigned long mod;
void *hcpu;
};
/* Take this CPU down. */
static int __ref take_cpu_down(void *_param)
{
struct take_cpu_down_param *param = _param;
int err;
/* 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);
return 0;
}
/* Requires cpu_add_remove_lock to be held */
static int __ref _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;
if (!cpu_online(cpu))
return -EINVAL;
cpu_hotplug_begin();
err = __cpu_notify(CPU_DOWN_PREPARE | mod, hcpu, -1, &nr_calls);
if (err) {
nr_calls--;
__cpu_notify(CPU_DOWN_FAILED | mod, hcpu, nr_calls, NULL);
printk("%s: attempt to take down CPU %u failed\n",
__func__, cpu);
goto out_release;
}
err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
if (err) {
/* CPU didn't die: tell everyone. Can't complain. */
cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu);
goto out_release;
}
BUG_ON(cpu_online(cpu));
/*
* The migration_call() CPU_DYING callback will have removed all
* runnable tasks from the cpu, there's only the idle task left now
* that the migration thread is done doing the stop_machine thing.
*
* Wait for the stop thread to go away.
*/
while (!idle_cpu(cpu))
cpu_relax();
/* This actually kills the CPU. */
__cpu_die(cpu);
/* CPU is completely dead: tell everyone. Too late to complain. */
cpu_notify_nofail(CPU_DEAD | mod, hcpu);
check_for_tasks(cpu);
out_release:
cpu_hotplug_done();
if (!err)
cpu_notify_nofail(CPU_POST_DEAD | mod, hcpu);
return err;
}
int __ref cpu_down(unsigned int cpu)
{
int err;
cpu_maps_update_begin();
if (cpu_hotplug_disabled) {
err = -EBUSY;
goto out;
}
err = _cpu_down(cpu, 0);
out:
cpu_maps_update_done();
return err;
}
EXPORT_SYMBOL(cpu_down);
#endif /*CONFIG_HOTPLUG_CPU*/
/* Requires cpu_add_remove_lock to be held */
static int __cpuinit _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;
if (cpu_online(cpu) || !cpu_present(cpu))
return -EINVAL;
cpu_hotplug_begin();
ret = smpboot_prepare(cpu);
if (ret)
goto out;
ret = __cpu_notify(CPU_UP_PREPARE | mod, hcpu, -1, &nr_calls);
if (ret) {
nr_calls--;
printk(KERN_WARNING "%s: attempt to bring up CPU %u failed\n",
__func__, cpu);
goto out_notify;
}
/* Arch-specific enabling code. */
ret = __cpu_up(cpu, NULL);
if (ret != 0)
goto out_notify;
BUG_ON(!cpu_online(cpu));
/* Now call notifier in preparation. */
cpu_notify(CPU_ONLINE | mod, hcpu);
out_notify:
if (ret != 0)
__cpu_notify(CPU_UP_CANCELED | mod, hcpu, nr_calls, NULL);
out:
cpu_hotplug_done();
return ret;
}
int __cpuinit cpu_up(unsigned int cpu)
{
int err = 0;
#ifdef CONFIG_MEMORY_HOTPLUG
int nid;
pg_data_t *pgdat;
#endif
if (!cpu_possible(cpu)) {
printk(KERN_ERR "can't online cpu %d because it is not "
"configured as may-hotadd at boot time\n", cpu);
#if defined(CONFIG_IA64)
printk(KERN_ERR "please check additional_cpus= boot "
"parameter\n");
#endif
return -EINVAL;
}
#ifdef CONFIG_MEMORY_HOTPLUG
nid = cpu_to_node(cpu);
if (!node_online(nid)) {
err = mem_online_node(nid);
if (err)
return err;
}
pgdat = NODE_DATA(nid);
if (!pgdat) {
printk(KERN_ERR
"Can't online cpu %d due to NULL pgdat\n", cpu);
return -ENOMEM;
}
if (pgdat->node_zonelists->_zonerefs->zone == NULL) {
mutex_lock(&zonelists_mutex);
build_all_zonelists(NULL);
mutex_unlock(&zonelists_mutex);
}
#endif
cpu_maps_update_begin();
if (cpu_hotplug_disabled) {
err = -EBUSY;
goto out;
}
err = _cpu_up(cpu, 0);
out:
cpu_maps_update_done();
return err;
}
EXPORT_SYMBOL_GPL(cpu_up);
#ifdef CONFIG_PM_SLEEP_SMP
static cpumask_var_t frozen_cpus;
void __weak arch_disable_nonboot_cpus_begin(void)
{
}
void __weak arch_disable_nonboot_cpus_end(void)
{
}
int disable_nonboot_cpus(void)
{
int cpu, first_cpu, error = 0;
cpu_maps_update_begin();
first_cpu = cpumask_first(cpu_online_mask);
/*
* We take down all of the non-boot CPUs in one shot to avoid races
* with the userspace trying to use the CPU hotplug at the same time
*/
cpumask_clear(frozen_cpus);
arch_disable_nonboot_cpus_begin();
printk("Disabling non-boot CPUs ...\n");
for_each_online_cpu(cpu) {
if (cpu == first_cpu)
continue;
error = _cpu_down(cpu, 1);
if (!error)
cpumask_set_cpu(cpu, frozen_cpus);
else {
printk(KERN_ERR "Error taking CPU%d down: %d\n",
cpu, error);
break;
}
}
arch_disable_nonboot_cpus_end();
if (!error) {
BUG_ON(num_online_cpus() > 1);
/* Make sure the CPUs won't be enabled by someone else */
cpu_hotplug_disabled = 1;
} else {
printk(KERN_ERR "Non-boot CPUs are not disabled\n");
}
cpu_maps_update_done();
return error;
}
void __weak arch_enable_nonboot_cpus_begin(void)
{
}
void __weak arch_enable_nonboot_cpus_end(void)
{
}
void __ref enable_nonboot_cpus(void)
{
int cpu, error;
/* Allow everyone to use the CPU hotplug again */
cpu_maps_update_begin();
cpu_hotplug_disabled = 0;
if (cpumask_empty(frozen_cpus))
goto out;
printk(KERN_INFO "Enabling non-boot CPUs ...\n");
arch_enable_nonboot_cpus_begin();
for_each_cpu(cpu, frozen_cpus) {
error = _cpu_up(cpu, 1);
if (!error) {
printk(KERN_INFO "CPU%d is up\n", cpu);
continue;
}
printk(KERN_WARNING "Error taking CPU%d up: %d\n", cpu, error);
}
arch_enable_nonboot_cpus_end();
cpumask_clear(frozen_cpus);
out:
cpu_maps_update_done();
}
static int __init alloc_frozen_cpus(void)
{
if (!alloc_cpumask_var(&frozen_cpus, GFP_KERNEL|__GFP_ZERO))
return -ENOMEM;
return 0;
}
core_initcall(alloc_frozen_cpus);
/*
* Prevent regular CPU hotplug from racing with the freezer, by disabling CPU
* hotplug when tasks are about to be frozen. Also, don't allow the freezer
* to continue until any currently running CPU hotplug operation gets
* completed.
* To modify the 'cpu_hotplug_disabled' flag, we need to acquire the
* 'cpu_add_remove_lock'. And this same lock is also taken by the regular
* CPU hotplug path and released only after it is complete. Thus, we
* (and hence the freezer) will block here until any currently running CPU
* hotplug operation gets completed.
*/
void cpu_hotplug_disable_before_freeze(void)
{
cpu_maps_update_begin();
cpu_hotplug_disabled = 1;
cpu_maps_update_done();
}
/*
* When tasks have been thawed, re-enable regular CPU hotplug (which had been
* disabled while beginning to freeze tasks).
*/
void cpu_hotplug_enable_after_thaw(void)
{
cpu_maps_update_begin();
cpu_hotplug_disabled = 0;
cpu_maps_update_done();
}
/*
* When callbacks for CPU hotplug notifications are being executed, we must
* ensure that the state of the system with respect to the tasks being frozen
* or not, as reported by the notification, remains unchanged *throughout the
* duration* of the execution of the callbacks.
* Hence we need to prevent the freezer from racing with regular CPU hotplug.
*
* This synchronization is implemented by mutually excluding regular CPU
* hotplug and Suspend/Hibernate call paths by hooking onto the Suspend/
* Hibernate notifications.
*/
static int
cpu_hotplug_pm_callback(struct notifier_block *nb,
unsigned long action, void *ptr)
{
switch (action) {
case PM_SUSPEND_PREPARE:
case PM_HIBERNATION_PREPARE:
cpu_hotplug_disable_before_freeze();
break;
case PM_POST_SUSPEND:
case PM_POST_HIBERNATION:
cpu_hotplug_enable_after_thaw();
break;
default:
return NOTIFY_DONE;
}
return NOTIFY_OK;
}
static int __init cpu_hotplug_pm_sync_init(void)
{
pm_notifier(cpu_hotplug_pm_callback, 0);
return 0;
}
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 __cpuinit 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);
}
#endif /* CONFIG_SMP */
/*
* cpu_bit_bitmap[] is a special, "compressed" data structure that
* represents all NR_CPUS bits binary values of 1<<nr.
*
* It is used by cpumask_of() to get a constant address to a CPU
* mask value that has a single bit set only.
*/
/* cpu_bit_bitmap[0] is empty - so we can back into it */
#define MASK_DECLARE_1(x) [x+1][0] = (1UL << (x))
#define MASK_DECLARE_2(x) MASK_DECLARE_1(x), MASK_DECLARE_1(x+1)
#define MASK_DECLARE_4(x) MASK_DECLARE_2(x), MASK_DECLARE_2(x+2)
#define MASK_DECLARE_8(x) MASK_DECLARE_4(x), MASK_DECLARE_4(x+4)
const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)] = {
MASK_DECLARE_8(0), MASK_DECLARE_8(8),
MASK_DECLARE_8(16), MASK_DECLARE_8(24),
#if BITS_PER_LONG > 32
MASK_DECLARE_8(32), MASK_DECLARE_8(40),
MASK_DECLARE_8(48), MASK_DECLARE_8(56),
#endif
};
EXPORT_SYMBOL_GPL(cpu_bit_bitmap);
const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL;
EXPORT_SYMBOL(cpu_all_bits);
#ifdef CONFIG_INIT_ALL_POSSIBLE
static DECLARE_BITMAP(cpu_possible_bits, CONFIG_NR_CPUS) __read_mostly
= CPU_BITS_ALL;
#else
static DECLARE_BITMAP(cpu_possible_bits, CONFIG_NR_CPUS) __read_mostly;
#endif
const struct cpumask *const cpu_possible_mask = to_cpumask(cpu_possible_bits);
EXPORT_SYMBOL(cpu_possible_mask);
static DECLARE_BITMAP(cpu_online_bits, CONFIG_NR_CPUS) __read_mostly;
const struct cpumask *const cpu_online_mask = to_cpumask(cpu_online_bits);
EXPORT_SYMBOL(cpu_online_mask);
static DECLARE_BITMAP(cpu_present_bits, CONFIG_NR_CPUS) __read_mostly;
const struct cpumask *const cpu_present_mask = to_cpumask(cpu_present_bits);
EXPORT_SYMBOL(cpu_present_mask);
static DECLARE_BITMAP(cpu_active_bits, CONFIG_NR_CPUS) __read_mostly;
const struct cpumask *const cpu_active_mask = to_cpumask(cpu_active_bits);
EXPORT_SYMBOL(cpu_active_mask);
void set_cpu_possible(unsigned int cpu, bool possible)
{
if (possible)
cpumask_set_cpu(cpu, to_cpumask(cpu_possible_bits));
else
cpumask_clear_cpu(cpu, to_cpumask(cpu_possible_bits));
}
void set_cpu_present(unsigned int cpu, bool present)
{
if (present)
cpumask_set_cpu(cpu, to_cpumask(cpu_present_bits));
else
cpumask_clear_cpu(cpu, to_cpumask(cpu_present_bits));
}
void set_cpu_online(unsigned int cpu, bool online)
{
if (online)
cpumask_set_cpu(cpu, to_cpumask(cpu_online_bits));
else
cpumask_clear_cpu(cpu, to_cpumask(cpu_online_bits));
}
void set_cpu_active(unsigned int cpu, bool active)
{
if (active)
cpumask_set_cpu(cpu, to_cpumask(cpu_active_bits));
else
cpumask_clear_cpu(cpu, to_cpumask(cpu_active_bits));
}
void init_cpu_present(const struct cpumask *src)
{
cpumask_copy(to_cpumask(cpu_present_bits), src);
}
void init_cpu_possible(const struct cpumask *src)
{
cpumask_copy(to_cpumask(cpu_possible_bits), src);
}
void init_cpu_online(const struct cpumask *src)
{
cpumask_copy(to_cpumask(cpu_online_bits), src);
}