linux/kernel/softirq.c
Steven Rostedt 2232c2d8e0 rcu: add support for dynamic ticks and preempt rcu
The PREEMPT-RCU can get stuck if a CPU goes idle and NO_HZ is set. The
idle CPU will not progress the RCU through its grace period and a
synchronize_rcu my get stuck. Without this patch I have a box that will
not boot when PREEMPT_RCU and NO_HZ are set. That same box boots fine
with this patch.

This patch comes from the -rt kernel where it has been tested for
several months.

Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-02-29 18:46:50 +01:00

667 lines
15 KiB
C

/*
* linux/kernel/softirq.c
*
* Copyright (C) 1992 Linus Torvalds
*
* Distribute under GPLv2.
*
* Rewritten. Old one was good in 2.2, but in 2.3 it was immoral. --ANK (990903)
*/
#include <linux/module.h>
#include <linux/kernel_stat.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/notifier.h>
#include <linux/percpu.h>
#include <linux/cpu.h>
#include <linux/freezer.h>
#include <linux/kthread.h>
#include <linux/rcupdate.h>
#include <linux/smp.h>
#include <linux/tick.h>
#include <asm/irq.h>
/*
- No shared variables, all the data are CPU local.
- If a softirq needs serialization, let it serialize itself
by its own spinlocks.
- Even if softirq is serialized, only local cpu is marked for
execution. Hence, we get something sort of weak cpu binding.
Though it is still not clear, will it result in better locality
or will not.
Examples:
- NET RX softirq. It is multithreaded and does not require
any global serialization.
- NET TX softirq. It kicks software netdevice queues, hence
it is logically serialized per device, but this serialization
is invisible to common code.
- Tasklets: serialized wrt itself.
*/
#ifndef __ARCH_IRQ_STAT
irq_cpustat_t irq_stat[NR_CPUS] ____cacheline_aligned;
EXPORT_SYMBOL(irq_stat);
#endif
static struct softirq_action softirq_vec[32] __cacheline_aligned_in_smp;
static DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
/*
* we cannot loop indefinitely here to avoid userspace starvation,
* but we also don't want to introduce a worst case 1/HZ latency
* to the pending events, so lets the scheduler to balance
* the softirq load for us.
*/
static inline void wakeup_softirqd(void)
{
/* Interrupts are disabled: no need to stop preemption */
struct task_struct *tsk = __get_cpu_var(ksoftirqd);
if (tsk && tsk->state != TASK_RUNNING)
wake_up_process(tsk);
}
/*
* This one is for softirq.c-internal use,
* where hardirqs are disabled legitimately:
*/
#ifdef CONFIG_TRACE_IRQFLAGS
static void __local_bh_disable(unsigned long ip)
{
unsigned long flags;
WARN_ON_ONCE(in_irq());
raw_local_irq_save(flags);
add_preempt_count(SOFTIRQ_OFFSET);
/*
* Were softirqs turned off above:
*/
if (softirq_count() == SOFTIRQ_OFFSET)
trace_softirqs_off(ip);
raw_local_irq_restore(flags);
}
#else /* !CONFIG_TRACE_IRQFLAGS */
static inline void __local_bh_disable(unsigned long ip)
{
add_preempt_count(SOFTIRQ_OFFSET);
barrier();
}
#endif /* CONFIG_TRACE_IRQFLAGS */
void local_bh_disable(void)
{
__local_bh_disable((unsigned long)__builtin_return_address(0));
}
EXPORT_SYMBOL(local_bh_disable);
void __local_bh_enable(void)
{
WARN_ON_ONCE(in_irq());
/*
* softirqs should never be enabled by __local_bh_enable(),
* it always nests inside local_bh_enable() sections:
*/
WARN_ON_ONCE(softirq_count() == SOFTIRQ_OFFSET);
sub_preempt_count(SOFTIRQ_OFFSET);
}
EXPORT_SYMBOL_GPL(__local_bh_enable);
/*
* Special-case - softirqs can safely be enabled in
* cond_resched_softirq(), or by __do_softirq(),
* without processing still-pending softirqs:
*/
void _local_bh_enable(void)
{
WARN_ON_ONCE(in_irq());
WARN_ON_ONCE(!irqs_disabled());
if (softirq_count() == SOFTIRQ_OFFSET)
trace_softirqs_on((unsigned long)__builtin_return_address(0));
sub_preempt_count(SOFTIRQ_OFFSET);
}
EXPORT_SYMBOL(_local_bh_enable);
void local_bh_enable(void)
{
#ifdef CONFIG_TRACE_IRQFLAGS
unsigned long flags;
WARN_ON_ONCE(in_irq());
#endif
WARN_ON_ONCE(irqs_disabled());
#ifdef CONFIG_TRACE_IRQFLAGS
local_irq_save(flags);
#endif
/*
* Are softirqs going to be turned on now:
*/
if (softirq_count() == SOFTIRQ_OFFSET)
trace_softirqs_on((unsigned long)__builtin_return_address(0));
/*
* Keep preemption disabled until we are done with
* softirq processing:
*/
sub_preempt_count(SOFTIRQ_OFFSET - 1);
if (unlikely(!in_interrupt() && local_softirq_pending()))
do_softirq();
dec_preempt_count();
#ifdef CONFIG_TRACE_IRQFLAGS
local_irq_restore(flags);
#endif
preempt_check_resched();
}
EXPORT_SYMBOL(local_bh_enable);
void local_bh_enable_ip(unsigned long ip)
{
#ifdef CONFIG_TRACE_IRQFLAGS
unsigned long flags;
WARN_ON_ONCE(in_irq());
local_irq_save(flags);
#endif
/*
* Are softirqs going to be turned on now:
*/
if (softirq_count() == SOFTIRQ_OFFSET)
trace_softirqs_on(ip);
/*
* Keep preemption disabled until we are done with
* softirq processing:
*/
sub_preempt_count(SOFTIRQ_OFFSET - 1);
if (unlikely(!in_interrupt() && local_softirq_pending()))
do_softirq();
dec_preempt_count();
#ifdef CONFIG_TRACE_IRQFLAGS
local_irq_restore(flags);
#endif
preempt_check_resched();
}
EXPORT_SYMBOL(local_bh_enable_ip);
/*
* We restart softirq processing MAX_SOFTIRQ_RESTART times,
* and we fall back to softirqd after that.
*
* This number has been established via experimentation.
* The two things to balance is latency against fairness -
* we want to handle softirqs as soon as possible, but they
* should not be able to lock up the box.
*/
#define MAX_SOFTIRQ_RESTART 10
asmlinkage void __do_softirq(void)
{
struct softirq_action *h;
__u32 pending;
int max_restart = MAX_SOFTIRQ_RESTART;
int cpu;
pending = local_softirq_pending();
account_system_vtime(current);
__local_bh_disable((unsigned long)__builtin_return_address(0));
trace_softirq_enter();
cpu = smp_processor_id();
restart:
/* Reset the pending bitmask before enabling irqs */
set_softirq_pending(0);
local_irq_enable();
h = softirq_vec;
do {
if (pending & 1) {
h->action(h);
rcu_bh_qsctr_inc(cpu);
}
h++;
pending >>= 1;
} while (pending);
local_irq_disable();
pending = local_softirq_pending();
if (pending && --max_restart)
goto restart;
if (pending)
wakeup_softirqd();
trace_softirq_exit();
account_system_vtime(current);
_local_bh_enable();
}
#ifndef __ARCH_HAS_DO_SOFTIRQ
asmlinkage void do_softirq(void)
{
__u32 pending;
unsigned long flags;
if (in_interrupt())
return;
local_irq_save(flags);
pending = local_softirq_pending();
if (pending)
__do_softirq();
local_irq_restore(flags);
}
#endif
/*
* Enter an interrupt context.
*/
void irq_enter(void)
{
#ifdef CONFIG_NO_HZ
int cpu = smp_processor_id();
if (idle_cpu(cpu) && !in_interrupt())
tick_nohz_stop_idle(cpu);
#endif
__irq_enter();
#ifdef CONFIG_NO_HZ
if (idle_cpu(cpu))
tick_nohz_update_jiffies();
#endif
}
#ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED
# define invoke_softirq() __do_softirq()
#else
# define invoke_softirq() do_softirq()
#endif
/*
* Exit an interrupt context. Process softirqs if needed and possible:
*/
void irq_exit(void)
{
account_system_vtime(current);
trace_hardirq_exit();
sub_preempt_count(IRQ_EXIT_OFFSET);
if (!in_interrupt() && local_softirq_pending())
invoke_softirq();
#ifdef CONFIG_NO_HZ
/* Make sure that timer wheel updates are propagated */
if (!in_interrupt() && idle_cpu(smp_processor_id()) && !need_resched())
tick_nohz_stop_sched_tick();
rcu_irq_exit();
#endif
preempt_enable_no_resched();
}
/*
* This function must run with irqs disabled!
*/
inline void raise_softirq_irqoff(unsigned int nr)
{
__raise_softirq_irqoff(nr);
/*
* If we're in an interrupt or softirq, we're done
* (this also catches softirq-disabled code). We will
* actually run the softirq once we return from
* the irq or softirq.
*
* Otherwise we wake up ksoftirqd to make sure we
* schedule the softirq soon.
*/
if (!in_interrupt())
wakeup_softirqd();
}
void raise_softirq(unsigned int nr)
{
unsigned long flags;
local_irq_save(flags);
raise_softirq_irqoff(nr);
local_irq_restore(flags);
}
void open_softirq(int nr, void (*action)(struct softirq_action*), void *data)
{
softirq_vec[nr].data = data;
softirq_vec[nr].action = action;
}
/* Tasklets */
struct tasklet_head
{
struct tasklet_struct *list;
};
/* Some compilers disobey section attribute on statics when not
initialized -- RR */
static DEFINE_PER_CPU(struct tasklet_head, tasklet_vec) = { NULL };
static DEFINE_PER_CPU(struct tasklet_head, tasklet_hi_vec) = { NULL };
void __tasklet_schedule(struct tasklet_struct *t)
{
unsigned long flags;
local_irq_save(flags);
t->next = __get_cpu_var(tasklet_vec).list;
__get_cpu_var(tasklet_vec).list = t;
raise_softirq_irqoff(TASKLET_SOFTIRQ);
local_irq_restore(flags);
}
EXPORT_SYMBOL(__tasklet_schedule);
void __tasklet_hi_schedule(struct tasklet_struct *t)
{
unsigned long flags;
local_irq_save(flags);
t->next = __get_cpu_var(tasklet_hi_vec).list;
__get_cpu_var(tasklet_hi_vec).list = t;
raise_softirq_irqoff(HI_SOFTIRQ);
local_irq_restore(flags);
}
EXPORT_SYMBOL(__tasklet_hi_schedule);
static void tasklet_action(struct softirq_action *a)
{
struct tasklet_struct *list;
local_irq_disable();
list = __get_cpu_var(tasklet_vec).list;
__get_cpu_var(tasklet_vec).list = NULL;
local_irq_enable();
while (list) {
struct tasklet_struct *t = list;
list = list->next;
if (tasklet_trylock(t)) {
if (!atomic_read(&t->count)) {
if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state))
BUG();
t->func(t->data);
tasklet_unlock(t);
continue;
}
tasklet_unlock(t);
}
local_irq_disable();
t->next = __get_cpu_var(tasklet_vec).list;
__get_cpu_var(tasklet_vec).list = t;
__raise_softirq_irqoff(TASKLET_SOFTIRQ);
local_irq_enable();
}
}
static void tasklet_hi_action(struct softirq_action *a)
{
struct tasklet_struct *list;
local_irq_disable();
list = __get_cpu_var(tasklet_hi_vec).list;
__get_cpu_var(tasklet_hi_vec).list = NULL;
local_irq_enable();
while (list) {
struct tasklet_struct *t = list;
list = list->next;
if (tasklet_trylock(t)) {
if (!atomic_read(&t->count)) {
if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state))
BUG();
t->func(t->data);
tasklet_unlock(t);
continue;
}
tasklet_unlock(t);
}
local_irq_disable();
t->next = __get_cpu_var(tasklet_hi_vec).list;
__get_cpu_var(tasklet_hi_vec).list = t;
__raise_softirq_irqoff(HI_SOFTIRQ);
local_irq_enable();
}
}
void tasklet_init(struct tasklet_struct *t,
void (*func)(unsigned long), unsigned long data)
{
t->next = NULL;
t->state = 0;
atomic_set(&t->count, 0);
t->func = func;
t->data = data;
}
EXPORT_SYMBOL(tasklet_init);
void tasklet_kill(struct tasklet_struct *t)
{
if (in_interrupt())
printk("Attempt to kill tasklet from interrupt\n");
while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) {
do
yield();
while (test_bit(TASKLET_STATE_SCHED, &t->state));
}
tasklet_unlock_wait(t);
clear_bit(TASKLET_STATE_SCHED, &t->state);
}
EXPORT_SYMBOL(tasklet_kill);
void __init softirq_init(void)
{
open_softirq(TASKLET_SOFTIRQ, tasklet_action, NULL);
open_softirq(HI_SOFTIRQ, tasklet_hi_action, NULL);
}
static int ksoftirqd(void * __bind_cpu)
{
set_current_state(TASK_INTERRUPTIBLE);
while (!kthread_should_stop()) {
preempt_disable();
if (!local_softirq_pending()) {
preempt_enable_no_resched();
schedule();
preempt_disable();
}
__set_current_state(TASK_RUNNING);
while (local_softirq_pending()) {
/* Preempt disable stops cpu going offline.
If already offline, we'll be on wrong CPU:
don't process */
if (cpu_is_offline((long)__bind_cpu))
goto wait_to_die;
do_softirq();
preempt_enable_no_resched();
cond_resched();
preempt_disable();
}
preempt_enable();
set_current_state(TASK_INTERRUPTIBLE);
}
__set_current_state(TASK_RUNNING);
return 0;
wait_to_die:
preempt_enable();
/* Wait for kthread_stop */
set_current_state(TASK_INTERRUPTIBLE);
while (!kthread_should_stop()) {
schedule();
set_current_state(TASK_INTERRUPTIBLE);
}
__set_current_state(TASK_RUNNING);
return 0;
}
#ifdef CONFIG_HOTPLUG_CPU
/*
* tasklet_kill_immediate is called to remove a tasklet which can already be
* scheduled for execution on @cpu.
*
* Unlike tasklet_kill, this function removes the tasklet
* _immediately_, even if the tasklet is in TASKLET_STATE_SCHED state.
*
* When this function is called, @cpu must be in the CPU_DEAD state.
*/
void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu)
{
struct tasklet_struct **i;
BUG_ON(cpu_online(cpu));
BUG_ON(test_bit(TASKLET_STATE_RUN, &t->state));
if (!test_bit(TASKLET_STATE_SCHED, &t->state))
return;
/* CPU is dead, so no lock needed. */
for (i = &per_cpu(tasklet_vec, cpu).list; *i; i = &(*i)->next) {
if (*i == t) {
*i = t->next;
return;
}
}
BUG();
}
static void takeover_tasklets(unsigned int cpu)
{
struct tasklet_struct **i;
/* CPU is dead, so no lock needed. */
local_irq_disable();
/* Find end, append list for that CPU. */
for (i = &__get_cpu_var(tasklet_vec).list; *i; i = &(*i)->next);
*i = per_cpu(tasklet_vec, cpu).list;
per_cpu(tasklet_vec, cpu).list = NULL;
raise_softirq_irqoff(TASKLET_SOFTIRQ);
for (i = &__get_cpu_var(tasklet_hi_vec).list; *i; i = &(*i)->next);
*i = per_cpu(tasklet_hi_vec, cpu).list;
per_cpu(tasklet_hi_vec, cpu).list = NULL;
raise_softirq_irqoff(HI_SOFTIRQ);
local_irq_enable();
}
#endif /* CONFIG_HOTPLUG_CPU */
static int __cpuinit cpu_callback(struct notifier_block *nfb,
unsigned long action,
void *hcpu)
{
int hotcpu = (unsigned long)hcpu;
struct task_struct *p;
switch (action) {
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
p = kthread_create(ksoftirqd, hcpu, "ksoftirqd/%d", hotcpu);
if (IS_ERR(p)) {
printk("ksoftirqd for %i failed\n", hotcpu);
return NOTIFY_BAD;
}
kthread_bind(p, hotcpu);
per_cpu(ksoftirqd, hotcpu) = p;
break;
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
wake_up_process(per_cpu(ksoftirqd, hotcpu));
break;
#ifdef CONFIG_HOTPLUG_CPU
case CPU_UP_CANCELED:
case CPU_UP_CANCELED_FROZEN:
if (!per_cpu(ksoftirqd, hotcpu))
break;
/* Unbind so it can run. Fall thru. */
kthread_bind(per_cpu(ksoftirqd, hotcpu),
any_online_cpu(cpu_online_map));
case CPU_DEAD:
case CPU_DEAD_FROZEN: {
struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
p = per_cpu(ksoftirqd, hotcpu);
per_cpu(ksoftirqd, hotcpu) = NULL;
sched_setscheduler(p, SCHED_FIFO, &param);
kthread_stop(p);
takeover_tasklets(hotcpu);
break;
}
#endif /* CONFIG_HOTPLUG_CPU */
}
return NOTIFY_OK;
}
static struct notifier_block __cpuinitdata cpu_nfb = {
.notifier_call = cpu_callback
};
__init int spawn_ksoftirqd(void)
{
void *cpu = (void *)(long)smp_processor_id();
int err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
BUG_ON(err == NOTIFY_BAD);
cpu_callback(&cpu_nfb, CPU_ONLINE, cpu);
register_cpu_notifier(&cpu_nfb);
return 0;
}
#ifdef CONFIG_SMP
/*
* Call a function on all processors
*/
int on_each_cpu(void (*func) (void *info), void *info, int retry, int wait)
{
int ret = 0;
preempt_disable();
ret = smp_call_function(func, info, retry, wait);
local_irq_disable();
func(info);
local_irq_enable();
preempt_enable();
return ret;
}
EXPORT_SYMBOL(on_each_cpu);
#endif