linux/kernel/softirq.c
Ben Greear 34376a50fb Fix lockup related to stop_machine being stuck in __do_softirq.
The stop machine logic can lock up if all but one of the migration
threads make it through the disable-irq step and the one remaining
thread gets stuck in __do_softirq.  The reason __do_softirq can hang is
that it has a bail-out based on jiffies timeout, but in the lockup case,
jiffies itself is not incremented.

To work around this, re-add the max_restart counter in __do_irq and stop
processing irqs after 10 restarts.

Thanks to Tejun Heo and Rusty Russell and others for helping me track
this down.

This was introduced in 3.9 by commit c10d73671a ("softirq: reduce
latencies").

It may be worth looking into ath9k to see if it has issues with its irq
handler at a later date.

The hang stack traces look something like this:

    ------------[ cut here ]------------
    WARNING: at kernel/watchdog.c:245 watchdog_overflow_callback+0x9c/0xa7()
    Watchdog detected hard LOCKUP on cpu 2
    Modules linked in: ath9k ath9k_common ath9k_hw ath mac80211 cfg80211 nfsv4 auth_rpcgss nfs fscache nf_nat_ipv4 nf_nat veth 8021q garp stp mrp llc pktgen lockd sunrpc]
    Pid: 23, comm: migration/2 Tainted: G         C   3.9.4+ #11
    Call Trace:
     <NMI>   warn_slowpath_common+0x85/0x9f
      warn_slowpath_fmt+0x46/0x48
      watchdog_overflow_callback+0x9c/0xa7
      __perf_event_overflow+0x137/0x1cb
      perf_event_overflow+0x14/0x16
      intel_pmu_handle_irq+0x2dc/0x359
      perf_event_nmi_handler+0x19/0x1b
      nmi_handle+0x7f/0xc2
      do_nmi+0xbc/0x304
      end_repeat_nmi+0x1e/0x2e
     <<EOE>>
      cpu_stopper_thread+0xae/0x162
      smpboot_thread_fn+0x258/0x260
      kthread+0xc7/0xcf
      ret_from_fork+0x7c/0xb0
    ---[ end trace 4947dfa9b0a4cec3 ]---
    BUG: soft lockup - CPU#1 stuck for 22s! [migration/1:17]
    Modules linked in: ath9k ath9k_common ath9k_hw ath mac80211 cfg80211 nfsv4 auth_rpcgss nfs fscache nf_nat_ipv4 nf_nat veth 8021q garp stp mrp llc pktgen lockd sunrpc]
    irq event stamp: 835637905
    hardirqs last  enabled at (835637904): __do_softirq+0x9f/0x257
    hardirqs last disabled at (835637905): apic_timer_interrupt+0x6d/0x80
    softirqs last  enabled at (5654720): __do_softirq+0x1ff/0x257
    softirqs last disabled at (5654725): irq_exit+0x5f/0xbb
    CPU 1
    Pid: 17, comm: migration/1 Tainted: G        WC   3.9.4+ #11 To be filled by O.E.M. To be filled by O.E.M./To be filled by O.E.M.
    RIP: tasklet_hi_action+0xf0/0xf0
    Process migration/1
    Call Trace:
     <IRQ>
      __do_softirq+0x117/0x257
      irq_exit+0x5f/0xbb
      smp_apic_timer_interrupt+0x8a/0x98
      apic_timer_interrupt+0x72/0x80
     <EOI>
      printk+0x4d/0x4f
      stop_machine_cpu_stop+0x22c/0x274
      cpu_stopper_thread+0xae/0x162
      smpboot_thread_fn+0x258/0x260
      kthread+0xc7/0xcf
      ret_from_fork+0x7c/0xb0

Signed-off-by: Ben Greear <greearb@candelatech.com>
Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: Pekka Riikonen <priikone@iki.fi>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: stable@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-06-10 17:46:57 -07:00

892 lines
21 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)
*
* Remote softirq infrastructure is by Jens Axboe.
*/
#include <linux/export.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/ftrace.h>
#include <linux/smp.h>
#include <linux/smpboot.h>
#include <linux/tick.h>
#define CREATE_TRACE_POINTS
#include <trace/events/irq.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[NR_SOFTIRQS] __cacheline_aligned_in_smp;
DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
char *softirq_to_name[NR_SOFTIRQS] = {
"HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "BLOCK_IOPOLL",
"TASKLET", "SCHED", "HRTIMER", "RCU"
};
/*
* 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 void wakeup_softirqd(void)
{
/* Interrupts are disabled: no need to stop preemption */
struct task_struct *tsk = __this_cpu_read(ksoftirqd);
if (tsk && tsk->state != TASK_RUNNING)
wake_up_process(tsk);
}
/*
* preempt_count and SOFTIRQ_OFFSET usage:
* - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving
* softirq processing.
* - preempt_count is changed by SOFTIRQ_DISABLE_OFFSET (= 2 * SOFTIRQ_OFFSET)
* on local_bh_disable or local_bh_enable.
* This lets us distinguish between whether we are currently processing
* softirq and whether we just have bh disabled.
*/
/*
* 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 int cnt)
{
unsigned long flags;
WARN_ON_ONCE(in_irq());
raw_local_irq_save(flags);
/*
* The preempt tracer hooks into add_preempt_count and will break
* lockdep because it calls back into lockdep after SOFTIRQ_OFFSET
* is set and before current->softirq_enabled is cleared.
* We must manually increment preempt_count here and manually
* call the trace_preempt_off later.
*/
preempt_count() += cnt;
/*
* Were softirqs turned off above:
*/
if (softirq_count() == cnt)
trace_softirqs_off(ip);
raw_local_irq_restore(flags);
if (preempt_count() == cnt)
trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
}
#else /* !CONFIG_TRACE_IRQFLAGS */
static inline void __local_bh_disable(unsigned long ip, unsigned int cnt)
{
add_preempt_count(cnt);
barrier();
}
#endif /* CONFIG_TRACE_IRQFLAGS */
void local_bh_disable(void)
{
__local_bh_disable((unsigned long)__builtin_return_address(0),
SOFTIRQ_DISABLE_OFFSET);
}
EXPORT_SYMBOL(local_bh_disable);
static void __local_bh_enable(unsigned int cnt)
{
WARN_ON_ONCE(in_irq());
WARN_ON_ONCE(!irqs_disabled());
if (softirq_count() == cnt)
trace_softirqs_on((unsigned long)__builtin_return_address(0));
sub_preempt_count(cnt);
}
/*
* 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)
{
__local_bh_enable(SOFTIRQ_DISABLE_OFFSET);
}
EXPORT_SYMBOL(_local_bh_enable);
static inline void _local_bh_enable_ip(unsigned long ip)
{
WARN_ON_ONCE(in_irq() || irqs_disabled());
#ifdef CONFIG_TRACE_IRQFLAGS
local_irq_disable();
#endif
/*
* Are softirqs going to be turned on now:
*/
if (softirq_count() == SOFTIRQ_DISABLE_OFFSET)
trace_softirqs_on(ip);
/*
* Keep preemption disabled until we are done with
* softirq processing:
*/
sub_preempt_count(SOFTIRQ_DISABLE_OFFSET - 1);
if (unlikely(!in_interrupt() && local_softirq_pending()))
do_softirq();
dec_preempt_count();
#ifdef CONFIG_TRACE_IRQFLAGS
local_irq_enable();
#endif
preempt_check_resched();
}
void local_bh_enable(void)
{
_local_bh_enable_ip((unsigned long)__builtin_return_address(0));
}
EXPORT_SYMBOL(local_bh_enable);
void local_bh_enable_ip(unsigned long ip)
{
_local_bh_enable_ip(ip);
}
EXPORT_SYMBOL(local_bh_enable_ip);
/*
* We restart softirq processing for at most MAX_SOFTIRQ_RESTART times,
* but break the loop if need_resched() is set or after 2 ms.
* The MAX_SOFTIRQ_TIME provides a nice upper bound in most cases, but in
* certain cases, such as stop_machine(), jiffies may cease to
* increment and so we need the MAX_SOFTIRQ_RESTART limit as
* well to make sure we eventually return from this method.
*
* These limits have 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_TIME msecs_to_jiffies(2)
#define MAX_SOFTIRQ_RESTART 10
asmlinkage void __do_softirq(void)
{
struct softirq_action *h;
__u32 pending;
unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
int cpu;
unsigned long old_flags = current->flags;
int max_restart = MAX_SOFTIRQ_RESTART;
/*
* Mask out PF_MEMALLOC s current task context is borrowed for the
* softirq. A softirq handled such as network RX might set PF_MEMALLOC
* again if the socket is related to swap
*/
current->flags &= ~PF_MEMALLOC;
pending = local_softirq_pending();
account_irq_enter_time(current);
__local_bh_disable((unsigned long)__builtin_return_address(0),
SOFTIRQ_OFFSET);
lockdep_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) {
unsigned int vec_nr = h - softirq_vec;
int prev_count = preempt_count();
kstat_incr_softirqs_this_cpu(vec_nr);
trace_softirq_entry(vec_nr);
h->action(h);
trace_softirq_exit(vec_nr);
if (unlikely(prev_count != preempt_count())) {
printk(KERN_ERR "huh, entered softirq %u %s %p"
"with preempt_count %08x,"
" exited with %08x?\n", vec_nr,
softirq_to_name[vec_nr], h->action,
prev_count, preempt_count());
preempt_count() = prev_count;
}
rcu_bh_qs(cpu);
}
h++;
pending >>= 1;
} while (pending);
local_irq_disable();
pending = local_softirq_pending();
if (pending) {
if (time_before(jiffies, end) && !need_resched() &&
--max_restart)
goto restart;
wakeup_softirqd();
}
lockdep_softirq_exit();
account_irq_exit_time(current);
__local_bh_enable(SOFTIRQ_OFFSET);
tsk_restore_flags(current, old_flags, PF_MEMALLOC);
}
#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)
{
int cpu = smp_processor_id();
rcu_irq_enter();
if (is_idle_task(current) && !in_interrupt()) {
/*
* Prevent raise_softirq from needlessly waking up ksoftirqd
* here, as softirq will be serviced on return from interrupt.
*/
local_bh_disable();
tick_check_idle(cpu);
_local_bh_enable();
}
__irq_enter();
}
static inline void invoke_softirq(void)
{
if (!force_irqthreads)
__do_softirq();
else
wakeup_softirqd();
}
static inline void tick_irq_exit(void)
{
#ifdef CONFIG_NO_HZ_COMMON
int cpu = smp_processor_id();
/* Make sure that timer wheel updates are propagated */
if ((idle_cpu(cpu) && !need_resched()) || tick_nohz_full_cpu(cpu)) {
if (!in_interrupt())
tick_nohz_irq_exit();
}
#endif
}
/*
* Exit an interrupt context. Process softirqs if needed and possible:
*/
void irq_exit(void)
{
#ifndef __ARCH_IRQ_EXIT_IRQS_DISABLED
local_irq_disable();
#else
WARN_ON_ONCE(!irqs_disabled());
#endif
account_irq_exit_time(current);
trace_hardirq_exit();
sub_preempt_count(HARDIRQ_OFFSET);
if (!in_interrupt() && local_softirq_pending())
invoke_softirq();
tick_irq_exit();
rcu_irq_exit();
}
/*
* 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 __raise_softirq_irqoff(unsigned int nr)
{
trace_softirq_raise(nr);
or_softirq_pending(1UL << nr);
}
void open_softirq(int nr, void (*action)(struct softirq_action *))
{
softirq_vec[nr].action = action;
}
/*
* Tasklets
*/
struct tasklet_head
{
struct tasklet_struct *head;
struct tasklet_struct **tail;
};
static DEFINE_PER_CPU(struct tasklet_head, tasklet_vec);
static DEFINE_PER_CPU(struct tasklet_head, tasklet_hi_vec);
void __tasklet_schedule(struct tasklet_struct *t)
{
unsigned long flags;
local_irq_save(flags);
t->next = NULL;
*__this_cpu_read(tasklet_vec.tail) = t;
__this_cpu_write(tasklet_vec.tail, &(t->next));
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 = NULL;
*__this_cpu_read(tasklet_hi_vec.tail) = t;
__this_cpu_write(tasklet_hi_vec.tail, &(t->next));
raise_softirq_irqoff(HI_SOFTIRQ);
local_irq_restore(flags);
}
EXPORT_SYMBOL(__tasklet_hi_schedule);
void __tasklet_hi_schedule_first(struct tasklet_struct *t)
{
BUG_ON(!irqs_disabled());
t->next = __this_cpu_read(tasklet_hi_vec.head);
__this_cpu_write(tasklet_hi_vec.head, t);
__raise_softirq_irqoff(HI_SOFTIRQ);
}
EXPORT_SYMBOL(__tasklet_hi_schedule_first);
static void tasklet_action(struct softirq_action *a)
{
struct tasklet_struct *list;
local_irq_disable();
list = __this_cpu_read(tasklet_vec.head);
__this_cpu_write(tasklet_vec.head, NULL);
__this_cpu_write(tasklet_vec.tail, &__get_cpu_var(tasklet_vec).head);
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 = NULL;
*__this_cpu_read(tasklet_vec.tail) = t;
__this_cpu_write(tasklet_vec.tail, &(t->next));
__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 = __this_cpu_read(tasklet_hi_vec.head);
__this_cpu_write(tasklet_hi_vec.head, NULL);
__this_cpu_write(tasklet_hi_vec.tail, &__get_cpu_var(tasklet_hi_vec).head);
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 = NULL;
*__this_cpu_read(tasklet_hi_vec.tail) = t;
__this_cpu_write(tasklet_hi_vec.tail, &(t->next));
__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);
/*
* tasklet_hrtimer
*/
/*
* The trampoline is called when the hrtimer expires. It schedules a tasklet
* to run __tasklet_hrtimer_trampoline() which in turn will call the intended
* hrtimer callback, but from softirq context.
*/
static enum hrtimer_restart __hrtimer_tasklet_trampoline(struct hrtimer *timer)
{
struct tasklet_hrtimer *ttimer =
container_of(timer, struct tasklet_hrtimer, timer);
tasklet_hi_schedule(&ttimer->tasklet);
return HRTIMER_NORESTART;
}
/*
* Helper function which calls the hrtimer callback from
* tasklet/softirq context
*/
static void __tasklet_hrtimer_trampoline(unsigned long data)
{
struct tasklet_hrtimer *ttimer = (void *)data;
enum hrtimer_restart restart;
restart = ttimer->function(&ttimer->timer);
if (restart != HRTIMER_NORESTART)
hrtimer_restart(&ttimer->timer);
}
/**
* tasklet_hrtimer_init - Init a tasklet/hrtimer combo for softirq callbacks
* @ttimer: tasklet_hrtimer which is initialized
* @function: hrtimer callback function which gets called from softirq context
* @which_clock: clock id (CLOCK_MONOTONIC/CLOCK_REALTIME)
* @mode: hrtimer mode (HRTIMER_MODE_ABS/HRTIMER_MODE_REL)
*/
void tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer,
enum hrtimer_restart (*function)(struct hrtimer *),
clockid_t which_clock, enum hrtimer_mode mode)
{
hrtimer_init(&ttimer->timer, which_clock, mode);
ttimer->timer.function = __hrtimer_tasklet_trampoline;
tasklet_init(&ttimer->tasklet, __tasklet_hrtimer_trampoline,
(unsigned long)ttimer);
ttimer->function = function;
}
EXPORT_SYMBOL_GPL(tasklet_hrtimer_init);
/*
* Remote softirq bits
*/
DEFINE_PER_CPU(struct list_head [NR_SOFTIRQS], softirq_work_list);
EXPORT_PER_CPU_SYMBOL(softirq_work_list);
static void __local_trigger(struct call_single_data *cp, int softirq)
{
struct list_head *head = &__get_cpu_var(softirq_work_list[softirq]);
list_add_tail(&cp->list, head);
/* Trigger the softirq only if the list was previously empty. */
if (head->next == &cp->list)
raise_softirq_irqoff(softirq);
}
#ifdef CONFIG_USE_GENERIC_SMP_HELPERS
static void remote_softirq_receive(void *data)
{
struct call_single_data *cp = data;
unsigned long flags;
int softirq;
softirq = *(int *)cp->info;
local_irq_save(flags);
__local_trigger(cp, softirq);
local_irq_restore(flags);
}
static int __try_remote_softirq(struct call_single_data *cp, int cpu, int softirq)
{
if (cpu_online(cpu)) {
cp->func = remote_softirq_receive;
cp->info = &softirq;
cp->flags = 0;
__smp_call_function_single(cpu, cp, 0);
return 0;
}
return 1;
}
#else /* CONFIG_USE_GENERIC_SMP_HELPERS */
static int __try_remote_softirq(struct call_single_data *cp, int cpu, int softirq)
{
return 1;
}
#endif
/**
* __send_remote_softirq - try to schedule softirq work on a remote cpu
* @cp: private SMP call function data area
* @cpu: the remote cpu
* @this_cpu: the currently executing cpu
* @softirq: the softirq for the work
*
* Attempt to schedule softirq work on a remote cpu. If this cannot be
* done, the work is instead queued up on the local cpu.
*
* Interrupts must be disabled.
*/
void __send_remote_softirq(struct call_single_data *cp, int cpu, int this_cpu, int softirq)
{
if (cpu == this_cpu || __try_remote_softirq(cp, cpu, softirq))
__local_trigger(cp, softirq);
}
EXPORT_SYMBOL(__send_remote_softirq);
/**
* send_remote_softirq - try to schedule softirq work on a remote cpu
* @cp: private SMP call function data area
* @cpu: the remote cpu
* @softirq: the softirq for the work
*
* Like __send_remote_softirq except that disabling interrupts and
* computing the current cpu is done for the caller.
*/
void send_remote_softirq(struct call_single_data *cp, int cpu, int softirq)
{
unsigned long flags;
int this_cpu;
local_irq_save(flags);
this_cpu = smp_processor_id();
__send_remote_softirq(cp, cpu, this_cpu, softirq);
local_irq_restore(flags);
}
EXPORT_SYMBOL(send_remote_softirq);
static int __cpuinit remote_softirq_cpu_notify(struct notifier_block *self,
unsigned long action, void *hcpu)
{
/*
* If a CPU goes away, splice its entries to the current CPU
* and trigger a run of the softirq
*/
if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
int cpu = (unsigned long) hcpu;
int i;
local_irq_disable();
for (i = 0; i < NR_SOFTIRQS; i++) {
struct list_head *head = &per_cpu(softirq_work_list[i], cpu);
struct list_head *local_head;
if (list_empty(head))
continue;
local_head = &__get_cpu_var(softirq_work_list[i]);
list_splice_init(head, local_head);
raise_softirq_irqoff(i);
}
local_irq_enable();
}
return NOTIFY_OK;
}
static struct notifier_block __cpuinitdata remote_softirq_cpu_notifier = {
.notifier_call = remote_softirq_cpu_notify,
};
void __init softirq_init(void)
{
int cpu;
for_each_possible_cpu(cpu) {
int i;
per_cpu(tasklet_vec, cpu).tail =
&per_cpu(tasklet_vec, cpu).head;
per_cpu(tasklet_hi_vec, cpu).tail =
&per_cpu(tasklet_hi_vec, cpu).head;
for (i = 0; i < NR_SOFTIRQS; i++)
INIT_LIST_HEAD(&per_cpu(softirq_work_list[i], cpu));
}
register_hotcpu_notifier(&remote_softirq_cpu_notifier);
open_softirq(TASKLET_SOFTIRQ, tasklet_action);
open_softirq(HI_SOFTIRQ, tasklet_hi_action);
}
static int ksoftirqd_should_run(unsigned int cpu)
{
return local_softirq_pending();
}
static void run_ksoftirqd(unsigned int cpu)
{
local_irq_disable();
if (local_softirq_pending()) {
__do_softirq();
rcu_note_context_switch(cpu);
local_irq_enable();
cond_resched();
return;
}
local_irq_enable();
}
#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).head; *i; i = &(*i)->next) {
if (*i == t) {
*i = t->next;
/* If this was the tail element, move the tail ptr */
if (*i == NULL)
per_cpu(tasklet_vec, cpu).tail = i;
return;
}
}
BUG();
}
static void takeover_tasklets(unsigned int cpu)
{
/* CPU is dead, so no lock needed. */
local_irq_disable();
/* Find end, append list for that CPU. */
if (&per_cpu(tasklet_vec, cpu).head != per_cpu(tasklet_vec, cpu).tail) {
*__this_cpu_read(tasklet_vec.tail) = per_cpu(tasklet_vec, cpu).head;
this_cpu_write(tasklet_vec.tail, per_cpu(tasklet_vec, cpu).tail);
per_cpu(tasklet_vec, cpu).head = NULL;
per_cpu(tasklet_vec, cpu).tail = &per_cpu(tasklet_vec, cpu).head;
}
raise_softirq_irqoff(TASKLET_SOFTIRQ);
if (&per_cpu(tasklet_hi_vec, cpu).head != per_cpu(tasklet_hi_vec, cpu).tail) {
*__this_cpu_read(tasklet_hi_vec.tail) = per_cpu(tasklet_hi_vec, cpu).head;
__this_cpu_write(tasklet_hi_vec.tail, per_cpu(tasklet_hi_vec, cpu).tail);
per_cpu(tasklet_hi_vec, cpu).head = NULL;
per_cpu(tasklet_hi_vec, cpu).tail = &per_cpu(tasklet_hi_vec, cpu).head;
}
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)
{
switch (action) {
#ifdef CONFIG_HOTPLUG_CPU
case CPU_DEAD:
case CPU_DEAD_FROZEN:
takeover_tasklets((unsigned long)hcpu);
break;
#endif /* CONFIG_HOTPLUG_CPU */
}
return NOTIFY_OK;
}
static struct notifier_block __cpuinitdata cpu_nfb = {
.notifier_call = cpu_callback
};
static struct smp_hotplug_thread softirq_threads = {
.store = &ksoftirqd,
.thread_should_run = ksoftirqd_should_run,
.thread_fn = run_ksoftirqd,
.thread_comm = "ksoftirqd/%u",
};
static __init int spawn_ksoftirqd(void)
{
register_cpu_notifier(&cpu_nfb);
BUG_ON(smpboot_register_percpu_thread(&softirq_threads));
return 0;
}
early_initcall(spawn_ksoftirqd);
/*
* [ These __weak aliases are kept in a separate compilation unit, so that
* GCC does not inline them incorrectly. ]
*/
int __init __weak early_irq_init(void)
{
return 0;
}
#ifdef CONFIG_GENERIC_HARDIRQS
int __init __weak arch_probe_nr_irqs(void)
{
return NR_IRQS_LEGACY;
}
int __init __weak arch_early_irq_init(void)
{
return 0;
}
#endif