linux/kernel/softirq.c
Linus Torvalds 534c97b095 Merge branch 'timers-nohz-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull 'full dynticks' support from Ingo Molnar:
 "This tree from Frederic Weisbecker adds a new, (exciting! :-) core
  kernel feature to the timer and scheduler subsystems: 'full dynticks',
  or CONFIG_NO_HZ_FULL=y.

  This feature extends the nohz variable-size timer tick feature from
  idle to busy CPUs (running at most one task) as well, potentially
  reducing the number of timer interrupts significantly.

  This feature got motivated by real-time folks and the -rt tree, but
  the general utility and motivation of full-dynticks runs wider than
  that:

   - HPC workloads get faster: CPUs running a single task should be able
     to utilize a maximum amount of CPU power.  A periodic timer tick at
     HZ=1000 can cause a constant overhead of up to 1.0%.  This feature
     removes that overhead - and speeds up the system by 0.5%-1.0% on
     typical distro configs even on modern systems.

   - Real-time workload latency reduction: CPUs running critical tasks
     should experience as little jitter as possible.  The last remaining
     source of kernel-related jitter was the periodic timer tick.

   - A single task executing on a CPU is a pretty common situation,
     especially with an increasing number of cores/CPUs, so this feature
     helps desktop and mobile workloads as well.

  The cost of the feature is mainly related to increased timer
  reprogramming overhead when a CPU switches its tick period, and thus
  slightly longer to-idle and from-idle latency.

  Configuration-wise a third mode of operation is added to the existing
  two NOHZ kconfig modes:

   - CONFIG_HZ_PERIODIC: [formerly !CONFIG_NO_HZ], now explicitly named
     as a config option.  This is the traditional Linux periodic tick
     design: there's a HZ tick going on all the time, regardless of
     whether a CPU is idle or not.

   - CONFIG_NO_HZ_IDLE: [formerly CONFIG_NO_HZ=y], this turns off the
     periodic tick when a CPU enters idle mode.

   - CONFIG_NO_HZ_FULL: this new mode, in addition to turning off the
     tick when a CPU is idle, also slows the tick down to 1 Hz (one
     timer interrupt per second) when only a single task is running on a
     CPU.

  The .config behavior is compatible: existing !CONFIG_NO_HZ and
  CONFIG_NO_HZ=y settings get translated to the new values, without the
  user having to configure anything.  CONFIG_NO_HZ_FULL is turned off by
  default.

  This feature is based on a lot of infrastructure work that has been
  steadily going upstream in the last 2-3 cycles: related RCU support
  and non-periodic cputime support in particular is upstream already.

  This tree adds the final pieces and activates the feature.  The pull
  request is marked RFC because:

   - it's marked 64-bit only at the moment - the 32-bit support patch is
     small but did not get ready in time.

   - it has a number of fresh commits that came in after the merge
     window.  The overwhelming majority of commits are from before the
     merge window, but still some aspects of the tree are fresh and so I
     marked it RFC.

   - it's a pretty wide-reaching feature with lots of effects - and
     while the components have been in testing for some time, the full
     combination is still not very widely used.  That it's default-off
     should reduce its regression abilities and obviously there are no
     known regressions with CONFIG_NO_HZ_FULL=y enabled either.

   - the feature is not completely idempotent: there is no 100%
     equivalent replacement for a periodic scheduler/timer tick.  In
     particular there's ongoing work to map out and reduce its effects
     on scheduler load-balancing and statistics.  This should not impact
     correctness though, there are no known regressions related to this
     feature at this point.

   - it's a pretty ambitious feature that with time will likely be
     enabled by most Linux distros, and we'd like you to make input on
     its design/implementation, if you dislike some aspect we missed.
     Without flaming us to crisp! :-)

  Future plans:

   - there's ongoing work to reduce 1Hz to 0Hz, to essentially shut off
     the periodic tick altogether when there's a single busy task on a
     CPU.  We'd first like 1 Hz to be exposed more widely before we go
     for the 0 Hz target though.

   - once we reach 0 Hz we can remove the periodic tick assumption from
     nr_running>=2 as well, by essentially interrupting busy tasks only
     as frequently as the sched_latency constraints require us to do -
     once every 4-40 msecs, depending on nr_running.

  I am personally leaning towards biting the bullet and doing this in
  v3.10, like the -rt tree this effort has been going on for too long -
  but the final word is up to you as usual.

  More technical details can be found in Documentation/timers/NO_HZ.txt"

* 'timers-nohz-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (39 commits)
  sched: Keep at least 1 tick per second for active dynticks tasks
  rcu: Fix full dynticks' dependency on wide RCU nocb mode
  nohz: Protect smp_processor_id() in tick_nohz_task_switch()
  nohz_full: Add documentation.
  cputime_nsecs: use math64.h for nsec resolution conversion helpers
  nohz: Select VIRT_CPU_ACCOUNTING_GEN from full dynticks config
  nohz: Reduce overhead under high-freq idling patterns
  nohz: Remove full dynticks' superfluous dependency on RCU tree
  nohz: Fix unavailable tick_stop tracepoint in dynticks idle
  nohz: Add basic tracing
  nohz: Select wide RCU nocb for full dynticks
  nohz: Disable the tick when irq resume in full dynticks CPU
  nohz: Re-evaluate the tick for the new task after a context switch
  nohz: Prepare to stop the tick on irq exit
  nohz: Implement full dynticks kick
  nohz: Re-evaluate the tick from the scheduler IPI
  sched: New helper to prevent from stopping the tick in full dynticks
  sched: Kick full dynticks CPU that have more than one task enqueued.
  perf: New helper to prevent full dynticks CPUs from stopping tick
  perf: Kick full dynticks CPU if events rotation is needed
  ...
2013-05-05 13:23:27 -07:00

885 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 2 ms,
* and if need_resched() is not set.
*
* 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)
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;
/*
* 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())
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