/*
* 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();
}
interrupt.h中定义
#define __raise_softirq_irqoff(nr) do { or_softirq_pending(1UL << (nr)); } while (0)
#define set_softirq_pending(x) (local_softirq_pending() = (x))
#define or_softirq_pending(x) (local_softirq_pending() |= (x))
irq_cpustat.h中定义
/* arch independent irq_stat fields */
#define local_softirq_pending() \
__IRQ_STAT(smp_processor_id(), __softirq_pending)
extern irq_cpustat_t irq_stat[]; /* defined in asm/hardirq.h */
#define __IRQ_STAT(cpu, member) (irq_stat[cpu].member) ///很奇妙吧，宏也可以这么用
smp.h中定义
# define smp_processor_id() raw_smp_processor_id()
#define raw_smp_processor_id() 0
hardirq.h中定义
typedef struct {
unsigned int __softirq_pending;
unsigned int local_timer_irqs;
} irq_cpustat_t;
//////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
main.c的start_kernel()中调用
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);
}
intterupt.h中
enum
{
HI_SOFTIRQ=0,
TIMER_SOFTIRQ,
NET_TX_SOFTIRQ,
NET_RX_SOFTIRQ,
BLOCK_SOFTIRQ,
TASKLET_SOFTIRQ,
SCHED_SOFTIRQ,
#ifdef CONFIG_HIGH_RES_TIMERS
HRTIMER_SOFTIRQ,
#endif
RCU_SOFTIRQ, /* Preferable RCU should always be the last softirq */
NR_SOFTIRQS
};
在softirq.c中
void open_softirq(int nr, void (*action)(struct softirq_action *))
{
softirq_vec[nr].action = action;
}
interrupt.h
static struct softirq_action softirq_vec[NR_SOFTIRQS] ;
struct softirq_action
{
void (*action)(struct softirq_action *);
};
软中断向量TASKLET_SOFTIRQ的服务程序tasklet_action（）
函数tasklet_action()是tasklet机制与软中断向量TASKLET_SOFTIRQ的联系纽带。正是
该函数将当前CPU的tasklet队列中的各个tasklet放到当前CPU上来执行的。该函数实现
在kernel/softirq.c文件中，其源代码如下：
static void tasklet_action(struct softirq_action *a)
{
struct tasklet_struct *list;
local_irq_disable();
list = __get_cpu_var(tasklet_vec).head;
__get_cpu_var(tasklet_vec).head = NULL;
__get_cpu_var(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;
*__get_cpu_var(tasklet_vec).tail = t;
__get_cpu_var(tasklet_vec).tail = &(t->next);
__raise_softirq_irqoff(TASKLET_SOFTIRQ);
local_irq_enable();
}
}
注释如下：
①首先，在当前CPU关中断的情况下，“原子”地读取当前CPU的tasklet队列头部指针，
将其保存到局部变量list指针中，然后将当前CPU的tasklet队列头部指针设置为NULL，
以表示理论上当前CPU将不再有tasklet需要执行（但{BANNED}最佳后的实际结果却并不一定如此，
下面将会看到）。
②然后，用一个while{}循环来遍历由list所指向的tasklet队列，队列中的各个元素就
是将在当前CPU上执行的tasklet。循环体的执行步骤如下：
l 用指针t来表示当前队列元素，即当前需要执行的tasklet。
l 更新list指针为list->next，使它指向下一个要执行的tasklet。
l 用tasklet_trylock()宏试图对当前要执行的tasklet（由指针t所指向）进行加锁，如
果加锁成功（当前没有任何其他CPU正在执行这个tasklet），则用原子读函数
atomic_read()进一步判断count成员的值。如果count为0，说明这个tasklet是允许执行
的，于是：（1）先清除TASKLET_STATE_SCHED位；（2）然后，调用这个tasklet的可执
行函数func；（3）执行barrier()操作；（4）调用宏tasklet_unlock()来清除
TASKLET_STATE_RUN位。（5）{BANNED}最佳后，执行continue语句跳过下面的步骤，回到while循环
继续遍历队列中的下一个元素。如果count不为0，说明这个tasklet是禁止运行的，于是
调用tasklet_unlock()清除前面用tasklet_trylock()设置的TASKLET_STATE_RUN位。
l 如果tasklet_trylock()加锁不成功，或者因为当前tasklet的count值非0而不允许执
行时，我们必须将这个tasklet重新放回到当前CPU的tasklet队列中，以留待这个CPU下
次服务软中断向量TASKLET_SOFTIRQ时再执行。为此进行这样几步操作：（1）先关CPU中
断，以保证下面操作的原子性。（2）把这个tasklet重新放回到当前CPU的tasklet队列
的首部；（3）调用__cpu_raise_softirq()函数在当前CPU上再触发一次软中断请求
TASKLET_SOFTIRQ；（4）开中断。
l {BANNED}最佳后，回到while循环继续遍历队列。
///////////////////////////////////////////////////////////////////////////////////////////////////////////////////
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);
}
//////////////////////////////////////////////////////////////////////////////////////////////////////////////////
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));
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) {
int prev_count = preempt_count();
kstat_incr_softirqs_this_cpu(h - softirq_vec);
trace_softirq_entry(h, softirq_vec);
h->action(h);
trace_softirq_exit(h, softirq_vec);
if (unlikely(prev_count != preempt_count())) {
printk(KERN_ERR "huh, entered softirq %td %s %p"
"with preempt_count %08x,"
" exited with %08x?\n", h - softirq_vec,
softirq_to_name[h - softirq_vec],
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 && --max_restart)
goto restart;
if (pending)
wakeup_softirqd();
lockdep_softirq_exit();
account_system_vtime(current);
_local_bh_enable();
}
/////////////////////////////////////////////////////////////////////////////////////////////////////////
softirq.c
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;
}
//////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
softirq.c
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_nocheck(p, SCHED_FIFO, ¶m);
kthread_stop(p);
takeover_tasklets(hotcpu);
break;
}
#endif /* CONFIG_HOTPLUG_CPU */
}
return NOTIFY_OK;
}
/////////////////////////////////////////
/*
* Declared notifiers so far. I can imagine quite a few more chains
* over time (eg laptop power reset chains, reboot chain (to clean
* device units up), device [un]mount chain, module load/unload chain,
* low memory chain, screenblank chain (for plug in modular screenblankers)
* VC switch chains (for loadable kernel svgalib VC switch helpers) etc...
*/
include/linux/notifier.h文件中定义了 CPU的几种状态
#define SYS_DOWN 0x0001 /* Notify of system down */
#define SYS_RESTART SYS_DOWN
#define SYS_HALT 0x0002 /* Notify of system halt */
#define SYS_POWER_OFF 0x0003 /* Notify of system power off */
#define NETLINK_URELEASE 0x0001 /* Unicast netlink socket released */
#define CPU_ONLINE 0x0002 /* CPU (unsigned)v is up */
#define CPU_UP_PREPARE 0x0003 /* CPU (unsigned)v coming up */
#define CPU_UP_CANCELED 0x0004 /* CPU (unsigned)v NOT coming up */
#define CPU_DOWN_PREPARE 0x0005 /* CPU (unsigned)v going down */
#define CPU_DOWN_FAILED 0x0006 /* CPU (unsigned)v NOT going down */
#define CPU_DEAD 0x0007 /* CPU (unsigned)v dead */
#define CPU_DYING 0x0008 /* CPU (unsigned)v not running any task,
* not handling interrupts, soon dead.
* Called on the dying cpu, interrupts
* are already disabled. Must not
* sleep, must not fail */
#define CPU_POST_DEAD 0x0009 /* CPU (unsigned)v dead, cpu_hotplug
* lock is dropped */
#define CPU_STARTING 0x000A /* CPU (unsigned)v soon running.
* Called on the new cpu, just before
* enabling interrupts. Must not sleep,
* must not fail */
/* Used for CPU hotplug events occuring while tasks are frozen due to a suspend
* operation in progress
*/
#define CPU_TASKS_FROZEN 0x0010
#define CPU_ONLINE_FROZEN (CPU_ONLINE | CPU_TASKS_FROZEN)
#define CPU_UP_PREPARE_FROZEN (CPU_UP_PREPARE | CPU_TASKS_FROZEN)
#define CPU_UP_CANCELED_FROZEN (CPU_UP_CANCELED | CPU_TASKS_FROZEN)
#define CPU_DOWN_PREPARE_FROZEN (CPU_DOWN_PREPARE | CPU_TASKS_FROZEN)
#define CPU_DOWN_FAILED_FROZEN (CPU_DOWN_FAILED | CPU_TASKS_FROZEN)
#define CPU_DEAD_FROZEN (CPU_DEAD | CPU_TASKS_FROZEN)
#define CPU_DYING_FROZEN (CPU_DYING | CPU_TASKS_FROZEN)
#define CPU_STARTING_FROZEN (CPU_STARTING | CPU_TASKS_FROZEN)
////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
