Linux 的softirq机制是与SMP紧密不可分的。为此,整个softirq机制的设计与实现中自始自终都贯彻了一个思想:“谁触发,谁执行”(Who marks,Who runs),也即触发软中断的那个CPU负责执行它所触发的软中断,而且每个CPU都由它自己的软中断触发与控制机制。这个设计思想也使得softirq 机制充分利用了SMP系统的性能和特点。 多个softirq可以并行执行,甚至同一个softirq可以在多个processor上同时执行。
一、softirq的实现
每个softirq在内核中通过struct softirq_action来表示,另外,通过全局属组softirq_vec标识当前内核支持的所有的softirq。
/* softirq mask and active fields moved to irq_cpustat_t in * asm/hardirq.h to get better cache usage. KAO */ struct softirq_action { void (*action)(struct softirq_action *); }; static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp; Linux内核最多可以支持32个softirq(思考:为什么是32个?),但当前只实现了10个,如下: enum { HI_SOFTIRQ=0, TIMER_SOFTIRQ, NET_TX_SOFTIRQ, NET_RX_SOFTIRQ, BLOCK_SOFTIRQ, BLOCK_IOPOLL_SOFTIRQ, TASKLET_SOFTIRQ, SCHED_SOFTIRQ, HRTIMER_SOFTIRQ, RCU_SOFTIRQ, /* Preferable RCU should always be the last softirq */ NR_SOFTIRQS };
二、softirq处理函数
struct softirq_action结构体中,只有一个函数指针成员action,即指向用户定义的softirq处理函数。当执行时,可以通过如下代码:
softirq_vec[i]->action(i);
一个注册的softirq在执行之前必须被激活,术语称为"raise the softirq"。被激活的softirq通常并不会立即执行,一般会在之后的某个时刻检查当前系统中是否有被pending的softirq,如果有就去执行,Linux内核中检查是否有softirq挂起的检查点主要有以下三类:
(1)硬件中断代码返回的时候
/* * 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(); rcu_irq_exit(); #ifdef CONFIG_NO_HZ /* Make sure that timer wheel updates are propagated */ if (idle_cpu(smp_processor_id()) && !in_interrupt() && !need_resched()) tick_nohz_stop_sched_tick(0); #endif preempt_enable_no_resched(); }
(2)ksoftirqd内核服务线程运行的时候
static int run_ksoftirqd(void * __bind_cpu) { ... ... 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(); rcu_note_context_switch((long)__bind_cpu); } preempt_enable(); set_current_state(TASK_INTERRUPTIBLE); } __set_current_state(TASK_RUNNING); return 0; ... ... }
(3)在一些内核子系统中显示的去检查挂起的softirq
int netif_rx_ni(struct sk_buff *skb) { int err; preempt_disable(); err = netif_rx(skb); if (local_softirq_pending()) do_softirq(); preemptenable(); return err; }
下面重点分析以下do_softirq(),了解Linux内核到底是怎么来处理softirq的。
asmlinkage void do_softirq(void) { unsigned long flags; struct thread_info *curctx; union irq_ctx *irqctx; u32 *isp; if (in_interrupt()) /*首先判断是否在中断上下文中*/ return; local_irq_save(flags); if (local_softirq_pending()) { curctx = current_thread_info(); irqctx = __get_cpu_var(softirq_ctx); irqctx->tinfo.task = curctx->task; irqctx->tinfo.previous_esp = current_stack_pointer; /* build the stack frame on the softirq stack */ isp = (u32 *) ((char *)irqctx + sizeof(*irqctx)); call_on_stack(__do_softirq, isp); /* * Shouldnt happen, we returned above if in_interrupt(): */ WARN_ON_ONCE(softirq_count()); } local_irq_restore(flags); }
实际的处理函数为__do_softirq:
asmlinkage void __do_softirq(void) { struct softirq_action *h; __u32 pending; int max_restart = MAX_SOFTIRQ_RESTART; /*不启动ksoftirqd之前,最大的处理softirq的次数,经验值*/ int cpu; /*取得当前被挂起的softirq,同时这里也解释了为什么Linux内核最多支持32个softirq,因为pending只有32bit*/ 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);/*获取了pending的softirq之后,清空所有pending的softirq的标志*/ local_irq_enable(); h = softirq_vec; do { if (pending & 1) { /*从最低位开始,循环右移逐位处理pending的softirq*/ int prev_count = preempt_count(); kstat_incr_softirqs_this_cpu(h - softirq_vec); trace_softirq_entry(h, softirq_vec); h->action(h); /*执行softirq的处理函数*/ 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; /*循环右移*/ } while (pending); local_irq_disable(); pending = local_softirq_pending(); if (pending && --max_restart) /*启动ksoftirqd的阈值*/ goto restart; if (pending) /*启动ksoftirqd去处理softirq,此时说明pending的softirq比较多,比较频繁,上面的处理过程中,又不断有softirq被pending*/ wakeup_softirqd(); lockdep_softirq_exit(); account_system_vtime(current); _local_bh_enable(); }
三、使用softirq
softirq一般用在对实时性要求比较强的地方,当前的Linux内核中,只有两个子系统直接使用了softirq:网络子系统和块设备子系统。另外,增加新的softirq需要重新编译内核,因此,除非必须需要,最好考虑tasklet和kernel timer是否适合当前需要。
如果必须需要使用softirq,那么需要考虑的一个重要的问题就是新增加的softirq的优先级,默认情况下,softirq的数值越小优先级越高,根据实际经验,新增加的softirq最好在BLOCK_SOFTIRQ和TASKLET_SOFTIRQ之间。
softirq的处理函数通过open_softirq进行注册,此函数接收两个参数,一个是softirq的整数索引,另一个是该softirq对应的处理函数。例如在网络子系统中,注册了如下两个softirq及其处理函数:
open_softirq(NET_TX_SOFTIRQ, net_tx_action);
open_softirq(NET_RX_SOFTIRQ, net_rx_action);
前面提到,软中断处理函数注册后,还需要将该软中断激活,此软中断才能被执行,激活操作是通过raise_softirq函数来实现,在网络子系统中激活代码如下:
/* Called with irq disabled */ static inline void ____napi_schedule(struct softnet_data *sd, struct napi_struct *napi) { list_add_tail(&napi->poll_list, &sd->poll_list); __raise_softirq_irqoff(NET_RX_SOFTIRQ); }
这里的__raise_softirq_irqoff和raise_softirq的区别是,前者在事先已经关中断的情况下可以被使用,后者自己完成中断的关闭和恢复。