目录
驱动中的中断处理
通过上一节的分析不难发现，要在驱动中支持中断，则需要构造一个 struct irqaction的结构对象，并根据IRQ 号加入到对应的链表中(因为 irq_des 已经在内核初始化时建好了)。不过内核有相应的API 接口，我们只需要调用就可以了。向内核注册一个中断处理函数的函数原型如下。
int request_irq(unsigned int irg, irg_handler_t handler, unsigned long flags,const char *name, void *dev);
各个形参说明如下。
irq:设备上所用中断的IRQ 号，这个号不是硬件手册上查到的号，而是内核中的IRQ号，这个号将会用于决定构造的 struct irqaction 对象被插入到哪个链表，并用于初始化struct irqaction 对象中的irg 成员。
handler: 指向中断处理函数的指针，类型定义如下。
irqreturn_t (*irg_handler_t)(int, void *);
中断发生后中断处理函数会被自动调用，第一个参数是 IRQ 号，第二个参数是对应的设备ID，也是 struct irqaction 结构中的dev_id 成员。handler 用于初始化 struct irqaction对象中的 handler 成员。
中断处理函数的返回值是一个枚举类型 irqretun_t，包含如下几个举值
IRQNONE:不是驱动所管理的设备产生的中断，用于共享中断。
IRQ_HANDLED:中断被正常处理。
IRQ_WAKE_THREAD:需要唤醒一个内核线程。
flags:与中断相关的标志，用于初始化 struct irgaction 对象中的flags 成员，常用的标志如下，这些标志可以用位或的方式来设置多个。
IRQF_TRIGGER_RISING: 上升沿触发。
IRQF_TRIGGER_FALLING:下降沿触发
IRQF_TRIGGER_HIGH;高电平触发。
IRQF_TRIGGER_LOW:低电平触发。
IRQF_DISABLED:中断函数执行期间禁止中断，将会被废弃
IRQF_SHARED:共享中断必须设置的标志。
IRQF_TIMER;定时器专用中断标志。
name: 该中断在/proc 中的名字，用于初始化 struct irqaction 对象中的 name 成员。
dev:区别共享中断中的不同设备所对应的 struct irqaction 对象，在 struct irqaction对象从链表中移除时需要，dev 用于初始化 struct irqaction 对象中的 dev_id 成员。共享中断必须传递一个非 NULL 的实参，非共享中断可以传 NULL。中断发生后，调用中断处理函数时，内核也会将该参数传给中断处理函数。
request_irq函数成功返回0，失败返回负值。需要说明的是，request_irq 函数根据传入的参数构造好一个struct irqaction 对象，并加入到对应的链表后，还将对应的中断使能了。所以我们并不需要再使能中断。
注销一个中断处理函数的函数原型如下。
void free_irq(unsigned int, void *); 其中,第一个参数是IRQ号,第二个参数是dev_id,共享中断必须要传递一个非NULL的实参，和request_irq 中的dev_id 保持一致。
除了中断的注册和注销函数之外，还有一些关于中断使能和禁止的函数或宏，这些函数不常用到，简单罗列如下。
local_irq_enable():使能本地CPU 的中断
local_irq_disable0:禁止本地CPU 的中断
local_irq_save(flags):使能本地 CPU的中断，并将之前的中断使能状态保存在flags中。
local_irq_restore(flags):用flags 中的中断使能状态恢复中断使能标志。
void enable_irq(unsigned int irq): 使能irq 指定的中断。
void disable_irq(unsigned int irq):同步禁止irq 指定的中断，即要等到irq 上的所有中断处理程序执行完成后才能禁止中断。很显然，在中断处理函数中不能调用。
void disable_irq_nosync(unsigned int irg):立即禁止irq 指定的中断。
有了上面对中断API函数的认识，接下来就可以在我们的驱动中添加中断处理函数.在下面的例子中，让虚拟串口和以太网卡共享中断，为了得到以太网卡的 IRQ 号，可以使用下面的命令来查询，其中 eth0 对应的 170就是以太网卡使用的 IRQ号。
另外，FS4412目标板上使用的是DM9000 网卡芯片，查阅芯片手册可知，中断触发的类型为高电平。有了这些信息后，可以在虚拟串口驱动中添加的有关中断支持的代码如下
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/fs.h>
#include <linux/cdev.h>
#include <linux/kfifo.h>
#include <linux/ioctl.h>
#include <linux/uaccess.h>
#include <linux/wait.h>
#include <linux/sched.h>
#include <linux/poll.h>
#include <linux/aio.h>
#include <linux/interrupt.h>
#include <linux/random.h>
#include "vser.h"
#define VSER_MAJOR 256
#define VSER_MINOR 0
#define VSER_DEV_CNT 1
#define VSER_DEV_NAME "vser"
struct vser_dev {
unsigned int baud;
struct option opt;
struct cdev cdev;
wait_queue_head_t rwqh;
wait_queue_head_t wwqh;
struct fasync_struct *fapp;
};
DEFINE_KFIFO(vsfifo, char, 32);
static struct vser_dev vsdev;
static int vser_fasync(int fd, struct file *filp, int on);
static int vser_open(struct inode *inode, struct file *filp)
{
return 0;
}
static int vser_release(struct inode *inode, struct file *filp)
{
vser_fasync(-1, filp, 0);
return 0;
}
static ssize_t vser_read(struct file *filp, char __user *buf, size_t count, loff_t *pos)
{
int ret;
unsigned int copied = 0;
if (kfifo_is_empty(&vsfifo)) {
if (filp->f_flags & O_NONBLOCK)
return -EAGAIN;
if (wait_event_interruptible_exclusive(vsdev.rwqh, !kfifo_is_empty(&vsfifo)))
return -ERESTARTSYS;
}
ret = kfifo_to_user(&vsfifo, buf, count, &copied);
if (!kfifo_is_full(&vsfifo)) {
wake_up_interruptible(&vsdev.wwqh);
kill_fasync(&vsdev.fapp, SIGIO, POLL_OUT);
}
return ret == 0 ? copied : ret;
}
static ssize_t vser_write(struct file *filp, const char __user *buf, size_t count, loff_t *pos)
{
int ret;
unsigned int copied = 0;
if (kfifo_is_full(&vsfifo)) {
if (filp->f_flags & O_NONBLOCK)
return -EAGAIN;
if (wait_event_interruptible_exclusive(vsdev.wwqh, !kfifo_is_full(&vsfifo)))
return -ERESTARTSYS;
}
ret = kfifo_from_user(&vsfifo, buf, count, &copied);
if (!kfifo_is_empty(&vsfifo)) {
wake_up_interruptible(&vsdev.rwqh);
kill_fasync(&vsdev.fapp, SIGIO, POLL_IN);
}
return ret == 0 ? copied : ret;
}
static long vser_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
if (_IOC_TYPE(cmd) != VS_MAGIC)
return -ENOTTY;
switch (cmd) {
case VS_SET_BAUD:
vsdev.baud = arg;
break;
case VS_GET_BAUD:
arg = vsdev.baud;
break;
case VS_SET_FFMT:
if (copy_from_user(&vsdev.opt, (struct option __user *)arg, sizeof(struct option)))
return -EFAULT;
break;
case VS_GET_FFMT:
if (copy_to_user((struct option __user *)arg, &vsdev.opt, sizeof(struct option)))
return -EFAULT;
break;
default:
return -ENOTTY;
}
return 0;
}
static unsigned int vser_poll(struct file *filp, struct poll_table_struct *p)
{
int mask = 0;
poll_wait(filp, &vsdev.rwqh, p);
poll_wait(filp, &vsdev.wwqh, p);
if (!kfifo_is_empty(&vsfifo))
mask |= POLLIN | POLLRDNORM;
if (!kfifo_is_full(&vsfifo))
mask |= POLLOUT | POLLWRNORM;
return mask;
}
static ssize_t vser_aio_read(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos)
{
size_t read = 0;
unsigned long i;
ssize_t ret;
for (i = 0; i < nr_segs; i++) {
ret = vser_read(iocb->ki_filp, iov[i].iov_base, iov[i].iov_len, &pos);
if (ret < 0)
break;
read += ret;
}
return read ? read : -EFAULT;
}
static ssize_t vser_aio_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos)
{
size_t written = 0;
unsigned long i;
ssize_t ret;
for (i = 0; i < nr_segs; i++) {
ret = vser_write(iocb->ki_filp, iov[i].iov_base, iov[i].iov_len, &pos);
if (ret < 0)
break;
written += ret;
}
return written ? written : -EFAULT;
}
static int vser_fasync(int fd, struct file *filp, int on)
{
return fasync_helper(fd, filp, on, &vsdev.fapp);
}
static irqreturn_t vser_handler(int irq, void *dev_id)
{
char data;
get_random_bytes(&data, sizeof(data));
data %= 26;
data += 'A';
if (!kfifo_is_full(&vsfifo))
if(!kfifo_in(&vsfifo, &data, sizeof(data)))
printk(KERN_ERR "vser: kfifo_in failure\n");
if (!kfifo_is_empty(&vsfifo)) {
wake_up_interruptible(&vsdev.rwqh);
kill_fasync(&vsdev.fapp, SIGIO, POLL_IN);
}
return IRQ_HANDLED;
}
static struct file_operations vser_ops = {
.owner = THIS_MODULE,
.open = vser_open,
.release = vser_release,
.read = vser_read,
.write = vser_write,
.unlocked_ioctl = vser_ioctl,
.poll = vser_poll,
.aio_read = vser_aio_read,
.aio_write = vser_aio_write,
.fasync = vser_fasync,
};
static int __init vser_init(void)
{
int ret;
dev_t dev;
dev = MKDEV(VSER_MAJOR, VSER_MINOR);
ret = register_chrdev_region(dev, VSER_DEV_CNT, VSER_DEV_NAME);
if (ret)
goto reg_err;
cdev_init(&vsdev.cdev, &vser_ops);
vsdev.cdev.owner = THIS_MODULE;
vsdev.baud = 115200;
vsdev.opt.datab = 8;
vsdev.opt.parity = 0;
vsdev.opt.stopb = 1;
ret = cdev_add(&vsdev.cdev, dev, VSER_DEV_CNT);
if (ret)
goto add_err;
init_waitqueue_head(&vsdev.rwqh);
init_waitqueue_head(&vsdev.wwqh);
ret = request_irq(167, vser_handler, IRQF_TRIGGER_HIGH | IRQF_SHARED, "vser", &vsdev);
if (ret)
goto irq_err;
return 0;
irq_err:
cdev_del(&vsdev.cdev);
add_err:
unregister_chrdev_region(dev, VSER_DEV_CNT);
reg_err:
return ret;
}
static void __exit vser_exit(void)
{
dev_t dev;
dev = MKDEV(VSER_MAJOR, VSER_MINOR);
free_irq(167, &vsdev);
cdev_del(&vsdev.cdev);
unregister_chrdev_region(dev, VSER_DEV_CNT);
}
module_init(vser_init);
module_exit(vser_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("name <e-mail>");
MODULE_DESCRIPTION("A simple character device driver");
MODULE_ALIAS("virtual-serial");
程序的IRQ号需要对应修改
代码第235行使用requcst_irq 注册了中断处理函数 vser_handler，因为是共享中断,并且是高电平触发，所以flags 参数设置为IRQF_TRIGGER_HIGH | IRQF_SHARED，而且共享中断必须设置最后一个参数，通常该参数传递代表设备的结构对象指针即可，本例中传送的实参为&vsdev。
代码第255行表示在模块卸载时需要注销中断，分别传递了中断号和&vsdev。
代码第 179 行至第 196 行是中断处理函数的实现。代码第 183 行至第 188 行产生了一个随机的大写英文字符并写入到 FIFO 中，用到了两个新的函数 get_random_bytes 和 kfifo_in，由于函数简单，通过代码就可以知道使用的方法，所以在这里不再详细讲解。
代码第 190 行至第193 行分别是阻塞进程的唤醒和信号发送操作。代码 195 行返回IRQ_HANDLED，表示中断处理正常。
需要说明的是，对于共享中断的中断处理函数应该获取硬件的中断标志来判断该中断是否是本设备所产生的，如果不是则不应该进行相应的中断处理，并返回IRQ_NONE由于例子中是一个虚拟设备，没有相关的标志，所以没有做相关的处理。
最后，中断处理函数应该快速完成，不能消耗太长的时间。因为在 ARM 处理器进入中断后，相应的中断被屏 (IRQ中断禁止IRQ中断，FIQ 中断禁止IRQ中断和FIQ中断，内核没有使用FIQ 中断)，在之后的代码中又没有重新开启中断。所以在整个中断处理过程中中断是禁止的，如果中断处理函数执行时间过长，那么其他的中断将会被挂起，从而将会对其他中断的响应造成严重的影响。必须记住的一条准则是，在中断处理函数中一定不能调用调度器，即一定不能调用可能会引起进程切换的函数(因为一旦中断处理程序被切换，将不能再次被调度)，这是内核对中断处理函数的一个严格限制。到目前为止，我们学过的可能会引起进程切换的函数有 kfifo_to_user、kfifo_from_user、copy_from_user、copy_to_user、wait_event_xxx。后面遇到此类函数会再次指出。另外在中断处理函数中如果调用disable_irq 可能会死锁。
驱动的编译和测试命今如下。
make ARCH=arm
./lazy
中断下半部
在上一节的最后我们提到，中断处理函数应该尽快完成，否则将会影响对其他中断的及时响应，从而影响整个系统的性能。但有时候这些耗时的操作可能又避免不了，以网卡为例，当网卡收到数据后会产生一个中断，在中断处理程序中需要将网卡收到的数据从网卡的缓存中复制出来，然后对数据包做严格的检查(是否有帧格式错误，是否有校验和错误等)，检查完成后再根据协议对数据包进行拆包处理，最后将拆包后的数据包递交给上层。如果在这个过程中网卡又收到新的数据，从而再次产生中断，因为上一个中断正在处理的过程中，所以新的中断将会被挂起，新收到的数据就得不到及时处理。因为网卡的缓冲区大小有限，如果后面有更多的数据包到来，那么缓冲区最终会溢出,从而产生丢包。为了解决这个问题，Linux 将中断分成了两部分:上半部和下半部(顶半部和底半部)，上半部完成紧急但能很快完成的事情，下半部完成不紧急但比较耗时的操作。对于网卡来说，将数据从网卡的缓存复制到内存中就是紧急但可以快速完成的事，需要放在上半部执行。而对包进行校验和拆包则是不紧急但比较耗时的操作，可以放在下半部执行。下半部在执行的过程中，中断被重新使能，所以如果有新的硬件中断产生，将会停止执行下半部的程序，转为执行硬件中断的上半部。
软中断
下半部虽然可以推迟执行，但是我们还是希望它能尽快执行。那么什么时候可以试执行下半部呢?肯定是在上半部执行完成之后。为了能更直观地了解这个过程，现在将这部分代码再次摘录如下。
/* arch/arm/kernel/irq.c*/
/*
* linux/arch/arm/kernel/irq.c
*
* Copyright (C) 1992 Linus Torvalds
* Modifications for ARM processor Copyright (C) 1995-2000 Russell King.
*
* Support for Dynamic Tick Timer Copyright (C) 2004-2005 Nokia Corporation.
* Dynamic Tick Timer written by Tony Lindgren <tony@atomide.com> and
* Tuukka Tikkanen <tuukka.tikkanen@elektrobit.com>.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
* This file contains the code used by various IRQ handling routines:
* asking for different IRQ's should be done through these routines
* instead of just grabbing them. Thus setups with different IRQ numbers
* shouldn't result in any weird surprises, and installing new handlers
* should be easier.
*
* IRQ's are in fact implemented a bit like signal handlers for the kernel.
* Naturally it's not a 1:1 relation, but there are similarities.
*/
#include <linux/kernel_stat.h>
#include <linux/signal.h>
#include <linux/ioport.h>
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/irqchip.h>
#include <linux/random.h>
#include <linux/smp.h>
#include <linux/init.h>
#include <linux/seq_file.h>
#include <linux/errno.h>
#include <linux/list.h>
#include <linux/kallsyms.h>
#include <linux/proc_fs.h>
#include <linux/export.h>
#include <asm/exception.h>
#include <asm/mach/arch.h>
#include <asm/mach/irq.h>
#include <asm/mach/time.h>
unsigned long irq_err_count;
int arch_show_interrupts(struct seq_file *p, int prec)
{
#ifdef CONFIG_FIQ
show_fiq_list(p, prec);
#endif
#ifdef CONFIG_SMP
show_ipi_list(p, prec);
#endif
seq_printf(p, "%*s: %10lu\n", prec, "Err", irq_err_count);
return 0;
}
/*
* handle_IRQ handles all hardware IRQ's. Decoded IRQs should
* not come via this function. Instead, they should provide their
* own 'handler'. Used by platform code implementing C-based 1st
* level decoding.
*/
void handle_IRQ(unsigned int irq, struct pt_regs *regs)
{
struct pt_regs *old_regs = set_irq_regs(regs);
irq_enter();
/*
* Some hardware gives randomly wrong interrupts. Rather
* than crashing, do something sensible.
*/
if (unlikely(irq >= nr_irqs)) {
if (printk_ratelimit())
printk(KERN_WARNING "Bad IRQ%u\n", irq);
ack_bad_irq(irq);
} else {
generic_handle_irq(irq);
}
irq_exit();
set_irq_regs(old_regs);
}
/*
* asm_do_IRQ is the interface to be used from assembly code.
*/
asmlinkage void __exception_irq_entry
asm_do_IRQ(unsigned int irq, struct pt_regs *regs)
{
handle_IRQ(irq, regs);
}
void set_irq_flags(unsigned int irq, unsigned int iflags)
{
unsigned long clr = 0, set = IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN;
if (irq >= nr_irqs) {
printk(KERN_ERR "Trying to set irq flags for IRQ%d\n", irq);
return;
}
if (iflags & IRQF_VALID)
clr |= IRQ_NOREQUEST;
if (iflags & IRQF_PROBE)
clr |= IRQ_NOPROBE;
if (!(iflags & IRQF_NOAUTOEN))
clr |= IRQ_NOAUTOEN;
/* Order is clear bits in "clr" then set bits in "set" */
irq_modify_status(irq, clr, set & ~clr);
}
EXPORT_SYMBOL_GPL(set_irq_flags);
void __init init_IRQ(void)
{
if (IS_ENABLED(CONFIG_OF) && !machine_desc->init_irq)
irqchip_init();
else
machine_desc->init_irq();
}
#ifdef CONFIG_MULTI_IRQ_HANDLER
void __init set_handle_irq(void (*handle_irq)(struct pt_regs *))
{
if (handle_arch_irq)
return;
handle_arch_irq = handle_irq;
}
#endif
#ifdef CONFIG_SPARSE_IRQ
int __init arch_probe_nr_irqs(void)
{
nr_irqs = machine_desc->nr_irqs ? machine_desc->nr_irqs : NR_IRQS;
return nr_irqs;
}
#endif
#ifdef CONFIG_HOTPLUG_CPU
static bool migrate_one_irq(struct irq_desc *desc)
{
struct irq_data *d = irq_desc_get_irq_data(desc);
const struct cpumask *affinity = d->affinity;
struct irq_chip *c;
bool ret = false;
/*
* If this is a per-CPU interrupt, or the affinity does not
* include this CPU, then we have nothing to do.
*/
if (irqd_is_per_cpu(d) || !cpumask_test_cpu(smp_processor_id(), affinity))
return false;
if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
affinity = cpu_online_mask;
ret = true;
}
c = irq_data_get_irq_chip(d);
if (!c->irq_set_affinity)
pr_debug("IRQ%u: unable to set affinity\n", d->irq);
else if (c->irq_set_affinity(d, affinity, true) == IRQ_SET_MASK_OK && ret)
cpumask_copy(d->affinity, affinity);
return ret;
}
/*
* The current CPU has been marked offline. Migrate IRQs off this CPU.
* If the affinity settings do not allow other CPUs, force them onto any
* available CPU.
*
* Note: we must iterate over all IRQs, whether they have an attached
* action structure or not, as we need to get chained interrupts too.
*/
void migrate_irqs(void)
{
unsigned int i;
struct irq_desc *desc;
unsigned long flags;
local_irq_save(flags);
for_each_irq_desc(i, desc) {
bool affinity_broken;
raw_spin_lock(&desc->lock);
affinity_broken = migrate_one_irq(desc);
raw_spin_unlock(&desc->lock);
if (affinity_broken && printk_ratelimit())
pr_warning("IRQ%u no longer affine to CPU%u\n", i,
smp_processor_id());
}
local_irq_restore(flags);
}
#endif /* CONFIG_HOTPLUG_CPU */
在前面的分析中我们知道，中断处理的过程中会调用上面列出的 handle_IRQ函数该函数首先调用 irqenter 函数将被中断进程中的抢占计数器 preempt_count 加上了HARDIRQ_OFFSET 这个值(主要是为了防止内核抢占，以及作为是否在硬件中断中的一个判断条件)。当中断的上半部处理完,即generic_handle_irq函数返回后,又调用了irq_exit函数，代码如下。
/* arch/arm/kernel/irq.c */
见上面源码。
在这个函数中又将 preempt_count减去了 HARDIRQ_OFFSET这个值，如果没有发生中断嵌套，那么preempt_count 中关于硬件中断的计数值就为0,表示上半部已经执行完接下来代码第387行调用in_interrupt和local_softirq_pending函数来分别判断是否可以执行中断下半部，以及是否有中断下半部等待执行 (in_interrupt 函数主要是检测preempt_count 中相关域的值，如果为0表示具备执行中断下半部的条件)。如果条件满足就调用invoke_softirq 来立即执行中断下半部。由此可知，中断下半部的最早执行时间是中断上半部执行完成之后，但是中断还没有完全返回之前的时候。在 FS4412 目标板对应的3.14.25版本的内核源码配置中，invoke_softirg 函数调用了do_softirq_own_stack函数，该函数又调用了__do_softirq 函数，这是中断下半部的核心处理函数。在了解这个函数之前，我们首先来认识一下 softirq，即软中断。
软中断是中断下半部机制中的一种，描述软中断的结构是struct softirq_action，它的定义非常简单，就是内嵌了一个函数指针。内核共定义了 NR_SOFTIRQS个(目前有 10个)struct softirq_action 对象，这些对象被放在一个名叫 softirq_vec 的数组中，对象在数组中的下标就是这个软中断的编号。内核中有一个全局整型变量来记录是否有相应的软中断需要执行，比如要执行编号为1的软中断，那么就需要把这个全局整型变量的比特1置位。当内核在相应的代码中检测到该比特位置 1，就会用这个比特位的位数去索引softirq_vec 这个数组，然后调用softirq_action 对象中的action 指针所指向的函数。目前内核中定义的软中断的编号如下。
/*include/linux/interrupt.h */
/* interrupt.h */
#ifndef _LINUX_INTERRUPT_H
#define _LINUX_INTERRUPT_H
#include <linux/kernel.h>
#include <linux/linkage.h>
#include <linux/bitops.h>
#include <linux/preempt.h>
#include <linux/cpumask.h>
#include <linux/irqreturn.h>
#include <linux/irqnr.h>
#include <linux/hardirq.h>
#include <linux/irqflags.h>
#include <linux/hrtimer.h>
#include <linux/kref.h>
#include <linux/workqueue.h>
#include <linux/atomic.h>
#include <asm/ptrace.h>
#include <asm/irq.h>
/*
* These correspond to the IORESOURCE_IRQ_* defines in
* linux/ioport.h to select the interrupt line behaviour. When
* requesting an interrupt without specifying a IRQF_TRIGGER, the
* setting should be assumed to be "as already configured", which
* may be as per machine or firmware initialisation.
*/
#define IRQF_TRIGGER_NONE 0x00000000
#define IRQF_TRIGGER_RISING 0x00000001
#define IRQF_TRIGGER_FALLING 0x00000002
#define IRQF_TRIGGER_HIGH 0x00000004
#define IRQF_TRIGGER_LOW 0x00000008
#define IRQF_TRIGGER_MASK (IRQF_TRIGGER_HIGH | IRQF_TRIGGER_LOW | \
IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING)
#define IRQF_TRIGGER_PROBE 0x00000010
/*
* These flags used only by the kernel as part of the
* irq handling routines.
*
* IRQF_DISABLED - keep irqs disabled when calling the action handler.
* DEPRECATED. This flag is a NOOP and scheduled to be removed
* IRQF_SHARED - allow sharing the irq among several devices
* IRQF_PROBE_SHARED - set by callers when they expect sharing mismatches to occur
* IRQF_TIMER - Flag to mark this interrupt as timer interrupt
* IRQF_PERCPU - Interrupt is per cpu
* IRQF_NOBALANCING - Flag to exclude this interrupt from irq balancing
* IRQF_IRQPOLL - Interrupt is used for polling (only the interrupt that is
* registered first in an shared interrupt is considered for
* performance reasons)
* IRQF_ONESHOT - Interrupt is not reenabled after the hardirq handler finished.
* Used by threaded interrupts which need to keep the
* irq line disabled until the threaded handler has been run.
* IRQF_NO_SUSPEND - Do not disable this IRQ during suspend
* IRQF_FORCE_RESUME - Force enable it on resume even if IRQF_NO_SUSPEND is set
* IRQF_NO_THREAD - Interrupt cannot be threaded
* IRQF_EARLY_RESUME - Resume IRQ early during syscore instead of at device
* resume time.
*/
#define IRQF_DISABLED 0x00000020
#define IRQF_SHARED 0x00000080
#define IRQF_PROBE_SHARED 0x00000100
#define __IRQF_TIMER 0x00000200
#define IRQF_PERCPU 0x00000400
#define IRQF_NOBALANCING 0x00000800
#define IRQF_IRQPOLL 0x00001000
#define IRQF_ONESHOT 0x00002000
#define IRQF_NO_SUSPEND 0x00004000
#define IRQF_FORCE_RESUME 0x00008000
#define IRQF_NO_THREAD 0x00010000
#define IRQF_EARLY_RESUME 0x00020000
#define IRQF_TIMER (__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD)
/*
* These values can be returned by request_any_context_irq() and
* describe the context the interrupt will be run in.
*
* IRQC_IS_HARDIRQ - interrupt runs in hardirq context
* IRQC_IS_NESTED - interrupt runs in a nested threaded context
*/
enum {
IRQC_IS_HARDIRQ = 0,
IRQC_IS_NESTED,
};
typedef irqreturn_t (*irq_handler_t)(int, void *);
/**
* struct irqaction - per interrupt action descriptor
* @handler: interrupt handler function
* @name: name of the device
* @dev_id: cookie to identify the device
* @percpu_dev_id: cookie to identify the device
* @next: pointer to the next irqaction for shared interrupts
* @irq: interrupt number
* @flags: flags (see IRQF_* above)
* @thread_fn: interrupt handler function for threaded interrupts
* @thread: thread pointer for threaded interrupts
* @thread_flags: flags related to @thread
* @thread_mask: bitmask for keeping track of @thread activity
* @dir: pointer to the proc/irq/NN/name entry
*/
struct irqaction {
irq_handler_t handler;
void *dev_id;
void __percpu *percpu_dev_id;
struct irqaction *next;
irq_handler_t thread_fn;
struct task_struct *thread;
unsigned int irq;
unsigned int flags;
unsigned long thread_flags;
unsigned long thread_mask;
const char *name;
struct proc_dir_entry *dir;
} ____cacheline_internodealigned_in_smp;
extern irqreturn_t no_action(int cpl, void *dev_id);
extern int __must_check
request_threaded_irq(unsigned int irq, irq_handler_t handler,
irq_handler_t thread_fn,
unsigned long flags, const char *name, void *dev);
static inline int __must_check
request_irq(unsigned int irq, irq_handler_t handler, unsigned long flags,
const char *name, void *dev)
{
return request_threaded_irq(irq, handler, NULL, flags, name, dev);
}
extern int __must_check
request_any_context_irq(unsigned int irq, irq_handler_t handler,
unsigned long flags, const char *name, void *dev_id);
extern int __must_check
request_percpu_irq(unsigned int irq, irq_handler_t handler,
const char *devname, void __percpu *percpu_dev_id);
extern void free_irq(unsigned int, void *);
extern void free_percpu_irq(unsigned int, void __percpu *);
struct device;
extern int __must_check
devm_request_threaded_irq(struct device *dev, unsigned int irq,
irq_handler_t handler, irq_handler_t thread_fn,
unsigned long irqflags, const char *devname,
void *dev_id);
static inline int __must_check
devm_request_irq(struct device *dev, unsigned int irq, irq_handler_t handler,
unsigned long irqflags, const char *devname, void *dev_id)
{
return devm_request_threaded_irq(dev, irq, handler, NULL, irqflags,
devname, dev_id);
}
extern int __must_check
devm_request_any_context_irq(struct device *dev, unsigned int irq,
irq_handler_t handler, unsigned long irqflags,
const char *devname, void *dev_id);
extern void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id);
/*
* On lockdep we dont want to enable hardirqs in hardirq
* context. Use local_irq_enable_in_hardirq() to annotate
* kernel code that has to do this nevertheless (pretty much
* the only valid case is for old/broken hardware that is
* insanely slow).
*
* NOTE: in theory this might break fragile code that relies
* on hardirq delivery - in practice we dont seem to have such
* places left. So the only effect should be slightly increased
* irqs-off latencies.
*/
#ifdef CONFIG_LOCKDEP
# define local_irq_enable_in_hardirq() do { } while (0)
#else
# define local_irq_enable_in_hardirq() local_irq_enable()
#endif
extern void disable_irq_nosync(unsigned int irq);
extern void disable_irq(unsigned int irq);
extern void disable_percpu_irq(unsigned int irq);
extern void enable_irq(unsigned int irq);
extern void enable_percpu_irq(unsigned int irq, unsigned int type);
/* The following three functions are for the core kernel use only. */
extern void suspend_device_irqs(void);
extern void resume_device_irqs(void);
#ifdef CONFIG_PM_SLEEP
extern int check_wakeup_irqs(void);
#else
static inline int check_wakeup_irqs(void) { return 0; }
#endif
#if defined(CONFIG_SMP)
extern cpumask_var_t irq_default_affinity;
extern int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask);
extern int irq_can_set_affinity(unsigned int irq);
extern int irq_select_affinity(unsigned int irq);
extern int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m);
/**
* struct irq_affinity_notify - context for notification of IRQ affinity changes
* @irq: Interrupt to which notification applies
* @kref: Reference count, for internal use
* @work: Work item, for internal use
* @notify: Function to be called on change. This will be
* called in process context.
* @release: Function to be called on release. This will be
* called in process context. Once registered, the
* structure must only be freed when this function is
* called or later.
*/
struct irq_affinity_notify {
unsigned int irq;
struct kref kref;
struct work_struct work;
void (*notify)(struct irq_affinity_notify *, const cpumask_t *mask);
void (*release)(struct kref *ref);
};
extern int
irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify);
#else /* CONFIG_SMP */
static inline int irq_set_affinity(unsigned int irq, const struct cpumask *m)
{
return -EINVAL;
}
static inline int irq_can_set_affinity(unsigned int irq)
{
return 0;
}
static inline int irq_select_affinity(unsigned int irq) { return 0; }
static inline int irq_set_affinity_hint(unsigned int irq,
const struct cpumask *m)
{
return -EINVAL;
}
#endif /* CONFIG_SMP */
/*
* Special lockdep variants of irq disabling/enabling.
* These should be used for locking constructs that
* know that a particular irq context which is disabled,
* and which is the only irq-context user of a lock,
* that it's safe to take the lock in the irq-disabled
* section without disabling hardirqs.
*
* On !CONFIG_LOCKDEP they are equivalent to the normal
* irq disable/enable methods.
*/
static inline void disable_irq_nosync_lockdep(unsigned int irq)
{
disable_irq_nosync(irq);
#ifdef CONFIG_LOCKDEP
local_irq_disable();
#endif
}
static inline void disable_irq_nosync_lockdep_irqsave(unsigned int irq, unsigned long *flags)
{
disable_irq_nosync(irq);
#ifdef CONFIG_LOCKDEP
local_irq_save(*flags);
#endif
}
static inline void disable_irq_lockdep(unsigned int irq)
{
disable_irq(irq);
#ifdef CONFIG_LOCKDEP
local_irq_disable();
#endif
}
static inline void enable_irq_lockdep(unsigned int irq)
{
#ifdef CONFIG_LOCKDEP
local_irq_enable();
#endif
enable_irq(irq);
}
static inline void enable_irq_lockdep_irqrestore(unsigned int irq, unsigned long *flags)
{
#ifdef CONFIG_LOCKDEP
local_irq_restore(*flags);
#endif
enable_irq(irq);
}
/* IRQ wakeup (PM) control: */
extern int irq_set_irq_wake(unsigned int irq, unsigned int on);
static inline int enable_irq_wake(unsigned int irq)
{
return irq_set_irq_wake(irq, 1);
}
static inline int disable_irq_wake(unsigned int irq)
{
return irq_set_irq_wake(irq, 0);
}
#ifdef CONFIG_IRQ_FORCED_THREADING
extern bool force_irqthreads;
#else
#define force_irqthreads (0)
#endif
#ifndef __ARCH_SET_SOFTIRQ_PENDING
#define set_softirq_pending(x) (local_softirq_pending() = (x))
#define or_softirq_pending(x) (local_softirq_pending() |= (x))
#endif
/* Some architectures might implement lazy enabling/disabling of
* interrupts. In some cases, such as stop_machine, we might want
* to ensure that after a local_irq_disable(), interrupts have
* really been disabled in hardware. Such architectures need to
* implement the following hook.
*/
#ifndef hard_irq_disable
#define hard_irq_disable() do { } while(0)
#endif
/* PLEASE, avoid to allocate new softirqs, if you need not _really_ high
frequency threaded job scheduling. For almost all the purposes
tasklets are more than enough. F.e. all serial device BHs et
al. should be converted to tasklets, not to softirqs.
*/
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
};
#define SOFTIRQ_STOP_IDLE_MASK (~(1 << RCU_SOFTIRQ))
/* map softirq index to softirq name. update 'softirq_to_name' in
* kernel/softirq.c when adding a new softirq.
*/
extern const char * const softirq_to_name[NR_SOFTIRQS];
/* 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 *);
};
asmlinkage void do_softirq(void);
asmlinkage void __do_softirq(void);
#ifdef __ARCH_HAS_DO_SOFTIRQ
void do_softirq_own_stack(void);
#else
static inline void do_softirq_own_stack(void)
{
__do_softirq();
}
#endif
extern void open_softirq(int nr, void (*action)(struct softirq_action *));
extern void softirq_init(void);
extern void __raise_softirq_irqoff(unsigned int nr);
extern void raise_softirq_irqoff(unsigned int nr);
extern void raise_softirq(unsigned int nr);
DECLARE_PER_CPU(struct task_struct *, ksoftirqd);
static inline struct task_struct *this_cpu_ksoftirqd(void)
{
return this_cpu_read(ksoftirqd);
}
/* Tasklets --- multithreaded analogue of BHs.
Main feature differing them of generic softirqs: tasklet
is running only on one CPU simultaneously.
Main feature differing them of BHs: different tasklets
may be run simultaneously on different CPUs.
Properties:
* If tasklet_schedule() is called, then tasklet is guaranteed
to be executed on some cpu at least once after this.
* If the tasklet is already scheduled, but its execution is still not
started, it will be executed only once.
* If this tasklet is already running on another CPU (or schedule is called
from tasklet itself), it is rescheduled for later.
* Tasklet is strictly serialized wrt itself, but not
wrt another tasklets. If client needs some intertask synchronization,
he makes it with spinlocks.
*/
struct tasklet_struct
{
struct tasklet_struct *next;
unsigned long state;
atomic_t count;
void (*func)(unsigned long);
unsigned long data;
};
#define DECLARE_TASKLET(name, func, data) \
struct tasklet_struct name = { NULL, 0, ATOMIC_INIT(0), func, data }
#define DECLARE_TASKLET_DISABLED(name, func, data) \
struct tasklet_struct name = { NULL, 0, ATOMIC_INIT(1), func, data }
enum
{
TASKLET_STATE_SCHED, /* Tasklet is scheduled for execution */
TASKLET_STATE_RUN /* Tasklet is running (SMP only) */
};
#ifdef CONFIG_SMP
static inline int tasklet_trylock(struct tasklet_struct *t)
{
return !test_and_set_bit(TASKLET_STATE_RUN, &(t)->state);
}
static inline void tasklet_unlock(struct tasklet_struct *t)
{
smp_mb__before_clear_bit();
clear_bit(TASKLET_STATE_RUN, &(t)->state);
}
static inline void tasklet_unlock_wait(struct tasklet_struct *t)
{
while (test_bit(TASKLET_STATE_RUN, &(t)->state)) { barrier(); }
}
#else
#define tasklet_trylock(t) 1
#define tasklet_unlock_wait(t) do { } while (0)
#define tasklet_unlock(t) do { } while (0)
#endif
extern void __tasklet_schedule(struct tasklet_struct *t);
static inline void tasklet_schedule(struct tasklet_struct *t)
{
if (!test_and_set_bit(TASKLET_STATE_SCHED, &t->state))
__tasklet_schedule(t);
}
extern void __tasklet_hi_schedule(struct tasklet_struct *t);
static inline void tasklet_hi_schedule(struct tasklet_struct *t)
{
if (!test_and_set_bit(TASKLET_STATE_SCHED, &t->state))
__tasklet_hi_schedule(t);
}
extern void __tasklet_hi_schedule_first(struct tasklet_struct *t);
/*
* This version avoids touching any other tasklets. Needed for kmemcheck
* in order not to take any page faults while enqueueing this tasklet;
* consider VERY carefully whether you really need this or
* tasklet_hi_schedule()...
*/
static inline void tasklet_hi_schedule_first(struct tasklet_struct *t)
{
if (!test_and_set_bit(TASKLET_STATE_SCHED, &t->state))
__tasklet_hi_schedule_first(t);
}
static inline void tasklet_disable_nosync(struct tasklet_struct *t)
{
atomic_inc(&t->count);
smp_mb__after_atomic_inc();
}
static inline void tasklet_disable(struct tasklet_struct *t)
{
tasklet_disable_nosync(t);
tasklet_unlock_wait(t);
smp_mb();
}
static inline void tasklet_enable(struct tasklet_struct *t)
{
smp_mb__before_atomic_dec();
atomic_dec(&t->count);
}
static inline void tasklet_hi_enable(struct tasklet_struct *t)
{
smp_mb__before_atomic_dec();
atomic_dec(&t->count);
}
extern void tasklet_kill(struct tasklet_struct *t);
extern void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu);
extern void tasklet_init(struct tasklet_struct *t,
void (*func)(unsigned long), unsigned long data);
struct tasklet_hrtimer {
struct hrtimer timer;
struct tasklet_struct tasklet;
enum hrtimer_restart (*function)(struct hrtimer *);
};
extern void
tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer,
enum hrtimer_restart (*function)(struct hrtimer *),
clockid_t which_clock, enum hrtimer_mode mode);
static inline
int tasklet_hrtimer_start(struct tasklet_hrtimer *ttimer, ktime_t time,
const enum hrtimer_mode mode)
{
return hrtimer_start(&ttimer->timer, time, mode);
}
static inline
void tasklet_hrtimer_cancel(struct tasklet_hrtimer *ttimer)
{
hrtimer_cancel(&ttimer->timer);
tasklet_kill(&ttimer->tasklet);
}
/*
* Autoprobing for irqs:
*
* probe_irq_on() and probe_irq_off() provide robust primitives
* for accurate IRQ probing during kernel initialization. They are
* reasonably simple to use, are not "fooled" by spurious interrupts,
* and, unlike other attempts at IRQ probing, they do not get hung on
* stuck interrupts (such as unused PS2 mouse interfaces on ASUS boards).
*
* For reasonably foolproof probing, use them as follows:
*
* 1. clear and/or mask the device's internal interrupt.
* 2. sti();
* 3. irqs = probe_irq_on(); // "take over" all unassigned idle IRQs
* 4. enable the device and cause it to trigger an interrupt.
* 5. wait for the device to interrupt, using non-intrusive polling or a delay.
* 6. irq = probe_irq_off(irqs); // get IRQ number, 0=none, negative=multiple
* 7. service the device to clear its pending interrupt.
* 8. loop again if paranoia is required.
*
* probe_irq_on() returns a mask of allocated irq's.
*
* probe_irq_off() takes the mask as a parameter,
* and returns the irq number which occurred,
* or zero if none occurred, or a negative irq number
* if more than one irq occurred.
*/
#if !defined(CONFIG_GENERIC_IRQ_PROBE)
static inline unsigned long probe_irq_on(void)
{
return 0;
}
static inline int probe_irq_off(unsigned long val)
{
return 0;
}
static inline unsigned int probe_irq_mask(unsigned long val)
{
return 0;
}
#else
extern unsigned long probe_irq_on(void); /* returns 0 on failure */
extern int probe_irq_off(unsigned long); /* returns 0 or negative on failure */
extern unsigned int probe_irq_mask(unsigned long); /* returns mask of ISA interrupts */
#endif
#ifdef CONFIG_PROC_FS
/* Initialize /proc/irq/ */
extern void init_irq_proc(void);
#else
static inline void init_irq_proc(void)
{
}
#endif
struct seq_file;
int show_interrupts(struct seq_file *p, void *v);
int arch_show_interrupts(struct seq_file *p, int prec);
extern int early_irq_init(void);
extern int arch_probe_nr_irqs(void);
extern int arch_early_irq_init(void);
#endif
比如，NET_RX_SOFTIRQ 就代表网卡接收中断所对应的软中断编号，而这个编号所对应的软中断处理函数就是 net_rx_action。
接下来就来看看 __do_softirq 的实现，代码如下。
/* kernel/softirq.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)
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#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>
/*
- 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);
const char * const 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
void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
{
unsigned long flags;
WARN_ON_ONCE(in_irq());
raw_local_irq_save(flags);
/*
* The preempt tracer hooks into preempt_count_add 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_add(cnt);
/*
* Were softirqs turned off above:
*/
if (softirq_count() == (cnt & SOFTIRQ_MASK))
trace_softirqs_off(ip);
raw_local_irq_restore(flags);
if (preempt_count() == cnt)
trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
}
EXPORT_SYMBOL(__local_bh_disable_ip);
#endif /* CONFIG_TRACE_IRQFLAGS */
static void __local_bh_enable(unsigned int cnt)
{
WARN_ON_ONCE(!irqs_disabled());
if (softirq_count() == (cnt & SOFTIRQ_MASK))
trace_softirqs_on(_RET_IP_);
preempt_count_sub(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)
{
WARN_ON_ONCE(in_irq());
__local_bh_enable(SOFTIRQ_DISABLE_OFFSET);
}
EXPORT_SYMBOL(_local_bh_enable);
void __local_bh_enable_ip(unsigned long ip, unsigned int cnt)
{
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:
*/
preempt_count_sub(cnt - 1);
if (unlikely(!in_interrupt() && local_softirq_pending())) {
/*
* Run softirq if any pending. And do it in its own stack
* as we may be calling this deep in a task call stack already.
*/
do_softirq();
}
preempt_count_dec();
#ifdef CONFIG_TRACE_IRQFLAGS
local_irq_enable();
#endif
preempt_check_resched();
}
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
#ifdef CONFIG_TRACE_IRQFLAGS
/*
* When we run softirqs from irq_exit() and thus on the hardirq stack we need
* to keep the lockdep irq context tracking as tight as possible in order to
* not miss-qualify lock contexts and miss possible deadlocks.
*/
static inline bool lockdep_softirq_start(void)
{
bool in_hardirq = false;
if (trace_hardirq_context(current)) {
in_hardirq = true;
trace_hardirq_exit();
}
lockdep_softirq_enter();
return in_hardirq;
}
static inline void lockdep_softirq_end(bool in_hardirq)
{
lockdep_softirq_exit();
if (in_hardirq)
trace_hardirq_enter();
}
#else
static inline bool lockdep_softirq_start(void) { return false; }
static inline void lockdep_softirq_end(bool in_hardirq) { }
#endif
asmlinkage void __do_softirq(void)
{
unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
unsigned long old_flags = current->flags;
int max_restart = MAX_SOFTIRQ_RESTART;
struct softirq_action *h;
bool in_hardirq;
__u32 pending;
int softirq_bit;
int cpu;
/*
* 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_ip(_RET_IP_, SOFTIRQ_OFFSET);
in_hardirq = lockdep_softirq_start();
cpu = smp_processor_id();
restart:
/* Reset the pending bitmask before enabling irqs */
set_softirq_pending(0);
local_irq_enable();
h = softirq_vec;
while ((softirq_bit = ffs(pending))) {
unsigned int vec_nr;
int prev_count;
h += softirq_bit - 1;
vec_nr = h - softirq_vec;
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())) {
pr_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_set(prev_count);
}
rcu_bh_qs(cpu);
h++;
pending >>= softirq_bit;
}
local_irq_disable();
pending = local_softirq_pending();
if (pending) {
if (time_before(jiffies, end) && !need_resched() &&
--max_restart)
goto restart;
wakeup_softirqd();
}
lockdep_softirq_end(in_hardirq);
account_irq_exit_time(current);
__local_bh_enable(SOFTIRQ_OFFSET);
WARN_ON_ONCE(in_interrupt());
tsk_restore_flags(current, old_flags, PF_MEMALLOC);
}
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_own_stack();
local_irq_restore(flags);
}
/*
* Enter an interrupt context.
*/
void irq_enter(void)
{
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_irq_enter();
_local_bh_enable();
}
__irq_enter();
}
static inline void invoke_softirq(void)
{
if (!force_irqthreads) {
#ifdef CONFIG_HAVE_IRQ_EXIT_ON_IRQ_STACK
/*
* We can safely execute softirq on the current stack if
* it is the irq stack, because it should be near empty
* at this stage.
*/
__do_softirq();
#else
/*
* Otherwise, irq_exit() is called on the task stack that can
* be potentially deep already. So call softirq in its own stack
* to prevent from any overrun.
*/
do_softirq_own_stack();
#endif
} 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);
preempt_count_sub(HARDIRQ_OFFSET);
if (!in_interrupt() && local_softirq_pending())
invoke_softirq();
tick_irq_exit();
rcu_irq_exit();
trace_hardirq_exit(); /* must be last! */
}
/*
* 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())
pr_notice("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);
void __init softirq_init(void)
{
int cpu;
for_each_possible_cpu(cpu) {
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;
}
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()) {
/*
* We can safely run softirq on inline stack, as we are not deep
* in the task stack here.
*/
__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 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 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;
}
int __init __weak arch_probe_nr_irqs(void)
{
return NR_IRQS_LEGACY;
}
int __init __weak arch_early_irq_init(void)
{
return 0;
}
从上面的代码可以清楚地看到, __do_softirq 首先用 local_softirq_pending 来获取记所有挂起的软中断的全局整型变量的值，然后调用 local_irq_enable 重新使能了中断(就意味着软中断在执行过程中是可以响应新的硬件中断的)，接下来将 softirq_vec 数组元素的地址赋值给h,在while循环中,遍历被设置了的位,并索引得到对应的softirq_action对象，再调用该对象的action 成员所指向的函数。
虽然软中断可以实现中断的下半部，但是软中断基本上是内核开发者预定义好的通常用在对性能要求特别高的场合，而且需要一些内核的编程技巧，不太适合于驱动开发者。上面介绍的内容更多的是让读者清楚中断的下半部是怎样执行的，并且重点指出了在中断下半部执行的过程中，中断被重新使能了，所以可以响应新的硬件中断。还需要说明的是，除了在中断返回前执行软中断，内核还为每个 CPU创建了一个软中断内核线程，当需要在中断处理函数之外执行软中断时，可以唤醒该内核线程，该线程最终也会调用上面的__do_softirg函数
最后需要注意的是，软中断也处于中断上下文中，因此对中断处理函数的限制同样适用于软中断，只是没有时间上的严格限定。
tasklet
虽然软中断通常是由内核开发者来设计的，但是内核开发者专门保留了一个软中断给驱动开发者，它就是 TASKLET_SOFTIRQ，相应的软中断处理函数是 tasklet_action,下面是相关的代码。
/* kernel/softirq.c*/
程序见上面源码
在软中断的处理过程中，如果 TASKLET_SOFTIRQ对应的比特位被设置了，则根据前面的分析，tasklet_action 函数将会被调用。在代码第487 行，首先得到了本 CPU 的一个struct tasklet_struct 对象的链表，然后遍历该链表，调用其中 func 成员所指向的函数并将data成员作为参数传递过去。struct tasklet_struct 的类型定义如下。
/*include/linux/interrupt.h */
见上面源码
其中，next是构成链表的指针，state 是该tasklet 被调度的状态(已经被调度还是已经在执行)，count 用于禁止 tasklet 执行(非0时)，func 是 tasklet 的下半部函数，data是传递给下半部函数的参数。从上面可知，驱动开发者要实现 tasklet 的下半部，就要构造个struct tasklet_struct 结构对象，并初始化里面的成员，然后放入对应CPU 的 tasklet链表中，最后设置软中断号TASKLET_SOFTIRQ所对应的比特位。不过内核已经有封装好的宏和函数，大大地简化了这一操作。下面列出这些常用的宏和函数。
/*include/linux/interrupt.h */
见上面源码
其中，DECLARE_TASKLET 静态定义一个 struct tasklet_struct 结构对象，名字为name，下半部函数为 func，传递的参数为 data，该 tasklet 可以被执行。而DECLARE_TASKLET_DISABLED和 DECLARE_TASKLET相似,只是 count 成员的值被初始化为1,不能被执行，需要调用 tasklet_enable 来使能。tasklet_init 通常用于初始化一个动态分配的 struct tasklet_struct 结构对象。tasklet_schedule 将指定的 struct tasklet_struct 结构对象加入到对应CPU的 tasklet 链表中，下半部函数将会在未来的某个时间被调度。
添加了 tasklet 下半部的虚拟串口驱动的相关驱动代码如下
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/fs.h>
#include <linux/cdev.h>
#include <linux/kfifo.h>
#include <linux/ioctl.h>
#include <linux/uaccess.h>
#include <linux/wait.h>
#include <linux/sched.h>
#include <linux/poll.h>
#include <linux/aio.h>
#include <linux/interrupt.h>
#include <linux/random.h>
#include "vser.h"
#define VSER_MAJOR 256
#define VSER_MINOR 0
#define VSER_DEV_CNT 1
#define VSER_DEV_NAME "vser"
struct vser_dev {
unsigned int baud;
struct option opt;
struct cdev cdev;
wait_queue_head_t rwqh;
wait_queue_head_t wwqh;
struct fasync_struct *fapp;
};
DEFINE_KFIFO(vsfifo, char, 32);
static struct vser_dev vsdev;
static void vser_tsklet(unsigned long arg);
DECLARE_TASKLET(vstsklet, vser_tsklet, (unsigned long)&vsdev);
static int vser_fasync(int fd, struct file *filp, int on);
static int vser_open(struct inode *inode, struct file *filp)
{
return 0;
}
static int vser_release(struct inode *inode, struct file *filp)
{
vser_fasync(-1, filp, 0);
return 0;
}
static ssize_t vser_read(struct file *filp, char __user *buf, size_t count, loff_t *pos)
{
int ret;
unsigned int copied = 0;
if (kfifo_is_empty(&vsfifo)) {
if (filp->f_flags & O_NONBLOCK)
return -EAGAIN;
if (wait_event_interruptible_exclusive(vsdev.rwqh, !kfifo_is_empty(&vsfifo)))
return -ERESTARTSYS;
}
ret = kfifo_to_user(&vsfifo, buf, count, &copied);
if (!kfifo_is_full(&vsfifo)) {
wake_up_interruptible(&vsdev.wwqh);
kill_fasync(&vsdev.fapp, SIGIO, POLL_OUT);
}
return ret == 0 ? copied : ret;
}
static ssize_t vser_write(struct file *filp, const char __user *buf, size_t count, loff_t *pos)
{
int ret;
unsigned int copied = 0;
if (kfifo_is_full(&vsfifo)) {
if (filp->f_flags & O_NONBLOCK)
return -EAGAIN;
if (wait_event_interruptible_exclusive(vsdev.wwqh, !kfifo_is_full(&vsfifo)))
return -ERESTARTSYS;
}
ret = kfifo_from_user(&vsfifo, buf, count, &copied);
if (!kfifo_is_empty(&vsfifo)) {
wake_up_interruptible(&vsdev.rwqh);
kill_fasync(&vsdev.fapp, SIGIO, POLL_IN);
}
return ret == 0 ? copied : ret;
}
static long vser_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
if (_IOC_TYPE(cmd) != VS_MAGIC)
return -ENOTTY;
switch (cmd) {
case VS_SET_BAUD:
vsdev.baud = arg;
break;
case VS_GET_BAUD:
arg = vsdev.baud;
break;
case VS_SET_FFMT:
if (copy_from_user(&vsdev.opt, (struct option __user *)arg, sizeof(struct option)))
return -EFAULT;
break;
case VS_GET_FFMT:
if (copy_to_user((struct option __user *)arg, &vsdev.opt, sizeof(struct option)))
return -EFAULT;
break;
default:
return -ENOTTY;
}
return 0;
}
static unsigned int vser_poll(struct file *filp, struct poll_table_struct *p)
{
int mask = 0;
poll_wait(filp, &vsdev.rwqh, p);
poll_wait(filp, &vsdev.wwqh, p);
if (!kfifo_is_empty(&vsfifo))
mask |= POLLIN | POLLRDNORM;
if (!kfifo_is_full(&vsfifo))
mask |= POLLOUT | POLLWRNORM;
return mask;
}
static ssize_t vser_aio_read(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos)
{
size_t read = 0;
unsigned long i;
ssize_t ret;
for (i = 0; i < nr_segs; i++) {
ret = vser_read(iocb->ki_filp, iov[i].iov_base, iov[i].iov_len, &pos);
if (ret < 0)
break;
read += ret;
}
return read ? read : -EFAULT;
}
static ssize_t vser_aio_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos)
{
size_t written = 0;
unsigned long i;
ssize_t ret;
for (i = 0; i < nr_segs; i++) {
ret = vser_write(iocb->ki_filp, iov[i].iov_base, iov[i].iov_len, &pos);
if (ret < 0)
break;
written += ret;
}
return written ? written : -EFAULT;
}
static int vser_fasync(int fd, struct file *filp, int on)
{
return fasync_helper(fd, filp, on, &vsdev.fapp);
}
static irqreturn_t vser_handler(int irq, void *dev_id)
{
tasklet_schedule(&vstsklet);
return IRQ_HANDLED;
}
static void vser_tsklet(unsigned long arg)
{
char data;
get_random_bytes(&data, sizeof(data));
data %= 26;
data += 'A';
if (!kfifo_is_full(&vsfifo))
if(!kfifo_in(&vsfifo, &data, sizeof(data)))
printk(KERN_ERR "vser: kfifo_in failure\n");
if (!kfifo_is_empty(&vsfifo)) {
wake_up_interruptible(&vsdev.rwqh);
kill_fasync(&vsdev.fapp, SIGIO, POLL_IN);
}
}
static struct file_operations vser_ops = {
.owner = THIS_MODULE,
.open = vser_open,
.release = vser_release,
.read = vser_read,
.write = vser_write,
.unlocked_ioctl = vser_ioctl,
.poll = vser_poll,
.aio_read = vser_aio_read,
.aio_write = vser_aio_write,
.fasync = vser_fasync,
};
static int __init vser_init(void)
{
int ret;
dev_t dev;
dev = MKDEV(VSER_MAJOR, VSER_MINOR);
ret = register_chrdev_region(dev, VSER_DEV_CNT, VSER_DEV_NAME);
if (ret)
goto reg_err;
cdev_init(&vsdev.cdev, &vser_ops);
vsdev.cdev.owner = THIS_MODULE;
vsdev.baud = 115200;
vsdev.opt.datab = 8;
vsdev.opt.parity = 0;
vsdev.opt.stopb = 1;
ret = cdev_add(&vsdev.cdev, dev, VSER_DEV_CNT);
if (ret)
goto add_err;
init_waitqueue_head(&vsdev.rwqh);
init_waitqueue_head(&vsdev.wwqh);
ret = request_irq(167, vser_handler, IRQF_TRIGGER_HIGH | IRQF_SHARED, "vser", &vsdev);
if (ret)
goto irq_err;
return 0;
irq_err:
cdev_del(&vsdev.cdev);
add_err:
unregister_chrdev_region(dev, VSER_DEV_CNT);
reg_err:
return ret;
}
static void __exit vser_exit(void)
{
dev_t dev;
dev = MKDEV(VSER_MAJOR, VSER_MINOR);
free_irq(167, &vsdev);
cdev_del(&vsdev.cdev);
unregister_chrdev_region(dev, VSER_DEV_CNT);
}
module_init(vser_init);
module_exit(vser_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("name <email>");
MODULE_DESCRIPTION("A simple character device driver");
MODULE_ALIAS("virtual-serial");
代码第40 行静态定义了一个 struct tasklet_struct 结构对象，名字叫 vstsklet，执行函数是vser_tsklet，传递的参数是&vsdev。代码第183 行直接调度 tasklet，中断的上半部中没有做过多的其他操作，然后就返回了IRQ_HANDLED。代码第 192行到第 203行vser_tsklet函数的实现，它是以前的中断中上半部完成的事情。
最后，对 tasklet 的主要特性进行一些总结。
(1)tasklet 是一个特定的软中断，处于中断的上下文。
(2)tasklet_schedule 函数被调用后，对应的下半部会保证被至少执行一次 (3)如果一个 tasklet 已经被调度，但是还没有被执行，那么新的调度将会被忽略，
工作队列
前面讲解的下半部机制不管是软中断还是 tasklet 都有一个限制，就是在中断上下文中执行不能直接或间接地调用调度器。为了解决这个问题，内核又提供了另一种下半部机制，叫作工作队列。它的实现思想也比较简单，就是内核在启动的时候创建一个或多个(在多核的处理器上)内核工作线程，工作线程取出工作队列中的每一个工作，然后执行，当队列中没有工作时，工作线程休眠。当驱动想要延迟执行某一个工作时，构造一个工作队列节点对象，然后加入到相应的工作队列，并唤醒工作线程，工作线程又取出队列上的节点来完成工作，所有工作完成后又休眠。因为是运行在进程上下文中，所以工作可以调用调度器。工作队列提供了一种延迟执行的机制，很显然这种机制也适用于中断的下半部。另外，除了内核本身的工作队列之外，驱动开发者也可以使用内核的基础设施来创建自己的工作队列。下面是工作队列节点的结构类型定义。
/*include/linux/workqueue.h */
/*
* workqueue.h --- work queue handling for Linux.
*/
#ifndef _LINUX_WORKQUEUE_H
#define _LINUX_WORKQUEUE_H
#include <linux/timer.h>
#include <linux/linkage.h>
#include <linux/bitops.h>
#include <linux/lockdep.h>
#include <linux/threads.h>
#include <linux/atomic.h>
#include <linux/cpumask.h>
struct workqueue_struct;
struct work_struct;
typedef void (*work_func_t)(struct work_struct *work);
void delayed_work_timer_fn(unsigned long __data);
/*
* The first word is the work queue pointer and the flags rolled into
* one
*/
#define work_data_bits(work) ((unsigned long *)(&(work)->data))
enum {
WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */
WORK_STRUCT_DELAYED_BIT = 1, /* work item is delayed */
WORK_STRUCT_PWQ_BIT = 2, /* data points to pwq */
WORK_STRUCT_LINKED_BIT = 3, /* next work is linked to this one */
#ifdef CONFIG_DEBUG_OBJECTS_WORK
WORK_STRUCT_STATIC_BIT = 4, /* static initializer (debugobjects) */
WORK_STRUCT_COLOR_SHIFT = 5, /* color for workqueue flushing */
#else
WORK_STRUCT_COLOR_SHIFT = 4, /* color for workqueue flushing */
#endif
WORK_STRUCT_COLOR_BITS = 4,
WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT,
WORK_STRUCT_DELAYED = 1 << WORK_STRUCT_DELAYED_BIT,
WORK_STRUCT_PWQ = 1 << WORK_STRUCT_PWQ_BIT,
WORK_STRUCT_LINKED = 1 << WORK_STRUCT_LINKED_BIT,
#ifdef CONFIG_DEBUG_OBJECTS_WORK
WORK_STRUCT_STATIC = 1 << WORK_STRUCT_STATIC_BIT,
#else
WORK_STRUCT_STATIC = 0,
#endif
/*
* The last color is no color used for works which don't
* participate in workqueue flushing.
*/
WORK_NR_COLORS = (1 << WORK_STRUCT_COLOR_BITS) - 1,
WORK_NO_COLOR = WORK_NR_COLORS,
/* special cpu IDs */
WORK_CPU_UNBOUND = NR_CPUS,
WORK_CPU_END = NR_CPUS + 1,
/*
* Reserve 7 bits off of pwq pointer w/ debugobjects turned off.
* This makes pwqs aligned to 256 bytes and allows 15 workqueue
* flush colors.
*/
WORK_STRUCT_FLAG_BITS = WORK_STRUCT_COLOR_SHIFT +
WORK_STRUCT_COLOR_BITS,
/* data contains off-queue information when !WORK_STRUCT_PWQ */
WORK_OFFQ_FLAG_BASE = WORK_STRUCT_COLOR_SHIFT,
WORK_OFFQ_CANCELING = (1 << WORK_OFFQ_FLAG_BASE),
/*
* When a work item is off queue, its high bits point to the last
* pool it was on. Cap at 31 bits and use the highest number to
* indicate that no pool is associated.
*/
WORK_OFFQ_FLAG_BITS = 1,
WORK_OFFQ_POOL_SHIFT = WORK_OFFQ_FLAG_BASE + WORK_OFFQ_FLAG_BITS,
WORK_OFFQ_LEFT = BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT,
WORK_OFFQ_POOL_BITS = WORK_OFFQ_LEFT <= 31 ? WORK_OFFQ_LEFT : 31,
WORK_OFFQ_POOL_NONE = (1LU << WORK_OFFQ_POOL_BITS) - 1,
/* convenience constants */
WORK_STRUCT_FLAG_MASK = (1UL << WORK_STRUCT_FLAG_BITS) - 1,
WORK_STRUCT_WQ_DATA_MASK = ~WORK_STRUCT_FLAG_MASK,
WORK_STRUCT_NO_POOL = (unsigned long)WORK_OFFQ_POOL_NONE << WORK_OFFQ_POOL_SHIFT,
/* bit mask for work_busy() return values */
WORK_BUSY_PENDING = 1 << 0,
WORK_BUSY_RUNNING = 1 << 1,
/* maximum string length for set_worker_desc() */
WORKER_DESC_LEN = 24,
};
struct work_struct {
atomic_long_t data;
struct list_head entry;
work_func_t func;
#ifdef CONFIG_LOCKDEP
struct lockdep_map lockdep_map;
#endif
};
#define WORK_DATA_INIT() ATOMIC_LONG_INIT(WORK_STRUCT_NO_POOL)
#define WORK_DATA_STATIC_INIT() \
ATOMIC_LONG_INIT(WORK_STRUCT_NO_POOL | WORK_STRUCT_STATIC)
struct delayed_work {
struct work_struct work;
struct timer_list timer;
/* target workqueue and CPU ->timer uses to queue ->work */
struct workqueue_struct *wq;
int cpu;
};
/*
* A struct for workqueue attributes. This can be used to change
* attributes of an unbound workqueue.
*
* Unlike other fields, ->no_numa isn't a property of a worker_pool. It
* only modifies how apply_workqueue_attrs() select pools and thus doesn't
* participate in pool hash calculations or equality comparisons.
*/
struct workqueue_attrs {
int nice; /* nice level */
cpumask_var_t cpumask; /* allowed CPUs */
bool no_numa; /* disable NUMA affinity */
};
static inline struct delayed_work *to_delayed_work(struct work_struct *work)
{
return container_of(work, struct delayed_work, work);
}
struct execute_work {
struct work_struct work;
};
#ifdef CONFIG_LOCKDEP
/*
* NB: because we have to copy the lockdep_map, setting _key
* here is required, otherwise it could get initialised to the
* copy of the lockdep_map!
*/
#define __WORK_INIT_LOCKDEP_MAP(n, k) \
.lockdep_map = STATIC_LOCKDEP_MAP_INIT(n, k),
#else
#define __WORK_INIT_LOCKDEP_MAP(n, k)
#endif
#define __WORK_INITIALIZER(n, f) { \
.data = WORK_DATA_STATIC_INIT(), \
.entry = { &(n).entry, &(n).entry }, \
.func = (f), \
__WORK_INIT_LOCKDEP_MAP(#n, &(n)) \
}
#define __DELAYED_WORK_INITIALIZER(n, f, tflags) { \
.work = __WORK_INITIALIZER((n).work, (f)), \
.timer = __TIMER_INITIALIZER(delayed_work_timer_fn, \
0, (unsigned long)&(n), \
(tflags) | TIMER_IRQSAFE), \
}
#define DECLARE_WORK(n, f) \
struct work_struct n = __WORK_INITIALIZER(n, f)
#define DECLARE_DELAYED_WORK(n, f) \
struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f, 0)
#define DECLARE_DEFERRABLE_WORK(n, f) \
struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f, TIMER_DEFERRABLE)
/*
* initialize a work item's function pointer
*/
#define PREPARE_WORK(_work, _func) \
do { \
(_work)->func = (_func); \
} while (0)
#define PREPARE_DELAYED_WORK(_work, _func) \
PREPARE_WORK(&(_work)->work, (_func))
#ifdef CONFIG_DEBUG_OBJECTS_WORK
extern void __init_work(struct work_struct *work, int onstack);
extern void destroy_work_on_stack(struct work_struct *work);
static inline unsigned int work_static(struct work_struct *work)
{
return *work_data_bits(work) & WORK_STRUCT_STATIC;
}
#else
static inline void __init_work(struct work_struct *work, int onstack) { }
static inline void destroy_work_on_stack(struct work_struct *work) { }
static inline unsigned int work_static(struct work_struct *work) { return 0; }
#endif
/*
* initialize all of a work item in one go
*
* NOTE! No point in using "atomic_long_set()": using a direct
* assignment of the work data initializer allows the compiler
* to generate better code.
*/
#ifdef CONFIG_LOCKDEP
#define __INIT_WORK(_work, _func, _onstack) \
do { \
static struct lock_class_key __key; \
\
__init_work((_work), _onstack); \
(_work)->data = (atomic_long_t) WORK_DATA_INIT(); \
lockdep_init_map(&(_work)->lockdep_map, #_work, &__key, 0); \
INIT_LIST_HEAD(&(_work)->entry); \
PREPARE_WORK((_work), (_func)); \
} while (0)
#else
#define __INIT_WORK(_work, _func, _onstack) \
do { \
__init_work((_work), _onstack); \
(_work)->data = (atomic_long_t) WORK_DATA_INIT(); \
INIT_LIST_HEAD(&(_work)->entry); \
PREPARE_WORK((_work), (_func)); \
} while (0)
#endif
#define INIT_WORK(_work, _func) \
do { \
__INIT_WORK((_work), (_func), 0); \
} while (0)
#define INIT_WORK_ONSTACK(_work, _func) \
do { \
__INIT_WORK((_work), (_func), 1); \
} while (0)
#define __INIT_DELAYED_WORK(_work, _func, _tflags) \
do { \
INIT_WORK(&(_work)->work, (_func)); \
__setup_timer(&(_work)->timer, delayed_work_timer_fn, \
(unsigned long)(_work), \
(_tflags) | TIMER_IRQSAFE); \
} while (0)
#define __INIT_DELAYED_WORK_ONSTACK(_work, _func, _tflags) \
do { \
INIT_WORK_ONSTACK(&(_work)->work, (_func)); \
__setup_timer_on_stack(&(_work)->timer, \
delayed_work_timer_fn, \
(unsigned long)(_work), \
(_tflags) | TIMER_IRQSAFE); \
} while (0)
#define INIT_DELAYED_WORK(_work, _func) \
__INIT_DELAYED_WORK(_work, _func, 0)
#define INIT_DELAYED_WORK_ONSTACK(_work, _func) \
__INIT_DELAYED_WORK_ONSTACK(_work, _func, 0)
#define INIT_DEFERRABLE_WORK(_work, _func) \
__INIT_DELAYED_WORK(_work, _func, TIMER_DEFERRABLE)
#define INIT_DEFERRABLE_WORK_ONSTACK(_work, _func) \
__INIT_DELAYED_WORK_ONSTACK(_work, _func, TIMER_DEFERRABLE)
/**
* work_pending - Find out whether a work item is currently pending
* @work: The work item in question
*/
#define work_pending(work) \
test_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))
/**
* delayed_work_pending - Find out whether a delayable work item is currently
* pending
* @work: The work item in question
*/
#define delayed_work_pending(w) \
work_pending(&(w)->work)
/**
* work_clear_pending - for internal use only, mark a work item as not pending
* @work: The work item in question
*/
#define work_clear_pending(work) \
clear_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))
/*
* Workqueue flags and constants. For details, please refer to
* Documentation/workqueue.txt.
*/
enum {
/*
* All wqs are now non-reentrant making the following flag
* meaningless. Will be removed.
*/
WQ_NON_REENTRANT = 1 << 0, /* DEPRECATED */
WQ_UNBOUND = 1 << 1, /* not bound to any cpu */
WQ_FREEZABLE = 1 << 2, /* freeze during suspend */
WQ_MEM_RECLAIM = 1 << 3, /* may be used for memory reclaim */
WQ_HIGHPRI = 1 << 4, /* high priority */
WQ_CPU_INTENSIVE = 1 << 5, /* cpu instensive workqueue */
WQ_SYSFS = 1 << 6, /* visible in sysfs, see wq_sysfs_register() */
/*
* Per-cpu workqueues are generally preferred because they tend to
* show better performance thanks to cache locality. Per-cpu
* workqueues exclude the scheduler from choosing the CPU to
* execute the worker threads, which has an unfortunate side effect
* of increasing power consumption.
*
* The scheduler considers a CPU idle if it doesn't have any task
* to execute and tries to keep idle cores idle to conserve power;
* however, for example, a per-cpu work item scheduled from an
* interrupt handler on an idle CPU will force the scheduler to
* excute the work item on that CPU breaking the idleness, which in
* turn may lead to more scheduling choices which are sub-optimal
* in terms of power consumption.
*
* Workqueues marked with WQ_POWER_EFFICIENT are per-cpu by default
* but become unbound if workqueue.power_efficient kernel param is
* specified. Per-cpu workqueues which are identified to
* contribute significantly to power-consumption are identified and
* marked with this flag and enabling the power_efficient mode
* leads to noticeable power saving at the cost of small
* performance disadvantage.
*
* http://thread.gmane.org/gmane.linux.kernel/1480396
*/
WQ_POWER_EFFICIENT = 1 << 7,
__WQ_DRAINING = 1 << 16, /* internal: workqueue is draining */
__WQ_ORDERED = 1 << 17, /* internal: workqueue is ordered */
WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */
WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */
WQ_DFL_ACTIVE = WQ_MAX_ACTIVE / 2,
};
/* unbound wq's aren't per-cpu, scale max_active according to #cpus */
#define WQ_UNBOUND_MAX_ACTIVE \
max_t(int, WQ_MAX_ACTIVE, num_possible_cpus() * WQ_MAX_UNBOUND_PER_CPU)
/*
* System-wide workqueues which are always present.
*
* system_wq is the one used by schedule[_delayed]_work[_on]().
* Multi-CPU multi-threaded. There are users which expect relatively
* short queue flush time. Don't queue works which can run for too
* long.
*
* system_long_wq is similar to system_wq but may host long running
* works. Queue flushing might take relatively long.
*
* system_unbound_wq is unbound workqueue. Workers are not bound to
* any specific CPU, not concurrency managed, and all queued works are
* executed immediately as long as max_active limit is not reached and
* resources are available.
*
* system_freezable_wq is equivalent to system_wq except that it's
* freezable.
*
* *_power_efficient_wq are inclined towards saving power and converted
* into WQ_UNBOUND variants if 'wq_power_efficient' is enabled; otherwise,
* they are same as their non-power-efficient counterparts - e.g.
* system_power_efficient_wq is identical to system_wq if
* 'wq_power_efficient' is disabled. See WQ_POWER_EFFICIENT for more info.
*/
extern struct workqueue_struct *system_wq;
extern struct workqueue_struct *system_long_wq;
extern struct workqueue_struct *system_unbound_wq;
extern struct workqueue_struct *system_freezable_wq;
extern struct workqueue_struct *system_power_efficient_wq;
extern struct workqueue_struct *system_freezable_power_efficient_wq;
static inline struct workqueue_struct * __deprecated __system_nrt_wq(void)
{
return system_wq;
}
static inline struct workqueue_struct * __deprecated __system_nrt_freezable_wq(void)
{
return system_freezable_wq;
}
/* equivlalent to system_wq and system_freezable_wq, deprecated */
#define system_nrt_wq __system_nrt_wq()
#define system_nrt_freezable_wq __system_nrt_freezable_wq()
extern struct workqueue_struct *
__alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active,
struct lock_class_key *key, const char *lock_name, ...) __printf(1, 6);
/**
* alloc_workqueue - allocate a workqueue
* @fmt: printf format for the name of the workqueue
* @flags: WQ_* flags
* @max_active: max in-flight work items, 0 for default
* @args: args for @fmt
*
* Allocate a workqueue with the specified parameters. For detailed
* information on WQ_* flags, please refer to Documentation/workqueue.txt.
*
* The __lock_name macro dance is to guarantee that single lock_class_key
* doesn't end up with different namesm, which isn't allowed by lockdep.
*
* RETURNS:
* Pointer to the allocated workqueue on success, %NULL on failure.
*/
#ifdef CONFIG_LOCKDEP
#define alloc_workqueue(fmt, flags, max_active, args...) \
({ \
static struct lock_class_key __key; \
const char *__lock_name; \
\
__lock_name = #fmt#args; \
\
__alloc_workqueue_key((fmt), (flags), (max_active), \
&__key, __lock_name, ##args); \
})
#else
#define alloc_workqueue(fmt, flags, max_active, args...) \
__alloc_workqueue_key((fmt), (flags), (max_active), \
NULL, NULL, ##args)
#endif
/**
* alloc_ordered_workqueue - allocate an ordered workqueue
* @fmt: printf format for the name of the workqueue
* @flags: WQ_* flags (only WQ_FREEZABLE and WQ_MEM_RECLAIM are meaningful)
* @args: args for @fmt
*
* Allocate an ordered workqueue. An ordered workqueue executes at
* most one work item at any given time in the queued order. They are
* implemented as unbound workqueues with @max_active of one.
*
* RETURNS:
* Pointer to the allocated workqueue on success, %NULL on failure.
*/
#define alloc_ordered_workqueue(fmt, flags, args...) \
alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args)
#define create_workqueue(name) \
alloc_workqueue("%s", WQ_MEM_RECLAIM, 1, (name))
#define create_freezable_workqueue(name) \
alloc_workqueue("%s", WQ_FREEZABLE | WQ_UNBOUND | WQ_MEM_RECLAIM, \
1, (name))
#define create_singlethread_workqueue(name) \
alloc_workqueue("%s", WQ_UNBOUND | WQ_MEM_RECLAIM, 1, (name))
extern void destroy_workqueue(struct workqueue_struct *wq);
struct workqueue_attrs *alloc_workqueue_attrs(gfp_t gfp_mask);
void free_workqueue_attrs(struct workqueue_attrs *attrs);
int apply_workqueue_attrs(struct workqueue_struct *wq,
const struct workqueue_attrs *attrs);
extern bool queue_work_on(int cpu, struct workqueue_struct *wq,
struct work_struct *work);
extern bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
struct delayed_work *work, unsigned long delay);
extern bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq,
struct delayed_work *dwork, unsigned long delay);
extern void flush_workqueue(struct workqueue_struct *wq);
extern void drain_workqueue(struct workqueue_struct *wq);
extern void flush_scheduled_work(void);
extern int schedule_on_each_cpu(work_func_t func);
int execute_in_process_context(work_func_t fn, struct execute_work *);
extern bool flush_work(struct work_struct *work);
extern bool cancel_work_sync(struct work_struct *work);
extern bool flush_delayed_work(struct delayed_work *dwork);
extern bool cancel_delayed_work(struct delayed_work *dwork);
extern bool cancel_delayed_work_sync(struct delayed_work *dwork);
extern void workqueue_set_max_active(struct workqueue_struct *wq,
int max_active);
extern bool current_is_workqueue_rescuer(void);
extern bool workqueue_congested(int cpu, struct workqueue_struct *wq);
extern unsigned int work_busy(struct work_struct *work);
extern __printf(1, 2) void set_worker_desc(const char *fmt, ...);
extern void print_worker_info(const char *log_lvl, struct task_struct *task);
/**
* queue_work - queue work on a workqueue
* @wq: workqueue to use
* @work: work to queue
*
* Returns %false if @work was already on a queue, %true otherwise.
*
* We queue the work to the CPU on which it was submitted, but if the CPU dies
* it can be processed by another CPU.
*/
static inline bool queue_work(struct workqueue_struct *wq,
struct work_struct *work)
{
return queue_work_on(WORK_CPU_UNBOUND, wq, work);
}
/**
* queue_delayed_work - queue work on a workqueue after delay
* @wq: workqueue to use
* @dwork: delayable work to queue
* @delay: number of jiffies to wait before queueing
*
* Equivalent to queue_delayed_work_on() but tries to use the local CPU.
*/
static inline bool queue_delayed_work(struct workqueue_struct *wq,
struct delayed_work *dwork,
unsigned long delay)
{
return queue_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay);
}
/**
* mod_delayed_work - modify delay of or queue a delayed work
* @wq: workqueue to use
* @dwork: work to queue
* @delay: number of jiffies to wait before queueing
*
* mod_delayed_work_on() on local CPU.
*/
static inline bool mod_delayed_work(struct workqueue_struct *wq,
struct delayed_work *dwork,
unsigned long delay)
{
return mod_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay);
}
/**
* schedule_work_on - put work task on a specific cpu
* @cpu: cpu to put the work task on
* @work: job to be done
*
* This puts a job on a specific cpu
*/
static inline bool schedule_work_on(int cpu, struct work_struct *work)
{
return queue_work_on(cpu, system_wq, work);
}
/**
* schedule_work - put work task in global workqueue
* @work: job to be done
*
* Returns %false if @work was already on the kernel-global workqueue and
* %true otherwise.
*
* This puts a job in the kernel-global workqueue if it was not already
* queued and leaves it in the same position on the kernel-global
* workqueue otherwise.
*/
static inline bool schedule_work(struct work_struct *work)
{
return queue_work(system_wq, work);
}
/**
* schedule_delayed_work_on - queue work in global workqueue on CPU after delay
* @cpu: cpu to use
* @dwork: job to be done
* @delay: number of jiffies to wait
*
* After waiting for a given time this puts a job in the kernel-global
* workqueue on the specified CPU.
*/
static inline bool schedule_delayed_work_on(int cpu, struct delayed_work *dwork,
unsigned long delay)
{
return queue_delayed_work_on(cpu, system_wq, dwork, delay);
}
/**
* schedule_delayed_work - put work task in global workqueue after delay
* @dwork: job to be done
* @delay: number of jiffies to wait or 0 for immediate execution
*
* After waiting for a given time this puts a job in the kernel-global
* workqueue.
*/
static inline bool schedule_delayed_work(struct delayed_work *dwork,
unsigned long delay)
{
return queue_delayed_work(system_wq, dwork, delay);
}
/**
* keventd_up - is workqueue initialized yet?
*/
static inline bool keventd_up(void)
{
return system_wq != NULL;
}
/*
* Like above, but uses del_timer() instead of del_timer_sync(). This means,
* if it returns 0 the timer function may be running and the queueing is in
* progress.
*/
static inline bool __deprecated __cancel_delayed_work(struct delayed_work *work)
{
bool ret;
ret = del_timer(&work->timer);
if (ret)
work_clear_pending(&work->work);
return ret;
}
/* used to be different but now identical to flush_work(), deprecated */
static inline bool __deprecated flush_work_sync(struct work_struct *work)
{
return flush_work(work);
}
/* used to be different but now identical to flush_delayed_work(), deprecated */
static inline bool __deprecated flush_delayed_work_sync(struct delayed_work *dwork)
{
return flush_delayed_work(dwork);
}
#ifndef CONFIG_SMP
static inline long work_on_cpu(int cpu, long (*fn)(void *), void *arg)
{
return fn(arg);
}
#else
long work_on_cpu(int cpu, long (*fn)(void *), void *arg);
#endif /* CONFIG_SMP */
#ifdef CONFIG_FREEZER
extern void freeze_workqueues_begin(void);
extern bool freeze_workqueues_busy(void);
extern void thaw_workqueues(void);
#endif /* CONFIG_FREEZER */
#ifdef CONFIG_SYSFS
int workqueue_sysfs_register(struct workqueue_struct *wq);
#else /* CONFIG_SYSFS */
static inline int workqueue_sysfs_register(struct workqueue_struct *wq)
{ return 0; }
#endif /* CONFIG_SYSFS */
#endif
(struct work_struct)
data: 传递给工作函数的参数，可以是一个整型数，但更常用的是指针
entry:构成工作队列的链表节点对象。
func: 工作函数，工作线程取出工作队列节点后执行，data 会作为调用该函数的参数常用的与工作队列相关的宏和函数如下。
DECLARE_WORK:静态定义一个工作队列节点，n 是节点的名字，f是工作函数。
DECLARE_DELAYED_WORK:静态定义一个延迟的工作队列节点。
INIT_WORK:常用于动态分配的工作队列节点的初始化。
schedule_work:将工作队列节点加入到内核定义的全局工作队列中
schedule_delayed_work:在 delay 指定的时间后将一个延迟工作队列节点加入到全局的工作队列中。
下面是使用工作队列来实现中断下半部的相关代码
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/fs.h>
#include <linux/cdev.h>
#include <linux/kfifo.h>
#include <linux/ioctl.h>
#include <linux/uaccess.h>
#include <linux/wait.h>
#include <linux/sched.h>
#include <linux/poll.h>
#include <linux/aio.h>
#include <linux/interrupt.h>
#include <linux/random.h>
#include "vser.h"
#define VSER_MAJOR 256
#define VSER_MINOR 0
#define VSER_DEV_CNT 1
#define VSER_DEV_NAME "vser"
struct vser_dev {
unsigned int baud;
struct option opt;
struct cdev cdev;
wait_queue_head_t rwqh;
wait_queue_head_t wwqh;
struct fasync_struct *fapp;
};
DEFINE_KFIFO(vsfifo, char, 32);
static struct vser_dev vsdev;
static void vser_work(struct work_struct *work);
DECLARE_WORK(vswork, vser_work);
static int vser_fasync(int fd, struct file *filp, int on);
static int vser_open(struct inode *inode, struct file *filp)
{
return 0;
}
static int vser_release(struct inode *inode, struct file *filp)
{
vser_fasync(-1, filp, 0);
return 0;
}
static ssize_t vser_read(struct file *filp, char __user *buf, size_t count, loff_t *pos)
{
int ret;
unsigned int copied = 0;
if (kfifo_is_empty(&vsfifo)) {
if (filp->f_flags & O_NONBLOCK)
return -EAGAIN;
if (wait_event_interruptible_exclusive(vsdev.rwqh, !kfifo_is_empty(&vsfifo)))
return -ERESTARTSYS;
}
ret = kfifo_to_user(&vsfifo, buf, count, &copied);
if (!kfifo_is_full(&vsfifo)) {
wake_up_interruptible(&vsdev.wwqh);
kill_fasync(&vsdev.fapp, SIGIO, POLL_OUT);
}
return ret == 0 ? copied : ret;
}
static ssize_t vser_write(struct file *filp, const char __user *buf, size_t count, loff_t *pos)
{
int ret;
unsigned int copied = 0;
if (kfifo_is_full(&vsfifo)) {
if (filp->f_flags & O_NONBLOCK)
return -EAGAIN;
if (wait_event_interruptible_exclusive(vsdev.wwqh, !kfifo_is_full(&vsfifo)))
return -ERESTARTSYS;
}
ret = kfifo_from_user(&vsfifo, buf, count, &copied);
if (!kfifo_is_empty(&vsfifo)) {
wake_up_interruptible(&vsdev.rwqh);
kill_fasync(&vsdev.fapp, SIGIO, POLL_IN);
}
return ret == 0 ? copied : ret;
}
static long vser_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
if (_IOC_TYPE(cmd) != VS_MAGIC)
return -ENOTTY;
switch (cmd) {
case VS_SET_BAUD:
vsdev.baud = arg;
break;
case VS_GET_BAUD:
arg = vsdev.baud;
break;
case VS_SET_FFMT:
if (copy_from_user(&vsdev.opt, (struct option __user *)arg, sizeof(struct option)))
return -EFAULT;
break;
case VS_GET_FFMT:
if (copy_to_user((struct option __user *)arg, &vsdev.opt, sizeof(struct option)))
return -EFAULT;
break;
default:
return -ENOTTY;
}
return 0;
}
static unsigned int vser_poll(struct file *filp, struct poll_table_struct *p)
{
int mask = 0;
poll_wait(filp, &vsdev.rwqh, p);
poll_wait(filp, &vsdev.wwqh, p);
if (!kfifo_is_empty(&vsfifo))
mask |= POLLIN | POLLRDNORM;
if (!kfifo_is_full(&vsfifo))
mask |= POLLOUT | POLLWRNORM;
return mask;
}
static ssize_t vser_aio_read(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos)
{
size_t read = 0;
unsigned long i;
ssize_t ret;
for (i = 0; i < nr_segs; i++) {
ret = vser_read(iocb->ki_filp, iov[i].iov_base, iov[i].iov_len, &pos);
if (ret < 0)
break;
read += ret;
}
return read ? read : -EFAULT;
}
static ssize_t vser_aio_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos)
{
size_t written = 0;
unsigned long i;
ssize_t ret;
for (i = 0; i < nr_segs; i++) {
ret = vser_write(iocb->ki_filp, iov[i].iov_base, iov[i].iov_len, &pos);
if (ret < 0)
break;
written += ret;
}
return written ? written : -EFAULT;
}
static int vser_fasync(int fd, struct file *filp, int on)
{
return fasync_helper(fd, filp, on, &vsdev.fapp);
}
static irqreturn_t vser_handler(int irq, void *dev_id)
{
schedule_work(&vswork);
return IRQ_HANDLED;
}
static void vser_work(struct work_struct *work)
{
char data;
get_random_bytes(&data, sizeof(data));
data %= 26;
data += 'A';
if (!kfifo_is_full(&vsfifo))
if(!kfifo_in(&vsfifo, &data, sizeof(data)))
printk(KERN_ERR "vser: kfifo_in failure\n");
if (!kfifo_is_empty(&vsfifo)) {
wake_up_interruptible(&vsdev.rwqh);
kill_fasync(&vsdev.fapp, SIGIO, POLL_IN);
}
}
static struct file_operations vser_ops = {
.owner = THIS_MODULE,
.open = vser_open,
.release = vser_release,
.read = vser_read,
.write = vser_write,
.unlocked_ioctl = vser_ioctl,
.poll = vser_poll,
.aio_read = vser_aio_read,
.aio_write = vser_aio_write,
.fasync = vser_fasync,
};
static int __init vser_init(void)
{
int ret;
dev_t dev;
dev = MKDEV(VSER_MAJOR, VSER_MINOR);
ret = register_chrdev_region(dev, VSER_DEV_CNT, VSER_DEV_NAME);
if (ret)
goto reg_err;
cdev_init(&vsdev.cdev, &vser_ops);
vsdev.cdev.owner = THIS_MODULE;
vsdev.baud = 115200;
vsdev.opt.datab = 8;
vsdev.opt.parity = 0;
vsdev.opt.stopb = 1;
ret = cdev_add(&vsdev.cdev, dev, VSER_DEV_CNT);
if (ret)
goto add_err;
init_waitqueue_head(&vsdev.rwqh);
init_waitqueue_head(&vsdev.wwqh);
ret = request_irq(167, vser_handler, IRQF_TRIGGER_HIGH | IRQF_SHARED, "vser", &vsdev);
if (ret)
goto irq_err;
return 0;
irq_err:
cdev_del(&vsdev.cdev);
add_err:
unregister_chrdev_region(dev, VSER_DEV_CNT);
reg_err:
return ret;
}
static void __exit vser_exit(void)
{
dev_t dev;
dev = MKDEV(VSER_MAJOR, VSER_MINOR);
free_irq(167, &vsdev);
cdev_del(&vsdev.cdev);
unregister_chrdev_region(dev, VSER_DEV_CNT);
}
module_init(vser_init);
module_exit(vser_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("name <email>");
MODULE_DESCRIPTION("A simple character device driver");
MODULE_ALIAS("virtual-serial");
代码第40行定义了一个工作队列节点，名字叫 vswork，工作函数是 vser_work。和tasklet 类似，中断上半部调度了工作然后就返回了，以前中断上半部的事情交由下半部的工作函数来处理。
最后，对工作队列的主要特性进行一些总结。
(1)工作队列的工作函数运行在进程上下文，可以调度调度器
(2) 如果上一个工作还没有完成，又重新调度下一个工作，那么新的工作将不会被调度。
扫一扫
668
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
