rwsem-spinlock.c

/* rwsem-spinlock.c: R/W semaphores: contention handling functions for
 * generic spinlock implementation
 *
 * Copyright (c) 2001   David Howells (dhowells@redhat.com).
 * - Derived partially from idea by Andrea Arcangeli <andrea@suse.de>
 * - Derived also from comments by Linus
 */
#include <linux/rwsem.h>
#include <linux/sched.h>
#include <linux/export.h>

enum rwsem_waiter_type {
	RWSEM_WAITING_FOR_WRITE,
	RWSEM_WAITING_FOR_READ
};

struct rwsem_waiter {
	struct list_head list;
	struct task_struct *task;
	enum rwsem_waiter_type type;
};

int rwsem_is_locked(struct rw_semaphore *sem)
{
	int ret = 1;
	unsigned long flags;

	if (raw_spin_trylock_irqsave(&sem->wait_lock, flags)) {
		ret = (sem->activity != 0);
		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
	}
	return ret;
}
EXPORT_SYMBOL(rwsem_is_locked);

/*
 * initialise the semaphore
 */
void __init_rwsem(struct rw_semaphore *sem, const char *name,
		  struct lock_class_key *key)
{
#ifdef CONFIG_DEBUG_LOCK_ALLOC
	/*
	 * Make sure we are not reinitializing a held semaphore:
	 */
	debug_check_no_locks_freed((void *)sem, sizeof(*sem));
	lockdep_init_map(&sem->dep_map, name, key, 0);
#endif
	sem->activity = 0;
	raw_spin_lock_init(&sem->wait_lock);
	INIT_LIST_HEAD(&sem->wait_list);
}
EXPORT_SYMBOL(__init_rwsem);

/*
 * handle the lock release when processes blocked on it that can now run
 * - if we come here, then:
 *   - the 'active count' _reached_ zero
 *   - the 'waiting count' is non-zero
 * - the spinlock must be held by the caller
 * - woken process blocks are discarded from the list after having task zeroed
 * - writers are only woken if wakewrite is non-zero
 */
static inline struct rw_semaphore *
__rwsem_do_wake(struct rw_semaphore *sem, int wakewrite)
{
	struct rwsem_waiter *waiter;
	struct task_struct *tsk;
	int woken;

	waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);

	if (waiter->type == RWSEM_WAITING_FOR_WRITE) {
		if (wakewrite)
			/* Wake up a writer. Note that we do not grant it the
			 * lock - it will have to acquire it when it runs. */
			wake_up_process(waiter->task);
		goto out;
	}

	/* grant an infinite number of read locks to the front of the queue */
	woken = 0;
	do {
		struct list_head *next = waiter->list.next;

		list_del(&waiter->list);
		tsk = waiter->task;
		smp_mb();
		waiter->task = NULL;
		wake_up_process(tsk);
		put_task_struct(tsk);
		woken++;
		if (next == &sem->wait_list)
			break;
		waiter = list_entry(next, struct rwsem_waiter, list);
	} while (waiter->type != RWSEM_WAITING_FOR_WRITE);

	sem->activity += woken;

 out:
	return sem;
}

/*
 * wake a single writer
 */
static inline struct rw_semaphore *
__rwsem_wake_one_writer(struct rw_semaphore *sem)
{
	struct rwsem_waiter *waiter;

	waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
	wake_up_process(waiter->task);

	return sem;
}

/*
 * get a read lock on the semaphore
 */
void __sched __down_read(struct rw_semaphore *sem)
{
	struct rwsem_waiter waiter;
	struct task_struct *tsk;
	unsigned long flags;

	raw_spin_lock_irqsave(&sem->wait_lock, flags);

	if (sem->activity >= 0 && list_empty(&sem->wait_list)) {
		/* granted */
		sem->activity++;
		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
		goto out;
	}

	tsk = current;
	set_task_state(tsk, TASK_UNINTERRUPTIBLE);

	/* set up my own style of waitqueue */
	waiter.task = tsk;
	waiter.type = RWSEM_WAITING_FOR_READ;
	get_task_struct(tsk);

	list_add_tail(&waiter.list, &sem->wait_list);

	/* we don't need to touch the semaphore struct anymore */
	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);

	/* wait to be given the lock */
	for (;;) {
		if (!waiter.task)
			break;
		schedule();
		set_task_state(tsk, TASK_UNINTERRUPTIBLE);
	}

	tsk->state = TASK_RUNNING;
 out:
	;
}

/*
 * trylock for reading -- returns 1 if successful, 0 if contention
 */
int __down_read_trylock(struct rw_semaphore *sem)
{
	unsigned long flags;
	int ret = 0;


	raw_spin_lock_irqsave(&sem->wait_lock, flags);

	if (sem->activity >= 0 && list_empty(&sem->wait_list)) {
		/* granted */
		sem->activity++;
		ret = 1;
	}

	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);

	return ret;
}

/*
 * get a write lock on the semaphore
 */
void __sched __down_write_nested(struct rw_semaphore *sem, int subclass)
{
	struct rwsem_waiter waiter;
	struct task_struct *tsk;
	unsigned long flags;

	raw_spin_lock_irqsave(&sem->wait_lock, flags);

	/* set up my own style of waitqueue */
	tsk = current;
	waiter.task = tsk;
	waiter.type = RWSEM_WAITING_FOR_WRITE;
	list_add_tail(&waiter.list, &sem->wait_list);

	/* wait for someone to release the lock */
	for (;;) {
		/*
		 * That is the key to support write lock stealing: allows the
		 * task already on CPU to get the lock soon rather than put
		 * itself into sleep and waiting for system woke it or someone
		 * else in the head of the wait list up.
		 */
		if (sem->activity == 0)
			break;
		set_task_state(tsk, TASK_UNINTERRUPTIBLE);
		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
		schedule();
		raw_spin_lock_irqsave(&sem->wait_lock, flags);
	}
	/* got the lock */
	sem->activity = -1;
	list_del(&waiter.list);

	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
}

void __sched __down_write(struct rw_semaphore *sem)
{
	__down_write_nested(sem, 0);
}

/*
 * trylock for writing -- returns 1 if successful, 0 if contention
 */
int __down_write_trylock(struct rw_semaphore *sem)
{
	unsigned long flags;
	int ret = 0;

	raw_spin_lock_irqsave(&sem->wait_lock, flags);

	if (sem->activity == 0) {
		/* got the lock */
		sem->activity = -1;
		ret = 1;
	}

	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);

	return ret;
}

/*
 * release a read lock on the semaphore
 */
void __up_read(struct rw_semaphore *sem)
{
	unsigned long flags;

	raw_spin_lock_irqsave(&sem->wait_lock, flags);

	if (--sem->activity == 0 && !list_empty(&sem->wait_list))
		sem = __rwsem_wake_one_writer(sem);

	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
}

/*
 * release a write lock on the semaphore
 */
void __up_write(struct rw_semaphore *sem)
{
	unsigned long flags;

	raw_spin_lock_irqsave(&sem->wait_lock, flags);

	sem->activity = 0;
	if (!list_empty(&sem->wait_list))
		sem = __rwsem_do_wake(sem, 1);

	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
}

/*
 * downgrade a write lock into a read lock
 * - just wake up any readers at the front of the queue
 */
void __downgrade_write(struct rw_semaphore *sem)
{
	unsigned long flags;

	raw_spin_lock_irqsave(&sem->wait_lock, flags);

	sem->activity = 1;
	if (!list_empty(&sem->wait_list))
		sem = __rwsem_do_wake(sem, 0);

	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
}

关于rwsem的代码,这里主要是代码中关于rwsem的初始化,以及down_read ,down_write,up_read,up_write的具体操作

struct rw_semaphore的结构体中:

struct rw_semaphore {
    /*读/写信号量定义：
    * - 如果activity为0，那么没有激活的读者或写者。
    * - 如果activity为+ve，那么将有ve个激活的读者。
    * - 如果activity为-1，那么将有1个激活的写者。 */
    __s32 activity; /*信号量值*/
    spinlock_t wait_lock; /*用于锁等待队列wait_list*/
    struct list_head wait_list; /*如果非空，表示有进程等待该信号量*/
#ifdef CONFIG_DEBUG_LOCK_ALLOC /*用于锁调试*/
    struct lockdep_map dep_map;
#endif
};

 

wait_list中存放的是等待队列，在信号阻塞时，依次会将进程放进该链表，且链表遵循FIFO

其他的部分实际上有这些基本概念，都是好理解的。

__down_read:

1. read lock 可用时，activity + 1;

2.read lock 不可用时

       a.当前进程置为TASK_UNINTERRUPTIBLE 

      b.waiter.task 保存当前进程，并把 waiter.type置为waite for read

      c.waiter 加入等待队列，也就是把当前阻塞的进程加入等待队列

       d.死循环

           for (;;)

           {

                if (!waiter.task)             //当前进程已经不再等待队列里面的时候，可以跳出循环，这是由于在__up_XX函数中有wake操作，在释放锁之后，会把可以拿到锁的进程都从等待队列中移除。所以当task不在队列中时，说明该进程拿到锁了，可以激活了。

                      break;

                schedule();                    //主动放弃当前CPU ，进行调度，实现挂起

                set_task_state(tsk, TASK_UNINTERRUPTIBLE);   //调度回来时，当前进程是TASK_RUNNING，先将当前进程置为TASK_UNINTERRUPTIBLE，这样下次判断没有拿到锁时，直接schedule();                   

            }

          tsk->state = TASK_RUNNING;  //拿到锁，跳出循环后，置TASK_RUNNING ，使进程运行而不被调度。

__up_write:

        void __up_write(struct rw_semaphore *sem)

       {

             unsigned long flags;

             raw_spin_lock_irqsave(&sem->wait_lock, flags);

             sem->activity = 0;

             if (!list_empty(&sem->wait_list))

                         sem = __rwsem_do_wake(sem, 1);                          //唤醒等待队列的地方

            raw_spin_unlock_irqrestore(&sem->wait_lock, flags);

      }

 在__down_write中，直接调用的__down_write_nested

void __sched __down_write_nested(struct rw_semaphore *sem, int subclass)
{
     struct rwsem_waiter waiter;
     struct task_struct *tsk;
     unsigned long flags;

     raw_spin_lock_irqsave(&sem->wait_lock, flags);

     /* set up my own style of waitqueue */
     tsk = current;
     waiter.task = tsk;
     waiter.type = RWSEM_WAITING_FOR_WRITE;
     list_add_tail(&waiter.list, &sem->wait_list);

    //当前进程连接到等待队列

     /* wait for someone to release the lock */
     for (;;) {
      /*
       * That is the key to support write lock stealing: allows the
       * task already on CPU to get the lock soon rather than put
       * itself into sleep and waiting for system woke it or someone
       * else in the head of the wait list up.
       */
       if (sem->activity == 0)             //当前锁既不在read也不在write，空闲状态

               break;
       set_task_state(tsk, TASK_UNINTERRUPTIBLE);
      raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
      schedule();
      raw_spin_lock_irqsave(&sem->wait_lock, flags);
     }
     /* got the lock */
     sem->activity = -1;                  //设置当前信号为正在写
     list_del(&waiter.list);               //从队列中删除当前进程

     raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
    }

__up_read :

void __up_read(struct rw_semaphore *sem)
{
    unsigned long flags;

    raw_spin_lock_irqsave(&sem->wait_lock, flags);

    if (--sem->activity == 0 && !list_empty(&sem->wait_list))  //当read释放锁之后，如果有阻塞的write进程就将其唤醒，wake_up_process(waiter->task);
        sem = __rwsem_wake_one_writer(sem);

    raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
}

最后是关于__up_write 中的

 __rwsem_do_wake:

/*
 * handle the lock release when processes blocked on it that can now run
 * - if we come here, then:
 *   - the 'active count' _reached_ zero
 *   - the 'waiting count' is non-zero
 * - the spinlock must be held by the caller
 * - woken process blocks are discarded from the list after having task zeroed
 * - writers are only woken if wakewrite is non-zero
 */
static inline struct rw_semaphore *
__rwsem_do_wake(struct rw_semaphore *sem, int wakewrite)
{
 struct rwsem_waiter *waiter;
 struct task_struct *tsk;
 int woken;

 waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);

 if (waiter->type == RWSEM_WAITING_FOR_WRITE) {                    //检测到队列首部是write的，就直接唤醒
  if (wakewrite)
   /* Wake up a writer. Note that we do not grant it the
    * lock - it will have to acquire it when it runs. */
   wake_up_process(waiter->task);
  goto out;
 }
 //为什么没有对waiter 的检查
 /* grant an infinite number of read locks to the front of the queue */
 woken = 0;
 do {                                                              //检测到是read，就将read之后的所有连续read都激活
  struct list_head *next = waiter->list.next;

  list_del(&waiter->list);
  tsk = waiter->task;
  smp_mb();
  waiter->task = NULL;
  wake_up_process(tsk);
  put_task_struct(tsk);
  woken++;
  if (next == &sem->wait_list)
   break;
  waiter = list_entry(next, struct rwsem_waiter, list);
 } while (waiter->type != RWSEM_WAITING_FOR_WRITE);

 sem->activity += woken;

 out:
 return sem;
}