Linux開發--使用Memory barrier實現無鎖環形緩衝區

一 說明

    涉及到併發編程中較底層的memory barrier相關知識，本人水平有限，在此不展開講述，讀者自行查閱。

二 代碼

    Linux內核中，實現了一個無鎖（只有一個讀線程和一個寫線程時）環形緩衝區 kfifo 使用到了 Memory barrier，實現源碼如下：

/*
 * A simple kernel FIFO implementation.
 *
 * Copyright (C) 2004 Stelian Pop <[email protected]>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 *
 */
 
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/err.h>
#include <linux/kfifo.h>
#include <linux/log2.h>
 
/**
 * kfifo_init - allocates a new FIFO using a preallocated buffer
 * @buffer: the preallocated buffer to be used.
 * @size: the size of the internal buffer, this have to be a power of 2.
 * @gfp_mask: get_free_pages mask, passed to kmalloc()
 * @lock: the lock to be used to protect the fifo buffer
 *
 * Do NOT pass the kfifo to kfifo_free() after use! Simply free the
 * &struct kfifo with kfree().
 */
struct kfifo *kfifo_init(unsigned char *buffer, unsigned int size,
                         gfp_t gfp_mask, spinlock_t *lock)
{
    struct kfifo *fifo;
 
    /* size must be a power of 2 */
    BUG_ON(!is_power_of_2(size));
 
    fifo = kmalloc(sizeof(struct kfifo), gfp_mask);
    if (!fifo)
        return ERR_PTR(-ENOMEM);
 
    fifo->buffer = buffer;
    fifo->size = size;
    fifo->in = fifo->out = 0;
    fifo->lock = lock;
 
    return fifo;
}
EXPORT_SYMBOL(kfifo_init);
 
/**
 * kfifo_alloc - allocates a new FIFO and its internal buffer
 * @size: the size of the internal buffer to be allocated.
 * @gfp_mask: get_free_pages mask, passed to kmalloc()
 * @lock: the lock to be used to protect the fifo buffer
 *
 * The size will be rounded-up to a power of 2.
 */
struct kfifo *kfifo_alloc(unsigned int size, gfp_t gfp_mask, spinlock_t *lock)
{
    unsigned char *buffer;
    struct kfifo *ret;
 
    /*
     * round up to the next power of 2, since our 'let the indices
     * wrap' technique works only in this case.
     */
    if (!is_power_of_2(size)) {
        BUG_ON(size > 0x80000000);
        size = roundup_pow_of_two(size);
    }
 
    buffer = kmalloc(size, gfp_mask);
    if (!buffer)
        return ERR_PTR(-ENOMEM);
 
    ret = kfifo_init(buffer, size, gfp_mask, lock);
 
    if (IS_ERR(ret))
        kfree(buffer);
 
    return ret;
}
EXPORT_SYMBOL(kfifo_alloc);
 
/**
 * kfifo_free - frees the FIFO
 * @fifo: the fifo to be freed.
 */
void kfifo_free(struct kfifo *fifo)
{
    kfree(fifo->buffer);
    kfree(fifo);
}
EXPORT_SYMBOL(kfifo_free);
 
/**
 * __kfifo_put - puts some data into the FIFO, no locking version
 * @fifo: the fifo to be used.
 * @buffer: the data to be added.
 * @len: the length of the data to be added.
 *
 * This function copies at most @len bytes from the @buffer into
 * the FIFO depending on the free space, and returns the number of
 * bytes copied.
 *
 * Note that with only one concurrent reader and one concurrent
 * writer, you don't need extra locking to use these functions.
 */
unsigned int __kfifo_put(struct kfifo *fifo,
                         const unsigned char *buffer, unsigned int len)
{
    unsigned int l;
 
    len = min(len, fifo->size - fifo->in + fifo->out);
 
    /*
     * Ensure that we sample the fifo->out index -before- we
     * start putting bytes into the kfifo.
     */
 
    smp_mb();
 
    /* first put the data starting from fifo->in to buffer end */
    l = min(len, fifo->size - (fifo->in & (fifo->size - 1)));
    memcpy(fifo->buffer + (fifo->in & (fifo->size - 1)), buffer, l);
 
    /* then put the rest (if any) at the beginning of the buffer */
    memcpy(fifo->buffer, buffer + l, len - l);
 
    /*
     * Ensure that we add the bytes to the kfifo -before-
     * we update the fifo->in index.
     */
 
    smp_wmb();
 
    fifo->in += len;
 
    return len;
}
EXPORT_SYMBOL(__kfifo_put);
 
/**
 * __kfifo_get - gets some data from the FIFO, no locking version
 * @fifo: the fifo to be used.
 * @buffer: where the data must be copied.
 * @len: the size of the destination buffer.
 *
 * This function copies at most @len bytes from the FIFO into the
 * @buffer and returns the number of copied bytes.
 *
 * Note that with only one concurrent reader and one concurrent
 * writer, you don't need extra locking to use these functions.
 */
unsigned int __kfifo_get(struct kfifo *fifo,
                         unsigned char *buffer, unsigned int len)
{
    unsigned int l;
 
    len = min(len, fifo->in - fifo->out);
 
    /*
     * Ensure that we sample the fifo->in index -before- we
     * start removing bytes from the kfifo.
     */
 
    smp_rmb();
 
    /* first get the data from fifo->out until the end of the buffer */
    l = min(len, fifo->size - (fifo->out & (fifo->size - 1)));
    memcpy(buffer, fifo->buffer + (fifo->out & (fifo->size - 1)), l);
 
    /* then get the rest (if any) from the beginning of the buffer */
    memcpy(buffer + l, fifo->buffer, len - l);
 
    /*
     * Ensure that we remove the bytes from the kfifo -before-
     * we update the fifo->out index.
     */
 
    smp_mb();
 
    fifo->out += len;
 
    return len;
}
EXPORT_SYMBOL(__kfifo_get);

上述代碼在實現環形緩衝區時使用的一些技巧：

  1 使用與操作來求取環形緩衝區的下標，相比取餘操作來求取下標的做法效率要高不少。使用與操作求取下標的前提是環形緩衝區的大小必須是 2 的 N 次方，換而言之就是說環形緩衝區的大小爲一個僅有一個 1 的二進制數，那麼 index & (size – 1) 則爲求取的下標（這不難理解）
  2 使用了 in 和 out 兩個索引且 in 和 out 是一直遞增的（此做法比較巧妙），這樣能夠避免一些複雜的條件判斷（某些實現下，in == out 時還無法區分緩衝區是空還是滿）