buffer.c

嵌入式系统设计与实例开发实验教材二源码 多线程应用程序设计 串行端口程序设计 AD接口实验 CAN总线通信实验 GPS通信实验 Linux内核移植与编译实验 IC卡读写实验 SD驱动使

	/* If we're getting into imbalance, start write-out */
	spin_lock(&lru_list_lock);
	write_some_buffers(NODEV);

	/*
	 * And if we're _really_ out of balance, wait for
	 * some of the dirty/locked buffers ourselves and
	 * start bdflush.
	 * This will throttle heavy writers.
	 */
	if (state > 0) {
		wait_for_some_buffers(NODEV);
		wakeup_bdflush();
	}
}

inline void __mark_dirty(struct buffer_head *bh)
{
	bh->b_flushtime = jiffies + bdf_prm.b_un.age_buffer;
	refile_buffer(bh);
}

/* atomic version, the user must call balance_dirty() by hand
   as soon as it become possible to block */
void __mark_buffer_dirty(struct buffer_head *bh)
{
	if (!atomic_set_buffer_dirty(bh))
		__mark_dirty(bh);
}

void mark_buffer_dirty(struct buffer_head *bh)
{
	if (!atomic_set_buffer_dirty(bh)) {
		__mark_dirty(bh);
		balance_dirty();
	}
}

void set_buffer_flushtime(struct buffer_head *bh)
{
	bh->b_flushtime = jiffies + bdf_prm.b_un.age_buffer;
}
EXPORT_SYMBOL(set_buffer_flushtime);

/*
 * A buffer may need to be moved from one buffer list to another
 * (e.g. in case it is not shared any more). Handle this.
 */
static void __refile_buffer(struct buffer_head *bh)
{
	int dispose = BUF_CLEAN;
	if (buffer_locked(bh))
		dispose = BUF_LOCKED;
	if (buffer_dirty(bh))
		dispose = BUF_DIRTY;
	if (dispose != bh->b_list) {
		__remove_from_lru_list(bh);
		bh->b_list = dispose;
		if (dispose == BUF_CLEAN)
			remove_inode_queue(bh);
		__insert_into_lru_list(bh, dispose);
	}
}

void refile_buffer(struct buffer_head *bh)
{
	spin_lock(&lru_list_lock);
	__refile_buffer(bh);
	spin_unlock(&lru_list_lock);
}

/*
 * Release a buffer head
 */
void __brelse(struct buffer_head * buf)
{
	if (atomic_read(&buf->b_count)) {
		put_bh(buf);
		return;
	}
	printk(KERN_ERR "VFS: brelse: Trying to free free buffer\n");
}

/*
 * bforget() is like brelse(), except it discards any
 * potentially dirty data.
 */
void __bforget(struct buffer_head * buf)
{
	mark_buffer_clean(buf);
	__brelse(buf);
}

/**
 *	bread() - reads a specified block and returns the bh
 *	@block: number of block
 *	@size: size (in bytes) to read
 * 
 *	Reads a specified block, and returns buffer head that
 *	contains it. It returns NULL if the block was unreadable.
 */
struct buffer_head * bread(kdev_t dev, int block, int size)
{
	struct buffer_head * bh;

	bh = getblk(dev, block, size);
	touch_buffer(bh);
	if (buffer_uptodate(bh))
		return bh;
	ll_rw_block(READ, 1, &bh);
	wait_on_buffer(bh);
	if (buffer_uptodate(bh))
		return bh;
	brelse(bh);
	return NULL;
}

/*
 * Note: the caller should wake up the buffer_wait list if needed.
 */
static void __put_unused_buffer_head(struct buffer_head * bh)
{
	if (bh->b_inode)
		BUG();
	if (nr_unused_buffer_heads >= MAX_UNUSED_BUFFERS) {
		kmem_cache_free(bh_cachep, bh);
	} else {
		bh->b_dev = B_FREE;
		bh->b_blocknr = -1;
		bh->b_this_page = NULL;

		nr_unused_buffer_heads++;
		bh->b_next_free = unused_list;
		unused_list = bh;
	}
}

void put_unused_buffer_head(struct buffer_head *bh)
{
	spin_lock(&unused_list_lock);
	__put_unused_buffer_head(bh);
	spin_unlock(&unused_list_lock);
}
EXPORT_SYMBOL(put_unused_buffer_head);

/*
 * Reserve NR_RESERVED buffer heads for async IO requests to avoid
 * no-buffer-head deadlock.  Return NULL on failure; waiting for
 * buffer heads is now handled in create_buffers().
 */ 
struct buffer_head * get_unused_buffer_head(int async)
{
	struct buffer_head * bh;

	spin_lock(&unused_list_lock);
	if (nr_unused_buffer_heads > NR_RESERVED) {
		bh = unused_list;
		unused_list = bh->b_next_free;
		nr_unused_buffer_heads--;
		spin_unlock(&unused_list_lock);
		return bh;
	}
	spin_unlock(&unused_list_lock);

	/* This is critical.  We can't call out to the FS
	 * to get more buffer heads, because the FS may need
	 * more buffer-heads itself.  Thus SLAB_NOFS.
	 */
	if((bh = kmem_cache_alloc(bh_cachep, SLAB_NOFS)) != NULL) {
		bh->b_blocknr = -1;
		bh->b_this_page = NULL;
		return bh;
	}

	/*
	 * If we need an async buffer, use the reserved buffer heads.
	 */
	if (async) {
		spin_lock(&unused_list_lock);
		if (unused_list) {
			bh = unused_list;
			unused_list = bh->b_next_free;
			nr_unused_buffer_heads--;
			spin_unlock(&unused_list_lock);
			return bh;
		}
		spin_unlock(&unused_list_lock);
	}

	return NULL;
}
EXPORT_SYMBOL(get_unused_buffer_head);

void set_bh_page (struct buffer_head *bh, struct page *page, unsigned long offset)
{
	bh->b_page = page;
	if (offset >= PAGE_SIZE)
		BUG();
	if (PageHighMem(page))
		/*
		 * This catches illegal uses and preserves the offset:
		 */
		bh->b_data = (char *)(0 + offset);
	else
		bh->b_data = page_address(page) + offset;
}
EXPORT_SYMBOL(set_bh_page);

/*
 * Create the appropriate buffers when given a page for data area and
 * the size of each buffer.. Use the bh->b_this_page linked list to
 * follow the buffers created.  Return NULL if unable to create more
 * buffers.
 * The async flag is used to differentiate async IO (paging, swapping)
 * from ordinary buffer allocations, and only async requests are allowed
 * to sleep waiting for buffer heads. 
 */
static struct buffer_head * create_buffers(struct page * page, unsigned long size, int async)
{
	struct buffer_head *bh, *head;
	long offset;

try_again:
	head = NULL;
	offset = PAGE_SIZE;
	while ((offset -= size) >= 0) {
		bh = get_unused_buffer_head(async);
		if (!bh)
			goto no_grow;

		bh->b_dev = NODEV;
		bh->b_this_page = head;
		head = bh;

		bh->b_state = 0;
		bh->b_next_free = NULL;
		bh->b_pprev = NULL;
		atomic_set(&bh->b_count, 0);
		bh->b_size = size;

		set_bh_page(bh, page, offset);

		bh->b_list = BUF_CLEAN;
		bh->b_end_io = NULL;
	}
	return head;
/*
 * In case anything failed, we just free everything we got.
 */
no_grow:
	if (head) {
		spin_lock(&unused_list_lock);
		do {
			bh = head;
			head = head->b_this_page;
			__put_unused_buffer_head(bh);
		} while (head);
		spin_unlock(&unused_list_lock);

		/* Wake up any waiters ... */
		wake_up(&buffer_wait);
	}

	/*
	 * Return failure for non-async IO requests.  Async IO requests
	 * are not allowed to fail, so we have to wait until buffer heads
	 * become available.  But we don't want tasks sleeping with 
	 * partially complete buffers, so all were released above.
	 */
	if (!async)
		return NULL;

	/* We're _really_ low on memory. Now we just
	 * wait for old buffer heads to become free due to
	 * finishing IO.  Since this is an async request and
	 * the reserve list is empty, we're sure there are 
	 * async buffer heads in use.
	 */
	run_task_queue(&tq_disk);

	free_more_memory();
	goto try_again;
}

/*
 * Called when truncating a buffer on a page completely.
 */
static void discard_buffer(struct buffer_head * bh)
{
	if (buffer_mapped(bh)) {
		mark_buffer_clean(bh);
		lock_buffer(bh);
		clear_bit(BH_Uptodate, &bh->b_state);
		clear_bit(BH_Mapped, &bh->b_state);
		clear_bit(BH_Req, &bh->b_state);
		clear_bit(BH_New, &bh->b_state);
		remove_from_queues(bh);
		unlock_buffer(bh);
	}
}

/**
 * try_to_release_page - release old fs-specific metadata on a page
 *
 */

int try_to_release_page(struct page * page, int gfp_mask)
{
	if (!PageLocked(page))
		BUG();
	
	if (!page->mapping)
		goto try_to_free;
	if (!page->mapping->a_ops->releasepage)
		goto try_to_free;
	if (page->mapping->a_ops->releasepage(page, gfp_mask))
		goto try_to_free;
	/*
	 * We couldn't release buffer metadata; don't even bother trying
	 * to release buffers.
	 */
	return 0;
try_to_free:	
	return try_to_free_buffers(page, gfp_mask);
}

/*
 * We don't have to release all buffers here, but
 * we have to be sure that no dirty buffer is left
 * and no IO is going on (no buffer is locked), because
 * we have truncated the file and are going to free the
 * blocks on-disk..
 */
int discard_bh_page(struct page *page, unsigned long offset, int drop_pagecache)
{
	struct buffer_head *head, *bh, *next;
	unsigned int curr_off = 0;

	if (!PageLocked(page))
		BUG();
	if (!page->buffers)
		return 1;

	head = page->buffers;
	bh = head;
	do {
		unsigned int next_off = curr_off + bh->b_size;
		next = bh->b_this_page;

		/*
		 * is this block fully flushed?
		 */
		if (offset <= curr_off)
			discard_buffer(bh);
		curr_off = next_off;
		bh = next;
	} while (bh != head);

	/*
	 * subtle. We release buffer-heads only if this is
	 * the 'final' flushpage. We have invalidated the get_block
	 * cached value unconditionally, so real IO is not
	 * possible anymore.
	 *
	 * If the free doesn't work out, the buffers can be
	 * left around - they just turn into anonymous buffers
	 * instead.
	 */
	if (!offset) {
		if (!try_to_release_page(page, 0))
			return 0;
	}

	return 1;
}

void create_empty_buffers(struct page *page, kdev_t dev, unsigned long blocksize)
{
	struct buffer_head *bh, *head, *tail;

	/* FIXME: create_buffers should fail if there's no enough memory */
	head = create_buffers(page, blocksize, 1);
	if (page->buffers)
		BUG();

	bh = head;
	do {
		bh->b_dev = dev;
		bh->b_blocknr = 0;
		bh->b_end_io = NULL;
		tail = bh;
		bh = bh->b_this_page;
	} while (bh);
	tail->b_this_page = head;
	page->buffers = head;
	page_cache_get(page);
}
EXPORT_SYMBOL(create_empty_buffers);

/*
 * We are taking a block for data and we don't want any output from any
 * buffer-cache aliases starting from return from that function and
 * until the moment when something will explicitly mark the buffer
 * dirty (hopefully that will not happen until we will free that block ;-)
 * We don't even need to mark it not-uptodate - nobody can expect
 * anything from a newly allocated buffer anyway. We used to used
 * unmap_buffer() for such invalidation, but that was wrong. We definitely
 * don't want to mark the alias unmapped, for example - it would confuse
 * anyone who might pick it with bread() afterwards...
 */

static void unmap_underlying_metadata(struct buffer_head * bh)
{
	struct buffer_head *old_bh;

	old_bh = get_hash_table(bh->b_dev, bh->b_blocknr, bh->b_size);
	if (old_bh) {
		mark_buffer_clean(old_bh);
		wait_on_buffer(old_bh);
		clear_bit(BH_Req, &old_bh->b_state);
		__brelse(old_bh);
	}
}

/*
 * NOTE! All mapped/uptodate combinations are valid:
 *
 *	Mapped	Uptodate	Meaning
 *
 *	No	No		"unknown" - must do get_block()
 *	No	Yes		"hole" - zero-filled
 *	Yes	No		"allocated" - allocated on disk, not read in
 *	Yes	Yes		"valid" - allocated and up-to-date in memory.
 *
 * "Dirty" is valid only with the last case (mapped+uptodate).
 */

/*
 * block_write_full_page() is SMP threaded - the kernel lock is not held.
 */
static int __block_write_full_page(struct inode *inode, struct page *page, get_block_t *get_block)
{
	int err, i;
	unsigned long block;
	struct buffer_head *bh, *head;
	int need_unlock;

	if (!PageLocked(page))
		BUG();

	if (!page->buffers)
		create_empty_buffers(page, inode->i_dev, 1 << inode->i_blkbits);
	head = page->buffers;

	block = page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);

	bh = head;
	i = 0;

	/* Stage 1: make sure we have all the buffers mapped! */
	do {
		/*
		 * If the buffer isn't up-to-date, we can't be sure
		 * that the buffer has been initialized with the proper
		 * block number information etc..
		 *
		 * Leave it to the low-level FS to make all those
		 * decisions (block #0 may actually be a valid block)
		 */
		if (!buffer_mapped(bh)) {
			err = get_block(inode, block, bh, 1);
			if (err)
				goto out;
			if (buffer_new(bh))
				unmap_underlying_metadata(bh);
		}
		bh = bh->b_this_page;
		block++;
	} while (bh != head);

	/* Stage 2: lock the buffers, mark them clean */
	do {
		lock_buffer(bh);
		set_buffer_async_io(bh);
		set_bit(BH_Uptodate, &bh->b_state);
		clear_bit(BH_Dirty, &bh->b_state);
		bh = bh->b_this_page;
	} while (bh != head);

	/* Stage 3: submit the IO */
	do {
		struct buffer_head *next = bh->b_this_page;
		submit_bh(WRITE, bh);
		bh = next;
	} while (bh != head);

	/* Done - end_buffer_io_async will unlock */
	SetPageUptodate(page);
	return 0;

out:
	/*
	 * ENOSPC, or some other error.  We may already have added some
	 * blocks to the file, so we need to write these out to avoid
	 * exposing stale data.
	 */
	ClearPageUptodate(page);
	bh = head;
	need_unlock = 1;
	/* Recovery: lock and submit the mapped buffers */
	do {
		if (buffer_mapped(bh)) {
			lock_buffer(bh);
			set_buffer_async_io(bh);
			need_unlock = 0;
		}
		bh = bh->b_this_page;
	} while (bh != head);
	do {
		struct buffer_head *next = bh->b_this_page;
		if (buffer_mapped(bh)) {
			set_bit(BH_Uptodate, &bh->b_state);
			clear_bit(BH_Dirty, &bh->b_state);
			submit_bh(WRITE, bh);
		}
		bh = next;
	} while (bh != head);
	if (need_unlock)
		UnlockPage(page);
	return err;
}

static int __block_prepare_write(struct inode *inode, struct page *page,
		unsigned from, unsigned to, get_block_t *get_block)
{
	unsigned block_start, block_end;
	unsigned long block;
	int err = 0;