ll_rw_blk.c

讲述linux的初始化过程

 *
 * generic_make_request() does not return any status.  The
 * success/failure status of the request, along with notification of
 * completion, is delivered asynchronously through the bh->b_end_io
 * function described (one day) else where.
 *
 * The caller of generic_make_request must make sure that b_page,
 * b_addr, b_size are set to describe the memory buffer, that b_rdev
 * and b_rsector are set to describe the device address, and the
 * b_end_io and optionally b_private are set to describe how
 * completion notification should be signaled.  BH_Mapped should also
 * be set (to confirm that b_dev and b_blocknr are valid).
 *
 * generic_make_request and the drivers it calls may use b_reqnext,
 * and may change b_rdev and b_rsector.  So the values of these fields
 * should NOT be depended on after the call to generic_make_request.
 * Because of this, the caller should record the device address
 * information in b_dev and b_blocknr.
 *
 * Apart from those fields mentioned above, no other fields, and in
 * particular, no other flags, are changed by generic_make_request or
 * any lower level drivers.
 * */
void generic_make_request (int rw, struct buffer_head * bh)
{
	int major = MAJOR(bh->b_rdev);
	request_queue_t *q;

	if (!bh->b_end_io) BUG();
	if (blk_size[major]) {
		unsigned long maxsector = (blk_size[major][MINOR(bh->b_rdev)] << 1) + 1;
		unsigned int sector, count;

		count = bh->b_size >> 9;
		sector = bh->b_rsector;

		if (maxsector < count || maxsector - count < sector) {
			bh->b_state &= (1 << BH_Lock) | (1 << BH_Mapped);
			if (blk_size[major][MINOR(bh->b_rdev)]) {
				
				/* This may well happen - the kernel calls bread()
				   without checking the size of the device, e.g.,
				   when mounting a device. */
				printk(KERN_INFO
				       "attempt to access beyond end of device\n");
				printk(KERN_INFO "%s: rw=%d, want=%d, limit=%d\n",
				       kdevname(bh->b_rdev), rw,
				       (sector + count)>>1,
				       blk_size[major][MINOR(bh->b_rdev)]);
			}
			bh->b_end_io(bh, 0);
			return;
		}
	}

	/*
	 * Resolve the mapping until finished. (drivers are
	 * still free to implement/resolve their own stacking
	 * by explicitly returning 0)
	 */
	/* NOTE: we don't repeat the blk_size check for each new device.
	 * Stacking drivers are expected to know what they are doing.
	 */
	do {
		q = blk_get_queue(bh->b_rdev);
		if (!q) {
			printk(KERN_ERR
			       "generic_make_request: Trying to access nonexistent block-device %s (%ld)\n",
			       kdevname(bh->b_rdev), bh->b_rsector);
			buffer_IO_error(bh);
			break;
		}

	}
	while (q->make_request_fn(q, rw, bh));
}


/**
 * submit_bh: submit a buffer_head to the block device later for I/O
 * @rw: whether to %READ or %WRITE, or mayve to %READA (read ahead)
 * @bh: The &struct buffer_head which describes the I/O
 *
 * submit_bh() is very similar in purpose to generic_make_request(), and
 * uses that function to do most of the work.
 *
 * The extra functionality provided by submit_bh is to determine
 * b_rsector from b_blocknr and b_size, and to set b_rdev from b_dev.
 * This is is appropriate for IO requests that come from the buffer
 * cache and page cache which (currently) always use aligned blocks.
 */
void submit_bh(int rw, struct buffer_head * bh)
{
	if (!test_bit(BH_Lock, &bh->b_state))
		BUG();

	set_bit(BH_Req, &bh->b_state);

	/*
	 * First step, 'identity mapping' - RAID or LVM might
	 * further remap this.
	 */
	bh->b_rdev = bh->b_dev;
	bh->b_rsector = bh->b_blocknr * (bh->b_size>>9);

	generic_make_request(rw, bh);

	switch (rw) {
		case WRITE:
			kstat.pgpgout++;
			break;
		default:
			kstat.pgpgin++;
			break;
	}
}

/*
 * Default IO end handler, used by "ll_rw_block()".
 */
static void end_buffer_io_sync(struct buffer_head *bh, int uptodate)
{
	mark_buffer_uptodate(bh, uptodate);
	unlock_buffer(bh);
}

/**
 * ll_rw_block: low-level access to block devices
 * @rw: whether to %READ or %WRITE or maybe %READA (readahead)
 * @nr: number of &struct buffer_heads in the array
 * @bhs: array of pointers to &struct buffer_head
 *
 * ll_rw_block() takes an array of pointers to &struct buffer_heads,
 * and requests an I/O operation on them, either a %READ or a %WRITE.
 * The third %READA option is described in the documentation for
 * generic_make_request() which ll_rw_block() calls.
 *
 * This function provides extra functionality that is not in
 * generic_make_request() that is relevant to buffers in the buffer
 * cache or page cache.  In particular it drops any buffer that it
 * cannot get a lock on (with the BH_Lock state bit), any buffer that
 * appears to be clean when doing a write request, and any buffer that
 * appears to be up-to-date when doing read request.  Further it marks
 * as clean buffers that are processed for writing (the buffer cache
 * wont assume that they are actually clean until the buffer gets
 * unlocked).
 *
 * ll_rw_block sets b_end_io to simple completion handler that marks
 * the buffer up-to-date (if approriate), unlocks the buffer and wakes
 * any waiters.  As client that needs a more interesting completion
 * routine should call submit_bh() (or generic_make_request())
 * directly.
 *
 * Caveat:
 *  All of the buffers must be for the same device, and must also be
 *  of the current approved size for the device.  */

void ll_rw_block(int rw, int nr, struct buffer_head * bhs[])
{
	unsigned int major;
	int correct_size;
	int i;

	major = MAJOR(bhs[0]->b_dev);

	/* Determine correct block size for this device. */
	correct_size = BLOCK_SIZE;
	if (blksize_size[major]) {
		i = blksize_size[major][MINOR(bhs[0]->b_dev)];
		if (i)
			correct_size = i;
	}

	/* Verify requested block sizes. */
	for (i = 0; i < nr; i++) {
		struct buffer_head *bh;
		bh = bhs[i];
		if (bh->b_size != correct_size) {
			printk(KERN_NOTICE "ll_rw_block: device %s: "
			       "only %d-char blocks implemented (%u)\n",
			       kdevname(bhs[0]->b_dev),
			       correct_size, bh->b_size);
			goto sorry;
		}
	}

	if ((rw & WRITE) && is_read_only(bhs[0]->b_dev)) {
		printk(KERN_NOTICE "Can't write to read-only device %s\n",
		       kdevname(bhs[0]->b_dev));
		goto sorry;
	}

	for (i = 0; i < nr; i++) {
		struct buffer_head *bh;
		bh = bhs[i];

		/* Only one thread can actually submit the I/O. */
		if (test_and_set_bit(BH_Lock, &bh->b_state))
			continue;

		/* We have the buffer lock */
		bh->b_end_io = end_buffer_io_sync;

		switch(rw) {
		case WRITE:
			if (!atomic_set_buffer_clean(bh))
				/* Hmmph! Nothing to write */
				goto end_io;
			__mark_buffer_clean(bh);
			break;

		case READA:
		case READ:
			if (buffer_uptodate(bh))
				/* Hmmph! Already have it */
				goto end_io;
			break;
		default:
			BUG();
	end_io:
			bh->b_end_io(bh, test_bit(BH_Uptodate, &bh->b_state));
			continue;
		}

		submit_bh(rw, bh);
	}
	return;

sorry:
	/* Make sure we don't get infinite dirty retries.. */
	for (i = 0; i < nr; i++)
		mark_buffer_clean(bhs[i]);
}

#ifdef CONFIG_STRAM_SWAP
extern int stram_device_init (void);
#endif

/*
 * First step of what used to be end_request
 *
 * 0 means continue with end_that_request_last,
 * 1 means we are done
 */

int end_that_request_first (struct request *req, int uptodate, char *name)
{
	struct buffer_head * bh;
	int nsect;

	req->errors = 0;
	if (!uptodate)
		printk("end_request: I/O error, dev %s (%s), sector %lu\n",
			kdevname(req->rq_dev), name, req->sector);

	if ((bh = req->bh) != NULL) {
		nsect = bh->b_size >> 9;
		req->bh = bh->b_reqnext;
		bh->b_reqnext = NULL;
		bh->b_end_io(bh, uptodate);
		if ((bh = req->bh) != NULL) {
			req->hard_sector += nsect;
			req->hard_nr_sectors -= nsect;
			req->sector = req->hard_sector;
			req->nr_sectors = req->hard_nr_sectors;

			req->current_nr_sectors = bh->b_size >> 9;
			if (req->nr_sectors < req->current_nr_sectors) {
				req->nr_sectors = req->current_nr_sectors;
				printk("end_request: buffer-list destroyed\n");
			}
			req->buffer = bh->b_data;
			return 1;
		}
	}
	return 0;
}

void end_that_request_last(struct request *req)
{
	if (req->e) {
		printk("end_that_request_last called with non-dequeued req\n");
		BUG();
	}
	if (req->sem != NULL)
		up(req->sem);

	blkdev_release_request(req);
}

int __init blk_dev_init(void)
{
	struct blk_dev_struct *dev;

	request_cachep = kmem_cache_create("blkdev_requests",
					   sizeof(struct request),
					   0, SLAB_HWCACHE_ALIGN, NULL, NULL);

	if (!request_cachep)
		panic("Can't create request pool slab cache\n");

	for (dev = blk_dev + MAX_BLKDEV; dev-- != blk_dev;)
		dev->queue = NULL;

	memset(ro_bits,0,sizeof(ro_bits));
	memset(max_readahead, 0, sizeof(max_readahead));
	memset(max_sectors, 0, sizeof(max_sectors));
#ifdef CONFIG_AMIGA_Z2RAM
	z2_init();
#endif
#ifdef CONFIG_STRAM_SWAP
	stram_device_init();
#endif
#ifdef CONFIG_BLK_DEV_RAM
	rd_init();
#endif
#ifdef CONFIG_BLK_DEV_LOOP
	loop_init();
#endif
#ifdef CONFIG_ISP16_CDI
	isp16_init();
#endif
#if defined(CONFIG_IDE) && defined(CONFIG_BLK_DEV_IDE)
	ide_init();		/* this MUST precede hd_init */
#endif
#if defined(CONFIG_IDE) && defined(CONFIG_BLK_DEV_HD)
	hd_init();
#endif
#ifdef CONFIG_BLK_DEV_PS2
	ps2esdi_init();
#endif
#ifdef CONFIG_BLK_DEV_XD
	xd_init();
#endif
#ifdef CONFIG_BLK_DEV_MFM
	mfm_init();
#endif
#ifdef CONFIG_PARIDE
	{ extern void paride_init(void); paride_init(); };
#endif
#ifdef CONFIG_MAC_FLOPPY
	swim3_init();
#endif
#ifdef CONFIG_BLK_DEV_SWIM_IOP
	swimiop_init();
#endif
#ifdef CONFIG_AMIGA_FLOPPY
	amiga_floppy_init();
#endif
#ifdef CONFIG_ATARI_FLOPPY
	atari_floppy_init();
#endif
#ifdef CONFIG_BLK_DEV_FD
	floppy_init();
#else
#if defined(__i386__)	/* Do we even need this? */
	outb_p(0xc, 0x3f2);
#endif
#endif
#ifdef CONFIG_CDU31A
	cdu31a_init();
#endif
#ifdef CONFIG_ATARI_ACSI
	acsi_init();
#endif
#ifdef CONFIG_MCD
	mcd_init();
#endif
#ifdef CONFIG_MCDX
	mcdx_init();
#endif
#ifdef CONFIG_SBPCD
	sbpcd_init();
#endif
#ifdef CONFIG_AZTCD
	aztcd_init();
#endif
#ifdef CONFIG_CDU535
	sony535_init();
#endif
#ifdef CONFIG_GSCD
	gscd_init();
#endif
#ifdef CONFIG_CM206
	cm206_init();
#endif
#ifdef CONFIG_OPTCD
	optcd_init();
#endif
#ifdef CONFIG_SJCD
	sjcd_init();
#endif
#ifdef CONFIG_APBLOCK
	ap_init();
#endif
#ifdef CONFIG_DDV
	ddv_init();
#endif
#ifdef CONFIG_BLK_DEV_NBD
	nbd_init();
#endif
#ifdef CONFIG_MDISK
	mdisk_init();
#endif
#ifdef CONFIG_DASD
	dasd_init();
#endif
#ifdef CONFIG_SUN_JSFLASH
	jsfd_init();
#endif
#ifdef CONFIG_BLK_DEV_LVM
	lvm_init();
#endif
	return 0;
};

EXPORT_SYMBOL(io_request_lock);
EXPORT_SYMBOL(end_that_request_first);
EXPORT_SYMBOL(end_that_request_last);
EXPORT_SYMBOL(blk_init_queue);
EXPORT_SYMBOL(blk_get_queue);
EXPORT_SYMBOL(blk_cleanup_queue);
EXPORT_SYMBOL(blk_queue_headactive);
EXPORT_SYMBOL(blk_queue_pluggable);
EXPORT_SYMBOL(blk_queue_make_request);
EXPORT_SYMBOL(generic_make_request);
EXPORT_SYMBOL(blkdev_release_request);