sd.c

linux 内核源代码

/*
 *      sd.c Copyright (C) 1992 Drew Eckhardt
 *           Copyright (C) 1993, 1994, 1995, 1999 Eric Youngdale
 *
 *      Linux scsi disk driver
 *              Initial versions: Drew Eckhardt
 *              Subsequent revisions: Eric Youngdale
 *	Modification history:
 *       - Drew Eckhardt <[e-mail]> original
 *       - Eric Youngdale <[e-mail]> add scatter-gather, multiple 
 *         outstanding request, and other enhancements.
 *         Support loadable low-level scsi drivers.
 *       - Jirka Hanika <[e-mail]> support more scsi disks using 
 *         eight major numbers.
 *       - Richard Gooch <[e-mail]> support devfs.
 *	 - Torben Mathiasen <[e-mail]> Resource allocation fixes in 
 *	   sd_init and cleanups.
 *	 - Alex Davis <[e-mail]> Fix problem where partition info
 *	   not being read in sd_open. Fix problem where removable media 
 *	   could be ejected after sd_open.
 *	 - Douglas Gilbert <[e-mail]> cleanup for lk 2.5.x
 *	 - Badari Pulavarty <[e-mail]>, Matthew Wilcox 
 *	   <[e-mail]>, Kurt Garloff <[e-mail]>: 
 *	   Support 32k/1M disks.
 *
 *	Logging policy (needs CONFIG_SCSI_LOGGING defined):
 *	 - setting up transfer: SCSI_LOG_HLQUEUE levels 1 and 2
 *	 - end of transfer (bh + scsi_lib): SCSI_LOG_HLCOMPLETE level 1
 *	 - entering sd_ioctl: SCSI_LOG_IOCTL level 1
 *	 - entering other commands: SCSI_LOG_HLQUEUE level 3
 *	Note: when the logging level is set by the user, it must be greater
 *	than the level indicated above to trigger output.	
 */

#include <linux/module.h>
#include <linux/fs.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/bio.h>
#include <linux/genhd.h>
#include <linux/hdreg.h>
#include <linux/errno.h>
#include <linux/idr.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/blkdev.h>
#include <linux/blkpg.h>
#include <linux/delay.h>
#include <linux/mutex.h>
#include <asm/uaccess.h>

#include <scsi/scsi.h>
#include <scsi/scsi_cmnd.h>
#include <scsi/scsi_dbg.h>
#include <scsi/scsi_device.h>
#include <scsi/scsi_driver.h>
#include <scsi/scsi_eh.h>
#include <scsi/scsi_host.h>
#include <scsi/scsi_ioctl.h>
#include <scsi/scsicam.h>
#include <scsi/sd.h>

#include "scsi_logging.h"

MODULE_AUTHOR("Eric Youngdale");
MODULE_DESCRIPTION("SCSI disk (sd) driver");
MODULE_LICENSE("GPL");

MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK0_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK1_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK2_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK3_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK4_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK5_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK6_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK7_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK8_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK9_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK10_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK11_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK12_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK13_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK14_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK15_MAJOR);
MODULE_ALIAS_SCSI_DEVICE(TYPE_DISK);
MODULE_ALIAS_SCSI_DEVICE(TYPE_MOD);
MODULE_ALIAS_SCSI_DEVICE(TYPE_RBC);

static int  sd_revalidate_disk(struct gendisk *);
static int  sd_probe(struct device *);
static int  sd_remove(struct device *);
static void sd_shutdown(struct device *);
static int sd_suspend(struct device *, pm_message_t state);
static int sd_resume(struct device *);
static void sd_rescan(struct device *);
static int sd_done(struct scsi_cmnd *);
static void sd_read_capacity(struct scsi_disk *sdkp, unsigned char *buffer);
static void scsi_disk_release(struct class_device *cdev);
static void sd_print_sense_hdr(struct scsi_disk *, struct scsi_sense_hdr *);
static void sd_print_result(struct scsi_disk *, int);

static DEFINE_IDR(sd_index_idr);
static DEFINE_SPINLOCK(sd_index_lock);

/* This semaphore is used to mediate the 0->1 reference get in the
 * face of object destruction (i.e. we can't allow a get on an
 * object after last put) */
static DEFINE_MUTEX(sd_ref_mutex);

static const char *sd_cache_types[] = {
	"write through", "none", "write back",
	"write back, no read (daft)"
};

static ssize_t sd_store_cache_type(struct class_device *cdev, const char *buf,
				   size_t count)
{
	int i, ct = -1, rcd, wce, sp;
	struct scsi_disk *sdkp = to_scsi_disk(cdev);
	struct scsi_device *sdp = sdkp->device;
	char buffer[64];
	char *buffer_data;
	struct scsi_mode_data data;
	struct scsi_sense_hdr sshdr;
	int len;

	if (sdp->type != TYPE_DISK)
		/* no cache control on RBC devices; theoretically they
		 * can do it, but there's probably so many exceptions
		 * it's not worth the risk */
		return -EINVAL;

	for (i = 0; i < ARRAY_SIZE(sd_cache_types); i++) {
		const int len = strlen(sd_cache_types[i]);
		if (strncmp(sd_cache_types[i], buf, len) == 0 &&
		    buf[len] == '\n') {
			ct = i;
			break;
		}
	}
	if (ct < 0)
		return -EINVAL;
	rcd = ct & 0x01 ? 1 : 0;
	wce = ct & 0x02 ? 1 : 0;
	if (scsi_mode_sense(sdp, 0x08, 8, buffer, sizeof(buffer), SD_TIMEOUT,
			    SD_MAX_RETRIES, &data, NULL))
		return -EINVAL;
	len = min_t(size_t, sizeof(buffer), data.length - data.header_length -
		  data.block_descriptor_length);
	buffer_data = buffer + data.header_length +
		data.block_descriptor_length;
	buffer_data[2] &= ~0x05;
	buffer_data[2] |= wce << 2 | rcd;
	sp = buffer_data[0] & 0x80 ? 1 : 0;

	if (scsi_mode_select(sdp, 1, sp, 8, buffer_data, len, SD_TIMEOUT,
			     SD_MAX_RETRIES, &data, &sshdr)) {
		if (scsi_sense_valid(&sshdr))
			sd_print_sense_hdr(sdkp, &sshdr);
		return -EINVAL;
	}
	sd_revalidate_disk(sdkp->disk);
	return count;
}

static ssize_t sd_store_manage_start_stop(struct class_device *cdev,
					  const char *buf, size_t count)
{
	struct scsi_disk *sdkp = to_scsi_disk(cdev);
	struct scsi_device *sdp = sdkp->device;

	if (!capable(CAP_SYS_ADMIN))
		return -EACCES;

	sdp->manage_start_stop = simple_strtoul(buf, NULL, 10);

	return count;
}

static ssize_t sd_store_allow_restart(struct class_device *cdev, const char *buf,
				      size_t count)
{
	struct scsi_disk *sdkp = to_scsi_disk(cdev);
	struct scsi_device *sdp = sdkp->device;

	if (!capable(CAP_SYS_ADMIN))
		return -EACCES;

	if (sdp->type != TYPE_DISK)
		return -EINVAL;

	sdp->allow_restart = simple_strtoul(buf, NULL, 10);

	return count;
}

static ssize_t sd_show_cache_type(struct class_device *cdev, char *buf)
{
	struct scsi_disk *sdkp = to_scsi_disk(cdev);
	int ct = sdkp->RCD + 2*sdkp->WCE;

	return snprintf(buf, 40, "%s\n", sd_cache_types[ct]);
}

static ssize_t sd_show_fua(struct class_device *cdev, char *buf)
{
	struct scsi_disk *sdkp = to_scsi_disk(cdev);

	return snprintf(buf, 20, "%u\n", sdkp->DPOFUA);
}

static ssize_t sd_show_manage_start_stop(struct class_device *cdev, char *buf)
{
	struct scsi_disk *sdkp = to_scsi_disk(cdev);
	struct scsi_device *sdp = sdkp->device;

	return snprintf(buf, 20, "%u\n", sdp->manage_start_stop);
}

static ssize_t sd_show_allow_restart(struct class_device *cdev, char *buf)
{
	struct scsi_disk *sdkp = to_scsi_disk(cdev);

	return snprintf(buf, 40, "%d\n", sdkp->device->allow_restart);
}

static struct class_device_attribute sd_disk_attrs[] = {
	__ATTR(cache_type, S_IRUGO|S_IWUSR, sd_show_cache_type,
	       sd_store_cache_type),
	__ATTR(FUA, S_IRUGO, sd_show_fua, NULL),
	__ATTR(allow_restart, S_IRUGO|S_IWUSR, sd_show_allow_restart,
	       sd_store_allow_restart),
	__ATTR(manage_start_stop, S_IRUGO|S_IWUSR, sd_show_manage_start_stop,
	       sd_store_manage_start_stop),
	__ATTR_NULL,
};

static struct class sd_disk_class = {
	.name		= "scsi_disk",
	.owner		= THIS_MODULE,
	.release	= scsi_disk_release,
	.class_dev_attrs = sd_disk_attrs,
};

static struct scsi_driver sd_template = {
	.owner			= THIS_MODULE,
	.gendrv = {
		.name		= "sd",
		.probe		= sd_probe,
		.remove		= sd_remove,
		.suspend	= sd_suspend,
		.resume		= sd_resume,
		.shutdown	= sd_shutdown,
	},
	.rescan			= sd_rescan,
	.done			= sd_done,
};

/*
 * Device no to disk mapping:
 * 
 *       major         disc2     disc  p1
 *   |............|.............|....|....| <- dev_t
 *    31        20 19          8 7  4 3  0
 * 
 * Inside a major, we have 16k disks, however mapped non-
 * contiguously. The first 16 disks are for major0, the next
 * ones with major1, ... Disk 256 is for major0 again, disk 272 
 * for major1, ... 
 * As we stay compatible with our numbering scheme, we can reuse 
 * the well-know SCSI majors 8, 65--71, 136--143.
 */
static int sd_major(int major_idx)
{
	switch (major_idx) {
	case 0:
		return SCSI_DISK0_MAJOR;
	case 1 ... 7:
		return SCSI_DISK1_MAJOR + major_idx - 1;
	case 8 ... 15:
		return SCSI_DISK8_MAJOR + major_idx - 8;
	default:
		BUG();
		return 0;	/* shut up gcc */
	}
}

static inline struct scsi_disk *scsi_disk(struct gendisk *disk)
{
	return container_of(disk->private_data, struct scsi_disk, driver);
}

static struct scsi_disk *__scsi_disk_get(struct gendisk *disk)
{
	struct scsi_disk *sdkp = NULL;

	if (disk->private_data) {
		sdkp = scsi_disk(disk);
		if (scsi_device_get(sdkp->device) == 0)
			class_device_get(&sdkp->cdev);
		else
			sdkp = NULL;
	}
	return sdkp;
}

static struct scsi_disk *scsi_disk_get(struct gendisk *disk)
{
	struct scsi_disk *sdkp;

	mutex_lock(&sd_ref_mutex);
	sdkp = __scsi_disk_get(disk);
	mutex_unlock(&sd_ref_mutex);
	return sdkp;
}

static struct scsi_disk *scsi_disk_get_from_dev(struct device *dev)
{
	struct scsi_disk *sdkp;

	mutex_lock(&sd_ref_mutex);
	sdkp = dev_get_drvdata(dev);
	if (sdkp)
		sdkp = __scsi_disk_get(sdkp->disk);
	mutex_unlock(&sd_ref_mutex);
	return sdkp;
}

static void scsi_disk_put(struct scsi_disk *sdkp)
{
	struct scsi_device *sdev = sdkp->device;

	mutex_lock(&sd_ref_mutex);
	class_device_put(&sdkp->cdev);
	scsi_device_put(sdev);
	mutex_unlock(&sd_ref_mutex);
}

/**
 *	sd_init_command - build a scsi (read or write) command from
 *	information in the request structure.
 *	@SCpnt: pointer to mid-level's per scsi command structure that
 *	contains request and into which the scsi command is written
 *
 *	Returns 1 if successful and 0 if error (or cannot be done now).
 **/
static int sd_prep_fn(struct request_queue *q, struct request *rq)
{
	struct scsi_cmnd *SCpnt;
	struct scsi_device *sdp = q->queuedata;
	struct gendisk *disk = rq->rq_disk;
	sector_t block = rq->sector;
	unsigned int this_count = rq->nr_sectors;
	unsigned int timeout = sdp->timeout;
	int ret;

	if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
		ret = scsi_setup_blk_pc_cmnd(sdp, rq);
		goto out;
	} else if (rq->cmd_type != REQ_TYPE_FS) {
		ret = BLKPREP_KILL;
		goto out;
	}
	ret = scsi_setup_fs_cmnd(sdp, rq);
	if (ret != BLKPREP_OK)
		goto out;
	SCpnt = rq->special;

	/* from here on until we're complete, any goto out
	 * is used for a killable error condition */
	ret = BLKPREP_KILL;

	SCSI_LOG_HLQUEUE(1, scmd_printk(KERN_INFO, SCpnt,
					"sd_init_command: block=%llu, "
					"count=%d\n",
					(unsigned long long)block,
					this_count));

	if (!sdp || !scsi_device_online(sdp) ||
 	    block + rq->nr_sectors > get_capacity(disk)) {
		SCSI_LOG_HLQUEUE(2, scmd_printk(KERN_INFO, SCpnt,
						"Finishing %ld sectors\n",
						rq->nr_sectors));
		SCSI_LOG_HLQUEUE(2, scmd_printk(KERN_INFO, SCpnt,
						"Retry with 0x%p\n", SCpnt));
		goto out;
	}

	if (sdp->changed) {
		/*
		 * quietly refuse to do anything to a changed disc until 
		 * the changed bit has been reset
		 */
		/* printk("SCSI disk has been changed. Prohibiting further I/O.\n"); */
		goto out;
	}

	SCSI_LOG_HLQUEUE(2, scmd_printk(KERN_INFO, SCpnt, "block=%llu\n",
					(unsigned long long)block));

	/*
	 * If we have a 1K hardware sectorsize, prevent access to single
	 * 512 byte sectors.  In theory we could handle this - in fact
	 * the scsi cdrom driver must be able to handle this because
	 * we typically use 1K blocksizes, and cdroms typically have
	 * 2K hardware sectorsizes.  Of course, things are simpler
	 * with the cdrom, since it is read-only.  For performance
	 * reasons, the filesystems should be able to handle this
	 * and not force the scsi disk driver to use bounce buffers
	 * for this.
	 */
	if (sdp->sector_size == 1024) {
		if ((block & 1) || (rq->nr_sectors & 1)) {
			scmd_printk(KERN_ERR, SCpnt,
				    "Bad block number requested\n");
			goto out;
		} else {
			block = block >> 1;
			this_count = this_count >> 1;
		}
	}
	if (sdp->sector_size == 2048) {
		if ((block & 3) || (rq->nr_sectors & 3)) {
			scmd_printk(KERN_ERR, SCpnt,
				    "Bad block number requested\n");
			goto out;
		} else {
			block = block >> 2;
			this_count = this_count >> 2;
		}
	}
	if (sdp->sector_size == 4096) {
		if ((block & 7) || (rq->nr_sectors & 7)) {
			scmd_printk(KERN_ERR, SCpnt,
				    "Bad block number requested\n");
			goto out;
		} else {
			block = block >> 3;
			this_count = this_count >> 3;
		}
	}
	if (rq_data_dir(rq) == WRITE) {
		if (!sdp->writeable) {
			goto out;
		}
		SCpnt->cmnd[0] = WRITE_6;
		SCpnt->sc_data_direction = DMA_TO_DEVICE;
	} else if (rq_data_dir(rq) == READ) {
		SCpnt->cmnd[0] = READ_6;
		SCpnt->sc_data_direction = DMA_FROM_DEVICE;
	} else {
		scmd_printk(KERN_ERR, SCpnt, "Unknown command %x\n", rq->cmd_flags);
		goto out;
	}

	SCSI_LOG_HLQUEUE(2, scmd_printk(KERN_INFO, SCpnt,
					"%s %d/%ld 512 byte blocks.\n",
					(rq_data_dir(rq) == WRITE) ?
					"writing" : "reading", this_count,
					rq->nr_sectors));

	SCpnt->cmnd[1] = 0;
	
	if (block > 0xffffffff) {
		SCpnt->cmnd[0] += READ_16 - READ_6;
		SCpnt->cmnd[1] |= blk_fua_rq(rq) ? 0x8 : 0;
		SCpnt->cmnd[2] = sizeof(block) > 4 ? (unsigned char) (block >> 56) & 0xff : 0;
		SCpnt->cmnd[3] = sizeof(block) > 4 ? (unsigned char) (block >> 48) & 0xff : 0;
		SCpnt->cmnd[4] = sizeof(block) > 4 ? (unsigned char) (block >> 40) & 0xff : 0;
		SCpnt->cmnd[5] = sizeof(block) > 4 ? (unsigned char) (block >> 32) & 0xff : 0;
		SCpnt->cmnd[6] = (unsigned char) (block >> 24) & 0xff;
		SCpnt->cmnd[7] = (unsigned char) (block >> 16) & 0xff;
		SCpnt->cmnd[8] = (unsigned char) (block >> 8) & 0xff;
		SCpnt->cmnd[9] = (unsigned char) block & 0xff;
		SCpnt->cmnd[10] = (unsigned char) (this_count >> 24) & 0xff;
		SCpnt->cmnd[11] = (unsigned char) (this_count >> 16) & 0xff;
		SCpnt->cmnd[12] = (unsigned char) (this_count >> 8) & 0xff;
		SCpnt->cmnd[13] = (unsigned char) this_count & 0xff;
		SCpnt->cmnd[14] = SCpnt->cmnd[15] = 0;
	} else if ((this_count > 0xff) || (block > 0x1fffff) ||