sd.c

Linux Kernel 2.6.9 for OMAP1710

/*
 *      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/config.h>
#include <linux/module.h>
#include <linux/fs.h>
#include <linux/kernel.h>
#include <linux/sched.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/kref.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/scsi_request.h>
#include <scsi/scsicam.h>

#include "scsi_logging.h"

/*
 * More than enough for everybody ;)  The huge number of majors
 * is a leftover from 16bit dev_t days, we don't really need that
 * much numberspace.
 */
#define SD_MAJORS	16

/*
 * This is limited by the naming scheme enforced in sd_probe,
 * add another character to it if you really need more disks.
 */
#define SD_MAX_DISKS	(((26 * 26) + 26 + 1) * 26)

/*
 * Time out in seconds for disks and Magneto-opticals (which are slower).
 */
#define SD_TIMEOUT		(30 * HZ)
#define SD_MOD_TIMEOUT		(75 * HZ)

/*
 * Number of allowed retries
 */
#define SD_MAX_RETRIES		5

static void scsi_disk_release(struct kref *kref);

struct scsi_disk {
	struct scsi_driver *driver;	/* always &sd_template */
	struct scsi_device *device;
	struct kref	kref;
	struct gendisk	*disk;
	unsigned int	openers;	/* protected by BKL for now, yuck */
	sector_t	capacity;	/* size in 512-byte sectors */
	u32		index;
	u8		media_present;
	u8		write_prot;
	unsigned	WCE : 1;	/* state of disk WCE bit */
	unsigned	RCD : 1;	/* state of disk RCD bit, unused */
};

static DEFINE_IDR(sd_index_idr);
static spinlock_t sd_index_lock = SPIN_LOCK_UNLOCKED;

/* 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 DECLARE_MUTEX(sd_ref_sem);

static int sd_revalidate_disk(struct gendisk *disk);
static void sd_rw_intr(struct scsi_cmnd * SCpnt);

static int sd_probe(struct device *);
static int sd_remove(struct device *);
static void sd_shutdown(struct device *dev);
static void sd_rescan(struct device *);
static int sd_init_command(struct scsi_cmnd *);
static int sd_issue_flush(struct device *, sector_t *);
static void sd_read_capacity(struct scsi_disk *sdkp, char *diskname,
		 struct scsi_request *SRpnt, unsigned char *buffer);

static struct scsi_driver sd_template = {
	.owner			= THIS_MODULE,
	.gendrv = {
		.name		= "sd",
		.probe		= sd_probe,
		.remove		= sd_remove,
		.shutdown	= sd_shutdown,
	},
	.rescan			= sd_rescan,
	.init_command		= sd_init_command,
	.issue_flush		= sd_issue_flush,
};

/*
 * 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 */
	}
}

#define to_scsi_disk(obj) container_of(obj,struct scsi_disk,kref)

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;

	down(&sd_ref_sem);
	if (disk->private_data == NULL)
		goto out;
	sdkp = scsi_disk(disk);
	kref_get(&sdkp->kref);
	if (scsi_device_get(sdkp->device))
		goto out_put;
	up(&sd_ref_sem);
	return sdkp;

 out_put:
	kref_put(&sdkp->kref, scsi_disk_release);
	sdkp = NULL;
 out:
	up(&sd_ref_sem);
	return sdkp;
}

static void scsi_disk_put(struct scsi_disk *sdkp)
{
	down(&sd_ref_sem);
	scsi_device_put(sdkp->device);
	kref_put(&sdkp->kref, scsi_disk_release);
	up(&sd_ref_sem);
}

/**
 *	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_init_command(struct scsi_cmnd * SCpnt)
{
	unsigned int this_count, timeout;
	struct gendisk *disk;
	sector_t block;
	struct scsi_device *sdp = SCpnt->device;

	timeout = sdp->timeout;

	/*
	 * these are already setup, just copy cdb basically
	 */
	if (SCpnt->request->flags & REQ_BLOCK_PC) {
		struct request *rq = SCpnt->request;

		if (sizeof(rq->cmd) > sizeof(SCpnt->cmnd))
			return 0;

		memcpy(SCpnt->cmnd, rq->cmd, sizeof(SCpnt->cmnd));
		if (rq_data_dir(rq) == WRITE)
			SCpnt->sc_data_direction = DMA_TO_DEVICE;
		else if (rq->data_len)
			SCpnt->sc_data_direction = DMA_FROM_DEVICE;
		else
			SCpnt->sc_data_direction = DMA_NONE;

		this_count = rq->data_len;
		if (rq->timeout)
			timeout = rq->timeout;

		SCpnt->transfersize = rq->data_len;
		goto queue;
	}

	/*
	 * we only do REQ_CMD and REQ_BLOCK_PC
	 */
	if (!(SCpnt->request->flags & REQ_CMD))
		return 0;

	disk = SCpnt->request->rq_disk;
	block = SCpnt->request->sector;
	this_count = SCpnt->request_bufflen >> 9;

	SCSI_LOG_HLQUEUE(1, printk("sd_init_command: disk=%s, block=%llu, "
			    "count=%d\n", disk->disk_name, (unsigned long long)block, this_count));

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

	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"); */
		return 0;
	}
	SCSI_LOG_HLQUEUE(2, printk("%s : block=%llu\n",
				   disk->disk_name, (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) || (SCpnt->request->nr_sectors & 1)) {
			printk(KERN_ERR "sd: Bad block number requested");
			return 0;
		} else {
			block = block >> 1;
			this_count = this_count >> 1;
		}
	}
	if (sdp->sector_size == 2048) {
		if ((block & 3) || (SCpnt->request->nr_sectors & 3)) {
			printk(KERN_ERR "sd: Bad block number requested");
			return 0;
		} else {
			block = block >> 2;
			this_count = this_count >> 2;
		}
	}
	if (sdp->sector_size == 4096) {
		if ((block & 7) || (SCpnt->request->nr_sectors & 7)) {
			printk(KERN_ERR "sd: Bad block number requested");
			return 0;
		} else {
			block = block >> 3;
			this_count = this_count >> 3;
		}
	}
	if (rq_data_dir(SCpnt->request) == WRITE) {
		if (!sdp->writeable) {
			return 0;
		}
		SCpnt->cmnd[0] = WRITE_6;
		SCpnt->sc_data_direction = DMA_TO_DEVICE;
	} else if (rq_data_dir(SCpnt->request) == READ) {
		SCpnt->cmnd[0] = READ_6;
		SCpnt->sc_data_direction = DMA_FROM_DEVICE;
	} else {
		printk(KERN_ERR "sd: Unknown command %lx\n", 
		       SCpnt->request->flags);
/* overkill 	panic("Unknown sd command %lx\n", SCpnt->request->flags); */
		return 0;
	}

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

	SCpnt->cmnd[1] = 0;
	
	if (block > 0xffffffff) {
		SCpnt->cmnd[0] += READ_16 - READ_6;
		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) ||
		   SCpnt->device->use_10_for_rw) {
		if (this_count > 0xffff)
			this_count = 0xffff;

		SCpnt->cmnd[0] += READ_10 - READ_6;
		SCpnt->cmnd[2] = (unsigned char) (block >> 24) & 0xff;
		SCpnt->cmnd[3] = (unsigned char) (block >> 16) & 0xff;
		SCpnt->cmnd[4] = (unsigned char) (block >> 8) & 0xff;
		SCpnt->cmnd[5] = (unsigned char) block & 0xff;
		SCpnt->cmnd[6] = SCpnt->cmnd[9] = 0;
		SCpnt->cmnd[7] = (unsigned char) (this_count >> 8) & 0xff;
		SCpnt->cmnd[8] = (unsigned char) this_count & 0xff;
	} else {
		if (this_count > 0xff)
			this_count = 0xff;

		SCpnt->cmnd[1] |= (unsigned char) ((block >> 16) & 0x1f);
		SCpnt->cmnd[2] = (unsigned char) ((block >> 8) & 0xff);
		SCpnt->cmnd[3] = (unsigned char) block & 0xff;
		SCpnt->cmnd[4] = (unsigned char) this_count;
		SCpnt->cmnd[5] = 0;
	}
	SCpnt->request_bufflen = SCpnt->bufflen =
			this_count * sdp->sector_size;

	/*
	 * We shouldn't disconnect in the middle of a sector, so with a dumb
	 * host adapter, it's safe to assume that we can at least transfer
	 * this many bytes between each connect / disconnect.
	 */
	SCpnt->transfersize = sdp->sector_size;
	SCpnt->underflow = this_count << 9;

queue:
	SCpnt->allowed = SD_MAX_RETRIES;
	SCpnt->timeout_per_command = timeout;

	/*
	 * This is the completion routine we use.  This is matched in terms
	 * of capability to this function.
	 */
	SCpnt->done = sd_rw_intr;

	/*
	 * This indicates that the command is ready from our end to be
	 * queued.
	 */
	return 1;
}

/**
 *	sd_open - open a scsi disk device
 *	@inode: only i_rdev member may be used
 *	@filp: only f_mode and f_flags may be used
 *
 *	Returns 0 if successful. Returns a negated errno value in case 
 *	of error.
 *
 *	Note: This can be called from a user context (e.g. fsck(1) )
 *	or from within the kernel (e.g. as a result of a mount(1) ).
 *	In the latter case @inode and @filp carry an abridged amount
 *	of information as noted above.
 **/
static int sd_open(struct inode *inode, struct file *filp)
{
	struct gendisk *disk = inode->i_bdev->bd_disk;
	struct scsi_disk *sdkp;
	struct scsi_device *sdev;
	int retval;

	if (!(sdkp = scsi_disk_get(disk)))
		return -ENXIO;


	SCSI_LOG_HLQUEUE(3, printk("sd_open: disk=%s\n", disk->disk_name));

	sdev = sdkp->device;

	/*
	 * If the device is in error recovery, wait until it is done.
	 * If the device is offline, then disallow any access to it.
	 */
	retval = -ENXIO;
	if (!scsi_block_when_processing_errors(sdev))
		goto error_out;

	if (sdev->removable || sdkp->write_prot)
		check_disk_change(inode->i_bdev);

	/*
	 * If the drive is empty, just let the open fail.
	 */
	retval = -ENOMEDIUM;
	if (sdev->removable && !sdkp->media_present &&
	    !(filp->f_flags & O_NDELAY))
		goto error_out;

	/*
	 * If the device has the write protect tab set, have the open fail
	 * if the user expects to be able to write to the thing.
	 */
	retval = -EROFS;
	if (sdkp->write_prot && (filp->f_mode & FMODE_WRITE))
		goto error_out;

	/*
	 * It is possible that the disk changing stuff resulted in
	 * the device being taken offline.  If this is the case,
	 * report this to the user, and don't pretend that the
	 * open actually succeeded.
	 */
	retval = -ENXIO;
	if (!scsi_device_online(sdev))
		goto error_out;

	if (!sdkp->openers++ && sdev->removable) {
		if (scsi_block_when_processing_errors(sdev))
			scsi_set_medium_removal(sdev, SCSI_REMOVAL_PREVENT);
	}

	return 0;

error_out:
	scsi_disk_put(sdkp);
	return retval;	
}

/**
 *	sd_release - invoked when the (last) close(2) is called on this
 *	scsi disk.
 *	@inode: only i_rdev member may be used
 *	@filp: only f_mode and f_flags may be used
 *
 *	Returns 0. 
 *
 *	Note: may block (uninterruptible) if error recovery is underway
 *	on this disk.
 **/
static int sd_release(struct inode *inode, struct file *filp)
{
	struct gendisk *disk = inode->i_bdev->bd_disk;
	struct scsi_disk *sdkp = scsi_disk(disk);
	struct scsi_device *sdev = sdkp->device;

	SCSI_LOG_HLQUEUE(3, printk("sd_release: disk=%s\n", disk->disk_name));

	if (!--sdkp->openers && sdev->removable) {
		if (scsi_block_when_processing_errors(sdev))
			scsi_set_medium_removal(sdev, SCSI_REMOVAL_ALLOW);
	}

	/*
	 * XXX and what if there are packets in flight and this close()
	 * XXX is followed by a "rmmod sd_mod"?
	 */
	scsi_disk_put(sdkp);
	return 0;
}

static int sd_hdio_getgeo(struct block_device *bdev, struct hd_geometry __user *loc)
{
	struct scsi_disk *sdkp = scsi_disk(bdev->bd_disk);
	struct scsi_device *sdp = sdkp->device;
	struct Scsi_Host *host = sdp->host;
	int diskinfo[4];

	/* default to most commonly used values */
        diskinfo[0] = 0x40;	/* 1 << 6 */
       	diskinfo[1] = 0x20;	/* 1 << 5 */
       	diskinfo[2] = sdkp->capacity >> 11;
	
	/* override with calculated, extended default, or driver values */
	if (host->hostt->bios_param)
		host->hostt->bios_param(sdp, bdev, sdkp->capacity, diskinfo);
	else
		scsicam_bios_param(bdev, sdkp->capacity, diskinfo);

	if (put_user(diskinfo[0], &loc->heads))
		return -EFAULT;
	if (put_user(diskinfo[1], &loc->sectors))
		return -EFAULT;
	if (put_user(diskinfo[2], &loc->cylinders))
		return -EFAULT;
	if (put_user((unsigned)get_start_sect(bdev),