/*	$NetBSD: subr_disk.c,v 1.14 1995/12/28 19:16:39 thorpej Exp $	*/

/*
 * Copyright (c) 1982, 1986, 1988, 1993
 *	The Regents of the University of California.  All rights reserved.
 * (c) UNIX System Laboratories, Inc.
 * All or some portions of this file are derived from material licensed
 * to the University of California by American Telephone and Telegraph
 * Co. or Unix System Laboratories, Inc. and are reproduced herein with
 * the permission of UNIX System Laboratories, Inc.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 3. All advertising materials mentioning features or use of this software
 *    must display the following acknowledgement:
 *	This product includes software developed by the University of
 *	California, Berkeley and its contributors.
 * 4. Neither the name of the University nor the names of its contributors
 *    may be used to endorse or promote products derived from this software
 *    without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 *
 *	@(#)ufs_disksubr.c	8.5 (Berkeley) 1/21/94
 */

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/buf.h>
#include <sys/disklabel.h>
#include <sys/syslog.h>
#include <sys/dkstat.h>		/* XXX */

/*
 * Old-style disk instrumentation structures.  These will go away
 * someday.
 */
long	dk_seek[DK_NDRIVE];
long	dk_time[DK_NDRIVE];
long	dk_wds[DK_NDRIVE];
long	dk_wpms[DK_NDRIVE];
long	dk_xfer[DK_NDRIVE];
int	dk_busy;
int	dk_ndrive = DK_NDRIVE;
int	dkn;			/* number of slots filled so far */

/*
 * Seek sort for disks.  We depend on the driver which calls us using b_resid
 * as the current cylinder number.
 *
 * The argument ap structure holds a b_actf activity chain pointer on which we
 * keep two queues, sorted in ascending cylinder order.  The first queue holds
 * those requests which are positioned after the current cylinder (in the first
 * request); the second holds requests which came in after their cylinder number
 * was passed.  Thus we implement a one way scan, retracting after reaching the
 * end of the drive to the first request on the second queue, at which time it
 * becomes the first queue.
 *
 * A one-way scan is natural because of the way UNIX read-ahead blocks are
 * allocated.
 */

void
disksort(ap, bp)
	register struct buf *ap, *bp;
{
	register struct buf *bq;

	/* If the queue is empty, then it's easy. */
	if (ap->b_actf == NULL) {
		bp->b_actf = NULL;
		ap->b_actf = bp;
		return;
	}

	/*
	 * If we lie after the first (currently active) request, then we
	 * must locate the second request list and add ourselves to it.
	 */
	bq = ap->b_actf;
	if (bp->b_cylinder < bq->b_cylinder) {
		while (bq->b_actf) {
			/*
			 * Check for an ``inversion'' in the normally ascending
			 * cylinder numbers, indicating the start of the second
			 * request list.
			 */
			if (bq->b_actf->b_cylinder < bq->b_cylinder) {
				/*
				 * Search the second request list for the first
				 * request at a larger cylinder number.  We go
				 * before that; if there is no such request, we
				 * go at end.
				 */
				do {
					if (bp->b_cylinder <
					    bq->b_actf->b_cylinder)
						goto insert;
					if (bp->b_cylinder ==
					    bq->b_actf->b_cylinder &&
					    bp->b_blkno < bq->b_actf->b_blkno)
						goto insert;
					bq = bq->b_actf;
				} while (bq->b_actf);
				goto insert;		/* after last */
			}
			bq = bq->b_actf;
		}
		/*
		 * No inversions... we will go after the last, and
		 * be the first request in the second request list.
		 */
		goto insert;
	}
	/*
	 * Request is at/after the current request...
	 * sort in the first request list.
	 */
	while (bq->b_actf) {
		/*
		 * We want to go after the current request if there is an
		 * inversion after it (i.e. it is the end of the first
		 * request list), or if the next request is a larger cylinder
		 * than our request.
		 */
		if (bq->b_actf->b_cylinder < bq->b_cylinder ||
		    bp->b_cylinder < bq->b_actf->b_cylinder ||
		    (bp->b_cylinder == bq->b_actf->b_cylinder &&
		    bp->b_blkno < bq->b_actf->b_blkno))
			goto insert;
		bq = bq->b_actf;
	}
	/*
	 * Neither a second list nor a larger request... we go at the end of
	 * the first list, which is the same as the end of the whole schebang.
	 */
insert:	bp->b_actf = bq->b_actf;
	bq->b_actf = bp;
}

/* encoding of disk minor numbers, should be elsewhere... */
#define dkunit(dev)		(minor(dev) >> 3)
#define dkpart(dev)		(minor(dev) & 07)
#define dkminor(unit, part)	(((unit) << 3) | (part))

/*
 * Compute checksum for disk label.
 */
u_int
dkcksum(lp)
	register struct disklabel *lp;
{
	register u_short *start, *end;
	register u_short sum = 0;

	start = (u_short *)lp;
	end = (u_short *)&lp->d_partitions[lp->d_npartitions];
	while (start < end)
		sum ^= *start++;
	return (sum);
}

/*
 * Disk error is the preface to plaintive error messages
 * about failing disk transfers.  It prints messages of the form

hp0g: hard error reading fsbn 12345 of 12344-12347 (hp0 bn %d cn %d tn %d sn %d)

 * if the offset of the error in the transfer and a disk label
 * are both available.  blkdone should be -1 if the position of the error
 * is unknown; the disklabel pointer may be null from drivers that have not
 * been converted to use them.  The message is printed with printf
 * if pri is LOG_PRINTF, otherwise it uses log at the specified priority.
 * The message should be completed (with at least a newline) with printf
 * or addlog, respectively.  There is no trailing space.
 */
void
diskerr(bp, dname, what, pri, blkdone, lp)
	register struct buf *bp;
	char *dname, *what;
	int pri, blkdone;
	register struct disklabel *lp;
{
	int unit = dkunit(bp->b_dev), part = dkpart(bp->b_dev);
	register void (*pr) __P((const char *, ...));
	char partname = 'a' + part;
	int sn;

	if (pri != LOG_PRINTF) {
		log(pri, "");
		pr = addlog;
	} else
		pr = printf;
	(*pr)("%s%d%c: %s %sing fsbn ", dname, unit, partname, what,
	    bp->b_flags & B_READ ? "read" : "writ");
	sn = bp->b_blkno;
	if (bp->b_bcount <= DEV_BSIZE)
		(*pr)("%d", sn);
	else {
		if (blkdone >= 0) {
			sn += blkdone;
			(*pr)("%d of ", sn);
		}
		(*pr)("%d-%d", bp->b_blkno,
		    bp->b_blkno + (bp->b_bcount - 1) / DEV_BSIZE);
	}
	if (lp && (blkdone >= 0 || bp->b_bcount <= lp->d_secsize)) {
#ifdef tahoe
		sn *= DEV_BSIZE / lp->d_secsize;		/* XXX */
#endif
		sn += lp->d_partitions[part].p_offset;
		(*pr)(" (%s%d bn %d; cn %d", dname, unit, sn,
		    sn / lp->d_secpercyl);
		sn %= lp->d_secpercyl;
		(*pr)(" tn %d sn %d)", sn / lp->d_nsectors, sn % lp->d_nsectors);
	}
}