fs.h

FSD file system driver

/*	$NetBSD: fs.h,v 1.43 2004/03/21 18:48:24 dsl Exp $	*/

/*
 * Copyright (c) 1982, 1986, 1993
 *	The Regents of the University of California.  All rights reserved.
 *
 * 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. 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.
 *
 *	@(#)fs.h	8.13 (Berkeley) 3/21/95
 */

#ifndef	_UFS_FFS_FS_H_
#define	_UFS_FFS_FS_H_

#include "type.h"

/*
 * Each disk drive contains some number of file systems.
 * A file system consists of a number of cylinder groups.
 * Each cylinder group has inodes and data.
 *
 * A file system is described by its super-block, which in turn
 * describes the cylinder groups.  The super-block is critical
 * data and is replicated in each cylinder group to protect against
 * catastrophic loss.  This is done at `newfs' time and the critical
 * super-block data does not change, so the copies need not be
 * referenced further unless disaster strikes.
 *
 * For file system fs, the offsets of the various blocks of interest
 * are given in the super block as:
 *	[fs->fs_sblkno]		Super-block
 *	[fs->fs_cblkno]		Cylinder group block
 *	[fs->fs_iblkno]		Inode blocks
 *	[fs->fs_dblkno]		Data blocks
 * The beginning of cylinder group cg in fs, is given by
 * the ``cgbase(fs, cg)'' macro.
 *
 * Depending on the architecture and the media, the superblock may
 * reside in any one of four places. For tiny media where every block 
 * counts, it is placed at the very front of the partition. Historically,
 * UFS1 placed it 8K from the front to leave room for the disk label and
 * a small bootstrap. For UFS2 it got moved to 64K from the front to leave
 * room for the disk label and a bigger bootstrap, and for really piggy
 * systems we check at 256K from the front if the first three fail. In
 * all cases the size of the superblock will be SBLOCKSIZE. All values are
 * given in byte-offset form, so they do not imply a sector size. The
 * SBLOCKSEARCH specifies the order in which the locations should be searched.
 *
 * Unfortunately the UFS2/FFSv2 change was done without adequate consideration
 * of backward compatibility.  In particular 'newfs' for a FFSv2 partition
 * must overwrite any old FFSv1 superblock at 8k, and preferrably as many
 * of the alternates as it can find - otherwise attempting to mount on a
 * system that only supports FFSv1 is likely to succeed!.
 * For a small FFSv1 filesystem, an old FFSv2 superblock can be left on
 * the disk, and a system that tries to find an FFSv2 filesystem in preference
 * to and FFSv1 one (as NetBSD does) can mount the old FFSv2 filesystem.
 * As a added bonus, the 'first alternate' superblock of a FFSv1 filesystem
 * with 64k blocks is at 64k - just where the code looks first when playing
 * 'hunt the superblock'.
 *
 * The ffsv2 superblock layout (which might contain an ffsv1 filesystem)
 * can be detected by checking for sb->fs_old_flags & FS_FLAGS_UPDATED.
 * This is the default suberblock type for NetBSD since ffsv2 support was added.
 */
#define	BBSIZE		8192
#define	BBOFF		((off_t)(0))
#define	BBLOCK		((daddr_t)(0))

#define SBLOCK_FLOPPY      0
#define SBLOCK_UFS1     8192
#define SBLOCK_UFS2    65536
#define SBLOCK_PIGGY  262144
#define SBLOCKSIZE      8192
/*
 * NB: Do not, under any circumstances, look for an ffsv1 filesystem at
 * SBLOCK_UFS2.  Doing so will find the wrong superblock for filesystems
 * with a 64k block size.
 */
#define SBLOCKSEARCH \
	{ SBLOCK_UFS2, SBLOCK_UFS1, SBLOCK_FLOPPY, SBLOCK_PIGGY, -1 }

/*
 * Max number of fragments per block. This value is NOT tweakable.
 */
#define MAXFRAG		8



/*
 * Addresses stored in inodes are capable of addressing fragments
 * of `blocks'. File system blocks of at most size MAXBSIZE can
 * be optionally broken into 2, 4, or 8 pieces, each of which is
 * addressable; these pieces may be DEV_BSIZE, or some multiple of
 * a DEV_BSIZE unit.
 *
 * Large files consist of exclusively large data blocks.  To avoid
 * undue wasted disk space, the last data block of a small file may be
 * allocated as only as many fragments of a large block as are
 * necessary.  The file system format retains only a single pointer
 * to such a fragment, which is a piece of a single large block that
 * has been divided.  The size of such a fragment is determinable from
 * information in the inode, using the ``blksize(fs, ip, lbn)'' macro.
 *
 * The file system records space availability at the fragment level;
 * to determine block availability, aligned fragments are examined.
 */

/*
 * MINBSIZE is the smallest allowable block size.
 * In order to insure that it is possible to create files of size
 * 2^32 with only two levels of indirection, MINBSIZE is set to 4096.
 * MINBSIZE must be big enough to hold a cylinder group block,
 * thus changes to (struct cg) must keep its size within MINBSIZE.
 * Note that super blocks are always of size SBSIZE,
 * and that both SBSIZE and MAXBSIZE must be >= MINBSIZE.
 */
#define	MINBSIZE	4096

/*
 * The path name on which the file system is mounted is maintained
 * in fs_fsmnt. MAXMNTLEN defines the amount of space allocated in
 * the super block for this name.
 */
#define	MAXMNTLEN	468

/*
 * The volume name for this filesystem is maintained in fs_volname.
 * MAXVOLLEN defines the length of the buffer allocated.
 * This space used to be part of of fs_fsmnt.
 */
#define MAXVOLLEN	32

/*
 * There is a 128-byte region in the superblock reserved for in-core
 * pointers to summary information. Originally this included an array
 * of pointers to blocks of struct csum; now there are just four
 * pointers and the remaining space is padded with fs_ocsp[].
 * NOCSPTRS determines the size of this padding. One pointer (fs_csp)
 * is taken away to point to a contiguous array of struct csum for
 * all cylinder groups; a second (fs_maxcluster) points to an array
 * of cluster sizes that is computed as cylinder groups are inspected;
 * the third (fs_contigdirs) points to an array that tracks the
 * creation of new directories; and the fourth (fs_active) is used
 * by snapshots.
 */
#define	NOCSPTRS	((128 / sizeof(void *)) - 4)

/*
 * A summary of contiguous blocks of various sizes is maintained
 * in each cylinder group. Normally this is set by the initial
 * value of fs_maxcontig. To conserve space, a maximum summary size
 * is set by FS_MAXCONTIG.
 */
#define	FS_MAXCONTIG	16

/*
 * Unused value currently, FreeBSD compat.
 */
#define FSMAXSNAP 20

/*
 * MINFREE gives the minimum acceptable percentage of file system
 * blocks which may be free. If the freelist drops below this level
 * only the superuser may continue to allocate blocks. This may
 * be set to 0 if no reserve of free blocks is deemed necessary,
 * however throughput drops by fifty percent if the file system
 * is run at between 95% and 100% full; thus the minimum default
 * value of fs_minfree is 5%. However, to get good clustering
 * performance, 10% is a better choice. hence we use 10% as our
 * default value. With 10% free space, fragmentation is not a
 * problem, so we choose to optimize for time.
 */
#define	MINFREE		5
#define	DEFAULTOPT	FS_OPTTIME

/*
 * Grigoriy Orlov <[e-mail]> has done some extensive work to fine
 * tune the layout preferences for directories within a filesystem.
 * His algorithm can be tuned by adjusting the following parameters
 * which tell the system the average file size and the average number
 * of files per directory. These defaults are well selected for typical
 * filesystems, but may need to be tuned for odd cases like filesystems
 * being used for squid caches or news spools.
 */
#define	AVFILESIZ	16384	/* expected average file size */
#define	AFPDIR		64	/* expected number of files per directory */

/*
 * Per cylinder group information; summarized in blocks allocated
 * from first cylinder group data blocks.  These blocks have to be
 * read in from fs_csaddr (size fs_cssize) in addition to the
 * super block.
 */
struct csum {
	int32_t	cs_ndir;		/* number of directories */
	int32_t	cs_nbfree;		/* number of free blocks */
	int32_t	cs_nifree;		/* number of free inodes */
	int32_t	cs_nffree;		/* number of free frags */
};

struct csum_total {
	int64_t cs_ndir;		/* number of directories */
	int64_t cs_nbfree;		/* number of free blocks */
	int64_t cs_nifree;		/* number of free inodes */
	int64_t cs_nffree;		/* number of free frags */
	int64_t cs_spare[4];		/* future expansion */
};


/*
 * Super block for an FFS file system in memory.
 */
struct fs {
	int32_t	 fs_firstfield;		/* historic file system linked list, */
	int32_t	 fs_unused_1;		/*     used for incore super blocks */
	int32_t  fs_sblkno;		/* addr of super-block in filesys */
	int32_t  fs_cblkno;		/* offset of cyl-block in filesys */
	int32_t  fs_iblkno;		/* offset of inode-blocks in filesys */
	int32_t  fs_dblkno;		/* offset of first data after cg */
	int32_t	 fs_old_cgoffset;	/* cylinder group offset in cylinder */
	int32_t	 fs_old_cgmask;		/* used to calc mod fs_ntrak */
	int32_t	 fs_old_time;		/* last time written */
	int32_t	 fs_old_size;		/* number of blocks in fs */
	int32_t	 fs_old_dsize;		/* number of data blocks in fs */
	int32_t	 fs_ncg;		/* number of cylinder groups */
	int32_t	 fs_bsize;		/* size of basic blocks in fs */
	int32_t	 fs_fsize;		/* size of frag blocks in fs */
	int32_t	 fs_frag;		/* number of frags in a block in fs */
/* these are configuration parameters */
	int32_t	 fs_minfree;		/* minimum percentage of free blocks */
	int32_t	 fs_old_rotdelay;	/* num of ms for optimal next block */
	int32_t	 fs_old_rps;		/* disk revolutions per second */
/* these fields can be computed from the others */
	int32_t	 fs_bmask;		/* ``blkoff'' calc of blk offsets */
	int32_t	 fs_fmask;		/* ``fragoff'' calc of frag offsets */
	int32_t	 fs_bshift;		/* ``lblkno'' calc of logical blkno */
	int32_t	 fs_fshift;		/* ``numfrags'' calc number of frags */
/* these are configuration parameters */
	int32_t	 fs_maxcontig;		/* max number of contiguous blks */
	int32_t	 fs_maxbpg;		/* max number of blks per cyl group */
/* these fields can be computed from the others */
	int32_t	 fs_fragshift;		/* block to frag shift */
	int32_t	 fs_fsbtodb;		/* fsbtodb and dbtofsb shift constant */
	int32_t	 fs_sbsize;		/* actual size of super block */
	int32_t	 fs_spare1[2];		/* old fs_csmask */
					/* old fs_csshift */
	int32_t	 fs_nindir;		/* value of NINDIR */
	int32_t	 fs_inopb;		/* value of INOPB */
	int32_t	 fs_old_nspf;		/* value of NSPF */
/* yet another configuration parameter */
	int32_t	 fs_optim;		/* optimization preference, see below */
/* these fields are derived from the hardware */
	int32_t	 fs_old_npsect;		/* # sectors/track including spares */
	int32_t	 fs_old_interleave;	/* hardware sector interleave */
	int32_t	 fs_old_trackskew;	/* sector 0 skew, per track */
/* fs_id takes the space of the unused fs_headswitch and fs_trkseek fields */
	int32_t	 fs_id[2];		/* unique file system id */
/* sizes determined by number of cylinder groups and their sizes */
	int32_t  fs_old_csaddr;		/* blk addr of cyl grp summary area */
	int32_t	 fs_cssize;		/* size of cyl grp summary area */
	int32_t	 fs_cgsize;		/* cylinder group size */
/* these fields are derived from the hardware */
	int32_t	 fs_spare2;		/* old fs_ntrak */
	int32_t	 fs_old_nsect;		/* sectors per track */
	int32_t	 fs_old_spc;		/* sectors per cylinder */
	int32_t	 fs_old_ncyl;		/* cylinders in file system */
	int32_t	 fs_old_cpg;		/* cylinders per group */
	int32_t	 fs_ipg;		/* inodes per group */
	int32_t	 fs_fpg;		/* blocks per group * fs_frag */
/* this data must be re-computed after crashes */
	struct	csum fs_old_cstotal;	/* cylinder summary information */
/* these fields are cleared at mount time */
	int8_t	 fs_fmod;		/* super block modified flag */
	int8_t	 fs_clean;		/* file system is clean flag */
	int8_t	 fs_ronly;		/* mounted read-only flag */
	uint8_t	 fs_old_flags;		/* see FS_ flags below */
	u_char	 fs_fsmnt[MAXMNTLEN];	/* name mounted on */
	u_char   fs_volname[MAXVOLLEN];	/* volume name */
	uint64_t fs_swuid;		/* system-wide uid */
	int32_t	 fs_pad;
/* these fields retain the current block allocation info */
	int32_t	 fs_cgrotor;		/* last cg searched (UNUSED) */
	void 	*fs_ocsp[NOCSPTRS];	/* padding; was list of fs_cs buffers */
	u_int8_t *fs_contigdirs;	/* # of contiguously allocated dirs */
	struct csum *fs_csp;		/* cg summary info buffer for fs_cs */
	int32_t	*fs_maxcluster;		/* max cluster in each cyl group */
	u_int	*fs_active;		/* used by snapshots to track fs */
	int32_t	 fs_old_cpc;		/* cyl per cycle in postbl */
/* this area is otherwise allocated unless fs_old_flags & FS_FLAGS_UPDATED */
	int32_t	 fs_maxbsize;		/* maximum blocking factor permitted */
	int64_t	 fs_sparecon64[17];	/* old rotation block list head */
	int64_t	 fs_sblockloc;		/* byte offset of standard superblock */
	struct	csum_total fs_cstotal;	/* cylinder summary information */
	int64_t  fs_time;		/* last time written */
	int64_t	 fs_size;		/* number of blocks in fs */
	int64_t	 fs_dsize;		/* number of data blocks in fs */
	int64_t  fs_csaddr;		/* blk addr of cyl grp summary area */
	int64_t	 fs_pendingblocks;	/* blocks in process of being freed */
	int32_t	 fs_pendinginodes;	/* inodes in process of being freed */
	int32_t	 fs_snapinum[FSMAXSNAP];/* list of snapshot inode numbers */
/* back to stuff that has been around a while */
	int32_t	 fs_avgfilesize;	/* expected average file size */
	int32_t	 fs_avgfpdir;		/* expected # of files per directory */
	int32_t	 fs_save_cgsize;	/* save real cg size to use fs_bsize */
	int32_t	 fs_sparecon32[26];	/* reserved for future constants */
	uint32_t fs_flags;		/* see FS_ flags below */
/* back to stuff that has been around a while (again) */
	int32_t	 fs_contigsumsize;	/* size of cluster summary array */ 
	int32_t	 fs_maxsymlinklen;	/* max length of an internal symlink */
	int32_t	 fs_old_inodefmt;	/* format of on-disk inodes */
	u_int64_t fs_maxfilesize;	/* maximum representable file size */
	int64_t	 fs_qbmask;		/* ~fs_bmask for use with 64-bit size */
	int64_t	 fs_qfmask;		/* ~fs_fmask for use with 64-bit size */
	int32_t	 fs_state;		/* validate fs_clean field (UNUSED) */
	int32_t	 fs_old_postblformat;	/* format of positional layout tables */
	int32_t	 fs_old_nrpos;		/* number of rotational positions */
	int32_t  fs_spare5[2];		/* old fs_postbloff */
					/* old fs_rotbloff */
	int32_t	 fs_magic;		/* magic number */
};

#define fs_old_postbloff	fs_spare5[0]
#define fs_old_rotbloff		fs_spare5[1]
#define fs_old_postbl_start	fs_maxbsize
#define fs_old_headswitch	fs_id[0]
#define fs_old_trkseek	fs_id[1]
#define fs_old_csmask	fs_spare1[0]