xfs_mount.c

linux 内核源代码

/*
 * Copyright (c) 2000-2005 Silicon Graphics, Inc.
 * All Rights Reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it would be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write the Free Software Foundation,
 * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_types.h"
#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_inum.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_dir2.h"
#include "xfs_dmapi.h"
#include "xfs_mount.h"
#include "xfs_bmap_btree.h"
#include "xfs_alloc_btree.h"
#include "xfs_ialloc_btree.h"
#include "xfs_dir2_sf.h"
#include "xfs_attr_sf.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_btree.h"
#include "xfs_ialloc.h"
#include "xfs_alloc.h"
#include "xfs_rtalloc.h"
#include "xfs_bmap.h"
#include "xfs_error.h"
#include "xfs_rw.h"
#include "xfs_quota.h"
#include "xfs_fsops.h"

STATIC void	xfs_mount_log_sbunit(xfs_mount_t *, __int64_t);
STATIC int	xfs_uuid_mount(xfs_mount_t *);
STATIC void	xfs_uuid_unmount(xfs_mount_t *mp);
STATIC void	xfs_unmountfs_wait(xfs_mount_t *);


#ifdef HAVE_PERCPU_SB
STATIC void	xfs_icsb_destroy_counters(xfs_mount_t *);
STATIC void	xfs_icsb_balance_counter(xfs_mount_t *, xfs_sb_field_t,
						int, int);
STATIC void	xfs_icsb_sync_counters(xfs_mount_t *);
STATIC int	xfs_icsb_modify_counters(xfs_mount_t *, xfs_sb_field_t,
						int64_t, int);
STATIC int	xfs_icsb_disable_counter(xfs_mount_t *, xfs_sb_field_t);

#else

#define xfs_icsb_destroy_counters(mp)			do { } while (0)
#define xfs_icsb_balance_counter(mp, a, b, c)		do { } while (0)
#define xfs_icsb_sync_counters(mp)			do { } while (0)
#define xfs_icsb_modify_counters(mp, a, b, c)		do { } while (0)

#endif

static const struct {
	short offset;
	short type;	/* 0 = integer
			 * 1 = binary / string (no translation)
			 */
} xfs_sb_info[] = {
    { offsetof(xfs_sb_t, sb_magicnum),   0 },
    { offsetof(xfs_sb_t, sb_blocksize),  0 },
    { offsetof(xfs_sb_t, sb_dblocks),    0 },
    { offsetof(xfs_sb_t, sb_rblocks),    0 },
    { offsetof(xfs_sb_t, sb_rextents),   0 },
    { offsetof(xfs_sb_t, sb_uuid),       1 },
    { offsetof(xfs_sb_t, sb_logstart),   0 },
    { offsetof(xfs_sb_t, sb_rootino),    0 },
    { offsetof(xfs_sb_t, sb_rbmino),     0 },
    { offsetof(xfs_sb_t, sb_rsumino),    0 },
    { offsetof(xfs_sb_t, sb_rextsize),   0 },
    { offsetof(xfs_sb_t, sb_agblocks),   0 },
    { offsetof(xfs_sb_t, sb_agcount),    0 },
    { offsetof(xfs_sb_t, sb_rbmblocks),  0 },
    { offsetof(xfs_sb_t, sb_logblocks),  0 },
    { offsetof(xfs_sb_t, sb_versionnum), 0 },
    { offsetof(xfs_sb_t, sb_sectsize),   0 },
    { offsetof(xfs_sb_t, sb_inodesize),  0 },
    { offsetof(xfs_sb_t, sb_inopblock),  0 },
    { offsetof(xfs_sb_t, sb_fname[0]),   1 },
    { offsetof(xfs_sb_t, sb_blocklog),   0 },
    { offsetof(xfs_sb_t, sb_sectlog),    0 },
    { offsetof(xfs_sb_t, sb_inodelog),   0 },
    { offsetof(xfs_sb_t, sb_inopblog),   0 },
    { offsetof(xfs_sb_t, sb_agblklog),   0 },
    { offsetof(xfs_sb_t, sb_rextslog),   0 },
    { offsetof(xfs_sb_t, sb_inprogress), 0 },
    { offsetof(xfs_sb_t, sb_imax_pct),   0 },
    { offsetof(xfs_sb_t, sb_icount),     0 },
    { offsetof(xfs_sb_t, sb_ifree),      0 },
    { offsetof(xfs_sb_t, sb_fdblocks),   0 },
    { offsetof(xfs_sb_t, sb_frextents),  0 },
    { offsetof(xfs_sb_t, sb_uquotino),   0 },
    { offsetof(xfs_sb_t, sb_gquotino),   0 },
    { offsetof(xfs_sb_t, sb_qflags),     0 },
    { offsetof(xfs_sb_t, sb_flags),      0 },
    { offsetof(xfs_sb_t, sb_shared_vn),  0 },
    { offsetof(xfs_sb_t, sb_inoalignmt), 0 },
    { offsetof(xfs_sb_t, sb_unit),	 0 },
    { offsetof(xfs_sb_t, sb_width),	 0 },
    { offsetof(xfs_sb_t, sb_dirblklog),	 0 },
    { offsetof(xfs_sb_t, sb_logsectlog), 0 },
    { offsetof(xfs_sb_t, sb_logsectsize),0 },
    { offsetof(xfs_sb_t, sb_logsunit),	 0 },
    { offsetof(xfs_sb_t, sb_features2),	 0 },
    { sizeof(xfs_sb_t),			 0 }
};

/*
 * Return a pointer to an initialized xfs_mount structure.
 */
xfs_mount_t *
xfs_mount_init(void)
{
	xfs_mount_t *mp;

	mp = kmem_zalloc(sizeof(xfs_mount_t), KM_SLEEP);

	if (xfs_icsb_init_counters(mp)) {
		mp->m_flags |= XFS_MOUNT_NO_PERCPU_SB;
	}

	AIL_LOCKINIT(&mp->m_ail_lock, "xfs_ail");
	spinlock_init(&mp->m_sb_lock, "xfs_sb");
	mutex_init(&mp->m_ilock);
	mutex_init(&mp->m_growlock);
	/*
	 * Initialize the AIL.
	 */
	xfs_trans_ail_init(mp);

	atomic_set(&mp->m_active_trans, 0);

	return mp;
}

/*
 * Free up the resources associated with a mount structure.  Assume that
 * the structure was initially zeroed, so we can tell which fields got
 * initialized.
 */
void
xfs_mount_free(
	xfs_mount_t	*mp)
{
	if (mp->m_perag) {
		int	agno;

		for (agno = 0; agno < mp->m_maxagi; agno++)
			if (mp->m_perag[agno].pagb_list)
				kmem_free(mp->m_perag[agno].pagb_list,
						sizeof(xfs_perag_busy_t) *
							XFS_PAGB_NUM_SLOTS);
		kmem_free(mp->m_perag,
			  sizeof(xfs_perag_t) * mp->m_sb.sb_agcount);
	}

	AIL_LOCK_DESTROY(&mp->m_ail_lock);
	spinlock_destroy(&mp->m_sb_lock);
	mutex_destroy(&mp->m_ilock);
	mutex_destroy(&mp->m_growlock);
	if (mp->m_quotainfo)
		XFS_QM_DONE(mp);

	if (mp->m_fsname != NULL)
		kmem_free(mp->m_fsname, mp->m_fsname_len);
	if (mp->m_rtname != NULL)
		kmem_free(mp->m_rtname, strlen(mp->m_rtname) + 1);
	if (mp->m_logname != NULL)
		kmem_free(mp->m_logname, strlen(mp->m_logname) + 1);

	xfs_icsb_destroy_counters(mp);
}

/*
 * Check size of device based on the (data/realtime) block count.
 * Note: this check is used by the growfs code as well as mount.
 */
int
xfs_sb_validate_fsb_count(
	xfs_sb_t	*sbp,
	__uint64_t	nblocks)
{
	ASSERT(PAGE_SHIFT >= sbp->sb_blocklog);
	ASSERT(sbp->sb_blocklog >= BBSHIFT);

#if XFS_BIG_BLKNOS     /* Limited by ULONG_MAX of page cache index */
	if (nblocks >> (PAGE_CACHE_SHIFT - sbp->sb_blocklog) > ULONG_MAX)
		return E2BIG;
#else                  /* Limited by UINT_MAX of sectors */
	if (nblocks << (sbp->sb_blocklog - BBSHIFT) > UINT_MAX)
		return E2BIG;
#endif
	return 0;
}

/*
 * Check the validity of the SB found.
 */
STATIC int
xfs_mount_validate_sb(
	xfs_mount_t	*mp,
	xfs_sb_t	*sbp,
	int		flags)
{
	/*
	 * If the log device and data device have the
	 * same device number, the log is internal.
	 * Consequently, the sb_logstart should be non-zero.  If
	 * we have a zero sb_logstart in this case, we may be trying to mount
	 * a volume filesystem in a non-volume manner.
	 */
	if (sbp->sb_magicnum != XFS_SB_MAGIC) {
		xfs_fs_mount_cmn_err(flags, "bad magic number");
		return XFS_ERROR(EWRONGFS);
	}

	if (!XFS_SB_GOOD_VERSION(sbp)) {
		xfs_fs_mount_cmn_err(flags, "bad version");
		return XFS_ERROR(EWRONGFS);
	}

	if (unlikely(
	    sbp->sb_logstart == 0 && mp->m_logdev_targp == mp->m_ddev_targp)) {
		xfs_fs_mount_cmn_err(flags,
			"filesystem is marked as having an external log; "
			"specify logdev on the\nmount command line.");
		return XFS_ERROR(EINVAL);
	}

	if (unlikely(
	    sbp->sb_logstart != 0 && mp->m_logdev_targp != mp->m_ddev_targp)) {
		xfs_fs_mount_cmn_err(flags,
			"filesystem is marked as having an internal log; "
			"do not specify logdev on\nthe mount command line.");
		return XFS_ERROR(EINVAL);
	}

	/*
	 * More sanity checking. These were stolen directly from
	 * xfs_repair.
	 */
	if (unlikely(
	    sbp->sb_agcount <= 0					||
	    sbp->sb_sectsize < XFS_MIN_SECTORSIZE			||
	    sbp->sb_sectsize > XFS_MAX_SECTORSIZE			||
	    sbp->sb_sectlog < XFS_MIN_SECTORSIZE_LOG			||
	    sbp->sb_sectlog > XFS_MAX_SECTORSIZE_LOG			||
	    sbp->sb_blocksize < XFS_MIN_BLOCKSIZE			||
	    sbp->sb_blocksize > XFS_MAX_BLOCKSIZE			||
	    sbp->sb_blocklog < XFS_MIN_BLOCKSIZE_LOG			||
	    sbp->sb_blocklog > XFS_MAX_BLOCKSIZE_LOG			||
	    sbp->sb_inodesize < XFS_DINODE_MIN_SIZE			||
	    sbp->sb_inodesize > XFS_DINODE_MAX_SIZE			||
	    sbp->sb_inodelog < XFS_DINODE_MIN_LOG			||
	    sbp->sb_inodelog > XFS_DINODE_MAX_LOG			||
	    (sbp->sb_blocklog - sbp->sb_inodelog != sbp->sb_inopblog)	||
	    (sbp->sb_rextsize * sbp->sb_blocksize > XFS_MAX_RTEXTSIZE)	||
	    (sbp->sb_rextsize * sbp->sb_blocksize < XFS_MIN_RTEXTSIZE)	||
	    (sbp->sb_imax_pct > 100 /* zero sb_imax_pct is valid */))) {
		xfs_fs_mount_cmn_err(flags, "SB sanity check 1 failed");
		return XFS_ERROR(EFSCORRUPTED);
	}

	/*
	 * Sanity check AG count, size fields against data size field
	 */
	if (unlikely(
	    sbp->sb_dblocks == 0 ||
	    sbp->sb_dblocks >
	     (xfs_drfsbno_t)sbp->sb_agcount * sbp->sb_agblocks ||
	    sbp->sb_dblocks < (xfs_drfsbno_t)(sbp->sb_agcount - 1) *
			      sbp->sb_agblocks + XFS_MIN_AG_BLOCKS)) {
		xfs_fs_mount_cmn_err(flags, "SB sanity check 2 failed");
		return XFS_ERROR(EFSCORRUPTED);
	}

	if (xfs_sb_validate_fsb_count(sbp, sbp->sb_dblocks) ||
	    xfs_sb_validate_fsb_count(sbp, sbp->sb_rblocks)) {
		xfs_fs_mount_cmn_err(flags,
			"file system too large to be mounted on this system.");
		return XFS_ERROR(E2BIG);
	}

	if (unlikely(sbp->sb_inprogress)) {
		xfs_fs_mount_cmn_err(flags, "file system busy");
		return XFS_ERROR(EFSCORRUPTED);
	}

	/*
	 * Version 1 directory format has never worked on Linux.
	 */
	if (unlikely(!XFS_SB_VERSION_HASDIRV2(sbp))) {
		xfs_fs_mount_cmn_err(flags,
			"file system using version 1 directory format");
		return XFS_ERROR(ENOSYS);
	}

	/*
	 * Until this is fixed only page-sized or smaller data blocks work.
	 */
	if (unlikely(sbp->sb_blocksize > PAGE_SIZE)) {
		xfs_fs_mount_cmn_err(flags,
			"file system with blocksize %d bytes",
			sbp->sb_blocksize);
		xfs_fs_mount_cmn_err(flags,
			"only pagesize (%ld) or less will currently work.",
			PAGE_SIZE);
		return XFS_ERROR(ENOSYS);
	}

	return 0;
}

STATIC void
xfs_initialize_perag_icache(
	xfs_perag_t	*pag)
{
	if (!pag->pag_ici_init) {
		rwlock_init(&pag->pag_ici_lock);
		INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC);
		pag->pag_ici_init = 1;
	}
}

xfs_agnumber_t
xfs_initialize_perag(
	xfs_mount_t	*mp,
	xfs_agnumber_t	agcount)
{
	xfs_agnumber_t	index, max_metadata;
	xfs_perag_t	*pag;
	xfs_agino_t	agino;
	xfs_ino_t	ino;
	xfs_sb_t	*sbp = &mp->m_sb;
	xfs_ino_t	max_inum = XFS_MAXINUMBER_32;

	/* Check to see if the filesystem can overflow 32 bit inodes */
	agino = XFS_OFFBNO_TO_AGINO(mp, sbp->sb_agblocks - 1, 0);
	ino = XFS_AGINO_TO_INO(mp, agcount - 1, agino);

	/* Clear the mount flag if no inode can overflow 32 bits
	 * on this filesystem, or if specifically requested..
	 */
	if ((mp->m_flags & XFS_MOUNT_SMALL_INUMS) && ino > max_inum) {
		mp->m_flags |= XFS_MOUNT_32BITINODES;
	} else {
		mp->m_flags &= ~XFS_MOUNT_32BITINODES;
	}

	/* If we can overflow then setup the ag headers accordingly */
	if (mp->m_flags & XFS_MOUNT_32BITINODES) {
		/* Calculate how much should be reserved for inodes to
		 * meet the max inode percentage.
		 */
		if (mp->m_maxicount) {
			__uint64_t	icount;

			icount = sbp->sb_dblocks * sbp->sb_imax_pct;
			do_div(icount, 100);
			icount += sbp->sb_agblocks - 1;
			do_div(icount, sbp->sb_agblocks);
			max_metadata = icount;
		} else {
			max_metadata = agcount;
		}
		for (index = 0; index < agcount; index++) {
			ino = XFS_AGINO_TO_INO(mp, index, agino);
			if (ino > max_inum) {
				index++;
				break;
			}

			/* This ag is preferred for inodes */
			pag = &mp->m_perag[index];
			pag->pagi_inodeok = 1;
			if (index < max_metadata)
				pag->pagf_metadata = 1;
			xfs_initialize_perag_icache(pag);
		}
	} else {
		/* Setup default behavior for smaller filesystems */
		for (index = 0; index < agcount; index++) {
			pag = &mp->m_perag[index];
			pag->pagi_inodeok = 1;
			xfs_initialize_perag_icache(pag);
		}
	}
	return index;
}

void
xfs_sb_from_disk(
	xfs_sb_t	*to,
	xfs_dsb_t	*from)
{
	to->sb_magicnum = be32_to_cpu(from->sb_magicnum);
	to->sb_blocksize = be32_to_cpu(from->sb_blocksize);
	to->sb_dblocks = be64_to_cpu(from->sb_dblocks);
	to->sb_rblocks = be64_to_cpu(from->sb_rblocks);
	to->sb_rextents = be64_to_cpu(from->sb_rextents);
	memcpy(&to->sb_uuid, &from->sb_uuid, sizeof(to->sb_uuid));
	to->sb_logstart = be64_to_cpu(from->sb_logstart);
	to->sb_rootino = be64_to_cpu(from->sb_rootino);
	to->sb_rbmino = be64_to_cpu(from->sb_rbmino);
	to->sb_rsumino = be64_to_cpu(from->sb_rsumino);
	to->sb_rextsize = be32_to_cpu(from->sb_rextsize);
	to->sb_agblocks = be32_to_cpu(from->sb_agblocks);
	to->sb_agcount = be32_to_cpu(from->sb_agcount);
	to->sb_rbmblocks = be32_to_cpu(from->sb_rbmblocks);
	to->sb_logblocks = be32_to_cpu(from->sb_logblocks);
	to->sb_versionnum = be16_to_cpu(from->sb_versionnum);
	to->sb_sectsize = be16_to_cpu(from->sb_sectsize);
	to->sb_inodesize = be16_to_cpu(from->sb_inodesize);
	to->sb_inopblock = be16_to_cpu(from->sb_inopblock);
	memcpy(&to->sb_fname, &from->sb_fname, sizeof(to->sb_fname));
	to->sb_blocklog = from->sb_blocklog;
	to->sb_sectlog = from->sb_sectlog;
	to->sb_inodelog = from->sb_inodelog;
	to->sb_inopblog = from->sb_inopblog;
	to->sb_agblklog = from->sb_agblklog;
	to->sb_rextslog = from->sb_rextslog;
	to->sb_inprogress = from->sb_inprogress;
	to->sb_imax_pct = from->sb_imax_pct;
	to->sb_icount = be64_to_cpu(from->sb_icount);
	to->sb_ifree = be64_to_cpu(from->sb_ifree);
	to->sb_fdblocks = be64_to_cpu(from->sb_fdblocks);
	to->sb_frextents = be64_to_cpu(from->sb_frextents);
	to->sb_uquotino = be64_to_cpu(from->sb_uquotino);
	to->sb_gquotino = be64_to_cpu(from->sb_gquotino);
	to->sb_qflags = be16_to_cpu(from->sb_qflags);
	to->sb_flags = from->sb_flags;
	to->sb_shared_vn = from->sb_shared_vn;
	to->sb_inoalignmt = be32_to_cpu(from->sb_inoalignmt);
	to->sb_unit = be32_to_cpu(from->sb_unit);
	to->sb_width = be32_to_cpu(from->sb_width);
	to->sb_dirblklog = from->sb_dirblklog;
	to->sb_logsectlog = from->sb_logsectlog;
	to->sb_logsectsize = be16_to_cpu(from->sb_logsectsize);
	to->sb_logsunit = be32_to_cpu(from->sb_logsunit);
	to->sb_features2 = be32_to_cpu(from->sb_features2);
}

/*
 * Copy in core superblock to ondisk one.
 *
 * The fields argument is mask of superblock fields to copy.
 */
void
xfs_sb_to_disk(
	xfs_dsb_t	*to,
	xfs_sb_t	*from,
	__int64_t	fields)
{
	xfs_caddr_t	to_ptr = (xfs_caddr_t)to;
	xfs_caddr_t	from_ptr = (xfs_caddr_t)from;
	xfs_sb_field_t	f;
	int		first;
	int		size;

	ASSERT(fields);
	if (!fields)
		return;

	while (fields) {
		f = (xfs_sb_field_t)xfs_lowbit64((__uint64_t)fields);
		first = xfs_sb_info[f].offset;
		size = xfs_sb_info[f + 1].offset - first;

		ASSERT(xfs_sb_info[f].type == 0 || xfs_sb_info[f].type == 1);