xfs_inode.c

linux 内核源代码

/*
 * Copyright (c) 2000-2006 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_imap.h"
#include "xfs_trans.h"
#include "xfs_trans_priv.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_buf_item.h"
#include "xfs_inode_item.h"
#include "xfs_btree.h"
#include "xfs_alloc.h"
#include "xfs_ialloc.h"
#include "xfs_bmap.h"
#include "xfs_rw.h"
#include "xfs_error.h"
#include "xfs_utils.h"
#include "xfs_dir2_trace.h"
#include "xfs_quota.h"
#include "xfs_acl.h"
#include "xfs_filestream.h"
#include "xfs_vnodeops.h"

kmem_zone_t *xfs_ifork_zone;
kmem_zone_t *xfs_inode_zone;
kmem_zone_t *xfs_icluster_zone;

/*
 * Used in xfs_itruncate().  This is the maximum number of extents
 * freed from a file in a single transaction.
 */
#define	XFS_ITRUNC_MAX_EXTENTS	2

STATIC int xfs_iflush_int(xfs_inode_t *, xfs_buf_t *);
STATIC int xfs_iformat_local(xfs_inode_t *, xfs_dinode_t *, int, int);
STATIC int xfs_iformat_extents(xfs_inode_t *, xfs_dinode_t *, int);
STATIC int xfs_iformat_btree(xfs_inode_t *, xfs_dinode_t *, int);

#ifdef DEBUG
/*
 * Make sure that the extents in the given memory buffer
 * are valid.
 */
STATIC void
xfs_validate_extents(
	xfs_ifork_t		*ifp,
	int			nrecs,
	xfs_exntfmt_t		fmt)
{
	xfs_bmbt_irec_t		irec;
	xfs_bmbt_rec_host_t	rec;
	int			i;

	for (i = 0; i < nrecs; i++) {
		xfs_bmbt_rec_host_t *ep = xfs_iext_get_ext(ifp, i);
		rec.l0 = get_unaligned(&ep->l0);
		rec.l1 = get_unaligned(&ep->l1);
		xfs_bmbt_get_all(&rec, &irec);
		if (fmt == XFS_EXTFMT_NOSTATE)
			ASSERT(irec.br_state == XFS_EXT_NORM);
	}
}
#else /* DEBUG */
#define xfs_validate_extents(ifp, nrecs, fmt)
#endif /* DEBUG */

/*
 * Check that none of the inode's in the buffer have a next
 * unlinked field of 0.
 */
#if defined(DEBUG)
void
xfs_inobp_check(
	xfs_mount_t	*mp,
	xfs_buf_t	*bp)
{
	int		i;
	int		j;
	xfs_dinode_t	*dip;

	j = mp->m_inode_cluster_size >> mp->m_sb.sb_inodelog;

	for (i = 0; i < j; i++) {
		dip = (xfs_dinode_t *)xfs_buf_offset(bp,
					i * mp->m_sb.sb_inodesize);
		if (!dip->di_next_unlinked)  {
			xfs_fs_cmn_err(CE_ALERT, mp,
				"Detected a bogus zero next_unlinked field in incore inode buffer 0x%p.  About to pop an ASSERT.",
				bp);
			ASSERT(dip->di_next_unlinked);
		}
	}
}
#endif

/*
 * This routine is called to map an inode number within a file
 * system to the buffer containing the on-disk version of the
 * inode.  It returns a pointer to the buffer containing the
 * on-disk inode in the bpp parameter, and in the dip parameter
 * it returns a pointer to the on-disk inode within that buffer.
 *
 * If a non-zero error is returned, then the contents of bpp and
 * dipp are undefined.
 *
 * Use xfs_imap() to determine the size and location of the
 * buffer to read from disk.
 */
STATIC int
xfs_inotobp(
	xfs_mount_t	*mp,
	xfs_trans_t	*tp,
	xfs_ino_t	ino,
	xfs_dinode_t	**dipp,
	xfs_buf_t	**bpp,
	int		*offset)
{
	int		di_ok;
	xfs_imap_t	imap;
	xfs_buf_t	*bp;
	int		error;
	xfs_dinode_t	*dip;

	/*
	 * Call the space management code to find the location of the
	 * inode on disk.
	 */
	imap.im_blkno = 0;
	error = xfs_imap(mp, tp, ino, &imap, XFS_IMAP_LOOKUP);
	if (error != 0) {
		cmn_err(CE_WARN,
	"xfs_inotobp: xfs_imap()  returned an "
	"error %d on %s.  Returning error.", error, mp->m_fsname);
		return error;
	}

	/*
	 * If the inode number maps to a block outside the bounds of the
	 * file system then return NULL rather than calling read_buf
	 * and panicing when we get an error from the driver.
	 */
	if ((imap.im_blkno + imap.im_len) >
	    XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks)) {
		cmn_err(CE_WARN,
	"xfs_inotobp: inode number (%llu + %d) maps to a block outside the bounds "
	"of the file system %s.  Returning EINVAL.",
			(unsigned long long)imap.im_blkno,
			imap.im_len, mp->m_fsname);
		return XFS_ERROR(EINVAL);
	}

	/*
	 * Read in the buffer.  If tp is NULL, xfs_trans_read_buf() will
	 * default to just a read_buf() call.
	 */
	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap.im_blkno,
				   (int)imap.im_len, XFS_BUF_LOCK, &bp);

	if (error) {
		cmn_err(CE_WARN,
	"xfs_inotobp: xfs_trans_read_buf()  returned an "
	"error %d on %s.  Returning error.", error, mp->m_fsname);
		return error;
	}
	dip = (xfs_dinode_t *)xfs_buf_offset(bp, 0);
	di_ok =
		be16_to_cpu(dip->di_core.di_magic) == XFS_DINODE_MAGIC &&
		XFS_DINODE_GOOD_VERSION(dip->di_core.di_version);
	if (unlikely(XFS_TEST_ERROR(!di_ok, mp, XFS_ERRTAG_ITOBP_INOTOBP,
			XFS_RANDOM_ITOBP_INOTOBP))) {
		XFS_CORRUPTION_ERROR("xfs_inotobp", XFS_ERRLEVEL_LOW, mp, dip);
		xfs_trans_brelse(tp, bp);
		cmn_err(CE_WARN,
	"xfs_inotobp: XFS_TEST_ERROR()  returned an "
	"error on %s.  Returning EFSCORRUPTED.",  mp->m_fsname);
		return XFS_ERROR(EFSCORRUPTED);
	}

	xfs_inobp_check(mp, bp);

	/*
	 * Set *dipp to point to the on-disk inode in the buffer.
	 */
	*dipp = (xfs_dinode_t *)xfs_buf_offset(bp, imap.im_boffset);
	*bpp = bp;
	*offset = imap.im_boffset;
	return 0;
}


/*
 * This routine is called to map an inode to the buffer containing
 * the on-disk version of the inode.  It returns a pointer to the
 * buffer containing the on-disk inode in the bpp parameter, and in
 * the dip parameter it returns a pointer to the on-disk inode within
 * that buffer.
 *
 * If a non-zero error is returned, then the contents of bpp and
 * dipp are undefined.
 *
 * If the inode is new and has not yet been initialized, use xfs_imap()
 * to determine the size and location of the buffer to read from disk.
 * If the inode has already been mapped to its buffer and read in once,
 * then use the mapping information stored in the inode rather than
 * calling xfs_imap().  This allows us to avoid the overhead of looking
 * at the inode btree for small block file systems (see xfs_dilocate()).
 * We can tell whether the inode has been mapped in before by comparing
 * its disk block address to 0.  Only uninitialized inodes will have
 * 0 for the disk block address.
 */
int
xfs_itobp(
	xfs_mount_t	*mp,
	xfs_trans_t	*tp,
	xfs_inode_t	*ip,
	xfs_dinode_t	**dipp,
	xfs_buf_t	**bpp,
	xfs_daddr_t	bno,
	uint		imap_flags)
{
	xfs_imap_t	imap;
	xfs_buf_t	*bp;
	int		error;
	int		i;
	int		ni;

	if (ip->i_blkno == (xfs_daddr_t)0) {
		/*
		 * Call the space management code to find the location of the
		 * inode on disk.
		 */
		imap.im_blkno = bno;
		if ((error = xfs_imap(mp, tp, ip->i_ino, &imap,
					XFS_IMAP_LOOKUP | imap_flags)))
			return error;

		/*
		 * If the inode number maps to a block outside the bounds
		 * of the file system then return NULL rather than calling
		 * read_buf and panicing when we get an error from the
		 * driver.
		 */
		if ((imap.im_blkno + imap.im_len) >
		    XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks)) {
#ifdef DEBUG
			xfs_fs_cmn_err(CE_ALERT, mp, "xfs_itobp: "
					"(imap.im_blkno (0x%llx) "
					"+ imap.im_len (0x%llx)) > "
					" XFS_FSB_TO_BB(mp, "
					"mp->m_sb.sb_dblocks) (0x%llx)",
					(unsigned long long) imap.im_blkno,
					(unsigned long long) imap.im_len,
					XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks));
#endif /* DEBUG */
			return XFS_ERROR(EINVAL);
		}

		/*
		 * Fill in the fields in the inode that will be used to
		 * map the inode to its buffer from now on.
		 */
		ip->i_blkno = imap.im_blkno;
		ip->i_len = imap.im_len;
		ip->i_boffset = imap.im_boffset;
	} else {
		/*
		 * We've already mapped the inode once, so just use the
		 * mapping that we saved the first time.
		 */
		imap.im_blkno = ip->i_blkno;
		imap.im_len = ip->i_len;
		imap.im_boffset = ip->i_boffset;
	}
	ASSERT(bno == 0 || bno == imap.im_blkno);

	/*
	 * Read in the buffer.  If tp is NULL, xfs_trans_read_buf() will
	 * default to just a read_buf() call.
	 */
	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap.im_blkno,
				   (int)imap.im_len, XFS_BUF_LOCK, &bp);
	if (error) {
#ifdef DEBUG
		xfs_fs_cmn_err(CE_ALERT, mp, "xfs_itobp: "
				"xfs_trans_read_buf() returned error %d, "
				"imap.im_blkno 0x%llx, imap.im_len 0x%llx",
				error, (unsigned long long) imap.im_blkno,
				(unsigned long long) imap.im_len);
#endif /* DEBUG */
		return error;
	}

	/*
	 * Validate the magic number and version of every inode in the buffer
	 * (if DEBUG kernel) or the first inode in the buffer, otherwise.
	 * No validation is done here in userspace (xfs_repair).
	 */
#if !defined(__KERNEL__)
	ni = 0;
#elif defined(DEBUG)
	ni = BBTOB(imap.im_len) >> mp->m_sb.sb_inodelog;
#else	/* usual case */
	ni = 1;
#endif

	for (i = 0; i < ni; i++) {
		int		di_ok;
		xfs_dinode_t	*dip;

		dip = (xfs_dinode_t *)xfs_buf_offset(bp,
					(i << mp->m_sb.sb_inodelog));
		di_ok = be16_to_cpu(dip->di_core.di_magic) == XFS_DINODE_MAGIC &&
			    XFS_DINODE_GOOD_VERSION(dip->di_core.di_version);
		if (unlikely(XFS_TEST_ERROR(!di_ok, mp,
						XFS_ERRTAG_ITOBP_INOTOBP,
						XFS_RANDOM_ITOBP_INOTOBP))) {
			if (imap_flags & XFS_IMAP_BULKSTAT) {
				xfs_trans_brelse(tp, bp);
				return XFS_ERROR(EINVAL);
			}
#ifdef DEBUG
			cmn_err(CE_ALERT,
					"Device %s - bad inode magic/vsn "
					"daddr %lld #%d (magic=%x)",
				XFS_BUFTARG_NAME(mp->m_ddev_targp),
				(unsigned long long)imap.im_blkno, i,
				be16_to_cpu(dip->di_core.di_magic));
#endif
			XFS_CORRUPTION_ERROR("xfs_itobp", XFS_ERRLEVEL_HIGH,
					     mp, dip);
			xfs_trans_brelse(tp, bp);
			return XFS_ERROR(EFSCORRUPTED);
		}
	}

	xfs_inobp_check(mp, bp);

	/*
	 * Mark the buffer as an inode buffer now that it looks good
	 */
	XFS_BUF_SET_VTYPE(bp, B_FS_INO);

	/*
	 * Set *dipp to point to the on-disk inode in the buffer.
	 */
	*dipp = (xfs_dinode_t *)xfs_buf_offset(bp, imap.im_boffset);
	*bpp = bp;
	return 0;
}

/*
 * Move inode type and inode format specific information from the
 * on-disk inode to the in-core inode.  For fifos, devs, and sockets
 * this means set if_rdev to the proper value.  For files, directories,
 * and symlinks this means to bring in the in-line data or extent
 * pointers.  For a file in B-tree format, only the root is immediately
 * brought in-core.  The rest will be in-lined in if_extents when it
 * is first referenced (see xfs_iread_extents()).
 */
STATIC int
xfs_iformat(
	xfs_inode_t		*ip,
	xfs_dinode_t		*dip)
{
	xfs_attr_shortform_t	*atp;
	int			size;
	int			error;
	xfs_fsize_t             di_size;
	ip->i_df.if_ext_max =
		XFS_IFORK_DSIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t);
	error = 0;

	if (unlikely(be32_to_cpu(dip->di_core.di_nextents) +
		     be16_to_cpu(dip->di_core.di_anextents) >
		     be64_to_cpu(dip->di_core.di_nblocks))) {
		xfs_fs_repair_cmn_err(CE_WARN, ip->i_mount,
			"corrupt dinode %Lu, extent total = %d, nblocks = %Lu.",
			(unsigned long long)ip->i_ino,
			(int)(be32_to_cpu(dip->di_core.di_nextents) +
			      be16_to_cpu(dip->di_core.di_anextents)),
			(unsigned long long)
				be64_to_cpu(dip->di_core.di_nblocks));
		XFS_CORRUPTION_ERROR("xfs_iformat(1)", XFS_ERRLEVEL_LOW,
				     ip->i_mount, dip);
		return XFS_ERROR(EFSCORRUPTED);
	}

	if (unlikely(dip->di_core.di_forkoff > ip->i_mount->m_sb.sb_inodesize)) {
		xfs_fs_repair_cmn_err(CE_WARN, ip->i_mount,
			"corrupt dinode %Lu, forkoff = 0x%x.",
			(unsigned long long)ip->i_ino,
			dip->di_core.di_forkoff);
		XFS_CORRUPTION_ERROR("xfs_iformat(2)", XFS_ERRLEVEL_LOW,
				     ip->i_mount, dip);
		return XFS_ERROR(EFSCORRUPTED);
	}

	switch (ip->i_d.di_mode & S_IFMT) {