xfs_inode_item.c

linux 内核源代码

/*
 * Copyright (c) 2000-2002,2005 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_buf_item.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_dir2.h"
#include "xfs_dmapi.h"
#include "xfs_mount.h"
#include "xfs_trans_priv.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_inode_item.h"
#include "xfs_btree.h"
#include "xfs_ialloc.h"
#include "xfs_rw.h"


kmem_zone_t	*xfs_ili_zone;		/* inode log item zone */

/*
 * This returns the number of iovecs needed to log the given inode item.
 *
 * We need one iovec for the inode log format structure, one for the
 * inode core, and possibly one for the inode data/extents/b-tree root
 * and one for the inode attribute data/extents/b-tree root.
 */
STATIC uint
xfs_inode_item_size(
	xfs_inode_log_item_t	*iip)
{
	uint		nvecs;
	xfs_inode_t	*ip;

	ip = iip->ili_inode;
	nvecs = 2;

	/*
	 * Only log the data/extents/b-tree root if there is something
	 * left to log.
	 */
	iip->ili_format.ilf_fields |= XFS_ILOG_CORE;

	switch (ip->i_d.di_format) {
	case XFS_DINODE_FMT_EXTENTS:
		iip->ili_format.ilf_fields &=
			~(XFS_ILOG_DDATA | XFS_ILOG_DBROOT |
			  XFS_ILOG_DEV | XFS_ILOG_UUID);
		if ((iip->ili_format.ilf_fields & XFS_ILOG_DEXT) &&
		    (ip->i_d.di_nextents > 0) &&
		    (ip->i_df.if_bytes > 0)) {
			ASSERT(ip->i_df.if_u1.if_extents != NULL);
			nvecs++;
		} else {
			iip->ili_format.ilf_fields &= ~XFS_ILOG_DEXT;
		}
		break;

	case XFS_DINODE_FMT_BTREE:
		ASSERT(ip->i_df.if_ext_max ==
		       XFS_IFORK_DSIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t));
		iip->ili_format.ilf_fields &=
			~(XFS_ILOG_DDATA | XFS_ILOG_DEXT |
			  XFS_ILOG_DEV | XFS_ILOG_UUID);
		if ((iip->ili_format.ilf_fields & XFS_ILOG_DBROOT) &&
		    (ip->i_df.if_broot_bytes > 0)) {
			ASSERT(ip->i_df.if_broot != NULL);
			nvecs++;
		} else {
			ASSERT(!(iip->ili_format.ilf_fields &
				 XFS_ILOG_DBROOT));
#ifdef XFS_TRANS_DEBUG
			if (iip->ili_root_size > 0) {
				ASSERT(iip->ili_root_size ==
				       ip->i_df.if_broot_bytes);
				ASSERT(memcmp(iip->ili_orig_root,
					    ip->i_df.if_broot,
					    iip->ili_root_size) == 0);
			} else {
				ASSERT(ip->i_df.if_broot_bytes == 0);
			}
#endif
			iip->ili_format.ilf_fields &= ~XFS_ILOG_DBROOT;
		}
		break;

	case XFS_DINODE_FMT_LOCAL:
		iip->ili_format.ilf_fields &=
			~(XFS_ILOG_DEXT | XFS_ILOG_DBROOT |
			  XFS_ILOG_DEV | XFS_ILOG_UUID);
		if ((iip->ili_format.ilf_fields & XFS_ILOG_DDATA) &&
		    (ip->i_df.if_bytes > 0)) {
			ASSERT(ip->i_df.if_u1.if_data != NULL);
			ASSERT(ip->i_d.di_size > 0);
			nvecs++;
		} else {
			iip->ili_format.ilf_fields &= ~XFS_ILOG_DDATA;
		}
		break;

	case XFS_DINODE_FMT_DEV:
		iip->ili_format.ilf_fields &=
			~(XFS_ILOG_DDATA | XFS_ILOG_DBROOT |
			  XFS_ILOG_DEXT | XFS_ILOG_UUID);
		break;

	case XFS_DINODE_FMT_UUID:
		iip->ili_format.ilf_fields &=
			~(XFS_ILOG_DDATA | XFS_ILOG_DBROOT |
			  XFS_ILOG_DEXT | XFS_ILOG_DEV);
		break;

	default:
		ASSERT(0);
		break;
	}

	/*
	 * If there are no attributes associated with this file,
	 * then there cannot be anything more to log.
	 * Clear all attribute-related log flags.
	 */
	if (!XFS_IFORK_Q(ip)) {
		iip->ili_format.ilf_fields &=
			~(XFS_ILOG_ADATA | XFS_ILOG_ABROOT | XFS_ILOG_AEXT);
		return nvecs;
	}

	/*
	 * Log any necessary attribute data.
	 */
	switch (ip->i_d.di_aformat) {
	case XFS_DINODE_FMT_EXTENTS:
		iip->ili_format.ilf_fields &=
			~(XFS_ILOG_ADATA | XFS_ILOG_ABROOT);
		if ((iip->ili_format.ilf_fields & XFS_ILOG_AEXT) &&
		    (ip->i_d.di_anextents > 0) &&
		    (ip->i_afp->if_bytes > 0)) {
			ASSERT(ip->i_afp->if_u1.if_extents != NULL);
			nvecs++;
		} else {
			iip->ili_format.ilf_fields &= ~XFS_ILOG_AEXT;
		}
		break;

	case XFS_DINODE_FMT_BTREE:
		iip->ili_format.ilf_fields &=
			~(XFS_ILOG_ADATA | XFS_ILOG_AEXT);
		if ((iip->ili_format.ilf_fields & XFS_ILOG_ABROOT) &&
		    (ip->i_afp->if_broot_bytes > 0)) {
			ASSERT(ip->i_afp->if_broot != NULL);
			nvecs++;
		} else {
			iip->ili_format.ilf_fields &= ~XFS_ILOG_ABROOT;
		}
		break;

	case XFS_DINODE_FMT_LOCAL:
		iip->ili_format.ilf_fields &=
			~(XFS_ILOG_AEXT | XFS_ILOG_ABROOT);
		if ((iip->ili_format.ilf_fields & XFS_ILOG_ADATA) &&
		    (ip->i_afp->if_bytes > 0)) {
			ASSERT(ip->i_afp->if_u1.if_data != NULL);
			nvecs++;
		} else {
			iip->ili_format.ilf_fields &= ~XFS_ILOG_ADATA;
		}
		break;

	default:
		ASSERT(0);
		break;
	}

	return nvecs;
}

/*
 * This is called to fill in the vector of log iovecs for the
 * given inode log item.  It fills the first item with an inode
 * log format structure, the second with the on-disk inode structure,
 * and a possible third and/or fourth with the inode data/extents/b-tree
 * root and inode attributes data/extents/b-tree root.
 */
STATIC void
xfs_inode_item_format(
	xfs_inode_log_item_t	*iip,
	xfs_log_iovec_t		*log_vector)
{
	uint			nvecs;
	xfs_log_iovec_t		*vecp;
	xfs_inode_t		*ip;
	size_t			data_bytes;
	xfs_bmbt_rec_t		*ext_buffer;
	int			nrecs;
	xfs_mount_t		*mp;

	ip = iip->ili_inode;
	vecp = log_vector;

	vecp->i_addr = (xfs_caddr_t)&iip->ili_format;
	vecp->i_len  = sizeof(xfs_inode_log_format_t);
	XLOG_VEC_SET_TYPE(vecp, XLOG_REG_TYPE_IFORMAT);
	vecp++;
	nvecs	     = 1;

	/*
	 * Clear i_update_core if the timestamps (or any other
	 * non-transactional modification) need flushing/logging
	 * and we're about to log them with the rest of the core.
	 *
	 * This is the same logic as xfs_iflush() but this code can't
	 * run at the same time as xfs_iflush because we're in commit
	 * processing here and so we have the inode lock held in
	 * exclusive mode.  Although it doesn't really matter
	 * for the timestamps if both routines were to grab the
	 * timestamps or not.  That would be ok.
	 *
	 * We clear i_update_core before copying out the data.
	 * This is for coordination with our timestamp updates
	 * that don't hold the inode lock. They will always
	 * update the timestamps BEFORE setting i_update_core,
	 * so if we clear i_update_core after they set it we
	 * are guaranteed to see their updates to the timestamps
	 * either here.  Likewise, if they set it after we clear it
	 * here, we'll see it either on the next commit of this
	 * inode or the next time the inode gets flushed via
	 * xfs_iflush().  This depends on strongly ordered memory
	 * semantics, but we have that.  We use the SYNCHRONIZE
	 * macro to make sure that the compiler does not reorder
	 * the i_update_core access below the data copy below.
	 */
	if (ip->i_update_core)  {
		ip->i_update_core = 0;
		SYNCHRONIZE();
	}

	/*
	 * We don't have to worry about re-ordering here because
	 * the update_size field is protected by the inode lock
	 * and we have that held in exclusive mode.
	 */
	if (ip->i_update_size)
		ip->i_update_size = 0;

	/*
	 * Make sure to get the latest atime from the Linux inode.
	 */
	xfs_synchronize_atime(ip);

	vecp->i_addr = (xfs_caddr_t)&ip->i_d;
	vecp->i_len  = sizeof(xfs_dinode_core_t);
	XLOG_VEC_SET_TYPE(vecp, XLOG_REG_TYPE_ICORE);
	vecp++;
	nvecs++;
	iip->ili_format.ilf_fields |= XFS_ILOG_CORE;

	/*
	 * If this is really an old format inode, then we need to
	 * log it as such.  This means that we have to copy the link
	 * count from the new field to the old.  We don't have to worry
	 * about the new fields, because nothing trusts them as long as
	 * the old inode version number is there.  If the superblock already
	 * has a new version number, then we don't bother converting back.
	 */
	mp = ip->i_mount;
	ASSERT(ip->i_d.di_version == XFS_DINODE_VERSION_1 ||
	       XFS_SB_VERSION_HASNLINK(&mp->m_sb));
	if (ip->i_d.di_version == XFS_DINODE_VERSION_1) {
		if (!XFS_SB_VERSION_HASNLINK(&mp->m_sb)) {
			/*
			 * Convert it back.
			 */
			ASSERT(ip->i_d.di_nlink <= XFS_MAXLINK_1);
			ip->i_d.di_onlink = ip->i_d.di_nlink;
		} else {
			/*
			 * The superblock version has already been bumped,
			 * so just make the conversion to the new inode
			 * format permanent.
			 */
			ip->i_d.di_version = XFS_DINODE_VERSION_2;
			ip->i_d.di_onlink = 0;
			memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad));
		}
	}

	switch (ip->i_d.di_format) {
	case XFS_DINODE_FMT_EXTENTS:
		ASSERT(!(iip->ili_format.ilf_fields &
			 (XFS_ILOG_DDATA | XFS_ILOG_DBROOT |
			  XFS_ILOG_DEV | XFS_ILOG_UUID)));
		if (iip->ili_format.ilf_fields & XFS_ILOG_DEXT) {
			ASSERT(ip->i_df.if_bytes > 0);
			ASSERT(ip->i_df.if_u1.if_extents != NULL);
			ASSERT(ip->i_d.di_nextents > 0);
			ASSERT(iip->ili_extents_buf == NULL);
			nrecs = ip->i_df.if_bytes /
				(uint)sizeof(xfs_bmbt_rec_t);
			ASSERT(nrecs > 0);
#ifdef XFS_NATIVE_HOST
			if (nrecs == ip->i_d.di_nextents) {
				/*
				 * There are no delayed allocation
				 * extents, so just point to the
				 * real extents array.
				 */
				vecp->i_addr =
					(char *)(ip->i_df.if_u1.if_extents);
				vecp->i_len = ip->i_df.if_bytes;
				XLOG_VEC_SET_TYPE(vecp, XLOG_REG_TYPE_IEXT);
			} else
#endif
			{
				/*
				 * There are delayed allocation extents
				 * in the inode, or we need to convert
				 * the extents to on disk format.
				 * Use xfs_iextents_copy()
				 * to copy only the real extents into
				 * a separate buffer.  We'll free the
				 * buffer in the unlock routine.
				 */
				ext_buffer = kmem_alloc(ip->i_df.if_bytes,
					KM_SLEEP);
				iip->ili_extents_buf = ext_buffer;
				vecp->i_addr = (xfs_caddr_t)ext_buffer;
				vecp->i_len = xfs_iextents_copy(ip, ext_buffer,
						XFS_DATA_FORK);
				XLOG_VEC_SET_TYPE(vecp, XLOG_REG_TYPE_IEXT);
			}
			ASSERT(vecp->i_len <= ip->i_df.if_bytes);
			iip->ili_format.ilf_dsize = vecp->i_len;
			vecp++;
			nvecs++;
		}
		break;

	case XFS_DINODE_FMT_BTREE:
		ASSERT(!(iip->ili_format.ilf_fields &
			 (XFS_ILOG_DDATA | XFS_ILOG_DEXT |
			  XFS_ILOG_DEV | XFS_ILOG_UUID)));
		if (iip->ili_format.ilf_fields & XFS_ILOG_DBROOT) {
			ASSERT(ip->i_df.if_broot_bytes > 0);
			ASSERT(ip->i_df.if_broot != NULL);
			vecp->i_addr = (xfs_caddr_t)ip->i_df.if_broot;
			vecp->i_len = ip->i_df.if_broot_bytes;