*/
static int
xfs_swap_extents_check_format(
- xfs_inode_t *ip, /* target inode */
- xfs_inode_t *tip) /* tmp inode */
+ struct xfs_inode *ip, /* target inode */
+ struct xfs_inode *tip) /* tmp inode */
{
/* Should never get a local format */
if (ip->i_d.di_nextents < tip->i_d.di_nextents)
return -EINVAL;
+ /*
+ * If we have to use the (expensive) rmap swap method, we can
+ * handle any number of extents and any format.
+ */
+ if (xfs_sb_version_hasrmapbt(&ip->i_mount->m_sb))
+ return 0;
+
/*
* if the target inode is in extent form and the temp inode is in btree
* form then we will end up with the target inode in the wrong format
return 0;
}
-int
-xfs_swap_extents(
- xfs_inode_t *ip, /* target inode */
- xfs_inode_t *tip, /* tmp inode */
- xfs_swapext_t *sxp)
+/*
+ * Move extents from one file to another, when rmap is enabled.
+ */
+STATIC int
+xfs_swap_extent_rmap(
+ struct xfs_trans **tpp,
+ struct xfs_inode *ip,
+ struct xfs_inode *tip)
{
- xfs_mount_t *mp = ip->i_mount;
- xfs_trans_t *tp;
- xfs_bstat_t *sbp = &sxp->sx_stat;
- xfs_ifork_t *tempifp, *ifp, *tifp;
- int src_log_flags, target_log_flags;
- int error = 0;
- int aforkblks = 0;
- int taforkblks = 0;
- __uint64_t tmp;
- int lock_flags;
- struct xfs_ifork *cowfp;
- __uint64_t f;
-
- /* XXX: we can't do this with rmap, will fix later */
- if (xfs_sb_version_hasrmapbt(&mp->m_sb))
- return -EOPNOTSUPP;
-
- tempifp = kmem_alloc(sizeof(xfs_ifork_t), KM_MAYFAIL);
- if (!tempifp) {
- error = -ENOMEM;
- goto out;
- }
+ struct xfs_bmbt_irec irec;
+ struct xfs_bmbt_irec uirec;
+ struct xfs_bmbt_irec tirec;
+ xfs_fileoff_t offset_fsb;
+ xfs_fileoff_t end_fsb;
+ xfs_filblks_t count_fsb;
+ xfs_fsblock_t firstfsb;
+ struct xfs_defer_ops dfops;
+ int error;
+ xfs_filblks_t ilen;
+ xfs_filblks_t rlen;
+ int nimaps;
+ __uint64_t tip_flags2;
/*
- * Lock the inodes against other IO, page faults and truncate to
- * begin with. Then we can ensure the inodes are flushed and have no
- * page cache safely. Once we have done this we can take the ilocks and
- * do the rest of the checks.
+ * If the source file has shared blocks, we must flag the donor
+ * file as having shared blocks so that we get the shared-block
+ * rmap functions when we go to fix up the rmaps. The flags
+ * will be switch for reals later.
*/
- lock_flags = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
- xfs_lock_two_inodes(ip, tip, XFS_IOLOCK_EXCL);
- xfs_lock_two_inodes(ip, tip, XFS_MMAPLOCK_EXCL);
-
- /* Verify that both files have the same format */
- if ((VFS_I(ip)->i_mode & S_IFMT) != (VFS_I(tip)->i_mode & S_IFMT)) {
- error = -EINVAL;
- goto out_unlock;
- }
+ tip_flags2 = tip->i_d.di_flags2;
+ if (ip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK)
+ tip->i_d.di_flags2 |= XFS_DIFLAG2_REFLINK;
+
+ offset_fsb = 0;
+ end_fsb = XFS_B_TO_FSB(ip->i_mount, i_size_read(VFS_I(ip)));
+ count_fsb = (xfs_filblks_t)(end_fsb - offset_fsb);
+
+ while (count_fsb) {
+ /* Read extent from the donor file */
+ nimaps = 1;
+ error = xfs_bmapi_read(tip, offset_fsb, count_fsb, &tirec,
+ &nimaps, 0);
+ if (error)
+ goto out;
+ ASSERT(nimaps == 1);
+ ASSERT(tirec.br_startblock != DELAYSTARTBLOCK);
+
+ trace_xfs_swap_extent_rmap_remap(tip, &tirec);
+ ilen = tirec.br_blockcount;
+
+ /* Unmap the old blocks in the source file. */
+ while (tirec.br_blockcount) {
+ xfs_defer_init(&dfops, &firstfsb);
+ trace_xfs_swap_extent_rmap_remap_piece(tip, &tirec);
+
+ /* Read extent from the source file */
+ nimaps = 1;
+ error = xfs_bmapi_read(ip, tirec.br_startoff,
+ tirec.br_blockcount, &irec,
+ &nimaps, 0);
+ if (error)
+ goto out_defer;
+ ASSERT(nimaps == 1);
+ ASSERT(tirec.br_startoff == irec.br_startoff);
+ trace_xfs_swap_extent_rmap_remap_piece(ip, &irec);
+
+ /* Trim the extent. */
+ uirec = tirec;
+ uirec.br_blockcount = rlen = min_t(xfs_filblks_t,
+ tirec.br_blockcount,
+ irec.br_blockcount);
+ trace_xfs_swap_extent_rmap_remap_piece(tip, &uirec);
+
+ /* Remove the mapping from the donor file. */
+ error = xfs_bmap_unmap_extent((*tpp)->t_mountp, &dfops,
+ tip, &uirec);
+ if (error)
+ goto out_defer;
- /* Verify both files are either real-time or non-realtime */
- if (XFS_IS_REALTIME_INODE(ip) != XFS_IS_REALTIME_INODE(tip)) {
- error = -EINVAL;
- goto out_unlock;
- }
+ /* Remove the mapping from the source file. */
+ error = xfs_bmap_unmap_extent((*tpp)->t_mountp, &dfops,
+ ip, &irec);
+ if (error)
+ goto out_defer;
- error = xfs_swap_extent_flush(ip);
- if (error)
- goto out_unlock;
- error = xfs_swap_extent_flush(tip);
- if (error)
- goto out_unlock;
+ /* Map the donor file's blocks into the source file. */
+ error = xfs_bmap_map_extent((*tpp)->t_mountp, &dfops,
+ ip, &uirec);
+ if (error)
+ goto out_defer;
- error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp);
- if (error)
- goto out_unlock;
+ /* Map the source file's blocks into the donor file. */
+ error = xfs_bmap_map_extent((*tpp)->t_mountp, &dfops,
+ tip, &irec);
+ if (error)
+ goto out_defer;
- /*
- * Lock and join the inodes to the tansaction so that transaction commit
- * or cancel will unlock the inodes from this point onwards.
- */
- xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);
- lock_flags |= XFS_ILOCK_EXCL;
- xfs_trans_ijoin(tp, ip, lock_flags);
- xfs_trans_ijoin(tp, tip, lock_flags);
+ error = xfs_defer_finish(tpp, &dfops, ip);
+ if (error)
+ goto out_defer;
+ tirec.br_startoff += rlen;
+ if (tirec.br_startblock != HOLESTARTBLOCK &&
+ tirec.br_startblock != DELAYSTARTBLOCK)
+ tirec.br_startblock += rlen;
+ tirec.br_blockcount -= rlen;
+ }
- /* Verify all data are being swapped */
- if (sxp->sx_offset != 0 ||
- sxp->sx_length != ip->i_d.di_size ||
- sxp->sx_length != tip->i_d.di_size) {
- error = -EFAULT;
- goto out_trans_cancel;
+ /* Roll on... */
+ count_fsb -= ilen;
+ offset_fsb += ilen;
}
- trace_xfs_swap_extent_before(ip, 0);
- trace_xfs_swap_extent_before(tip, 1);
+ tip->i_d.di_flags2 = tip_flags2;
+ return 0;
- /* check inode formats now that data is flushed */
- error = xfs_swap_extents_check_format(ip, tip);
- if (error) {
- xfs_notice(mp,
- "%s: inode 0x%llx format is incompatible for exchanging.",
- __func__, ip->i_ino);
- goto out_trans_cancel;
- }
+out_defer:
+ xfs_defer_cancel(&dfops);
+out:
+ trace_xfs_swap_extent_rmap_error(ip, error, _RET_IP_);
+ tip->i_d.di_flags2 = tip_flags2;
+ return error;
+}
+
+/* Swap the extents of two files by swapping data forks. */
+STATIC int
+xfs_swap_extent_forks(
+ struct xfs_trans *tp,
+ struct xfs_inode *ip,
+ struct xfs_inode *tip,
+ int *src_log_flags,
+ int *target_log_flags)
+{
+ struct xfs_ifork tempifp, *ifp, *tifp;
+ int aforkblks = 0;
+ int taforkblks = 0;
+ __uint64_t tmp;
+ int error;
- /*
- * Compare the current change & modify times with that
- * passed in. If they differ, we abort this swap.
- * This is the mechanism used to ensure the calling
- * process that the file was not changed out from
- * under it.
- */
- if ((sbp->bs_ctime.tv_sec != VFS_I(ip)->i_ctime.tv_sec) ||
- (sbp->bs_ctime.tv_nsec != VFS_I(ip)->i_ctime.tv_nsec) ||
- (sbp->bs_mtime.tv_sec != VFS_I(ip)->i_mtime.tv_sec) ||
- (sbp->bs_mtime.tv_nsec != VFS_I(ip)->i_mtime.tv_nsec)) {
- error = -EBUSY;
- goto out_trans_cancel;
- }
/*
* Count the number of extended attribute blocks
*/
if ( ((XFS_IFORK_Q(ip) != 0) && (ip->i_d.di_anextents > 0)) &&
(ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)) {
- error = xfs_bmap_count_blocks(tp, ip, XFS_ATTR_FORK, &aforkblks);
+ error = xfs_bmap_count_blocks(tp, ip, XFS_ATTR_FORK,
+ &aforkblks);
if (error)
- goto out_trans_cancel;
+ return error;
}
if ( ((XFS_IFORK_Q(tip) != 0) && (tip->i_d.di_anextents > 0)) &&
(tip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)) {
error = xfs_bmap_count_blocks(tp, tip, XFS_ATTR_FORK,
- &taforkblks);
+ &taforkblks);
if (error)
- goto out_trans_cancel;
+ return error;
}
/*
* buffers, and so the validation done on read will expect the owner
* field to be correctly set. Once we change the owners, we can swap the
* inode forks.
- *
- * Note the trickiness in setting the log flags - we set the owner log
- * flag on the opposite inode (i.e. the inode we are setting the new
- * owner to be) because once we swap the forks and log that, log
- * recovery is going to see the fork as owned by the swapped inode,
- * not the pre-swapped inodes.
*/
- src_log_flags = XFS_ILOG_CORE;
- target_log_flags = XFS_ILOG_CORE;
if (ip->i_d.di_version == 3 &&
ip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
- target_log_flags |= XFS_ILOG_DOWNER;
+ (*target_log_flags) |= XFS_ILOG_DOWNER;
error = xfs_bmbt_change_owner(tp, ip, XFS_DATA_FORK,
tip->i_ino, NULL);
if (error)
- goto out_trans_cancel;
+ return error;
}
if (tip->i_d.di_version == 3 &&
tip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
- src_log_flags |= XFS_ILOG_DOWNER;
+ (*src_log_flags) |= XFS_ILOG_DOWNER;
error = xfs_bmbt_change_owner(tp, tip, XFS_DATA_FORK,
ip->i_ino, NULL);
if (error)
- goto out_trans_cancel;
+ return error;
}
/*
*/
ifp = &ip->i_df;
tifp = &tip->i_df;
- *tempifp = *ifp; /* struct copy */
+ tempifp = *ifp; /* struct copy */
*ifp = *tifp; /* struct copy */
- *tifp = *tempifp; /* struct copy */
+ *tifp = tempifp; /* struct copy */
/*
* Fix the on-disk inode values
ifp->if_u1.if_extents =
ifp->if_u2.if_inline_ext;
}
- src_log_flags |= XFS_ILOG_DEXT;
+ (*src_log_flags) |= XFS_ILOG_DEXT;
break;
case XFS_DINODE_FMT_BTREE:
ASSERT(ip->i_d.di_version < 3 ||
- (src_log_flags & XFS_ILOG_DOWNER));
- src_log_flags |= XFS_ILOG_DBROOT;
+ (*src_log_flags & XFS_ILOG_DOWNER));
+ (*src_log_flags) |= XFS_ILOG_DBROOT;
break;
}
tifp->if_u1.if_extents =
tifp->if_u2.if_inline_ext;
}
- target_log_flags |= XFS_ILOG_DEXT;
+ (*target_log_flags) |= XFS_ILOG_DEXT;
break;
case XFS_DINODE_FMT_BTREE:
- target_log_flags |= XFS_ILOG_DBROOT;
+ (*target_log_flags) |= XFS_ILOG_DBROOT;
ASSERT(tip->i_d.di_version < 3 ||
- (target_log_flags & XFS_ILOG_DOWNER));
+ (*target_log_flags & XFS_ILOG_DOWNER));
break;
}
+ return 0;
+}
+
+int
+xfs_swap_extents(
+ struct xfs_inode *ip, /* target inode */
+ struct xfs_inode *tip, /* tmp inode */
+ struct xfs_swapext *sxp)
+{
+ struct xfs_mount *mp = ip->i_mount;
+ struct xfs_trans *tp;
+ struct xfs_bstat *sbp = &sxp->sx_stat;
+ int src_log_flags, target_log_flags;
+ int error = 0;
+ int lock_flags;
+ struct xfs_ifork *cowfp;
+ __uint64_t f;
+ int resblks;
+
+ /*
+ * Lock the inodes against other IO, page faults and truncate to
+ * begin with. Then we can ensure the inodes are flushed and have no
+ * page cache safely. Once we have done this we can take the ilocks and
+ * do the rest of the checks.
+ */
+ lock_flags = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
+ xfs_lock_two_inodes(ip, tip, XFS_IOLOCK_EXCL);
+ xfs_lock_two_inodes(ip, tip, XFS_MMAPLOCK_EXCL);
+
+ /* Verify that both files have the same format */
+ if ((VFS_I(ip)->i_mode & S_IFMT) != (VFS_I(tip)->i_mode & S_IFMT)) {
+ error = -EINVAL;
+ goto out_unlock;
+ }
+
+ /* Verify both files are either real-time or non-realtime */
+ if (XFS_IS_REALTIME_INODE(ip) != XFS_IS_REALTIME_INODE(tip)) {
+ error = -EINVAL;
+ goto out_unlock;
+ }
+
+ error = xfs_swap_extent_flush(ip);
+ if (error)
+ goto out_unlock;
+ error = xfs_swap_extent_flush(tip);
+ if (error)
+ goto out_unlock;
+
+ /*
+ * Extent "swapping" with rmap requires a permanent reservation and
+ * a block reservation because it's really just a remap operation
+ * performed with log redo items!
+ */
+ if (xfs_sb_version_hasrmapbt(&mp->m_sb)) {
+ /*
+ * Conceptually this shouldn't affect the shape of either
+ * bmbt, but since we atomically move extents one by one,
+ * we reserve enough space to rebuild both trees.
+ */
+ resblks = XFS_SWAP_RMAP_SPACE_RES(mp,
+ XFS_IFORK_NEXTENTS(ip, XFS_DATA_FORK),
+ XFS_DATA_FORK) +
+ XFS_SWAP_RMAP_SPACE_RES(mp,
+ XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK),
+ XFS_DATA_FORK);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks,
+ 0, 0, &tp);
+ } else
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0,
+ 0, 0, &tp);
+ if (error)
+ goto out_unlock;
+
+ /*
+ * Lock and join the inodes to the tansaction so that transaction commit
+ * or cancel will unlock the inodes from this point onwards.
+ */
+ xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);
+ lock_flags |= XFS_ILOCK_EXCL;
+ xfs_trans_ijoin(tp, ip, 0);
+ xfs_trans_ijoin(tp, tip, 0);
+
+
+ /* Verify all data are being swapped */
+ if (sxp->sx_offset != 0 ||
+ sxp->sx_length != ip->i_d.di_size ||
+ sxp->sx_length != tip->i_d.di_size) {
+ error = -EFAULT;
+ goto out_trans_cancel;
+ }
+
+ trace_xfs_swap_extent_before(ip, 0);
+ trace_xfs_swap_extent_before(tip, 1);
+
+ /* check inode formats now that data is flushed */
+ error = xfs_swap_extents_check_format(ip, tip);
+ if (error) {
+ xfs_notice(mp,
+ "%s: inode 0x%llx format is incompatible for exchanging.",
+ __func__, ip->i_ino);
+ goto out_trans_cancel;
+ }
+
+ /*
+ * Compare the current change & modify times with that
+ * passed in. If they differ, we abort this swap.
+ * This is the mechanism used to ensure the calling
+ * process that the file was not changed out from
+ * under it.
+ */
+ if ((sbp->bs_ctime.tv_sec != VFS_I(ip)->i_ctime.tv_sec) ||
+ (sbp->bs_ctime.tv_nsec != VFS_I(ip)->i_ctime.tv_nsec) ||
+ (sbp->bs_mtime.tv_sec != VFS_I(ip)->i_mtime.tv_sec) ||
+ (sbp->bs_mtime.tv_nsec != VFS_I(ip)->i_mtime.tv_nsec)) {
+ error = -EBUSY;
+ goto out_trans_cancel;
+ }
+
+ /*
+ * Note the trickiness in setting the log flags - we set the owner log
+ * flag on the opposite inode (i.e. the inode we are setting the new
+ * owner to be) because once we swap the forks and log that, log
+ * recovery is going to see the fork as owned by the swapped inode,
+ * not the pre-swapped inodes.
+ */
+ src_log_flags = XFS_ILOG_CORE;
+ target_log_flags = XFS_ILOG_CORE;
+
+ if (xfs_sb_version_hasrmapbt(&mp->m_sb))
+ error = xfs_swap_extent_rmap(&tp, ip, tip);
+ else
+ error = xfs_swap_extent_forks(tp, ip, tip, &src_log_flags,
+ &target_log_flags);
+ if (error)
+ goto out_trans_cancel;
+
/* Do we have to swap reflink flags? */
if ((ip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK) ^
(tip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK)) {
trace_xfs_swap_extent_after(ip, 0);
trace_xfs_swap_extent_after(tip, 1);
-out:
- kmem_free(tempifp);
- return error;
-out_unlock:
xfs_iunlock(ip, lock_flags);
xfs_iunlock(tip, lock_flags);
- goto out;
+ return error;
out_trans_cancel:
xfs_trans_cancel(tp);
- goto out;
+
+out_unlock:
+ xfs_iunlock(ip, lock_flags);
+ xfs_iunlock(tip, lock_flags);
+ return error;
}
projects / cascardo / linux.git / blobdiff