summaryrefslogtreecommitdiffstats
path: root/fs/xfs/xfs_bmap_util.c
diff options
context:
space:
mode:
authorDave Chinner <dchinner@redhat.com>2013-08-12 20:49:48 +1000
committerBen Myers <bpm@sgi.com>2013-08-12 16:56:06 -0500
commita133d952b44cef278d2da664d742d51ef95f4dd3 (patch)
tree7a6f2d8bfc9be9d29246f2ed94582186331cbd45 /fs/xfs/xfs_bmap_util.c
parente546cb79ef7ebe53060369dae665fa449a544353 (diff)
downloadop-kernel-dev-a133d952b44cef278d2da664d742d51ef95f4dd3.zip
op-kernel-dev-a133d952b44cef278d2da664d742d51ef95f4dd3.tar.gz
xfs: consolidate extent swap code
So we don't need xfs_dfrag.h in userspace anymore, move the extent swap ioctl structure definition to xfs_fs.h where most of the other ioctl structure definitions are. Now that we don't need separate files for extent swapping, separate the basic file descriptor checking code to xfs_ioctl.c, and the code that does the extent swap operation to xfs_bmap_util.c. This cleanly separates the user interface code from the physical mechanism used to do the extent swap. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
Diffstat (limited to 'fs/xfs/xfs_bmap_util.c')
-rw-r--r--fs/xfs/xfs_bmap_util.c343
1 files changed, 343 insertions, 0 deletions
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index f557022..b5232d0 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1693,3 +1693,346 @@ xfs_change_file_space(
xfs_trans_set_sync(tp);
return xfs_trans_commit(tp, 0);
}
+
+/*
+ * We need to check that the format of the data fork in the temporary inode is
+ * valid for the target inode before doing the swap. This is not a problem with
+ * attr1 because of the fixed fork offset, but attr2 has a dynamically sized
+ * data fork depending on the space the attribute fork is taking so we can get
+ * invalid formats on the target inode.
+ *
+ * E.g. target has space for 7 extents in extent format, temp inode only has
+ * space for 6. If we defragment down to 7 extents, then the tmp format is a
+ * btree, but when swapped it needs to be in extent format. Hence we can't just
+ * blindly swap data forks on attr2 filesystems.
+ *
+ * Note that we check the swap in both directions so that we don't end up with
+ * a corrupt temporary inode, either.
+ *
+ * Note that fixing the way xfs_fsr sets up the attribute fork in the source
+ * inode will prevent this situation from occurring, so all we do here is
+ * reject and log the attempt. basically we are putting the responsibility on
+ * userspace to get this right.
+ */
+static int
+xfs_swap_extents_check_format(
+ xfs_inode_t *ip, /* target inode */
+ xfs_inode_t *tip) /* tmp inode */
+{
+
+ /* Should never get a local format */
+ if (ip->i_d.di_format == XFS_DINODE_FMT_LOCAL ||
+ tip->i_d.di_format == XFS_DINODE_FMT_LOCAL)
+ return EINVAL;
+
+ /*
+ * if the target inode has less extents that then temporary inode then
+ * why did userspace call us?
+ */
+ if (ip->i_d.di_nextents < tip->i_d.di_nextents)
+ return EINVAL;
+
+ /*
+ * 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
+ * as we already know there are less extents in the temp inode.
+ */
+ if (ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
+ tip->i_d.di_format == XFS_DINODE_FMT_BTREE)
+ return EINVAL;
+
+ /* Check temp in extent form to max in target */
+ if (tip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
+ XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK) >
+ XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK))
+ return EINVAL;
+
+ /* Check target in extent form to max in temp */
+ if (ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
+ XFS_IFORK_NEXTENTS(ip, XFS_DATA_FORK) >
+ XFS_IFORK_MAXEXT(tip, XFS_DATA_FORK))
+ return EINVAL;
+
+ /*
+ * If we are in a btree format, check that the temp root block will fit
+ * in the target and that it has enough extents to be in btree format
+ * in the target.
+ *
+ * Note that we have to be careful to allow btree->extent conversions
+ * (a common defrag case) which will occur when the temp inode is in
+ * extent format...
+ */
+ if (tip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
+ if (XFS_IFORK_BOFF(ip) &&
+ XFS_BMAP_BMDR_SPACE(tip->i_df.if_broot) > XFS_IFORK_BOFF(ip))
+ return EINVAL;
+ if (XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK) <=
+ XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK))
+ return EINVAL;
+ }
+
+ /* Reciprocal target->temp btree format checks */
+ if (ip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
+ if (XFS_IFORK_BOFF(tip) &&
+ XFS_BMAP_BMDR_SPACE(ip->i_df.if_broot) > XFS_IFORK_BOFF(tip))
+ return EINVAL;
+ if (XFS_IFORK_NEXTENTS(ip, XFS_DATA_FORK) <=
+ XFS_IFORK_MAXEXT(tip, XFS_DATA_FORK))
+ return EINVAL;
+ }
+
+ return 0;
+}
+
+int
+xfs_swap_extents(
+ xfs_inode_t *ip, /* target inode */
+ xfs_inode_t *tip, /* tmp inode */
+ xfs_swapext_t *sxp)
+{
+ 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;
+
+ /*
+ * We have no way of updating owner information in the BMBT blocks for
+ * each inode on CRC enabled filesystems, so to avoid corrupting the
+ * this metadata we simply don't allow extent swaps to occur.
+ */
+ if (xfs_sb_version_hascrc(&mp->m_sb))
+ return XFS_ERROR(EINVAL);
+
+ tempifp = kmem_alloc(sizeof(xfs_ifork_t), KM_MAYFAIL);
+ if (!tempifp) {
+ error = XFS_ERROR(ENOMEM);
+ goto out;
+ }
+
+ /*
+ * we have to do two separate lock calls here to keep lockdep
+ * happy. If we try to get all the locks in one call, lock will
+ * report false positives when we drop the ILOCK and regain them
+ * below.
+ */
+ xfs_lock_two_inodes(ip, tip, XFS_IOLOCK_EXCL);
+ xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);
+
+ /* Verify that both files have the same format */
+ if ((ip->i_d.di_mode & S_IFMT) != (tip->i_d.di_mode & S_IFMT)) {
+ error = XFS_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 = XFS_ERROR(EINVAL);
+ goto out_unlock;
+ }
+
+ error = -filemap_write_and_wait(VFS_I(tip)->i_mapping);
+ if (error)
+ goto out_unlock;
+ truncate_pagecache_range(VFS_I(tip), 0, -1);
+
+ /* Verify O_DIRECT for ftmp */
+ if (VN_CACHED(VFS_I(tip)) != 0) {
+ error = XFS_ERROR(EINVAL);
+ goto out_unlock;
+ }
+
+ /* 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 = XFS_ERROR(EFAULT);
+ goto out_unlock;
+ }
+
+ 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_unlock;
+ }
+
+ /*
+ * 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 = XFS_ERROR(EBUSY);
+ goto out_unlock;
+ }
+
+ /* We need to fail if the file is memory mapped. Once we have tossed
+ * all existing pages, the page fault will have no option
+ * but to go to the filesystem for pages. By making the page fault call
+ * vop_read (or write in the case of autogrow) they block on the iolock
+ * until we have switched the extents.
+ */
+ if (VN_MAPPED(VFS_I(ip))) {
+ error = XFS_ERROR(EBUSY);
+ goto out_unlock;
+ }
+
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ xfs_iunlock(tip, XFS_ILOCK_EXCL);
+
+ /*
+ * There is a race condition here since we gave up the
+ * ilock. However, the data fork will not change since
+ * we have the iolock (locked for truncation too) so we
+ * are safe. We don't really care if non-io related
+ * fields change.
+ */
+ truncate_pagecache_range(VFS_I(ip), 0, -1);
+
+ tp = xfs_trans_alloc(mp, XFS_TRANS_SWAPEXT);
+ if ((error = xfs_trans_reserve(tp, 0,
+ XFS_ICHANGE_LOG_RES(mp), 0,
+ 0, 0))) {
+ xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+ xfs_iunlock(tip, XFS_IOLOCK_EXCL);
+ xfs_trans_cancel(tp, 0);
+ goto out;
+ }
+ xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);
+
+ /*
+ * 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);
+ if (error)
+ goto out_trans_cancel;
+ }
+ 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);
+ if (error)
+ goto out_trans_cancel;
+ }
+
+ /*
+ * Swap the data forks of the inodes
+ */
+ ifp = &ip->i_df;
+ tifp = &tip->i_df;
+ *tempifp = *ifp; /* struct copy */
+ *ifp = *tifp; /* struct copy */
+ *tifp = *tempifp; /* struct copy */
+
+ /*
+ * Fix the on-disk inode values
+ */
+ tmp = (__uint64_t)ip->i_d.di_nblocks;
+ ip->i_d.di_nblocks = tip->i_d.di_nblocks - taforkblks + aforkblks;
+ tip->i_d.di_nblocks = tmp + taforkblks - aforkblks;
+
+ tmp = (__uint64_t) ip->i_d.di_nextents;
+ ip->i_d.di_nextents = tip->i_d.di_nextents;
+ tip->i_d.di_nextents = tmp;
+
+ tmp = (__uint64_t) ip->i_d.di_format;
+ ip->i_d.di_format = tip->i_d.di_format;
+ tip->i_d.di_format = tmp;
+
+ /*
+ * The extents in the source inode could still contain speculative
+ * preallocation beyond EOF (e.g. the file is open but not modified
+ * while defrag is in progress). In that case, we need to copy over the
+ * number of delalloc blocks the data fork in the source inode is
+ * tracking beyond EOF so that when the fork is truncated away when the
+ * temporary inode is unlinked we don't underrun the i_delayed_blks
+ * counter on that inode.
+ */
+ ASSERT(tip->i_delayed_blks == 0);
+ tip->i_delayed_blks = ip->i_delayed_blks;
+ ip->i_delayed_blks = 0;
+
+ src_log_flags = XFS_ILOG_CORE;
+ switch (ip->i_d.di_format) {
+ case XFS_DINODE_FMT_EXTENTS:
+ /* If the extents fit in the inode, fix the
+ * pointer. Otherwise it's already NULL or
+ * pointing to the extent.
+ */
+ if (ip->i_d.di_nextents <= XFS_INLINE_EXTS) {
+ ifp->if_u1.if_extents =
+ ifp->if_u2.if_inline_ext;
+ }
+ src_log_flags |= XFS_ILOG_DEXT;
+ break;
+ case XFS_DINODE_FMT_BTREE:
+ src_log_flags |= XFS_ILOG_DBROOT;
+ break;
+ }
+
+ target_log_flags = XFS_ILOG_CORE;
+ switch (tip->i_d.di_format) {
+ case XFS_DINODE_FMT_EXTENTS:
+ /* If the extents fit in the inode, fix the
+ * pointer. Otherwise it's already NULL or
+ * pointing to the extent.
+ */
+ if (tip->i_d.di_nextents <= XFS_INLINE_EXTS) {
+ tifp->if_u1.if_extents =
+ tifp->if_u2.if_inline_ext;
+ }
+ target_log_flags |= XFS_ILOG_DEXT;
+ break;
+ case XFS_DINODE_FMT_BTREE:
+ target_log_flags |= XFS_ILOG_DBROOT;
+ break;
+ }
+
+
+ xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
+ xfs_trans_ijoin(tp, tip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
+
+ xfs_trans_log_inode(tp, ip, src_log_flags);
+ xfs_trans_log_inode(tp, tip, target_log_flags);
+
+ /*
+ * If this is a synchronous mount, make sure that the
+ * transaction goes to disk before returning to the user.
+ */
+ if (mp->m_flags & XFS_MOUNT_WSYNC)
+ xfs_trans_set_sync(tp);
+
+ error = xfs_trans_commit(tp, 0);
+
+ 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, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
+ xfs_iunlock(tip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
+ goto out;
+
+out_trans_cancel:
+ xfs_trans_cancel(tp, 0);
+ goto out_unlock;
+}
OpenPOWER on IntegriCloud