* as the tree is sparse and a gang lookup walks to find
* the number of objects requested.
*/
- read_lock(&pag->pag_ici_lock);
if (tag == XFS_ICI_NO_TAG) {
nr_found = radix_tree_gang_lookup(&pag->pag_ici_root,
(void **)&ip, *first_index, 1);
(void **)&ip, *first_index, 1, tag);
}
if (!nr_found)
- goto unlock;
+ return NULL;
/*
* Update the index for the next lookup. Catch overflows
*/
*first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1);
if (*first_index < XFS_INO_TO_AGINO(mp, ip->i_ino))
- goto unlock;
-
+ return NULL;
return ip;
-
-unlock:
- read_unlock(&pag->pag_ici_lock);
- return NULL;
}
STATIC int
int (*execute)(struct xfs_inode *ip,
struct xfs_perag *pag, int flags),
int flags,
- int tag)
+ int tag,
+ int exclusive)
{
struct xfs_perag *pag = &mp->m_perag[ag];
uint32_t first_index;
int error = 0;
xfs_inode_t *ip;
+ if (exclusive)
+ write_lock(&pag->pag_ici_lock);
+ else
+ read_lock(&pag->pag_ici_lock);
ip = xfs_inode_ag_lookup(mp, pag, &first_index, tag);
- if (!ip)
+ if (!ip) {
+ if (exclusive)
+ write_unlock(&pag->pag_ici_lock);
+ else
+ read_unlock(&pag->pag_ici_lock);
break;
+ }
+ /* execute releases pag->pag_ici_lock */
error = execute(ip, pag, flags);
if (error == EAGAIN) {
skipped++;
}
if (error)
last_error = error;
- /*
- * bail out if the filesystem is corrupted.
- */
+
+ /* bail out if the filesystem is corrupted. */
if (error == EFSCORRUPTED)
break;
int (*execute)(struct xfs_inode *ip,
struct xfs_perag *pag, int flags),
int flags,
- int tag)
+ int tag,
+ int exclusive)
{
int error = 0;
int last_error = 0;
for (ag = 0; ag < mp->m_sb.sb_agcount; ag++) {
if (!mp->m_perag[ag].pag_ici_init)
continue;
- error = xfs_inode_ag_walk(mp, ag, execute, flags, tag);
+ error = xfs_inode_ag_walk(mp, ag, execute, flags, tag,
+ exclusive);
if (error) {
last_error = error;
if (error == EFSCORRUPTED)
struct xfs_perag *pag)
{
struct inode *inode = VFS_I(ip);
+ int error = EFSCORRUPTED;
/* nothing to sync during shutdown */
- if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
- read_unlock(&pag->pag_ici_lock);
- return EFSCORRUPTED;
- }
+ if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+ goto out_unlock;
- /*
- * If we can't get a reference on the inode, it must be in reclaim.
- * Leave it for the reclaim code to flush. Also avoid inodes that
- * haven't been fully initialised.
- */
- if (!igrab(inode)) {
- read_unlock(&pag->pag_ici_lock);
- return ENOENT;
- }
- read_unlock(&pag->pag_ici_lock);
+ /* avoid new or reclaimable inodes. Leave for reclaim code to flush */
+ error = ENOENT;
+ if (xfs_iflags_test(ip, XFS_INEW | XFS_IRECLAIMABLE | XFS_IRECLAIM))
+ goto out_unlock;
- if (is_bad_inode(inode) || xfs_iflags_test(ip, XFS_INEW)) {
+ /* If we can't grab the inode, it must on it's way to reclaim. */
+ if (!igrab(inode))
+ goto out_unlock;
+
+ if (is_bad_inode(inode)) {
IRELE(ip);
- return ENOENT;
+ goto out_unlock;
}
- return 0;
+ /* inode is valid */
+ error = 0;
+out_unlock:
+ read_unlock(&pag->pag_ici_lock);
+ return error;
}
STATIC int
ASSERT((flags & ~(SYNC_TRYLOCK|SYNC_WAIT)) == 0);
error = xfs_inode_ag_iterator(mp, xfs_sync_inode_data, flags,
- XFS_ICI_NO_TAG);
+ XFS_ICI_NO_TAG, 0);
if (error)
return XFS_ERROR(error);
ASSERT((flags & ~SYNC_WAIT) == 0);
return xfs_inode_ag_iterator(mp, xfs_sync_inode_attr, flags,
- XFS_ICI_NO_TAG);
+ XFS_ICI_NO_TAG, 0);
}
STATIC int
kthread_stop(mp->m_sync_task);
}
-STATIC int
-xfs_reclaim_inode(
- xfs_inode_t *ip,
- int sync_mode)
-{
- xfs_perag_t *pag = xfs_get_perag(ip->i_mount, ip->i_ino);
-
- /* The hash lock here protects a thread in xfs_iget_core from
- * racing with us on linking the inode back with a vnode.
- * Once we have the XFS_IRECLAIM flag set it will not touch
- * us.
- */
- write_lock(&pag->pag_ici_lock);
- spin_lock(&ip->i_flags_lock);
- if (__xfs_iflags_test(ip, XFS_IRECLAIM) ||
- !__xfs_iflags_test(ip, XFS_IRECLAIMABLE)) {
- spin_unlock(&ip->i_flags_lock);
- write_unlock(&pag->pag_ici_lock);
- return -EAGAIN;
- }
- __xfs_iflags_set(ip, XFS_IRECLAIM);
- spin_unlock(&ip->i_flags_lock);
- write_unlock(&pag->pag_ici_lock);
- xfs_put_perag(ip->i_mount, pag);
-
- /*
- * If the inode is still dirty, then flush it out. If the inode
- * is not in the AIL, then it will be OK to flush it delwri as
- * long as xfs_iflush() does not keep any references to the inode.
- * We leave that decision up to xfs_iflush() since it has the
- * knowledge of whether it's OK to simply do a delwri flush of
- * the inode or whether we need to wait until the inode is
- * pulled from the AIL.
- * We get the flush lock regardless, though, just to make sure
- * we don't free it while it is being flushed.
- */
- xfs_ilock(ip, XFS_ILOCK_EXCL);
- xfs_iflock(ip);
-
- /*
- * In the case of a forced shutdown we rely on xfs_iflush() to
- * wait for the inode to be unpinned before returning an error.
- */
- if (!is_bad_inode(VFS_I(ip)) && xfs_iflush(ip, sync_mode) == 0) {
- /* synchronize with xfs_iflush_done */
- xfs_iflock(ip);
- xfs_ifunlock(ip);
- }
-
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
- xfs_ireclaim(ip);
- return 0;
-}
-
void
__xfs_inode_set_reclaim_tag(
struct xfs_perag *pag,
}
STATIC int
-xfs_reclaim_inode_now(
+xfs_reclaim_inode(
struct xfs_inode *ip,
struct xfs_perag *pag,
- int flags)
+ int sync_mode)
{
- /* ignore if already under reclaim */
- if (xfs_iflags_test(ip, XFS_IRECLAIM)) {
- read_unlock(&pag->pag_ici_lock);
+ /*
+ * The radix tree lock here protects a thread in xfs_iget from racing
+ * with us starting reclaim on the inode. Once we have the
+ * XFS_IRECLAIM flag set it will not touch us.
+ */
+ spin_lock(&ip->i_flags_lock);
+ ASSERT_ALWAYS(__xfs_iflags_test(ip, XFS_IRECLAIMABLE));
+ if (__xfs_iflags_test(ip, XFS_IRECLAIM)) {
+ /* ignore as it is already under reclaim */
+ spin_unlock(&ip->i_flags_lock);
+ write_unlock(&pag->pag_ici_lock);
return 0;
}
- read_unlock(&pag->pag_ici_lock);
+ __xfs_iflags_set(ip, XFS_IRECLAIM);
+ spin_unlock(&ip->i_flags_lock);
+ write_unlock(&pag->pag_ici_lock);
- return xfs_reclaim_inode(ip, flags);
+ /*
+ * If the inode is still dirty, then flush it out. If the inode
+ * is not in the AIL, then it will be OK to flush it delwri as
+ * long as xfs_iflush() does not keep any references to the inode.
+ * We leave that decision up to xfs_iflush() since it has the
+ * knowledge of whether it's OK to simply do a delwri flush of
+ * the inode or whether we need to wait until the inode is
+ * pulled from the AIL.
+ * We get the flush lock regardless, though, just to make sure
+ * we don't free it while it is being flushed.
+ */
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+ xfs_iflock(ip);
+
+ /*
+ * In the case of a forced shutdown we rely on xfs_iflush() to
+ * wait for the inode to be unpinned before returning an error.
+ */
+ if (!is_bad_inode(VFS_I(ip)) && xfs_iflush(ip, sync_mode) == 0) {
+ /* synchronize with xfs_iflush_done */
+ xfs_iflock(ip);
+ xfs_ifunlock(ip);
+ }
+
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ xfs_ireclaim(ip);
+ return 0;
}
int
xfs_mount_t *mp,
int mode)
{
- return xfs_inode_ag_iterator(mp, xfs_reclaim_inode_now, mode,
- XFS_ICI_RECLAIM_TAG);
+ return xfs_inode_ag_iterator(mp, xfs_reclaim_inode, mode,
+ XFS_ICI_RECLAIM_TAG, 1);
}
return error;
}
+/*
+ * 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) > ip->i_df.if_ext_max)
+ 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) > tip->i_df.if_ext_max)
+ return EINVAL;
+
+ /* Check root block of temp in btree form to max in target */
+ if (tip->i_d.di_format == XFS_DINODE_FMT_BTREE &&
+ XFS_IFORK_BOFF(ip) &&
+ tip->i_df.if_broot_bytes > XFS_IFORK_BOFF(ip))
+ return EINVAL;
+
+ /* Check root block of target in btree form to max in temp */
+ if (ip->i_d.di_format == XFS_DINODE_FMT_BTREE &&
+ XFS_IFORK_BOFF(tip) &&
+ ip->i_df.if_broot_bytes > XFS_IFORK_BOFF(tip))
+ return EINVAL;
+
+ return 0;
+}
+
int
xfs_swap_extents(
- xfs_inode_t *ip,
- xfs_inode_t *tip,
+ xfs_inode_t *ip, /* target inode */
+ xfs_inode_t *tip, /* tmp inode */
xfs_swapext_t *sxp)
{
xfs_mount_t *mp;
goto out_unlock;
}
- /* 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) {
- error = XFS_ERROR(EINVAL);
- goto out_unlock;
- }
-
if (VN_CACHED(VFS_I(tip)) != 0) {
error = xfs_flushinval_pages(tip, 0, -1,
FI_REMAPF_LOCKED);
goto out_unlock;
}
- /*
- * If the target has extended attributes, the tmp file
- * must also in order to ensure the correct data fork
- * format.
- */
- if ( XFS_IFORK_Q(ip) != XFS_IFORK_Q(tip) ) {
- error = XFS_ERROR(EINVAL);
+ /* check inode formats now that data is flushed */
+ error = xfs_swap_extents_check_format(ip, tip);
+ if (error) {
+ xfs_fs_cmn_err(CE_NOTE, mp,
+ "%s: inode 0x%llx format is incompatible for exchanging.",
+ __FILE__, ip->i_ino);
goto out_unlock;
}
*ifp = *tifp; /* struct copy */
*tifp = *tempifp; /* struct copy */
+ /*
+ * Fix the in-memory data fork values that are dependent on the fork
+ * offset in the inode. We can't assume they remain the same as attr2
+ * has dynamic fork offsets.
+ */
+ ifp->if_ext_max = XFS_IFORK_SIZE(ip, XFS_DATA_FORK) /
+ (uint)sizeof(xfs_bmbt_rec_t);
+ tifp->if_ext_max = XFS_IFORK_SIZE(tip, XFS_DATA_FORK) /
+ (uint)sizeof(xfs_bmbt_rec_t);
+
/*
* Fix the on-disk inode values
*/