{
struct inode *inode = VFS_I(ip);
+ ASSERT(rcu_read_lock_held());
+
+ /*
+ * check for stale RCU freed inode
+ *
+ * If the inode has been reallocated, it doesn't matter if it's not in
+ * the AG we are walking - we are walking for writeback, so if it
+ * passes all the "valid inode" checks and is dirty, then we'll write
+ * it back anyway. If it has been reallocated and still being
+ * initialised, the XFS_INEW check below will catch it.
+ */
+ spin_lock(&ip->i_flags_lock);
+ if (!ip->i_ino)
+ goto out_unlock_noent;
+
+ /* avoid new or reclaimable inodes. Leave for reclaim code to flush */
+ if (__xfs_iflags_test(ip, XFS_INEW | XFS_IRECLAIMABLE | XFS_IRECLAIM))
+ goto out_unlock_noent;
+ spin_unlock(&ip->i_flags_lock);
+
/* nothing to sync during shutdown */
if (XFS_FORCED_SHUTDOWN(ip->i_mount))
return EFSCORRUPTED;
- /* avoid new or reclaimable inodes. Leave for reclaim code to flush */
- if (xfs_iflags_test(ip, XFS_INEW | XFS_IRECLAIMABLE | XFS_IRECLAIM))
- return ENOENT;
-
/* If we can't grab the inode, it must on it's way to reclaim. */
if (!igrab(inode))
return ENOENT;
/* inode is valid */
return 0;
+
+out_unlock_noent:
+ spin_unlock(&ip->i_flags_lock);
+ return ENOENT;
}
STATIC int
int error = 0;
int i;
- read_lock(&pag->pag_ici_lock);
+ rcu_read_lock();
nr_found = radix_tree_gang_lookup(&pag->pag_ici_root,
(void **)batch, first_index,
XFS_LOOKUP_BATCH);
if (!nr_found) {
- read_unlock(&pag->pag_ici_lock);
+ rcu_read_unlock();
break;
}
batch[i] = NULL;
/*
- * Update the index for the next lookup. Catch overflows
- * into the next AG range which can occur if we have inodes
- * in the last block of the AG and we are currently
- * pointing to the last inode.
+ * Update the index for the next lookup. Catch
+ * overflows into the next AG range which can occur if
+ * we have inodes in the last block of the AG and we
+ * are currently pointing to the last inode.
+ *
+ * Because we may see inodes that are from the wrong AG
+ * due to RCU freeing and reallocation, only update the
+ * index if it lies in this AG. It was a race that lead
+ * us to see this inode, so another lookup from the
+ * same index will not find it again.
*/
+ if (XFS_INO_TO_AGNO(mp, ip->i_ino) != pag->pag_agno)
+ continue;
first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1);
if (first_index < XFS_INO_TO_AGINO(mp, ip->i_ino))
done = 1;
}
/* unlock now we've grabbed the inodes. */
- read_unlock(&pag->pag_ici_lock);
+ rcu_read_unlock();
for (i = 0; i < nr_found; i++) {
if (!batch[i])
/* mark the log as covered if needed */
if (xfs_log_need_covered(mp))
- error2 = xfs_fs_log_dummy(mp, SYNC_WAIT);
+ error2 = xfs_fs_log_dummy(mp);
/* flush data-only devices */
if (mp->m_rtdev_targp)
int error;
if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
- xfs_log_force(mp, 0);
- xfs_reclaim_inodes(mp, 0);
/* dgc: errors ignored here */
- error = xfs_qm_sync(mp, SYNC_TRYLOCK);
if (mp->m_super->s_frozen == SB_UNFROZEN &&
xfs_log_need_covered(mp))
- error = xfs_fs_log_dummy(mp, 0);
+ error = xfs_fs_log_dummy(mp);
+ else
+ xfs_log_force(mp, 0);
+ xfs_reclaim_inodes(mp, 0);
+ error = xfs_qm_sync(mp, SYNC_TRYLOCK);
}
mp->m_sync_seq++;
wake_up(&mp->m_wait_single_sync_task);
struct xfs_perag *pag;
pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
- write_lock(&pag->pag_ici_lock);
+ spin_lock(&pag->pag_ici_lock);
spin_lock(&ip->i_flags_lock);
__xfs_inode_set_reclaim_tag(pag, ip);
__xfs_iflags_set(ip, XFS_IRECLAIMABLE);
spin_unlock(&ip->i_flags_lock);
- write_unlock(&pag->pag_ici_lock);
+ spin_unlock(&pag->pag_ici_lock);
xfs_perag_put(pag);
}
struct xfs_inode *ip,
int flags)
{
+ ASSERT(rcu_read_lock_held());
+
+ /* quick check for stale RCU freed inode */
+ if (!ip->i_ino)
+ return 1;
/*
- * do some unlocked checks first to avoid unnecceary lock traffic.
+ * do some unlocked checks first to avoid unnecessary lock traffic.
* The first is a flush lock check, the second is a already in reclaim
* check. Only do these checks if we are not going to block on locks.
*/
* 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.
+ *
+ * Due to RCU lookup, we may find inodes that have been freed and only
+ * have XFS_IRECLAIM set. Indeed, we may see reallocated inodes that
+ * aren't candidates for reclaim at all, so we must check the
+ * XFS_IRECLAIMABLE is set first before proceeding to reclaim.
*/
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 */
+ if (!__xfs_iflags_test(ip, XFS_IRECLAIMABLE) ||
+ __xfs_iflags_test(ip, XFS_IRECLAIM)) {
+ /* not a reclaim candidate. */
spin_unlock(&ip->i_flags_lock);
return 1;
}
* added to the tree assert that it's been there before to catch
* problems with the inode life time early on.
*/
- write_lock(&pag->pag_ici_lock);
+ spin_lock(&pag->pag_ici_lock);
if (!radix_tree_delete(&pag->pag_ici_root,
XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino)))
ASSERT(0);
__xfs_inode_clear_reclaim(pag, ip);
- write_unlock(&pag->pag_ici_lock);
+ spin_unlock(&pag->pag_ici_lock);
/*
* Here we do an (almost) spurious inode lock in order to coordinate
struct xfs_inode *batch[XFS_LOOKUP_BATCH];
int i;
- write_lock(&pag->pag_ici_lock);
+ rcu_read_lock();
nr_found = radix_tree_gang_lookup_tag(
&pag->pag_ici_root,
(void **)batch, first_index,
XFS_LOOKUP_BATCH,
XFS_ICI_RECLAIM_TAG);
if (!nr_found) {
- write_unlock(&pag->pag_ici_lock);
+ rcu_read_unlock();
break;
}
* occur if we have inodes in the last block of
* the AG and we are currently pointing to the
* last inode.
+ *
+ * Because we may see inodes that are from the
+ * wrong AG due to RCU freeing and
+ * reallocation, only update the index if it
+ * lies in this AG. It was a race that lead us
+ * to see this inode, so another lookup from
+ * the same index will not find it again.
*/
+ if (XFS_INO_TO_AGNO(mp, ip->i_ino) !=
+ pag->pag_agno)
+ continue;
first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1);
if (first_index < XFS_INO_TO_AGINO(mp, ip->i_ino))
done = 1;
}
/* unlock now we've grabbed the inodes. */
- write_unlock(&pag->pag_ici_lock);
+ rcu_read_unlock();
for (i = 0; i < nr_found; i++) {
if (!batch[i])
projects / mv-sheeva.git / blobdiff