summaryrefslogtreecommitdiffstats
path: root/fs/xfs/xfs_inode_item.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/xfs/xfs_inode_item.c')
-rw-r--r--fs/xfs/xfs_inode_item.c149
1 files changed, 149 insertions, 0 deletions
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index ca2941ab6cbc..91c847a84e10 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -29,6 +29,153 @@ static inline struct xfs_inode_log_item *INODE_ITEM(struct xfs_log_item *lip)
return container_of(lip, struct xfs_inode_log_item, ili_item);
}
+static uint64_t
+xfs_inode_item_sort(
+ struct xfs_log_item *lip)
+{
+ return INODE_ITEM(lip)->ili_inode->i_ino;
+}
+
+/*
+ * Prior to finally logging the inode, we have to ensure that all the
+ * per-modification inode state changes are applied. This includes VFS inode
+ * state updates, format conversions, verifier state synchronisation and
+ * ensuring the inode buffer remains in memory whilst the inode is dirty.
+ *
+ * We have to be careful when we grab the inode cluster buffer due to lock
+ * ordering constraints. The unlinked inode modifications (xfs_iunlink_item)
+ * require AGI -> inode cluster buffer lock order. The inode cluster buffer is
+ * not locked until ->precommit, so it happens after everything else has been
+ * modified.
+ *
+ * Further, we have AGI -> AGF lock ordering, and with O_TMPFILE handling we
+ * have AGI -> AGF -> iunlink item -> inode cluster buffer lock order. Hence we
+ * cannot safely lock the inode cluster buffer in xfs_trans_log_inode() because
+ * it can be called on a inode (e.g. via bumplink/droplink) before we take the
+ * AGF lock modifying directory blocks.
+ *
+ * Rather than force a complete rework of all the transactions to call
+ * xfs_trans_log_inode() once and once only at the end of every transaction, we
+ * move the pinning of the inode cluster buffer to a ->precommit operation. This
+ * matches how the xfs_iunlink_item locks the inode cluster buffer, and it
+ * ensures that the inode cluster buffer locking is always done last in a
+ * transaction. i.e. we ensure the lock order is always AGI -> AGF -> inode
+ * cluster buffer.
+ *
+ * If we return the inode number as the precommit sort key then we'll also
+ * guarantee that the order all inode cluster buffer locking is the same all the
+ * inodes and unlink items in the transaction.
+ */
+static int
+xfs_inode_item_precommit(
+ struct xfs_trans *tp,
+ struct xfs_log_item *lip)
+{
+ struct xfs_inode_log_item *iip = INODE_ITEM(lip);
+ struct xfs_inode *ip = iip->ili_inode;
+ struct inode *inode = VFS_I(ip);
+ unsigned int flags = iip->ili_dirty_flags;
+
+ /*
+ * Don't bother with i_lock for the I_DIRTY_TIME check here, as races
+ * don't matter - we either will need an extra transaction in 24 hours
+ * to log the timestamps, or will clear already cleared fields in the
+ * worst case.
+ */
+ if (inode->i_state & I_DIRTY_TIME) {
+ spin_lock(&inode->i_lock);
+ inode->i_state &= ~I_DIRTY_TIME;
+ spin_unlock(&inode->i_lock);
+ }
+
+ /*
+ * If we're updating the inode core or the timestamps and it's possible
+ * to upgrade this inode to bigtime format, do so now.
+ */
+ if ((flags & (XFS_ILOG_CORE | XFS_ILOG_TIMESTAMP)) &&
+ xfs_has_bigtime(ip->i_mount) &&
+ !xfs_inode_has_bigtime(ip)) {
+ ip->i_diflags2 |= XFS_DIFLAG2_BIGTIME;
+ flags |= XFS_ILOG_CORE;
+ }
+
+ /*
+ * Inode verifiers do not check that the extent size hint is an integer
+ * multiple of the rt extent size on a directory with both rtinherit
+ * and extszinherit flags set. If we're logging a directory that is
+ * misconfigured in this way, clear the hint.
+ */
+ if ((ip->i_diflags & XFS_DIFLAG_RTINHERIT) &&
+ (ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) &&
+ (ip->i_extsize % ip->i_mount->m_sb.sb_rextsize) > 0) {
+ ip->i_diflags &= ~(XFS_DIFLAG_EXTSIZE |
+ XFS_DIFLAG_EXTSZINHERIT);
+ ip->i_extsize = 0;
+ flags |= XFS_ILOG_CORE;
+ }
+
+ /*
+ * Record the specific change for fdatasync optimisation. This allows
+ * fdatasync to skip log forces for inodes that are only timestamp
+ * dirty. Once we've processed the XFS_ILOG_IVERSION flag, convert it
+ * to XFS_ILOG_CORE so that the actual on-disk dirty tracking
+ * (ili_fields) correctly tracks that the version has changed.
+ */
+ spin_lock(&iip->ili_lock);
+ iip->ili_fsync_fields |= (flags & ~XFS_ILOG_IVERSION);
+ if (flags & XFS_ILOG_IVERSION)
+ flags = ((flags & ~XFS_ILOG_IVERSION) | XFS_ILOG_CORE);
+
+ if (!iip->ili_item.li_buf) {
+ struct xfs_buf *bp;
+ int error;
+
+ /*
+ * We hold the ILOCK here, so this inode is not going to be
+ * flushed while we are here. Further, because there is no
+ * buffer attached to the item, we know that there is no IO in
+ * progress, so nothing will clear the ili_fields while we read
+ * in the buffer. Hence we can safely drop the spin lock and
+ * read the buffer knowing that the state will not change from
+ * here.
+ */
+ spin_unlock(&iip->ili_lock);
+ error = xfs_imap_to_bp(ip->i_mount, tp, &ip->i_imap, &bp);
+ if (error)
+ return error;
+
+ /*
+ * We need an explicit buffer reference for the log item but
+ * don't want the buffer to remain attached to the transaction.
+ * Hold the buffer but release the transaction reference once
+ * we've attached the inode log item to the buffer log item
+ * list.
+ */
+ xfs_buf_hold(bp);
+ spin_lock(&iip->ili_lock);
+ iip->ili_item.li_buf = bp;
+ bp->b_flags |= _XBF_INODES;
+ list_add_tail(&iip->ili_item.li_bio_list, &bp->b_li_list);
+ xfs_trans_brelse(tp, bp);
+ }
+
+ /*
+ * Always OR in the bits from the ili_last_fields field. This is to
+ * coordinate with the xfs_iflush() and xfs_buf_inode_iodone() routines
+ * in the eventual clearing of the ili_fields bits. See the big comment
+ * in xfs_iflush() for an explanation of this coordination mechanism.
+ */
+ iip->ili_fields |= (flags | iip->ili_last_fields);
+ spin_unlock(&iip->ili_lock);
+
+ /*
+ * We are done with the log item transaction dirty state, so clear it so
+ * that it doesn't pollute future transactions.
+ */
+ iip->ili_dirty_flags = 0;
+ return 0;
+}
+
/*
* The logged size of an inode fork is always the current size of the inode
* fork. This means that when an inode fork is relogged, the size of the logged
@@ -662,6 +809,8 @@ xfs_inode_item_committing(
}
static const struct xfs_item_ops xfs_inode_item_ops = {
+ .iop_sort = xfs_inode_item_sort,
+ .iop_precommit = xfs_inode_item_precommit,
.iop_size = xfs_inode_item_size,
.iop_format = xfs_inode_item_format,
.iop_pin = xfs_inode_item_pin,