pnfs: avoid using stale stateids after layoutreturn

After we issued a layoutreturn operations the may free the layout stateid
and will thus cause bad stateid error when the client uses it again.

We currently try to avoid this case by chosing the open stateid if not
lsegs are present for this inode.  But various places can hold refererence
on lsegs and thus cause the list not to be empty shortly after a layout
return.  Add an explicit flag to mark the current layout stateid invalid
and force usage of the openstateid after we did a full file layoutreturn.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>

fs/nfs/pnfs.c

@@ -738,7 +738,8 @@ pnfs_choose_layoutget_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo,
 		status = -EAGAIN;
 	} else if (!nfs4_valid_open_stateid(open_state)) {
 		status = -EBADF;
-	} else if (list_empty(&lo->plh_segs)) {
+	} else if (list_empty(&lo->plh_segs) ||
+		   test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags)) {
 		int seq;
 
 		do {
@@ -860,6 +861,8 @@ _pnfs_return_layout(struct inode *ino)
 		dprintk("NFS: %s no layout segments to return\n", __func__);
 		goto out;
 	}
+
+	set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
 	lo->plh_block_lgets++;
 	spin_unlock(&ino->i_lock);
 	pnfs_free_lseg_list(&tmp_list);
@@ -1380,6 +1383,8 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
 		lo->plh_barrier = be32_to_cpu(res->stateid.seqid);
 	}
 
+	clear_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
+
 	pnfs_get_lseg(lseg);
 	pnfs_layout_insert_lseg(lo, lseg);
 

fs/nfs/pnfs.h

@@ -65,6 +65,7 @@ enum {
 	NFS_LAYOUT_BULK_RECALL,		/* bulk recall affecting layout */
 	NFS_LAYOUT_ROC,			/* some lseg had roc bit set */
 	NFS_LAYOUT_RETURN,		/* Return this layout ASAP */
+	NFS_LAYOUT_INVALID_STID,	/* layout stateid id is invalid */
 };
 
 enum layoutdriver_policy_flags {