NFS41: make close wait for layoutreturn
If we send a layoutreturn asynchronously before close, the close
might reach server first and layoutreturn would fail with BADSTATEID
because there is nothing keeping the layout stateid alive.
Also do not pretend sending layoutreturn if we are not.
Signed-off-by: Peng Tao <tao.peng@primarydata.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index ba12464..8abe271 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1104,20 +1104,15 @@
mark_lseg_invalid(lseg, &tmp_list);
found = true;
}
- /* pnfs_prepare_layoutreturn() grabs lo ref and it will be put
- * in pnfs_roc_release(). We don't really send a layoutreturn but
- * still want others to view us like we are sending one!
- *
- * If pnfs_prepare_layoutreturn() fails, it means someone else is doing
- * LAYOUTRETURN, so we proceed like there are no layouts to return.
- *
- * ROC in three conditions:
+ /* ROC in two conditions:
* 1. there are ROC lsegs
* 2. we don't send layoutreturn
- * 3. no others are sending layoutreturn
*/
- if (found && !layoutreturn && pnfs_prepare_layoutreturn(lo))
+ if (found && !layoutreturn) {
+ /* lo ref dropped in pnfs_roc_release() */
+ pnfs_get_layout_hdr(lo);
roc = true;
+ }
out_noroc:
spin_unlock(&ino->i_lock);
@@ -1172,6 +1167,26 @@
spin_unlock(&ino->i_lock);
}
+bool pnfs_wait_on_layoutreturn(struct inode *ino, struct rpc_task *task)
+{
+ struct nfs_inode *nfsi = NFS_I(ino);
+ struct pnfs_layout_hdr *lo;
+ bool sleep = false;
+
+ /* we might not have grabbed lo reference. so need to check under
+ * i_lock */
+ spin_lock(&ino->i_lock);
+ lo = nfsi->layout;
+ if (lo && test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
+ sleep = true;
+ spin_unlock(&ino->i_lock);
+
+ if (sleep)
+ rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL);
+
+ return sleep;
+}
+
/*
* Compare two layout segments for sorting into layout cache.
* We want to preferentially return RW over RO layouts, so ensure those