NFS4.1 Fix data server connection race

Unlike meta data server mounts which support multiple mount points to
the same server via struct nfs_server, data servers support a single connection.

Concurrent calls to setup the data server connection can race where the first
call allocates the nfs_client struct, and before the cache struct nfs_client
pointer can be set, a second call also tries to setup the connection, finds the
already allocated nfs_client, bumps the reference count, re-initializes the
session,etc. This results in a hanging data server session after umount.

Signed-off-by: Andy Adamson <andros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>

1 files changed, 24 insertions, 2 deletions

diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c
index 1fe284f..661a0f6 100644
--- a/fs/nfs/nfs4filelayoutdev.c
+++ b/fs/nfs/nfs4filelayoutdev.c
@@ -775,6 +775,22 @@ nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j)
 	return flseg->fh_array[i];
 }
 
+static void nfs4_wait_ds_connect(struct nfs4_pnfs_ds *ds)
+{
+	might_sleep();
+	wait_on_bit(&ds->ds_state, NFS4DS_CONNECTING,
+			nfs_wait_bit_killable, TASK_KILLABLE);
+}
+
+static void nfs4_clear_ds_conn_bit(struct nfs4_pnfs_ds *ds)
+{
+	smp_mb__before_clear_bit();
+	clear_bit(NFS4DS_CONNECTING, &ds->ds_state);
+	smp_mb__after_clear_bit();
+	wake_up_bit(&ds->ds_state, NFS4DS_CONNECTING);
+}
+
+
 struct nfs4_pnfs_ds *
 nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
 {
@@ -791,16 +807,22 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
 		filelayout_mark_devid_invalid(devid);
 		return NULL;
 	}
+	if (ds->ds_clp)
+		return ds;
 
-	if (!ds->ds_clp) {
+	if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) {
 		struct nfs_server *s = NFS_SERVER(lseg->pls_layout->plh_inode);
 		int err;
 
 		err = nfs4_ds_connect(s, ds);
 		if (err) {
 			nfs4_mark_deviceid_unavailable(devid);
-			return NULL;
+			ds = NULL;
 		}
+		nfs4_clear_ds_conn_bit(ds);
+	} else {
+		/* Either ds is connected, or ds is NULL */
+		nfs4_wait_ds_connect(ds);
 	}
 	return ds;
 }