NFSD: Move callback_wq into struct nfs4_client

Commit 883820366747 ("nfsd: update workqueue creation") made the
callback_wq single-threaded, presumably to protect modifications of
cl_cb_client. See documenting comment for nfsd4_process_cb_update().

However, cl_cb_client is per-lease. There's no other reason that all
callback operations need to be dispatched via a single thread. The
single threading here means all client callbacks can be blocked by a
problem with one client.

Change the NFSv4 callback client so it serializes per-lease instead
of serializing all NFSv4 callback operations on the server.

Reported-by: Dai Ngo <dai.ngo@oracle.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>

1 files changed, 9 insertions, 22 deletions

diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index e88aca0c6e8e..d756f443fc44 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -978,12 +978,12 @@ static int max_cb_time(struct net *net)
 	return max(((u32)nn->nfsd4_lease)/10, 1u) * HZ;
 }
 
-static struct workqueue_struct *callback_wq;
-
 static bool nfsd4_queue_cb(struct nfsd4_callback *cb)
 {
-	trace_nfsd_cb_queue(cb->cb_clp, cb);
-	return queue_work(callback_wq, &cb->cb_work);
+	struct nfs4_client *clp = cb->cb_clp;
+
+	trace_nfsd_cb_queue(clp, cb);
+	return queue_work(clp->cl_callback_wq, &cb->cb_work);
 }
 
 static void nfsd41_cb_inflight_begin(struct nfs4_client *clp)
@@ -1153,7 +1153,7 @@ void nfsd4_probe_callback(struct nfs4_client *clp)
 void nfsd4_probe_callback_sync(struct nfs4_client *clp)
 {
 	nfsd4_probe_callback(clp);
-	flush_workqueue(callback_wq);
+	flush_workqueue(clp->cl_callback_wq);
 }
 
 void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *conn)
@@ -1372,19 +1372,6 @@ static const struct rpc_call_ops nfsd4_cb_ops = {
 	.rpc_release = nfsd4_cb_release,
 };
 
-int nfsd4_create_callback_queue(void)
-{
-	callback_wq = alloc_ordered_workqueue("nfsd4_callbacks", 0);
-	if (!callback_wq)
-		return -ENOMEM;
-	return 0;
-}
-
-void nfsd4_destroy_callback_queue(void)
-{
-	destroy_workqueue(callback_wq);
-}
-
 /* must be called under the state lock */
 void nfsd4_shutdown_callback(struct nfs4_client *clp)
 {
@@ -1398,7 +1385,7 @@ void nfsd4_shutdown_callback(struct nfs4_client *clp)
 	 * client, destroy the rpc client, and stop:
 	 */
 	nfsd4_run_cb(&clp->cl_cb_null);
-	flush_workqueue(callback_wq);
+	flush_workqueue(clp->cl_callback_wq);
 	nfsd41_cb_inflight_wait_complete(clp);
 }
 
@@ -1420,9 +1407,9 @@ static struct nfsd4_conn * __nfsd4_find_backchannel(struct nfs4_client *clp)
 
 /*
  * Note there isn't a lot of locking in this code; instead we depend on
- * the fact that it is run from the callback_wq, which won't run two
- * work items at once.  So, for example, callback_wq handles all access
- * of cl_cb_client and all calls to rpc_create or rpc_shutdown_client.
+ * the fact that it is run from clp->cl_callback_wq, which won't run two
+ * work items at once.  So, for example, clp->cl_callback_wq handles all
+ * access of cl_cb_client and all calls to rpc_create or rpc_shutdown_client.
  */
 static void nfsd4_process_cb_update(struct nfsd4_callback *cb)
 {