cifs: reconnect work should have reference on server struct

The delayed work for reconnect takes server struct
as a parameter. But it does so without holding a ref
to it. Normally, this may not show a problem as
the reconnect work is only cancelled on umount.

However, since we now plan to support scaling down of
channels, and the scale down can happen from reconnect
work itself, we need to fix it.

This change takes a reference on the server struct
before it is passed to the delayed work. And drops
the reference in the delayed work itself. Or if
the delayed work is successfully cancelled, by the
process that cancels it.

Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>

diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index bb9f75175f315828ac4222de207bb38ed8a15fa3..f7f6e8b2e002bd9a2e4a350b9421da33386913cf 100644 (file)
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -389,7 +389,13 @@ static int __cifs_reconnect(struct TCP_Server_Info *server,
                        spin_unlock(&server->srv_lock);
                        cifs_swn_reset_server_dstaddr(server);
                        cifs_server_unlock(server);
-                       mod_delayed_work(cifsiod_wq, &server->reconnect, 0);
+
+                       /* increase ref count which reconnect work will drop */
+                       spin_lock(&cifs_tcp_ses_lock);
+                       server->srv_count++;
+                       spin_unlock(&cifs_tcp_ses_lock);
+                       if (mod_delayed_work(cifsiod_wq, &server->reconnect, 0))
+                               cifs_put_tcp_session(server, false);
                }
        } while (server->tcpStatus == CifsNeedReconnect);
 
@@ -519,7 +525,13 @@ static int reconnect_dfs_server(struct TCP_Server_Info *server)
                spin_unlock(&server->srv_lock);
                cifs_swn_reset_server_dstaddr(server);
                cifs_server_unlock(server);
-               mod_delayed_work(cifsiod_wq, &server->reconnect, 0);
+
+               /* increase ref count which reconnect work will drop */
+               spin_lock(&cifs_tcp_ses_lock);
+               server->srv_count++;
+               spin_unlock(&cifs_tcp_ses_lock);
+               if (mod_delayed_work(cifsiod_wq, &server->reconnect, 0))
+                       cifs_put_tcp_session(server, false);
        } while (server->tcpStatus == CifsNeedReconnect);
 
        mutex_lock(&server->refpath_lock);
@@ -1600,16 +1612,19 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect)
 
        cancel_delayed_work_sync(&server->echo);
 
-       if (from_reconnect)
+       if (from_reconnect) {
                /*
                 * Avoid deadlock here: reconnect work calls
                 * cifs_put_tcp_session() at its end. Need to be sure
                 * that reconnect work does nothing with server pointer after
                 * that step.
                 */
-               cancel_delayed_work(&server->reconnect);
-       else
-               cancel_delayed_work_sync(&server->reconnect);
+               if (cancel_delayed_work(&server->reconnect))
+                       cifs_put_tcp_session(server, from_reconnect);
+       } else {
+               if (cancel_delayed_work_sync(&server->reconnect))
+                       cifs_put_tcp_session(server, from_reconnect);
+       }
 
        spin_lock(&server->srv_lock);
        server->tcpStatus = CifsExiting;

diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index ef4558979c30e43cec728a823ce0ec0302f136e2..a07d465d1b3d0edf3d9394b9afe5f783b9af7039 100644 (file)
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -3852,12 +3852,6 @@ void smb2_reconnect_server(struct work_struct *work)
                }
                spin_unlock(&ses->chan_lock);
        }
-       /*
-        * Get the reference to server struct to be sure that the last call of
-        * cifs_put_tcon() in the loop below won't release the server pointer.
-        */
-       if (tcon_exist || ses_exist)
-               server->srv_count++;
 
        spin_unlock(&cifs_tcp_ses_lock);
 
@@ -3905,13 +3899,17 @@ void smb2_reconnect_server(struct work_struct *work)
 
 done:
        cifs_dbg(FYI, "Reconnecting tcons and channels finished\n");
-       if (resched)
+       if (resched) {
                queue_delayed_work(cifsiod_wq, &server->reconnect, 2 * HZ);
+               mutex_unlock(&pserver->reconnect_mutex);
+
+               /* no need to put tcp session as we're retrying */
+               return;
+       }
        mutex_unlock(&pserver->reconnect_mutex);
 
        /* now we can safely release srv struct */
-       if (tcon_exist || ses_exist)
-               cifs_put_tcp_session(server, 1);
+       cifs_put_tcp_session(server, true);
 }
 
 int
@@ -3931,7 +3929,12 @@ SMB2_echo(struct TCP_Server_Info *server)
            server->ops->need_neg(server)) {
                spin_unlock(&server->srv_lock);
                /* No need to send echo on newly established connections */
-               mod_delayed_work(cifsiod_wq, &server->reconnect, 0);
+               spin_lock(&cifs_tcp_ses_lock);
+               server->srv_count++;
+               spin_unlock(&cifs_tcp_ses_lock);
+               if (mod_delayed_work(cifsiod_wq, &server->reconnect, 0))
+                       cifs_put_tcp_session(server, false);
+
                return rc;
        }
        spin_unlock(&server->srv_lock);