[Devel] [PATCH RHEL7 COMMIT] nfs: protect callback execution against per-net callback thread shutdown

[Konstantin Khorenko]

The commit is pushed to "branch-rh7-3.10.0-693.1.1.vz7.37.x-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git
after rh7-3.10.0-693.1.1.vz7.37.27
------>
commit c1cd5be61d00591c64888d4ae012d675b3073d8e
Author: Stanislav Kinsburskiy <skinsbursky at virtuozzo.com>
Date:   Mon Nov 13 17:11:42 2017 +0300

    nfs: protect callback execution against per-net callback thread shutdown
    
    Patchset description:
    nfs: fix race between callback shutdown and execution
    
    The idea is to use mutex for protecting callback execution agains per-net
    callback shutdown and destroying all the net-related backchannel requests
    before transports destruction.
    
    Stanislav Kinsburskiy (2):
            sunrpc: bc_svc_flush_queue_net() helper introduced
            nfs: protect callback execution against per-net callback thread shutdown
    
    ======================
    This patch description:
    
    Here is the race:
    
    CPU #0				CPU#1
    
    cleanup_mnt			nfs41_callback_svc (get xprt from the list)
    nfs_callback_down		...
    ...				...
    svc_close_net			...
    ...				...
    svc_xprt_free			...
    svc_bc_sock_free		bc_svc_process
    kfree(xprt)			svc_process_common
    				rqstp->rq_xprt->xpt_ops (use after free)
    
    The problem is that per-net SUNRPC transports shutdown is done regardless
    current callback execution. This is a race leading to transport use-after-free
    in callback handler.
    This patch fixes it in stright-forward way. I.e. it protects callback
    execution with the same mutex used for per-net data creation and destruction.
    Hopefully, it won't slow down NFS client significantly.
    
    https://jira.sw.ru/browse/PSBM-75751
    
    v6: destroy all per-net backchannel requests only for NFSv4.1
    
    v5: destroy all per-net backchannel requests before transports on in
    nfs_callback_down_net
    
    v4: use another mutex to protect callback execution agains per-net transports
    shutdown.
    This guarantees, that transports won't be destroyed by shutdown callback while
    execution is in progress and vice versa.
    
    v3: Fix mutex deadlock, when shutdown callback waits for thread to exit (with
    mutex taken), while thread wait for the mutex to take.
    The idea is to simply check if thread has to exit, if mutex lock has failed.
    This is a busy loop, but it shouldn't happend often and for long.
    
    Signed-off-by: Stanislav Kinsburskiy <skinsbursky at virtuozzo.com>
    Reviewed-by: Kirill Tkhai <ktkhai at virtuozzo.com>
---
 fs/nfs/callback.c          | 20 ++++++++++++++++++++
 include/linux/sunrpc/svc.h |  1 +
 2 files changed, 21 insertions(+)

diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index 0beb275..feffccf 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -99,6 +99,8 @@ nfs4_callback_up(struct svc_serv *serv)
 }
 
 #if defined(CONFIG_NFS_V4_1)
+static DEFINE_MUTEX(nfs41_callback_mutex);
+
 /*
  * The callback service for NFSv4.1 callbacks
  */
@@ -117,6 +119,12 @@ nfs41_callback_svc(void *vrqstp)
 		if (try_to_freeze())
 			continue;
 
+		mutex_lock(&nfs41_callback_mutex);
+		if (kthread_should_stop()) {
+			mutex_unlock(&nfs41_callback_mutex);
+			return 0;
+		}
+
 		prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_INTERRUPTIBLE);
 		spin_lock_bh(&serv->sv_cb_lock);
 		if (!list_empty(&serv->sv_cb_list)) {
@@ -129,8 +137,10 @@ nfs41_callback_svc(void *vrqstp)
 			error = bc_svc_process(serv, req, rqstp);
 			dprintk("bc_svc_process() returned w/ error code= %d\n",
 				error);
+			mutex_unlock(&nfs41_callback_mutex);
 		} else {
 			spin_unlock_bh(&serv->sv_cb_lock);
+			mutex_unlock(&nfs41_callback_mutex);
 			schedule();
 			finish_wait(&serv->sv_cb_waitq, &wq);
 		}
@@ -139,6 +149,13 @@ nfs41_callback_svc(void *vrqstp)
 	return 0;
 }
 
+static void nfs41_callback_down_net(struct svc_serv *serv, struct net *net)
+{
+	mutex_lock(&nfs41_callback_mutex);
+	bc_svc_flush_queue_net(serv, net);
+	mutex_unlock(&nfs41_callback_mutex);
+}
+
 /*
  * Bring up the NFSv4.1 callback service
  */
@@ -150,6 +167,7 @@ nfs41_callback_up(struct svc_serv *serv)
 	INIT_LIST_HEAD(&serv->sv_cb_list);
 	spin_lock_init(&serv->sv_cb_lock);
 	init_waitqueue_head(&serv->sv_cb_waitq);
+	serv->svc_cb_down_net = nfs41_callback_down_net;
 	rqstp = svc_prepare_thread(serv, &serv->sv_pools[0], NUMA_NO_NODE);
 	dprintk("--> %s return %d\n", __func__, PTR_ERR_OR_ZERO(rqstp));
 	return rqstp;
@@ -242,6 +260,8 @@ static void nfs_callback_down_net(u32 minorversion, struct svc_serv *serv, struc
 		return;
 
 	dprintk("NFS: destroy per-net callback data; net=%p\n", net);
+	if (serv->svc_cb_down_net)
+		serv->svc_cb_down_net(serv, net);
 	svc_shutdown_net(serv, net);
 }
 
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index fe70ff0..c04ef80 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -108,6 +108,7 @@ struct svc_serv {
 	wait_queue_head_t	sv_cb_waitq;	/* sleep here if there are no
 						 * entries in the svc_cb_list */
 	struct svc_xprt		*sv_bc_xprt;	/* callback on fore channel */
+	void			(*svc_cb_down_net)(struct svc_serv *serv, struct net *net);
 #endif /* CONFIG_SUNRPC_BACKCHANNEL */
 };