From: Trond Myklebust <[email protected]>

                   -------------------
    This is a commit scheduled for the next v2.6.34 longterm release.
    http://git.kernel.org/?p=linux/kernel/git/paulg/longterm-queue-2.6.34.git
    If you see a problem with using this for longterm, please comment.
                   -------------------

commit 0b760113a3a155269a3fba93a409c640031dd68f upstream.

If the NLM daemon is killed on the NFS server, we can currently end up
hanging forever on an 'unlock' request, instead of aborting. Basically,
if the rpcbind request fails, or the server keeps returning garbage, we
really want to quit instead of retrying.

Tested-by: Vasily Averin <[email protected]>
Signed-off-by: Trond Myklebust <[email protected]>
[PG: struct rpc_task in sched.h slightly different layout vs. v3.0]
Signed-off-by: Paul Gortmaker <[email protected]>
---
 fs/lockd/clntproc.c          | 8 +++++++-
 include/linux/sunrpc/sched.h | 1 +
 net/sunrpc/clnt.c            | 3 +++
 net/sunrpc/sched.c           | 1 +
 4 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c
index 7932c39..f4ef9d1 100644
--- a/fs/lockd/clntproc.c
+++ b/fs/lockd/clntproc.c
@@ -710,7 +710,13 @@ static void nlmclnt_unlock_callback(struct rpc_task *task, 
void *data)
 
        if (task->tk_status < 0) {
                dprintk("lockd: unlock failed (err = %d)\n", -task->tk_status);
-               goto retry_rebind;
+               switch (task->tk_status) {
+               case -EACCES:
+               case -EIO:
+                       goto die;
+               default:
+                       goto retry_rebind;
+               }
        }
        if (status == NLM_LCK_DENIED_GRACE_PERIOD) {
                rpc_delay(task, NLMCLNT_GRACE_WAIT);
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index 7bc7fd5..f2338ca 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -55,6 +55,7 @@ struct rpc_task {
        struct rpc_message      tk_msg;         /* RPC call info */
        __u8                    tk_garb_retry;
        __u8                    tk_cred_retry;
+       __u8                    tk_rebind_retry;
 
        /*
         * callback     to be executed after waking up
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 0ad7828..018903c 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1053,6 +1053,9 @@ call_bind_status(struct rpc_task *task)
                        status = -EOPNOTSUPP;
                        break;
                }
+               if (task->tk_rebind_retry == 0)
+                       break;
+               task->tk_rebind_retry--;
                rpc_delay(task, 3*HZ);
                goto retry_timeout;
        case -ETIMEDOUT:
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 416ca5e..e961e06 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -799,6 +799,7 @@ static void rpc_init_task(struct rpc_task *task, const 
struct rpc_task_setup *ta
        /* Initialize retry counters */
        task->tk_garb_retry = 2;
        task->tk_cred_retry = 2;
+       task->tk_rebind_retry = 2;
 
        task->tk_priority = task_setup_data->priority - RPC_PRIORITY_LOW;
        task->tk_owner = current->tgid;
-- 
1.7.12.rc2

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email protected]
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Reply via email to