summaryrefslogtreecommitdiffstats
path: root/net/sunrpc
diff options
context:
space:
mode:
authorBill Baker <Bill.Baker@Oracle.com>2018-06-19 16:24:58 -0500
committerAnna Schumaker <Anna.Schumaker@Netapp.com>2018-07-31 12:53:40 -0400
commit0f90be132cbf1537d87a6a8b9e80867adac892f6 (patch)
treeef067b9220fd2a66da0be40359de526fc3f95579 /net/sunrpc
parent32cd3ee511f4e07ca25d71163b50e704808d22f4 (diff)
downloadlinux-0f90be132cbf1537d87a6a8b9e80867adac892f6.tar.bz2
NFSv4 client live hangs after live data migration recovery
After a live data migration event at the NFS server, the client may send I/O requests to the wrong server, causing a live hang due to repeated recovery events. On the wire, this will appear as an I/O request failing with NFS4ERR_BADSESSION, followed by successful CREATE_SESSION, repeatedly. NFS4ERR_BADSSESSION is returned because the session ID being used was issued by the other server and is not valid at the old server. The failure is caused by async worker threads having cached the transport (xprt) in the rpc_task structure. After the migration recovery completes, the task is redispatched and the task resends the request to the wrong server based on the old value still present in tk_xprt. The solution is to recompute the tk_xprt field of the rpc_task structure so that the request goes to the correct server. Signed-off-by: Bill Baker <bill.baker@oracle.com> Reviewed-by: Chuck Lever <chuck.lever@oracle.com> Tested-by: Helen Chao <helen.chao@oracle.com> Fixes: fb43d17210ba ("SUNRPC: Use the multipath iterator to assign a ...") Cc: stable@vger.kernel.org # v4.9+ Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Diffstat (limited to 'net/sunrpc')
-rw-r--r--net/sunrpc/clnt.c28
1 files changed, 20 insertions, 8 deletions
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index d839c33ae7d9..0d85425b1e07 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -965,10 +965,20 @@ out:
}
EXPORT_SYMBOL_GPL(rpc_bind_new_program);
+void rpc_task_release_transport(struct rpc_task *task)
+{
+ struct rpc_xprt *xprt = task->tk_xprt;
+
+ if (xprt) {
+ task->tk_xprt = NULL;
+ xprt_put(xprt);
+ }
+}
+EXPORT_SYMBOL_GPL(rpc_task_release_transport);
+
void rpc_task_release_client(struct rpc_task *task)
{
struct rpc_clnt *clnt = task->tk_client;
- struct rpc_xprt *xprt = task->tk_xprt;
if (clnt != NULL) {
/* Remove from client task list */
@@ -979,12 +989,14 @@ void rpc_task_release_client(struct rpc_task *task)
rpc_release_client(clnt);
}
+ rpc_task_release_transport(task);
+}
- if (xprt != NULL) {
- task->tk_xprt = NULL;
-
- xprt_put(xprt);
- }
+static
+void rpc_task_set_transport(struct rpc_task *task, struct rpc_clnt *clnt)
+{
+ if (!task->tk_xprt)
+ task->tk_xprt = xprt_iter_get_next(&clnt->cl_xpi);
}
static
@@ -992,8 +1004,7 @@ void rpc_task_set_client(struct rpc_task *task, struct rpc_clnt *clnt)
{
if (clnt != NULL) {
- if (task->tk_xprt == NULL)
- task->tk_xprt = xprt_iter_get_next(&clnt->cl_xpi);
+ rpc_task_set_transport(task, clnt);
task->tk_client = clnt;
atomic_inc(&clnt->cl_count);
if (clnt->cl_softrtry)
@@ -1512,6 +1523,7 @@ call_start(struct rpc_task *task)
clnt->cl_program->version[clnt->cl_vers]->counts[idx]++;
clnt->cl_stats->rpccnt++;
task->tk_action = call_reserve;
+ rpc_task_set_transport(task, clnt);
}
/*