[ Upstream commit
b18cba09e374637a0a3759d856a6bca94c133952 ]
Commit
28460803dd20 ("SUNRPC: allow for upcalls for the same uid
but different gss service") introduced `auth` argument to
__gss_find_upcall(), but in gss_pipe_downcall() it was left as NULL
since it (and auth->service) was not (yet) determined.
When multiple upcalls with the same uid and different service are
ongoing, it could happen that __gss_find_upcall(), which returns the
first match found in the pipe->in_downcall list, could not find the
correct gss_msg corresponding to the downcall we are looking for.
Moreover, it might return a msg which is not sent to rpc.gssd yet.
We could see mount.nfs process hung in D state with multiple mount.nfs
are executed in parallel. The call trace below is of CentOS 7.9
kernel-3.10.0-1160.24.1.el7.x86_64 but we observed the same hang w/
elrepo kernel-ml-6.0.7-1.el7.
PID: 71258 TASK:
ffff91ebd4be0000 CPU: 36 COMMAND: "mount.nfs"
#0 [
ffff9203ca3234f8] __schedule at
ffffffffa3b8899f
#1 [
ffff9203ca323580] schedule at
ffffffffa3b88eb9
#2 [
ffff9203ca323590] gss_cred_init at
ffffffffc0355818 [auth_rpcgss]
#3 [
ffff9203ca323658] rpcauth_lookup_credcache at
ffffffffc0421ebc
[sunrpc]
#4 [
ffff9203ca3236d8] gss_lookup_cred at
ffffffffc0353633 [auth_rpcgss]
#5 [
ffff9203ca3236e8] rpcauth_lookupcred at
ffffffffc0421581 [sunrpc]
#6 [
ffff9203ca323740] rpcauth_refreshcred at
ffffffffc04223d3 [sunrpc]
#7 [
ffff9203ca3237a0] call_refresh at
ffffffffc04103dc [sunrpc]
#8 [
ffff9203ca3237b8] __rpc_execute at
ffffffffc041e1c9 [sunrpc]
#9 [
ffff9203ca323820] rpc_execute at
ffffffffc0420a48 [sunrpc]
The scenario is like this. Let's say there are two upcalls for
services A and B, A -> B in pipe->in_downcall, B -> A in pipe->pipe.
When rpc.gssd reads pipe to get the upcall msg corresponding to
service B from pipe->pipe and then writes the response, in
gss_pipe_downcall the msg corresponding to service A will be picked
because only uid is used to find the msg and it is before the one for
B in pipe->in_downcall. And the process waiting for the msg
corresponding to service A will be woken up.
Actual scheduing of that process might be after rpc.gssd processes the
next msg. In rpc_pipe_generic_upcall it clears msg->errno (for A).
The process is scheduled to see gss_msg->ctx == NULL and
gss_msg->msg.errno == 0, therefore it cannot break the loop in
gss_create_upcall and is never woken up after that.
This patch adds a simple check to ensure that a msg which is not
sent to rpc.gssd yet is not chosen as the matching upcall upon
receiving a downcall.
Signed-off-by: minoura makoto <minoura@valinux.co.jp>
Signed-off-by: Hiroshi Shimamoto <h-shimamoto@nec.com>
Tested-by: Hiroshi Shimamoto <h-shimamoto@nec.com>
Cc: Trond Myklebust <trondmy@hammerspace.com>
Fixes: 28460803dd20 ("SUNRPC: allow for upcalls for same uid but different gss service")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
char __user *, size_t);
extern int rpc_queue_upcall(struct rpc_pipe *, struct rpc_pipe_msg *);
+/* returns true if the msg is in-flight, i.e., already eaten by the peer */
+static inline bool rpc_msg_is_inflight(const struct rpc_pipe_msg *msg) {
+ return (msg->copied != 0 && list_empty(&msg->list));
+}
+
struct rpc_clnt;
extern struct dentry *rpc_create_client_dir(struct dentry *, const char *, struct rpc_clnt *);
extern int rpc_remove_client_dir(struct rpc_clnt *);
list_for_each_entry(pos, &pipe->in_downcall, list) {
if (!uid_eq(pos->uid, uid))
continue;
- if (auth && pos->auth->service != auth->service)
+ if (pos->auth->service != auth->service)
continue;
refcount_inc(&pos->count);
return pos;
return err;
}
+static struct gss_upcall_msg *
+gss_find_downcall(struct rpc_pipe *pipe, kuid_t uid)
+{
+ struct gss_upcall_msg *pos;
+ list_for_each_entry(pos, &pipe->in_downcall, list) {
+ if (!uid_eq(pos->uid, uid))
+ continue;
+ if (!rpc_msg_is_inflight(&pos->msg))
+ continue;
+ refcount_inc(&pos->count);
+ return pos;
+ }
+ return NULL;
+}
+
#define MSG_BUF_MAXSIZE 1024
static ssize_t
err = -ENOENT;
/* Find a matching upcall */
spin_lock(&pipe->lock);
- gss_msg = __gss_find_upcall(pipe, uid, NULL);
+ gss_msg = gss_find_downcall(pipe, uid);
if (gss_msg == NULL) {
spin_unlock(&pipe->lock);
goto err_put_ctx;