summaryrefslogtreecommitdiffstats
path: root/net/sunrpc
diff options
context:
space:
mode:
authorminoura makoto <minoura@valinux.co.jp>2022-12-13 13:14:31 +0900
committerTrond Myklebust <trond.myklebust@hammerspace.com>2022-12-15 18:13:53 -0500
commitb18cba09e374637a0a3759d856a6bca94c133952 (patch)
tree3425d77fa3d2f9c3636d8d51cfb97fb00e35640b /net/sunrpc
parent7fd461c47c6cfab4ca4d003790ec276209e52978 (diff)
downloadlinux-b18cba09e374637a0a3759d856a6bca94c133952.tar.bz2
SUNRPC: ensure the matching upcall is in-flight upon downcall
Commit 9130b8dbc6ac ("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: 9130b8dbc6ac ("SUNRPC: allow for upcalls for same uid but different gss service") Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Diffstat (limited to 'net/sunrpc')
-rw-r--r--net/sunrpc/auth_gss/auth_gss.c19
1 files changed, 17 insertions, 2 deletions
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 7bb247c51e2f..2d7b1e03110a 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -302,7 +302,7 @@ __gss_find_upcall(struct rpc_pipe *pipe, kuid_t uid, const struct gss_auth *auth
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;
@@ -686,6 +686,21 @@ out:
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
@@ -732,7 +747,7 @@ gss_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
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;