[PATCH] net/sunrpc: fix reference count leaks in rpc_sysfs_xprt_state_change
From: Xiyu Yang <hidden>
Date: 2021-09-09 04:33:34
Also in:
linux-nfs, lkml
Subsystem:
kernel nfsd, sunrpc, and lockd servers, networking [general], nfs, sunrpc, and lockd clients, the rest · Maintainers:
Chuck Lever, Jeff Layton, "David S. Miller", Eric Dumazet, Jakub Kicinski, Paolo Abeni, Trond Myklebust, Anna Schumaker, Linus Torvalds
The refcount leak issues take place in an error handling path. When the 3rd argument buf doesn't match with "offline", "online" or "remove", the function simply returns -EINVAL and forgets to decrease the reference count of a rpc_xprt object and a rpc_xprt_switch object increased by rpc_sysfs_xprt_kobj_get_xprt() and rpc_sysfs_xprt_kobj_get_xprt_switch(), causing reference count leaks of both unused objects. Fix this issue by jumping to the error handling path labelled with out_put when buf matches none of "offline", "online" or "remove". Signed-off-by: Xiyu Yang <redacted> Signed-off-by: Xin Xiong <redacted> Signed-off-by: Xin Tan <redacted> --- net/sunrpc/sysfs.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/net/sunrpc/sysfs.c b/net/sunrpc/sysfs.c
index 64da3bfd28e6..0cce0375107f 100644
--- a/net/sunrpc/sysfs.c
+++ b/net/sunrpc/sysfs.c@@ -265,8 +265,10 @@ static ssize_t rpc_sysfs_xprt_state_change(struct kobject *kobj, online = 1; else if (!strncmp(buf, "remove", 6)) remove = 1; - else - return -EINVAL; + else { + count = -EINVAL; + goto out_put; + } if (wait_on_bit_lock(&xprt->state, XPRT_LOCKED, TASK_KILLABLE)) { count = -EINTR;
--
2.7.4