@@ -393,15 +393,6 @@ static void netlink_skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
static void netlink_sock_destruct(struct sock *sk)
{
- struct netlink_sock *nlk = nlk_sk(sk);
-
- if (nlk->cb_running) {
- if (nlk->cb.done)
- nlk->cb.done(&nlk->cb);
- module_put(nlk->cb.module);
- kfree_skb(nlk->cb.skb);
- }
-
skb_queue_purge(&sk->sk_receive_queue);
if (!sock_flag(sk, SOCK_DEAD)) {
@@ -414,14 +405,6 @@ static void netlink_sock_destruct(struct sock *sk)
WARN_ON(nlk_sk(sk)->groups);
}
-static void netlink_sock_destruct_work(struct work_struct *work)
-{
- struct netlink_sock *nlk = container_of(work, struct netlink_sock,
- work);
-
- sk_free(&nlk->sk);
-}
-
/* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it is _very_ bad on
* SMP. Look, when several writers sleep and reader wakes them up, all but one
* immediately hit write lock and grab all the cpus. Exclusive sleep solves
@@ -731,12 +714,6 @@ static void deferred_put_nlk_sk(struct rcu_head *head)
if (!refcount_dec_and_test(&sk->sk_refcnt))
return;
- if (nlk->cb_running && nlk->cb.done) {
- INIT_WORK(&nlk->work, netlink_sock_destruct_work);
- schedule_work(&nlk->work);
- return;
- }
-
sk_free(sk);
}
@@ -788,6 +765,14 @@ static int netlink_release(struct socket *sock)
NETLINK_URELEASE, &n);
}
+ /* Terminate any outstanding dump */
+ if (nlk->cb_running) {
+ if (nlk->cb.done)
+ nlk->cb.done(&nlk->cb);
+ module_put(nlk->cb.module);
+ kfree_skb(nlk->cb.skb);
+ }
+
module_put(nlk->module);
if (netlink_is_kernel(sk)) {
@@ -4,7 +4,6 @@
#include <linux/rhashtable.h>
#include <linux/atomic.h>
-#include <linux/workqueue.h>
#include <net/sock.h>
/* flags */
@@ -50,7 +49,6 @@ struct netlink_sock {
struct rhash_head node;
struct rcu_head rcu;
- struct work_struct work;
};
static inline struct netlink_sock *nlk_sk(struct sock *sk)
Netlink supports iterative dumping of data. It provides the families the following ops: - start - (optional) kicks off the dumping process - dump - actual dump helper, keeps getting called until it returns 0 - done - (optional) pairs with .start, can be used for cleanup The whole process is asynchronous and the repeated calls to .dump don't actually happen in a tight loop, but rather are triggered in response to recvmsg() on the socket. This gives the user full control over the dump, but also means that the user can close the socket without getting to the end of the dump. To make sure .start is always paired with .done we check if there is an ongoing dump before freeing the socket, and if so call .done. The complication is that sockets can get freed from BH and .done is allowed to sleep. So we use a workqueue to defer the call, when needed. Unfortunately this does not work correctly. What we defer is not the cleanup but rather releasing a reference on the socket. We have no guarantee that we own the last reference, if someone else holds the socket they may release it in BH and we're back to square one. The whole dance, however, appears to be unnecessary. Only the user can interact with dumps, so we can clean up when socket is closed. And close always happens in process context. Some async code may still access the socket after close, queue notification skbs to it etc. but no dumps can start, end or otherwise make progress. Delete the workqueue and flush the dump state directly from the release handler. Note that further cleanup is possible in -next, for instance we now always call .done before releasing the main module reference, so dump doesn't have to take a reference of its own. Reported-by: syzkaller <syzkaller@googlegroups.com> Fixes: ed5d7788a934 ("netlink: Do not schedule work from sk_destruct") Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org> --- v2: - change reported tag v1: https://lore.kernel.org/20241105010347.2079981-1-kuba@kernel.org --- net/netlink/af_netlink.c | 31 ++++++++----------------------- net/netlink/af_netlink.h | 2 -- 2 files changed, 8 insertions(+), 25 deletions(-)