From: Wang Yufen <wangyufen@huawei.com>
Date: Fri, 4 Mar 2022 16:11:42 +0800
Subject: bpf, sockmap: Fix memleak in sk_psock_queue_msg
Patch-mainline: v5.18-rc1
Git-commit: 938d3480b92fa5e454b7734294f12a7b75126f09
References: jsc#PED-1377

If tcp_bpf_sendmsg is running during a tear down operation we may enqueue
data on the ingress msg queue while tear down is trying to free it.

 sk1 (redirect sk2)                         sk2
 -------------------                      ---------------
tcp_bpf_sendmsg()
 tcp_bpf_send_verdict()
  tcp_bpf_sendmsg_redir()
   bpf_tcp_ingress()
                                          sock_map_close()
                                           lock_sock()
    lock_sock() ... blocking
                                           sk_psock_stop
                                            sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED);
                                           release_sock(sk);
    lock_sock()
    sk_mem_charge()
    get_page()
    sk_psock_queue_msg()
     sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED);
      drop_sk_msg()
    release_sock()

While drop_sk_msg(), the msg has charged memory form sk by sk_mem_charge
and has sg pages need to put. To fix we use sk_msg_free() and then kfee()
msg.

This issue can cause the following info:
WARNING: CPU: 0 PID: 9202 at net/core/stream.c:205 sk_stream_kill_queues+0xc8/0xe0
Call Trace:
 <IRQ>
 inet_csk_destroy_sock+0x55/0x110
 tcp_rcv_state_process+0xe5f/0xe90
 ? sk_filter_trim_cap+0x10d/0x230
 ? tcp_v4_do_rcv+0x161/0x250
 tcp_v4_do_rcv+0x161/0x250
 tcp_v4_rcv+0xc3a/0xce0
 ip_protocol_deliver_rcu+0x3d/0x230
 ip_local_deliver_finish+0x54/0x60
 ip_local_deliver+0xfd/0x110
 ? ip_protocol_deliver_rcu+0x230/0x230
 ip_rcv+0xd6/0x100
 ? ip_local_deliver+0x110/0x110
 __netif_receive_skb_one_core+0x85/0xa0
 process_backlog+0xa4/0x160
 __napi_poll+0x29/0x1b0
 net_rx_action+0x287/0x300
 __do_softirq+0xff/0x2fc
 do_softirq+0x79/0x90
 </IRQ>

WARNING: CPU: 0 PID: 531 at net/ipv4/af_inet.c:154 inet_sock_destruct+0x175/0x1b0
Call Trace:
 <TASK>
 __sk_destruct+0x24/0x1f0
 sk_psock_destroy+0x19b/0x1c0
 process_one_work+0x1b3/0x3c0
 ? process_one_work+0x3c0/0x3c0
 worker_thread+0x30/0x350
 ? process_one_work+0x3c0/0x3c0
 kthread+0xe6/0x110
 ? kthread_complete_and_exit+0x20/0x20
 ret_from_fork+0x22/0x30
 </TASK>

Fixes: 9635720b7c88 ("bpf, sockmap: Fix memleak on ingress msg enqueue")
Signed-off-by: Wang Yufen <wangyufen@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20220304081145.2037182-2-wangyufen@huawei.com
Acked-by: Shung-Hsi Yu <shung-hsi.yu@suse.com>
---
 include/linux/skmsg.h |   13 ++++---------
 1 file changed, 4 insertions(+), 9 deletions(-)

--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -304,21 +304,16 @@ static inline void sock_drop(struct sock
 	kfree_skb(skb);
 }
 
-static inline void drop_sk_msg(struct sk_psock *psock, struct sk_msg *msg)
-{
-	if (msg->skb)
-		sock_drop(psock->sk, msg->skb);
-	kfree(msg);
-}
-
 static inline void sk_psock_queue_msg(struct sk_psock *psock,
 				      struct sk_msg *msg)
 {
 	spin_lock_bh(&psock->ingress_lock);
 	if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))
 		list_add_tail(&msg->list, &psock->ingress_msg);
-	else
-		drop_sk_msg(psock, msg);
+	else {
+		sk_msg_free(psock->sk, msg);
+		kfree(msg);
+	}
 	spin_unlock_bh(&psock->ingress_lock);
 }