linux-kernel - Re: [syzbot] [can?] WARNING: refcount bug in j1939_session

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <tencent_FD6E4F9F8DDFA5970D8A921DDDB65D851907@qq.com>
Date: Wed,  7 Aug 2024 14:21:21 +0800
From: Edward Adam Davis <eadavis@...com>
To: syzbot+ad601904231505ad6617@...kaller.appspotmail.com
Cc: linux-kernel@...r.kernel.org,
	syzkaller-bugs@...glegroups.com
Subject: Re: [syzbot] [can?] WARNING: refcount bug in j1939_session_put

Fixes: c9c0ee5f20c5 ("net: skbuff: Skip early return in skb_unref when debugging")

Root cause: In commit c9c0ee5f20c5, There are following rules:
In debug builds (CONFIG_DEBUG_NET set), the reference count is always  decremented, even when it's 1

This rule will cause the reference count to be 0 after calling skc_unref,
which will affect the release of skb.

#syz test: net-next 743ff02152bc

diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c
index 4be73de5033c..bff135a62712 100644
--- a/net/can/j1939/transport.c
+++ b/net/can/j1939/transport.c
@@ -261,6 +261,7 @@ static void __j1939_session_drop(struct j1939_session *session)
 static void j1939_session_destroy(struct j1939_session *session)
 {
 	struct sk_buff *skb;
+	struct j1939_sk_buff_cb *skcb;
 
 	if (session->transmission) {
 		if (session->err)
@@ -278,7 +279,11 @@ static void j1939_session_destroy(struct j1939_session *session)
 
 	while ((skb = skb_dequeue(&session->skb_queue)) != NULL) {
 		/* drop ref taken in j1939_session_skb_queue() */
-		skb_unref(skb);
+		skcb = j1939_skb_to_cb(skb);
+		if (skcb->flags & J1939_ECU_LOCAL_SRC)
+			skb_unref(skb);
+
+		printk("refcnt: %d, skb: %p, %s\n", refcount_read(&skb->users), skb, __func__);
 		kfree_skb(skb);
 	}
 	__j1939_session_drop(session);
@@ -341,6 +346,7 @@ static void j1939_session_skb_drop_old(struct j1939_session *session)
 	if ((do_skcb->offset + do_skb->len) < offset_start) {
 		__skb_unlink(do_skb, &session->skb_queue);
 		/* drop ref taken in j1939_session_skb_queue() */
+		printk("refcnt: %d, skb: %p, %s\n", refcount_read(&do_skb->users), do_skb, __func__);
 		skb_unref(do_skb);
 		spin_unlock_irqrestore(&session->skb_queue.lock, flags);
 
@@ -365,6 +371,7 @@ void j1939_session_skb_queue(struct j1939_session *session,
 	skcb->flags |= J1939_ECU_LOCAL_SRC;
 
 	skb_get(skb);
+	printk("refcnt: %d, skb: %p, %s\n", refcount_read(&skb->users), skb, __func__);
 	skb_queue_tail(&session->skb_queue, skb);
 }