Merge branch 'team-fix-header_ops-type-confusion-and-add-selftest'

Jiayuan Chen says:

====================
team: fix header_ops type confusion and add selftest

Hi,

This patch series fixes a panic reported by syzkaller in the team/bond/gre
stacked non-Ethernet configuration:
https://syzkaller.appspot.com/bug?extid=3d8bc31c45e11450f24c

The first patch fixes the header_ops type confusion / parse recursion
context issue in team. The second patch adds a selftest to reproduce the
reported scenario and prevent regressions in the future.

v1: https://lore.kernel.org/netdev/[email protected]/
v2: https://lore.kernel.org/netdev/[email protected]/
====================

Link: https://patch.msgid.link/[email protected]
Signed-off-by: Paolo Abeni <[email protected]>

Author: Paolo Abeni

drivers/net/team/team_core.c

@@ -2058,6 +2058,68 @@ static const struct ethtool_ops team_ethtool_ops = {
  * rt netlink interface
  ***********************/
 
+/* For tx path we need a linkup && enabled port and for parse any port
+ * suffices.
+ */
+static struct team_port *team_header_port_get_rcu(struct team *team,
+						  bool txable)
+{
+	struct team_port *port;
+
+	list_for_each_entry_rcu(port, &team->port_list, list) {
+		if (!txable || team_port_txable(port))
+			return port;
+	}
+
+	return NULL;
+}
+
+static int team_header_create(struct sk_buff *skb, struct net_device *team_dev,
+			      unsigned short type, const void *daddr,
+			      const void *saddr, unsigned int len)
+{
+	struct team *team = netdev_priv(team_dev);
+	const struct header_ops *port_ops;
+	struct team_port *port;
+	int ret = 0;
+
+	rcu_read_lock();
+	port = team_header_port_get_rcu(team, true);
+	if (port) {
+		port_ops = READ_ONCE(port->dev->header_ops);
+		if (port_ops && port_ops->create)
+			ret = port_ops->create(skb, port->dev,
+					       type, daddr, saddr, len);
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
+static int team_header_parse(const struct sk_buff *skb,
+			     const struct net_device *team_dev,
+			     unsigned char *haddr)
+{
+	struct team *team = netdev_priv(team_dev);
+	const struct header_ops *port_ops;
+	struct team_port *port;
+	int ret = 0;
+
+	rcu_read_lock();
+	port = team_header_port_get_rcu(team, false);
+	if (port) {
+		port_ops = READ_ONCE(port->dev->header_ops);
+		if (port_ops && port_ops->parse)
+			ret = port_ops->parse(skb, port->dev, haddr);
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
+static const struct header_ops team_header_ops = {
+	.create		= team_header_create,
+	.parse		= team_header_parse,
+};
+
 static void team_setup_by_port(struct net_device *dev,
 			       struct net_device *port_dev)
 {
@@ -2066,7 +2128,8 @@ static void team_setup_by_port(struct net_device *dev,
 	if (port_dev->type == ARPHRD_ETHER)
 		dev->header_ops	= team->header_ops_cache;
 	else
-		dev->header_ops	= port_dev->header_ops;
+		dev->header_ops	= port_dev->header_ops ?
+				  &team_header_ops : NULL;
 	dev->type = port_dev->type;
 	dev->hard_header_len = port_dev->hard_header_len;
 	dev->needed_headroom = port_dev->needed_headroom;

tools/testing/selftests/drivers/net/team/Makefile

@@ -3,6 +3,7 @@
 
 TEST_PROGS := \
 	dev_addr_lists.sh \
+	non_ether_header_ops.sh \
 	options.sh \
 	propagation.sh \
 	refleak.sh \

tools/testing/selftests/drivers/net/team/config

@@ -1,7 +1,9 @@
+CONFIG_BONDING=y
 CONFIG_DUMMY=y
 CONFIG_IPV6=y
 CONFIG_MACVLAN=y
 CONFIG_NETDEVSIM=m
+CONFIG_NET_IPGRE=y
 CONFIG_NET_TEAM=y
 CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=y
 CONFIG_NET_TEAM_MODE_LOADBALANCE=y

tools/testing/selftests/drivers/net/team/non_ether_header_ops.sh

@@ -0,0 +1,41 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# shellcheck disable=SC2154
+#
+# Reproduce the non-Ethernet header_ops confusion scenario with:
+#   g0 (gre) -> b0 (bond) -> t0 (team)
+#
+# Before the fix, direct header_ops inheritance in this stack could call
+# callbacks with the wrong net_device context and crash.
+
+lib_dir=$(dirname "$0")
+source "$lib_dir"/../../../net/lib.sh
+
+trap cleanup_all_ns EXIT
+
+setup_ns ns1
+
+ip -n "$ns1" link add d0 type dummy
+ip -n "$ns1" addr add 10.10.10.1/24 dev d0
+ip -n "$ns1" link set d0 up
+
+ip -n "$ns1" link add g0 type gre local 10.10.10.1
+ip -n "$ns1" link add b0 type bond mode active-backup
+ip -n "$ns1" link add t0 type team
+
+ip -n "$ns1" link set g0 master b0
+ip -n "$ns1" link set b0 master t0
+
+ip -n "$ns1" link set g0 up
+ip -n "$ns1" link set b0 up
+ip -n "$ns1" link set t0 up
+
+# IPv6 address assignment triggers MLD join reports that call
+# dev_hard_header() on t0, exercising the inherited header_ops path.
+ip -n "$ns1" -6 addr add 2001:db8:1::1/64 dev t0 nodad
+for i in $(seq 1 20); do
+	ip netns exec "$ns1" ping -6 -I t0 ff02::1 -c1 -W1 &>/dev/null || true
+done
+
+echo "PASS: non-Ethernet header_ops stacking did not crash"
+exit "$EXIT_STATUS"