[PATCH net v2] net: cpsw_new: Execute ndo_set_rx_mode callback in a work queue

[Kevin Hao <haokexin@gmail.com>]

Commit 1767bb2d47b7 ("ipv6: mcast: Don't hold RTNL for
IPV6_ADD_MEMBERSHIP and MCAST_JOIN_GROUP.") removed the RTNL lock for
IPV6_ADD_MEMBERSHIP and MCAST_JOIN_GROUP operations. However, this
change triggered the following call trace on my BeagleBone Black board:
  WARNING: net/8021q/vlan_core.c:236 at vlan_for_each+0x120/0x124, CPU#0: rpcbind/496
  RTNL: assertion failed at net/8021q/vlan_core.c (236)
  Modules linked in:
  CPU: 0 UID: 997 PID: 496 Comm: rpcbind Not tainted 6.19.0-rc6-next-20260122-yocto-standard+ #8 PREEMPT
  Hardware name: Generic AM33XX (Flattened Device Tree)
  Call trace:
   unwind_backtrace from show_stack+0x28/0x2c
   show_stack from dump_stack_lvl+0x30/0x38
   dump_stack_lvl from __warn+0xb8/0x11c
   __warn from warn_slowpath_fmt+0x130/0x194
   warn_slowpath_fmt from vlan_for_each+0x120/0x124
   vlan_for_each from cpsw_add_mc_addr+0x54/0xd8
   cpsw_add_mc_addr from __hw_addr_ref_sync_dev+0xc4/0xec
   __hw_addr_ref_sync_dev from __dev_mc_add+0x78/0x88
   __dev_mc_add from igmp6_group_added+0x84/0xec
   igmp6_group_added from __ipv6_dev_mc_inc+0x1fc/0x2f0
   __ipv6_dev_mc_inc from __ipv6_sock_mc_join+0x124/0x1b4
   __ipv6_sock_mc_join from do_ipv6_setsockopt+0x84c/0x1168
   do_ipv6_setsockopt from ipv6_setsockopt+0x88/0xc8
   ipv6_setsockopt from do_sock_setsockopt+0xe8/0x19c
   do_sock_setsockopt from __sys_setsockopt+0x84/0xac
   __sys_setsockopt from ret_fast_syscall+0x0/0x5

This trace occurs because vlan_for_each() is called within
cpsw_ndo_set_rx_mode(), which expects the RTNL lock to be held.
Since modifying vlan_for_each() to operate without the RTNL lock is not
straightforward, and because ndo_set_rx_mode() is invoked both with and
without the RTNL lock across different code paths, simply adding
rtnl_lock() in cpsw_ndo_set_rx_mode() is not a viable solution.

To resolve this issue, we opt to execute the actual processing within
a work queue, following the approach used by the icssg-prueth driver.

Fixes: 1767bb2d47b7 ("ipv6: mcast: Don't hold RTNL for IPV6_ADD_MEMBERSHIP and MCAST_JOIN_GROUP.")
Signed-off-by: Kevin Hao <haokexin@gmail.com>
Cc: stable@vger.kernel.org
---
Changes in v2:
- Addresses the issue identified in the AI review [1]:
  - Adds a netif_running() check in cpsw_ndo_set_rx_mode_work()
  - Cancels the rx_mode_work in cpsw_ndo_stop()

- Link to v1: https://lore.kernel.org/r/20260123-bbb-v1-1-176b0b71834d@gmail.com

[1] https://netdev-ai.bots.linux.dev/ai-review.html?id=bd885e1e-1aed-4755-ad60-7150737ad0f5
---
Please note that the cpsw driver also has the same issue. If this resolution
is acceptable, I will create another patch to fix the issue in cpsw.

Cc: Siddharth Vadapalli <s-vadapalli@ti.com>
Cc: Roger Quadros <rogerq@kernel.org>
Cc: Andrew Lunn <andrew+netdev@lunn.ch>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: Vladimir Oltean <vladimir.oltean@nxp.com>
Cc: Kuniyuki Iwashima <kuniyu@google.com>
Cc: linux-omap@vger.kernel.org
---
 drivers/net/ethernet/ti/cpsw_new.c  | 34 ++++++++++++++++++++++++++++++++--
 drivers/net/ethernet/ti/cpsw_priv.h |  2 ++
 2 files changed, 34 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c
index ab88d4c02cbde76207f89cf433e2b383dcde6a83..a631df9691e06fef563da6276f8ee9358c4cf911 100644
--- a/drivers/net/ethernet/ti/cpsw_new.c
+++ b/drivers/net/ethernet/ti/cpsw_new.c
@@ -248,15 +248,23 @@ static int cpsw_purge_all_mc(struct net_device *ndev, const u8 *addr, int num)
 	return 0;
 }
 
-static void cpsw_ndo_set_rx_mode(struct net_device *ndev)
+static void cpsw_ndo_set_rx_mode_work(struct work_struct *work)
 {
-	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_priv *priv = container_of(work, struct cpsw_priv, rx_mode_work);
 	struct cpsw_common *cpsw = priv->cpsw;
+	struct net_device *ndev = priv->ndev;
 
+	if (!netif_running(ndev))
+		return;
+
+	rtnl_lock();
+	netif_addr_lock_bh(ndev);
 	if (ndev->flags & IFF_PROMISC) {
 		/* Enable promiscuous mode */
 		cpsw_set_promiscious(ndev, true);
 		cpsw_ale_set_allmulti(cpsw->ale, IFF_ALLMULTI, priv->emac_port);
+		netif_addr_unlock_bh(ndev);
+		rtnl_unlock();
 		return;
 	}
 
@@ -270,6 +278,16 @@ static void cpsw_ndo_set_rx_mode(struct net_device *ndev)
 	/* add/remove mcast address either for real netdev or for vlan */
 	__hw_addr_ref_sync_dev(&ndev->mc, ndev, cpsw_add_mc_addr,
 			       cpsw_del_mc_addr);
+	netif_addr_unlock_bh(ndev);
+	rtnl_unlock();
+}
+
+static void cpsw_ndo_set_rx_mode(struct net_device *ndev)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+
+	queue_work(cpsw->cmd_wq, &priv->rx_mode_work);
 }
 
 static unsigned int cpsw_rxbuf_total_len(unsigned int len)
@@ -813,6 +831,8 @@ static int cpsw_ndo_stop(struct net_device *ndev)
 
 	__hw_addr_ref_unsync_dev(&ndev->mc, ndev, cpsw_purge_all_mc);
 
+	cancel_work_sync(&priv->rx_mode_work);
+
 	if (cpsw->usage_count <= 1) {
 		napi_disable(&cpsw->napi_rx);
 		napi_disable(&cpsw->napi_tx);
@@ -1398,6 +1418,7 @@ static int cpsw_create_ports(struct cpsw_common *cpsw)
 		priv->msg_enable = netif_msg_init(debug_level, CPSW_DEBUG);
 		priv->emac_port = i + 1;
 		priv->tx_packet_min = CPSW_MIN_PACKET_SIZE;
+		INIT_WORK(&priv->rx_mode_work, cpsw_ndo_set_rx_mode_work);
 
 		if (is_valid_ether_addr(slave_data->mac_addr)) {
 			ether_addr_copy(priv->mac_addr, slave_data->mac_addr);
@@ -1976,6 +1997,13 @@ static int cpsw_probe(struct platform_device *pdev)
 	}
 	cpsw_split_res(cpsw);
 
+	cpsw->cmd_wq = create_singlethread_workqueue("cpsw_cmd_wq");
+	if (!cpsw->cmd_wq) {
+		dev_err(dev, "error initializing workqueue\n");
+		ret = -ENOMEM;
+		goto clean_cpts;
+	}
+
 	/* setup netdevs */
 	ret = cpsw_create_ports(cpsw);
 	if (ret)
@@ -2042,6 +2070,7 @@ static int cpsw_probe(struct platform_device *pdev)
 clean_unregister_notifiers:
 	cpsw_unregister_notifiers(cpsw);
 clean_unregister_netdev:
+	destroy_workqueue(cpsw->cmd_wq);
 	cpsw_unregister_ports(cpsw);
 clean_cpts:
 	cpts_release(cpsw->cpts);
@@ -2068,6 +2097,7 @@ static void cpsw_remove(struct platform_device *pdev)
 		return;
 	}
 
+	destroy_workqueue(cpsw->cmd_wq);
 	cpsw_unregister_notifiers(cpsw);
 	cpsw_unregister_devlink(cpsw);
 	cpsw_unregister_ports(cpsw);
diff --git a/drivers/net/ethernet/ti/cpsw_priv.h b/drivers/net/ethernet/ti/cpsw_priv.h
index 91add8925e235c6cf5542fde11f3383b9234c872..8cdf4bff198fcc05436ff381a7e4326b3e3c27b1 100644
--- a/drivers/net/ethernet/ti/cpsw_priv.h
+++ b/drivers/net/ethernet/ti/cpsw_priv.h
@@ -362,6 +362,7 @@ struct cpsw_common {
 	struct net_device *hw_bridge_dev;
 	bool ale_bypass;
 	u8 base_mac[ETH_ALEN];
+	struct workqueue_struct *cmd_wq;
 };
 
 struct cpsw_ale_ratelimit {
@@ -391,6 +392,7 @@ struct cpsw_priv {
 	u32 tx_packet_min;
 	struct cpsw_ale_ratelimit ale_bc_ratelimit;
 	struct cpsw_ale_ratelimit ale_mc_ratelimit;
+	struct work_struct rx_mode_work;
 };
 
 #define ndev_to_cpsw(ndev) (((struct cpsw_priv *)netdev_priv(ndev))->cpsw)

---
base-commit: ca3a02fda4da8e2c1cb6baee5d72352e9e2cfaea
change-id: 20260123-bbb-dc3675f671d0

Best regards,
-- 
Kevin Hao <haokexin@gmail.com>