net: enetc: block concurrent XDP transmissions during ring reconfiguration

When testing the XDP_REDIRECT function on the LS1028A platform, we
found a very reproducible issue that the Tx frames can no longer be
sent out even if XDP_REDIRECT is turned off. Specifically, if there
is a lot of traffic on Rx direction, when XDP_REDIRECT is turned on,
the console may display some warnings like "timeout for tx ring openbmc#6
clear", and all redirected frames will be dropped, the detailed log
is as follows.

root@ls1028ardb:~# ./xdp-bench redirect eno0 eno2
Redirecting from eno0 (ifindex 3; driver fsl_enetc) to eno2 (ifindex 4; driver fsl_enetc)
[203.849809] fsl_enetc 0000:00:00.2 eno2: timeout for tx ring openbmc#5 clear
[204.006051] fsl_enetc 0000:00:00.2 eno2: timeout for tx ring openbmc#6 clear
[204.161944] fsl_enetc 0000:00:00.2 eno2: timeout for tx ring openbmc#7 clear
eno0->eno2     1420505 rx/s       1420590 err,drop/s      0 xmit/s
  xmit eno0->eno2    0 xmit/s     1420590 drop/s     0 drv_err/s     15.71 bulk-avg
eno0->eno2     1420484 rx/s       1420485 err,drop/s      0 xmit/s
  xmit eno0->eno2    0 xmit/s     1420485 drop/s     0 drv_err/s     15.71 bulk-avg

By analyzing the XDP_REDIRECT implementation of enetc driver, the
driver will reconfigure Tx and Rx BD rings when a bpf program is
installed or uninstalled, but there is no mechanisms to block the
redirected frames when enetc driver reconfigures rings. Similarly,
XDP_TX verdicts on received frames can also lead to frames being
enqueued in the Tx rings. Because XDP ignores the state set by the
netif_tx_wake_queue() API, so introduce the ENETC_TX_DOWN flag to
suppress transmission of XDP frames.

Fixes: c33bfaf ("net: enetc: set up XDP program under enetc_reconfigure()")
Cc: stable@vger.kernel.org
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://patch.msgid.link/20241010092056.298128-3-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Author: Wei Fang

drivers/net/ethernet/freescale/enetc/enetc.c

@@ -902,6 +902,7 @@ static bool enetc_clean_tx_ring(struct enetc_bdr *tx_ring, int napi_budget)
 
 	if (unlikely(tx_frm_cnt && netif_carrier_ok(ndev) &&
 		     __netif_subqueue_stopped(ndev, tx_ring->index) &&
+		     !test_bit(ENETC_TX_DOWN, &priv->flags) &&
 		     (enetc_bd_unused(tx_ring) >= ENETC_TXBDS_MAX_NEEDED))) {
 		netif_wake_subqueue(ndev, tx_ring->index);
 	}
@@ -1377,6 +1378,9 @@ int enetc_xdp_xmit(struct net_device *ndev, int num_frames,
 	int xdp_tx_bd_cnt, i, k;
 	int xdp_tx_frm_cnt = 0;
 
+	if (unlikely(test_bit(ENETC_TX_DOWN, &priv->flags)))
+		return -ENETDOWN;
+
 	enetc_lock_mdio();
 
 	tx_ring = priv->xdp_tx_ring[smp_processor_id()];
@@ -1602,6 +1606,12 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
 			break;
 		case XDP_TX:
 			tx_ring = priv->xdp_tx_ring[rx_ring->index];
+			if (unlikely(test_bit(ENETC_TX_DOWN, &priv->flags))) {
+				enetc_xdp_drop(rx_ring, orig_i, i);
+				tx_ring->stats.xdp_tx_drops++;
+				break;
+			}
+
 			xdp_tx_bd_cnt = enetc_rx_swbd_to_xdp_tx_swbd(xdp_tx_arr,
 								     rx_ring,
 								     orig_i, i);
@@ -2463,6 +2473,8 @@ void enetc_start(struct net_device *ndev)
 	enetc_enable_bdrs(priv);
 
 	netif_tx_start_all_queues(ndev);
+
+	clear_bit(ENETC_TX_DOWN, &priv->flags);
 }
 EXPORT_SYMBOL_GPL(enetc_start);
 
@@ -2520,6 +2532,8 @@ void enetc_stop(struct net_device *ndev)
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
 	int i;
 
+	set_bit(ENETC_TX_DOWN, &priv->flags);
+
 	netif_tx_stop_all_queues(ndev);
 
 	enetc_disable_bdrs(priv);

drivers/net/ethernet/freescale/enetc/enetc.h

@@ -325,6 +325,7 @@ enum enetc_active_offloads {
 
 enum enetc_flags_bit {
 	ENETC_TX_ONESTEP_TSTAMP_IN_PROGRESS = 0,
+	ENETC_TX_DOWN,
 };
 
 /* interrupt coalescing modes */