net: enetc: fix the deadlock of enetc_mdio_lock

After applying the workaround for err050089, the LS1028A platform
experiences RCU stalls on RT kernel. This issue is caused by the
recursive acquisition of the read lock enetc_mdio_lock. Here list some
of the call stacks identified under the enetc_poll path that may lead to
a deadlock:

enetc_poll
  -> enetc_lock_mdio
  -> enetc_clean_rx_ring OR napi_complete_done
     -> napi_gro_receive
        -> enetc_start_xmit
           -> enetc_lock_mdio
           -> enetc_map_tx_buffs
           -> enetc_unlock_mdio
  -> enetc_unlock_mdio

After enetc_poll acquires the read lock, a higher-priority writer attempts
to acquire the lock, causing preemption. The writer detects that a
read lock is already held and is scheduled out. However, readers under
enetc_poll cannot acquire the read lock again because a writer is already
waiting, leading to a thread hang.

Currently, the deadlock is avoided by adjusting enetc_lock_mdio to prevent
recursive lock acquisition.

Fixes: 6d36ecdbc441 ("net: enetc: take the MDIO lock only once per NAPI poll cycle")
Signed-off-by: Jianpeng Chang <jianpeng.chang.cn@windriver.com>
Acked-by: Wei Fang <wei.fang@nxp.com>
Link: https://patch.msgid.link/20251015021427.180757-1-jianpeng.chang.cn@windriver.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 21 insertions, 4 deletions

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index aae462a0cf5a..0535e92404e3 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -1595,6 +1595,8 @@ static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring,
 	/* next descriptor to process */
 	i = rx_ring->next_to_clean;
 
+	enetc_lock_mdio();
+
 	while (likely(rx_frm_cnt < work_limit)) {
 		union enetc_rx_bd *rxbd;
 		struct sk_buff *skb;
@@ -1630,7 +1632,9 @@ static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring,
 		rx_byte_cnt += skb->len + ETH_HLEN;
 		rx_frm_cnt++;
 
+		enetc_unlock_mdio();
 		napi_gro_receive(napi, skb);
+		enetc_lock_mdio();
 	}
 
 	rx_ring->next_to_clean = i;
@@ -1638,6 +1642,8 @@ static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring,
 	rx_ring->stats.packets += rx_frm_cnt;
 	rx_ring->stats.bytes += rx_byte_cnt;
 
+	enetc_unlock_mdio();
+
 	return rx_frm_cnt;
 }
 
@@ -1947,6 +1953,8 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
 	/* next descriptor to process */
 	i = rx_ring->next_to_clean;
 
+	enetc_lock_mdio();
+
 	while (likely(rx_frm_cnt < work_limit)) {
 		union enetc_rx_bd *rxbd, *orig_rxbd;
 		struct xdp_buff xdp_buff;
@@ -2010,7 +2018,9 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
 			 */
 			enetc_bulk_flip_buff(rx_ring, orig_i, i);
 
+			enetc_unlock_mdio();
 			napi_gro_receive(napi, skb);
+			enetc_lock_mdio();
 			break;
 		case XDP_TX:
 			tx_ring = priv->xdp_tx_ring[rx_ring->index];
@@ -2045,7 +2055,9 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
 			}
 			break;
 		case XDP_REDIRECT:
+			enetc_unlock_mdio();
 			err = xdp_do_redirect(rx_ring->ndev, &xdp_buff, prog);
+			enetc_lock_mdio();
 			if (unlikely(err)) {
 				enetc_xdp_drop(rx_ring, orig_i, i);
 				rx_ring->stats.xdp_redirect_failures++;
@@ -2065,8 +2077,11 @@ out:
 	rx_ring->stats.packets += rx_frm_cnt;
 	rx_ring->stats.bytes += rx_byte_cnt;
 
-	if (xdp_redirect_frm_cnt)
+	if (xdp_redirect_frm_cnt) {
+		enetc_unlock_mdio();
 		xdp_do_flush();
+		enetc_lock_mdio();
+	}
 
 	if (xdp_tx_frm_cnt)
 		enetc_update_tx_ring_tail(tx_ring);
@@ -2075,6 +2090,8 @@ out:
 		enetc_refill_rx_ring(rx_ring, enetc_bd_unused(rx_ring) -
 				     rx_ring->xdp.xdp_tx_in_flight);
 
+	enetc_unlock_mdio();
+
 	return rx_frm_cnt;
 }
 
@@ -2093,6 +2110,7 @@ static int enetc_poll(struct napi_struct *napi, int budget)
 	for (i = 0; i < v->count_tx_rings; i++)
 		if (!enetc_clean_tx_ring(&v->tx_ring[i], budget))
 			complete = false;
+	enetc_unlock_mdio();
 
 	prog = rx_ring->xdp.prog;
 	if (prog)
@@ -2104,10 +2122,8 @@ static int enetc_poll(struct napi_struct *napi, int budget)
 	if (work_done)
 		v->rx_napi_work = true;
 
-	if (!complete) {
-		enetc_unlock_mdio();
+	if (!complete)
 		return budget;
-	}
 
 	napi_complete_done(napi, work_done);
 
@@ -2116,6 +2132,7 @@ static int enetc_poll(struct napi_struct *napi, int budget)
 
 	v->rx_napi_work = false;
 
+	enetc_lock_mdio();
 	/* enable interrupts */
 	enetc_wr_reg_hot(v->rbier, ENETC_RBIER_RXTIE);