6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jianpeng Chang jianpeng.chang.cn@windriver.com
[ Upstream commit 50bd33f6b3922a6b760aa30d409cae891cec8fb5 ]
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... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/freescale/enetc/enetc.c | 25 ++++++++++++++++---- 1 file changed, 21 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 49c61aa920b02..7accf3a3e9f0d 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -1246,6 +1246,8 @@ 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; @@ -1281,7 +1283,9 @@ 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; @@ -1289,6 +1293,8 @@ 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; }
@@ -1598,6 +1604,8 @@ 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; int orig_i, orig_cleaned_cnt; @@ -1657,7 +1665,9 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring, if (unlikely(!skb)) goto out;
+ enetc_unlock_mdio(); napi_gro_receive(napi, skb); + enetc_lock_mdio(); break; case XDP_TX: tx_ring = priv->xdp_tx_ring[rx_ring->index]; @@ -1692,7 +1702,9 @@ 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++; @@ -1712,8 +1724,11 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring, 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); @@ -1722,6 +1737,8 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring, 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; }
@@ -1740,6 +1757,7 @@ 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) @@ -1751,10 +1769,8 @@ 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);
@@ -1763,6 +1779,7 @@ 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);