Merge branch 'eth-bnxt-handle-invalid-tx-completions-more-gracefully'

Jakub Kicinski says:

====================
eth: bnxt: handle invalid Tx completions more gracefully

bnxt trusts the events generated by the device which may lead to kernel
crashes. These are extremely rare but they do happen. For a while
I thought crashing may be intentional, because device reporting invalid
completions should never happen, and having a core dump could be useful
if it does. But in practice I haven't found any clues in the core dumps,
and panic_on_warn exists.

Series was tested by forcing the recovery path manually. Because of
how rare the real crashes are I can't confirm it works for the actual
device errors until it's been widely deployed.

v1: https://lore.kernel.org/all/20230710205611.1198878-1-kuba@kernel.org/
====================

Link: https://lore.kernel.org/r/20230720010440.1967136-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 91 insertions, 70 deletions

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index d84ded8db93d..a3bbd13c070f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -293,6 +293,60 @@ static void bnxt_db_cq(struct bnxt *bp, struct bnxt_db_info *db, u32 idx)
 		BNXT_DB_CQ(db, idx);
 }
 
+static void bnxt_queue_fw_reset_work(struct bnxt *bp, unsigned long delay)
+{
+	if (!(test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)))
+		return;
+
+	if (BNXT_PF(bp))
+		queue_delayed_work(bnxt_pf_wq, &bp->fw_reset_task, delay);
+	else
+		schedule_delayed_work(&bp->fw_reset_task, delay);
+}
+
+static void __bnxt_queue_sp_work(struct bnxt *bp)
+{
+	if (BNXT_PF(bp))
+		queue_work(bnxt_pf_wq, &bp->sp_task);
+	else
+		schedule_work(&bp->sp_task);
+}
+
+static void bnxt_queue_sp_work(struct bnxt *bp, unsigned int event)
+{
+	set_bit(event, &bp->sp_event);
+	__bnxt_queue_sp_work(bp);
+}
+
+static void bnxt_sched_reset_rxr(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
+{
+	if (!rxr->bnapi->in_reset) {
+		rxr->bnapi->in_reset = true;
+		if (bp->flags & BNXT_FLAG_CHIP_P5)
+			set_bit(BNXT_RESET_TASK_SP_EVENT, &bp->sp_event);
+		else
+			set_bit(BNXT_RST_RING_SP_EVENT, &bp->sp_event);
+		__bnxt_queue_sp_work(bp);
+	}
+	rxr->rx_next_cons = 0xffff;
+}
+
+void bnxt_sched_reset_txr(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
+			  int idx)
+{
+	struct bnxt_napi *bnapi = txr->bnapi;
+
+	if (bnapi->tx_fault)
+		return;
+
+	netdev_err(bp->dev, "Invalid Tx completion (ring:%d tx_pkts:%d cons:%u prod:%u i:%d)",
+		   txr->txq_index, bnapi->tx_pkts,
+		   txr->tx_cons, txr->tx_prod, idx);
+	WARN_ON_ONCE(1);
+	bnapi->tx_fault = 1;
+	bnxt_queue_sp_work(bp, BNXT_RESET_TASK_SP_EVENT);
+}
+
 const u16 bnxt_lhint_arr[] = {
 	TX_BD_FLAGS_LHINT_512_AND_SMALLER,
 	TX_BD_FLAGS_LHINT_512_TO_1023,
@@ -652,6 +706,11 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts)
 		skb = tx_buf->skb;
 		tx_buf->skb = NULL;
 
+		if (unlikely(!skb)) {
+			bnxt_sched_reset_txr(bp, txr, i);
+			return;
+		}
+
 		tx_bytes += skb->len;
 
 		if (tx_buf->is_push) {
@@ -1234,38 +1293,6 @@ static int bnxt_discard_rx(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	return 0;
 }
 
-static void bnxt_queue_fw_reset_work(struct bnxt *bp, unsigned long delay)
-{
-	if (!(test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)))
-		return;
-
-	if (BNXT_PF(bp))
-		queue_delayed_work(bnxt_pf_wq, &bp->fw_reset_task, delay);
-	else
-		schedule_delayed_work(&bp->fw_reset_task, delay);
-}
-
-static void bnxt_queue_sp_work(struct bnxt *bp)
-{
-	if (BNXT_PF(bp))
-		queue_work(bnxt_pf_wq, &bp->sp_task);
-	else
-		schedule_work(&bp->sp_task);
-}
-
-static void bnxt_sched_reset(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
-{
-	if (!rxr->bnapi->in_reset) {
-		rxr->bnapi->in_reset = true;
-		if (bp->flags & BNXT_FLAG_CHIP_P5)
-			set_bit(BNXT_RESET_TASK_SP_EVENT, &bp->sp_event);
-		else
-			set_bit(BNXT_RST_RING_SP_EVENT, &bp->sp_event);
-		bnxt_queue_sp_work(bp);
-	}
-	rxr->rx_next_cons = 0xffff;
-}
-
 static u16 bnxt_alloc_agg_idx(struct bnxt_rx_ring_info *rxr, u16 agg_id)
 {
 	struct bnxt_tpa_idx_map *map = rxr->rx_tpa_idx_map;
@@ -1320,7 +1347,7 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 		netdev_warn(bp->dev, "TPA cons %x, expected cons %x, error code %x\n",
 			    cons, rxr->rx_next_cons,
 			    TPA_START_ERROR_CODE(tpa_start1));
-		bnxt_sched_reset(bp, rxr);
+		bnxt_sched_reset_rxr(bp, rxr);
 		return;
 	}
 	/* Store cfa_code in tpa_info to use in tpa_end
@@ -1844,7 +1871,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 		if (rxr->rx_next_cons != 0xffff)
 			netdev_warn(bp->dev, "RX cons %x != expected cons %x\n",
 				    cons, rxr->rx_next_cons);
-		bnxt_sched_reset(bp, rxr);
+		bnxt_sched_reset_rxr(bp, rxr);
 		if (rc1)
 			return rc1;
 		goto next_rx_no_prod_no_len;
@@ -1882,7 +1909,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 			    !(bp->fw_cap & BNXT_FW_CAP_RING_MONITOR)) {
 				netdev_warn_once(bp->dev, "RX buffer error %x\n",
 						 rx_err);
-				bnxt_sched_reset(bp, rxr);
+				bnxt_sched_reset_rxr(bp, rxr);
 			}
 		}
 		goto next_rx_no_len;
@@ -2329,7 +2356,7 @@ static int bnxt_async_event_process(struct bnxt *bp,
 			goto async_event_process_exit;
 		}
 		rxr = bp->bnapi[grp_idx]->rx_ring;
-		bnxt_sched_reset(bp, rxr);
+		bnxt_sched_reset_rxr(bp, rxr);
 		goto async_event_process_exit;
 	}
 	case ASYNC_EVENT_CMPL_EVENT_ID_ECHO_REQUEST: {
@@ -2384,7 +2411,7 @@ static int bnxt_async_event_process(struct bnxt *bp,
 	default:
 		goto async_event_process_exit;
 	}
-	bnxt_queue_sp_work(bp);
+	__bnxt_queue_sp_work(bp);
 async_event_process_exit:
 	return 0;
 }
@@ -2413,8 +2440,7 @@ static int bnxt_hwrm_handler(struct bnxt *bp, struct tx_cmp *txcmp)
 		}
 
 		set_bit(vf_id - bp->pf.first_vf_id, bp->pf.vf_event_bmap);
-		set_bit(BNXT_HWRM_EXEC_FWD_REQ_SP_EVENT, &bp->sp_event);
-		bnxt_queue_sp_work(bp);
+		bnxt_queue_sp_work(bp, BNXT_HWRM_EXEC_FWD_REQ_SP_EVENT);
 		break;
 
 	case CMPL_BASE_TYPE_HWRM_ASYNC_EVENT:
@@ -2571,7 +2597,7 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 
 static void __bnxt_poll_work_done(struct bnxt *bp, struct bnxt_napi *bnapi)
 {
-	if (bnapi->tx_pkts) {
+	if (bnapi->tx_pkts && !bnapi->tx_fault) {
 		bnapi->tx_int(bp, bnapi, bnapi->tx_pkts);
 		bnapi->tx_pkts = 0;
 	}
@@ -9424,6 +9450,8 @@ static void bnxt_enable_napi(struct bnxt *bp)
 		struct bnxt_napi *bnapi = bp->bnapi[i];
 		struct bnxt_cp_ring_info *cpr;
 
+		bnapi->tx_fault = 0;
+
 		cpr = &bnapi->cp_ring;
 		if (bnapi->in_reset)
 			cpr->sw_stats.rx.rx_resets++;
@@ -11031,8 +11059,7 @@ static void bnxt_set_rx_mode(struct net_device *dev)
 	if (mask != vnic->rx_mask || uc_update || mc_update) {
 		vnic->rx_mask = mask;
 
-		set_bit(BNXT_RX_MASK_SP_EVENT, &bp->sp_event);
-		bnxt_queue_sp_work(bp);
+		bnxt_queue_sp_work(bp, BNXT_RX_MASK_SP_EVENT);
 	}
 }
 
@@ -11597,8 +11624,7 @@ static void bnxt_tx_timeout(struct net_device *dev, unsigned int txqueue)
 	struct bnxt *bp = netdev_priv(dev);
 
 	netdev_err(bp->dev,  "TX timeout detected, starting reset task!\n");
-	set_bit(BNXT_RESET_TASK_SP_EVENT, &bp->sp_event);
-	bnxt_queue_sp_work(bp);
+	bnxt_queue_sp_work(bp, BNXT_RESET_TASK_SP_EVENT);
 }
 
 static void bnxt_fw_health_check(struct bnxt *bp)
@@ -11635,8 +11661,7 @@ static void bnxt_fw_health_check(struct bnxt *bp)
 	return;
 
 fw_reset:
-	set_bit(BNXT_FW_EXCEPTION_SP_EVENT, &bp->sp_event);
-	bnxt_queue_sp_work(bp);
+	bnxt_queue_sp_work(bp, BNXT_FW_EXCEPTION_SP_EVENT);
 }
 
 static void bnxt_timer(struct timer_list *t)
@@ -11653,21 +11678,15 @@ static void bnxt_timer(struct timer_list *t)
 	if (bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY)
 		bnxt_fw_health_check(bp);
 
-	if (BNXT_LINK_IS_UP(bp) && bp->stats_coal_ticks) {
-		set_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event);
-		bnxt_queue_sp_work(bp);
-	}
+	if (BNXT_LINK_IS_UP(bp) && bp->stats_coal_ticks)
+		bnxt_queue_sp_work(bp, BNXT_PERIODIC_STATS_SP_EVENT);
 
-	if (bnxt_tc_flower_enabled(bp)) {
-		set_bit(BNXT_FLOW_STATS_SP_EVENT, &bp->sp_event);
-		bnxt_queue_sp_work(bp);
-	}
+	if (bnxt_tc_flower_enabled(bp))
+		bnxt_queue_sp_work(bp, BNXT_FLOW_STATS_SP_EVENT);
 
 #ifdef CONFIG_RFS_ACCEL
-	if ((bp->flags & BNXT_FLAG_RFS) && bp->ntp_fltr_count) {
-		set_bit(BNXT_RX_NTP_FLTR_SP_EVENT, &bp->sp_event);
-		bnxt_queue_sp_work(bp);
-	}
+	if ((bp->flags & BNXT_FLAG_RFS) && bp->ntp_fltr_count)
+		bnxt_queue_sp_work(bp, BNXT_RX_NTP_FLTR_SP_EVENT);
 #endif /*CONFIG_RFS_ACCEL*/
 
 	if (bp->link_info.phy_retry) {
@@ -11675,21 +11694,17 @@ static void bnxt_timer(struct timer_list *t)
 			bp->link_info.phy_retry = false;
 			netdev_warn(bp->dev, "failed to update phy settings after maximum retries.\n");
 		} else {
-			set_bit(BNXT_UPDATE_PHY_SP_EVENT, &bp->sp_event);
-			bnxt_queue_sp_work(bp);
+			bnxt_queue_sp_work(bp, BNXT_UPDATE_PHY_SP_EVENT);
 		}
 	}
 
-	if (test_bit(BNXT_STATE_L2_FILTER_RETRY, &bp->state)) {
-		set_bit(BNXT_RX_MASK_SP_EVENT, &bp->sp_event);
-		bnxt_queue_sp_work(bp);
-	}
+	if (test_bit(BNXT_STATE_L2_FILTER_RETRY, &bp->state))
+		bnxt_queue_sp_work(bp, BNXT_RX_MASK_SP_EVENT);
 
 	if ((bp->flags & BNXT_FLAG_CHIP_P5) && !bp->chip_rev &&
-	    netif_carrier_ok(dev)) {
-		set_bit(BNXT_RING_COAL_NOW_SP_EVENT, &bp->sp_event);
-		bnxt_queue_sp_work(bp);
-	}
+	    netif_carrier_ok(dev))
+		bnxt_queue_sp_work(bp, BNXT_RING_COAL_NOW_SP_EVENT);
+
 bnxt_restart_timer:
 	mod_timer(&bp->timer, jiffies + bp->current_interval);
 }
@@ -12968,8 +12983,7 @@ static int bnxt_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 	bp->ntp_fltr_count++;
 	spin_unlock_bh(&bp->ntp_fltr_lock);
 
-	set_bit(BNXT_RX_NTP_FLTR_SP_EVENT, &bp->sp_event);
-	bnxt_queue_sp_work(bp);
+	bnxt_queue_sp_work(bp, BNXT_RX_NTP_FLTR_SP_EVENT);
 
 	return new_fltr->sw_id;
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 080e73496066..9d16757e27fe 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1008,6 +1008,7 @@ struct bnxt_napi {
 					  int);
 	int			tx_pkts;
 	u8			events;
+	u8			tx_fault:1;
 
 	u32			flags;
 #define BNXT_NAPI_FLAG_XDP	0x1
@@ -2329,6 +2330,8 @@ int bnxt_get_avail_msix(struct bnxt *bp, int num);
 int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init);
 void bnxt_tx_disable(struct bnxt *bp);
 void bnxt_tx_enable(struct bnxt *bp);
+void bnxt_sched_reset_txr(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
+			  int idx);
 void bnxt_report_link(struct bnxt *bp);
 int bnxt_update_link(struct bnxt *bp, bool chng_link_state);
 int bnxt_hwrm_set_pause(struct bnxt *);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 4efa5fe6972b..5b6fbdc4dc40 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -149,6 +149,7 @@ void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts)
 			tx_buf->action = 0;
 			tx_buf->xdpf = NULL;
 		} else if (tx_buf->action == XDP_TX) {
+			tx_buf->action = 0;
 			rx_doorbell_needed = true;
 			last_tx_cons = tx_cons;
 
@@ -158,6 +159,9 @@ void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts)
 				tx_buf = &txr->tx_buf_ring[tx_cons];
 				page_pool_recycle_direct(rxr->page_pool, tx_buf->page);
 			}
+		} else {
+			bnxt_sched_reset_txr(bp, txr, i);
+			return;
 		}
 		tx_cons = NEXT_TX(tx_cons);
 	}