openwrt/target/linux/generic/backport-5.15/729-21-v6.3-net-ethernet-mtk_eth_soc-add-dma-checks-to-mtk_hw_re.patch

From: Lorenzo Bianconi <[email protected]>
Date: Sat, 14 Jan 2023 18:01:31 +0100
Subject: [PATCH] net: ethernet: mtk_eth_soc: add dma checks to
 mtk_hw_reset_check

Introduce mtk_hw_check_dma_hang routine to monitor possible dma hangs.

Reviewed-by: Leon Romanovsky <[email protected]>
Tested-by: Daniel Golle <[email protected]>
Co-developed-by: Sujuan Chen <[email protected]>
Signed-off-by: Sujuan Chen <[email protected]>
Signed-off-by: Lorenzo Bianconi <[email protected]>
Signed-off-by: Paolo Abeni <[email protected]>
---

--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -50,6 +50,7 @@ static const struct mtk_reg_map mtk_reg_
 		.delay_irq	= 0x0a0c,
 		.irq_status	= 0x0a20,
 		.irq_mask	= 0x0a28,
+		.adma_rx_dbg0	= 0x0a38,
 		.int_grp	= 0x0a50,
 	},
 	.qdma = {
@@ -79,6 +80,8 @@ static const struct mtk_reg_map mtk_reg_
 		[0]		= 0x2800,
 		[1]		= 0x2c00,
 	},
+	.pse_iq_sta		= 0x0110,
+	.pse_oq_sta		= 0x0118,
 };
 
 static const struct mtk_reg_map mt7628_reg_map = {
@@ -109,6 +112,7 @@ static const struct mtk_reg_map mt7986_r
 		.delay_irq	= 0x620c,
 		.irq_status	= 0x6220,
 		.irq_mask	= 0x6228,
+		.adma_rx_dbg0	= 0x6238,
 		.int_grp	= 0x6250,
 	},
 	.qdma = {
@@ -138,6 +142,8 @@ static const struct mtk_reg_map mt7986_r
 		[0]		= 0x4800,
 		[1]		= 0x4c00,
 	},
+	.pse_iq_sta		= 0x0180,
+	.pse_oq_sta		= 0x01a0,
 };
 
 /* strings used by ethtool */
@@ -3285,6 +3291,102 @@ static void mtk_hw_warm_reset(struct mtk
 			val, rst_mask);
 }
 
+static bool mtk_hw_check_dma_hang(struct mtk_eth *eth)
+{
+	const struct mtk_reg_map *reg_map = eth->soc->reg_map;
+	bool gmac1_tx, gmac2_tx, gdm1_tx, gdm2_tx;
+	bool oq_hang, cdm1_busy, adma_busy;
+	bool wtx_busy, cdm_full, oq_free;
+	u32 wdidx, val, gdm1_fc, gdm2_fc;
+	bool qfsm_hang, qfwd_hang;
+	bool ret = false;
+
+	if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628))
+		return false;
+
+	/* WDMA sanity checks */
+	wdidx = mtk_r32(eth, reg_map->wdma_base[0] + 0xc);
+
+	val = mtk_r32(eth, reg_map->wdma_base[0] + 0x204);
+	wtx_busy = FIELD_GET(MTK_TX_DMA_BUSY, val);
+
+	val = mtk_r32(eth, reg_map->wdma_base[0] + 0x230);
+	cdm_full = !FIELD_GET(MTK_CDM_TXFIFO_RDY, val);
+
+	oq_free  = (!(mtk_r32(eth, reg_map->pse_oq_sta) & GENMASK(24, 16)) &&
+		    !(mtk_r32(eth, reg_map->pse_oq_sta + 0x4) & GENMASK(8, 0)) &&
+		    !(mtk_r32(eth, reg_map->pse_oq_sta + 0x10) & GENMASK(24, 16)));
+
+	if (wdidx == eth->reset.wdidx && wtx_busy && cdm_full && oq_free) {
+		if (++eth->reset.wdma_hang_count > 2) {
+			eth->reset.wdma_hang_count = 0;
+			ret = true;
+		}
+		goto out;
+	}
+
+	/* QDMA sanity checks */
+	qfsm_hang = !!mtk_r32(eth, reg_map->qdma.qtx_cfg + 0x234);
+	qfwd_hang = !mtk_r32(eth, reg_map->qdma.qtx_cfg + 0x308);
+
+	gdm1_tx = FIELD_GET(GENMASK(31, 16), mtk_r32(eth, MTK_FE_GDM1_FSM)) > 0;
+	gdm2_tx = FIELD_GET(GENMASK(31, 16), mtk_r32(eth, MTK_FE_GDM2_FSM)) > 0;
+	gmac1_tx = FIELD_GET(GENMASK(31, 24), mtk_r32(eth, MTK_MAC_FSM(0))) != 1;
+	gmac2_tx = FIELD_GET(GENMASK(31, 24), mtk_r32(eth, MTK_MAC_FSM(1))) != 1;
+	gdm1_fc = mtk_r32(eth, reg_map->gdm1_cnt + 0x24);
+	gdm2_fc = mtk_r32(eth, reg_map->gdm1_cnt + 0x64);
+
+	if (qfsm_hang && qfwd_hang &&
+	    ((gdm1_tx && gmac1_tx && gdm1_fc < 1) ||
+	     (gdm2_tx && gmac2_tx && gdm2_fc < 1))) {
+		if (++eth->reset.qdma_hang_count > 2) {
+			eth->reset.qdma_hang_count = 0;
+			ret = true;
+		}
+		goto out;
+	}
+
+	/* ADMA sanity checks */
+	oq_hang = !!(mtk_r32(eth, reg_map->pse_oq_sta) & GENMASK(8, 0));
+	cdm1_busy = !!(mtk_r32(eth, MTK_FE_CDM1_FSM) & GENMASK(31, 16));
+	adma_busy = !(mtk_r32(eth, reg_map->pdma.adma_rx_dbg0) & GENMASK(4, 0)) &&
+		    !(mtk_r32(eth, reg_map->pdma.adma_rx_dbg0) & BIT(6));
+
+	if (oq_hang && cdm1_busy && adma_busy) {
+		if (++eth->reset.adma_hang_count > 2) {
+			eth->reset.adma_hang_count = 0;
+			ret = true;
+		}
+		goto out;
+	}
+
+	eth->reset.wdma_hang_count = 0;
+	eth->reset.qdma_hang_count = 0;
+	eth->reset.adma_hang_count = 0;
+out:
+	eth->reset.wdidx = wdidx;
+
+	return ret;
+}
+
+static void mtk_hw_reset_monitor_work(struct work_struct *work)
+{
+	struct delayed_work *del_work = to_delayed_work(work);
+	struct mtk_eth *eth = container_of(del_work, struct mtk_eth,
+					   reset.monitor_work);
+
+	if (test_bit(MTK_RESETTING, &eth->state))
+		goto out;
+
+	/* DMA stuck checks */
+	if (mtk_hw_check_dma_hang(eth))
+		schedule_work(&eth->pending_work);
+
+out:
+	schedule_delayed_work(&eth->reset.monitor_work,
+			      MTK_DMA_MONITOR_TIMEOUT);
+}
+
 static int mtk_hw_init(struct mtk_eth *eth, bool reset)
 {
 	u32 dma_mask = ETHSYS_DMA_AG_MAP_PDMA | ETHSYS_DMA_AG_MAP_QDMA |
@@ -3600,6 +3702,7 @@ static int mtk_cleanup(struct mtk_eth *e
 	mtk_unreg_dev(eth);
 	mtk_free_dev(eth);
 	cancel_work_sync(&eth->pending_work);
+	cancel_delayed_work_sync(&eth->reset.monitor_work);
 
 	return 0;
 }
@@ -4037,6 +4140,7 @@ static int mtk_probe(struct platform_dev
 
 	eth->rx_dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
 	INIT_WORK(&eth->rx_dim.work, mtk_dim_rx);
+	INIT_DELAYED_WORK(&eth->reset.monitor_work, mtk_hw_reset_monitor_work);
 
 	eth->tx_dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
 	INIT_WORK(&eth->tx_dim.work, mtk_dim_tx);
@@ -4241,6 +4345,8 @@ static int mtk_probe(struct platform_dev
 		       NAPI_POLL_WEIGHT);
 
 	platform_set_drvdata(pdev, eth);
+	schedule_delayed_work(&eth->reset.monitor_work,
+			      MTK_DMA_MONITOR_TIMEOUT);
 
 	return 0;
 
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -256,6 +256,8 @@
 
 #define MTK_RX_DONE_INT_V2	BIT(14)
 
+#define MTK_CDM_TXFIFO_RDY	BIT(7)
+
 /* QDMA Interrupt grouping registers */
 #define MTK_RLS_DONE_INT	BIT(0)
 
@@ -538,6 +540,17 @@
 #define MT7628_SDM_RBCNT	(MT7628_SDM_OFFSET + 0x10c)
 #define MT7628_SDM_CS_ERR	(MT7628_SDM_OFFSET + 0x110)
 
+#define MTK_FE_CDM1_FSM		0x220
+#define MTK_FE_CDM2_FSM		0x224
+#define MTK_FE_CDM3_FSM		0x238
+#define MTK_FE_CDM4_FSM		0x298
+#define MTK_FE_CDM5_FSM		0x318
+#define MTK_FE_CDM6_FSM		0x328
+#define MTK_FE_GDM1_FSM		0x228
+#define MTK_FE_GDM2_FSM		0x22C
+
+#define MTK_MAC_FSM(x)		(0x1010C + ((x) * 0x100))
+
 struct mtk_rx_dma {
 	unsigned int rxd1;
 	unsigned int rxd2;
@@ -934,6 +947,7 @@ struct mtk_reg_map {
 		u32	delay_irq;	/* delay interrupt */
 		u32	irq_status;	/* interrupt status */
 		u32	irq_mask;	/* interrupt mask */
+		u32	adma_rx_dbg0;
 		u32	int_grp;
 	} pdma;
 	struct {
@@ -960,6 +974,8 @@ struct mtk_reg_map {
 	u32	gdma_to_ppe0;
 	u32	ppe_base;
 	u32	wdma_base[2];
+	u32	pse_iq_sta;
+	u32	pse_oq_sta;
 };
 
 /* struct mtk_eth_data -	This is the structure holding all differences
@@ -1002,6 +1018,8 @@ struct mtk_soc_data {
 	} txrx;
 };
 
+#define MTK_DMA_MONITOR_TIMEOUT		msecs_to_jiffies(1000)
+
 /* currently no SoC has more than 2 macs */
 #define MTK_MAX_DEVS			2
 
@@ -1124,6 +1142,14 @@ struct mtk_eth {
 	struct rhashtable		flow_table;
 
 	struct bpf_prog			__rcu *prog;
+
+	struct {
+		struct delayed_work monitor_work;
+		u32 wdidx;
+		u8 wdma_hang_count;
+		u8 qdma_hang_count;
+		u8 adma_hang_count;
+	} reset;
 };
 
 /* struct mtk_mac -	the structure that holds the info about the MACs of the