realtek: avoid interrupt storm on mass packet receive

RTL83xx devices have two types of receive interrupts for each of its
8 rings. One for packet received and another for ring overflow. When
the switch is flooded with incoming packets the receive handler will
disable the packet receive notification but still keeps the overflow
notification enabled. While the receive path "slowly" processes the
received packets each new packet triggers the overflow IRQ again. The
device becomes unresponsive and eventually produces messages like:

[18441.709764] rcu: Stack dump where RCU GP kthread last ran:
[18441.727892] Sending NMI from CPU 1 to CPUs 0:
[18441.742300] NMI backtrace for cpu 0 skipped: idling at 0x8080e994
[18415.251700] rcu: INFO: rcu_sched detected stalls on CPUs/tasks:
[18415.271350] rcu:     0-...!: (0 ticks this GP) idle=d740/0/0x0 ...
[18415.303046] rcu:     (detected by 1, t=6004 jiffies, g=230925, ...
[18415.326095] Sending NMI from CPU 1 to CPUs 0:
[18415.340540] NMI backtrace for cpu 0

Fix this issue by always disabling receive and overflow interrupts at
the same time.

Test with hping3 --udp -p 5021 -d 1400 --flood 192.168.2.72

Before (3sec run):
[183260.324846] rtl838x-eth 1b00a300.ethernet eth0: RX buffer overrun: status 0x101, mask: 0x7ffeff
[183260.340524] rtl838x-eth 1b00a300.ethernet eth0: RX buffer overrun: status 0x1, mask: 0x7ffeff
[183260.345799] net_ratelimit: 489997 callbacks suppressed

After (3 sec run):
[  373.981479] rtl838x-eth 1b00a300.ethernet eth0: rx ring overrun: status 0x101, mask: 0x7fffff
[  374.031118] rtl838x-eth 1b00a300.ethernet eth0: rx ring overrun: status 0x101, mask: 0x7fffff
[  377.919996] net_ratelimit: 34 callbacks suppressed

Signed-off-by: Markus Stockhausen <[email protected]>
Link: https://github.com/openwrt/openwrt/pull/19365
(cherry picked from commit 963ee6ac3fc287328ce5a1e49d7f5910b060ec96)
Signed-off-by: Felix Baumann <[email protected]>
Link: https://github.com/openwrt/openwrt/pull/19891
Signed-off-by: Hauke Mehrtens <[email protected]>

target/linux/realtek/files-6.6/drivers/net/ethernet/rtl838x_eth.c

@@ -436,28 +436,25 @@ static irqreturn_t rtl83xx_net_irq(int irq, void *dev_id)
 	struct net_device *ndev = dev_id;
 	struct rtl838x_eth_priv *priv = netdev_priv(ndev);
 	u32 status = sw_r32(priv->r->dma_if_intr_sts);
+	unsigned long ring, rings;
 
-	netdev_dbg(ndev, "RX IRQ received: %08x\n", status);
+	netdev_dbg(ndev, "rx interrupt received, status %08x\n", status);
 
-	if ((status & RTL83XX_DMA_IF_INTR_STS_RX_RUN_OUT_MASK) && net_ratelimit())
-		netdev_warn(ndev, "RX buffer overrun: status 0x%x, mask: 0x%x\n",
-			   status, sw_r32(priv->r->dma_if_intr_msk));
+	if (status & RTL83XX_DMA_IF_INTR_RX_RUN_OUT_MASK)
+		if (net_ratelimit())
+			netdev_warn(ndev, "rx ring overrun, status 0x%08x, mask 0x%08x\n",
+				    status, sw_r32(priv->r->dma_if_intr_msk));
 
-	if (status & RTL83XX_DMA_IF_INTR_STS_RX_DONE_MASK) {
-		/* Disable rx interrupts */
-		sw_w32_mask(0xff00 & status, 0, priv->r->dma_if_intr_msk);
-		for (int i = 0; i < priv->rxrings; i++) {
-			if (status & BIT(i + 8)) {
-				pr_debug("Scheduling queue: %d\n", i);
-				napi_schedule(&priv->rx_qs[i].napi);
-			}
-		}
+	rings = FIELD_GET(RTL83XX_DMA_IF_INTR_RX_DONE_MASK, status);
+	for_each_set_bit(ring, &rings, priv->rxrings) {
+		netdev_dbg(ndev, "schedule rx ring %lu\n", ring);
+		sw_w32_mask(RTL83XX_DMA_IF_INTR_RX_MASK(ring), 0, priv->r->dma_if_intr_msk);
+		napi_schedule(&priv->rx_qs[ring].napi);
 	}
 
-	if ((status & RTL83XX_DMA_IF_INTR_STS_NOTIFY_MASK) && priv->family_id == RTL8390_FAMILY_ID)
+	if (status & RTL839X_DMA_IF_INTR_NOTIFY_MASK)
 		rtl839x_l2_notification_handler(priv);
 
-	/* Acknowledge all interrupts */
 	sw_w32(status, priv->r->dma_if_intr_sts);
 
 	return IRQ_HANDLED;
@@ -1337,25 +1334,22 @@ static int rtl838x_poll_rx(struct napi_struct *napi, int budget)
 {
 	struct rtl838x_rx_q *rx_q = container_of(napi, struct rtl838x_rx_q, napi);
 	struct rtl838x_eth_priv *priv = rx_q->priv;
+	int ring = rx_q->id;
 	int work_done = 0;
-	int r = rx_q->id;
-	int work;
 
 	while (work_done < budget) {
-		work = rtl838x_hw_receive(priv->netdev, r, budget - work_done);
+		int work = rtl838x_hw_receive(priv->netdev, ring, budget - work_done);
 		if (!work)
 			break;
 		work_done += work;
 	}
 
-	if (work_done < budget) {
-		napi_complete_done(napi, work_done);
-
-		/* Enable RX interrupt */
+	if (work_done < budget && napi_complete_done(napi, work_done)) {
+		/* Re-enable rx interrupts */
 		if (priv->family_id == RTL9300_FAMILY_ID || priv->family_id == RTL9310_FAMILY_ID)
 			sw_w32(0xffffffff, priv->r->dma_if_intr_rx_done_msk);
 		else
-			sw_w32_mask(0, 0xf00ff | BIT(r + 8), priv->r->dma_if_intr_msk);
+			sw_w32_mask(0, RTL83XX_DMA_IF_INTR_RX_MASK(ring), priv->r->dma_if_intr_msk);
 	}
 
 	return work_done;

target/linux/realtek/files-6.6/drivers/net/ethernet/rtl838x_eth.h

@@ -48,9 +48,10 @@
 #define RTL930X_MAC_FORCE_MODE_CTRL		(0xCA1C)
 #define RTL931X_MAC_FORCE_MODE_CTRL		(0x0ddc)
 
-#define RTL83XX_DMA_IF_INTR_STS_NOTIFY_MASK	GENMASK(22, 20)
-#define RTL83XX_DMA_IF_INTR_STS_RX_DONE_MASK	GENMASK(15, 8)
-#define RTL83XX_DMA_IF_INTR_STS_RX_RUN_OUT_MASK	GENMASK(7, 0)
+#define RTL839X_DMA_IF_INTR_NOTIFY_MASK		GENMASK(22, 20)
+#define RTL83XX_DMA_IF_INTR_RX_DONE_MASK	GENMASK(15, 8)
+#define RTL83XX_DMA_IF_INTR_RX_RUN_OUT_MASK	GENMASK(7, 0)
+#define RTL83XX_DMA_IF_INTR_RX_MASK(ring)	(BIT(ring) | BIT(ring + 8))
 
 /* MAC address settings */
 #define RTL838X_MAC				(0xa9ec)