Thread (5 messages) 5 messages, 2 authors, 2d ago

[PATCH net v3 1/2] net: bcmgenet: recover from a failed resume

flat view
WARM2d

From: Nicolai Buchwitz <nb@tipi-net.de>
Date: 2026-10-22 08:54:17
Also in: lkml
Subsystem: broadcom genet ethernet driver, networking drivers, the rest · Maintainers: Doug Berger, Florian Fainelli, Nicolai Buchwitz, Andrew Lunn, "David S. Miller", Eric Dumazet, Jakub Kicinski, Paolo Abeni, Linus Torvalds

Revision v3 of 3 in this series.

Revisions (3)
  1. v1 [diff vs current]
  2. v2 [diff vs current]
  3. v3 current
A resume that fails in bcmgenet_init_dma() returns with the interface
still IFF_UP and the datapath gone. The next ifdown runs the teardown
a second time and napi_disable() waits for a NAPI_STATE_SCHED bit that
nothing will clear:

  task:ip  state:D
    usleep_range_state+0xec/0x158
    napi_disable_locked+0x254/0x318
    napi_disable+0x3c/0x68
    bcmgenet_netif_stop+0x1c8/0x318
    bcmgenet_close+0x24/0xd0
    __dev_close_many+0x18c/0x310

RTNL is held across the wait, so everything else blocks behind it.

The same resume gates the clock and detaches the device. Close releases
the clock a second time and ifup fails with -ENODEV. The hardware filters
stay armed, so the next WoL suspend wakes on any frame. That suspend sets
CMD_RX_EN for magic packet detection, so the WoL resume reuses rings that
are gone.

A failed resume should leave a state the ordinary paths can handle. Clear
rx_cbs and tx_cbs as they are freed so they answer whether a datapath
exists, and leave the clock alone so close and suspend release it once.
The WoL resume rebuilds instead, so stop the PHY first, phy_start() only
takes PHY_READY or PHY_HALTED.

Flagged in a sashiko review and reproduced on a CM4 by forcing the resume
allocation to fail.

Fixes: b6e978e50444 ("net: bcmgenet: add suspend/resume callbacks")
Fixes: 254f3239dd07 ("net: bcmgenet: revise suspend/resume")	# for the WoL parts
Signed-off-by: Nicolai Buchwitz <nb@tipi-net.de>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 92 +++++++++++++++++---------
 1 file changed, 62 insertions(+), 30 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index f4cfbff49a1b8..e7dec73d5b1c0 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -3117,7 +3117,9 @@ static void bcmgenet_fini_dma(struct bcmgenet_priv *priv)
 	bcmgenet_free_rx_buffers(priv);
 	bcmgenet_destroy_rx_page_pools(priv);
 	kfree(priv->rx_cbs);
+	priv->rx_cbs = NULL;
 	kfree(priv->tx_cbs);
+	priv->tx_cbs = NULL;
 }
 
 /* init_edma: Initialize DMA control register */
@@ -3175,6 +3177,7 @@ static int bcmgenet_init_dma(struct bcmgenet_priv *priv, bool flush_rx)
 	priv->tx_cbs = kzalloc_objs(struct enet_cb, priv->num_tx_bds);
 	if (!priv->tx_cbs) {
 		kfree(priv->rx_cbs);
+		priv->rx_cbs = NULL;
 		return -ENOMEM;
 	}
 
@@ -3194,7 +3197,9 @@ static int bcmgenet_init_dma(struct bcmgenet_priv *priv, bool flush_rx)
 		bcmgenet_free_rx_buffers(priv);
 		bcmgenet_destroy_rx_page_pools(priv);
 		kfree(priv->rx_cbs);
+		priv->rx_cbs = NULL;
 		kfree(priv->tx_cbs);
+		priv->tx_cbs = NULL;
 		return ret;
 	}
 
@@ -3503,7 +3508,9 @@ static int bcmgenet_close(struct net_device *dev)
 
 	netif_dbg(priv, ifdown, dev, "bcmgenet_close\n");
 
-	bcmgenet_netif_stop(dev, false);
+	/* A failed resume has torn the datapath down already */
+	if (priv->tx_cbs)
+		bcmgenet_netif_stop(dev, false);
 
 	/* Really kill the PHY state machine and disconnect from it */
 	phy_disconnect(dev->phydev);
@@ -3511,6 +3518,9 @@ static int bcmgenet_close(struct net_device *dev)
 	free_irq(priv->irq0, priv);
 	free_irq(priv->irq1, priv);
 
+	/* A failed resume left the device detached, __dev_open() refuses that */
+	netif_device_attach(dev);
+
 	if (priv->internal_phy)
 		ret = bcmgenet_power_down(priv, GENET_POWER_PASSIVE);
 
@@ -4268,7 +4278,11 @@ static int bcmgenet_resume(struct device *d)
 
 	if (device_may_wakeup(d) && priv->wolopts) {
 		reg = bcmgenet_umac_readl(priv, UMAC_CMD);
-		if (reg & CMD_RX_EN) {
+
+		/* The WoL power down sets CMD_RX_EN itself, so the bit
+		 * alone does not mean the rings survived
+		 */
+		if (priv->tx_cbs && (reg & CMD_RX_EN)) {
 			/* Successfully exited WoL, just resume data flows */
 			list_for_each_entry(rule, &priv->rxnfc_list, list)
 				if (rule->state == BCMGENET_RXNFC_STATE_ENABLED)
@@ -4298,6 +4312,9 @@ static int bcmgenet_resume(struct device *d)
 		bcmgenet_rdma_disable(priv);
 		bcmgenet_intr_disable(priv);
 		bcmgenet_fini_dma(priv);
+		if (phy_is_started(dev->phydev) ||
+		    dev->phydev->state == PHY_ERROR)
+			phy_stop(dev->phydev);
 		enable_irq(priv->irq1);
 	}
 
@@ -4320,8 +4337,9 @@ static int bcmgenet_resume(struct device *d)
 	/* Reinitialize TDMA and RDMA and SW housekeeping */
 	ret = bcmgenet_init_dma(priv, false);
 	if (ret) {
+		/* Leave the block clocked, close and suspend tear it down */
 		netdev_err(dev, "failed to initialize DMA\n");
-		goto out_clk_disable;
+		return ret;
 	}
 
 	if (!device_may_wakeup(d))
@@ -4332,24 +4350,57 @@ static int bcmgenet_resume(struct device *d)
 	netif_device_attach(dev);
 
 	return 0;
+}
 
-out_clk_disable:
-	if (priv->internal_phy)
-		bcmgenet_power_down(priv, GENET_POWER_PASSIVE);
-	clk_disable_unprepare(priv->clk);
-	return ret;
+/* Arm the configured wake filters and drop the rest, then clear old
+ * matches so that only a new one wakes the system
+ */
+static void bcmgenet_wol_arm_filters(struct bcmgenet_priv *priv)
+{
+	struct bcmgenet_rxnfc_rule *rule;
+	u32 reg, hfb_enable = 0;
+
+	if (priv->wolopts & WAKE_FILTER)
+		list_for_each_entry(rule, &priv->rxnfc_list, list)
+			if (rule->fs.ring_cookie == RX_CLS_FLOW_WAKE &&
+			    rule->state == BCMGENET_RXNFC_STATE_ENABLED)
+				hfb_enable |= 1 << rule->fs.location;
+
+	reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
+	if (GENET_IS_V1(priv) || GENET_IS_V2(priv)) {
+		reg &= ~RBUF_HFB_FILTER_EN_MASK;
+		reg |= hfb_enable << (RBUF_HFB_FILTER_EN_SHIFT + 1);
+	} else {
+		bcmgenet_hfb_reg_writel(priv, hfb_enable << 1,
+					HFB_FLT_ENABLE_V3PLUS + 4);
+	}
+	if (!hfb_enable)
+		reg &= ~RBUF_HFB_EN;
+	bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
+
+	bcmgenet_intrl2_0_writel(priv, 0xFFFFFFFF, INTRL2_CPU_MASK_SET);
+	bcmgenet_intrl2_0_writel(priv, 0xFFFFFFFF, INTRL2_CPU_CLEAR);
 }
 
 static int bcmgenet_suspend(struct device *d)
 {
 	struct net_device *dev = dev_get_drvdata(d);
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	struct bcmgenet_rxnfc_rule *rule;
-	u32 reg, hfb_enable = 0;
 
 	if (!netif_running(dev))
 		return 0;
 
+	/* A failed resume has torn the datapath down already. Resume still
+	 * enables irq1 on the WoL path, so it has to be disabled here.
+	 */
+	if (!priv->tx_cbs) {
+		if (device_may_wakeup(d) && priv->wolopts) {
+			bcmgenet_wol_arm_filters(priv);
+			disable_irq(priv->irq1);
+		}
+		return 0;
+	}
+
 	netif_device_detach(dev);
 
 	if (device_may_wakeup(d) && priv->wolopts) {
@@ -4358,26 +4409,7 @@ static int bcmgenet_suspend(struct device *d)
 		netif_tx_disable(dev);
 
 		/* Suspend non-wake Rx data flows */
-		if (priv->wolopts & WAKE_FILTER)
-			list_for_each_entry(rule, &priv->rxnfc_list, list)
-				if (rule->fs.ring_cookie == RX_CLS_FLOW_WAKE &&
-				    rule->state == BCMGENET_RXNFC_STATE_ENABLED)
-					hfb_enable |= 1 << rule->fs.location;
-		reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
-		if (GENET_IS_V1(priv) || GENET_IS_V2(priv)) {
-			reg &= ~RBUF_HFB_FILTER_EN_MASK;
-			reg |= hfb_enable << (RBUF_HFB_FILTER_EN_SHIFT + 1);
-		} else {
-			bcmgenet_hfb_reg_writel(priv, hfb_enable << 1,
-						HFB_FLT_ENABLE_V3PLUS + 4);
-		}
-		if (!hfb_enable)
-			reg &= ~RBUF_HFB_EN;
-		bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
-
-		/* Clear any old filter matches so only new matches wake */
-		bcmgenet_intrl2_0_writel(priv, 0xFFFFFFFF, INTRL2_CPU_MASK_SET);
-		bcmgenet_intrl2_0_writel(priv, 0xFFFFFFFF, INTRL2_CPU_CLEAR);
+		bcmgenet_wol_arm_filters(priv);
 
 		if (-ETIMEDOUT == bcmgenet_tdma_disable(priv))
 			netdev_warn(priv->dev,
-- 
2.53.0
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help