[PATCH v2 6/7] net: ravb: fix resource teardown ordering

[Jiale Yao]

ravb_remove() frees the netdev before devres releases the managed IRQs.
The handlers use the netdev as their data pointer, so an interrupt during
that window can access freed memory. Probe error paths have the same
ordering problem.

The remove callback also returns when runtime resume fails. That leaves
the netdev registered while the driver core still releases its managed
resources. A running interface already holds a runtime PM reference, so
the extra get cannot invoke a failing resume. A resume failure therefore
occurs while the interface is down and ndo_stop() will not be called.

Place the IRQ resources in a dedicated devres group and release it before
freeing the netdev. Continue unregistering and freeing software resources
when runtime resume fails, but skip the unmatched runtime PM put.

Fixes: c156633f1353 ("Renesas Ethernet AVB driver proper")
Fixes: 48f894ab07c4 ("net: ravb: Add runtime PM support")
Cc: stable@xxxxxxxxxxxxxxx
Signed-off-by: Jiale Yao <yaojiale02@xxxxxxx>
---
 drivers/net/ethernet/renesas/ravb_main.c | 23 +++++++++++++++++------
 1 file changed, 17 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index ea1c7e536791..a25f5ac7062f 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -2963,28 +2963,35 @@ static int ravb_probe(struct platform_device *pdev)
 		priv->num_rx_ring[RAVB_NC] = NC_RX_RING_SIZE;
 	}
 
+	if (!devres_open_group(&pdev->dev, priv, GFP_KERNEL)) {
+		error = -ENOMEM;
+		goto out_reset_assert;
+	}
+
 	error = ravb_setup_irqs(priv);
 	if (error)
-		goto out_reset_assert;
+		goto out_release_irqs;
+
+	devres_close_group(&pdev->dev, priv);
 
 	priv->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(priv->clk)) {
 		error = PTR_ERR(priv->clk);
-		goto out_reset_assert;
+		goto out_release_irqs;
 	}
 
 	if (info->gptp_ref_clk) {
 		priv->gptp_clk = devm_clk_get(&pdev->dev, "gptp");
 		if (IS_ERR(priv->gptp_clk)) {
 			error = PTR_ERR(priv->gptp_clk);
-			goto out_reset_assert;
+			goto out_release_irqs;
 		}
 	}
 
 	priv->refclk = devm_clk_get_optional(&pdev->dev, "refclk");
 	if (IS_ERR(priv->refclk)) {
 		error = PTR_ERR(priv->refclk);
-		goto out_reset_assert;
+		goto out_release_irqs;
 	}
 	clk_prepare(priv->refclk);
 
@@ -3124,6 +3131,8 @@ static int ravb_probe(struct platform_device *pdev)
 	pm_runtime_disable(&pdev->dev);
 	pm_runtime_dont_use_autosuspend(&pdev->dev);
 	clk_unprepare(priv->refclk);
+out_release_irqs:
+	devres_release_group(&pdev->dev, priv);
 out_reset_assert:
 	reset_control_assert(rstc);
 out_free_netdev:
@@ -3141,9 +3150,10 @@ static void ravb_remove(struct platform_device *pdev)
 
 	error = pm_runtime_resume_and_get(dev);
 	if (error < 0)
-		return;
+		dev_warn(dev, "failed to resume device: %d\n", error);
 
 	unregister_netdev(ndev);
+	devres_release_group(dev, priv);
 	if (info->nc_queues)
 		netif_napi_del(&priv->napi[RAVB_NC]);
 	netif_napi_del(&priv->napi[RAVB_BE]);
@@ -3153,7 +3163,8 @@ static void ravb_remove(struct platform_device *pdev)
 	dma_free_coherent(ndev->dev.parent, priv->desc_bat_size, priv->desc_bat,
 			  priv->desc_bat_dma);
 
-	pm_runtime_put_sync_suspend(&pdev->dev);
+	if (error >= 0)
+		pm_runtime_put_sync_suspend(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 	pm_runtime_dont_use_autosuspend(dev);
 	clk_unprepare(priv->refclk);
-- 
2.34.1