public inbox for netdev@vger.kernel.org
 help / color / mirror / Atom feed
From: Jiawen Wu <jiawenwu@trustnetic.com>
To: netdev@vger.kernel.org
Cc: Mengyuan Lou <mengyuanlou@net-swift.com>,
	Andrew Lunn <andrew+netdev@lunn.ch>,
	"David S. Miller" <davem@davemloft.net>,
	Eric Dumazet <edumazet@google.com>,
	Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
	Richard Cochran <richardcochran@gmail.com>,
	Russell King <linux@armlinux.org.uk>,
	Simon Horman <horms@kernel.org>, Kees Cook <kees@kernel.org>,
	Larysa Zaremba <larysa.zaremba@intel.com>,
	Breno Leitao <leitao@debian.org>, Joe Damato <joe@dama.to>,
	Jacob Keller <jacob.e.keller@intel.com>,
	Fabio Baltieri <fabio.baltieri@gmail.com>,
	Jiawen Wu <jiawenwu@trustnetic.com>
Subject: [RFC PATCH net-next 5/5] net: wangxun: implement pci_error_handlers ops
Date: Wed, 22 Apr 2026 17:56:17 +0800	[thread overview]
Message-ID: <20260422095617.27080-6-jiawenwu@trustnetic.com> (raw)
In-Reply-To: <20260422095617.27080-1-jiawenwu@trustnetic.com>

Support AER driver to handle the PCIe errors.

Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
---
 drivers/net/ethernet/wangxun/libwx/wx_err.c   | 107 ++++++++++++++++++
 drivers/net/ethernet/wangxun/libwx/wx_err.h   |   2 +
 drivers/net/ethernet/wangxun/libwx/wx_type.h  |   1 +
 drivers/net/ethernet/wangxun/ngbe/ngbe_main.c |   9 +-
 .../net/ethernet/wangxun/txgbe/txgbe_main.c   |   5 +-
 5 files changed, 121 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/wangxun/libwx/wx_err.c b/drivers/net/ethernet/wangxun/libwx/wx_err.c
index e7c9dcb148b5..1aefae402c8e 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_err.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_err.c
@@ -3,11 +3,118 @@
 
 #include <linux/netdevice.h>
 #include <linux/pci.h>
+#include <linux/aer.h>
 
 #include "wx_type.h"
 #include "wx_lib.h"
 #include "wx_err.h"
 
+/**
+ * wx_io_error_detected - called when PCI error is detected
+ * @pdev: Pointer to PCI device
+ * @state: The current pci connection state
+ *
+ * Return: pci_ers_result_t.
+ *
+ * This function is called after a PCI bus error affecting
+ * this device has been detected.
+ */
+static pci_ers_result_t wx_io_error_detected(struct pci_dev *pdev,
+					     pci_channel_state_t state)
+{
+	struct wx *wx = pci_get_drvdata(pdev);
+	struct net_device *netdev;
+
+	netdev = wx->netdev;
+	if (!netif_device_present(netdev))
+		return PCI_ERS_RESULT_DISCONNECT;
+
+	rtnl_lock();
+	netif_device_detach(netdev);
+
+	if (netif_running(netdev))
+		wx->close_suspend(wx);
+
+	if (state == pci_channel_io_perm_failure) {
+		rtnl_unlock();
+		return PCI_ERS_RESULT_DISCONNECT;
+	}
+
+	if (!test_and_set_bit(WX_STATE_DISABLED, wx->state))
+		pci_disable_device(pdev);
+	rtnl_unlock();
+
+	/* Request a slot reset. */
+	return PCI_ERS_RESULT_NEED_RESET;
+}
+
+/**
+ * wx_io_slot_reset - called after the pci bus has been reset.
+ * @pdev: Pointer to PCI device
+ *
+ * Return: pci_ers_result_t.
+ *
+ * Restart the card from scratch, as if from a cold-boot.
+ */
+static pci_ers_result_t wx_io_slot_reset(struct pci_dev *pdev)
+{
+	struct wx *wx = pci_get_drvdata(pdev);
+	pci_ers_result_t result;
+
+	if (pci_enable_device_mem(pdev)) {
+		wx_err(wx, "Cannot re-enable PCI device after reset.\n");
+		result = PCI_ERS_RESULT_DISCONNECT;
+	} else {
+		/* make all bar access done before reset. */
+		smp_mb__before_atomic();
+		clear_bit(WX_STATE_DISABLED, wx->state);
+		pci_set_master(pdev);
+		pci_restore_state(pdev);
+		pci_wake_from_d3(pdev, false);
+
+		wx->do_reset(wx->netdev, false);
+		result = PCI_ERS_RESULT_RECOVERED;
+	}
+
+	pci_aer_clear_nonfatal_status(pdev);
+
+	return result;
+}
+
+/**
+ * wx_io_resume - called when traffic can start flowing again.
+ * @pdev: Pointer to PCI device
+ *
+ * This callback is called when the error recovery driver tells us that
+ * its OK to resume normal operation.
+ */
+static void wx_io_resume(struct pci_dev *pdev)
+{
+	struct wx *wx = pci_get_drvdata(pdev);
+	struct net_device *netdev;
+	int err;
+
+	netdev = wx->netdev;
+	rtnl_lock();
+	if (netif_running(netdev)) {
+		err = netdev->netdev_ops->ndo_open(netdev);
+		if (err) {
+			wx_err(wx, "Failed to open netdev after reset\n");
+			goto out;
+		}
+	}
+	netif_device_attach(netdev);
+out:
+	rtnl_unlock();
+}
+
+const struct pci_error_handlers wx_err_handler = {
+	.error_detected = wx_io_error_detected,
+	.slot_reset = wx_io_slot_reset,
+	.resume = wx_io_resume,
+};
+EXPORT_SYMBOL(wx_err_handler);
+
 static void wx_reset_subtask(struct wx *wx)
 {
 	if (!test_bit(WX_FLAG_NEED_PF_RESET, wx->flags))
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_err.h b/drivers/net/ethernet/wangxun/libwx/wx_err.h
index e317e6c8d928..8b1a7863b5b1 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_err.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_err.h
@@ -7,6 +7,8 @@
 #ifndef _WX_ERR_H_
 #define _WX_ERR_H_
 
+extern const struct pci_error_handlers wx_err_handler;
+
 void wx_handle_errors_subtask(struct wx *wx);
 void wx_tx_timeout(struct net_device *netdev, unsigned int txqueue);
 void wx_handle_tx_hang(struct wx_ring *tx_ring, unsigned int next);
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h
index 4b72835ddec1..81e12609d3fa 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_type.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h
@@ -1215,6 +1215,7 @@ enum wx_state {
 	WX_STATE_PTP_RUNNING,
 	WX_STATE_PTP_TX_IN_PROGRESS,
 	WX_STATE_SERVICE_SCHED,
+	WX_STATE_DISABLED,
 	WX_STATE_NBITS		/* must be last */
 };
 
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
index bd6c0c9c51ba..a174605d1105 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
@@ -570,7 +570,8 @@ static void ngbe_dev_shutdown(struct pci_dev *pdev, bool *enable_wake)
 	*enable_wake = !!wufc;
 	wx_control_hw(wx, false);
 
-	pci_disable_device(pdev);
+	if (!test_and_set_bit(WX_STATE_DISABLED, wx->state))
+		pci_disable_device(pdev);
 }
 
 static void ngbe_shutdown(struct pci_dev *pdev)
@@ -856,6 +857,7 @@ static int ngbe_probe(struct pci_dev *pdev,
 		goto err_register;
 
 	pci_set_drvdata(pdev, wx);
+	pci_save_state(pdev);
 
 	return 0;
 
@@ -907,7 +909,8 @@ static void ngbe_remove(struct pci_dev *pdev)
 	kfree(wx->mac_table);
 	wx_clear_interrupt_scheme(wx);
 
-	pci_disable_device(pdev);
+	if (!test_and_set_bit(WX_STATE_DISABLED, wx->state))
+		pci_disable_device(pdev);
 }
 
 static int ngbe_suspend(struct pci_dev *pdev, pm_message_t state)
@@ -934,6 +937,7 @@ static int ngbe_resume(struct pci_dev *pdev)
 		wx_err(wx, "Cannot enable PCI device from suspend\n");
 		return err;
 	}
+	clear_bit(WX_STATE_DISABLED, wx->state);
 	pci_set_master(pdev);
 	device_wakeup_disable(&pdev->dev);
 
@@ -958,6 +962,7 @@ static struct pci_driver ngbe_driver = {
 	.resume   = ngbe_resume,
 	.shutdown = ngbe_shutdown,
 	.sriov_configure = wx_pci_sriov_configure,
+	.err_handler = &wx_err_handler,
 };
 
 module_pci_driver(ngbe_driver);
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
index 20969dd7d47a..56e8482c1896 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
@@ -899,6 +899,7 @@ static int txgbe_probe(struct pci_dev *pdev,
 		goto err_remove_phy;
 
 	pci_set_drvdata(pdev, wx);
+	pci_save_state(pdev);
 
 	netif_tx_stop_all_queues(netdev);
 
@@ -969,7 +970,8 @@ static void txgbe_remove(struct pci_dev *pdev)
 	kfree(wx->mac_table);
 	wx_clear_interrupt_scheme(wx);
 
-	pci_disable_device(pdev);
+	if (!test_and_set_bit(WX_STATE_DISABLED, wx->state))
+		pci_disable_device(pdev);
 }
 
 static struct pci_driver txgbe_driver = {
@@ -979,6 +981,7 @@ static struct pci_driver txgbe_driver = {
 	.remove   = txgbe_remove,
 	.shutdown = txgbe_shutdown,
 	.sriov_configure = wx_pci_sriov_configure,
+	.err_handler = &wx_err_handler,
 };
 
 module_pci_driver(txgbe_driver);
-- 
2.51.0


      parent reply	other threads:[~2026-04-22  9:57 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-04-22  9:56 [RFC PATCH net-next 0/5] net: wangxun: timeout and error Jiawen Wu
2026-04-22  9:56 ` [RFC PATCH net-next 1/5] net: ngbe: implement libwx reset ops Jiawen Wu
2026-04-22  9:56 ` [RFC PATCH net-next 2/5] net: wangxun: add Tx timeout process Jiawen Wu
2026-04-22  9:56 ` [RFC PATCH net-next 3/5] net: wangxun: add reinit parameter to wx->do_reset callback Jiawen Wu
2026-04-22  9:56 ` [RFC PATCH net-next 4/5] net: wangxun: extract the close_suspend sequence Jiawen Wu
2026-04-22  9:56 ` Jiawen Wu [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260422095617.27080-6-jiawenwu@trustnetic.com \
    --to=jiawenwu@trustnetic.com \
    --cc=andrew+netdev@lunn.ch \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=fabio.baltieri@gmail.com \
    --cc=horms@kernel.org \
    --cc=jacob.e.keller@intel.com \
    --cc=joe@dama.to \
    --cc=kees@kernel.org \
    --cc=kuba@kernel.org \
    --cc=larysa.zaremba@intel.com \
    --cc=leitao@debian.org \
    --cc=linux@armlinux.org.uk \
    --cc=mengyuanlou@net-swift.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=richardcochran@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox