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 2/5] net: wangxun: add Tx timeout process
Date: Wed, 22 Apr 2026 17:56:14 +0800 [thread overview]
Message-ID: <20260422095617.27080-3-jiawenwu@trustnetic.com> (raw)
In-Reply-To: <20260422095617.27080-1-jiawenwu@trustnetic.com>
Implement .ndo_tx_timeout to handle Tx side timeout event. When Tx
timeout event occur, it will triger driver into reset process.
The WX_HANG_CHECK_ARMED bit is set to indicate a potential hang. It will
be cleared if a pause frame is received to remove false hang detection
due to 802.3 frames.
Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
---
drivers/net/ethernet/wangxun/libwx/Makefile | 2 +-
drivers/net/ethernet/wangxun/libwx/wx_err.c | 125 ++++++++++++++++++
drivers/net/ethernet/wangxun/libwx/wx_err.h | 14 ++
drivers/net/ethernet/wangxun/libwx/wx_hw.c | 17 ++-
drivers/net/ethernet/wangxun/libwx/wx_lib.c | 37 ++++++
drivers/net/ethernet/wangxun/libwx/wx_lib.h | 1 +
drivers/net/ethernet/wangxun/libwx/wx_type.h | 12 +-
drivers/net/ethernet/wangxun/ngbe/ngbe_main.c | 4 +
.../net/ethernet/wangxun/txgbe/txgbe_main.c | 4 +
9 files changed, 211 insertions(+), 5 deletions(-)
create mode 100644 drivers/net/ethernet/wangxun/libwx/wx_err.c
create mode 100644 drivers/net/ethernet/wangxun/libwx/wx_err.h
diff --git a/drivers/net/ethernet/wangxun/libwx/Makefile b/drivers/net/ethernet/wangxun/libwx/Makefile
index a71b0ad77de3..c8724bb129aa 100644
--- a/drivers/net/ethernet/wangxun/libwx/Makefile
+++ b/drivers/net/ethernet/wangxun/libwx/Makefile
@@ -4,5 +4,5 @@
obj-$(CONFIG_LIBWX) += libwx.o
-libwx-objs := wx_hw.o wx_lib.o wx_ethtool.o wx_ptp.o wx_mbx.o wx_sriov.o
+libwx-objs := wx_hw.o wx_lib.o wx_ethtool.o wx_ptp.o wx_mbx.o wx_sriov.o wx_err.o
libwx-objs += wx_vf.o wx_vf_lib.o wx_vf_common.o
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_err.c b/drivers/net/ethernet/wangxun/libwx/wx_err.c
new file mode 100644
index 000000000000..42e00f0bd8da
--- /dev/null
+++ b/drivers/net/ethernet/wangxun/libwx/wx_err.c
@@ -0,0 +1,125 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2015 - 2026 Beijing WangXun Technology Co., Ltd. */
+
+#include <linux/netdevice.h>
+#include <linux/pci.h>
+
+#include "wx_type.h"
+#include "wx_lib.h"
+#include "wx_err.h"
+
+static void wx_reset_subtask(struct wx *wx)
+{
+ if (!test_bit(WX_FLAG_NEED_PF_RESET, wx->flags))
+ return;
+
+ rtnl_lock();
+
+ if (!netif_running(wx->netdev) ||
+ test_bit(WX_STATE_RESETTING, wx->state))
+ return;
+
+ wx_warn(wx, "Reset adapter.\n");
+
+ if (test_and_clear_bit(WX_FLAG_NEED_PF_RESET, wx->flags)) {
+ if (wx->do_reset)
+ wx->do_reset(wx->netdev);
+ }
+
+ rtnl_unlock();
+}
+
+/*
+ * wx_check_tx_hang_subtask - check for hung queues and dropped interrupts
+ * @wx - pointer to the device wx structure
+ *
+ * This function serves two purposes. First it strobes the interrupt lines
+ * in order to make certain interrupts are occurring. Secondly it sets the
+ * bits needed to check for TX hangs. As a result we should immediately
+ * determine if a hang has occurred.
+ */
+static void wx_check_tx_hang_subtask(struct wx *wx)
+{
+ int i;
+
+ /* If we're down or resetting, just bail */
+ if (!netif_running(wx->netdev) ||
+ test_bit(WX_STATE_RESETTING, wx->state))
+ return;
+
+ /* Force detection of hung controller */
+ if (netif_carrier_ok(wx->netdev)) {
+ for (i = 0; i < wx->num_tx_queues; i++)
+ set_bit(WX_TX_DETECT_HANG, wx->tx_ring[i]->state);
+ }
+}
+
+void wx_handle_errors_subtask(struct wx *wx)
+{
+ wx_reset_subtask(wx);
+ wx_check_tx_hang_subtask(wx);
+}
+EXPORT_SYMBOL(wx_handle_errors_subtask);
+
+static void wx_tx_timeout_reset(struct wx *wx)
+{
+ if (!netif_running(wx->netdev))
+ return;
+
+ set_bit(WX_FLAG_NEED_PF_RESET, wx->flags);
+ wx_warn(wx, "initiating reset due to tx timeout\n");
+ wx_service_event_schedule(wx);
+}
+
+void wx_tx_timeout(struct net_device *netdev, unsigned int txqueue)
+{
+ struct wx *wx = netdev_priv(netdev);
+ u32 head, tail;
+ int i;
+
+ for (i = 0; i < wx->num_tx_queues; i++) {
+ struct wx_ring *tx_ring = wx->tx_ring[i];
+
+ if (test_bit(WX_TX_DETECT_HANG, tx_ring->state) &&
+ wx_check_tx_hang(tx_ring))
+ wx_warn(wx, "Real tx hang detected on queue %d\n", i);
+
+ head = rd32(wx, WX_PX_TR_RP(tx_ring->reg_idx));
+ tail = rd32(wx, WX_PX_TR_WP(tx_ring->reg_idx));
+ wx_warn(wx,
+ "tx ring %d next_to_use is %d, next_to_clean is %d\n",
+ i, tx_ring->next_to_use,
+ tx_ring->next_to_clean);
+ wx_warn(wx, "tx ring %d hw rp is 0x%x, wp is 0x%x\n",
+ i, head, tail);
+ }
+
+ wx_tx_timeout_reset(wx);
+}
+EXPORT_SYMBOL(wx_tx_timeout);
+
+void wx_handle_tx_hang(struct wx_ring *tx_ring, unsigned int next)
+{
+ struct wx *wx = netdev_priv(tx_ring->netdev);
+
+ wx_warn(wx, "Detected Tx Unit Hang\n"
+ " Tx Queue <%d>\n"
+ " TDH, TDT <%x>, <%x>\n"
+ " next_to_use <%x>\n"
+ " next_to_clean <%x>\n"
+ "tx_buffer_info[next_to_clean]\n"
+ " time_stamp <%lx>\n"
+ " jiffies <%lx>\n",
+ tx_ring->queue_index,
+ rd32(wx, WX_PX_TR_RP(tx_ring->reg_idx)),
+ rd32(wx, WX_PX_TR_WP(tx_ring->reg_idx)),
+ tx_ring->next_to_use, next,
+ tx_ring->tx_buffer_info[next].time_stamp, jiffies);
+
+ netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index);
+
+ wx_warn(wx, "tx hang detected on queue %d, resetting adapter\n",
+ tx_ring->queue_index);
+
+ wx_tx_timeout_reset(wx);
+}
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_err.h b/drivers/net/ethernet/wangxun/libwx/wx_err.h
new file mode 100644
index 000000000000..e317e6c8d928
--- /dev/null
+++ b/drivers/net/ethernet/wangxun/libwx/wx_err.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * WangXun Gigabit PCI Express Linux driver
+ * Copyright (c) 2015 - 2026 Beijing WangXun Technology Co., Ltd.
+ */
+
+#ifndef _WX_ERR_H_
+#define _WX_ERR_H_
+
+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);
+
+#endif /* _WX_ERR_H_ */
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
index d3772d01e00b..401dc7eb1137 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
@@ -1932,6 +1932,7 @@ static void wx_configure_tx_ring(struct wx *wx,
else
ring->atr_sample_rate = 0;
+ bitmap_zero(ring->state, WX_RING_STATE_NBITS);
/* reinitialize tx_buffer_info */
memset(ring->tx_buffer_info, 0,
sizeof(struct wx_tx_buffer) * ring->count);
@@ -2847,16 +2848,26 @@ EXPORT_SYMBOL(wx_fc_enable);
static void wx_update_xoff_rx_lfc(struct wx *wx)
{
struct wx_hw_stats *hwstats = &wx->stats;
+ u64 data;
+ int i;
if (wx->fc.mode != wx_fc_full &&
wx->fc.mode != wx_fc_rx_pause)
return;
if (wx->mac.type >= wx_mac_aml)
- hwstats->lxoffrxc += rd32_wrap(wx, WX_MAC_LXOFFRXC_AML,
- &wx->last_stats.lxoffrxc);
+ data = rd32_wrap(wx, WX_MAC_LXOFFRXC_AML,
+ &wx->last_stats.lxoffrxc);
else
- hwstats->lxoffrxc += rd64(wx, WX_MAC_LXOFFRXC);
+ data = rd64(wx, WX_MAC_LXOFFRXC);
+ hwstats->lxoffrxc += data;
+
+ /* refill credits (no tx hang) if we received xoff */
+ if (!data)
+ return;
+
+ for (i = 0; i < wx->num_tx_queues; i++)
+ clear_bit(WX_HANG_CHECK_ARMED, wx->tx_ring[i]->state);
}
/**
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
index 746623fa59b4..9e6167b43f75 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
@@ -14,6 +14,7 @@
#include "wx_type.h"
#include "wx_lib.h"
+#include "wx_err.h"
#include "wx_ptp.h"
#include "wx_hw.h"
#include "wx_vf_lib.h"
@@ -742,6 +743,36 @@ static struct netdev_queue *wx_txring_txq(const struct wx_ring *ring)
return netdev_get_tx_queue(ring->netdev, ring->queue_index);
}
+static u32 wx_get_tx_pending(struct wx_ring *ring)
+{
+ unsigned int head, tail;
+
+ head = ring->next_to_clean;
+ tail = ring->next_to_use;
+
+ return ((head <= tail) ? tail : tail + ring->count) - head;
+}
+
+bool wx_check_tx_hang(struct wx_ring *ring)
+{
+ u32 tx_done_old = ring->tx_stats.tx_done_old;
+ u32 tx_pending = wx_get_tx_pending(ring);
+ u32 tx_done = ring->stats.packets;
+
+ clear_bit(WX_TX_DETECT_HANG, ring->state);
+
+ if (tx_done_old == tx_done && tx_pending)
+ /* make sure it is true for two checks in a row */
+ return test_and_set_bit(WX_HANG_CHECK_ARMED, ring->state);
+
+ /* update completed stats and continue */
+ ring->tx_stats.tx_done_old = tx_done;
+ /* reset the countdown */
+ clear_bit(WX_HANG_CHECK_ARMED, ring->state);
+
+ return false;
+}
+
/**
* wx_clean_tx_irq - Reclaim resources after transmit completes
* @q_vector: structure containing interrupt and ring information
@@ -866,6 +897,12 @@ static bool wx_clean_tx_irq(struct wx_q_vector *q_vector,
netdev_tx_completed_queue(wx_txring_txq(tx_ring),
total_packets, total_bytes);
+ if (test_bit(WX_TX_DETECT_HANG, tx_ring->state) &&
+ wx_check_tx_hang(tx_ring)) {
+ wx_handle_tx_hang(tx_ring, i);
+ return true;
+ }
+
#define TX_WAKE_THRESHOLD (DESC_NEEDED * 2)
if (unlikely(total_packets && netif_carrier_ok(tx_ring->netdev) &&
(wx_desc_unused(tx_ring) >= TX_WAKE_THRESHOLD))) {
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.h b/drivers/net/ethernet/wangxun/libwx/wx_lib.h
index aed6ea8cf0d6..e373cd7f05d3 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_lib.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.h
@@ -10,6 +10,7 @@
struct wx_dec_ptype wx_decode_ptype(const u8 ptype);
void wx_alloc_rx_buffers(struct wx_ring *rx_ring, u16 cleaned_count);
u16 wx_desc_unused(struct wx_ring *ring);
+bool wx_check_tx_hang(struct wx_ring *ring);
netdev_tx_t wx_xmit_frame(struct sk_buff *skb,
struct net_device *netdev);
void wx_napi_enable_all(struct wx *wx);
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h
index 0da5565ee4ff..f65c2d7bae39 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_type.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h
@@ -1039,6 +1039,7 @@ struct wx_queue_stats {
struct wx_tx_queue_stats {
u64 restart_queue;
u64 tx_busy;
+ u32 tx_done_old;
};
struct wx_rx_queue_stats {
@@ -1054,6 +1055,12 @@ struct wx_rx_queue_stats {
#define wx_for_each_ring(posm, headm) \
for (posm = (headm).ring; posm; posm = posm->next)
+enum wx_ring_state {
+ WX_TX_DETECT_HANG,
+ WX_HANG_CHECK_ARMED,
+ WX_RING_STATE_NBITS
+};
+
struct wx_ring_container {
struct wx_ring *ring; /* pointer to linked list of rings */
unsigned int total_bytes; /* total bytes processed this int */
@@ -1073,6 +1080,7 @@ struct wx_ring {
struct wx_tx_buffer *tx_buffer_info;
struct wx_rx_buffer *rx_buffer_info;
};
+ DECLARE_BITMAP(state, WX_RING_STATE_NBITS);
u8 __iomem *tail;
dma_addr_t dma; /* phys. address of descriptor ring */
dma_addr_t headwb_dma;
@@ -1273,6 +1281,7 @@ enum wx_pf_flags {
WX_FLAG_NEED_DO_RESET,
WX_FLAG_RX_MERGE_ENABLED,
WX_FLAG_TXHEAD_WB_ENABLED,
+ WX_FLAG_NEED_PF_RESET,
WX_PF_FLAGS_NBITS /* must be last */
};
@@ -1503,7 +1512,8 @@ rd32_wrap(struct wx *wx, u32 reg, u32 *last)
#define wx_err(wx, fmt, arg...) \
dev_err(&(wx)->pdev->dev, fmt, ##arg)
-
+#define wx_warn(wx, fmt, arg...) \
+ dev_warn(&(wx)->pdev->dev, fmt, ##arg)
#define wx_dbg(wx, fmt, arg...) \
dev_dbg(&(wx)->pdev->dev, fmt, ##arg)
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
index bd905e267575..e9561996b970 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
@@ -14,6 +14,7 @@
#include "../libwx/wx_type.h"
#include "../libwx/wx_hw.h"
#include "../libwx/wx_lib.h"
+#include "../libwx/wx_err.h"
#include "../libwx/wx_ptp.h"
#include "../libwx/wx_mbx.h"
#include "../libwx/wx_sriov.h"
@@ -147,6 +148,7 @@ static void ngbe_service_task(struct work_struct *work)
{
struct wx *wx = container_of(work, struct wx, service_task);
+ wx_handle_errors_subtask(wx);
wx_update_stats(wx);
wx_service_event_complete(wx);
@@ -642,6 +644,7 @@ static const struct net_device_ops ngbe_netdev_ops = {
.ndo_stop = ngbe_close,
.ndo_change_mtu = wx_change_mtu,
.ndo_start_xmit = wx_xmit_frame,
+ .ndo_tx_timeout = wx_tx_timeout,
.ndo_set_rx_mode = wx_set_rx_mode,
.ndo_set_features = wx_set_features,
.ndo_fix_features = wx_fix_features,
@@ -731,6 +734,7 @@ static int ngbe_probe(struct pci_dev *pdev,
wx->driver_name = ngbe_driver_name;
ngbe_set_ethtool_ops(netdev);
netdev->netdev_ops = &ngbe_netdev_ops;
+ netdev->watchdog_timeo = 5 * HZ;
netdev->features = NETIF_F_SG | NETIF_F_IP_CSUM |
NETIF_F_TSO | NETIF_F_TSO6 |
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
index ec32a5f422f2..b13c48507374 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
@@ -14,6 +14,7 @@
#include "../libwx/wx_type.h"
#include "../libwx/wx_lib.h"
+#include "../libwx/wx_err.h"
#include "../libwx/wx_ptp.h"
#include "../libwx/wx_hw.h"
#include "../libwx/wx_mbx.h"
@@ -128,6 +129,7 @@ static void txgbe_service_task(struct work_struct *work)
{
struct wx *wx = container_of(work, struct wx, service_task);
+ wx_handle_errors_subtask(wx);
txgbe_module_detection_subtask(wx);
txgbe_link_config_subtask(wx);
wx_update_stats(wx);
@@ -659,6 +661,7 @@ static const struct net_device_ops txgbe_netdev_ops = {
.ndo_stop = txgbe_close,
.ndo_change_mtu = wx_change_mtu,
.ndo_start_xmit = wx_xmit_frame,
+ .ndo_tx_timeout = wx_tx_timeout,
.ndo_set_rx_mode = wx_set_rx_mode,
.ndo_set_features = wx_set_features,
.ndo_fix_features = wx_fix_features,
@@ -750,6 +753,7 @@ static int txgbe_probe(struct pci_dev *pdev,
wx->driver_name = txgbe_driver_name;
txgbe_set_ethtool_ops(netdev);
netdev->netdev_ops = &txgbe_netdev_ops;
+ netdev->watchdog_timeo = 5 * HZ;
netdev->udp_tunnel_nic_info = &txgbe_udp_tunnels;
/* setup the private structure */
--
2.51.0
next prev 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 ` Jiawen Wu [this message]
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 ` [RFC PATCH net-next 5/5] net: wangxun: implement pci_error_handlers ops Jiawen Wu
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=20260422095617.27080-3-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