igc: Add ndo_tx_timeout support

On some platforms, 100/1000/2500 speeds seem to have sometimes problems
reporting false positive tx unit hang during stressful UDP traffic. Likely
other Intel drivers introduce responses to a tx hang. Update the 'tx hang'
comparator with the comparison of the head and tail of ring pointers and
restore the tx_timeout_factor to the previous value (one).

This can be test by using netperf or iperf3 applications.
Example:
iperf3 -s -p 5001
iperf3 -c 192.168.0.2 --udp -p 5001 --time 600 -b 0

netserver -p 16604
netperf -H 192.168.0.2 -l 600 -p 16604 -t UDP_STREAM -- -m 64000

Fixes: b27b8dc77b5e ("igc: Increase timeout value for Speed 100/1000/2500")
Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Naama Meir <naamax.meir@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://lore.kernel.org/r/20230206235818.662384-1-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 44b1740dc09834888b2946793057e250c76313bc..1dd2a7fee8d46d8ecf7769f52cb055ea24977231 100644 (file)
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2942,7 +2942,9 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget)
                if (tx_buffer->next_to_watch &&
                    time_after(jiffies, tx_buffer->time_stamp +
                    (adapter->tx_timeout_factor * HZ)) &&
-                   !(rd32(IGC_STATUS) & IGC_STATUS_TXOFF)) {
+                   !(rd32(IGC_STATUS) & IGC_STATUS_TXOFF) &&
+                   (rd32(IGC_TDH(tx_ring->reg_idx)) !=
+                    readl(tx_ring->tail))) {
                        /* detected Tx unit hang */
                        netdev_err(tx_ring->netdev,
                                   "Detected Tx Unit Hang\n"
@@ -5068,6 +5070,24 @@ static int igc_change_mtu(struct net_device *netdev, int new_mtu)
        return 0;
 }
 
+/**
+ * igc_tx_timeout - Respond to a Tx Hang
+ * @netdev: network interface device structure
+ * @txqueue: queue number that timed out
+ **/
+static void igc_tx_timeout(struct net_device *netdev,
+                          unsigned int __always_unused txqueue)
+{
+       struct igc_adapter *adapter = netdev_priv(netdev);
+       struct igc_hw *hw = &adapter->hw;
+
+       /* Do the reset outside of interrupt context */
+       adapter->tx_timeout_count++;
+       schedule_work(&adapter->reset_task);
+       wr32(IGC_EICS,
+            (adapter->eims_enable_mask & ~adapter->eims_other));
+}
+
 /**
  * igc_get_stats64 - Get System Network Statistics
  * @netdev: network interface device structure
@@ -5495,7 +5515,7 @@ static void igc_watchdog_task(struct work_struct *work)
                        case SPEED_100:
                        case SPEED_1000:
                        case SPEED_2500:
-                               adapter->tx_timeout_factor = 7;
+                               adapter->tx_timeout_factor = 1;
                                break;
                        }
 
@@ -6320,6 +6340,7 @@ static const struct net_device_ops igc_netdev_ops = {
        .ndo_set_rx_mode        = igc_set_rx_mode,
        .ndo_set_mac_address    = igc_set_mac,
        .ndo_change_mtu         = igc_change_mtu,
+       .ndo_tx_timeout         = igc_tx_timeout,
        .ndo_get_stats64        = igc_get_stats64,
        .ndo_fix_features       = igc_fix_features,
        .ndo_set_features       = igc_set_features,