sfc: Do not reset when hardware monitor detects a fault

The TX watchdog should trigger a reset, but a temperature/power alarm
should not as this is unlikely to solve the problem.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>

diff --git a/drivers/net/sfc/efx.c b/drivers/net/sfc/efx.c
index f9139377989ff05c94f4cccd0a0edf01f5fe56c4..ac7bdbf3fd4abf7e9a562cfd3e4e122d005ad5a4 100644 (file)
--- a/drivers/net/sfc/efx.c
+++ b/drivers/net/sfc/efx.c
@@ -77,11 +77,6 @@ static int napi_weight = 64;
  */
 unsigned int efx_monitor_interval = 1 * HZ;
 
-/* This controls whether or not the hardware monitor will trigger a
- * reset when it detects an error condition.
- */
-static unsigned int monitor_reset = true;
-
 /* This controls whether or not the driver will initialise devices
  * with invalid MAC addresses stored in the EEPROM or flash.  If true,
  * such devices will be initialised with a random locally-generated
@@ -1176,17 +1171,6 @@ static void efx_monitor(struct work_struct *data)
                rc = falcon_check_xmac(efx);
        mutex_unlock(&efx->mac_lock);
 
-       if (rc) {
-               if (monitor_reset) {
-                       EFX_ERR(efx, "hardware monitor detected a fault: "
-                               "triggering reset\n");
-                       efx_schedule_reset(efx, RESET_TYPE_MONITOR);
-               } else {
-                       EFX_ERR(efx, "hardware monitor detected a fault, "
-                               "skipping reset\n");
-               }
-       }
-
        queue_delayed_work(efx->workqueue, &efx->monitor_work,
                           efx_monitor_interval);
 }
@@ -1358,12 +1342,11 @@ static void efx_watchdog(struct net_device *net_dev)
 {
        struct efx_nic *efx = netdev_priv(net_dev);
 
-       EFX_ERR(efx, "TX stuck with stop_count=%d port_enabled=%d: %s\n",
-               atomic_read(&efx->netif_stop_count), efx->port_enabled,
-               monitor_reset ? "resetting channels" : "skipping reset");
+       EFX_ERR(efx, "TX stuck with stop_count=%d port_enabled=%d:"
+               " resetting channels\n",
+               atomic_read(&efx->netif_stop_count), efx->port_enabled);
 
-       if (monitor_reset)
-               efx_schedule_reset(efx, RESET_TYPE_MONITOR);
+       efx_schedule_reset(efx, RESET_TYPE_TX_WATCHDOG);
 }
 
 

diff --git a/drivers/net/sfc/enum.h b/drivers/net/sfc/enum.h
index cec15dbb88e474b4705d0141e6b264d2c79ec606..41e758e8fdb18438b88ed577675dbe546de3c67d 100644 (file)
--- a/drivers/net/sfc/enum.h
+++ b/drivers/net/sfc/enum.h
@@ -72,7 +72,7 @@ extern const char *efx_loopback_mode_names[];
  * @RESET_TYPE_ALL: reset everything but PCI core blocks
  * @RESET_TYPE_WORLD: reset everything, save & restore PCI config
  * @RESET_TYPE_DISABLE: disable NIC
- * @RESET_TYPE_MONITOR: reset due to hardware monitor
+ * @RESET_TYPE_TX_WATCHDOG: reset due to TX watchdog
  * @RESET_TYPE_INT_ERROR: reset due to internal error
  * @RESET_TYPE_RX_RECOVERY: reset to recover from RX datapath errors
  * @RESET_TYPE_RX_DESC_FETCH: pcie error during rx descriptor fetch
@@ -86,7 +86,7 @@ enum reset_type {
        RESET_TYPE_WORLD = 2,
        RESET_TYPE_DISABLE = 3,
        RESET_TYPE_MAX_METHOD,
-       RESET_TYPE_MONITOR,
+       RESET_TYPE_TX_WATCHDOG,
        RESET_TYPE_INT_ERROR,
        RESET_TYPE_RX_RECOVERY,
        RESET_TYPE_RX_DESC_FETCH,