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 f913937..ac7bdbf 100644
--- a/drivers/net/sfc/efx.c
+++ b/drivers/net/sfc/efx.c
@@ -77,11 +77,6 @@
*/
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 @@
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 @@
{
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 cec15db..41e758e 100644
--- a/drivers/net/sfc/enum.h
+++ b/drivers/net/sfc/enum.h
@@ -72,7 +72,7 @@
* @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 @@
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,