bnx2x: add fan failure event handling

Shut down the device in case of fan failure to prevent HW damage.

Signed-off-by: Dmitry Kravkov <dmitry@broadcom.com>
Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 26 insertions, 1 deletions

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index 23e91f4c1485..78613effd7e4 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -1141,6 +1141,7 @@ struct bnx2x_fw_stats_data {
 enum {
         BNX2X_SP_RTNL_SETUP_TC,
         BNX2X_SP_RTNL_TX_TIMEOUT,
+        BNX2X_SP_RTNL_FAN_FAILURE,
 };
 
 
@@ -2048,6 +2049,8 @@ static inline u32 reg_poll(struct bnx2x *bp, u32 reg, u32 expected, int ms,
 #define BNX2X_VPD_LEN                   128
 #define VENDOR_ID_LEN                   4
 
+int bnx2x_close(struct net_device *dev);
+
 /* Congestion management fairness mode */
 #define CMNG_FNS_NONE           0
 #define CMNG_FNS_MINMAX         1
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 967c41b8b172..33ff60d9fec8 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -3299,6 +3299,17 @@ static inline void bnx2x_fan_failure(struct bnx2x *bp)
         netdev_err(bp->dev, "Fan Failure on Network Controller has caused"
                " the driver to shutdown the card to prevent permanent"
                " damage.  Please contact OEM Support for assistance\n");
+
+        /*
+         * Scheudle device reset (unload)
+         * This is due to some boards consuming sufficient power when driver is
+         * up to overheat if fan fails.
+         */
+        smp_mb__before_clear_bit();
+        set_bit(BNX2X_SP_RTNL_FAN_FAILURE, &bp->sp_rtnl_state);
+        smp_mb__after_clear_bit();
+        schedule_delayed_work(&bp->sp_rtnl_task, 0);
+
 }
 
 static inline void bnx2x_attn_int_deasserted0(struct bnx2x *bp, u32 attn)
@@ -8503,6 +8514,17 @@ sp_rtnl_not_reset:
         if (test_and_clear_bit(BNX2X_SP_RTNL_SETUP_TC, &bp->sp_rtnl_state))
                 bnx2x_setup_tc(bp->dev, bp->dcbx_port_params.ets.num_of_cos);
 
+        /*
+         * in case of fan failure we need to reset id if the "stop on error"
+         * debug flag is set, since we trying to prevent permanent overheating
+         * damage
+         */
+        if (test_and_clear_bit(BNX2X_SP_RTNL_FAN_FAILURE, &bp->sp_rtnl_state)) {
+                DP(BNX2X_MSG_SP, "fan failure detected. Unloading driver");
+                netif_device_detach(bp->dev);
+                bnx2x_close(bp->dev);
+        }
+
 sp_rtnl_exit:
         rtnl_unlock();
 }
@@ -9969,7 +9991,7 @@ static int bnx2x_open(struct net_device *dev)
 }
 
 /* called with rtnl_lock */
-static int bnx2x_close(struct net_device *dev)
+int bnx2x_close(struct net_device *dev)
 {
         struct bnx2x *bp = netdev_priv(dev);