bnxt_en: Fix error recovery regression

BugLink: https://bugs.launchpad.net/bugs/1948873
commit eca4cf12acda306f851f6d2a05b1c9ef62cf0e81 upstream.

The recent patch has introduced a regression by not reading the reset
count in the ERROR_RECOVERY async event handler.  We may have just
gone through a reset and the reset count has just incremented.  If
we don't update the reset count in the ERROR_RECOVERY event handler,
the health check timer will see that the reset count has changed and
will initiate an unintended reset.

Restore the unconditional update of the reset count in
bnxt_async_event_process() if error recovery watchdog is enabled.
Also, update the reset count at the end of the reset sequence to
make it even more robust.

Fixes: 1b2b91831983 ("bnxt_en: Fix possible unintended driver initiated error recovery")
Reviewed-by: Edwin Peer <edwin.peer@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
Signed-off-by: Kelsey Skunberg <kelsey.skunberg@canonical.com>

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 687b497bea652741c8d27c46411fe1288ad94622..5be8902d5bb26766d2a9a317b56ba4dae67d2144 100644 (file)
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -2123,12 +2123,11 @@ static int bnxt_async_event_process(struct bnxt *bp,
                        DIV_ROUND_UP(fw_health->polling_dsecs * HZ,
                                     bp->current_interval * 10);
                fw_health->tmr_counter = fw_health->tmr_multiplier;
-               if (!fw_health->enabled) {
+               if (!fw_health->enabled)
                        fw_health->last_fw_heartbeat =
                                bnxt_fw_health_readl(bp, BNXT_FW_HEARTBEAT_REG);
-                       fw_health->last_fw_reset_cnt =
-                               bnxt_fw_health_readl(bp, BNXT_FW_RESET_CNT_REG);
-               }
+               fw_health->last_fw_reset_cnt =
+                       bnxt_fw_health_readl(bp, BNXT_FW_RESET_CNT_REG);
                netif_info(bp, drv, bp->dev,
                           "Error recovery info: error recovery[1], master[%d], reset count[%u], health status: 0x%x\n",
                           fw_health->master, fw_health->last_fw_reset_cnt,
@@ -11653,6 +11652,11 @@ static void bnxt_fw_reset_task(struct work_struct *work)
                        dev_close(bp->dev);
                }
 
+               if ((bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY) &&
+                   bp->fw_health->enabled) {
+                       bp->fw_health->last_fw_reset_cnt =
+                               bnxt_fw_health_readl(bp, BNXT_FW_RESET_CNT_REG);
+               }
                bp->fw_reset_state = 0;
                /* Make sure fw_reset_state is 0 before clearing the flag */
                smp_mb__before_atomic();