i40e: prevent overlapping tx_timeout recover

If a TX hang occurs, we attempt to recover by incrementally resetting.
If we're starved for CPU time, it's possible the reset doesn't actually
complete (or even fire) before another tx_timeout fires causing us to
fly through the different resets without actually doing them.

This adds a bit to set and check if a timeout recovery is already
pending and, if so, bail out of tx_timeout.  The bit will get cleared at
the end of i40e_rebuild when reset is complete.

Signed-off-by: Alan Brady <alan.brady@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index cda37d7..8de9085 100644 (file)
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -122,6 +122,7 @@ enum i40e_state_t {
        __I40E_MDD_EVENT_PENDING,
        __I40E_VFLR_EVENT_PENDING,
        __I40E_RESET_RECOVERY_PENDING,
+       __I40E_TIMEOUT_RECOVERY_PENDING,
        __I40E_MISC_IRQ_REQUESTED,
        __I40E_RESET_INTR_RECEIVED,
        __I40E_REINIT_REQUESTED,

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index d4461ee..47f0fda 100644 (file)
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -338,6 +338,10 @@ static void i40e_tx_timeout(struct net_device *netdev)
                      (pf->tx_timeout_last_recovery + netdev->watchdog_timeo)))
                return;   /* don't do any new action before the next timeout */
 
+       /* don't kick off another recovery if one is already pending */
+       if (test_and_set_bit(__I40E_TIMEOUT_RECOVERY_PENDING, pf->state))
+               return;
+
        if (tx_ring) {
                head = i40e_get_head(tx_ring);
                /* Read interrupt register */
@@ -9631,6 +9635,7 @@ end_core_reset:
        clear_bit(__I40E_RESET_FAILED, pf->state);
 clear_recovery:
        clear_bit(__I40E_RESET_RECOVERY_PENDING, pf->state);
+       clear_bit(__I40E_TIMEOUT_RECOVERY_PENDING, pf->state);
 }
 
 /**