From 4c88931af582a2d928ab300587c8fadccda5c75a Mon Sep 17 00:00:00 2001 From: Alan Brady Date: Tue, 2 Aug 2022 10:19:17 +0200 Subject: i40e: Fix to stop tx_timeout recovery if GLOBR fails commit 57c942bc3bef0970f0b21f8e0998e76a900ea80d upstream. When a tx_timeout fires, the PF attempts to recover by incrementally resetting. First we try a PFR, then CORER and finally a GLOBR. If the GLOBR fails, then we keep hitting the tx_timeout and incrementing the recovery level and issuing dmesgs, which is both annoying to the user and accomplishes nothing. If the GLOBR fails, then we're pretty much totally hosed, and there's not much else we can do to recover, so this makes it such that we just kill the VSI and stop hitting the tx_timeout in such a case. Fixes: 41c445ff0f48 ("i40e: main driver core") Signed-off-by: Alan Brady Signed-off-by: Mateusz Palczewski Tested-by: Gurucharan (A Contingent worker at Intel) Signed-off-by: Tony Nguyen Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/intel/i40e/i40e_main.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 2f3b393e5506..85337806efc7 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -397,7 +397,9 @@ static void i40e_tx_timeout(struct net_device *netdev) set_bit(__I40E_GLOBAL_RESET_REQUESTED, pf->state); break; default: - netdev_err(netdev, "tx_timeout recovery unsuccessful\n"); + netdev_err(netdev, "tx_timeout recovery unsuccessful, device is in non-recoverable state.\n"); + set_bit(__I40E_DOWN_REQUESTED, pf->state); + set_bit(__I40E_VSI_DOWN_REQUESTED, vsi->state); break; } -- cgit v1.2.3