i40e: Fix erroneous adapter reinitialization during recovery process

Fix an issue when driver incorrectly detects state
of recovery process and erroneously reinitializes interrupts,
which results in a kernel error and call trace message.

The issue was caused by a combination of two factors:
1. Assuming the EMP reset issued after completing
firmware recovery means the whole recovery process is complete.
2. Erroneous reinitialization of interrupt vector after detecting
the above mentioned EMP reset.

Fixes (1) by changing how recovery state change is detected
and (2) by adjusting the conditional expression to ensure using proper
interrupt reinitialization method, depending on the situation.

Fixes: bdbcceb6036b ("i40e: Introduce recovery mode support")
Signed-off-by: Dawid Lukwinski <dawid.lukwinski@intel.com>
Signed-off-by: Jan Sokolowski <jan.sokolowski@intel.com>
Tested-by: Konrad Jankowski <konrad0.jankowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://lore.kernel.org/r/20220715214542.2968762-1-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index aa786fd5595113c521c6f1b500ed94b4f0d80dd1..7f1a0d90dc51eabbfef366527bdea7cfb70245f5 100644 (file)
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -10650,7 +10650,7 @@ static int i40e_reset(struct i40e_pf *pf)
  **/
 static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 {
-       int old_recovery_mode_bit = test_bit(__I40E_RECOVERY_MODE, pf->state);
+       const bool is_recovery_mode_reported = i40e_check_recovery_mode(pf);
        struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
        struct i40e_hw *hw = &pf->hw;
        i40e_status ret;
@@ -10658,13 +10658,11 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
        int v;
 
        if (test_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state) &&
-           i40e_check_recovery_mode(pf)) {
+           is_recovery_mode_reported)
                i40e_set_ethtool_ops(pf->vsi[pf->lan_vsi]->netdev);
-       }
 
        if (test_bit(__I40E_DOWN, pf->state) &&
-           !test_bit(__I40E_RECOVERY_MODE, pf->state) &&
-           !old_recovery_mode_bit)
+           !test_bit(__I40E_RECOVERY_MODE, pf->state))
                goto clear_recovery;
        dev_dbg(&pf->pdev->dev, "Rebuilding internal switch\n");
 
@@ -10691,13 +10689,12 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
         * accordingly with regard to resources initialization
         * and deinitialization
         */
-       if (test_bit(__I40E_RECOVERY_MODE, pf->state) ||
-           old_recovery_mode_bit) {
+       if (test_bit(__I40E_RECOVERY_MODE, pf->state)) {
                if (i40e_get_capabilities(pf,
                                          i40e_aqc_opc_list_func_capabilities))
                        goto end_unlock;
 
-               if (test_bit(__I40E_RECOVERY_MODE, pf->state)) {
+               if (is_recovery_mode_reported) {
                        /* we're staying in recovery mode so we'll reinitialize
                         * misc vector here
                         */