i40e: Fix an issue when PF reset fails

We shouldn't restart Admin queue subtask if PF reset fails since we do
not have the AQ setup at that point. This patch makes sure we disable AQ
clean subtask when PF reset fails.

This will resolve an occasional kernel panic when PF reset fails for
some reason.

Change-ID: I11a747773362a8c5c0ad7a10cd34be0bda8eb9e8
Signed-off-by: Anjali Singhai Jain <anjali.singhai@intel.com>
Tested-by: Jim Young <jamesx.m.young@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 4e97ba1b04deadc22e96321696cbb1b5df96b28b..f1e33f896439b1d6ccbc5f2428d9aef05fcbcee3 100644 (file)
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -145,6 +145,7 @@ enum i40e_state_t {
        __I40E_BAD_EEPROM,
        __I40E_DOWN_REQUESTED,
        __I40E_FD_FLUSH_REQUESTED,
+       __I40E_RESET_FAILED,
 };
 
 enum i40e_interrupt_policy {

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 55a31ab22f5c6b4fddb2211b3177a3722ce11bf0..64b8683fda1e96081a665e0b7b0254345f2abcee 100644 (file)
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -5568,6 +5568,10 @@ static void i40e_clean_adminq_subtask(struct i40e_pf *pf)
        u32 oldval;
        u32 val;
 
+       /* Do not run clean AQ when PF reset fails */
+       if (test_bit(__I40E_RESET_FAILED, &pf->state))
+               return;
+
        /* check for error indications */
        val = rd32(&pf->hw, pf->hw.aq.arq.len);
        oldval = val;
@@ -5973,19 +5977,20 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
        ret = i40e_pf_reset(hw);
        if (ret) {
                dev_info(&pf->pdev->dev, "PF reset failed, %d\n", ret);
-               goto end_core_reset;
+               set_bit(__I40E_RESET_FAILED, &pf->state);
+               goto clear_recovery;
        }
        pf->pfr_count++;
 
        if (test_bit(__I40E_DOWN, &pf->state))
-               goto end_core_reset;
+               goto clear_recovery;
        dev_dbg(&pf->pdev->dev, "Rebuilding internal switch\n");
 
        /* rebuild the basics for the AdminQ, HMC, and initial HW switch */
        ret = i40e_init_adminq(&pf->hw);
        if (ret) {
                dev_info(&pf->pdev->dev, "Rebuild AdminQ failed, %d\n", ret);
-               goto end_core_reset;
+               goto clear_recovery;
        }
 
        /* re-verify the eeprom if we just had an EMP reset */
@@ -6103,6 +6108,8 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
        i40e_send_version(pf);
 
 end_core_reset:
+       clear_bit(__I40E_RESET_FAILED, &pf->state);
+clear_recovery:
        clear_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state);
 }