From: Xuanqiang Luo <[email protected]>

i40e_remove() currently tears down PTP and device resources before
claiming RESET_RECOVERY_PENDING. A service task can pass its initial state
check before removal starts and continue into reset recovery after the
remove path has begun teardown. This can make i40e_reset_and_rebuild()
access or recreate resources that are being released.

Stop the service timer and disable the service work before claiming reset
ownership. disable_work_sync() drains the current service task and rejects
later queue_work() attempts, including those from interrupts. Claim the
reset bit before starting teardown so an existing reset owner completes
first.

Fixes: 6533e558c650 ("i40e: Fix reset path while removing the driver")
Signed-off-by: Xuanqiang Luo <[email protected]>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 28 ++++++++++-----------
 1 file changed, 14 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c 
b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 8c28788ac634f..5922f83f324ae 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -16159,6 +16159,20 @@ static void i40e_remove(struct pci_dev *pdev)
 
        i40e_devlink_unregister(pf);
 
+       /* Interrupts can queue the service task until __I40E_DOWN is set.
+        * Disable it so no service work can outlive the PF.
+        */
+       set_bit(__I40E_SUSPENDED, pf->state);
+       if (pf->service_timer.function)
+               timer_shutdown_sync(&pf->service_timer);
+       if (pf->service_task.func)
+               disable_work_sync(&pf->service_task);
+
+       /* Wait for any reset owner before tearing down device resources. */
+       while (test_and_set_bit(__I40E_RESET_RECOVERY_PENDING, pf->state))
+               usleep_range(1000, 2000);
+       set_bit(__I40E_IN_REMOVE, pf->state);
+
        i40e_dbg_pf_exit(pf);
 
        i40e_ptp_stop(pf);
@@ -16167,26 +16181,12 @@ static void i40e_remove(struct pci_dev *pdev)
        i40e_write_rx_ctl(hw, I40E_PFQF_HENA(0), 0);
        i40e_write_rx_ctl(hw, I40E_PFQF_HENA(1), 0);
 
-       /* Grab __I40E_RESET_RECOVERY_PENDING and set __I40E_IN_REMOVE
-        * flags, once they are set, i40e_rebuild should not be called as
-        * i40e_prep_for_reset always returns early.
-        */
-       while (test_and_set_bit(__I40E_RESET_RECOVERY_PENDING, pf->state))
-               usleep_range(1000, 2000);
-       set_bit(__I40E_IN_REMOVE, pf->state);
-
        if (test_bit(I40E_FLAG_SRIOV_ENA, pf->flags)) {
                set_bit(__I40E_VF_RESETS_DISABLED, pf->state);
                i40e_free_vfs(pf);
                clear_bit(I40E_FLAG_SRIOV_ENA, pf->flags);
        }
-       /* no more scheduling of any task */
-       set_bit(__I40E_SUSPENDED, pf->state);
        set_bit(__I40E_DOWN, pf->state);
-       if (pf->service_timer.function)
-               timer_shutdown_sync(&pf->service_timer);
-       if (pf->service_task.func)
-               cancel_work_sync(&pf->service_task);
 
        if (test_bit(__I40E_RECOVERY_MODE, pf->state)) {
                struct i40e_vsi *vsi = pf->vsi[0];
-- 
2.43.0

Reply via email to