pds_core: Prevent health thread from running during reset/remove

[ Upstream commit d9407ff ]

The PCIe reset handlers can run at the same time as the
health thread. This can cause the health thread to
stomp on the PCIe reset. Fix this by preventing the
health thread from running while a PCIe reset is happening.

As part of this use timer_shutdown_sync() during reset and
remove to make sure the timer doesn't ever get rearmed.

Fixes: ffa5585 ("pds_core: implement pci reset handlers")
Signed-off-by: Brett Creeley <brett.creeley@amd.com>
Reviewed-by: Shannon Nelson <shannon.nelson@amd.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Link: https://lore.kernel.org/r/20240129234035.69802-2-brett.creeley@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>

drivers/net/ethernet/amd/pds_core/main.c

@@ -298,7 +298,7 @@ static int pdsc_init_pf(struct pdsc *pdsc)
 err_out_teardown:
 	pdsc_teardown(pdsc, PDSC_TEARDOWN_REMOVING);
 err_out_unmap_bars:
-	del_timer_sync(&pdsc->wdtimer);
+	timer_shutdown_sync(&pdsc->wdtimer);
 	if (pdsc->wq)
 		destroy_workqueue(pdsc->wq);
 	mutex_destroy(&pdsc->config_lock);
@@ -425,7 +425,7 @@ static void pdsc_remove(struct pci_dev *pdev)
 		 */
 		pdsc_sriov_configure(pdev, 0);
 
-		del_timer_sync(&pdsc->wdtimer);
+		timer_shutdown_sync(&pdsc->wdtimer);
 		if (pdsc->wq)
 			destroy_workqueue(pdsc->wq);
 
@@ -449,10 +449,24 @@ static void pdsc_remove(struct pci_dev *pdev)
 	devlink_free(dl);
 }
 
+static void pdsc_stop_health_thread(struct pdsc *pdsc)
+{
+	timer_shutdown_sync(&pdsc->wdtimer);
+	if (pdsc->health_work.func)
+		cancel_work_sync(&pdsc->health_work);
+}
+
+static void pdsc_restart_health_thread(struct pdsc *pdsc)
+{
+	timer_setup(&pdsc->wdtimer, pdsc_wdtimer_cb, 0);
+	mod_timer(&pdsc->wdtimer, jiffies + 1);
+}
+
 static void pdsc_reset_prepare(struct pci_dev *pdev)
 {
 	struct pdsc *pdsc = pci_get_drvdata(pdev);
 
+	pdsc_stop_health_thread(pdsc);
 	pdsc_fw_down(pdsc);
 
 	pdsc_unmap_bars(pdsc);
@@ -489,6 +503,7 @@ static void pdsc_reset_done(struct pci_dev *pdev)
 	}
 
 	pdsc_fw_up(pdsc);
+	pdsc_restart_health_thread(pdsc);
 }
 
 static const struct pci_error_handlers pdsc_err_handler = {