3 files changed, 58 insertions, 39 deletions

diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.c b/drivers/accel/amdxdna/amdxdna_pci_drv.c
index 97d4a032171f..f5b8497cf5ad 100644
--- a/drivers/accel/amdxdna/amdxdna_pci_drv.c
+++ b/drivers/accel/amdxdna/amdxdna_pci_drv.c
@@ -21,6 +21,11 @@
 
 #define AMDXDNA_AUTOSUSPEND_DELAY	5000 /* milliseconds */
 
+MODULE_FIRMWARE("amdnpu/1502_00/npu.sbin");
+MODULE_FIRMWARE("amdnpu/17f0_10/npu.sbin");
+MODULE_FIRMWARE("amdnpu/17f0_11/npu.sbin");
+MODULE_FIRMWARE("amdnpu/17f0_20/npu.sbin");
+
 /*
  * Bind the driver base on (vendor_id, device_id) pair and later use the
  * (device_id, rev_id) pair as a key to select the devices. The devices with
diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index 1e8ffbe25eee..38cf1c342c72 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -397,15 +397,19 @@ int ivpu_boot(struct ivpu_device *vdev)
 	if (ivpu_fw_is_cold_boot(vdev)) {
 		ret = ivpu_pm_dct_init(vdev);
 		if (ret)
-			goto err_diagnose_failure;
+			goto err_disable_ipc;
 
 		ret = ivpu_hw_sched_init(vdev);
 		if (ret)
-			goto err_diagnose_failure;
+			goto err_disable_ipc;
 	}
 
 	return 0;
 
+err_disable_ipc:
+	ivpu_ipc_disable(vdev);
+	ivpu_hw_irq_disable(vdev);
+	disable_irq(vdev->irq);
 err_diagnose_failure:
 	ivpu_hw_diagnose_failure(vdev);
 	ivpu_mmu_evtq_dump(vdev);
diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
index 87d7411ae059..5060c5dd40d1 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -115,41 +115,57 @@ err_power_down:
 	return ret;
 }
 
-static void ivpu_pm_recovery_work(struct work_struct *work)
+static void ivpu_pm_reset_begin(struct ivpu_device *vdev)
 {
-	struct ivpu_pm_info *pm = container_of(work, struct ivpu_pm_info, recovery_work);
-	struct ivpu_device *vdev = pm->vdev;
-	char *evt[2] = {"IVPU_PM_EVENT=IVPU_RECOVER", NULL};
-	int ret;
-
-	ivpu_err(vdev, "Recovering the NPU (reset #%d)\n", atomic_read(&vdev->pm->reset_counter));
-
-	ret = pm_runtime_resume_and_get(vdev->drm.dev);
-	if (ret)
-		ivpu_err(vdev, "Failed to resume NPU: %d\n", ret);
-
-	ivpu_jsm_state_dump(vdev);
-	ivpu_dev_coredump(vdev);
+	pm_runtime_disable(vdev->drm.dev);
 
 	atomic_inc(&vdev->pm->reset_counter);
 	atomic_set(&vdev->pm->reset_pending, 1);
 	down_write(&vdev->pm->reset_lock);
+}
+
+static void ivpu_pm_reset_complete(struct ivpu_device *vdev)
+{
+	int ret;
 
-	ivpu_suspend(vdev);
 	ivpu_pm_prepare_cold_boot(vdev);
 	ivpu_jobs_abort_all(vdev);
 	ivpu_ms_cleanup_all(vdev);
 
 	ret = ivpu_resume(vdev);
-	if (ret)
+	if (ret) {
 		ivpu_err(vdev, "Failed to resume NPU: %d\n", ret);
+		pm_runtime_set_suspended(vdev->drm.dev);
+	} else {
+		pm_runtime_set_active(vdev->drm.dev);
+	}
 
 	up_write(&vdev->pm->reset_lock);
 	atomic_set(&vdev->pm->reset_pending, 0);
 
-	kobject_uevent_env(&vdev->drm.dev->kobj, KOBJ_CHANGE, evt);
 	pm_runtime_mark_last_busy(vdev->drm.dev);
-	pm_runtime_put_autosuspend(vdev->drm.dev);
+	pm_runtime_enable(vdev->drm.dev);
+}
+
+static void ivpu_pm_recovery_work(struct work_struct *work)
+{
+	struct ivpu_pm_info *pm = container_of(work, struct ivpu_pm_info, recovery_work);
+	struct ivpu_device *vdev = pm->vdev;
+	char *evt[2] = {"IVPU_PM_EVENT=IVPU_RECOVER", NULL};
+
+	ivpu_err(vdev, "Recovering the NPU (reset #%d)\n", atomic_read(&vdev->pm->reset_counter));
+
+	ivpu_pm_reset_begin(vdev);
+
+	if (!pm_runtime_status_suspended(vdev->drm.dev)) {
+		ivpu_jsm_state_dump(vdev);
+		ivpu_dev_coredump(vdev);
+		ivpu_suspend(vdev);
+	}
+
+	ivpu_pm_reset_complete(vdev);
+
+	kobject_uevent_env(&vdev->drm.dev->kobj, KOBJ_CHANGE, evt);
 }
 
 void ivpu_pm_trigger_recovery(struct ivpu_device *vdev, const char *reason)
@@ -309,7 +325,10 @@ int ivpu_rpm_get(struct ivpu_device *vdev)
 	int ret;
 
 	ret = pm_runtime_resume_and_get(vdev->drm.dev);
-	drm_WARN_ON(&vdev->drm, ret < 0);
+	if (ret < 0) {
+		ivpu_err(vdev, "Failed to resume NPU: %d\n", ret);
+		pm_runtime_set_suspended(vdev->drm.dev);
+	}
 
 	return ret;
 }
@@ -325,16 +344,13 @@ void ivpu_pm_reset_prepare_cb(struct pci_dev *pdev)
 	struct ivpu_device *vdev = pci_get_drvdata(pdev);
 
 	ivpu_dbg(vdev, PM, "Pre-reset..\n");
-	atomic_inc(&vdev->pm->reset_counter);
-	atomic_set(&vdev->pm->reset_pending, 1);
 
-	pm_runtime_get_sync(vdev->drm.dev);
-	down_write(&vdev->pm->reset_lock);
-	ivpu_prepare_for_reset(vdev);
-	ivpu_hw_reset(vdev);
-	ivpu_pm_prepare_cold_boot(vdev);
-	ivpu_jobs_abort_all(vdev);
-	ivpu_ms_cleanup_all(vdev);
+	ivpu_pm_reset_begin(vdev);
+
+	if (!pm_runtime_status_suspended(vdev->drm.dev)) {
+		ivpu_prepare_for_reset(vdev);
+		ivpu_hw_reset(vdev);
+	}
 
 	ivpu_dbg(vdev, PM, "Pre-reset done.\n");
 }
@@ -342,18 +358,12 @@ void ivpu_pm_reset_prepare_cb(struct pci_dev *pdev)
 void ivpu_pm_reset_done_cb(struct pci_dev *pdev)
 {
 	struct ivpu_device *vdev = pci_get_drvdata(pdev);
-	int ret;
 
 	ivpu_dbg(vdev, PM, "Post-reset..\n");
-	ret = ivpu_resume(vdev);
-	if (ret)
-		ivpu_err(vdev, "Failed to set RESUME state: %d\n", ret);
-	up_write(&vdev->pm->reset_lock);
-	atomic_set(&vdev->pm->reset_pending, 0);
-	ivpu_dbg(vdev, PM, "Post-reset done.\n");
 
-	pm_runtime_mark_last_busy(vdev->drm.dev);
-	pm_runtime_put_autosuspend(vdev->drm.dev);
+	ivpu_pm_reset_complete(vdev);
+
+	ivpu_dbg(vdev, PM, "Post-reset done.\n");
 }
 
 void ivpu_pm_init(struct ivpu_device *vdev)