diff mbox series

[3/3] accel/ivpu: Fix error handling in recovery/reset

Message ID 20250129124009.1039982-4-jacek.lawrynowicz@linux.intel.com (mailing list archive)
State New
Headers show
Series accel/ivpu: Fixes for 6.14 | expand

Commit Message

Jacek Lawrynowicz Jan. 29, 2025, 12:40 p.m. UTC 
Disable runtime PM for the duration of reset/recovery so it is possible
to set the correct runtime PM state depending on the outcome of the
`ivpu_resume()`. Don’t suspend or reset the HW if the NPU is suspended
when the reset/recovery is requested. Also, move common reset/recovery
code to separate functions for better code readability.

Fixes: 27d19268cf39 ("accel/ivpu: Improve recovery and reset support")
Cc: <stable@vger.kernel.org> # v6.8+
Reviewed-by: Maciej Falkowski <maciej.falkowski@linux.intel.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
---
 drivers/accel/ivpu/ivpu_pm.c | 79 ++++++++++++++++++++----------------
 1 file changed, 43 insertions(+), 36 deletions(-)

Comments

Jeffrey Hugo Jan. 31, 2025, 6:29 p.m. UTC | #1 
On 1/29/2025 5:40 AM, Jacek Lawrynowicz wrote:
> Disable runtime PM for the duration of reset/recovery so it is possible
> to set the correct runtime PM state depending on the outcome of the
> `ivpu_resume()`. Don’t suspend or reset the HW if the NPU is suspended
> when the reset/recovery is requested. Also, move common reset/recovery
> code to separate functions for better code readability.
> 
> Fixes: 27d19268cf39 ("accel/ivpu: Improve recovery and reset support")
> Cc: <stable@vger.kernel.org> # v6.8+
> Reviewed-by: Maciej Falkowski <maciej.falkowski@linux.intel.com>
> Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>

Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
diff mbox series

Patch

diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
index c3774d2221326..8b2b050cc41a9 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -115,41 +115,57 @@  static int ivpu_resume(struct ivpu_device *vdev)
 	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)
@@ -328,16 +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");
 }
@@ -345,18 +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)