2 files changed, 54 insertions, 29 deletions

diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c
index 77accd029c4a..89af1006df55 100644
--- a/drivers/accel/ivpu/ivpu_hw_37xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_37xx.c
@@ -510,16 +510,6 @@ static int ivpu_boot_pwr_domain_enable(struct ivpu_device *vdev)
 	return ret;
 }
 
-static int ivpu_boot_pwr_domain_disable(struct ivpu_device *vdev)
-{
-	ivpu_boot_dpu_active_drive(vdev, false);
-	ivpu_boot_pwr_island_isolation_drive(vdev, true);
-	ivpu_boot_pwr_island_trickle_drive(vdev, false);
-	ivpu_boot_pwr_island_drive(vdev, false);
-
-	return ivpu_boot_wait_for_pwr_island_status(vdev, 0x0);
-}
-
 static void ivpu_boot_no_snoop_enable(struct ivpu_device *vdev)
 {
 	u32 val = REGV_RD32(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES);
@@ -616,12 +606,37 @@ static int ivpu_hw_37xx_info_init(struct ivpu_device *vdev)
 	return 0;
 }
 
+static int ivpu_hw_37xx_ip_reset(struct ivpu_device *vdev)
+{
+	int ret;
+	u32 val;
+
+	if (IVPU_WA(punit_disabled))
+		return 0;
+
+	ret = REGB_POLL_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, 0, TIMEOUT_US);
+	if (ret) {
+		ivpu_err(vdev, "Timed out waiting for TRIGGER bit\n");
+		return ret;
+	}
+
+	val = REGB_RD32(VPU_37XX_BUTTRESS_VPU_IP_RESET);
+	val = REG_SET_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, val);
+	REGB_WR32(VPU_37XX_BUTTRESS_VPU_IP_RESET, val);
+
+	ret = REGB_POLL_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, 0, TIMEOUT_US);
+	if (ret)
+		ivpu_err(vdev, "Timed out waiting for RESET completion\n");
+
+	return ret;
+}
+
 static int ivpu_hw_37xx_reset(struct ivpu_device *vdev)
 {
 	int ret = 0;
 
-	if (ivpu_boot_pwr_domain_disable(vdev)) {
-		ivpu_err(vdev, "Failed to disable power domain\n");
+	if (ivpu_hw_37xx_ip_reset(vdev)) {
+		ivpu_err(vdev, "Failed to reset NPU\n");
 		ret = -EIO;
 	}
 
@@ -661,6 +676,11 @@ static int ivpu_hw_37xx_power_up(struct ivpu_device *vdev)
 {
 	int ret;
 
+	/* PLL requests may fail when powering down, so issue WP 0 here */
+	ret = ivpu_pll_disable(vdev);
+	if (ret)
+		ivpu_warn(vdev, "Failed to disable PLL: %d\n", ret);
+
 	ret = ivpu_hw_37xx_d0i3_disable(vdev);
 	if (ret)
 		ivpu_warn(vdev, "Failed to disable D0I3: %d\n", ret);
diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
index 981777c93cf5..814882ae5059 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -58,11 +58,14 @@ static int ivpu_suspend(struct ivpu_device *vdev)
 {
 	int ret;
 
+	/* Save PCI state before powering down as it sometimes gets corrupted if NPU hangs */
+	pci_save_state(to_pci_dev(vdev->drm.dev));
+
 	ret = ivpu_shutdown(vdev);
-	if (ret) {
+	if (ret)
 		ivpu_err(vdev, "Failed to shutdown VPU: %d\n", ret);
-		return ret;
-	}
+
+	pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot);
 
 	return ret;
 }
@@ -71,6 +74,9 @@ static int ivpu_resume(struct ivpu_device *vdev)
 {
 	int ret;
 
+	pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D0);
+	pci_restore_state(to_pci_dev(vdev->drm.dev));
+
 retry:
 	ret = ivpu_hw_power_up(vdev);
 	if (ret) {
@@ -120,15 +126,20 @@ static void ivpu_pm_recovery_work(struct work_struct *work)
 
 	ivpu_fw_log_dump(vdev);
 
-retry:
-	ret = pci_try_reset_function(to_pci_dev(vdev->drm.dev));
-	if (ret == -EAGAIN && !drm_dev_is_unplugged(&vdev->drm)) {
-		cond_resched();
-		goto retry;
-	}
+	atomic_inc(&vdev->pm->reset_counter);
+	atomic_set(&vdev->pm->reset_pending, 1);
+	down_write(&vdev->pm->reset_lock);
+
+	ivpu_suspend(vdev);
+	ivpu_pm_prepare_cold_boot(vdev);
+	ivpu_jobs_abort_all(vdev);
+
+	ret = ivpu_resume(vdev);
+	if (ret)
+		ivpu_err(vdev, "Failed to resume NPU: %d\n", ret);
 
-	if (ret && ret != -EAGAIN)
-		ivpu_err(vdev, "Failed to reset VPU: %d\n", ret);
+	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);
@@ -200,9 +211,6 @@ int ivpu_pm_suspend_cb(struct device *dev)
 	ivpu_suspend(vdev);
 	ivpu_pm_prepare_warm_boot(vdev);
 
-	pci_save_state(to_pci_dev(dev));
-	pci_set_power_state(to_pci_dev(dev), PCI_D3hot);
-
 	ivpu_dbg(vdev, PM, "Suspend done.\n");
 
 	return 0;
@@ -216,9 +224,6 @@ int ivpu_pm_resume_cb(struct device *dev)
 
 	ivpu_dbg(vdev, PM, "Resume..\n");
 
-	pci_set_power_state(to_pci_dev(dev), PCI_D0);
-	pci_restore_state(to_pci_dev(dev));
-
 	ret = ivpu_resume(vdev);
 	if (ret)
 		ivpu_err(vdev, "Failed to resume: %d\n", ret);