Commit 2a0a839b authored by Moti Haimovski's avatar Moti Haimovski Committed by Oded Gabbay
Browse files

habanalabs: extend fatal messages to contain PCI info



This commit attaches the PCI device address to driver fatal messages
in order to ease debugging in multi-device setups.

Signed-off-by: default avatarMoti Haimovski <mhaimovski@habana.ai>
Reviewed-by: default avatarOded Gabbay <ogabbay@kernel.org>
Signed-off-by: default avatarOded Gabbay <ogabbay@kernel.org>
parent eaca606e
Loading
Loading
Loading
Loading
+25 −13
Original line number Diff line number Diff line
@@ -1563,7 +1563,8 @@ int hl_device_reset(struct hl_device *hdev, u32 flags)
		if (rc == -EBUSY) {
			if (hdev->device_fini_pending) {
				dev_crit(hdev->dev,
					"Failed to kill all open processes, stopping hard reset\n");
					"%s Failed to kill all open processes, stopping hard reset\n",
					dev_name(&(hdev)->pdev->dev));
				goto out_err;
			}

@@ -1573,7 +1574,8 @@ int hl_device_reset(struct hl_device *hdev, u32 flags)

		if (rc) {
			dev_crit(hdev->dev,
				"Failed to kill all open processes, stopping hard reset\n");
				"%s Failed to kill all open processes, stopping hard reset\n",
				dev_name(&(hdev)->pdev->dev));
			goto out_err;
		}

@@ -1624,14 +1626,16 @@ int hl_device_reset(struct hl_device *hdev, u32 flags)
			 * ensure driver puts the driver in a unusable state
			 */
			dev_crit(hdev->dev,
				"Consecutive FW fatal errors received, stopping hard reset\n");
				"%s Consecutive FW fatal errors received, stopping hard reset\n",
				dev_name(&(hdev)->pdev->dev));
			rc = -EIO;
			goto out_err;
		}

		if (hdev->kernel_ctx) {
			dev_crit(hdev->dev,
				"kernel ctx was alive during hard reset, something is terribly wrong\n");
				"%s kernel ctx was alive during hard reset, something is terribly wrong\n",
				dev_name(&(hdev)->pdev->dev));
			rc = -EBUSY;
			goto out_err;
		}
@@ -1749,9 +1753,13 @@ int hl_device_reset(struct hl_device *hdev, u32 flags)
	hdev->reset_info.needs_reset = false;

	if (hard_reset)
		dev_info(hdev->dev, "Successfully finished resetting the device\n");
		dev_info(hdev->dev,
			 "Successfully finished resetting the %s device\n",
			 dev_name(&(hdev)->pdev->dev));
	else
		dev_dbg(hdev->dev, "Successfully finished resetting the device\n");
		dev_dbg(hdev->dev,
			"Successfully finished resetting the %s device\n",
			dev_name(&(hdev)->pdev->dev));

	if (hard_reset) {
		hdev->reset_info.hard_reset_cnt++;
@@ -1786,7 +1794,9 @@ int hl_device_reset(struct hl_device *hdev, u32 flags)
	hdev->reset_info.in_compute_reset = 0;

	if (hard_reset) {
		dev_err(hdev->dev, "Failed to reset! Device is NOT usable\n");
		dev_err(hdev->dev,
			"%s Failed to reset! Device is NOT usable\n",
			dev_name(&(hdev)->pdev->dev));
		hdev->reset_info.hard_reset_cnt++;
	} else if (reset_upon_device_release) {
		spin_unlock(&hdev->reset_info.lock);
@@ -2185,7 +2195,8 @@ int hl_device_init(struct hl_device *hdev, struct class *hclass)
	}

	dev_notice(hdev->dev,
		"Successfully added device to habanalabs driver\n");
		"Successfully added device %s to habanalabs driver\n",
		dev_name(&(hdev)->pdev->dev));

	hdev->init_done = true;

@@ -2234,11 +2245,11 @@ int hl_device_init(struct hl_device *hdev, struct class *hclass)
		device_cdev_sysfs_add(hdev);
	if (hdev->pdev)
		dev_err(&hdev->pdev->dev,
			"Failed to initialize hl%d. Device is NOT usable !\n",
			hdev->cdev_idx);
			"Failed to initialize hl%d. Device %s is NOT usable !\n",
			hdev->cdev_idx, dev_name(&(hdev)->pdev->dev));
	else
		pr_err("Failed to initialize hl%d. Device is NOT usable !\n",
			hdev->cdev_idx);
		pr_err("Failed to initialize hl%d. Device %s is NOT usable !\n",
			hdev->cdev_idx, dev_name(&(hdev)->pdev->dev));

	return rc;
}
@@ -2294,7 +2305,8 @@ void hl_device_fini(struct hl_device *hdev)

		if (ktime_compare(ktime_get(), timeout) > 0) {
			dev_crit(hdev->dev,
				"Failed to remove device because reset function did not finish\n");
				"%s Failed to remove device because reset function did not finish\n",
				dev_name(&(hdev)->pdev->dev));
			return;
		}
	}