+static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev,
+ pci_channel_state_t state)
+{
+ struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
+ struct mlx5_priv *priv = &dev->priv;
+
+ dev_info(&pdev->dev, "%s was called\n", __func__);
+ mlx5_enter_error_state(dev);
+ mlx5_unload_one(dev, priv);
+ mlx5_pci_disable_device(dev);
+ return state == pci_channel_io_perm_failure ?
+ PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_NEED_RESET;
+}
+
+static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev)
+{
+ struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
+ int err = 0;
+
+ dev_info(&pdev->dev, "%s was called\n", __func__);
+
+ err = mlx5_pci_enable_device(dev);
+ if (err) {
+ dev_err(&pdev->dev, "%s: mlx5_pci_enable_device failed with error code: %d\n"
+ , __func__, err);
+ return PCI_ERS_RESULT_DISCONNECT;
+ }
+ pci_set_master(pdev);
+ pci_set_power_state(pdev, PCI_D0);
+ pci_restore_state(pdev);
+
+ return err ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED;
+}
+
+void mlx5_disable_device(struct mlx5_core_dev *dev)
+{
+ mlx5_pci_err_detected(dev->pdev, 0);
+}
+
+/* wait for the device to show vital signs. For now we check
+ * that we can read the device ID and that the health buffer
+ * shows a non zero value which is different than 0xffffffff
+ */
+static void wait_vital(struct pci_dev *pdev)
+{
+ struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
+ struct mlx5_core_health *health = &dev->priv.health;
+ const int niter = 100;
+ u32 count;
+ u16 did;
+ int i;
+
+ /* Wait for firmware to be ready after reset */
+ msleep(1000);
+ for (i = 0; i < niter; i++) {
+ if (pci_read_config_word(pdev, 2, &did)) {
+ dev_warn(&pdev->dev, "failed reading config word\n");
+ break;
+ }
+ if (did == pdev->device) {
+ dev_info(&pdev->dev, "device ID correctly read after %d iterations\n", i);
+ break;
+ }
+ msleep(50);
+ }
+ if (i == niter)
+ dev_warn(&pdev->dev, "%s-%d: could not read device ID\n", __func__, __LINE__);
+
+ for (i = 0; i < niter; i++) {
+ count = ioread32be(health->health_counter);
+ if (count && count != 0xffffffff) {
+ dev_info(&pdev->dev, "Counter value 0x%x after %d iterations\n", count, i);
+ break;
+ }
+ msleep(50);
+ }
+
+ if (i == niter)
+ dev_warn(&pdev->dev, "%s-%d: could not read device ID\n", __func__, __LINE__);
+}
+
+static void mlx5_pci_resume(struct pci_dev *pdev)
+{
+ struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
+ struct mlx5_priv *priv = &dev->priv;
+ int err;
+
+ dev_info(&pdev->dev, "%s was called\n", __func__);
+
+ pci_save_state(pdev);
+ wait_vital(pdev);
+
+ err = mlx5_load_one(dev, priv);
+ if (err)
+ dev_err(&pdev->dev, "%s: mlx5_load_one failed with error code: %d\n"
+ , __func__, err);
+ else
+ dev_info(&pdev->dev, "%s: device recovered\n", __func__);
+}
+
+static const struct pci_error_handlers mlx5_err_handler = {
+ .error_detected = mlx5_pci_err_detected,
+ .slot_reset = mlx5_pci_slot_reset,
+ .resume = mlx5_pci_resume
+};
+