Merge branch 'pds_core-pci-reset'

Shannon Nelson says:

====================
pds_core: add PCI reset handling

Make sure pds_core can handle and recover from PCI function resets and
similar PCI bus issues: add detection and handlers for PCI problems.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/amd/pds_core/core.c

@@ -445,12 +445,13 @@ int pdsc_setup(struct pdsc *pdsc, bool init)
 		goto err_out_teardown;
 
 	/* Set up the VIFs */
+	if (init) {
 		err = pdsc_viftypes_init(pdsc);
 		if (err)
 			goto err_out_teardown;
 
-	if (init)
 		pdsc_debugfs_add_viftype(pdsc);
+	}
 
 	clear_bit(PDSC_S_FW_DEAD, &pdsc->state);
 	return 0;
@@ -469,8 +470,10 @@ void pdsc_teardown(struct pdsc *pdsc, bool removing)
 	pdsc_qcq_free(pdsc, &pdsc->notifyqcq);
 	pdsc_qcq_free(pdsc, &pdsc->adminqcq);
 
+	if (removing) {
 		kfree(pdsc->viftype_status);
 		pdsc->viftype_status = NULL;
+	}
 
 	if (pdsc->intr_info) {
 		for (i = 0; i < pdsc->nintrs; i++)
@@ -512,7 +515,7 @@ void pdsc_stop(struct pdsc *pdsc)
 					   PDS_CORE_INTR_MASK_SET);
 }
 
-static void pdsc_fw_down(struct pdsc *pdsc)
+void pdsc_fw_down(struct pdsc *pdsc)
 {
 	union pds_core_notifyq_comp reset_event = {
 		.reset.ecode = cpu_to_le16(PDS_EVENT_RESET),
@@ -520,10 +523,13 @@ static void pdsc_fw_down(struct pdsc *pdsc)
 	};
 
 	if (test_and_set_bit(PDSC_S_FW_DEAD, &pdsc->state)) {
-		dev_err(pdsc->dev, "%s: already happening\n", __func__);
+		dev_warn(pdsc->dev, "%s: already happening\n", __func__);
 		return;
 	}
 
+	if (pdsc->pdev->is_virtfn)
+		return;
+
 	/* Notify clients of fw_down */
 	if (pdsc->fw_reporter)
 		devlink_health_report(pdsc->fw_reporter, "FW down reported", pdsc);
@@ -533,7 +539,7 @@ static void pdsc_fw_down(struct pdsc *pdsc)
 	pdsc_teardown(pdsc, PDSC_TEARDOWN_RECOVERY);
 }
 
-static void pdsc_fw_up(struct pdsc *pdsc)
+void pdsc_fw_up(struct pdsc *pdsc)
 {
 	union pds_core_notifyq_comp reset_event = {
 		.reset.ecode = cpu_to_le16(PDS_EVENT_RESET),
@@ -546,6 +552,11 @@ static void pdsc_fw_up(struct pdsc *pdsc)
 		return;
 	}
 
+	if (pdsc->pdev->is_virtfn) {
+		clear_bit(PDSC_S_FW_DEAD, &pdsc->state);
+		return;
+	}
+
 	err = pdsc_setup(pdsc, PDSC_SETUP_RECOVERY);
 	if (err)
 		goto err_out;
@@ -567,6 +578,18 @@ err_out:
 	pdsc_teardown(pdsc, PDSC_TEARDOWN_RECOVERY);
 }
 
+static void pdsc_check_pci_health(struct pdsc *pdsc)
+{
+	u8 fw_status = ioread8(&pdsc->info_regs->fw_status);
+
+	/* is PCI broken? */
+	if (fw_status != PDS_RC_BAD_PCI)
+		return;
+
+	pdsc_reset_prepare(pdsc->pdev);
+	pdsc_reset_done(pdsc->pdev);
+}
+
 void pdsc_health_thread(struct work_struct *work)
 {
 	struct pdsc *pdsc = container_of(work, struct pdsc, health_work);
@@ -593,6 +616,8 @@ void pdsc_health_thread(struct work_struct *work)
 			pdsc_fw_down(pdsc);
 	}
 
+	pdsc_check_pci_health(pdsc);
+
 	pdsc->fw_generation = pdsc->fw_status & PDS_CORE_FW_STS_F_GENERATION;
 
 out_unlock:

drivers/net/ethernet/amd/pds_core/core.h

@@ -283,6 +283,9 @@ int pdsc_devcmd_reset(struct pdsc *pdsc);
 int pdsc_dev_reinit(struct pdsc *pdsc);
 int pdsc_dev_init(struct pdsc *pdsc);
 
+void pdsc_reset_prepare(struct pci_dev *pdev);
+void pdsc_reset_done(struct pci_dev *pdev);
+
 int pdsc_intr_alloc(struct pdsc *pdsc, char *name,
 		    irq_handler_t handler, void *data);
 void pdsc_intr_free(struct pdsc *pdsc, int index);
@@ -309,4 +312,8 @@ irqreturn_t pdsc_adminq_isr(int irq, void *data);
 
 int pdsc_firmware_update(struct pdsc *pdsc, const struct firmware *fw,
 			 struct netlink_ext_ack *extack);
+
+void pdsc_fw_down(struct pdsc *pdsc);
+void pdsc_fw_up(struct pdsc *pdsc);
+
 #endif /* _PDSC_H_ */

drivers/net/ethernet/amd/pds_core/dev.c

@@ -42,6 +42,8 @@ int pdsc_err_to_errno(enum pds_core_status_code code)
 		return -ERANGE;
 	case PDS_RC_BAD_ADDR:
 		return -EFAULT;
+	case PDS_RC_BAD_PCI:
+		return -ENXIO;
 	case PDS_RC_EOPCODE:
 	case PDS_RC_EINTR:
 	case PDS_RC_DEV_CMD:
@@ -62,7 +64,7 @@ bool pdsc_is_fw_running(struct pdsc *pdsc)
 	/* Firmware is useful only if the running bit is set and
 	 * fw_status != 0xff (bad PCI read)
 	 */
-	return (pdsc->fw_status != 0xff) &&
+	return (pdsc->fw_status != PDS_RC_BAD_PCI) &&
 		(pdsc->fw_status & PDS_CORE_FW_STS_F_RUNNING);
 }
 
@@ -128,6 +130,7 @@ static int pdsc_devcmd_wait(struct pdsc *pdsc, u8 opcode, int max_seconds)
 	unsigned long max_wait;
 	unsigned long duration;
 	int timeout = 0;
+	bool running;
 	int done = 0;
 	int err = 0;
 	int status;
@@ -136,6 +139,10 @@ static int pdsc_devcmd_wait(struct pdsc *pdsc, u8 opcode, int max_seconds)
 	max_wait = start_time + (max_seconds * HZ);
 
 	while (!done && !timeout) {
+		running = pdsc_is_fw_running(pdsc);
+		if (!running)
+			break;
+
 		done = pdsc_devcmd_done(pdsc);
 		if (done)
 			break;
@@ -152,7 +159,7 @@ static int pdsc_devcmd_wait(struct pdsc *pdsc, u8 opcode, int max_seconds)
 		dev_dbg(dev, "DEVCMD %d %s after %ld secs\n",
 			opcode, pdsc_devcmd_str(opcode), duration / HZ);
 
-	if (!done || timeout) {
+	if ((!done || timeout) && running) {
 		dev_err(dev, "DEVCMD %d %s timeout, done %d timeout %d max_seconds=%d\n",
 			opcode, pdsc_devcmd_str(opcode), done, timeout,
 			max_seconds);

drivers/net/ethernet/amd/pds_core/main.c

@@ -445,12 +445,62 @@ static void pdsc_remove(struct pci_dev *pdev)
 	devlink_free(dl);
 }
 
+void pdsc_reset_prepare(struct pci_dev *pdev)
+{
+	struct pdsc *pdsc = pci_get_drvdata(pdev);
+
+	pdsc_fw_down(pdsc);
+
+	pci_free_irq_vectors(pdev);
+	pdsc_unmap_bars(pdsc);
+	pci_release_regions(pdev);
+	pci_disable_device(pdev);
+}
+
+void pdsc_reset_done(struct pci_dev *pdev)
+{
+	struct pdsc *pdsc = pci_get_drvdata(pdev);
+	struct device *dev = pdsc->dev;
+	int err;
+
+	err = pci_enable_device(pdev);
+	if (err) {
+		dev_err(dev, "Cannot enable PCI device: %pe\n", ERR_PTR(err));
+		return;
+	}
+	pci_set_master(pdev);
+
+	if (!pdev->is_virtfn) {
+		pcie_print_link_status(pdsc->pdev);
+
+		err = pci_request_regions(pdsc->pdev, PDS_CORE_DRV_NAME);
+		if (err) {
+			dev_err(pdsc->dev, "Cannot request PCI regions: %pe\n",
+				ERR_PTR(err));
+			return;
+		}
+
+		err = pdsc_map_bars(pdsc);
+		if (err)
+			return;
+	}
+
+	pdsc_fw_up(pdsc);
+}
+
+static const struct pci_error_handlers pdsc_err_handler = {
+	/* FLR handling */
+	.reset_prepare      = pdsc_reset_prepare,
+	.reset_done         = pdsc_reset_done,
+};
+
 static struct pci_driver pdsc_driver = {
 	.name = PDS_CORE_DRV_NAME,
 	.id_table = pdsc_id_table,
 	.probe = pdsc_probe,
 	.remove = pdsc_remove,
 	.sriov_configure = pdsc_sriov_configure,
+	.err_handler = &pdsc_err_handler,
 };
 
 void *pdsc_get_pf_struct(struct pci_dev *vf_pdev)

include/linux/pds/pds_core_if.h

@@ -79,6 +79,7 @@ enum pds_core_status_code {
 	PDS_RC_EVFID	= 31,	/* VF ID does not exist */
 	PDS_RC_BAD_FW	= 32,	/* FW file is invalid or corrupted */
 	PDS_RC_ECLIENT	= 33,   /* No such client id */
+	PDS_RC_BAD_PCI	= 255,  /* Broken PCI when reading status */
 };
 
 /**