From patchwork series 489611

https://patchwork.ozlabs.org//project/linuxppc-dev/list/?series=489611

Author: Fox Snowpatch

drivers/pci/pci.c

@@ -2246,7 +2246,7 @@ void pcie_clear_device_status(struct pci_dev *dev)
 	u16 sta;
 
 	pcie_capability_read_word(dev, PCI_EXP_DEVSTA, &sta);
-	pcie_capability_write_word(dev, PCI_EXP_DEVSTA, sta);
+	pcie_capability_write_word(dev, PCI_EXP_DEVSTA, sta & PCI_EXP_DEVSTA_ERR);
 }
 #endif
 

drivers/pci/pci.h

@@ -746,8 +746,10 @@ struct aer_err_info {
 	struct pcie_tlp_log tlp;	/* TLP Header */
 };
 
-int aer_get_device_error_info(struct aer_err_info *info, int i);
+int aer_get_device_error_info(struct aer_err_info *info, int i,
+			      bool link_healthy);
 void aer_print_error(struct aer_err_info *info, int i);
+void aer_report_frozen_error(struct pci_dev *dev);
 
 int pcie_read_tlp_log(struct pci_dev *dev, int where, int where2,
 		      unsigned int tlp_len, bool flit,
@@ -771,7 +773,7 @@ struct rcec_ea {
 void pci_save_dpc_state(struct pci_dev *dev);
 void pci_restore_dpc_state(struct pci_dev *dev);
 void pci_dpc_init(struct pci_dev *pdev);
-void dpc_process_error(struct pci_dev *pdev);
+struct pci_dev *dpc_process_error(struct pci_dev *pdev);
 pci_ers_result_t dpc_reset_link(struct pci_dev *pdev);
 bool pci_dpc_recovered(struct pci_dev *pdev);
 unsigned int dpc_tlp_log_len(struct pci_dev *dev);

drivers/pci/pcie/aer.c

@@ -1384,12 +1384,14 @@ EXPORT_SYMBOL_GPL(aer_recover_queue);
  * aer_get_device_error_info - read error status from dev and store it to info
  * @info: pointer to structure to store the error record
  * @i: index into info->dev[]
+ * @link_healthy: link is healthy or not
  *
  * Return: 1 on success, 0 on error.
  *
  * Note that @info is reused among all error devices. Clear fields properly.
  */
-int aer_get_device_error_info(struct aer_err_info *info, int i)
+int aer_get_device_error_info(struct aer_err_info *info, int i,
+			      bool link_healthy)
 {
 	struct pci_dev *dev;
 	int type, aer;
@@ -1420,7 +1422,8 @@ int aer_get_device_error_info(struct aer_err_info *info, int i)
 	} else if (type == PCI_EXP_TYPE_ROOT_PORT ||
 		   type == PCI_EXP_TYPE_RC_EC ||
 		   type == PCI_EXP_TYPE_DOWNSTREAM ||
-		   info->severity == AER_NONFATAL) {
+		   info->severity == AER_NONFATAL ||
+		   (info->severity == AER_FATAL && link_healthy)) {
 
 		/* Link is still healthy for IO reads */
 		pci_read_config_dword(dev, aer + PCI_ERR_UNCOR_STATUS,
@@ -1447,17 +1450,38 @@ int aer_get_device_error_info(struct aer_err_info *info, int i)
 	return 1;
 }
 
+void aer_report_frozen_error(struct pci_dev *dev)
+{
+	struct aer_err_info info;
+	int type = pci_pcie_type(dev);
+
+	if (type != PCI_EXP_TYPE_ENDPOINT && type != PCI_EXP_TYPE_RC_END)
+		return;
+
+	info.error_dev_num = 0;
+	info.severity = AER_FATAL;
+	info.level = KERN_ERR;
+	add_error_device(&info, dev);
+
+	if (aer_get_device_error_info(&info, 0, true)) {
+		pci_err(dev, "Errors reported prior to reset\n");
+		aer_print_error(&info, 0);
+	}
+
+	pci_dev_put(dev); /* pairs with pci_dev_get() in add_error_device() */
+}
+
 static inline void aer_process_err_devices(struct aer_err_info *e_info)
 {
 	int i;
 
 	/* Report all before handling them, to not lose records by reset etc. */
 	for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) {
-		if (aer_get_device_error_info(e_info, i))
+		if (aer_get_device_error_info(e_info, i, false))
 			aer_print_error(e_info, i);
 	}
 	for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) {
-		if (aer_get_device_error_info(e_info, i))
+		if (aer_get_device_error_info(e_info, i, false))
 			handle_error_source(e_info->dev[i], e_info);
 	}
 }

drivers/pci/pcie/dpc.c

@@ -260,10 +260,20 @@ static int dpc_get_aer_uncorrect_severity(struct pci_dev *dev,
 	return 1;
 }
 
-void dpc_process_error(struct pci_dev *pdev)
+/**
+ * dpc_process_error - handle the DPC error status
+ * @pdev: the port that experienced the containment event
+ *
+ * Return: the device that detected the error.
+ *
+ * NOTE: The device reference count is increased, the caller must decrement
+ * the reference count by calling pci_dev_put().
+ */
+struct pci_dev *dpc_process_error(struct pci_dev *pdev)
 {
 	u16 cap = pdev->dpc_cap, status, source, reason, ext_reason;
 	struct aer_err_info info = {};
+	struct pci_dev *err_dev;
 
 	pci_read_config_word(pdev, cap + PCI_EXP_DPC_STATUS, &status);
 
@@ -274,11 +284,12 @@ void dpc_process_error(struct pci_dev *pdev)
 		pci_warn(pdev, "containment event, status:%#06x: unmasked uncorrectable error detected\n",
 			 status);
 		if (dpc_get_aer_uncorrect_severity(pdev, &info) &&
-		    aer_get_device_error_info(&info, 0)) {
+		    aer_get_device_error_info(&info, 0, false)) {
 			aer_print_error(&info, 0);
 			pci_aer_clear_nonfatal_status(pdev);
 			pci_aer_clear_fatal_status(pdev);
 		}
+		err_dev = pci_dev_get(pdev);
 		break;
 	case PCI_EXP_DPC_STATUS_TRIGGER_RSN_NFE:
 	case PCI_EXP_DPC_STATUS_TRIGGER_RSN_FE:
@@ -290,6 +301,8 @@ void dpc_process_error(struct pci_dev *pdev)
 				"ERR_FATAL" : "ERR_NONFATAL",
 			 pci_domain_nr(pdev->bus), PCI_BUS_NUM(source),
 			 PCI_SLOT(source), PCI_FUNC(source));
+		err_dev = pci_get_domain_bus_and_slot(pci_domain_nr(pdev->bus),
+					    PCI_BUS_NUM(source), source & 0xff);
 		break;
 	case PCI_EXP_DPC_STATUS_TRIGGER_RSN_IN_EXT:
 		ext_reason = status & PCI_EXP_DPC_STATUS_TRIGGER_RSN_EXT;
@@ -304,8 +317,11 @@ void dpc_process_error(struct pci_dev *pdev)
 		if (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_RP_PIO &&
 		    pdev->dpc_rp_extensions)
 			dpc_process_rp_pio_error(pdev);
+		err_dev = pci_dev_get(pdev);
 		break;
 	}
+
+	return err_dev;
 }
 
 static void pci_clear_surpdn_errors(struct pci_dev *pdev)
@@ -361,21 +377,22 @@ static bool dpc_is_surprise_removal(struct pci_dev *pdev)
 
 static irqreturn_t dpc_handler(int irq, void *context)
 {
-	struct pci_dev *pdev = context;
+	struct pci_dev *err_port = context, *err_dev;
 
 	/*
 	 * According to PCIe r6.0 sec 6.7.6, errors are an expected side effect
 	 * of async removal and should be ignored by software.
 	 */
-	if (dpc_is_surprise_removal(pdev)) {
-		dpc_handle_surprise_removal(pdev);
+	if (dpc_is_surprise_removal(err_port)) {
+		dpc_handle_surprise_removal(err_port);
 		return IRQ_HANDLED;
 	}
 
-	dpc_process_error(pdev);
+	err_dev = dpc_process_error(err_port);
 
 	/* We configure DPC so it only triggers on ERR_FATAL */
-	pcie_do_recovery(pdev, pci_channel_io_frozen, dpc_reset_link);
+	pcie_do_recovery(err_dev, pci_channel_io_frozen, dpc_reset_link);
+	pci_dev_put(err_dev);
 
 	return IRQ_HANDLED;
 }

drivers/pci/pcie/edr.c

@@ -150,7 +150,7 @@ static int acpi_send_edr_status(struct pci_dev *pdev, struct pci_dev *edev,
 
 static void edr_handle_event(acpi_handle handle, u32 event, void *data)
 {
-	struct pci_dev *pdev = data, *edev;
+	struct pci_dev *pdev = data, *err_port, *err_dev;
 	pci_ers_result_t estate = PCI_ERS_RESULT_DISCONNECT;
 	u16 status;
 
@@ -169,36 +169,37 @@ static void edr_handle_event(acpi_handle handle, u32 event, void *data)
 	 * may be that port or a parent of it (PCI Firmware r3.3, sec
 	 * 4.6.13).
 	 */
-	edev = acpi_dpc_port_get(pdev);
-	if (!edev) {
+	err_port = acpi_dpc_port_get(pdev);
+	if (!err_port) {
 		pci_err(pdev, "Firmware failed to locate DPC port\n");
 		return;
 	}
 
-	pci_dbg(pdev, "Reported EDR dev: %s\n", pci_name(edev));
+	pci_dbg(pdev, "Reported EDR dev: %s\n", pci_name(err_port));
 
 	/* If port does not support DPC, just send the OST */
-	if (!edev->dpc_cap) {
-		pci_err(edev, FW_BUG "This device doesn't support DPC\n");
+	if (!err_port->dpc_cap) {
+		pci_err(err_port, FW_BUG "This device doesn't support DPC\n");
 		goto send_ost;
 	}
 
 	/* Check if there is a valid DPC trigger */
-	pci_read_config_word(edev, edev->dpc_cap + PCI_EXP_DPC_STATUS, &status);
+	pci_read_config_word(err_port, err_port->dpc_cap + PCI_EXP_DPC_STATUS, &status);
 	if (!(status & PCI_EXP_DPC_STATUS_TRIGGER)) {
-		pci_err(edev, "Invalid DPC trigger %#010x\n", status);
+		pci_err(err_port, "Invalid DPC trigger %#010x\n", status);
 		goto send_ost;
 	}
 
-	dpc_process_error(edev);
-	pci_aer_raw_clear_status(edev);
+	err_dev = dpc_process_error(err_port);
+	pci_aer_raw_clear_status(err_port);
 
 	/*
 	 * Irrespective of whether the DPC event is triggered by ERR_FATAL
 	 * or ERR_NONFATAL, since the link is already down, use the FATAL
 	 * error recovery path for both cases.
 	 */
-	estate = pcie_do_recovery(edev, pci_channel_io_frozen, dpc_reset_link);
+	estate = pcie_do_recovery(err_dev, pci_channel_io_frozen, dpc_reset_link);
+	pci_dev_put(err_dev);
 
 send_ost:
 
@@ -207,15 +208,15 @@ static void edr_handle_event(acpi_handle handle, u32 event, void *data)
 	 * to firmware. If not successful, send _OST(0xF, BDF << 16 | 0x81).
 	 */
 	if (estate == PCI_ERS_RESULT_RECOVERED) {
-		pci_dbg(edev, "DPC port successfully recovered\n");
-		pcie_clear_device_status(edev);
-		acpi_send_edr_status(pdev, edev, EDR_OST_SUCCESS);
+		pci_dbg(err_port, "DPC port successfully recovered\n");
+		pcie_clear_device_status(err_port);
+		acpi_send_edr_status(pdev, err_port, EDR_OST_SUCCESS);
 	} else {
-		pci_dbg(edev, "DPC port recovery failed\n");
-		acpi_send_edr_status(pdev, edev, EDR_OST_FAILED);
+		pci_dbg(err_port, "DPC port recovery failed\n");
+		acpi_send_edr_status(pdev, err_port, EDR_OST_FAILED);
 	}
 
-	pci_dev_put(edev);
+	pci_dev_put(err_port);
 }
 
 void pci_acpi_add_edr_notifier(struct pci_dev *pdev)

drivers/pci/pcie/err.c

@@ -253,6 +253,11 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev,
 			pci_warn(bridge, "subordinate device reset failed\n");
 			goto failed;
 		}
+
+		/* Link recovered, report fatal errors of RCiEP or EP */
+		if (state == pci_channel_io_frozen)
+			aer_report_frozen_error(dev);
+
 	}
 
 	if (status == PCI_ERS_RESULT_NEED_RESET) {
@@ -280,7 +285,7 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev,
 	 */
 	if (host->native_aer || pcie_ports_native) {
 		pcie_clear_device_status(dev);
-		pci_aer_clear_nonfatal_status(dev);
+		pci_aer_raw_clear_status(dev);
 	}
 
 	pci_walk_bridge(bridge, pci_pm_runtime_put, NULL);

include/uapi/linux/pci_regs.h

@@ -534,6 +534,7 @@
 #define  PCI_EXP_DEVSTA_NFED	0x0002	/* Non-Fatal Error Detected */
 #define  PCI_EXP_DEVSTA_FED	0x0004	/* Fatal Error Detected */
 #define  PCI_EXP_DEVSTA_URD	0x0008	/* Unsupported Request Detected */
+#define  PCI_EXP_DEVSTA_ERR	0xf	/* Error bits */
 #define  PCI_EXP_DEVSTA_AUXPD	0x0010	/* AUX Power Detected */
 #define  PCI_EXP_DEVSTA_TRPND	0x0020	/* Transactions Pending */
 #define PCI_CAP_EXP_RC_ENDPOINT_SIZEOF_V1	12	/* v1 endpoints without link end here */