Address error and recovery for AER and DPC

index 6402f7f..fd053e5 100644
@@ -462,7 +462,7 @@ static void ghes_do_proc(struct ghes *ghes,
 				 * use, so treat it as a fatal AER error.
 				 */
 				if (gdata->flags & CPER_SEC_RESET)
-					aer_severity = AER_FATAL;
+					aer_severity = PCI_ERR_AER_FATAL;
 
 				aer_recover_queue(pcie_err->device_id.segment,
 						  pcie_err->device_id.bus,

index 5449e5c..bc9db53 100644
@@ -76,36 +76,6 @@ struct aer_rpc {
 					 */
 };
 
-struct aer_broadcast_data {
-	enum pci_channel_state state;
-	enum pci_ers_result result;
-};
-
-static inline pci_ers_result_t merge_result(enum pci_ers_result orig,
-		enum pci_ers_result new)
-{
-	if (new == PCI_ERS_RESULT_NO_AER_DRIVER)
-		return PCI_ERS_RESULT_NO_AER_DRIVER;
-
-	if (new == PCI_ERS_RESULT_NONE)
-		return orig;
-
-	switch (orig) {
-	case PCI_ERS_RESULT_CAN_RECOVER:
-	case PCI_ERS_RESULT_RECOVERED:
-		orig = new;
-		break;
-	case PCI_ERS_RESULT_DISCONNECT:
-		if (new == PCI_ERS_RESULT_NEED_RESET)
-			orig = PCI_ERS_RESULT_NEED_RESET;
-		break;
-	default:
-		break;
-	}
-
-	return orig;
-}
-
 extern struct bus_type pcie_port_bus_type;
 void aer_isr(struct work_struct *work);
 void aer_print_error(struct pci_dev *dev, struct aer_err_info *info);

373 lines not on this page · raw message

index 54c4b69..222c56c 100644
@@ -29,11 +29,14 @@
 #define AER_AGENT_COMPLETER		2
 #define AER_AGENT_TRANSMITTER		3
 
-#define AER_AGENT_REQUESTER_MASK(t)	((t == AER_CORRECTABLE) ?	\
+#define AER_AGENT_REQUESTER_MASK(t)		\
+	((t == PCI_ERR_AER_CORRECTABLE) ?	\
 	0 : (PCI_ERR_UNC_COMP_TIME|PCI_ERR_UNC_UNSUP))
-#define AER_AGENT_COMPLETER_MASK(t)	((t == AER_CORRECTABLE) ?	\
+#define AER_AGENT_COMPLETER_MASK(t)		\
+	((t == PCI_ERR_AER_CORRECTABLE) ?	\
 	0 : PCI_ERR_UNC_COMP_ABORT)
-#define AER_AGENT_TRANSMITTER_MASK(t)	((t == AER_CORRECTABLE) ?	\
+#define AER_AGENT_TRANSMITTER_MASK(t)		\
+	((t == PCI_ERR_AER_CORRECTABLE) ?	\
 	(PCI_ERR_COR_REP_ROLL|PCI_ERR_COR_REP_TIMER) : 0)
 
 #define AER_GET_AGENT(t, e)						\

@@ -46,9 +49,11 @@
 #define AER_DATA_LINK_LAYER_ERROR	1
 #define AER_TRANSACTION_LAYER_ERROR	2
 
-#define AER_PHYSICAL_LAYER_ERROR_MASK(t) ((t == AER_CORRECTABLE) ?	\
+#define AER_PHYSICAL_LAYER_ERROR_MASK(t)	\
+	((t == PCI_ERR_AER_CORRECTABLE) ?	\
 	PCI_ERR_COR_RCVR : 0)
-#define AER_DATA_LINK_LAYER_ERROR_MASK(t) ((t == AER_CORRECTABLE) ?	\
+#define AER_DATA_LINK_LAYER_ERROR_MASK(t)	\
+	((t == PCI_ERR_AER_CORRECTABLE) ?	\
 	(PCI_ERR_COR_BAD_TLP|						\
 	PCI_ERR_COR_BAD_DLLP|						\
 	PCI_ERR_COR_REP_ROLL|						\

@@ -147,7 +152,7 @@ static void __aer_print_error(struct pci_dev *dev,
 		if (!(status & (1 << i)))
 			continue;
 
-		if (info->severity == AER_CORRECTABLE)
+		if (info->severity == PCI_ERR_AER_CORRECTABLE)
 			errmsg = i < ARRAY_SIZE(aer_correctable_error_string) ?
 				aer_correctable_error_string[i] : NULL;
 		else

@@ -210,11 +215,11 @@ int cper_severity_to_aer(int cper_severity)
 {
 	switch (cper_severity) {
 	case CPER_SEV_RECOVERABLE:
-		return AER_NONFATAL;
+		return PCI_ERR_AER_NONFATAL;
 	case CPER_SEV_FATAL:
-		return AER_FATAL;
+		return PCI_ERR_AER_FATAL;
 	default:
-		return AER_CORRECTABLE;
+		return PCI_ERR_AER_CORRECTABLE;
 	}
 }
 EXPORT_SYMBOL_GPL(cper_severity_to_aer);

@@ -226,7 +231,7 @@ void cper_print_aer(struct pci_dev *dev, int aer_severity,
 	u32 status, mask;
 	const char **status_strs;
 
-	if (aer_severity == AER_CORRECTABLE) {
+	if (aer_severity == PCI_ERR_AER_CORRECTABLE) {
 		status = aer->cor_status;
 		mask = aer->cor_mask;
 		status_strs = aer_correctable_error_string;

@@ -247,7 +252,7 @@ void cper_print_aer(struct pci_dev *dev, int aer_severity,
 	dev_err(&dev->dev, "aer_layer=%s, aer_agent=%s\n",
 		aer_error_layer[layer], aer_agent_string[agent]);
 
-	if (aer_severity != AER_CORRECTABLE)
+	if (aer_severity != PCI_ERR_AER_CORRECTABLE)
 		dev_err(&dev->dev, "aer_uncor_severity: 0x%08x\n",
 			aer->uncor_severity);
 

333 lines not on this page · raw message

index a854bc5..4f1992d 100644
@@ -79,4 +79,5 @@ static inline void pcie_port_platform_notify(struct pci_dev *port, int *mask)
 static inline void pcie_port_platform_notify(struct pci_dev *port, int *mask){}
 #endif /* !CONFIG_ACPI */
 
+struct pcie_port_service_driver *pci_find_aer_service(struct pci_dev *dev);
 #endif /* _PORTDRV_H_ */

index 8f87bbe..3eac8ed 100644
@@ -11,10 +11,6 @@
 #include <linux/errno.h>
 #include <linux/types.h>
 
-#define AER_NONFATAL			0
-#define AER_FATAL			1
-#define AER_CORRECTABLE			2
-
 struct pci_dev;
 
 struct aer_header_log_regs {

index c170c92..083408e 100644
@@ -739,6 +739,10 @@ struct pci_error_handlers {
 	void (*resume)(struct pci_dev *dev);
 };
 
+struct pci_err_broadcast_data {
+	enum pci_channel_state state;
+	enum pci_ers_result result;
+};
 
 struct module;
 struct pci_driver {

@@ -1998,6 +2002,23 @@ static inline resource_size_t pci_iov_resource_size(struct pci_dev *dev, int res
 void pci_hp_remove_module_link(struct pci_slot *pci_slot);
 #endif
 
+#define PCI_ERR_AER_NONFATAL		0
+#define PCI_ERR_AER_FATAL		1
+#define PCI_ERR_AER_CORRECTABLE		2
+
+pci_ers_result_t pci_broadcast_error_message(struct pci_dev *dev,
+					enum pci_channel_state state,
+					char *error_mesg,
+					int (*cb)(struct pci_dev *, void *));
+int pci_report_mmio_enabled(struct pci_dev *dev, void *data);
+int pci_report_slot_reset(struct pci_dev *dev, void *data);
+int pci_report_resume(struct pci_dev *dev, void *data);
+int pci_report_error_detected(struct pci_dev *dev, void *data);
+pci_ers_result_t pci_reset_link(struct pci_dev *dev);
+pci_ers_result_t pci_merge_result(enum pci_ers_result orig,
+				enum pci_ers_result new);
+void pci_do_recovery(struct pci_dev *dev, int severity);
+
 /**
  * pci_pcie_cap - get the saved PCIe capability offset
  * @dev: PCI device

index 2d976a6..e7ced58 100644
@@ -15,6 +15,9 @@
 #include <linux/pci.h>
 #include <linux/pcieport_if.h>
 #include "../pci.h"
+#include "portdrv.h"
+
+static pci_ers_result_t dpc_reset_link(struct pci_dev *pdev);
 
 struct rp_pio_header_log_regs {
 	u32 dw0;

@@ -67,6 +70,60 @@ struct dpc_dev {
 	"Memory Request Completion Timeout",		 /* Bit Position 18 */
 };
 
+static int find_dpc_dev_iter(struct device *device, void *data)
+{
+	struct pcie_port_service_driver *service_driver;
+	struct device **dev;
+
+	dev = (struct device **) data;
+
+	if (device->bus == &pcie_port_bus_type && device->driver) {
+		service_driver = to_service_driver(device->driver);
+		if (service_driver->service == PCIE_PORT_SERVICE_DPC) {
+			*dev = device;
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
+struct device *pci_find_dpc_dev(struct pci_dev *pdev)
+{
+	struct device *dev = NULL;
+
+	device_for_each_child(&pdev->dev, &dev, find_dpc_dev_iter);
+
+	return dev;
+}
+
+static int find_dpc_service_iter(struct device *device, void *data)
+{
+	struct pcie_port_service_driver *service_driver, **drv;
+
+	drv = (struct pcie_port_service_driver **) data;
+
+	if (device->bus == &pcie_port_bus_type && device->driver) {
+		service_driver = to_service_driver(device->driver);
+		if (service_driver->service == PCIE_PORT_SERVICE_DPC) {
+			*drv = service_driver;
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
+struct pcie_port_service_driver *pci_find_dpc_service(struct pci_dev *dev)
+{
+	struct pcie_port_service_driver *drv = NULL;
+
+	device_for_each_child(&dev->dev, &drv, find_dpc_service_iter);
+
+	return drv;
+}
+EXPORT_SYMBOL(pci_find_dpc_service);
+
 static int dpc_wait_rp_inactive(struct dpc_dev *dpc)
 {
 	unsigned long timeout = jiffies + HZ;

@@ -104,11 +161,23 @@ static void dpc_wait_link_inactive(struct dpc_dev *dpc)
 		dev_warn(dev, "Link state not disabled for DPC event\n");
 }
 
-static void interrupt_event_handler(struct work_struct *work)
+/**
+ * dpc_reset_link - reset link DPC  routine
+ * @dev: pointer to Root Port's pci_dev data structure
+ *
+ * Invoked by Port Bus driver when performing link reset at Root Port.
+ */
+static pci_ers_result_t dpc_reset_link(struct pci_dev *pdev)
 {
-	struct dpc_dev *dpc = container_of(work, struct dpc_dev, work);
-	struct pci_dev *dev, *temp, *pdev = dpc->dev->port;
 	struct pci_bus *parent = pdev->subordinate;
+	struct pci_dev *dev, *temp;
+	struct dpc_dev *dpc;
+	struct pcie_device *pciedev;
+	struct device *devdpc;
+
+	devdpc = pci_find_dpc_dev(pdev);
+	pciedev = to_pcie_device(devdpc);
+	dpc = get_service_data(pciedev);
 
 	pci_lock_rescan_remove();
 	list_for_each_entry_safe_reverse(dev, temp, &parent->devices,

@@ -125,7 +194,7 @@ static void interrupt_event_handler(struct work_struct *work)
 
 	dpc_wait_link_inactive(dpc);
 	if (dpc->rp && dpc_wait_rp_inactive(dpc))
-		return;
+		return PCI_ERS_RESULT_DISCONNECT;
 	if (dpc->rp && dpc->rp_pio_status) {
 		pci_write_config_dword(pdev,
 				      dpc->cap_pos + PCI_EXP_DPC_RP_PIO_STATUS,

@@ -135,6 +204,17 @@ static void interrupt_event_handler(struct work_struct *work)
 
 	pci_write_config_word(pdev, dpc->cap_pos + PCI_EXP_DPC_STATUS,
 		PCI_EXP_DPC_STATUS_TRIGGER | PCI_EXP_DPC_STATUS_INTERRUPT);
+
+	return PCI_ERS_RESULT_RECOVERED;
+}
+
+static void interrupt_event_handler(struct work_struct *work)
+{
+	struct dpc_dev *dpc = container_of(work, struct dpc_dev, work);
+	struct pci_dev *pdev = dpc->dev->port;
+
+	/* From DPC point of view error is always FATAL. */
+	pci_do_recovery(pdev, PCI_ERR_DPC_FATAL);
 }
 
 static void dpc_rp_pio_print_tlp_header(struct device *dev,

@@ -339,6 +419,7 @@ static void dpc_remove(struct pcie_device *dev)
 	.service	= PCIE_PORT_SERVICE_DPC,
 	.probe		= dpc_probe,
 	.remove		= dpc_remove,
+	.reset_link     = dpc_reset_link,
 };
 
 static int __init dpc_service_init(void)

index d59866c..8bac584 100644
@@ -176,7 +176,7 @@ static pci_ers_result_t pci_default_reset_link(struct pci_dev *dev)
 	return PCI_ERS_RESULT_RECOVERED;
 }
 
-pci_ers_result_t pci_reset_link(struct pci_dev *dev)
+pci_ers_result_t pci_reset_link(struct pci_dev *dev, int severity)
 {
 	struct pci_dev *udev;
 	pci_ers_result_t status;

@@ -191,7 +191,10 @@ pci_ers_result_t pci_reset_link(struct pci_dev *dev)
 	}
 
 	/* Use the aer driver of the component firstly */
-	driver = pci_find_aer_service(udev);
+	if (severity == PCI_ERR_DPC_FATAL)
+		driver = pci_find_dpc_service(udev);
+	else
+		driver = pci_find_aer_service(udev);
 
 	if (driver && driver->reset_link) {
 		status = driver->reset_link(udev);

@@ -280,7 +283,8 @@ void pci_do_recovery(struct pci_dev *dev, int severity)
 
 	mutex_lock(&pci_err_recovery_lock);
 
-	if (severity == PCI_ERR_AER_FATAL)
+	if ((severity == PCI_ERR_AER_FATAL) ||
+	    (severity == PCI_ERR_DPC_FATAL))
 		state = pci_channel_io_frozen;
 	else
 		state = pci_channel_io_normal;

@@ -290,8 +294,9 @@ void pci_do_recovery(struct pci_dev *dev, int severity)
 			"error_detected",
 			pci_report_error_detected);
 
-	if (severity == PCI_ERR_AER_FATAL) {
-		result = pci_reset_link(dev);
+	if ((severity == PCI_ERR_AER_FATAL) ||
+	    (severity == PCI_ERR_DPC_FATAL)) {
+		result = pci_reset_link(dev, severity);
 		if (result != PCI_ERS_RESULT_RECOVERED)
 			goto failed;
 	}

index 4f1992d..b013e24 100644
@@ -80,4 +80,5 @@ static inline void pcie_port_platform_notify(struct pci_dev *port, int *mask){}
 #endif /* !CONFIG_ACPI */
 
 struct pcie_port_service_driver *pci_find_aer_service(struct pci_dev *dev);
+struct pcie_port_service_driver *pci_find_dpc_service(struct pci_dev *dev);
 #endif /* _PORTDRV_H_ */

index 083408e..123ee15 100644
@@ -2005,6 +2005,7 @@ static inline resource_size_t pci_iov_resource_size(struct pci_dev *dev, int res
 #define PCI_ERR_AER_NONFATAL		0
 #define PCI_ERR_AER_FATAL		1
 #define PCI_ERR_AER_CORRECTABLE		2
+#define PCI_ERR_DPC_FATAL		4
 
 pci_ers_result_t pci_broadcast_error_message(struct pci_dev *dev,
 					enum pci_channel_state state,

@@ -2014,7 +2015,7 @@ pci_ers_result_t pci_broadcast_error_message(struct pci_dev *dev,
 int pci_report_slot_reset(struct pci_dev *dev, void *data);
 int pci_report_resume(struct pci_dev *dev, void *data);
 int pci_report_error_detected(struct pci_dev *dev, void *data);
-pci_ers_result_t pci_reset_link(struct pci_dev *dev);
+pci_ers_result_t pci_reset_link(struct pci_dev *dev, int severity);
 pci_ers_result_t pci_merge_result(enum pci_ers_result orig,
 				enum pci_ers_result new);
 void pci_do_recovery(struct pci_dev *dev, int severity);

index 8bac584..1f01e76 100644
@@ -267,6 +267,22 @@ pci_ers_result_t pci_broadcast_error_message(struct pci_dev *dev,
 	return result_data.result;
 }
 
+/*
+ * pcie_port_upstream_bridge - returns immediate upstream bridge.
+ * dev: pcie device
+ */
+static struct pci_dev *pcie_port_upstream_bridge(struct pci_dev *dev)
+{
+	struct pci_dev *parent;
+
+	parent = pci_upstream_bridge(dev);
+
+	if (parent && pci_is_pcie(parent))
+		return parent;
+
+	return NULL;
+}
+
 /**
  * pci_do_recovery - handle nonfatal/fatal error recovery process
  * @dev: pointer to a pci_dev data structure of agent detecting an error

@@ -280,9 +296,29 @@ void pci_do_recovery(struct pci_dev *dev, int severity)
 {
 	pci_ers_result_t status, result = PCI_ERS_RESULT_RECOVERED;
 	enum pci_channel_state state;
+	struct pcie_port_service_driver *driver;
+	struct pci_dev *pdev = dev;
 
 	mutex_lock(&pci_err_recovery_lock);
 
+	if (severity != PCI_ERR_DPC_FATAL) {
+		/*
+		 * DPC service could be running in RP
+		 * or any upstream switch.
+		 */
+		do {
+			driver = pci_find_dpc_service(pdev);
+			if (driver) {
+				dev_printk(KERN_NOTICE, &dev->dev,
+				"AER: Recovery to be done by DPC %s\n",
+				pci_name(dev));
+				mutex_unlock(&pci_err_recovery_lock);
+				return;
+			}
+		pdev = pcie_port_upstream_bridge(dev);
+		} while (pdev);
+	}
+
 	if ((severity == PCI_ERR_AER_FATAL) ||
 	    (severity == PCI_ERR_DPC_FATAL))
 		state = pci_channel_io_frozen;

index e7ced58..78e557f 100644
@@ -161,6 +161,43 @@ static void dpc_wait_link_inactive(struct dpc_dev *dpc)
 		dev_warn(dev, "Link state not disabled for DPC event\n");
 }
 
+static bool dpc_wait_link_active(struct pci_dev *pdev)
+{
+	unsigned long timeout = jiffies + HZ;
+	u16 lnk_status;
+	bool ret = true;
+
+	pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnk_status);
+
+	while (!(lnk_status & PCI_EXP_LNKSTA_DLLLA) &&
+					!time_after(jiffies, timeout)) {
+		msleep(10);
+		pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnk_status);
+	}
+
+	if (!(lnk_status & PCI_EXP_LNKSTA_DLLLA)) {
+		dev_warn(&pdev->dev, "Link state not enabled after DPC event\n");
+		ret = false;
+	}
+
+	return ret;
+}
+
+/**
+ * dpc_error_resume - enumerate the devices beneath
+ * @dev: pointer to Root Port's pci_dev data structure
+ *
+ * Invoked by Port Bus driver during nonfatal recovery.
+ */
+static void dpc_error_resume(struct pci_dev *pdev)
+{
+	if (dpc_wait_link_active(pdev)) {
+		pci_lock_rescan_remove();
+		pci_rescan_bus(pdev->bus);
+		pci_unlock_rescan_remove();
+	}
+}
+
 /**
  * dpc_reset_link - reset link DPC  routine
  * @dev: pointer to Root Port's pci_dev data structure

@@ -419,6 +456,7 @@ static void dpc_remove(struct pcie_device *dev)
 	.service	= PCIE_PORT_SERVICE_DPC,
 	.probe		= dpc_probe,
 	.remove		= dpc_remove,
+	.error_resume	= dpc_error_resume,
 	.reset_link     = dpc_reset_link,
 };
 

index 1f01e76..9c4377c 100644
@@ -231,7 +231,8 @@ pci_ers_result_t pci_reset_link(struct pci_dev *dev, int severity)
 pci_ers_result_t pci_broadcast_error_message(struct pci_dev *dev,
 	enum pci_channel_state state,
 	char *error_mesg,
-	int (*cb)(struct pci_dev *, void *))
+	int (*cb)(struct pci_dev *, void *),
+	int severity)
 {
 	struct pci_err_broadcast_data result_data;
 

@@ -243,6 +244,15 @@ pci_ers_result_t pci_broadcast_error_message(struct pci_dev *dev,
 		result_data.result = PCI_ERS_RESULT_RECOVERED;
 
 	if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
+		/* If DPC is triggered, call resume error hanlder
+		 * because, at this point we can safely assume that
+		 * link recovery has happened.
+		 */
+		if ((severity == PCI_ERR_DPC_FATAL) &&
+			(cb == pci_report_resume)) {
+			cb(dev, NULL);
+			return PCI_ERS_RESULT_RECOVERED;
+		}
 		/*
 		 * If the error is reported by a bridge, we think this error
 		 * is related to the downstream link of the bridge, so we

@@ -328,7 +338,8 @@ void pci_do_recovery(struct pci_dev *dev, int severity)
 	status = pci_broadcast_error_message(dev,
 			state,
 			"error_detected",
-			pci_report_error_detected);
+			pci_report_error_detected,
+			severity);
 
 	if ((severity == PCI_ERR_AER_FATAL) ||
 	    (severity == PCI_ERR_DPC_FATAL)) {

@@ -337,11 +348,15 @@ void pci_do_recovery(struct pci_dev *dev, int severity)
 			goto failed;
 	}
 
+	if (severity == PCI_ERR_DPC_FATAL)
+		goto resume;
+
 	if (status == PCI_ERS_RESULT_CAN_RECOVER)
 		status = pci_broadcast_error_message(dev,
 				state,
 				"mmio_enabled",
-				pci_report_mmio_enabled);
+				pci_report_mmio_enabled,
+				severity);
 
 	if (status == PCI_ERS_RESULT_NEED_RESET) {
 		/*

@@ -352,16 +367,19 @@ void pci_do_recovery(struct pci_dev *dev, int severity)
 		status = pci_broadcast_error_message(dev,
 				state,
 				"slot_reset",
-				pci_report_slot_reset);
+				pci_report_slot_reset,
+				severity);
 	}
 
 	if (status != PCI_ERS_RESULT_RECOVERED)
 		goto failed;
 
+resume:
 	pci_broadcast_error_message(dev,
 				state,
 				"resume",
-				pci_report_resume);
+				pci_report_resume,
+				severity);
 
 	dev_info(&dev->dev, "Device recovery successful\n");
 	mutex_unlock(&pci_err_recovery_lock);

index 123ee15..46e2526 100644
@@ -2010,7 +2010,8 @@ static inline resource_size_t pci_iov_resource_size(struct pci_dev *dev, int res
 pci_ers_result_t pci_broadcast_error_message(struct pci_dev *dev,
 					enum pci_channel_state state,
 					char *error_mesg,
-					int (*cb)(struct pci_dev *, void *));
+					int (*cb)(struct pci_dev *, void *),
+					int severity);
 int pci_report_mmio_enabled(struct pci_dev *dev, void *data);
 int pci_report_slot_reset(struct pci_dev *dev, void *data);
 int pci_report_resume(struct pci_dev *dev, void *data);