Address error and recovery for AER and DPC

index 7448052..6cb1b36 100644
@@ -482,7 +482,7 @@ static pci_ers_result_t reset_link(struct pci_dev *dev)
 }
 
 /**
- * do_recovery - handle nonfatal/fatal error recovery process
+ * pci_do_recovery - handle nonfatal/fatal error recovery process
  * @dev: pointer to a pci_dev data structure of agent detecting an error
  * @severity: error severity type
  *

@@ -490,7 +490,7 @@ static pci_ers_result_t reset_link(struct pci_dev *dev)
  * error detected message to all downstream drivers within a hierarchy in
  * question and return the returned code.
  */
-static void do_recovery(struct pci_dev *dev, int severity)
+static 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;

@@ -569,7 +569,7 @@ static void handle_error_source(struct pcie_device *aerdev,
 			pci_write_config_dword(dev, pos + PCI_ERR_COR_STATUS,
 					info->status);
 	} else
-		do_recovery(dev, info->severity);
+		pci_do_recovery(dev, info->severity);
 }
 
 #ifdef CONFIG_ACPI_APEI_PCIEAER

@@ -633,7 +633,7 @@ static void aer_recover_work_func(struct work_struct *work)
 			continue;
 		}
 		cper_print_aer(pdev, entry.severity, entry.regs);
-		do_recovery(pdev, entry.severity);
+		pci_do_recovery(pdev, entry.severity);
 		pci_dev_put(pdev);
 	}
 }

index f6b58b3..665ff6c 100644
@@ -342,6 +342,9 @@ static inline resource_size_t pci_resource_alignment(struct pci_dev *dev,
 
 void pci_enable_acs(struct pci_dev *dev);
 
+/* PCI error reporting and recovery */
+void pci_do_recovery(struct pci_dev *dev, int severity);
+
 #ifdef CONFIG_PCIE_PTM
 void pci_ptm_init(struct pci_dev *dev);
 #else

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);

313 lines not on this page · raw message

334 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..cd4f086 100644
@@ -11,9 +11,9 @@
 #include <linux/errno.h>
 #include <linux/types.h>
 
-#define AER_NONFATAL			0
-#define AER_FATAL			1
-#define AER_CORRECTABLE			2
+#define AER_NONFATAL		0
+#define AER_FATAL		1
+#define AER_CORRECTABLE		2
 
 struct pci_dev;
 

index 2d976a6..ed916765 100644
@@ -13,8 +13,12 @@
 #include <linux/interrupt.h>
 #include <linux/init.h>
 #include <linux/pci.h>
+#include <linux/dpc.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 +71,60 @@ 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;
+}
+
+static 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 +162,23 @@ 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 +195,7 @@ 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 +205,17 @@ 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, DPC_FATAL);
 }
 
 static void dpc_rp_pio_print_tlp_header(struct device *dev,

@@ -339,6 +420,7 @@ 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 a532fe0..8ce1de1 100644
@@ -17,9 +17,12 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/aer.h>
+#include <linux/dpc.h>
 #include <linux/pcieport_if.h>
 #include "portdrv.h"
 
+static DEFINE_MUTEX(pci_err_recovery_lock);
+
 struct aer_broadcast_data {
 	enum pci_channel_state state;
 	enum pci_ers_result result;

@@ -179,7 +182,7 @@ static pci_ers_result_t default_reset_link(struct pci_dev *dev)
 	return PCI_ERS_RESULT_RECOVERED;
 }
 
-static pci_ers_result_t reset_link(struct pci_dev *dev)
+static pci_ers_result_t reset_link(struct pci_dev *dev, int severity)
 {
 	struct pci_dev *udev;
 	pci_ers_result_t status;

@@ -193,9 +196,17 @@ static pci_ers_result_t reset_link(struct pci_dev *dev)
 		udev = dev->bus->self;
 	}
 
+
+	/* Use the service driver of the component firstly */
+#if IS_ENABLED(CONFIG_PCIE_DPC)
+	if (severity == DPC_FATAL)
+		driver = pci_find_dpc_service(udev);
+#endif
 #if IS_ENABLED(CONFIG_PCIEAER)
-	/* Use the aer driver of the component firstly */
-	driver = pci_find_aer_service(udev);
+	if ((severity == AER_FATAL) ||
+	    (severity == AER_NONFATAL) ||
+	    (severity == AER_CORRECTABLE))
+		driver = pci_find_aer_service(udev);
 #endif
 
 	if (driver && driver->reset_link) {

@@ -283,7 +294,10 @@ 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;
 
-	if (severity == AER_FATAL)
+	mutex_lock(&pci_err_recovery_lock);
+
+	if ((severity == AER_FATAL) ||
+	    (severity == DPC_FATAL))
 		state = pci_channel_io_frozen;
 	else
 		state = pci_channel_io_normal;

@@ -293,8 +307,9 @@ void pci_do_recovery(struct pci_dev *dev, int severity)
 			"error_detected",
 			report_error_detected);
 
-	if (severity == AER_FATAL) {
-		result = reset_link(dev);
+	if ((severity == AER_FATAL) ||
+	    (severity == DPC_FATAL)) {
+		result = reset_link(dev, severity);
 		if (result != PCI_ERS_RESULT_RECOVERED)
 			goto failed;
 	}

@@ -326,9 +341,11 @@ void pci_do_recovery(struct pci_dev *dev, int severity)
 				report_resume);
 
 	dev_info(&dev->dev, "Device recovery successful\n");
+	mutex_unlock(&pci_err_recovery_lock);
 	return;
 
 failed:
 	/* TODO: Should kernel panic here? */
+	mutex_unlock(&pci_err_recovery_lock);
 	dev_info(&dev->dev, "Device recovery failed\n");
 }

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_ */

new file mode 100644
index 0000000..2019ce4
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _DPC_H_
+#define _DPC_H_
+
+#define DPC_FATAL		4
+
+#endif //_DPC_H_
+

index ed916765..f99adcae 100644
@@ -162,6 +162,43 @@ 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

@@ -420,6 +457,7 @@ 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 8ce1de1..de72b0a 100644
@@ -236,6 +236,7 @@ static pci_ers_result_t reset_link(struct pci_dev *dev, int severity)
  * @state: error state
  * @error_mesg: message to print
  * @cb: callback to be broadcasted
+ * @severity: error severity
  *
  * Invoked during error recovery process. Once being invoked, the content
  * of error severity will be broadcasted to all downstream drivers in a

@@ -244,7 +245,8 @@ static pci_ers_result_t reset_link(struct pci_dev *dev, int severity)
 static pci_ers_result_t 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 aer_broadcast_data result_data;
 

@@ -256,6 +258,15 @@ static pci_ers_result_t 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 == DPC_FATAL) &&
+			(cb == 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

@@ -305,7 +316,8 @@ void pci_do_recovery(struct pci_dev *dev, int severity)
 	status = broadcast_error_message(dev,
 			state,
 			"error_detected",
-			report_error_detected);
+			report_error_detected,
+			severity);
 
 	if ((severity == AER_FATAL) ||
 	    (severity == DPC_FATAL)) {

@@ -318,7 +330,8 @@ void pci_do_recovery(struct pci_dev *dev, int severity)
 		status = broadcast_error_message(dev,
 				state,
 				"mmio_enabled",
-				report_mmio_enabled);
+				report_mmio_enabled,
+				severity);
 
 	if (status == PCI_ERS_RESULT_NEED_RESET) {
 		/*

@@ -329,7 +342,8 @@ void pci_do_recovery(struct pci_dev *dev, int severity)
 		status = broadcast_error_message(dev,
 				state,
 				"slot_reset",
-				report_slot_reset);
+				report_slot_reset,
+				severity);
 	}
 
 	if (status != PCI_ERS_RESULT_RECOVERED)

@@ -338,7 +352,8 @@ void pci_do_recovery(struct pci_dev *dev, int severity)
 	broadcast_error_message(dev,
 				state,
 				"resume",
-				report_resume);
+				report_resume,
+				severity);
 
 	dev_info(&dev->dev, "Device recovery successful\n");
 	mutex_unlock(&pci_err_recovery_lock);