aerdrv_core.c

linux 内核源代码

/*
 * drivers/pci/pcie/aer/aerdrv_core.c
 *
 * This file is subject to the terms and conditions of the GNU General Public
 * License.  See the file "COPYING" in the main directory of this archive
 * for more details.
 *
 * This file implements the core part of PCI-Express AER. When an pci-express
 * error is delivered, an error message will be collected and printed to
 * console, then, an error recovery procedure will be executed by following
 * the pci error recovery rules.
 *
 * Copyright (C) 2006 Intel Corp.
 *	Tom Long Nguyen ([e-mail])
 *	Zhang Yanmin ([e-mail])
 *
 */

#include <linux/module.h>
#include <linux/pci.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/pm.h>
#include <linux/suspend.h>
#include <linux/delay.h>
#include "aerdrv.h"

static int forceload;
module_param(forceload, bool, 0);

#define PCI_CFG_SPACE_SIZE	(0x100)
int pci_find_aer_capability(struct pci_dev *dev)
{
	int pos;
	u32 reg32 = 0;

	/* Check if it's a pci-express device */
	pos = pci_find_capability(dev, PCI_CAP_ID_EXP);
	if (!pos)
		return 0;

	/* Check if it supports pci-express AER */
	pos = PCI_CFG_SPACE_SIZE;
	while (pos) {
		if (pci_read_config_dword(dev, pos, &reg32))
			return 0;

		/* some broken boards return ~0 */
		if (reg32 == 0xffffffff)
			return 0;

		if (PCI_EXT_CAP_ID(reg32) == PCI_EXT_CAP_ID_ERR)
			break;

		pos = reg32 >> 20;
	}

	return pos;
}

int pci_enable_pcie_error_reporting(struct pci_dev *dev)
{
	u16 reg16 = 0;
	int pos;

	pos = pci_find_capability(dev, PCI_CAP_ID_EXP);
	if (!pos)
		return -EIO;

	pci_read_config_word(dev, pos+PCI_EXP_DEVCTL, &reg16);
	reg16 = reg16 |
		PCI_EXP_DEVCTL_CERE |
		PCI_EXP_DEVCTL_NFERE |
		PCI_EXP_DEVCTL_FERE |
		PCI_EXP_DEVCTL_URRE;
	pci_write_config_word(dev, pos+PCI_EXP_DEVCTL,
			reg16);
	return 0;
}

int pci_disable_pcie_error_reporting(struct pci_dev *dev)
{
	u16 reg16 = 0;
	int pos;

	pos = pci_find_capability(dev, PCI_CAP_ID_EXP);
	if (!pos)
		return -EIO;

	pci_read_config_word(dev, pos+PCI_EXP_DEVCTL, &reg16);
	reg16 = reg16 & ~(PCI_EXP_DEVCTL_CERE |
			PCI_EXP_DEVCTL_NFERE |
			PCI_EXP_DEVCTL_FERE |
			PCI_EXP_DEVCTL_URRE);
	pci_write_config_word(dev, pos+PCI_EXP_DEVCTL,
			reg16);
	return 0;
}

int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev)
{
	int pos;
	u32 status, mask;

	pos = pci_find_aer_capability(dev);
	if (!pos)
		return -EIO;

	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status);
	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, &mask);
	if (dev->error_state == pci_channel_io_normal)
		status &= ~mask; /* Clear corresponding nonfatal bits */
	else
		status &= mask; /* Clear corresponding fatal bits */
	pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, status);

	return 0;
}

int pci_cleanup_aer_correct_error_status(struct pci_dev *dev)
{
	int pos;
	u32 status;

	pos = pci_find_aer_capability(dev);
	if (!pos)
		return -EIO;

	pci_read_config_dword(dev, pos + PCI_ERR_COR_STATUS, &status);
	pci_write_config_dword(dev, pos + PCI_ERR_COR_STATUS, status);

	return 0;
}

static int find_device_iter(struct device *device, void *data)
{
	struct pci_dev *dev;
	u16 id = *(unsigned long *)data;
	u8 secondary, subordinate, d_bus = id >> 8;

	if (device->bus == &pci_bus_type) {
		dev = to_pci_dev(device);
		if (id == ((dev->bus->number << 8) | dev->devfn)) {
			/*
			 * Device ID match
			 */
			*(unsigned long*)data = (unsigned long)device;
			return 1;
		}

		/*
		 * If device is P2P, check if it is an upstream?
		 */
		if (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE) {
			pci_read_config_byte(dev, PCI_SECONDARY_BUS,
				&secondary);
			pci_read_config_byte(dev, PCI_SUBORDINATE_BUS,
				&subordinate);
			if (d_bus >= secondary && d_bus <= subordinate) {
				*(unsigned long*)data = (unsigned long)device;
				return 1;
			}
		}
	}

	return 0;
}

/**
 * find_source_device - search through device hierarchy for source device
 * @parent: pointer to Root Port pci_dev data structure
 * @id: device ID of agent who sends an error message to this Root Port
 *
 * Invoked when error is detected at the Root Port.
 */
static struct device* find_source_device(struct pci_dev *parent, u16 id)
{
	struct pci_dev *dev = parent;
	struct device *device;
	unsigned long device_addr;
	int status;

	/* Is Root Port an agent that sends error message? */
	if (id == ((dev->bus->number << 8) | dev->devfn))
		return &dev->dev;

	do {
		device_addr = id;
 		if ((status = device_for_each_child(&dev->dev,
			&device_addr, find_device_iter))) {
			device = (struct device*)device_addr;
			dev = to_pci_dev(device);
			if (id == ((dev->bus->number << 8) | dev->devfn))
				return device;
		}
 	}while (status);

	return NULL;
}

static void report_error_detected(struct pci_dev *dev, void *data)
{
	pci_ers_result_t vote;
	struct pci_error_handlers *err_handler;
	struct aer_broadcast_data *result_data;
	result_data = (struct aer_broadcast_data *) data;

	dev->error_state = result_data->state;

	if (!dev->driver ||
		!dev->driver->err_handler ||
		!dev->driver->err_handler->error_detected) {
		if (result_data->state == pci_channel_io_frozen &&
			!(dev->hdr_type & PCI_HEADER_TYPE_BRIDGE)) {
			/*
			 * In case of fatal recovery, if one of down-
			 * stream device has no driver. We might be
			 * unable to recover because a later insmod
			 * of a driver for this device is unaware of
			 * its hw state.
			 */
			printk(KERN_DEBUG "Device ID[%s] has %s\n",
					dev->dev.bus_id, (dev->driver) ?
					"no AER-aware driver" : "no driver");
		}
		return;
	}

	err_handler = dev->driver->err_handler;
	vote = err_handler->error_detected(dev, result_data->state);
	result_data->result = merge_result(result_data->result, vote);
	return;
}

static void report_mmio_enabled(struct pci_dev *dev, void *data)
{
	pci_ers_result_t vote;
	struct pci_error_handlers *err_handler;
	struct aer_broadcast_data *result_data;
	result_data = (struct aer_broadcast_data *) data;

	if (!dev->driver ||
		!dev->driver->err_handler ||
		!dev->driver->err_handler->mmio_enabled)
		return;

	err_handler = dev->driver->err_handler;
	vote = err_handler->mmio_enabled(dev);
	result_data->result = merge_result(result_data->result, vote);
	return;
}

static void report_slot_reset(struct pci_dev *dev, void *data)
{
	pci_ers_result_t vote;
	struct pci_error_handlers *err_handler;
	struct aer_broadcast_data *result_data;
	result_data = (struct aer_broadcast_data *) data;

	if (!dev->driver ||
		!dev->driver->err_handler ||
		!dev->driver->err_handler->slot_reset)
		return;

	err_handler = dev->driver->err_handler;
	vote = err_handler->slot_reset(dev);
	result_data->result = merge_result(result_data->result, vote);
	return;
}

static void report_resume(struct pci_dev *dev, void *data)
{
	struct pci_error_handlers *err_handler;

	dev->error_state = pci_channel_io_normal;

	if (!dev->driver ||
		!dev->driver->err_handler ||
		!dev->driver->err_handler->slot_reset)
		return;

	err_handler = dev->driver->err_handler;
	err_handler->resume(dev);
	return;
}

/**
 * broadcast_error_message - handle message broadcast to downstream drivers
 * @dev: pointer to from where in a hierarchy message is broadcasted down
 * @state: error state
 * @error_mesg: message to print
 * @cb: callback to be broadcasted
 *
 * Invoked during error recovery process. Once being invoked, the content
 * of error severity will be broadcasted to all downstream drivers in a
 * hierarchy in question.
 */
static pci_ers_result_t broadcast_error_message(struct pci_dev *dev,
	enum pci_channel_state state,
	char *error_mesg,
	void (*cb)(struct pci_dev *, void *))
{
	struct aer_broadcast_data result_data;

	printk(KERN_DEBUG "Broadcast %s message\n", error_mesg);
	result_data.state = state;
	if (cb == report_error_detected)
		result_data.result = PCI_ERS_RESULT_CAN_RECOVER;
	else
		result_data.result = PCI_ERS_RESULT_RECOVERED;

	if (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE) {
		/*
		 * If the error is reported by a bridge, we think this error
		 * is related to the downstream link of the bridge, so we
		 * do error recovery on all subordinates of the bridge instead
		 * of the bridge and clear the error status of the bridge.
		 */
		if (cb == report_error_detected)
			dev->error_state = state;
		pci_walk_bus(dev->subordinate, cb, &result_data);
		if (cb == report_resume) {
			pci_cleanup_aer_uncorrect_error_status(dev);
			dev->error_state = pci_channel_io_normal;
		}
	}
	else {
		/*
		 * If the error is reported by an end point, we think this
		 * error is related to the upstream link of the end point.
		 */
		pci_walk_bus(dev->bus, cb, &result_data);
	}

	return result_data.result;
}

struct find_aer_service_data {
	struct pcie_port_service_driver *aer_driver;
	int is_downstream;
};

static int find_aer_service_iter(struct device *device, void *data)
{
	struct device_driver *driver;
	struct pcie_port_service_driver *service_driver;
	struct pcie_device *pcie_dev;
	struct find_aer_service_data *result;

	result = (struct find_aer_service_data *) data;

	if (device->bus == &pcie_port_bus_type) {
		pcie_dev = to_pcie_device(device);
		if (pcie_dev->id.port_type == PCIE_SW_DOWNSTREAM_PORT)
			result->is_downstream = 1;

		driver = device->driver;
		if (driver) {
			service_driver = to_service_driver(driver);
			if (service_driver->id_table->service_type ==
					PCIE_PORT_SERVICE_AER) {
				result->aer_driver = service_driver;
				return 1;
			}
		}
	}

	return 0;
}

static void find_aer_service(struct pci_dev *dev,
		struct find_aer_service_data *data)
{
	int retval;
	retval = device_for_each_child(&dev->dev, data, find_aer_service_iter);
}

static pci_ers_result_t reset_link(struct pcie_device *aerdev,
		struct pci_dev *dev)
{
	struct pci_dev *udev;