Fixed MTP to work with TWRP

drivers/pci/pcie/Kconfig

@@ -0,0 +1,82 @@
+#
+# PCI Express Port Bus Configuration
+#
+config PCIEPORTBUS
+	bool "PCI Express Port Bus support"
+	depends on PCI
+	help
+	  This automatically enables PCI Express Port Bus support. Users can
+	  choose Native Hot-Plug support, Advanced Error Reporting support,
+	  Power Management Event support and Virtual Channel support to run
+	  on PCI Express Ports (Root or Switch).
+
+#
+# Include service Kconfig here
+#
+config HOTPLUG_PCI_PCIE
+	bool "PCI Express Hotplug driver"
+	depends on HOTPLUG_PCI && PCIEPORTBUS
+	help
+	  Say Y here if you have a motherboard that supports PCI Express Native
+	  Hotplug
+
+	  When in doubt, say N.
+
+source "drivers/pci/pcie/aer/Kconfig"
+
+#
+# PCI Express ASPM
+#
+config PCIEASPM
+	bool "PCI Express ASPM control" if EXPERT
+	depends on PCI && PCIEPORTBUS
+	default n
+	help
+	  This enables OS control over PCI Express ASPM (Active State
+	  Power Management) and Clock Power Management. ASPM supports
+	  state L0/L0s/L1.
+
+	  ASPM is initially set up by the firmware. With this option enabled,
+	  Linux can modify this state in order to disable ASPM on known-bad
+	  hardware or configurations and enable it when known-safe.
+
+	  ASPM can be disabled or enabled at runtime via
+	  /sys/module/pcie_aspm/parameters/policy
+
+	  When in doubt, say Y.
+config PCIEASPM_DEBUG
+	bool "Debug PCI Express ASPM"
+	depends on PCIEASPM
+	default n
+	help
+	  This enables PCI Express ASPM debug support. It will add per-device
+	  interface to control ASPM.
+
+choice
+	prompt "Default ASPM policy"
+	default PCIEASPM_DEFAULT
+	depends on PCIEASPM
+
+config PCIEASPM_DEFAULT
+        bool "BIOS default"
+	depends on PCIEASPM
+	help
+	  Use the BIOS defaults for PCI Express ASPM.
+
+config PCIEASPM_POWERSAVE
+        bool "Powersave"
+	depends on PCIEASPM
+	help
+	  Enable PCI Express ASPM L0s and L1 where possible, even if the
+	  BIOS did not.
+
+config PCIEASPM_PERFORMANCE
+        bool "Performance"
+	depends on PCIEASPM
+	help
+	  Disable PCI Express ASPM L0s and L1, even if the BIOS enabled them.
+endchoice
+
+config PCIE_PME
+	def_bool y
+	depends on PCIEPORTBUS && PM_RUNTIME

drivers/pci/pcie/Makefile

@@ -0,0 +1,16 @@
+#
+# Makefile for PCI-Express PORT Driver
+#
+
+# Build PCI Express ASPM if needed
+obj-$(CONFIG_PCIEASPM)		+= aspm.o
+
+pcieportdrv-y			:= portdrv_core.o portdrv_pci.o portdrv_bus.o
+pcieportdrv-$(CONFIG_ACPI)	+= portdrv_acpi.o
+
+obj-$(CONFIG_PCIEPORTBUS)	+= pcieportdrv.o
+
+# Build PCI Express AER if needed
+obj-$(CONFIG_PCIEAER)		+= aer/
+
+obj-$(CONFIG_PCIE_PME) += pme.o

drivers/pci/pcie/aer/Kconfig

@@ -0,0 +1,28 @@
+#
+# PCI Express Root Port Device AER Configuration
+#
+
+config PCIEAER
+	boolean "Root Port Advanced Error Reporting support"
+	depends on PCIEPORTBUS
+	select RAS
+	default y
+	help
+	  This enables PCI Express Root Port Advanced Error Reporting
+	  (AER) driver support. Error reporting messages sent to Root
+	  Port will be handled by PCI Express AER driver.
+
+
+#
+# PCI Express ECRC
+#
+config PCIE_ECRC
+	bool "PCI Express ECRC settings control"
+	depends on PCIEAER
+	help
+	  Used to override firmware/bios settings for PCI Express ECRC
+	  (transaction layer end-to-end CRC checking).
+
+	  When in doubt, say N.
+
+source "drivers/pci/pcie/aer/Kconfig.debug"

drivers/pci/pcie/aer/Kconfig.debug

@@ -0,0 +1,18 @@
+#
+# PCI Express Root Port Device AER Debug Configuration
+#
+
+config PCIEAER_INJECT
+	tristate "PCIe AER error injector support"
+	depends on PCIEAER
+	default n
+	help
+	  This enables PCI Express Root Port Advanced Error Reporting
+	  (AER) software error injector.
+
+	  Debugging PCIe AER code is quite difficult because it is hard
+	  to trigger various real hardware errors. Software based
+	  error injection can fake almost all kinds of errors with the
+	  help of a user space helper tool aer-inject, which can be
+	  gotten from:
+	     http://www.kernel.org/pub/linux/utils/pci/aer-inject/

drivers/pci/pcie/aer/Makefile

@@ -0,0 +1,12 @@
+#
+# Makefile for PCI-Express Root Port Advanced Error Reporting Driver
+#
+
+obj-$(CONFIG_PCIEAER) += aerdriver.o
+
+obj-$(CONFIG_PCIE_ECRC)	+= ecrc.o
+
+aerdriver-objs := aerdrv_errprint.o aerdrv_core.o aerdrv.o
+aerdriver-$(CONFIG_ACPI) += aerdrv_acpi.o
+
+obj-$(CONFIG_PCIEAER_INJECT) += aer_inject.o

drivers/pci/pcie/aer/aer_inject.c

@@ -0,0 +1,536 @@
+/*
+ * PCIe AER software error injection support.
+ *
+ * Debuging PCIe AER code is quite difficult because it is hard to
+ * trigger various real hardware errors. Software based error
+ * injection can fake almost all kinds of errors with the help of a
+ * user space helper tool aer-inject, which can be gotten from:
+ *   http://www.kernel.org/pub/linux/utils/pci/aer-inject/
+ *
+ * Copyright 2009 Intel Corporation.
+ *     Huang Ying <ying.huang@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/miscdevice.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/uaccess.h>
+#include <linux/stddef.h>
+#include "aerdrv.h"
+
+/* Override the existing corrected and uncorrected error masks */
+static bool aer_mask_override;
+module_param(aer_mask_override, bool, 0);
+
+struct aer_error_inj {
+	u8 bus;
+	u8 dev;
+	u8 fn;
+	u32 uncor_status;
+	u32 cor_status;
+	u32 header_log0;
+	u32 header_log1;
+	u32 header_log2;
+	u32 header_log3;
+	u16 domain;
+};
+
+struct aer_error {
+	struct list_head list;
+	u16 domain;
+	unsigned int bus;
+	unsigned int devfn;
+	int pos_cap_err;
+
+	u32 uncor_status;
+	u32 cor_status;
+	u32 header_log0;
+	u32 header_log1;
+	u32 header_log2;
+	u32 header_log3;
+	u32 root_status;
+	u32 source_id;
+};
+
+struct pci_bus_ops {
+	struct list_head list;
+	struct pci_bus *bus;
+	struct pci_ops *ops;
+};
+
+static LIST_HEAD(einjected);
+
+static LIST_HEAD(pci_bus_ops_list);
+
+/* Protect einjected and pci_bus_ops_list */
+static DEFINE_SPINLOCK(inject_lock);
+
+static void aer_error_init(struct aer_error *err, u16 domain,
+			   unsigned int bus, unsigned int devfn,
+			   int pos_cap_err)
+{
+	INIT_LIST_HEAD(&err->list);
+	err->domain = domain;
+	err->bus = bus;
+	err->devfn = devfn;
+	err->pos_cap_err = pos_cap_err;
+}
+
+/* inject_lock must be held before calling */
+static struct aer_error *__find_aer_error(u16 domain, unsigned int bus,
+					  unsigned int devfn)
+{
+	struct aer_error *err;
+
+	list_for_each_entry(err, &einjected, list) {
+		if (domain == err->domain &&
+		    bus == err->bus &&
+		    devfn == err->devfn)
+			return err;
+	}
+	return NULL;
+}
+
+/* inject_lock must be held before calling */
+static struct aer_error *__find_aer_error_by_dev(struct pci_dev *dev)
+{
+	int domain = pci_domain_nr(dev->bus);
+	if (domain < 0)
+		return NULL;
+	return __find_aer_error((u16)domain, dev->bus->number, dev->devfn);
+}
+
+/* inject_lock must be held before calling */
+static struct pci_ops *__find_pci_bus_ops(struct pci_bus *bus)
+{
+	struct pci_bus_ops *bus_ops;
+
+	list_for_each_entry(bus_ops, &pci_bus_ops_list, list) {
+		if (bus_ops->bus == bus)
+			return bus_ops->ops;
+	}
+	return NULL;
+}
+
+static struct pci_bus_ops *pci_bus_ops_pop(void)
+{
+	unsigned long flags;
+	struct pci_bus_ops *bus_ops = NULL;
+
+	spin_lock_irqsave(&inject_lock, flags);
+	if (list_empty(&pci_bus_ops_list))
+		bus_ops = NULL;
+	else {
+		struct list_head *lh = pci_bus_ops_list.next;
+		list_del(lh);
+		bus_ops = list_entry(lh, struct pci_bus_ops, list);
+	}
+	spin_unlock_irqrestore(&inject_lock, flags);
+	return bus_ops;
+}
+
+static u32 *find_pci_config_dword(struct aer_error *err, int where,
+				  int *prw1cs)
+{
+	int rw1cs = 0;
+	u32 *target = NULL;
+
+	if (err->pos_cap_err == -1)
+		return NULL;
+
+	switch (where - err->pos_cap_err) {
+	case PCI_ERR_UNCOR_STATUS:
+		target = &err->uncor_status;
+		rw1cs = 1;
+		break;
+	case PCI_ERR_COR_STATUS:
+		target = &err->cor_status;
+		rw1cs = 1;
+		break;
+	case PCI_ERR_HEADER_LOG:
+		target = &err->header_log0;
+		break;
+	case PCI_ERR_HEADER_LOG+4:
+		target = &err->header_log1;
+		break;
+	case PCI_ERR_HEADER_LOG+8:
+		target = &err->header_log2;
+		break;
+	case PCI_ERR_HEADER_LOG+12:
+		target = &err->header_log3;
+		break;
+	case PCI_ERR_ROOT_STATUS:
+		target = &err->root_status;
+		rw1cs = 1;
+		break;
+	case PCI_ERR_ROOT_ERR_SRC:
+		target = &err->source_id;
+		break;
+	}
+	if (prw1cs)
+		*prw1cs = rw1cs;
+	return target;
+}
+
+static int pci_read_aer(struct pci_bus *bus, unsigned int devfn, int where,
+			int size, u32 *val)
+{
+	u32 *sim;
+	struct aer_error *err;
+	unsigned long flags;
+	struct pci_ops *ops;
+	int domain;
+
+	spin_lock_irqsave(&inject_lock, flags);
+	if (size != sizeof(u32))
+		goto out;
+	domain = pci_domain_nr(bus);
+	if (domain < 0)
+		goto out;
+	err = __find_aer_error((u16)domain, bus->number, devfn);
+	if (!err)
+		goto out;
+
+	sim = find_pci_config_dword(err, where, NULL);
+	if (sim) {
+		*val = *sim;
+		spin_unlock_irqrestore(&inject_lock, flags);
+		return 0;
+	}
+out:
+	ops = __find_pci_bus_ops(bus);
+	spin_unlock_irqrestore(&inject_lock, flags);
+	return ops->read(bus, devfn, where, size, val);
+}
+
+static int pci_write_aer(struct pci_bus *bus, unsigned int devfn, int where,
+			 int size, u32 val)
+{
+	u32 *sim;
+	struct aer_error *err;
+	unsigned long flags;
+	int rw1cs;
+	struct pci_ops *ops;
+	int domain;
+
+	spin_lock_irqsave(&inject_lock, flags);
+	if (size != sizeof(u32))
+		goto out;
+	domain = pci_domain_nr(bus);
+	if (domain < 0)
+		goto out;
+	err = __find_aer_error((u16)domain, bus->number, devfn);
+	if (!err)
+		goto out;
+
+	sim = find_pci_config_dword(err, where, &rw1cs);
+	if (sim) {
+		if (rw1cs)
+			*sim ^= val;
+		else
+			*sim = val;
+		spin_unlock_irqrestore(&inject_lock, flags);
+		return 0;
+	}
+out:
+	ops = __find_pci_bus_ops(bus);
+	spin_unlock_irqrestore(&inject_lock, flags);
+	return ops->write(bus, devfn, where, size, val);
+}
+
+static struct pci_ops pci_ops_aer = {
+	.read = pci_read_aer,
+	.write = pci_write_aer,
+};
+
+static void pci_bus_ops_init(struct pci_bus_ops *bus_ops,
+			     struct pci_bus *bus,
+			     struct pci_ops *ops)
+{
+	INIT_LIST_HEAD(&bus_ops->list);
+	bus_ops->bus = bus;
+	bus_ops->ops = ops;
+}
+
+static int pci_bus_set_aer_ops(struct pci_bus *bus)
+{
+	struct pci_ops *ops;
+	struct pci_bus_ops *bus_ops;
+	unsigned long flags;
+
+	bus_ops = kmalloc(sizeof(*bus_ops), GFP_KERNEL);
+	if (!bus_ops)
+		return -ENOMEM;
+	ops = pci_bus_set_ops(bus, &pci_ops_aer);
+	spin_lock_irqsave(&inject_lock, flags);
+	if (ops == &pci_ops_aer)
+		goto out;
+	pci_bus_ops_init(bus_ops, bus, ops);
+	list_add(&bus_ops->list, &pci_bus_ops_list);
+	bus_ops = NULL;
+out:
+	spin_unlock_irqrestore(&inject_lock, flags);
+	kfree(bus_ops);
+	return 0;
+}
+
+static struct pci_dev *pcie_find_root_port(struct pci_dev *dev)
+{
+	while (1) {
+		if (!pci_is_pcie(dev))
+			break;
+		if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT)
+			return dev;
+		if (!dev->bus->self)
+			break;
+		dev = dev->bus->self;
+	}
+	return NULL;
+}
+
+static int find_aer_device_iter(struct device *device, void *data)
+{
+	struct pcie_device **result = data;
+	struct pcie_device *pcie_dev;
+
+	if (device->bus == &pcie_port_bus_type) {
+		pcie_dev = to_pcie_device(device);
+		if (pcie_dev->service & PCIE_PORT_SERVICE_AER) {
+			*result = pcie_dev;
+			return 1;
+		}
+	}
+	return 0;
+}
+
+static int find_aer_device(struct pci_dev *dev, struct pcie_device **result)
+{
+	return device_for_each_child(&dev->dev, result, find_aer_device_iter);
+}
+
+static int aer_inject(struct aer_error_inj *einj)
+{
+	struct aer_error *err, *rperr;
+	struct aer_error *err_alloc = NULL, *rperr_alloc = NULL;
+	struct pci_dev *dev, *rpdev;
+	struct pcie_device *edev;
+	unsigned long flags;
+	unsigned int devfn = PCI_DEVFN(einj->dev, einj->fn);
+	int pos_cap_err, rp_pos_cap_err;
+	u32 sever, cor_mask, uncor_mask, cor_mask_orig = 0, uncor_mask_orig = 0;
+	int ret = 0;
+
+	dev = pci_get_domain_bus_and_slot((int)einj->domain, einj->bus, devfn);
+	if (!dev)
+		return -ENODEV;
+	rpdev = pcie_find_root_port(dev);
+	if (!rpdev) {
+		ret = -ENODEV;
+		goto out_put;
+	}
+
+	pos_cap_err = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
+	if (!pos_cap_err) {
+		ret = -EPERM;
+		goto out_put;
+	}
+	pci_read_config_dword(dev, pos_cap_err + PCI_ERR_UNCOR_SEVER, &sever);
+	pci_read_config_dword(dev, pos_cap_err + PCI_ERR_COR_MASK, &cor_mask);
+	pci_read_config_dword(dev, pos_cap_err + PCI_ERR_UNCOR_MASK,
+			      &uncor_mask);
+
+	rp_pos_cap_err = pci_find_ext_capability(rpdev, PCI_EXT_CAP_ID_ERR);
+	if (!rp_pos_cap_err) {
+		ret = -EPERM;
+		goto out_put;
+	}
+
+	err_alloc =  kzalloc(sizeof(struct aer_error), GFP_KERNEL);
+	if (!err_alloc) {
+		ret = -ENOMEM;
+		goto out_put;
+	}
+	rperr_alloc =  kzalloc(sizeof(struct aer_error), GFP_KERNEL);
+	if (!rperr_alloc) {
+		ret = -ENOMEM;
+		goto out_put;
+	}
+
+	if (aer_mask_override) {
+		cor_mask_orig = cor_mask;
+		cor_mask &= !(einj->cor_status);
+		pci_write_config_dword(dev, pos_cap_err + PCI_ERR_COR_MASK,
+				       cor_mask);
+
+		uncor_mask_orig = uncor_mask;
+		uncor_mask &= !(einj->uncor_status);
+		pci_write_config_dword(dev, pos_cap_err + PCI_ERR_UNCOR_MASK,
+				       uncor_mask);
+	}
+
+	spin_lock_irqsave(&inject_lock, flags);
+
+	err = __find_aer_error_by_dev(dev);
+	if (!err) {
+		err = err_alloc;
+		err_alloc = NULL;
+		aer_error_init(err, einj->domain, einj->bus, devfn,
+			       pos_cap_err);
+		list_add(&err->list, &einjected);
+	}
+	err->uncor_status |= einj->uncor_status;
+	err->cor_status |= einj->cor_status;
+	err->header_log0 = einj->header_log0;
+	err->header_log1 = einj->header_log1;
+	err->header_log2 = einj->header_log2;
+	err->header_log3 = einj->header_log3;
+
+	if (!aer_mask_override && einj->cor_status &&
+	    !(einj->cor_status & ~cor_mask)) {
+		ret = -EINVAL;
+		printk(KERN_WARNING "The correctable error(s) is masked by device\n");
+		spin_unlock_irqrestore(&inject_lock, flags);
+		goto out_put;
+	}
+	if (!aer_mask_override && einj->uncor_status &&
+	    !(einj->uncor_status & ~uncor_mask)) {
+		ret = -EINVAL;
+		printk(KERN_WARNING "The uncorrectable error(s) is masked by device\n");
+		spin_unlock_irqrestore(&inject_lock, flags);
+		goto out_put;
+	}
+
+	rperr = __find_aer_error_by_dev(rpdev);
+	if (!rperr) {
+		rperr = rperr_alloc;
+		rperr_alloc = NULL;
+		aer_error_init(rperr, pci_domain_nr(rpdev->bus),
+			       rpdev->bus->number, rpdev->devfn,
+			       rp_pos_cap_err);
+		list_add(&rperr->list, &einjected);
+	}
+	if (einj->cor_status) {
+		if (rperr->root_status & PCI_ERR_ROOT_COR_RCV)
+			rperr->root_status |= PCI_ERR_ROOT_MULTI_COR_RCV;
+		else
+			rperr->root_status |= PCI_ERR_ROOT_COR_RCV;
+		rperr->source_id &= 0xffff0000;
+		rperr->source_id |= (einj->bus << 8) | devfn;
+	}
+	if (einj->uncor_status) {
+		if (rperr->root_status & PCI_ERR_ROOT_UNCOR_RCV)
+			rperr->root_status |= PCI_ERR_ROOT_MULTI_UNCOR_RCV;
+		if (sever & einj->uncor_status) {
+			rperr->root_status |= PCI_ERR_ROOT_FATAL_RCV;
+			if (!(rperr->root_status & PCI_ERR_ROOT_UNCOR_RCV))
+				rperr->root_status |= PCI_ERR_ROOT_FIRST_FATAL;
+		} else
+			rperr->root_status |= PCI_ERR_ROOT_NONFATAL_RCV;
+		rperr->root_status |= PCI_ERR_ROOT_UNCOR_RCV;
+		rperr->source_id &= 0x0000ffff;
+		rperr->source_id |= ((einj->bus << 8) | devfn) << 16;
+	}
+	spin_unlock_irqrestore(&inject_lock, flags);
+
+	if (aer_mask_override) {
+		pci_write_config_dword(dev, pos_cap_err + PCI_ERR_COR_MASK,
+				       cor_mask_orig);
+		pci_write_config_dword(dev, pos_cap_err + PCI_ERR_UNCOR_MASK,
+				       uncor_mask_orig);
+	}
+
+	ret = pci_bus_set_aer_ops(dev->bus);
+	if (ret)
+		goto out_put;
+	ret = pci_bus_set_aer_ops(rpdev->bus);
+	if (ret)
+		goto out_put;
+
+	if (find_aer_device(rpdev, &edev)) {
+		if (!get_service_data(edev)) {
+			printk(KERN_WARNING "AER service is not initialized\n");
+			ret = -EINVAL;
+			goto out_put;
+		}
+		aer_irq(-1, edev);
+	} else
+		ret = -EINVAL;
+out_put:
+	kfree(err_alloc);
+	kfree(rperr_alloc);
+	pci_dev_put(dev);
+	return ret;
+}
+
+static ssize_t aer_inject_write(struct file *filp, const char __user *ubuf,
+				size_t usize, loff_t *off)
+{
+	struct aer_error_inj einj;
+	int ret;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	if (usize < offsetof(struct aer_error_inj, domain) ||
+	    usize > sizeof(einj))
+		return -EINVAL;
+
+	memset(&einj, 0, sizeof(einj));
+	if (copy_from_user(&einj, ubuf, usize))
+		return -EFAULT;
+
+	ret = aer_inject(&einj);
+	return ret ? ret : usize;
+}
+
+static const struct file_operations aer_inject_fops = {
+	.write = aer_inject_write,
+	.owner = THIS_MODULE,
+	.llseek = noop_llseek,
+};
+
+static struct miscdevice aer_inject_device = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "aer_inject",
+	.fops = &aer_inject_fops,
+};
+
+static int __init aer_inject_init(void)
+{
+	return misc_register(&aer_inject_device);
+}
+
+static void __exit aer_inject_exit(void)
+{
+	struct aer_error *err, *err_next;
+	unsigned long flags;
+	struct pci_bus_ops *bus_ops;
+
+	misc_deregister(&aer_inject_device);
+
+	while ((bus_ops = pci_bus_ops_pop())) {
+		pci_bus_set_ops(bus_ops->bus, bus_ops->ops);
+		kfree(bus_ops);
+	}
+
+	spin_lock_irqsave(&inject_lock, flags);
+	list_for_each_entry_safe(err, err_next, &einjected, list) {
+		list_del(&err->list);
+		kfree(err);
+	}
+	spin_unlock_irqrestore(&inject_lock, flags);
+}
+
+module_init(aer_inject_init);
+module_exit(aer_inject_exit);
+
+MODULE_DESCRIPTION("PCIe AER software error injector");
+MODULE_LICENSE("GPL");

drivers/pci/pcie/aer/aerdrv.c

@@ -0,0 +1,434 @@
+/*
+ * drivers/pci/pcie/aer/aerdrv.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 AER root port service driver. The driver will
+ * register an irq handler. When root port triggers an AER interrupt, the irq
+ * handler will collect root port status and schedule a work.
+ *
+ * Copyright (C) 2006 Intel Corp.
+ *	Tom Long Nguyen (tom.l.nguyen@intel.com)
+ *	Zhang Yanmin (yanmin.zhang@intel.com)
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/pci-acpi.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/pm.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <linux/pcieport_if.h>
+#include <linux/slab.h>
+
+#include "aerdrv.h"
+#include "../../pci.h"
+
+/*
+ * Version Information
+ */
+#define DRIVER_VERSION "v1.0"
+#define DRIVER_AUTHOR "tom.l.nguyen@intel.com"
+#define DRIVER_DESC "Root Port Advanced Error Reporting Driver"
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
+MODULE_LICENSE("GPL");
+
+static int aer_probe(struct pcie_device *dev);
+static void aer_remove(struct pcie_device *dev);
+static pci_ers_result_t aer_error_detected(struct pci_dev *dev,
+	enum pci_channel_state error);
+static void aer_error_resume(struct pci_dev *dev);
+static pci_ers_result_t aer_root_reset(struct pci_dev *dev);
+
+static const struct pci_error_handlers aer_error_handlers = {
+	.error_detected = aer_error_detected,
+	.resume		= aer_error_resume,
+};
+
+static struct pcie_port_service_driver aerdriver = {
+	.name		= "aer",
+	.port_type	= PCI_EXP_TYPE_ROOT_PORT,
+	.service	= PCIE_PORT_SERVICE_AER,
+
+	.probe		= aer_probe,
+	.remove		= aer_remove,
+
+	.err_handler	= &aer_error_handlers,
+
+	.reset_link	= aer_root_reset,
+};
+
+static int pcie_aer_disable;
+
+void pci_no_aer(void)
+{
+	pcie_aer_disable = 1;	/* has priority over 'forceload' */
+}
+
+bool pci_aer_available(void)
+{
+	return !pcie_aer_disable && pci_msi_enabled();
+}
+
+static int set_device_error_reporting(struct pci_dev *dev, void *data)
+{
+	bool enable = *((bool *)data);
+	int type = pci_pcie_type(dev);
+
+	if ((type == PCI_EXP_TYPE_ROOT_PORT) ||
+	    (type == PCI_EXP_TYPE_UPSTREAM) ||
+	    (type == PCI_EXP_TYPE_DOWNSTREAM)) {
+		if (enable)
+			pci_enable_pcie_error_reporting(dev);
+		else
+			pci_disable_pcie_error_reporting(dev);
+	}
+
+	if (enable)
+		pcie_set_ecrc_checking(dev);
+
+	return 0;
+}
+
+/**
+ * set_downstream_devices_error_reporting - enable/disable the error reporting  bits on the root port and its downstream ports.
+ * @dev: pointer to root port's pci_dev data structure
+ * @enable: true = enable error reporting, false = disable error reporting.
+ */
+static void set_downstream_devices_error_reporting(struct pci_dev *dev,
+						   bool enable)
+{
+	set_device_error_reporting(dev, &enable);
+
+	if (!dev->subordinate)
+		return;
+	pci_walk_bus(dev->subordinate, set_device_error_reporting, &enable);
+}
+
+/**
+ * aer_enable_rootport - enable Root Port's interrupts when receiving messages
+ * @rpc: pointer to a Root Port data structure
+ *
+ * Invoked when PCIe bus loads AER service driver.
+ */
+static void aer_enable_rootport(struct aer_rpc *rpc)
+{
+	struct pci_dev *pdev = rpc->rpd->port;
+	int aer_pos;
+	u16 reg16;
+	u32 reg32;
+
+	/* Clear PCIe Capability's Device Status */
+	pcie_capability_read_word(pdev, PCI_EXP_DEVSTA, &reg16);
+	pcie_capability_write_word(pdev, PCI_EXP_DEVSTA, reg16);
+
+	/* Disable system error generation in response to error messages */
+	pcie_capability_clear_word(pdev, PCI_EXP_RTCTL,
+				   SYSTEM_ERROR_INTR_ON_MESG_MASK);
+
+	aer_pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR);
+	/* Clear error status */
+	pci_read_config_dword(pdev, aer_pos + PCI_ERR_ROOT_STATUS, &reg32);
+	pci_write_config_dword(pdev, aer_pos + PCI_ERR_ROOT_STATUS, reg32);
+	pci_read_config_dword(pdev, aer_pos + PCI_ERR_COR_STATUS, &reg32);
+	pci_write_config_dword(pdev, aer_pos + PCI_ERR_COR_STATUS, reg32);
+	pci_read_config_dword(pdev, aer_pos + PCI_ERR_UNCOR_STATUS, &reg32);
+	pci_write_config_dword(pdev, aer_pos + PCI_ERR_UNCOR_STATUS, reg32);
+
+	/*
+	 * Enable error reporting for the root port device and downstream port
+	 * devices.
+	 */
+	set_downstream_devices_error_reporting(pdev, true);
+
+	/* Enable Root Port's interrupt in response to error messages */
+	pci_read_config_dword(pdev, aer_pos + PCI_ERR_ROOT_COMMAND, &reg32);
+	reg32 |= ROOT_PORT_INTR_ON_MESG_MASK;
+	pci_write_config_dword(pdev, aer_pos + PCI_ERR_ROOT_COMMAND, reg32);
+}
+
+/**
+ * aer_disable_rootport - disable Root Port's interrupts when receiving messages
+ * @rpc: pointer to a Root Port data structure
+ *
+ * Invoked when PCIe bus unloads AER service driver.
+ */
+static void aer_disable_rootport(struct aer_rpc *rpc)
+{
+	struct pci_dev *pdev = rpc->rpd->port;
+	u32 reg32;
+	int pos;
+
+	/*
+	 * Disable error reporting for the root port device and downstream port
+	 * devices.
+	 */
+	set_downstream_devices_error_reporting(pdev, false);
+
+	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR);
+	/* Disable Root's interrupt in response to error messages */
+	pci_read_config_dword(pdev, pos + PCI_ERR_ROOT_COMMAND, &reg32);
+	reg32 &= ~ROOT_PORT_INTR_ON_MESG_MASK;
+	pci_write_config_dword(pdev, pos + PCI_ERR_ROOT_COMMAND, reg32);
+
+	/* Clear Root's error status reg */
+	pci_read_config_dword(pdev, pos + PCI_ERR_ROOT_STATUS, &reg32);
+	pci_write_config_dword(pdev, pos + PCI_ERR_ROOT_STATUS, reg32);
+}
+
+/**
+ * aer_irq - Root Port's ISR
+ * @irq: IRQ assigned to Root Port
+ * @context: pointer to Root Port data structure
+ *
+ * Invoked when Root Port detects AER messages.
+ */
+irqreturn_t aer_irq(int irq, void *context)
+{
+	unsigned int status, id;
+	struct pcie_device *pdev = (struct pcie_device *)context;
+	struct aer_rpc *rpc = get_service_data(pdev);
+	int next_prod_idx;
+	unsigned long flags;
+	int pos;
+
+	pos = pci_find_ext_capability(pdev->port, PCI_EXT_CAP_ID_ERR);
+	/*
+	 * Must lock access to Root Error Status Reg, Root Error ID Reg,
+	 * and Root error producer/consumer index
+	 */
+	spin_lock_irqsave(&rpc->e_lock, flags);
+
+	/* Read error status */
+	pci_read_config_dword(pdev->port, pos + PCI_ERR_ROOT_STATUS, &status);
+	if (!(status & (PCI_ERR_ROOT_UNCOR_RCV|PCI_ERR_ROOT_COR_RCV))) {
+		spin_unlock_irqrestore(&rpc->e_lock, flags);
+		return IRQ_NONE;
+	}
+
+	/* Read error source and clear error status */
+	pci_read_config_dword(pdev->port, pos + PCI_ERR_ROOT_ERR_SRC, &id);
+	pci_write_config_dword(pdev->port, pos + PCI_ERR_ROOT_STATUS, status);
+
+	/* Store error source for later DPC handler */
+	next_prod_idx = rpc->prod_idx + 1;
+	if (next_prod_idx == AER_ERROR_SOURCES_MAX)
+		next_prod_idx = 0;
+	if (next_prod_idx == rpc->cons_idx) {
+		/*
+		 * Error Storm Condition - possibly the same error occurred.
+		 * Drop the error.
+		 */
+		spin_unlock_irqrestore(&rpc->e_lock, flags);
+		return IRQ_HANDLED;
+	}
+	rpc->e_sources[rpc->prod_idx].status =  status;
+	rpc->e_sources[rpc->prod_idx].id = id;
+	rpc->prod_idx = next_prod_idx;
+	spin_unlock_irqrestore(&rpc->e_lock, flags);
+
+	/*  Invoke DPC handler */
+	schedule_work(&rpc->dpc_handler);
+
+	return IRQ_HANDLED;
+}
+EXPORT_SYMBOL_GPL(aer_irq);
+
+/**
+ * aer_alloc_rpc - allocate Root Port data structure
+ * @dev: pointer to the pcie_dev data structure
+ *
+ * Invoked when Root Port's AER service is loaded.
+ */
+static struct aer_rpc *aer_alloc_rpc(struct pcie_device *dev)
+{
+	struct aer_rpc *rpc;
+
+	rpc = kzalloc(sizeof(struct aer_rpc), GFP_KERNEL);
+	if (!rpc)
+		return NULL;
+
+	/* Initialize Root lock access, e_lock, to Root Error Status Reg */
+	spin_lock_init(&rpc->e_lock);
+
+	rpc->rpd = dev;
+	INIT_WORK(&rpc->dpc_handler, aer_isr);
+	mutex_init(&rpc->rpc_mutex);
+	init_waitqueue_head(&rpc->wait_release);
+
+	/* Use PCIe bus function to store rpc into PCIe device */
+	set_service_data(dev, rpc);
+
+	return rpc;
+}
+
+/**
+ * aer_remove - clean up resources
+ * @dev: pointer to the pcie_dev data structure
+ *
+ * Invoked when PCI Express bus unloads or AER probe fails.
+ */
+static void aer_remove(struct pcie_device *dev)
+{
+	struct aer_rpc *rpc = get_service_data(dev);
+
+	if (rpc) {
+		/* If register interrupt service, it must be free. */
+		if (rpc->isr)
+			free_irq(dev->irq, dev);
+
+		wait_event(rpc->wait_release, rpc->prod_idx == rpc->cons_idx);
+
+		aer_disable_rootport(rpc);
+		kfree(rpc);
+		set_service_data(dev, NULL);
+	}
+}
+
+/**
+ * aer_probe - initialize resources
+ * @dev: pointer to the pcie_dev data structure
+ * @id: pointer to the service id data structure
+ *
+ * Invoked when PCI Express bus loads AER service driver.
+ */
+static int aer_probe(struct pcie_device *dev)
+{
+	int status;
+	struct aer_rpc *rpc;
+	struct device *device = &dev->device;
+
+	/* Init */
+	status = aer_init(dev);
+	if (status)
+		return status;
+
+	/* Alloc rpc data structure */
+	rpc = aer_alloc_rpc(dev);
+	if (!rpc) {
+		dev_printk(KERN_DEBUG, device, "alloc rpc failed\n");
+		aer_remove(dev);
+		return -ENOMEM;
+	}
+
+	/* Request IRQ ISR */
+	status = request_irq(dev->irq, aer_irq, IRQF_SHARED, "aerdrv", dev);
+	if (status) {
+		dev_printk(KERN_DEBUG, device, "request IRQ failed\n");
+		aer_remove(dev);
+		return status;
+	}
+
+	rpc->isr = 1;
+
+	aer_enable_rootport(rpc);
+
+	return status;
+}
+
+/**
+ * aer_root_reset - reset link on Root Port
+ * @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 aer_root_reset(struct pci_dev *dev)
+{
+	u32 reg32;
+	int pos;
+
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
+
+	/* Disable Root's interrupt in response to error messages */
+	pci_read_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, &reg32);
+	reg32 &= ~ROOT_PORT_INTR_ON_MESG_MASK;
+	pci_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, reg32);
+
+	pci_reset_bridge_secondary_bus(dev);
+	dev_printk(KERN_DEBUG, &dev->dev, "Root Port link has been reset\n");
+
+	/* Clear Root Error Status */
+	pci_read_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, &reg32);
+	pci_write_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, reg32);
+
+	/* Enable Root Port's interrupt in response to error messages */
+	pci_read_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, &reg32);
+	reg32 |= ROOT_PORT_INTR_ON_MESG_MASK;
+	pci_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, reg32);
+
+	return PCI_ERS_RESULT_RECOVERED;
+}
+
+/**
+ * aer_error_detected - update severity status
+ * @dev: pointer to Root Port's pci_dev data structure
+ * @error: error severity being notified by port bus
+ *
+ * Invoked by Port Bus driver during error recovery.
+ */
+static pci_ers_result_t aer_error_detected(struct pci_dev *dev,
+			enum pci_channel_state error)
+{
+	/* Root Port has no impact. Always recovers. */
+	return PCI_ERS_RESULT_CAN_RECOVER;
+}
+
+/**
+ * aer_error_resume - clean up corresponding error status bits
+ * @dev: pointer to Root Port's pci_dev data structure
+ *
+ * Invoked by Port Bus driver during nonfatal recovery.
+ */
+static void aer_error_resume(struct pci_dev *dev)
+{
+	int pos;
+	u32 status, mask;
+	u16 reg16;
+
+	/* Clean up Root device status */
+	pcie_capability_read_word(dev, PCI_EXP_DEVSTA, &reg16);
+	pcie_capability_write_word(dev, PCI_EXP_DEVSTA, reg16);
+
+	/* Clean AER Root Error Status */
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
+	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);
+}
+
+/**
+ * aer_service_init - register AER root service driver
+ *
+ * Invoked when AER root service driver is loaded.
+ */
+static int __init aer_service_init(void)
+{
+	if (!pci_aer_available() || aer_acpi_firmware_first())
+		return -ENXIO;
+	return pcie_port_service_register(&aerdriver);
+}
+
+/**
+ * aer_service_exit - unregister AER root service driver
+ *
+ * Invoked when AER root service driver is unloaded.
+ */
+static void __exit aer_service_exit(void)
+{
+	pcie_port_service_unregister(&aerdriver);
+}
+
+module_init(aer_service_init);
+module_exit(aer_service_exit);

drivers/pci/pcie/aer/aerdrv.h

@@ -0,0 +1,132 @@
+/*
+ * Copyright (C) 2006 Intel Corp.
+ *	Tom Long Nguyen (tom.l.nguyen@intel.com)
+ *	Zhang Yanmin (yanmin.zhang@intel.com)
+ *
+ */
+
+#ifndef _AERDRV_H_
+#define _AERDRV_H_
+
+#include <linux/workqueue.h>
+#include <linux/pcieport_if.h>
+#include <linux/aer.h>
+#include <linux/interrupt.h>
+
+#define SYSTEM_ERROR_INTR_ON_MESG_MASK	(PCI_EXP_RTCTL_SECEE|	\
+					PCI_EXP_RTCTL_SENFEE|	\
+					PCI_EXP_RTCTL_SEFEE)
+#define ROOT_PORT_INTR_ON_MESG_MASK	(PCI_ERR_ROOT_CMD_COR_EN|	\
+					PCI_ERR_ROOT_CMD_NONFATAL_EN|	\
+					PCI_ERR_ROOT_CMD_FATAL_EN)
+#define ERR_COR_ID(d)			(d & 0xffff)
+#define ERR_UNCOR_ID(d)			(d >> 16)
+
+#define AER_ERROR_SOURCES_MAX		100
+
+#define AER_LOG_TLP_MASKS		(PCI_ERR_UNC_POISON_TLP|	\
+					PCI_ERR_UNC_ECRC|		\
+					PCI_ERR_UNC_UNSUP|		\
+					PCI_ERR_UNC_COMP_ABORT|		\
+					PCI_ERR_UNC_UNX_COMP|		\
+					PCI_ERR_UNC_MALF_TLP)
+
+#define AER_MAX_MULTI_ERR_DEVICES	5	/* Not likely to have more */
+struct aer_err_info {
+	struct pci_dev *dev[AER_MAX_MULTI_ERR_DEVICES];
+	int error_dev_num;
+
+	unsigned int id:16;
+
+	unsigned int severity:2;	/* 0:NONFATAL | 1:FATAL | 2:COR */
+	unsigned int __pad1:5;
+	unsigned int multi_error_valid:1;
+
+	unsigned int first_error:5;
+	unsigned int __pad2:2;
+	unsigned int tlp_header_valid:1;
+
+	unsigned int status;		/* COR/UNCOR Error Status */
+	unsigned int mask;		/* COR/UNCOR Error Mask */
+	struct aer_header_log_regs tlp;	/* TLP Header */
+};
+
+struct aer_err_source {
+	unsigned int status;
+	unsigned int id;
+};
+
+struct aer_rpc {
+	struct pcie_device *rpd;	/* Root Port device */
+	struct work_struct dpc_handler;
+	struct aer_err_source e_sources[AER_ERROR_SOURCES_MAX];
+	unsigned short prod_idx;	/* Error Producer Index */
+	unsigned short cons_idx;	/* Error Consumer Index */
+	int isr;
+	spinlock_t e_lock;		/*
+					 * Lock access to Error Status/ID Regs
+					 * and error producer/consumer index
+					 */
+	struct mutex rpc_mutex;		/*
+					 * only one thread could do
+					 * recovery on the same
+					 * root port hierarchy
+					 */
+	wait_queue_head_t wait_release;
+};
+
+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;
+int aer_init(struct pcie_device *dev);
+void aer_isr(struct work_struct *work);
+void aer_print_error(struct pci_dev *dev, struct aer_err_info *info);
+void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info);
+irqreturn_t aer_irq(int irq, void *context);
+
+#ifdef CONFIG_ACPI_APEI
+int pcie_aer_get_firmware_first(struct pci_dev *pci_dev);
+#else
+static inline int pcie_aer_get_firmware_first(struct pci_dev *pci_dev)
+{
+	if (pci_dev->__aer_firmware_first_valid)
+		return pci_dev->__aer_firmware_first;
+	return 0;
+}
+#endif
+
+static inline void pcie_aer_force_firmware_first(struct pci_dev *pci_dev,
+						 int enable)
+{
+	pci_dev->__aer_firmware_first = !!enable;
+	pci_dev->__aer_firmware_first_valid = 1;
+}
+#endif /* _AERDRV_H_ */

drivers/pci/pcie/aer/aerdrv_acpi.c

@@ -0,0 +1,141 @@
+/*
+ * Access ACPI _OSC method
+ *
+ * Copyright (C) 2006 Intel Corp.
+ *	Tom Long Nguyen (tom.l.nguyen@intel.com)
+ *	Zhang Yanmin (yanmin.zhang@intel.com)
+ *
+ */
+
+#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/acpi.h>
+#include <linux/pci-acpi.h>
+#include <linux/delay.h>
+#include <acpi/apei.h>
+#include "aerdrv.h"
+
+#ifdef CONFIG_ACPI_APEI
+static inline int hest_match_pci(struct acpi_hest_aer_common *p,
+				 struct pci_dev *pci)
+{
+	return   ACPI_HEST_SEGMENT(p->bus) == pci_domain_nr(pci->bus) &&
+		 ACPI_HEST_BUS(p->bus)     == pci->bus->number &&
+		 p->device                 == PCI_SLOT(pci->devfn) &&
+		 p->function               == PCI_FUNC(pci->devfn);
+}
+
+static inline bool hest_match_type(struct acpi_hest_header *hest_hdr,
+				struct pci_dev *dev)
+{
+	u16 hest_type = hest_hdr->type;
+	u8 pcie_type = pci_pcie_type(dev);
+
+	if ((hest_type == ACPI_HEST_TYPE_AER_ROOT_PORT &&
+		pcie_type == PCI_EXP_TYPE_ROOT_PORT) ||
+	    (hest_type == ACPI_HEST_TYPE_AER_ENDPOINT &&
+		pcie_type == PCI_EXP_TYPE_ENDPOINT) ||
+	    (hest_type == ACPI_HEST_TYPE_AER_BRIDGE &&
+		(dev->class >> 16) == PCI_BASE_CLASS_BRIDGE))
+		return true;
+	return false;
+}
+
+struct aer_hest_parse_info {
+	struct pci_dev *pci_dev;
+	int firmware_first;
+};
+
+static int hest_source_is_pcie_aer(struct acpi_hest_header *hest_hdr)
+{
+	if (hest_hdr->type == ACPI_HEST_TYPE_AER_ROOT_PORT ||
+	    hest_hdr->type == ACPI_HEST_TYPE_AER_ENDPOINT ||
+	    hest_hdr->type == ACPI_HEST_TYPE_AER_BRIDGE)
+		return 1;
+	return 0;
+}
+
+static int aer_hest_parse(struct acpi_hest_header *hest_hdr, void *data)
+{
+	struct aer_hest_parse_info *info = data;
+	struct acpi_hest_aer_common *p;
+	int ff;
+
+	if (!hest_source_is_pcie_aer(hest_hdr))
+		return 0;
+
+	p = (struct acpi_hest_aer_common *)(hest_hdr + 1);
+	ff = !!(p->flags & ACPI_HEST_FIRMWARE_FIRST);
+
+	/*
+	 * If no specific device is supplied, determine whether
+	 * FIRMWARE_FIRST is set for *any* PCIe device.
+	 */
+	if (!info->pci_dev) {
+		info->firmware_first |= ff;
+		return 0;
+	}
+
+	/* Otherwise, check the specific device */
+	if (p->flags & ACPI_HEST_GLOBAL) {
+		if (hest_match_type(hest_hdr, info->pci_dev))
+			info->firmware_first = ff;
+	} else
+		if (hest_match_pci(p, info->pci_dev))
+			info->firmware_first = ff;
+
+	return 0;
+}
+
+static void aer_set_firmware_first(struct pci_dev *pci_dev)
+{
+	int rc;
+	struct aer_hest_parse_info info = {
+		.pci_dev	= pci_dev,
+		.firmware_first	= 0,
+	};
+
+	rc = apei_hest_parse(aer_hest_parse, &info);
+
+	if (rc)
+		pci_dev->__aer_firmware_first = 0;
+	else
+		pci_dev->__aer_firmware_first = info.firmware_first;
+	pci_dev->__aer_firmware_first_valid = 1;
+}
+
+int pcie_aer_get_firmware_first(struct pci_dev *dev)
+{
+	if (!pci_is_pcie(dev))
+		return 0;
+
+	if (!dev->__aer_firmware_first_valid)
+		aer_set_firmware_first(dev);
+	return dev->__aer_firmware_first;
+}
+
+static bool aer_firmware_first;
+
+/**
+ * aer_acpi_firmware_first - Check if APEI should control AER.
+ */
+bool aer_acpi_firmware_first(void)
+{
+	static bool parsed = false;
+	struct aer_hest_parse_info info = {
+		.pci_dev	= NULL,	/* Check all PCIe devices */
+		.firmware_first	= 0,
+	};
+
+	if (!parsed) {
+		apei_hest_parse(aer_hest_parse, &info);
+		aer_firmware_first = info.firmware_first;
+		parsed = true;
+	}
+	return aer_firmware_first;
+}
+#endif

drivers/pci/pcie/aer/aerdrv_core.c

@@ -0,0 +1,805 @@
+/*
+ * 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 (tom.l.nguyen@intel.com)
+ *	Zhang Yanmin (yanmin.zhang@intel.com)
+ *
+ */
+
+#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 <linux/slab.h>
+#include <linux/kfifo.h>
+#include "aerdrv.h"
+
+static bool forceload;
+static bool nosourceid;
+module_param(forceload, bool, 0);
+module_param(nosourceid, bool, 0);
+
+#define	PCI_EXP_AER_FLAGS	(PCI_EXP_DEVCTL_CERE | PCI_EXP_DEVCTL_NFERE | \
+				 PCI_EXP_DEVCTL_FERE | PCI_EXP_DEVCTL_URRE)
+
+int pci_enable_pcie_error_reporting(struct pci_dev *dev)
+{
+	if (pcie_aer_get_firmware_first(dev))
+		return -EIO;
+
+	if (!pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR))
+		return -EIO;
+
+	return pcie_capability_set_word(dev, PCI_EXP_DEVCTL, PCI_EXP_AER_FLAGS);
+}
+EXPORT_SYMBOL_GPL(pci_enable_pcie_error_reporting);
+
+int pci_disable_pcie_error_reporting(struct pci_dev *dev)
+{
+	if (pcie_aer_get_firmware_first(dev))
+		return -EIO;
+
+	return pcie_capability_clear_word(dev, PCI_EXP_DEVCTL,
+					  PCI_EXP_AER_FLAGS);
+}
+EXPORT_SYMBOL_GPL(pci_disable_pcie_error_reporting);
+
+int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev)
+{
+	int pos;
+	u32 status;
+
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
+	if (!pos)
+		return -EIO;
+
+	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status);
+	if (status)
+		pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, status);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pci_cleanup_aer_uncorrect_error_status);
+
+/**
+ * add_error_device - list device to be handled
+ * @e_info: pointer to error info
+ * @dev: pointer to pci_dev to be added
+ */
+static int add_error_device(struct aer_err_info *e_info, struct pci_dev *dev)
+{
+	if (e_info->error_dev_num < AER_MAX_MULTI_ERR_DEVICES) {
+		e_info->dev[e_info->error_dev_num] = dev;
+		e_info->error_dev_num++;
+		return 0;
+	}
+	return -ENOSPC;
+}
+
+/**
+ * is_error_source - check whether the device is source of reported error
+ * @dev: pointer to pci_dev to be checked
+ * @e_info: pointer to reported error info
+ */
+static bool is_error_source(struct pci_dev *dev, struct aer_err_info *e_info)
+{
+	int pos;
+	u32 status, mask;
+	u16 reg16;
+
+	/*
+	 * When bus id is equal to 0, it might be a bad id
+	 * reported by root port.
+	 */
+	if (!nosourceid && (PCI_BUS_NUM(e_info->id) != 0)) {
+		/* Device ID match? */
+		if (e_info->id == ((dev->bus->number << 8) | dev->devfn))
+			return true;
+
+		/* Continue id comparing if there is no multiple error */
+		if (!e_info->multi_error_valid)
+			return false;
+	}
+
+	/*
+	 * When either
+	 *      1) nosourceid==y;
+	 *      2) bus id is equal to 0. Some ports might lose the bus
+	 *              id of error source id;
+	 *      3) There are multiple errors and prior id comparing fails;
+	 * We check AER status registers to find possible reporter.
+	 */
+	if (atomic_read(&dev->enable_cnt) == 0)
+		return false;
+
+	/* Check if AER is enabled */
+	pcie_capability_read_word(dev, PCI_EXP_DEVCTL, &reg16);
+	if (!(reg16 & PCI_EXP_AER_FLAGS))
+		return false;
+
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
+	if (!pos)
+		return false;
+
+	/* Check if error is recorded */
+	if (e_info->severity == AER_CORRECTABLE) {
+		pci_read_config_dword(dev, pos + PCI_ERR_COR_STATUS, &status);
+		pci_read_config_dword(dev, pos + PCI_ERR_COR_MASK, &mask);
+	} else {
+		pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status);
+		pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, &mask);
+	}
+	if (status & ~mask)
+		return true;
+
+	return false;
+}
+
+static int find_device_iter(struct pci_dev *dev, void *data)
+{
+	struct aer_err_info *e_info = (struct aer_err_info *)data;
+
+	if (is_error_source(dev, e_info)) {
+		/* List this device */
+		if (add_error_device(e_info, dev)) {
+			/* We cannot handle more... Stop iteration */
+			/* TODO: Should print error message here? */
+			return 1;
+		}
+
+		/* If there is only a single error, stop iteration */
+		if (!e_info->multi_error_valid)
+			return 1;
+	}
+	return 0;
+}
+
+/**
+ * find_source_device - search through device hierarchy for source device
+ * @parent: pointer to Root Port pci_dev data structure
+ * @e_info: including detailed error information such like id
+ *
+ * Return true if found.
+ *
+ * Invoked by DPC when error is detected at the Root Port.
+ * Caller of this function must set id, severity, and multi_error_valid of
+ * struct aer_err_info pointed by @e_info properly.  This function must fill
+ * e_info->error_dev_num and e_info->dev[], based on the given information.
+ */
+static bool find_source_device(struct pci_dev *parent,
+		struct aer_err_info *e_info)
+{
+	struct pci_dev *dev = parent;
+	int result;
+
+	/* Must reset in this function */
+	e_info->error_dev_num = 0;
+
+	/* Is Root Port an agent that sends error message? */
+	result = find_device_iter(dev, e_info);
+	if (result)
+		return true;
+
+	pci_walk_bus(parent->subordinate, find_device_iter, e_info);
+
+	if (!e_info->error_dev_num) {
+		dev_printk(KERN_DEBUG, &parent->dev,
+				"can't find device of ID%04x\n",
+				e_info->id);
+		return false;
+	}
+	return true;
+}
+
+static int report_error_detected(struct pci_dev *dev, void *data)
+{
+	pci_ers_result_t vote;
+	const struct pci_error_handlers *err_handler;
+	struct aer_broadcast_data *result_data;
+	result_data = (struct aer_broadcast_data *) data;
+
+	device_lock(&dev->dev);
+	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.
+			 */
+			dev_printk(KERN_DEBUG, &dev->dev, "device has %s\n",
+				   dev->driver ?
+				   "no AER-aware driver" : "no driver");
+		}
+
+		/*
+		 * If there's any device in the subtree that does not
+		 * have an error_detected callback, returning
+		 * PCI_ERS_RESULT_NO_AER_DRIVER prevents calling of
+		 * the subsequent mmio_enabled/slot_reset/resume
+		 * callbacks of "any" device in the subtree. All the
+		 * devices in the subtree are left in the error state
+		 * without recovery.
+		 */
+
+		if (!(dev->hdr_type & PCI_HEADER_TYPE_BRIDGE))
+			vote = PCI_ERS_RESULT_NO_AER_DRIVER;
+		else
+			vote = PCI_ERS_RESULT_NONE;
+	} else {
+		err_handler = dev->driver->err_handler;
+		vote = err_handler->error_detected(dev, result_data->state);
+	}
+
+	result_data->result = merge_result(result_data->result, vote);
+	device_unlock(&dev->dev);
+	return 0;
+}
+
+static int report_mmio_enabled(struct pci_dev *dev, void *data)
+{
+	pci_ers_result_t vote;
+	const struct pci_error_handlers *err_handler;
+	struct aer_broadcast_data *result_data;
+	result_data = (struct aer_broadcast_data *) data;
+
+	device_lock(&dev->dev);
+	if (!dev->driver ||
+		!dev->driver->err_handler ||
+		!dev->driver->err_handler->mmio_enabled)
+		goto out;
+
+	err_handler = dev->driver->err_handler;
+	vote = err_handler->mmio_enabled(dev);
+	result_data->result = merge_result(result_data->result, vote);
+out:
+	device_unlock(&dev->dev);
+	return 0;
+}
+
+static int report_slot_reset(struct pci_dev *dev, void *data)
+{
+	pci_ers_result_t vote;
+	const struct pci_error_handlers *err_handler;
+	struct aer_broadcast_data *result_data;
+	result_data = (struct aer_broadcast_data *) data;
+
+	device_lock(&dev->dev);
+	if (!dev->driver ||
+		!dev->driver->err_handler ||
+		!dev->driver->err_handler->slot_reset)
+		goto out;
+
+	err_handler = dev->driver->err_handler;
+	vote = err_handler->slot_reset(dev);
+	result_data->result = merge_result(result_data->result, vote);
+out:
+	device_unlock(&dev->dev);
+	return 0;
+}
+
+static int report_resume(struct pci_dev *dev, void *data)
+{
+	const struct pci_error_handlers *err_handler;
+
+	device_lock(&dev->dev);
+	dev->error_state = pci_channel_io_normal;
+
+	if (!dev->driver ||
+		!dev->driver->err_handler ||
+		!dev->driver->err_handler->resume)
+		goto out;
+
+	err_handler = dev->driver->err_handler;
+	err_handler->resume(dev);
+out:
+	device_unlock(&dev->dev);
+	return 0;
+}
+
+/**
+ * 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,
+	int (*cb)(struct pci_dev *, void *))
+{
+	struct aer_broadcast_data result_data;
+
+	dev_printk(KERN_DEBUG, &dev->dev, "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;
+}
+
+/**
+ * default_reset_link - default reset function
+ * @dev: pointer to pci_dev data structure
+ *
+ * Invoked when performing link reset on a Downstream Port or a
+ * Root Port with no aer driver.
+ */
+static pci_ers_result_t default_reset_link(struct pci_dev *dev)
+{
+	pci_reset_bridge_secondary_bus(dev);
+	dev_printk(KERN_DEBUG, &dev->dev, "downstream link has been reset\n");
+	return PCI_ERS_RESULT_RECOVERED;
+}
+
+static int find_aer_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_AER) {
+			*drv = service_driver;
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
+static struct pcie_port_service_driver *find_aer_service(struct pci_dev *dev)
+{
+	struct pcie_port_service_driver *drv = NULL;
+
+	device_for_each_child(&dev->dev, &drv, find_aer_service_iter);
+
+	return drv;
+}
+
+static pci_ers_result_t reset_link(struct pci_dev *dev)
+{
+	struct pci_dev *udev;
+	pci_ers_result_t status;
+	struct pcie_port_service_driver *driver;
+
+	if (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE) {
+		/* Reset this port for all subordinates */
+		udev = dev;
+	} else {
+		/* Reset the upstream component (likely downstream port) */
+		udev = dev->bus->self;
+	}
+
+	/* Use the aer driver of the component firstly */
+	driver = find_aer_service(udev);
+
+	if (driver && driver->reset_link) {
+		status = driver->reset_link(udev);
+	} else if (pci_pcie_type(udev) == PCI_EXP_TYPE_DOWNSTREAM ||
+		pci_pcie_type(udev) == PCI_EXP_TYPE_ROOT_PORT) {
+		status = default_reset_link(udev);
+	} else {
+		dev_printk(KERN_DEBUG, &dev->dev,
+			"no link-reset support at upstream device %s\n",
+			pci_name(udev));
+		return PCI_ERS_RESULT_DISCONNECT;
+	}
+
+	if (status != PCI_ERS_RESULT_RECOVERED) {
+		dev_printk(KERN_DEBUG, &dev->dev,
+			"link reset at upstream device %s failed\n",
+			pci_name(udev));
+		return PCI_ERS_RESULT_DISCONNECT;
+	}
+
+	return status;
+}
+
+/**
+ * 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
+ *
+ * Invoked when an error is nonfatal/fatal. Once being invoked, broadcast
+ * 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)
+{
+	pci_ers_result_t status, result = PCI_ERS_RESULT_RECOVERED;
+	enum pci_channel_state state;
+
+	if (severity == AER_FATAL)
+		state = pci_channel_io_frozen;
+	else
+		state = pci_channel_io_normal;
+
+	status = broadcast_error_message(dev,
+			state,
+			"error_detected",
+			report_error_detected);
+
+	if (severity == AER_FATAL) {
+		result = reset_link(dev);
+		if (result != PCI_ERS_RESULT_RECOVERED)
+			goto failed;
+	}
+
+	if (status == PCI_ERS_RESULT_CAN_RECOVER)
+		status = broadcast_error_message(dev,
+				state,
+				"mmio_enabled",
+				report_mmio_enabled);
+
+	if (status == PCI_ERS_RESULT_NEED_RESET) {
+		/*
+		 * TODO: Should call platform-specific
+		 * functions to reset slot before calling
+		 * drivers' slot_reset callbacks?
+		 */
+		status = broadcast_error_message(dev,
+				state,
+				"slot_reset",
+				report_slot_reset);
+	}
+
+	if (status != PCI_ERS_RESULT_RECOVERED)
+		goto failed;
+
+	broadcast_error_message(dev,
+				state,
+				"resume",
+				report_resume);
+
+	dev_info(&dev->dev, "AER: Device recovery successful\n");
+	return;
+
+failed:
+	/* TODO: Should kernel panic here? */
+	dev_info(&dev->dev, "AER: Device recovery failed\n");
+}
+
+/**
+ * handle_error_source - handle logging error into an event log
+ * @aerdev: pointer to pcie_device data structure of the root port
+ * @dev: pointer to pci_dev data structure of error source device
+ * @info: comprehensive error information
+ *
+ * Invoked when an error being detected by Root Port.
+ */
+static void handle_error_source(struct pcie_device *aerdev,
+	struct pci_dev *dev,
+	struct aer_err_info *info)
+{
+	int pos;
+
+	if (info->severity == AER_CORRECTABLE) {
+		/*
+		 * Correctable error does not need software intervention.
+		 * No need to go through error recovery process.
+		 */
+		pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
+		if (pos)
+			pci_write_config_dword(dev, pos + PCI_ERR_COR_STATUS,
+					info->status);
+	} else
+		do_recovery(dev, info->severity);
+}
+
+#ifdef CONFIG_ACPI_APEI_PCIEAER
+static void aer_recover_work_func(struct work_struct *work);
+
+#define AER_RECOVER_RING_ORDER		4
+#define AER_RECOVER_RING_SIZE		(1 << AER_RECOVER_RING_ORDER)
+
+struct aer_recover_entry {
+	u8	bus;
+	u8	devfn;
+	u16	domain;
+	int	severity;
+	struct aer_capability_regs *regs;
+};
+
+static DEFINE_KFIFO(aer_recover_ring, struct aer_recover_entry,
+		    AER_RECOVER_RING_SIZE);
+/*
+ * Mutual exclusion for writers of aer_recover_ring, reader side don't
+ * need lock, because there is only one reader and lock is not needed
+ * between reader and writer.
+ */
+static DEFINE_SPINLOCK(aer_recover_ring_lock);
+static DECLARE_WORK(aer_recover_work, aer_recover_work_func);
+
+void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn,
+		       int severity, struct aer_capability_regs *aer_regs)
+{
+	unsigned long flags;
+	struct aer_recover_entry entry = {
+		.bus		= bus,
+		.devfn		= devfn,
+		.domain		= domain,
+		.severity	= severity,
+		.regs		= aer_regs,
+	};
+
+	spin_lock_irqsave(&aer_recover_ring_lock, flags);
+	if (kfifo_put(&aer_recover_ring, entry))
+		schedule_work(&aer_recover_work);
+	else
+		pr_err("AER recover: Buffer overflow when recovering AER for %04x:%02x:%02x:%x\n",
+		       domain, bus, PCI_SLOT(devfn), PCI_FUNC(devfn));
+	spin_unlock_irqrestore(&aer_recover_ring_lock, flags);
+}
+EXPORT_SYMBOL_GPL(aer_recover_queue);
+
+static void aer_recover_work_func(struct work_struct *work)
+{
+	struct aer_recover_entry entry;
+	struct pci_dev *pdev;
+
+	while (kfifo_get(&aer_recover_ring, &entry)) {
+		pdev = pci_get_domain_bus_and_slot(entry.domain, entry.bus,
+						   entry.devfn);
+		if (!pdev) {
+			pr_err("AER recover: Can not find pci_dev for %04x:%02x:%02x:%x\n",
+			       entry.domain, entry.bus,
+			       PCI_SLOT(entry.devfn), PCI_FUNC(entry.devfn));
+			continue;
+		}
+		cper_print_aer(pdev, entry.severity, entry.regs);
+		do_recovery(pdev, entry.severity);
+		pci_dev_put(pdev);
+	}
+}
+#endif
+
+/**
+ * get_device_error_info - read error status from dev and store it to info
+ * @dev: pointer to the device expected to have a error record
+ * @info: pointer to structure to store the error record
+ *
+ * Return 1 on success, 0 on error.
+ *
+ * Note that @info is reused among all error devices. Clear fields properly.
+ */
+static int get_device_error_info(struct pci_dev *dev, struct aer_err_info *info)
+{
+	int pos, temp;
+
+	/* Must reset in this function */
+	info->status = 0;
+	info->tlp_header_valid = 0;
+
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
+
+	/* The device might not support AER */
+	if (!pos)
+		return 1;
+
+	if (info->severity == AER_CORRECTABLE) {
+		pci_read_config_dword(dev, pos + PCI_ERR_COR_STATUS,
+			&info->status);
+		pci_read_config_dword(dev, pos + PCI_ERR_COR_MASK,
+			&info->mask);
+		if (!(info->status & ~info->mask))
+			return 0;
+	} else if (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE ||
+		info->severity == AER_NONFATAL) {
+
+		/* Link is still healthy for IO reads */
+		pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS,
+			&info->status);
+		pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_MASK,
+			&info->mask);
+		if (!(info->status & ~info->mask))
+			return 0;
+
+		/* Get First Error Pointer */
+		pci_read_config_dword(dev, pos + PCI_ERR_CAP, &temp);
+		info->first_error = PCI_ERR_CAP_FEP(temp);
+
+		if (info->status & AER_LOG_TLP_MASKS) {
+			info->tlp_header_valid = 1;
+			pci_read_config_dword(dev,
+				pos + PCI_ERR_HEADER_LOG, &info->tlp.dw0);
+			pci_read_config_dword(dev,
+				pos + PCI_ERR_HEADER_LOG + 4, &info->tlp.dw1);
+			pci_read_config_dword(dev,
+				pos + PCI_ERR_HEADER_LOG + 8, &info->tlp.dw2);
+			pci_read_config_dword(dev,
+				pos + PCI_ERR_HEADER_LOG + 12, &info->tlp.dw3);
+		}
+	}
+
+	return 1;
+}
+
+static inline void aer_process_err_devices(struct pcie_device *p_device,
+			struct aer_err_info *e_info)
+{
+	int i;
+
+	/* Report all before handle them, not to lost records by reset etc. */
+	for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) {
+		if (get_device_error_info(e_info->dev[i], e_info))
+			aer_print_error(e_info->dev[i], e_info);
+	}
+	for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) {
+		if (get_device_error_info(e_info->dev[i], e_info))
+			handle_error_source(p_device, e_info->dev[i], e_info);
+	}
+}
+
+/**
+ * aer_isr_one_error - consume an error detected by root port
+ * @p_device: pointer to error root port service device
+ * @e_src: pointer to an error source
+ */
+static void aer_isr_one_error(struct pcie_device *p_device,
+		struct aer_err_source *e_src)
+{
+	struct aer_err_info *e_info;
+
+	/* struct aer_err_info might be big, so we allocate it with slab */
+	e_info = kmalloc(sizeof(struct aer_err_info), GFP_KERNEL);
+	if (!e_info) {
+		dev_printk(KERN_DEBUG, &p_device->port->dev,
+			"Can't allocate mem when processing AER errors\n");
+		return;
+	}
+
+	/*
+	 * There is a possibility that both correctable error and
+	 * uncorrectable error being logged. Report correctable error first.
+	 */
+	if (e_src->status & PCI_ERR_ROOT_COR_RCV) {
+		e_info->id = ERR_COR_ID(e_src->id);
+		e_info->severity = AER_CORRECTABLE;
+
+		if (e_src->status & PCI_ERR_ROOT_MULTI_COR_RCV)
+			e_info->multi_error_valid = 1;
+		else
+			e_info->multi_error_valid = 0;
+
+		aer_print_port_info(p_device->port, e_info);
+
+		if (find_source_device(p_device->port, e_info))
+			aer_process_err_devices(p_device, e_info);
+	}
+
+	if (e_src->status & PCI_ERR_ROOT_UNCOR_RCV) {
+		e_info->id = ERR_UNCOR_ID(e_src->id);
+
+		if (e_src->status & PCI_ERR_ROOT_FATAL_RCV)
+			e_info->severity = AER_FATAL;
+		else
+			e_info->severity = AER_NONFATAL;
+
+		if (e_src->status & PCI_ERR_ROOT_MULTI_UNCOR_RCV)
+			e_info->multi_error_valid = 1;
+		else
+			e_info->multi_error_valid = 0;
+
+		aer_print_port_info(p_device->port, e_info);
+
+		if (find_source_device(p_device->port, e_info))
+			aer_process_err_devices(p_device, e_info);
+	}
+
+	kfree(e_info);
+}
+
+/**
+ * get_e_source - retrieve an error source
+ * @rpc: pointer to the root port which holds an error
+ * @e_src: pointer to store retrieved error source
+ *
+ * Return 1 if an error source is retrieved, otherwise 0.
+ *
+ * Invoked by DPC handler to consume an error.
+ */
+static int get_e_source(struct aer_rpc *rpc, struct aer_err_source *e_src)
+{
+	unsigned long flags;
+
+	/* Lock access to Root error producer/consumer index */
+	spin_lock_irqsave(&rpc->e_lock, flags);
+	if (rpc->prod_idx == rpc->cons_idx) {
+		spin_unlock_irqrestore(&rpc->e_lock, flags);
+		return 0;
+	}
+
+	*e_src = rpc->e_sources[rpc->cons_idx];
+	rpc->cons_idx++;
+	if (rpc->cons_idx == AER_ERROR_SOURCES_MAX)
+		rpc->cons_idx = 0;
+	spin_unlock_irqrestore(&rpc->e_lock, flags);
+
+	return 1;
+}
+
+/**
+ * aer_isr - consume errors detected by root port
+ * @work: definition of this work item
+ *
+ * Invoked, as DPC, when root port records new detected error
+ */
+void aer_isr(struct work_struct *work)
+{
+	struct aer_rpc *rpc = container_of(work, struct aer_rpc, dpc_handler);
+	struct pcie_device *p_device = rpc->rpd;
+	struct aer_err_source uninitialized_var(e_src);
+
+	mutex_lock(&rpc->rpc_mutex);
+	while (get_e_source(rpc, &e_src))
+		aer_isr_one_error(p_device, &e_src);
+	mutex_unlock(&rpc->rpc_mutex);
+
+	wake_up(&rpc->wait_release);
+}
+
+/**
+ * aer_init - provide AER initialization
+ * @dev: pointer to AER pcie device
+ *
+ * Invoked when AER service driver is loaded.
+ */
+int aer_init(struct pcie_device *dev)
+{
+	if (forceload) {
+		dev_printk(KERN_DEBUG, &dev->device,
+			   "aerdrv forceload requested.\n");
+		pcie_aer_force_firmware_first(dev->port, 0);
+	}
+	return 0;
+}

drivers/pci/pcie/aer/aerdrv_errprint.c

@@ -0,0 +1,262 @@
+/*
+ * drivers/pci/pcie/aer/aerdrv_errprint.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.
+ *
+ * Format error messages and print them to console.
+ *
+ * Copyright (C) 2006 Intel Corp.
+ *	Tom Long Nguyen (tom.l.nguyen@intel.com)
+ *	Zhang Yanmin (yanmin.zhang@intel.com)
+ *
+ */
+
+#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/cper.h>
+
+#include "aerdrv.h"
+#include <ras/ras_event.h>
+
+#define AER_AGENT_RECEIVER		0
+#define AER_AGENT_REQUESTER		1
+#define AER_AGENT_COMPLETER		2
+#define AER_AGENT_TRANSMITTER		3
+
+#define AER_AGENT_REQUESTER_MASK(t)	((t == AER_CORRECTABLE) ?	\
+	0 : (PCI_ERR_UNC_COMP_TIME|PCI_ERR_UNC_UNSUP))
+#define AER_AGENT_COMPLETER_MASK(t)	((t == AER_CORRECTABLE) ?	\
+	0 : PCI_ERR_UNC_COMP_ABORT)
+#define AER_AGENT_TRANSMITTER_MASK(t)	((t == AER_CORRECTABLE) ?	\
+	(PCI_ERR_COR_REP_ROLL|PCI_ERR_COR_REP_TIMER) : 0)
+
+#define AER_GET_AGENT(t, e)						\
+	((e & AER_AGENT_COMPLETER_MASK(t)) ? AER_AGENT_COMPLETER :	\
+	(e & AER_AGENT_REQUESTER_MASK(t)) ? AER_AGENT_REQUESTER :	\
+	(e & AER_AGENT_TRANSMITTER_MASK(t)) ? AER_AGENT_TRANSMITTER :	\
+	AER_AGENT_RECEIVER)
+
+#define AER_PHYSICAL_LAYER_ERROR	0
+#define AER_DATA_LINK_LAYER_ERROR	1
+#define AER_TRANSACTION_LAYER_ERROR	2
+
+#define AER_PHYSICAL_LAYER_ERROR_MASK(t) ((t == AER_CORRECTABLE) ?	\
+	PCI_ERR_COR_RCVR : 0)
+#define AER_DATA_LINK_LAYER_ERROR_MASK(t) ((t == AER_CORRECTABLE) ?	\
+	(PCI_ERR_COR_BAD_TLP|						\
+	PCI_ERR_COR_BAD_DLLP|						\
+	PCI_ERR_COR_REP_ROLL|						\
+	PCI_ERR_COR_REP_TIMER) : PCI_ERR_UNC_DLP)
+
+#define AER_GET_LAYER_ERROR(t, e)					\
+	((e & AER_PHYSICAL_LAYER_ERROR_MASK(t)) ? AER_PHYSICAL_LAYER_ERROR : \
+	(e & AER_DATA_LINK_LAYER_ERROR_MASK(t)) ? AER_DATA_LINK_LAYER_ERROR : \
+	AER_TRANSACTION_LAYER_ERROR)
+
+/*
+ * AER error strings
+ */
+static const char *aer_error_severity_string[] = {
+	"Uncorrected (Non-Fatal)",
+	"Uncorrected (Fatal)",
+	"Corrected"
+};
+
+static const char *aer_error_layer[] = {
+	"Physical Layer",
+	"Data Link Layer",
+	"Transaction Layer"
+};
+
+static const char *aer_correctable_error_string[] = {
+	"Receiver Error",		/* Bit Position 0	*/
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	"Bad TLP",			/* Bit Position 6	*/
+	"Bad DLLP",			/* Bit Position 7	*/
+	"RELAY_NUM Rollover",		/* Bit Position 8	*/
+	NULL,
+	NULL,
+	NULL,
+	"Replay Timer Timeout",		/* Bit Position 12	*/
+	"Advisory Non-Fatal",		/* Bit Position 13	*/
+	"Corrected Internal Error",	/* Bit Position 14	*/
+	"Header Log Overflow",		/* Bit Position 15	*/
+};
+
+static const char *aer_uncorrectable_error_string[] = {
+	"Undefined",			/* Bit Position 0	*/
+	NULL,
+	NULL,
+	NULL,
+	"Data Link Protocol",		/* Bit Position 4	*/
+	"Surprise Down Error",		/* Bit Position 5	*/
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	"Poisoned TLP",			/* Bit Position 12	*/
+	"Flow Control Protocol",	/* Bit Position 13	*/
+	"Completion Timeout",		/* Bit Position 14	*/
+	"Completer Abort",		/* Bit Position 15	*/
+	"Unexpected Completion",	/* Bit Position 16	*/
+	"Receiver Overflow",		/* Bit Position 17	*/
+	"Malformed TLP",		/* Bit Position 18	*/
+	"ECRC",				/* Bit Position 19	*/
+	"Unsupported Request",		/* Bit Position 20	*/
+	"ACS Violation",		/* Bit Position 21	*/
+	"Uncorrectable Internal Error",	/* Bit Position 22	*/
+	"MC Blocked TLP",		/* Bit Position 23	*/
+	"AtomicOp Egress Blocked",	/* Bit Position 24	*/
+	"TLP Prefix Blocked Error",	/* Bit Position 25	*/
+};
+
+static const char *aer_agent_string[] = {
+	"Receiver ID",
+	"Requester ID",
+	"Completer ID",
+	"Transmitter ID"
+};
+
+static void __print_tlp_header(struct pci_dev *dev,
+			       struct aer_header_log_regs *t)
+{
+	dev_err(&dev->dev, "  TLP Header: %08x %08x %08x %08x\n",
+		t->dw0, t->dw1, t->dw2, t->dw3);
+}
+
+static void __aer_print_error(struct pci_dev *dev,
+			      struct aer_err_info *info)
+{
+	int i, status;
+	const char *errmsg = NULL;
+	status = (info->status & ~info->mask);
+
+	for (i = 0; i < 32; i++) {
+		if (!(status & (1 << i)))
+			continue;
+
+		if (info->severity == AER_CORRECTABLE)
+			errmsg = i < ARRAY_SIZE(aer_correctable_error_string) ?
+				aer_correctable_error_string[i] : NULL;
+		else
+			errmsg = i < ARRAY_SIZE(aer_uncorrectable_error_string) ?
+				aer_uncorrectable_error_string[i] : NULL;
+
+		if (errmsg)
+			dev_err(&dev->dev, "   [%2d] %-22s%s\n", i, errmsg,
+				info->first_error == i ? " (First)" : "");
+		else
+			dev_err(&dev->dev, "   [%2d] Unknown Error Bit%s\n",
+				i, info->first_error == i ? " (First)" : "");
+	}
+}
+
+void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
+{
+	int layer, agent;
+	int id = ((dev->bus->number << 8) | dev->devfn);
+
+	if (!info->status) {
+		dev_err(&dev->dev, "PCIe Bus Error: severity=%s, type=Unaccessible, id=%04x(Unregistered Agent ID)\n",
+			aer_error_severity_string[info->severity], id);
+		goto out;
+	}
+
+	layer = AER_GET_LAYER_ERROR(info->severity, info->status);
+	agent = AER_GET_AGENT(info->severity, info->status);
+
+	dev_err(&dev->dev, "PCIe Bus Error: severity=%s, type=%s, id=%04x(%s)\n",
+		aer_error_severity_string[info->severity],
+		aer_error_layer[layer], id, aer_agent_string[agent]);
+
+	dev_err(&dev->dev, "  device [%04x:%04x] error status/mask=%08x/%08x\n",
+		dev->vendor, dev->device,
+		info->status, info->mask);
+
+	__aer_print_error(dev, info);
+
+	if (info->tlp_header_valid)
+		__print_tlp_header(dev, &info->tlp);
+
+out:
+	if (info->id && info->error_dev_num > 1 && info->id == id)
+		dev_err(&dev->dev, "  Error of this Agent(%04x) is reported first\n", id);
+
+	trace_aer_event(dev_name(&dev->dev), (info->status & ~info->mask),
+			info->severity);
+}
+
+void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info)
+{
+	dev_info(&dev->dev, "AER: %s%s error received: id=%04x\n",
+		info->multi_error_valid ? "Multiple " : "",
+		aer_error_severity_string[info->severity], info->id);
+}
+
+#ifdef CONFIG_ACPI_APEI_PCIEAER
+int cper_severity_to_aer(int cper_severity)
+{
+	switch (cper_severity) {
+	case CPER_SEV_RECOVERABLE:
+		return AER_NONFATAL;
+	case CPER_SEV_FATAL:
+		return AER_FATAL;
+	default:
+		return AER_CORRECTABLE;
+	}
+}
+EXPORT_SYMBOL_GPL(cper_severity_to_aer);
+
+void cper_print_aer(struct pci_dev *dev, int cper_severity,
+		    struct aer_capability_regs *aer)
+{
+	int aer_severity, layer, agent, status_strs_size, tlp_header_valid = 0;
+	u32 status, mask;
+	const char **status_strs;
+
+	aer_severity = cper_severity_to_aer(cper_severity);
+
+	if (aer_severity == AER_CORRECTABLE) {
+		status = aer->cor_status;
+		mask = aer->cor_mask;
+		status_strs = aer_correctable_error_string;
+		status_strs_size = ARRAY_SIZE(aer_correctable_error_string);
+	} else {
+		status = aer->uncor_status;
+		mask = aer->uncor_mask;
+		status_strs = aer_uncorrectable_error_string;
+		status_strs_size = ARRAY_SIZE(aer_uncorrectable_error_string);
+		tlp_header_valid = status & AER_LOG_TLP_MASKS;
+	}
+
+	layer = AER_GET_LAYER_ERROR(aer_severity, status);
+	agent = AER_GET_AGENT(aer_severity, status);
+
+	dev_err(&dev->dev, "aer_status: 0x%08x, aer_mask: 0x%08x\n", status, mask);
+	cper_print_bits("", status, status_strs, status_strs_size);
+	dev_err(&dev->dev, "aer_layer=%s, aer_agent=%s\n",
+		aer_error_layer[layer], aer_agent_string[agent]);
+
+	if (aer_severity != AER_CORRECTABLE)
+		dev_err(&dev->dev, "aer_uncor_severity: 0x%08x\n",
+			aer->uncor_severity);
+
+	if (tlp_header_valid)
+		__print_tlp_header(dev, &aer->header_log);
+
+	trace_aer_event(dev_name(&dev->dev), (status & ~mask),
+			aer_severity);
+}
+#endif

drivers/pci/pcie/aer/ecrc.c

@@ -0,0 +1,131 @@
+/*
+ *    Enables/disables PCIe ECRC checking.
+ *
+ *    (C) Copyright 2009 Hewlett-Packard Development Company, L.P.
+ *    Andrew Patterson <andrew.patterson@hp.com>
+ *
+ *    This program is free software; you can redistribute it and/or modify
+ *    it under the terms of the GNU General Public License as published by
+ *    the Free Software Foundation; version 2 of the License.
+ *
+ *    This program is distributed in the hope that it will be useful,
+ *    but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *    MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ *    General Public License for more details.
+ *
+ *    You should have received a copy of the GNU General Public License
+ *    along with this program; if not, write to the Free Software
+ *    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
+ *    02111-1307, USA.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/pci.h>
+#include <linux/pci_regs.h>
+#include <linux/errno.h>
+#include "../../pci.h"
+
+#define ECRC_POLICY_DEFAULT 0		/* ECRC set by BIOS */
+#define ECRC_POLICY_OFF     1		/* ECRC off for performance */
+#define ECRC_POLICY_ON      2		/* ECRC on for data integrity */
+
+static int ecrc_policy = ECRC_POLICY_DEFAULT;
+
+static const char *ecrc_policy_str[] = {
+	[ECRC_POLICY_DEFAULT] = "bios",
+	[ECRC_POLICY_OFF] = "off",
+	[ECRC_POLICY_ON] = "on"
+};
+
+/**
+ * enable_ercr_checking - enable PCIe ECRC checking for a device
+ * @dev: the PCI device
+ *
+ * Returns 0 on success, or negative on failure.
+ */
+static int enable_ecrc_checking(struct pci_dev *dev)
+{
+	int pos;
+	u32 reg32;
+
+	if (!pci_is_pcie(dev))
+		return -ENODEV;
+
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
+	if (!pos)
+		return -ENODEV;
+
+	pci_read_config_dword(dev, pos + PCI_ERR_CAP, &reg32);
+	if (reg32 & PCI_ERR_CAP_ECRC_GENC)
+		reg32 |= PCI_ERR_CAP_ECRC_GENE;
+	if (reg32 & PCI_ERR_CAP_ECRC_CHKC)
+		reg32 |= PCI_ERR_CAP_ECRC_CHKE;
+	pci_write_config_dword(dev, pos + PCI_ERR_CAP, reg32);
+
+	return 0;
+}
+
+/**
+ * disable_ercr_checking - disables PCIe ECRC checking for a device
+ * @dev: the PCI device
+ *
+ * Returns 0 on success, or negative on failure.
+ */
+static int disable_ecrc_checking(struct pci_dev *dev)
+{
+	int pos;
+	u32 reg32;
+
+	if (!pci_is_pcie(dev))
+		return -ENODEV;
+
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
+	if (!pos)
+		return -ENODEV;
+
+	pci_read_config_dword(dev, pos + PCI_ERR_CAP, &reg32);
+	reg32 &= ~(PCI_ERR_CAP_ECRC_GENE | PCI_ERR_CAP_ECRC_CHKE);
+	pci_write_config_dword(dev, pos + PCI_ERR_CAP, reg32);
+
+	return 0;
+}
+
+/**
+ * pcie_set_ecrc_checking - set/unset PCIe ECRC checking for a device based on global policy
+ * @dev: the PCI device
+ */
+void pcie_set_ecrc_checking(struct pci_dev *dev)
+{
+	switch (ecrc_policy) {
+	case ECRC_POLICY_DEFAULT:
+		return;
+	case ECRC_POLICY_OFF:
+		disable_ecrc_checking(dev);
+		break;
+	case ECRC_POLICY_ON:
+		enable_ecrc_checking(dev);
+		break;
+	default:
+		return;
+	}
+}
+
+/**
+ * pcie_ecrc_get_policy - parse kernel command-line ecrc option
+ */
+void pcie_ecrc_get_policy(char *str)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(ecrc_policy_str); i++)
+		if (!strncmp(str, ecrc_policy_str[i],
+			     strlen(ecrc_policy_str[i])))
+			break;
+	if (i >= ARRAY_SIZE(ecrc_policy_str))
+		return;
+
+	ecrc_policy = i;
+}

drivers/pci/pcie/aspm.c

@@ -0,0 +1,991 @@
+/*
+ * File:	drivers/pci/pcie/aspm.c
+ * Enabling PCIe link L0s/L1 state and Clock Power Management
+ *
+ * Copyright (C) 2007 Intel
+ * Copyright (C) Zhang Yanmin (yanmin.zhang@intel.com)
+ * Copyright (C) Shaohua Li (shaohua.li@intel.com)
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/pci.h>
+#include <linux/pci_regs.h>
+#include <linux/errno.h>
+#include <linux/pm.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/jiffies.h>
+#include <linux/delay.h>
+#include <linux/pci-aspm.h>
+#include "../pci.h"
+
+#ifdef MODULE_PARAM_PREFIX
+#undef MODULE_PARAM_PREFIX
+#endif
+#define MODULE_PARAM_PREFIX "pcie_aspm."
+
+/* Note: those are not register definitions */
+#define ASPM_STATE_L0S_UP	(1)	/* Upstream direction L0s state */
+#define ASPM_STATE_L0S_DW	(2)	/* Downstream direction L0s state */
+#define ASPM_STATE_L1		(4)	/* L1 state */
+#define ASPM_STATE_L0S		(ASPM_STATE_L0S_UP | ASPM_STATE_L0S_DW)
+#define ASPM_STATE_ALL		(ASPM_STATE_L0S | ASPM_STATE_L1)
+
+struct aspm_latency {
+	u32 l0s;			/* L0s latency (nsec) */
+	u32 l1;				/* L1 latency (nsec) */
+};
+
+struct pcie_link_state {
+	struct pci_dev *pdev;		/* Upstream component of the Link */
+	struct pcie_link_state *root;	/* pointer to the root port link */
+	struct pcie_link_state *parent;	/* pointer to the parent Link state */
+	struct list_head sibling;	/* node in link_list */
+	struct list_head children;	/* list of child link states */
+	struct list_head link;		/* node in parent's children list */
+
+	/* ASPM state */
+	u32 aspm_support:3;		/* Supported ASPM state */
+	u32 aspm_enabled:3;		/* Enabled ASPM state */
+	u32 aspm_capable:3;		/* Capable ASPM state with latency */
+	u32 aspm_default:3;		/* Default ASPM state by BIOS */
+	u32 aspm_disable:3;		/* Disabled ASPM state */
+
+	/* Clock PM state */
+	u32 clkpm_capable:1;		/* Clock PM capable? */
+	u32 clkpm_enabled:1;		/* Current Clock PM state */
+	u32 clkpm_default:1;		/* Default Clock PM state by BIOS */
+
+	/* Exit latencies */
+	struct aspm_latency latency_up;	/* Upstream direction exit latency */
+	struct aspm_latency latency_dw;	/* Downstream direction exit latency */
+	/*
+	 * Endpoint acceptable latencies. A pcie downstream port only
+	 * has one slot under it, so at most there are 8 functions.
+	 */
+	struct aspm_latency acceptable[8];
+};
+
+static int aspm_disabled, aspm_force;
+static bool aspm_support_enabled = true;
+static DEFINE_MUTEX(aspm_lock);
+static LIST_HEAD(link_list);
+
+#define POLICY_DEFAULT 0	/* BIOS default setting */
+#define POLICY_PERFORMANCE 1	/* high performance */
+#define POLICY_POWERSAVE 2	/* high power saving */
+
+#ifdef CONFIG_PCIEASPM_PERFORMANCE
+static int aspm_policy = POLICY_PERFORMANCE;
+#elif defined CONFIG_PCIEASPM_POWERSAVE
+static int aspm_policy = POLICY_POWERSAVE;
+#else
+static int aspm_policy;
+#endif
+
+static const char *policy_str[] = {
+	[POLICY_DEFAULT] = "default",
+	[POLICY_PERFORMANCE] = "performance",
+	[POLICY_POWERSAVE] = "powersave"
+};
+
+#define LINK_RETRAIN_TIMEOUT HZ
+
+static int policy_to_aspm_state(struct pcie_link_state *link)
+{
+	switch (aspm_policy) {
+	case POLICY_PERFORMANCE:
+		/* Disable ASPM and Clock PM */
+		return 0;
+	case POLICY_POWERSAVE:
+		/* Enable ASPM L0s/L1 */
+		return ASPM_STATE_ALL;
+	case POLICY_DEFAULT:
+		return link->aspm_default;
+	}
+	return 0;
+}
+
+static int policy_to_clkpm_state(struct pcie_link_state *link)
+{
+	switch (aspm_policy) {
+	case POLICY_PERFORMANCE:
+		/* Disable ASPM and Clock PM */
+		return 0;
+	case POLICY_POWERSAVE:
+		/* Disable Clock PM */
+		return 1;
+	case POLICY_DEFAULT:
+		return link->clkpm_default;
+	}
+	return 0;
+}
+
+static void pcie_set_clkpm_nocheck(struct pcie_link_state *link, int enable)
+{
+	struct pci_dev *child;
+	struct pci_bus *linkbus = link->pdev->subordinate;
+
+	list_for_each_entry(child, &linkbus->devices, bus_list) {
+		if (enable)
+			pcie_capability_set_word(child, PCI_EXP_LNKCTL,
+						 PCI_EXP_LNKCTL_CLKREQ_EN);
+		else
+			pcie_capability_clear_word(child, PCI_EXP_LNKCTL,
+						   PCI_EXP_LNKCTL_CLKREQ_EN);
+	}
+	link->clkpm_enabled = !!enable;
+}
+
+static void pcie_set_clkpm(struct pcie_link_state *link, int enable)
+{
+	/* Don't enable Clock PM if the link is not Clock PM capable */
+	if (!link->clkpm_capable && enable)
+		enable = 0;
+	/* Need nothing if the specified equals to current state */
+	if (link->clkpm_enabled == enable)
+		return;
+	pcie_set_clkpm_nocheck(link, enable);
+}
+
+static void pcie_clkpm_cap_init(struct pcie_link_state *link, int blacklist)
+{
+	int capable = 1, enabled = 1;
+	u32 reg32;
+	u16 reg16;
+	struct pci_dev *child;
+	struct pci_bus *linkbus = link->pdev->subordinate;
+
+	/* All functions should have the same cap and state, take the worst */
+	list_for_each_entry(child, &linkbus->devices, bus_list) {
+		pcie_capability_read_dword(child, PCI_EXP_LNKCAP, &reg32);
+		if (!(reg32 & PCI_EXP_LNKCAP_CLKPM)) {
+			capable = 0;
+			enabled = 0;
+			break;
+		}
+		pcie_capability_read_word(child, PCI_EXP_LNKCTL, &reg16);
+		if (!(reg16 & PCI_EXP_LNKCTL_CLKREQ_EN))
+			enabled = 0;
+	}
+	link->clkpm_enabled = enabled;
+	link->clkpm_default = enabled;
+	link->clkpm_capable = (blacklist) ? 0 : capable;
+}
+
+/*
+ * pcie_aspm_configure_common_clock: check if the 2 ends of a link
+ *   could use common clock. If they are, configure them to use the
+ *   common clock. That will reduce the ASPM state exit latency.
+ */
+static void pcie_aspm_configure_common_clock(struct pcie_link_state *link)
+{
+	int same_clock = 1;
+	u16 reg16, parent_reg, child_reg[8];
+	unsigned long start_jiffies;
+	struct pci_dev *child, *parent = link->pdev;
+	struct pci_bus *linkbus = parent->subordinate;
+	/*
+	 * All functions of a slot should have the same Slot Clock
+	 * Configuration, so just check one function
+	 */
+	child = list_entry(linkbus->devices.next, struct pci_dev, bus_list);
+	BUG_ON(!pci_is_pcie(child));
+
+	/* Check downstream component if bit Slot Clock Configuration is 1 */
+	pcie_capability_read_word(child, PCI_EXP_LNKSTA, &reg16);
+	if (!(reg16 & PCI_EXP_LNKSTA_SLC))
+		same_clock = 0;
+
+	/* Check upstream component if bit Slot Clock Configuration is 1 */
+	pcie_capability_read_word(parent, PCI_EXP_LNKSTA, &reg16);
+	if (!(reg16 & PCI_EXP_LNKSTA_SLC))
+		same_clock = 0;
+
+	/* Configure downstream component, all functions */
+	list_for_each_entry(child, &linkbus->devices, bus_list) {
+		pcie_capability_read_word(child, PCI_EXP_LNKCTL, &reg16);
+		child_reg[PCI_FUNC(child->devfn)] = reg16;
+		if (same_clock)
+			reg16 |= PCI_EXP_LNKCTL_CCC;
+		else
+			reg16 &= ~PCI_EXP_LNKCTL_CCC;
+		pcie_capability_write_word(child, PCI_EXP_LNKCTL, reg16);
+	}
+
+	/* Configure upstream component */
+	pcie_capability_read_word(parent, PCI_EXP_LNKCTL, &reg16);
+	parent_reg = reg16;
+	if (same_clock)
+		reg16 |= PCI_EXP_LNKCTL_CCC;
+	else
+		reg16 &= ~PCI_EXP_LNKCTL_CCC;
+	pcie_capability_write_word(parent, PCI_EXP_LNKCTL, reg16);
+
+	/* Retrain link */
+	reg16 |= PCI_EXP_LNKCTL_RL;
+	pcie_capability_write_word(parent, PCI_EXP_LNKCTL, reg16);
+
+	/* Wait for link training end. Break out after waiting for timeout */
+	start_jiffies = jiffies;
+	for (;;) {
+		pcie_capability_read_word(parent, PCI_EXP_LNKSTA, &reg16);
+		if (!(reg16 & PCI_EXP_LNKSTA_LT))
+			break;
+		if (time_after(jiffies, start_jiffies + LINK_RETRAIN_TIMEOUT))
+			break;
+		msleep(1);
+	}
+	if (!(reg16 & PCI_EXP_LNKSTA_LT))
+		return;
+
+	/* Training failed. Restore common clock configurations */
+	dev_err(&parent->dev, "ASPM: Could not configure common clock\n");
+	list_for_each_entry(child, &linkbus->devices, bus_list)
+		pcie_capability_write_word(child, PCI_EXP_LNKCTL,
+					   child_reg[PCI_FUNC(child->devfn)]);
+	pcie_capability_write_word(parent, PCI_EXP_LNKCTL, parent_reg);
+}
+
+/* Convert L0s latency encoding to ns */
+static u32 calc_l0s_latency(u32 encoding)
+{
+	if (encoding == 0x7)
+		return (5 * 1000);	/* > 4us */
+	return (64 << encoding);
+}
+
+/* Convert L0s acceptable latency encoding to ns */
+static u32 calc_l0s_acceptable(u32 encoding)
+{
+	if (encoding == 0x7)
+		return -1U;
+	return (64 << encoding);
+}
+
+/* Convert L1 latency encoding to ns */
+static u32 calc_l1_latency(u32 encoding)
+{
+	if (encoding == 0x7)
+		return (65 * 1000);	/* > 64us */
+	return (1000 << encoding);
+}
+
+/* Convert L1 acceptable latency encoding to ns */
+static u32 calc_l1_acceptable(u32 encoding)
+{
+	if (encoding == 0x7)
+		return -1U;
+	return (1000 << encoding);
+}
+
+struct aspm_register_info {
+	u32 support:2;
+	u32 enabled:2;
+	u32 latency_encoding_l0s;
+	u32 latency_encoding_l1;
+};
+
+static void pcie_get_aspm_reg(struct pci_dev *pdev,
+			      struct aspm_register_info *info)
+{
+	u16 reg16;
+	u32 reg32;
+
+	pcie_capability_read_dword(pdev, PCI_EXP_LNKCAP, &reg32);
+	info->support = (reg32 & PCI_EXP_LNKCAP_ASPMS) >> 10;
+	info->latency_encoding_l0s = (reg32 & PCI_EXP_LNKCAP_L0SEL) >> 12;
+	info->latency_encoding_l1  = (reg32 & PCI_EXP_LNKCAP_L1EL) >> 15;
+	pcie_capability_read_word(pdev, PCI_EXP_LNKCTL, &reg16);
+	info->enabled = reg16 & PCI_EXP_LNKCTL_ASPMC;
+}
+
+static void pcie_aspm_check_latency(struct pci_dev *endpoint)
+{
+	u32 latency, l1_switch_latency = 0;
+	struct aspm_latency *acceptable;
+	struct pcie_link_state *link;
+
+	/* Device not in D0 doesn't need latency check */
+	if ((endpoint->current_state != PCI_D0) &&
+	    (endpoint->current_state != PCI_UNKNOWN))
+		return;
+
+	link = endpoint->bus->self->link_state;
+	acceptable = &link->acceptable[PCI_FUNC(endpoint->devfn)];
+
+	while (link) {
+		/* Check upstream direction L0s latency */
+		if ((link->aspm_capable & ASPM_STATE_L0S_UP) &&
+		    (link->latency_up.l0s > acceptable->l0s))
+			link->aspm_capable &= ~ASPM_STATE_L0S_UP;
+
+		/* Check downstream direction L0s latency */
+		if ((link->aspm_capable & ASPM_STATE_L0S_DW) &&
+		    (link->latency_dw.l0s > acceptable->l0s))
+			link->aspm_capable &= ~ASPM_STATE_L0S_DW;
+		/*
+		 * Check L1 latency.
+		 * Every switch on the path to root complex need 1
+		 * more microsecond for L1. Spec doesn't mention L0s.
+		 */
+		latency = max_t(u32, link->latency_up.l1, link->latency_dw.l1);
+		if ((link->aspm_capable & ASPM_STATE_L1) &&
+		    (latency + l1_switch_latency > acceptable->l1))
+			link->aspm_capable &= ~ASPM_STATE_L1;
+		l1_switch_latency += 1000;
+
+		link = link->parent;
+	}
+}
+
+static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist)
+{
+	struct pci_dev *child, *parent = link->pdev;
+	struct pci_bus *linkbus = parent->subordinate;
+	struct aspm_register_info upreg, dwreg;
+
+	if (blacklist) {
+		/* Set enabled/disable so that we will disable ASPM later */
+		link->aspm_enabled = ASPM_STATE_ALL;
+		link->aspm_disable = ASPM_STATE_ALL;
+		return;
+	}
+
+	/* Configure common clock before checking latencies */
+	pcie_aspm_configure_common_clock(link);
+
+	/* Get upstream/downstream components' register state */
+	pcie_get_aspm_reg(parent, &upreg);
+	child = list_entry(linkbus->devices.next, struct pci_dev, bus_list);
+	pcie_get_aspm_reg(child, &dwreg);
+
+	/*
+	 * Setup L0s state
+	 *
+	 * Note that we must not enable L0s in either direction on a
+	 * given link unless components on both sides of the link each
+	 * support L0s.
+	 */
+	if (dwreg.support & upreg.support & PCIE_LINK_STATE_L0S)
+		link->aspm_support |= ASPM_STATE_L0S;
+	if (dwreg.enabled & PCIE_LINK_STATE_L0S)
+		link->aspm_enabled |= ASPM_STATE_L0S_UP;
+	if (upreg.enabled & PCIE_LINK_STATE_L0S)
+		link->aspm_enabled |= ASPM_STATE_L0S_DW;
+	link->latency_up.l0s = calc_l0s_latency(upreg.latency_encoding_l0s);
+	link->latency_dw.l0s = calc_l0s_latency(dwreg.latency_encoding_l0s);
+
+	/* Setup L1 state */
+	if (upreg.support & dwreg.support & PCIE_LINK_STATE_L1)
+		link->aspm_support |= ASPM_STATE_L1;
+	if (upreg.enabled & dwreg.enabled & PCIE_LINK_STATE_L1)
+		link->aspm_enabled |= ASPM_STATE_L1;
+	link->latency_up.l1 = calc_l1_latency(upreg.latency_encoding_l1);
+	link->latency_dw.l1 = calc_l1_latency(dwreg.latency_encoding_l1);
+
+	/* Save default state */
+	link->aspm_default = link->aspm_enabled;
+
+	/* Setup initial capable state. Will be updated later */
+	link->aspm_capable = link->aspm_support;
+	/*
+	 * If the downstream component has pci bridge function, don't
+	 * do ASPM for now.
+	 */
+	list_for_each_entry(child, &linkbus->devices, bus_list) {
+		if (pci_pcie_type(child) == PCI_EXP_TYPE_PCI_BRIDGE) {
+			link->aspm_disable = ASPM_STATE_ALL;
+			break;
+		}
+	}
+
+	/* Get and check endpoint acceptable latencies */
+	list_for_each_entry(child, &linkbus->devices, bus_list) {
+		u32 reg32, encoding;
+		struct aspm_latency *acceptable =
+			&link->acceptable[PCI_FUNC(child->devfn)];
+
+		if (pci_pcie_type(child) != PCI_EXP_TYPE_ENDPOINT &&
+		    pci_pcie_type(child) != PCI_EXP_TYPE_LEG_END)
+			continue;
+
+		pcie_capability_read_dword(child, PCI_EXP_DEVCAP, &reg32);
+		/* Calculate endpoint L0s acceptable latency */
+		encoding = (reg32 & PCI_EXP_DEVCAP_L0S) >> 6;
+		acceptable->l0s = calc_l0s_acceptable(encoding);
+		/* Calculate endpoint L1 acceptable latency */
+		encoding = (reg32 & PCI_EXP_DEVCAP_L1) >> 9;
+		acceptable->l1 = calc_l1_acceptable(encoding);
+
+		pcie_aspm_check_latency(child);
+	}
+}
+
+static void pcie_config_aspm_dev(struct pci_dev *pdev, u32 val)
+{
+	pcie_capability_clear_and_set_word(pdev, PCI_EXP_LNKCTL,
+					   PCI_EXP_LNKCTL_ASPMC, val);
+}
+
+static void pcie_config_aspm_link(struct pcie_link_state *link, u32 state)
+{
+	u32 upstream = 0, dwstream = 0;
+	struct pci_dev *child, *parent = link->pdev;
+	struct pci_bus *linkbus = parent->subordinate;
+
+	/* Nothing to do if the link is already in the requested state */
+	state &= (link->aspm_capable & ~link->aspm_disable);
+	if (link->aspm_enabled == state)
+		return;
+	/* Convert ASPM state to upstream/downstream ASPM register state */
+	if (state & ASPM_STATE_L0S_UP)
+		dwstream |= PCI_EXP_LNKCTL_ASPM_L0S;
+	if (state & ASPM_STATE_L0S_DW)
+		upstream |= PCI_EXP_LNKCTL_ASPM_L0S;
+	if (state & ASPM_STATE_L1) {
+		upstream |= PCI_EXP_LNKCTL_ASPM_L1;
+		dwstream |= PCI_EXP_LNKCTL_ASPM_L1;
+	}
+	/*
+	 * Spec 2.0 suggests all functions should be configured the
+	 * same setting for ASPM. Enabling ASPM L1 should be done in
+	 * upstream component first and then downstream, and vice
+	 * versa for disabling ASPM L1. Spec doesn't mention L0S.
+	 */
+	if (state & ASPM_STATE_L1)
+		pcie_config_aspm_dev(parent, upstream);
+	list_for_each_entry(child, &linkbus->devices, bus_list)
+		pcie_config_aspm_dev(child, dwstream);
+	if (!(state & ASPM_STATE_L1))
+		pcie_config_aspm_dev(parent, upstream);
+
+	link->aspm_enabled = state;
+}
+
+static void pcie_config_aspm_path(struct pcie_link_state *link)
+{
+	while (link) {
+		pcie_config_aspm_link(link, policy_to_aspm_state(link));
+		link = link->parent;
+	}
+}
+
+static void free_link_state(struct pcie_link_state *link)
+{
+	link->pdev->link_state = NULL;
+	kfree(link);
+}
+
+static int pcie_aspm_sanity_check(struct pci_dev *pdev)
+{
+	struct pci_dev *child;
+	u32 reg32;
+
+	/*
+	 * Some functions in a slot might not all be PCIe functions,
+	 * very strange. Disable ASPM for the whole slot
+	 */
+	list_for_each_entry(child, &pdev->subordinate->devices, bus_list) {
+		if (!pci_is_pcie(child))
+			return -EINVAL;
+
+		/*
+		 * If ASPM is disabled then we're not going to change
+		 * the BIOS state. It's safe to continue even if it's a
+		 * pre-1.1 device
+		 */
+
+		if (aspm_disabled)
+			continue;
+
+		/*
+		 * Disable ASPM for pre-1.1 PCIe device, we follow MS to use
+		 * RBER bit to determine if a function is 1.1 version device
+		 */
+		pcie_capability_read_dword(child, PCI_EXP_DEVCAP, &reg32);
+		if (!(reg32 & PCI_EXP_DEVCAP_RBER) && !aspm_force) {
+			dev_info(&child->dev, "disabling ASPM on pre-1.1 PCIe device.  You can enable it with 'pcie_aspm=force'\n");
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
+static struct pcie_link_state *alloc_pcie_link_state(struct pci_dev *pdev)
+{
+	struct pcie_link_state *link;
+
+	link = kzalloc(sizeof(*link), GFP_KERNEL);
+	if (!link)
+		return NULL;
+	INIT_LIST_HEAD(&link->sibling);
+	INIT_LIST_HEAD(&link->children);
+	INIT_LIST_HEAD(&link->link);
+	link->pdev = pdev;
+	if (pci_pcie_type(pdev) == PCI_EXP_TYPE_DOWNSTREAM) {
+		struct pcie_link_state *parent;
+		parent = pdev->bus->parent->self->link_state;
+		if (!parent) {
+			kfree(link);
+			return NULL;
+		}
+		link->parent = parent;
+		list_add(&link->link, &parent->children);
+	}
+	/* Setup a pointer to the root port link */
+	if (!link->parent)
+		link->root = link;
+	else
+		link->root = link->parent->root;
+
+	list_add(&link->sibling, &link_list);
+	pdev->link_state = link;
+	return link;
+}
+
+/*
+ * pcie_aspm_init_link_state: Initiate PCI express link state.
+ * It is called after the pcie and its children devices are scanned.
+ * @pdev: the root port or switch downstream port
+ */
+void pcie_aspm_init_link_state(struct pci_dev *pdev)
+{
+	struct pcie_link_state *link;
+	int blacklist = !!pcie_aspm_sanity_check(pdev);
+
+	if (!aspm_support_enabled)
+		return;
+
+	if (!pci_is_pcie(pdev) || pdev->link_state)
+		return;
+	if (pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT &&
+	    pci_pcie_type(pdev) != PCI_EXP_TYPE_DOWNSTREAM)
+		return;
+
+	/* VIA has a strange chipset, root port is under a bridge */
+	if (pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT &&
+	    pdev->bus->self)
+		return;
+
+	down_read(&pci_bus_sem);
+	if (list_empty(&pdev->subordinate->devices))
+		goto out;
+
+	mutex_lock(&aspm_lock);
+	link = alloc_pcie_link_state(pdev);
+	if (!link)
+		goto unlock;
+	/*
+	 * Setup initial ASPM state. Note that we need to configure
+	 * upstream links also because capable state of them can be
+	 * update through pcie_aspm_cap_init().
+	 */
+	pcie_aspm_cap_init(link, blacklist);
+
+	/* Setup initial Clock PM state */
+	pcie_clkpm_cap_init(link, blacklist);
+
+	/*
+	 * At this stage drivers haven't had an opportunity to change the
+	 * link policy setting. Enabling ASPM on broken hardware can cripple
+	 * it even before the driver has had a chance to disable ASPM, so
+	 * default to a safe level right now. If we're enabling ASPM beyond
+	 * the BIOS's expectation, we'll do so once pci_enable_device() is
+	 * called.
+	 */
+	if (aspm_policy != POLICY_POWERSAVE) {
+		pcie_config_aspm_path(link);
+		pcie_set_clkpm(link, policy_to_clkpm_state(link));
+	}
+
+unlock:
+	mutex_unlock(&aspm_lock);
+out:
+	up_read(&pci_bus_sem);
+}
+
+/* Recheck latencies and update aspm_capable for links under the root */
+static void pcie_update_aspm_capable(struct pcie_link_state *root)
+{
+	struct pcie_link_state *link;
+	BUG_ON(root->parent);
+	list_for_each_entry(link, &link_list, sibling) {
+		if (link->root != root)
+			continue;
+		link->aspm_capable = link->aspm_support;
+	}
+	list_for_each_entry(link, &link_list, sibling) {
+		struct pci_dev *child;
+		struct pci_bus *linkbus = link->pdev->subordinate;
+		if (link->root != root)
+			continue;
+		list_for_each_entry(child, &linkbus->devices, bus_list) {
+			if ((pci_pcie_type(child) != PCI_EXP_TYPE_ENDPOINT) &&
+			    (pci_pcie_type(child) != PCI_EXP_TYPE_LEG_END))
+				continue;
+			pcie_aspm_check_latency(child);
+		}
+	}
+}
+
+/* @pdev: the endpoint device */
+void pcie_aspm_exit_link_state(struct pci_dev *pdev)
+{
+	struct pci_dev *parent = pdev->bus->self;
+	struct pcie_link_state *link, *root, *parent_link;
+
+	if (!parent || !parent->link_state)
+		return;
+
+	down_read(&pci_bus_sem);
+	mutex_lock(&aspm_lock);
+	/*
+	 * All PCIe functions are in one slot, remove one function will remove
+	 * the whole slot, so just wait until we are the last function left.
+	 */
+	if (!list_is_last(&pdev->bus_list, &parent->subordinate->devices))
+		goto out;
+
+	link = parent->link_state;
+	root = link->root;
+	parent_link = link->parent;
+
+	/* All functions are removed, so just disable ASPM for the link */
+	pcie_config_aspm_link(link, 0);
+	list_del(&link->sibling);
+	list_del(&link->link);
+	/* Clock PM is for endpoint device */
+	free_link_state(link);
+
+	/* Recheck latencies and configure upstream links */
+	if (parent_link) {
+		pcie_update_aspm_capable(root);
+		pcie_config_aspm_path(parent_link);
+	}
+out:
+	mutex_unlock(&aspm_lock);
+	up_read(&pci_bus_sem);
+}
+
+/* @pdev: the root port or switch downstream port */
+void pcie_aspm_pm_state_change(struct pci_dev *pdev)
+{
+	struct pcie_link_state *link = pdev->link_state;
+
+	if (aspm_disabled || !pci_is_pcie(pdev) || !link)
+		return;
+	if ((pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT) &&
+	    (pci_pcie_type(pdev) != PCI_EXP_TYPE_DOWNSTREAM))
+		return;
+	/*
+	 * Devices changed PM state, we should recheck if latency
+	 * meets all functions' requirement
+	 */
+	down_read(&pci_bus_sem);
+	mutex_lock(&aspm_lock);
+	pcie_update_aspm_capable(link->root);
+	pcie_config_aspm_path(link);
+	mutex_unlock(&aspm_lock);
+	up_read(&pci_bus_sem);
+}
+
+void pcie_aspm_powersave_config_link(struct pci_dev *pdev)
+{
+	struct pcie_link_state *link = pdev->link_state;
+
+	if (aspm_disabled || !pci_is_pcie(pdev) || !link)
+		return;
+
+	if (aspm_policy != POLICY_POWERSAVE)
+		return;
+
+	if ((pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT) &&
+	    (pci_pcie_type(pdev) != PCI_EXP_TYPE_DOWNSTREAM))
+		return;
+
+	down_read(&pci_bus_sem);
+	mutex_lock(&aspm_lock);
+	pcie_config_aspm_path(link);
+	pcie_set_clkpm(link, policy_to_clkpm_state(link));
+	mutex_unlock(&aspm_lock);
+	up_read(&pci_bus_sem);
+}
+
+static void __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem,
+				     bool force)
+{
+	struct pci_dev *parent = pdev->bus->self;
+	struct pcie_link_state *link;
+
+	if (!pci_is_pcie(pdev))
+		return;
+
+	if (pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT ||
+	    pci_pcie_type(pdev) == PCI_EXP_TYPE_DOWNSTREAM)
+		parent = pdev;
+	if (!parent || !parent->link_state)
+		return;
+
+	/*
+	 * A driver requested that ASPM be disabled on this device, but
+	 * if we don't have permission to manage ASPM (e.g., on ACPI
+	 * systems we have to observe the FADT ACPI_FADT_NO_ASPM bit and
+	 * the _OSC method), we can't honor that request.  Windows has
+	 * a similar mechanism using "PciASPMOptOut", which is also
+	 * ignored in this situation.
+	 */
+	if (aspm_disabled && !force) {
+		dev_warn(&pdev->dev, "can't disable ASPM; OS doesn't have ASPM control\n");
+		return;
+	}
+
+	if (sem)
+		down_read(&pci_bus_sem);
+	mutex_lock(&aspm_lock);
+	link = parent->link_state;
+	if (state & PCIE_LINK_STATE_L0S)
+		link->aspm_disable |= ASPM_STATE_L0S;
+	if (state & PCIE_LINK_STATE_L1)
+		link->aspm_disable |= ASPM_STATE_L1;
+	pcie_config_aspm_link(link, policy_to_aspm_state(link));
+
+	if (state & PCIE_LINK_STATE_CLKPM) {
+		link->clkpm_capable = 0;
+		pcie_set_clkpm(link, 0);
+	}
+	mutex_unlock(&aspm_lock);
+	if (sem)
+		up_read(&pci_bus_sem);
+}
+
+void pci_disable_link_state_locked(struct pci_dev *pdev, int state)
+{
+	__pci_disable_link_state(pdev, state, false, false);
+}
+EXPORT_SYMBOL(pci_disable_link_state_locked);
+
+/**
+ * pci_disable_link_state - Disable device's link state, so the link will
+ * never enter specific states.  Note that if the BIOS didn't grant ASPM
+ * control to the OS, this does nothing because we can't touch the LNKCTL
+ * register.
+ *
+ * @pdev: PCI device
+ * @state: ASPM link state to disable
+ */
+void pci_disable_link_state(struct pci_dev *pdev, int state)
+{
+	__pci_disable_link_state(pdev, state, true, false);
+}
+EXPORT_SYMBOL(pci_disable_link_state);
+
+void pcie_clear_aspm(struct pci_bus *bus)
+{
+	struct pci_dev *child;
+
+	if (aspm_force)
+		return;
+
+	/*
+	 * Clear any ASPM setup that the firmware has carried out on this bus
+	 */
+	list_for_each_entry(child, &bus->devices, bus_list) {
+		__pci_disable_link_state(child, PCIE_LINK_STATE_L0S |
+					 PCIE_LINK_STATE_L1 |
+					 PCIE_LINK_STATE_CLKPM,
+					 false, true);
+	}
+}
+
+static int pcie_aspm_set_policy(const char *val, struct kernel_param *kp)
+{
+	int i;
+	struct pcie_link_state *link;
+
+	if (aspm_disabled)
+		return -EPERM;
+	for (i = 0; i < ARRAY_SIZE(policy_str); i++)
+		if (!strncmp(val, policy_str[i], strlen(policy_str[i])))
+			break;
+	if (i >= ARRAY_SIZE(policy_str))
+		return -EINVAL;
+	if (i == aspm_policy)
+		return 0;
+
+	down_read(&pci_bus_sem);
+	mutex_lock(&aspm_lock);
+	aspm_policy = i;
+	list_for_each_entry(link, &link_list, sibling) {
+		pcie_config_aspm_link(link, policy_to_aspm_state(link));
+		pcie_set_clkpm(link, policy_to_clkpm_state(link));
+	}
+	mutex_unlock(&aspm_lock);
+	up_read(&pci_bus_sem);
+	return 0;
+}
+
+static int pcie_aspm_get_policy(char *buffer, struct kernel_param *kp)
+{
+	int i, cnt = 0;
+	for (i = 0; i < ARRAY_SIZE(policy_str); i++)
+		if (i == aspm_policy)
+			cnt += sprintf(buffer + cnt, "[%s] ", policy_str[i]);
+		else
+			cnt += sprintf(buffer + cnt, "%s ", policy_str[i]);
+	return cnt;
+}
+
+module_param_call(policy, pcie_aspm_set_policy, pcie_aspm_get_policy,
+	NULL, 0644);
+
+#ifdef CONFIG_PCIEASPM_DEBUG
+static ssize_t link_state_show(struct device *dev,
+		struct device_attribute *attr,
+		char *buf)
+{
+	struct pci_dev *pci_device = to_pci_dev(dev);
+	struct pcie_link_state *link_state = pci_device->link_state;
+
+	return sprintf(buf, "%d\n", link_state->aspm_enabled);
+}
+
+static ssize_t link_state_store(struct device *dev,
+		struct device_attribute *attr,
+		const char *buf,
+		size_t n)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct pcie_link_state *link, *root = pdev->link_state->root;
+	u32 val = buf[0] - '0', state = 0;
+
+	if (aspm_disabled)
+		return -EPERM;
+	if (n < 1 || val > 3)
+		return -EINVAL;
+
+	/* Convert requested state to ASPM state */
+	if (val & PCIE_LINK_STATE_L0S)
+		state |= ASPM_STATE_L0S;
+	if (val & PCIE_LINK_STATE_L1)
+		state |= ASPM_STATE_L1;
+
+	down_read(&pci_bus_sem);
+	mutex_lock(&aspm_lock);
+	list_for_each_entry(link, &link_list, sibling) {
+		if (link->root != root)
+			continue;
+		pcie_config_aspm_link(link, state);
+	}
+	mutex_unlock(&aspm_lock);
+	up_read(&pci_bus_sem);
+	return n;
+}
+
+static ssize_t clk_ctl_show(struct device *dev,
+		struct device_attribute *attr,
+		char *buf)
+{
+	struct pci_dev *pci_device = to_pci_dev(dev);
+	struct pcie_link_state *link_state = pci_device->link_state;
+
+	return sprintf(buf, "%d\n", link_state->clkpm_enabled);
+}
+
+static ssize_t clk_ctl_store(struct device *dev,
+		struct device_attribute *attr,
+		const char *buf,
+		size_t n)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	int state;
+
+	if (n < 1)
+		return -EINVAL;
+	state = buf[0]-'0';
+
+	down_read(&pci_bus_sem);
+	mutex_lock(&aspm_lock);
+	pcie_set_clkpm_nocheck(pdev->link_state, !!state);
+	mutex_unlock(&aspm_lock);
+	up_read(&pci_bus_sem);
+
+	return n;
+}
+
+static DEVICE_ATTR(link_state, 0644, link_state_show, link_state_store);
+static DEVICE_ATTR(clk_ctl, 0644, clk_ctl_show, clk_ctl_store);
+
+static char power_group[] = "power";
+void pcie_aspm_create_sysfs_dev_files(struct pci_dev *pdev)
+{
+	struct pcie_link_state *link_state = pdev->link_state;
+
+	if (!pci_is_pcie(pdev) ||
+	    (pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT &&
+	     pci_pcie_type(pdev) != PCI_EXP_TYPE_DOWNSTREAM) || !link_state)
+		return;
+
+	if (link_state->aspm_support)
+		sysfs_add_file_to_group(&pdev->dev.kobj,
+			&dev_attr_link_state.attr, power_group);
+	if (link_state->clkpm_capable)
+		sysfs_add_file_to_group(&pdev->dev.kobj,
+			&dev_attr_clk_ctl.attr, power_group);
+}
+
+void pcie_aspm_remove_sysfs_dev_files(struct pci_dev *pdev)
+{
+	struct pcie_link_state *link_state = pdev->link_state;
+
+	if (!pci_is_pcie(pdev) ||
+	    (pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT &&
+	     pci_pcie_type(pdev) != PCI_EXP_TYPE_DOWNSTREAM) || !link_state)
+		return;
+
+	if (link_state->aspm_support)
+		sysfs_remove_file_from_group(&pdev->dev.kobj,
+			&dev_attr_link_state.attr, power_group);
+	if (link_state->clkpm_capable)
+		sysfs_remove_file_from_group(&pdev->dev.kobj,
+			&dev_attr_clk_ctl.attr, power_group);
+}
+#endif
+
+static int __init pcie_aspm_disable(char *str)
+{
+	if (!strcmp(str, "off")) {
+		aspm_policy = POLICY_DEFAULT;
+		aspm_disabled = 1;
+		aspm_support_enabled = false;
+		printk(KERN_INFO "PCIe ASPM is disabled\n");
+	} else if (!strcmp(str, "force")) {
+		aspm_force = 1;
+		printk(KERN_INFO "PCIe ASPM is forcibly enabled\n");
+	}
+	return 1;
+}
+
+__setup("pcie_aspm=", pcie_aspm_disable);
+
+void pcie_no_aspm(void)
+{
+	/*
+	 * Disabling ASPM is intended to prevent the kernel from modifying
+	 * existing hardware state, not to clear existing state. To that end:
+	 * (a) set policy to POLICY_DEFAULT in order to avoid changing state
+	 * (b) prevent userspace from changing policy
+	 */
+	if (!aspm_force) {
+		aspm_policy = POLICY_DEFAULT;
+		aspm_disabled = 1;
+	}
+}
+
+bool pcie_aspm_support_enabled(void)
+{
+	return aspm_support_enabled;
+}
+EXPORT_SYMBOL(pcie_aspm_support_enabled);

drivers/pci/pcie/pme.c

@@ -0,0 +1,481 @@
+/*
+ * PCIe Native PME support
+ *
+ * Copyright (C) 2007 - 2009 Intel Corp
+ * Copyright (C) 2007 - 2009 Shaohua Li <shaohua.li@intel.com>
+ * Copyright (C) 2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License V2.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/device.h>
+#include <linux/pcieport_if.h>
+#include <linux/pm_runtime.h>
+
+#include "../pci.h"
+#include "portdrv.h"
+
+/*
+ * If this switch is set, MSI will not be used for PCIe PME signaling.  This
+ * causes the PCIe port driver to use INTx interrupts only, but it turns out
+ * that using MSI for PCIe PME signaling doesn't play well with PCIe PME-based
+ * wake-up from system sleep states.
+ */
+bool pcie_pme_msi_disabled;
+
+static int __init pcie_pme_setup(char *str)
+{
+	if (!strncmp(str, "nomsi", 5))
+		pcie_pme_msi_disabled = true;
+
+	return 1;
+}
+__setup("pcie_pme=", pcie_pme_setup);
+
+enum pme_suspend_level {
+	PME_SUSPEND_NONE = 0,
+	PME_SUSPEND_WAKEUP,
+	PME_SUSPEND_NOIRQ,
+};
+
+struct pcie_pme_service_data {
+	spinlock_t lock;
+	struct pcie_device *srv;
+	struct work_struct work;
+	enum pme_suspend_level suspend_level;
+};
+
+/**
+ * pcie_pme_interrupt_enable - Enable/disable PCIe PME interrupt generation.
+ * @dev: PCIe root port or event collector.
+ * @enable: Enable or disable the interrupt.
+ */
+void pcie_pme_interrupt_enable(struct pci_dev *dev, bool enable)
+{
+	if (enable)
+		pcie_capability_set_word(dev, PCI_EXP_RTCTL,
+					 PCI_EXP_RTCTL_PMEIE);
+	else
+		pcie_capability_clear_word(dev, PCI_EXP_RTCTL,
+					   PCI_EXP_RTCTL_PMEIE);
+}
+
+/**
+ * pcie_pme_walk_bus - Scan a PCI bus for devices asserting PME#.
+ * @bus: PCI bus to scan.
+ *
+ * Scan given PCI bus and all buses under it for devices asserting PME#.
+ */
+static bool pcie_pme_walk_bus(struct pci_bus *bus)
+{
+	struct pci_dev *dev;
+	bool ret = false;
+
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		/* Skip PCIe devices in case we started from a root port. */
+		if (!pci_is_pcie(dev) && pci_check_pme_status(dev)) {
+			if (dev->pme_poll)
+				dev->pme_poll = false;
+
+			pci_wakeup_event(dev);
+			pm_request_resume(&dev->dev);
+			ret = true;
+		}
+
+		if (dev->subordinate && pcie_pme_walk_bus(dev->subordinate))
+			ret = true;
+	}
+
+	return ret;
+}
+
+/**
+ * pcie_pme_from_pci_bridge - Check if PCIe-PCI bridge generated a PME.
+ * @bus: Secondary bus of the bridge.
+ * @devfn: Device/function number to check.
+ *
+ * PME from PCI devices under a PCIe-PCI bridge may be converted to an in-band
+ * PCIe PME message.  In such that case the bridge should use the Requester ID
+ * of device/function number 0 on its secondary bus.
+ */
+static bool pcie_pme_from_pci_bridge(struct pci_bus *bus, u8 devfn)
+{
+	struct pci_dev *dev;
+	bool found = false;
+
+	if (devfn)
+		return false;
+
+	dev = pci_dev_get(bus->self);
+	if (!dev)
+		return false;
+
+	if (pci_is_pcie(dev) && pci_pcie_type(dev) == PCI_EXP_TYPE_PCI_BRIDGE) {
+		down_read(&pci_bus_sem);
+		if (pcie_pme_walk_bus(bus))
+			found = true;
+		up_read(&pci_bus_sem);
+	}
+
+	pci_dev_put(dev);
+	return found;
+}
+
+/**
+ * pcie_pme_handle_request - Find device that generated PME and handle it.
+ * @port: Root port or event collector that generated the PME interrupt.
+ * @req_id: PCIe Requester ID of the device that generated the PME.
+ */
+static void pcie_pme_handle_request(struct pci_dev *port, u16 req_id)
+{
+	u8 busnr = req_id >> 8, devfn = req_id & 0xff;
+	struct pci_bus *bus;
+	struct pci_dev *dev;
+	bool found = false;
+
+	/* First, check if the PME is from the root port itself. */
+	if (port->devfn == devfn && port->bus->number == busnr) {
+		if (port->pme_poll)
+			port->pme_poll = false;
+
+		if (pci_check_pme_status(port)) {
+			pm_request_resume(&port->dev);
+			found = true;
+		} else {
+			/*
+			 * Apparently, the root port generated the PME on behalf
+			 * of a non-PCIe device downstream.  If this is done by
+			 * a root port, the Requester ID field in its status
+			 * register may contain either the root port's, or the
+			 * source device's information (PCI Express Base
+			 * Specification, Rev. 2.0, Section 6.1.9).
+			 */
+			down_read(&pci_bus_sem);
+			found = pcie_pme_walk_bus(port->subordinate);
+			up_read(&pci_bus_sem);
+		}
+		goto out;
+	}
+
+	/* Second, find the bus the source device is on. */
+	bus = pci_find_bus(pci_domain_nr(port->bus), busnr);
+	if (!bus)
+		goto out;
+
+	/* Next, check if the PME is from a PCIe-PCI bridge. */
+	found = pcie_pme_from_pci_bridge(bus, devfn);
+	if (found)
+		goto out;
+
+	/* Finally, try to find the PME source on the bus. */
+	down_read(&pci_bus_sem);
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		pci_dev_get(dev);
+		if (dev->devfn == devfn) {
+			found = true;
+			break;
+		}
+		pci_dev_put(dev);
+	}
+	up_read(&pci_bus_sem);
+
+	if (found) {
+		/* The device is there, but we have to check its PME status. */
+		found = pci_check_pme_status(dev);
+		if (found) {
+			if (dev->pme_poll)
+				dev->pme_poll = false;
+
+			pci_wakeup_event(dev);
+			pm_request_resume(&dev->dev);
+		}
+		pci_dev_put(dev);
+	} else if (devfn) {
+		/*
+		 * The device is not there, but we can still try to recover by
+		 * assuming that the PME was reported by a PCIe-PCI bridge that
+		 * used devfn different from zero.
+		 */
+		dev_dbg(&port->dev, "PME interrupt generated for non-existent device %02x:%02x.%d\n",
+			busnr, PCI_SLOT(devfn), PCI_FUNC(devfn));
+		found = pcie_pme_from_pci_bridge(bus, 0);
+	}
+
+ out:
+	if (!found)
+		dev_dbg(&port->dev, "Spurious native PME interrupt!\n");
+}
+
+/**
+ * pcie_pme_work_fn - Work handler for PCIe PME interrupt.
+ * @work: Work structure giving access to service data.
+ */
+static void pcie_pme_work_fn(struct work_struct *work)
+{
+	struct pcie_pme_service_data *data =
+			container_of(work, struct pcie_pme_service_data, work);
+	struct pci_dev *port = data->srv->port;
+	u32 rtsta;
+
+	spin_lock_irq(&data->lock);
+
+	for (;;) {
+		if (data->suspend_level != PME_SUSPEND_NONE)
+			break;
+
+		pcie_capability_read_dword(port, PCI_EXP_RTSTA, &rtsta);
+		if (rtsta & PCI_EXP_RTSTA_PME) {
+			/*
+			 * Clear PME status of the port.  If there are other
+			 * pending PMEs, the status will be set again.
+			 */
+			pcie_clear_root_pme_status(port);
+
+			spin_unlock_irq(&data->lock);
+			pcie_pme_handle_request(port, rtsta & 0xffff);
+			spin_lock_irq(&data->lock);
+
+			continue;
+		}
+
+		/* No need to loop if there are no more PMEs pending. */
+		if (!(rtsta & PCI_EXP_RTSTA_PENDING))
+			break;
+
+		spin_unlock_irq(&data->lock);
+		cpu_relax();
+		spin_lock_irq(&data->lock);
+	}
+
+	if (data->suspend_level == PME_SUSPEND_NONE)
+		pcie_pme_interrupt_enable(port, true);
+
+	spin_unlock_irq(&data->lock);
+}
+
+/**
+ * pcie_pme_irq - Interrupt handler for PCIe root port PME interrupt.
+ * @irq: Interrupt vector.
+ * @context: Interrupt context pointer.
+ */
+static irqreturn_t pcie_pme_irq(int irq, void *context)
+{
+	struct pci_dev *port;
+	struct pcie_pme_service_data *data;
+	u32 rtsta;
+	unsigned long flags;
+
+	port = ((struct pcie_device *)context)->port;
+	data = get_service_data((struct pcie_device *)context);
+
+	spin_lock_irqsave(&data->lock, flags);
+	pcie_capability_read_dword(port, PCI_EXP_RTSTA, &rtsta);
+
+	if (!(rtsta & PCI_EXP_RTSTA_PME)) {
+		spin_unlock_irqrestore(&data->lock, flags);
+		return IRQ_NONE;
+	}
+
+	pcie_pme_interrupt_enable(port, false);
+	spin_unlock_irqrestore(&data->lock, flags);
+
+	/* We don't use pm_wq, because it's freezable. */
+	schedule_work(&data->work);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * pcie_pme_set_native - Set the PME interrupt flag for given device.
+ * @dev: PCI device to handle.
+ * @ign: Ignored.
+ */
+static int pcie_pme_set_native(struct pci_dev *dev, void *ign)
+{
+	dev_info(&dev->dev, "Signaling PME through PCIe PME interrupt\n");
+
+	device_set_run_wake(&dev->dev, true);
+	dev->pme_interrupt = true;
+	return 0;
+}
+
+/**
+ * pcie_pme_mark_devices - Set the PME interrupt flag for devices below a port.
+ * @port: PCIe root port or event collector to handle.
+ *
+ * For each device below given root port, including the port itself (or for each
+ * root complex integrated endpoint if @port is a root complex event collector)
+ * set the flag indicating that it can signal run-time wake-up events via PCIe
+ * PME interrupts.
+ */
+static void pcie_pme_mark_devices(struct pci_dev *port)
+{
+	pcie_pme_set_native(port, NULL);
+	if (port->subordinate) {
+		pci_walk_bus(port->subordinate, pcie_pme_set_native, NULL);
+	} else {
+		struct pci_bus *bus = port->bus;
+		struct pci_dev *dev;
+
+		/* Check if this is a root port event collector. */
+		if (pci_pcie_type(port) != PCI_EXP_TYPE_RC_EC || !bus)
+			return;
+
+		down_read(&pci_bus_sem);
+		list_for_each_entry(dev, &bus->devices, bus_list)
+			if (pci_is_pcie(dev)
+			    && pci_pcie_type(dev) == PCI_EXP_TYPE_RC_END)
+				pcie_pme_set_native(dev, NULL);
+		up_read(&pci_bus_sem);
+	}
+}
+
+/**
+ * pcie_pme_probe - Initialize PCIe PME service for given root port.
+ * @srv: PCIe service to initialize.
+ */
+static int pcie_pme_probe(struct pcie_device *srv)
+{
+	struct pci_dev *port;
+	struct pcie_pme_service_data *data;
+	int ret;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	spin_lock_init(&data->lock);
+	INIT_WORK(&data->work, pcie_pme_work_fn);
+	data->srv = srv;
+	set_service_data(srv, data);
+
+	port = srv->port;
+	pcie_pme_interrupt_enable(port, false);
+	pcie_clear_root_pme_status(port);
+
+	ret = request_irq(srv->irq, pcie_pme_irq, IRQF_SHARED, "PCIe PME", srv);
+	if (ret) {
+		kfree(data);
+	} else {
+		pcie_pme_mark_devices(port);
+		pcie_pme_interrupt_enable(port, true);
+	}
+
+	return ret;
+}
+
+static bool pcie_pme_check_wakeup(struct pci_bus *bus)
+{
+	struct pci_dev *dev;
+
+	if (!bus)
+		return false;
+
+	list_for_each_entry(dev, &bus->devices, bus_list)
+		if (device_may_wakeup(&dev->dev)
+		    || pcie_pme_check_wakeup(dev->subordinate))
+			return true;
+
+	return false;
+}
+
+/**
+ * pcie_pme_suspend - Suspend PCIe PME service device.
+ * @srv: PCIe service device to suspend.
+ */
+static int pcie_pme_suspend(struct pcie_device *srv)
+{
+	struct pcie_pme_service_data *data = get_service_data(srv);
+	struct pci_dev *port = srv->port;
+	bool wakeup;
+	int ret;
+
+	if (device_may_wakeup(&port->dev)) {
+		wakeup = true;
+	} else {
+		down_read(&pci_bus_sem);
+		wakeup = pcie_pme_check_wakeup(port->subordinate);
+		up_read(&pci_bus_sem);
+	}
+	spin_lock_irq(&data->lock);
+	if (wakeup) {
+		ret = enable_irq_wake(srv->irq);
+		data->suspend_level = PME_SUSPEND_WAKEUP;
+	}
+	if (!wakeup || ret) {
+		struct pci_dev *port = srv->port;
+
+		pcie_pme_interrupt_enable(port, false);
+		pcie_clear_root_pme_status(port);
+		data->suspend_level = PME_SUSPEND_NOIRQ;
+	}
+	spin_unlock_irq(&data->lock);
+
+	synchronize_irq(srv->irq);
+
+	return 0;
+}
+
+/**
+ * pcie_pme_resume - Resume PCIe PME service device.
+ * @srv - PCIe service device to resume.
+ */
+static int pcie_pme_resume(struct pcie_device *srv)
+{
+	struct pcie_pme_service_data *data = get_service_data(srv);
+
+	spin_lock_irq(&data->lock);
+	if (data->suspend_level == PME_SUSPEND_NOIRQ) {
+		struct pci_dev *port = srv->port;
+
+		pcie_clear_root_pme_status(port);
+		pcie_pme_interrupt_enable(port, true);
+	} else {
+		disable_irq_wake(srv->irq);
+	}
+	data->suspend_level = PME_SUSPEND_NONE;
+	spin_unlock_irq(&data->lock);
+
+	return 0;
+}
+
+/**
+ * pcie_pme_remove - Prepare PCIe PME service device for removal.
+ * @srv - PCIe service device to remove.
+ */
+static void pcie_pme_remove(struct pcie_device *srv)
+{
+	pcie_pme_suspend(srv);
+	free_irq(srv->irq, srv);
+	kfree(get_service_data(srv));
+}
+
+static struct pcie_port_service_driver pcie_pme_driver = {
+	.name		= "pcie_pme",
+	.port_type	= PCI_EXP_TYPE_ROOT_PORT,
+	.service	= PCIE_PORT_SERVICE_PME,
+
+	.probe		= pcie_pme_probe,
+	.suspend	= pcie_pme_suspend,
+	.resume		= pcie_pme_resume,
+	.remove		= pcie_pme_remove,
+};
+
+/**
+ * pcie_pme_service_init - Register the PCIe PME service driver.
+ */
+static int __init pcie_pme_service_init(void)
+{
+	return pcie_port_service_register(&pcie_pme_driver);
+}
+
+module_init(pcie_pme_service_init);

drivers/pci/pcie/portdrv.h

@@ -0,0 +1,83 @@
+/*
+ * File:	portdrv.h
+ * Purpose:	PCI Express Port Bus Driver's Internal Data Structures
+ *
+ * Copyright (C) 2004 Intel
+ * Copyright (C) Tom Long Nguyen (tom.l.nguyen@intel.com)
+ */
+
+#ifndef _PORTDRV_H_
+#define _PORTDRV_H_
+
+#include <linux/compiler.h>
+
+#define PCIE_PORT_DEVICE_MAXSERVICES   4
+/*
+ * According to the PCI Express Base Specification 2.0, the indices of
+ * the MSI-X table entries used by port services must not exceed 31
+ */
+#define PCIE_PORT_MAX_MSIX_ENTRIES	32
+
+#define get_descriptor_id(type, service) (((type - 4) << 4) | service)
+
+extern struct bus_type pcie_port_bus_type;
+int pcie_port_device_register(struct pci_dev *dev);
+#ifdef CONFIG_PM
+int pcie_port_device_suspend(struct device *dev);
+int pcie_port_device_resume(struct device *dev);
+#endif
+void pcie_port_device_remove(struct pci_dev *dev);
+int __must_check pcie_port_bus_register(void);
+void pcie_port_bus_unregister(void);
+
+struct pci_dev;
+
+void pcie_clear_root_pme_status(struct pci_dev *dev);
+
+#ifdef CONFIG_HOTPLUG_PCI_PCIE
+extern bool pciehp_msi_disabled;
+
+static inline bool pciehp_no_msi(void)
+{
+	return pciehp_msi_disabled;
+}
+
+#else  /* !CONFIG_HOTPLUG_PCI_PCIE */
+static inline bool pciehp_no_msi(void) { return false; }
+#endif /* !CONFIG_HOTPLUG_PCI_PCIE */
+
+#ifdef CONFIG_PCIE_PME
+extern bool pcie_pme_msi_disabled;
+
+static inline void pcie_pme_disable_msi(void)
+{
+	pcie_pme_msi_disabled = true;
+}
+
+static inline bool pcie_pme_no_msi(void)
+{
+	return pcie_pme_msi_disabled;
+}
+
+void pcie_pme_interrupt_enable(struct pci_dev *dev, bool enable);
+#else /* !CONFIG_PCIE_PME */
+static inline void pcie_pme_disable_msi(void) {}
+static inline bool pcie_pme_no_msi(void) { return false; }
+static inline void pcie_pme_interrupt_enable(struct pci_dev *dev, bool en) {}
+#endif /* !CONFIG_PCIE_PME */
+
+#ifdef CONFIG_ACPI
+int pcie_port_acpi_setup(struct pci_dev *port, int *mask);
+
+static inline int pcie_port_platform_notify(struct pci_dev *port, int *mask)
+{
+	return pcie_port_acpi_setup(port, mask);
+}
+#else /* !CONFIG_ACPI */
+static inline int pcie_port_platform_notify(struct pci_dev *port, int *mask)
+{
+	return 0;
+}
+#endif /* !CONFIG_ACPI */
+
+#endif /* _PORTDRV_H_ */

drivers/pci/pcie/portdrv_acpi.c

@@ -0,0 +1,63 @@
+/*
+ * PCIe Port Native Services Support, ACPI-Related Part
+ *
+ * Copyright (C) 2010 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License V2.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/pci.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/acpi.h>
+#include <linux/pci-acpi.h>
+#include <linux/pcieport_if.h>
+
+#include "aer/aerdrv.h"
+#include "../pci.h"
+#include "portdrv.h"
+
+/**
+ * pcie_port_acpi_setup - Request the BIOS to release control of PCIe services.
+ * @port: PCIe Port service for a root port or event collector.
+ * @srv_mask: Bit mask of services that can be enabled for @port.
+ *
+ * Invoked when @port is identified as a PCIe port device.  To avoid conflicts
+ * with the BIOS PCIe port native services support requires the BIOS to yield
+ * control of these services to the kernel.  The mask of services that the BIOS
+ * allows to be enabled for @port is written to @srv_mask.
+ *
+ * NOTE: It turns out that we cannot do that for individual port services
+ * separately, because that would make some systems work incorrectly.
+ */
+int pcie_port_acpi_setup(struct pci_dev *port, int *srv_mask)
+{
+	struct acpi_pci_root *root;
+	acpi_handle handle;
+	u32 flags;
+
+	if (acpi_pci_disabled)
+		return 0;
+
+	handle = acpi_find_root_bridge_handle(port);
+	if (!handle)
+		return -EINVAL;
+
+	root = acpi_pci_find_root(handle);
+	if (!root)
+		return -ENODEV;
+
+	flags = root->osc_control_set;
+
+	*srv_mask = PCIE_PORT_SERVICE_VC;
+	if (flags & OSC_PCI_EXPRESS_NATIVE_HP_CONTROL)
+		*srv_mask |= PCIE_PORT_SERVICE_HP;
+	if (flags & OSC_PCI_EXPRESS_PME_CONTROL)
+		*srv_mask |= PCIE_PORT_SERVICE_PME;
+	if (flags & OSC_PCI_EXPRESS_AER_CONTROL)
+		*srv_mask |= PCIE_PORT_SERVICE_AER;
+
+	return 0;
+}

drivers/pci/pcie/portdrv_bus.c

@@ -0,0 +1,55 @@
+/*
+ * File:	portdrv_bus.c
+ * Purpose:	PCI Express Port Bus Driver's Bus Overloading Functions
+ *
+ * Copyright (C) 2004 Intel
+ * Copyright (C) Tom Long Nguyen (tom.l.nguyen@intel.com)
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/pm.h>
+
+#include <linux/pcieport_if.h>
+#include "portdrv.h"
+
+static int pcie_port_bus_match(struct device *dev, struct device_driver *drv);
+
+struct bus_type pcie_port_bus_type = {
+	.name		= "pci_express",
+	.match		= pcie_port_bus_match,
+};
+EXPORT_SYMBOL_GPL(pcie_port_bus_type);
+
+static int pcie_port_bus_match(struct device *dev, struct device_driver *drv)
+{
+	struct pcie_device *pciedev;
+	struct pcie_port_service_driver *driver;
+
+	if (drv->bus != &pcie_port_bus_type || dev->bus != &pcie_port_bus_type)
+		return 0;
+
+	pciedev = to_pcie_device(dev);
+	driver = to_service_driver(drv);
+
+	if (driver->service != pciedev->service)
+		return 0;
+
+	if ((driver->port_type != PCIE_ANY_PORT) &&
+	    (driver->port_type != pci_pcie_type(pciedev->port)))
+		return 0;
+
+	return 1;
+}
+
+int pcie_port_bus_register(void)
+{
+	return bus_register(&pcie_port_bus_type);
+}
+
+void pcie_port_bus_unregister(void)
+{
+	bus_unregister(&pcie_port_bus_type);
+}

drivers/pci/pcie/portdrv_core.c

@@ -0,0 +1,577 @@
+/*
+ * File:	portdrv_core.c
+ * Purpose:	PCI Express Port Bus Driver's Core Functions
+ *
+ * Copyright (C) 2004 Intel
+ * Copyright (C) Tom Long Nguyen (tom.l.nguyen@intel.com)
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/pm.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/pcieport_if.h>
+#include <linux/aer.h>
+
+#include "../pci.h"
+#include "portdrv.h"
+
+bool pciehp_msi_disabled;
+
+static int __init pciehp_setup(char *str)
+{
+	if (!strncmp(str, "nomsi", 5))
+		pciehp_msi_disabled = true;
+
+	return 1;
+}
+__setup("pcie_hp=", pciehp_setup);
+
+/**
+ * release_pcie_device - free PCI Express port service device structure
+ * @dev: Port service device to release
+ *
+ * Invoked automatically when device is being removed in response to
+ * device_unregister(dev).  Release all resources being claimed.
+ */
+static void release_pcie_device(struct device *dev)
+{
+	kfree(to_pcie_device(dev));
+}
+
+/**
+ * pcie_port_msix_add_entry - add entry to given array of MSI-X entries
+ * @entries: Array of MSI-X entries
+ * @new_entry: Index of the entry to add to the array
+ * @nr_entries: Number of entries already in the array
+ *
+ * Return value: Position of the added entry in the array
+ */
+static int pcie_port_msix_add_entry(
+	struct msix_entry *entries, int new_entry, int nr_entries)
+{
+	int j;
+
+	for (j = 0; j < nr_entries; j++)
+		if (entries[j].entry == new_entry)
+			return j;
+
+	entries[j].entry = new_entry;
+	return j;
+}
+
+/**
+ * pcie_port_enable_msix - try to set up MSI-X as interrupt mode for given port
+ * @dev: PCI Express port to handle
+ * @vectors: Array of interrupt vectors to populate
+ * @mask: Bitmask of port capabilities returned by get_port_device_capability()
+ *
+ * Return value: 0 on success, error code on failure
+ */
+static int pcie_port_enable_msix(struct pci_dev *dev, int *vectors, int mask)
+{
+	struct msix_entry *msix_entries;
+	int idx[PCIE_PORT_DEVICE_MAXSERVICES];
+	int nr_entries, status, pos, i, nvec;
+	u16 reg16;
+	u32 reg32;
+
+	nr_entries = pci_msix_vec_count(dev);
+	if (nr_entries < 0)
+		return nr_entries;
+	BUG_ON(!nr_entries);
+	if (nr_entries > PCIE_PORT_MAX_MSIX_ENTRIES)
+		nr_entries = PCIE_PORT_MAX_MSIX_ENTRIES;
+
+	msix_entries = kzalloc(sizeof(*msix_entries) * nr_entries, GFP_KERNEL);
+	if (!msix_entries)
+		return -ENOMEM;
+
+	/*
+	 * Allocate as many entries as the port wants, so that we can check
+	 * which of them will be useful.  Moreover, if nr_entries is correctly
+	 * equal to the number of entries this port actually uses, we'll happily
+	 * go through without any tricks.
+	 */
+	for (i = 0; i < nr_entries; i++)
+		msix_entries[i].entry = i;
+
+	status = pci_enable_msix_exact(dev, msix_entries, nr_entries);
+	if (status)
+		goto Exit;
+
+	for (i = 0; i < PCIE_PORT_DEVICE_MAXSERVICES; i++)
+		idx[i] = -1;
+	status = -EIO;
+	nvec = 0;
+
+	if (mask & (PCIE_PORT_SERVICE_PME | PCIE_PORT_SERVICE_HP)) {
+		int entry;
+
+		/*
+		 * The code below follows the PCI Express Base Specification 2.0
+		 * stating in Section 6.1.6 that "PME and Hot-Plug Event
+		 * interrupts (when both are implemented) always share the same
+		 * MSI or MSI-X vector, as indicated by the Interrupt Message
+		 * Number field in the PCI Express Capabilities register", where
+		 * according to Section 7.8.2 of the specification "For MSI-X,
+		 * the value in this field indicates which MSI-X Table entry is
+		 * used to generate the interrupt message."
+		 */
+		pcie_capability_read_word(dev, PCI_EXP_FLAGS, &reg16);
+		entry = (reg16 & PCI_EXP_FLAGS_IRQ) >> 9;
+		if (entry >= nr_entries)
+			goto Error;
+
+		i = pcie_port_msix_add_entry(msix_entries, entry, nvec);
+		if (i == nvec)
+			nvec++;
+
+		idx[PCIE_PORT_SERVICE_PME_SHIFT] = i;
+		idx[PCIE_PORT_SERVICE_HP_SHIFT] = i;
+	}
+
+	if (mask & PCIE_PORT_SERVICE_AER) {
+		int entry;
+
+		/*
+		 * The code below follows Section 7.10.10 of the PCI Express
+		 * Base Specification 2.0 stating that bits 31-27 of the Root
+		 * Error Status Register contain a value indicating which of the
+		 * MSI/MSI-X vectors assigned to the port is going to be used
+		 * for AER, where "For MSI-X, the value in this register
+		 * indicates which MSI-X Table entry is used to generate the
+		 * interrupt message."
+		 */
+		pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
+		pci_read_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, &reg32);
+		entry = reg32 >> 27;
+		if (entry >= nr_entries)
+			goto Error;
+
+		i = pcie_port_msix_add_entry(msix_entries, entry, nvec);
+		if (i == nvec)
+			nvec++;
+
+		idx[PCIE_PORT_SERVICE_AER_SHIFT] = i;
+	}
+
+	/*
+	 * If nvec is equal to the allocated number of entries, we can just use
+	 * what we have.  Otherwise, the port has some extra entries not for the
+	 * services we know and we need to work around that.
+	 */
+	if (nvec == nr_entries) {
+		status = 0;
+	} else {
+		/* Drop the temporary MSI-X setup */
+		pci_disable_msix(dev);
+
+		/* Now allocate the MSI-X vectors for real */
+		status = pci_enable_msix_exact(dev, msix_entries, nvec);
+		if (status)
+			goto Exit;
+	}
+
+	for (i = 0; i < PCIE_PORT_DEVICE_MAXSERVICES; i++)
+		vectors[i] = idx[i] >= 0 ? msix_entries[idx[i]].vector : -1;
+
+ Exit:
+	kfree(msix_entries);
+	return status;
+
+ Error:
+	pci_disable_msix(dev);
+	goto Exit;
+}
+
+/**
+ * init_service_irqs - initialize irqs for PCI Express port services
+ * @dev: PCI Express port to handle
+ * @irqs: Array of irqs to populate
+ * @mask: Bitmask of port capabilities returned by get_port_device_capability()
+ *
+ * Return value: Interrupt mode associated with the port
+ */
+static int init_service_irqs(struct pci_dev *dev, int *irqs, int mask)
+{
+	int i, irq = -1;
+
+	/*
+	 * If MSI cannot be used for PCIe PME or hotplug, we have to use
+	 * INTx or other interrupts, e.g. system shared interrupt.
+	 */
+	if (((mask & PCIE_PORT_SERVICE_PME) && pcie_pme_no_msi()) ||
+	    ((mask & PCIE_PORT_SERVICE_HP) && pciehp_no_msi())) {
+		if (dev->irq)
+			irq = dev->irq;
+		goto no_msi;
+	}
+
+	/* Try to use MSI-X if supported */
+	if (!pcie_port_enable_msix(dev, irqs, mask))
+		return 0;
+
+	/*
+	 * We're not going to use MSI-X, so try MSI and fall back to INTx.
+	 * If neither MSI/MSI-X nor INTx available, try other interrupt.  On
+	 * some platforms, root port doesn't support MSI/MSI-X/INTx in RC mode.
+	 */
+	if (!pci_enable_msi(dev) || dev->irq)
+		irq = dev->irq;
+
+ no_msi:
+	for (i = 0; i < PCIE_PORT_DEVICE_MAXSERVICES; i++)
+		irqs[i] = irq;
+	irqs[PCIE_PORT_SERVICE_VC_SHIFT] = -1;
+
+	if (irq < 0)
+		return -ENODEV;
+	return 0;
+}
+
+static void cleanup_service_irqs(struct pci_dev *dev)
+{
+	if (dev->msix_enabled)
+		pci_disable_msix(dev);
+	else if (dev->msi_enabled)
+		pci_disable_msi(dev);
+}
+
+/**
+ * get_port_device_capability - discover capabilities of a PCI Express port
+ * @dev: PCI Express port to examine
+ *
+ * The capabilities are read from the port's PCI Express configuration registers
+ * as described in PCI Express Base Specification 1.0a sections 7.8.2, 7.8.9 and
+ * 7.9 - 7.11.
+ *
+ * Return value: Bitmask of discovered port capabilities
+ */
+static int get_port_device_capability(struct pci_dev *dev)
+{
+	int services = 0;
+	u32 reg32;
+	int cap_mask = 0;
+	int err;
+
+	if (pcie_ports_disabled)
+		return 0;
+
+	cap_mask = PCIE_PORT_SERVICE_PME | PCIE_PORT_SERVICE_HP
+			| PCIE_PORT_SERVICE_VC;
+	if (pci_aer_available())
+		cap_mask |= PCIE_PORT_SERVICE_AER;
+
+	if (pcie_ports_auto) {
+		err = pcie_port_platform_notify(dev, &cap_mask);
+		if (err)
+			return 0;
+	}
+
+	/* Hot-Plug Capable */
+	if ((cap_mask & PCIE_PORT_SERVICE_HP) &&
+	    pcie_caps_reg(dev) & PCI_EXP_FLAGS_SLOT) {
+		pcie_capability_read_dword(dev, PCI_EXP_SLTCAP, &reg32);
+		if (reg32 & PCI_EXP_SLTCAP_HPC) {
+			services |= PCIE_PORT_SERVICE_HP;
+			/*
+			 * Disable hot-plug interrupts in case they have been
+			 * enabled by the BIOS and the hot-plug service driver
+			 * is not loaded.
+			 */
+			pcie_capability_clear_word(dev, PCI_EXP_SLTCTL,
+				PCI_EXP_SLTCTL_CCIE | PCI_EXP_SLTCTL_HPIE);
+		}
+	}
+	/* AER capable */
+	if ((cap_mask & PCIE_PORT_SERVICE_AER)
+	    && pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR)) {
+		services |= PCIE_PORT_SERVICE_AER;
+		/*
+		 * Disable AER on this port in case it's been enabled by the
+		 * BIOS (the AER service driver will enable it when necessary).
+		 */
+		pci_disable_pcie_error_reporting(dev);
+	}
+	/* VC support */
+	if (pci_find_ext_capability(dev, PCI_EXT_CAP_ID_VC))
+		services |= PCIE_PORT_SERVICE_VC;
+	/* Root ports are capable of generating PME too */
+	if ((cap_mask & PCIE_PORT_SERVICE_PME)
+	    && pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT) {
+		services |= PCIE_PORT_SERVICE_PME;
+		/*
+		 * Disable PME interrupt on this port in case it's been enabled
+		 * by the BIOS (the PME service driver will enable it when
+		 * necessary).
+		 */
+		pcie_pme_interrupt_enable(dev, false);
+	}
+
+	return services;
+}
+
+/**
+ * pcie_device_init - allocate and initialize PCI Express port service device
+ * @pdev: PCI Express port to associate the service device with
+ * @service: Type of service to associate with the service device
+ * @irq: Interrupt vector to associate with the service device
+ */
+static int pcie_device_init(struct pci_dev *pdev, int service, int irq)
+{
+	int retval;
+	struct pcie_device *pcie;
+	struct device *device;
+
+	pcie = kzalloc(sizeof(*pcie), GFP_KERNEL);
+	if (!pcie)
+		return -ENOMEM;
+	pcie->port = pdev;
+	pcie->irq = irq;
+	pcie->service = service;
+
+	/* Initialize generic device interface */
+	device = &pcie->device;
+	device->bus = &pcie_port_bus_type;
+	device->release = release_pcie_device;	/* callback to free pcie dev */
+	dev_set_name(device, "%s:pcie%02x",
+		     pci_name(pdev),
+		     get_descriptor_id(pci_pcie_type(pdev), service));
+	device->parent = &pdev->dev;
+
+	retval = device_register(device);
+	if (retval) {
+		put_device(device);
+		return retval;
+	}
+
+	return 0;
+}
+
+/**
+ * pcie_port_device_register - register PCI Express port
+ * @dev: PCI Express port to register
+ *
+ * Allocate the port extension structure and register services associated with
+ * the port.
+ */
+int pcie_port_device_register(struct pci_dev *dev)
+{
+	int status, capabilities, i, nr_service;
+	int irqs[PCIE_PORT_DEVICE_MAXSERVICES];
+
+	/* Enable PCI Express port device */
+	status = pci_enable_device(dev);
+	if (status)
+		return status;
+
+	/* Get and check PCI Express port services */
+	capabilities = get_port_device_capability(dev);
+	if (!capabilities)
+		return 0;
+
+	pci_set_master(dev);
+	/*
+	 * Initialize service irqs. Don't use service devices that
+	 * require interrupts if there is no way to generate them.
+	 * However, some drivers may have a polling mode (e.g. pciehp_poll_mode)
+	 * that can be used in the absence of irqs.  Allow them to determine
+	 * if that is to be used.
+	 */
+	status = init_service_irqs(dev, irqs, capabilities);
+	if (status) {
+		capabilities &= PCIE_PORT_SERVICE_VC | PCIE_PORT_SERVICE_HP;
+		if (!capabilities)
+			goto error_disable;
+	}
+
+	/* Allocate child services if any */
+	status = -ENODEV;
+	nr_service = 0;
+	for (i = 0; i < PCIE_PORT_DEVICE_MAXSERVICES; i++) {
+		int service = 1 << i;
+		if (!(capabilities & service))
+			continue;
+		if (!pcie_device_init(dev, service, irqs[i]))
+			nr_service++;
+	}
+	if (!nr_service)
+		goto error_cleanup_irqs;
+
+	return 0;
+
+error_cleanup_irqs:
+	cleanup_service_irqs(dev);
+error_disable:
+	pci_disable_device(dev);
+	return status;
+}
+
+#ifdef CONFIG_PM
+static int suspend_iter(struct device *dev, void *data)
+{
+	struct pcie_port_service_driver *service_driver;
+
+	if ((dev->bus == &pcie_port_bus_type) && dev->driver) {
+		service_driver = to_service_driver(dev->driver);
+		if (service_driver->suspend)
+			service_driver->suspend(to_pcie_device(dev));
+	}
+	return 0;
+}
+
+/**
+ * pcie_port_device_suspend - suspend port services associated with a PCIe port
+ * @dev: PCI Express port to handle
+ */
+int pcie_port_device_suspend(struct device *dev)
+{
+	return device_for_each_child(dev, NULL, suspend_iter);
+}
+
+static int resume_iter(struct device *dev, void *data)
+{
+	struct pcie_port_service_driver *service_driver;
+
+	if ((dev->bus == &pcie_port_bus_type) &&
+	    (dev->driver)) {
+		service_driver = to_service_driver(dev->driver);
+		if (service_driver->resume)
+			service_driver->resume(to_pcie_device(dev));
+	}
+	return 0;
+}
+
+/**
+ * pcie_port_device_suspend - resume port services associated with a PCIe port
+ * @dev: PCI Express port to handle
+ */
+int pcie_port_device_resume(struct device *dev)
+{
+	return device_for_each_child(dev, NULL, resume_iter);
+}
+#endif /* PM */
+
+static int remove_iter(struct device *dev, void *data)
+{
+	if (dev->bus == &pcie_port_bus_type)
+		device_unregister(dev);
+	return 0;
+}
+
+/**
+ * pcie_port_device_remove - unregister PCI Express port service devices
+ * @dev: PCI Express port the service devices to unregister are associated with
+ *
+ * Remove PCI Express port service devices associated with given port and
+ * disable MSI-X or MSI for the port.
+ */
+void pcie_port_device_remove(struct pci_dev *dev)
+{
+	device_for_each_child(&dev->dev, NULL, remove_iter);
+	cleanup_service_irqs(dev);
+	pci_disable_device(dev);
+}
+
+/**
+ * pcie_port_probe_service - probe driver for given PCI Express port service
+ * @dev: PCI Express port service device to probe against
+ *
+ * If PCI Express port service driver is registered with
+ * pcie_port_service_register(), this function will be called by the driver core
+ * whenever match is found between the driver and a port service device.
+ */
+static int pcie_port_probe_service(struct device *dev)
+{
+	struct pcie_device *pciedev;
+	struct pcie_port_service_driver *driver;
+	int status;
+
+	if (!dev || !dev->driver)
+		return -ENODEV;
+
+	driver = to_service_driver(dev->driver);
+	if (!driver || !driver->probe)
+		return -ENODEV;
+
+	pciedev = to_pcie_device(dev);
+	status = driver->probe(pciedev);
+	if (status)
+		return status;
+
+	dev_printk(KERN_DEBUG, dev, "service driver %s loaded\n", driver->name);
+	get_device(dev);
+	return 0;
+}
+
+/**
+ * pcie_port_remove_service - detach driver from given PCI Express port service
+ * @dev: PCI Express port service device to handle
+ *
+ * If PCI Express port service driver is registered with
+ * pcie_port_service_register(), this function will be called by the driver core
+ * when device_unregister() is called for the port service device associated
+ * with the driver.
+ */
+static int pcie_port_remove_service(struct device *dev)
+{
+	struct pcie_device *pciedev;
+	struct pcie_port_service_driver *driver;
+
+	if (!dev || !dev->driver)
+		return 0;
+
+	pciedev = to_pcie_device(dev);
+	driver = to_service_driver(dev->driver);
+	if (driver && driver->remove) {
+		dev_printk(KERN_DEBUG, dev, "unloading service driver %s\n",
+			driver->name);
+		driver->remove(pciedev);
+		put_device(dev);
+	}
+	return 0;
+}
+
+/**
+ * pcie_port_shutdown_service - shut down given PCI Express port service
+ * @dev: PCI Express port service device to handle
+ *
+ * If PCI Express port service driver is registered with
+ * pcie_port_service_register(), this function will be called by the driver core
+ * when device_shutdown() is called for the port service device associated
+ * with the driver.
+ */
+static void pcie_port_shutdown_service(struct device *dev) {}
+
+/**
+ * pcie_port_service_register - register PCI Express port service driver
+ * @new: PCI Express port service driver to register
+ */
+int pcie_port_service_register(struct pcie_port_service_driver *new)
+{
+	if (pcie_ports_disabled)
+		return -ENODEV;
+
+	new->driver.name = new->name;
+	new->driver.bus = &pcie_port_bus_type;
+	new->driver.probe = pcie_port_probe_service;
+	new->driver.remove = pcie_port_remove_service;
+	new->driver.shutdown = pcie_port_shutdown_service;
+
+	return driver_register(&new->driver);
+}
+EXPORT_SYMBOL(pcie_port_service_register);
+
+/**
+ * pcie_port_service_unregister - unregister PCI Express port service driver
+ * @drv: PCI Express port service driver to unregister
+ */
+void pcie_port_service_unregister(struct pcie_port_service_driver *drv)
+{
+	driver_unregister(&drv->driver);
+}
+EXPORT_SYMBOL(pcie_port_service_unregister);

drivers/pci/pcie/portdrv_pci.c

@@ -0,0 +1,364 @@
+/*
+ * File:	portdrv_pci.c
+ * Purpose:	PCI Express Port Bus Driver
+ *
+ * Copyright (C) 2004 Intel
+ * Copyright (C) Tom Long Nguyen (tom.l.nguyen@intel.com)
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/pm.h>
+#include <linux/pm_runtime.h>
+#include <linux/init.h>
+#include <linux/pcieport_if.h>
+#include <linux/aer.h>
+#include <linux/dmi.h>
+#include <linux/pci-aspm.h>
+
+#include "portdrv.h"
+#include "aer/aerdrv.h"
+
+/*
+ * Version Information
+ */
+#define DRIVER_VERSION "v1.0"
+#define DRIVER_AUTHOR "tom.l.nguyen@intel.com"
+#define DRIVER_DESC "PCIe Port Bus Driver"
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
+MODULE_LICENSE("GPL");
+
+/* If this switch is set, PCIe port native services should not be enabled. */
+bool pcie_ports_disabled;
+
+/*
+ * If this switch is set, ACPI _OSC will be used to determine whether or not to
+ * enable PCIe port native services.
+ */
+bool pcie_ports_auto = true;
+
+static int __init pcie_port_setup(char *str)
+{
+	if (!strncmp(str, "compat", 6)) {
+		pcie_ports_disabled = true;
+	} else if (!strncmp(str, "native", 6)) {
+		pcie_ports_disabled = false;
+		pcie_ports_auto = false;
+	} else if (!strncmp(str, "auto", 4)) {
+		pcie_ports_disabled = false;
+		pcie_ports_auto = true;
+	}
+
+	return 1;
+}
+__setup("pcie_ports=", pcie_port_setup);
+
+/* global data */
+
+/**
+ * pcie_clear_root_pme_status - Clear root port PME interrupt status.
+ * @dev: PCIe root port or event collector.
+ */
+void pcie_clear_root_pme_status(struct pci_dev *dev)
+{
+	pcie_capability_set_dword(dev, PCI_EXP_RTSTA, PCI_EXP_RTSTA_PME);
+}
+
+static int pcie_portdrv_restore_config(struct pci_dev *dev)
+{
+	int retval;
+
+	retval = pci_enable_device(dev);
+	if (retval)
+		return retval;
+	pci_set_master(dev);
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int pcie_port_resume_noirq(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+
+	/*
+	 * Some BIOSes forget to clear Root PME Status bits after system wakeup
+	 * which breaks ACPI-based runtime wakeup on PCI Express, so clear those
+	 * bits now just in case (shouldn't hurt).
+	 */
+	if (pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT)
+		pcie_clear_root_pme_status(pdev);
+	return 0;
+}
+
+static const struct dev_pm_ops pcie_portdrv_pm_ops = {
+	.suspend	= pcie_port_device_suspend,
+	.resume		= pcie_port_device_resume,
+	.freeze		= pcie_port_device_suspend,
+	.thaw		= pcie_port_device_resume,
+	.poweroff	= pcie_port_device_suspend,
+	.restore	= pcie_port_device_resume,
+	.resume_noirq	= pcie_port_resume_noirq,
+};
+
+#define PCIE_PORTDRV_PM_OPS	(&pcie_portdrv_pm_ops)
+
+#else /* !PM */
+
+#define PCIE_PORTDRV_PM_OPS	NULL
+#endif /* !PM */
+
+/*
+ * pcie_portdrv_probe - Probe PCI-Express port devices
+ * @dev: PCI-Express port device being probed
+ *
+ * If detected invokes the pcie_port_device_register() method for
+ * this port device.
+ *
+ */
+static int pcie_portdrv_probe(struct pci_dev *dev,
+					const struct pci_device_id *id)
+{
+	int status;
+
+	if (!pci_is_pcie(dev) ||
+	    ((pci_pcie_type(dev) != PCI_EXP_TYPE_ROOT_PORT) &&
+	     (pci_pcie_type(dev) != PCI_EXP_TYPE_UPSTREAM) &&
+	     (pci_pcie_type(dev) != PCI_EXP_TYPE_DOWNSTREAM)))
+		return -ENODEV;
+
+	status = pcie_port_device_register(dev);
+	if (status)
+		return status;
+
+	pci_save_state(dev);
+	/*
+	 * D3cold may not work properly on some PCIe port, so disable
+	 * it by default.
+	 */
+	dev->d3cold_allowed = false;
+	return 0;
+}
+
+static void pcie_portdrv_remove(struct pci_dev *dev)
+{
+	pcie_port_device_remove(dev);
+}
+
+static int error_detected_iter(struct device *device, void *data)
+{
+	struct pcie_device *pcie_device;
+	struct pcie_port_service_driver *driver;
+	struct aer_broadcast_data *result_data;
+	pci_ers_result_t status;
+
+	result_data = (struct aer_broadcast_data *) data;
+
+	if (device->bus == &pcie_port_bus_type && device->driver) {
+		driver = to_service_driver(device->driver);
+		if (!driver ||
+			!driver->err_handler ||
+			!driver->err_handler->error_detected)
+			return 0;
+
+		pcie_device = to_pcie_device(device);
+
+		/* Forward error detected message to service drivers */
+		status = driver->err_handler->error_detected(
+			pcie_device->port,
+			result_data->state);
+		result_data->result =
+			merge_result(result_data->result, status);
+	}
+
+	return 0;
+}
+
+static pci_ers_result_t pcie_portdrv_error_detected(struct pci_dev *dev,
+					enum pci_channel_state error)
+{
+	struct aer_broadcast_data data = {error, PCI_ERS_RESULT_CAN_RECOVER};
+
+	/* get true return value from &data */
+	device_for_each_child(&dev->dev, &data, error_detected_iter);
+	return data.result;
+}
+
+static int mmio_enabled_iter(struct device *device, void *data)
+{
+	struct pcie_device *pcie_device;
+	struct pcie_port_service_driver *driver;
+	pci_ers_result_t status, *result;
+
+	result = (pci_ers_result_t *) data;
+
+	if (device->bus == &pcie_port_bus_type && device->driver) {
+		driver = to_service_driver(device->driver);
+		if (driver &&
+			driver->err_handler &&
+			driver->err_handler->mmio_enabled) {
+			pcie_device = to_pcie_device(device);
+
+			/* Forward error message to service drivers */
+			status = driver->err_handler->mmio_enabled(
+					pcie_device->port);
+			*result = merge_result(*result, status);
+		}
+	}
+
+	return 0;
+}
+
+static pci_ers_result_t pcie_portdrv_mmio_enabled(struct pci_dev *dev)
+{
+	pci_ers_result_t status = PCI_ERS_RESULT_RECOVERED;
+
+	/* get true return value from &status */
+	device_for_each_child(&dev->dev, &status, mmio_enabled_iter);
+	return status;
+}
+
+static int slot_reset_iter(struct device *device, void *data)
+{
+	struct pcie_device *pcie_device;
+	struct pcie_port_service_driver *driver;
+	pci_ers_result_t status, *result;
+
+	result = (pci_ers_result_t *) data;
+
+	if (device->bus == &pcie_port_bus_type && device->driver) {
+		driver = to_service_driver(device->driver);
+		if (driver &&
+			driver->err_handler &&
+			driver->err_handler->slot_reset) {
+			pcie_device = to_pcie_device(device);
+
+			/* Forward error message to service drivers */
+			status = driver->err_handler->slot_reset(
+					pcie_device->port);
+			*result = merge_result(*result, status);
+		}
+	}
+
+	return 0;
+}
+
+static pci_ers_result_t pcie_portdrv_slot_reset(struct pci_dev *dev)
+{
+	pci_ers_result_t status = PCI_ERS_RESULT_RECOVERED;
+
+	/* If fatal, restore cfg space for possible link reset at upstream */
+	if (dev->error_state == pci_channel_io_frozen) {
+		dev->state_saved = true;
+		pci_restore_state(dev);
+		pcie_portdrv_restore_config(dev);
+		pci_enable_pcie_error_reporting(dev);
+	}
+
+	/* get true return value from &status */
+	device_for_each_child(&dev->dev, &status, slot_reset_iter);
+	return status;
+}
+
+static int resume_iter(struct device *device, void *data)
+{
+	struct pcie_device *pcie_device;
+	struct pcie_port_service_driver *driver;
+
+	if (device->bus == &pcie_port_bus_type && device->driver) {
+		driver = to_service_driver(device->driver);
+		if (driver &&
+			driver->err_handler &&
+			driver->err_handler->resume) {
+			pcie_device = to_pcie_device(device);
+
+			/* Forward error message to service drivers */
+			driver->err_handler->resume(pcie_device->port);
+		}
+	}
+
+	return 0;
+}
+
+static void pcie_portdrv_err_resume(struct pci_dev *dev)
+{
+	device_for_each_child(&dev->dev, NULL, resume_iter);
+}
+
+/*
+ * LINUX Device Driver Model
+ */
+static const struct pci_device_id port_pci_ids[] = { {
+	/* handle any PCI-Express port */
+	PCI_DEVICE_CLASS(((PCI_CLASS_BRIDGE_PCI << 8) | 0x00), ~0),
+	}, { /* end: all zeroes */ }
+};
+MODULE_DEVICE_TABLE(pci, port_pci_ids);
+
+static const struct pci_error_handlers pcie_portdrv_err_handler = {
+	.error_detected = pcie_portdrv_error_detected,
+	.mmio_enabled = pcie_portdrv_mmio_enabled,
+	.slot_reset = pcie_portdrv_slot_reset,
+	.resume = pcie_portdrv_err_resume,
+};
+
+static struct pci_driver pcie_portdriver = {
+	.name		= "pcieport",
+	.id_table	= &port_pci_ids[0],
+
+	.probe		= pcie_portdrv_probe,
+	.remove		= pcie_portdrv_remove,
+
+	.err_handler	= &pcie_portdrv_err_handler,
+
+	.driver.pm	= PCIE_PORTDRV_PM_OPS,
+};
+
+static int __init dmi_pcie_pme_disable_msi(const struct dmi_system_id *d)
+{
+	pr_notice("%s detected: will not use MSI for PCIe PME signaling\n",
+		  d->ident);
+	pcie_pme_disable_msi();
+	return 0;
+}
+
+static struct dmi_system_id __initdata pcie_portdrv_dmi_table[] = {
+	/*
+	 * Boxes that should not use MSI for PCIe PME signaling.
+	 */
+	{
+	 .callback = dmi_pcie_pme_disable_msi,
+	 .ident = "MSI Wind U-100",
+	 .matches = {
+		     DMI_MATCH(DMI_SYS_VENDOR,
+				"MICRO-STAR INTERNATIONAL CO., LTD"),
+		     DMI_MATCH(DMI_PRODUCT_NAME, "U-100"),
+		     },
+	 },
+	 {}
+};
+
+static int __init pcie_portdrv_init(void)
+{
+	int retval;
+
+	if (pcie_ports_disabled)
+		return pci_register_driver(&pcie_portdriver);
+
+	dmi_check_system(pcie_portdrv_dmi_table);
+
+	retval = pcie_port_bus_register();
+	if (retval) {
+		printk(KERN_WARNING "PCIE: bus_register error: %d\n", retval);
+		goto out;
+	}
+	retval = pci_register_driver(&pcie_portdriver);
+	if (retval)
+		pcie_port_bus_unregister();
+ out:
+	return retval;
+}
+
+module_init(pcie_portdrv_init);