Merge master.kernel.org:/pub/scm/linux/kernel/git/gregkh/pci-2.6

* master.kernel.org:/pub/scm/linux/kernel/git/gregkh/pci-2.6: (28 commits)
  pciehp - fix wrong return value
  IA64: PCI: dont disable irq which is not enabled
  acpiphp: add support for ioapic hot-remove
  PCI: assign ioapic resource at hotplug
  acpiphp: disable bridges
  acpiphp: stop bus device before acpi_bus_trim
  PCI: add pci_stop_bus_device
  acpiphp: do not initialize existing ioapics
  acpiphp: initialize ioapics before starting devices
  acpiphp: set hpp values before starting devices
  PCI Hotplug: cleanup pcihp skeleton code.
  PCI: Restore PCI Express capability registers after PM event
  PCI: drivers/pci/hotplug/acpiphp_glue.c: make a function static
  PCI: Multiprobe sanitizer
  PCI: fix __must_check warnings
  PCI Hotplug: fix __must_check warnings
  SHPCHP: fix __must_check warnings
  PCI-Express AER implemetation: pcie_portdrv error handler
  PCI-Express AER implemetation: AER core and aerdriver
  PCI-Express AER implemetation: export pcie_port_bus_type
  ...

Documentation/pcieaer-howto.txt

+   The PCI Express Advanced Error Reporting Driver Guide HOWTO
+		T. Long Nguyen	<tom.l.nguyen@intel.com>
+		Yanmin Zhang	<yanmin.zhang@intel.com>
+				07/29/2006
+
+
+1. Overview
+
+1.1 About this guide
+
+This guide describes the basics of the PCI Express Advanced Error
+Reporting (AER) driver and provides information on how to use it, as
+well as how to enable the drivers of endpoint devices to conform with
+PCI Express AER driver.
+
+1.2 Copyright © Intel Corporation 2006.
+
+1.3 What is the PCI Express AER Driver?
+
+PCI Express error signaling can occur on the PCI Express link itself
+or on behalf of transactions initiated on the link. PCI Express
+defines two error reporting paradigms: the baseline capability and
+the Advanced Error Reporting capability. The baseline capability is
+required of all PCI Express components providing a minimum defined
+set of error reporting requirements. Advanced Error Reporting
+capability is implemented with a PCI Express advanced error reporting
+extended capability structure providing more robust error reporting.
+
+The PCI Express AER driver provides the infrastructure to support PCI
+Express Advanced Error Reporting capability. The PCI Express AER
+driver provides three basic functions:
+
+-	Gathers the comprehensive error information if errors occurred.
+-	Reports error to the users.
+-	Performs error recovery actions.
+
+AER driver only attaches root ports which support PCI-Express AER
+capability.
+
+
+2. User Guide
+
+2.1 Include the PCI Express AER Root Driver into the Linux Kernel
+
+The PCI Express AER Root driver is a Root Port service driver attached
+to the PCI Express Port Bus driver. If a user wants to use it, the driver
+has to be compiled. Option CONFIG_PCIEAER supports this capability. It
+depends on CONFIG_PCIEPORTBUS, so pls. set CONFIG_PCIEPORTBUS=y and
+CONFIG_PCIEAER = y.
+
+2.2 Load PCI Express AER Root Driver
+There is a case where a system has AER support in BIOS. Enabling the AER
+Root driver and having AER support in BIOS may result unpredictable
+behavior. To avoid this conflict, a successful load of the AER Root driver
+requires ACPI _OSC support in the BIOS to allow the AER Root driver to
+request for native control of AER. See the PCI FW 3.0 Specification for
+details regarding OSC usage. Currently, lots of firmwares don't provide
+_OSC support while they use PCI Express. To support such firmwares,
+forceload, a parameter of type bool, could enable AER to continue to
+be initiated although firmwares have no _OSC support. To enable the
+walkaround, pls. add aerdriver.forceload=y to kernel boot parameter line
+when booting kernel. Note that forceload=n by default.
+
+2.3 AER error output
+When a PCI-E AER error is captured, an error message will be outputed to
+console. If it's a correctable error, it is outputed as a warning.
+Otherwise, it is printed as an error. So users could choose different
+log level to filter out correctable error messages.
+
+Below shows an example.
++------ PCI-Express Device Error -----+
+Error Severity          : Uncorrected (Fatal)
+PCIE Bus Error type     : Transaction Layer
+Unsupported Request     : First
+Requester ID            : 0500
+VendorID=8086h, DeviceID=0329h, Bus=05h, Device=00h, Function=00h
+TLB Header:
+04000001 00200a03 05010000 00050100
+
+In the example, 'Requester ID' means the ID of the device who sends
+the error message to root port. Pls. refer to pci express specs for
+other fields.
+
+
+3. Developer Guide
+
+To enable AER aware support requires a software driver to configure
+the AER capability structure within its device and to provide callbacks.
+
+To support AER better, developers need understand how AER does work
+firstly.
+
+PCI Express errors are classified into two types: correctable errors
+and uncorrectable errors. This classification is based on the impacts
+of those errors, which may result in degraded performance or function
+failure.
+
+Correctable errors pose no impacts on the functionality of the
+interface. The PCI Express protocol can recover without any software
+intervention or any loss of data. These errors are detected and
+corrected by hardware. Unlike correctable errors, uncorrectable
+errors impact functionality of the interface. Uncorrectable errors
+can cause a particular transaction or a particular PCI Express link
+to be unreliable. Depending on those error conditions, uncorrectable
+errors are further classified into non-fatal errors and fatal errors.
+Non-fatal errors cause the particular transaction to be unreliable,
+but the PCI Express link itself is fully functional. Fatal errors, on
+the other hand, cause the link to be unreliable.
+
+When AER is enabled, a PCI Express device will automatically send an
+error message to the PCIE root port above it when the device captures
+an error. The Root Port, upon receiving an error reporting message,
+internally processes and logs the error message in its PCI Express
+capability structure. Error information being logged includes storing
+the error reporting agent's requestor ID into the Error Source
+Identification Registers and setting the error bits of the Root Error
+Status Register accordingly. If AER error reporting is enabled in Root
+Error Command Register, the Root Port generates an interrupt if an
+error is detected.
+
+Note that the errors as described above are related to the PCI Express
+hierarchy and links. These errors do not include any device specific
+errors because device specific errors will still get sent directly to
+the device driver.
+
+3.1 Configure the AER capability structure
+
+AER aware drivers of PCI Express component need change the device
+control registers to enable AER. They also could change AER registers,
+including mask and severity registers. Helper function
+pci_enable_pcie_error_reporting could be used to enable AER. See
+section 3.3.
+
+3.2. Provide callbacks
+
+3.2.1 callback reset_link to reset pci express link
+
+This callback is used to reset the pci express physical link when a
+fatal error happens. The root port aer service driver provides a
+default reset_link function, but different upstream ports might
+have different specifications to reset pci express link, so all
+upstream ports should provide their own reset_link functions.
+
+In struct pcie_port_service_driver, a new pointer, reset_link, is
+added.
+
+pci_ers_result_t (*reset_link) (struct pci_dev *dev);
+
+Section 3.2.2.2 provides more detailed info on when to call
+reset_link.
+
+3.2.2 PCI error-recovery callbacks
+
+The PCI Express AER Root driver uses error callbacks to coordinate
+with downstream device drivers associated with a hierarchy in question
+when performing error recovery actions.
+
+Data struct pci_driver has a pointer, err_handler, to point to
+pci_error_handlers who consists of a couple of callback function
+pointers. AER driver follows the rules defined in
+pci-error-recovery.txt except pci express specific parts (e.g.
+reset_link). Pls. refer to pci-error-recovery.txt for detailed
+definitions of the callbacks.
+
+Below sections specify when to call the error callback functions.
+
+3.2.2.1 Correctable errors
+
+Correctable errors pose no impacts on the functionality of
+the interface. The PCI Express protocol can recover without any
+software intervention or any loss of data. These errors do not
+require any recovery actions. The AER driver clears the device's
+correctable error status register accordingly and logs these errors.
+
+3.2.2.2 Non-correctable (non-fatal and fatal) errors
+
+If an error message indicates a non-fatal error, performing link reset
+at upstream is not required. The AER driver calls error_detected(dev,
+pci_channel_io_normal) to all drivers associated within a hierarchy in
+question. for example,
+EndPoint<==>DownstreamPort B<==>UpstreamPort A<==>RootPort.
+If Upstream port A captures an AER error, the hierarchy consists of
+Downstream port B and EndPoint.
+
+A driver may return PCI_ERS_RESULT_CAN_RECOVER,
+PCI_ERS_RESULT_DISCONNECT, or PCI_ERS_RESULT_NEED_RESET, depending on
+whether it can recover or the AER driver calls mmio_enabled as next.
+
+If an error message indicates a fatal error, kernel will broadcast
+error_detected(dev, pci_channel_io_frozen) to all drivers within
+a hierarchy in question. Then, performing link reset at upstream is
+necessary. As different kinds of devices might use different approaches
+to reset link, AER port service driver is required to provide the
+function to reset link. Firstly, kernel looks for if the upstream
+component has an aer driver. If it has, kernel uses the reset_link
+callback of the aer driver. If the upstream component has no aer driver
+and the port is downstream port, we will use the aer driver of the
+root port who reports the AER error. As for upstream ports,
+they should provide their own aer service drivers with reset_link
+function. If error_detected returns PCI_ERS_RESULT_CAN_RECOVER and
+reset_link returns PCI_ERS_RESULT_RECOVERED, the error handling goes
+to mmio_enabled.
+
+3.3 helper functions
+
+3.3.1 int pci_find_aer_capability(struct pci_dev *dev);
+pci_find_aer_capability locates the PCI Express AER capability
+in the device configuration space. If the device doesn't support
+PCI-Express AER, the function returns 0.
+
+3.3.2 int pci_enable_pcie_error_reporting(struct pci_dev *dev);
+pci_enable_pcie_error_reporting enables the device to send error
+messages to root port when an error is detected. Note that devices
+don't enable the error reporting by default, so device drivers need
+call this function to enable it.
+
+3.3.3 int pci_disable_pcie_error_reporting(struct pci_dev *dev);
+pci_disable_pcie_error_reporting disables the device to send error
+messages to root port when an error is detected.
+
+3.3.4 int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev);
+pci_cleanup_aer_uncorrect_error_status cleanups the uncorrectable
+error status register.
+
+3.4 Frequent Asked Questions
+
+Q: What happens if a PCI Express device driver does not provide an
+error recovery handler (pci_driver->err_handler is equal to NULL)?
+
+A: The devices attached with the driver won't be recovered. If the
+error is fatal, kernel will print out warning messages. Please refer
+to section 3 for more information.
+
+Q: What happens if an upstream port service driver does not provide
+callback reset_link?
+
+A: Fatal error recovery will fail if the errors are reported by the
+upstream ports who are attached by the service driver.
+
+Q: How does this infrastructure deal with driver that is not PCI
+Express aware?
+
+A: This infrastructure calls the error callback functions of the
+driver when an error happens. But if the driver is not aware of
+PCI Express, the device might not report its own errors to root
+port.
+
+Q: What modifications will that driver need to make it compatible
+with the PCI Express AER Root driver?
+
+A: It could call the helper functions to enable AER in devices and
+cleanup uncorrectable status register. Pls. refer to section 3.3.
+

arch/ia64/pci/pci.c

@@ -562,6 +562,7 @@ pcibios_enable_device (struct pci_dev *dev, int mask)
 void
 pcibios_disable_device (struct pci_dev *dev)
 {
+	if (dev->is_enabled)
 		acpi_pci_irq_disable(dev);
 }
 

arch/powerpc/sysdev/mpic.c

@@ -339,7 +339,7 @@ static void __init mpic_scan_ht_pic(struct mpic *mpic, u8 __iomem *devbase,
 	for (pos = readb(devbase + PCI_CAPABILITY_LIST); pos != 0;
 	     pos = readb(devbase + pos + PCI_CAP_LIST_NEXT)) {
 		u8 id = readb(devbase + pos + PCI_CAP_LIST_ID);
-		if (id == PCI_CAP_ID_HT_IRQCONF) {
+		if (id == PCI_CAP_ID_HT) {
 			id = readb(devbase + pos + 3);
 			if (id == 0x80)
 				break;

drivers/infiniband/hw/ipath/ipath_iba6110.c

@@ -742,7 +742,6 @@ static int ipath_setup_ht_reset(struct ipath_devdata *dd)
 	return 0;
 }
 
-#define HT_CAPABILITY_ID   0x08	/* HT capabilities not defined in kernel */
 #define HT_INTR_DISC_CONFIG  0x80	/* HT interrupt and discovery cap */
 #define HT_INTR_REG_INDEX    2	/* intconfig requires indirect accesses */
 
@@ -973,7 +972,7 @@ static int ipath_setup_ht_config(struct ipath_devdata *dd,
 	 * do this early, before we ever enable errors or hardware errors,
 	 * mostly to avoid causing the chip to enter freeze mode.
 	 */
-	pos = pci_find_capability(pdev, HT_CAPABILITY_ID);
+	pos = pci_find_capability(pdev, PCI_CAP_ID_HT);
 	if (!pos) {
 		ipath_dev_err(dd, "Couldn't find HyperTransport "
 			      "capability; no interrupts\n");
@@ -996,7 +995,7 @@ static int ipath_setup_ht_config(struct ipath_devdata *dd,
 		else if (cap_type == HT_INTR_DISC_CONFIG)
 			ihandler = set_int_handler(dd, pdev, pos);
 	} while ((pos = pci_find_next_capability(pdev, pos,
-						 HT_CAPABILITY_ID)));
+						 PCI_CAP_ID_HT)));
 
 	if (!ihandler) {
 		ipath_dev_err(dd, "Couldn't find interrupt handler in "

drivers/pci/bus.c

@@ -77,9 +77,12 @@ pci_bus_alloc_resource(struct pci_bus *bus, struct resource *res,
  * This adds a single pci device to the global
  * device list and adds sysfs and procfs entries
  */
-void __devinit pci_bus_add_device(struct pci_dev *dev)
+int __devinit pci_bus_add_device(struct pci_dev *dev)
 {
-	device_add(&dev->dev);
+	int retval;
+	retval = device_add(&dev->dev);
+	if (retval)
+		return retval;
 
 	down_write(&pci_bus_sem);
 	list_add_tail(&dev->global_list, &pci_devices);
@@ -87,6 +90,7 @@ void __devinit pci_bus_add_device(struct pci_dev *dev)
 
 	pci_proc_attach_device(dev);
 	pci_create_sysfs_dev_files(dev);
+	return 0;
 }
 
 /**
@@ -104,6 +108,7 @@ void __devinit pci_bus_add_device(struct pci_dev *dev)
 void __devinit pci_bus_add_devices(struct pci_bus *bus)
 {
 	struct pci_dev *dev;
+	int retval;
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
 		/*
@@ -112,7 +117,9 @@ void __devinit pci_bus_add_devices(struct pci_bus *bus)
 		 */
 		if (!list_empty(&dev->global_list))
 			continue;
-		pci_bus_add_device(dev);
+		retval = pci_bus_add_device(dev);
+		if (retval)
+			dev_err(&dev->dev, "Error adding device, continuing\n");
 	}
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
@@ -131,8 +138,11 @@ void __devinit pci_bus_add_devices(struct pci_bus *bus)
 			       up_write(&pci_bus_sem);
 			}
 			pci_bus_add_devices(dev->subordinate);
-
-			sysfs_create_link(&dev->subordinate->class_dev.kobj, &dev->dev.kobj, "bridge");
+			retval = sysfs_create_link(&dev->subordinate->class_dev.kobj,
+						   &dev->dev.kobj, "bridge");
+			if (retval)
+				dev_err(&dev->dev, "Error creating sysfs "
+					"bridge symlink, continuing...\n");
 		}
 	}
 }

drivers/pci/hotplug/acpiphp.h

@@ -150,6 +150,11 @@ struct acpiphp_attention_info
 	struct module *owner;
 };
 
+struct acpiphp_ioapic {
+	struct pci_dev *dev;
+	u32 gsi_base;
+	struct list_head list;
+};
 
 /* PCI bus bridge HID */
 #define ACPI_PCI_HOST_HID		"PNP0A03"

drivers/pci/hotplug/acpiphp_glue.c

@@ -53,6 +53,8 @@
 #include "acpiphp.h"
 
 static LIST_HEAD(bridge_list);
+static LIST_HEAD(ioapic_list);
+static DEFINE_SPINLOCK(ioapic_list_lock);
 
 #define MY_NAME "acpiphp_glue"
 
@@ -797,6 +799,7 @@ ioapic_add(acpi_handle handle, u32 lvl, void *context, void **rv)
 	struct pci_dev *pdev;
 	u32 gsi_base;
 	u64 phys_addr;
+	struct acpiphp_ioapic *ioapic;
 
 	/* Evaluate _STA if present */
 	status = acpi_evaluate_integer(handle, "_STA", NULL, &sta);
@@ -811,41 +814,107 @@ ioapic_add(acpi_handle handle, u32 lvl, void *context, void **rv)
 	if (get_gsi_base(handle, &gsi_base))
 		return AE_OK;
 
+	ioapic = kmalloc(sizeof(*ioapic), GFP_KERNEL);
+	if (!ioapic)
+		return AE_NO_MEMORY;
+
 	pdev = get_apic_pci_info(handle);
 	if (!pdev)
-		return AE_OK;
+		goto exit_kfree;
 
-	if (pci_enable_device(pdev)) {
-		pci_dev_put(pdev);
-		return AE_OK;
-	}
+	if (pci_enable_device(pdev))
+		goto exit_pci_dev_put;
 
 	pci_set_master(pdev);
 
-	if (pci_request_region(pdev, 0, "I/O APIC(acpiphp)")) {
-		pci_disable_device(pdev);
-		pci_dev_put(pdev);
-		return AE_OK;
-	}
+	if (pci_request_region(pdev, 0, "I/O APIC(acpiphp)"))
+		goto exit_pci_disable_device;
 
 	phys_addr = pci_resource_start(pdev, 0);
-	if (acpi_register_ioapic(handle, phys_addr, gsi_base)) {
+	if (acpi_register_ioapic(handle, phys_addr, gsi_base))
+		goto exit_pci_release_region;
+
+	ioapic->gsi_base = gsi_base;
+	ioapic->dev = pdev;
+	spin_lock(&ioapic_list_lock);
+	list_add_tail(&ioapic->list, &ioapic_list);
+	spin_unlock(&ioapic_list_lock);
+
+	return AE_OK;
+
+ exit_pci_release_region:
 	pci_release_region(pdev, 0);
+ exit_pci_disable_device:
 	pci_disable_device(pdev);
+ exit_pci_dev_put:
 	pci_dev_put(pdev);
+ exit_kfree:
+	kfree(ioapic);
+
+	return AE_OK;
+}
+
+static acpi_status
+ioapic_remove(acpi_handle handle, u32 lvl, void *context, void **rv)
+{
+	acpi_status status;
+	unsigned long sta;
+	acpi_handle tmp;
+	u32 gsi_base;
+	struct acpiphp_ioapic *pos, *n, *ioapic = NULL;
+
+	/* Evaluate _STA if present */
+	status = acpi_evaluate_integer(handle, "_STA", NULL, &sta);
+	if (ACPI_SUCCESS(status) && sta != ACPI_STA_ALL)
+		return AE_CTRL_DEPTH;
+
+	/* Scan only PCI bus scope */
+	status = acpi_get_handle(handle, "_HID", &tmp);
+	if (ACPI_SUCCESS(status))
+		return AE_CTRL_DEPTH;
+
+	if (get_gsi_base(handle, &gsi_base))
 		return AE_OK;
+
+	acpi_unregister_ioapic(handle, gsi_base);
+
+	spin_lock(&ioapic_list_lock);
+	list_for_each_entry_safe(pos, n, &ioapic_list, list) {
+		if (pos->gsi_base != gsi_base)
+			continue;
+		ioapic = pos;
+		list_del(&ioapic->list);
+		break;
 	}
+	spin_unlock(&ioapic_list_lock);
+
+	if (!ioapic)
+		return AE_OK;
+
+	pci_release_region(ioapic->dev, 0);
+	pci_disable_device(ioapic->dev);
+	pci_dev_put(ioapic->dev);
+	kfree(ioapic);
 
 	return AE_OK;
 }
 
 static int acpiphp_configure_ioapics(acpi_handle handle)
 {
+	ioapic_add(handle, 0, NULL, NULL);
 	acpi_walk_namespace(ACPI_TYPE_DEVICE, handle,
 			    ACPI_UINT32_MAX, ioapic_add, NULL, NULL);
 	return 0;
 }
 
+static int acpiphp_unconfigure_ioapics(acpi_handle handle)
+{
+	ioapic_remove(handle, 0, NULL, NULL);
+	acpi_walk_namespace(ACPI_TYPE_DEVICE, handle,
+			    ACPI_UINT32_MAX, ioapic_remove, NULL, NULL);
+	return 0;
+}
+
 static int power_on_slot(struct acpiphp_slot *slot)
 {
 	acpi_status status;
@@ -997,7 +1066,7 @@ static int acpiphp_bus_add(struct acpiphp_func *func)
  * @handle: handle to acpi namespace
  *
  */
-int acpiphp_bus_trim(acpi_handle handle)
+static int acpiphp_bus_trim(acpi_handle handle)
 {
 	struct acpi_device *device;
 	int retval;
@@ -1074,10 +1143,11 @@ static int enable_device(struct acpiphp_slot *slot)
 
 	pci_bus_assign_resources(bus);
 	acpiphp_sanitize_bus(bus);
+	acpiphp_set_hpp_values(slot->bridge->handle, bus);
+	list_for_each_entry(func, &slot->funcs, sibling)
+		acpiphp_configure_ioapics(func->handle);
 	pci_enable_bridges(bus);
 	pci_bus_add_devices(bus);
-	acpiphp_set_hpp_values(slot->bridge->handle, bus);
-	acpiphp_configure_ioapics(slot->bridge->handle);
 
 	/* associate pci_dev to our representation */
 	list_for_each (l, &slot->funcs) {
@@ -1103,6 +1173,16 @@ static int enable_device(struct acpiphp_slot *slot)
 	return retval;
 }
 
+static void disable_bridges(struct pci_bus *bus)
+{
+	struct pci_dev *dev;
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		if (dev->subordinate) {
+			disable_bridges(dev->subordinate);
+			pci_disable_device(dev);
+		}
+	}
+}
 
 /**
  * disable_device - disable a slot
@@ -1127,6 +1207,19 @@ static int disable_device(struct acpiphp_slot *slot)
 			func->bridge = NULL;
 		}
 
+		if (func->pci_dev) {
+			pci_stop_bus_device(func->pci_dev);
+			if (func->pci_dev->subordinate) {
+				disable_bridges(func->pci_dev->subordinate);
+				pci_disable_device(func->pci_dev);
+			}
+		}
+	}
+
+	list_for_each (l, &slot->funcs) {
+		func = list_entry(l, struct acpiphp_func, sibling);
+
+		acpiphp_unconfigure_ioapics(func->handle);
 		acpiphp_bus_trim(func->handle);
 		/* try to remove anyway.
 		 * acpiphp_bus_add might have been failed */

drivers/pci/hotplug/fakephp.c

@@ -176,7 +176,9 @@ static void pci_rescan_slot(struct pci_dev *temp)
 	struct pci_bus *bus = temp->bus;
 	struct pci_dev *dev;
 	int func;
+	int retval;
 	u8 hdr_type;
+
 	if (!pci_read_config_byte(temp, PCI_HEADER_TYPE, &hdr_type)) {
 		temp->hdr_type = hdr_type & 0x7f;
 		if (!pci_find_slot(bus->number, temp->devfn)) {
@@ -185,7 +187,11 @@ static void pci_rescan_slot(struct pci_dev *temp)
 				dbg("New device on %s function %x:%x\n",
 					bus->name, temp->devfn >> 3,
 					temp->devfn & 7);
-				pci_bus_add_device(dev);
+				retval = pci_bus_add_device(dev);
+				if (retval)
+					dev_err(&dev->dev, "error adding "
+						"device, continuing.\n");
+				else
 					add_slot(dev);
 			}
 		}
@@ -205,7 +211,11 @@ static void pci_rescan_slot(struct pci_dev *temp)
 					dbg("New device on %s function %x:%x\n",
 						bus->name, temp->devfn >> 3,
 						temp->devfn & 7);
-					pci_bus_add_device(dev);
+					retval = pci_bus_add_device(dev);
+					if (retval)
+						dev_err(&dev->dev, "error adding "
+							"device, continuing.\n");
+					else
 						add_slot(dev);
 				}
 			}

drivers/pci/hotplug/pci_hotplug.h

@@ -172,7 +172,7 @@ struct hotplug_slot {
 
 extern int pci_hp_register		(struct hotplug_slot *slot);
 extern int pci_hp_deregister		(struct hotplug_slot *slot);
-extern int pci_hp_change_slot_info	(struct hotplug_slot *slot,
+extern int __must_check pci_hp_change_slot_info	(struct hotplug_slot *slot,
 						 struct hotplug_slot_info *info);
 extern struct subsystem pci_hotplug_slots_subsys;
 

drivers/pci/hotplug/pci_hotplug_core.c

@@ -482,31 +482,95 @@ static int has_test_file (struct hotplug_slot *slot)
 
 static int fs_add_slot (struct hotplug_slot *slot)
 {
-	if (has_power_file(slot) == 0)
-		sysfs_create_file(&slot->kobj, &hotplug_slot_attr_power.attr);
+	int retval = 0;
 
-	if (has_attention_file(slot) == 0)
-		sysfs_create_file(&slot->kobj, &hotplug_slot_attr_attention.attr);
+	if (has_power_file(slot) == 0) {
+		retval = sysfs_create_file(&slot->kobj, &hotplug_slot_attr_power.attr);
+		if (retval)
+			goto exit_power;
+	}
 
-	if (has_latch_file(slot) == 0)
-		sysfs_create_file(&slot->kobj, &hotplug_slot_attr_latch.attr);
+	if (has_attention_file(slot) == 0) {
+		retval = sysfs_create_file(&slot->kobj,
+					   &hotplug_slot_attr_attention.attr);
+		if (retval)
+			goto exit_attention;
+	}
 
-	if (has_adapter_file(slot) == 0)
-		sysfs_create_file(&slot->kobj, &hotplug_slot_attr_presence.attr);
+	if (has_latch_file(slot) == 0) {
+		retval = sysfs_create_file(&slot->kobj,
+					   &hotplug_slot_attr_latch.attr);
+		if (retval)
+			goto exit_latch;
+	}
 
-	if (has_address_file(slot) == 0)
-		sysfs_create_file(&slot->kobj, &hotplug_slot_attr_address.attr);
+	if (has_adapter_file(slot) == 0) {
+		retval = sysfs_create_file(&slot->kobj,
+					   &hotplug_slot_attr_presence.attr);
+		if (retval)
+			goto exit_adapter;
+	}
 
-	if (has_max_bus_speed_file(slot) == 0)
-		sysfs_create_file(&slot->kobj, &hotplug_slot_attr_max_bus_speed.attr);
+	if (has_address_file(slot) == 0) {
+		retval = sysfs_create_file(&slot->kobj,
+					   &hotplug_slot_attr_address.attr);
+		if (retval)
+			goto exit_address;
+	}
+
+	if (has_max_bus_speed_file(slot) == 0) {
+		retval = sysfs_create_file(&slot->kobj,
+					   &hotplug_slot_attr_max_bus_speed.attr);
+		if (retval)
+			goto exit_max_speed;
+	}
+
+	if (has_cur_bus_speed_file(slot) == 0) {
+		retval = sysfs_create_file(&slot->kobj,
+					   &hotplug_slot_attr_cur_bus_speed.attr);
+		if (retval)
+			goto exit_cur_speed;
+	}
+
+	if (has_test_file(slot) == 0) {
+		retval = sysfs_create_file(&slot->kobj,
+					   &hotplug_slot_attr_test.attr);
+		if (retval)
+			goto exit_test;
+	}
+
+	goto exit;
 
+exit_test:
 	if (has_cur_bus_speed_file(slot) == 0)
-		sysfs_create_file(&slot->kobj, &hotplug_slot_attr_cur_bus_speed.attr);
+		sysfs_remove_file(&slot->kobj, &hotplug_slot_attr_cur_bus_speed.attr);
 
-	if (has_test_file(slot) == 0)
-		sysfs_create_file(&slot->kobj, &hotplug_slot_attr_test.attr);
+exit_cur_speed:
+	if (has_max_bus_speed_file(slot) == 0)
+		sysfs_remove_file(&slot->kobj, &hotplug_slot_attr_max_bus_speed.attr);
 
-	return 0;
+exit_max_speed:
+	if (has_address_file(slot) == 0)
+		sysfs_remove_file(&slot->kobj, &hotplug_slot_attr_address.attr);
+
+exit_address:
+	if (has_adapter_file(slot) == 0)
+		sysfs_remove_file(&slot->kobj, &hotplug_slot_attr_presence.attr);
+
+exit_adapter:
+	if (has_latch_file(slot) == 0)
+		sysfs_remove_file(&slot->kobj, &hotplug_slot_attr_latch.attr);
+
+exit_latch:
+	if (has_attention_file(slot) == 0)
+		sysfs_remove_file(&slot->kobj, &hotplug_slot_attr_attention.attr);
+
+exit_attention:
+	if (has_power_file(slot) == 0)
+		sysfs_remove_file(&slot->kobj, &hotplug_slot_attr_power.attr);
+exit_power:
+exit:
+	return retval;
 }
 
 static void fs_remove_slot (struct hotplug_slot *slot)
@@ -626,8 +690,11 @@ int pci_hp_deregister (struct hotplug_slot *slot)
  *
  * Returns 0 if successful, anything else for an error.
  */
-int pci_hp_change_slot_info (struct hotplug_slot *slot, struct hotplug_slot_info *info)
+int __must_check pci_hp_change_slot_info(struct hotplug_slot *slot,
+					 struct hotplug_slot_info *info)
 {
+	int retval;
+
 	if ((slot == NULL) || (info == NULL))
 		return -ENODEV;
 
@@ -636,32 +703,60 @@ int pci_hp_change_slot_info (struct hotplug_slot *slot, struct hotplug_slot_info
 	* for the files referring to the fields that have now changed.
 	*/
 	if ((has_power_file(slot) == 0) &&
-	    (slot->info->power_status != info->power_status))
-		sysfs_update_file(&slot->kobj, &hotplug_slot_attr_power.attr);
+	    (slot->info->power_status != info->power_status)) {
+		retval = sysfs_update_file(&slot->kobj,
+					   &hotplug_slot_attr_power.attr);
+		if (retval)
+			return retval;
+	}
 
 	if ((has_attention_file(slot) == 0) &&
-	    (slot->info->attention_status != info->attention_status))
-		sysfs_update_file(&slot->kobj, &hotplug_slot_attr_attention.attr);
+	    (slot->info->attention_status != info->attention_status)) {
+		retval = sysfs_update_file(&slot->kobj,
+					   &hotplug_slot_attr_attention.attr);
+		if (retval)
+			return retval;
+	}
 
 	if ((has_latch_file(slot) == 0) &&
-	    (slot->info->latch_status != info->latch_status))
-		sysfs_update_file(&slot->kobj, &hotplug_slot_attr_latch.attr);
+	    (slot->info->latch_status != info->latch_status)) {
+		retval = sysfs_update_file(&slot->kobj,
+					   &hotplug_slot_attr_latch.attr);
+		if (retval)
+			return retval;
+	}
 
 	if ((has_adapter_file(slot) == 0) &&
-	    (slot->info->adapter_status != info->adapter_status))
-		sysfs_update_file(&slot->kobj, &hotplug_slot_attr_presence.attr);
+	    (slot->info->adapter_status != info->adapter_status)) {
+		retval = sysfs_update_file(&slot->kobj,
+					   &hotplug_slot_attr_presence.attr);
+		if (retval)
+			return retval;
+	}
 
 	if ((has_address_file(slot) == 0) &&
-	    (slot->info->address != info->address))
-		sysfs_update_file(&slot->kobj, &hotplug_slot_attr_address.attr);
+	    (slot->info->address != info->address)) {
+		retval = sysfs_update_file(&slot->kobj,
+					   &hotplug_slot_attr_address.attr);
+		if (retval)
+			return retval;
+	}
 
 	if ((has_max_bus_speed_file(slot) == 0) &&
-	    (slot->info->max_bus_speed != info->max_bus_speed))
-		sysfs_update_file(&slot->kobj, &hotplug_slot_attr_max_bus_speed.attr);
+	    (slot->info->max_bus_speed != info->max_bus_speed)) {
+		retval = sysfs_update_file(&slot->kobj,
+					   &hotplug_slot_attr_max_bus_speed.attr);
+		if (retval)
+			return retval;
+	}
 
 	if ((has_cur_bus_speed_file(slot) == 0) &&
-	    (slot->info->cur_bus_speed != info->cur_bus_speed))
-		sysfs_update_file(&slot->kobj, &hotplug_slot_attr_cur_bus_speed.attr);
+	    (slot->info->cur_bus_speed != info->cur_bus_speed)) {
+		retval = sysfs_update_file(&slot->kobj,
+					   &hotplug_slot_attr_cur_bus_speed.attr);
+		if (retval)
+			return retval;
+	}
 
 	memcpy (slot->info, info, sizeof (struct hotplug_slot_info));
 

drivers/pci/hotplug/pciehp_ctrl.c

@@ -762,14 +762,14 @@ int pciehp_enable_slot(struct slot *p_slot)
 	if (rc || !getstatus) {
 		info("%s: no adapter on slot(%x)\n", __FUNCTION__, p_slot->number);
 		mutex_unlock(&p_slot->ctrl->crit_sect);
-		return 1;
+		return -ENODEV;
 	}
 	if (MRL_SENS(p_slot->ctrl->ctrlcap)) {	
 		rc = p_slot->hpc_ops->get_latch_status(p_slot, &getstatus);
 		if (rc || getstatus) {
 			info("%s: latch open on slot(%x)\n", __FUNCTION__, p_slot->number);
 			mutex_unlock(&p_slot->ctrl->crit_sect);
-			return 1;
+			return -ENODEV;
 		}
 	}
 	
@@ -778,7 +778,7 @@ int pciehp_enable_slot(struct slot *p_slot)
 		if (rc || getstatus) {
 			info("%s: already enabled on slot(%x)\n", __FUNCTION__, p_slot->number);
 			mutex_unlock(&p_slot->ctrl->crit_sect);
-			return 1;
+			return -EINVAL;
 		}
 	}
 	mutex_unlock(&p_slot->ctrl->crit_sect);
@@ -813,7 +813,7 @@ int pciehp_disable_slot(struct slot *p_slot)
 		if (ret || !getstatus) {
 			info("%s: no adapter on slot(%x)\n", __FUNCTION__, p_slot->number);
 			mutex_unlock(&p_slot->ctrl->crit_sect);
-			return 1;
+			return -ENODEV;
 		}
 	}
 
@@ -822,7 +822,7 @@ int pciehp_disable_slot(struct slot *p_slot)
 		if (ret || getstatus) {
 			info("%s: latch open on slot(%x)\n", __FUNCTION__, p_slot->number);
 			mutex_unlock(&p_slot->ctrl->crit_sect);
-			return 1;
+			return -ENODEV;
 		}
 	}
 
@@ -831,7 +831,7 @@ int pciehp_disable_slot(struct slot *p_slot)
 		if (ret || !getstatus) {
 			info("%s: already disabled slot(%x)\n", __FUNCTION__, p_slot->number);
 			mutex_unlock(&p_slot->ctrl->crit_sect);
-			return 1;
+			return -EINVAL;
 		}
 	}
 

drivers/pci/hotplug/pcihp_skeleton.c

 /*
- * PCI Hot Plug Controller Skeleton Driver - 0.2
+ * PCI Hot Plug Controller Skeleton Driver - 0.3
  *
  * Copyright (C) 2001,2003 Greg Kroah-Hartman (greg@kroah.com)
  * Copyright (C) 2001,2003 IBM Corp.
@@ -21,7 +21,7 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  *
- * This driver is to be used as a skeleton driver to be show how to interface
+ * This driver is to be used as a skeleton driver to show how to interface
  * with the pci hotplug core easily.
  *
  * Send feedback to <greg@kroah.com>
@@ -58,8 +58,6 @@ static LIST_HEAD(slot_list);
 #define info(format, arg...) printk(KERN_INFO "%s: " format "\n", MY_NAME , ## arg)
 #define warn(format, arg...) printk(KERN_WARNING "%s: " format "\n", MY_NAME , ## arg)
 
-
-
 /* local variables */
 static int debug;
 static int num_slots;
@@ -109,7 +107,6 @@ static int enable_slot(struct hotplug_slot *hotplug_slot)
 	return retval;
 }
 
-
 static int disable_slot(struct hotplug_slot *hotplug_slot)
 {
 	struct slot *slot = hotplug_slot->private;
@@ -342,7 +339,7 @@ static int __init pcihp_skel_init(void)
 	info(DRIVER_DESC " version: " DRIVER_VERSION "\n");
 	/*
 	 * Do specific initialization stuff for your driver here
-	 * Like initializing your controller hardware (if any) and
+	 * like initializing your controller hardware (if any) and
 	 * determining the number of slots you have in the system
 	 * right now.
 	 */

drivers/pci/hotplug/shpchp.h

@@ -173,7 +173,7 @@ struct controller {
 #define msg_button_cancel	"PCI slot #%s - action canceled due to button press.\n"
 
 /* sysfs functions for the hotplug controller info */
-extern void shpchp_create_ctrl_files	(struct controller *ctrl);
+extern int __must_check shpchp_create_ctrl_files(struct controller *ctrl);
 
 extern int	shpchp_sysfs_enable_slot(struct slot *slot);
 extern int	shpchp_sysfs_disable_slot(struct slot *slot);

drivers/pci/hotplug/shpchp_core.c

@@ -449,10 +449,14 @@ static int shpc_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		ctrl->speed = PCI_SPEED_33MHz;
 	}
 
-	shpchp_create_ctrl_files(ctrl);
+	rc = shpchp_create_ctrl_files(ctrl);
+	if (rc)
+		goto err_cleanup_slots;
 
 	return 0;
 
+err_cleanup_slots:
+	cleanup_slots(ctrl);
 err_out_release_ctlr:
 	ctrl->hpc_ops->release_ctlr(ctrl);
 err_out_free_ctrl:

drivers/pci/hotplug/shpchp_sysfs.c

@@ -91,9 +91,9 @@ static ssize_t show_ctrl (struct device *dev, struct device_attribute *attr, cha
 }
 static DEVICE_ATTR (ctrl, S_IRUGO, show_ctrl, NULL);
 
-void shpchp_create_ctrl_files (struct controller *ctrl)
+int __must_check shpchp_create_ctrl_files (struct controller *ctrl)
 {
-	device_create_file (&ctrl->pci_dev->dev, &dev_attr_ctrl);
+	return device_create_file (&ctrl->pci_dev->dev, &dev_attr_ctrl);
 }
 
 void shpchp_remove_ctrl_files(struct controller *ctrl)

drivers/pci/msi.c

@@ -900,6 +900,33 @@ static int msix_capability_init(struct pci_dev *dev,
 	return 0;
 }
 
+/**
+ * pci_msi_supported - check whether MSI may be enabled on device
+ * @dev: pointer to the pci_dev data structure of MSI device function
+ *
+ * MSI must be globally enabled and supported by the device and its root
+ * bus. But, the root bus is not easy to find since some architectures
+ * have virtual busses on top of the PCI hierarchy (for instance the
+ * hypertransport bus), while the actual bus where MSI must be supported
+ * is below. So we test the MSI flag on all parent busses and assume
+ * that no quirk will ever set the NO_MSI flag on a non-root bus.
+ **/
+static
+int pci_msi_supported(struct pci_dev * dev)
+{
+	struct pci_bus *bus;
+
+	if (!pci_msi_enable || !dev || dev->no_msi)
+		return -EINVAL;
+
+	/* check MSI flags of all parent busses */
+	for (bus = dev->bus; bus; bus = bus->parent)
+		if (bus->bus_flags & PCI_BUS_FLAGS_NO_MSI)
+			return -EINVAL;
+
+	return 0;
+}
+
 /**
  * pci_enable_msi - configure device's MSI capability structure
  * @dev: pointer to the pci_dev data structure of MSI device function
@@ -912,18 +939,10 @@ static int msix_capability_init(struct pci_dev *dev,
  **/
 int pci_enable_msi(struct pci_dev* dev)
 {
-	struct pci_bus *bus;
-	int pos, temp, status = -EINVAL;
+	int pos, temp, status;
 	u16 control;
 
-	if (!pci_msi_enable || !dev)
- 		return status;
-
-	if (dev->no_msi)
-		return status;
-
-	for (bus = dev->bus; bus; bus = bus->parent)
-		if (bus->bus_flags & PCI_BUS_FLAGS_NO_MSI)
+	if (pci_msi_supported(dev) < 0)
 		return -EINVAL;
 
 	temp = dev->irq;
@@ -1134,20 +1153,12 @@ static int reroute_msix_table(int head, struct msix_entry *entries, int *nvec)
  **/
 int pci_enable_msix(struct pci_dev* dev, struct msix_entry *entries, int nvec)
 {
-	struct pci_bus *bus;
 	int status, pos, nr_entries, free_vectors;
 	int i, j, temp;
 	u16 control;
 	unsigned long flags;
 
-	if (!pci_msi_enable || !dev || !entries)
- 		return -EINVAL;
-
-	if (dev->no_msi)
-		return -EINVAL;
-
-	for (bus = dev->bus; bus; bus = bus->parent)
-		if (bus->bus_flags & PCI_BUS_FLAGS_NO_MSI)
+	if (!entries || pci_msi_supported(dev) < 0)
  		return -EINVAL;
 
 	status = msi_init();

drivers/pci/pci-driver.c

@@ -56,6 +56,7 @@ store_new_id(struct device_driver *driver, const char *buf, size_t count)
 		subdevice=PCI_ANY_ID, class=0, class_mask=0;
 	unsigned long driver_data=0;
 	int fields=0;
+	int retval = 0;
 
 	fields = sscanf(buf, "%x %x %x %x %x %x %lux",
 			&vendor, &device, &subvendor, &subdevice,
@@ -82,10 +83,12 @@ store_new_id(struct device_driver *driver, const char *buf, size_t count)
 	spin_unlock(&pdrv->dynids.lock);
 
 	if (get_driver(&pdrv->driver)) {
-		driver_attach(&pdrv->driver);
+		retval = driver_attach(&pdrv->driver);
 		put_driver(&pdrv->driver);
 	}
 
+	if (retval)
+		return retval;
 	return count;
 }
 static DRIVER_ATTR(new_id, S_IWUSR, NULL, store_new_id);
@@ -418,7 +421,11 @@ int __pci_register_driver(struct pci_driver *drv, struct module *owner)
 	drv->driver.bus = &pci_bus_type;
 	drv->driver.owner = owner;
 	drv->driver.kobj.ktype = &pci_driver_kobj_type;
+
+	if (pci_multithread_probe)
 		drv->driver.multithread_probe = pci_multithread_probe;
+	else
+		drv->driver.multithread_probe = drv->multithread_probe;
 
 	spin_lock_init(&drv->dynids.lock);
 	INIT_LIST_HEAD(&drv->dynids.list);

drivers/pci/pci-sysfs.c

@@ -117,6 +117,7 @@ is_enabled_store(struct device *dev, struct device_attribute *attr,
 		const char *buf, size_t count)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
+	int retval = 0;
 
 	/* this can crash the machine when done on the "wrong" device */
 	if (!capable(CAP_SYS_ADMIN))
@@ -126,11 +127,53 @@ is_enabled_store(struct device *dev, struct device_attribute *attr,
 		pci_disable_device(pdev);
 
 	if (*buf == '1')
-		pci_enable_device(pdev);
+		retval = pci_enable_device(pdev);
 
+	if (retval)
+		return retval;
 	return count;
 }
 
+static ssize_t
+msi_bus_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+
+	if (!pdev->subordinate)
+		return 0;
+
+	return sprintf (buf, "%u\n",
+			!(pdev->subordinate->bus_flags & PCI_BUS_FLAGS_NO_MSI));
+}
+
+static ssize_t
+msi_bus_store(struct device *dev, struct device_attribute *attr,
+	      const char *buf, size_t count)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+
+	/* bad things may happen if the no_msi flag is changed
+	 * while some drivers are loaded */
+	if (!capable(CAP_SYS_ADMIN))
+		return count;
+
+	if (!pdev->subordinate)
+		return count;
+
+	if (*buf == '0') {
+		pdev->subordinate->bus_flags |= PCI_BUS_FLAGS_NO_MSI;
+		dev_warn(&pdev->dev, "forced subordinate bus to not support MSI,"
+			 " bad things could happen.\n");
+	}
+
+	if (*buf == '1') {
+		pdev->subordinate->bus_flags &= ~PCI_BUS_FLAGS_NO_MSI;
+		dev_warn(&pdev->dev, "forced subordinate bus to support MSI,"
+			 " bad things could happen.\n");
+	}
+
+	return count;
+}
 
 struct device_attribute pci_dev_attrs[] = {
 	__ATTR_RO(resource),
@@ -145,6 +188,7 @@ struct device_attribute pci_dev_attrs[] = {
 	__ATTR(enable, 0600, is_enabled_show, is_enabled_store),
 	__ATTR(broken_parity_status,(S_IRUGO|S_IWUSR),
 		broken_parity_status_show,broken_parity_status_store),
+	__ATTR(msi_bus, 0644, msi_bus_show, msi_bus_store),
 	__ATTR_NULL,
 };
 
@@ -384,16 +428,39 @@ pci_mmap_resource(struct kobject *kobj, struct bin_attribute *attr,
 	return pci_mmap_page_range(pdev, vma, mmap_type, 0);
 }
 
+/**
+ * pci_remove_resource_files - cleanup resource files
+ * @dev: dev to cleanup
+ *
+ * If we created resource files for @dev, remove them from sysfs and
+ * free their resources.
+ */
+static void
+pci_remove_resource_files(struct pci_dev *pdev)
+{
+	int i;
+
+	for (i = 0; i < PCI_ROM_RESOURCE; i++) {
+		struct bin_attribute *res_attr;
+
+		res_attr = pdev->res_attr[i];
+		if (res_attr) {
+			sysfs_remove_bin_file(&pdev->dev.kobj, res_attr);
+			kfree(res_attr);
+		}
+	}
+}
+
 /**
  * pci_create_resource_files - create resource files in sysfs for @dev
  * @dev: dev in question
  *
  * Walk the resources in @dev creating files for each resource available.
  */
-static void
-pci_create_resource_files(struct pci_dev *pdev)
+static int pci_create_resource_files(struct pci_dev *pdev)
 {
 	int i;
+	int retval;
 
 	/* Expose the PCI resources from this device as files */
 	for (i = 0; i < PCI_ROM_RESOURCE; i++) {
@@ -416,35 +483,19 @@ pci_create_resource_files(struct pci_dev *pdev)
 			res_attr->size = pci_resource_len(pdev, i);
 			res_attr->mmap = pci_mmap_resource;
 			res_attr->private = &pdev->resource[i];
-			sysfs_create_bin_file(&pdev->dev.kobj, res_attr);
-		}
+			retval = sysfs_create_bin_file(&pdev->dev.kobj, res_attr);
+			if (retval) {
+				pci_remove_resource_files(pdev);
+				return retval;
 			}
-}
-
-/**
- * pci_remove_resource_files - cleanup resource files
- * @dev: dev to cleanup
- *
- * If we created resource files for @dev, remove them from sysfs and
- * free their resources.
- */
-static void
-pci_remove_resource_files(struct pci_dev *pdev)
-{
-	int i;
-
-	for (i = 0; i < PCI_ROM_RESOURCE; i++) {
-		struct bin_attribute *res_attr;
-
-		res_attr = pdev->res_attr[i];
-		if (res_attr) {
-			sysfs_remove_bin_file(&pdev->dev.kobj, res_attr);
-			kfree(res_attr);
+		} else {
+			return -ENOMEM;
 		}
 	}
+	return 0;
 }
 #else /* !HAVE_PCI_MMAP */
-static inline void pci_create_resource_files(struct pci_dev *dev) { return; }
+static inline int pci_create_resource_files(struct pci_dev *dev) { return 0; }
 static inline void pci_remove_resource_files(struct pci_dev *dev) { return; }
 #endif /* HAVE_PCI_MMAP */
 
@@ -529,22 +580,27 @@ static struct bin_attribute pcie_config_attr = {
 	.write = pci_write_config,
 };
 
-int pci_create_sysfs_dev_files (struct pci_dev *pdev)
+int __must_check pci_create_sysfs_dev_files (struct pci_dev *pdev)
 {
+	struct bin_attribute *rom_attr = NULL;
+	int retval;
+
 	if (!sysfs_initialized)
 		return -EACCES;
 
 	if (pdev->cfg_size < 4096)
-		sysfs_create_bin_file(&pdev->dev.kobj, &pci_config_attr);
+		retval = sysfs_create_bin_file(&pdev->dev.kobj, &pci_config_attr);
 	else
-		sysfs_create_bin_file(&pdev->dev.kobj, &pcie_config_attr);
+		retval = sysfs_create_bin_file(&pdev->dev.kobj, &pcie_config_attr);
+	if (retval)
+		goto err;
 
-	pci_create_resource_files(pdev);
+	retval = pci_create_resource_files(pdev);
+	if (retval)
+		goto err_bin_file;
 
 	/* If the device has a ROM, try to expose it in sysfs. */
 	if (pci_resource_len(pdev, PCI_ROM_RESOURCE)) {
-		struct bin_attribute *rom_attr;
-		
 		rom_attr = kzalloc(sizeof(*rom_attr), GFP_ATOMIC);
 		if (rom_attr) {
 			pdev->rom_attr = rom_attr;
@@ -554,13 +610,28 @@ int pci_create_sysfs_dev_files (struct pci_dev *pdev)
 			rom_attr->attr.owner = THIS_MODULE;
 			rom_attr->read = pci_read_rom;
 			rom_attr->write = pci_write_rom;
-			sysfs_create_bin_file(&pdev->dev.kobj, rom_attr);
+			retval = sysfs_create_bin_file(&pdev->dev.kobj, rom_attr);
+			if (retval)
+				goto err_rom;
+		} else {
+			retval = -ENOMEM;
+			goto err_bin_file;
 		}
 	}
 	/* add platform-specific attributes */
 	pcibios_add_platform_entries(pdev);
 
 	return 0;
+
+err_rom:
+	kfree(rom_attr);
+err_bin_file:
+	if (pdev->cfg_size < 4096)
+		sysfs_remove_bin_file(&pdev->dev.kobj, &pci_config_attr);
+	else
+		sysfs_remove_bin_file(&pdev->dev.kobj, &pcie_config_attr);
+err:
+	return retval;
 }
 
 /**
@@ -589,10 +660,14 @@ void pci_remove_sysfs_dev_files(struct pci_dev *pdev)
 static int __init pci_sysfs_init(void)
 {
 	struct pci_dev *pdev = NULL;
+	int retval;
 
 	sysfs_initialized = 1;
-	for_each_pci_dev(pdev)
-		pci_create_sysfs_dev_files(pdev);
+	for_each_pci_dev(pdev) {
+		retval = pci_create_sysfs_dev_files(pdev);
+		if (retval)
+			return retval;
+	}
 
 	return 0;
 }

drivers/pci/pci.c

@@ -445,6 +445,51 @@ pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state)
 
 EXPORT_SYMBOL(pci_choose_state);
 
+static int pci_save_pcie_state(struct pci_dev *dev)
+{
+	int pos, i = 0;
+	struct pci_cap_saved_state *save_state;
+	u16 *cap;
+
+	pos = pci_find_capability(dev, PCI_CAP_ID_EXP);
+	if (pos <= 0)
+		return 0;
+
+	save_state = kzalloc(sizeof(*save_state) + sizeof(u16) * 4, GFP_KERNEL);
+	if (!save_state) {
+		dev_err(&dev->dev, "Out of memory in pci_save_pcie_state\n");
+		return -ENOMEM;
+	}
+	cap = (u16 *)&save_state->data[0];
+
+	pci_read_config_word(dev, pos + PCI_EXP_DEVCTL, &cap[i++]);
+	pci_read_config_word(dev, pos + PCI_EXP_LNKCTL, &cap[i++]);
+	pci_read_config_word(dev, pos + PCI_EXP_SLTCTL, &cap[i++]);
+	pci_read_config_word(dev, pos + PCI_EXP_RTCTL, &cap[i++]);
+	pci_add_saved_cap(dev, save_state);
+	return 0;
+}
+
+static void pci_restore_pcie_state(struct pci_dev *dev)
+{
+	int i = 0, pos;
+	struct pci_cap_saved_state *save_state;
+	u16 *cap;
+
+	save_state = pci_find_saved_cap(dev, PCI_CAP_ID_EXP);
+	pos = pci_find_capability(dev, PCI_CAP_ID_EXP);
+	if (!save_state || pos <= 0)
+		return;
+	cap = (u16 *)&save_state->data[0];
+
+	pci_write_config_word(dev, pos + PCI_EXP_DEVCTL, cap[i++]);
+	pci_write_config_word(dev, pos + PCI_EXP_LNKCTL, cap[i++]);
+	pci_write_config_word(dev, pos + PCI_EXP_SLTCTL, cap[i++]);
+	pci_write_config_word(dev, pos + PCI_EXP_RTCTL, cap[i++]);
+	pci_remove_saved_cap(save_state);
+	kfree(save_state);
+}
+
 /**
  * pci_save_state - save the PCI configuration space of a device before suspending
  * @dev: - PCI device that we're dealing with
@@ -460,6 +505,8 @@ pci_save_state(struct pci_dev *dev)
 		return i;
 	if ((i = pci_save_msix_state(dev)) != 0)
 		return i;
+	if ((i = pci_save_pcie_state(dev)) != 0)
+		return i;
 	return 0;
 }
 
@@ -473,6 +520,9 @@ pci_restore_state(struct pci_dev *dev)
 	int i;
 	int val;
 
+	/* PCI Express register must be restored first */
+	pci_restore_pcie_state(dev);
+
 	/*
 	 * The Base Address register should be programmed before the command
 	 * register(s)

drivers/pci/pci.h

@@ -42,7 +42,7 @@ extern void pci_remove_legacy_files(struct pci_bus *bus);
 /* Lock for read/write access to pci device and bus lists */
 extern struct rw_semaphore pci_bus_sem;
 
-#ifdef CONFIG_X86_IO_APIC
+#ifdef CONFIG_PCI_MSI
 extern int pci_msi_quirk;
 #else
 #define pci_msi_quirk 0

drivers/pci/pcie/Kconfig

@@ -34,3 +34,4 @@ config HOTPLUG_PCI_PCIE_POLL_EVENT_MODE
 	   
 	  When in doubt, say N.
 
+source "drivers/pci/pcie/aer/Kconfig"

drivers/pci/pcie/Makefile

@@ -5,3 +5,6 @@
 pcieportdrv-y			:= portdrv_core.o portdrv_pci.o portdrv_bus.o
 
 obj-$(CONFIG_PCIEPORTBUS)	+= pcieportdrv.o
+
+# Build PCI Express AER if needed
+obj-$(CONFIG_PCIEAER)		+= aer/

drivers/pci/pcie/aer/Kconfig

+#
+# PCI Express Root Port Device AER Configuration
+#
+
+config PCIEAER
+	boolean "Root Port Advanced Error Reporting support"
+	depends on PCIEPORTBUS && ACPI
+	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.

drivers/pci/pcie/aer/Makefile

+#
+# Makefile for PCI-Express Root Port Advanced Error Reporting Driver
+#
+
+obj-$(CONFIG_PCIEAER) += aerdriver.o
+
+aerdriver-objs := aerdrv_errprint.o aerdrv_core.o aerdrv.o aerdrv_acpi.o
+

drivers/pci/pcie/aer/aerdrv.c

+/*
+ * 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/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 "aerdrv.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 __devinit aer_probe (struct pcie_device *dev,
+	const struct pcie_port_service_id *id );
+static void aer_remove(struct pcie_device *dev);
+static int aer_suspend(struct pcie_device *dev, pm_message_t state)
+{return 0;}
+static int aer_resume(struct pcie_device *dev) {return 0;}
+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);
+
+/*
+ * PCI Express bus's AER Root service driver data structure
+ */
+static struct pcie_port_service_id aer_id[] = {
+	{
+	.vendor 	= PCI_ANY_ID,
+	.device 	= PCI_ANY_ID,
+	.port_type 	= PCIE_RC_PORT,
+	.service_type 	= PCIE_PORT_SERVICE_AER,
+	},
+	{ /* end: all zeroes */ }
+};
+
+static struct pci_error_handlers aer_error_handlers = {
+	.error_detected = aer_error_detected,
+	.resume = aer_error_resume,
+};
+
+static struct pcie_port_service_driver aerdrv = {
+	.name		= "aer",
+	.id_table	= &aer_id[0],
+
+	.probe		= aer_probe,
+	.remove		= aer_remove,
+
+	.suspend	= aer_suspend,
+	.resume		= aer_resume,
+
+	.err_handler	= &aer_error_handlers,
+
+	.reset_link	= aer_root_reset,
+};
+
+/**
+ * aer_irq - Root Port's ISR
+ * @irq: IRQ assigned to Root Port
+ * @context: pointer to Root Port data structure
+ * @r: pointer struct pt_regs
+ *
+ * Invoked when Root Port detects AER messages.
+ **/
+static irqreturn_t aer_irq(int irq, void *context, struct pt_regs * r)
+{
+	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_aer_capability(pdev->port);
+	/*
+	 * 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 & ROOT_ERR_STATUS_MASKS)) {
+		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_COR_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;
+}
+
+/**
+ * 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;
+
+	if (!(rpc = (struct aer_rpc *)kmalloc(sizeof(struct aer_rpc),
+		GFP_KERNEL)))
+		return NULL;
+
+	memset(rpc, 0, sizeof(struct aer_rpc));
+	/*
+	 * Initialize Root lock access, e_lock, to Root Error Status Reg,
+	 * Root Error ID Reg, and Root error producer/consumer index.
+	 */
+	rpc->e_lock = SPIN_LOCK_UNLOCKED;
+
+	rpc->rpd = dev;
+	INIT_WORK(&rpc->dpc_handler, aer_isr, (void *)dev);
+	rpc->prod_idx = rpc->cons_idx = 0;
+	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_delete_rootport(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 __devinit aer_probe (struct pcie_device *dev,
+				const struct pcie_port_service_id *id )
+{
+	int status;
+	struct aer_rpc *rpc;
+	struct device *device = &dev->device;
+
+	/* Init */
+	if ((status = aer_init(dev)))
+		return status;
+
+	/* Alloc rpc data structure */
+	if (!(rpc = aer_alloc_rpc(dev))) {
+		printk(KERN_DEBUG "%s: Alloc rpc fails on PCIE device[%s]\n",
+			__FUNCTION__, device->bus_id);
+		aer_remove(dev);
+		return -ENOMEM;
+	}
+
+	/* Request IRQ ISR */
+	if ((status = request_irq(dev->irq, aer_irq, SA_SHIRQ, "aerdrv",
+				dev))) {
+		printk(KERN_DEBUG "%s: Request ISR fails on PCIE device[%s]\n",
+			__FUNCTION__, device->bus_id);
+		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)
+{
+	u16 p2p_ctrl;
+	u32 status;
+	int pos;
+
+	pos = pci_find_aer_capability(dev);
+
+	/* Disable Root's interrupt in response to error messages */
+	pci_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, 0);
+
+	/* Assert Secondary Bus Reset */
+	pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &p2p_ctrl);
+	p2p_ctrl |= PCI_CB_BRIDGE_CTL_CB_RESET;
+	pci_write_config_word(dev, PCI_BRIDGE_CONTROL, p2p_ctrl);
+
+	/* De-assert Secondary Bus Reset */
+	p2p_ctrl &= ~PCI_CB_BRIDGE_CTL_CB_RESET;
+	pci_write_config_word(dev, PCI_BRIDGE_CONTROL, p2p_ctrl);
+
+	/*
+	 * System software must wait for at least 100ms from the end
+	 * of a reset of one or more device before it is permitted
+	 * to issue Configuration Requests to those devices.
+	 */
+	msleep(200);
+	printk(KERN_DEBUG "Complete link reset at Root[%s]\n", dev->dev.bus_id);
+
+	/* Enable Root Port's interrupt in response to error messages */
+	pci_read_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, &status);
+	pci_write_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, status);
+	pci_write_config_dword(dev,
+		pos + PCI_ERR_ROOT_COMMAND,
+		ROOT_PORT_INTR_ON_MESG_MASK);
+
+	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 */
+	pos = pci_find_capability(dev, PCI_CAP_ID_EXP);
+	pci_read_config_word(dev, pos + PCI_EXP_DEVSTA, &reg16);
+	pci_write_config_word(dev, pos + PCI_EXP_DEVSTA, reg16);
+
+	/* Clean AER Root Error Status */
+	pos = pci_find_aer_capability(dev);
+	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)
+{
+	return pcie_port_service_register(&aerdrv);
+}
+
+/**
+ * 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(&aerdrv);
+}
+
+module_init(aer_service_init);
+module_exit(aer_service_exit);

drivers/pci/pcie/aer/aerdrv.h

+/*
+ * 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/pcieport_if.h>
+#include <linux/aer.h>
+
+#define AER_NONFATAL			0
+#define AER_FATAL			1
+#define AER_CORRECTABLE			2
+#define AER_UNCORRECTABLE		4
+#define AER_ERROR_MASK			0x001fffff
+#define AER_ERROR(d)			(d & AER_ERROR_MASK)
+
+#define OSC_METHOD_RUN_SUCCESS		0
+#define OSC_METHOD_NOT_SUPPORTED	1
+#define OSC_METHOD_RUN_FAILURE		2
+
+/* Root Error Status Register Bits */
+#define ROOT_ERR_STATUS_MASKS			0x0f
+
+#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_SUCCESS			0
+#define AER_UNSUCCESS			1
+#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)
+
+/* AER Error Info Flags */
+#define AER_TLP_HEADER_VALID_FLAG	0x00000001
+#define AER_MULTI_ERROR_VALID_FLAG	0x00000002
+
+#define ERR_CORRECTABLE_ERROR_MASK	0x000031c1
+#define ERR_UNCORRECTABLE_ERROR_MASK	0x001ff010
+
+struct header_log_regs {
+	unsigned int dw0;
+	unsigned int dw1;
+	unsigned int dw2;
+	unsigned int dw3;
+};
+
+struct aer_err_info {
+	int severity;			/* 0:NONFATAL | 1:FATAL | 2:COR */
+	int flags;
+	unsigned int status;		/* COR/UNCOR Error Status */
+	struct 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 hierachy
+					 */
+	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)
+{
+	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 = new;
+		break;
+	default:
+		break;
+	}
+
+	return orig;
+}
+
+extern struct bus_type pcie_port_bus_type;
+extern void aer_enable_rootport(struct aer_rpc *rpc);
+extern void aer_delete_rootport(struct aer_rpc *rpc);
+extern int aer_init(struct pcie_device *dev);
+extern void aer_isr(void *context);
+extern void aer_print_error(struct pci_dev *dev, struct aer_err_info *info);
+extern int aer_osc_setup(struct pci_dev *dev);
+
+#endif //_AERDRV_H_

drivers/pci/pcie/aer/aerdrv_acpi.c

+/*
+ * 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 "aerdrv.h"
+
+/**
+ * aer_osc_setup - run ACPI _OSC method
+ *
+ * Return:
+ *	Zero if success. Nonzero for otherwise.
+ *
+ * Invoked when PCIE bus loads AER service driver. To avoid conflict with
+ * BIOS AER support requires BIOS to yield AER control to OS native driver.
+ **/
+int aer_osc_setup(struct pci_dev *dev)
+{
+	int retval = OSC_METHOD_RUN_SUCCESS;
+	acpi_status status;
+	acpi_handle handle = DEVICE_ACPI_HANDLE(&dev->dev);
+	struct pci_dev *pdev = dev;
+	struct pci_bus *parent;
+
+	while (!handle) {
+		if (!pdev || !pdev->bus->parent)
+			break;
+		parent = pdev->bus->parent;
+		if (!parent->self)
+			/* Parent must be a host bridge */
+			handle = acpi_get_pci_rootbridge_handle(
+					pci_domain_nr(parent),
+					parent->number);
+		else
+			handle = DEVICE_ACPI_HANDLE(
+					&(parent->self->dev));
+		pdev = parent->self;
+	}
+
+	if (!handle)
+		return OSC_METHOD_NOT_SUPPORTED;
+
+	pci_osc_support_set(OSC_EXT_PCI_CONFIG_SUPPORT);
+	status = pci_osc_control_set(handle, OSC_PCI_EXPRESS_AER_CONTROL |
+		OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL);
+	if (ACPI_FAILURE(status)) {
+		if (status == AE_SUPPORT)
+			retval = OSC_METHOD_NOT_SUPPORTED;
+	 	else
+			retval = OSC_METHOD_RUN_FAILURE;
+	}
+
+	return retval;
+}
+

drivers/pci/pcie/aer/aerdrv_core.c

+/*
+ * 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/acpi.h>
+#include <linux/pci-acpi.h>
+#include <linux/delay.h>
+#include "aerdrv.h"
+
+static int forceload;
+module_param(forceload, bool, 0);
+
+#define PCI_CFG_SPACE_SIZE	(0x100)
+int pci_find_aer_capability(struct pci_dev *dev)
+{
+	int pos;
+	u32 reg32 = 0;
+
+	/* Check if it's a pci-express device */
+	pos = pci_find_capability(dev, PCI_CAP_ID_EXP);
+	if (!pos)
+		return 0;
+
+	/* Check if it supports pci-express AER */
+	pos = PCI_CFG_SPACE_SIZE;
+	while (pos) {
+		if (pci_read_config_dword(dev, pos, &reg32))
+			return 0;
+
+		/* some broken boards return ~0 */
+		if (reg32 == 0xffffffff)
+			return 0;
+
+		if (PCI_EXT_CAP_ID(reg32) == PCI_EXT_CAP_ID_ERR)
+			break;
+
+		pos = reg32 >> 20;
+	}
+
+	return pos;
+}
+
+int pci_enable_pcie_error_reporting(struct pci_dev *dev)
+{
+	u16 reg16 = 0;
+	int pos;
+
+	pos = pci_find_capability(dev, PCI_CAP_ID_EXP);
+	if (!pos)
+		return -EIO;
+
+	pci_read_config_word(dev, pos+PCI_EXP_DEVCTL, &reg16);
+	reg16 = reg16 |
+		PCI_EXP_DEVCTL_CERE |
+		PCI_EXP_DEVCTL_NFERE |
+		PCI_EXP_DEVCTL_FERE |
+		PCI_EXP_DEVCTL_URRE;
+	pci_write_config_word(dev, pos+PCI_EXP_DEVCTL,
+			reg16);
+	return 0;
+}
+
+int pci_disable_pcie_error_reporting(struct pci_dev *dev)
+{
+	u16 reg16 = 0;
+	int pos;
+
+	pos = pci_find_capability(dev, PCI_CAP_ID_EXP);
+	if (!pos)
+		return -EIO;
+
+	pci_read_config_word(dev, pos+PCI_EXP_DEVCTL, &reg16);
+	reg16 = reg16 & ~(PCI_EXP_DEVCTL_CERE |
+			PCI_EXP_DEVCTL_NFERE |
+			PCI_EXP_DEVCTL_FERE |
+			PCI_EXP_DEVCTL_URRE);
+	pci_write_config_word(dev, pos+PCI_EXP_DEVCTL,
+			reg16);
+	return 0;
+}
+
+int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev)
+{
+	int pos;
+	u32 status, mask;
+
+	pos = pci_find_aer_capability(dev);
+	if (!pos)
+		return -EIO;
+
+	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status);
+	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, &mask);
+	if (dev->error_state == pci_channel_io_normal)
+		status &= ~mask; /* Clear corresponding nonfatal bits */
+	else
+		status &= mask; /* Clear corresponding fatal bits */
+	pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, status);
+
+	return 0;
+}
+
+static int find_device_iter(struct device *device, void *data)
+{
+	struct pci_dev *dev;
+	u16 id = *(unsigned long *)data;
+	u8 secondary, subordinate, d_bus = id >> 8;
+
+	if (device->bus == &pci_bus_type) {
+		dev = to_pci_dev(device);
+		if (id == ((dev->bus->number << 8) | dev->devfn)) {
+			/*
+			 * Device ID match
+			 */
+			*(unsigned long*)data = (unsigned long)device;
+			return 1;
+		}
+
+		/*
+		 * If device is P2P, check if it is an upstream?
+		 */
+		if (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE) {
+			pci_read_config_byte(dev, PCI_SECONDARY_BUS,
+				&secondary);
+			pci_read_config_byte(dev, PCI_SUBORDINATE_BUS,
+				&subordinate);
+			if (d_bus >= secondary && d_bus <= subordinate) {
+				*(unsigned long*)data = (unsigned long)device;
+				return 1;
+			}
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * find_source_device - search through device hierarchy for source device
+ * @p_dev: pointer to Root Port pci_dev data structure
+ * @id: device ID of agent who sends an error message to this Root Port
+ *
+ * Invoked when error is detected at the Root Port.
+ **/
+static struct device* find_source_device(struct pci_dev *parent, u16 id)
+{
+	struct pci_dev *dev = parent;
+	struct device *device;
+	unsigned long device_addr;
+	int status;
+
+	/* Is Root Port an agent that sends error message? */
+	if (id == ((dev->bus->number << 8) | dev->devfn))
+		return &dev->dev;
+
+	do {
+		device_addr = id;
+ 		if ((status = device_for_each_child(&dev->dev,
+			&device_addr, find_device_iter))) {
+			device = (struct device*)device_addr;
+			dev = to_pci_dev(device);
+			if (id == ((dev->bus->number << 8) | dev->devfn))
+				return device;
+		}
+ 	}while (status);
+
+	return NULL;
+}
+
+static void report_error_detected(struct pci_dev *dev, void *data)
+{
+	pci_ers_result_t vote;
+	struct pci_error_handlers *err_handler;
+	struct aer_broadcast_data *result_data;
+	result_data = (struct aer_broadcast_data *) data;
+
+	dev->error_state = result_data->state;
+
+	if (!dev->driver ||
+		!dev->driver->err_handler ||
+		!dev->driver->err_handler->error_detected) {
+		if (result_data->state == pci_channel_io_frozen &&
+			!(dev->hdr_type & PCI_HEADER_TYPE_BRIDGE)) {
+			/*
+			 * In case of fatal recovery, if one of down-
+			 * stream device has no driver. We might be
+			 * unable to recover because a later insmod
+			 * of a driver for this device is unaware of
+			 * its hw state.
+			 */
+			printk(KERN_DEBUG "Device ID[%s] has %s\n",
+					dev->dev.bus_id, (dev->driver) ?
+					"no AER-aware driver" : "no driver");
+		}
+		return;
+	}
+
+	err_handler = dev->driver->err_handler;
+	vote = err_handler->error_detected(dev, result_data->state);
+	result_data->result = merge_result(result_data->result, vote);
+	return;
+}
+
+static void report_mmio_enabled(struct pci_dev *dev, void *data)
+{
+	pci_ers_result_t vote;
+	struct pci_error_handlers *err_handler;
+	struct aer_broadcast_data *result_data;
+	result_data = (struct aer_broadcast_data *) data;
+
+	if (!dev->driver ||
+		!dev->driver->err_handler ||
+		!dev->driver->err_handler->mmio_enabled)
+		return;
+
+	err_handler = dev->driver->err_handler;
+	vote = err_handler->mmio_enabled(dev);
+	result_data->result = merge_result(result_data->result, vote);
+	return;
+}
+
+static void report_slot_reset(struct pci_dev *dev, void *data)
+{
+	pci_ers_result_t vote;
+	struct pci_error_handlers *err_handler;
+	struct aer_broadcast_data *result_data;
+	result_data = (struct aer_broadcast_data *) data;
+
+	if (!dev->driver ||
+		!dev->driver->err_handler ||
+		!dev->driver->err_handler->slot_reset)
+		return;
+
+	err_handler = dev->driver->err_handler;
+	vote = err_handler->slot_reset(dev);
+	result_data->result = merge_result(result_data->result, vote);
+	return;
+}
+
+static void report_resume(struct pci_dev *dev, void *data)
+{
+	struct pci_error_handlers *err_handler;
+
+	dev->error_state = pci_channel_io_normal;
+
+	if (!dev->driver ||
+		!dev->driver->err_handler ||
+		!dev->driver->err_handler->slot_reset)
+		return;
+
+	err_handler = dev->driver->err_handler;
+	err_handler->resume(dev);
+	return;
+}
+
+/**
+ * broadcast_error_message - handle message broadcast to downstream drivers
+ * @device: pointer to from where in a hierarchy message is broadcasted down
+ * @api: callback to be broadcasted
+ * @state: error state
+ *
+ * Invoked during error recovery process. Once being invoked, the content
+ * of error severity will be broadcasted to all downstream drivers in a
+ * hierarchy in question.
+ **/
+static pci_ers_result_t broadcast_error_message(struct pci_dev *dev,
+	enum pci_channel_state state,
+	char *error_mesg,
+	void (*cb)(struct pci_dev *, void *))
+{
+	struct aer_broadcast_data result_data;
+
+	printk(KERN_DEBUG "Broadcast %s message\n", error_mesg);
+	result_data.state = state;
+	if (cb == report_error_detected)
+		result_data.result = PCI_ERS_RESULT_CAN_RECOVER;
+	else
+		result_data.result = PCI_ERS_RESULT_RECOVERED;
+
+	if (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE) {
+		/*
+		 * If the error is reported by a bridge, we think this error
+		 * is related to the downstream link of the bridge, so we
+		 * do error recovery on all subordinates of the bridge instead
+		 * of the bridge and clear the error status of the bridge.
+		 */
+		if (cb == report_error_detected)
+			dev->error_state = state;
+		pci_walk_bus(dev->subordinate, cb, &result_data);
+		if (cb == report_resume) {
+			pci_cleanup_aer_uncorrect_error_status(dev);
+			dev->error_state = pci_channel_io_normal;
+		}
+	}
+	else {
+		/*
+		 * If the error is reported by an end point, we think this
+		 * error is related to the upstream link of the end point.
+		 */
+		pci_walk_bus(dev->bus, cb, &result_data);
+	}
+
+	return result_data.result;
+}
+
+struct find_aer_service_data {
+	struct pcie_port_service_driver *aer_driver;
+	int is_downstream;
+};
+
+static int find_aer_service_iter(struct device *device, void *data)
+{
+	struct device_driver *driver;
+	struct pcie_port_service_driver *service_driver;
+	struct pcie_device *pcie_dev;
+	struct find_aer_service_data *result;
+
+	result = (struct find_aer_service_data *) data;
+
+	if (device->bus == &pcie_port_bus_type) {
+		pcie_dev = to_pcie_device(device);
+		if (pcie_dev->id.port_type == PCIE_SW_DOWNSTREAM_PORT)
+			result->is_downstream = 1;
+
+		driver = device->driver;
+		if (driver) {
+			service_driver = to_service_driver(driver);
+			if (service_driver->id_table->service_type ==
+					PCIE_PORT_SERVICE_AER) {
+				result->aer_driver = service_driver;
+				return 1;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static void find_aer_service(struct pci_dev *dev,
+		struct find_aer_service_data *data)
+{
+	int retval;
+	retval = device_for_each_child(&dev->dev, data, find_aer_service_iter);
+}
+
+static pci_ers_result_t reset_link(struct pcie_device *aerdev,
+		struct pci_dev *dev)
+{
+	struct pci_dev *udev;
+	pci_ers_result_t status;
+	struct find_aer_service_data data;
+
+	if (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE)
+		udev = dev;
+	else
+		udev= dev->bus->self;
+
+	data.is_downstream = 0;
+	data.aer_driver = NULL;
+	find_aer_service(udev, &data);
+
+	/*
+	 * Use the aer driver of the error agent firstly.
+	 * If it hasn't the aer driver, use the root port's
+	 */
+	if (!data.aer_driver || !data.aer_driver->reset_link) {
+		if (data.is_downstream &&
+			aerdev->device.driver &&
+			to_service_driver(aerdev->device.driver)->reset_link) {
+			data.aer_driver =
+				to_service_driver(aerdev->device.driver);
+		} else {
+			printk(KERN_DEBUG "No link-reset support to Device ID"
+				"[%s]\n",
+				dev->dev.bus_id);
+			return PCI_ERS_RESULT_DISCONNECT;
+		}
+	}
+
+	status = data.aer_driver->reset_link(udev);
+	if (status != PCI_ERS_RESULT_RECOVERED) {
+		printk(KERN_DEBUG "Link reset at upstream Device ID"
+			"[%s] failed\n",
+			udev->dev.bus_id);
+		return PCI_ERS_RESULT_DISCONNECT;
+	}
+
+	return status;
+}
+
+/**
+ * do_recovery - handle nonfatal/fatal error recovery process
+ * @aerdev: pointer to a pcie_device data structure of root port
+ * @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 pci_ers_result_t do_recovery(struct pcie_device *aerdev,
+		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(aerdev, dev);
+		if (result != PCI_ERS_RESULT_RECOVERED) {
+			/* TODO: Should panic here? */
+			return result;
+		}
+	}
+
+	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)
+		broadcast_error_message(dev,
+				state,
+				"resume",
+				report_resume);
+
+	return status;
+}
+
+/**
+ * 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)
+{
+	pci_ers_result_t status = 0;
+	int pos;
+
+	if (info.severity == AER_CORRECTABLE) {
+		/*
+		 * Correctable error does not need software intevention.
+		 * No need to go through error recovery process.
+		 */
+		pos = pci_find_aer_capability(dev);
+		if (pos)
+			pci_write_config_dword(dev, pos + PCI_ERR_COR_STATUS,
+					info.status);
+	} else {
+		status = do_recovery(aerdev, dev, info.severity);
+		if (status == PCI_ERS_RESULT_RECOVERED) {
+			printk(KERN_DEBUG "AER driver successfully recovered\n");
+		} else {
+			/* TODO: Should kernel panic here? */
+			printk(KERN_DEBUG "AER driver didn't recover\n");
+		}
+	}
+}
+
+/**
+ * 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.
+ **/
+void aer_enable_rootport(struct aer_rpc *rpc)
+{
+	struct pci_dev *pdev = rpc->rpd->port;
+	int pos, aer_pos;
+	u16 reg16;
+	u32 reg32;
+
+	pos = pci_find_capability(pdev, PCI_CAP_ID_EXP);
+	/* Clear PCIE Capability's Device Status */
+	pci_read_config_word(pdev, pos+PCI_EXP_DEVSTA, &reg16);
+	pci_write_config_word(pdev, pos+PCI_EXP_DEVSTA, reg16);
+
+	/* Disable system error generation in response to error messages */
+	pci_read_config_word(pdev, pos + PCI_EXP_RTCTL, &reg16);
+	reg16 &= ~(SYSTEM_ERROR_INTR_ON_MESG_MASK);
+	pci_write_config_word(pdev, pos + PCI_EXP_RTCTL, reg16);
+
+	aer_pos = pci_find_aer_capability(pdev);
+	/* 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 Root Port device reporting error itself */
+	pci_read_config_word(pdev, pos+PCI_EXP_DEVCTL, &reg16);
+	reg16 = reg16 |
+		PCI_EXP_DEVCTL_CERE |
+		PCI_EXP_DEVCTL_NFERE |
+		PCI_EXP_DEVCTL_FERE |
+		PCI_EXP_DEVCTL_URRE;
+	pci_write_config_word(pdev, pos+PCI_EXP_DEVCTL,
+		reg16);
+
+	/* Enable Root Port's interrupt in response to error messages */
+	pci_write_config_dword(pdev,
+		aer_pos + PCI_ERR_ROOT_COMMAND,
+		ROOT_PORT_INTR_ON_MESG_MASK);
+}
+
+/**
+ * disable_root_aer - 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 disable_root_aer(struct aer_rpc *rpc)
+{
+	struct pci_dev *pdev = rpc->rpd->port;
+	u32 reg32;
+	int pos;
+
+	pos = pci_find_aer_capability(pdev);
+	/* Disable Root's interrupt in response to error messages */
+	pci_write_config_dword(pdev, pos + PCI_ERR_ROOT_COMMAND, 0);
+
+	/* 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);
+}
+
+/**
+ * get_e_source - retrieve an error source
+ * @rpc: pointer to the root port which holds an error
+ *
+ * Invoked by DPC handler to consume an error.
+ **/
+static struct aer_err_source* get_e_source(struct aer_rpc *rpc)
+{
+	struct aer_err_source *e_source;
+	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 NULL;
+	}
+	e_source = &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 e_source;
+}
+
+static int get_device_error_info(struct pci_dev *dev, struct aer_err_info *info)
+{
+	int pos;
+
+	pos = pci_find_aer_capability(dev);
+
+	/* The device might not support AER */
+	if (!pos)
+		return AER_SUCCESS;
+
+	if (info->severity == AER_CORRECTABLE) {
+		pci_read_config_dword(dev, pos + PCI_ERR_COR_STATUS,
+			&info->status);
+		if (!(info->status & ERR_CORRECTABLE_ERROR_MASK))
+			return AER_UNSUCCESS;
+	} 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);
+		if (!(info->status & ERR_UNCORRECTABLE_ERROR_MASK))
+			return AER_UNSUCCESS;
+
+		if (info->status & AER_LOG_TLP_MASKS) {
+			info->flags |= AER_TLP_HEADER_VALID_FLAG;
+			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 AER_SUCCESS;
+}
+
+/**
+ * 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 device *s_device;
+	struct aer_err_info e_info = {0, 0, 0,};
+	int i;
+	u16 id;
+
+	/*
+	 * There is a possibility that both correctable error and
+	 * uncorrectable error being logged. Report correctable error first.
+	 */
+	for (i = 1; i & ROOT_ERR_STATUS_MASKS ; i <<= 2) {
+		if (i > 4)
+			break;
+		if (!(e_src->status & i))
+			continue;
+
+		/* Init comprehensive error information */
+		if (i & PCI_ERR_ROOT_COR_RCV) {
+			id = ERR_COR_ID(e_src->id);
+			e_info.severity = AER_CORRECTABLE;
+		} else {
+			id = ERR_UNCOR_ID(e_src->id);
+			e_info.severity = ((e_src->status >> 6) & 1);
+		}
+		if (e_src->status &
+			(PCI_ERR_ROOT_MULTI_COR_RCV |
+			 PCI_ERR_ROOT_MULTI_UNCOR_RCV))
+			e_info.flags |= AER_MULTI_ERROR_VALID_FLAG;
+		if (!(s_device = find_source_device(p_device->port, id))) {
+			printk(KERN_DEBUG "%s->can't find device of ID%04x\n",
+				__FUNCTION__, id);
+			continue;
+		}
+		if (get_device_error_info(to_pci_dev(s_device), &e_info) ==
+				AER_SUCCESS) {
+			aer_print_error(to_pci_dev(s_device), &e_info);
+			handle_error_source(p_device,
+				to_pci_dev(s_device),
+				e_info);
+		}
+	}
+}
+
+/**
+ * aer_isr - consume errors detected by root port
+ * @context: pointer to a private data of pcie device
+ *
+ * Invoked, as DPC, when root port records new detected error
+ **/
+void aer_isr(void *context)
+{
+	struct pcie_device *p_device = (struct pcie_device *) context;
+	struct aer_rpc *rpc = get_service_data(p_device);
+	struct aer_err_source *e_src;
+
+	mutex_lock(&rpc->rpc_mutex);
+	e_src = get_e_source(rpc);
+	while (e_src) {
+		aer_isr_one_error(p_device, e_src);
+		e_src = get_e_source(rpc);
+	}
+	mutex_unlock(&rpc->rpc_mutex);
+
+	wake_up(&rpc->wait_release);
+}
+
+/**
+ * aer_delete_rootport - disable root port aer and delete service data
+ * @rpc: pointer to a root port device being deleted
+ *
+ * Invoked when AER service unloaded on a specific Root Port
+ **/
+void aer_delete_rootport(struct aer_rpc *rpc)
+{
+	/* Disable root port AER itself */
+	disable_root_aer(rpc);
+
+	kfree(rpc);
+}
+
+/**
+ * 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)
+{
+	int status;
+
+	/* Run _OSC Method */
+	status = aer_osc_setup(dev->port);
+
+	if(status != OSC_METHOD_RUN_SUCCESS) {
+		printk(KERN_DEBUG "%s: AER service init fails - %s\n",
+		__FUNCTION__,
+		(status == OSC_METHOD_NOT_SUPPORTED) ?
+			"No ACPI _OSC support" : "Run ACPI _OSC fails");
+
+		if (!forceload)
+			return status;
+	}
+
+	return AER_SUCCESS;
+}
+
+EXPORT_SYMBOL_GPL(pci_find_aer_capability);
+EXPORT_SYMBOL_GPL(pci_enable_pcie_error_reporting);
+EXPORT_SYMBOL_GPL(pci_disable_pcie_error_reporting);
+EXPORT_SYMBOL_GPL(pci_cleanup_aer_uncorrect_error_status);
+

drivers/pci/pcie/aer/aerdrv_errprint.c

+/*
+ * 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 "aerdrv.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	(PCI_ERR_UNC_COMP_TIME|	\
+					PCI_ERR_UNC_UNSUP)
+
+#define AER_AGENT_COMPLETER_MASK	PCI_ERR_UNC_COMP_ABORT
+
+#define AER_AGENT_TRANSMITTER_MASK(t, e) (e & (PCI_ERR_COR_REP_ROLL| \
+	((t == AER_CORRECTABLE) ? PCI_ERR_COR_REP_TIMER: 0)))
+
+#define AER_GET_AGENT(t, e)						\
+	((e & AER_AGENT_COMPLETER_MASK) ? AER_AGENT_COMPLETER :		\
+	(e & AER_AGENT_REQUESTER_MASK) ? AER_AGENT_REQUESTER :		\
+	(AER_AGENT_TRANSMITTER_MASK(t, e)) ? AER_AGENT_TRANSMITTER :	\
+	AER_AGENT_RECEIVER)
+
+#define AER_PHYSICAL_LAYER_ERROR_MASK	PCI_ERR_COR_RCVR
+#define AER_DATA_LINK_LAYER_ERROR_MASK(t, e)	\
+		(PCI_ERR_UNC_DLP|		\
+		PCI_ERR_COR_BAD_TLP| 		\
+		PCI_ERR_COR_BAD_DLLP|		\
+		PCI_ERR_COR_REP_ROLL| 		\
+		((t == AER_CORRECTABLE) ?	\
+		PCI_ERR_COR_REP_TIMER: 0))
+
+#define AER_PHYSICAL_LAYER_ERROR	0
+#define AER_DATA_LINK_LAYER_ERROR	1
+#define AER_TRANSACTION_LAYER_ERROR	2
+
+#define AER_GET_LAYER_ERROR(t, e)				\
+	((e & AER_PHYSICAL_LAYER_ERROR_MASK) ?			\
+	AER_PHYSICAL_LAYER_ERROR :				\
+	(e & AER_DATA_LINK_LAYER_ERROR_MASK(t, e)) ?		\
+		AER_DATA_LINK_LAYER_ERROR : 			\
+		AER_TRANSACTION_LAYER_ERROR)
+
+/*
+ * AER error strings
+ */
+static char* aer_error_severity_string[] = {
+	"Uncorrected (Non-Fatal)",
+	"Uncorrected (Fatal)",
+	"Corrected"
+};
+
+static char* aer_error_layer[] = {
+	"Physical Layer",
+	"Data Link Layer",
+	"Transaction Layer"
+};
+static 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	*/
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+};
+
+static char* aer_uncorrectable_error_string[] = {
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	"Data Link Protocol    ",	/* Bit Position 4	*/
+	NULL,
+	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	*/
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+};
+
+static char* aer_agent_string[] = {
+	"Receiver ID",
+	"Requester ID",
+	"Completer ID",
+	"Transmitter ID"
+};
+
+static char * aer_get_error_source_name(int severity,
+			unsigned int status,
+			char errmsg_buff[])
+{
+	int i;
+	char * errmsg = NULL;
+
+	for (i = 0; i < 32; i++) {
+		if (!(status & (1 << i)))
+			continue;
+
+		if (severity == AER_CORRECTABLE)
+			errmsg = aer_correctable_error_string[i];
+		else
+			errmsg = aer_uncorrectable_error_string[i];
+
+		if (!errmsg) {
+			sprintf(errmsg_buff, "Unknown Error Bit %2d  ", i);
+			errmsg = errmsg_buff;
+		}
+
+		break;
+	}
+
+	return errmsg;
+}
+
+static DEFINE_SPINLOCK(logbuf_lock);
+static char errmsg_buff[100];
+void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
+{
+	char * errmsg;
+	int err_layer, agent;
+	char * loglevel;
+
+	if (info->severity == AER_CORRECTABLE)
+		loglevel = KERN_WARNING;
+	else
+		loglevel = KERN_ERR;
+
+	printk("%s+------ PCI-Express Device Error ------+\n", loglevel);
+	printk("%sError Severity\t\t: %s\n", loglevel,
+		aer_error_severity_string[info->severity]);
+
+	if ( info->status == 0) {
+		printk("%sPCIE Bus Error type\t: (Unaccessible)\n", loglevel);
+		printk("%sUnaccessible Received\t: %s\n", loglevel,
+			info->flags & AER_MULTI_ERROR_VALID_FLAG ?
+				"Multiple" : "First");
+		printk("%sUnregistered Agent ID\t: %04x\n", loglevel,
+			(dev->bus->number << 8) | dev->devfn);
+	} else {
+		err_layer = AER_GET_LAYER_ERROR(info->severity, info->status);
+		printk("%sPCIE Bus Error type\t: %s\n", loglevel,
+			aer_error_layer[err_layer]);
+
+		spin_lock(&logbuf_lock);
+		errmsg = aer_get_error_source_name(info->severity,
+				info->status,
+				errmsg_buff);
+		printk("%s%s\t: %s\n", loglevel, errmsg,
+			info->flags & AER_MULTI_ERROR_VALID_FLAG ?
+				"Multiple" : "First");
+		spin_unlock(&logbuf_lock);
+
+		agent = AER_GET_AGENT(info->severity, info->status);
+		printk("%s%s\t\t: %04x\n", loglevel,
+			aer_agent_string[agent],
+			(dev->bus->number << 8) | dev->devfn);
+
+		printk("%sVendorID=%04xh, DeviceID=%04xh,"
+			" Bus=%02xh, Device=%02xh, Function=%02xh\n",
+			loglevel,
+			dev->vendor,
+			dev->device,
+			dev->bus->number,
+			PCI_SLOT(dev->devfn),
+			PCI_FUNC(dev->devfn));
+
+		if (info->flags & AER_TLP_HEADER_VALID_FLAG) {
+			unsigned char *tlp = (unsigned char *) &info->tlp;
+			printk("%sTLB Header:\n", loglevel);
+			printk("%s%02x%02x%02x%02x %02x%02x%02x%02x"
+				" %02x%02x%02x%02x %02x%02x%02x%02x\n",
+				loglevel,
+				*(tlp + 3), *(tlp + 2), *(tlp + 1), *tlp,
+				*(tlp + 7), *(tlp + 6), *(tlp + 5), *(tlp + 4),
+				*(tlp + 11), *(tlp + 10), *(tlp + 9),
+				*(tlp + 8), *(tlp + 15), *(tlp + 14),
+				*(tlp + 13), *(tlp + 12));
+		}
+	}
+}
+

drivers/pci/pcie/portdrv.h

@@ -39,7 +39,7 @@ extern int pcie_port_device_suspend(struct pci_dev *dev, pm_message_t state);
 extern int pcie_port_device_resume(struct pci_dev *dev);
 #endif
 extern void pcie_port_device_remove(struct pci_dev *dev);
-extern void pcie_port_bus_register(void);
+extern int pcie_port_bus_register(void);
 extern void pcie_port_bus_unregister(void);
 
 #endif /* _PORTDRV_H_ */

drivers/pci/pcie/portdrv_bus.c

@@ -24,6 +24,7 @@ struct bus_type pcie_port_bus_type = {
 	.suspend	= pcie_port_bus_suspend,
 	.resume		= pcie_port_bus_resume, 
 };
+EXPORT_SYMBOL_GPL(pcie_port_bus_type);
 
 static int pcie_port_bus_match(struct device *dev, struct device_driver *drv)
 {

drivers/pci/pcie/portdrv_core.c

@@ -6,6 +6,7 @@
  * Copyright (C) Tom Long Nguyen (tom.l.nguyen@intel.com)
  */
 
+#include <linux/compiler.h>
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/kernel.h>
@@ -339,8 +340,7 @@ static int suspend_iter(struct device *dev, void *data)
 
 int pcie_port_device_suspend(struct pci_dev *dev, pm_message_t state)
 {
-	device_for_each_child(&dev->dev, &state, suspend_iter);
-	return 0;
+	return device_for_each_child(&dev->dev, &state, suspend_iter);
 }
 
 static int resume_iter(struct device *dev, void *data)
@@ -358,8 +358,7 @@ static int resume_iter(struct device *dev, void *data)
 
 int pcie_port_device_resume(struct pci_dev *dev)
 {
-	device_for_each_child(&dev->dev, NULL, resume_iter);
-	return 0;
+	return device_for_each_child(&dev->dev, NULL, resume_iter);
 }
 #endif
 
@@ -402,9 +401,9 @@ void pcie_port_device_remove(struct pci_dev *dev)
 		pci_disable_msi(dev);
 }
 
-void pcie_port_bus_register(void)
+int __must_check pcie_port_bus_register(void)
 {
-	bus_register(&pcie_port_bus_type);
+	return bus_register(&pcie_port_bus_type);
 }
 
 void pcie_port_bus_unregister(void)

drivers/pci/pcie/portdrv_pci.c

@@ -14,8 +14,10 @@
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/pcieport_if.h>
+#include <linux/aer.h>
 
 #include "portdrv.h"
+#include "aer/aerdrv.h"
 
 /*
  * Version Information
@@ -30,6 +32,43 @@ MODULE_LICENSE("GPL");
 /* global data */
 static const char device_name[] = "pcieport-driver";
 
+static int pcie_portdrv_save_config(struct pci_dev *dev)
+{
+	return pci_save_state(dev);
+}
+
+#ifdef CONFIG_PM
+static int pcie_portdrv_restore_config(struct pci_dev *dev)
+{
+	int retval;
+
+	pci_restore_state(dev);
+	retval = pci_enable_device(dev);
+	if (retval)
+		return retval;
+	pci_set_master(dev);
+	return 0;
+}
+
+static int pcie_portdrv_suspend(struct pci_dev *dev, pm_message_t state)
+{
+	int ret = pcie_port_device_suspend(dev, state);
+
+	if (!ret)
+		ret = pcie_portdrv_save_config(dev);
+	return ret;
+}
+
+static int pcie_portdrv_resume(struct pci_dev *dev)
+{
+	pcie_portdrv_restore_config(dev);
+	return pcie_port_device_resume(dev);
+}
+#else
+#define pcie_portdrv_suspend NULL
+#define pcie_portdrv_resume NULL
+#endif
+
 /*
  * pcie_portdrv_probe - Probe PCI-Express port devices
  * @dev: PCI-Express port device being probed
@@ -61,6 +100,10 @@ static int __devinit pcie_portdrv_probe (struct pci_dev *dev,
 		return -ENOMEM;
 	}
 
+	pcie_portdrv_save_config(dev);
+
+	pci_enable_pcie_error_reporting(dev);
+
 	return 0;
 }
 
@@ -70,39 +113,151 @@ static void pcie_portdrv_remove (struct pci_dev *dev)
 	kfree(pci_get_drvdata(dev));
 }
 
-#ifdef CONFIG_PM
-static int pcie_portdrv_save_config(struct pci_dev *dev)
+static int error_detected_iter(struct device *device, void *data)
 {
-	return pci_save_state(dev);
+	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 int pcie_portdrv_restore_config(struct pci_dev *dev)
+static pci_ers_result_t pcie_portdrv_error_detected(struct pci_dev *dev,
+					enum pci_channel_state error)
 {
+	struct aer_broadcast_data result_data =
+			{error, PCI_ERS_RESULT_CAN_RECOVER};
 	int retval;
 
-	pci_restore_state(dev);
-	retval = pci_enable_device(dev);
-	if (retval)
-		return retval;
-	pci_set_master(dev);
+	/* can not fail */
+	retval = device_for_each_child(&dev->dev, &result_data, error_detected_iter);
+
+	return result_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 int pcie_portdrv_suspend (struct pci_dev *dev, pm_message_t state)
+static pci_ers_result_t pcie_portdrv_mmio_enabled(struct pci_dev *dev)
 {
-	int ret = pcie_port_device_suspend(dev, state);
+	pci_ers_result_t status = PCI_ERS_RESULT_RECOVERED;
+	int retval;
 
-	if (!ret)
-		ret = pcie_portdrv_save_config(dev);
-	return ret;
+	/* get true return value from &status */
+	retval = device_for_each_child(&dev->dev, &status, mmio_enabled_iter);
+	return status;
 }
 
-static int pcie_portdrv_resume (struct pci_dev *dev)
+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;
+	int retval;
+
+	/* If fatal, restore cfg space for possible link reset at upstream */
+	if (dev->error_state == pci_channel_io_frozen) {
 		pcie_portdrv_restore_config(dev);
-	return pcie_port_device_resume(dev);
+		pci_enable_pcie_error_reporting(dev);
+	}
+
+	/* get true return value from &status */
+	retval = 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)
+{
+	int retval;
+	/* nothing to do with error value, if it ever happens */
+	retval = device_for_each_child(&dev->dev, NULL, resume_iter);
 }
-#endif
 
 /*
  * LINUX Device Driver Model
@@ -114,6 +269,13 @@ static const struct pci_device_id port_pci_ids[] = { {
 };
 MODULE_DEVICE_TABLE(pci, port_pci_ids);
 
+static 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_portdrv = {
 	.name		= (char *)device_name,
 	.id_table	= &port_pci_ids[0],
@@ -121,20 +283,25 @@ static struct pci_driver pcie_portdrv = {
 	.probe		= pcie_portdrv_probe,
 	.remove		= pcie_portdrv_remove,
 
-#ifdef	CONFIG_PM
 	.suspend	= pcie_portdrv_suspend,
 	.resume		= pcie_portdrv_resume,
-#endif	/* PM */
+
+	.err_handler 	= &pcie_portdrv_err_handler,
 };
 
 static int __init pcie_portdrv_init(void)
 {
-	int retval = 0;
+	int retval;
 
-	pcie_port_bus_register();
+	retval = pcie_port_bus_register();
+	if (retval) {
+		printk(KERN_WARNING "PCIE: bus_register error: %d\n", retval);
+		goto out;
+	}
 	retval = pci_register_driver(&pcie_portdrv);
 	if (retval)
 		pcie_port_bus_unregister();
+ out:
 	return retval;
 }
 

drivers/pci/probe.c

@@ -339,6 +339,7 @@ pci_alloc_child_bus(struct pci_bus *parent, struct pci_dev *bridge, int busnr)
 {
 	struct pci_bus *child;
 	int i;
+	int retval;
 
 	/*
 	 * Allocate a new bus, and inherit stuff from the parent..
@@ -356,8 +357,13 @@ pci_alloc_child_bus(struct pci_bus *parent, struct pci_dev *bridge, int busnr)
 
 	child->class_dev.class = &pcibus_class;
 	sprintf(child->class_dev.class_id, "%04x:%02x", pci_domain_nr(child), busnr);
-	class_device_register(&child->class_dev);
-	class_device_create_file(&child->class_dev, &class_device_attr_cpuaffinity);
+	retval = class_device_register(&child->class_dev);
+	if (retval)
+		goto error_register;
+	retval = class_device_create_file(&child->class_dev,
+					  &class_device_attr_cpuaffinity);
+	if (retval)
+		goto error_file_create;
 
 	/*
 	 * Set up the primary, secondary and subordinate
@@ -375,6 +381,12 @@ pci_alloc_child_bus(struct pci_bus *parent, struct pci_dev *bridge, int busnr)
 	bridge->subordinate = child;
 
 	return child;
+
+error_file_create:
+	class_device_unregister(&child->class_dev);
+error_register:
+	kfree(child);
+	return NULL;
 }
 
 struct pci_bus * __devinit pci_add_new_bus(struct pci_bus *parent, struct pci_dev *dev, int busnr)

drivers/pci/quirks.c

@@ -577,8 +577,6 @@ static void __init quirk_ioapic_rmw(struct pci_dev *dev)
 }
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SI,	PCI_ANY_ID,			quirk_ioapic_rmw );
 
-int pci_msi_quirk;
-
 #define AMD8131_revA0        0x01
 #define AMD8131_revB0        0x11
 #define AMD8131_MISC         0x40
@@ -587,12 +585,6 @@ static void __init quirk_amd_8131_ioapic(struct pci_dev *dev)
 { 
         unsigned char revid, tmp;
         
-	if (dev->subordinate) {
-		printk(KERN_WARNING "PCI: MSI quirk detected. "
-		       "PCI_BUS_FLAGS_NO_MSI set for subordinate bus.\n");
-		dev->subordinate->bus_flags |= PCI_BUS_FLAGS_NO_MSI;
-	}
-
         if (nr_ioapics == 0) 
                 return;
 
@@ -605,13 +597,6 @@ static void __init quirk_amd_8131_ioapic(struct pci_dev *dev)
         }
 } 
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_8131_BRIDGE, quirk_amd_8131_ioapic);
-
-static void __init quirk_svw_msi(struct pci_dev *dev)
-{
-	pci_msi_quirk = 1;
-	printk(KERN_WARNING "PCI: MSI quirk detected. pci_msi_quirk set.\n");
-}
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SERVERWORKS, PCI_DEVICE_ID_SERVERWORKS_GCNB_LE, quirk_svw_msi );
 #endif /* CONFIG_X86_IO_APIC */
 
 
@@ -1690,6 +1675,95 @@ static void __devinit quirk_nvidia_ck804_pcie_aer_ext_cap(struct pci_dev *dev)
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA,  PCI_DEVICE_ID_NVIDIA_CK804_PCIE,
 			quirk_nvidia_ck804_pcie_aer_ext_cap);
 
+#ifdef CONFIG_PCI_MSI
+/* To disable MSI globally */
+int pci_msi_quirk;
+
+/* The Serverworks PCI-X chipset does not support MSI. We cannot easily rely
+ * on setting PCI_BUS_FLAGS_NO_MSI in its bus flags because there are actually
+ * some other busses controlled by the chipset even if Linux is not aware of it.
+ * Instead of setting the flag on all busses in the machine, simply disable MSI
+ * globally.
+ */
+static void __init quirk_svw_msi(struct pci_dev *dev)
+{
+	pci_msi_quirk = 1;
+	printk(KERN_WARNING "PCI: MSI quirk detected. pci_msi_quirk set.\n");
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SERVERWORKS, PCI_DEVICE_ID_SERVERWORKS_GCNB_LE, quirk_svw_msi);
+
+/* Disable MSI on chipsets that are known to not support it */
+static void __devinit quirk_disable_msi(struct pci_dev *dev)
+{
+	if (dev->subordinate) {
+		printk(KERN_WARNING "PCI: MSI quirk detected. "
+		       "PCI_BUS_FLAGS_NO_MSI set for %s subordinate bus.\n",
+		       pci_name(dev));
+		dev->subordinate->bus_flags |= PCI_BUS_FLAGS_NO_MSI;
+	}
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_8131_BRIDGE, quirk_disable_msi);
+
+/* Go through the list of Hypertransport capabilities and
+ * return 1 if a HT MSI capability is found and enabled */
+static int __devinit msi_ht_cap_enabled(struct pci_dev *dev)
+{
+	u8 pos;
+	int ttl;
+	for (pos = pci_find_capability(dev, PCI_CAP_ID_HT), ttl = 48;
+	     pos && ttl;
+	     pos = pci_find_next_capability(dev, pos, PCI_CAP_ID_HT), ttl--) {
+		u32 cap_hdr;
+		/* MSI mapping section according to Hypertransport spec */
+		if (pci_read_config_dword(dev, pos, &cap_hdr) == 0
+		    && (cap_hdr & 0xf8000000) == 0xa8000000 /* MSI mapping */) {
+			printk(KERN_INFO "PCI: Found HT MSI mapping on %s with capability %s\n",
+			       pci_name(dev), cap_hdr & 0x10000 ? "enabled" : "disabled");
+			return (cap_hdr & 0x10000) != 0; /* MSI mapping cap enabled */
+		}
+	}
+	return 0;
+}
+
+/* Check the hypertransport MSI mapping to know whether MSI is enabled or not */
+static void __devinit quirk_msi_ht_cap(struct pci_dev *dev)
+{
+	if (dev->subordinate && !msi_ht_cap_enabled(dev)) {
+		printk(KERN_WARNING "PCI: MSI quirk detected. "
+		       "MSI disabled on chipset %s.\n",
+		       pci_name(dev));
+		dev->subordinate->bus_flags |= PCI_BUS_FLAGS_NO_MSI;
+	}
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SERVERWORKS, PCI_DEVICE_ID_SERVERWORKS_HT2000_PCIE,
+			quirk_msi_ht_cap);
+
+/* The nVidia CK804 chipset may have 2 HT MSI mappings.
+ * MSI are supported if the MSI capability set in any of these mappings.
+ */
+static void __devinit quirk_nvidia_ck804_msi_ht_cap(struct pci_dev *dev)
+{
+	struct pci_dev *pdev;
+
+	if (!dev->subordinate)
+		return;
+
+	/* check HT MSI cap on this chipset and the root one.
+	 * a single one having MSI is enough to be sure that MSI are supported.
+	 */
+	pdev = pci_find_slot(dev->bus->number, 0);
+	if (dev->subordinate && !msi_ht_cap_enabled(dev)
+	    && !msi_ht_cap_enabled(pdev)) {
+		printk(KERN_WARNING "PCI: MSI quirk detected. "
+		       "MSI disabled on chipset %s.\n",
+		       pci_name(dev));
+		dev->subordinate->bus_flags |= PCI_BUS_FLAGS_NO_MSI;
+	}
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_CK804_PCIE,
+			quirk_nvidia_ck804_msi_ht_cap);
+#endif /* CONFIG_PCI_MSI */
+
 EXPORT_SYMBOL(pcie_mch_quirk);
 #ifdef CONFIG_HOTPLUG
 EXPORT_SYMBOL(pci_fixup_device);

drivers/pci/remove.c

@@ -16,8 +16,11 @@ static void pci_free_resources(struct pci_dev *dev)
 	}
 }
 
-static void pci_destroy_dev(struct pci_dev *dev)
+static void pci_stop_dev(struct pci_dev *dev)
 {
+	if (!dev->global_list.next)
+		return;
+
 	if (!list_empty(&dev->global_list)) {
 		pci_proc_detach_device(dev);
 		pci_remove_sysfs_dev_files(dev);
@@ -27,6 +30,11 @@ static void pci_destroy_dev(struct pci_dev *dev)
 		dev->global_list.next = dev->global_list.prev = NULL;
 		up_write(&pci_bus_sem);
 	}
+}
+
+static void pci_destroy_dev(struct pci_dev *dev)
+{
+	pci_stop_dev(dev);
 
 	/* Remove the device from the device lists, and prevent any further
 	 * list accesses from this device */
@@ -119,5 +127,32 @@ void pci_remove_behind_bridge(struct pci_dev *dev)
 	}
 }
 
+static void pci_stop_bus_devices(struct pci_bus *bus)
+{
+	struct list_head *l, *n;
+
+	list_for_each_safe(l, n, &bus->devices) {
+		struct pci_dev *dev = pci_dev_b(l);
+		pci_stop_bus_device(dev);
+	}
+}
+
+/**
+ * pci_stop_bus_device - stop a PCI device and any children
+ * @dev: the device to stop
+ *
+ * Stop a PCI device (detach the driver, remove from the global list
+ * and so on). This also stop any subordinate buses and children in a
+ * depth-first manner.
+ */
+void pci_stop_bus_device(struct pci_dev *dev)
+{
+	if (dev->subordinate)
+		pci_stop_bus_devices(dev->subordinate);
+
+	pci_stop_dev(dev);
+}
+
 EXPORT_SYMBOL(pci_remove_bus_device);
 EXPORT_SYMBOL(pci_remove_behind_bridge);
+EXPORT_SYMBOL_GPL(pci_stop_bus_device);

drivers/pci/setup-bus.c

@@ -55,12 +55,19 @@ pbus_assign_resources_sorted(struct pci_bus *bus)
 	list_for_each_entry(dev, &bus->devices, bus_list) {
 		u16 class = dev->class >> 8;
 
-		/* Don't touch classless devices or host bridges or ioapics.  */
+		/* Don't touch classless devices or host bridges. */
 		if (class == PCI_CLASS_NOT_DEFINED ||
-		    class == PCI_CLASS_BRIDGE_HOST ||
-		    class == PCI_CLASS_SYSTEM_PIC)
+		    class == PCI_CLASS_BRIDGE_HOST)
 			continue;
 
+		/* Don't touch ioapics if it has the assigned resources. */
+		if (class == PCI_CLASS_SYSTEM_PIC) {
+			res = &dev->resource[0];
+			if (res[0].start || res[1].start || res[2].start ||
+			    res[3].start || res[4].start || res[5].start)
+				continue;
+		}
+
 		pdev_sort_resources(dev, &head);
 	}
 

include/linux/aer.h

+/*
+ * Copyright (C) 2006 Intel Corp.
+ *     Tom Long Nguyen (tom.l.nguyen@intel.com)
+ *     Zhang Yanmin (yanmin.zhang@intel.com)
+ */
+
+#ifndef _AER_H_
+#define _AER_H_
+
+#if defined(CONFIG_PCIEAER)
+/* pci-e port driver needs this function to enable aer */
+extern int pci_enable_pcie_error_reporting(struct pci_dev *dev);
+extern int pci_find_aer_capability(struct pci_dev *dev);
+extern int pci_disable_pcie_error_reporting(struct pci_dev *dev);
+extern int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev);
+#else
+#define pci_enable_pcie_error_reporting(dev)		do { } while (0)
+#define pci_find_aer_capability(dev)			do { } while (0)
+#define pci_disable_pcie_error_reporting(dev)		do { } while (0)
+#define pci_cleanup_aer_uncorrect_error_status(dev)	do { } while (0)
+#endif
+
+#endif //_AER_H_
+

include/linux/pci.h

@@ -356,6 +356,8 @@ struct pci_driver {
 	struct pci_error_handlers *err_handler;
 	struct device_driver	driver;
 	struct pci_dynids dynids;
+
+	int multithread_probe;
 };
 
 #define	to_pci_driver(drv) container_of(drv,struct pci_driver, driver)
@@ -431,7 +433,7 @@ int pci_scan_slot(struct pci_bus *bus, int devfn);
 struct pci_dev * pci_scan_single_device(struct pci_bus *bus, int devfn);
 void pci_device_add(struct pci_dev *dev, struct pci_bus *bus);
 unsigned int pci_scan_child_bus(struct pci_bus *bus);
-void pci_bus_add_device(struct pci_dev *dev);
+int __must_check pci_bus_add_device(struct pci_dev *dev);
 void pci_read_bridge_bases(struct pci_bus *child);
 struct resource *pci_find_parent_resource(const struct pci_dev *dev, struct resource *res);
 int pci_get_interrupt_pin(struct pci_dev *dev, struct pci_dev **bridge);
@@ -439,6 +441,7 @@ extern struct pci_dev *pci_dev_get(struct pci_dev *dev);
 extern void pci_dev_put(struct pci_dev *dev);
 extern void pci_remove_bus(struct pci_bus *b);
 extern void pci_remove_bus_device(struct pci_dev *dev);
+extern void pci_stop_bus_device(struct pci_dev *dev);
 void pci_setup_cardbus(struct pci_bus *bus);
 
 /* Generic PCI functions exported to card drivers */

include/linux/pci_ids.h

@@ -1411,6 +1411,7 @@
 #define PCI_DEVICE_ID_SERVERWORKS_LE	  0x0009
 #define PCI_DEVICE_ID_SERVERWORKS_GCNB_LE 0x0017
 #define PCI_DEVICE_ID_SERVERWORKS_EPB	  0x0103
+#define PCI_DEVICE_ID_SERVERWORKS_HT2000_PCIE	0x0132
 #define PCI_DEVICE_ID_SERVERWORKS_OSB4	  0x0200
 #define PCI_DEVICE_ID_SERVERWORKS_CSB5	  0x0201
 #define PCI_DEVICE_ID_SERVERWORKS_CSB6    0x0203

include/linux/pci_regs.h

@@ -196,7 +196,7 @@
 #define  PCI_CAP_ID_MSI		0x05	/* Message Signalled Interrupts */
 #define  PCI_CAP_ID_CHSWP	0x06	/* CompactPCI HotSwap */
 #define  PCI_CAP_ID_PCIX	0x07	/* PCI-X */
-#define  PCI_CAP_ID_HT_IRQCONF	0x08	/* HyperTransport IRQ Configuration */
+#define  PCI_CAP_ID_HT		0x08	/* HyperTransport */
 #define  PCI_CAP_ID_VNDR	0x09	/* Vendor specific capability */
 #define  PCI_CAP_ID_SHPC 	0x0C	/* PCI Standard Hot-Plug Controller */
 #define  PCI_CAP_ID_EXP 	0x10	/* PCI Express */

include/linux/pcieport_if.h

@@ -62,6 +62,12 @@ struct pcie_port_service_driver {
 	int (*suspend) (struct pcie_device *dev, pm_message_t state);
 	int (*resume) (struct pcie_device *dev);
 
+	/* Service Error Recovery Handler */
+	struct pci_error_handlers *err_handler;
+
+	/* Link Reset Capability - AER service driver specific */
+	pci_ers_result_t (*reset_link) (struct pci_dev *dev);
+
 	const struct pcie_port_service_id *id_table;
 	struct device_driver driver;
 };

kernel/resource.c

@@ -344,12 +344,11 @@ EXPORT_SYMBOL(allocate_resource);
  *
  * Returns 0 on success, -EBUSY if the resource can't be inserted.
  *
- * This function is equivalent of request_resource when no conflict
+ * This function is equivalent to request_resource when no conflict
  * happens. If a conflict happens, and the conflicting resources
  * entirely fit within the range of the new resource, then the new
- * resource is inserted and the conflicting resources become childs of
- * the new resource.  Otherwise the new resource becomes the child of
- * the conflicting resource
+ * resource is inserted and the conflicting resources become children of
+ * the new resource.
  */
 int insert_resource(struct resource *parent, struct resource *new)
 {
@@ -357,7 +356,8 @@ int insert_resource(struct resource *parent, struct resource *new)
 	struct resource *first, *next;
 
 	write_lock(&resource_lock);
- begin:
+
+	for (;; parent = first) {
 	 	result = 0;
 		first = __request_resource(parent, new);
 		if (!first)
@@ -367,10 +367,10 @@ int insert_resource(struct resource *parent, struct resource *new)
 		if (first == parent)
 			goto out;
 
-	/* Resource fully contained by the clashing resource? Recurse into it */
-	if (first->start <= new->start && first->end >= new->end) {
-		parent = first;
-		goto begin;
+		if ((first->start > new->start) || (first->end < new->end))
+			break;
+		if ((first->start == new->start) && (first->end == new->end))
+			break;
 	}
 
 	for (next = first; ; next = next->sibling) {