Merge branch 'linux-next' of git://git.kernel.org/pub/scm/linux/kernel/git/jbarnes/pci-2.6

* 'linux-next' of git://git.kernel.org/pub/scm/linux/kernel/git/jbarnes/pci-2.6: (88 commits)
  PCI: fix HT MSI mapping fix
  PCI: don't enable too much HT MSI mapping
  x86/PCI: make pci=lastbus=255 work when acpi is on
  PCI: save and restore PCIe 2.0 registers
  PCI: update fakephp for bus_id removal
  PCI: fix kernel oops on bridge removal
  PCI: fix conflict between SR-IOV and config space sizing
  powerpc/PCI: include pci.h in powerpc MSI implementation
  PCI Hotplug: schedule fakephp for feature removal
  PCI Hotplug: rename legacy_fakephp to fakephp
  PCI Hotplug: restore fakephp interface with complete reimplementation
  PCI: Introduce /sys/bus/pci/devices/.../rescan
  PCI: Introduce /sys/bus/pci/devices/.../remove
  PCI: Introduce /sys/bus/pci/rescan
  PCI: Introduce pci_rescan_bus()
  PCI: do not enable bridges more than once
  PCI: do not initialize bridges more than once
  PCI: always scan child buses
  PCI: pci_scan_slot() returns newly found devices
  PCI: don't scan existing devices
  ...

Fix trivial append-only conflict in Documentation/feature-removal-schedule.txt

Documentation/ABI/testing/sysfs-bus-pci

@@ -41,6 +41,49 @@ Description:
 		for the device and attempt to bind to it.  For example:
 		# echo "8086 10f5" > /sys/bus/pci/drivers/foo/new_id
 
+What:		/sys/bus/pci/drivers/.../remove_id
+Date:		February 2009
+Contact:	Chris Wright <chrisw@sous-sol.org>
+Description:
+		Writing a device ID to this file will remove an ID
+		that was dynamically added via the new_id sysfs entry.
+		The format for the device ID is:
+		VVVV DDDD SVVV SDDD CCCC MMMM.	That is Vendor ID, Device
+		ID, Subsystem Vendor ID, Subsystem Device ID, Class,
+		and Class Mask.  The Vendor ID and Device ID fields are
+		required, the rest are optional.  After successfully
+		removing an ID, the driver will no longer support the
+		device.  This is useful to ensure auto probing won't
+		match the driver to the device.  For example:
+		# echo "8086 10f5" > /sys/bus/pci/drivers/foo/remove_id
+
+What:		/sys/bus/pci/rescan
+Date:		January 2009
+Contact:	Linux PCI developers <linux-pci@vger.kernel.org>
+Description:
+		Writing a non-zero value to this attribute will
+		force a rescan of all PCI buses in the system, and
+		re-discover previously removed devices.
+		Depends on CONFIG_HOTPLUG.
+
+What:		/sys/bus/pci/devices/.../remove
+Date:		January 2009
+Contact:	Linux PCI developers <linux-pci@vger.kernel.org>
+Description:
+		Writing a non-zero value to this attribute will
+		hot-remove the PCI device and any of its children.
+		Depends on CONFIG_HOTPLUG.
+
+What:		/sys/bus/pci/devices/.../rescan
+Date:		January 2009
+Contact:	Linux PCI developers <linux-pci@vger.kernel.org>
+Description:
+		Writing a non-zero value to this attribute will
+		force a rescan of the device's parent bus and all
+		child buses, and re-discover devices removed earlier
+		from this part of the device tree.
+		Depends on CONFIG_HOTPLUG.
+
 What:		/sys/bus/pci/devices/.../vpd
 Date:		February 2008
 Contact:	Ben Hutchings <bhutchings@solarflare.com>
@@ -52,3 +95,30 @@ Description:
 		that some devices may have malformatted data.  If the
 		underlying VPD has a writable section then the
 		corresponding section of this file will be writable.
+
+What:		/sys/bus/pci/devices/.../virtfnN
+Date:		March 2009
+Contact:	Yu Zhao <yu.zhao@intel.com>
+Description:
+		This symbolic link appears when hardware supports the SR-IOV
+		capability and the Physical Function driver has enabled it.
+		The symbolic link points to the PCI device sysfs entry of the
+		Virtual Function whose index is N (0...MaxVFs-1).
+
+What:		/sys/bus/pci/devices/.../dep_link
+Date:		March 2009
+Contact:	Yu Zhao <yu.zhao@intel.com>
+Description:
+		This symbolic link appears when hardware supports the SR-IOV
+		capability and the Physical Function driver has enabled it,
+		and this device has vendor specific dependencies with others.
+		The symbolic link points to the PCI device sysfs entry of
+		Physical Function this device depends on.
+
+What:		/sys/bus/pci/devices/.../physfn
+Date:		March 2009
+Contact:	Yu Zhao <yu.zhao@intel.com>
+Description:
+		This symbolic link appears when a device is a Virtual Function.
+		The symbolic link points to the PCI device sysfs entry of the
+		Physical Function this device associates with.

Documentation/DocBook/kernel-api.tmpl

@@ -199,6 +199,7 @@ X!Edrivers/pci/hotplug.c
 -->
 !Edrivers/pci/probe.c
 !Edrivers/pci/rom.c
+!Edrivers/pci/iov.c
      </sect1>
      <sect1><title>PCI Hotplug Support Library</title>
 !Edrivers/pci/hotplug/pci_hotplug_core.c

Documentation/PCI/pci-iov-howto.txt

+		PCI Express I/O Virtualization Howto
+		Copyright (C) 2009 Intel Corporation
+		    Yu Zhao <yu.zhao@intel.com>
+
+
+1. Overview
+
+1.1 What is SR-IOV
+
+Single Root I/O Virtualization (SR-IOV) is a PCI Express Extended
+capability which makes one physical device appear as multiple virtual
+devices. The physical device is referred to as Physical Function (PF)
+while the virtual devices are referred to as Virtual Functions (VF).
+Allocation of the VF can be dynamically controlled by the PF via
+registers encapsulated in the capability. By default, this feature is
+not enabled and the PF behaves as traditional PCIe device. Once it's
+turned on, each VF's PCI configuration space can be accessed by its own
+Bus, Device and Function Number (Routing ID). And each VF also has PCI
+Memory Space, which is used to map its register set. VF device driver
+operates on the register set so it can be functional and appear as a
+real existing PCI device.
+
+2. User Guide
+
+2.1 How can I enable SR-IOV capability
+
+The device driver (PF driver) will control the enabling and disabling
+of the capability via API provided by SR-IOV core. If the hardware
+has SR-IOV capability, loading its PF driver would enable it and all
+VFs associated with the PF.
+
+2.2 How can I use the Virtual Functions
+
+The VF is treated as hot-plugged PCI devices in the kernel, so they
+should be able to work in the same way as real PCI devices. The VF
+requires device driver that is same as a normal PCI device's.
+
+3. Developer Guide
+
+3.1 SR-IOV API
+
+To enable SR-IOV capability:
+	int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn);
+	'nr_virtfn' is number of VFs to be enabled.
+
+To disable SR-IOV capability:
+	void pci_disable_sriov(struct pci_dev *dev);
+
+To notify SR-IOV core of Virtual Function Migration:
+	irqreturn_t pci_sriov_migration(struct pci_dev *dev);
+
+3.2 Usage example
+
+Following piece of code illustrates the usage of the SR-IOV API.
+
+static int __devinit dev_probe(struct pci_dev *dev, const struct pci_device_id *id)
+{
+	pci_enable_sriov(dev, NR_VIRTFN);
+
+	...
+
+	return 0;
+}
+
+static void __devexit dev_remove(struct pci_dev *dev)
+{
+	pci_disable_sriov(dev);
+
+	...
+}
+
+static int dev_suspend(struct pci_dev *dev, pm_message_t state)
+{
+	...
+
+	return 0;
+}
+
+static int dev_resume(struct pci_dev *dev)
+{
+	...
+
+	return 0;
+}
+
+static void dev_shutdown(struct pci_dev *dev)
+{
+	...
+}
+
+static struct pci_driver dev_driver = {
+	.name =		"SR-IOV Physical Function driver",
+	.id_table =	dev_id_table,
+	.probe =	dev_probe,
+	.remove =	__devexit_p(dev_remove),
+	.suspend =	dev_suspend,
+	.resume =	dev_resume,
+	.shutdown =	dev_shutdown,
+};

Documentation/feature-removal-schedule.txt

@@ -392,3 +392,35 @@ Why:	The defines and typedefs (hw_interrupt_type, no_irq_type, irq_desc_t)
 	have been kept around for migration reasons. After more than two years
 	it's time to remove them finally
 Who:	Thomas Gleixner <tglx@linutronix.de>
+
+---------------------------
+
+What:	fakephp and associated sysfs files in /sys/bus/pci/slots/
+When:	2011
+Why:	In 2.6.27, the semantics of /sys/bus/pci/slots was redefined to
+	represent a machine's physical PCI slots. The change in semantics
+	had userspace implications, as the hotplug core no longer allowed
+	drivers to create multiple sysfs files per physical slot (required
+	for multi-function devices, e.g.). fakephp was seen as a developer's
+	tool only, and its interface changed. Too late, we learned that
+	there were some users of the fakephp interface.
+
+	In 2.6.30, the original fakephp interface was restored. At the same
+	time, the PCI core gained the ability that fakephp provided, namely
+	function-level hot-remove and hot-add.
+
+	Since the PCI core now provides the same functionality, exposed in:
+
+		/sys/bus/pci/rescan
+		/sys/bus/pci/devices/.../remove
+		/sys/bus/pci/devices/.../rescan
+
+	there is no functional reason to maintain fakephp as well.
+
+	We will keep the existing module so that 'modprobe fakephp' will
+	present the old /sys/bus/pci/slots/... interface for compatibility,
+	but users are urged to migrate their applications to the API above.
+
+	After a reasonable transition period, we will remove the legacy
+	fakephp interface.
+Who:	Alex Chiang <achiang@hp.com>

Documentation/filesystems/sysfs-pci.txt

@@ -12,6 +12,7 @@ that support it.  For example, a given bus might look like this:
      |   |-- enable
      |   |-- irq
      |   |-- local_cpus
+     |   |-- remove
      |   |-- resource
      |   |-- resource0
      |   |-- resource1
@@ -36,6 +37,7 @@ files, each with their own function.
        enable	           Whether the device is enabled (ascii, rw)
        irq		   IRQ number (ascii, ro)
        local_cpus	   nearby CPU mask (cpumask, ro)
+       remove		   remove device from kernel's list (ascii, wo)
        resource		   PCI resource host addresses (ascii, ro)
        resource0..N	   PCI resource N, if present (binary, mmap)
        resource0_wc..N_wc  PCI WC map resource N, if prefetchable (binary, mmap)
@@ -46,6 +48,7 @@ files, each with their own function.
 
   ro - read only file
   rw - file is readable and writable
+  wo - write only file
   mmap - file is mmapable
   ascii - file contains ascii text
   binary - file contains binary data
@@ -73,6 +76,13 @@ that the device must be enabled for a rom read to return data succesfully.
 In the event a driver is not bound to the device, it can be enabled using the
 'enable' file, documented above.
 
+The 'remove' file is used to remove the PCI device, by writing a non-zero
+integer to the file.  This does not involve any kind of hot-plug functionality,
+e.g. powering off the device.  The device is removed from the kernel's list of
+PCI devices, the sysfs directory for it is removed, and the device will be
+removed from any drivers attached to it. Removal of PCI root buses is
+disallowed.
+
 Accessing legacy resources through sysfs
 ----------------------------------------
 

Documentation/kernel-parameters.txt

@@ -1695,6 +1695,8 @@ and is between 256 and 4096 characters. It is defined in the file
 			See also Documentation/blockdev/paride.txt.
 
 	pci=option[,option...]	[PCI] various PCI subsystem options:
+		earlydump	[X86] dump PCI config space before the kernel
+			        changes anything
 		off		[X86] don't probe for the PCI bus
 		bios		[X86-32] force use of PCI BIOS, don't access
 				the hardware directly. Use this if your machine
@@ -1794,6 +1796,15 @@ and is between 256 and 4096 characters. It is defined in the file
 		cbmemsize=nn[KMG]	The fixed amount of bus space which is
 				reserved for the CardBus bridge's memory
 				window. The default value is 64 megabytes.
+		resource_alignment=
+				Format:
+				[<order of align>@][<domain>:]<bus>:<slot>.<func>[; ...]
+				Specifies alignment and device to reassign
+				aligned memory resources.
+				If <order of align> is not specified,
+				PAGE_SIZE is used as alignment.
+				PCI-PCI bridge can be specified, if resource
+				windows need to be expanded.
 
 	pcie_aspm=	[PCIE] Forcibly enable or disable PCIe Active State Power
 			Management.

arch/alpha/include/asm/pci.h

@@ -273,4 +273,18 @@ struct pci_dev *alpha_gendev_to_pci(struct device *dev);
 
 extern struct pci_dev *isa_bridge;
 
+extern int pci_legacy_read(struct pci_bus *bus, loff_t port, u32 *val,
+			   size_t count);
+extern int pci_legacy_write(struct pci_bus *bus, loff_t port, u32 val,
+			    size_t count);
+extern int pci_mmap_legacy_page_range(struct pci_bus *bus,
+				      struct vm_area_struct *vma,
+				      enum pci_mmap_state mmap_state);
+extern void pci_adjust_legacy_attr(struct pci_bus *bus,
+				   enum pci_mmap_state mmap_type);
+#define HAVE_PCI_LEGACY	1
+
+extern int pci_create_resource_files(struct pci_dev *dev);
+extern void pci_remove_resource_files(struct pci_dev *dev);
+
 #endif /* __ALPHA_PCI_H */

arch/alpha/kernel/Makefile

@@ -12,7 +12,7 @@ obj-y    := entry.o traps.o process.o init_task.o osf_sys.o irq.o \
 
 obj-$(CONFIG_VGA_HOSE)	+= console.o
 obj-$(CONFIG_SMP)	+= smp.o
-obj-$(CONFIG_PCI)	+= pci.o pci_iommu.o
+obj-$(CONFIG_PCI)	+= pci.o pci_iommu.o pci-sysfs.o
 obj-$(CONFIG_SRM_ENV)	+= srm_env.o
 obj-$(CONFIG_MODULES)	+= module.o
 

arch/alpha/kernel/pci-sysfs.c

+/*
+ * arch/alpha/kernel/pci-sysfs.c
+ *
+ * Copyright (C) 2009 Ivan Kokshaysky
+ *
+ * Alpha PCI resource files.
+ *
+ * Loosely based on generic HAVE_PCI_MMAP implementation in
+ * drivers/pci/pci-sysfs.c
+ */
+
+#include <linux/sched.h>
+#include <linux/pci.h>
+
+static int hose_mmap_page_range(struct pci_controller *hose,
+				struct vm_area_struct *vma,
+				enum pci_mmap_state mmap_type, int sparse)
+{
+	unsigned long base;
+
+	if (mmap_type == pci_mmap_mem)
+		base = sparse ? hose->sparse_mem_base : hose->dense_mem_base;
+	else
+		base = sparse ? hose->sparse_io_base : hose->dense_io_base;
+
+	vma->vm_pgoff += base >> PAGE_SHIFT;
+	vma->vm_flags |= (VM_IO | VM_RESERVED);
+
+	return io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
+				  vma->vm_end - vma->vm_start,
+				  vma->vm_page_prot);
+}
+
+static int __pci_mmap_fits(struct pci_dev *pdev, int num,
+			   struct vm_area_struct *vma, int sparse)
+{
+	unsigned long nr, start, size;
+	int shift = sparse ? 5 : 0;
+
+	nr = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+	start = vma->vm_pgoff;
+	size = ((pci_resource_len(pdev, num) - 1) >> (PAGE_SHIFT - shift)) + 1;
+
+	if (start < size && size - start >= nr)
+		return 1;
+	WARN(1, "process \"%s\" tried to map%s 0x%08lx-0x%08lx on %s BAR %d "
+		"(size 0x%08lx)\n",
+		current->comm, sparse ? " sparse" : "", start, start + nr,
+		pci_name(pdev), num, size);
+	return 0;
+}
+
+/**
+ * pci_mmap_resource - map a PCI resource into user memory space
+ * @kobj: kobject for mapping
+ * @attr: struct bin_attribute for the file being mapped
+ * @vma: struct vm_area_struct passed into the mmap
+ * @sparse: address space type
+ *
+ * Use the bus mapping routines to map a PCI resource into userspace.
+ */
+static int pci_mmap_resource(struct kobject *kobj, struct bin_attribute *attr,
+			     struct vm_area_struct *vma, int sparse)
+{
+	struct pci_dev *pdev = to_pci_dev(container_of(kobj,
+						       struct device, kobj));
+	struct resource *res = (struct resource *)attr->private;
+	enum pci_mmap_state mmap_type;
+	struct pci_bus_region bar;
+	int i;
+
+	for (i = 0; i < PCI_ROM_RESOURCE; i++)
+		if (res == &pdev->resource[i])
+			break;
+	if (i >= PCI_ROM_RESOURCE)
+		return -ENODEV;
+
+	if (!__pci_mmap_fits(pdev, i, vma, sparse))
+		return -EINVAL;
+
+	if (iomem_is_exclusive(res->start))
+		return -EINVAL;
+
+	pcibios_resource_to_bus(pdev, &bar, res);
+	vma->vm_pgoff += bar.start >> (PAGE_SHIFT - (sparse ? 5 : 0));
+	mmap_type = res->flags & IORESOURCE_MEM ? pci_mmap_mem : pci_mmap_io;
+
+	return hose_mmap_page_range(pdev->sysdata, vma, mmap_type, sparse);
+}
+
+static int pci_mmap_resource_sparse(struct kobject *kobj,
+				    struct bin_attribute *attr,
+				    struct vm_area_struct *vma)
+{
+	return pci_mmap_resource(kobj, attr, vma, 1);
+}
+
+static int pci_mmap_resource_dense(struct kobject *kobj,
+				   struct bin_attribute *attr,
+				   struct vm_area_struct *vma)
+{
+	return pci_mmap_resource(kobj, attr, vma, 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.
+ */
+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);
+		}
+
+		res_attr = pdev->res_attr_wc[i];
+		if (res_attr) {
+			sysfs_remove_bin_file(&pdev->dev.kobj, res_attr);
+			kfree(res_attr);
+		}
+	}
+}
+
+static int sparse_mem_mmap_fits(struct pci_dev *pdev, int num)
+{
+	struct pci_bus_region bar;
+	struct pci_controller *hose = pdev->sysdata;
+	long dense_offset;
+	unsigned long sparse_size;
+
+	pcibios_resource_to_bus(pdev, &bar, &pdev->resource[num]);
+
+	/* All core logic chips have 4G sparse address space, except
+	   CIA which has 16G (see xxx_SPARSE_MEM and xxx_DENSE_MEM
+	   definitions in asm/core_xxx.h files). This corresponds
+	   to 128M or 512M of the bus space. */
+	dense_offset = (long)(hose->dense_mem_base - hose->sparse_mem_base);
+	sparse_size = dense_offset >= 0x400000000UL ? 0x20000000 : 0x8000000;
+
+	return bar.end < sparse_size;
+}
+
+static int pci_create_one_attr(struct pci_dev *pdev, int num, char *name,
+			       char *suffix, struct bin_attribute *res_attr,
+			       unsigned long sparse)
+{
+	size_t size = pci_resource_len(pdev, num);
+
+	sprintf(name, "resource%d%s", num, suffix);
+	res_attr->mmap = sparse ? pci_mmap_resource_sparse :
+				  pci_mmap_resource_dense;
+	res_attr->attr.name = name;
+	res_attr->attr.mode = S_IRUSR | S_IWUSR;
+	res_attr->size = sparse ? size << 5 : size;
+	res_attr->private = &pdev->resource[num];
+	return sysfs_create_bin_file(&pdev->dev.kobj, res_attr);
+}
+
+static int pci_create_attr(struct pci_dev *pdev, int num)
+{
+	/* allocate attribute structure, piggyback attribute name */
+	int retval, nlen1, nlen2 = 0, res_count = 1;
+	unsigned long sparse_base, dense_base;
+	struct bin_attribute *attr;
+	struct pci_controller *hose = pdev->sysdata;
+	char *suffix, *attr_name;
+
+	suffix = "";	/* Assume bwx machine, normal resourceN files. */
+	nlen1 = 10;
+
+	if (pdev->resource[num].flags & IORESOURCE_MEM) {
+		sparse_base = hose->sparse_mem_base;
+		dense_base = hose->dense_mem_base;
+		if (sparse_base && !sparse_mem_mmap_fits(pdev, num)) {
+			sparse_base = 0;
+			suffix = "_dense";
+			nlen1 = 16;	/* resourceN_dense */
+		}
+	} else {
+		sparse_base = hose->sparse_io_base;
+		dense_base = hose->dense_io_base;
+	}
+
+	if (sparse_base) {
+		suffix = "_sparse";
+		nlen1 = 17;
+		if (dense_base) {
+			nlen2 = 16;	/* resourceN_dense */
+			res_count = 2;
+		}
+	}
+
+	attr = kzalloc(sizeof(*attr) * res_count + nlen1 + nlen2, GFP_ATOMIC);
+	if (!attr)
+		return -ENOMEM;
+
+	/* Create bwx, sparse or single dense file */
+	attr_name = (char *)(attr + res_count);
+	pdev->res_attr[num] = attr;
+	retval = pci_create_one_attr(pdev, num, attr_name, suffix, attr,
+				     sparse_base);
+	if (retval || res_count == 1)
+		return retval;
+
+	/* Create dense file */
+	attr_name += nlen1;
+	attr++;
+	pdev->res_attr_wc[num] = attr;
+	return pci_create_one_attr(pdev, num, attr_name, "_dense", attr, 0);
+}
+
+/**
+ * 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.
+ */
+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++) {
+
+		/* skip empty resources */
+		if (!pci_resource_len(pdev, i))
+			continue;
+
+		retval = pci_create_attr(pdev, i);
+		if (retval) {
+			pci_remove_resource_files(pdev);
+			return retval;
+		}
+	}
+	return 0;
+}
+
+/* Legacy I/O bus mapping stuff. */
+
+static int __legacy_mmap_fits(struct pci_controller *hose,
+			      struct vm_area_struct *vma,
+			      unsigned long res_size, int sparse)
+{
+	unsigned long nr, start, size;
+
+	nr = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+	start = vma->vm_pgoff;
+	size = ((res_size - 1) >> PAGE_SHIFT) + 1;
+
+	if (start < size && size - start >= nr)
+		return 1;
+	WARN(1, "process \"%s\" tried to map%s 0x%08lx-0x%08lx on hose %d "
+		"(size 0x%08lx)\n",
+		current->comm, sparse ? " sparse" : "", start, start + nr,
+		hose->index, size);
+	return 0;
+}
+
+static inline int has_sparse(struct pci_controller *hose,
+			     enum pci_mmap_state mmap_type)
+{
+	unsigned long base;
+
+	base = (mmap_type == pci_mmap_mem) ? hose->sparse_mem_base :
+					     hose->sparse_io_base;
+
+	return base != 0;
+}
+
+int pci_mmap_legacy_page_range(struct pci_bus *bus, struct vm_area_struct *vma,
+			       enum pci_mmap_state mmap_type)
+{
+	struct pci_controller *hose = bus->sysdata;
+	int sparse = has_sparse(hose, mmap_type);
+	unsigned long res_size;
+
+	res_size = (mmap_type == pci_mmap_mem) ? bus->legacy_mem->size :
+						 bus->legacy_io->size;
+	if (!__legacy_mmap_fits(hose, vma, res_size, sparse))
+		return -EINVAL;
+
+	return hose_mmap_page_range(hose, vma, mmap_type, sparse);
+}
+
+/**
+ * pci_adjust_legacy_attr - adjustment of legacy file attributes
+ * @b: bus to create files under
+ * @mmap_type: I/O port or memory
+ *
+ * Adjust file name and size for sparse mappings.
+ */
+void pci_adjust_legacy_attr(struct pci_bus *bus, enum pci_mmap_state mmap_type)
+{
+	struct pci_controller *hose = bus->sysdata;
+
+	if (!has_sparse(hose, mmap_type))
+		return;
+
+	if (mmap_type == pci_mmap_mem) {
+		bus->legacy_mem->attr.name = "legacy_mem_sparse";
+		bus->legacy_mem->size <<= 5;
+	} else {
+		bus->legacy_io->attr.name = "legacy_io_sparse";
+		bus->legacy_io->size <<= 5;
+	}
+	return;
+}
+
+/* Legacy I/O bus read/write functions */
+int pci_legacy_read(struct pci_bus *bus, loff_t port, u32 *val, size_t size)
+{
+	struct pci_controller *hose = bus->sysdata;
+
+	port += hose->io_space->start;
+
+	switch(size) {
+	case 1:
+		*((u8 *)val) = inb(port);
+		return 1;
+	case 2:
+		if (port & 1)
+			return -EINVAL;
+		*((u16 *)val) = inw(port);
+		return 2;
+	case 4:
+		if (port & 3)
+			return -EINVAL;
+		*((u32 *)val) = inl(port);
+		return 4;
+	}
+	return -EINVAL;
+}
+
+int pci_legacy_write(struct pci_bus *bus, loff_t port, u32 val, size_t size)
+{
+	struct pci_controller *hose = bus->sysdata;
+
+	port += hose->io_space->start;
+
+	switch(size) {
+	case 1:
+		outb(port, val);
+		return 1;
+	case 2:
+		if (port & 1)
+			return -EINVAL;
+		outw(port, val);
+		return 2;
+	case 4:
+		if (port & 3)
+			return -EINVAL;
+		outl(port, val);
+		return 4;
+	}
+	return -EINVAL;
+}

arch/powerpc/include/asm/pci.h

@@ -114,6 +114,10 @@ extern int pci_domain_nr(struct pci_bus *bus);
 /* Decide whether to display the domain number in /proc */
 extern int pci_proc_domain(struct pci_bus *bus);
 
+/* MSI arch hooks */
+#define arch_setup_msi_irqs arch_setup_msi_irqs
+#define arch_teardown_msi_irqs arch_teardown_msi_irqs
+#define arch_msi_check_device arch_msi_check_device
 
 struct vm_area_struct;
 /* Map a range of PCI memory or I/O space for a device into user space */

arch/powerpc/kernel/msi.c

@@ -9,6 +9,7 @@
 
 #include <linux/kernel.h>
 #include <linux/msi.h>
+#include <linux/pci.h>
 
 #include <asm/machdep.h>
 
@@ -19,6 +20,10 @@ int arch_msi_check_device(struct pci_dev* dev, int nvec, int type)
 		return -ENOSYS;
 	}
 
+	/* PowerPC doesn't support multiple MSI yet */
+	if (type == PCI_CAP_ID_MSI && nvec > 1)
+		return 1;
+
 	if (ppc_md.msi_check_device) {
 		pr_debug("msi: Using platform check routine.\n");
 		return ppc_md.msi_check_device(dev, nvec, type);

arch/x86/include/asm/pci.h

@@ -86,6 +86,9 @@ static inline void early_quirks(void) { }
 
 extern void pci_iommu_alloc(void);
 
+/* MSI arch hook */
+#define arch_setup_msi_irqs arch_setup_msi_irqs
+
 #endif  /* __KERNEL__ */
 
 #ifdef CONFIG_X86_32

arch/x86/kernel/apic/io_apic.c

@@ -3468,6 +3468,10 @@ int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 	struct intel_iommu *iommu = NULL;
 	int index = 0;
 
+	/* x86 doesn't support multiple MSI yet */
+	if (type == PCI_CAP_ID_MSI && nvec > 1)
+		return 1;
+
 	irq_want = nr_irqs_gsi;
 	sub_handle = 0;
 	list_for_each_entry(msidesc, &dev->msi_list, list) {

arch/x86/kernel/pci-dma.c

@@ -300,8 +300,7 @@ fs_initcall(pci_iommu_init);
 static __devinit void via_no_dac(struct pci_dev *dev)
 {
 	if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI && forbid_dac == 0) {
-		printk(KERN_INFO
-			"PCI: VIA PCI bridge detected. Disabling DAC.\n");
+		dev_info(&dev->dev, "disabling DAC on VIA PCI bridge\n");
 		forbid_dac = 1;
 	}
 }

arch/x86/pci/early.c

@@ -69,11 +69,12 @@ void early_dump_pci_device(u8 bus, u8 slot, u8 func)
 	int j;
 	u32 val;
 
-	printk(KERN_INFO "PCI: %02x:%02x:%02x", bus, slot, func);
+	printk(KERN_INFO "pci 0000:%02x:%02x.%d config space:",
+	       bus, slot, func);
 
 	for (i = 0; i < 256; i += 4) {
 		if (!(i & 0x0f))
-			printk("\n%04x:",i);
+			printk("\n  %02x:",i);
 
 		val = read_pci_config(bus, slot, func, i);
 		for (j = 0; j < 4; j++) {
@@ -96,20 +97,22 @@ void early_dump_pci_devices(void)
 			for (func = 0; func < 8; func++) {
 				u32 class;
 				u8 type;
+
 				class = read_pci_config(bus, slot, func,
 							PCI_CLASS_REVISION);
 				if (class == 0xffffffff)
-					break;
+					continue;
 
 				early_dump_pci_device(bus, slot, func);
 
-				/* No multi-function device? */
-				type = read_pci_config_byte(bus, slot, func,
+				if (func == 0) {
+					type = read_pci_config_byte(bus, slot,
+								    func,
 							       PCI_HEADER_TYPE);
-				if (!(type & 0x80))
-					break;
+					if (!(type & 0x80))
+						break;
+				}
 			}
 		}
 	}
 }
-

arch/x86/pci/fixup.c

@@ -494,26 +494,6 @@ static void __devinit pci_siemens_interrupt_controller(struct pci_dev *dev)
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SIEMENS, 0x0015,
 			  pci_siemens_interrupt_controller);
 
-/*
- * Regular PCI devices have 256 bytes, but AMD Family 10h/11h CPUs have
- * 4096 bytes configuration space for each function of their processor
- * configuration space.
- */
-static void amd_cpu_pci_cfg_space_size(struct pci_dev *dev)
-{
-	dev->cfg_size = pci_cfg_space_size_ext(dev);
-}
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1200, amd_cpu_pci_cfg_space_size);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1201, amd_cpu_pci_cfg_space_size);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1202, amd_cpu_pci_cfg_space_size);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1203, amd_cpu_pci_cfg_space_size);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1204, amd_cpu_pci_cfg_space_size);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1300, amd_cpu_pci_cfg_space_size);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1301, amd_cpu_pci_cfg_space_size);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1302, amd_cpu_pci_cfg_space_size);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1303, amd_cpu_pci_cfg_space_size);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1304, amd_cpu_pci_cfg_space_size);
-
 /*
  * SB600: Disable BAR1 on device 14.0 to avoid HPET resources from
  * confusing the PCI engine:

arch/x86/pci/legacy.c

@@ -50,8 +50,6 @@ static int __init pci_legacy_init(void)
 	if (pci_root_bus)
 		pci_bus_add_devices(pci_root_bus);
 
-	pcibios_fixup_peer_bridges();
-
 	return 0;
 }
 
@@ -67,6 +65,7 @@ int __init pci_subsys_init(void)
 	pci_visws_init();
 #endif
 	pci_legacy_init();
+	pcibios_fixup_peer_bridges();
 	pcibios_irq_init();
 	pcibios_init();
 

arch/x86/pci/mmconfig-shared.c

@@ -14,6 +14,7 @@
 #include <linux/init.h>
 #include <linux/acpi.h>
 #include <linux/bitmap.h>
+#include <linux/sort.h>
 #include <asm/e820.h>
 #include <asm/pci_x86.h>
 
@@ -24,24 +25,49 @@
 /* Indicate if the mmcfg resources have been placed into the resource table. */
 static int __initdata pci_mmcfg_resources_inserted;
 
+static __init int extend_mmcfg(int num)
+{
+	struct acpi_mcfg_allocation *new;
+	int new_num = pci_mmcfg_config_num + num;
+
+	new = kzalloc(sizeof(pci_mmcfg_config[0]) * new_num, GFP_KERNEL);
+	if (!new)
+		return -1;
+
+	if (pci_mmcfg_config) {
+		memcpy(new, pci_mmcfg_config,
+			 sizeof(pci_mmcfg_config[0]) * new_num);
+		kfree(pci_mmcfg_config);
+	}
+	pci_mmcfg_config = new;
+
+	return 0;
+}
+
+static __init void fill_one_mmcfg(u64 addr, int segment, int start, int end)
+{
+	int i = pci_mmcfg_config_num;
+
+	pci_mmcfg_config_num++;
+	pci_mmcfg_config[i].address = addr;
+	pci_mmcfg_config[i].pci_segment = segment;
+	pci_mmcfg_config[i].start_bus_number = start;
+	pci_mmcfg_config[i].end_bus_number = end;
+}
+
 static const char __init *pci_mmcfg_e7520(void)
 {
 	u32 win;
 	raw_pci_ops->read(0, 0, PCI_DEVFN(0, 0), 0xce, 2, &win);
 
 	win = win & 0xf000;
-	if(win == 0x0000 || win == 0xf000)
-		pci_mmcfg_config_num = 0;
-	else {
-		pci_mmcfg_config_num = 1;
-		pci_mmcfg_config = kzalloc(sizeof(pci_mmcfg_config[0]), GFP_KERNEL);
-		if (!pci_mmcfg_config)
-			return NULL;
-		pci_mmcfg_config[0].address = win << 16;
-		pci_mmcfg_config[0].pci_segment = 0;
-		pci_mmcfg_config[0].start_bus_number = 0;
-		pci_mmcfg_config[0].end_bus_number = 255;
-	}
+	if (win == 0x0000 || win == 0xf000)
+		return NULL;
+
+	if (extend_mmcfg(1) == -1)
+		return NULL;
+
+	fill_one_mmcfg(win << 16, 0, 0, 255);
 
 	return "Intel Corporation E7520 Memory Controller Hub";
 }
@@ -50,13 +76,11 @@ static const char __init *pci_mmcfg_intel_945(void)
 {
 	u32 pciexbar, mask = 0, len = 0;
 
-	pci_mmcfg_config_num = 1;
-
 	raw_pci_ops->read(0, 0, PCI_DEVFN(0, 0), 0x48, 4, &pciexbar);
 
 	/* Enable bit */
 	if (!(pciexbar & 1))
-		pci_mmcfg_config_num = 0;
+		return NULL;
 
 	/* Size bits */
 	switch ((pciexbar >> 1) & 3) {
@@ -73,28 +97,23 @@ static const char __init *pci_mmcfg_intel_945(void)
 		len  = 0x04000000U;
 		break;
 	default:
-		pci_mmcfg_config_num = 0;
+		return NULL;
 	}
 
 	/* Errata #2, things break when not aligned on a 256Mb boundary */
 	/* Can only happen in 64M/128M mode */
 
 	if ((pciexbar & mask) & 0x0fffffffU)
-		pci_mmcfg_config_num = 0;
+		return NULL;
 
 	/* Don't hit the APIC registers and their friends */
 	if ((pciexbar & mask) >= 0xf0000000U)
-		pci_mmcfg_config_num = 0;
-
-	if (pci_mmcfg_config_num) {
-		pci_mmcfg_config = kzalloc(sizeof(pci_mmcfg_config[0]), GFP_KERNEL);
-		if (!pci_mmcfg_config)
-			return NULL;
-		pci_mmcfg_config[0].address = pciexbar & mask;
-		pci_mmcfg_config[0].pci_segment = 0;
-		pci_mmcfg_config[0].start_bus_number = 0;
-		pci_mmcfg_config[0].end_bus_number = (len >> 20) - 1;
-	}
+		return NULL;
+
+	if (extend_mmcfg(1) == -1)
+		return NULL;
+
+	fill_one_mmcfg(pciexbar & mask, 0, 0, (len >> 20) - 1);
 
 	return "Intel Corporation 945G/GZ/P/PL Express Memory Controller Hub";
 }
@@ -138,22 +157,77 @@ static const char __init *pci_mmcfg_amd_fam10h(void)
 		busnbits = 8;
 	}
 
-	pci_mmcfg_config_num = (1 << segnbits);
-	pci_mmcfg_config = kzalloc(sizeof(pci_mmcfg_config[0]) *
-				   pci_mmcfg_config_num, GFP_KERNEL);
-	if (!pci_mmcfg_config)
+	if (extend_mmcfg(1 << segnbits) == -1)
 		return NULL;
 
-	for (i = 0; i < (1 << segnbits); i++) {
-		pci_mmcfg_config[i].address = base + (1<<28) * i;
-		pci_mmcfg_config[i].pci_segment = i;
-		pci_mmcfg_config[i].start_bus_number = 0;
-		pci_mmcfg_config[i].end_bus_number = (1 << busnbits) - 1;
-	}
+	for (i = 0; i < (1 << segnbits); i++)
+		fill_one_mmcfg(base + (1<<28) * i, i, 0, (1 << busnbits) - 1);
 
 	return "AMD Family 10h NB";
 }
 
+static bool __initdata mcp55_checked;
+static const char __init *pci_mmcfg_nvidia_mcp55(void)
+{
+	int bus;
+	int mcp55_mmconf_found = 0;
+
+	static const u32 extcfg_regnum		= 0x90;
+	static const u32 extcfg_regsize		= 4;
+	static const u32 extcfg_enable_mask	= 1<<31;
+	static const u32 extcfg_start_mask	= 0xff<<16;
+	static const int extcfg_start_shift	= 16;
+	static const u32 extcfg_size_mask	= 0x3<<28;
+	static const int extcfg_size_shift	= 28;
+	static const int extcfg_sizebus[]	= {0x100, 0x80, 0x40, 0x20};
+	static const u32 extcfg_base_mask[]	= {0x7ff8, 0x7ffc, 0x7ffe, 0x7fff};
+	static const int extcfg_base_lshift	= 25;
+
+	/*
+	 * do check if amd fam10h already took over
+	 */
+	if (!acpi_disabled || pci_mmcfg_config_num || mcp55_checked)
+		return NULL;
+
+	mcp55_checked = true;
+	for (bus = 0; bus < 256; bus++) {
+		u64 base;
+		u32 l, extcfg;
+		u16 vendor, device;
+		int start, size_index, end;
+
+		raw_pci_ops->read(0, bus, PCI_DEVFN(0, 0), 0, 4, &l);
+		vendor = l & 0xffff;
+		device = (l >> 16) & 0xffff;
+
+		if (PCI_VENDOR_ID_NVIDIA != vendor || 0x0369 != device)
+			continue;
+
+		raw_pci_ops->read(0, bus, PCI_DEVFN(0, 0), extcfg_regnum,
+				  extcfg_regsize, &extcfg);
+
+		if (!(extcfg & extcfg_enable_mask))
+			continue;
+
+		if (extend_mmcfg(1) == -1)
+			continue;
+
+		size_index = (extcfg & extcfg_size_mask) >> extcfg_size_shift;
+		base = extcfg & extcfg_base_mask[size_index];
+		/* base could > 4G */
+		base <<= extcfg_base_lshift;
+		start = (extcfg & extcfg_start_mask) >> extcfg_start_shift;
+		end = start + extcfg_sizebus[size_index] - 1;
+		fill_one_mmcfg(base, 0, start, end);
+		mcp55_mmconf_found++;
+	}
+
+	if (!mcp55_mmconf_found)
+		return NULL;
+
+	return "nVidia MCP55";
+}
+
 struct pci_mmcfg_hostbridge_probe {
 	u32 bus;
 	u32 devfn;
@@ -171,8 +245,52 @@ static struct pci_mmcfg_hostbridge_probe pci_mmcfg_probes[] __initdata = {
 	  0x1200, pci_mmcfg_amd_fam10h },
 	{ 0xff, PCI_DEVFN(0, 0), PCI_VENDOR_ID_AMD,
 	  0x1200, pci_mmcfg_amd_fam10h },
+	{ 0, PCI_DEVFN(0, 0), PCI_VENDOR_ID_NVIDIA,
+	  0x0369, pci_mmcfg_nvidia_mcp55 },
 };
 
+static int __init cmp_mmcfg(const void *x1, const void *x2)
+{
+	const typeof(pci_mmcfg_config[0]) *m1 = x1;
+	const typeof(pci_mmcfg_config[0]) *m2 = x2;
+	int start1, start2;
+
+	start1 = m1->start_bus_number;
+	start2 = m2->start_bus_number;
+
+	return start1 - start2;
+}
+
+static void __init pci_mmcfg_check_end_bus_number(void)
+{
+	int i;
+	typeof(pci_mmcfg_config[0]) *cfg, *cfgx;
+
+	/* sort them at first */
+	sort(pci_mmcfg_config, pci_mmcfg_config_num,
+		 sizeof(pci_mmcfg_config[0]), cmp_mmcfg, NULL);
+
+	/* last one*/
+	if (pci_mmcfg_config_num > 0) {
+		i = pci_mmcfg_config_num - 1;
+		cfg = &pci_mmcfg_config[i];
+		if (cfg->end_bus_number < cfg->start_bus_number)
+			cfg->end_bus_number = 255;
+	}
+
+	/* don't overlap please */
+	for (i = 0; i < pci_mmcfg_config_num - 1; i++) {
+		cfg = &pci_mmcfg_config[i];
+		cfgx = &pci_mmcfg_config[i+1];
+
+		if (cfg->end_bus_number < cfg->start_bus_number)
+			cfg->end_bus_number = 255;
+
+		if (cfg->end_bus_number >= cfgx->start_bus_number)
+			cfg->end_bus_number = cfgx->start_bus_number - 1;
+	}
+}
+
 static int __init pci_mmcfg_check_hostbridge(void)
 {
 	u32 l;
@@ -186,31 +304,33 @@ static int __init pci_mmcfg_check_hostbridge(void)
 
 	pci_mmcfg_config_num = 0;
 	pci_mmcfg_config = NULL;
-	name = NULL;
 
-	for (i = 0; !name && i < ARRAY_SIZE(pci_mmcfg_probes); i++) {
+	for (i = 0; i < ARRAY_SIZE(pci_mmcfg_probes); i++) {
 		bus =  pci_mmcfg_probes[i].bus;
 		devfn = pci_mmcfg_probes[i].devfn;
 		raw_pci_ops->read(0, bus, devfn, 0, 4, &l);
 		vendor = l & 0xffff;
 		device = (l >> 16) & 0xffff;
 
+		name = NULL;
 		if (pci_mmcfg_probes[i].vendor == vendor &&
 		    pci_mmcfg_probes[i].device == device)
 			name = pci_mmcfg_probes[i].probe();
-	}
 
-	if (name) {
-		printk(KERN_INFO "PCI: Found %s %s MMCONFIG support.\n",
-		       name, pci_mmcfg_config_num ? "with" : "without");
+		if (name)
+			printk(KERN_INFO "PCI: Found %s with MMCONFIG support.\n",
+			       name);
 	}
 
-	return name != NULL;
+	/* some end_bus_number is crazy, fix it */
+	pci_mmcfg_check_end_bus_number();
+
+	return pci_mmcfg_config_num != 0;
 }
 
 static void __init pci_mmcfg_insert_resources(void)
 {
-#define PCI_MMCFG_RESOURCE_NAME_LEN 19
+#define PCI_MMCFG_RESOURCE_NAME_LEN 24
 	int i;
 	struct resource *res;
 	char *names;
@@ -228,9 +348,10 @@ static void __init pci_mmcfg_insert_resources(void)
 		struct acpi_mcfg_allocation *cfg = &pci_mmcfg_config[i];
 		num_buses = cfg->end_bus_number - cfg->start_bus_number + 1;
 		res->name = names;
-		snprintf(names, PCI_MMCFG_RESOURCE_NAME_LEN, "PCI MMCONFIG %u",
-			 cfg->pci_segment);
-		res->start = cfg->address;
+		snprintf(names, PCI_MMCFG_RESOURCE_NAME_LEN,
+			 "PCI MMCONFIG %u [%02x-%02x]", cfg->pci_segment,
+			 cfg->start_bus_number, cfg->end_bus_number);
+		res->start = cfg->address + (cfg->start_bus_number << 20);
 		res->end = res->start + (num_buses << 20) - 1;
 		res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
 		insert_resource(&iomem_resource, res);
@@ -354,8 +475,6 @@ static void __init pci_mmcfg_reject_broken(int early)
 	    (pci_mmcfg_config[0].address == 0))
 		return;
 
-	cfg = &pci_mmcfg_config[0];
-
 	for (i = 0; i < pci_mmcfg_config_num; i++) {
 		int valid = 0;
 		u64 addr, size;
@@ -423,10 +542,10 @@ static void __init __pci_mmcfg_init(int early)
 			known_bridge = 1;
 	}
 
-	if (!known_bridge) {
+	if (!known_bridge)
 		acpi_table_parse(ACPI_SIG_MCFG, acpi_parse_mcfg);
-		pci_mmcfg_reject_broken(early);
-	}
+
+	pci_mmcfg_reject_broken(early);
 
 	if ((pci_mmcfg_config_num == 0) ||
 	    (pci_mmcfg_config == NULL) ||

arch/x86/pci/mmconfig_64.c

@@ -112,13 +112,18 @@ static struct pci_raw_ops pci_mmcfg = {
 static void __iomem * __init mcfg_ioremap(struct acpi_mcfg_allocation *cfg)
 {
 	void __iomem *addr;
-	u32 size;
-
-	size = (cfg->end_bus_number + 1) << 20;
-	addr = ioremap_nocache(cfg->address, size);
+	u64 start, size;
+
+	start = cfg->start_bus_number;
+	start <<= 20;
+	start += cfg->address;
+	size = cfg->end_bus_number + 1 - cfg->start_bus_number;
+	size <<= 20;
+	addr = ioremap_nocache(start, size);
 	if (addr) {
 		printk(KERN_INFO "PCI: Using MMCONFIG at %Lx - %Lx\n",
-		       cfg->address, cfg->address + size - 1);
+		       start, start + size - 1);
+		addr -= cfg->start_bus_number << 20;
 	}
 	return addr;
 }
@@ -157,7 +162,7 @@ void __init pci_mmcfg_arch_free(void)
 
 	for (i = 0; i < pci_mmcfg_config_num; ++i) {
 		if (pci_mmcfg_virt[i].virt) {
-			iounmap(pci_mmcfg_virt[i].virt);
+			iounmap(pci_mmcfg_virt[i].virt + (pci_mmcfg_virt[i].cfg->start_bus_number << 20));
 			pci_mmcfg_virt[i].virt = NULL;
 			pci_mmcfg_virt[i].cfg = NULL;
 		}

drivers/acpi/pci_root.c

@@ -66,11 +66,18 @@ struct acpi_pci_root {
 	struct acpi_device * device;
 	struct acpi_pci_id id;
 	struct pci_bus *bus;
+
+	u32 osc_support_set;	/* _OSC state of support bits */
+	u32 osc_control_set;	/* _OSC state of control bits */
+	u32 osc_control_qry;	/* the latest _OSC query result */
+
+	u32 osc_queried:1;	/* has _OSC control been queried? */
 };
 
 static LIST_HEAD(acpi_pci_roots);
 
 static struct acpi_pci_driver *sub_driver;
+static DEFINE_MUTEX(osc_lock);
 
 int acpi_pci_register_driver(struct acpi_pci_driver *driver)
 {
@@ -185,6 +192,175 @@ static void acpi_pci_bridge_scan(struct acpi_device *device)
 		}
 }
 
+static u8 OSC_UUID[16] = {0x5B, 0x4D, 0xDB, 0x33, 0xF7, 0x1F, 0x1C, 0x40,
+			  0x96, 0x57, 0x74, 0x41, 0xC0, 0x3D, 0xD7, 0x66};
+
+static acpi_status acpi_pci_run_osc(acpi_handle handle,
+				    const u32 *capbuf, u32 *retval)
+{
+	acpi_status status;
+	struct acpi_object_list input;
+	union acpi_object in_params[4];
+	struct acpi_buffer output = {ACPI_ALLOCATE_BUFFER, NULL};
+	union acpi_object *out_obj;
+	u32 errors;
+
+	/* Setting up input parameters */
+	input.count = 4;
+	input.pointer = in_params;
+	in_params[0].type 		= ACPI_TYPE_BUFFER;
+	in_params[0].buffer.length 	= 16;
+	in_params[0].buffer.pointer	= OSC_UUID;
+	in_params[1].type 		= ACPI_TYPE_INTEGER;
+	in_params[1].integer.value 	= 1;
+	in_params[2].type 		= ACPI_TYPE_INTEGER;
+	in_params[2].integer.value	= 3;
+	in_params[3].type		= ACPI_TYPE_BUFFER;
+	in_params[3].buffer.length 	= 12;
+	in_params[3].buffer.pointer 	= (u8 *)capbuf;
+
+	status = acpi_evaluate_object(handle, "_OSC", &input, &output);
+	if (ACPI_FAILURE(status))
+		return status;
+
+	if (!output.length)
+		return AE_NULL_OBJECT;
+
+	out_obj = output.pointer;
+	if (out_obj->type != ACPI_TYPE_BUFFER) {
+		printk(KERN_DEBUG "_OSC evaluation returned wrong type\n");
+		status = AE_TYPE;
+		goto out_kfree;
+	}
+	/* Need to ignore the bit0 in result code */
+	errors = *((u32 *)out_obj->buffer.pointer) & ~(1 << 0);
+	if (errors) {
+		if (errors & OSC_REQUEST_ERROR)
+			printk(KERN_DEBUG "_OSC request failed\n");
+		if (errors & OSC_INVALID_UUID_ERROR)
+			printk(KERN_DEBUG "_OSC invalid UUID\n");
+		if (errors & OSC_INVALID_REVISION_ERROR)
+			printk(KERN_DEBUG "_OSC invalid revision\n");
+		if (errors & OSC_CAPABILITIES_MASK_ERROR) {
+			if (capbuf[OSC_QUERY_TYPE] & OSC_QUERY_ENABLE)
+				goto out_success;
+			printk(KERN_DEBUG
+			       "Firmware did not grant requested _OSC control\n");
+			status = AE_SUPPORT;
+			goto out_kfree;
+		}
+		status = AE_ERROR;
+		goto out_kfree;
+	}
+out_success:
+	*retval = *((u32 *)(out_obj->buffer.pointer + 8));
+	status = AE_OK;
+
+out_kfree:
+	kfree(output.pointer);
+	return status;
+}
+
+static acpi_status acpi_pci_query_osc(struct acpi_pci_root *root, u32 flags)
+{
+	acpi_status status;
+	u32 support_set, result, capbuf[3];
+
+	/* do _OSC query for all possible controls */
+	support_set = root->osc_support_set | (flags & OSC_SUPPORT_MASKS);
+	capbuf[OSC_QUERY_TYPE] = OSC_QUERY_ENABLE;
+	capbuf[OSC_SUPPORT_TYPE] = support_set;
+	capbuf[OSC_CONTROL_TYPE] = OSC_CONTROL_MASKS;
+
+	status = acpi_pci_run_osc(root->device->handle, capbuf, &result);
+	if (ACPI_SUCCESS(status)) {
+		root->osc_support_set = support_set;
+		root->osc_control_qry = result;
+		root->osc_queried = 1;
+	}
+	return status;
+}
+
+static acpi_status acpi_pci_osc_support(struct acpi_pci_root *root, u32 flags)
+{
+	acpi_status status;
+	acpi_handle tmp;
+
+	status = acpi_get_handle(root->device->handle, "_OSC", &tmp);
+	if (ACPI_FAILURE(status))
+		return status;
+	mutex_lock(&osc_lock);
+	status = acpi_pci_query_osc(root, flags);
+	mutex_unlock(&osc_lock);
+	return status;
+}
+
+static struct acpi_pci_root *acpi_pci_find_root(acpi_handle handle)
+{
+	struct acpi_pci_root *root;
+	list_for_each_entry(root, &acpi_pci_roots, node) {
+		if (root->device->handle == handle)
+			return root;
+	}
+	return NULL;
+}
+
+/**
+ * acpi_pci_osc_control_set - commit requested control to Firmware
+ * @handle: acpi_handle for the target ACPI object
+ * @flags: driver's requested control bits
+ *
+ * Attempt to take control from Firmware on requested control bits.
+ **/
+acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 flags)
+{
+	acpi_status status;
+	u32 control_req, result, capbuf[3];
+	acpi_handle tmp;
+	struct acpi_pci_root *root;
+
+	status = acpi_get_handle(handle, "_OSC", &tmp);
+	if (ACPI_FAILURE(status))
+		return status;
+
+	control_req = (flags & OSC_CONTROL_MASKS);
+	if (!control_req)
+		return AE_TYPE;
+
+	root = acpi_pci_find_root(handle);
+	if (!root)
+		return AE_NOT_EXIST;
+
+	mutex_lock(&osc_lock);
+	/* No need to evaluate _OSC if the control was already granted. */
+	if ((root->osc_control_set & control_req) == control_req)
+		goto out;
+
+	/* Need to query controls first before requesting them */
+	if (!root->osc_queried) {
+		status = acpi_pci_query_osc(root, root->osc_support_set);
+		if (ACPI_FAILURE(status))
+			goto out;
+	}
+	if ((root->osc_control_qry & control_req) != control_req) {
+		printk(KERN_DEBUG
+		       "Firmware did not grant requested _OSC control\n");
+		status = AE_SUPPORT;
+		goto out;
+	}
+
+	capbuf[OSC_QUERY_TYPE] = 0;
+	capbuf[OSC_SUPPORT_TYPE] = root->osc_support_set;
+	capbuf[OSC_CONTROL_TYPE] = root->osc_control_set | control_req;
+	status = acpi_pci_run_osc(handle, capbuf, &result);
+	if (ACPI_SUCCESS(status))
+		root->osc_control_set = result;
+out:
+	mutex_unlock(&osc_lock);
+	return status;
+}
+EXPORT_SYMBOL(acpi_pci_osc_control_set);
+
 static int __devinit acpi_pci_root_add(struct acpi_device *device)
 {
 	int result = 0;
@@ -217,7 +393,7 @@ static int __devinit acpi_pci_root_add(struct acpi_device *device)
 	 * PCI domains, so we indicate this in _OSC support capabilities.
 	 */
 	flags = base_flags = OSC_PCI_SEGMENT_GROUPS_SUPPORT;
-	pci_acpi_osc_support(device->handle, flags);
+	acpi_pci_osc_support(root, flags);
 
 	/* 
 	 * Segment
@@ -353,7 +529,7 @@ static int __devinit acpi_pci_root_add(struct acpi_device *device)
 	if (pci_msi_enabled())
 		flags |= OSC_MSI_SUPPORT;
 	if (flags != base_flags)
-		pci_acpi_osc_support(device->handle, flags);
+		acpi_pci_osc_support(root, flags);
 
       end:
 	if (result) {

drivers/pci/Kconfig

@@ -59,3 +59,13 @@ config HT_IRQ
 	   This allows native hypertransport devices to use interrupts.
 
 	   If unsure say Y.
+
+config PCI_IOV
+	bool "PCI IOV support"
+	depends on PCI
+	help
+	  I/O Virtualization is a PCI feature supported by some devices
+	  which allows them to create virtual devices which share their
+	  physical resources.
+
+	  If unsure, say N.

drivers/pci/Makefile

@@ -29,6 +29,8 @@ obj-$(CONFIG_DMAR) += dmar.o iova.o intel-iommu.o
 
 obj-$(CONFIG_INTR_REMAP) += dmar.o intr_remapping.o
 
+obj-$(CONFIG_PCI_IOV) += iov.o
+
 #
 # Some architectures use the generic PCI setup functions
 #

drivers/pci/bus.c

@@ -133,7 +133,7 @@ int pci_bus_add_child(struct pci_bus *bus)
  *
  * Call hotplug for each new devices.
  */
-void pci_bus_add_devices(struct pci_bus *bus)
+void pci_bus_add_devices(const struct pci_bus *bus)
 {
 	struct pci_dev *dev;
 	struct pci_bus *child;
@@ -184,8 +184,10 @@ void pci_enable_bridges(struct pci_bus *bus)
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
 		if (dev->subordinate) {
-			retval = pci_enable_device(dev);
-			pci_set_master(dev);
+			if (atomic_read(&dev->enable_cnt) == 0) {
+				retval = pci_enable_device(dev);
+				pci_set_master(dev);
+			}
 			pci_enable_bridges(dev->subordinate);
 		}
 	}

drivers/pci/hotplug/acpi_pcihp.c

@@ -30,9 +30,8 @@
 #include <linux/types.h>
 #include <linux/pci.h>
 #include <linux/pci_hotplug.h>
+#include <linux/acpi.h>
 #include <linux/pci-acpi.h>
-#include <acpi/acpi.h>
-#include <acpi/acpi_bus.h>
 
 #define MY_NAME	"acpi_pcihp"
 
@@ -333,19 +332,14 @@ acpi_status acpi_get_hp_params_from_firmware(struct pci_bus *bus,
 {
 	acpi_status status = AE_NOT_FOUND;
 	acpi_handle handle, phandle;
-	struct pci_bus *pbus = bus;
-	struct pci_dev *pdev;
-
-	do {
-		pdev = pbus->self;
-		if (!pdev) {
-			handle = acpi_get_pci_rootbridge_handle(
-				pci_domain_nr(pbus), pbus->number);
+	struct pci_bus *pbus;
+
+	handle = NULL;
+	for (pbus = bus; pbus; pbus = pbus->parent) {
+		handle = acpi_pci_get_bridge_handle(pbus);
+		if (handle)
 			break;
-		}
-		handle = DEVICE_ACPI_HANDLE(&(pdev->dev));
-		pbus = pbus->parent;
-	} while (!handle);
+	}
 
 	/*
 	 * _HPP settings apply to all child buses, until another _HPP is
@@ -378,12 +372,10 @@ EXPORT_SYMBOL_GPL(acpi_get_hp_params_from_firmware);
  *
  * Attempt to take hotplug control from firmware.
  */
-int acpi_get_hp_hw_control_from_firmware(struct pci_dev *dev, u32 flags)
+int acpi_get_hp_hw_control_from_firmware(struct pci_dev *pdev, u32 flags)
 {
 	acpi_status status;
 	acpi_handle chandle, handle;
-	struct pci_dev *pdev = dev;
-	struct pci_bus *parent;
 	struct acpi_buffer string = { ACPI_ALLOCATE_BUFFER, NULL };
 
 	flags &= (OSC_PCI_EXPRESS_NATIVE_HP_CONTROL |
@@ -408,33 +400,25 @@ int acpi_get_hp_hw_control_from_firmware(struct pci_dev *dev, u32 flags)
 		acpi_get_name(handle, ACPI_FULL_PATHNAME, &string);
 		dbg("Trying to get hotplug control for %s\n",
 				(char *)string.pointer);
-		status = pci_osc_control_set(handle, flags);
+		status = acpi_pci_osc_control_set(handle, flags);
 		if (ACPI_SUCCESS(status))
 			goto got_one;
 		kfree(string.pointer);
 		string = (struct acpi_buffer){ ACPI_ALLOCATE_BUFFER, NULL };
 	}
 
-	pdev = dev;
-	handle = DEVICE_ACPI_HANDLE(&dev->dev);
-	while (!handle) {
+	handle = DEVICE_ACPI_HANDLE(&pdev->dev);
+	if (!handle) {
 		/*
 		 * This hotplug controller was not listed in the ACPI name
 		 * space at all. Try to get acpi handle of parent pci bus.
 		 */
-		if (!pdev || !pdev->bus->parent)
-			break;
-		parent = pdev->bus->parent;
-		dbg("Could not find %s in acpi namespace, trying parent\n",
-		    pci_name(pdev));
-		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;
+		struct pci_bus *pbus;
+		for (pbus = pdev->bus; pbus; pbus = pbus->parent) {
+			handle = acpi_pci_get_bridge_handle(pbus);
+			if (handle)
+				break;
+		}
 	}
 
 	while (handle) {
@@ -453,13 +437,13 @@ int acpi_get_hp_hw_control_from_firmware(struct pci_dev *dev, u32 flags)
 	}
 
 	dbg("Cannot get control of hotplug hardware for pci %s\n",
-	    pci_name(dev));
+	    pci_name(pdev));
 
 	kfree(string.pointer);
 	return -ENODEV;
 got_one:
-	dbg("Gained control for hotplug HW for pci %s (%s)\n", pci_name(dev),
-			(char *)string.pointer);
+	dbg("Gained control for hotplug HW for pci %s (%s)\n",
+	    pci_name(pdev), (char *)string.pointer);
 	kfree(string.pointer);
 	return 0;
 }

drivers/pci/hotplug/pciehp.h

@@ -46,10 +46,10 @@ extern int pciehp_force;
 extern struct workqueue_struct *pciehp_wq;
 
 #define dbg(format, arg...)						\
-	do {								\
-		if (pciehp_debug)					\
-			printk("%s: " format, MY_NAME , ## arg);	\
-	} while (0)
+do {									\
+	if (pciehp_debug)						\
+		printk(KERN_DEBUG "%s: " format, MY_NAME , ## arg);	\
+} while (0)
 #define err(format, arg...)						\
 	printk(KERN_ERR "%s: " format, MY_NAME , ## arg)
 #define info(format, arg...)						\
@@ -60,7 +60,7 @@ extern struct workqueue_struct *pciehp_wq;
 #define ctrl_dbg(ctrl, format, arg...)					\
 	do {								\
 		if (pciehp_debug)					\
-			dev_printk(, &ctrl->pcie->device,		\
+			dev_printk(KERN_DEBUG, &ctrl->pcie->device,	\
 					format, ## arg);		\
 	} while (0)
 #define ctrl_err(ctrl, format, arg...)					\
@@ -108,10 +108,11 @@ struct controller {
 	u32 slot_cap;
 	u8 cap_base;
 	struct timer_list poll_timer;
-	int cmd_busy;
+	unsigned int cmd_busy:1;
 	unsigned int no_cmd_complete:1;
 	unsigned int link_active_reporting:1;
 	unsigned int notification_enabled:1;
+	unsigned int power_fault_detected;
 };
 
 #define INT_BUTTON_IGNORE		0

drivers/pci/hotplug/pciehp_acpi.c

@@ -67,37 +67,27 @@ static int __init parse_detect_mode(void)
 	return PCIEHP_DETECT_DEFAULT;
 }
 
-static struct pcie_port_service_id __initdata port_pci_ids[] = {
-	{
-		.vendor = PCI_ANY_ID,
-		.device = PCI_ANY_ID,
-		.port_type = PCIE_ANY_PORT,
-		.service_type = PCIE_PORT_SERVICE_HP,
-		.driver_data =  0,
-        }, { /* end: all zeroes */ }
-};
-
 static int __initdata dup_slot_id;
 static int __initdata acpi_slot_detected;
 static struct list_head __initdata dummy_slots = LIST_HEAD_INIT(dummy_slots);
 
 /* Dummy driver for dumplicate name detection */
-static int __init dummy_probe(struct pcie_device *dev,
-			      const struct pcie_port_service_id *id)
+static int __init dummy_probe(struct pcie_device *dev)
 {
 	int pos;
 	u32 slot_cap;
 	struct slot *slot, *tmp;
 	struct pci_dev *pdev = dev->port;
 	struct pci_bus *pbus = pdev->subordinate;
-	if (!(slot = kzalloc(sizeof(*slot), GFP_KERNEL)))
-		return -ENOMEM;
 	/* Note: pciehp_detect_mode != PCIEHP_DETECT_ACPI here */
 	if (pciehp_get_hp_hw_control_from_firmware(pdev))
 		return -ENODEV;
 	if (!(pos = pci_find_capability(pdev, PCI_CAP_ID_EXP)))
 		return -ENODEV;
 	pci_read_config_dword(pdev, pos + PCI_EXP_SLTCAP, &slot_cap);
+	slot = kzalloc(sizeof(*slot), GFP_KERNEL);
+	if (!slot)
+		return -ENOMEM;
 	slot->number = slot_cap >> 19;
 	list_for_each_entry(tmp, &dummy_slots, slot_list) {
 		if (tmp->number == slot->number)
@@ -111,7 +101,8 @@ static int __init dummy_probe(struct pcie_device *dev,
 
 static struct pcie_port_service_driver __initdata dummy_driver = {
         .name           = "pciehp_dummy",
-        .id_table       = port_pci_ids,
+	.port_type	= PCIE_ANY_PORT,
+	.service	= PCIE_PORT_SERVICE_HP,
         .probe          = dummy_probe,
 };
 

drivers/pci/hotplug/pciehp_core.c

@@ -401,7 +401,7 @@ static int get_cur_bus_speed(struct hotplug_slot *hotplug_slot, enum pci_bus_spe
 	return 0;
 }
 
-static int pciehp_probe(struct pcie_device *dev, const struct pcie_port_service_id *id)
+static int pciehp_probe(struct pcie_device *dev)
 {
 	int rc;
 	struct controller *ctrl;
@@ -475,7 +475,7 @@ static void pciehp_remove (struct pcie_device *dev)
 }
 
 #ifdef CONFIG_PM
-static int pciehp_suspend (struct pcie_device *dev, pm_message_t state)
+static int pciehp_suspend (struct pcie_device *dev)
 {
 	dev_info(&dev->device, "%s ENTRY\n", __func__);
 	return 0;
@@ -503,20 +503,12 @@ static int pciehp_resume (struct pcie_device *dev)
 	}
 	return 0;
 }
-#endif
-
-static struct pcie_port_service_id port_pci_ids[] = { {
-	.vendor = PCI_ANY_ID,
-	.device = PCI_ANY_ID,
-	.port_type = PCIE_ANY_PORT,
-	.service_type = PCIE_PORT_SERVICE_HP,
-	.driver_data =	0,
-	}, { /* end: all zeroes */ }
-};
+#endif /* PM */
 
 static struct pcie_port_service_driver hpdriver_portdrv = {
 	.name		= PCIE_MODULE_NAME,
-	.id_table	= &port_pci_ids[0],
+	.port_type	= PCIE_ANY_PORT,
+	.service	= PCIE_PORT_SERVICE_HP,
 
 	.probe		= pciehp_probe,
 	.remove		= pciehp_remove,

drivers/pci/hotplug/pciehp_hpc.c

@@ -548,23 +548,21 @@ static int hpc_power_on_slot(struct slot * slot)
 
 	slot_cmd = POWER_ON;
 	cmd_mask = PCI_EXP_SLTCTL_PCC;
-	/* Enable detection that we turned off at slot power-off time */
 	if (!pciehp_poll_mode) {
-		slot_cmd |= (PCI_EXP_SLTCTL_PFDE | PCI_EXP_SLTCTL_MRLSCE |
-			     PCI_EXP_SLTCTL_PDCE);
-		cmd_mask |= (PCI_EXP_SLTCTL_PFDE | PCI_EXP_SLTCTL_MRLSCE |
-			     PCI_EXP_SLTCTL_PDCE);
+		/* Enable power fault detection turned off at power off time */
+		slot_cmd |= PCI_EXP_SLTCTL_PFDE;
+		cmd_mask |= PCI_EXP_SLTCTL_PFDE;
 	}
 
 	retval = pcie_write_cmd(ctrl, slot_cmd, cmd_mask);
-
 	if (retval) {
 		ctrl_err(ctrl, "Write %x command failed!\n", slot_cmd);
-		return -1;
+		return retval;
 	}
 	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n",
 		 __func__, ctrl->cap_base + PCI_EXP_SLTCTL, slot_cmd);
 
+	ctrl->power_fault_detected = 0;
 	return retval;
 }
 
@@ -621,18 +619,10 @@ static int hpc_power_off_slot(struct slot * slot)
 
 	slot_cmd = POWER_OFF;
 	cmd_mask = PCI_EXP_SLTCTL_PCC;
-	/*
-	 * If we get MRL or presence detect interrupts now, the isr
-	 * will notice the sticky power-fault bit too and issue power
-	 * indicator change commands. This will lead to an endless loop
-	 * of command completions, since the power-fault bit remains on
-	 * till the slot is powered on again.
-	 */
 	if (!pciehp_poll_mode) {
-		slot_cmd &= ~(PCI_EXP_SLTCTL_PFDE | PCI_EXP_SLTCTL_MRLSCE |
-			      PCI_EXP_SLTCTL_PDCE);
-		cmd_mask |= (PCI_EXP_SLTCTL_PFDE | PCI_EXP_SLTCTL_MRLSCE |
-			     PCI_EXP_SLTCTL_PDCE);
+		/* Disable power fault detection */
+		slot_cmd &= ~PCI_EXP_SLTCTL_PFDE;
+		cmd_mask |= PCI_EXP_SLTCTL_PFDE;
 	}
 
 	retval = pcie_write_cmd(ctrl, slot_cmd, cmd_mask);
@@ -672,10 +662,11 @@ static irqreturn_t pcie_isr(int irq, void *dev_id)
 		detected &= (PCI_EXP_SLTSTA_ABP | PCI_EXP_SLTSTA_PFD |
 			     PCI_EXP_SLTSTA_MRLSC | PCI_EXP_SLTSTA_PDC |
 			     PCI_EXP_SLTSTA_CC);
+		detected &= ~intr_loc;
 		intr_loc |= detected;
 		if (!intr_loc)
 			return IRQ_NONE;
-		if (detected && pciehp_writew(ctrl, PCI_EXP_SLTSTA, detected)) {
+		if (detected && pciehp_writew(ctrl, PCI_EXP_SLTSTA, intr_loc)) {
 			ctrl_err(ctrl, "%s: Cannot write to SLOTSTATUS\n",
 				 __func__);
 			return IRQ_NONE;
@@ -709,9 +700,10 @@ static irqreturn_t pcie_isr(int irq, void *dev_id)
 		pciehp_handle_presence_change(p_slot);
 
 	/* Check Power Fault Detected */
-	if (intr_loc & PCI_EXP_SLTSTA_PFD)
+	if ((intr_loc & PCI_EXP_SLTSTA_PFD) && !ctrl->power_fault_detected) {
+		ctrl->power_fault_detected = 1;
 		pciehp_handle_power_fault(p_slot);
-
+	}
 	return IRQ_HANDLED;
 }
 

drivers/pci/hotplug/shpchp.h

@@ -48,10 +48,10 @@ extern int shpchp_debug;
 extern struct workqueue_struct *shpchp_wq;
 
 #define dbg(format, arg...)						\
-	do {								\
-		if (shpchp_debug)					\
-			printk("%s: " format, MY_NAME , ## arg);	\
-	} while (0)
+do {									\
+	if (shpchp_debug)						\
+		printk(KERN_DEBUG "%s: " format, MY_NAME , ## arg);	\
+} while (0)
 #define err(format, arg...)						\
 	printk(KERN_ERR "%s: " format, MY_NAME , ## arg)
 #define info(format, arg...)						\
@@ -62,7 +62,7 @@ extern struct workqueue_struct *shpchp_wq;
 #define ctrl_dbg(ctrl, format, arg...)					\
 	do {								\
 		if (shpchp_debug)					\
-			dev_printk(, &ctrl->pci_dev->dev,		\
+			dev_printk(KERN_DEBUG, &ctrl->pci_dev->dev,	\
 					format, ## arg);		\
 	} while (0)
 #define ctrl_err(ctrl, format, arg...)					\

drivers/pci/hotplug/shpchp_pci.c

@@ -137,7 +137,7 @@ int __ref shpchp_configure_device(struct slot *p_slot)
 							busnr))
 					break;
 			}
-			if (busnr >= end) {
+			if (busnr > end) {
 				ctrl_err(ctrl,
 					 "No free bus for hot-added bridge\n");
 				pci_dev_put(dev);

drivers/pci/intel-iommu.c

@@ -1782,7 +1782,7 @@ static inline void iommu_prepare_isa(void)
 	ret = iommu_prepare_identity_map(pdev, 0, 16*1024*1024);
 
 	if (ret)
-		printk("IOMMU: Failed to create 0-64M identity map, "
+		printk(KERN_ERR "IOMMU: Failed to create 0-64M identity map, "
 			"floppy might not work\n");
 
 }

drivers/pci/msi.h

@@ -20,14 +20,8 @@
 #define msi_mask_bits_reg(base, is64bit) \
 	( (is64bit == 1) ? base+PCI_MSI_MASK_BIT : base+PCI_MSI_MASK_BIT-4)
 #define msi_disable(control)		control &= ~PCI_MSI_FLAGS_ENABLE
-#define multi_msi_capable(control) \
-	(1 << ((control & PCI_MSI_FLAGS_QMASK) >> 1))
-#define multi_msi_enable(control, num) \
-	control |= (((num >> 1) << 4) & PCI_MSI_FLAGS_QSIZE);
 #define is_64bit_address(control)	(!!(control & PCI_MSI_FLAGS_64BIT))
 #define is_mask_bit_support(control)	(!!(control & PCI_MSI_FLAGS_MASKBIT))
-#define msi_enable(control, num) multi_msi_enable(control, num); \
-	control |= PCI_MSI_FLAGS_ENABLE
 
 #define msix_table_offset_reg(base)	(base + 0x04)
 #define msix_pba_offset_reg(base)	(base + 0x08)

drivers/pci/pci-acpi.c

@@ -18,221 +18,6 @@
 #include <linux/pci-acpi.h>
 #include "pci.h"
 
-struct acpi_osc_data {
-	acpi_handle handle;
-	u32 support_set;
-	u32 control_set;
-	u32 control_query;
-	int is_queried;
-	struct list_head sibiling;
-};
-static LIST_HEAD(acpi_osc_data_list);
-
-struct acpi_osc_args {
-	u32 capbuf[3];
-};
-
-static DEFINE_MUTEX(pci_acpi_lock);
-
-static struct acpi_osc_data *acpi_get_osc_data(acpi_handle handle)
-{
-	struct acpi_osc_data *data;
-
-	list_for_each_entry(data, &acpi_osc_data_list, sibiling) {
-		if (data->handle == handle)
-			return data;
-	}
-	data = kzalloc(sizeof(*data), GFP_KERNEL);
-	if (!data)
-		return NULL;
-	INIT_LIST_HEAD(&data->sibiling);
-	data->handle = handle;
-	list_add_tail(&data->sibiling, &acpi_osc_data_list);
-	return data;
-}
-
-static u8 OSC_UUID[16] = {0x5B, 0x4D, 0xDB, 0x33, 0xF7, 0x1F, 0x1C, 0x40,
-			  0x96, 0x57, 0x74, 0x41, 0xC0, 0x3D, 0xD7, 0x66};
-
-static acpi_status acpi_run_osc(acpi_handle handle,
-				struct acpi_osc_args *osc_args, u32 *retval)
-{
-	acpi_status status;
-	struct acpi_object_list input;
-	union acpi_object in_params[4];
-	struct acpi_buffer output = {ACPI_ALLOCATE_BUFFER, NULL};
-	union acpi_object *out_obj;
-	u32 errors, flags = osc_args->capbuf[OSC_QUERY_TYPE];
-
-	/* Setting up input parameters */
-	input.count = 4;
-	input.pointer = in_params;
-	in_params[0].type 		= ACPI_TYPE_BUFFER;
-	in_params[0].buffer.length 	= 16;
-	in_params[0].buffer.pointer	= OSC_UUID;
-	in_params[1].type 		= ACPI_TYPE_INTEGER;
-	in_params[1].integer.value 	= 1;
-	in_params[2].type 		= ACPI_TYPE_INTEGER;
-	in_params[2].integer.value	= 3;
-	in_params[3].type		= ACPI_TYPE_BUFFER;
-	in_params[3].buffer.length 	= 12;
-	in_params[3].buffer.pointer 	= (u8 *)osc_args->capbuf;
-
-	status = acpi_evaluate_object(handle, "_OSC", &input, &output);
-	if (ACPI_FAILURE(status))
-		return status;
-
-	if (!output.length)
-		return AE_NULL_OBJECT;
-
-	out_obj = output.pointer;
-	if (out_obj->type != ACPI_TYPE_BUFFER) {
-		printk(KERN_DEBUG "Evaluate _OSC returns wrong type\n");
-		status = AE_TYPE;
-		goto out_kfree;
-	}
-	/* Need to ignore the bit0 in result code */
-	errors = *((u32 *)out_obj->buffer.pointer) & ~(1 << 0);
-	if (errors) {
-		if (errors & OSC_REQUEST_ERROR)
-			printk(KERN_DEBUG "_OSC request fails\n"); 
-		if (errors & OSC_INVALID_UUID_ERROR)
-			printk(KERN_DEBUG "_OSC invalid UUID\n"); 
-		if (errors & OSC_INVALID_REVISION_ERROR)
-			printk(KERN_DEBUG "_OSC invalid revision\n"); 
-		if (errors & OSC_CAPABILITIES_MASK_ERROR) {
-			if (flags & OSC_QUERY_ENABLE)
-				goto out_success;
-			printk(KERN_DEBUG "_OSC FW not grant req. control\n");
-			status = AE_SUPPORT;
-			goto out_kfree;
-		}
-		status = AE_ERROR;
-		goto out_kfree;
-	}
-out_success:
-	*retval = *((u32 *)(out_obj->buffer.pointer + 8));
-	status = AE_OK;
-
-out_kfree:
-	kfree(output.pointer);
-	return status;
-}
-
-static acpi_status __acpi_query_osc(u32 flags, struct acpi_osc_data *osc_data)
-{
-	acpi_status status;
-	u32 support_set, result;
-	struct acpi_osc_args osc_args;
-
-	/* do _OSC query for all possible controls */
-	support_set = osc_data->support_set | (flags & OSC_SUPPORT_MASKS);
-	osc_args.capbuf[OSC_QUERY_TYPE] = OSC_QUERY_ENABLE;
-	osc_args.capbuf[OSC_SUPPORT_TYPE] = support_set;
-	osc_args.capbuf[OSC_CONTROL_TYPE] = OSC_CONTROL_MASKS;
-
-	status = acpi_run_osc(osc_data->handle, &osc_args, &result);
-	if (ACPI_SUCCESS(status)) {
-		osc_data->support_set = support_set;
-		osc_data->control_query = result;
-		osc_data->is_queried = 1;
-	}
-
-	return status;
-}
-
-/*
- * pci_acpi_osc_support: Invoke _OSC indicating support for the given feature
- * @flags: Bitmask of flags to support
- *
- * See the ACPI spec for the definition of the flags
- */
-int pci_acpi_osc_support(acpi_handle handle, u32 flags)
-{
-	acpi_status status;
-	acpi_handle tmp;
-	struct acpi_osc_data *osc_data;
-	int rc = 0;
-
-	status = acpi_get_handle(handle, "_OSC", &tmp);
-	if (ACPI_FAILURE(status))
-		return -ENOTTY;
-
-	mutex_lock(&pci_acpi_lock);
-	osc_data = acpi_get_osc_data(handle);
-	if (!osc_data) {
-		printk(KERN_ERR "acpi osc data array is full\n");
-		rc = -ENOMEM;
-		goto out;
-	}
-
-	__acpi_query_osc(flags, osc_data);
-out:
-	mutex_unlock(&pci_acpi_lock);
-	return rc;
-}
-
-/**
- * pci_osc_control_set - commit requested control to Firmware
- * @handle: acpi_handle for the target ACPI object
- * @flags: driver's requested control bits
- *
- * Attempt to take control from Firmware on requested control bits.
- **/
-acpi_status pci_osc_control_set(acpi_handle handle, u32 flags)
-{
-	acpi_status status;
-	u32 control_req, control_set, result;
-	acpi_handle tmp;
-	struct acpi_osc_data *osc_data;
-	struct acpi_osc_args osc_args;
-
-	status = acpi_get_handle(handle, "_OSC", &tmp);
-	if (ACPI_FAILURE(status))
-		return status;
-
-	mutex_lock(&pci_acpi_lock);
-	osc_data = acpi_get_osc_data(handle);
-	if (!osc_data) {
-		printk(KERN_ERR "acpi osc data array is full\n");
-		status = AE_ERROR;
-		goto out;
-	}
-
-	control_req = (flags & OSC_CONTROL_MASKS);
-	if (!control_req) {
-		status = AE_TYPE;
-		goto out;
-	}
-
-	/* No need to evaluate _OSC if the control was already granted. */
-	if ((osc_data->control_set & control_req) == control_req)
-		goto out;
-
-	if (!osc_data->is_queried) {
-		status = __acpi_query_osc(osc_data->support_set, osc_data);
-		if (ACPI_FAILURE(status))
-			goto out;
-	}
-
-	if ((osc_data->control_query & control_req) != control_req) {
-		status = AE_SUPPORT;
-		goto out;
-	}
-
-	control_set = osc_data->control_set | control_req;
-	osc_args.capbuf[OSC_QUERY_TYPE] = 0;
-	osc_args.capbuf[OSC_SUPPORT_TYPE] = osc_data->support_set;
-	osc_args.capbuf[OSC_CONTROL_TYPE] = control_set;
-	status = acpi_run_osc(handle, &osc_args, &result);
-	if (ACPI_SUCCESS(status))
-		osc_data->control_set = result;
-out:
-	mutex_unlock(&pci_acpi_lock);
-	return status;
-}
-EXPORT_SYMBOL(pci_osc_control_set);
-
 /*
  * _SxD returns the D-state with the highest power
  * (lowest D-state number) supported in the S-state "x".

drivers/pci/pci-driver.c

@@ -99,6 +99,52 @@ store_new_id(struct device_driver *driver, const char *buf, size_t count)
 }
 static DRIVER_ATTR(new_id, S_IWUSR, NULL, store_new_id);
 
+/**
+ * store_remove_id - remove a PCI device ID from this driver
+ * @driver: target device driver
+ * @buf: buffer for scanning device ID data
+ * @count: input size
+ *
+ * Removes a dynamic pci device ID to this driver.
+ */
+static ssize_t
+store_remove_id(struct device_driver *driver, const char *buf, size_t count)
+{
+	struct pci_dynid *dynid, *n;
+	struct pci_driver *pdrv = to_pci_driver(driver);
+	__u32 vendor, device, subvendor = PCI_ANY_ID,
+		subdevice = PCI_ANY_ID, class = 0, class_mask = 0;
+	int fields = 0;
+	int retval = -ENODEV;
+
+	fields = sscanf(buf, "%x %x %x %x %x %x",
+			&vendor, &device, &subvendor, &subdevice,
+			&class, &class_mask);
+	if (fields < 2)
+		return -EINVAL;
+
+	spin_lock(&pdrv->dynids.lock);
+	list_for_each_entry_safe(dynid, n, &pdrv->dynids.list, node) {
+		struct pci_device_id *id = &dynid->id;
+		if ((id->vendor == vendor) &&
+		    (id->device == device) &&
+		    (subvendor == PCI_ANY_ID || id->subvendor == subvendor) &&
+		    (subdevice == PCI_ANY_ID || id->subdevice == subdevice) &&
+		    !((id->class ^ class) & class_mask)) {
+			list_del(&dynid->node);
+			kfree(dynid);
+			retval = 0;
+			break;
+		}
+	}
+	spin_unlock(&pdrv->dynids.lock);
+
+	if (retval)
+		return retval;
+	return count;
+}
+static DRIVER_ATTR(remove_id, S_IWUSR, NULL, store_remove_id);
+
 static void
 pci_free_dynids(struct pci_driver *drv)
 {
@@ -125,6 +171,20 @@ static void pci_remove_newid_file(struct pci_driver *drv)
 {
 	driver_remove_file(&drv->driver, &driver_attr_new_id);
 }
+
+static int
+pci_create_removeid_file(struct pci_driver *drv)
+{
+	int error = 0;
+	if (drv->probe != NULL)
+		error = driver_create_file(&drv->driver,&driver_attr_remove_id);
+	return error;
+}
+
+static void pci_remove_removeid_file(struct pci_driver *drv)
+{
+	driver_remove_file(&drv->driver, &driver_attr_remove_id);
+}
 #else /* !CONFIG_HOTPLUG */
 static inline void pci_free_dynids(struct pci_driver *drv) {}
 static inline int pci_create_newid_file(struct pci_driver *drv)
@@ -132,6 +192,11 @@ static inline int pci_create_newid_file(struct pci_driver *drv)
 	return 0;
 }
 static inline void pci_remove_newid_file(struct pci_driver *drv) {}
+static inline int pci_create_removeid_file(struct pci_driver *drv)
+{
+	return 0;
+}
+static inline void pci_remove_removeid_file(struct pci_driver *drv) {}
 #endif
 
 /**
@@ -899,13 +964,23 @@ int __pci_register_driver(struct pci_driver *drv, struct module *owner,
 	/* register with core */
 	error = driver_register(&drv->driver);
 	if (error)
-		return error;
+		goto out;
 
 	error = pci_create_newid_file(drv);
 	if (error)
-		driver_unregister(&drv->driver);
+		goto out_newid;
 
+	error = pci_create_removeid_file(drv);
+	if (error)
+		goto out_removeid;
+out:
 	return error;
+
+out_removeid:
+	pci_remove_newid_file(drv);
+out_newid:
+	driver_unregister(&drv->driver);
+	goto out;
 }
 
 /**
@@ -921,6 +996,7 @@ int __pci_register_driver(struct pci_driver *drv, struct module *owner,
 void
 pci_unregister_driver(struct pci_driver *drv)
 {
+	pci_remove_removeid_file(drv);
 	pci_remove_newid_file(drv);
 	driver_unregister(&drv->driver);
 	pci_free_dynids(drv);
@@ -1020,6 +1096,7 @@ struct bus_type pci_bus_type = {
 	.remove		= pci_device_remove,
 	.shutdown	= pci_device_shutdown,
 	.dev_attrs	= pci_dev_attrs,
+	.bus_attrs	= pci_bus_attrs,
 	.pm		= PCI_PM_OPS_PTR,
 };
 

drivers/pci/pci-sysfs.c

@@ -219,6 +219,83 @@ msi_bus_store(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
+#ifdef CONFIG_HOTPLUG
+static DEFINE_MUTEX(pci_remove_rescan_mutex);
+static ssize_t bus_rescan_store(struct bus_type *bus, const char *buf,
+				size_t count)
+{
+	unsigned long val;
+	struct pci_bus *b = NULL;
+
+	if (strict_strtoul(buf, 0, &val) < 0)
+		return -EINVAL;
+
+	if (val) {
+		mutex_lock(&pci_remove_rescan_mutex);
+		while ((b = pci_find_next_bus(b)) != NULL)
+			pci_rescan_bus(b);
+		mutex_unlock(&pci_remove_rescan_mutex);
+	}
+	return count;
+}
+
+struct bus_attribute pci_bus_attrs[] = {
+	__ATTR(rescan, (S_IWUSR|S_IWGRP), NULL, bus_rescan_store),
+	__ATTR_NULL
+};
+
+static ssize_t
+dev_rescan_store(struct device *dev, struct device_attribute *attr,
+		 const char *buf, size_t count)
+{
+	unsigned long val;
+	struct pci_dev *pdev = to_pci_dev(dev);
+
+	if (strict_strtoul(buf, 0, &val) < 0)
+		return -EINVAL;
+
+	if (val) {
+		mutex_lock(&pci_remove_rescan_mutex);
+		pci_rescan_bus(pdev->bus);
+		mutex_unlock(&pci_remove_rescan_mutex);
+	}
+	return count;
+}
+
+static void remove_callback(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+
+	mutex_lock(&pci_remove_rescan_mutex);
+	pci_remove_bus_device(pdev);
+	mutex_unlock(&pci_remove_rescan_mutex);
+}
+
+static ssize_t
+remove_store(struct device *dev, struct device_attribute *dummy,
+	     const char *buf, size_t count)
+{
+	int ret = 0;
+	unsigned long val;
+	struct pci_dev *pdev = to_pci_dev(dev);
+
+	if (strict_strtoul(buf, 0, &val) < 0)
+		return -EINVAL;
+
+	if (pci_is_root_bus(pdev->bus))
+		return -EBUSY;
+
+	/* An attribute cannot be unregistered by one of its own methods,
+	 * so we have to use this roundabout approach.
+	 */
+	if (val)
+		ret = device_schedule_callback(dev, remove_callback);
+	if (ret)
+		count = ret;
+	return count;
+}
+#endif
+
 struct device_attribute pci_dev_attrs[] = {
 	__ATTR_RO(resource),
 	__ATTR_RO(vendor),
@@ -237,9 +314,24 @@ struct device_attribute pci_dev_attrs[] = {
 	__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),
+#ifdef CONFIG_HOTPLUG
+	__ATTR(remove, (S_IWUSR|S_IWGRP), NULL, remove_store),
+	__ATTR(rescan, (S_IWUSR|S_IWGRP), NULL, dev_rescan_store),
+#endif
 	__ATTR_NULL,
 };
 
+static ssize_t
+boot_vga_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+
+	return sprintf(buf, "%u\n",
+		!!(pdev->resource[PCI_ROM_RESOURCE].flags &
+		   IORESOURCE_ROM_SHADOW));
+}
+struct device_attribute vga_attr = __ATTR_RO(boot_vga);
+
 static ssize_t
 pci_read_config(struct kobject *kobj, struct bin_attribute *bin_attr,
 		char *buf, loff_t off, size_t count)
@@ -492,6 +584,19 @@ pci_mmap_legacy_io(struct kobject *kobj, struct bin_attribute *attr,
         return pci_mmap_legacy_page_range(bus, vma, pci_mmap_io);
 }
 
+/**
+ * pci_adjust_legacy_attr - adjustment of legacy file attributes
+ * @b: bus to create files under
+ * @mmap_type: I/O port or memory
+ *
+ * Stub implementation. Can be overridden by arch if necessary.
+ */
+void __weak
+pci_adjust_legacy_attr(struct pci_bus *b, enum pci_mmap_state mmap_type)
+{
+	return;
+}
+
 /**
  * pci_create_legacy_files - create legacy I/O port and memory files
  * @b: bus to create files under
@@ -518,6 +623,7 @@ void pci_create_legacy_files(struct pci_bus *b)
 	b->legacy_io->read = pci_read_legacy_io;
 	b->legacy_io->write = pci_write_legacy_io;
 	b->legacy_io->mmap = pci_mmap_legacy_io;
+	pci_adjust_legacy_attr(b, pci_mmap_io);
 	error = device_create_bin_file(&b->dev, b->legacy_io);
 	if (error)
 		goto legacy_io_err;
@@ -528,6 +634,7 @@ void pci_create_legacy_files(struct pci_bus *b)
 	b->legacy_mem->size = 1024*1024;
 	b->legacy_mem->attr.mode = S_IRUSR | S_IWUSR;
 	b->legacy_mem->mmap = pci_mmap_legacy_mem;
+	pci_adjust_legacy_attr(b, pci_mmap_mem);
 	error = device_create_bin_file(&b->dev, b->legacy_mem);
 	if (error)
 		goto legacy_mem_err;
@@ -719,8 +826,8 @@ static int pci_create_resource_files(struct pci_dev *pdev)
 	return 0;
 }
 #else /* !HAVE_PCI_MMAP */
-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; }
+int __weak pci_create_resource_files(struct pci_dev *dev) { return 0; }
+void __weak pci_remove_resource_files(struct pci_dev *dev) { return; }
 #endif /* HAVE_PCI_MMAP */
 
 /**
@@ -884,18 +991,27 @@ int __must_check pci_create_sysfs_dev_files (struct pci_dev *pdev)
 		pdev->rom_attr = attr;
 	}
 
+	if ((pdev->class >> 8) == PCI_CLASS_DISPLAY_VGA) {
+		retval = device_create_file(&pdev->dev, &vga_attr);
+		if (retval)
+			goto err_rom_file;
+	}
+
 	/* add platform-specific attributes */
 	retval = pcibios_add_platform_entries(pdev);
 	if (retval)
-		goto err_rom_file;
+		goto err_vga_file;
 
 	/* add sysfs entries for various capabilities */
 	retval = pci_create_capabilities_sysfs(pdev);
 	if (retval)
-		goto err_rom_file;
+		goto err_vga_file;
 
 	return 0;
 
+err_vga_file:
+	if ((pdev->class >> 8) == PCI_CLASS_DISPLAY_VGA)
+		device_remove_file(&pdev->dev, &vga_attr);
 err_rom_file:
 	if (rom_size) {
 		sysfs_remove_bin_file(&pdev->dev.kobj, pdev->rom_attr);

drivers/pci/pcie/aer/aerdrv_acpi.c

@@ -38,7 +38,7 @@ int aer_osc_setup(struct pcie_device *pciedev)
 
 	handle = acpi_find_root_bridge_handle(pdev);
 	if (handle) {
-		status = pci_osc_control_set(handle,
+		status = acpi_pci_osc_control_set(handle,
 					OSC_PCI_EXPRESS_AER_CONTROL |
 					OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL);
 	}

drivers/pci/pcie/aer/aerdrv_core.c

@@ -351,21 +351,21 @@ 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)
+		struct pcie_port_data *port_data;
+
+		port_data = pci_get_drvdata(to_pcie_device(device)->port);
+		if (port_data->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) {
+			if (service_driver->service == PCIE_PORT_SERVICE_AER) {
 				result->aer_driver = service_driver;
 				return 1;
 			}