27 files changed, 647 insertions, 188 deletions

diff --git a/Documentation/ABI/testing/sysfs-bus-pci b/Documentation/ABI/testing/sysfs-bus-pci
index dff1f48d252..1ce5ae329c0 100644
--- a/Documentation/ABI/testing/sysfs-bus-pci
+++ b/Documentation/ABI/testing/sysfs-bus-pci
@@ -222,3 +222,37 @@ Description:
 		satisfied too.  Reading this attribute will show the current
 		value of d3cold_allowed bit.  Writing this attribute will set
 		the value of d3cold_allowed bit.
+
+What:		/sys/bus/pci/devices/.../sriov_totalvfs
+Date:		November 2012
+Contact:	Donald Dutile <ddutile@redhat.com>
+Description:
+		This file appears when a physical PCIe device supports SR-IOV.
+		Userspace applications can read this file to determine the
+		maximum number of Virtual Functions (VFs) a PCIe physical
+		function (PF) can support. Typically, this is the value reported
+		in the PF's SR-IOV extended capability structure's TotalVFs
+		element.  Drivers have the ability at probe time to reduce the
+		value read from this file via the pci_sriov_set_totalvfs()
+		function.
+
+What:		/sys/bus/pci/devices/.../sriov_numvfs
+Date:		November 2012
+Contact:	Donald Dutile <ddutile@redhat.com>
+Description:
+		This file appears when a physical PCIe device supports SR-IOV.
+		Userspace applications can read and write to this file to
+		determine and control the enablement or disablement of Virtual
+		Functions (VFs) on the physical function (PF). A read of this
+		file will return the number of VFs that are enabled on this PF.
+		A number written to this file will enable the specified
+		number of VFs. A userspace application would typically read the
+		file and check that the value is zero, and then write the number
+		of VFs that should be enabled on the PF; the value written
+		should be less than or equal to the value in the sriov_totalvfs
+		file. A userspace application wanting to disable the VFs would
+		write a zero to this file. The core ensures that valid values
+		are written to this file, and returns errors when values are not
+		valid.  For example, writing a 2 to this file when sriov_numvfs
+		is not 0 and not 2 already will return an error. Writing a 10
+		when the value of sriov_totalvfs is 8 will return an error.
diff --git a/Documentation/PCI/pci-iov-howto.txt b/Documentation/PCI/pci-iov-howto.txt
index fc73ef5d65b..cfaca7e6989 100644
--- a/Documentation/PCI/pci-iov-howto.txt
+++ b/Documentation/PCI/pci-iov-howto.txt
@@ -2,6 +2,9 @@
 		Copyright (C) 2009 Intel Corporation
 		    Yu Zhao <yu.zhao@intel.com>
 
+		Update: November 2012
+			-- sysfs-based SRIOV enable-/disable-ment
+		Donald Dutile <ddutile@redhat.com>
 
 1. Overview
 
@@ -24,10 +27,21 @@ real existing PCI device.
 
 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.
+Multiple methods are available for SR-IOV enablement.
+In the first method, 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.  Some PF drivers require
+a module parameter to be set to determine the number of VFs to enable.
+In the second method, a write to the sysfs file sriov_numvfs will
+enable and disable the VFs associated with a PCIe PF.  This method
+enables per-PF, VF enable/disable values versus the first method,
+which applies to all PFs of the same device.  Additionally, the
+PCI SRIOV core support ensures that enable/disable operations are
+valid to reduce duplication in multiple drivers for the same
+checks, e.g., check numvfs == 0 if enabling VFs, ensure
+numvfs <= totalvfs.
+The second method is the recommended method for new/future VF devices.
 
 2.2 How can I use the Virtual Functions
 
@@ -40,13 +54,22 @@ requires device driver that is same as a normal PCI device's.
 3.1 SR-IOV API
 
 To enable SR-IOV capability:
+(a) For the first method, in the driver:
 	int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn);
 	'nr_virtfn' is number of VFs to be enabled.
+(b) For the second method, from sysfs:
+	echo 'nr_virtfn' > \
+        /sys/bus/pci/devices/<DOMAIN:BUS:DEVICE.FUNCTION>/sriov_numvfs
 
 To disable SR-IOV capability:
+(a) For the first method, in the driver:
 	void pci_disable_sriov(struct pci_dev *dev);
+(b) For the second method, from sysfs:
+	echo  0 > \
+        /sys/bus/pci/devices/<DOMAIN:BUS:DEVICE.FUNCTION>/sriov_numvfs
 
 To notify SR-IOV core of Virtual Function Migration:
+(a) In the driver:
 	irqreturn_t pci_sriov_migration(struct pci_dev *dev);
 
 3.2 Usage example
@@ -88,6 +111,22 @@ static void dev_shutdown(struct pci_dev *dev)
 	...
 }
 
+static int dev_sriov_configure(struct pci_dev *dev, int numvfs)
+{
+	if (numvfs > 0) {
+		...
+		pci_enable_sriov(dev, numvfs);
+		...
+		return numvfs;
+	}
+	if (numvfs == 0) {
+		....
+		pci_disable_sriov(dev);
+		...
+		return 0;
+	}
+}
+
 static struct pci_driver dev_driver = {
 	.name =		"SR-IOV Physical Function driver",
 	.id_table =	dev_id_table,
@@ -96,4 +135,5 @@ static struct pci_driver dev_driver = {
 	.suspend =	dev_suspend,
 	.resume =	dev_resume,
 	.shutdown =	dev_shutdown,
+	.sriov_configure = dev_sriov_configure,
 };
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 192397c9860..0c01261fe5a 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -12,6 +12,7 @@ struct pci_root_info {
 	char name[16];
 	unsigned int res_num;
 	struct resource *res;
+	resource_size_t *res_offset;
 	struct pci_sysdata sd;
 #ifdef	CONFIG_PCI_MMCONFIG
 	bool mcfg_added;
@@ -22,6 +23,7 @@ struct pci_root_info {
 };
 
 static bool pci_use_crs = true;
+static bool pci_ignore_seg = false;
 
 static int __init set_use_crs(const struct dmi_system_id *id)
 {
@@ -35,7 +37,14 @@ static int __init set_nouse_crs(const struct dmi_system_id *id)
 	return 0;
 }
 
-static const struct dmi_system_id pci_use_crs_table[] __initconst = {
+static int __init set_ignore_seg(const struct dmi_system_id *id)
+{
+	printk(KERN_INFO "PCI: %s detected: ignoring ACPI _SEG\n", id->ident);
+	pci_ignore_seg = true;
+	return 0;
+}
+
+static const struct dmi_system_id pci_crs_quirks[] __initconst = {
 	/* http://bugzilla.kernel.org/show_bug.cgi?id=14183 */
 	{
 		.callback = set_use_crs,
@@ -98,6 +107,16 @@ static const struct dmi_system_id pci_use_crs_table[] __initconst = {
 			DMI_MATCH(DMI_BIOS_VERSION, "6JET85WW (1.43 )"),
 		},
 	},
+
+	/* https://bugzilla.kernel.org/show_bug.cgi?id=15362 */
+	{
+		.callback = set_ignore_seg,
+		.ident = "HP xw9300",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HP xw9300 Workstation"),
+		},
+	},
 	{}
 };
 
@@ -108,7 +127,7 @@ void __init pci_acpi_crs_quirks(void)
 	if (dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL) && year < 2008)
 		pci_use_crs = false;
 
-	dmi_check_system(pci_use_crs_table);
+	dmi_check_system(pci_crs_quirks);
 
 	/*
 	 * If the user specifies "pci=use_crs" or "pci=nocrs" explicitly, that
@@ -305,6 +324,7 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
 	res->flags = flags;
 	res->start = start;
 	res->end = end;
+	info->res_offset[info->res_num] = addr.translation_offset;
 
 	if (!pci_use_crs) {
 		dev_printk(KERN_DEBUG, &info->bridge->dev,
@@ -374,7 +394,8 @@ static void add_resources(struct pci_root_info *info,
 				 "ignoring host bridge window %pR (conflicts with %s %pR)\n",
 				 res, conflict->name, conflict);
 		else
-			pci_add_resource(resources, res);
+			pci_add_resource_offset(resources, res,
+					info->res_offset[i]);
 	}
 }
 
@@ -382,6 +403,8 @@ static void free_pci_root_info_res(struct pci_root_info *info)
 {
 	kfree(info->res);
 	info->res = NULL;
+	kfree(info->res_offset);
+	info->res_offset = NULL;
 	info->res_num = 0;
 }
 
@@ -432,10 +455,20 @@ probe_pci_root_info(struct pci_root_info *info, struct acpi_device *device,
 		return;
 
 	size = sizeof(*info->res) * info->res_num;
-	info->res_num = 0;
 	info->res = kzalloc(size, GFP_KERNEL);
-	if (!info->res)
+	if (!info->res) {
+		info->res_num = 0;
+		return;
+	}
+
+	size = sizeof(*info->res_offset) * info->res_num;
+	info->res_num = 0;
+	info->res_offset = kzalloc(size, GFP_KERNEL);
+	if (!info->res_offset) {
+		kfree(info->res);
+		info->res = NULL;
 		return;
+	}
 
 	acpi_walk_resources(device->handle, METHOD_NAME__CRS, setup_resource,
 				info);
@@ -455,6 +488,9 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_pci_root *root)
 	int pxm;
 #endif
 
+	if (pci_ignore_seg)
+		domain = 0;
+
 	if (domain && !pci_domains_supported) {
 		printk(KERN_WARNING "pci_bus %04x:%02x: "
 		       "ignored (multiple domains not supported)\n",
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 720e973fc34..52dbf1aeeb6 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -626,7 +626,7 @@ void pcibios_disable_device (struct pci_dev *dev)
 		pcibios_disable_irq(dev);
 }
 
-int pci_ext_cfg_avail(struct pci_dev *dev)
+int pci_ext_cfg_avail(void)
 {
 	if (raw_pci_ext_ops)
 		return 1;
diff --git a/drivers/acpi/pci_bind.c b/drivers/acpi/pci_bind.c
index 2ef04098cc1..a1dee29beed 100644
--- a/drivers/acpi/pci_bind.c
+++ b/drivers/acpi/pci_bind.c
@@ -45,11 +45,12 @@ static int acpi_pci_unbind(struct acpi_device *device)
 
 	device_set_run_wake(&dev->dev, false);
 	pci_acpi_remove_pm_notifier(device);
+	acpi_power_resource_unregister_device(&dev->dev, device->handle);
 
 	if (!dev->subordinate)
 		goto out;
 
-	acpi_pci_irq_del_prt(dev->subordinate);
+	acpi_pci_irq_del_prt(pci_domain_nr(dev->bus), dev->subordinate->number);
 
 	device->ops.bind = NULL;
 	device->ops.unbind = NULL;
@@ -63,7 +64,7 @@ static int acpi_pci_bind(struct acpi_device *device)
 {
 	acpi_status status;
 	acpi_handle handle;
-	struct pci_bus *bus;
+	unsigned char bus;
 	struct pci_dev *dev;
 
 	dev = acpi_get_pci_dev(device->handle);
@@ -71,6 +72,7 @@ static int acpi_pci_bind(struct acpi_device *device)
 		return 0;
 
 	pci_acpi_add_pm_notifier(device, dev);
+	acpi_power_resource_register_device(&dev->dev, device->handle);
 	if (device->wakeup.flags.run_wake)
 		device_set_run_wake(&dev->dev, true);
 
@@ -100,11 +102,11 @@ static int acpi_pci_bind(struct acpi_device *device)
 		goto out;
 
 	if (dev->subordinate)
-		bus = dev->subordinate;
+		bus = dev->subordinate->number;
 	else
-		bus = dev->bus;
+		bus = dev->bus->number;
 
-	acpi_pci_irq_add_prt(device->handle, bus);
+	acpi_pci_irq_add_prt(device->handle, pci_domain_nr(dev->bus), bus);
 
 out:
 	pci_dev_put(dev);
diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c
index 0eefa12e648..8835cc38aa3 100644
--- a/drivers/acpi/pci_irq.c
+++ b/drivers/acpi/pci_irq.c
@@ -184,7 +184,7 @@ static void do_prt_fixups(struct acpi_prt_entry *entry,
 	}
 }
 
-static int acpi_pci_irq_add_entry(acpi_handle handle, struct pci_bus *bus,
+static int acpi_pci_irq_add_entry(acpi_handle handle, int segment, int bus,
 				  struct acpi_pci_routing_table *prt)
 {
 	struct acpi_prt_entry *entry;
@@ -198,8 +198,8 @@ static int acpi_pci_irq_add_entry(acpi_handle handle, struct pci_bus *bus,
 	 * 1=INTA, 2=INTB.  We use the PCI encoding throughout, so convert
 	 * it here.
 	 */
-	entry->id.segment = pci_domain_nr(bus);
-	entry->id.bus = bus->number;
+	entry->id.segment = segment;
+	entry->id.bus = bus;
 	entry->id.device = (prt->address >> 16) & 0xFFFF;
 	entry->pin = prt->pin + 1;
 
@@ -244,7 +244,7 @@ static int acpi_pci_irq_add_entry(acpi_handle handle, struct pci_bus *bus,
 	return 0;
 }
 
-int acpi_pci_irq_add_prt(acpi_handle handle, struct pci_bus *bus)
+int acpi_pci_irq_add_prt(acpi_handle handle, int segment, int bus)
 {
 	acpi_status status;
 	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
@@ -273,7 +273,7 @@ int acpi_pci_irq_add_prt(acpi_handle handle, struct pci_bus *bus)
 
 	entry = buffer.pointer;
 	while (entry && (entry->length > 0)) {
-		acpi_pci_irq_add_entry(handle, bus, entry);
+		acpi_pci_irq_add_entry(handle, segment, bus, entry);
 		entry = (struct acpi_pci_routing_table *)
 		    ((unsigned long)entry + entry->length);
 	}
@@ -282,17 +282,16 @@ int acpi_pci_irq_add_prt(acpi_handle handle, struct pci_bus *bus)
 	return 0;
 }
 
-void acpi_pci_irq_del_prt(struct pci_bus *bus)
+void acpi_pci_irq_del_prt(int segment, int bus)
 {
 	struct acpi_prt_entry *entry, *tmp;
 
 	printk(KERN_DEBUG
 	       "ACPI: Delete PCI Interrupt Routing Table for %04x:%02x\n",
-	       pci_domain_nr(bus), bus->number);
+	       segment, bus);
 	spin_lock(&acpi_prt_lock);
 	list_for_each_entry_safe(entry, tmp, &acpi_prt_list, list) {
-		if (pci_domain_nr(bus) == entry->id.segment
-			&& bus->number == entry->id.bus) {
+		if (segment == entry->id.segment && bus == entry->id.bus) {
 			list_del(&entry->list);
 			kfree(entry);
 		}
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index bce469c0b48..ab781f00e32 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -454,6 +454,7 @@ static int __devinit acpi_pci_root_add(struct acpi_device *device)
 	acpi_handle handle;
 	struct acpi_device *child;
 	u32 flags, base_flags;
+	bool is_osc_granted = false;
 
 	root = kzalloc(sizeof(struct acpi_pci_root), GFP_KERNEL);
 	if (!root)
@@ -501,85 +502,47 @@ static int __devinit acpi_pci_root_add(struct acpi_device *device)
 	strcpy(acpi_device_class(device), ACPI_PCI_ROOT_CLASS);
 	device->driver_data = root;
 
-	root->mcfg_addr = acpi_pci_root_get_mcfg_addr(device->handle);
-
-	/*
-	 * All supported architectures that use ACPI have support for
-	 * PCI domains, so we indicate this in _OSC support capabilities.
-	 */
-	flags = base_flags = OSC_PCI_SEGMENT_GROUPS_SUPPORT;
-	acpi_pci_osc_support(root, flags);
-
-	/*
-	 * TBD: Need PCI interface for enumeration/configuration of roots.
-	 */
-
-	mutex_lock(&acpi_pci_root_lock);
-	list_add_tail(&root->node, &acpi_pci_roots);
-	mutex_unlock(&acpi_pci_root_lock);
-
 	printk(KERN_INFO PREFIX "%s [%s] (domain %04x %pR)\n",
 	       acpi_device_name(device), acpi_device_bid(device),
 	       root->segment, &root->secondary);
 
 	/*
-	 * Scan the Root Bridge
-	 * --------------------
-	 * Must do this prior to any attempt to bind the root device, as the
-	 * PCI namespace does not get created until this call is made (and 
-	 * thus the root bridge's pci_dev does not exist).
-	 */
-	root->bus = pci_acpi_scan_root(root);
-	if (!root->bus) {
-		printk(KERN_ERR PREFIX
-			    "Bus %04x:%02x not present in PCI namespace\n",
-			    root->segment, (unsigned int)root->secondary.start);
-		result = -ENODEV;
-		goto out_del_root;
-	}
-
-	/*
-	 * Attach ACPI-PCI Context
-	 * -----------------------
-	 * Thus binding the ACPI and PCI devices.
-	 */
-	result = acpi_pci_bind_root(device);
-	if (result)
-		goto out_del_root;
-
-	/*
 	 * PCI Routing Table
 	 * -----------------
 	 * Evaluate and parse _PRT, if exists.
 	 */
 	status = acpi_get_handle(device->handle, METHOD_NAME__PRT, &handle);
 	if (ACPI_SUCCESS(status))
-		result = acpi_pci_irq_add_prt(device->handle, root->bus);
+		result = acpi_pci_irq_add_prt(device->handle, root->segment,
+					      root->secondary.start);
+
+	root->mcfg_addr = acpi_pci_root_get_mcfg_addr(device->handle);
 
 	/*
-	 * Scan and bind all _ADR-Based Devices
+	 * All supported architectures that use ACPI have support for
+	 * PCI domains, so we indicate this in _OSC support capabilities.
 	 */
-	list_for_each_entry(child, &device->children, node)
-		acpi_pci_bridge_scan(child);
+	flags = base_flags = OSC_PCI_SEGMENT_GROUPS_SUPPORT;
+	acpi_pci_osc_support(root, flags);
 
 	/* Indicate support for various _OSC capabilities. */
-	if (pci_ext_cfg_avail(root->bus->self))
+	if (pci_ext_cfg_avail())
 		flags |= OSC_EXT_PCI_CONFIG_SUPPORT;
-	if (pcie_aspm_support_enabled())
+	if (pcie_aspm_support_enabled()) {
 		flags |= OSC_ACTIVE_STATE_PWR_SUPPORT |
-			OSC_CLOCK_PWR_CAPABILITY_SUPPORT;
+		OSC_CLOCK_PWR_CAPABILITY_SUPPORT;
+	}
 	if (pci_msi_enabled())
 		flags |= OSC_MSI_SUPPORT;
 	if (flags != base_flags) {
 		status = acpi_pci_osc_support(root, flags);
 		if (ACPI_FAILURE(status)) {
-			dev_info(root->bus->bridge, "ACPI _OSC support "
+			dev_info(&device->dev, "ACPI _OSC support "
 				"notification failed, disabling PCIe ASPM\n");
 			pcie_no_aspm();
 			flags = base_flags;
 		}
 	}
-
 	if (!pcie_ports_disabled
 	    && (flags & ACPI_PCIE_REQ_SUPPORT) == ACPI_PCIE_REQ_SUPPORT) {
 		flags = OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL
@@ -588,40 +551,81 @@ static int __devinit acpi_pci_root_add(struct acpi_device *device)
 
 		if (pci_aer_available()) {
 			if (aer_acpi_firmware_first())
-				dev_dbg(root->bus->bridge,
+				dev_dbg(&device->dev,
 					"PCIe errors handled by BIOS.\n");
 			else
 				flags |= OSC_PCI_EXPRESS_AER_CONTROL;
 		}
 
-		dev_info(root->bus->bridge,
+		dev_info(&device->dev,
 			"Requesting ACPI _OSC control (0x%02x)\n", flags);
 
 		status = acpi_pci_osc_control_set(device->handle, &flags,
-					OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL);
+				       OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL);
 		if (ACPI_SUCCESS(status)) {
-			dev_info(root->bus->bridge,
+			is_osc_granted = true;
+			dev_info(&device->dev,
 				"ACPI _OSC control (0x%02x) granted\n", flags);
-			if (acpi_gbl_FADT.boot_flags & ACPI_FADT_NO_ASPM) {
-				/*
-				 * We have ASPM control, but the FADT indicates
-				 * that it's unsupported. Clear it.
-				 */
-				pcie_clear_aspm(root->bus);
-			}
 		} else {
-			dev_info(root->bus->bridge,
+			is_osc_granted = false;
+			dev_info(&device->dev,
 				"ACPI _OSC request failed (%s), "
 				"returned control mask: 0x%02x\n",
 				acpi_format_exception(status), flags);
-			pr_info("ACPI _OSC control for PCIe not granted, "
-				"disabling ASPM\n");
-			pcie_no_aspm();
 		}
 	} else {
-		dev_info(root->bus->bridge,
-			 "Unable to request _OSC control "
-			 "(_OSC support mask: 0x%02x)\n", flags);
+		dev_info(&device->dev,
+			"Unable to request _OSC control "
+			"(_OSC support mask: 0x%02x)\n", flags);
+	}
+
+	/*
+	 * TBD: Need PCI interface for enumeration/configuration of roots.
+	 */
+
+	mutex_lock(&acpi_pci_root_lock);
+	list_add_tail(&root->node, &acpi_pci_roots);
+	mutex_unlock(&acpi_pci_root_lock);
+
+	/*
+	 * Scan the Root Bridge
+	 * --------------------
+	 * Must do this prior to any attempt to bind the root device, as the
+	 * PCI namespace does not get created until this call is made (and 
+	 * thus the root bridge's pci_dev does not exist).
+	 */
+	root->bus = pci_acpi_scan_root(root);
+	if (!root->bus) {
+		printk(KERN_ERR PREFIX
+			    "Bus %04x:%02x not present in PCI namespace\n",
+			    root->segment, (unsigned int)root->secondary.start);
+		result = -ENODEV;
+		goto out_del_root;
+	}
+
+	/*
+	 * Attach ACPI-PCI Context
+	 * -----------------------
+	 * Thus binding the ACPI and PCI devices.
+	 */
+	result = acpi_pci_bind_root(device);
+	if (result)
+		goto out_del_root;
+
+	/*
+	 * Scan and bind all _ADR-Based Devices
+	 */
+	list_for_each_entry(child, &device->children, node)
+		acpi_pci_bridge_scan(child);
+
+	/* ASPM setting */
+	if (is_osc_granted) {
+		if (acpi_gbl_FADT.boot_flags & ACPI_FADT_NO_ASPM)
+			pcie_clear_aspm(root->bus);
+	} else {
+		pr_info("ACPI _OSC control for PCIe not granted, "
+			"disabling ASPM\n");
+		pcie_no_aspm();
 	}
 
 	pci_acpi_add_bus_pm_notifier(device, root->bus);
@@ -634,6 +638,8 @@ out_del_root:
 	mutex_lock(&acpi_pci_root_lock);
 	list_del(&root->node);
 	mutex_unlock(&acpi_pci_root_lock);
+
+	acpi_pci_irq_del_prt(root->segment, root->secondary.start);
 end:
 	kfree(root);
 	return result;
@@ -644,12 +650,19 @@ static int acpi_pci_root_start(struct acpi_device *device)
 	struct acpi_pci_root *root = acpi_driver_data(device);
 	struct acpi_pci_driver *driver;
 
+	if (system_state != SYSTEM_BOOTING)
+		pci_assign_unassigned_bus_resources(root->bus);
+
 	mutex_lock(&acpi_pci_root_lock);
 	list_for_each_entry(driver, &acpi_pci_drivers, node)
 		if (driver->add)
 			driver->add(root);
 	mutex_unlock(&acpi_pci_root_lock);
 
+	/* need to after hot-added ioapic is registered */
+	if (system_state != SYSTEM_BOOTING)
+		pci_enable_bridges(root->bus);
+
 	pci_bus_add_devices(root->bus);
 
 	return 0;
@@ -657,17 +670,29 @@ static int acpi_pci_root_start(struct acpi_device *device)
 
 static int acpi_pci_root_remove(struct acpi_device *device, int type)
 {
+	acpi_status status;
+	acpi_handle handle;
 	struct acpi_pci_root *root = acpi_driver_data(device);
 	struct acpi_pci_driver *driver;
 
+	pci_stop_root_bus(root->bus);
+
 	mutex_lock(&acpi_pci_root_lock);
-	list_for_each_entry(driver, &acpi_pci_drivers, node)
+	list_for_each_entry_reverse(driver, &acpi_pci_drivers, node)
 		if (driver->remove)
 			driver->remove(root);
+	mutex_unlock(&acpi_pci_root_lock);
 
 	device_set_run_wake(root->bus->bridge, false);
 	pci_acpi_remove_bus_pm_notifier(device);
 
+	status = acpi_get_handle(device->handle, METHOD_NAME__PRT, &handle);
+	if (ACPI_SUCCESS(status))
+		acpi_pci_irq_del_prt(root->segment, root->secondary.start);
+
+	pci_remove_root_bus(root->bus);
+
+	mutex_lock(&acpi_pci_root_lock);
 	list_del(&root->node);
 	mutex_unlock(&acpi_pci_root_lock);
 	kfree(root);
diff --git a/drivers/pci/ioapic.c b/drivers/pci/ioapic.c
index 205af8dc83c..22436f74eb5 100644
--- a/drivers/pci/ioapic.c
+++ b/drivers/pci/ioapic.c
@@ -125,3 +125,5 @@ static void __exit ioapic_exit(void)
 
 module_init(ioapic_init);
 module_exit(ioapic_exit);
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index aeccc911abb..bafd2bbcaf6 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -106,7 +106,7 @@ static int virtfn_add(struct pci_dev *dev, int id, int reset)
 		virtfn->resource[i].name = pci_name(virtfn);
 		virtfn->resource[i].flags = res->flags;
 		size = resource_size(res);
-		do_div(size, iov->total);
+		do_div(size, iov->total_VFs);
 		virtfn->resource[i].start = res->start + size * id;
 		virtfn->resource[i].end = virtfn->resource[i].start + size - 1;
 		rc = request_resource(res, &virtfn->resource[i]);
@@ -194,7 +194,7 @@ static int sriov_migration(struct pci_dev *dev)
 	u16 status;
 	struct pci_sriov *iov = dev->sriov;
 
-	if (!iov->nr_virtfn)
+	if (!iov->num_VFs)
 		return 0;
 
 	if (!(iov->cap & PCI_SRIOV_CAP_VFM))
@@ -216,7 +216,7 @@ static void sriov_migration_task(struct work_struct *work)
 	u16 status;
 	struct pci_sriov *iov = container_of(work, struct pci_sriov, mtask);
 
-	for (i = iov->initial; i < iov->nr_virtfn; i++) {
+	for (i = iov->initial_VFs; i < iov->num_VFs; i++) {
 		state = readb(iov->mstate + i);
 		if (state == PCI_SRIOV_VFM_MI) {
 			writeb(PCI_SRIOV_VFM_AV, iov->mstate + i);
@@ -244,7 +244,7 @@ static int sriov_enable_migration(struct pci_dev *dev, int nr_virtfn)
 	resource_size_t pa;
 	struct pci_sriov *iov = dev->sriov;
 
-	if (nr_virtfn <= iov->initial)
+	if (nr_virtfn <= iov->initial_VFs)
 		return 0;
 
 	pci_read_config_dword(dev, iov->pos + PCI_SRIOV_VFM, &table);
@@ -294,15 +294,15 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn)
 	if (!nr_virtfn)
 		return 0;
 
-	if (iov->nr_virtfn)
+	if (iov->num_VFs)
 		return -EINVAL;
 
 	pci_read_config_word(dev, iov->pos + PCI_SRIOV_INITIAL_VF, &initial);
-	if (initial > iov->total ||
-	    (!(iov->cap & PCI_SRIOV_CAP_VFM) && (initial != iov->total)))
+	if (initial > iov->total_VFs ||
+	    (!(iov->cap & PCI_SRIOV_CAP_VFM) && (initial != iov->total_VFs)))
 		return -EIO;
 
-	if (nr_virtfn < 0 || nr_virtfn > iov->total ||
+	if (nr_virtfn < 0 || nr_virtfn > iov->total_VFs ||
 	    (!(iov->cap & PCI_SRIOV_CAP_VFM) && (nr_virtfn > initial)))
 		return -EINVAL;
 
@@ -359,7 +359,7 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn)
 	msleep(100);
 	pci_cfg_access_unlock(dev);
 
-	iov->initial = initial;
+	iov->initial_VFs = initial;
 	if (nr_virtfn < initial)
 		initial = nr_virtfn;
 
@@ -376,7 +376,7 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn)
 	}
 
 	kobject_uevent(&dev->dev.kobj, KOBJ_CHANGE);
-	iov->nr_virtfn = nr_virtfn;
+	iov->num_VFs = nr_virtfn;
 
 	return 0;
 
@@ -401,13 +401,13 @@ static void sriov_disable(struct pci_dev *dev)
 	int i;
 	struct pci_sriov *iov = dev->sriov;
 
-	if (!iov->nr_virtfn)
+	if (!iov->num_VFs)
 		return;
 
 	if (iov->cap & PCI_SRIOV_CAP_VFM)
 		sriov_disable_migration(dev);
 
-	for (i = 0; i < iov->nr_virtfn; i++)
+	for (i = 0; i < iov->num_VFs; i++)
 		virtfn_remove(dev, i, 0);
 
 	iov->ctrl &= ~(PCI_SRIOV_CTRL_VFE | PCI_SRIOV_CTRL_MSE);
@@ -419,7 +419,7 @@ static void sriov_disable(struct pci_dev *dev)
 	if (iov->link != dev->devfn)
 		sysfs_remove_link(&dev->dev.kobj, "dep_link");
 
-	iov->nr_virtfn = 0;
+	iov->num_VFs = 0;
 }
 
 static int sriov_init(struct pci_dev *dev, int pos)
@@ -496,7 +496,7 @@ found:
 	iov->pos = pos;
 	iov->nres = nres;
 	iov->ctrl = ctrl;
-	iov->total = total;
+	iov->total_VFs = total;
 	iov->offset = offset;
 	iov->stride = stride;
 	iov->pgsz = pgsz;
@@ -529,7 +529,7 @@ failed:
 
 static void sriov_release(struct pci_dev *dev)
 {
-	BUG_ON(dev->sriov->nr_virtfn);
+	BUG_ON(dev->sriov->num_VFs);
 
 	if (dev != dev->sriov->dev)
 		pci_dev_put(dev->sriov->dev);
@@ -554,7 +554,7 @@ static void sriov_restore_state(struct pci_dev *dev)
 		pci_update_resource(dev, i);
 
 	pci_write_config_dword(dev, iov->pos + PCI_SRIOV_SYS_PGSIZE, iov->pgsz);
-	pci_write_config_word(dev, iov->pos + PCI_SRIOV_NUM_VF, iov->nr_virtfn);
+	pci_write_config_word(dev, iov->pos + PCI_SRIOV_NUM_VF, iov->num_VFs);
 	pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, iov->ctrl);
 	if (iov->ctrl & PCI_SRIOV_CTRL_VFE)
 		msleep(100);
@@ -661,7 +661,7 @@ int pci_iov_bus_range(struct pci_bus *bus)
 	list_for_each_entry(dev, &bus->devices, bus_list) {
 		if (!dev->is_physfn)
 			continue;
-		busnr = virtfn_bus(dev, dev->sriov->total - 1);
+		busnr = virtfn_bus(dev, dev->sriov->total_VFs - 1);
 		if (busnr > max)
 			max = busnr;
 	}
@@ -729,9 +729,56 @@ EXPORT_SYMBOL_GPL(pci_sriov_migration);
  */
 int pci_num_vf(struct pci_dev *dev)
 {
-	if (!dev || !dev->is_physfn)
+	if (!dev->is_physfn)
 		return 0;
-	else
-		return dev->sriov->nr_virtfn;
+
+	return dev->sriov->num_VFs;
 }
 EXPORT_SYMBOL_GPL(pci_num_vf);
+
+/**
+ * pci_sriov_set_totalvfs -- reduce the TotalVFs available
+ * @dev: the PCI PF device
+ * numvfs: number that should be used for TotalVFs supported
+ *
+ * Should be called from PF driver's probe routine with
+ * device's mutex held.
+ *
+ * Returns 0 if PF is an SRIOV-capable device and
+ * value of numvfs valid. If not a PF with VFS, return -EINVAL;
+ * if VFs already enabled, return -EBUSY.
+ */
+int pci_sriov_set_totalvfs(struct pci_dev *dev, u16 numvfs)
+{
+	if (!dev->is_physfn || (numvfs > dev->sriov->total_VFs))
+		return -EINVAL;
+
+	/* Shouldn't change if VFs already enabled */
+	if (dev->sriov->ctrl & PCI_SRIOV_CTRL_VFE)
+		return -EBUSY;
+	else
+		dev->sriov->driver_max_VFs = numvfs;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pci_sriov_set_totalvfs);
+
+/**
+ * pci_sriov_get_totalvfs -- get total VFs supported on this devic3
+ * @dev: the PCI PF device
+ *
+ * For a PCIe device with SRIOV support, return the PCIe
+ * SRIOV capability value of TotalVFs or the value of driver_max_VFs
+ * if the driver reduced it.  Otherwise, -EINVAL.
+ */
+int pci_sriov_get_totalvfs(struct pci_dev *dev)
+{
+	if (!dev->is_physfn)
+		return -EINVAL;
+
+	if (dev->sriov->driver_max_VFs)
+		return dev->sriov->driver_max_VFs;
+
+	return dev->sriov->total_VFs;
+}