Merge branch 'pci/host-hv' into next

* pci/host-hv:
  PCI: hv: Add paravirtual PCI front-end for Microsoft Hyper-V VMs
  PCI: Look up IRQ domain by fwnode_handle
  PCI: Add fwnode_handle to x86 pci_sysdata

7 files changed, 2389 insertions, 1 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index b2122f7ea727..85d7907e4095 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5193,6 +5193,7 @@ F:	arch/x86/kernel/cpu/mshyperv.c
 F:	drivers/hid/hid-hyperv.c
 F:	drivers/hv/
 F:	drivers/input/serio/hyperv-keyboard.c
+F:	drivers/pci/host/pci-hyperv.c
 F:	drivers/net/hyperv/
 F:	drivers/scsi/storvsc_drv.c
 F:	drivers/video/fbdev/hyperv_fb.c
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 7fd8eaa8714d..9ab7507ca1c2 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -20,6 +20,9 @@ struct pci_sysdata {
 #ifdef CONFIG_X86_64
 	void		*iommu;		/* IOMMU private data */
 #endif
+#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN
+	void		*fwnode;	/* IRQ domain for MSI assignment */
+#endif
 };
 
 extern int pci_routeirq;
@@ -32,6 +35,7 @@ extern int noioapicreroute;
 static inline int pci_domain_nr(struct pci_bus *bus)
 {
 	struct pci_sysdata *sd = bus->sysdata;
+
 	return sd->domain;
 }
 
@@ -41,6 +45,17 @@ static inline int pci_proc_domain(struct pci_bus *bus)
 }
 #endif
 
+#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN
+static inline void *_pci_root_bus_fwnode(struct pci_bus *bus)
+{
+	struct pci_sysdata *sd = bus->sysdata;
+
+	return sd->fwnode;
+}
+
+#define pci_root_bus_fwnode	_pci_root_bus_fwnode
+#endif
+
 /* Can be used to override the logic in pci_scan_bus for skipping
    already-configured bus numbers - to be used for buggy BIOSes
    or architectures with incomplete PCI setup by the loader */
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index 616165d72a17..a1f37db745ab 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -121,5 +121,11 @@ config PCI_LABEL
 	def_bool y if (DMI || ACPI)
 	select NLS
 
-source "drivers/pci/hotplug/Kconfig"
+config PCI_HYPERV
+        tristate "Hyper-V PCI Frontend"
+        depends on PCI && X86 && HYPERV && PCI_MSI && PCI_MSI_IRQ_DOMAIN && X86_64
+        help
+          The PCI device frontend driver allows the kernel to import arbitrary
+          PCI devices from a PCI backend to support PCI driver domains.
+
 source "drivers/pci/host/Kconfig"
diff --git a/drivers/pci/host/Makefile b/drivers/pci/host/Makefile
index 3ccd743e20b9..d85b5faf9bbc 100644
--- a/drivers/pci/host/Makefile
+++ b/drivers/pci/host/Makefile
@@ -3,6 +3,7 @@ obj-$(CONFIG_PCIE_DW_PLAT) += pcie-designware-plat.o
 obj-$(CONFIG_PCI_DRA7XX) += pci-dra7xx.o
 obj-$(CONFIG_PCI_EXYNOS) += pci-exynos.o
 obj-$(CONFIG_PCI_IMX6) += pci-imx6.o
+obj-$(CONFIG_PCI_HYPERV) += pci-hyperv.o
 obj-$(CONFIG_PCI_MVEBU) += pci-mvebu.o
 obj-$(CONFIG_PCI_TEGRA) += pci-tegra.o
 obj-$(CONFIG_PCI_RCAR_GEN2) += pci-rcar-gen2.o
diff --git a/drivers/pci/host/pci-hyperv.c b/drivers/pci/host/pci-hyperv.c
new file mode 100644
index 000000000000..ed651baa7c50
--- /dev/null
+++ b/drivers/pci/host/pci-hyperv.c
@@ -0,0 +1,2346 @@
+/*
+ * Copyright (c) Microsoft Corporation.
+ *
+ * Author:
+ *   Jake Oshins <jakeo@microsoft.com>
+ *
+ * This driver acts as a paravirtual front-end for PCI Express root buses.
+ * When a PCI Express function (either an entire device or an SR-IOV
+ * Virtual Function) is being passed through to the VM, this driver exposes
+ * a new bus to the guest VM.  This is modeled as a root PCI bus because
+ * no bridges are being exposed to the VM.  In fact, with a "Generation 2"
+ * VM within Hyper-V, there may seem to be no PCI bus at all in the VM
+ * until a device as been exposed using this driver.
+ *
+ * Each root PCI bus has its own PCI domain, which is called "Segment" in
+ * the PCI Firmware Specifications.  Thus while each device passed through
+ * to the VM using this front-end will appear at "device 0", the domain will
+ * be unique.  Typically, each bus will have one PCI function on it, though
+ * this driver does support more than one.
+ *
+ * In order to map the interrupts from the device through to the guest VM,
+ * this driver also implements an IRQ Domain, which handles interrupts (either
+ * MSI or MSI-X) associated with the functions on the bus.  As interrupts are
+ * set up, torn down, or reaffined, this driver communicates with the
+ * underlying hypervisor to adjust the mappings in the I/O MMU so that each
+ * interrupt will be delivered to the correct virtual processor at the right
+ * vector.  This driver does not support level-triggered (line-based)
+ * interrupts, and will report that the Interrupt Line register in the
+ * function's configuration space is zero.
+ *
+ * The rest of this driver mostly maps PCI concepts onto underlying Hyper-V
+ * facilities.  For instance, the configuration space of a function exposed
+ * by Hyper-V is mapped into a single page of memory space, and the
+ * read and write handlers for config space must be aware of this mechanism.
+ * Similarly, device setup and teardown involves messages sent to and from
+ * the PCI back-end driver in Hyper-V.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/semaphore.h>
+#include <linux/irqdomain.h>
+#include <asm/irqdomain.h>
+#include <asm/apic.h>
+#include <linux/msi.h>
+#include <linux/hyperv.h>
+#include <asm/mshyperv.h>
+
+/*
+ * Protocol versions. The low word is the minor version, the high word the
+ * major version.
+ */
+
+#define PCI_MAKE_VERSION(major, minor) ((u32)(((major) << 16) | (major)))
+#define PCI_MAJOR_VERSION(version) ((u32)(version) >> 16)
+#define PCI_MINOR_VERSION(version) ((u32)(version) & 0xff)
+
+enum {
+	PCI_PROTOCOL_VERSION_1_1 = PCI_MAKE_VERSION(1, 1),
+	PCI_PROTOCOL_VERSION_CURRENT = PCI_PROTOCOL_VERSION_1_1
+};
+
+#define PCI_CONFIG_MMIO_LENGTH	0x2000
+#define CFG_PAGE_OFFSET 0x1000
+#define CFG_PAGE_SIZE (PCI_CONFIG_MMIO_LENGTH - CFG_PAGE_OFFSET)
+
+#define MAX_SUPPORTED_MSI_MESSAGES 0x400
+
+/*
+ * Message Types
+ */
+
+enum pci_message_type {
+	/*
+	 * Version 1.1
+	 */
+	PCI_MESSAGE_BASE                = 0x42490000,
+	PCI_BUS_RELATIONS               = PCI_MESSAGE_BASE + 0,
+	PCI_QUERY_BUS_RELATIONS         = PCI_MESSAGE_BASE + 1,
+	PCI_POWER_STATE_CHANGE          = PCI_MESSAGE_BASE + 4,
+	PCI_QUERY_RESOURCE_REQUIREMENTS = PCI_MESSAGE_BASE + 5,
+	PCI_QUERY_RESOURCE_RESOURCES    = PCI_MESSAGE_BASE + 6,
+	PCI_BUS_D0ENTRY                 = PCI_MESSAGE_BASE + 7,
+	PCI_BUS_D0EXIT                  = PCI_MESSAGE_BASE + 8,
+	PCI_READ_BLOCK                  = PCI_MESSAGE_BASE + 9,
+	PCI_WRITE_BLOCK                 = PCI_MESSAGE_BASE + 0xA,
+	PCI_EJECT                       = PCI_MESSAGE_BASE + 0xB,
+	PCI_QUERY_STOP                  = PCI_MESSAGE_BASE + 0xC,
+	PCI_REENABLE                    = PCI_MESSAGE_BASE + 0xD,
+	PCI_QUERY_STOP_FAILED           = PCI_MESSAGE_BASE + 0xE,
+	PCI_EJECTION_COMPLETE           = PCI_MESSAGE_BASE + 0xF,
+	PCI_RESOURCES_ASSIGNED          = PCI_MESSAGE_BASE + 0x10,
+	PCI_RESOURCES_RELEASED          = PCI_MESSAGE_BASE + 0x11,
+	PCI_INVALIDATE_BLOCK            = PCI_MESSAGE_BASE + 0x12,
+	PCI_QUERY_PROTOCOL_VERSION      = PCI_MESSAGE_BASE + 0x13,
+	PCI_CREATE_INTERRUPT_MESSAGE    = PCI_MESSAGE_BASE + 0x14,
+	PCI_DELETE_INTERRUPT_MESSAGE    = PCI_MESSAGE_BASE + 0x15,
+	PCI_MESSAGE_MAXIMUM
+};
+
+/*
+ * Structures defining the virtual PCI Express protocol.
+ */
+
+union pci_version {
+	struct {
+		u16 minor_version;
+		u16 major_version;
+	} parts;
+	u32 version;
+} __packed;
+
+/*
+ * Function numbers are 8-bits wide on Express, as interpreted through ARI,
+ * which is all this driver does.  This representation is the one used in
+ * Windows, which is what is expected when sending this back and forth with
+ * the Hyper-V parent partition.
+ */
+union win_slot_encoding {
+	struct {
+		u32	func:8;
+		u32	reserved:24;
+	} bits;
+	u32 slot;
+} __packed;
+
+/*
+ * Pretty much as defined in the PCI Specifications.
+ */
+struct pci_function_description {
+	u16	v_id;	/* vendor ID */
+	u16	d_id;	/* device ID */
+	u8	rev;
+	u8	prog_intf;
+	u8	subclass;
+	u8	base_class;
+	u32	subsystem_id;
+	union win_slot_encoding win_slot;
+	u32	ser;	/* serial number */
+} __packed;
+
+/**
+ * struct hv_msi_desc
+ * @vector:		IDT entry
+ * @delivery_mode:	As defined in Intel's Programmer's
+ *			Reference Manual, Volume 3, Chapter 8.
+ * @vector_count:	Number of contiguous entries in the
+ *			Interrupt Descriptor Table that are
+ *			occupied by this Message-Signaled
+ *			Interrupt. For "MSI", as first defined
+ *			in PCI 2.2, this can be between 1 and
+ *			32. For "MSI-X," as first defined in PCI
+ *			3.0, this must be 1, as each MSI-X table
+ *			entry would have its own descriptor.
+ * @reserved:		Empty space
+ * @cpu_mask:		All the target virtual processors.
+ */
+struct hv_msi_desc {
+	u8	vector;
+	u8	delivery_mode;
+	u16	vector_count;
+	u32	reserved;
+	u64	cpu_mask;
+} __packed;
+
+/**
+ * struct tran_int_desc
+ * @reserved:		unused, padding
+ * @vector_count:	same as in hv_msi_desc
+ * @data:		This is the "data payload" value that is
+ *			written by the device when it generates
+ *			a message-signaled interrupt, either MSI
+ *			or MSI-X.
+ * @address:		This is the address to which the data
+ *			payload is written on interrupt
+ *			generation.
+ */
+struct tran_int_desc {
+	u16	reserved;
+	u16	vector_count;
+	u32	data;
+	u64	address;
+} __packed;
+
+/*
+ * A generic message format for virtual PCI.
+ * Specific message formats are defined later in the file.
+ */
+
+struct pci_message {
+	u32 message_type;
+} __packed;
+
+struct pci_child_message {
+	u32 message_type;
+	union win_slot_encoding wslot;
+} __packed;
+
+struct pci_incoming_message {
+	struct vmpacket_descriptor hdr;
+	struct pci_message message_type;
+} __packed;
+
+struct pci_response {
+	struct vmpacket_descriptor hdr;
+	s32 status;			/* negative values are failures */
+} __packed;
+
+struct pci_packet {
+	void (*completion_func)(void *context, struct pci_response *resp,
+				int resp_packet_size);
+	void *compl_ctxt;
+	struct pci_message message;
+};
+
+/*
+ * Specific message types supporting the PCI protocol.
+ */
+
+/*
+ * Version negotiation message. Sent from the guest to the host.
+ * The guest is free to try different versions until the host
+ * accepts the version.
+ *
+ * pci_version: The protocol version requested.
+ * is_last_attempt: If TRUE, this is the last version guest will request.
+ * reservedz: Reserved field, set to zero.
+ */
+
+struct pci_version_request {
+	struct pci_message message_type;
+	enum pci_message_type protocol_version;
+} __packed;
+
+/*
+ * Bus D0 Entry.  This is sent from the guest to the host when the virtual
+ * bus (PCI Express port) is ready for action.
+ */
+
+struct pci_bus_d0_entry {
+	struct pci_message message_type;
+	u32 reserved;
+	u64 mmio_base;
+} __packed;
+
+struct pci_bus_relations {
+	struct pci_incoming_message incoming;
+	u32 device_count;
+	struct pci_function_description func[1];
+} __packed;
+
+struct pci_q_res_req_response {
+	struct vmpacket_descriptor hdr;
+	s32 status;			/* negative values are failures */
+	u32 probed_bar[6];
+} __packed;
+
+struct pci_set_power {
+	struct pci_message message_type;
+	union win_slot_encoding wslot;
+	u32 power_state;		/* In Windows terms */
+	u32 reserved;
+} __packed;
+
+struct pci_set_power_response {
+	struct vmpacket_descriptor hdr;
+	s32 status;			/* negative values are failures */
+	union win_slot_encoding wslot;
+	u32 resultant_state;		/* In Windows terms */
+	u32 reserved;
+} __packed;
+
+struct pci_resources_assigned {
+	struct pci_message message_type;
+	union win_slot_encoding wslot;
+	u8 memory_range[0x14][6];	/* not used here */
+	u32 msi_descriptors;
+	u32 reserved[4];
+} __packed;
+
+struct pci_create_interrupt {
+	struct pci_message message_type;
+	union win_slot_encoding wslot;
+	struct hv_msi_desc int_desc;
+} __packed;
+
+struct pci_create_int_response {
+	struct pci_response response;
+	u32 reserved;
+	struct tran_int_desc int_desc;
+} __packed;
+
+struct pci_delete_interrupt {
+	struct pci_message message_type;
+	union win_slot_encoding wslot;
+	struct tran_int_desc int_desc;
+} __packed;
+
+struct pci_dev_incoming {
+	struct pci_incoming_message incoming;
+	union win_slot_encoding wslot;
+} __packed;
+
+struct pci_eject_response {
+	u32 message_type;
+	union win_slot_encoding wslot;
+	u32 status;
+} __packed;
+
+static int pci_ring_size = (4 * PAGE_SIZE);
+
+/*
+ * Definitions or interrupt steering hypercall.
+ */
+#define HV_PARTITION_ID_SELF		((u64)-1)
+#define HVCALL_RETARGET_INTERRUPT	0x7e
+
+struct retarget_msi_interrupt {
+	u64	partition_id;		/* use "self" */
+	u64	device_id;
+	u32	source;			/* 1 for MSI(-X) */
+	u32	reserved1;
+	u32	address;
+	u32	data;
+	u64	reserved2;
+	u32	vector;
+	u32	flags;
+	u64	vp_mask;
+} __packed;
+
+/*
+ * Driver specific state.
+ */
+
+enum hv_pcibus_state {
+	hv_pcibus_init = 0,
+	hv_pcibus_probed,
+	hv_pcibus_installed,
+	hv_pcibus_maximum
+};
+
+struct hv_pcibus_device {
+	struct pci_sysdata sysdata;
+	enum hv_pcibus_state state;
+	atomic_t remove_lock;
+	struct hv_device *hdev;
+	resource_size_t low_mmio_space;
+	resource_size_t high_mmio_space;
+	struct resource *mem_config;
+	struct resource *low_mmio_res;
+	struct resource *high_mmio_res;
+	struct completion *survey_event;
+	struct completion remove_event;
+	struct pci_bus *pci_bus;
+	spinlock_t config_lock;	/* Avoid two threads writing index page */
+	spinlock_t device_list_lock;	/* Protect lists below */
+	void __iomem *cfg_addr;
+
+	struct semaphore enum_sem;
+	struct list_head resources_for_children;
+
+	struct list_head children;
+	struct list_head dr_list;
+	struct work_struct wrk;
+
+	struct msi_domain_info msi_info;
+	struct msi_controller msi_chip;
+	struct irq_domain *irq_domain;
+};
+
+/*
+ * Tracks "Device Relations" messages from the host, which must be both
+ * processed in order and deferred so that they don't run in the context
+ * of the incoming packet callback.
+ */
+struct hv_dr_work {
+	struct work_struct wrk;
+	struct hv_pcibus_device *bus;
+};
+
+struct hv_dr_state {
+	struct list_head list_entry;
+	u32 device_count;
+	struct pci_function_description func[1];
+};
+
+enum hv_pcichild_state {
+	hv_pcichild_init = 0,
+	hv_pcichild_requirements,
+	hv_pcichild_resourced,
+	hv_pcichild_ejecting,
+	hv_pcichild_maximum
+};
+
+enum hv_pcidev_ref_reason {
+	hv_pcidev_ref_invalid = 0,
+	hv_pcidev_ref_initial,
+	hv_pcidev_ref_by_slot,
+	hv_pcidev_ref_packet,
+	hv_pcidev_ref_pnp,
+	hv_pcidev_ref_childlist,
+	hv_pcidev_irqdata,
+	hv_pcidev_ref_max
+};
+
+struct hv_pci_dev {
+	/* List protected by pci_rescan_remove_lock */
+	struct list_head list_entry;
+	atomic_t refs;
+	enum hv_pcichild_state state;
+	struct pci_function_description desc;
+	bool reported_missing;
+	struct hv_pcibus_device *hbus;
+	struct work_struct wrk;
+
+	/*
+	 * What would be observed if one wrote 0xFFFFFFFF to a BAR and then
+	 * read it back, for each of the BAR offsets within config space.
+	 */
+	u32 probed_bar[6];
+};
+
+struct hv_pci_compl {
+	struct completion host_event;
+	s32 completion_status;
+};
+
+/**
+ * hv_pci_generic_compl() - Invoked for a completion packet
+ * @context:		Set up by the sender of the packet.
+ * @resp:		The response packet
+ * @resp_packet_size:	Size in bytes of the packet
+ *
+ * This function is used to trigger an event and report status
+ * for any message for which the completion packet contains a
+ * status and nothing else.
+ */
+static
+void
+hv_pci_generic_compl(void *context, struct pci_response *resp,
+		     int resp_packet_size)
+{
+	struct hv_pci_compl *comp_pkt = context;
+
+	if (resp_packet_size >= offsetofend(struct pci_response, status))
+		comp_pkt->completion_status = resp->status;
+	complete(&comp_pkt->host_event);
+}
+
+static struct hv_pci_dev *get_pcichild_wslot(struct hv_pcibus_device *hbus,
+						u32 wslot);
+static void get_pcichild(struct hv_pci_dev *hv_pcidev,
+			 enum hv_pcidev_ref_reason reason);
+static void put_pcichild(struct hv_pci_dev *hv_pcidev,
+			 enum hv_pcidev_ref_reason reason);
+
+static void get_hvpcibus(struct hv_pcibus_device *hv_pcibus);
+static void put_hvpcibus(struct hv_pcibus_device *hv_pcibus);
+
+/**
+ * devfn_to_wslot() - Convert from Linux PCI slot to Windows
+ * @devfn:	The Linux representation of PCI slot
+ *
+ * Windows uses a slightly different representation of PCI slot.
+ *
+ * Return: The Windows representation
+ */
+static u32 devfn_to_wslot(int devfn)
+{
+	union win_slot_encoding wslot;
+
+	wslot.slot = 0;
+	wslot.bits.func = PCI_SLOT(devfn) | (PCI_FUNC(devfn) << 5);
+
+	return wslot.slot;
+}
+
+/**
+ * wslot_to_devfn() - Convert from Windows PCI slot to Linux
+ * @wslot:	The Windows representation of PCI slot
+ *
+ * Windows uses a slightly different representation of PCI slot.
+ *
+ * Return: The Linux representation
+ */
+static int wslot_to_devfn(u32 wslot)
+{
+	union win_slot_encoding slot_no;
+
+	slot_no.slot = wslot;
+	return PCI_DEVFN(0, slot_no.bits.func);
+}
+
+/*
+ * PCI Configuration Space for these root PCI buses is implemented as a pair
+ * of pages in memory-mapped I/O space.  Writing to the first page chooses
+ * the PCI function being written or read.  Once the first page has been
+ * written to, the following page maps in the entire configuration space of
+ * the function.
+ */
+
+/**
+ * _hv_pcifront_read_config() - Internal PCI config read
+ * @hpdev:	The PCI driver's representation of the device
+ * @where:	Offset within config space
+ * @size:	Size of the transfer
+ * @val:	Pointer to the buffer receiving the data
+ */
+static void _hv_pcifront_read_config(struct hv_pci_dev *hpdev, int where,
+				     int size, u32 *val)
+{
+	unsigned long flags;
+	void __iomem *addr = hpdev->hbus->cfg_addr + CFG_PAGE_OFFSET + where;
+
+	/*
+	 * If the attempt is to read the IDs or the ROM BAR, simulate that.
+	 */
+	if (where + size <= PCI_COMMAND) {
+		memcpy(val, ((u8 *)&hpdev->desc.v_id) + where, size);
+	} else if (where >= PCI_CLASS_REVISION && where + size <=
+		   PCI_CACHE_LINE_SIZE) {
+		memcpy(val, ((u8 *)&hpdev->desc.rev) + where -
+		       PCI_CLASS_REVISION, size);
+	} else if (where >= PCI_SUBSYSTEM_VENDOR_ID && where + size <=
+		   PCI_ROM_ADDRESS) {
+		memcpy(val, (u8 *)&hpdev->desc.subsystem_id + where -
+		       PCI_SUBSYSTEM_VENDOR_ID, size);
+	} else if (where >= PCI_ROM_ADDRESS && where + size <=
+		   PCI_CAPABILITY_LIST) {
+		/* ROM BARs are unimplemented */
+		*val = 0;
+	} else if (where >= PCI_INTERRUPT_LINE && where + size <=
+		   PCI_INTERRUPT_PIN) {
+		/*
+		 * Interrupt Line and Interrupt PIN are hard-wired to zero
+		 * because this front-end only supports message-signaled
+		 * interrupts.
+		 */
+		*val = 0;
+	} else if (where + size <= CFG_PAGE_SIZE) {
+		spin_lock_irqsave(&hpdev->hbus->config_lock, flags);
+		/* Choose the function to be read. (See comment above) */
+		writel(hpdev->desc.win_slot.slot, hpdev->hbus->cfg_addr);
+		/* Read from that function's config space. */
+		switch (size) {
+		case 1:
+			*val = readb(addr);
+			break;
+		case 2:
+			*val = readw(addr);
+			break;
+		default:
+			*val = readl(addr);
+			break;
+		}
+		spin_unlock_irqrestore(&hpdev->hbus->config_lock, flags);
+	} else {
+		dev_err(&hpdev->hbus->hdev->device,
+			"Attempt to read beyond a function's config space.\n");
+	}
+}
+
+/**
+ * _hv_pcifront_write_config() - Internal PCI config write
+ * @hpdev:	The PCI driver's representation of the device
+ * @where:	Offset within config space
+ * @size:	Size of the transfer
+ * @val:	The data being transferred
+ */
+static void _hv_pcifront_write_config(struct hv_pci_dev *hpdev, int where,
+				      int size, u32 val)
+{
+	unsigned long flags;
+	void __iomem *addr = hpdev->hbus->cfg_addr + CFG_PAGE_OFFSET + where;
+
+	if (where >= PCI_SUBSYSTEM_VENDOR_ID &&
+	    where + size <= PCI_CAPABILITY_LIST) {
+		/* SSIDs and ROM BARs are read-only */
+	} else if (where >= PCI_COMMAND && where + size <= CFG_PAGE_SIZE) {
+		spin_lock_irqsave(&hpdev->hbus->config_lock, flags);
+		/* Choose the function to be written. (See comment above) */
+		writel(hpdev->desc.win_slot.slot, hpdev->hbus->cfg_addr);
+		/* Write to that function's config space. */
+		switch (size) {
+		case 1:
+			writeb(val, addr);
+			break;
+		case 2:
+			writew(val, addr);
+			break;
+		default:
+			writel(val, addr);
+			break;
+		}
+		spin_unlock_irqrestore(&hpdev->hbus->config_lock, flags);
+	} else {
+		dev_err(&hpdev->hbus->hdev->device,
+			"Attempt to write beyond a function's config space.\n");
+	}
+}
+
+/**
+ * hv_pcifront_read_config() - Read configuration space
+ * @bus: PCI Bus structure
+ * @devfn: Device/function
+ * @where: Offset from base
+ * @size: Byte/word/dword
+ * @val: Value to be read
+ *
+ * Return: PCIBIOS_SUCCESSFUL on success
+ *	   PCIBIOS_DEVICE_NOT_FOUND on failure
+ */
+static int hv_pcifront_read_config(struct pci_bus *bus, unsigned int devfn,
+				   int where, int size, u32 *val)
+{
+	struct hv_pcibus_device *hbus =
+		container_of(bus->sysdata, struct hv_pcibus_device, sysdata);
+	struct hv_pci_dev *hpdev;
+
+	hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(devfn));
+	if (!hpdev)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	_hv_pcifront_read_config(hpdev, where, size, val);
+
+	put_pcichild(hpdev, hv_pcidev_ref_by_slot);
+	return PCIBIOS_SUCCESSFUL;
+}
+
+/**
+ * hv_pcifront_write_config() - Write configuration space
+ * @bus: PCI Bus structure
+ * @devfn: Device/function
+ * @where: Offset from base
+ * @size: Byte/word/dword
+ * @val: Value to be written to device
+ *
+ * Return: PCIBIOS_SUCCESSFUL on success
+ *	   PCIBIOS_DEVICE_NOT_FOUND on failure
+ */
+static int hv_pcifront_write_config(struct pci_bus *bus, unsigned int devfn,
+				    int where, int size, u32 val)
+{
+	struct hv_pcibus_device *hbus =
+	    container_of(bus->sysdata, struct hv_pcibus_device, sysdata);
+	struct hv_pci_dev *hpdev;
+
+	hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(devfn));
+	if (!hpdev)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	_hv_pcifront_write_config(hpdev, where, size, val);
+
+	put_pcichild(hpdev, hv_pcidev_ref_by_slot);
+	return PCIBIOS_SUCCESSFUL;
+}
+
+/* PCIe operations */
+static struct pci_ops hv_pcifront_ops = {
+	.read  = hv_pcifront_read_config,
+	.write = hv_pcifront_write_config,
+};
+
+/* Interrupt management hooks */
+static void hv_int_desc_free(struct hv_pci_dev *hpdev,
+			     struct tran_int_desc *int_desc)
+{
+	struct pci_delete_interrupt *int_pkt;
+	struct {
+		struct pci_packet pkt;
+		u8 buffer[sizeof(struct pci_delete_interrupt) -
+			  sizeof(struct pci_message)];
+	} ctxt;
+
+	memset(&ctxt, 0, sizeof(ctxt));
+	int_pkt = (struct pci_delete_interrupt *)&ctxt.pkt.message;
+	int_pkt->message_type.message_type =
+		PCI_DELETE_INTERRUPT_MESSAGE;
+	int_pkt->wslot.slot = hpdev->desc.win_slot.slot;
+	int_pkt->int_desc = *int_desc;
+	vmbus_sendpacket(hpdev->hbus->hdev->channel, int_pkt, sizeof(*int_pkt),
+			 (unsigned long)&ctxt.pkt, VM_PKT_DATA_INBAND, 0);
+	kfree(int_desc);
+}
+
+/**
+ * hv_msi_free() - Free the MSI.
+ * @domain:	The interrupt domain pointer
+ * @info:	Extra MSI-related context
+ * @irq:	Identifies the IRQ.
+ *
+ * The Hyper-V parent partition and hypervisor are tracking the
+ * messages that are in use, keeping the interrupt redirection
+ * table up to date.  This callback sends a message that frees
+ * the IRT entry and related tracking nonsense.
+ */
+static void hv_msi_free(struct irq_domain *domain, struct msi_domain_info *info,
+			unsigned int irq)
+{
+	struct hv_pcibus_device *hbus;
+	struct hv_pci_dev *hpdev;
+	struct pci_dev *pdev;
+	struct tran_int_desc *int_desc;
+	struct irq_data *irq_data = irq_domain_get_irq_data(domain, irq);
+	struct msi_desc *msi = irq_data_get_msi_desc(irq_data);
+
+	pdev = msi_desc_to_pci_dev(msi);
+	hbus = info->data;
+	hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(pdev->devfn));
+	if (!hpdev)
+		return;
+
+	int_desc = irq_data_get_irq_chip_data(irq_data);
+	if (int_desc) {
+		irq_data->chip_data = NULL;
+		hv_int_desc_free(hpdev, int_desc);
+	}
+
+	put_pcichild(hpdev, hv_pcidev_ref_by_slot);
+}
+
+static int hv_set_affinity(struct irq_data *data, const struct cpumask *dest,
+			   bool force)
+{
+	struct irq_data *parent = data->parent_data;
+
+	return parent->chip->irq_set_affinity(parent, dest, force);
+}
+
+void hv_irq_mask(struct irq_data *data)
+{
+	pci_msi_mask_irq(data);
+}
+
+/**
+ * hv_irq_unmask() - "Unmask" the IRQ by setting its current
+ * affinity.
+ * @data:	Describes the IRQ
+ *
+ * Build new a destination for the MSI and make a hypercall to
+ * update the Interrupt Redirection Table. "Device Logical ID"
+ * is built out of this PCI bus's instance GUID and the function
+ * number of the device.
+ */
+void hv_irq_unmask(struct irq_data *data)
+{
+	struct msi_desc *msi_desc = irq_data_get_msi_desc(data);
+	struct irq_cfg *cfg = irqd_cfg(data);
+	struct retarget_msi_interrupt params;
+	struct hv_pcibus_device *hbus;
+	struct cpumask *dest;
+	struct pci_bus *pbus;
+	struct pci_dev *pdev;
+	int cpu;
+
+	dest = irq_data_get_affinity_mask(data);
+	pdev = msi_desc_to_pci_dev(msi_desc);
+	pbus = pdev->bus;
+	hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata);
+
+	memset(&params, 0, sizeof(params));
+	params.partition_id = HV_PARTITION_ID_SELF;
+	params.source = 1; /* MSI(-X) */
+	params.address = msi_desc->msg.address_lo;
+	params.data = msi_desc->msg.data;
+	params.device_id = (hbus->hdev->dev_instance.b[5] << 24) |
+			   (hbus->hdev->dev_instance.b[4] << 16) |
+			   (hbus->hdev->dev_instance.b[7] << 8) |
+			   (hbus->hdev->dev_instance.b[6] & 0xf8) |
+			   PCI_FUNC(pdev->devfn);
+	params.vector = cfg->vector;
+
+	for_each_cpu_and(cpu, dest, cpu_online_mask)
+		params.vp_mask |= (1ULL << vmbus_cpu_number_to_vp_number(cpu));
+
+	hv_do_hypercall(HVCALL_RETARGET_INTERRUPT, &params, NULL);
+
+	pci_msi_unmask_irq(data);
+}
+
+struct compose_comp_ctxt {
+	struct hv_pci_compl comp_pkt;
+	struct tran_int_desc int_desc;
+};
+
+static void hv_pci_compose_compl(void *context, struct pci_response *resp,
+				 int resp_packet_size)
+{
+	struct compose_comp_ctxt *comp_pkt = context;
+	struct pci_create_int_response *int_resp =
+		(struct pci_create_int_response *)resp;
+
+	comp_pkt->comp_pkt.completion_status = resp->status;
+	comp_pkt->int_desc = int_resp->int_desc;
+	complete(&comp_pkt->comp_pkt.host_event);
+}
+
+/**
+ * hv_compose_msi_msg() - Supplies a valid MSI address/data
+ * @data:	Everything about this MSI
+ * @msg:	Buffer that is filled in by this function
+ *
+ * This function unpacks the IRQ looking for target CPU set, IDT
+ * vector and mode and sends a message to the parent partition
+ * asking for a mapping for that tuple in this partition.  The
+ * response supplies a data value and address to which that data
+ * should be written to trigger that interrupt.
+ */
+static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
+{
+	struct irq_cfg *cfg = irqd_cfg(data);
+	struct hv_pcibus_device *hbus;
+	struct hv_pci_dev *hpdev;
+	struct pci_bus *pbus;
+	struct pci_dev *pdev;
+	struct pci_create_interrupt *int_pkt;
+	struct compose_comp_ctxt comp;
+	struct tran_int_desc *int_desc;
+	struct cpumask *affinity;
+	struct {
+		struct pci_packet pkt;
+		u8 buffer[sizeof(struct pci_create_interrupt) -
+			  sizeof(struct pci_message)];
+	} ctxt;
+	int cpu;
+	int ret;
+
+	pdev = msi_desc_to_pci_dev(irq_data_get_msi_desc(data));
+	pbus = pdev->bus;
+	hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata);
+	hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(pdev->devfn));
+	if (!hpdev)
+		goto return_null_message;
+
+	/* Free any previous message that might have already been composed. */
+	if (data->chip_data) {
+		int_desc = data->chip_data;
+		data->chip_data = NULL;
+		hv_int_desc_free(hpdev, int_desc);
+	}
+
+	int_desc = kzalloc(sizeof(*int_desc), GFP_KERNEL);
+	if (!int_desc)
+		goto drop_reference;
+
+	memset(&ctxt, 0, sizeof(ctxt));
+	init_completion(&comp.comp_pkt.host_event);
+	ctxt.pkt.completion_func = hv_pci_compose_compl;
+	ctxt.pkt.compl_ctxt = &comp;
+	int_pkt = (struct pci_create_interrupt *)&ctxt.pkt.message;
+	int_pkt->message_type.message_type = PCI_CREATE_INTERRUPT_MESSAGE;
+	int_pkt->wslot.slot = hpdev->desc.win_slot.slot;
+	int_pkt->int_desc.vector = cfg->vector;
+	int_pkt->int_desc.vector_count = 1;
+	int_pkt->int_desc.delivery_mode =
+		(apic->irq_delivery_mode == dest_LowestPrio) ? 1 : 0;
+
+	/*
+	 * This bit doesn't have to work on machines with more than 64
+	 * processors because Hyper-V only supports 64 in a guest.
+	 */
+	affinity = irq_data_get_affinity_mask(data);
+	for_each_cpu_and(cpu, affinity, cpu_online_mask) {
+		int_pkt->int_desc.cpu_mask |=
+			(1ULL << vmbus_cpu_number_to_vp_number(cpu));
+	}
+
+	ret = vmbus_sendpacket(hpdev->hbus->hdev->channel, int_pkt,
+			       sizeof(*int_pkt), (unsigned long)&ctxt.pkt,
+			       VM_PKT_DATA_INBAND,
+			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
+	if (!ret)
+		wait_for_completion(&comp.comp_pkt.host_event);
+
+	if (comp.comp_pkt.completion_status < 0) {
+		dev_err(&hbus->hdev->device,
+			"Request for interrupt failed: 0x%x",
+			comp.comp_pkt.completion_status);
+		goto free_int_desc;
+	}
+
+	/*
+	 * Record the assignment so that this can be unwound later. Using
+	 * irq_set_chip_data() here would be appropriate, but the lock it takes
+	 * is already held.
+	 */
+	*int_desc = comp.int_desc;
+	data->chip_data = int_desc;
+
+	/* Pass up the result. */
+	msg->address_hi = comp.int_desc.address >> 32;
+	msg->address_lo = comp.int_desc.address & 0xffffffff;
+	msg->data = comp.int_desc.data;
+
+	put_pcichild(hpdev, hv_pcidev_ref_by_slot);
+	return;
+
+free_int_desc:
+	kfree(int_desc);
+drop_reference:
+	put_pcichild(hpdev, hv_pcidev_ref_by_slot);
+return_null_message:
+	msg->address_hi = 0;
+	msg->address_lo = 0;
+	msg->data = 0;
+}
+
+/* HW Interrupt Chip Descriptor */
+static struct irq_chip hv_msi_irq_chip = {
+	.name			= "Hyper-V PCIe MSI",
+	.irq_compose_msi_msg	= hv_compose_msi_msg,
+	.irq_set_affinity	= hv_set_affinity,
+	.irq_ack		= irq_chip_ack_parent,
+	.irq_mask		= hv_irq_mask,
+	.irq_unmask		= hv_irq_unmask,
+};
+
+static irq_hw_number_t hv_msi_domain_ops_get_hwirq(struct msi_domain_info *info,
+						   msi_alloc_info_t *arg)
+{
+	return arg->msi_hwirq;
+}
+
+static struct msi_domain_ops hv_msi_ops = {
+	.get_hwirq	= hv_msi_domain_ops_get_hwirq,
+	.msi_prepare	= pci_msi_prepare,
+	.set_desc	= pci_msi_set_desc,
+	.msi_free	= hv_msi_free,
+};
+
+/**
+ * hv_pcie_init_irq_domain() - Initialize IRQ domain
+ * @hbus:	The root PCI bus
+ *
+ * This function creates an IRQ domain which will be used for
+ * interrupts from devices that have been passed through.  These
+ * devices only support MSI and MSI-X, not line-based interrupts
+ * or simulations of line-based interrupts through PCIe's