PCI: Collect all native drivers under drivers/pci/controller/

Native PCI drivers for root complex devices were originally all in
drivers/pci/host/.  Some of these devices can also be operated in endpoint
mode.  Drivers for endpoint mode didn't seem to fit in the "host"
directory, so we put both the root complex and endpoint drivers in
per-device directories, e.g., drivers/pci/dwc/, drivers/pci/cadence/, etc.

These per-device directories contain trivial Kconfig and Makefiles and
clutter drivers/pci/.  Make a new drivers/pci/controllers/ directory and
collect all the device-specific drivers there.

No functional change intended.

Link: https://lkml.kernel.org/r/1520304202-232891-1-git-send-email-shawn.lin@rock-chips.com
Signed-off-by: Shawn Lin <shawn.lin@rock-chips.com>
[bhelgaas: changelog]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>

1 files changed, 2694 insertions, 0 deletions

diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
new file mode 100644
index 000000000000..6cc5036ac83c
--- /dev/null
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -0,0 +1,2694 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * 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.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/delay.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 <linux/refcount.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) | (minor)))
+#define PCI_MAJOR_VERSION(version) ((u32)(version) >> 16)
+#define PCI_MINOR_VERSION(version) ((u32)(version) & 0xff)
+
+enum pci_protocol_version_t {
+	PCI_PROTOCOL_VERSION_1_1 = PCI_MAKE_VERSION(1, 1),	/* Win10 */
+	PCI_PROTOCOL_VERSION_1_2 = PCI_MAKE_VERSION(1, 2),	/* RS1 */
+};
+
+#define CPU_AFFINITY_ALL	-1ULL
+
+/*
+ * Supported protocol versions in the order of probing - highest go
+ * first.
+ */
+static enum pci_protocol_version_t pci_protocol_versions[] = {
+	PCI_PROTOCOL_VERSION_1_2,
+	PCI_PROTOCOL_VERSION_1_1,
+};
+
+/*
+ * Protocol version negotiated by hv_pci_protocol_negotiation().
+ */
+static enum pci_protocol_version_t pci_protocol_version;
+
+#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
+
+#define STATUS_REVISION_MISMATCH 0xC0000059
+
+/*
+ * 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_RESOURCES_ASSIGNED2		= PCI_MESSAGE_BASE + 0x16,
+	PCI_CREATE_INTERRUPT_MESSAGE2	= PCI_MESSAGE_BASE + 0x17,
+	PCI_DELETE_INTERRUPT_MESSAGE2	= PCI_MESSAGE_BASE + 0x18, /* unused */
+	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	dev:5;
+		u32	func:3;
+		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 hv_msi_desc2 - 1.2 version of 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.
+ * @processor_count:	number of bits enabled in array.
+ * @processor_array:	All the target virtual processors.
+ */
+struct hv_msi_desc2 {
+	u8	vector;
+	u8	delivery_mode;
+	u16	vector_count;
+	u16	processor_count;
+	u16	processor_array[32];
+} __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 type;
+} __packed;
+
+struct pci_child_message {
+	struct pci_message 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[0];
+};
+
+/*
+ * 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;
+	u32 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[0];
+} __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_resources_assigned2 {
+	struct pci_message message_type;
+	union win_slot_encoding wslot;
+	u8 memory_range[0x14][6];	/* not used here */
+	u32 msi_descriptor_count;
+	u8 reserved[70];
+} __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_create_interrupt2 {
+	struct pci_message message_type;
+	union win_slot_encoding wslot;
+	struct hv_msi_desc2 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 {
+	struct pci_message 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 hv_interrupt_entry {
+	u32	source;			/* 1 for MSI(-X) */
+	u32	reserved1;
+	u32	address;
+	u32	data;
+};
+
+#define HV_VP_SET_BANK_COUNT_MAX	5 /* current implementation limit */
+
+struct hv_vp_set {
+	u64	format;			/* 0 (HvGenericSetSparse4k) */
+	u64	valid_banks;
+	u64	masks[HV_VP_SET_BANK_COUNT_MAX];
+};
+
+/*
+ * flags for hv_device_interrupt_target.flags
+ */
+#define HV_DEVICE_INTERRUPT_TARGET_MULTICAST		1
+#define HV_DEVICE_INTERRUPT_TARGET_PROCESSOR_SET	2
+
+struct hv_device_interrupt_target {
+	u32	vector;
+	u32	flags;
+	union {
+		u64		 vp_mask;
+		struct hv_vp_set vp_set;
+	};
+};
+
+struct retarget_msi_interrupt {
+	u64	partition_id;		/* use "self" */
+	u64	device_id;
+	struct hv_interrupt_entry int_entry;
+	u64	reserved2;
+	struct hv_device_interrupt_target int_target;
+} __packed;
+
+/*
+ * Driver specific state.
+ */
+
+enum hv_pcibus_state {
+	hv_pcibus_init = 0,
+	hv_pcibus_probed,
+	hv_pcibus_installed,
+	hv_pcibus_removed,
+	hv_pcibus_maximum
+};
+
+struct hv_pcibus_device {
+	struct pci_sysdata sysdata;
+	enum hv_pcibus_state state;
+	refcount_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 list_head resources_for_children;
+
+	struct list_head children;
+	struct list_head dr_list;
+
+	struct msi_domain_info msi_info;
+	struct msi_controller msi_chip;
+	struct irq_domain *irq_domain;
+
+	/* hypercall arg, must not cross page boundary */
+	struct retarget_msi_interrupt retarget_msi_interrupt_params;
+
+	spinlock_t retarget_msi_interrupt_lock;
+
+	struct workqueue_struct *wq;
+};
+
+/*
+ * 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[0];
+};
+
+enum hv_pcichild_state {
+	hv_pcichild_init = 0,
+	hv_pcichild_requirements,
+	hv_pcichild_resourced,
+	hv_pcichild_ejecting,
+	hv_pcichild_maximum
+};
+
+struct hv_pci_dev {
+	/* List protected by pci_rescan_remove_lock */
+	struct list_head list_entry;
+	refcount_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;
+};
+
+static void hv_pci_onchannelcallback(void *context);
+
+/**
+ * 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;
+	else
+		comp_pkt->completion_status = -1;
+
+	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 *hpdev)
+{
+	refcount_inc(&hpdev->refs);
+}
+
+static void put_pcichild(struct hv_pci_dev *hpdev)
+{
+	if (refcount_dec_and_test(&hpdev->refs))
+		kfree(hpdev);
+}
+
+static void get_hvpcibus(struct hv_pcibus_device *hv_pcibus);
+static void put_hvpcibus(struct hv_pcibus_device *hv_pcibus);
+
+/*
+ * There is no good way to get notified from vmbus_onoffer_rescind(),
+ * so let's use polling here, since this is not a hot path.
+ */
+static int wait_for_response(struct hv_device *hdev,
+			     struct completion *comp)
+{
+	while (true) {
+		if (hdev->channel->rescind) {
+			dev_warn_once(&hdev->device, "The device is gone.\n");
+			return -ENODEV;
+		}
+
+		if (wait_for_completion_timeout(comp, HZ / 10))
+			break;
+	}
+
+	return 0;
+}
+
+/**
+ * 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.dev = PCI_SLOT(devfn);
+	wslot.bits.func = PCI_FUNC(devfn);
+
+	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(slot_no.bits.dev, 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);
+		/* Make sure the function was chosen before we start reading. */
+		mb();
+		/* 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;
+		}
+		/*
+		 * Make sure the read was done before we release the spinlock
+		 * allowing consecutive reads/writes.
+		 */
+		mb();
+		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");
+	}
+}
+
+static u16 hv_pcifront_get_vendor_id(struct hv_pci_dev *hpdev)
+{
+	u16 ret;
+	unsigned long flags;
+	void __iomem *addr = hpdev->hbus->cfg_addr + CFG_PAGE_OFFSET +
+			     PCI_VENDOR_ID;
+
+	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);
+	/* Make sure the function was chosen before we start reading. */
+	mb();
+	/* Read from that function's config space. */
+	ret = readw(addr);
+	/*
+	 * mb() is not required here, because the spin_unlock_irqrestore()
+	 * is a barrier.
+	 */
+
+	spin_unlock_irqrestore(&hpdev->hbus->config_lock, flags);
+
+	return ret;
+}
+
+/**
+ * _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);
+		/* Make sure the function was chosen before we start writing. */
+		wmb();
+		/* 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;
+		}
+		/*
+		 * Make sure the write was done before we release the spinlock
+		 * allowing consecutive reads/writes.
+		 */
+		mb();
+		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);
+	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);
+	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)];
+	} ctxt;
+
+	memset(&ctxt, 0, sizeof(ctxt));
+	int_pkt = (struct pci_delete_interrupt *)&ctxt.pkt.message;
+	int_pkt->message_type.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;
+	int_desc = irq_data_get_irq_chip_data(irq_data);
+	if (!int_desc)
+		return;
+
+	irq_data->chip_data = NULL;
+	hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(pdev->devfn));
+	if (!hpdev) {
+		kfree(int_desc);
+		return;
+	}
+
+	hv_int_desc_free(hpdev, int_desc);
+	put_pcichild(hpdev);
+}
+
+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);
+}
+
+static 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.
+ */
+static 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;
+	unsigned long flags;
+	u32 var_size = 0;
+	int cpu_vmbus;
+	int cpu;
+	u64 res;
+
+	dest = irq_data_get_effective_affinity_mask(data);
+	pdev = msi_desc_to_pci_dev(msi_desc);
+	pbus = pdev->bus;
+	hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata);
+
+	spin_lock_irqsave(&hbus->retarget_msi_interrupt_lock, flags);
+
+	params = &hbus->retarget_msi_interrupt_params;
+	memset(params, 0, sizeof(*params));
+	params->partition_id = HV_PARTITION_ID_SELF;
+	params->int_entry.source = 1; /* MSI(-X) */
+	params->int_entry.address = msi_desc->msg.address_lo;
+	params->int_entry.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->int_target.vector = cfg->vector;
+
+	/*
+	 * Honoring apic->irq_delivery_mode set to dest_Fixed by
+	 * setting the HV_DEVICE_INTERRUPT_TARGET_MULTICAST flag results in a
+	 * spurious interrupt storm. Not doing so does not seem to have a
+	 * negative effect (yet?).
+	 */
+
+	if (pci_protocol_version >= PCI_PROTOCOL_VERSION_1_2) {
+		/*
+		 * PCI_PROTOCOL_VERSION_1_2 supports the VP_SET version of the
+		 * HVCALL_RETARGET_INTERRUPT hypercall, which also coincides
+		 * with >64 VP support.
+		 * ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED
+		 * is not sufficient for this hypercall.
+		 */
+		params->int_target.flags |=
+			HV_DEVICE_INTERRUPT_TARGET_PROCESSOR_SET;
+		params->int_target.vp_set.valid_banks =
+			(1ull << HV_VP_SET_BANK_COUNT_MAX) - 1;
+
+		/*
+		 * var-sized hypercall, var-size starts after vp_mask (thus
+		 * vp_set.format does not count, but vp_set.valid_banks does).
+		 */
+		var_size = 1 + HV_VP_SET_BANK_COUNT_MAX;
+
+		for_each_cpu_and(cpu, dest, cpu_online_mask) {
+			cpu_vmbus = hv_cpu_number_to_vp_number(cpu);
+
+			if (cpu_vmbus >= HV_VP_SET_BANK_COUNT_MAX * 64) {
+				dev_err(&hbus->hdev->device,
+					"too high CPU %d", cpu_vmbus);
+				res = 1;
+				goto exit_unlock;
+			}
+
+			params->int_target.vp_set.masks[cpu_vmbus / 64] |=
+				(1ULL << (cpu_vmbus & 63));
+		}
+	} else {
+		for_each_cpu_and(cpu, dest, cpu_online_mask) {
+			params->int_target.vp_mask |=
+				(1ULL << hv_cpu_number_to_vp_number(cpu));
+		}
+	}
+
+	res = hv_do_hypercall(HVCALL_RETARGET_INTERRUPT | (var_size << 17),
+			      params, NULL);
+
+exit_unlock:
+	spin_unlock_irqrestore(&hbus->retarget_msi_interrupt_lock, flags);
+
+	if (res) {
+		dev_err(&hbus->hdev->device,
+			"%s() failed: %#llx", __func__, res);
+		return;
+	}
+
+	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);
+}
+
+static u32 hv_compose_msi_req_v1(
+	struct pci_create_interrupt *int_pkt, struct cpumask *affinity,
+	u32 slot, u8 vector)
+{
+	int_pkt->message_type.type = PCI_CREATE_INTERRUPT_MESSAGE;
+	int_pkt->wslot.slot = slot;
+	int_pkt->int_desc.vector = vector;
+	int_pkt->int_desc.vector_count = 1;
+	int_pkt->int_desc.delivery_mode = dest_Fixed;
+
+	/*
+	 * Create MSI w/ dummy vCPU set, overwritten by subsequent retarget in
+	 * hv_irq_unmask().
+	 */
+	int_pkt->int_desc.cpu_mask = CPU_AFFINITY_ALL;
+
+	return sizeof(*int_pkt);
+}
+
+static u32 hv_compose_msi_req_v2(
+	struct pci_create_interrupt2 *int_pkt, struct cpumask *affinity,
+	u32 slot, u8 vector)
+{
+	int cpu;
+
+	int_pkt->message_type.type = PCI_CREATE_INTERRUPT_MESSAGE2;
+	int_pkt->wslot.slot = slot;
+	int_pkt->int_desc.vector = vector;
+	int_pkt->int_desc.vector_count = 1;
+	int_pkt->int_desc.delivery_mode = dest_Fixed;
+
+	/*
+	 * Create MSI w/ dummy vCPU set targeting just one vCPU, overwritten
+	 * by subsequent retarget in hv_irq_unmask().
+	 */
+	cpu = cpumask_first_and(affinity, cpu_online_mask);
+	int_pkt->int_desc.processor_array[0] =
+		hv_cpu_number_to_vp_number(cpu);
+	int_pkt->int_desc.processor_count = 1;
+
+	return sizeof(*int_pkt);
+}
+
+/**
+ * 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 cpumask *dest;
+	struct compose_comp_ctxt comp;
+	struct tran_int_desc *int_desc;
+	struct {
+		struct pci_packet pci_pkt;
+		union {