Initial import

21 files changed, 8469 insertions, 0 deletions

diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig
new file mode 100644
index 000000000..7d092ddc8
--- /dev/null
+++ b/drivers/vfio/Kconfig
@@ -0,0 +1,35 @@
+config VFIO_IOMMU_TYPE1
+	tristate
+	depends on VFIO
+	default n
+
+config VFIO_IOMMU_SPAPR_TCE
+	tristate
+	depends on VFIO && SPAPR_TCE_IOMMU
+	default n
+
+config VFIO_SPAPR_EEH
+	tristate
+	depends on EEH && VFIO_IOMMU_SPAPR_TCE
+	default n
+
+config VFIO_VIRQFD
+	tristate
+	depends on VFIO && EVENTFD
+	default n
+
+menuconfig VFIO
+	tristate "VFIO Non-Privileged userspace driver framework"
+	depends on IOMMU_API
+	select VFIO_IOMMU_TYPE1 if (X86 || S390 || ARM_SMMU)
+	select VFIO_IOMMU_SPAPR_TCE if (PPC_POWERNV || PPC_PSERIES)
+	select VFIO_SPAPR_EEH if (PPC_POWERNV || PPC_PSERIES)
+	select ANON_INODES
+	help
+	  VFIO provides a framework for secure userspace device drivers.
+	  See Documentation/vfio.txt for more details.
+
+	  If you don't know what to do here, say N.
+
+source "drivers/vfio/pci/Kconfig"
+source "drivers/vfio/platform/Kconfig"
diff --git a/drivers/vfio/Makefile b/drivers/vfio/Makefile
new file mode 100644
index 000000000..7b8a31f63
--- /dev/null
+++ b/drivers/vfio/Makefile
@@ -0,0 +1,9 @@
+vfio_virqfd-y := virqfd.o
+
+obj-$(CONFIG_VFIO) += vfio.o
+obj-$(CONFIG_VFIO_VIRQFD) += vfio_virqfd.o
+obj-$(CONFIG_VFIO_IOMMU_TYPE1) += vfio_iommu_type1.o
+obj-$(CONFIG_VFIO_IOMMU_SPAPR_TCE) += vfio_iommu_spapr_tce.o
+obj-$(CONFIG_VFIO_SPAPR_EEH) += vfio_spapr_eeh.o
+obj-$(CONFIG_VFIO_PCI) += pci/
+obj-$(CONFIG_VFIO_PLATFORM) += platform/
diff --git a/drivers/vfio/pci/Kconfig b/drivers/vfio/pci/Kconfig
new file mode 100644
index 000000000..579d83bf5
--- /dev/null
+++ b/drivers/vfio/pci/Kconfig
@@ -0,0 +1,27 @@
+config VFIO_PCI
+	tristate "VFIO support for PCI devices"
+	depends on VFIO && PCI && EVENTFD
+	select VFIO_VIRQFD
+	help
+	  Support for the PCI VFIO bus driver.  This is required to make
+	  use of PCI drivers using the VFIO framework.
+
+	  If you don't know what to do here, say N.
+
+config VFIO_PCI_VGA
+	bool "VFIO PCI support for VGA devices"
+	depends on VFIO_PCI && X86 && VGA_ARB
+	help
+	  Support for VGA extension to VFIO PCI.  This exposes an additional
+	  region on VGA devices for accessing legacy VGA addresses used by
+	  BIOS and generic video drivers.
+
+	  If you don't know what to do here, say N.
+
+config VFIO_PCI_MMAP
+	depends on VFIO_PCI
+	def_bool y if !S390
+
+config VFIO_PCI_INTX
+	depends on VFIO_PCI
+	def_bool y if !S390
diff --git a/drivers/vfio/pci/Makefile b/drivers/vfio/pci/Makefile
new file mode 100644
index 000000000..131079255
--- /dev/null
+++ b/drivers/vfio/pci/Makefile
@@ -0,0 +1,4 @@
+
+vfio-pci-y := vfio_pci.o vfio_pci_intrs.o vfio_pci_rdwr.o vfio_pci_config.o
+
+obj-$(CONFIG_VFIO_PCI) += vfio-pci.o
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
new file mode 100644
index 000000000..e9851add6
--- /dev/null
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -0,0 +1,1215 @@
+/*
+ * Copyright (C) 2012 Red Hat, Inc.  All rights reserved.
+ *     Author: Alex Williamson <alex.williamson@redhat.com>
+ *
+ * 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.
+ *
+ * Derived from original vfio:
+ * Copyright 2010 Cisco Systems, Inc.  All rights reserved.
+ * Author: Tom Lyon, pugs@cisco.com
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/device.h>
+#include <linux/eventfd.h>
+#include <linux/file.h>
+#include <linux/interrupt.h>
+#include <linux/iommu.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/notifier.h>
+#include <linux/pci.h>
+#include <linux/pm_runtime.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <linux/vfio.h>
+#include <linux/vgaarb.h>
+
+#include "vfio_pci_private.h"
+
+#define DRIVER_VERSION  "0.2"
+#define DRIVER_AUTHOR   "Alex Williamson <alex.williamson@redhat.com>"
+#define DRIVER_DESC     "VFIO PCI - User Level meta-driver"
+
+static char ids[1024] __initdata;
+module_param_string(ids, ids, sizeof(ids), 0);
+MODULE_PARM_DESC(ids, "Initial PCI IDs to add to the vfio driver, format is \"vendor:device[:subvendor[:subdevice[:class[:class_mask]]]]\" and multiple comma separated entries can be specified");
+
+static bool nointxmask;
+module_param_named(nointxmask, nointxmask, bool, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(nointxmask,
+		  "Disable support for PCI 2.3 style INTx masking.  If this resolves problems for specific devices, report lspci -vvvxxx to linux-pci@vger.kernel.org so the device can be fixed automatically via the broken_intx_masking flag.");
+
+#ifdef CONFIG_VFIO_PCI_VGA
+static bool disable_vga;
+module_param(disable_vga, bool, S_IRUGO);
+MODULE_PARM_DESC(disable_vga, "Disable VGA resource access through vfio-pci");
+#endif
+
+static bool disable_idle_d3;
+module_param(disable_idle_d3, bool, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(disable_idle_d3,
+		 "Disable using the PCI D3 low power state for idle, unused devices");
+
+static DEFINE_MUTEX(driver_lock);
+
+static inline bool vfio_vga_disabled(void)
+{
+#ifdef CONFIG_VFIO_PCI_VGA
+	return disable_vga;
+#else
+	return true;
+#endif
+}
+
+/*
+ * Our VGA arbiter participation is limited since we don't know anything
+ * about the device itself.  However, if the device is the only VGA device
+ * downstream of a bridge and VFIO VGA support is disabled, then we can
+ * safely return legacy VGA IO and memory as not decoded since the user
+ * has no way to get to it and routing can be disabled externally at the
+ * bridge.
+ */
+static unsigned int vfio_pci_set_vga_decode(void *opaque, bool single_vga)
+{
+	struct vfio_pci_device *vdev = opaque;
+	struct pci_dev *tmp = NULL, *pdev = vdev->pdev;
+	unsigned char max_busnr;
+	unsigned int decodes;
+
+	if (single_vga || !vfio_vga_disabled() || pci_is_root_bus(pdev->bus))
+		return VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM |
+		       VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM;
+
+	max_busnr = pci_bus_max_busnr(pdev->bus);
+	decodes = VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM;
+
+	while ((tmp = pci_get_class(PCI_CLASS_DISPLAY_VGA << 8, tmp)) != NULL) {
+		if (tmp == pdev ||
+		    pci_domain_nr(tmp->bus) != pci_domain_nr(pdev->bus) ||
+		    pci_is_root_bus(tmp->bus))
+			continue;
+
+		if (tmp->bus->number >= pdev->bus->number &&
+		    tmp->bus->number <= max_busnr) {
+			pci_dev_put(tmp);
+			decodes |= VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM;
+			break;
+		}
+	}
+
+	return decodes;
+}
+
+static inline bool vfio_pci_is_vga(struct pci_dev *pdev)
+{
+	return (pdev->class >> 8) == PCI_CLASS_DISPLAY_VGA;
+}
+
+static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev);
+
+static int vfio_pci_enable(struct vfio_pci_device *vdev)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	int ret;
+	u16 cmd;
+	u8 msix_pos;
+
+	pci_set_power_state(pdev, PCI_D0);
+
+	/* Don't allow our initial saved state to include busmaster */
+	pci_clear_master(pdev);
+
+	ret = pci_enable_device(pdev);
+	if (ret)
+		return ret;
+
+	vdev->reset_works = (pci_reset_function(pdev) == 0);
+	pci_save_state(pdev);
+	vdev->pci_saved_state = pci_store_saved_state(pdev);
+	if (!vdev->pci_saved_state)
+		pr_debug("%s: Couldn't store %s saved state\n",
+			 __func__, dev_name(&pdev->dev));
+
+	ret = vfio_config_init(vdev);
+	if (ret) {
+		kfree(vdev->pci_saved_state);
+		vdev->pci_saved_state = NULL;
+		pci_disable_device(pdev);
+		return ret;
+	}
+
+	if (likely(!nointxmask))
+		vdev->pci_2_3 = pci_intx_mask_supported(pdev);
+
+	pci_read_config_word(pdev, PCI_COMMAND, &cmd);
+	if (vdev->pci_2_3 && (cmd & PCI_COMMAND_INTX_DISABLE)) {
+		cmd &= ~PCI_COMMAND_INTX_DISABLE;
+		pci_write_config_word(pdev, PCI_COMMAND, cmd);
+	}
+
+	msix_pos = pdev->msix_cap;
+	if (msix_pos) {
+		u16 flags;
+		u32 table;
+
+		pci_read_config_word(pdev, msix_pos + PCI_MSIX_FLAGS, &flags);
+		pci_read_config_dword(pdev, msix_pos + PCI_MSIX_TABLE, &table);
+
+		vdev->msix_bar = table & PCI_MSIX_TABLE_BIR;
+		vdev->msix_offset = table & PCI_MSIX_TABLE_OFFSET;
+		vdev->msix_size = ((flags & PCI_MSIX_FLAGS_QSIZE) + 1) * 16;
+	} else
+		vdev->msix_bar = 0xFF;
+
+	if (!vfio_vga_disabled() && vfio_pci_is_vga(pdev))
+		vdev->has_vga = true;
+
+	return 0;
+}
+
+static void vfio_pci_disable(struct vfio_pci_device *vdev)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	int bar;
+
+	/* Stop the device from further DMA */
+	pci_clear_master(pdev);
+
+	vfio_pci_set_irqs_ioctl(vdev, VFIO_IRQ_SET_DATA_NONE |
+				VFIO_IRQ_SET_ACTION_TRIGGER,
+				vdev->irq_type, 0, 0, NULL);
+
+	vdev->virq_disabled = false;
+
+	vfio_config_free(vdev);
+
+	for (bar = PCI_STD_RESOURCES; bar <= PCI_STD_RESOURCE_END; bar++) {
+		if (!vdev->barmap[bar])
+			continue;
+		pci_iounmap(pdev, vdev->barmap[bar]);
+		pci_release_selected_regions(pdev, 1 << bar);
+		vdev->barmap[bar] = NULL;
+	}
+
+	vdev->needs_reset = true;
+
+	/*
+	 * If we have saved state, restore it.  If we can reset the device,
+	 * even better.  Resetting with current state seems better than
+	 * nothing, but saving and restoring current state without reset
+	 * is just busy work.
+	 */
+	if (pci_load_and_free_saved_state(pdev, &vdev->pci_saved_state)) {
+		pr_info("%s: Couldn't reload %s saved state\n",
+			__func__, dev_name(&pdev->dev));
+
+		if (!vdev->reset_works)
+			goto out;
+
+		pci_save_state(pdev);
+	}
+
+	/*
+	 * Disable INTx and MSI, presumably to avoid spurious interrupts
+	 * during reset.  Stolen from pci_reset_function()
+	 */
+	pci_write_config_word(pdev, PCI_COMMAND, PCI_COMMAND_INTX_DISABLE);
+
+	/*
+	 * Try to reset the device.  The success of this is dependent on
+	 * being able to lock the device, which is not always possible.
+	 */
+	if (vdev->reset_works && !pci_try_reset_function(pdev))
+		vdev->needs_reset = false;
+
+	pci_restore_state(pdev);
+out:
+	pci_disable_device(pdev);
+
+	vfio_pci_try_bus_reset(vdev);
+
+	if (!disable_idle_d3)
+		pci_set_power_state(pdev, PCI_D3hot);
+}
+
+static void vfio_pci_release(void *device_data)
+{
+	struct vfio_pci_device *vdev = device_data;
+
+	mutex_lock(&driver_lock);
+
+	if (!(--vdev->refcnt)) {
+		vfio_spapr_pci_eeh_release(vdev->pdev);
+		vfio_pci_disable(vdev);
+	}
+
+	mutex_unlock(&driver_lock);
+
+	module_put(THIS_MODULE);
+}
+
+static int vfio_pci_open(void *device_data)
+{
+	struct vfio_pci_device *vdev = device_data;
+	int ret = 0;
+
+	if (!try_module_get(THIS_MODULE))
+		return -ENODEV;
+
+	mutex_lock(&driver_lock);
+
+	if (!vdev->refcnt) {
+		ret = vfio_pci_enable(vdev);
+		if (ret)
+			goto error;
+
+		vfio_spapr_pci_eeh_open(vdev->pdev);
+	}
+	vdev->refcnt++;
+error:
+	mutex_unlock(&driver_lock);
+	if (ret)
+		module_put(THIS_MODULE);
+	return ret;
+}
+
+static int vfio_pci_get_irq_count(struct vfio_pci_device *vdev, int irq_type)
+{
+	if (irq_type == VFIO_PCI_INTX_IRQ_INDEX) {
+		u8 pin;
+		pci_read_config_byte(vdev->pdev, PCI_INTERRUPT_PIN, &pin);
+		if (IS_ENABLED(CONFIG_VFIO_PCI_INTX) && pin)
+			return 1;
+
+	} else if (irq_type == VFIO_PCI_MSI_IRQ_INDEX) {
+		u8 pos;
+		u16 flags;
+
+		pos = vdev->pdev->msi_cap;
+		if (pos) {
+			pci_read_config_word(vdev->pdev,
+					     pos + PCI_MSI_FLAGS, &flags);
+			return 1 << ((flags & PCI_MSI_FLAGS_QMASK) >> 1);
+		}
+	} else if (irq_type == VFIO_PCI_MSIX_IRQ_INDEX) {
+		u8 pos;
+		u16 flags;
+
+		pos = vdev->pdev->msix_cap;
+		if (pos) {
+			pci_read_config_word(vdev->pdev,
+					     pos + PCI_MSIX_FLAGS, &flags);
+
+			return (flags & PCI_MSIX_FLAGS_QSIZE) + 1;
+		}
+	} else if (irq_type == VFIO_PCI_ERR_IRQ_INDEX) {
+		if (pci_is_pcie(vdev->pdev))
+			return 1;
+	} else if (irq_type == VFIO_PCI_REQ_IRQ_INDEX) {
+		return 1;
+	}
+
+	return 0;
+}
+
+static int vfio_pci_count_devs(struct pci_dev *pdev, void *data)
+{
+	(*(int *)data)++;
+	return 0;
+}
+
+struct vfio_pci_fill_info {
+	int max;
+	int cur;
+	struct vfio_pci_dependent_device *devices;
+};
+
+static int vfio_pci_fill_devs(struct pci_dev *pdev, void *data)
+{
+	struct vfio_pci_fill_info *fill = data;
+	struct iommu_group *iommu_group;
+
+	if (fill->cur == fill->max)
+		return -EAGAIN; /* Something changed, try again */
+
+	iommu_group = iommu_group_get(&pdev->dev);
+	if (!iommu_group)
+		return -EPERM; /* Cannot reset non-isolated devices */
+
+	fill->devices[fill->cur].group_id = iommu_group_id(iommu_group);
+	fill->devices[fill->cur].segment = pci_domain_nr(pdev->bus);
+	fill->devices[fill->cur].bus = pdev->bus->number;
+	fill->devices[fill->cur].devfn = pdev->devfn;
+	fill->cur++;
+	iommu_group_put(iommu_group);
+	return 0;
+}
+
+struct vfio_pci_group_entry {
+	struct vfio_group *group;
+	int id;
+};
+
+struct vfio_pci_group_info {
+	int count;
+	struct vfio_pci_group_entry *groups;
+};
+
+static int vfio_pci_validate_devs(struct pci_dev *pdev, void *data)
+{
+	struct vfio_pci_group_info *info = data;
+	struct iommu_group *group;
+	int id, i;
+
+	group = iommu_group_get(&pdev->dev);
+	if (!group)
+		return -EPERM;
+
+	id = iommu_group_id(group);
+
+	for (i = 0; i < info->count; i++)
+		if (info->groups[i].id == id)
+			break;
+
+	iommu_group_put(group);
+
+	return (i == info->count) ? -EINVAL : 0;
+}
+
+static bool vfio_pci_dev_below_slot(struct pci_dev *pdev, struct pci_slot *slot)
+{
+	for (; pdev; pdev = pdev->bus->self)
+		if (pdev->bus == slot->bus)
+			return (pdev->slot == slot);
+	return false;
+}
+
+struct vfio_pci_walk_info {
+	int (*fn)(struct pci_dev *, void *data);
+	void *data;
+	struct pci_dev *pdev;
+	bool slot;
+	int ret;
+};
+
+static int vfio_pci_walk_wrapper(struct pci_dev *pdev, void *data)
+{
+	struct vfio_pci_walk_info *walk = data;
+
+	if (!walk->slot || vfio_pci_dev_below_slot(pdev, walk->pdev->slot))
+		walk->ret = walk->fn(pdev, walk->data);
+
+	return walk->ret;
+}
+
+static int vfio_pci_for_each_slot_or_bus(struct pci_dev *pdev,
+					 int (*fn)(struct pci_dev *,
+						   void *data), void *data,
+					 bool slot)
+{
+	struct vfio_pci_walk_info walk = {
+		.fn = fn, .data = data, .pdev = pdev, .slot = slot, .ret = 0,
+	};
+
+	pci_walk_bus(pdev->bus, vfio_pci_walk_wrapper, &walk);
+
+	return walk.ret;
+}
+
+static long vfio_pci_ioctl(void *device_data,
+			   unsigned int cmd, unsigned long arg)
+{
+	struct vfio_pci_device *vdev = device_data;
+	unsigned long minsz;
+
+	if (cmd == VFIO_DEVICE_GET_INFO) {
+		struct vfio_device_info info;
+
+		minsz = offsetofend(struct vfio_device_info, num_irqs);
+
+		if (copy_from_user(&info, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (info.argsz < minsz)
+			return -EINVAL;
+
+		info.flags = VFIO_DEVICE_FLAGS_PCI;
+
+		if (vdev->reset_works)
+			info.flags |= VFIO_DEVICE_FLAGS_RESET;
+
+		info.num_regions = VFIO_PCI_NUM_REGIONS;
+		info.num_irqs = VFIO_PCI_NUM_IRQS;
+
+		return copy_to_user((void __user *)arg, &info, minsz);
+
+	} else if (cmd == VFIO_DEVICE_GET_REGION_INFO) {
+		struct pci_dev *pdev = vdev->pdev;
+		struct vfio_region_info info;
+
+		minsz = offsetofend(struct vfio_region_info, offset);
+
+		if (copy_from_user(&info, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (info.argsz < minsz)
+			return -EINVAL;
+
+		switch (info.index) {
+		case VFIO_PCI_CONFIG_REGION_INDEX:
+			info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index);
+			info.size = pdev->cfg_size;
+			info.flags = VFIO_REGION_INFO_FLAG_READ |
+				     VFIO_REGION_INFO_FLAG_WRITE;
+			break;
+		case VFIO_PCI_BAR0_REGION_INDEX ... VFIO_PCI_BAR5_REGION_INDEX:
+			info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index);
+			info.size = pci_resource_len(pdev, info.index);
+			if (!info.size) {
+				info.flags = 0;
+				break;
+			}
+
+			info.flags = VFIO_REGION_INFO_FLAG_READ |
+				     VFIO_REGION_INFO_FLAG_WRITE;
+			if (IS_ENABLED(CONFIG_VFIO_PCI_MMAP) &&
+			    pci_resource_flags(pdev, info.index) &
+			    IORESOURCE_MEM && info.size >= PAGE_SIZE)
+				info.flags |= VFIO_REGION_INFO_FLAG_MMAP;
+			break;
+		case VFIO_PCI_ROM_REGION_INDEX:
+		{
+			void __iomem *io;
+			size_t size;
+
+			info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index);
+			info.flags = 0;
+
+			/* Report the BAR size, not the ROM size */
+			info.size = pci_resource_len(pdev, info.index);
+			if (!info.size)
+				break;
+
+			/* Is it really there? */
+			io = pci_map_rom(pdev, &size);
+			if (!io || !size) {
+				info.size = 0;
+				break;
+			}
+			pci_unmap_rom(pdev, io);
+
+			info.flags = VFIO_REGION_INFO_FLAG_READ;
+			break;
+		}
+		case VFIO_PCI_VGA_REGION_INDEX:
+			if (!vdev->has_vga)
+				return -EINVAL;
+
+			info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index);
+			info.size = 0xc0000;
+			info.flags = VFIO_REGION_INFO_FLAG_READ |
+				     VFIO_REGION_INFO_FLAG_WRITE;
+
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		return copy_to_user((void __user *)arg, &info, minsz);
+
+	} else if (cmd == VFIO_DEVICE_GET_IRQ_INFO) {
+		struct vfio_irq_info info;
+
+		minsz = offsetofend(struct vfio_irq_info, count);
+
+		if (copy_from_user(&info, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (info.argsz < minsz || info.index >= VFIO_PCI_NUM_IRQS)
+			return -EINVAL;
+
+		switch (info.index) {
+		case VFIO_PCI_INTX_IRQ_INDEX ... VFIO_PCI_MSIX_IRQ_INDEX:
+		case VFIO_PCI_REQ_IRQ_INDEX:
+			break;
+		case VFIO_PCI_ERR_IRQ_INDEX:
+			if (pci_is_pcie(vdev->pdev))
+				break;
+		/* pass thru to return error */
+		default:
+			return -EINVAL;
+		}
+
+		info.flags = VFIO_IRQ_INFO_EVENTFD;
+
+		info.count = vfio_pci_get_irq_count(vdev, info.index);
+
+		if (info.index == VFIO_PCI_INTX_IRQ_INDEX)
+			info.flags |= (VFIO_IRQ_INFO_MASKABLE |
+				       VFIO_IRQ_INFO_AUTOMASKED);
+		else
+			info.flags |= VFIO_IRQ_INFO_NORESIZE;
+
+		return copy_to_user((void __user *)arg, &info, minsz);
+
+	} else if (cmd == VFIO_DEVICE_SET_IRQS) {
+		struct vfio_irq_set hdr;
+		u8 *data = NULL;
+		int ret = 0;
+
+		minsz = offsetofend(struct vfio_irq_set, count);
+
+		if (copy_from_user(&hdr, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (hdr.argsz < minsz || hdr.index >= VFIO_PCI_NUM_IRQS ||
+		    hdr.flags & ~(VFIO_IRQ_SET_DATA_TYPE_MASK |
+				  VFIO_IRQ_SET_ACTION_TYPE_MASK))
+			return -EINVAL;
+
+		if (!(hdr.flags & VFIO_IRQ_SET_DATA_NONE)) {
+			size_t size;
+			int max = vfio_pci_get_irq_count(vdev, hdr.index);
+
+			if (hdr.flags & VFIO_IRQ_SET_DATA_BOOL)
+				size = sizeof(uint8_t);
+			else if (hdr.flags & VFIO_IRQ_SET_DATA_EVENTFD)
+				size = sizeof(int32_t);
+			else
+				return -EINVAL;
+
+			if (hdr.argsz - minsz < hdr.count * size ||
+			    hdr.start >= max || hdr.start + hdr.count > max)
+				return -EINVAL;
+
+			data = memdup_user((void __user *)(arg + minsz),
+					   hdr.count * size);
+			if (IS_ERR(data))
+				return PTR_ERR(data);
+		}
+
+		mutex_lock(&vdev->igate);
+
+		ret = vfio_pci_set_irqs_ioctl(vdev, hdr.flags, hdr.index,
+					      hdr.start, hdr.count, data);
+
+		mutex_unlock(&vdev->igate);
+		kfree(data);
+
+		return ret;
+
+	} else if (cmd == VFIO_DEVICE_RESET) {
+		return vdev->reset_works ?
+			pci_try_reset_function(vdev->pdev) : -EINVAL;
+
+	} else if (cmd == VFIO_DEVICE_GET_PCI_HOT_RESET_INFO) {
+		struct vfio_pci_hot_reset_info hdr;
+		struct vfio_pci_fill_info fill = { 0 };
+		struct vfio_pci_dependent_device *devices = NULL;
+		bool slot = false;
+		int ret = 0;
+
+		minsz = offsetofend(struct vfio_pci_hot_reset_info, count);
+
+		if (copy_from_user(&hdr, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (hdr.argsz < minsz)
+			return -EINVAL;
+
+		hdr.flags = 0;
+
+		/* Can we do a slot or bus reset or neither? */
+		if (!pci_probe_reset_slot(vdev->pdev->slot))
+			slot = true;
+		else if (pci_probe_reset_bus(vdev->pdev->bus))
+			return -ENODEV;
+
+		/* How many devices are affected? */
+		ret = vfio_pci_for_each_slot_or_bus(vdev->pdev,
+						    vfio_pci_count_devs,
+						    &fill.max, slot);
+		if (ret)
+			return ret;
+
+		WARN_ON(!fill.max); /* Should always be at least one */
+
+		/*
+		 * If there's enough space, fill it now, otherwise return
+		 * -ENOSPC and the number of devices affected.
+		 */
+		if (hdr.argsz < sizeof(hdr) + (fill.max * sizeof(*devices))) {
+			ret = -ENOSPC;
+			hdr.count = fill.max;
+			goto reset_info_exit;
+		}
+
+		devices = kcalloc(fill.max, sizeof(*devices), GFP_KERNEL);
+		if (!devices)
+			return -ENOMEM;
+
+		fill.devices = devices;
+
+		ret = vfio_pci_for_each_slot_or_bus(vdev->pdev,
+						    vfio_pci_fill_devs,
+						    &fill, slot);
+
+		/*
+		 * If a device was removed between counting and filling,
+		 * we may come up short of fill.max.  If a device was
+		 * added, we'll have a return of -EAGAIN above.
+		 */
+		if (!ret)
+			hdr.count = fill.cur;
+
+reset_info_exit:
+		if (copy_to_user((void __user *)arg, &hdr, minsz))
+			ret = -EFAULT;
+
+		if (!ret) {
+			if (copy_to_user((void __user *)(arg + minsz), devices,
+					 hdr.count * sizeof(*devices)))
+				ret = -EFAULT;
+		}
+
+		kfree(devices);
+		return ret;
+
+	} else if (cmd == VFIO_DEVICE_PCI_HOT_RESET) {
+		struct vfio_pci_hot_reset hdr;
+		int32_t *group_fds;
+		struct vfio_pci_group_entry *groups;
+		struct vfio_pci_group_info info;
+		bool slot = false;
+		int i, count = 0, ret = 0;
+
+		minsz = offsetofend(struct vfio_pci_hot_reset, count);
+
+		if (copy_from_user(&hdr, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (hdr.argsz < minsz || hdr.flags)
+			return -EINVAL;
+
+		/* Can we do a slot or bus reset or neither? */
+		if (!pci_probe_reset_slot(vdev->pdev->slot))
+			slot = true;
+		else if (pci_probe_reset_bus(vdev->pdev->bus))
+			return -ENODEV;
+
+		/*
+		 * We can't let userspace give us an arbitrarily large
+		 * buffer to copy, so verify how many we think there
+		 * could be.  Note groups can have multiple devices so
+		 * one group per device is the max.
+		 */
+		ret = vfio_pci_for_each_slot_or_bus(vdev->pdev,
+						    vfio_pci_count_devs,
+						    &count, slot);
+		if (ret)
+			return ret;
+
+		/* Somewhere between 1 and count is OK */
+		if (!hdr.count || hdr.count > count)
+			return -EINVAL;
+
+		group_fds = kcalloc(hdr.count, sizeof(*group_fds), GFP_KERNEL);
+		groups = kcalloc(hdr.count, sizeof(*groups), GFP_KERNEL);
+		if (!group_fds || !groups) {
+			kfree(group_fds);
+			kfree(groups);
+			return -ENOMEM;
+		}
+
+		if (copy_from_user(group_fds, (void __user *)(arg + minsz),
+				   hdr.count * sizeof(*group_fds))) {
+			kfree(group_fds);
+			kfree(groups);
+			return -EFAULT;
+		}
+
+		/*
+		 * For each group_fd, get the group through the vfio external
+		 * user interface and store the group and iommu ID.  This
+		 * ensures the group is held across the reset.
+		 */
+		for (i = 0; i < hdr.count; i++) {
+			struct vfio_group *group;
+			struct fd f = fdget(group_fds[i]);
+			if (!f.file) {
+				ret = -EBADF;
+				break;
+			}
+
+			group = vfio_group_get_external_user(f.file);
+			fdput(f);
+			if (IS_ERR(group)) {
+				ret = PTR_ERR(group);
+				break;
+			}
+
+			groups[i].group = group;
+			groups[i].id = vfio_external_user_iommu_id(group);
+		}
+
+		kfree(group_fds);
+
+		/* release reference to groups on error */
+		if (ret)
+			goto hot_reset_release;
+
+		info.count = hdr.count;
+		info.groups = groups;
+
+		/*
+		 * Test whether all the affected devices are contained
+		 * by the set of groups provided by the user.
+		 */
+		ret = vfio_pci_for_each_slot_or_bus(vdev->pdev,
+						    vfio_pci_validate_devs,
+						    &info, slot);
+		if (!ret)
+			/* User has access, do the reset */
+			ret = slot ? pci_try_reset_slot(vdev->pdev->slot) :
+				     pci_try_reset_bus(vdev->pdev->bus);
+
+hot_reset_release:
+		for (i--; i >= 0; i--)
+			vfio_group_put_external_user(groups[i].group);
+
+		kfree(groups);
+		return ret;
+	}
+
+	return -ENOTTY;
+}
+
+static ssize_t vfio_pci_rw(void *device_data, char __user *buf,
+			   size_t count, loff_t *ppos, bool iswrite)
+{
+	unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos);
+	struct vfio_pci_device *vdev = device_data;
+
+	if (index >= VFIO_PCI_NUM_REGIONS)
+		return -EINVAL;
+
+	switch (index) {
+	case VFIO_PCI_CONFIG_REGION_INDEX:
+		return vfio_pci_config_rw(vdev, buf, count, ppos, iswrite);
+
+	case VFIO_PCI_ROM_REGION_INDEX:
+		if (iswrite)
+			return -EINVAL;
+		return vfio_pci_bar_rw(vdev, buf, count, ppos, false);
+
+	case VFIO_PCI_BAR0_REGION_INDEX ... VFIO_PCI_BAR5_REGION_INDEX:
+		return vfio_pci_bar_rw(vdev, buf, count, ppos, iswrite);
+
+	case VFIO_PCI_VGA_REGION_INDEX:
+		return vfio_pci_vga_rw(vdev, buf, count, ppos, iswrite);
+	}
+
+	return -EINVAL;
+}
+
+static ssize_t vfio_pci_read(void *device_data, char __user *buf,
+			     size_t count, loff_t *ppos)
+{
+	if (!count)
+		return 0;
+
+	return vfio_pci_rw(device_data, buf, count, ppos, false);
+}
+
+static ssize_t vfio_pci_write(void *device_data, const char __user *buf,
+			      size_t count, loff_t *ppos)
+{
+	if (!count)
+		return 0;
+
+	return vfio_pci_rw(device_data, (char __user *)buf, count, ppos, true);
+}
+
+static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma)
+{
+	struct vfio_pci_device *vdev = device_data;
+	struct pci_dev *pdev = vdev->pdev;
+	unsigned int index;
+	u64 phys_len, req_len, pgoff, req_start;
+	int ret;
+
+	index = vma->vm_pgoff >> (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT);
+
+	if (vma->vm_end < vma->vm_start)
+		return -EINVAL;
+	if ((vma->vm_flags & VM_SHARED) == 0)
+		return -EINVAL;
+	if (index >= VFIO_PCI_ROM_REGION_INDEX)
+		return -EINVAL;
+	if (!(pci_resource_flags(pdev, index) & IORESOURCE_MEM))
+		return -EINVAL;
+
+	phys_len = pci_resource_len(pdev, index);
+	req_len = vma->vm_end - vma->vm_start;
+	pgoff = vma->vm_pgoff &
+		((1U << (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT)) - 1);
+	req_start = pgoff << PAGE_SHIFT;
+
+	if (phys_len < PAGE_SIZE || req_start + req_len > phys_len)
+		return -EINVAL;
+
+	if (index == vdev->msix_bar) {
+		/*
+		 * Disallow mmaps overlapping the MSI-X table; users don't
+		 * get to touch this directly.  We could find somewhere
+		 * else to map the overlap, but page granularity is only
+		 * a recommendation, not a requirement, so the user needs
+		 * to know which bits are real.  Requiring them to mmap
+		 * around the table makes that clear.
+		 */
+
+		/* If neither entirely above nor below, then it overlaps */
+		if (!(req_start >= vdev->msix_offset + vdev->msix_size ||
+		      req_start + req_len <= vdev->msix_offset))
+			return -EINVAL;
+	}
+
+	/*
+	 * Even though we don't make use of the barmap for the mmap,
+	 * we need to request the region and the barmap tracks that.
+	 */
+	if (!vdev->barmap[index]) {
+		ret = pci_request_selected_regions(pdev,
+						   1 << index, "vfio-pci");
+		if (ret)
+			return ret;
+
+		vdev->barmap[index] = pci_iomap(pdev, index, 0);
+	}
+
+	vma->vm_private_data = vdev;
+	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+	vma->vm_pgoff = (pci_resource_start(pdev, index) >> PAGE_SHIFT) + pgoff;
+
+	return remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
+			       req_len, vma->vm_page_prot);
+}
+
+static void vfio_pci_request(void *device_data, unsigned int count)
+{
+	struct vfio_pci_device *vdev = device_data;
+
+	mutex_lock(&vdev->igate);
+
+	if (vdev->req_trigger) {
+		if (!(count % 10))
+			dev_notice_ratelimited(&vdev->pdev->dev,
+				"Relaying device request to user (#%u)\n",
+				count);
+		eventfd_signal(vdev->req_trigger, 1);
+	} else if (count == 0) {
+		dev_warn(&vdev->pdev->dev,
+			"No device request channel registered, blocked until released by user\n");
+	}
+
+	mutex_unlock(&vdev->igate);
+}
+
+static const struct vfio_device_ops vfio_pci_ops = {
+	.name		= "vfio-pci",
+	.open		= vfio_pci_open,
+	.release	= vfio_pci_release,
+	.ioctl		= vfio_pci_ioctl,
+	.read		= vfio_pci_read,
+	.write		= vfio_pci_write,
+	.mmap		= vfio_pci_mmap,
+	.request	= vfio_pci_request,
+};
+
+static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct vfio_pci_device *vdev;
+	struct iommu_group *group;
+	int ret;
+
+	if (pdev->hdr_type != PCI_HEADER_TYPE_NORMAL)
+		return -EINVAL;
+
+	group = iommu_group_get(&pdev->dev);
+	if (!group)
+		return -EINVAL;
+
+	vdev = kzalloc(sizeof(*vdev), GFP_KERNEL);
+	if (!vdev) {
+		iommu_group_put(group);
+		return -ENOMEM;
+	}
+
+	vdev->pdev = pdev;
+	vdev->irq_type = VFIO_PCI_NUM_IRQS;
+	mutex_init(&vdev->igate);
+	spin_lock_init(&vdev->irqlock);
+
+	ret = vfio_add_group_dev(&pdev->dev, &vfio_pci_ops, vdev);
+	if (ret) {
+		iommu_group_put(group);
+		kfree(vdev);
+		return ret;
+	}
+
+	if (vfio_pci_is_vga(pdev)) {
+		vga_client_register(pdev, vdev, NULL, vfio_pci_set_vga_decode);
+		vga_set_legacy_decoding(pdev,
+					vfio_pci_set_vga_decode(vdev, false));
+	}
+
+	if (!disable_idle_d3) {
+		/*
+		 * pci-core sets the device power state to an unknown value at
+		 * bootup and after being removed from a driver.  The only
+		 * transition it allows from this unknown state is to D0, which
+		 * typically happens when a driver calls pci_enable_device().
+		 * We're not ready to enable the device yet, but we do want to
+		 * be able to get to D3.  Therefore first do a D0 transition
+		 * before going to D3.
+		 */
+		pci_set_power_state(pdev, PCI_D0);
+		pci_set_power_state(pdev, PCI_D3hot);
+	}
+
+	return ret;
+}
+
+static void vfio_pci_remove(struct pci_dev *pdev)
+{
+	struct vfio_pci_device *vdev;
+
+	vdev = vfio_del_group_dev(&pdev->dev);
+	if (!vdev)
+		return;
+
+	iommu_group_put(pdev->dev.iommu_group);
+	kfree(vdev);
+
+	if (vfio_pci_is_vga(pdev)) {
+		vga_client_register(pdev, NULL, NULL, NULL);
+		vga_set_legacy_decoding(pdev,
+				VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM |
+				VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM);
+	}
+
+	if (!disable_idle_d3)
+		pci_set_power_state(pdev, PCI_D0);
+}
+
+static pci_ers_result_t vfio_pci_aer_err_detected(struct pci_dev *pdev,
+						  pci_channel_state_t state)
+{
+	struct vfio_pci_device *vdev;
+	struct vfio_device *device;
+
+	device = vfio_device_get_from_dev(&pdev->dev);
+	if (device == NULL)
+		return PCI_ERS_RESULT_DISCONNECT;
+
+	vdev = vfio_device_data(device);
+	if (vdev == NULL) {
+		vfio_device_put(device);
+		return PCI_ERS_RESULT_DISCONNECT;
+	}
+
+	mutex_lock(&vdev->igate);
+
+	if (vdev->err_trigger)
+		eventfd_signal(vdev->err_trigger, 1);
+
+	mutex_unlock(&vdev->igate);
+
+	vfio_device_put(device);
+
+	return PCI_ERS_RESULT_CAN_RECOVER;
+}
+
+static struct pci_error_handlers vfio_err_handlers = {
+	.error_detected = vfio_pci_aer_err_detected,
+};
+
+static struct pci_driver vfio_pci_driver = {
+	.name		= "vfio-pci",
+	.id_table	= NULL, /* only dynamic ids */
+	.probe		= vfio_pci_probe,
+	.remove		= vfio_pci_remove,
+	.err_handler	= &vfio_err_handlers,
+};
+
+struct vfio_devices {
+	struct vfio_device **devices;
+	int cur_index;
+	int max_index;
+};
+
+static int vfio_pci_get_devs(struct pci_dev *pdev, void *data)
+{
+	struct vfio_devices *devs = data;
+	struct pci_driver *pci_drv = ACCESS_ONCE(pdev->driver);
+
+	if (pci_drv != &vfio_pci_driver)
+		return -EBUSY;
+
+	if (devs->cur_index == devs->max_index)
+		return -ENOSPC;
+
+	devs->devices[devs->cur_index] = vfio_device_get_from_dev(&pdev->dev);
+	if (!devs->devices[devs->cur_index])
+		return -EINVAL;
+
+	devs->cur_index++;
+	return 0;
+}
+
+/*
+ * Attempt to do a bus/slot reset if there are devices affected by a reset for
+ * this device that are needs_reset and all of the affected devices are unused
+ * (!refcnt).  Callers are required to hold driver_lock when calling this to
+ * prevent device opens and concurrent bus reset attempts.  We prevent device
+ * unbinds by acquiring and holding a reference to the vfio_device.
+ *
+ * NB: vfio-core considers a group to be viable even if some devices are
+ * bound to drivers like pci-stub or pcieport.  Here we require all devices
+ * to be bound to vfio_pci since that's the only way we can be sure they
+ * stay put.
+ */
+static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev)
+{
+	struct vfio_devices devs = { .cur_index = 0 };
+	int i = 0, ret = -EINVAL;
+	bool needs_reset = false, slot = false;
+	struct vfio_pci_device *tmp;
+
+	if (!pci_probe_reset_slot(vdev->pdev->slot))
+		slot = true;
+	else if (pci_probe_reset_bus(vdev->pdev->bus))
+		return;
+
+	if (vfio_pci_for_each_slot_or_bus(vdev->pdev, vfio_pci_count_devs,
+					  &i, slot) || !i)
+		return;
+
+	devs.max_index = i;
+	devs.devices = kcalloc(i, sizeof(struct vfio_device *), GFP_KERNEL);
+	if (!devs.devices)
+		return;
+
+	if (vfio_pci_for_each_slot_or_bus(vdev->pdev,
+					  vfio_pci_get_devs, &devs, slot))
+		goto put_devs;
+
+	for (i = 0; i < devs.cur_index; i++) {
+		tmp = vfio_device_data(devs.devices[i]);
+		if (tmp->needs_reset)
+			needs_reset = true;
+		if (tmp->refcnt)
+			goto put_devs;
+	}
+
+	if (needs_reset)
+		ret = slot ? pci_try_reset_slot(vdev->pdev->slot) :
+			     pci_try_reset_bus(vdev->pdev->bus);
+
+put_devs:
+	for (i = 0; i < devs.cur_index; i++) {
+		tmp = vfio_device_data(devs.devices[i]);
+		if (!ret)
+			tmp->needs_reset = false;
+
+		if (!tmp->refcnt && !disable_idle_d3)
+			pci_set_power_state(tmp->pdev, PCI_D3hot);
+
+		vfio_device_put(devs.devices[i]);
+	}
+
+	kfree(devs.devices);
+}
+
+static void __exit vfio_pci_cleanup(void)
+{
+	pci_unregister_driver(&vfio_pci_driver);
+	vfio_pci_uninit_perm_bits();
+}
+
+static void __init vfio_pci_fill_ids(void)
+{
+	char *p, *id;
+	int rc;
+
+	/* no ids passed actually */
+	if (ids[0] == '\0')
+		return;
+
+	/* add ids specified in the module parameter */
+	p = ids;
+	while ((id = strsep(&p, ","))) {
+		unsigned int vendor, device, subvendor = PCI_ANY_ID,
+			subdevice = PCI_ANY_ID, class = 0, class_mask = 0;
+		int fields;
+
+		if (!strlen(id))
+			continue;
+
+		fields = sscanf(id, "%x:%x:%x:%x:%x:%x",
+				&vendor, &device, &subvendor, &subdevice,
+				&class, &class_mask);
+
+		if (fields < 2) {
+			pr_warn("invalid id string \"%s\"\n", id);
+			continue;
+		}
+
+		rc = pci_add_dynid(&vfio_pci_driver, vendor, device,
+				   subvendor, subdevice, class, class_mask, 0);
+		if (rc)
+			pr_warn("failed to add dynamic id [%04hx:%04hx[%04hx:%04hx]] class %#08x/%08x (%d)\n",
+				vendor, device, subvendor, subdevice,
+				class, class_mask, rc);
+		else
+			pr_info("add [%04hx:%04hx[%04hx:%04hx]] class %#08x/%08x\n",
+				vendor, device, subvendor, subdevice,
+				class, class_mask);
+	}
+}
+
+static int __init vfio_pci_init(void)
+{
+	int ret;
+
+	/* Allocate shared config space permision data used by all devices */
+	ret = vfio_pci_init_perm_bits();
+	if (ret)
+		return ret;
+
+	/* Register and scan for devices */
+	ret = pci_register_driver(&vfio_pci_driver);
+	if (ret)
+		goto out_driver;
+
+	vfio_pci_fill_ids();
+
+	return 0;
+
+out_driver:
+	vfio_pci_uninit_perm_bits();
+	return ret;
+}
+
+module_init(vfio_pci_init);
+module_exit(vfio_pci_cleanup);
+
+MODULE_VERSION(DRIVER_VERSION);
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c
new file mode 100644
index 000000000..ff75ca31a
--- /dev/null
+++ b/drivers/vfio/pci/vfio_pci_config.c
@@ -0,0 +1,1602 @@
+/*
+ * VFIO PCI config space virtualization
+ *
+ * Copyright (C) 2012 Red Hat, Inc.  All rights reserved.
+ *     Author: Alex Williamson <alex.williamson@redhat.com>
+ *
+ * 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.
+ *
+ * Derived from original vfio:
+ * Copyright 2010 Cisco Systems, Inc.  All rights reserved.
+ * Author: Tom Lyon, pugs@cisco.com
+ */
+
+/*
+ * This code handles reading and writing of PCI configuration registers.
+ * This is hairy because we want to allow a lot of flexibility to the
+ * user driver, but cannot trust it with all of the config fields.
+ * Tables determine which fields can be read and written, as well as
+ * which fields are 'virtualized' - special actions and translations to
+ * make it appear to the user that he has control, when in fact things
+ * must be negotiated with the underlying OS.
+ */
+
+#include <linux/fs.h>
+#include <linux/pci.h>
+#include <linux/uaccess.h>
+#include <linux/vfio.h>
+#include <linux/slab.h>
+
+#include "vfio_pci_private.h"
+
+#define PCI_CFG_SPACE_SIZE	256
+
+/* Useful "pseudo" capabilities */
+#define PCI_CAP_ID_BASIC	0
+#define PCI_CAP_ID_INVALID	0xFF
+
+#define is_bar(offset)	\
+	((offset >= PCI_BASE_ADDRESS_0 && offset < PCI_BASE_ADDRESS_5 + 4) || \
+	 (offset >= PCI_ROM_ADDRESS && offset < PCI_ROM_ADDRESS + 4))
+
+/*
+ * Lengths of PCI Config Capabilities
+ *   0: Removed from the user visible capability list
+ *   FF: Variable length
+ */
+static u8 pci_cap_length[] = {
+	[PCI_CAP_ID_BASIC]	= PCI_STD_HEADER_SIZEOF, /* pci config header */
+	[PCI_CAP_ID_PM]		= PCI_PM_SIZEOF,
+	[PCI_CAP_ID_AGP]	= PCI_AGP_SIZEOF,
+	[PCI_CAP_ID_VPD]	= PCI_CAP_VPD_SIZEOF,
+	[PCI_CAP_ID_SLOTID]	= 0,		/* bridge - don't care */
+	[PCI_CAP_ID_MSI]	= 0xFF,		/* 10, 14, 20, or 24 */
+	[PCI_CAP_ID_CHSWP]	= 0,		/* cpci - not yet */
+	[PCI_CAP_ID_PCIX]	= 0xFF,		/* 8 or 24 */
+	[PCI_CAP_ID_HT]		= 0xFF,		/* hypertransport */
+	[PCI_CAP_ID_VNDR]	= 0xFF,		/* variable */
+	[PCI_CAP_ID_DBG]	= 0,		/* debug - don't care */
+	[PCI_CAP_ID_CCRC]	= 0,		/* cpci - not yet */
+	[PCI_CAP_ID_SHPC]	= 0,		/* hotswap - not yet */
+	[PCI_CAP_ID_SSVID]	= 0,		/* bridge - don't care */
+	[PCI_CAP_ID_AGP3]	= 0,		/* AGP8x - not yet */
+	[PCI_CAP_ID_SECDEV]	= 0,		/* secure device not yet */
+	[PCI_CAP_ID_EXP]	= 0xFF,		/* 20 or 44 */
+	[PCI_CAP_ID_MSIX]	= PCI_CAP_MSIX_SIZEOF,
+	[PCI_CAP_ID_SATA]	= 0xFF,
+	[PCI_CAP_ID_AF]		= PCI_CAP_AF_SIZEOF,
+};
+
+/*
+ * Lengths of PCIe/PCI-X Extended Config Capabilities
+ *   0: Removed or masked from the user visible capabilty list
+ *   FF: Variable length
+ */
+static u16 pci_ext_cap_length[] = {
+	[PCI_EXT_CAP_ID_ERR]	=	PCI_ERR_ROOT_COMMAND,
+	[PCI_EXT_CAP_ID_VC]	=	0xFF,
+	[PCI_EXT_CAP_ID_DSN]	=	PCI_EXT_CAP_DSN_SIZEOF,
+	[PCI_EXT_CAP_ID_PWR]	=	PCI_EXT_CAP_PWR_SIZEOF,
+	[PCI_EXT_CAP_ID_RCLD]	=	0,	/* root only - don't care */
+	[PCI_EXT_CAP_ID_RCILC]	=	0,	/* root only - don't care */
+	[PCI_EXT_CAP_ID_RCEC]	=	0,	/* root only - don't care */
+	[PCI_EXT_CAP_ID_MFVC]	=	0xFF,
+	[PCI_EXT_CAP_ID_VC9]	=	0xFF,	/* same as CAP_ID_VC */
+	[PCI_EXT_CAP_ID_RCRB]	=	0,	/* root only - don't care */
+	[PCI_EXT_CAP_ID_VNDR]	=	0xFF,
+	[PCI_EXT_CAP_ID_CAC]	=	0,	/* obsolete */
+	[PCI_EXT_CAP_ID_ACS]	=	0xFF,
+	[PCI_EXT_CAP_ID_ARI]	=	PCI_EXT_CAP_ARI_SIZEOF,
+	[PCI_EXT_CAP_ID_ATS]	=	PCI_EXT_CAP_ATS_SIZEOF,
+	[PCI_EXT_CAP_ID_SRIOV]	=	PCI_EXT_CAP_SRIOV_SIZEOF,
+	[PCI_EXT_CAP_ID_MRIOV]	=	0,	/* not yet */
+	[PCI_EXT_CAP_ID_MCAST]	=	PCI_EXT_CAP_MCAST_ENDPOINT_SIZEOF,
+	[PCI_EXT_CAP_ID_PRI]	=	PCI_EXT_CAP_PRI_SIZEOF,
+	[PCI_EXT_CAP_ID_AMD_XXX] =	0,	/* not yet */
+	[PCI_EXT_CAP_ID_REBAR]	=	0xFF,
+	[PCI_EXT_CAP_ID_DPA]	=	0xFF,
+	[PCI_EXT_CAP_ID_TPH]	=	0xFF,
+	[PCI_EXT_CAP_ID_LTR]	=	PCI_EXT_CAP_LTR_SIZEOF,
+	[PCI_EXT_CAP_ID_SECPCI]	=	0,	/* not yet */
+	[PCI_EXT_CAP_ID_PMUX]	=	0,	/* not yet */
+	[PCI_EXT_CAP_ID_PASID]	=	0,	/* not yet */
+};
+
+/*
+ * Read/Write Permission Bits - one bit for each bit in capability
+ * Any field can be read if it exists, but what is read depends on
+ * whether the field is 'virtualized', or just pass thru to the
+ * hardware.  Any virtualized field is also virtualized for writes.
+ * Writes are only permitted if they have a 1 bit here.
+ */
+struct perm_bits {
+	u8	*virt;		/* read/write virtual data, not hw */
+	u8	*write;		/* writeable bits */
+	int	(*readfn)(struct vfio_pci_device *vdev, int pos, int count,
+			  struct perm_bits *perm, int offset, __le32 *val);
+	int	(*writefn)(struct vfio_pci_device *vdev, int pos, int count,
+			   struct perm_bits *perm, int offset, __le32 val);
+};
+
+#define	NO_VIRT		0
+#define	ALL_VIRT	0xFFFFFFFFU
+#define	NO_WRITE	0
+#define	ALL_WRITE	0xFFFFFFFFU
+
+static int vfio_user_config_read(struct pci_dev *pdev, int offset,
+				 __le32 *val, int count)
+{
+	int ret = -EINVAL;
+	u32 tmp_val = 0;
+
+	switch (count) {
+	case 1:
+	{
+		u8 tmp;
+		ret = pci_user_read_config_byte(pdev, offset, &tmp);
+		tmp_val = tmp;
+		break;
+	}
+	case 2:
+	{
+		u16 tmp;
+		ret = pci_user_read_config_word(pdev, offset, &tmp);
+		tmp_val = tmp;
+		break;
+	}
+	case 4:
+		ret = pci_user_read_config_dword(pdev, offset, &tmp_val);
+		break;
+	}
+
+	*val = cpu_to_le32(tmp_val);
+
+	return pcibios_err_to_errno(ret);
+}
+
+static int vfio_user_config_write(struct pci_dev *pdev, int offset,
+				  __le32 val, int count)
+{
+	int ret = -EINVAL;
+	u32 tmp_val = le32_to_cpu(val);
+
+	switch (count) {
+	case 1:
+		ret = pci_user_write_config_byte(pdev, offset, tmp_val);
+		break;
+	case 2:
+		ret = pci_user_write_config_word(pdev, offset, tmp_val);
+		break;
+	case 4:
+		ret = pci_user_write_config_dword(pdev, offset, tmp_val);
+		break;
+	}
+
+	return pcibios_err_to_errno(ret);
+}
+
+static int vfio_default_config_read(struct vfio_pci_device *vdev, int pos,
+				    int count, struct perm_bits *perm,
+				    int offset, __le32 *val)
+{
+	__le32 virt = 0;
+
+	memcpy(val, vdev->vconfig + pos, count);
+
+	memcpy(&virt, perm->virt + offset, count);
+
+	/* Any non-virtualized bits? */
+	if (cpu_to_le32(~0U >> (32 - (count * 8))) != virt) {
+		struct pci_dev *pdev = vdev->pdev;
+		__le32 phys_val = 0;
+		int ret;
+
+		ret = vfio_user_config_read(pdev, pos, &phys_val, count);
+		if (ret)
+			return ret;
+
+		*val = (phys_val & ~virt) | (*val & virt);
+	}
+
+	return count;
+}
+
+static int vfio_default_config_write(struct vfio_pci_device *vdev, int pos,
+				     int count, struct perm_bits *perm,
+				     int offset, __le32 val)
+{
+	__le32 virt = 0, write = 0;
+
+	memcpy(&write, perm->write + offset, count);
+
+	if (!write)
+		return count; /* drop, no writable bits */
+
+	memcpy(&virt, perm->virt + offset, count);
+
+	/* Virtualized and writable bits go to vconfig */
+	if (write & virt) {
+		__le32 virt_val = 0;
+
+		memcpy(&virt_val, vdev->vconfig + pos, count);
+
+		virt_val &= ~(write & virt);
+		virt_val |= (val & (write & virt));
+
+		memcpy(vdev->vconfig + pos, &virt_val, count);
+	}
+
+	/* Non-virtualzed and writable bits go to hardware */
+	if (write & ~virt) {
+		struct pci_dev *pdev = vdev->pdev;
+		__le32 phys_val = 0;
+		int ret;
+
+		ret = vfio_user_config_read(pdev, pos, &phys_val, count);
+		if (ret)
+			return ret;
+
+		phys_val &= ~(write & ~virt);
+		phys_val |= (val & (write & ~virt));
+
+		ret = vfio_user_config_write(pdev, pos, phys_val, count);
+		if (ret)
+			return ret;
+	}
+
+	return count;
+}
+
+/* Allow direct read from hardware, except for capability next pointer */
+static int vfio_direct_config_read(struct vfio_pci_device *vdev, int pos,
+				   int count, struct perm_bits *perm,
+				   int offset, __le32 *val)
+{
+	int ret;
+
+	ret = vfio_user_config_read(vdev->pdev, pos, val, count);
+	if (ret)
+		return pcibios_err_to_errno(ret);
+
+	if (pos >= PCI_CFG_SPACE_SIZE) { /* Extended cap header mangling */
+		if (offset < 4)
+			memcpy(val, vdev->vconfig + pos, count);
+	} else if (pos >= PCI_STD_HEADER_SIZEOF) { /* Std cap mangling */
+		if (offset == PCI_CAP_LIST_ID && count > 1)
+			memcpy(val, vdev->vconfig + pos,
+			       min(PCI_CAP_FLAGS, count));
+		else if (offset == PCI_CAP_LIST_NEXT)
+			memcpy(val, vdev->vconfig + pos, 1);
+	}
+
+	return count;
+}
+
+/* Raw access skips any kind of virtualization */
+static int vfio_raw_config_write(struct vfio_pci_device *vdev, int pos,
+				 int count, struct perm_bits *perm,
+				 int offset, __le32 val)
+{
+	int ret;
+
+	ret = vfio_user_config_write(vdev->pdev, pos, val, count);
+	if (ret)
+		return ret;
+
+	return count;
+}
+
+static int vfio_raw_config_read(struct vfio_pci_device *vdev, int pos,
+				int count, struct perm_bits *perm,
+				int offset, __le32 *val)
+{
+	int ret;
+
+	ret = vfio_user_config_read(vdev->pdev, pos, val, count);
+	if (ret)
+		return pcibios_err_to_errno(ret);
+
+	return count;
+}
+
+/* Default capability regions to read-only, no-virtualization */
+static struct perm_bits cap_perms[PCI_CAP_ID_MAX + 1] = {
+	[0 ... PCI_CAP_ID_MAX] = { .readfn = vfio_direct_config_read }
+};
+static struct perm_bits ecap_perms[PCI_EXT_CAP_ID_MAX + 1] = {
+	[0 ... PCI_EXT_CAP_ID_MAX] = { .readfn = vfio_direct_config_read }
+};
+/*
+ * Default unassigned regions to raw read-write access.  Some devices
+ * require this to function as they hide registers between the gaps in
+ * config space (be2net).  Like MMIO and I/O port registers, we have
+ * to trust the hardware isolation.
+ */
+static struct perm_bits unassigned_perms = {
+	.readfn = vfio_raw_config_read,
+	.writefn = vfio_raw_config_write
+};
+
+static void free_perm_bits(struct perm_bits *perm)
+{
+	kfree(perm->virt);
+	kfree(perm->write);
+	perm->virt = NULL;
+	perm->write = NULL;
+}
+
+static int alloc_perm_bits(struct perm_bits *perm, int size)
+{
+	/*
+	 * Round up all permission bits to the next dword, this lets us
+	 * ignore whether a read/write exceeds the defined capability
+	 * structure.  We can do this because:
+	 *  - Standard config space is already dword aligned
+	 *  - Capabilities are all dword alinged (bits 0:1 of next reserved)
+	 *  - Express capabilities defined as dword aligned
+	 */
+	size = round_up(size, 4);
+
+	/*
+	 * Zero state is
+	 * - All Readable, None Writeable, None Virtualized
+	 */
+	perm->virt = kzalloc(size, GFP_KERNEL);
+	perm->write = kzalloc(size, GFP_KERNEL);
+	if (!perm->virt || !perm->write) {
+		free_perm_bits(perm);
+		return -ENOMEM;
+	}
+
+	perm->readfn = vfio_default_config_read;
+	perm->writefn = vfio_default_config_write;
+
+	return 0;
+}
+
+/*
+ * Helper functions for filling in permission tables
+ */
+static inline void p_setb(struct perm_bits *p, int off, u8 virt, u8 write)
+{
+	p->virt[off] = virt;
+	p->write[off] = write;
+}
+
+/* Handle endian-ness - pci and tables are little-endian */
+static inline void p_setw(struct perm_bits *p, int off, u16 virt, u16 write)
+{
+	*(__le16 *)(&p->virt[off]) = cpu_to_le16(virt);
+	*(__le16 *)(&p->write[off]) = cpu_to_le16(write);
+}
+
+/* Handle endian-ness - pci and tables are little-endian */
+static inline void p_setd(struct perm_bits *p, int off, u32 virt, u32 write)
+{
+	*(__le32 *)(&p->virt[off]) = cpu_to_le32(virt);
+	*(__le32 *)(&p->write[off]) = cpu_to_le32(write);
+}
+
+/*
+ * Restore the *real* BARs after we detect a FLR or backdoor reset.
+ * (backdoor = some device specific technique that we didn't catch)
+ */
+static void vfio_bar_restore(struct vfio_pci_device *vdev)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	u32 *rbar = vdev->rbar;
+	int i;
+
+	if (pdev->is_virtfn)
+		return;
+
+	pr_info("%s: %s reset recovery - restoring bars\n",
+		__func__, dev_name(&pdev->dev));
+
+	for (i = PCI_BASE_ADDRESS_0; i <= PCI_BASE_ADDRESS_5; i += 4, rbar++)
+		pci_user_write_config_dword(pdev, i, *rbar);
+
+	pci_user_write_config_dword(pdev, PCI_ROM_ADDRESS, *rbar);
+}
+
+static __le32 vfio_generate_bar_flags(struct pci_dev *pdev, int bar)
+{
+	unsigned long flags = pci_resource_flags(pdev, bar);
+	u32 val;
+
+	if (flags & IORESOURCE_IO)
+		return cpu_to_le32(PCI_BASE_ADDRESS_SPACE_IO);
+
+	val = PCI_BASE_ADDRESS_SPACE_MEMORY;
+
+	if (flags & IORESOURCE_PREFETCH)
+		val |= PCI_BASE_ADDRESS_MEM_PREFETCH;
+
+	if (flags & IORESOURCE_MEM_64)
+		val |= PCI_BASE_ADDRESS_MEM_TYPE_64;
+
+	return cpu_to_le32(val);
+}
+
+/*
+ * Pretend we're hardware and tweak the values of the *virtual* PCI BARs
+ * to reflect the hardware capabilities.  This implements BAR sizing.
+ */
+static void vfio_bar_fixup(struct vfio_pci_device *vdev)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	int i;
+	__le32 *bar;
+	u64 mask;
+
+	bar = (__le32 *)&vdev->vconfig[PCI_BASE_ADDRESS_0];
+
+	for (i = PCI_STD_RESOURCES; i <= PCI_STD_RESOURCE_END; i++, bar++) {
+		if (!pci_resource_start(pdev, i)) {
+			*bar = 0; /* Unmapped by host = unimplemented to user */
+			continue;
+		}
+
+		mask = ~(pci_resource_len(pdev, i) - 1);
+
+		*bar &= cpu_to_le32((u32)mask);
+		*bar |= vfio_generate_bar_flags(pdev, i);
+
+		if (*bar & cpu_to_le32(PCI_BASE_ADDRESS_MEM_TYPE_64)) {
+			bar++;
+			*bar &= cpu_to_le32((u32)(mask >> 32));
+			i++;
+		}
+	}
+
+	bar = (__le32 *)&vdev->vconfig[PCI_ROM_ADDRESS];
+
+	/*
+	 * NB. we expose the actual BAR size here, regardless of whether
+	 * we can read it.  When we report the REGION_INFO for the ROM
+	 * we report what PCI tells us is the actual ROM size.
+	 */
+	if (pci_resource_start(pdev, PCI_ROM_RESOURCE)) {
+		mask = ~(pci_resource_len(pdev, PCI_ROM_RESOURCE) - 1);
+		mask |= PCI_ROM_ADDRESS_ENABLE;
+		*bar &= cpu_to_le32((u32)mask);
+	} else
+		*bar = 0;
+
+	vdev->bardirty = false;
+}
+
+static int vfio_basic_config_read(struct vfio_pci_device *vdev, int pos,
+				  int count, struct perm_bits *perm,
+				  int offset, __le32 *val)
+{
+	if (is_bar(offset)) /* pos == offset for basic config */
+		vfio_bar_fixup(vdev);
+
+	count = vfio_default_config_read(vdev, pos, count, perm, offset, val);
+
+	/* Mask in virtual memory enable for SR-IOV devices */
+	if (offset == PCI_COMMAND && vdev->pdev->is_virtfn) {
+		u16 cmd = le16_to_cpu(*(__le16 *)&vdev->vconfig[PCI_COMMAND]);
+		u32 tmp_val = le32_to_cpu(*val);
+
+		tmp_val |= cmd & PCI_COMMAND_MEMORY;
+		*val = cpu_to_le32(tmp_val);
+	}
+
+	return count;
+}
+
+static int vfio_basic_config_write(struct vfio_pci_device *vdev, int pos,
+				   int count, struct perm_bits *perm,
+				   int offset, __le32 val)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	__le16 *virt_cmd;
+	u16 new_cmd = 0;
+	int ret;
+
+	virt_cmd = (__le16 *)&vdev->vconfig[PCI_COMMAND];
+
+	if (offset == PCI_COMMAND) {
+		bool phys_mem, virt_mem, new_mem, phys_io, virt_io, new_io;
+		u16 phys_cmd;
+
+		ret = pci_user_read_config_word(pdev, PCI_COMMAND, &phys_cmd);
+		if (ret)
+			return ret;
+
+		new_cmd = le32_to_cpu(val);
+
+		phys_mem = !!(phys_cmd & PCI_COMMAND_MEMORY);
+		virt_mem = !!(le16_to_cpu(*virt_cmd) & PCI_COMMAND_MEMORY);
+		new_mem = !!(new_cmd & PCI_COMMAND_MEMORY);
+
+		phys_io = !!(phys_cmd & PCI_COMMAND_IO);
+		virt_io = !!(le16_to_cpu(*virt_cmd) & PCI_COMMAND_IO);
+		new_io = !!(new_cmd & PCI_COMMAND_IO);
+
+		/*
+		 * If the user is writing mem/io enable (new_mem/io) and we
+		 * think it's already enabled (virt_mem/io), but the hardware
+		 * shows it disabled (phys_mem/io, then the device has
+		 * undergone some kind of backdoor reset and needs to be
+		 * restored before we allow it to enable the bars.
+		 * SR-IOV devices will trigger this, but we catch them later
+		 */
+		if ((new_mem && virt_mem && !phys_mem) ||
+		    (new_io && virt_io && !phys_io))
+			vfio_bar_restore(vdev);
+	}
+
+	count = vfio_default_config_write(vdev, pos, count, perm, offset, val);
+	if (count < 0)
+		return count;
+
+	/*
+	 * Save current memory/io enable bits in vconfig to allow for
+	 * the test above next time.
+	 */
+	if (offset == PCI_COMMAND) {
+		u16 mask = PCI_COMMAND_MEMORY | PCI_COMMAND_IO;
+
+		*virt_cmd &= cpu_to_le16(~mask);
+		*virt_cmd |= cpu_to_le16(new_cmd & mask);
+	}
+
+	/* Emulate INTx disable */
+	if (offset >= PCI_COMMAND && offset <= PCI_COMMAND + 1) {
+		bool virt_intx_disable;
+
+		virt_intx_disable = !!(le16_to_cpu(*virt_cmd) &
+				       PCI_COMMAND_INTX_DISABLE);
+
+		if (virt_intx_disable && !vdev->virq_disabled) {
+			vdev->virq_disabled = true;
+			vfio_pci_intx_mask(vdev);
+		} else if (!virt_intx_disable && vdev->virq_disabled) {
+			vdev->virq_disabled = false;
+			vfio_pci_intx_unmask(vdev);
+		}
+	}
+
+	if (is_bar(offset))
+		vdev->bardirty = true;
+
+	return count;
+}
+
+/* Permissions for the Basic PCI Header */
+static int __init init_pci_cap_basic_perm(struct perm_bits *perm)
+{
+	if (alloc_perm_bits(perm, PCI_STD_HEADER_SIZEOF))
+		return -ENOMEM;
+
+	perm->readfn = vfio_basic_config_read;
+	perm->writefn = vfio_basic_config_write;
+
+	/* Virtualized for SR-IOV functions, which just have FFFF */
+	p_setw(perm, PCI_VENDOR_ID, (u16)ALL_VIRT, NO_WRITE);
+	p_setw(perm, PCI_DEVICE_ID, (u16)ALL_VIRT, NO_WRITE);
+
+	/*
+	 * Virtualize INTx disable, we use it internally for interrupt
+	 * control and can emulate it for non-PCI 2.3 devices.
+	 */
+	p_setw(perm, PCI_COMMAND, PCI_COMMAND_INTX_DISABLE, (u16)ALL_WRITE);
+
+	/* Virtualize capability list, we might want to skip/disable */
+	p_setw(perm, PCI_STATUS, PCI_STATUS_CAP_LIST, NO_WRITE);
+
+	/* No harm to write */
+	p_setb(perm, PCI_CACHE_LINE_SIZE, NO_VIRT, (u8)ALL_WRITE);
+	p_setb(perm, PCI_LATENCY_TIMER, NO_VIRT, (u8)ALL_WRITE);
+	p_setb(perm, PCI_BIST, NO_VIRT, (u8)ALL_WRITE);
+
+	/* Virtualize all bars, can't touch the real ones */
+	p_setd(perm, PCI_BASE_ADDRESS_0, ALL_VIRT, ALL_WRITE);
+	p_setd(perm, PCI_BASE_ADDRESS_1, ALL_VIRT, ALL_WRITE);
+	p_setd(perm, PCI_BASE_ADDRESS_2, ALL_VIRT, ALL_WRITE);
+	p_setd(perm, PCI_BASE_ADDRESS_3, ALL_VIRT, ALL_WRITE);
+	p_setd(perm, PCI_BASE_ADDRESS_4, ALL_VIRT, ALL_WRITE);
+	p_setd(perm, PCI_BASE_ADDRESS_5, ALL_VIRT, ALL_WRITE);
+	p_setd(perm, PCI_ROM_ADDRESS, ALL_VIRT, ALL_WRITE);
+
+	/* Allow us to adjust capability chain */
+	p_setb(perm, PCI_CAPABILITY_LIST, (u8)ALL_VIRT, NO_WRITE);
+
+	/* Sometimes used by sw, just virtualize */
+	p_setb(perm, PCI_INTERRUPT_LINE, (u8)ALL_VIRT, (u8)ALL_WRITE);
+
+	/* Virtualize interrupt pin to allow hiding INTx */
+	p_setb(perm, PCI_INTERRUPT_PIN, (u8)ALL_VIRT, (u8)NO_WRITE);
+
+	return 0;
+}
+
+static int vfio_pm_config_write(struct vfio_pci_device *vdev, int pos,
+				int count, struct perm_bits *perm,
+				int offset, __le32 val)
+{
+	count = vfio_default_config_write(vdev, pos, count, perm, offset, val);
+	if (count < 0)
+		return count;
+
+	if (offset == PCI_PM_CTRL) {
+		pci_power_t state;
+
+		switch (le32_to_cpu(val) & PCI_PM_CTRL_STATE_MASK) {
+		case 0:
+			state = PCI_D0;
+			break;
+		case 1:
+			state = PCI_D1;
+			break;
+		case 2:
+			state = PCI_D2;
+			break;
+		case 3:
+			state = PCI_D3hot;
+			break;
+		}
+
+		pci_set_power_state(vdev->pdev, state);
+	}
+
+	return count;
+}
+
+/* Permissions for the Power Management capability */
+static int __init init_pci_cap_pm_perm(struct perm_bits *perm)
+{
+	if (alloc_perm_bits(perm, pci_cap_length[PCI_CAP_ID_PM]))
+		return -ENOMEM;
+
+	perm->writefn = vfio_pm_config_write;
+
+	/*
+	 * We always virtualize the next field so we can remove
+	 * capabilities from the chain if we want to.
+	 */
+	p_setb(perm, PCI_CAP_LIST_NEXT, (u8)ALL_VIRT, NO_WRITE);
+
+	/*
+	 * Power management is defined *per function*, so we can let
+	 * the user change power state, but we trap and initiate the
+	 * change ourselves, so the state bits are read-only.
+	 */
+	p_setd(perm, PCI_PM_CTRL, NO_VIRT, ~PCI_PM_CTRL_STATE_MASK);
+	return 0;
+}
+
+/* Permissions for PCI-X capability */
+static int __init init_pci_cap_pcix_perm(struct perm_bits *perm)
+{
+	/* Alloc 24, but only 8 are used in v0 */
+	if (alloc_perm_bits(perm, PCI_CAP_PCIX_SIZEOF_V2))
+		return -ENOMEM;
+
+	p_setb(perm, PCI_CAP_LIST_NEXT, (u8)ALL_VIRT, NO_WRITE);
+
+	p_setw(perm, PCI_X_CMD, NO_VIRT, (u16)ALL_WRITE);
+	p_setd(perm, PCI_X_ECC_CSR, NO_VIRT, ALL_WRITE);
+	return 0;
+}
+
+/* Permissions for PCI Express capability */
+static int __init init_pci_cap_exp_perm(struct perm_bits *perm)
+{
+	/* Alloc larger of two possible sizes */
+	if (alloc_perm_bits(perm, PCI_CAP_EXP_ENDPOINT_SIZEOF_V2))
+		return -ENOMEM;
+
+	p_setb(perm, PCI_CAP_LIST_NEXT, (u8)ALL_VIRT, NO_WRITE);
+
+	/*
+	 * Allow writes to device control fields (includes FLR!)
+	 * but not to devctl_phantom which could confuse IOMMU
+	 * or to the ARI bit in devctl2 which is set at probe time
+	 */
+	p_setw(perm, PCI_EXP_DEVCTL, NO_VIRT, ~PCI_EXP_DEVCTL_PHANTOM);
+	p_setw(perm, PCI_EXP_DEVCTL2, NO_VIRT, ~PCI_EXP_DEVCTL2_ARI);
+	return 0;
+}
+
+/* Permissions for Advanced Function capability */
+static int __init init_pci_cap_af_perm(struct perm_bits *perm)
+{
+	if (alloc_perm_bits(perm, pci_cap_length[PCI_CAP_ID_AF]))
+		return -ENOMEM;
+
+	p_setb(perm, PCI_CAP_LIST_NEXT, (u8)ALL_VIRT, NO_WRITE);
+	p_setb(perm, PCI_AF_CTRL, NO_VIRT, PCI_AF_CTRL_FLR);
+	return 0;
+}
+
+/* Permissions for Advanced Error Reporting extended capability */
+static int __init init_pci_ext_cap_err_perm(struct perm_bits *perm)
+{
+	u32 mask;
+
+	if (alloc_perm_bits(perm, pci_ext_cap_length[PCI_EXT_CAP_ID_ERR]))
+		return -ENOMEM;
+
+	/*
+	 * Virtualize the first dword of all express capabilities
+	 * because it includes the next pointer.  This lets us later
+	 * remove capabilities from the chain if we need to.
+	 */
+	p_setd(perm, 0, ALL_VIRT, NO_WRITE);
+
+	/* Writable bits mask */
+	mask =	PCI_ERR_UNC_UND |		/* Undefined */
+		PCI_ERR_UNC_DLP |		/* Data Link Protocol */
+		PCI_ERR_UNC_SURPDN |		/* Surprise Down */
+		PCI_ERR_UNC_POISON_TLP |	/* Poisoned TLP */
+		PCI_ERR_UNC_FCP |		/* Flow Control Protocol */
+		PCI_ERR_UNC_COMP_TIME |		/* Completion Timeout */
+		PCI_ERR_UNC_COMP_ABORT |	/* Completer Abort */
+		PCI_ERR_UNC_UNX_COMP |		/* Unexpected Completion */
+		PCI_ERR_UNC_RX_OVER |		/* Receiver Overflow */
+		PCI_ERR_UNC_MALF_TLP |		/* Malformed TLP */
+		PCI_ERR_UNC_ECRC |		/* ECRC Error Status */
+		PCI_ERR_UNC_UNSUP |		/* Unsupported Request */
+		PCI_ERR_UNC_ACSV |		/* ACS Violation */
+		PCI_ERR_UNC_INTN |		/* internal error */
+		PCI_ERR_UNC_MCBTLP |		/* MC blocked TLP */
+		PCI_ERR_UNC_ATOMEG |		/* Atomic egress blocked */
+		PCI_ERR_UNC_TLPPRE;		/* TLP prefix blocked */
+	p_setd(perm, PCI_ERR_UNCOR_STATUS, NO_VIRT, mask);
+	p_setd(perm, PCI_ERR_UNCOR_MASK, NO_VIRT, mask);
+	p_setd(perm, PCI_ERR_UNCOR_SEVER, NO_VIRT, mask);
+
+	mask =	PCI_ERR_COR_RCVR |		/* Receiver Error Status */
+		PCI_ERR_COR_BAD_TLP |		/* Bad TLP Status */
+		PCI_ERR_COR_BAD_DLLP |		/* Bad DLLP Status */
+		PCI_ERR_COR_REP_ROLL |		/* REPLAY_NUM Rollover */
+		PCI_ERR_COR_REP_TIMER |		/* Replay Timer Timeout */
+		PCI_ERR_COR_ADV_NFAT |		/* Advisory Non-Fatal */
+		PCI_ERR_COR_INTERNAL |		/* Corrected Internal */
+		PCI_ERR_COR_LOG_OVER;		/* Header Log Overflow */
+	p_setd(perm, PCI_ERR_COR_STATUS, NO_VIRT, mask);
+	p_setd(perm, PCI_ERR_COR_MASK, NO_VIRT, mask);
+
+	mask =	PCI_ERR_CAP_ECRC_GENE |		/* ECRC Generation Enable */
+		PCI_ERR_CAP_ECRC_CHKE;		/* ECRC Check Enable */
+	p_setd(perm, PCI_ERR_CAP, NO_VIRT, mask);
+	return 0;
+}
+
+/* Permissions for Power Budgeting extended capability */
+static int __init init_pci_ext_cap_pwr_perm(struct perm_bits *perm)
+{
+	if (alloc_perm_bits(perm, pci_ext_cap_length[PCI_EXT_CAP_ID_PWR]))
+		return -ENOMEM;
+
+	p_setd(perm, 0, ALL_VIRT, NO_WRITE);
+
+	/* Writing the data selector is OK, the info is still read-only */
+	p_setb(perm, PCI_PWR_DATA, NO_VIRT, (u8)ALL_WRITE);
+	return 0;
+}
+
+/*
+ * Initialize the shared permission tables
+ */
+void vfio_pci_uninit_perm_bits(void)
+{
+	free_perm_bits(&cap_perms[PCI_CAP_ID_BASIC]);
+
+	free_perm_bits(&cap_perms[PCI_CAP_ID_PM]);
+	free_perm_bits(&cap_perms[PCI_CAP_ID_PCIX]);
+	free_perm_bits(&cap_perms[PCI_CAP_ID_EXP]);
+	free_perm_bits(&cap_perms[PCI_CAP_ID_AF]);
+
+	free_perm_bits(&ecap_perms[PCI_EXT_CAP_ID_ERR]);
+	free_perm_bits(&ecap_perms[PCI_EXT_CAP_ID_PWR]);
+}
+
+int __init vfio_pci_init_perm_bits(void)
+{
+	int ret;
+
+	/* Basic config space */
+	ret = init_pci_cap_basic_perm(&cap_perms[PCI_CAP_ID_BASIC]);
+
+	/* Capabilities */
+	ret |= init_pci_cap_pm_perm(&cap_perms[PCI_CAP_ID_PM]);
+	cap_perms[PCI_CAP_ID_VPD].writefn = vfio_raw_config_write;
+	ret |= init_pci_cap_pcix_perm(&cap_perms[PCI_CAP_ID_PCIX]);
+	cap_perms[PCI_CAP_ID_VNDR].writefn = vfio_raw_config_write;
+	ret |= init_pci_cap_exp_perm(&cap_perms[PCI_CAP_ID_EXP]);
+	ret |= init_pci_cap_af_perm(&cap_perms[PCI_CAP_ID_AF]);
+
+	/* Extended capabilities */
+	ret |= init_pci_ext_cap_err_perm(&ecap_perms[PCI_EXT_CAP_ID_ERR]);
+	ret |= init_pci_ext_cap_pwr_perm(&ecap_perms[PCI_EXT_CAP_ID_PWR]);
+	ecap_perms[PCI_EXT_CAP_ID_VNDR].writefn = vfio_raw_config_write;
+
+	if (ret)
+		vfio_pci_uninit_perm_bits();
+
+	return ret;
+}
+
+static int vfio_find_cap_start(struct vfio_pci_device *vdev, int pos)
+{
+	u8 cap;
+	int base = (pos >= PCI_CFG_SPACE_SIZE) ? PCI_CFG_SPACE_SIZE :
+						 PCI_STD_HEADER_SIZEOF;
+	cap = vdev->pci_config_map[pos];
+
+	if (cap == PCI_CAP_ID_BASIC)
+		return 0;
+
+	/* XXX Can we have to abutting capabilities of the same type? */
+	while (pos - 1 >= base && vdev->pci_config_map[pos - 1] == cap)
+		pos--;
+
+	return pos;
+}
+
+static int vfio_msi_config_read(struct vfio_pci_device *vdev, int pos,
+				int count, struct perm_bits *perm,
+				int offset, __le32 *val)
+{
+	/* Update max available queue size from msi_qmax */
+	if (offset <= PCI_MSI_FLAGS && offset + count >= PCI_MSI_FLAGS) {
+		__le16 *flags;
+		int start;
+
+		start = vfio_find_cap_start(vdev, pos);
+
+		flags = (__le16 *)&vdev->vconfig[start];
+
+		*flags &= cpu_to_le16(~PCI_MSI_FLAGS_QMASK);
+		*flags |= cpu_to_le16(vdev->msi_qmax << 1);
+	}
+
+	return vfio_default_config_read(vdev, pos, count, perm, offset, val);
+}
+
+static int vfio_msi_config_write(struct vfio_pci_device *vdev, int pos,
+				 int count, struct perm_bits *perm,
+				 int offset, __le32 val)
+{
+	count = vfio_default_config_write(vdev, pos, count, perm, offset, val);
+	if (count < 0)
+		return count;
+
+	/* Fixup and write configured queue size and enable to hardware */
+	if (offset <= PCI_MSI_FLAGS && offset + count >= PCI_MSI_FLAGS) {
+		__le16 *pflags;
+		u16 flags;
+		int start, ret;
+
+		start = vfio_find_cap_start(vdev, pos);
+
+		pflags = (__le16 *)&vdev->vconfig[start + PCI_MSI_FLAGS];
+
+		flags = le16_to_cpu(*pflags);
+
+		/* MSI is enabled via ioctl */
+		if  (!is_msi(vdev))
+			flags &= ~PCI_MSI_FLAGS_ENABLE;
+
+		/* Check queue size */
+		if ((flags & PCI_MSI_FLAGS_QSIZE) >> 4 > vdev->msi_qmax) {
+			flags &= ~PCI_MSI_FLAGS_QSIZE;
+			flags |= vdev->msi_qmax << 4;
+		}
+
+		/* Write back to virt and to hardware */
+		*pflags = cpu_to_le16(flags);
+		ret = pci_user_write_config_word(vdev->pdev,
+						 start + PCI_MSI_FLAGS,
+						 flags);
+		if (ret)
+			return pcibios_err_to_errno(ret);
+	}
+
+	return count;
+}
+
+/*
+ * MSI determination is per-device, so this routine gets used beyond
+ * initialization time. Don't add __init
+ */
+static int init_pci_cap_msi_perm(struct perm_bits *perm, int len, u16 flags)
+{
+	if (alloc_perm_bits(perm, len))
+		return -ENOMEM;
+
+	perm->readfn = vfio_msi_config_read;
+	perm->writefn = vfio_msi_config_write;
+
+	p_setb(perm, PCI_CAP_LIST_NEXT, (u8)ALL_VIRT, NO_WRITE);
+
+	/*
+	 * The upper byte of the control register is reserved,
+	 * just setup the lower byte.
+	 */
+	p_setb(perm, PCI_MSI_FLAGS, (u8)ALL_VIRT, (u8)ALL_WRITE);
+	p_setd(perm, PCI_MSI_ADDRESS_LO, ALL_VIRT, ALL_WRITE);
+	if (flags & PCI_MSI_FLAGS_64BIT) {
+		p_setd(perm, PCI_MSI_ADDRESS_HI, ALL_VIRT, ALL_WRITE);
+		p_setw(perm, PCI_MSI_DATA_64, (u16)ALL_VIRT, (u16)ALL_WRITE);
+		if (flags & PCI_MSI_FLAGS_MASKBIT) {
+			p_setd(perm, PCI_MSI_MASK_64, NO_VIRT, ALL_WRITE);
+			p_setd(perm, PCI_MSI_PENDING_64, NO_VIRT, ALL_WRITE);
+		}
+	} else {
+		p_setw(perm, PCI_MSI_DATA_32, (u16)ALL_VIRT, (u16)ALL_WRITE);
+		if (flags & PCI_MSI_FLAGS_MASKBIT) {
+			p_setd(perm, PCI_MSI_MASK_32, NO_VIRT, ALL_WRITE);
+			p_setd(perm, PCI_MSI_PENDING_32, NO_VIRT, ALL_WRITE);
+		}
+	}
+	return 0;
+}
+
+/* Determine MSI CAP field length; initialize msi_perms on 1st call per vdev */
+static int vfio_msi_cap_len(struct vfio_pci_device *vdev, u8 pos)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	int len, ret;
+	u16 flags;
+
+	ret = pci_read_config_word(pdev, pos + PCI_MSI_FLAGS, &flags);
+	if (ret)
+		return pcibios_err_to_errno(ret);
+
+	len = 10; /* Minimum size */
+	if (flags & PCI_MSI_FLAGS_64BIT)
+		len += 4;
+	if (flags & PCI_MSI_FLAGS_MASKBIT)
+		len += 10;
+
+	if (vdev->msi_perm)
+		return len;
+
+	vdev->msi_perm = kmalloc(sizeof(struct perm_bits), GFP_KERNEL);
+	if (!vdev->msi_perm)
+		return -ENOMEM;
+
+	ret = init_pci_cap_msi_perm(vdev->msi_perm, len, flags);
+	if (ret)
+		return ret;
+
+	return len;
+}
+
+/* Determine extended capability length for VC (2 & 9) and MFVC */
+static int vfio_vc_cap_len(struct vfio_pci_device *vdev, u16 pos)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	u32 tmp;
+	int ret, evcc, phases, vc_arb;
+	int len = PCI_CAP_VC_BASE_SIZEOF;
+
+	ret = pci_read_config_dword(pdev, pos + PCI_VC_PORT_CAP1, &tmp);
+	if (ret)
+		return pcibios_err_to_errno(ret);
+
+	evcc = tmp & PCI_VC_CAP1_EVCC; /* extended vc count */
+	ret = pci_read_config_dword(pdev, pos + PCI_VC_PORT_CAP2, &tmp);
+	if (ret)
+		return pcibios_err_to_errno(ret);
+
+	if (tmp & PCI_VC_CAP2_128_PHASE)
+		phases = 128;
+	else if (tmp & PCI_VC_CAP2_64_PHASE)
+		phases = 64;
+	else if (tmp & PCI_VC_CAP2_32_PHASE)
+		phases = 32;
+	else
+		phases = 0;
+
+	vc_arb = phases * 4;
+
+	/*
+	 * Port arbitration tables are root & switch only;
+	 * function arbitration tables are function 0 only.
+	 * In either case, we'll never let user write them so
+	 * we don't care how big they are
+	 */
+	len += (1 + evcc) * PCI_CAP_VC_PER_VC_SIZEOF;
+	if (vc_arb) {
+		len = round_up(len, 16);
+		len += vc_arb / 8;
+	}
+	return len;
+}
+
+static int vfio_cap_len(struct vfio_pci_device *vdev, u8 cap, u8 pos)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	u32 dword;
+	u16 word;
+	u8 byte;
+	int ret;
+
+	switch (cap) {
+	case PCI_CAP_ID_MSI:
+		return vfio_msi_cap_len(vdev, pos);
+	case PCI_CAP_ID_PCIX:
+		ret = pci_read_config_word(pdev, pos + PCI_X_CMD, &word);
+		if (ret)
+			return pcibios_err_to_errno(ret);
+
+		if (PCI_X_CMD_VERSION(word)) {
+			/* Test for extended capabilities */
+			pci_read_config_dword(pdev, PCI_CFG_SPACE_SIZE, &dword);
+			vdev->extended_caps = (dword != 0);
+			return PCI_CAP_PCIX_SIZEOF_V2;
+		} else
+			return PCI_CAP_PCIX_SIZEOF_V0;
+	case PCI_CAP_ID_VNDR:
+		/* length follows next field */
+		ret = pci_read_config_byte(pdev, pos + PCI_CAP_FLAGS, &byte);
+		if (ret)
+			return pcibios_err_to_errno(ret);
+
+		return byte;
+	case PCI_CAP_ID_EXP:
+		/* Test for extended capabilities */
+		pci_read_config_dword(pdev, PCI_CFG_SPACE_SIZE, &dword);
+		vdev->extended_caps = (dword != 0);
+
+		/* length based on version */
+		if ((pcie_caps_reg(pdev) & PCI_EXP_FLAGS_VERS) == 1)
+			return PCI_CAP_EXP_ENDPOINT_SIZEOF_V1;
+		else
+			return PCI_CAP_EXP_ENDPOINT_SIZEOF_V2;
+	case PCI_CAP_ID_HT:
+		ret = pci_read_config_byte(pdev, pos + 3, &byte);
+		if (ret)
+			return pcibios_err_to_errno(ret);
+
+		return (byte & HT_3BIT_CAP_MASK) ?
+			HT_CAP_SIZEOF_SHORT : HT_CAP_SIZEOF_LONG;
+	case PCI_CAP_ID_SATA:
+		ret = pci_read_config_byte(pdev, pos + PCI_SATA_REGS, &byte);
+		if (ret)
+			return pcibios_err_to_errno(ret);
+
+		byte &= PCI_SATA_REGS_MASK;
+		if (byte == PCI_SATA_REGS_INLINE)
+			return PCI_SATA_SIZEOF_LONG;
+		else
+			return PCI_SATA_SIZEOF_SHORT;
+	default:
+		pr_warn("%s: %s unknown length for pci cap 0x%x@0x%x\n",
+			dev_name(&pdev->dev), __func__, cap, pos);
+	}
+
+	return 0;
+}
+
+static int vfio_ext_cap_len(struct vfio_pci_device *vdev, u16 ecap, u16 epos)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	u8 byte;
+	u32 dword;
+	int ret;
+
+	switch (ecap) {
+	case PCI_EXT_CAP_ID_VNDR:
+		ret = pci_read_config_dword(pdev, epos + PCI_VSEC_HDR, &dword);
+		if (ret)
+			return pcibios_err_to_errno(ret);
+
+		return dword >> PCI_VSEC_HDR_LEN_SHIFT;
+	case PCI_EXT_CAP_ID_VC:
+	case PCI_EXT_CAP_ID_VC9:
+	case PCI_EXT_CAP_ID_MFVC:
+		return vfio_vc_cap_len(vdev, epos);
+	case PCI_EXT_CAP_ID_ACS:
+		ret = pci_read_config_byte(pdev, epos + PCI_ACS_CAP, &byte);
+		if (ret)
+			return pcibios_err_to_errno(ret);
+
+		if (byte & PCI_ACS_EC) {
+			int bits;
+
+			ret = pci_read_config_byte(pdev,
+						   epos + PCI_ACS_EGRESS_BITS,
+						   &byte);
+			if (ret)
+				return pcibios_err_to_errno(ret);
+
+			bits = byte ? round_up(byte, 32) : 256;
+			return 8 + (bits / 8);
+		}
+		return 8;
+
+	case PCI_EXT_CAP_ID_REBAR:
+		ret = pci_read_config_byte(pdev, epos + PCI_REBAR_CTRL, &byte);
+		if (ret)
+			return pcibios_err_to_errno(ret);
+
+		byte &= PCI_REBAR_CTRL_NBAR_MASK;
+		byte >>= PCI_REBAR_CTRL_NBAR_SHIFT;
+
+		return 4 + (byte * 8);
+	case PCI_EXT_CAP_ID_DPA:
+		ret = pci_read_config_byte(pdev, epos + PCI_DPA_CAP, &byte);
+		if (ret)
+			return pcibios_err_to_errno(ret);
+
+		byte &= PCI_DPA_CAP_SUBSTATE_MASK;
+		return PCI_DPA_BASE_SIZEOF + byte + 1;
+	case PCI_EXT_CAP_ID_TPH:
+		ret = pci_read_config_dword(pdev, epos + PCI_TPH_CAP, &dword);
+		if (ret)
+			return pcibios_err_to_errno(ret);
+
+		if ((dword & PCI_TPH_CAP_LOC_MASK) == PCI_TPH_LOC_CAP) {
+			int sts;
+
+			sts = dword & PCI_TPH_CAP_ST_MASK;
+			sts >>= PCI_TPH_CAP_ST_SHIFT;
+			return PCI_TPH_BASE_SIZEOF + (sts * 2) + 2;
+		}
+		return PCI_TPH_BASE_SIZEOF;
+	default:
+		pr_warn("%s: %s unknown length for pci ecap 0x%x@0x%x\n",
+			dev_name(&pdev->dev), __func__, ecap, epos);
+	}
+
+	return 0;
+}
+
+static int vfio_fill_vconfig_bytes(struct vfio_pci_device *vdev,
+				   int offset, int size)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	int ret = 0;
+
+	/*
+	 * We try to read physical config space in the largest chunks
+	 * we can, assuming that all of the fields support dword access.
+	 * pci_save_state() makes this same assumption and seems to do ok.
+	 */
+	while (size) {
+		int filled;
+
+		if (size >= 4 && !(offset % 4)) {
+			__le32 *dwordp = (__le32 *)&vdev->vconfig[offset];
+			u32 dword;
+
+			ret = pci_read_config_dword(pdev, offset, &dword);
+			if (ret)
+				return ret;
+			*dwordp = cpu_to_le32(dword);
+			filled = 4;
+		} else if (size >= 2 && !(offset % 2)) {
+			__le16 *wordp = (__le16 *)&vdev->vconfig[offset];
+			u16 word;
+
+			ret = pci_read_config_word(pdev, offset, &word);
+			if (ret)
+				return ret;
+			*wordp = cpu_to_le16(word);
+			filled = 2;
+		} else {
+			u8 *byte = &vdev->vconfig[offset];
+			ret = pci_read_config_byte(pdev, offset, byte);
+			if (ret)
+				return ret;
+			filled = 1;
+		}
+
+		offset += filled;
+		size -= filled;
+	}
+
+	return ret;
+}
+
+static int vfio_cap_init(struct vfio_pci_device *vdev)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	u8 *map = vdev->pci_config_map;
+	u16 status;
+	u8 pos, *prev, cap;
+	int loops, ret, caps = 0;
+
+	/* Any capabilities? */
+	ret = pci_read_config_word(pdev, PCI_STATUS, &status);
+	if (ret)
+		return ret;
+
+	if (!(status & PCI_STATUS_CAP_LIST))
+		return 0; /* Done */
+
+	ret = pci_read_config_byte(pdev, PCI_CAPABILITY_LIST, &pos);
+	if (ret)
+		return ret;
+
+	/* Mark the previous position in case we want to skip a capability */
+	prev = &vdev->vconfig[PCI_CAPABILITY_LIST];
+
+	/* We can bound our loop, capabilities are dword aligned */
+	loops = (PCI_CFG_SPACE_SIZE - PCI_STD_HEADER_SIZEOF) / PCI_CAP_SIZEOF;
+	while (pos && loops--) {
+		u8 next;
+		int i, len = 0;
+
+		ret = pci_read_config_byte(pdev, pos, &cap);
+		if (ret)
+			return ret;
+
+		ret = pci_read_config_byte(pdev,
+					   pos + PCI_CAP_LIST_NEXT, &next);
+		if (ret)
+			return ret;
+
+		if (cap <= PCI_CAP_ID_MAX) {
+			len = pci_cap_length[cap];
+			if (len == 0xFF) { /* Variable length */
+				len = vfio_cap_len(vdev, cap, pos);
+				if (len < 0)
+					return len;
+			}
+		}
+
+		if (!len) {
+			pr_info("%s: %s hiding cap 0x%x\n",
+				__func__, dev_name(&pdev->dev), cap);
+			*prev = next;
+			pos = next;
+			continue;
+		}
+
+		/* Sanity check, do we overlap other capabilities? */
+		for (i = 0; i < len; i++) {
+			if (likely(map[pos + i] == PCI_CAP_ID_INVALID))
+				continue;
+
+			pr_warn("%s: %s pci config conflict @0x%x, was cap 0x%x now cap 0x%x\n",
+				__func__, dev_name(&pdev->dev),
+				pos + i, map[pos + i], cap);
+		}
+
+		memset(map + pos, cap, len);
+		ret = vfio_fill_vconfig_bytes(vdev, pos, len);
+		if (ret)
+			return ret;
+
+		prev = &vdev->vconfig[pos + PCI_CAP_LIST_NEXT];
+		pos = next;
+		caps++;
+	}
+
+	/* If we didn't fill any capabilities, clear the status flag */
+	if (!caps) {
+		__le16 *vstatus = (__le16 *)&vdev->vconfig[PCI_STATUS];
+		*vstatus &= ~cpu_to_le16(PCI_STATUS_CAP_LIST);
+	}
+
+	return 0;
+}
+
+static int vfio_ecap_init(struct vfio_pci_device *vdev)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	u8 *map = vdev->pci_config_map;
+	u16 epos;
+	__le32 *prev = NULL;
+	int loops, ret, ecaps = 0;
+
+	if (!vdev->extended_caps)
+		return 0;
+
+	epos = PCI_CFG_SPACE_SIZE;
+
+	loops = (pdev->cfg_size - PCI_CFG_SPACE_SIZE) / PCI_CAP_SIZEOF;
+
+	while (loops-- && epos >= PCI_CFG_SPACE_SIZE) {
+		u32 header;
+		u16 ecap;
+		int i, len = 0;
+		bool hidden = false;
+
+		ret = pci_read_config_dword(pdev, epos, &header);
+		if (ret)
+			return ret;
+
+		ecap = PCI_EXT_CAP_ID(header);
+
+		if (ecap <= PCI_EXT_CAP_ID_MAX) {
+			len = pci_ext_cap_length[ecap];
+			if (len == 0xFF) {
+				len = vfio_ext_cap_len(vdev, ecap, epos);
+				if (len < 0)
+					return ret;
+			}
+		}
+
+		if (!len) {
+			pr_info("%s: %s hiding ecap 0x%x@0x%x\n",
+				__func__, dev_name(&pdev->dev), ecap, epos);
+
+			/* If not the first in the chain, we can skip over it */
+			if (prev) {
+				u32 val = epos = PCI_EXT_CAP_NEXT(header);
+				*prev &= cpu_to_le32(~(0xffcU << 20));
+				*prev |= cpu_to_le32(val << 20);
+				continue;
+			}
+
+			/*
+			 * Otherwise, fill in a placeholder, the direct
+			 * readfn will virtualize this automatically
+			 */
+			len = PCI_CAP_SIZEOF;
+			hidden = true;
+		}
+
+		for (i = 0; i < len; i++) {
+			if (likely(map[epos + i] == PCI_CAP_ID_INVALID))
+				continue;
+
+			pr_warn("%s: %s pci config conflict @0x%x, was ecap 0x%x now ecap 0x%x\n",
+				__func__, dev_name(&pdev->dev),
+				epos + i, map[epos + i], ecap);
+		}
+
+		/*
+		 * Even though ecap is 2 bytes, we're currently a long way
+		 * from exceeding 1 byte capabilities.  If we ever make it
+		 * up to 0xFF we'll need to up this to a two-byte, byte map.
+		 */
+		BUILD_BUG_ON(PCI_EXT_CAP_ID_MAX >= PCI_CAP_ID_INVALID);
+
+		memset(map + epos, ecap, len);
+		ret = vfio_fill_vconfig_bytes(vdev, epos, len);
+		if (ret)
+			return ret;
+
+		/*
+		 * If we're just using this capability to anchor the list,
+		 * hide the real ID.  Only count real ecaps.  XXX PCI spec
+		 * indicates to use cap id = 0, version = 0, next = 0 if
+		 * ecaps are absent, hope users check all the way to next.
+		 */
+		if (hidden)
+			*(__le32 *)&vdev->vconfig[epos] &=
+				cpu_to_le32((0xffcU << 20));
+		else
+			ecaps++;
+
+		prev = (__le32 *)&vdev->vconfig[epos];
+		epos = PCI_EXT_CAP_NEXT(header);
+	}
+
+	if (!ecaps)
+		*(u32 *)&vdev->vconfig[PCI_CFG_SPACE_SIZE] = 0;
+
+	return 0;
+}
+
+/*
+ * For each device we allocate a pci_config_map that indicates the
+ * capability occupying each dword and thus the struct perm_bits we
+ * use for read and write.  We also allocate a virtualized config
+ * space which tracks reads and writes to bits that we emulate for
+ * the user.  Initial values filled from device.
+ *
+ * Using shared stuct perm_bits between all vfio-pci devices saves
+ * us from allocating cfg_size buffers for virt and write for every
+ * device.  We could remove vconfig and allocate individual buffers
+ * for each area requring emulated bits, but the array of pointers
+ * would be comparable in size (at least for standard config space).
+ */
+int vfio_config_init(struct vfio_pci_device *vdev)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	u8 *map, *vconfig;
+	int ret;
+
+	/*
+	 * Config space, caps and ecaps are all dword aligned, so we could
+	 * use one byte per dword to record the type.  However, there are
+	 * no requiremenst on the length of a capability, so the gap between
+	 * capabilities needs byte granularity.
+	 */
+	map = kmalloc(pdev->cfg_size, GFP_KERNEL);
+	if (!map)
+		return -ENOMEM;
+
+	vconfig = kmalloc(pdev->cfg_size, GFP_KERNEL);
+	if (!vconfig) {
+		kfree(map);
+		return -ENOMEM;
+	}
+
+	vdev->pci_config_map = map;
+	vdev->vconfig = vconfig;
+
+	memset(map, PCI_CAP_ID_BASIC, PCI_STD_HEADER_SIZEOF);
+	memset(map + PCI_STD_HEADER_SIZEOF, PCI_CAP_ID_INVALID,
+	       pdev->cfg_size - PCI_STD_HEADER_SIZEOF);
+
+	ret = vfio_fill_vconfig_bytes(vdev, 0, PCI_STD_HEADER_SIZEOF);
+	if (ret)
+		goto out;
+
+	vdev->bardirty = true;
+
+	/*
+	 * XXX can we just pci_load_saved_state/pci_restore_state?
+	 * may need to rebuild vconfig after that
+	 */
+
+	/* For restore after reset */
+	vdev->rbar[0] = le32_to_cpu(*(__le32 *)&vconfig[PCI_BASE_ADDRESS_0]);
+	vdev->rbar[1] = le32_to_cpu(*(__le32 *)&vconfig[PCI_BASE_ADDRESS_1]);
+	vdev->rbar[2] = le32_to_cpu(*(__le32 *)&vconfig[PCI_BASE_ADDRESS_2]);
+	vdev->rbar[3] = le32_to_cpu(*(__le32 *)&vconfig[PCI_BASE_ADDRESS_3]);
+	vdev->rbar[4] = le32_to_cpu(*(__le32 *)&vconfig[PCI_BASE_ADDRESS_4]);
+	vdev->rbar[5] = le32_to_cpu(*(__le32 *)&vconfig[PCI_BASE_ADDRESS_5]);
+	vdev->rbar[6] = le32_to_cpu(*(__le32 *)&vconfig[PCI_ROM_ADDRESS]);
+
+	if (pdev->is_virtfn) {
+		*(__le16 *)&vconfig[PCI_VENDOR_ID] = cpu_to_le16(pdev->vendor);
+		*(__le16 *)&vconfig[PCI_DEVICE_ID] = cpu_to_le16(pdev->device);
+	}
+
+	if (!IS_ENABLED(CONFIG_VFIO_PCI_INTX))
+		vconfig[PCI_INTERRUPT_PIN] = 0;
+
+	ret = vfio_cap_init(vdev);
+	if (ret)
+		goto out;
+
+	ret = vfio_ecap_init(vdev);
+	if (ret)
+		goto out;
+
+	return 0;
+
+out:
+	kfree(map);
+	vdev->pci_config_map = NULL;
+	kfree(vconfig);
+	vdev->vconfig = NULL;
+	return pcibios_err_to_errno(ret);
+}
+
+void vfio_config_free(struct vfio_pci_device *vdev)
+{
+	kfree(vdev->vconfig);
+	vdev->vconfig = NULL;
+	kfree(vdev->pci_config_map);
+	vdev->pci_config_map = NULL;
+	kfree(vdev->msi_perm);
+	vdev->msi_perm = NULL;
+}
+
+/*
+ * Find the remaining number of bytes in a dword that match the given
+ * position.  Stop at either the end of the capability or the dword boundary.
+ */
+static size_t vfio_pci_cap_remaining_dword(struct vfio_pci_device *vdev,
+					   loff_t pos)
+{
+	u8 cap = vdev->pci_config_map[pos];
+	size_t i;
+
+	for (i = 1; (pos + i) % 4 && vdev->pci_config_map[pos + i] == cap; i++)
+		/* nop */;
+
+	return i;
+}
+
+static ssize_t vfio_config_do_rw(struct vfio_pci_device *vdev, char __user *buf,
+				 size_t count, loff_t *ppos, bool iswrite)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	struct perm_bits *perm;
+	__le32 val = 0;
+	int cap_start = 0, offset;
+	u8 cap_id;
+	ssize_t ret;
+
+	if (*ppos < 0 || *ppos >= pdev->cfg_size ||
+	    *ppos + count > pdev->cfg_size)
+		return -EFAULT;
+
+	/*
+	 * Chop accesses into aligned chunks containing no more than a
+	 * single capability.  Caller increments to the next chunk.
+	 */
+	count = min(count, vfio_pci_cap_remaining_dword(vdev, *ppos));
+	if (count >= 4 && !(*ppos % 4))
+		count = 4;
+	else if (count >= 2 && !(*ppos % 2))
+		count = 2;
+	else
+		count = 1;
+
+	ret = count;
+
+	cap_id = vdev->pci_config_map[*ppos];
+
+	if (cap_id == PCI_CAP_ID_INVALID) {
+		perm = &unassigned_perms;
+		cap_start = *ppos;
+	} else {
+		if (*ppos >= PCI_CFG_SPACE_SIZE) {
+			WARN_ON(cap_id > PCI_EXT_CAP_ID_MAX);
+
+			perm = &ecap_perms[cap_id];
+			cap_start = vfio_find_cap_start(vdev, *ppos);
+		} else {
+			WARN_ON(cap_id > PCI_CAP_ID_MAX);
+
+			perm = &cap_perms[cap_id];
+
+			if (cap_id == PCI_CAP_ID_MSI)
+				perm = vdev->msi_perm;
+
+			if (cap_id > PCI_CAP_ID_BASIC)
+				cap_start = vfio_find_cap_start(vdev, *ppos);
+		}
+	}
+
+	WARN_ON(!cap_start && cap_id != PCI_CAP_ID_BASIC);
+	WARN_ON(cap_start > *ppos);
+
+	offset = *ppos - cap_start;
+
+	if (iswrite) {
+		if (!perm->writefn)
+			return ret;
+
+		if (copy_from_user(&val, buf, count))
+			return -EFAULT;
+
+		ret = perm->writefn(vdev, *ppos, count, perm, offset, val);
+	} else {
+		if (perm->readfn) {
+			ret = perm->readfn(vdev, *ppos, count,
+					   perm, offset, &val);
+			if (ret < 0)
+				return ret;
+		}
+
+		if (copy_to_user(buf, &val, count))
+			return -EFAULT;
+	}
+
+	return ret;
+}
+
+ssize_t vfio_pci_config_rw(struct vfio_pci_device *vdev, char __user *buf,
+			   size_t count, loff_t *ppos, bool iswrite)
+{
+	size_t done = 0;
+	int ret = 0;
+	loff_t pos = *ppos;
+
+	pos &= VFIO_PCI_OFFSET_MASK;
+
+	while (count) {
+		ret = vfio_config_do_rw(vdev, buf, count, &pos, iswrite);
+		if (ret < 0)
+			return ret;
+
+		count -= ret;
+		done += ret;
+		buf += ret;
+		pos += ret;
+	}
+
+	*ppos += done;
+
+	return done;
+}
diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
new file mode 100644
index 000000000..1f577b4ac
--- /dev/null
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -0,0 +1,675 @@
+/*
+ * VFIO PCI interrupt handling
+ *
+ * Copyright (C) 2012 Red Hat, Inc.  All rights reserved.
+ *     Author: Alex Williamson <alex.williamson@redhat.com>
+ *
+ * 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.
+ *
+ * Derived from original vfio:
+ * Copyright 2010 Cisco Systems, Inc.  All rights reserved.
+ * Author: Tom Lyon, pugs@cisco.com
+ */
+
+#include <linux/device.h>
+#include <linux/interrupt.h>
+#include <linux/eventfd.h>
+#include <linux/msi.h>
+#include <linux/pci.h>
+#include <linux/file.h>
+#include <linux/vfio.h>
+#include <linux/wait.h>
+#include <linux/slab.h>
+
+#include "vfio_pci_private.h"
+
+/*
+ * INTx
+ */
+static void vfio_send_intx_eventfd(void *opaque, void *unused)
+{
+	struct vfio_pci_device *vdev = opaque;
+
+	if (likely(is_intx(vdev) && !vdev->virq_disabled))
+		eventfd_signal(vdev->ctx[0].trigger, 1);
+}
+
+void vfio_pci_intx_mask(struct vfio_pci_device *vdev)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	unsigned long flags;
+
+	spin_lock_irqsave(&vdev->irqlock, flags);
+
+	/*
+	 * Masking can come from interrupt, ioctl, or config space
+	 * via INTx disable.  The latter means this can get called
+	 * even when not using intx delivery.  In this case, just
+	 * try to have the physical bit follow the virtual bit.
+	 */
+	if (unlikely(!is_intx(vdev))) {
+		if (vdev->pci_2_3)
+			pci_intx(pdev, 0);
+	} else if (!vdev->ctx[0].masked) {
+		/*
+		 * Can't use check_and_mask here because we always want to
+		 * mask, not just when something is pending.
+		 */
+		if (vdev->pci_2_3)
+			pci_intx(pdev, 0);
+		else
+			disable_irq_nosync(pdev->irq);
+
+		vdev->ctx[0].masked = true;
+	}
+
+	spin_unlock_irqrestore(&vdev->irqlock, flags);
+}
+
+/*
+ * If this is triggered by an eventfd, we can't call eventfd_signal
+ * or else we'll deadlock on the eventfd wait queue.  Return >0 when
+ * a signal is necessary, which can then be handled via a work queue
+ * or directly depending on the caller.
+ */
+static int vfio_pci_intx_unmask_handler(void *opaque, void *unused)
+{
+	struct vfio_pci_device *vdev = opaque;
+	struct pci_dev *pdev = vdev->pdev;
+	unsigned long flags;
+	int ret = 0;
+
+	spin_lock_irqsave(&vdev->irqlock, flags);
+
+	/*
+	 * Unmasking comes from ioctl or config, so again, have the
+	 * physical bit follow the virtual even when not using INTx.
+	 */
+	if (unlikely(!is_intx(vdev))) {
+		if (vdev->pci_2_3)
+			pci_intx(pdev, 1);
+	} else if (vdev->ctx[0].masked && !vdev->virq_disabled) {
+		/*
+		 * A pending interrupt here would immediately trigger,
+		 * but we can avoid that overhead by just re-sending
+		 * the interrupt to the user.
+		 */
+		if (vdev->pci_2_3) {
+			if (!pci_check_and_unmask_intx(pdev))
+				ret = 1;
+		} else
+			enable_irq(pdev->irq);
+
+		vdev->ctx[0].masked = (ret > 0);
+	}
+
+	spin_unlock_irqrestore(&vdev->irqlock, flags);
+
+	return ret;
+}
+
+void vfio_pci_intx_unmask(struct vfio_pci_device *vdev)
+{
+	if (vfio_pci_intx_unmask_handler(vdev, NULL) > 0)
+		vfio_send_intx_eventfd(vdev, NULL);
+}
+
+static irqreturn_t vfio_intx_handler(int irq, void *dev_id)
+{
+	struct vfio_pci_device *vdev = dev_id;
+	unsigned long flags;
+	int ret = IRQ_NONE;
+
+	spin_lock_irqsave(&vdev->irqlock, flags);
+
+	if (!vdev->pci_2_3) {
+		disable_irq_nosync(vdev->pdev->irq);
+		vdev->ctx[0].masked = true;
+		ret = IRQ_HANDLED;
+	} else if (!vdev->ctx[0].masked &&  /* may be shared */
+		   pci_check_and_mask_intx(vdev->pdev)) {
+		vdev->ctx[0].masked = true;
+		ret = IRQ_HANDLED;
+	}
+
+	spin_unlock_irqrestore(&vdev->irqlock, flags);
+
+	if (ret == IRQ_HANDLED)
+		vfio_send_intx_eventfd(vdev, NULL);
+
+	return ret;
+}
+
+static int vfio_intx_enable(struct vfio_pci_device *vdev)
+{
+	if (!is_irq_none(vdev))
+		return -EINVAL;
+
+	if (!vdev->pdev->irq)
+		return -ENODEV;
+
+	vdev->ctx = kzalloc(sizeof(struct vfio_pci_irq_ctx), GFP_KERNEL);
+	if (!vdev->ctx)
+		return -ENOMEM;
+
+	vdev->num_ctx = 1;
+
+	/*
+	 * If the virtual interrupt is masked, restore it.  Devices
+	 * supporting DisINTx can be masked at the hardware level
+	 * here, non-PCI-2.3 devices will have to wait until the
+	 * interrupt is enabled.
+	 */
+	vdev->ctx[0].masked = vdev->virq_disabled;
+	if (vdev->pci_2_3)
+		pci_intx(vdev->pdev, !vdev->ctx[0].masked);
+
+	vdev->irq_type = VFIO_PCI_INTX_IRQ_INDEX;
+
+	return 0;
+}
+
+static int vfio_intx_set_signal(struct vfio_pci_device *vdev, int fd)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	unsigned long irqflags = IRQF_SHARED;
+	struct eventfd_ctx *trigger;
+	unsigned long flags;
+	int ret;
+
+	if (vdev->ctx[0].trigger) {
+		free_irq(pdev->irq, vdev);
+		kfree(vdev->ctx[0].name);
+		eventfd_ctx_put(vdev->ctx[0].trigger);
+		vdev->ctx[0].trigger = NULL;
+	}
+
+	if (fd < 0) /* Disable only */
+		return 0;
+
+	vdev->ctx[0].name = kasprintf(GFP_KERNEL, "vfio-intx(%s)",
+				      pci_name(pdev));
+	if (!vdev->ctx[0].name)
+		return -ENOMEM;
+
+	trigger = eventfd_ctx_fdget(fd);
+	if (IS_ERR(trigger)) {
+		kfree(vdev->ctx[0].name);
+		return PTR_ERR(trigger);
+	}
+
+	vdev->ctx[0].trigger = trigger;
+
+	if (!vdev->pci_2_3)
+		irqflags = 0;
+
+	ret = request_irq(pdev->irq, vfio_intx_handler,
+			  irqflags, vdev->ctx[0].name, vdev);
+	if (ret) {
+		vdev->ctx[0].trigger = NULL;
+		kfree(vdev->ctx[0].name);
+		eventfd_ctx_put(trigger);
+		return ret;
+	}
+
+	/*
+	 * INTx disable will stick across the new irq setup,
+	 * disable_irq won't.
+	 */
+	spin_lock_irqsave(&vdev->irqlock, flags);
+	if (!vdev->pci_2_3 && vdev->ctx[0].masked)
+		disable_irq_nosync(pdev->irq);
+	spin_unlock_irqrestore(&vdev->irqlock, flags);
+
+	return 0;
+}
+
+static void vfio_intx_disable(struct vfio_pci_device *vdev)
+{
+	vfio_intx_set_signal(vdev, -1);
+	vfio_virqfd_disable(&vdev->ctx[0].unmask);
+	vfio_virqfd_disable(&vdev->ctx[0].mask);
+	vdev->irq_type = VFIO_PCI_NUM_IRQS;
+	vdev->num_ctx = 0;
+	kfree(vdev->ctx);
+}
+
+/*
+ * MSI/MSI-X
+ */
+static irqreturn_t vfio_msihandler(int irq, void *arg)
+{
+	struct eventfd_ctx *trigger = arg;
+
+	eventfd_signal(trigger, 1);
+	return IRQ_HANDLED;
+}
+
+static int vfio_msi_enable(struct vfio_pci_device *vdev, int nvec, bool msix)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	int ret;
+
+	if (!is_irq_none(vdev))
+		return -EINVAL;
+
+	vdev->ctx = kzalloc(nvec * sizeof(struct vfio_pci_irq_ctx), GFP_KERNEL);
+	if (!vdev->ctx)
+		return -ENOMEM;
+
+	if (msix) {
+		int i;
+
+		vdev->msix = kzalloc(nvec * sizeof(struct msix_entry),
+				     GFP_KERNEL);
+		if (!vdev->msix) {
+			kfree(vdev->ctx);
+			return -ENOMEM;
+		}
+
+		for (i = 0; i < nvec; i++)
+			vdev->msix[i].entry = i;
+
+		ret = pci_enable_msix_range(pdev, vdev->msix, 1, nvec);
+		if (ret < nvec) {
+			if (ret > 0)
+				pci_disable_msix(pdev);
+			kfree(vdev->msix);
+			kfree(vdev->ctx);
+			return ret;
+		}
+	} else {
+		ret = pci_enable_msi_range(pdev, 1, nvec);
+		if (ret < nvec) {
+			if (ret > 0)
+				pci_disable_msi(pdev);
+			kfree(vdev->ctx);
+			return ret;
+		}
+	}
+
+	vdev->num_ctx = nvec;
+	vdev->irq_type = msix ? VFIO_PCI_MSIX_IRQ_INDEX :
+				VFIO_PCI_MSI_IRQ_INDEX;
+
+	if (!msix) {
+		/*
+		 * Compute the virtual hardware field for max msi vectors -
+		 * it is the log base 2 of the number of vectors.
+		 */
+		vdev->msi_qmax = fls(nvec * 2 - 1) - 1;
+	}
+
+	return 0;
+}
+
+static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,
+				      int vector, int fd, bool msix)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	int irq = msix ? vdev->msix[vector].vector : pdev->irq + vector;
+	char *name = msix ? "vfio-msix" : "vfio-msi";
+	struct eventfd_ctx *trigger;
+	int ret;
+
+	if (vector >= vdev->num_ctx)
+		return -EINVAL;
+
+	if (vdev->ctx[vector].trigger) {
+		free_irq(irq, vdev->ctx[vector].trigger);
+		kfree(vdev->ctx[vector].name);
+		eventfd_ctx_put(vdev->ctx[vector].trigger);
+		vdev->ctx[vector].trigger = NULL;
+	}
+
+	if (fd < 0)
+		return 0;
+
+	vdev->ctx[vector].name = kasprintf(GFP_KERNEL, "%s[%d](%s)",
+					   name, vector, pci_name(pdev));
+	if (!vdev->ctx[vector].name)
+		return -ENOMEM;
+
+	trigger = eventfd_ctx_fdget(fd);
+	if (IS_ERR(trigger)) {
+		kfree(vdev->ctx[vector].name);
+		return PTR_ERR(trigger);
+	}
+
+	/*
+	 * The MSIx vector table resides in device memory which may be cleared
+	 * via backdoor resets. We don't allow direct access to the vector
+	 * table so even if a userspace driver attempts to save/restore around
+	 * such a reset it would be unsuccessful. To avoid this, restore the
+	 * cached value of the message prior to enabling.
+	 */
+	if (msix) {
+		struct msi_msg msg;
+
+		get_cached_msi_msg(irq, &msg);
+		pci_write_msi_msg(irq, &msg);
+	}
+
+	ret = request_irq(irq, vfio_msihandler, 0,
+			  vdev->ctx[vector].name, trigger);
+	if (ret) {
+		kfree(vdev->ctx[vector].name);
+		eventfd_ctx_put(trigger);
+		return ret;
+	}
+
+	vdev->ctx[vector].trigger = trigger;
+
+	return 0;
+}
+
+static int vfio_msi_set_block(struct vfio_pci_device *vdev, unsigned start,
+			      unsigned count, int32_t *fds, bool msix)
+{
+	int i, j, ret = 0;
+
+	if (start + count > vdev->num_ctx)
+		return -EINVAL;
+
+	for (i = 0, j = start; i < count && !ret; i++, j++) {
+		int fd = fds ? fds[i] : -1;
+		ret = vfio_msi_set_vector_signal(vdev, j, fd, msix);
+	}
+
+	if (ret) {
+		for (--j; j >= start; j--)
+			vfio_msi_set_vector_signal(vdev, j, -1, msix);
+	}
+
+	return ret;
+}
+
+static void vfio_msi_disable(struct vfio_pci_device *vdev, bool msix)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	int i;
+
+	vfio_msi_set_block(vdev, 0, vdev->num_ctx, NULL, msix);
+
+	for (i = 0; i < vdev->num_ctx; i++) {
+		vfio_virqfd_disable(&vdev->ctx[i].unmask);
+		vfio_virqfd_disable(&vdev->ctx[i].mask);
+	}
+
+	if (msix) {
+		pci_disable_msix(vdev->pdev);
+		kfree(vdev->msix);
+	} else
+		pci_disable_msi(pdev);
+
+	vdev->irq_type = VFIO_PCI_NUM_IRQS;
+	vdev->num_ctx = 0;
+	kfree(vdev->ctx);
+}
+
+/*
+ * IOCTL support
+ */
+static int vfio_pci_set_intx_unmask(struct vfio_pci_device *vdev,
+				    unsigned index, unsigned start,
+				    unsigned count, uint32_t flags, void *data)
+{
+	if (!is_intx(vdev) || start != 0 || count != 1)
+		return -EINVAL;
+
+	if (flags & VFIO_IRQ_SET_DATA_NONE) {
+		vfio_pci_intx_unmask(vdev);
+	} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
+		uint8_t unmask = *(uint8_t *)data;
+		if (unmask)
+			vfio_pci_intx_unmask(vdev);
+	} else if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
+		int32_t fd = *(int32_t *)data;
+		if (fd >= 0)
+			return vfio_virqfd_enable((void *) vdev,
+						  vfio_pci_intx_unmask_handler,
+						  vfio_send_intx_eventfd, NULL,
+						  &vdev->ctx[0].unmask, fd);
+
+		vfio_virqfd_disable(&vdev->ctx[0].unmask);
+	}
+
+	return 0;
+}
+
+static int vfio_pci_set_intx_mask(struct vfio_pci_device *vdev,
+				  unsigned index, unsigned start,
+				  unsigned count, uint32_t flags, void *data)
+{
+	if (!is_intx(vdev) || start != 0 || count != 1)
+		return -EINVAL;
+
+	if (flags & VFIO_IRQ_SET_DATA_NONE) {
+		vfio_pci_intx_mask(vdev);
+	} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
+		uint8_t mask = *(uint8_t *)data;
+		if (mask)
+			vfio_pci_intx_mask(vdev);
+	} else if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
+		return -ENOTTY; /* XXX implement me */
+	}
+
+	return 0;
+}
+
+static int vfio_pci_set_intx_trigger(struct vfio_pci_device *vdev,
+				     unsigned index, unsigned start,
+				     unsigned count, uint32_t flags, void *data)
+{
+	if (is_intx(vdev) && !count && (flags & VFIO_IRQ_SET_DATA_NONE)) {
+		vfio_intx_disable(vdev);
+		return 0;
+	}
+
+	if (!(is_intx(vdev) || is_irq_none(vdev)) || start != 0 || count != 1)
+		return -EINVAL;
+
+	if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
+		int32_t fd = *(int32_t *)data;
+		int ret;
+
+		if (is_intx(vdev))
+			return vfio_intx_set_signal(vdev, fd);
+
+		ret = vfio_intx_enable(vdev);
+		if (ret)
+			return ret;
+
+		ret = vfio_intx_set_signal(vdev, fd);
+		if (ret)
+			vfio_intx_disable(vdev);
+
+		return ret;
+	}
+
+	if (!is_intx(vdev))
+		return -EINVAL;
+
+	if (flags & VFIO_IRQ_SET_DATA_NONE) {
+		vfio_send_intx_eventfd(vdev, NULL);
+	} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
+		uint8_t trigger = *(uint8_t *)data;
+		if (trigger)
+			vfio_send_intx_eventfd(vdev, NULL);
+	}
+	return 0;
+}
+
+static int vfio_pci_set_msi_trigger(struct vfio_pci_device *vdev,
+				    unsigned index, unsigned start,
+				    unsigned count, uint32_t flags, void *data)
+{
+	int i;
+	bool msix = (index == VFIO_PCI_MSIX_IRQ_INDEX) ? true : false;
+
+	if (irq_is(vdev, index) && !count && (flags & VFIO_IRQ_SET_DATA_NONE)) {
+		vfio_msi_disable(vdev, msix);
+		return 0;
+	}
+
+	if (!(irq_is(vdev, index) || is_irq_none(vdev)))
+		return -EINVAL;
+
+	if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
+		int32_t *fds = data;
+		int ret;
+
+		if (vdev->irq_type == index)
+			return vfio_msi_set_block(vdev, start, count,
+						  fds, msix);
+
+		ret = vfio_msi_enable(vdev, start + count, msix);
+		if (ret)
+			return ret;
+
+		ret = vfio_msi_set_block(vdev, start, count, fds, msix);
+		if (ret)
+			vfio_msi_disable(vdev, msix);
+
+		return ret;
+	}
+
+	if (!irq_is(vdev, index) || start + count > vdev->num_ctx)
+		return -EINVAL;
+
+	for (i = start; i < start + count; i++) {
+		if (!vdev->ctx[i].trigger)
+			continue;
+		if (flags & VFIO_IRQ_SET_DATA_NONE) {
+			eventfd_signal(vdev->ctx[i].trigger, 1);
+		} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
+			uint8_t *bools = data;
+			if (bools[i - start])
+				eventfd_signal(vdev->ctx[i].trigger, 1);
+		}
+	}
+	return 0;
+}
+
+static int vfio_pci_set_ctx_trigger_single(struct eventfd_ctx **ctx,
+					   uint32_t flags, void *data)
+{
+	int32_t fd = *(int32_t *)data;
+
+	if (!(flags & VFIO_IRQ_SET_DATA_TYPE_MASK))
+		return -EINVAL;
+
+	/* DATA_NONE/DATA_BOOL enables loopback testing */
+	if (flags & VFIO_IRQ_SET_DATA_NONE) {
+		if (*ctx)
+			eventfd_signal(*ctx, 1);
+		return 0;
+	} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
+		uint8_t trigger = *(uint8_t *)data;
+		if (trigger && *ctx)
+			eventfd_signal(*ctx, 1);
+		return 0;
+	}
+
+	/* Handle SET_DATA_EVENTFD */
+	if (fd == -1) {
+		if (*ctx)
+			eventfd_ctx_put(*ctx);
+		*ctx = NULL;
+		return 0;
+	} else if (fd >= 0) {
+		struct eventfd_ctx *efdctx;
+		efdctx = eventfd_ctx_fdget(fd);
+		if (IS_ERR(efdctx))
+			return PTR_ERR(efdctx);
+		if (*ctx)
+			eventfd_ctx_put(*ctx);
+		*ctx = efdctx;
+		return 0;
+	} else
+		return -EINVAL;
+}
+
+static int vfio_pci_set_err_trigger(struct vfio_pci_device *vdev,
+				    unsigned index, unsigned start,
+				    unsigned count, uint32_t flags, void *data)
+{
+	if (index != VFIO_PCI_ERR_IRQ_INDEX)
+		return -EINVAL;
+
+	/*
+	 * We should sanitize start & count, but that wasn't caught
+	 * originally, so this IRQ index must forever ignore them :-(
+	 */
+
+	return vfio_pci_set_ctx_trigger_single(&vdev->err_trigger, flags, data);
+}
+
+static int vfio_pci_set_req_trigger(struct vfio_pci_device *vdev,
+				    unsigned index, unsigned start,
+				    unsigned count, uint32_t flags, void *data)
+{
+	if (index != VFIO_PCI_REQ_IRQ_INDEX || start != 0 || count != 1)
+		return -EINVAL;
+
+	return vfio_pci_set_ctx_trigger_single(&vdev->req_trigger, flags, data);
+}
+
+int vfio_pci_set_irqs_ioctl(struct vfio_pci_device *vdev, uint32_t flags,
+			    unsigned index, unsigned start, unsigned count,
+			    void *data)
+{
+	int (*func)(struct vfio_pci_device *vdev, unsigned index,
+		    unsigned start, unsigned count, uint32_t flags,
+		    void *data) = NULL;
+
+	switch (index) {
+	case VFIO_PCI_INTX_IRQ_INDEX:
+		switch (flags & VFIO_IRQ_SET_ACTION_TYPE_MASK) {
+		case VFIO_IRQ_SET_ACTION_MASK:
+			func = vfio_pci_set_intx_mask;
+			break;
+		case VFIO_IRQ_SET_ACTION_UNMASK:
+			func = vfio_pci_set_intx_unmask;
+			break;
+		case VFIO_IRQ_SET_ACTION_TRIGGER:
+			func = vfio_pci_set_intx_trigger;
+			break;
+		}
+		break;
+	case VFIO_PCI_MSI_IRQ_INDEX:
+	case VFIO_PCI_MSIX_IRQ_INDEX:
+		switch (flags & VFIO_IRQ_SET_ACTION_TYPE_MASK) {
+		case VFIO_IRQ_SET_ACTION_MASK:
+		case VFIO_IRQ_SET_ACTION_UNMASK:
+			/* XXX Need masking support exported */
+			break;
+		case VFIO_IRQ_SET_ACTION_TRIGGER:
+			func = vfio_pci_set_msi_trigger;
+			break;
+		}
+		break;
+	case VFIO_PCI_ERR_IRQ_INDEX:
+		switch (flags & VFIO_IRQ_SET_ACTION_TYPE_MASK) {
+		case VFIO_IRQ_SET_ACTION_TRIGGER:
+			if (pci_is_pcie(vdev->pdev))
+				func = vfio_pci_set_err_trigger;
+			break;
+		}
+		break;
+	case VFIO_PCI_REQ_IRQ_INDEX:
+		switch (flags & VFIO_IRQ_SET_ACTION_TYPE_MASK) {
+		case VFIO_IRQ_SET_ACTION_TRIGGER:
+			func = vfio_pci_set_req_trigger;
+			break;
+		}
+		break;
+	}
+
+	if (!func)
+		return -ENOTTY;
+
+	return func(vdev, index, start, count, flags, data);
+}
diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h
new file mode 100644
index 000000000..ae0e1b4c1
--- /dev/null
+++ b/drivers/vfio/pci/vfio_pci_private.h
@@ -0,0 +1,92 @@
+/*
+ * Copyright (C) 2012 Red Hat, Inc.  All rights reserved.
+ *     Author: Alex Williamson <alex.williamson@redhat.com>
+ *
+ * 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.
+ *
+ * Derived from original vfio:
+ * Copyright 2010 Cisco Systems, Inc.  All rights reserved.
+ * Author: Tom Lyon, pugs@cisco.com
+ */
+
+#include <linux/mutex.h>
+#include <linux/pci.h>
+
+#ifndef VFIO_PCI_PRIVATE_H
+#define VFIO_PCI_PRIVATE_H
+
+#define VFIO_PCI_OFFSET_SHIFT   40
+
+#define VFIO_PCI_OFFSET_TO_INDEX(off)	(off >> VFIO_PCI_OFFSET_SHIFT)
+#define VFIO_PCI_INDEX_TO_OFFSET(index)	((u64)(index) << VFIO_PCI_OFFSET_SHIFT)
+#define VFIO_PCI_OFFSET_MASK	(((u64)(1) << VFIO_PCI_OFFSET_SHIFT) - 1)
+
+struct vfio_pci_irq_ctx {
+	struct eventfd_ctx	*trigger;
+	struct virqfd		*unmask;
+	struct virqfd		*mask;
+	char			*name;
+	bool			masked;
+};
+
+struct vfio_pci_device {
+	struct pci_dev		*pdev;
+	void __iomem		*barmap[PCI_STD_RESOURCE_END + 1];
+	u8			*pci_config_map;
+	u8			*vconfig;
+	struct perm_bits	*msi_perm;
+	spinlock_t		irqlock;
+	struct mutex		igate;
+	struct msix_entry	*msix;
+	struct vfio_pci_irq_ctx	*ctx;
+	int			num_ctx;
+	int			irq_type;
+	u8			msi_qmax;
+	u8			msix_bar;
+	u16			msix_size;
+	u32			msix_offset;
+	u32			rbar[7];
+	bool			pci_2_3;
+	bool			virq_disabled;
+	bool			reset_works;
+	bool			extended_caps;
+	bool			bardirty;
+	bool			has_vga;
+	bool			needs_reset;
+	struct pci_saved_state	*pci_saved_state;
+	int			refcnt;
+	struct eventfd_ctx	*err_trigger;
+	struct eventfd_ctx	*req_trigger;
+};
+
+#define is_intx(vdev) (vdev->irq_type == VFIO_PCI_INTX_IRQ_INDEX)
+#define is_msi(vdev) (vdev->irq_type == VFIO_PCI_MSI_IRQ_INDEX)
+#define is_msix(vdev) (vdev->irq_type == VFIO_PCI_MSIX_IRQ_INDEX)
+#define is_irq_none(vdev) (!(is_intx(vdev) || is_msi(vdev) || is_msix(vdev)))
+#define irq_is(vdev, type) (vdev->irq_type == type)
+
+extern void vfio_pci_intx_mask(struct vfio_pci_device *vdev);
+extern void vfio_pci_intx_unmask(struct vfio_pci_device *vdev);
+
+extern int vfio_pci_set_irqs_ioctl(struct vfio_pci_device *vdev,
+				   uint32_t flags, unsigned index,
+				   unsigned start, unsigned count, void *data);
+
+extern ssize_t vfio_pci_config_rw(struct vfio_pci_device *vdev,
+				  char __user *buf, size_t count,
+				  loff_t *ppos, bool iswrite);
+
+extern ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf,
+			       size_t count, loff_t *ppos, bool iswrite);
+
+extern ssize_t vfio_pci_vga_rw(struct vfio_pci_device *vdev, char __user *buf,
+			       size_t count, loff_t *ppos, bool iswrite);
+
+extern int vfio_pci_init_perm_bits(void);
+extern void vfio_pci_uninit_perm_bits(void);
+
+extern int vfio_config_init(struct vfio_pci_device *vdev);
+extern void vfio_config_free(struct vfio_pci_device *vdev);
+#endif /* VFIO_PCI_PRIVATE_H */
diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c
new file mode 100644
index 000000000..210db24d2
--- /dev/null
+++ b/drivers/vfio/pci/vfio_pci_rdwr.c
@@ -0,0 +1,238 @@
+/*
+ * VFIO PCI I/O Port & MMIO access
+ *
+ * Copyright (C) 2012 Red Hat, Inc.  All rights reserved.
+ *     Author: Alex Williamson <alex.williamson@redhat.com>
+ *
+ * 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.
+ *
+ * Derived from original vfio:
+ * Copyright 2010 Cisco Systems, Inc.  All rights reserved.
+ * Author: Tom Lyon, pugs@cisco.com
+ */
+
+#include <linux/fs.h>
+#include <linux/pci.h>
+#include <linux/uaccess.h>
+#include <linux/io.h>
+#include <linux/vgaarb.h>
+
+#include "vfio_pci_private.h"
+
+/*
+ * Read or write from an __iomem region (MMIO or I/O port) with an excluded
+ * range which is inaccessible.  The excluded range drops writes and fills
+ * reads with -1.  This is intended for handling MSI-X vector tables and
+ * leftover space for ROM BARs.
+ */
+static ssize_t do_io_rw(void __iomem *io, char __user *buf,
+			loff_t off, size_t count, size_t x_start,
+			size_t x_end, bool iswrite)
+{
+	ssize_t done = 0;
+
+	while (count) {
+		size_t fillable, filled;
+
+		if (off < x_start)
+			fillable = min(count, (size_t)(x_start - off));
+		else if (off >= x_end)
+			fillable = count;
+		else
+			fillable = 0;
+
+		if (fillable >= 4 && !(off % 4)) {
+			__le32 val;
+
+			if (iswrite) {
+				if (copy_from_user(&val, buf, 4))
+					return -EFAULT;
+
+				iowrite32(le32_to_cpu(val), io + off);
+			} else {
+				val = cpu_to_le32(ioread32(io + off));
+
+				if (copy_to_user(buf, &val, 4))
+					return -EFAULT;
+			}
+
+			filled = 4;
+		} else if (fillable >= 2 && !(off % 2)) {
+			__le16 val;
+
+			if (iswrite) {
+				if (copy_from_user(&val, buf, 2))
+					return -EFAULT;
+
+				iowrite16(le16_to_cpu(val), io + off);
+			} else {
+				val = cpu_to_le16(ioread16(io + off));
+
+				if (copy_to_user(buf, &val, 2))
+					return -EFAULT;
+			}
+
+			filled = 2;
+		} else if (fillable) {
+			u8 val;
+
+			if (iswrite) {
+				if (copy_from_user(&val, buf, 1))
+					return -EFAULT;
+
+				iowrite8(val, io + off);
+			} else {
+				val = ioread8(io + off);
+
+				if (copy_to_user(buf, &val, 1))
+					return -EFAULT;
+			}
+
+			filled = 1;
+		} else {
+			/* Fill reads with -1, drop writes */
+			filled = min(count, (size_t)(x_end - off));
+			if (!iswrite) {
+				u8 val = 0xFF;
+				size_t i;
+
+				for (i = 0; i < filled; i++)
+					if (copy_to_user(buf + i, &val, 1))
+						return -EFAULT;
+			}
+		}
+
+		count -= filled;
+		done += filled;
+		off += filled;
+		buf += filled;
+	}
+
+	return done;
+}
+
+ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf,
+			size_t count, loff_t *ppos, bool iswrite)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK;
+	int bar = VFIO_PCI_OFFSET_TO_INDEX(*ppos);
+	size_t x_start = 0, x_end = 0;
+	resource_size_t end;
+	void __iomem *io;
+	ssize_t done;
+
+	if (!pci_resource_start(pdev, bar))
+		return -EINVAL;
+
+	end = pci_resource_len(pdev, bar);
+
+	if (pos >= end)
+		return -EINVAL;
+
+	count = min(count, (size_t)(end - pos));
+
+	if (bar == PCI_ROM_RESOURCE) {
+		/*
+		 * The ROM can fill less space than the BAR, so we start the
+		 * excluded range at the end of the actual ROM.  This makes
+		 * filling large ROM BARs much faster.
+		 */
+		io = pci_map_rom(pdev, &x_start);
+		if (!io)
+			return -ENOMEM;
+		x_end = end;
+	} else if (!vdev->barmap[bar]) {
+		int ret;
+
+		ret = pci_request_selected_regions(pdev, 1 << bar, "vfio");
+		if (ret)
+			return ret;
+
+		io = pci_iomap(pdev, bar, 0);
+		if (!io) {
+			pci_release_selected_regions(pdev, 1 << bar);
+			return -ENOMEM;
+		}
+
+		vdev->barmap[bar] = io;
+	} else
+		io = vdev->barmap[bar];
+
+	if (bar == vdev->msix_bar) {
+		x_start = vdev->msix_offset;
+		x_end = vdev->msix_offset + vdev->msix_size;
+	}
+
+	done = do_io_rw(io, buf, pos, count, x_start, x_end, iswrite);
+
+	if (done >= 0)
+		*ppos += done;
+
+	if (bar == PCI_ROM_RESOURCE)
+		pci_unmap_rom(pdev, io);
+
+	return done;
+}
+
+ssize_t vfio_pci_vga_rw(struct vfio_pci_device *vdev, char __user *buf,
+			       size_t count, loff_t *ppos, bool iswrite)
+{
+	int ret;
+	loff_t off, pos = *ppos & VFIO_PCI_OFFSET_MASK;
+	void __iomem *iomem = NULL;
+	unsigned int rsrc;
+	bool is_ioport;
+	ssize_t done;
+
+	if (!vdev->has_vga)
+		return -EINVAL;
+
+	switch (pos) {
+	case 0xa0000 ... 0xbffff:
+		count = min(count, (size_t)(0xc0000 - pos));
+		iomem = ioremap_nocache(0xa0000, 0xbffff - 0xa0000 + 1);
+		off = pos - 0xa0000;
+		rsrc = VGA_RSRC_LEGACY_MEM;
+		is_ioport = false;
+		break;
+	case 0x3b0 ... 0x3bb:
+		count = min(count, (size_t)(0x3bc - pos));
+		iomem = ioport_map(0x3b0, 0x3bb - 0x3b0 + 1);
+		off = pos - 0x3b0;
+		rsrc = VGA_RSRC_LEGACY_IO;
+		is_ioport = true;
+		break;
+	case 0x3c0 ... 0x3df:
+		count = min(count, (size_t)(0x3e0 - pos));
+		iomem = ioport_map(0x3c0, 0x3df - 0x3c0 + 1);
+		off = pos - 0x3c0;
+		rsrc = VGA_RSRC_LEGACY_IO;
+		is_ioport = true;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (!iomem)
+		return -ENOMEM;
+
+	ret = vga_get_interruptible(vdev->pdev, rsrc);
+	if (ret) {
+		is_ioport ? ioport_unmap(iomem) : iounmap(iomem);
+		return ret;
+	}
+
+	done = do_io_rw(iomem, buf, off, count, 0, 0, iswrite);
+
+	vga_put(vdev->pdev, rsrc);
+
+	is_ioport ? ioport_unmap(iomem) : iounmap(iomem);
+
+	if (done >= 0)
+		*ppos += done;
+
+	return done;
+}
diff --git a/drivers/vfio/platform/Kconfig b/drivers/vfio/platform/Kconfig
new file mode 100644
index 000000000..9a4403e2a
--- /dev/null
+++ b/drivers/vfio/platform/Kconfig
@@ -0,0 +1,20 @@
+config VFIO_PLATFORM
+	tristate "VFIO support for platform devices"
+	depends on VFIO && EVENTFD && ARM
+	select VFIO_VIRQFD
+	help
+	  Support for platform devices with VFIO. This is required to make
+	  use of platform devices present on the system using the VFIO
+	  framework.
+
+	  If you don't know what to do here, say N.
+
+config VFIO_AMBA
+	tristate "VFIO support for AMBA devices"
+	depends on VFIO_PLATFORM && ARM_AMBA
+	help
+	  Support for ARM AMBA devices with VFIO. This is required to make
+	  use of ARM AMBA devices present on the system using the VFIO
+	  framework.
+
+	  If you don't know what to do here, say N.
diff --git a/drivers/vfio/platform/Makefile b/drivers/vfio/platform/Makefile
new file mode 100644
index 000000000..81de144c0
--- /dev/null
+++ b/drivers/vfio/platform/Makefile
@@ -0,0 +1,8 @@
+
+vfio-platform-y := vfio_platform.o vfio_platform_common.o vfio_platform_irq.o
+
+obj-$(CONFIG_VFIO_PLATFORM) += vfio-platform.o
+
+vfio-amba-y := vfio_amba.o
+
+obj-$(CONFIG_VFIO_AMBA) += vfio-amba.o
diff --git a/drivers/vfio/platform/vfio_amba.c b/drivers/vfio/platform/vfio_amba.c
new file mode 100644
index 000000000..ff0331f72
--- /dev/null
+++ b/drivers/vfio/platform/vfio_amba.c
@@ -0,0 +1,115 @@
+/*
+ * Copyright (C) 2013 - Virtual Open Systems
+ * Author: Antonios Motakis <a.motakis@virtualopensystems.com>
+ *
+ * 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.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/vfio.h>
+#include <linux/amba/bus.h>
+
+#include "vfio_platform_private.h"
+
+#define DRIVER_VERSION  "0.10"
+#define DRIVER_AUTHOR   "Antonios Motakis <a.motakis@virtualopensystems.com>"
+#define DRIVER_DESC     "VFIO for AMBA devices - User Level meta-driver"
+
+/* probing devices from the AMBA bus */
+
+static struct resource *get_amba_resource(struct vfio_platform_device *vdev,
+					  int i)
+{
+	struct amba_device *adev = (struct amba_device *) vdev->opaque;
+
+	if (i == 0)
+		return &adev->res;
+
+	return NULL;
+}
+
+static int get_amba_irq(struct vfio_platform_device *vdev, int i)
+{
+	struct amba_device *adev = (struct amba_device *) vdev->opaque;
+	int ret = 0;
+
+	if (i < AMBA_NR_IRQS)
+		ret = adev->irq[i];
+
+	/* zero is an unset IRQ for AMBA devices */
+	return ret ? ret : -ENXIO;
+}
+
+static int vfio_amba_probe(struct amba_device *adev, const struct amba_id *id)
+{
+	struct vfio_platform_device *vdev;
+	int ret;
+
+	vdev = kzalloc(sizeof(*vdev), GFP_KERNEL);
+	if (!vdev)
+		return -ENOMEM;
+
+	vdev->name = kasprintf(GFP_KERNEL, "vfio-amba-%08x", adev->periphid);
+	if (!vdev->name) {
+		kfree(vdev);
+		return -ENOMEM;
+	}
+
+	vdev->opaque = (void *) adev;
+	vdev->flags = VFIO_DEVICE_FLAGS_AMBA;
+	vdev->get_resource = get_amba_resource;
+	vdev->get_irq = get_amba_irq;
+
+	ret = vfio_platform_probe_common(vdev, &adev->dev);
+	if (ret) {
+		kfree(vdev->name);
+		kfree(vdev);
+	}
+
+	return ret;
+}
+
+static int vfio_amba_remove(struct amba_device *adev)
+{
+	struct vfio_platform_device *vdev;
+
+	vdev = vfio_platform_remove_common(&adev->dev);
+	if (vdev) {
+		kfree(vdev->name);
+		kfree(vdev);
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static struct amba_id pl330_ids[] = {
+	{ 0, 0 },
+};
+
+MODULE_DEVICE_TABLE(amba, pl330_ids);
+
+static struct amba_driver vfio_amba_driver = {
+	.probe = vfio_amba_probe,
+	.remove = vfio_amba_remove,
+	.id_table = pl330_ids,
+	.drv = {
+		.name = "vfio-amba",
+		.owner = THIS_MODULE,
+	},
+};
+
+module_amba_driver(vfio_amba_driver);
+
+MODULE_VERSION(DRIVER_VERSION);
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
diff --git a/drivers/vfio/platform/vfio_platform.c b/drivers/vfio/platform/vfio_platform.c
new file mode 100644
index 000000000..cef645c83
--- /dev/null
+++ b/drivers/vfio/platform/vfio_platform.c
@@ -0,0 +1,103 @@
+/*
+ * Copyright (C) 2013 - Virtual Open Systems
+ * Author: Antonios Motakis <a.motakis@virtualopensystems.com>
+ *
+ * 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.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/vfio.h>
+#include <linux/platform_device.h>
+
+#include "vfio_platform_private.h"
+
+#define DRIVER_VERSION  "0.10"
+#define DRIVER_AUTHOR   "Antonios Motakis <a.motakis@virtualopensystems.com>"
+#define DRIVER_DESC     "VFIO for platform devices - User Level meta-driver"
+
+/* probing devices from the linux platform bus */
+
+static struct resource *get_platform_resource(struct vfio_platform_device *vdev,
+					      int num)
+{
+	struct platform_device *dev = (struct platform_device *) vdev->opaque;
+	int i;
+
+	for (i = 0; i < dev->num_resources; i++) {
+		struct resource *r = &dev->resource[i];
+
+		if (resource_type(r) & (IORESOURCE_MEM|IORESOURCE_IO)) {
+			if (!num)
+				return r;
+
+			num--;
+		}
+	}
+	return NULL;
+}
+
+static int get_platform_irq(struct vfio_platform_device *vdev, int i)
+{
+	struct platform_device *pdev = (struct platform_device *) vdev->opaque;
+
+	return platform_get_irq(pdev, i);
+}
+
+static int vfio_platform_probe(struct platform_device *pdev)
+{
+	struct vfio_platform_device *vdev;
+	int ret;
+
+	vdev = kzalloc(sizeof(*vdev), GFP_KERNEL);
+	if (!vdev)
+		return -ENOMEM;
+
+	vdev->opaque = (void *) pdev;
+	vdev->name = pdev->name;
+	vdev->flags = VFIO_DEVICE_FLAGS_PLATFORM;
+	vdev->get_resource = get_platform_resource;
+	vdev->get_irq = get_platform_irq;
+
+	ret = vfio_platform_probe_common(vdev, &pdev->dev);
+	if (ret)
+		kfree(vdev);
+
+	return ret;
+}
+
+static int vfio_platform_remove(struct platform_device *pdev)
+{
+	struct vfio_platform_device *vdev;
+
+	vdev = vfio_platform_remove_common(&pdev->dev);
+	if (vdev) {
+		kfree(vdev);
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static struct platform_driver vfio_platform_driver = {
+	.probe		= vfio_platform_probe,
+	.remove		= vfio_platform_remove,
+	.driver	= {
+		.name	= "vfio-platform",
+		.owner	= THIS_MODULE,
+	},
+};
+
+module_platform_driver(vfio_platform_driver);
+
+MODULE_VERSION(DRIVER_VERSION);
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
diff --git a/drivers/vfio/platform/vfio_platform_common.c b/drivers/vfio/platform/vfio_platform_common.c
new file mode 100644
index 000000000..abcff7a1a
--- /dev/null
+++ b/drivers/vfio/platform/vfio_platform_common.c
@@ -0,0 +1,521 @@
+/*
+ * Copyright (C) 2013 - Virtual Open Systems
+ * Author: Antonios Motakis <a.motakis@virtualopensystems.com>
+ *
+ * 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.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/device.h>
+#include <linux/iommu.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <linux/vfio.h>
+
+#include "vfio_platform_private.h"
+
+static DEFINE_MUTEX(driver_lock);
+
+static int vfio_platform_regions_init(struct vfio_platform_device *vdev)
+{
+	int cnt = 0, i;
+
+	while (vdev->get_resource(vdev, cnt))
+		cnt++;
+
+	vdev->regions = kcalloc(cnt, sizeof(struct vfio_platform_region),
+				GFP_KERNEL);
+	if (!vdev->regions)
+		return -ENOMEM;
+
+	for (i = 0; i < cnt;  i++) {
+		struct resource *res =
+			vdev->get_resource(vdev, i);
+
+		if (!res)
+			goto err;
+
+		vdev->regions[i].addr = res->start;
+		vdev->regions[i].size = resource_size(res);
+		vdev->regions[i].flags = 0;
+
+		switch (resource_type(res)) {
+		case IORESOURCE_MEM:
+			vdev->regions[i].type = VFIO_PLATFORM_REGION_TYPE_MMIO;
+			vdev->regions[i].flags |= VFIO_REGION_INFO_FLAG_READ;
+			if (!(res->flags & IORESOURCE_READONLY))
+				vdev->regions[i].flags |=
+					VFIO_REGION_INFO_FLAG_WRITE;
+
+			/*
+			 * Only regions addressed with PAGE granularity may be
+			 * MMAPed securely.
+			 */
+			if (!(vdev->regions[i].addr & ~PAGE_MASK) &&
+					!(vdev->regions[i].size & ~PAGE_MASK))
+				vdev->regions[i].flags |=
+					VFIO_REGION_INFO_FLAG_MMAP;
+
+			break;
+		case IORESOURCE_IO:
+			vdev->regions[i].type = VFIO_PLATFORM_REGION_TYPE_PIO;
+			break;
+		default:
+			goto err;
+		}
+	}
+
+	vdev->num_regions = cnt;
+
+	return 0;
+err:
+	kfree(vdev->regions);
+	return -EINVAL;
+}
+
+static void vfio_platform_regions_cleanup(struct vfio_platform_device *vdev)
+{
+	int i;
+
+	for (i = 0; i < vdev->num_regions; i++)
+		iounmap(vdev->regions[i].ioaddr);
+
+	vdev->num_regions = 0;
+	kfree(vdev->regions);
+}
+
+static void vfio_platform_release(void *device_data)
+{
+	struct vfio_platform_device *vdev = device_data;
+
+	mutex_lock(&driver_lock);
+
+	if (!(--vdev->refcnt)) {
+		vfio_platform_regions_cleanup(vdev);
+		vfio_platform_irq_cleanup(vdev);
+	}
+
+	mutex_unlock(&driver_lock);
+
+	module_put(THIS_MODULE);
+}
+
+static int vfio_platform_open(void *device_data)
+{
+	struct vfio_platform_device *vdev = device_data;
+	int ret;
+
+	if (!try_module_get(THIS_MODULE))
+		return -ENODEV;
+
+	mutex_lock(&driver_lock);
+
+	if (!vdev->refcnt) {
+		ret = vfio_platform_regions_init(vdev);
+		if (ret)
+			goto err_reg;
+
+		ret = vfio_platform_irq_init(vdev);
+		if (ret)
+			goto err_irq;
+	}
+
+	vdev->refcnt++;
+
+	mutex_unlock(&driver_lock);
+	return 0;
+
+err_irq:
+	vfio_platform_regions_cleanup(vdev);
+err_reg:
+	mutex_unlock(&driver_lock);
+	module_put(THIS_MODULE);
+	return ret;
+}
+
+static long vfio_platform_ioctl(void *device_data,
+				unsigned int cmd, unsigned long arg)
+{
+	struct vfio_platform_device *vdev = device_data;
+	unsigned long minsz;
+
+	if (cmd == VFIO_DEVICE_GET_INFO) {
+		struct vfio_device_info info;
+
+		minsz = offsetofend(struct vfio_device_info, num_irqs);
+
+		if (copy_from_user(&info, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (info.argsz < minsz)
+			return -EINVAL;
+
+		info.flags = vdev->flags;
+		info.num_regions = vdev->num_regions;
+		info.num_irqs = vdev->num_irqs;
+
+		return copy_to_user((void __user *)arg, &info, minsz);
+
+	} else if (cmd == VFIO_DEVICE_GET_REGION_INFO) {
+		struct vfio_region_info info;
+
+		minsz = offsetofend(struct vfio_region_info, offset);
+
+		if (copy_from_user(&info, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (info.argsz < minsz)
+			return -EINVAL;
+
+		if (info.index >= vdev->num_regions)
+			return -EINVAL;
+
+		/* map offset to the physical address  */
+		info.offset = VFIO_PLATFORM_INDEX_TO_OFFSET(info.index);
+		info.size = vdev->regions[info.index].size;
+		info.flags = vdev->regions[info.index].flags;
+
+		return copy_to_user((void __user *)arg, &info, minsz);
+
+	} else if (cmd == VFIO_DEVICE_GET_IRQ_INFO) {
+		struct vfio_irq_info info;
+
+		minsz = offsetofend(struct vfio_irq_info, count);
+
+		if (copy_from_user(&info, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (info.argsz < minsz)
+			return -EINVAL;
+
+		if (info.index >= vdev->num_irqs)
+			return -EINVAL;
+
+		info.flags = vdev->irqs[info.index].flags;
+		info.count = vdev->irqs[info.index].count;
+
+		return copy_to_user((void __user *)arg, &info, minsz);
+
+	} else if (cmd == VFIO_DEVICE_SET_IRQS) {
+		struct vfio_irq_set hdr;
+		u8 *data = NULL;
+		int ret = 0;
+
+		minsz = offsetofend(struct vfio_irq_set, count);
+
+		if (copy_from_user(&hdr, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (hdr.argsz < minsz)
+			return -EINVAL;
+
+		if (hdr.index >= vdev->num_irqs)
+			return -EINVAL;
+
+		if (hdr.flags & ~(VFIO_IRQ_SET_DATA_TYPE_MASK |
+				  VFIO_IRQ_SET_ACTION_TYPE_MASK))
+			return -EINVAL;
+
+		if (!(hdr.flags & VFIO_IRQ_SET_DATA_NONE)) {
+			size_t size;
+
+			if (hdr.flags & VFIO_IRQ_SET_DATA_BOOL)
+				size = sizeof(uint8_t);
+			else if (hdr.flags & VFIO_IRQ_SET_DATA_EVENTFD)
+				size = sizeof(int32_t);
+			else
+				return -EINVAL;
+
+			if (hdr.argsz - minsz < size)
+				return -EINVAL;
+
+			data = memdup_user((void __user *)(arg + minsz), size);
+			if (IS_ERR(data))
+				return PTR_ERR(data);
+		}
+
+		mutex_lock(&vdev->igate);
+
+		ret = vfio_platform_set_irqs_ioctl(vdev, hdr.flags, hdr.index,
+						   hdr.start, hdr.count, data);
+		mutex_unlock(&vdev->igate);
+		kfree(data);
+
+		return ret;
+
+	} else if (cmd == VFIO_DEVICE_RESET)
+		return -EINVAL;
+
+	return -ENOTTY;
+}
+
+static ssize_t vfio_platform_read_mmio(struct vfio_platform_region reg,
+				       char __user *buf, size_t count,
+				       loff_t off)
+{
+	unsigned int done = 0;
+
+	if (!reg.ioaddr) {
+		reg.ioaddr =
+			ioremap_nocache(reg.addr, reg.size);
+
+		if (!reg.ioaddr)
+			return -ENOMEM;
+	}
+
+	while (count) {
+		size_t filled;
+
+		if (count >= 4 && !(off % 4)) {
+			u32 val;
+
+			val = ioread32(reg.ioaddr + off);
+			if (copy_to_user(buf, &val, 4))
+				goto err;
+
+			filled = 4;
+		} else if (count >= 2 && !(off % 2)) {
+			u16 val;
+
+			val = ioread16(reg.ioaddr + off);
+			if (copy_to_user(buf, &val, 2))
+				goto err;
+
+			filled = 2;
+		} else {
+			u8 val;
+
+			val = ioread8(reg.ioaddr + off);
+			if (copy_to_user(buf, &val, 1))
+				goto err;
+
+			filled = 1;
+		}
+
+
+		count -= filled;
+		done += filled;
+		off += filled;
+		buf += filled;
+	}
+
+	return done;
+err:
+	return -EFAULT;
+}
+
+static ssize_t vfio_platform_read(void *device_data, char __user *buf,
+				  size_t count, loff_t *ppos)
+{
+	struct vfio_platform_device *vdev = device_data;
+	unsigned int index = VFIO_PLATFORM_OFFSET_TO_INDEX(*ppos);
+	loff_t off = *ppos & VFIO_PLATFORM_OFFSET_MASK;
+
+	if (index >= vdev->num_regions)
+		return -EINVAL;
+
+	if (!(vdev->regions[index].flags & VFIO_REGION_INFO_FLAG_READ))
+		return -EINVAL;
+
+	if (vdev->regions[index].type & VFIO_PLATFORM_REGION_TYPE_MMIO)
+		return vfio_platform_read_mmio(vdev->regions[index],
+							buf, count, off);
+	else if (vdev->regions[index].type & VFIO_PLATFORM_REGION_TYPE_PIO)
+		return -EINVAL; /* not implemented */
+
+	return -EINVAL;
+}
+
+static ssize_t vfio_platform_write_mmio(struct vfio_platform_region reg,
+					const char __user *buf, size_t count,
+					loff_t off)
+{
+	unsigned int done = 0;
+
+	if (!reg.ioaddr) {
+		reg.ioaddr =
+			ioremap_nocache(reg.addr, reg.size);
+
+		if (!reg.ioaddr)
+			return -ENOMEM;
+	}
+
+	while (count) {
+		size_t filled;
+
+		if (count >= 4 && !(off % 4)) {
+			u32 val;
+
+			if (copy_from_user(&val, buf, 4))
+				goto err;
+			iowrite32(val, reg.ioaddr + off);
+
+			filled = 4;
+		} else if (count >= 2 && !(off % 2)) {
+			u16 val;
+
+			if (copy_from_user(&val, buf, 2))
+				goto err;
+			iowrite16(val, reg.ioaddr + off);
+
+			filled = 2;
+		} else {
+			u8 val;
+
+			if (copy_from_user(&val, buf, 1))
+				goto err;
+			iowrite8(val, reg.ioaddr + off);
+
+			filled = 1;
+		}
+
+		count -= filled;
+		done += filled;
+		off += filled;
+		buf += filled;
+	}
+
+	return done;
+err:
+	return -EFAULT;
+}
+
+static ssize_t vfio_platform_write(void *device_data, const char __user *buf,
+				   size_t count, loff_t *ppos)
+{
+	struct vfio_platform_device *vdev = device_data;
+	unsigned int index = VFIO_PLATFORM_OFFSET_TO_INDEX(*ppos);
+	loff_t off = *ppos & VFIO_PLATFORM_OFFSET_MASK;
+
+	if (index >= vdev->num_regions)
+		return -EINVAL;
+
+	if (!(vdev->regions[index].flags & VFIO_REGION_INFO_FLAG_WRITE))
+		return -EINVAL;
+
+	if (vdev->regions[index].type & VFIO_PLATFORM_REGION_TYPE_MMIO)
+		return vfio_platform_write_mmio(vdev->regions[index],
+							buf, count, off);
+	else if (vdev->regions[index].type & VFIO_PLATFORM_REGION_TYPE_PIO)
+		return -EINVAL; /* not implemented */
+
+	return -EINVAL;
+}
+
+static int vfio_platform_mmap_mmio(struct vfio_platform_region region,
+				   struct vm_area_struct *vma)
+{
+	u64 req_len, pgoff, req_start;
+
+	req_len = vma->vm_end - vma->vm_start;
+	pgoff = vma->vm_pgoff &
+		((1U << (VFIO_PLATFORM_OFFSET_SHIFT - PAGE_SHIFT)) - 1);
+	req_start = pgoff << PAGE_SHIFT;
+
+	if (region.size < PAGE_SIZE || req_start + req_len > region.size)
+		return -EINVAL;
+
+	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+	vma->vm_pgoff = (region.addr >> PAGE_SHIFT) + pgoff;
+
+	return remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
+			       req_len, vma->vm_page_prot);
+}
+
+static int vfio_platform_mmap(void *device_data, struct vm_area_struct *vma)
+{
+	struct vfio_platform_device *vdev = device_data;
+	unsigned int index;
+
+	index = vma->vm_pgoff >> (VFIO_PLATFORM_OFFSET_SHIFT - PAGE_SHIFT);
+
+	if (vma->vm_end < vma->vm_start)
+		return -EINVAL;
+	if (!(vma->vm_flags & VM_SHARED))
+		return -EINVAL;
+	if (index >= vdev->num_regions)
+		return -EINVAL;
+	if (vma->vm_start & ~PAGE_MASK)
+		return -EINVAL;
+	if (vma->vm_end & ~PAGE_MASK)
+		return -EINVAL;
+
+	if (!(vdev->regions[index].flags & VFIO_REGION_INFO_FLAG_MMAP))
+		return -EINVAL;
+
+	if (!(vdev->regions[index].flags & VFIO_REGION_INFO_FLAG_READ)
+			&& (vma->vm_flags & VM_READ))
+		return -EINVAL;
+
+	if (!(vdev->regions[index].flags & VFIO_REGION_INFO_FLAG_WRITE)
+			&& (vma->vm_flags & VM_WRITE))
+		return -EINVAL;
+
+	vma->vm_private_data = vdev;
+
+	if (vdev->regions[index].type & VFIO_PLATFORM_REGION_TYPE_MMIO)
+		return vfio_platform_mmap_mmio(vdev->regions[index], vma);
+
+	else if (vdev->regions[index].type & VFIO_PLATFORM_REGION_TYPE_PIO)
+		return -EINVAL; /* not implemented */
+
+	return -EINVAL;
+}
+
+static const struct vfio_device_ops vfio_platform_ops = {
+	.name		= "vfio-platform",
+	.open		= vfio_platform_open,
+	.release	= vfio_platform_release,
+	.ioctl		= vfio_platform_ioctl,
+	.read		= vfio_platform_read,
+	.write		= vfio_platform_write,
+	.mmap		= vfio_platform_mmap,
+};
+
+int vfio_platform_probe_common(struct vfio_platform_device *vdev,
+			       struct device *dev)
+{
+	struct iommu_group *group;
+	int ret;
+
+	if (!vdev)
+		return -EINVAL;
+
+	group = iommu_group_get(dev);
+	if (!group) {
+		pr_err("VFIO: No IOMMU group for device %s\n", vdev->name);
+		return -EINVAL;
+	}
+
+	ret = vfio_add_group_dev(dev, &vfio_platform_ops, vdev);
+	if (ret) {
+		iommu_group_put(group);
+		return ret;
+	}
+
+	mutex_init(&vdev->igate);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(vfio_platform_probe_common);
+
+struct vfio_platform_device *vfio_platform_remove_common(struct device *dev)
+{
+	struct vfio_platform_device *vdev;
+
+	vdev = vfio_del_group_dev(dev);
+	if (vdev)
+		iommu_group_put(dev->iommu_group);
+
+	return vdev;
+}
+EXPORT_SYMBOL_GPL(vfio_platform_remove_common);
diff --git a/drivers/vfio/platform/vfio_platform_irq.c b/drivers/vfio/platform/vfio_platform_irq.c
new file mode 100644
index 000000000..88bba57b3
--- /dev/null
+++ b/drivers/vfio/platform/vfio_platform_irq.c
@@ -0,0 +1,336 @@
+/*
+ * VFIO platform devices interrupt handling
+ *
+ * Copyright (C) 2013 - Virtual Open Systems
+ * Author: Antonios Motakis <a.motakis@virtualopensystems.com>
+ *
+ * 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.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/eventfd.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/vfio.h>
+#include <linux/irq.h>
+
+#include "vfio_platform_private.h"
+
+static void vfio_platform_mask(struct vfio_platform_irq *irq_ctx)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&irq_ctx->lock, flags);
+
+	if (!irq_ctx->masked) {
+		disable_irq_nosync(irq_ctx->hwirq);
+		irq_ctx->masked = true;
+	}
+
+	spin_unlock_irqrestore(&irq_ctx->lock, flags);
+}
+
+static int vfio_platform_mask_handler(void *opaque, void *unused)
+{
+	struct vfio_platform_irq *irq_ctx = opaque;
+
+	vfio_platform_mask(irq_ctx);
+
+	return 0;
+}
+
+static int vfio_platform_set_irq_mask(struct vfio_platform_device *vdev,
+				      unsigned index, unsigned start,
+				      unsigned count, uint32_t flags,
+				      void *data)
+{
+	if (start != 0 || count != 1)
+		return -EINVAL;
+
+	if (!(vdev->irqs[index].flags & VFIO_IRQ_INFO_MASKABLE))
+		return -EINVAL;
+
+	if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
+		int32_t fd = *(int32_t *)data;
+
+		if (fd >= 0)
+			return vfio_virqfd_enable((void *) &vdev->irqs[index],
+						  vfio_platform_mask_handler,
+						  NULL, NULL,
+						  &vdev->irqs[index].mask, fd);
+
+		vfio_virqfd_disable(&vdev->irqs[index].mask);
+		return 0;
+	}
+
+	if (flags & VFIO_IRQ_SET_DATA_NONE) {
+		vfio_platform_mask(&vdev->irqs[index]);
+
+	} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
+		uint8_t mask = *(uint8_t *)data;
+
+		if (mask)
+			vfio_platform_mask(&vdev->irqs[index]);
+	}
+
+	return 0;
+}
+
+static void vfio_platform_unmask(struct vfio_platform_irq *irq_ctx)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&irq_ctx->lock, flags);
+
+	if (irq_ctx->masked) {
+		enable_irq(irq_ctx->hwirq);
+		irq_ctx->masked = false;
+	}
+
+	spin_unlock_irqrestore(&irq_ctx->lock, flags);
+}
+
+static int vfio_platform_unmask_handler(void *opaque, void *unused)
+{
+	struct vfio_platform_irq *irq_ctx = opaque;
+
+	vfio_platform_unmask(irq_ctx);
+
+	return 0;
+}
+
+static int vfio_platform_set_irq_unmask(struct vfio_platform_device *vdev,
+					unsigned index, unsigned start,
+					unsigned count, uint32_t flags,
+					void *data)
+{
+	if (start != 0 || count != 1)
+		return -EINVAL;
+
+	if (!(vdev->irqs[index].flags & VFIO_IRQ_INFO_MASKABLE))
+		return -EINVAL;
+
+	if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
+		int32_t fd = *(int32_t *)data;
+
+		if (fd >= 0)
+			return vfio_virqfd_enable((void *) &vdev->irqs[index],
+						  vfio_platform_unmask_handler,
+						  NULL, NULL,
+						  &vdev->irqs[index].unmask,
+						  fd);
+
+		vfio_virqfd_disable(&vdev->irqs[index].unmask);
+		return 0;
+	}
+
+	if (flags & VFIO_IRQ_SET_DATA_NONE) {
+		vfio_platform_unmask(&vdev->irqs[index]);
+
+	} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
+		uint8_t unmask = *(uint8_t *)data;
+
+		if (unmask)
+			vfio_platform_unmask(&vdev->irqs[index]);
+	}
+
+	return 0;
+}
+
+static irqreturn_t vfio_automasked_irq_handler(int irq, void *dev_id)
+{
+	struct vfio_platform_irq *irq_ctx = dev_id;
+	unsigned long flags;
+	int ret = IRQ_NONE;
+
+	spin_lock_irqsave(&irq_ctx->lock, flags);
+
+	if (!irq_ctx->masked) {
+		ret = IRQ_HANDLED;
+
+		/* automask maskable interrupts */
+		disable_irq_nosync(irq_ctx->hwirq);
+		irq_ctx->masked = true;
+	}
+
+	spin_unlock_irqrestore(&irq_ctx->lock, flags);
+
+	if (ret == IRQ_HANDLED)
+		eventfd_signal(irq_ctx->trigger, 1);
+
+	return ret;
+}
+
+static irqreturn_t vfio_irq_handler(int irq, void *dev_id)
+{
+	struct vfio_platform_irq *irq_ctx = dev_id;
+
+	eventfd_signal(irq_ctx->trigger, 1);
+
+	return IRQ_HANDLED;
+}
+
+static int vfio_set_trigger(struct vfio_platform_device *vdev, int index,
+			    int fd, irq_handler_t handler)
+{
+	struct vfio_platform_irq *irq = &vdev->irqs[index];
+	struct eventfd_ctx *trigger;
+	int ret;
+
+	if (irq->trigger) {
+		free_irq(irq->hwirq, irq);
+		kfree(irq->name);
+		eventfd_ctx_put(irq->trigger);
+		irq->trigger = NULL;
+	}
+
+	if (fd < 0) /* Disable only */
+		return 0;
+
+	irq->name = kasprintf(GFP_KERNEL, "vfio-irq[%d](%s)",
+						irq->hwirq, vdev->name);
+	if (!irq->name)
+		return -ENOMEM;
+
+	trigger = eventfd_ctx_fdget(fd);
+	if (IS_ERR(trigger)) {
+		kfree(irq->name);
+		return PTR_ERR(trigger);
+	}
+
+	irq->trigger = trigger;
+
+	irq_set_status_flags(irq->hwirq, IRQ_NOAUTOEN);
+	ret = request_irq(irq->hwirq, handler, 0, irq->name, irq);
+	if (ret) {
+		kfree(irq->name);
+		eventfd_ctx_put(trigger);
+		irq->trigger = NULL;
+		return ret;
+	}
+
+	if (!irq->masked)
+		enable_irq(irq->hwirq);
+
+	return 0;
+}
+
+static int vfio_platform_set_irq_trigger(struct vfio_platform_device *vdev,
+					 unsigned index, unsigned start,
+					 unsigned count, uint32_t flags,
+					 void *data)
+{
+	struct vfio_platform_irq *irq = &vdev->irqs[index];
+	irq_handler_t handler;
+
+	if (vdev->irqs[index].flags & VFIO_IRQ_INFO_AUTOMASKED)
+		handler = vfio_automasked_irq_handler;
+	else
+		handler = vfio_irq_handler;
+
+	if (!count && (flags & VFIO_IRQ_SET_DATA_NONE))
+		return vfio_set_trigger(vdev, index, -1, handler);
+
+	if (start != 0 || count != 1)
+		return -EINVAL;
+
+	if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
+		int32_t fd = *(int32_t *)data;
+
+		return vfio_set_trigger(vdev, index, fd, handler);
+	}
+
+	if (flags & VFIO_IRQ_SET_DATA_NONE) {
+		handler(irq->hwirq, irq);
+
+	} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
+		uint8_t trigger = *(uint8_t *)data;
+
+		if (trigger)
+			handler(irq->hwirq, irq);
+	}
+
+	return 0;
+}
+
+int vfio_platform_set_irqs_ioctl(struct vfio_platform_device *vdev,
+				 uint32_t flags, unsigned index, unsigned start,
+				 unsigned count, void *data)
+{
+	int (*func)(struct vfio_platform_device *vdev, unsigned index,
+		    unsigned start, unsigned count, uint32_t flags,
+		    void *data) = NULL;
+
+	switch (flags & VFIO_IRQ_SET_ACTION_TYPE_MASK) {
+	case VFIO_IRQ_SET_ACTION_MASK:
+		func = vfio_platform_set_irq_mask;
+		break;
+	case VFIO_IRQ_SET_ACTION_UNMASK:
+		func = vfio_platform_set_irq_unmask;
+		break;
+	case VFIO_IRQ_SET_ACTION_TRIGGER:
+		func = vfio_platform_set_irq_trigger;
+		break;
+	}
+
+	if (!func)
+		return -ENOTTY;
+
+	return func(vdev, index, start, count, flags, data);
+}
+
+int vfio_platform_irq_init(struct vfio_platform_device *vdev)
+{
+	int cnt = 0, i;
+
+	while (vdev->get_irq(vdev, cnt) >= 0)
+		cnt++;
+
+	vdev->irqs = kcalloc(cnt, sizeof(struct vfio_platform_irq), GFP_KERNEL);
+	if (!vdev->irqs)
+		return -ENOMEM;
+
+	for (i = 0; i < cnt; i++) {
+		int hwirq = vdev->get_irq(vdev, i);
+
+		if (hwirq < 0)
+			goto err;
+
+		spin_lock_init(&vdev->irqs[i].lock);
+
+		vdev->irqs[i].flags = VFIO_IRQ_INFO_EVENTFD;
+
+		if (irq_get_trigger_type(hwirq) & IRQ_TYPE_LEVEL_MASK)
+			vdev->irqs[i].flags |= VFIO_IRQ_INFO_MASKABLE
+						| VFIO_IRQ_INFO_AUTOMASKED;
+
+		vdev->irqs[i].count = 1;
+		vdev->irqs[i].hwirq = hwirq;
+		vdev->irqs[i].masked = false;
+	}
+
+	vdev->num_irqs = cnt;
+
+	return 0;
+err:
+	kfree(vdev->irqs);
+	return -EINVAL;
+}
+
+void vfio_platform_irq_cleanup(struct vfio_platform_device *vdev)
+{
+	int i;
+
+	for (i = 0; i < vdev->num_irqs; i++)
+		vfio_set_trigger(vdev, i, -1, NULL);
+
+	vdev->num_irqs = 0;
+	kfree(vdev->irqs);
+}
diff --git a/drivers/vfio/platform/vfio_platform_private.h b/drivers/vfio/platform/vfio_platform_private.h
new file mode 100644
index 000000000..5d31e0473
--- /dev/null
+++ b/drivers/vfio/platform/vfio_platform_private.h
@@ -0,0 +1,85 @@
+/*
+ * Copyright (C) 2013 - Virtual Open Systems
+ * Author: Antonios Motakis <a.motakis@virtualopensystems.com>
+ *
+ * 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.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef VFIO_PLATFORM_PRIVATE_H
+#define VFIO_PLATFORM_PRIVATE_H
+
+#include <linux/types.h>
+#include <linux/interrupt.h>
+
+#define VFIO_PLATFORM_OFFSET_SHIFT   40
+#define VFIO_PLATFORM_OFFSET_MASK (((u64)(1) << VFIO_PLATFORM_OFFSET_SHIFT) - 1)
+
+#define VFIO_PLATFORM_OFFSET_TO_INDEX(off)	\
+	(off >> VFIO_PLATFORM_OFFSET_SHIFT)
+
+#define VFIO_PLATFORM_INDEX_TO_OFFSET(index)	\
+	((u64)(index) << VFIO_PLATFORM_OFFSET_SHIFT)
+
+struct vfio_platform_irq {
+	u32			flags;
+	u32			count;
+	int			hwirq;
+	char			*name;
+	struct eventfd_ctx	*trigger;
+	bool			masked;
+	spinlock_t		lock;
+	struct virqfd		*unmask;
+	struct virqfd		*mask;
+};
+
+struct vfio_platform_region {
+	u64			addr;
+	resource_size_t		size;
+	u32			flags;
+	u32			type;
+#define VFIO_PLATFORM_REGION_TYPE_MMIO	1
+#define VFIO_PLATFORM_REGION_TYPE_PIO	2
+	void __iomem		*ioaddr;
+};
+
+struct vfio_platform_device {
+	struct vfio_platform_region	*regions;
+	u32				num_regions;
+	struct vfio_platform_irq	*irqs;
+	u32				num_irqs;
+	int				refcnt;
+	struct mutex			igate;
+
+	/*
+	 * These fields should be filled by the bus specific binder
+	 */
+	void		*opaque;
+	const char	*name;
+	uint32_t	flags;
+	/* callbacks to discover device resources */
+	struct resource*
+		(*get_resource)(struct vfio_platform_device *vdev, int i);
+	int	(*get_irq)(struct vfio_platform_device *vdev, int i);
+};
+
+extern int vfio_platform_probe_common(struct vfio_platform_device *vdev,
+				      struct device *dev);
+extern struct vfio_platform_device *vfio_platform_remove_common
+				     (struct device *dev);
+
+extern int vfio_platform_irq_init(struct vfio_platform_device *vdev);
+extern void vfio_platform_irq_cleanup(struct vfio_platform_device *vdev);
+
+extern int vfio_platform_set_irqs_ioctl(struct vfio_platform_device *vdev,
+					uint32_t flags, unsigned index,
+					unsigned start, unsigned count,
+					void *data);
+
+#endif /* VFIO_PLATFORM_PRIVATE_H */
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
new file mode 100644
index 000000000..e1278fe04
--- /dev/null
+++ b/drivers/vfio/vfio.c
@@ -0,0 +1,1612 @@
+/*
+ * VFIO core
+ *
+ * Copyright (C) 2012 Red Hat, Inc.  All rights reserved.
+ *     Author: Alex Williamson <alex.williamson@redhat.com>
+ *
+ * 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.
+ *
+ * Derived from original vfio:
+ * Copyright 2010 Cisco Systems, Inc.  All rights reserved.
+ * Author: Tom Lyon, pugs@cisco.com
+ */
+
+#include <linux/cdev.h>
+#include <linux/compat.h>
+#include <linux/device.h>
+#include <linux/file.h>
+#include <linux/anon_inodes.h>
+#include <linux/fs.h>
+#include <linux/idr.h>
+#include <linux/iommu.h>
+#include <linux/list.h>
+#include <linux/miscdevice.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/rwsem.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/stat.h>
+#include <linux/string.h>
+#include <linux/uaccess.h>
+#include <linux/vfio.h>
+#include <linux/wait.h>
+
+#define DRIVER_VERSION	"0.3"
+#define DRIVER_AUTHOR	"Alex Williamson <alex.williamson@redhat.com>"
+#define DRIVER_DESC	"VFIO - User Level meta-driver"
+
+static struct vfio {
+	struct class			*class;
+	struct list_head		iommu_drivers_list;
+	struct mutex			iommu_drivers_lock;
+	struct list_head		group_list;
+	struct idr			group_idr;
+	struct mutex			group_lock;
+	struct cdev			group_cdev;
+	dev_t				group_devt;
+	wait_queue_head_t		release_q;
+} vfio;
+
+struct vfio_iommu_driver {
+	const struct vfio_iommu_driver_ops	*ops;
+	struct list_head			vfio_next;
+};
+
+struct vfio_container {
+	struct kref			kref;
+	struct list_head		group_list;
+	struct rw_semaphore		group_lock;
+	struct vfio_iommu_driver	*iommu_driver;
+	void				*iommu_data;
+};
+
+struct vfio_unbound_dev {
+	struct device			*dev;
+	struct list_head		unbound_next;
+};
+
+struct vfio_group {
+	struct kref			kref;
+	int				minor;
+	atomic_t			container_users;
+	struct iommu_group		*iommu_group;
+	struct vfio_container		*container;
+	struct list_head		device_list;
+	struct mutex			device_lock;
+	struct device			*dev;
+	struct notifier_block		nb;
+	struct list_head		vfio_next;
+	struct list_head		container_next;
+	struct list_head		unbound_list;
+	struct mutex			unbound_lock;
+	atomic_t			opened;
+};
+
+struct vfio_device {
+	struct kref			kref;
+	struct device			*dev;
+	const struct vfio_device_ops	*ops;
+	struct vfio_group		*group;
+	struct list_head		group_next;
+	void				*device_data;
+};
+
+/**
+ * IOMMU driver registration
+ */
+int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops)
+{
+	struct vfio_iommu_driver *driver, *tmp;
+
+	driver = kzalloc(sizeof(*driver), GFP_KERNEL);
+	if (!driver)
+		return -ENOMEM;
+
+	driver->ops = ops;
+
+	mutex_lock(&vfio.iommu_drivers_lock);
+
+	/* Check for duplicates */
+	list_for_each_entry(tmp, &vfio.iommu_drivers_list, vfio_next) {
+		if (tmp->ops == ops) {
+			mutex_unlock(&vfio.iommu_drivers_lock);
+			kfree(driver);
+			return -EINVAL;
+		}
+	}
+
+	list_add(&driver->vfio_next, &vfio.iommu_drivers_list);
+
+	mutex_unlock(&vfio.iommu_drivers_lock);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(vfio_register_iommu_driver);
+
+void vfio_unregister_iommu_driver(const struct vfio_iommu_driver_ops *ops)
+{
+	struct vfio_iommu_driver *driver;
+
+	mutex_lock(&vfio.iommu_drivers_lock);
+	list_for_each_entry(driver, &vfio.iommu_drivers_list, vfio_next) {
+		if (driver->ops == ops) {
+			list_del(&driver->vfio_next);
+			mutex_unlock(&vfio.iommu_drivers_lock);
+			kfree(driver);
+			return;
+		}
+	}
+	mutex_unlock(&vfio.iommu_drivers_lock);
+}
+EXPORT_SYMBOL_GPL(vfio_unregister_iommu_driver);
+
+/**
+ * Group minor allocation/free - both called with vfio.group_lock held
+ */
+static int vfio_alloc_group_minor(struct vfio_group *group)
+{
+	return idr_alloc(&vfio.group_idr, group, 0, MINORMASK + 1, GFP_KERNEL);
+}
+
+static void vfio_free_group_minor(int minor)
+{
+	idr_remove(&vfio.group_idr, minor);
+}
+
+static int vfio_iommu_group_notifier(struct notifier_block *nb,
+				     unsigned long action, void *data);
+static void vfio_group_get(struct vfio_group *group);
+
+/**
+ * Container objects - containers are created when /dev/vfio/vfio is
+ * opened, but their lifecycle extends until the last user is done, so
+ * it's freed via kref.  Must support container/group/device being
+ * closed in any order.
+ */
+static void vfio_container_get(struct vfio_container *container)
+{
+	kref_get(&container->kref);
+}
+
+static void vfio_container_release(struct kref *kref)
+{
+	struct vfio_container *container;
+	container = container_of(kref, struct vfio_container, kref);
+
+	kfree(container);
+}
+
+static void vfio_container_put(struct vfio_container *container)
+{
+	kref_put(&container->kref, vfio_container_release);
+}
+
+static void vfio_group_unlock_and_free(struct vfio_group *group)
+{
+	mutex_unlock(&vfio.group_lock);
+	/*
+	 * Unregister outside of lock.  A spurious callback is harmless now
+	 * that the group is no longer in vfio.group_list.
+	 */
+	iommu_group_unregister_notifier(group->iommu_group, &group->nb);
+	kfree(group);
+}
+
+/**
+ * Group objects - create, release, get, put, search
+ */
+static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group)
+{
+	struct vfio_group *group, *tmp;
+	struct device *dev;
+	int ret, minor;
+
+	group = kzalloc(sizeof(*group), GFP_KERNEL);
+	if (!group)
+		return ERR_PTR(-ENOMEM);
+
+	kref_init(&group->kref);
+	INIT_LIST_HEAD(&group->device_list);
+	mutex_init(&group->device_lock);
+	INIT_LIST_HEAD(&group->unbound_list);
+	mutex_init(&group->unbound_lock);
+	atomic_set(&group->container_users, 0);
+	atomic_set(&group->opened, 0);
+	group->iommu_group = iommu_group;
+
+	group->nb.notifier_call = vfio_iommu_group_notifier;
+
+	/*
+	 * blocking notifiers acquire a rwsem around registering and hold
+	 * it around callback.  Therefore, need to register outside of
+	 * vfio.group_lock to avoid A-B/B-A contention.  Our callback won't
+	 * do anything unless it can find the group in vfio.group_list, so
+	 * no harm in registering early.
+	 */
+	ret = iommu_group_register_notifier(iommu_group, &group->nb);
+	if (ret) {
+		kfree(group);
+		return ERR_PTR(ret);
+	}
+
+	mutex_lock(&vfio.group_lock);
+
+	/* Did we race creating this group? */
+	list_for_each_entry(tmp, &vfio.group_list, vfio_next) {
+		if (tmp->iommu_group == iommu_group) {
+			vfio_group_get(tmp);
+			vfio_group_unlock_and_free(group);
+			return tmp;
+		}
+	}
+
+	minor = vfio_alloc_group_minor(group);
+	if (minor < 0) {
+		vfio_group_unlock_and_free(group);
+		return ERR_PTR(minor);
+	}
+
+	dev = device_create(vfio.class, NULL,
+			    MKDEV(MAJOR(vfio.group_devt), minor),
+			    group, "%d", iommu_group_id(iommu_group));
+	if (IS_ERR(dev)) {
+		vfio_free_group_minor(minor);
+		vfio_group_unlock_and_free(group);
+		return (struct vfio_group *)dev; /* ERR_PTR */
+	}
+
+	group->minor = minor;
+	group->dev = dev;
+
+	list_add(&group->vfio_next, &vfio.group_list);
+
+	mutex_unlock(&vfio.group_lock);
+
+	return group;
+}
+
+/* called with vfio.group_lock held */
+static void vfio_group_release(struct kref *kref)
+{
+	struct vfio_group *group = container_of(kref, struct vfio_group, kref);
+	struct vfio_unbound_dev *unbound, *tmp;
+	struct iommu_group *iommu_group = group->iommu_group;
+
+	WARN_ON(!list_empty(&group->device_list));
+
+	list_for_each_entry_safe(unbound, tmp,
+				 &group->unbound_list, unbound_next) {
+		list_del(&unbound->unbound_next);
+		kfree(unbound);
+	}
+
+	device_destroy(vfio.class, MKDEV(MAJOR(vfio.group_devt), group->minor));
+	list_del(&group->vfio_next);
+	vfio_free_group_minor(group->minor);
+	vfio_group_unlock_and_free(group);
+	iommu_group_put(iommu_group);
+}
+
+static void vfio_group_put(struct vfio_group *group)
+{
+	kref_put_mutex(&group->kref, vfio_group_release, &vfio.group_lock);
+}
+
+/* Assume group_lock or group reference is held */
+static void vfio_group_get(struct vfio_group *group)
+{
+	kref_get(&group->kref);
+}
+
+/*
+ * Not really a try as we will sleep for mutex, but we need to make
+ * sure the group pointer is valid under lock and get a reference.
+ */
+static struct vfio_group *vfio_group_try_get(struct vfio_group *group)
+{
+	struct vfio_group *target = group;
+
+	mutex_lock(&vfio.group_lock);
+	list_for_each_entry(group, &vfio.group_list, vfio_next) {
+		if (group == target) {
+			vfio_group_get(group);
+			mutex_unlock(&vfio.group_lock);
+			return group;
+		}
+	}
+	mutex_unlock(&vfio.group_lock);
+
+	return NULL;
+}
+
+static
+struct vfio_group *vfio_group_get_from_iommu(struct iommu_group *iommu_group)
+{
+	struct vfio_group *group;
+
+	mutex_lock(&vfio.group_lock);
+	list_for_each_entry(group, &vfio.group_list, vfio_next) {
+		if (group->iommu_group == iommu_group) {
+			vfio_group_get(group);
+			mutex_unlock(&vfio.group_lock);
+			return group;
+		}
+	}
+	mutex_unlock(&vfio.group_lock);
+
+	return NULL;
+}
+
+static struct vfio_group *vfio_group_get_from_minor(int minor)
+{
+	struct vfio_group *group;
+
+	mutex_lock(&vfio.group_lock);
+	group = idr_find(&vfio.group_idr, minor);
+	if (!group) {
+		mutex_unlock(&vfio.group_lock);
+		return NULL;
+	}
+	vfio_group_get(group);
+	mutex_unlock(&vfio.group_lock);
+
+	return group;
+}
+
+/**
+ * Device objects - create, release, get, put, search
+ */
+static
+struct vfio_device *vfio_group_create_device(struct vfio_group *group,
+					     struct device *dev,
+					     const struct vfio_device_ops *ops,
+					     void *device_data)
+{
+	struct vfio_device *device;
+
+	device = kzalloc(sizeof(*device), GFP_KERNEL);
+	if (!device)
+		return ERR_PTR(-ENOMEM);
+
+	kref_init(&device->kref);
+	device->dev = dev;
+	device->group = group;
+	device->ops = ops;
+	device->device_data = device_data;
+	dev_set_drvdata(dev, device);
+
+	/* No need to get group_lock, caller has group reference */
+	vfio_group_get(group);
+
+	mutex_lock(&group->device_lock);
+	list_add(&device->group_next, &group->device_list);
+	mutex_unlock(&group->device_lock);
+
+	return device;
+}
+
+static void vfio_device_release(struct kref *kref)
+{
+	struct vfio_device *device = container_of(kref,
+						  struct vfio_device, kref);
+	struct vfio_group *group = device->group;
+
+	list_del(&device->group_next);
+	mutex_unlock(&group->device_lock);
+
+	dev_set_drvdata(device->dev, NULL);
+
+	kfree(device);
+
+	/* vfio_del_group_dev may be waiting for this device */
+	wake_up(&vfio.release_q);
+}
+
+/* Device reference always implies a group reference */
+void vfio_device_put(struct vfio_device *device)
+{
+	struct vfio_group *group = device->group;
+	kref_put_mutex(&device->kref, vfio_device_release, &group->device_lock);
+	vfio_group_put(group);
+}
+EXPORT_SYMBOL_GPL(vfio_device_put);
+
+static void vfio_device_get(struct vfio_device *device)
+{
+	vfio_group_get(device->group);
+	kref_get(&device->kref);
+}
+
+static struct vfio_device *vfio_group_get_device(struct vfio_group *group,
+						 struct device *dev)
+{
+	struct vfio_device *device;
+
+	mutex_lock(&group->device_lock);
+	list_for_each_entry(device, &group->device_list, group_next) {
+		if (device->dev == dev) {
+			vfio_device_get(device);
+			mutex_unlock(&group->device_lock);
+			return device;
+		}
+	}
+	mutex_unlock(&group->device_lock);
+	return NULL;
+}
+
+/*
+ * Whitelist some drivers that we know are safe (no dma) or just sit on
+ * a device.  It's not always practical to leave a device within a group
+ * driverless as it could get re-bound to something unsafe.
+ */
+static const char * const vfio_driver_whitelist[] = { "pci-stub", "pcieport" };
+
+static bool vfio_whitelisted_driver(struct device_driver *drv)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(vfio_driver_whitelist); i++) {
+		if (!strcmp(drv->name, vfio_driver_whitelist[i]))
+			return true;
+	}
+
+	return false;
+}
+
+/*
+ * A vfio group is viable for use by userspace if all devices are in
+ * one of the following states:
+ *  - driver-less
+ *  - bound to a vfio driver
+ *  - bound to a whitelisted driver
+ *
+ * We use two methods to determine whether a device is bound to a vfio
+ * driver.  The first is to test whether the device exists in the vfio
+ * group.  The second is to test if the device exists on the group
+ * unbound_list, indicating it's in the middle of transitioning from
+ * a vfio driver to driver-less.
+ */
+static int vfio_dev_viable(struct device *dev, void *data)
+{
+	struct vfio_group *group = data;
+	struct vfio_device *device;
+	struct device_driver *drv = ACCESS_ONCE(dev->driver);
+	struct vfio_unbound_dev *unbound;
+	int ret = -EINVAL;
+
+	mutex_lock(&group->unbound_lock);
+	list_for_each_entry(unbound, &group->unbound_list, unbound_next) {
+		if (dev == unbound->dev) {
+			ret = 0;
+			break;
+		}
+	}
+	mutex_unlock(&group->unbound_lock);
+
+	if (!ret || !drv || vfio_whitelisted_driver(drv))
+		return 0;
+
+	device = vfio_group_get_device(group, dev);
+	if (device) {
+		vfio_device_put(device);
+		return 0;
+	}
+
+	return ret;
+}
+
+/**
+ * Async device support
+ */
+static int vfio_group_nb_add_dev(struct vfio_group *group, struct device *dev)
+{
+	struct vfio_device *device;
+
+	/* Do we already know about it?  We shouldn't */
+	device = vfio_group_get_device(group, dev);
+	if (WARN_ON_ONCE(device)) {
+		vfio_device_put(device);
+		return 0;
+	}
+
+	/* Nothing to do for idle groups */
+	if (!atomic_read(&group->container_users))
+		return 0;
+
+	/* TODO Prevent device auto probing */
+	WARN("Device %s added to live group %d!\n", dev_name(dev),
+	     iommu_group_id(group->iommu_group));
+
+	return 0;
+}
+
+static int vfio_group_nb_verify(struct vfio_group *group, struct device *dev)
+{
+	/* We don't care what happens when the group isn't in use */
+	if (!atomic_read(&group->container_users))
+		return 0;
+
+	return vfio_dev_viable(dev, group);
+}
+
+static int vfio_iommu_group_notifier(struct notifier_block *nb,
+				     unsigned long action, void *data)
+{
+	struct vfio_group *group = container_of(nb, struct vfio_group, nb);
+	struct device *dev = data;
+	struct vfio_unbound_dev *unbound;
+
+	/*
+	 * Need to go through a group_lock lookup to get a reference or we
+	 * risk racing a group being removed.  Ignore spurious notifies.
+	 */
+	group = vfio_group_try_get(group);
+	if (!group)
+		return NOTIFY_OK;
+
+	switch (action) {
+	case IOMMU_GROUP_NOTIFY_ADD_DEVICE:
+		vfio_group_nb_add_dev(group, dev);
+		break;
+	case IOMMU_GROUP_NOTIFY_DEL_DEVICE:
+		/*
+		 * Nothing to do here.  If the device is in use, then the
+		 * vfio sub-driver should block the remove callback until
+		 * it is unused.  If the device is unused or attached to a
+		 * stub driver, then it should be released and we don't
+		 * care that it will be going away.
+		 */
+		break;
+	case IOMMU_GROUP_NOTIFY_BIND_DRIVER:
+		pr_debug("%s: Device %s, group %d binding to driver\n",
+			 __func__, dev_name(dev),
+			 iommu_group_id(group->iommu_group));
+		break;
+	case IOMMU_GROUP_NOTIFY_BOUND_DRIVER:
+		pr_debug("%s: Device %s, group %d bound to driver %s\n",
+			 __func__, dev_name(dev),
+			 iommu_group_id(group->iommu_group), dev->driver->name);
+		BUG_ON(vfio_group_nb_verify(group, dev));
+		break;
+	case IOMMU_GROUP_NOTIFY_UNBIND_DRIVER:
+		pr_debug("%s: Device %s, group %d unbinding from driver %s\n",
+			 __func__, dev_name(dev),
+			 iommu_group_id(group->iommu_group), dev->driver->name);
+		break;
+	case IOMMU_GROUP_NOTIFY_UNBOUND_DRIVER:
+		pr_debug("%s: Device %s, group %d unbound from driver\n",
+			 __func__, dev_name(dev),
+			 iommu_group_id(group->iommu_group));
+		/*
+		 * XXX An unbound device in a live group is ok, but we'd
+		 * really like to avoid the above BUG_ON by preventing other
+		 * drivers from binding to it.  Once that occurs, we have to
+		 * stop the system to maintain isolation.  At a minimum, we'd
+		 * want a toggle to disable driver auto probe for this device.
+		 */
+
+		mutex_lock(&group->unbound_lock);
+		list_for_each_entry(unbound,
+				    &group->unbound_list, unbound_next) {
+			if (dev == unbound->dev) {
+				list_del(&unbound->unbound_next);
+				kfree(unbound);
+				break;
+			}
+		}
+		mutex_unlock(&group->unbound_lock);
+		break;
+	}
+
+	vfio_group_put(group);
+	return NOTIFY_OK;
+}
+
+/**
+ * VFIO driver API
+ */
+int vfio_add_group_dev(struct device *dev,
+		       const struct vfio_device_ops *ops, void *device_data)
+{
+	struct iommu_group *iommu_group;
+	struct vfio_group *group;
+	struct vfio_device *device;
+
+	iommu_group = iommu_group_get(dev);
+	if (!iommu_group)
+		return -EINVAL;
+
+	group = vfio_group_get_from_iommu(iommu_group);
+	if (!group) {
+		group = vfio_create_group(iommu_group);
+		if (IS_ERR(group)) {
+			iommu_group_put(iommu_group);
+			return PTR_ERR(group);
+		}
+	} else {
+		/*
+		 * A found vfio_group already holds a reference to the
+		 * iommu_group.  A created vfio_group keeps the reference.
+		 */
+		iommu_group_put(iommu_group);
+	}
+
+	device = vfio_group_get_device(group, dev);
+	if (device) {
+		WARN(1, "Device %s already exists on group %d\n",
+		     dev_name(dev), iommu_group_id(iommu_group));
+		vfio_device_put(device);
+		vfio_group_put(group);
+		return -EBUSY;
+	}
+
+	device = vfio_group_create_device(group, dev, ops, device_data);
+	if (IS_ERR(device)) {
+		vfio_group_put(group);
+		return PTR_ERR(device);
+	}
+
+	/*
+	 * Drop all but the vfio_device reference.  The vfio_device holds
+	 * a reference to the vfio_group, which holds a reference to the
+	 * iommu_group.
+	 */
+	vfio_group_put(group);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(vfio_add_group_dev);
+
+/**
+ * Get a reference to the vfio_device for a device that is known to
+ * be bound to a vfio driver.  The driver implicitly holds a
+ * vfio_device reference between vfio_add_group_dev and
+ * vfio_del_group_dev.  We can therefore use drvdata to increment
+ * that reference from the struct device.  This additional
+ * reference must be released by calling vfio_device_put.
+ */
+struct vfio_device *vfio_device_get_from_dev(struct device *dev)
+{
+	struct vfio_device *device = dev_get_drvdata(dev);
+
+	vfio_device_get(device);
+
+	return device;
+}
+EXPORT_SYMBOL_GPL(vfio_device_get_from_dev);
+
+/*
+ * Caller must hold a reference to the vfio_device
+ */
+void *vfio_device_data(struct vfio_device *device)
+{
+	return device->device_data;
+}
+EXPORT_SYMBOL_GPL(vfio_device_data);
+
+/* Given a referenced group, check if it contains the device */
+static bool vfio_dev_present(struct vfio_group *group, struct device *dev)
+{
+	struct vfio_device *device;
+
+	device = vfio_group_get_device(group, dev);
+	if (!device)
+		return false;
+
+	vfio_device_put(device);
+	return true;
+}
+
+/*
+ * Decrement the device reference count and wait for the device to be
+ * removed.  Open file descriptors for the device... */
+void *vfio_del_group_dev(struct device *dev)
+{
+	struct vfio_device *device = dev_get_drvdata(dev);
+	struct vfio_group *group = device->group;
+	void *device_data = device->device_data;
+	struct vfio_unbound_dev *unbound;
+	unsigned int i = 0;
+	long ret;
+	bool interrupted = false;
+
+	/*
+	 * The group exists so long as we have a device reference.  Get
+	 * a group reference and use it to scan for the device going away.
+	 */
+	vfio_group_get(group);
+
+	/*
+	 * When the device is removed from the group, the group suddenly
+	 * becomes non-viable; the device has a driver (until the unbind
+	 * completes), but it's not present in the group.  This is bad news
+	 * for any external users that need to re-acquire a group reference
+	 * in order to match and release their existing reference.  To
+	 * solve this, we track such devices on the unbound_list to bridge
+	 * the gap until they're fully unbound.
+	 */
+	unbound = kzalloc(sizeof(*unbound), GFP_KERNEL);
+	if (unbound) {
+		unbound->dev = dev;
+		mutex_lock(&group->unbound_lock);
+		list_add(&unbound->unbound_next, &group->unbound_list);
+		mutex_unlock(&group->unbound_lock);
+	}
+	WARN_ON(!unbound);
+
+	vfio_device_put(device);
+
+	/*
+	 * If the device is still present in the group after the above
+	 * 'put', then it is in use and we need to request it from the
+	 * bus driver.  The driver may in turn need to request the
+	 * device from the user.  We send the request on an arbitrary
+	 * interval with counter to allow the driver to take escalating
+	 * measures to release the device if it has the ability to do so.
+	 */
+	do {
+		device = vfio_group_get_device(group, dev);
+		if (!device)
+			break;
+
+		if (device->ops->request)
+			device->ops->request(device_data, i++);
+
+		vfio_device_put(device);
+
+		if (interrupted) {
+			ret = wait_event_timeout(vfio.release_q,
+					!vfio_dev_present(group, dev), HZ * 10);
+		} else {
+			ret = wait_event_interruptible_timeout(vfio.release_q,
+					!vfio_dev_present(group, dev), HZ * 10);
+			if (ret == -ERESTARTSYS) {
+				interrupted = true;
+				dev_warn(dev,
+					 "Device is currently in use, task"
+					 " \"%s\" (%d) "
+					 "blocked until device is released",
+					 current->comm, task_pid_nr(current));
+			}
+		}
+	} while (ret <= 0);
+
+	vfio_group_put(group);
+
+	return device_data;
+}
+EXPORT_SYMBOL_GPL(vfio_del_group_dev);
+
+/**
+ * VFIO base fd, /dev/vfio/vfio
+ */
+static long vfio_ioctl_check_extension(struct vfio_container *container,
+				       unsigned long arg)
+{
+	struct vfio_iommu_driver *driver;
+	long ret = 0;
+
+	down_read(&container->group_lock);
+
+	driver = container->iommu_driver;
+
+	switch (arg) {
+		/* No base extensions yet */
+	default:
+		/*
+		 * If no driver is set, poll all registered drivers for
+		 * extensions and return the first positive result.  If
+		 * a driver is already set, further queries will be passed
+		 * only to that driver.
+		 */
+		if (!driver) {
+			mutex_lock(&vfio.iommu_drivers_lock);
+			list_for_each_entry(driver, &vfio.iommu_drivers_list,
+					    vfio_next) {
+				if (!try_module_get(driver->ops->owner))
+					continue;
+
+				ret = driver->ops->ioctl(NULL,
+							 VFIO_CHECK_EXTENSION,
+							 arg);
+				module_put(driver->ops->owner);
+				if (ret > 0)
+					break;
+			}
+			mutex_unlock(&vfio.iommu_drivers_lock);
+		} else
+			ret = driver->ops->ioctl(container->iommu_data,
+						 VFIO_CHECK_EXTENSION, arg);
+	}
+
+	up_read(&container->group_lock);
+
+	return ret;
+}
+
+/* hold write lock on container->group_lock */
+static int __vfio_container_attach_groups(struct vfio_container *container,
+					  struct vfio_iommu_driver *driver,
+					  void *data)
+{
+	struct vfio_group *group;
+	int ret = -ENODEV;
+
+	list_for_each_entry(group, &container->group_list, container_next) {
+		ret = driver->ops->attach_group(data, group->iommu_group);
+		if (ret)
+			goto unwind;
+	}
+
+	return ret;
+
+unwind:
+	list_for_each_entry_continue_reverse(group, &container->group_list,
+					     container_next) {
+		driver->ops->detach_group(data, group->iommu_group);
+	}
+
+	return ret;
+}
+
+static long vfio_ioctl_set_iommu(struct vfio_container *container,
+				 unsigned long arg)
+{
+	struct vfio_iommu_driver *driver;
+	long ret = -ENODEV;
+
+	down_write(&container->group_lock);
+
+	/*
+	 * The container is designed to be an unprivileged interface while
+	 * the group can be assigned to specific users.  Therefore, only by
+	 * adding a group to a container does the user get the privilege of
+	 * enabling the iommu, which may allocate finite resources.  There
+	 * is no unset_iommu, but by removing all the groups from a container,
+	 * the container is deprivileged and returns to an unset state.
+	 */
+	if (list_empty(&container->group_list) || container->iommu_driver) {
+		up_write(&container->group_lock);
+		return -EINVAL;
+	}
+
+	mutex_lock(&vfio.iommu_drivers_lock);
+	list_for_each_entry(driver, &vfio.iommu_drivers_list, vfio_next) {
+		void *data;
+
+		if (!try_module_get(driver->ops->owner))
+			continue;
+
+		/*
+		 * The arg magic for SET_IOMMU is the same as CHECK_EXTENSION,
+		 * so test which iommu driver reported support for this
+		 * extension and call open on them.  We also pass them the
+		 * magic, allowing a single driver to support multiple
+		 * interfaces if they'd like.
+		 */
+		if (driver->ops->ioctl(NULL, VFIO_CHECK_EXTENSION, arg) <= 0) {
+			module_put(driver->ops->owner);
+			continue;
+		}
+
+		/* module reference holds the driver we're working on */
+		mutex_unlock(&vfio.iommu_drivers_lock);
+
+		data = driver->ops->open(arg);
+		if (IS_ERR(data)) {
+			ret = PTR_ERR(data);
+			module_put(driver->ops->owner);
+			goto skip_drivers_unlock;
+		}
+
+		ret = __vfio_container_attach_groups(container, driver, data);
+		if (!ret) {
+			container->iommu_driver = driver;
+			container->iommu_data = data;
+		} else {
+			driver->ops->release(data);
+			module_put(driver->ops->owner);
+		}
+
+		goto skip_drivers_unlock;
+	}
+
+	mutex_unlock(&vfio.iommu_drivers_lock);
+skip_drivers_unlock:
+	up_write(&container->group_lock);
+
+	return ret;
+}
+
+static long vfio_fops_unl_ioctl(struct file *filep,
+				unsigned int cmd, unsigned long arg)
+{
+	struct vfio_container *container = filep->private_data;
+	struct vfio_iommu_driver *driver;
+	void *data;
+	long ret = -EINVAL;
+
+	if (!container)
+		return ret;
+
+	switch (cmd) {
+	case VFIO_GET_API_VERSION:
+		ret = VFIO_API_VERSION;
+		break;
+	case VFIO_CHECK_EXTENSION:
+		ret = vfio_ioctl_check_extension(container, arg);
+		break;
+	case VFIO_SET_IOMMU:
+		ret = vfio_ioctl_set_iommu(container, arg);
+		break;
+	default:
+		down_read(&container->group_lock);
+
+		driver = container->iommu_driver;
+		data = container->iommu_data;
+
+		if (driver) /* passthrough all unrecognized ioctls */
+			ret = driver->ops->ioctl(data, cmd, arg);
+
+		up_read(&container->group_lock);
+	}
+
+	return ret;
+}
+
+#ifdef CONFIG_COMPAT
+static long vfio_fops_compat_ioctl(struct file *filep,
+				   unsigned int cmd, unsigned long arg)
+{
+	arg = (unsigned long)compat_ptr(arg);
+	return vfio_fops_unl_ioctl(filep, cmd, arg);
+}
+#endif	/* CONFIG_COMPAT */
+
+static int vfio_fops_open(struct inode *inode, struct file *filep)
+{
+	struct vfio_container *container;
+
+	container = kzalloc(sizeof(*container), GFP_KERNEL);
+	if (!container)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&container->group_list);
+	init_rwsem(&container->group_lock);
+	kref_init(&container->kref);
+
+	filep->private_data = container;
+
+	return 0;
+}
+
+static int vfio_fops_release(struct inode *inode, struct file *filep)
+{
+	struct vfio_container *container = filep->private_data;
+
+	filep->private_data = NULL;
+
+	vfio_container_put(container);
+
+	return 0;
+}
+
+/*
+ * Once an iommu driver is set, we optionally pass read/write/mmap
+ * on to the driver, allowing management interfaces beyond ioctl.
+ */
+static ssize_t vfio_fops_read(struct file *filep, char __user *buf,
+			      size_t count, loff_t *ppos)
+{
+	struct vfio_container *container = filep->private_data;
+	struct vfio_iommu_driver *driver;
+	ssize_t ret = -EINVAL;
+
+	down_read(&container->group_lock);
+
+	driver = container->iommu_driver;
+	if (likely(driver && driver->ops->read))
+		ret = driver->ops->read(container->iommu_data,
+					buf, count, ppos);
+
+	up_read(&container->group_lock);
+
+	return ret;
+}
+
+static ssize_t vfio_fops_write(struct file *filep, const char __user *buf,
+			       size_t count, loff_t *ppos)
+{
+	struct vfio_container *container = filep->private_data;
+	struct vfio_iommu_driver *driver;
+	ssize_t ret = -EINVAL;
+
+	down_read(&container->group_lock);
+
+	driver = container->iommu_driver;
+	if (likely(driver && driver->ops->write))
+		ret = driver->ops->write(container->iommu_data,
+					 buf, count, ppos);
+
+	up_read(&container->group_lock);
+
+	return ret;
+}
+
+static int vfio_fops_mmap(struct file *filep, struct vm_area_struct *vma)
+{
+	struct vfio_container *container = filep->private_data;
+	struct vfio_iommu_driver *driver;
+	int ret = -EINVAL;
+
+	down_read(&container->group_lock);
+
+	driver = container->iommu_driver;
+	if (likely(driver && driver->ops->mmap))
+		ret = driver->ops->mmap(container->iommu_data, vma);
+
+	up_read(&container->group_lock);
+
+	return ret;
+}
+
+static const struct file_operations vfio_fops = {
+	.owner		= THIS_MODULE,
+	.open		= vfio_fops_open,
+	.release	= vfio_fops_release,
+	.read		= vfio_fops_read,
+	.write		= vfio_fops_write,
+	.unlocked_ioctl	= vfio_fops_unl_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= vfio_fops_compat_ioctl,
+#endif
+	.mmap		= vfio_fops_mmap,
+};
+
+/**
+ * VFIO Group fd, /dev/vfio/$GROUP
+ */
+static void __vfio_group_unset_container(struct vfio_group *group)
+{
+	struct vfio_container *container = group->container;
+	struct vfio_iommu_driver *driver;
+
+	down_write(&container->group_lock);
+
+	driver = container->iommu_driver;
+	if (driver)
+		driver->ops->detach_group(container->iommu_data,
+					  group->iommu_group);
+
+	group->container = NULL;
+	list_del(&group->container_next);
+
+	/* Detaching the last group deprivileges a container, remove iommu */
+	if (driver && list_empty(&container->group_list)) {
+		driver->ops->release(container->iommu_data);
+		module_put(driver->ops->owner);
+		container->iommu_driver = NULL;
+		container->iommu_data = NULL;
+	}
+
+	up_write(&container->group_lock);
+
+	vfio_container_put(container);
+}
+
+/*
+ * VFIO_GROUP_UNSET_CONTAINER should fail if there are other users or
+ * if there was no container to unset.  Since the ioctl is called on
+ * the group, we know that still exists, therefore the only valid
+ * transition here is 1->0.
+ */
+static int vfio_group_unset_container(struct vfio_group *group)
+{
+	int users = atomic_cmpxchg(&group->container_users, 1, 0);
+
+	if (!users)
+		return -EINVAL;
+	if (users != 1)
+		return -EBUSY;
+
+	__vfio_group_unset_container(group);
+
+	return 0;
+}
+
+/*
+ * When removing container users, anything that removes the last user
+ * implicitly removes the group from the container.  That is, if the
+ * group file descriptor is closed, as well as any device file descriptors,
+ * the group is free.
+ */
+static void vfio_group_try_dissolve_container(struct vfio_group *group)
+{
+	if (0 == atomic_dec_if_positive(&group->container_users))
+		__vfio_group_unset_container(group);
+}
+
+static int vfio_group_set_container(struct vfio_group *group, int container_fd)
+{
+	struct fd f;
+	struct vfio_container *container;
+	struct vfio_iommu_driver *driver;
+	int ret = 0;
+
+	if (atomic_read(&group->container_users))
+		return -EINVAL;
+
+	f = fdget(container_fd);
+	if (!f.file)
+		return -EBADF;
+
+	/* Sanity check, is this really our fd? */
+	if (f.file->f_op != &vfio_fops) {
+		fdput(f);
+		return -EINVAL;
+	}
+
+	container = f.file->private_data;
+	WARN_ON(!container); /* fget ensures we don't race vfio_release */
+
+	down_write(&container->group_lock);
+
+	driver = container->iommu_driver;
+	if (driver) {
+		ret = driver->ops->attach_group(container->iommu_data,
+						group->iommu_group);
+		if (ret)
+			goto unlock_out;
+	}
+
+	group->container = container;
+	list_add(&group->container_next, &container->group_list);
+
+	/* Get a reference on the container and mark a user within the group */
+	vfio_container_get(container);
+	atomic_inc(&group->container_users);
+
+unlock_out:
+	up_write(&container->group_lock);
+	fdput(f);
+	return ret;
+}
+
+static bool vfio_group_viable(struct vfio_group *group)
+{
+	return (iommu_group_for_each_dev(group->iommu_group,
+					 group, vfio_dev_viable) == 0);
+}
+
+static const struct file_operations vfio_device_fops;
+
+static int vfio_group_get_device_fd(struct vfio_group *group, char *buf)
+{
+	struct vfio_device *device;
+	struct file *filep;
+	int ret = -ENODEV;
+
+	if (0 == atomic_read(&group->container_users) ||
+	    !group->container->iommu_driver || !vfio_group_viable(group))
+		return -EINVAL;
+
+	mutex_lock(&group->device_lock);
+	list_for_each_entry(device, &group->device_list, group_next) {
+		if (strcmp(dev_name(device->dev), buf))
+			continue;
+
+		ret = device->ops->open(device->device_data);
+		if (ret)
+			break;
+		/*
+		 * We can't use anon_inode_getfd() because we need to modify
+		 * the f_mode flags directly to allow more than just ioctls
+		 */
+		ret = get_unused_fd_flags(O_CLOEXEC);
+		if (ret < 0) {
+			device->ops->release(device->device_data);
+			break;
+		}
+
+		filep = anon_inode_getfile("[vfio-device]", &vfio_device_fops,
+					   device, O_RDWR);
+		if (IS_ERR(filep)) {
+			put_unused_fd(ret);
+			ret = PTR_ERR(filep);
+			device->ops->release(device->device_data);
+			break;
+		}
+
+		/*
+		 * TODO: add an anon_inode interface to do this.
+		 * Appears to be missing by lack of need rather than
+		 * explicitly prevented.  Now there's need.
+		 */
+		filep->f_mode |= (FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE);
+
+		vfio_device_get(device);
+		atomic_inc(&group->container_users);
+
+		fd_install(ret, filep);
+		break;
+	}
+	mutex_unlock(&group->device_lock);
+
+	return ret;
+}
+
+static long vfio_group_fops_unl_ioctl(struct file *filep,
+				      unsigned int cmd, unsigned long arg)
+{
+	struct vfio_group *group = filep->private_data;
+	long ret = -ENOTTY;
+
+	switch (cmd) {
+	case VFIO_GROUP_GET_STATUS:
+	{
+		struct vfio_group_status status;
+		unsigned long minsz;
+
+		minsz = offsetofend(struct vfio_group_status, flags);
+
+		if (copy_from_user(&status, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (status.argsz < minsz)
+			return -EINVAL;
+
+		status.flags = 0;
+
+		if (vfio_group_viable(group))
+			status.flags |= VFIO_GROUP_FLAGS_VIABLE;
+
+		if (group->container)
+			status.flags |= VFIO_GROUP_FLAGS_CONTAINER_SET;
+
+		if (copy_to_user((void __user *)arg, &status, minsz))
+			return -EFAULT;
+
+		ret = 0;
+		break;
+	}
+	case VFIO_GROUP_SET_CONTAINER:
+	{
+		int fd;
+
+		if (get_user(fd, (int __user *)arg))
+			return -EFAULT;
+
+		if (fd < 0)
+			return -EINVAL;
+
+		ret = vfio_group_set_container(group, fd);
+		break;
+	}
+	case VFIO_GROUP_UNSET_CONTAINER:
+		ret = vfio_group_unset_container(group);
+		break;
+	case VFIO_GROUP_GET_DEVICE_FD:
+	{
+		char *buf;
+
+		buf = strndup_user((const char __user *)arg, PAGE_SIZE);
+		if (IS_ERR(buf))
+			return PTR_ERR(buf);
+
+		ret = vfio_group_get_device_fd(group, buf);
+		kfree(buf);
+		break;
+	}
+	}
+
+	return ret;
+}
+
+#ifdef CONFIG_COMPAT
+static long vfio_group_fops_compat_ioctl(struct file *filep,
+					 unsigned int cmd, unsigned long arg)
+{
+	arg = (unsigned long)compat_ptr(arg);
+	return vfio_group_fops_unl_ioctl(filep, cmd, arg);
+}
+#endif	/* CONFIG_COMPAT */
+
+static int vfio_group_fops_open(struct inode *inode, struct file *filep)
+{
+	struct vfio_group *group;
+	int opened;
+
+	group = vfio_group_get_from_minor(iminor(inode));
+	if (!group)
+		return -ENODEV;
+
+	/* Do we need multiple instances of the group open?  Seems not. */
+	opened = atomic_cmpxchg(&group->opened, 0, 1);
+	if (opened) {
+		vfio_group_put(group);
+		return -EBUSY;
+	}
+
+	/* Is something still in use from a previous open? */
+	if (group->container) {
+		atomic_dec(&group->opened);
+		vfio_group_put(group);
+		return -EBUSY;
+	}
+
+	filep->private_data = group;
+
+	return 0;
+}
+
+static int vfio_group_fops_release(struct inode *inode, struct file *filep)
+{
+	struct vfio_group *group = filep->private_data;
+
+	filep->private_data = NULL;
+
+	vfio_group_try_dissolve_container(group);
+
+	atomic_dec(&group->opened);
+
+	vfio_group_put(group);
+
+	return 0;
+}
+
+static const struct file_operations vfio_group_fops = {
+	.owner		= THIS_MODULE,
+	.unlocked_ioctl	= vfio_group_fops_unl_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= vfio_group_fops_compat_ioctl,
+#endif
+	.open		= vfio_group_fops_open,
+	.release	= vfio_group_fops_release,
+};
+
+/**
+ * VFIO Device fd
+ */
+static int vfio_device_fops_release(struct inode *inode, struct file *filep)
+{
+	struct vfio_device *device = filep->private_data;
+
+	device->ops->release(device->device_data);
+
+	vfio_group_try_dissolve_container(device->group);
+
+	vfio_device_put(device);
+
+	return 0;
+}
+
+static long vfio_device_fops_unl_ioctl(struct file *filep,
+				       unsigned int cmd, unsigned long arg)
+{
+	struct vfio_device *device = filep->private_data;
+
+	if (unlikely(!device->ops->ioctl))
+		return -EINVAL;
+
+	return device->ops->ioctl(device->device_data, cmd, arg);
+}
+
+static ssize_t vfio_device_fops_read(struct file *filep, char __user *buf,
+				     size_t count, loff_t *ppos)
+{
+	struct vfio_device *device = filep->private_data;
+
+	if (unlikely(!device->ops->read))
+		return -EINVAL;
+
+	return device->ops->read(device->device_data, buf, count, ppos);
+}
+
+static ssize_t vfio_device_fops_write(struct file *filep,
+				      const char __user *buf,
+				      size_t count, loff_t *ppos)
+{
+	struct vfio_device *device = filep->private_data;
+
+	if (unlikely(!device->ops->write))
+		return -EINVAL;
+
+	return device->ops->write(device->device_data, buf, count, ppos);
+}
+
+static int vfio_device_fops_mmap(struct file *filep, struct vm_area_struct *vma)
+{
+	struct vfio_device *device = filep->private_data;
+
+	if (unlikely(!device->ops->mmap))
+		return -EINVAL;
+
+	return device->ops->mmap(device->device_data, vma);
+}
+
+#ifdef CONFIG_COMPAT
+static long vfio_device_fops_compat_ioctl(struct file *filep,
+					  unsigned int cmd, unsigned long arg)
+{
+	arg = (unsigned long)compat_ptr(arg);
+	return vfio_device_fops_unl_ioctl(filep, cmd, arg);
+}
+#endif	/* CONFIG_COMPAT */
+
+static const struct file_operations vfio_device_fops = {
+	.owner		= THIS_MODULE,
+	.release	= vfio_device_fops_release,
+	.read		= vfio_device_fops_read,
+	.write		= vfio_device_fops_write,
+	.unlocked_ioctl	= vfio_device_fops_unl_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= vfio_device_fops_compat_ioctl,
+#endif
+	.mmap		= vfio_device_fops_mmap,
+};
+
+/**
+ * External user API, exported by symbols to be linked dynamically.
+ *
+ * The protocol includes:
+ *  1. do normal VFIO init operation:
+ *	- opening a new container;
+ *	- attaching group(s) to it;
+ *	- setting an IOMMU driver for a container.
+ * When IOMMU is set for a container, all groups in it are
+ * considered ready to use by an external user.
+ *
+ * 2. User space passes a group fd to an external user.
+ * The external user calls vfio_group_get_external_user()
+ * to verify that:
+ *	- the group is initialized;
+ *	- IOMMU is set for it.
+ * If both checks passed, vfio_group_get_external_user()
+ * increments the container user counter to prevent
+ * the VFIO group from disposal before KVM exits.
+ *
+ * 3. The external user calls vfio_external_user_iommu_id()
+ * to know an IOMMU ID.
+ *
+ * 4. When the external KVM finishes, it calls
+ * vfio_group_put_external_user() to release the VFIO group.
+ * This call decrements the container user counter.
+ */
+struct vfio_group *vfio_group_get_external_user(struct file *filep)
+{
+	struct vfio_group *group = filep->private_data;
+
+	if (filep->f_op != &vfio_group_fops)
+		return ERR_PTR(-EINVAL);
+
+	if (!atomic_inc_not_zero(&group->container_users))
+		return ERR_PTR(-EINVAL);
+
+	if (!group->container->iommu_driver ||
+			!vfio_group_viable(group)) {
+		atomic_dec(&group->container_users);
+		return ERR_PTR(-EINVAL);
+	}
+
+	vfio_group_get(group);
+
+	return group;
+}
+EXPORT_SYMBOL_GPL(vfio_group_get_external_user);
+
+void vfio_group_put_external_user(struct vfio_group *group)
+{
+	vfio_group_put(group);
+	vfio_group_try_dissolve_container(group);
+}
+EXPORT_SYMBOL_GPL(vfio_group_put_external_user);
+
+int vfio_external_user_iommu_id(struct vfio_group *group)
+{
+	return iommu_group_id(group->iommu_group);
+}
+EXPORT_SYMBOL_GPL(vfio_external_user_iommu_id);
+
+long vfio_external_check_extension(struct vfio_group *group, unsigned long arg)
+{
+	return vfio_ioctl_check_extension(group->container, arg);
+}
+EXPORT_SYMBOL_GPL(vfio_external_check_extension);
+
+/**
+ * Module/class support
+ */
+static char *vfio_devnode(struct device *dev, umode_t *mode)
+{
+	return kasprintf(GFP_KERNEL, "vfio/%s", dev_name(dev));
+}
+
+static struct miscdevice vfio_dev = {
+	.minor = VFIO_MINOR,
+	.name = "vfio",
+	.fops = &vfio_fops,
+	.nodename = "vfio/vfio",
+	.mode = S_IRUGO | S_IWUGO,
+};
+
+static int __init vfio_init(void)
+{
+	int ret;
+
+	idr_init(&vfio.group_idr);
+	mutex_init(&vfio.group_lock);
+	mutex_init(&vfio.iommu_drivers_lock);
+	INIT_LIST_HEAD(&vfio.group_list);
+	INIT_LIST_HEAD(&vfio.iommu_drivers_list);
+	init_waitqueue_head(&vfio.release_q);
+
+	ret = misc_register(&vfio_dev);
+	if (ret) {
+		pr_err("vfio: misc device register failed\n");
+		return ret;
+	}
+
+	/* /dev/vfio/$GROUP */
+	vfio.class = class_create(THIS_MODULE, "vfio");
+	if (IS_ERR(vfio.class)) {
+		ret = PTR_ERR(vfio.class);
+		goto err_class;
+	}
+
+	vfio.class->devnode = vfio_devnode;
+
+	ret = alloc_chrdev_region(&vfio.group_devt, 0, MINORMASK, "vfio");
+	if (ret)
+		goto err_alloc_chrdev;
+
+	cdev_init(&vfio.group_cdev, &vfio_group_fops);
+	ret = cdev_add(&vfio.group_cdev, vfio.group_devt, MINORMASK);
+	if (ret)
+		goto err_cdev_add;
+
+	pr_info(DRIVER_DESC " version: " DRIVER_VERSION "\n");
+
+	/*
+	 * Attempt to load known iommu-drivers.  This gives us a working
+	 * environment without the user needing to explicitly load iommu
+	 * drivers.
+	 */
+	request_module_nowait("vfio_iommu_type1");
+	request_module_nowait("vfio_iommu_spapr_tce");
+
+	return 0;
+
+err_cdev_add:
+	unregister_chrdev_region(vfio.group_devt, MINORMASK);
+err_alloc_chrdev:
+	class_destroy(vfio.class);
+	vfio.class = NULL;
+err_class:
+	misc_deregister(&vfio_dev);
+	return ret;
+}
+
+static void __exit vfio_cleanup(void)
+{
+	WARN_ON(!list_empty(&vfio.group_list));
+
+	idr_destroy(&vfio.group_idr);
+	cdev_del(&vfio.group_cdev);
+	unregister_chrdev_region(vfio.group_devt, MINORMASK);
+	class_destroy(vfio.class);
+	vfio.class = NULL;
+	misc_deregister(&vfio_dev);
+}
+
+module_init(vfio_init);
+module_exit(vfio_cleanup);
+
+MODULE_VERSION(DRIVER_VERSION);
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
+MODULE_ALIAS_MISCDEV(VFIO_MINOR);
+MODULE_ALIAS("devname:vfio/vfio");
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
new file mode 100644
index 000000000..730b4ef3e
--- /dev/null
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -0,0 +1,392 @@
+/*
+ * VFIO: IOMMU DMA mapping support for TCE on POWER
+ *
+ * Copyright (C) 2013 IBM Corp.  All rights reserved.
+ *     Author: Alexey Kardashevskiy <aik@ozlabs.ru>
+ *
+ * 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.
+ *
+ * Derived from original vfio_iommu_type1.c:
+ * Copyright (C) 2012 Red Hat, Inc.  All rights reserved.
+ *     Author: Alex Williamson <alex.williamson@redhat.com>
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/err.h>
+#include <linux/vfio.h>
+#include <asm/iommu.h>
+#include <asm/tce.h>
+
+#define DRIVER_VERSION  "0.1"
+#define DRIVER_AUTHOR   "aik@ozlabs.ru"
+#define DRIVER_DESC     "VFIO IOMMU SPAPR TCE"
+
+static void tce_iommu_detach_group(void *iommu_data,
+		struct iommu_group *iommu_group);
+
+/*
+ * VFIO IOMMU fd for SPAPR_TCE IOMMU implementation
+ *
+ * This code handles mapping and unmapping of user data buffers
+ * into DMA'ble space using the IOMMU
+ */
+
+/*
+ * The container descriptor supports only a single group per container.
+ * Required by the API as the container is not supplied with the IOMMU group
+ * at the moment of initialization.
+ */
+struct tce_container {
+	struct mutex lock;
+	struct iommu_table *tbl;
+	bool enabled;
+};
+
+static int tce_iommu_enable(struct tce_container *container)
+{
+	int ret = 0;
+	unsigned long locked, lock_limit, npages;
+	struct iommu_table *tbl = container->tbl;
+
+	if (!container->tbl)
+		return -ENXIO;
+
+	if (!current->mm)
+		return -ESRCH; /* process exited */
+
+	if (container->enabled)
+		return -EBUSY;
+
+	/*
+	 * When userspace pages are mapped into the IOMMU, they are effectively
+	 * locked memory, so, theoretically, we need to update the accounting
+	 * of locked pages on each map and unmap.  For powerpc, the map unmap
+	 * paths can be very hot, though, and the accounting would kill
+	 * performance, especially since it would be difficult to impossible
+	 * to handle the accounting in real mode only.
+	 *
+	 * To address that, rather than precisely accounting every page, we
+	 * instead account for a worst case on locked memory when the iommu is
+	 * enabled and disabled.  The worst case upper bound on locked memory
+	 * is the size of the whole iommu window, which is usually relatively
+	 * small (compared to total memory sizes) on POWER hardware.
+	 *
+	 * Also we don't have a nice way to fail on H_PUT_TCE due to ulimits,
+	 * that would effectively kill the guest at random points, much better
+	 * enforcing the limit based on the max that the guest can map.
+	 */
+	down_write(&current->mm->mmap_sem);
+	npages = (tbl->it_size << IOMMU_PAGE_SHIFT_4K) >> PAGE_SHIFT;
+	locked = current->mm->locked_vm + npages;
+	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+	if (locked > lock_limit && !capable(CAP_IPC_LOCK)) {
+		pr_warn("RLIMIT_MEMLOCK (%ld) exceeded\n",
+				rlimit(RLIMIT_MEMLOCK));
+		ret = -ENOMEM;
+	} else {
+
+		current->mm->locked_vm += npages;
+		container->enabled = true;
+	}
+	up_write(&current->mm->mmap_sem);
+
+	return ret;
+}
+
+static void tce_iommu_disable(struct tce_container *container)
+{
+	if (!container->enabled)
+		return;
+
+	container->enabled = false;
+
+	if (!container->tbl || !current->mm)
+		return;
+
+	down_write(&current->mm->mmap_sem);
+	current->mm->locked_vm -= (container->tbl->it_size <<
+			IOMMU_PAGE_SHIFT_4K) >> PAGE_SHIFT;
+	up_write(&current->mm->mmap_sem);
+}
+
+static void *tce_iommu_open(unsigned long arg)
+{
+	struct tce_container *container;
+
+	if (arg != VFIO_SPAPR_TCE_IOMMU) {
+		pr_err("tce_vfio: Wrong IOMMU type\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	container = kzalloc(sizeof(*container), GFP_KERNEL);
+	if (!container)
+		return ERR_PTR(-ENOMEM);
+
+	mutex_init(&container->lock);
+
+	return container;
+}
+
+static void tce_iommu_release(void *iommu_data)
+{
+	struct tce_container *container = iommu_data;
+
+	WARN_ON(container->tbl && !container->tbl->it_group);
+	tce_iommu_disable(container);
+
+	if (container->tbl && container->tbl->it_group)
+		tce_iommu_detach_group(iommu_data, container->tbl->it_group);
+
+	mutex_destroy(&container->lock);
+
+	kfree(container);
+}
+
+static long tce_iommu_ioctl(void *iommu_data,
+				 unsigned int cmd, unsigned long arg)
+{
+	struct tce_container *container = iommu_data;
+	unsigned long minsz;
+	long ret;
+
+	switch (cmd) {
+	case VFIO_CHECK_EXTENSION:
+		switch (arg) {
+		case VFIO_SPAPR_TCE_IOMMU:
+			ret = 1;
+			break;
+		default:
+			ret = vfio_spapr_iommu_eeh_ioctl(NULL, cmd, arg);
+			break;
+		}
+
+		return (ret < 0) ? 0 : ret;
+
+	case VFIO_IOMMU_SPAPR_TCE_GET_INFO: {
+		struct vfio_iommu_spapr_tce_info info;
+		struct iommu_table *tbl = container->tbl;
+
+		if (WARN_ON(!tbl))
+			return -ENXIO;
+
+		minsz = offsetofend(struct vfio_iommu_spapr_tce_info,
+				dma32_window_size);
+
+		if (copy_from_user(&info, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (info.argsz < minsz)
+			return -EINVAL;
+
+		info.dma32_window_start = tbl->it_offset << IOMMU_PAGE_SHIFT_4K;
+		info.dma32_window_size = tbl->it_size << IOMMU_PAGE_SHIFT_4K;
+		info.flags = 0;
+
+		if (copy_to_user((void __user *)arg, &info, minsz))
+			return -EFAULT;
+
+		return 0;
+	}
+	case VFIO_IOMMU_MAP_DMA: {
+		struct vfio_iommu_type1_dma_map param;
+		struct iommu_table *tbl = container->tbl;
+		unsigned long tce, i;
+
+		if (!tbl)
+			return -ENXIO;
+
+		BUG_ON(!tbl->it_group);
+
+		minsz = offsetofend(struct vfio_iommu_type1_dma_map, size);
+
+		if (copy_from_user(&param, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (param.argsz < minsz)
+			return -EINVAL;
+
+		if (param.flags & ~(VFIO_DMA_MAP_FLAG_READ |
+				VFIO_DMA_MAP_FLAG_WRITE))
+			return -EINVAL;
+
+		if ((param.size & ~IOMMU_PAGE_MASK_4K) ||
+				(param.vaddr & ~IOMMU_PAGE_MASK_4K))
+			return -EINVAL;
+
+		/* iova is checked by the IOMMU API */
+		tce = param.vaddr;
+		if (param.flags & VFIO_DMA_MAP_FLAG_READ)
+			tce |= TCE_PCI_READ;
+		if (param.flags & VFIO_DMA_MAP_FLAG_WRITE)
+			tce |= TCE_PCI_WRITE;
+
+		ret = iommu_tce_put_param_check(tbl, param.iova, tce);
+		if (ret)
+			return ret;
+
+		for (i = 0; i < (param.size >> IOMMU_PAGE_SHIFT_4K); ++i) {
+			ret = iommu_put_tce_user_mode(tbl,
+					(param.iova >> IOMMU_PAGE_SHIFT_4K) + i,
+					tce);
+			if (ret)
+				break;
+			tce += IOMMU_PAGE_SIZE_4K;
+		}
+		if (ret)
+			iommu_clear_tces_and_put_pages(tbl,
+					param.iova >> IOMMU_PAGE_SHIFT_4K, i);
+
+		iommu_flush_tce(tbl);
+
+		return ret;
+	}
+	case VFIO_IOMMU_UNMAP_DMA: {
+		struct vfio_iommu_type1_dma_unmap param;
+		struct iommu_table *tbl = container->tbl;
+
+		if (WARN_ON(!tbl))
+			return -ENXIO;
+
+		minsz = offsetofend(struct vfio_iommu_type1_dma_unmap,
+				size);
+
+		if (copy_from_user(&param, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (param.argsz < minsz)
+			return -EINVAL;
+
+		/* No flag is supported now */
+		if (param.flags)
+			return -EINVAL;
+
+		if (param.size & ~IOMMU_PAGE_MASK_4K)
+			return -EINVAL;
+
+		ret = iommu_tce_clear_param_check(tbl, param.iova, 0,
+				param.size >> IOMMU_PAGE_SHIFT_4K);
+		if (ret)
+			return ret;
+
+		ret = iommu_clear_tces_and_put_pages(tbl,
+				param.iova >> IOMMU_PAGE_SHIFT_4K,
+				param.size >> IOMMU_PAGE_SHIFT_4K);
+		iommu_flush_tce(tbl);
+
+		return ret;
+	}
+	case VFIO_IOMMU_ENABLE:
+		mutex_lock(&container->lock);
+		ret = tce_iommu_enable(container);
+		mutex_unlock(&container->lock);
+		return ret;
+
+
+	case VFIO_IOMMU_DISABLE:
+		mutex_lock(&container->lock);
+		tce_iommu_disable(container);
+		mutex_unlock(&container->lock);
+		return 0;
+	case VFIO_EEH_PE_OP:
+		if (!container->tbl || !container->tbl->it_group)
+			return -ENODEV;
+
+		return vfio_spapr_iommu_eeh_ioctl(container->tbl->it_group,
+						  cmd, arg);
+	}
+
+	return -ENOTTY;
+}
+
+static int tce_iommu_attach_group(void *iommu_data,
+		struct iommu_group *iommu_group)
+{
+	int ret;
+	struct tce_container *container = iommu_data;
+	struct iommu_table *tbl = iommu_group_get_iommudata(iommu_group);
+
+	BUG_ON(!tbl);
+	mutex_lock(&container->lock);
+
+	/* pr_debug("tce_vfio: Attaching group #%u to iommu %p\n",
+			iommu_group_id(iommu_group), iommu_group); */
+	if (container->tbl) {
+		pr_warn("tce_vfio: Only one group per IOMMU container is allowed, existing id=%d, attaching id=%d\n",
+				iommu_group_id(container->tbl->it_group),
+				iommu_group_id(iommu_group));
+		ret = -EBUSY;
+	} else if (container->enabled) {
+		pr_err("tce_vfio: attaching group #%u to enabled container\n",
+				iommu_group_id(iommu_group));
+		ret = -EBUSY;
+	} else {
+		ret = iommu_take_ownership(tbl);
+		if (!ret)
+			container->tbl = tbl;
+	}
+
+	mutex_unlock(&container->lock);
+
+	return ret;
+}
+
+static void tce_iommu_detach_group(void *iommu_data,
+		struct iommu_group *iommu_group)
+{
+	struct tce_container *container = iommu_data;
+	struct iommu_table *tbl = iommu_group_get_iommudata(iommu_group);
+
+	BUG_ON(!tbl);
+	mutex_lock(&container->lock);
+	if (tbl != container->tbl) {
+		pr_warn("tce_vfio: detaching group #%u, expected group is #%u\n",
+				iommu_group_id(iommu_group),
+				iommu_group_id(tbl->it_group));
+	} else {
+		if (container->enabled) {
+			pr_warn("tce_vfio: detaching group #%u from enabled container, forcing disable\n",
+					iommu_group_id(tbl->it_group));
+			tce_iommu_disable(container);
+		}
+
+		/* pr_debug("tce_vfio: detaching group #%u from iommu %p\n",
+				iommu_group_id(iommu_group), iommu_group); */
+		container->tbl = NULL;
+		iommu_release_ownership(tbl);
+	}
+	mutex_unlock(&container->lock);
+}
+
+const struct vfio_iommu_driver_ops tce_iommu_driver_ops = {
+	.name		= "iommu-vfio-powerpc",
+	.owner		= THIS_MODULE,
+	.open		= tce_iommu_open,
+	.release	= tce_iommu_release,
+	.ioctl		= tce_iommu_ioctl,
+	.attach_group	= tce_iommu_attach_group,
+	.detach_group	= tce_iommu_detach_group,
+};
+
+static int __init tce_iommu_init(void)
+{
+	return vfio_register_iommu_driver(&tce_iommu_driver_ops);
+}
+
+static void __exit tce_iommu_cleanup(void)
+{
+	vfio_unregister_iommu_driver(&tce_iommu_driver_ops);
+}
+
+module_init(tce_iommu_init);
+module_exit(tce_iommu_cleanup);
+
+MODULE_VERSION(DRIVER_VERSION);
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
+
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
new file mode 100644
index 000000000..57d8c37a0
--- /dev/null
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -0,0 +1,1054 @@
+/*
+ * VFIO: IOMMU DMA mapping support for Type1 IOMMU
+ *
+ * Copyright (C) 2012 Red Hat, Inc.  All rights reserved.
+ *     Author: Alex Williamson <alex.williamson@redhat.com>
+ *
+ * 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.
+ *
+ * Derived from original vfio:
+ * Copyright 2010 Cisco Systems, Inc.  All rights reserved.
+ * Author: Tom Lyon, pugs@cisco.com
+ *
+ * We arbitrarily define a Type1 IOMMU as one matching the below code.
+ * It could be called the x86 IOMMU as it's designed for AMD-Vi & Intel
+ * VT-d, but that makes it harder to re-use as theoretically anyone
+ * implementing a similar IOMMU could make use of this.  We expect the
+ * IOMMU to support the IOMMU API and have few to no restrictions around
+ * the IOVA range that can be mapped.  The Type1 IOMMU is currently
+ * optimized for relatively static mappings of a userspace process with
+ * userpsace pages pinned into memory.  We also assume devices and IOMMU
+ * domains are PCI based as the IOMMU API is still centered around a
+ * device/bus interface rather than a group interface.
+ */
+
+#include <linux/compat.h>
+#include <linux/device.h>
+#include <linux/fs.h>
+#include <linux/iommu.h>
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/rbtree.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/vfio.h>
+#include <linux/workqueue.h>
+
+#define DRIVER_VERSION  "0.2"
+#define DRIVER_AUTHOR   "Alex Williamson <alex.williamson@redhat.com>"
+#define DRIVER_DESC     "Type1 IOMMU driver for VFIO"
+
+static bool allow_unsafe_interrupts;
+module_param_named(allow_unsafe_interrupts,
+		   allow_unsafe_interrupts, bool, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(allow_unsafe_interrupts,
+		 "Enable VFIO IOMMU support for on platforms without interrupt remapping support.");
+
+static bool disable_hugepages;
+module_param_named(disable_hugepages,
+		   disable_hugepages, bool, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(disable_hugepages,
+		 "Disable VFIO IOMMU support for IOMMU hugepages.");
+
+struct vfio_iommu {
+	struct list_head	domain_list;
+	struct mutex		lock;
+	struct rb_root		dma_list;
+	bool			v2;
+	bool			nesting;
+};
+
+struct vfio_domain {
+	struct iommu_domain	*domain;
+	struct list_head	next;
+	struct list_head	group_list;
+	int			prot;		/* IOMMU_CACHE */
+	bool			fgsp;		/* Fine-grained super pages */
+};
+
+struct vfio_dma {
+	struct rb_node		node;
+	dma_addr_t		iova;		/* Device address */
+	unsigned long		vaddr;		/* Process virtual addr */
+	size_t			size;		/* Map size (bytes) */
+	int			prot;		/* IOMMU_READ/WRITE */
+};
+
+struct vfio_group {
+	struct iommu_group	*iommu_group;
+	struct list_head	next;
+};
+
+/*
+ * This code handles mapping and unmapping of user data buffers
+ * into DMA'ble space using the IOMMU
+ */
+
+static struct vfio_dma *vfio_find_dma(struct vfio_iommu *iommu,
+				      dma_addr_t start, size_t size)
+{
+	struct rb_node *node = iommu->dma_list.rb_node;
+
+	while (node) {
+		struct vfio_dma *dma = rb_entry(node, struct vfio_dma, node);
+
+		if (start + size <= dma->iova)
+			node = node->rb_left;
+		else if (start >= dma->iova + dma->size)
+			node = node->rb_right;
+		else
+			return dma;
+	}
+
+	return NULL;
+}
+
+static void vfio_link_dma(struct vfio_iommu *iommu, struct vfio_dma *new)
+{
+	struct rb_node **link = &iommu->dma_list.rb_node, *parent = NULL;
+	struct vfio_dma *dma;
+
+	while (*link) {
+		parent = *link;
+		dma = rb_entry(parent, struct vfio_dma, node);
+
+		if (new->iova + new->size <= dma->iova)
+			link = &(*link)->rb_left;
+		else
+			link = &(*link)->rb_right;
+	}
+
+	rb_link_node(&new->node, parent, link);
+	rb_insert_color(&new->node, &iommu->dma_list);
+}
+
+static void vfio_unlink_dma(struct vfio_iommu *iommu, struct vfio_dma *old)
+{
+	rb_erase(&old->node, &iommu->dma_list);
+}
+
+struct vwork {
+	struct mm_struct	*mm;
+	long			npage;
+	struct work_struct	work;
+};
+
+/* delayed decrement/increment for locked_vm */
+static void vfio_lock_acct_bg(struct work_struct *work)
+{
+	struct vwork *vwork = container_of(work, struct vwork, work);
+	struct mm_struct *mm;
+
+	mm = vwork->mm;
+	down_write(&mm->mmap_sem);
+	mm->locked_vm += vwork->npage;
+	up_write(&mm->mmap_sem);
+	mmput(mm);
+	kfree(vwork);
+}
+
+static void vfio_lock_acct(long npage)
+{
+	struct vwork *vwork;
+	struct mm_struct *mm;
+
+	if (!current->mm || !npage)
+		return; /* process exited or nothing to do */
+
+	if (down_write_trylock(&current->mm->mmap_sem)) {
+		current->mm->locked_vm += npage;
+		up_write(&current->mm->mmap_sem);
+		return;
+	}
+
+	/*
+	 * Couldn't get mmap_sem lock, so must setup to update
+	 * mm->locked_vm later. If locked_vm were atomic, we
+	 * wouldn't need this silliness
+	 */
+	vwork = kmalloc(sizeof(struct vwork), GFP_KERNEL);
+	if (!vwork)
+		return;
+	mm = get_task_mm(current);
+	if (!mm) {
+		kfree(vwork);
+		return;
+	}
+	INIT_WORK(&vwork->work, vfio_lock_acct_bg);
+	vwork->mm = mm;
+	vwork->npage = npage;
+	schedule_work(&vwork->work);
+}
+
+/*
+ * Some mappings aren't backed by a struct page, for example an mmap'd
+ * MMIO range for our own or another device.  These use a different
+ * pfn conversion and shouldn't be tracked as locked pages.
+ */
+static bool is_invalid_reserved_pfn(unsigned long pfn)
+{
+	if (pfn_valid(pfn)) {
+		bool reserved;
+		struct page *tail = pfn_to_page(pfn);
+		struct page *head = compound_head(tail);
+		reserved = !!(PageReserved(head));
+		if (head != tail) {
+			/*
+			 * "head" is not a dangling pointer
+			 * (compound_head takes care of that)
+			 * but the hugepage may have been split
+			 * from under us (and we may not hold a
+			 * reference count on the head page so it can
+			 * be reused before we run PageReferenced), so
+			 * we've to check PageTail before returning
+			 * what we just read.
+			 */
+			smp_rmb();
+			if (PageTail(tail))
+				return reserved;
+		}
+		return PageReserved(tail);
+	}
+
+	return true;
+}
+
+static int put_pfn(unsigned long pfn, int prot)
+{
+	if (!is_invalid_reserved_pfn(pfn)) {
+		struct page *page = pfn_to_page(pfn);
+		if (prot & IOMMU_WRITE)
+			SetPageDirty(page);
+		put_page(page);
+		return 1;
+	}
+	return 0;
+}
+
+static int vaddr_get_pfn(unsigned long vaddr, int prot, unsigned long *pfn)
+{
+	struct page *page[1];
+	struct vm_area_struct *vma;
+	int ret = -EFAULT;
+
+	if (get_user_pages_fast(vaddr, 1, !!(prot & IOMMU_WRITE), page) == 1) {
+		*pfn = page_to_pfn(page[0]);
+		return 0;
+	}
+
+	down_read(&current->mm->mmap_sem);
+
+	vma = find_vma_intersection(current->mm, vaddr, vaddr + 1);
+
+	if (vma && vma->vm_flags & VM_PFNMAP) {
+		*pfn = ((vaddr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
+		if (is_invalid_reserved_pfn(*pfn))
+			ret = 0;
+	}
+
+	up_read(&current->mm->mmap_sem);
+
+	return ret;
+}
+
+/*
+ * Attempt to pin pages.  We really don't want to track all the pfns and
+ * the iommu can only map chunks of consecutive pfns anyway, so get the
+ * first page and all consecutive pages with the same locking.
+ */
+static long vfio_pin_pages(unsigned long vaddr, long npage,
+			   int prot, unsigned long *pfn_base)
+{
+	unsigned long limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+	bool lock_cap = capable(CAP_IPC_LOCK);
+	long ret, i;
+	bool rsvd;
+
+	if (!current->mm)
+		return -ENODEV;
+
+	ret = vaddr_get_pfn(vaddr, prot, pfn_base);
+	if (ret)
+		return ret;
+
+	rsvd = is_invalid_reserved_pfn(*pfn_base);
+
+	if (!rsvd && !lock_cap && current->mm->locked_vm + 1 > limit) {
+		put_pfn(*pfn_base, prot);
+		pr_warn("%s: RLIMIT_MEMLOCK (%ld) exceeded\n", __func__,
+			limit << PAGE_SHIFT);
+		return -ENOMEM;
+	}
+
+	if (unlikely(disable_hugepages)) {
+		if (!rsvd)
+			vfio_lock_acct(1);
+		return 1;
+	}
+
+	/* Lock all the consecutive pages from pfn_base */
+	for (i = 1, vaddr += PAGE_SIZE; i < npage; i++, vaddr += PAGE_SIZE) {
+		unsigned long pfn = 0;
+
+		ret = vaddr_get_pfn(vaddr, prot, &pfn);
+		if (ret)
+			break;
+
+		if (pfn != *pfn_base + i ||
+		    rsvd != is_invalid_reserved_pfn(pfn)) {
+			put_pfn(pfn, prot);
+			break;
+		}
+
+		if (!rsvd && !lock_cap &&
+		    current->mm->locked_vm + i + 1 > limit) {
+			put_pfn(pfn, prot);
+			pr_warn("%s: RLIMIT_MEMLOCK (%ld) exceeded\n",
+				__func__, limit << PAGE_SHIFT);
+			break;
+		}
+	}
+
+	if (!rsvd)
+		vfio_lock_acct(i);
+
+	return i;
+}
+
+static long vfio_unpin_pages(unsigned long pfn, long npage,
+			     int prot, bool do_accounting)
+{
+	unsigned long unlocked = 0;
+	long i;
+
+	for (i = 0; i < npage; i++)
+		unlocked += put_pfn(pfn++, prot);
+
+	if (do_accounting)
+		vfio_lock_acct(-unlocked);
+
+	return unlocked;
+}
+
+static void vfio_unmap_unpin(struct vfio_iommu *iommu, struct vfio_dma *dma)
+{
+	dma_addr_t iova = dma->iova, end = dma->iova + dma->size;
+	struct vfio_domain *domain, *d;
+	long unlocked = 0;
+
+	if (!dma->size)
+		return;
+	/*
+	 * We use the IOMMU to track the physical addresses, otherwise we'd
+	 * need a much more complicated tracking system.  Unfortunately that
+	 * means we need to use one of the iommu domains to figure out the
+	 * pfns to unpin.  The rest need to be unmapped in advance so we have
+	 * no iommu translations remaining when the pages are unpinned.
+	 */
+	domain = d = list_first_entry(&iommu->domain_list,
+				      struct vfio_domain, next);
+
+	list_for_each_entry_continue(d, &iommu->domain_list, next) {
+		iommu_unmap(d->domain, dma->iova, dma->size);
+		cond_resched();
+	}
+
+	while (iova < end) {
+		size_t unmapped, len;
+		phys_addr_t phys, next;
+
+		phys = iommu_iova_to_phys(domain->domain, iova);
+		if (WARN_ON(!phys)) {
+			iova += PAGE_SIZE;
+			continue;
+		}
+
+		/*
+		 * To optimize for fewer iommu_unmap() calls, each of which
+		 * may require hardware cache flushing, try to find the
+		 * largest contiguous physical memory chunk to unmap.
+		 */
+		for (len = PAGE_SIZE;
+		     !domain->fgsp && iova + len < end; len += PAGE_SIZE) {
+			next = iommu_iova_to_phys(domain->domain, iova + len);
+			if (next != phys + len)
+				break;
+		}
+
+		unmapped = iommu_unmap(domain->domain, iova, len);
+		if (WARN_ON(!unmapped))
+			break;
+
+		unlocked += vfio_unpin_pages(phys >> PAGE_SHIFT,
+					     unmapped >> PAGE_SHIFT,
+					     dma->prot, false);
+		iova += unmapped;
+
+		cond_resched();
+	}
+
+	vfio_lock_acct(-unlocked);
+}
+
+static void vfio_remove_dma(struct vfio_iommu *iommu, struct vfio_dma *dma)
+{
+	vfio_unmap_unpin(iommu, dma);
+	vfio_unlink_dma(iommu, dma);
+	kfree(dma);
+}
+
+static unsigned long vfio_pgsize_bitmap(struct vfio_iommu *iommu)
+{
+	struct vfio_domain *domain;
+	unsigned long bitmap = PAGE_MASK;
+
+	mutex_lock(&iommu->lock);
+	list_for_each_entry(domain, &iommu->domain_list, next)
+		bitmap &= domain->domain->ops->pgsize_bitmap;
+	mutex_unlock(&iommu->lock);
+
+	return bitmap;
+}
+
+static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
+			     struct vfio_iommu_type1_dma_unmap *unmap)
+{
+	uint64_t mask;
+	struct vfio_dma *dma;
+	size_t unmapped = 0;
+	int ret = 0;
+
+	mask = ((uint64_t)1 << __ffs(vfio_pgsize_bitmap(iommu))) - 1;
+
+	if (unmap->iova & mask)
+		return -EINVAL;
+	if (!unmap->size || unmap->size & mask)
+		return -EINVAL;
+
+	WARN_ON(mask & PAGE_MASK);
+
+	mutex_lock(&iommu->lock);
+
+	/*
+	 * vfio-iommu-type1 (v1) - User mappings were coalesced together to
+	 * avoid tracking individual mappings.  This means that the granularity
+	 * of the original mapping was lost and the user was allowed to attempt
+	 * to unmap any range.  Depending on the contiguousness of physical
+	 * memory and page sizes supported by the IOMMU, arbitrary unmaps may
+	 * or may not have worked.  We only guaranteed unmap granularity
+	 * matching the original mapping; even though it was untracked here,
+	 * the original mappings are reflected in IOMMU mappings.  This
+	 * resulted in a couple unusual behaviors.  First, if a range is not
+	 * able to be unmapped, ex. a set of 4k pages that was mapped as a
+	 * 2M hugepage into the IOMMU, the unmap ioctl returns success but with
+	 * a zero sized unmap.  Also, if an unmap request overlaps the first
+	 * address of a hugepage, the IOMMU will unmap the entire hugepage.
+	 * This also returns success and the returned unmap size reflects the
+	 * actual size unmapped.
+	 *
+	 * We attempt to maintain compatibility with this "v1" interface, but
+	 * we take control out of the hands of the IOMMU.  Therefore, an unmap
+	 * request offset from the beginning of the original mapping will
+	 * return success with zero sized unmap.  And an unmap request covering
+	 * the first iova of mapping will unmap the entire range.
+	 *
+	 * The v2 version of this interface intends to be more deterministic.
+	 * Unmap requests must fully cover previous mappings.  Multiple
+	 * mappings may still be unmaped by specifying large ranges, but there
+	 * must not be any previous mappings bisected by the range.  An error
+	 * will be returned if these conditions are not met.  The v2 interface
+	 * will only return success and a size of zero if there were no
+	 * mappings within the range.
+	 */
+	if (iommu->v2) {
+		dma = vfio_find_dma(iommu, unmap->iova, 0);
+		if (dma && dma->iova != unmap->iova) {
+			ret = -EINVAL;
+			goto unlock;
+		}
+		dma = vfio_find_dma(iommu, unmap->iova + unmap->size - 1, 0);
+		if (dma && dma->iova + dma->size != unmap->iova + unmap->size) {
+			ret = -EINVAL;
+			goto unlock;
+		}
+	}
+
+	while ((dma = vfio_find_dma(iommu, unmap->iova, unmap->size))) {
+		if (!iommu->v2 && unmap->iova > dma->iova)
+			break;
+		unmapped += dma->size;
+		vfio_remove_dma(iommu, dma);
+	}
+
+unlock:
+	mutex_unlock(&iommu->lock);
+
+	/* Report how much was unmapped */
+	unmap->size = unmapped;
+
+	return ret;
+}
+
+/*
+ * Turns out AMD IOMMU has a page table bug where it won't map large pages
+ * to a region that previously mapped smaller pages.  This should be fixed
+ * soon, so this is just a temporary workaround to break mappings down into
+ * PAGE_SIZE.  Better to map smaller pages than nothing.
+ */
+static int map_try_harder(struct vfio_domain *domain, dma_addr_t iova,
+			  unsigned long pfn, long npage, int prot)
+{
+	long i;
+	int ret;
+
+	for (i = 0; i < npage; i++, pfn++, iova += PAGE_SIZE) {
+		ret = iommu_map(domain->domain, iova,
+				(phys_addr_t)pfn << PAGE_SHIFT,
+				PAGE_SIZE, prot | domain->prot);
+		if (ret)
+			break;
+	}
+
+	for (; i < npage && i > 0; i--, iova -= PAGE_SIZE)
+		iommu_unmap(domain->domain, iova, PAGE_SIZE);
+
+	return ret;
+}
+
+static int vfio_iommu_map(struct vfio_iommu *iommu, dma_addr_t iova,
+			  unsigned long pfn, long npage, int prot)
+{
+	struct vfio_domain *d;
+	int ret;
+
+	list_for_each_entry(d, &iommu->domain_list, next) {
+		ret = iommu_map(d->domain, iova, (phys_addr_t)pfn << PAGE_SHIFT,
+				npage << PAGE_SHIFT, prot | d->prot);
+		if (ret) {
+			if (ret != -EBUSY ||
+			    map_try_harder(d, iova, pfn, npage, prot))
+				goto unwind;
+		}
+
+		cond_resched();
+	}
+
+	return 0;
+
+unwind:
+	list_for_each_entry_continue_reverse(d, &iommu->domain_list, next)
+		iommu_unmap(d->domain, iova, npage << PAGE_SHIFT);
+
+	return ret;
+}
+
+static int vfio_dma_do_map(struct vfio_iommu *iommu,
+			   struct vfio_iommu_type1_dma_map *map)
+{
+	dma_addr_t iova = map->iova;
+	unsigned long vaddr = map->vaddr;
+	size_t size = map->size;
+	long npage;
+	int ret = 0, prot = 0;
+	uint64_t mask;
+	struct vfio_dma *dma;
+	unsigned long pfn;
+
+	/* Verify that none of our __u64 fields overflow */
+	if (map->size != size || map->vaddr != vaddr || map->iova != iova)
+		return -EINVAL;
+
+	mask = ((uint64_t)1 << __ffs(vfio_pgsize_bitmap(iommu))) - 1;
+
+	WARN_ON(mask & PAGE_MASK);
+
+	/* READ/WRITE from device perspective */
+	if (map->flags & VFIO_DMA_MAP_FLAG_WRITE)
+		prot |= IOMMU_WRITE;
+	if (map->flags & VFIO_DMA_MAP_FLAG_READ)
+		prot |= IOMMU_READ;
+
+	if (!prot || !size || (size | iova | vaddr) & mask)
+		return -EINVAL;
+
+	/* Don't allow IOVA or virtual address wrap */
+	if (iova + size - 1 < iova || vaddr + size - 1 < vaddr)
+		return -EINVAL;
+
+	mutex_lock(&iommu->lock);
+
+	if (vfio_find_dma(iommu, iova, size)) {
+		mutex_unlock(&iommu->lock);
+		return -EEXIST;
+	}
+
+	dma = kzalloc(sizeof(*dma), GFP_KERNEL);
+	if (!dma) {
+		mutex_unlock(&iommu->lock);
+		return -ENOMEM;
+	}
+
+	dma->iova = iova;
+	dma->vaddr = vaddr;
+	dma->prot = prot;
+
+	/* Insert zero-sized and grow as we map chunks of it */
+	vfio_link_dma(iommu, dma);
+
+	while (size) {
+		/* Pin a contiguous chunk of memory */
+		npage = vfio_pin_pages(vaddr + dma->size,
+				       size >> PAGE_SHIFT, prot, &pfn);
+		if (npage <= 0) {
+			WARN_ON(!npage);
+			ret = (int)npage;
+			break;
+		}
+
+		/* Map it! */
+		ret = vfio_iommu_map(iommu, iova + dma->size, pfn, npage, prot);
+		if (ret) {
+			vfio_unpin_pages(pfn, npage, prot, true);
+			break;
+		}
+
+		size -= npage << PAGE_SHIFT;
+		dma->size += npage << PAGE_SHIFT;
+	}
+
+	if (ret)
+		vfio_remove_dma(iommu, dma);
+
+	mutex_unlock(&iommu->lock);
+	return ret;
+}
+
+static int vfio_bus_type(struct device *dev, void *data)
+{
+	struct bus_type **bus = data;
+
+	if (*bus && *bus != dev->bus)
+		return -EINVAL;
+
+	*bus = dev->bus;
+
+	return 0;
+}
+
+static int vfio_iommu_replay(struct vfio_iommu *iommu,
+			     struct vfio_domain *domain)
+{
+	struct vfio_domain *d;
+	struct rb_node *n;
+	int ret;
+
+	/* Arbitrarily pick the first domain in the list for lookups */
+	d = list_first_entry(&iommu->domain_list, struct vfio_domain, next);
+	n = rb_first(&iommu->dma_list);
+
+	/* If there's not a domain, there better not be any mappings */
+	if (WARN_ON(n && !d))
+		return -EINVAL;
+
+	for (; n; n = rb_next(n)) {
+		struct vfio_dma *dma;
+		dma_addr_t iova;
+
+		dma = rb_entry(n, struct vfio_dma, node);
+		iova = dma->iova;
+
+		while (iova < dma->iova + dma->size) {
+			phys_addr_t phys = iommu_iova_to_phys(d->domain, iova);
+			size_t size;
+
+			if (WARN_ON(!phys)) {
+				iova += PAGE_SIZE;
+				continue;
+			}
+
+			size = PAGE_SIZE;
+
+			while (iova + size < dma->iova + dma->size &&
+			       phys + size == iommu_iova_to_phys(d->domain,
+								 iova + size))
+				size += PAGE_SIZE;
+
+			ret = iommu_map(domain->domain, iova, phys,
+					size, dma->prot | domain->prot);
+			if (ret)
+				return ret;
+
+			iova += size;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * We change our unmap behavior slightly depending on whether the IOMMU
+ * supports fine-grained superpages.  IOMMUs like AMD-Vi will use a superpage
+ * for practically any contiguous power-of-two mapping we give it.  This means
+ * we don't need to look for contiguous chunks ourselves to make unmapping
+ * more efficient.  On IOMMUs with coarse-grained super pages, like Intel VT-d
+ * with discrete 2M/1G/512G/1T superpages, identifying contiguous chunks
+ * significantly boosts non-hugetlbfs mappings and doesn't seem to hurt when
+ * hugetlbfs is in use.
+ */
+static void vfio_test_domain_fgsp(struct vfio_domain *domain)
+{
+	struct page *pages;
+	int ret, order = get_order(PAGE_SIZE * 2);
+
+	pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
+	if (!pages)
+		return;
+
+	ret = iommu_map(domain->domain, 0, page_to_phys(pages), PAGE_SIZE * 2,
+			IOMMU_READ | IOMMU_WRITE | domain->prot);
+	if (!ret) {
+		size_t unmapped = iommu_unmap(domain->domain, 0, PAGE_SIZE);
+
+		if (unmapped == PAGE_SIZE)
+			iommu_unmap(domain->domain, PAGE_SIZE, PAGE_SIZE);
+		else
+			domain->fgsp = true;
+	}
+
+	__free_pages(pages, order);
+}
+
+static int vfio_iommu_type1_attach_group(void *iommu_data,
+					 struct iommu_group *iommu_group)
+{
+	struct vfio_iommu *iommu = iommu_data;
+	struct vfio_group *group, *g;
+	struct vfio_domain *domain, *d;
+	struct bus_type *bus = NULL;
+	int ret;
+
+	mutex_lock(&iommu->lock);
+
+	list_for_each_entry(d, &iommu->domain_list, next) {
+		list_for_each_entry(g, &d->group_list, next) {
+			if (g->iommu_group != iommu_group)
+				continue;
+
+			mutex_unlock(&iommu->lock);
+			return -EINVAL;
+		}
+	}
+
+	group = kzalloc(sizeof(*group), GFP_KERNEL);
+	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
+	if (!group || !domain) {
+		ret = -ENOMEM;
+		goto out_free;
+	}
+
+	group->iommu_group = iommu_group;
+
+	/* Determine bus_type in order to allocate a domain */
+	ret = iommu_group_for_each_dev(iommu_group, &bus, vfio_bus_type);
+	if (ret)
+		goto out_free;
+
+	domain->domain = iommu_domain_alloc(bus);
+	if (!domain->domain) {
+		ret = -EIO;
+		goto out_free;
+	}
+
+	if (iommu->nesting) {
+		int attr = 1;
+
+		ret = iommu_domain_set_attr(domain->domain, DOMAIN_ATTR_NESTING,
+					    &attr);
+		if (ret)
+			goto out_domain;
+	}
+
+	ret = iommu_attach_group(domain->domain, iommu_group);
+	if (ret)
+		goto out_domain;
+
+	INIT_LIST_HEAD(&domain->group_list);
+	list_add(&group->next, &domain->group_list);
+
+	if (!allow_unsafe_interrupts &&
+	    !iommu_capable(bus, IOMMU_CAP_INTR_REMAP)) {
+		pr_warn("%s: No interrupt remapping support.  Use the module param \"allow_unsafe_interrupts\" to enable VFIO IOMMU support on this platform\n",
+		       __func__);
+		ret = -EPERM;
+		goto out_detach;
+	}
+
+	if (iommu_capable(bus, IOMMU_CAP_CACHE_COHERENCY))
+		domain->prot |= IOMMU_CACHE;
+
+	/*
+	 * Try to match an existing compatible domain.  We don't want to
+	 * preclude an IOMMU driver supporting multiple bus_types and being
+	 * able to include different bus_types in the same IOMMU domain, so
+	 * we test whether the domains use the same iommu_ops rather than
+	 * testing if they're on the same bus_type.
+	 */
+	list_for_each_entry(d, &iommu->domain_list, next) {
+		if (d->domain->ops == domain->domain->ops &&
+		    d->prot == domain->prot) {
+			iommu_detach_group(domain->domain, iommu_group);
+			if (!iommu_attach_group(d->domain, iommu_group)) {
+				list_add(&group->next, &d->group_list);
+				iommu_domain_free(domain->domain);
+				kfree(domain);
+				mutex_unlock(&iommu->lock);
+				return 0;
+			}
+
+			ret = iommu_attach_group(domain->domain, iommu_group);
+			if (ret)
+				goto out_domain;
+		}
+	}
+
+	vfio_test_domain_fgsp(domain);
+
+	/* replay mappings on new domains */
+	ret = vfio_iommu_replay(iommu, domain);
+	if (ret)
+		goto out_detach;
+
+	list_add(&domain->next, &iommu->domain_list);
+
+	mutex_unlock(&iommu->lock);
+
+	return 0;
+
+out_detach:
+	iommu_detach_group(domain->domain, iommu_group);
+out_domain:
+	iommu_domain_free(domain->domain);
+out_free:
+	kfree(domain);
+	kfree(group);
+	mutex_unlock(&iommu->lock);
+	return ret;
+}
+
+static void vfio_iommu_unmap_unpin_all(struct vfio_iommu *iommu)
+{
+	struct rb_node *node;
+
+	while ((node = rb_first(&iommu->dma_list)))
+		vfio_remove_dma(iommu, rb_entry(node, struct vfio_dma, node));
+}
+
+static void vfio_iommu_type1_detach_group(void *iommu_data,
+					  struct iommu_group *iommu_group)
+{
+	struct vfio_iommu *iommu = iommu_data;
+	struct vfio_domain *domain;
+	struct vfio_group *group;
+
+	mutex_lock(&iommu->lock);
+
+	list_for_each_entry(domain, &iommu->domain_list, next) {
+		list_for_each_entry(group, &domain->group_list, next) {
+			if (group->iommu_group != iommu_group)
+				continue;
+
+			iommu_detach_group(domain->domain, iommu_group);
+			list_del(&group->next);
+			kfree(group);
+			/*
+			 * Group ownership provides privilege, if the group
+			 * list is empty, the domain goes away.  If it's the
+			 * last domain, then all the mappings go away too.
+			 */
+			if (list_empty(&domain->group_list)) {
+				if (list_is_singular(&iommu->domain_list))
+					vfio_iommu_unmap_unpin_all(iommu);
+				iommu_domain_free(domain->domain);
+				list_del(&domain->next);
+				kfree(domain);
+			}
+			goto done;
+		}
+	}
+
+done:
+	mutex_unlock(&iommu->lock);
+}
+
+static void *vfio_iommu_type1_open(unsigned long arg)
+{
+	struct vfio_iommu *iommu;
+
+	iommu = kzalloc(sizeof(*iommu), GFP_KERNEL);
+	if (!iommu)
+		return ERR_PTR(-ENOMEM);
+
+	switch (arg) {
+	case VFIO_TYPE1_IOMMU:
+		break;
+	case VFIO_TYPE1_NESTING_IOMMU:
+		iommu->nesting = true;
+	case VFIO_TYPE1v2_IOMMU:
+		iommu->v2 = true;
+		break;
+	default:
+		kfree(iommu);
+		return ERR_PTR(-EINVAL);
+	}
+
+	INIT_LIST_HEAD(&iommu->domain_list);
+	iommu->dma_list = RB_ROOT;
+	mutex_init(&iommu->lock);
+
+	return iommu;
+}
+
+static void vfio_iommu_type1_release(void *iommu_data)
+{
+	struct vfio_iommu *iommu = iommu_data;
+	struct vfio_domain *domain, *domain_tmp;
+	struct vfio_group *group, *group_tmp;
+
+	vfio_iommu_unmap_unpin_all(iommu);
+
+	list_for_each_entry_safe(domain, domain_tmp,
+				 &iommu->domain_list, next) {
+		list_for_each_entry_safe(group, group_tmp,
+					 &domain->group_list, next) {
+			iommu_detach_group(domain->domain, group->iommu_group);
+			list_del(&group->next);
+			kfree(group);
+		}
+		iommu_domain_free(domain->domain);
+		list_del(&domain->next);
+		kfree(domain);
+	}
+
+	kfree(iommu);
+}
+
+static int vfio_domains_have_iommu_cache(struct vfio_iommu *iommu)
+{
+	struct vfio_domain *domain;
+	int ret = 1;
+
+	mutex_lock(&iommu->lock);
+	list_for_each_entry(domain, &iommu->domain_list, next) {
+		if (!(domain->prot & IOMMU_CACHE)) {
+			ret = 0;
+			break;
+		}
+	}
+	mutex_unlock(&iommu->lock);
+
+	return ret;
+}
+
+static long vfio_iommu_type1_ioctl(void *iommu_data,
+				   unsigned int cmd, unsigned long arg)
+{
+	struct vfio_iommu *iommu = iommu_data;
+	unsigned long minsz;
+
+	if (cmd == VFIO_CHECK_EXTENSION) {
+		switch (arg) {
+		case VFIO_TYPE1_IOMMU:
+		case VFIO_TYPE1v2_IOMMU:
+		case VFIO_TYPE1_NESTING_IOMMU:
+			return 1;
+		case VFIO_DMA_CC_IOMMU:
+			if (!iommu)
+				return 0;
+			return vfio_domains_have_iommu_cache(iommu);
+		default:
+			return 0;
+		}
+	} else if (cmd == VFIO_IOMMU_GET_INFO) {
+		struct vfio_iommu_type1_info info;
+
+		minsz = offsetofend(struct vfio_iommu_type1_info, iova_pgsizes);
+
+		if (copy_from_user(&info, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (info.argsz < minsz)
+			return -EINVAL;
+
+		info.flags = 0;
+
+		info.iova_pgsizes = vfio_pgsize_bitmap(iommu);
+
+		return copy_to_user((void __user *)arg, &info, minsz);
+
+	} else if (cmd == VFIO_IOMMU_MAP_DMA) {
+		struct vfio_iommu_type1_dma_map map;
+		uint32_t mask = VFIO_DMA_MAP_FLAG_READ |
+				VFIO_DMA_MAP_FLAG_WRITE;
+
+		minsz = offsetofend(struct vfio_iommu_type1_dma_map, size);
+
+		if (copy_from_user(&map, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (map.argsz < minsz || map.flags & ~mask)
+			return -EINVAL;
+
+		return vfio_dma_do_map(iommu, &map);
+
+	} else if (cmd == VFIO_IOMMU_UNMAP_DMA) {
+		struct vfio_iommu_type1_dma_unmap unmap;
+		long ret;
+
+		minsz = offsetofend(struct vfio_iommu_type1_dma_unmap, size);
+
+		if (copy_from_user(&unmap, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (unmap.argsz < minsz || unmap.flags)
+			return -EINVAL;
+
+		ret = vfio_dma_do_unmap(iommu, &unmap);
+		if (ret)
+			return ret;
+
+		return copy_to_user((void __user *)arg, &unmap, minsz);
+	}
+
+	return -ENOTTY;
+}
+
+static const struct vfio_iommu_driver_ops vfio_iommu_driver_ops_type1 = {
+	.name		= "vfio-iommu-type1",
+	.owner		= THIS_MODULE,
+	.open		= vfio_iommu_type1_open,
+	.release	= vfio_iommu_type1_release,
+	.ioctl		= vfio_iommu_type1_ioctl,
+	.attach_group	= vfio_iommu_type1_attach_group,
+	.detach_group	= vfio_iommu_type1_detach_group,
+};
+
+static int __init vfio_iommu_type1_init(void)
+{
+	return vfio_register_iommu_driver(&vfio_iommu_driver_ops_type1);
+}
+
+static void __exit vfio_iommu_type1_cleanup(void)
+{
+	vfio_unregister_iommu_driver(&vfio_iommu_driver_ops_type1);
+}
+
+module_init(vfio_iommu_type1_init);
+module_exit(vfio_iommu_type1_cleanup);
+
+MODULE_VERSION(DRIVER_VERSION);
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
diff --git a/drivers/vfio/vfio_spapr_eeh.c b/drivers/vfio/vfio_spapr_eeh.c
new file mode 100644
index 000000000..5fa42db76
--- /dev/null
+++ b/drivers/vfio/vfio_spapr_eeh.c
@@ -0,0 +1,100 @@
+/*
+ * EEH functionality support for VFIO devices. The feature is only
+ * available on sPAPR compatible platforms.
+ *
+ * Copyright Gavin Shan, IBM Corporation 2014.
+ *
+ * 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.
+ */
+
+#include <linux/module.h>
+#include <linux/uaccess.h>
+#include <linux/vfio.h>
+#include <asm/eeh.h>
+
+#define DRIVER_VERSION	"0.1"
+#define DRIVER_AUTHOR	"Gavin Shan, IBM Corporation"
+#define DRIVER_DESC	"VFIO IOMMU SPAPR EEH"
+
+/* We might build address mapping here for "fast" path later */
+void vfio_spapr_pci_eeh_open(struct pci_dev *pdev)
+{
+	eeh_dev_open(pdev);
+}
+EXPORT_SYMBOL_GPL(vfio_spapr_pci_eeh_open);
+
+void vfio_spapr_pci_eeh_release(struct pci_dev *pdev)
+{
+	eeh_dev_release(pdev);
+}
+EXPORT_SYMBOL_GPL(vfio_spapr_pci_eeh_release);
+
+long vfio_spapr_iommu_eeh_ioctl(struct iommu_group *group,
+				unsigned int cmd, unsigned long arg)
+{
+	struct eeh_pe *pe;
+	struct vfio_eeh_pe_op op;
+	unsigned long minsz;
+	long ret = -EINVAL;
+
+	switch (cmd) {
+	case VFIO_CHECK_EXTENSION:
+		if (arg == VFIO_EEH)
+			ret = eeh_enabled() ? 1 : 0;
+		else
+			ret = 0;
+		break;
+	case VFIO_EEH_PE_OP:
+		pe = eeh_iommu_group_to_pe(group);
+		if (!pe)
+			return -ENODEV;
+
+		minsz = offsetofend(struct vfio_eeh_pe_op, op);
+		if (copy_from_user(&op, (void __user *)arg, minsz))
+			return -EFAULT;
+		if (op.argsz < minsz || op.flags)
+			return -EINVAL;
+
+		switch (op.op) {
+		case VFIO_EEH_PE_DISABLE:
+			ret = eeh_pe_set_option(pe, EEH_OPT_DISABLE);
+			break;
+		case VFIO_EEH_PE_ENABLE:
+			ret = eeh_pe_set_option(pe, EEH_OPT_ENABLE);
+			break;
+		case VFIO_EEH_PE_UNFREEZE_IO:
+			ret = eeh_pe_set_option(pe, EEH_OPT_THAW_MMIO);
+			break;
+		case VFIO_EEH_PE_UNFREEZE_DMA:
+			ret = eeh_pe_set_option(pe, EEH_OPT_THAW_DMA);
+			break;
+		case VFIO_EEH_PE_GET_STATE:
+			ret = eeh_pe_get_state(pe);
+			break;
+		case VFIO_EEH_PE_RESET_DEACTIVATE:
+			ret = eeh_pe_reset(pe, EEH_RESET_DEACTIVATE);
+			break;
+		case VFIO_EEH_PE_RESET_HOT:
+			ret = eeh_pe_reset(pe, EEH_RESET_HOT);
+			break;
+		case VFIO_EEH_PE_RESET_FUNDAMENTAL:
+			ret = eeh_pe_reset(pe, EEH_RESET_FUNDAMENTAL);
+			break;
+		case VFIO_EEH_PE_CONFIGURE:
+			ret = eeh_pe_configure(pe);
+			break;
+		default:
+			ret = -EINVAL;
+		}
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(vfio_spapr_iommu_eeh_ioctl);
+
+MODULE_VERSION(DRIVER_VERSION);
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
diff --git a/drivers/vfio/virqfd.c b/drivers/vfio/virqfd.c
new file mode 100644
index 000000000..27c89cd5d
--- /dev/null
+++ b/drivers/vfio/virqfd.c
@@ -0,0 +1,226 @@
+/*
+ * VFIO generic eventfd code for IRQFD support.
+ * Derived from drivers/vfio/pci/vfio_pci_intrs.c
+ *
+ * Copyright (C) 2012 Red Hat, Inc.  All rights reserved.
+ *     Author: Alex Williamson <alex.williamson@redhat.com>
+ *
+ * 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.
+ */
+
+#include <linux/vfio.h>
+#include <linux/eventfd.h>
+#include <linux/file.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+
+#define DRIVER_VERSION  "0.1"
+#define DRIVER_AUTHOR   "Alex Williamson <alex.williamson@redhat.com>"
+#define DRIVER_DESC     "IRQFD support for VFIO bus drivers"
+
+static struct workqueue_struct *vfio_irqfd_cleanup_wq;
+static DEFINE_SPINLOCK(virqfd_lock);
+
+static int __init vfio_virqfd_init(void)
+{
+	vfio_irqfd_cleanup_wq =
+		create_singlethread_workqueue("vfio-irqfd-cleanup");
+	if (!vfio_irqfd_cleanup_wq)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void __exit vfio_virqfd_exit(void)
+{
+	destroy_workqueue(vfio_irqfd_cleanup_wq);
+}
+
+static void virqfd_deactivate(struct virqfd *virqfd)
+{
+	queue_work(vfio_irqfd_cleanup_wq, &virqfd->shutdown);
+}
+
+static int virqfd_wakeup(wait_queue_t *wait, unsigned mode, int sync, void *key)
+{
+	struct virqfd *virqfd = container_of(wait, struct virqfd, wait);
+	unsigned long flags = (unsigned long)key;
+
+	if (flags & POLLIN) {
+		/* An event has been signaled, call function */
+		if ((!virqfd->handler ||
+		     virqfd->handler(virqfd->opaque, virqfd->data)) &&
+		    virqfd->thread)
+			schedule_work(&virqfd->inject);
+	}
+
+	if (flags & POLLHUP) {
+		unsigned long flags;
+		spin_lock_irqsave(&virqfd_lock, flags);
+
+		/*
+		 * The eventfd is closing, if the virqfd has not yet been
+		 * queued for release, as determined by testing whether the
+		 * virqfd pointer to it is still valid, queue it now.  As
+		 * with kvm irqfds, we know we won't race against the virqfd
+		 * going away because we hold the lock to get here.
+		 */
+		if (*(virqfd->pvirqfd) == virqfd) {
+			*(virqfd->pvirqfd) = NULL;
+			virqfd_deactivate(virqfd);
+		}
+
+		spin_unlock_irqrestore(&virqfd_lock, flags);
+	}
+
+	return 0;
+}
+
+static void virqfd_ptable_queue_proc(struct file *file,
+				     wait_queue_head_t *wqh, poll_table *pt)
+{
+	struct virqfd *virqfd = container_of(pt, struct virqfd, pt);
+	add_wait_queue(wqh, &virqfd->wait);
+}
+
+static void virqfd_shutdown(struct work_struct *work)
+{
+	struct virqfd *virqfd = container_of(work, struct virqfd, shutdown);
+	u64 cnt;
+
+	eventfd_ctx_remove_wait_queue(virqfd->eventfd, &virqfd->wait, &cnt);
+	flush_work(&virqfd->inject);
+	eventfd_ctx_put(virqfd->eventfd);
+
+	kfree(virqfd);
+}
+
+static void virqfd_inject(struct work_struct *work)
+{
+	struct virqfd *virqfd = container_of(work, struct virqfd, inject);
+	if (virqfd->thread)
+		virqfd->thread(virqfd->opaque, virqfd->data);
+}
+
+int vfio_virqfd_enable(void *opaque,
+		       int (*handler)(void *, void *),
+		       void (*thread)(void *, void *),
+		       void *data, struct virqfd **pvirqfd, int fd)
+{
+	struct fd irqfd;
+	struct eventfd_ctx *ctx;
+	struct virqfd *virqfd;
+	int ret = 0;
+	unsigned int events;
+
+	virqfd = kzalloc(sizeof(*virqfd), GFP_KERNEL);
+	if (!virqfd)
+		return -ENOMEM;
+
+	virqfd->pvirqfd = pvirqfd;
+	virqfd->opaque = opaque;
+	virqfd->handler = handler;
+	virqfd->thread = thread;
+	virqfd->data = data;
+
+	INIT_WORK(&virqfd->shutdown, virqfd_shutdown);
+	INIT_WORK(&virqfd->inject, virqfd_inject);
+
+	irqfd = fdget(fd);
+	if (!irqfd.file) {
+		ret = -EBADF;
+		goto err_fd;
+	}
+
+	ctx = eventfd_ctx_fileget(irqfd.file);
+	if (IS_ERR(ctx)) {
+		ret = PTR_ERR(ctx);
+		goto err_ctx;
+	}
+
+	virqfd->eventfd = ctx;
+
+	/*
+	 * virqfds can be released by closing the eventfd or directly
+	 * through ioctl.  These are both done through a workqueue, so
+	 * we update the pointer to the virqfd under lock to avoid
+	 * pushing multiple jobs to release the same virqfd.
+	 */
+	spin_lock_irq(&virqfd_lock);
+
+	if (*pvirqfd) {
+		spin_unlock_irq(&virqfd_lock);
+		ret = -EBUSY;
+		goto err_busy;
+	}
+	*pvirqfd = virqfd;
+
+	spin_unlock_irq(&virqfd_lock);
+
+	/*
+	 * Install our own custom wake-up handling so we are notified via
+	 * a callback whenever someone signals the underlying eventfd.
+	 */
+	init_waitqueue_func_entry(&virqfd->wait, virqfd_wakeup);
+	init_poll_funcptr(&virqfd->pt, virqfd_ptable_queue_proc);
+
+	events = irqfd.file->f_op->poll(irqfd.file, &virqfd->pt);
+
+	/*
+	 * Check if there was an event already pending on the eventfd
+	 * before we registered and trigger it as if we didn't miss it.
+	 */
+	if (events & POLLIN) {
+		if ((!handler || handler(opaque, data)) && thread)
+			schedule_work(&virqfd->inject);
+	}
+
+	/*
+	 * Do not drop the file until the irqfd is fully initialized,
+	 * otherwise we might race against the POLLHUP.
+	 */
+	fdput(irqfd);
+
+	return 0;
+err_busy:
+	eventfd_ctx_put(ctx);
+err_ctx:
+	fdput(irqfd);
+err_fd:
+	kfree(virqfd);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(vfio_virqfd_enable);
+
+void vfio_virqfd_disable(struct virqfd **pvirqfd)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&virqfd_lock, flags);
+
+	if (*pvirqfd) {
+		virqfd_deactivate(*pvirqfd);
+		*pvirqfd = NULL;
+	}
+
+	spin_unlock_irqrestore(&virqfd_lock, flags);
+
+	/*
+	 * Block until we know all outstanding shutdown jobs have completed.
+	 * Even if we don't queue the job, flush the wq to be sure it's
+	 * been released.
+	 */
+	flush_workqueue(vfio_irqfd_cleanup_wq);
+}
+EXPORT_SYMBOL_GPL(vfio_virqfd_disable);
+
+module_init(vfio_virqfd_init);
+module_exit(vfio_virqfd_exit);
+
+MODULE_VERSION(DRIVER_VERSION);
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);