Initial commit; kernel source import

drivers/vfio/Kconfig

@@ -0,0 +1,16 @@
+config VFIO_IOMMU_TYPE1
+	tristate
+	depends on VFIO
+	default n
+
+menuconfig VFIO
+	tristate "VFIO Non-Privileged userspace driver framework"
+	depends on IOMMU_API
+	select VFIO_IOMMU_TYPE1 if X86
+	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"

drivers/vfio/Makefile

@@ -0,0 +1,3 @@
+obj-$(CONFIG_VFIO) += vfio.o
+obj-$(CONFIG_VFIO_IOMMU_TYPE1) += vfio_iommu_type1.o
+obj-$(CONFIG_VFIO_PCI) += pci/

drivers/vfio/pci/Kconfig

@@ -0,0 +1,18 @@
+config VFIO_PCI
+	tristate "VFIO support for PCI devices"
+	depends on VFIO && PCI && EVENTFD
+	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.

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

drivers/vfio/pci/vfio_pci.c

@@ -0,0 +1,645 @@
+/*
+ * 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/eventfd.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 "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 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.");
+
+static int vfio_pci_enable(struct vfio_pci_device *vdev)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	int ret;
+	u16 cmd;
+	u8 msix_pos;
+
+	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) {
+		pci_load_and_free_saved_state(pdev, &vdev->pci_saved_state);
+		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;
+
+#ifdef CONFIG_VFIO_PCI_VGA
+	if ((pdev->class >> 8) == PCI_CLASS_DISPLAY_VGA)
+		vdev->has_vga = true;
+#endif
+
+	return 0;
+}
+
+static void vfio_pci_disable(struct vfio_pci_device *vdev)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	int bar;
+
+	pci_disable_device(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;
+	}
+
+	/*
+	 * 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)
+			return;
+
+		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);
+
+	if (vdev->reset_works)
+		__pci_reset_function(pdev);
+
+	pci_restore_state(pdev);
+}
+
+static void vfio_pci_release(void *device_data)
+{
+	struct vfio_pci_device *vdev = device_data;
+
+	if (atomic_dec_and_test(&vdev->refcnt))
+		vfio_pci_disable(vdev);
+
+	module_put(THIS_MODULE);
+}
+
+static int vfio_pci_open(void *device_data)
+{
+	struct vfio_pci_device *vdev = device_data;
+
+	if (!try_module_get(THIS_MODULE))
+		return -ENODEV;
+
+	if (atomic_inc_return(&vdev->refcnt) == 1) {
+		int ret = vfio_pci_enable(vdev);
+		if (ret) {
+			module_put(THIS_MODULE);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+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 (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);
+		}
+	} 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;
+
+	return 0;
+}
+
+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 (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:
+			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_reset_function(vdev->pdev) : -EINVAL;
+
+	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_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP;
+	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 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,
+};
+
+static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	u8 type;
+	struct vfio_pci_device *vdev;
+	struct iommu_group *group;
+	int ret;
+
+	pci_read_config_byte(pdev, PCI_HEADER_TYPE, &type);
+	if ((type & PCI_HEADER_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);
+	atomic_set(&vdev->refcnt, 0);
+
+	ret = vfio_add_group_dev(&pdev->dev, &vfio_pci_ops, vdev);
+	if (ret) {
+		iommu_group_put(group);
+		kfree(vdev);
+	}
+
+	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);
+}
+
+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;
+	}
+
+	if (vdev->err_trigger)
+		eventfd_signal(vdev->err_trigger, 1);
+
+	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,
+};
+
+static void __exit vfio_pci_cleanup(void)
+{
+	pci_unregister_driver(&vfio_pci_driver);
+	vfio_pci_virqfd_exit();
+	vfio_pci_uninit_perm_bits();
+}
+
+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;
+
+	/* Start the virqfd cleanup handler */
+	ret = vfio_pci_virqfd_init();
+	if (ret)
+		goto out_virqfd;
+
+	/* Register and scan for devices */
+	ret = pci_register_driver(&vfio_pci_driver);
+	if (ret)
+		goto out_driver;
+
+	return 0;
+
+out_driver:
+	vfio_pci_virqfd_exit();
+out_virqfd:
+	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);

drivers/vfio/pci/vfio_pci_intrs.c

@@ -0,0 +1,854 @@
+/*
+ * 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/pci.h>
+#include <linux/file.h>
+#include <linux/poll.h>
+#include <linux/vfio.h>
+#include <linux/wait.h>
+#include <linux/workqueue.h>
+#include <linux/slab.h>
+
+#include "vfio_pci_private.h"
+
+/*
+ * IRQfd - generic
+ */
+struct virqfd {
+	struct vfio_pci_device	*vdev;
+	struct eventfd_ctx	*eventfd;
+	int			(*handler)(struct vfio_pci_device *, void *);
+	void			(*thread)(struct vfio_pci_device *, void *);
+	void			*data;
+	struct work_struct	inject;
+	wait_queue_t		wait;
+	poll_table		pt;
+	struct work_struct	shutdown;
+	struct virqfd		**pvirqfd;
+};
+
+static struct workqueue_struct *vfio_irqfd_cleanup_wq;
+
+int __init vfio_pci_virqfd_init(void)
+{
+	vfio_irqfd_cleanup_wq =
+		create_singlethread_workqueue("vfio-irqfd-cleanup");
+	if (!vfio_irqfd_cleanup_wq)
+		return -ENOMEM;
+
+	return 0;
+}
+
+void vfio_pci_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->vdev, virqfd->data)) &&
+		    virqfd->thread)
+			schedule_work(&virqfd->inject);
+	}
+
+	if (flags & POLLHUP) {
+		unsigned long flags;
+		spin_lock_irqsave(&virqfd->vdev->irqlock, flags);
+
+		/*
+		 * The eventfd is closing, if the virqfd has not yet been
+		 * queued for release, as determined by testing whether the
+		 * vdev 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 wqh->lock to get here.
+		 */
+		if (*(virqfd->pvirqfd) == virqfd) {
+			*(virqfd->pvirqfd) = NULL;
+			virqfd_deactivate(virqfd);
+		}
+
+		spin_unlock_irqrestore(&virqfd->vdev->irqlock, 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->vdev, virqfd->data);
+}
+
+static int virqfd_enable(struct vfio_pci_device *vdev,
+			 int (*handler)(struct vfio_pci_device *, void *),
+			 void (*thread)(struct vfio_pci_device *, void *),
+			 void *data, struct virqfd **pvirqfd, int fd)
+{
+	struct file *file = NULL;
+	struct eventfd_ctx *ctx = NULL;
+	struct virqfd *virqfd;
+	int ret = 0;
+	unsigned int events;
+
+	virqfd = kzalloc(sizeof(*virqfd), GFP_KERNEL);
+	if (!virqfd)
+		return -ENOMEM;
+
+	virqfd->pvirqfd = pvirqfd;
+	virqfd->vdev = vdev;
+	virqfd->handler = handler;
+	virqfd->thread = thread;
+	virqfd->data = data;
+
+	INIT_WORK(&virqfd->shutdown, virqfd_shutdown);
+	INIT_WORK(&virqfd->inject, virqfd_inject);
+
+	file = eventfd_fget(fd);
+	if (IS_ERR(file)) {
+		ret = PTR_ERR(file);
+		goto fail;
+	}
+
+	ctx = eventfd_ctx_fileget(file);
+	if (IS_ERR(ctx)) {
+		ret = PTR_ERR(ctx);
+		goto fail;
+	}
+
+	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(&vdev->irqlock);
+
+	if (*pvirqfd) {
+		spin_unlock_irq(&vdev->irqlock);
+		ret = -EBUSY;
+		goto fail;
+	}
+	*pvirqfd = virqfd;
+
+	spin_unlock_irq(&vdev->irqlock);
+
+	/*
+	 * 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 = file->f_op->poll(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(vdev, data)) && thread)
+			schedule_work(&virqfd->inject);
+	}
+
+	/*
+	 * Do not drop the file until the irqfd is fully initialized,
+	 * otherwise we might race against the POLLHUP.
+	 */
+	fput(file);
+
+	return 0;
+
+fail:
+	if (ctx && !IS_ERR(ctx))
+		eventfd_ctx_put(ctx);
+
+	if (file && !IS_ERR(file))
+		fput(file);
+
+	kfree(virqfd);
+
+	return ret;
+}
+
+static void virqfd_disable(struct vfio_pci_device *vdev,
+			   struct virqfd **pvirqfd)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&vdev->irqlock, flags);
+
+	if (*pvirqfd) {
+		virqfd_deactivate(*pvirqfd);
+		*pvirqfd = NULL;
+	}
+
+	spin_unlock_irqrestore(&vdev->irqlock, 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);
+}
+
+/*
+ * INTx
+ */
+static void vfio_send_intx_eventfd(struct vfio_pci_device *vdev, void *unused)
+{
+	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(struct vfio_pci_device *vdev,
+					void *unused)
+{
+	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);
+	virqfd_disable(vdev, &vdev->ctx[0].unmask);
+	virqfd_disable(vdev, &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(pdev, vdev->msix, nvec);
+		if (ret) {
+			kfree(vdev->msix);
+			kfree(vdev->ctx);
+			return ret;
+		}
+	} else {
+		ret = pci_enable_msi_block(pdev, nvec);
+		if (ret) {
+			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);
+	}
+
+	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++) {
+		virqfd_disable(vdev, &vdev->ctx[i].unmask);
+		virqfd_disable(vdev, &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 virqfd_enable(vdev, vfio_pci_intx_unmask_handler,
+					     vfio_send_intx_eventfd, NULL,
+					     &vdev->ctx[0].unmask, fd);
+
+		virqfd_disable(vdev, &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_err_trigger(struct vfio_pci_device *vdev,
+				    unsigned index, unsigned start,
+				    unsigned count, uint32_t flags, void *data)
+{
+	int32_t fd = *(int32_t *)data;
+	struct pci_dev *pdev = vdev->pdev;
+
+	if ((index != VFIO_PCI_ERR_IRQ_INDEX) ||
+	    !(flags & VFIO_IRQ_SET_DATA_TYPE_MASK))
+		return -EINVAL;
+
+	/*
+	 * device_lock synchronizes setting and checking of
+	 * err_trigger. The vfio_pci_aer_err_detected() is also
+	 * called with device_lock held.
+	 */
+
+	/* DATA_NONE/DATA_BOOL enables loopback testing */
+
+	if (flags & VFIO_IRQ_SET_DATA_NONE) {
+		device_lock(&pdev->dev);
+		if (vdev->err_trigger)
+			eventfd_signal(vdev->err_trigger, 1);
+		device_unlock(&pdev->dev);
+		return 0;
+	} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
+		uint8_t trigger = *(uint8_t *)data;
+		device_lock(&pdev->dev);
+		if (trigger && vdev->err_trigger)
+			eventfd_signal(vdev->err_trigger, 1);
+		device_unlock(&pdev->dev);
+		return 0;
+	}
+
+	/* Handle SET_DATA_EVENTFD */
+
+	if (fd == -1) {
+		device_lock(&pdev->dev);
+		if (vdev->err_trigger)
+			eventfd_ctx_put(vdev->err_trigger);
+		vdev->err_trigger = NULL;
+		device_unlock(&pdev->dev);
+		return 0;
+	} else if (fd >= 0) {
+		struct eventfd_ctx *efdctx;
+		efdctx = eventfd_ctx_fdget(fd);
+		if (IS_ERR(efdctx))
+			return PTR_ERR(efdctx);
+		device_lock(&pdev->dev);
+		if (vdev->err_trigger)
+			eventfd_ctx_put(vdev->err_trigger);
+		vdev->err_trigger = efdctx;
+		device_unlock(&pdev->dev);
+		return 0;
+	} else
+		return -EINVAL;
+}
+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;
+		}
+	}
+
+	if (!func)
+		return -ENOTTY;
+
+	return func(vdev, index, start, count, flags, data);
+}

drivers/vfio/pci/vfio_pci_private.h

@@ -0,0 +1,93 @@
+/*
+ * 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;
+	struct pci_saved_state	*pci_saved_state;
+	atomic_t		refcnt;
+	struct eventfd_ctx	*err_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_pci_virqfd_init(void);
+extern void vfio_pci_virqfd_exit(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 */

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;
+}

drivers/vfio/vfio_iommu_type1.c

@@ -0,0 +1,753 @@
+/*
+ * 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/pci.h>		/* pci_bus_type */
+#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.");
+
+struct vfio_iommu {
+	struct iommu_domain	*domain;
+	struct mutex		lock;
+	struct list_head	dma_list;
+	struct list_head	group_list;
+	bool			cache;
+};
+
+struct vfio_dma {
+	struct list_head	next;
+	dma_addr_t		iova;		/* Device address */
+	unsigned long		vaddr;		/* Process virtual addr */
+	long			npage;		/* Number of pages */
+	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
+ */
+
+#define NPAGE_TO_SIZE(npage)	((size_t)(npage) << PAGE_SHIFT)
+
+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)
+		return; /* process exited */
+
+	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_trans_head(tail);
+		reserved = !!(PageReserved(head));
+		if (head != tail) {
+			/*
+			 * "head" is not a dangling pointer
+			 * (compound_trans_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;
+}
+
+/* Unmap DMA region */
+static long __vfio_dma_do_unmap(struct vfio_iommu *iommu, dma_addr_t iova,
+			     long npage, int prot)
+{
+	long i, unlocked = 0;
+
+	for (i = 0; i < npage; i++, iova += PAGE_SIZE) {
+		unsigned long pfn;
+
+		pfn = iommu_iova_to_phys(iommu->domain, iova) >> PAGE_SHIFT;
+		if (pfn) {
+			iommu_unmap(iommu->domain, iova, PAGE_SIZE);
+			unlocked += put_pfn(pfn, prot);
+		}
+	}
+	return unlocked;
+}
+
+static void vfio_dma_unmap(struct vfio_iommu *iommu, dma_addr_t iova,
+			   long npage, int prot)
+{
+	long unlocked;
+
+	unlocked = __vfio_dma_do_unmap(iommu, iova, npage, prot);
+	vfio_lock_acct(-unlocked);
+}
+
+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;
+}
+
+/* Map DMA region */
+static int __vfio_dma_map(struct vfio_iommu *iommu, dma_addr_t iova,
+			  unsigned long vaddr, long npage, int prot)
+{
+	dma_addr_t start = iova;
+	long i, locked = 0;
+	int ret;
+
+	/* Verify that pages are not already mapped */
+	for (i = 0; i < npage; i++, iova += PAGE_SIZE)
+		if (iommu_iova_to_phys(iommu->domain, iova))
+			return -EBUSY;
+
+	iova = start;
+
+	if (iommu->cache)
+		prot |= IOMMU_CACHE;
+
+	/*
+	 * XXX We break mappings into pages and use get_user_pages_fast to
+	 * pin the pages in memory.  It's been suggested that mlock might
+	 * provide a more efficient mechanism, but nothing prevents the
+	 * user from munlocking the pages, which could then allow the user
+	 * access to random host memory.  We also have no guarantee from the
+	 * IOMMU API that the iommu driver can unmap sub-pages of previous
+	 * mappings.  This means we might lose an entire range if a single
+	 * page within it is unmapped.  Single page mappings are inefficient,
+	 * but provide the most flexibility for now.
+	 */
+	for (i = 0; i < npage; i++, iova += PAGE_SIZE, vaddr += PAGE_SIZE) {
+		unsigned long pfn = 0;
+
+		ret = vaddr_get_pfn(vaddr, prot, &pfn);
+		if (ret) {
+			__vfio_dma_do_unmap(iommu, start, i, prot);
+			return ret;
+		}
+
+		/*
+		 * Only add actual locked pages to accounting
+		 * XXX We're effectively marking a page locked for every
+		 * IOVA page even though it's possible the user could be
+		 * backing multiple IOVAs with the same vaddr.  This over-
+		 * penalizes the user process, but we currently have no
+		 * easy way to do this properly.
+		 */
+		if (!is_invalid_reserved_pfn(pfn))
+			locked++;
+
+		ret = iommu_map(iommu->domain, iova,
+				(phys_addr_t)pfn << PAGE_SHIFT,
+				PAGE_SIZE, prot);
+		if (ret) {
+			/* Back out mappings on error */
+			put_pfn(pfn, prot);
+			__vfio_dma_do_unmap(iommu, start, i, prot);
+			return ret;
+		}
+	}
+	vfio_lock_acct(locked);
+	return 0;
+}
+
+static inline bool ranges_overlap(dma_addr_t start1, size_t size1,
+				  dma_addr_t start2, size_t size2)
+{
+	if (start1 < start2)
+		return (start2 - start1 < size1);
+	else if (start2 < start1)
+		return (start1 - start2 < size2);
+	return (size1 > 0 && size2 > 0);
+}
+
+static struct vfio_dma *vfio_find_dma(struct vfio_iommu *iommu,
+						dma_addr_t start, size_t size)
+{
+	struct vfio_dma *dma;
+
+	list_for_each_entry(dma, &iommu->dma_list, next) {
+		if (ranges_overlap(dma->iova, NPAGE_TO_SIZE(dma->npage),
+				   start, size))
+			return dma;
+	}
+	return NULL;
+}
+
+static long vfio_remove_dma_overlap(struct vfio_iommu *iommu, dma_addr_t start,
+				    size_t size, struct vfio_dma *dma)
+{
+	struct vfio_dma *split;
+	long npage_lo, npage_hi;
+
+	/* Existing dma region is completely covered, unmap all */
+	if (start <= dma->iova &&
+	    start + size >= dma->iova + NPAGE_TO_SIZE(dma->npage)) {
+		vfio_dma_unmap(iommu, dma->iova, dma->npage, dma->prot);
+		list_del(&dma->next);
+		npage_lo = dma->npage;
+		kfree(dma);
+		return npage_lo;
+	}
+
+	/* Overlap low address of existing range */
+	if (start <= dma->iova) {
+		size_t overlap;
+
+		overlap = start + size - dma->iova;
+		npage_lo = overlap >> PAGE_SHIFT;
+
+		vfio_dma_unmap(iommu, dma->iova, npage_lo, dma->prot);
+		dma->iova += overlap;
+		dma->vaddr += overlap;
+		dma->npage -= npage_lo;
+		return npage_lo;
+	}
+
+	/* Overlap high address of existing range */
+	if (start + size >= dma->iova + NPAGE_TO_SIZE(dma->npage)) {
+		size_t overlap;
+
+		overlap = dma->iova + NPAGE_TO_SIZE(dma->npage) - start;
+		npage_hi = overlap >> PAGE_SHIFT;
+
+		vfio_dma_unmap(iommu, start, npage_hi, dma->prot);
+		dma->npage -= npage_hi;
+		return npage_hi;
+	}
+
+	/* Split existing */
+	npage_lo = (start - dma->iova) >> PAGE_SHIFT;
+	npage_hi = dma->npage - (size >> PAGE_SHIFT) - npage_lo;
+
+	split = kzalloc(sizeof *split, GFP_KERNEL);
+	if (!split)
+		return -ENOMEM;
+
+	vfio_dma_unmap(iommu, start, size >> PAGE_SHIFT, dma->prot);
+
+	dma->npage = npage_lo;
+
+	split->npage = npage_hi;
+	split->iova = start + size;
+	split->vaddr = dma->vaddr + NPAGE_TO_SIZE(npage_lo) + size;
+	split->prot = dma->prot;
+	list_add(&split->next, &iommu->dma_list);
+	return size >> PAGE_SHIFT;
+}
+
+static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
+			     struct vfio_iommu_type1_dma_unmap *unmap)
+{
+	long ret = 0, npage = unmap->size >> PAGE_SHIFT;
+	struct vfio_dma *dma, *tmp;
+	uint64_t mask;
+
+	mask = ((uint64_t)1 << __ffs(iommu->domain->ops->pgsize_bitmap)) - 1;
+
+	if (unmap->iova & mask)
+		return -EINVAL;
+	if (unmap->size & mask)
+		return -EINVAL;
+
+	/* XXX We still break these down into PAGE_SIZE */
+	WARN_ON(mask & PAGE_MASK);
+
+	mutex_lock(&iommu->lock);
+
+	list_for_each_entry_safe(dma, tmp, &iommu->dma_list, next) {
+		if (ranges_overlap(dma->iova, NPAGE_TO_SIZE(dma->npage),
+				   unmap->iova, unmap->size)) {
+			ret = vfio_remove_dma_overlap(iommu, unmap->iova,
+						      unmap->size, dma);
+			if (ret > 0)
+				npage -= ret;
+			if (ret < 0 || npage == 0)
+				break;
+		}
+	}
+	mutex_unlock(&iommu->lock);
+	return ret > 0 ? 0 : (int)ret;
+}
+
+static int vfio_dma_do_map(struct vfio_iommu *iommu,
+			   struct vfio_iommu_type1_dma_map *map)
+{
+	struct vfio_dma *dma, *pdma = NULL;
+	dma_addr_t iova = map->iova;
+	unsigned long locked, lock_limit, vaddr = map->vaddr;
+	size_t size = map->size;
+	int ret = 0, prot = 0;
+	uint64_t mask;
+	long npage;
+
+	mask = ((uint64_t)1 << __ffs(iommu->domain->ops->pgsize_bitmap)) - 1;
+
+	/* 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)
+		return -EINVAL; /* No READ/WRITE? */
+
+	if (vaddr & mask)
+		return -EINVAL;
+	if (iova & mask)
+		return -EINVAL;
+	if (size & mask)
+		return -EINVAL;
+
+	/* XXX We still break these down into PAGE_SIZE */
+	WARN_ON(mask & PAGE_MASK);
+
+	/* Don't allow IOVA wrap */
+	if (iova + size && iova + size < iova)
+		return -EINVAL;
+
+	/* Don't allow virtual address wrap */
+	if (vaddr + size && vaddr + size < vaddr)
+		return -EINVAL;
+
+	npage = size >> PAGE_SHIFT;
+	if (!npage)
+		return -EINVAL;
+
+	mutex_lock(&iommu->lock);
+
+	if (vfio_find_dma(iommu, iova, size)) {
+		ret = -EBUSY;
+		goto out_lock;
+	}
+
+	/* account for locked pages */
+	locked = current->mm->locked_vm + npage;
+	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+	if (locked > lock_limit && !capable(CAP_IPC_LOCK)) {
+		pr_warn("%s: RLIMIT_MEMLOCK (%ld) exceeded\n",
+			__func__, rlimit(RLIMIT_MEMLOCK));
+		ret = -ENOMEM;
+		goto out_lock;
+	}
+
+	ret = __vfio_dma_map(iommu, iova, vaddr, npage, prot);
+	if (ret)
+		goto out_lock;
+
+	/* Check if we abut a region below - nothing below 0 */
+	if (iova) {
+		dma = vfio_find_dma(iommu, iova - 1, 1);
+		if (dma && dma->prot == prot &&
+		    dma->vaddr + NPAGE_TO_SIZE(dma->npage) == vaddr) {
+
+			dma->npage += npage;
+			iova = dma->iova;
+			vaddr = dma->vaddr;
+			npage = dma->npage;
+			size = NPAGE_TO_SIZE(npage);
+
+			pdma = dma;
+		}
+	}
+
+	/* Check if we abut a region above - nothing above ~0 + 1 */
+	if (iova + size) {
+		dma = vfio_find_dma(iommu, iova + size, 1);
+		if (dma && dma->prot == prot &&
+		    dma->vaddr == vaddr + size) {
+
+			dma->npage += npage;
+			dma->iova = iova;
+			dma->vaddr = vaddr;
+
+			/*
+			 * If merged above and below, remove previously
+			 * merged entry.  New entry covers it.
+			 */
+			if (pdma) {
+				list_del(&pdma->next);
+				kfree(pdma);
+			}
+			pdma = dma;
+		}
+	}
+
+	/* Isolated, new region */
+	if (!pdma) {
+		dma = kzalloc(sizeof *dma, GFP_KERNEL);
+		if (!dma) {
+			ret = -ENOMEM;
+			vfio_dma_unmap(iommu, iova, npage, prot);
+			goto out_lock;
+		}
+
+		dma->npage = npage;
+		dma->iova = iova;
+		dma->vaddr = vaddr;
+		dma->prot = prot;
+		list_add(&dma->next, &iommu->dma_list);
+	}
+
+out_lock:
+	mutex_unlock(&iommu->lock);
+	return ret;
+}
+
+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, *tmp;
+	int ret;
+
+	group = kzalloc(sizeof(*group), GFP_KERNEL);
+	if (!group)
+		return -ENOMEM;
+
+	mutex_lock(&iommu->lock);
+
+	list_for_each_entry(tmp, &iommu->group_list, next) {
+		if (tmp->iommu_group == iommu_group) {
+			mutex_unlock(&iommu->lock);
+			kfree(group);
+			return -EINVAL;
+		}
+	}
+
+	/*
+	 * TODO: Domain have capabilities that might change as we add
+	 * groups (see iommu->cache, currently never set).  Check for
+	 * them and potentially disallow groups to be attached when it
+	 * would change capabilities (ugh).
+	 */
+	ret = iommu_attach_group(iommu->domain, iommu_group);
+	if (ret) {
+		mutex_unlock(&iommu->lock);
+		kfree(group);
+		return ret;
+	}
+
+	group->iommu_group = iommu_group;
+	list_add(&group->next, &iommu->group_list);
+
+	mutex_unlock(&iommu->lock);
+
+	return 0;
+}
+
+static void vfio_iommu_type1_detach_group(void *iommu_data,
+					  struct iommu_group *iommu_group)
+{
+	struct vfio_iommu *iommu = iommu_data;
+	struct vfio_group *group;
+
+	mutex_lock(&iommu->lock);
+
+	list_for_each_entry(group, &iommu->group_list, next) {
+		if (group->iommu_group == iommu_group) {
+			iommu_detach_group(iommu->domain, iommu_group);
+			list_del(&group->next);
+			kfree(group);
+			break;
+		}
+	}
+
+	mutex_unlock(&iommu->lock);
+}
+
+static void *vfio_iommu_type1_open(unsigned long arg)
+{
+	struct vfio_iommu *iommu;
+
+	if (arg != VFIO_TYPE1_IOMMU)
+		return ERR_PTR(-EINVAL);
+
+	iommu = kzalloc(sizeof(*iommu), GFP_KERNEL);
+	if (!iommu)
+		return ERR_PTR(-ENOMEM);
+
+	INIT_LIST_HEAD(&iommu->group_list);
+	INIT_LIST_HEAD(&iommu->dma_list);
+	mutex_init(&iommu->lock);
+
+	/*
+	 * Wish we didn't have to know about bus_type here.
+	 */
+	iommu->domain = iommu_domain_alloc(&pci_bus_type);
+	if (!iommu->domain) {
+		kfree(iommu);
+		return ERR_PTR(-EIO);
+	}
+
+	/*
+	 * Wish we could specify required capabilities rather than create
+	 * a domain, see what comes out and hope it doesn't change along
+	 * the way.  Fortunately we know interrupt remapping is global for
+	 * our iommus.
+	 */
+	if (!allow_unsafe_interrupts &&
+	    !iommu_domain_has_cap(iommu->domain, 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__);
+		iommu_domain_free(iommu->domain);
+		kfree(iommu);
+		return ERR_PTR(-EPERM);
+	}
+
+	return iommu;
+}
+
+static void vfio_iommu_type1_release(void *iommu_data)
+{
+	struct vfio_iommu *iommu = iommu_data;
+	struct vfio_group *group, *group_tmp;
+	struct vfio_dma *dma, *dma_tmp;
+
+	list_for_each_entry_safe(group, group_tmp, &iommu->group_list, next) {
+		iommu_detach_group(iommu->domain, group->iommu_group);
+		list_del(&group->next);
+		kfree(group);
+	}
+
+	list_for_each_entry_safe(dma, dma_tmp, &iommu->dma_list, next) {
+		vfio_dma_unmap(iommu, dma->iova, dma->npage, dma->prot);
+		list_del(&dma->next);
+		kfree(dma);
+	}
+
+	iommu_domain_free(iommu->domain);
+	iommu->domain = NULL;
+	kfree(iommu);
+}
+
+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:
+			return 1;
+		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 = iommu->domain->ops->pgsize_bitmap;
+
+		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;
+
+		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;
+
+		return vfio_dma_do_unmap(iommu, &unmap);
+	}
+
+	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)
+{
+	if (!iommu_present(&pci_bus_type))
+		return -ENODEV;
+
+	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);